1 /*
2 * Copyright (c) 2002, 2025, 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.misc.PreviewFeatures;
30 import jdk.internal.value.DeserializeConstructor;
31 import jdk.internal.vm.annotation.AOTSafeClassInitializer;
32 import jdk.internal.vm.annotation.IntrinsicCandidate;
33 import jdk.internal.vm.annotation.Stable;
34
35 import java.lang.constant.Constable;
36 import java.lang.constant.DynamicConstantDesc;
37 import java.util.Arrays;
38 import java.util.HashMap;
39 import java.util.Locale;
40 import java.util.Map;
41 import java.util.Objects;
42 import java.util.Optional;
43
44 import static java.lang.constant.ConstantDescs.BSM_EXPLICIT_CAST;
45 import static java.lang.constant.ConstantDescs.CD_char;
46 import static java.lang.constant.ConstantDescs.DEFAULT_NAME;
47
48 /**
49 * The {@code Character} class is the {@linkplain
50 * java.lang##wrapperClass wrapper class} for values of the primitive
51 * type {@code char}. An object of type {@code Character} contains a
52 * single field whose type is {@code char}.
53 *
54 * <p>In addition, this class provides a large number of static methods for
55 * determining a character's category (lowercase letter, digit, etc.)
56 * and for converting characters from uppercase to lowercase and vice
57 * versa.
58 *
59 * <h2><a id="conformance">Unicode Conformance</a></h2>
60 * <p>
61 * The fields and methods of class {@code Character} are defined in terms
62 * of character information from the Unicode Standard, specifically the
63 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
64 * This file specifies properties including name and category for every
65 * assigned Unicode code point or character range. The file is available
66 * from the Unicode Consortium at
67 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
68 * <p>
69 * Character information is based on the Unicode Standard, version 17.0.
70 * <p>
71 * The Java platform has supported different versions of the Unicode
72 * Standard over time. Upgrades to newer versions of the Unicode Standard
73 * occurred in the following Java releases, each indicating the new version:
74 * <table class="striped">
75 * <caption style="display:none">Shows Java releases and supported Unicode versions</caption>
76 * <thead>
77 * <tr><th scope="col">Java release</th>
78 * <th scope="col">Unicode version</th></tr>
79 * </thead>
80 * <tbody>
81 * <tr><th scope="row" style="text-align:left">Java SE 26</th>
82 * <td>Unicode 17.0</td></tr>
83 * <tr><th scope="row" style="text-align:left">Java SE 24</th>
84 * <td>Unicode 16.0</td></tr>
85 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
86 * <td>Unicode 15.1</td></tr>
87 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
88 * <td>Unicode 15.0</td></tr>
89 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
90 * <td>Unicode 14.0</td></tr>
91 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
92 * <td>Unicode 13.0</td></tr>
93 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
94 * <td>Unicode 12.1</td></tr>
95 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
96 * <td>Unicode 11.0</td></tr>
97 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
98 * <td>Unicode 10.0</td></tr>
99 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
100 * <td>Unicode 8.0</td></tr>
101 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
102 * <td>Unicode 6.2</td></tr>
103 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
104 * <td>Unicode 6.0</td></tr>
105 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
106 * <td>Unicode 4.0</td></tr>
107 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
108 * <td>Unicode 3.0</td></tr>
109 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
110 * <td>Unicode 2.0</td></tr>
111 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
112 * <td>Unicode 1.1.5</td></tr>
113 * </tbody>
114 * </table>
115 * Variations from these base Unicode versions, such as recognized appendixes,
116 * are documented elsewhere.
117 * <h2><a id="unicode">Unicode Character Representations</a></h2>
118 *
119 * <p>The {@code char} data type (and therefore the value that a
120 * {@code Character} object encapsulates) are based on the
121 * original Unicode specification, which defined characters as
122 * fixed-width 16-bit entities. The Unicode Standard has since been
123 * changed to allow for characters whose representation requires more
124 * than 16 bits. The range of legal <em>code point</em>s is now
125 * U+0000 to U+10FFFF, known as
126 * <em><a href="https://www.unicode.org/glossary/#unicode_scalar_value">
127 * Unicode scalar value</a></em>.
128 *
129 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
130 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
131 * <a id="supplementary">Characters</a> whose code points are greater
132 * than U+FFFF are called <em>supplementary character</em>s. The Java
133 * platform uses the UTF-16 representation in {@code char} arrays and
134 * in the {@code String} and {@code StringBuffer} classes. In
135 * this representation, supplementary characters are represented as a pair
136 * of {@code char} values, the first from the <em>high-surrogates</em>
137 * range, (\uD800-\uDBFF), the second from the
138 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
139 *
140 * <p>A {@code char} value, therefore, represents Basic
141 * Multilingual Plane (BMP) code points, including the surrogate
142 * code points, or code units of the UTF-16 encoding. An
143 * {@code int} value represents all Unicode code points,
144 * including supplementary code points. The lower (least significant)
145 * 21 bits of {@code int} are used to represent Unicode code
146 * points and the upper (most significant) 11 bits must be zero.
147 * Unless otherwise specified, the behavior with respect to
148 * supplementary characters and surrogate {@code char} values is
149 * as follows:
150 *
151 * <ul>
152 * <li>The methods that only accept a {@code char} value cannot support
153 * supplementary characters. They treat {@code char} values from the
154 * surrogate ranges as undefined characters. For example,
155 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
156 * this specific value if followed by any low-surrogate value in a string
157 * would represent a letter.
158 *
159 * <li>The methods that accept an {@code int} value support all
160 * Unicode characters, including supplementary characters. For
161 * example, {@code Character.isLetter(0x2F81A)} returns
162 * {@code true} because the code point value represents a letter
163 * (a CJK ideograph).
164 * </ul>
165 *
166 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
167 * used for character values in the range between U+0000 and U+10FFFF,
168 * and <em>Unicode code unit</em> is used for 16-bit
169 * {@code char} values that are code units of the <em>UTF-16</em>
170 * encoding. For more information on Unicode terminology, refer to the
171 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
172 *
173 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
174 * class; programmers should treat instances that are {@linkplain #equals(Object) equal}
175 * as interchangeable and should not use instances for synchronization, mutexes, or
176 * with {@linkplain java.lang.ref.Reference object references}.
177 *
178 * <div class="preview-block">
179 * <div class="preview-comment">
180 * When preview features are enabled, {@code Character} is a {@linkplain Class#isValue value class}.
181 * Use of value class instances for synchronization, mutexes, or with
182 * {@linkplain java.lang.ref.Reference object references} result in
183 * {@link IdentityException}.
184 * </div>
185 * </div>
186 *
187 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
188 * @author Lee Boynton
189 * @author Guy Steele
190 * @author Akira Tanaka
191 * @author Martin Buchholz
192 * @author Ulf Zibis
193 * @since 1.0
194 */
195 @jdk.internal.MigratedValueClass
196 @jdk.internal.ValueBased
197 public final class Character implements java.io.Serializable, Comparable<Character>, Constable {
198 /**
199 * The minimum radix available for conversion to and from strings.
200 * The constant value of this field is the smallest value permitted
201 * for the radix argument in radix-conversion methods such as the
202 * {@code digit} method, the {@code forDigit} method, and the
203 * {@code toString} method of class {@code Integer}.
204 *
205 * @see Character#digit(char, int)
206 * @see Character#forDigit(int, int)
207 * @see Integer#toString(int, int)
208 * @see Integer#valueOf(String)
209 */
210 public static final int MIN_RADIX = 2;
211
212 /**
213 * The maximum radix available for conversion to and from strings.
214 * The constant value of this field is the largest value permitted
215 * for the radix argument in radix-conversion methods such as the
216 * {@code digit} method, the {@code forDigit} method, and the
217 * {@code toString} method of class {@code Integer}.
218 *
219 * @see Character#digit(char, int)
220 * @see Character#forDigit(int, int)
221 * @see Integer#toString(int, int)
222 * @see Integer#valueOf(String)
223 */
224 public static final int MAX_RADIX = 36;
225
226 /**
227 * The constant value of this field is the smallest value of type
228 * {@code char}, {@code '\u005Cu0000'}.
229 *
230 * @since 1.0.2
231 */
232 public static final char MIN_VALUE = '\u0000';
233
234 /**
235 * The constant value of this field is the largest value of type
236 * {@code char}, {@code '\u005CuFFFF'}.
237 *
238 * @since 1.0.2
239 */
240 public static final char MAX_VALUE = '\uFFFF';
241
242 /**
243 * The {@code Class} instance representing the primitive type
244 * {@code char}.
245 *
246 * @since 1.1
247 */
248 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
249
250 /*
251 * Normative general types
252 */
253
254 /*
255 * General character types
256 */
257
258 /**
259 * General category "Cn" in the Unicode specification.
260 * @since 1.1
261 */
262 public static final byte UNASSIGNED = 0;
263
264 /**
265 * General category "Lu" in the Unicode specification.
266 * @since 1.1
267 */
268 public static final byte UPPERCASE_LETTER = 1;
269
270 /**
271 * General category "Ll" in the Unicode specification.
272 * @since 1.1
273 */
274 public static final byte LOWERCASE_LETTER = 2;
275
276 /**
277 * General category "Lt" in the Unicode specification.
278 * @since 1.1
279 */
280 public static final byte TITLECASE_LETTER = 3;
281
282 /**
283 * General category "Lm" in the Unicode specification.
284 * @since 1.1
285 */
286 public static final byte MODIFIER_LETTER = 4;
287
288 /**
289 * General category "Lo" in the Unicode specification.
290 * @since 1.1
291 */
292 public static final byte OTHER_LETTER = 5;
293
294 /**
295 * General category "Mn" in the Unicode specification.
296 * @since 1.1
297 */
298 public static final byte NON_SPACING_MARK = 6;
299
300 /**
301 * General category "Me" in the Unicode specification.
302 * @since 1.1
303 */
304 public static final byte ENCLOSING_MARK = 7;
305
306 /**
307 * General category "Mc" in the Unicode specification.
308 * @since 1.1
309 */
310 public static final byte COMBINING_SPACING_MARK = 8;
311
312 /**
313 * General category "Nd" in the Unicode specification.
314 * @since 1.1
315 */
316 public static final byte DECIMAL_DIGIT_NUMBER = 9;
317
318 /**
319 * General category "Nl" in the Unicode specification.
320 * @since 1.1
321 */
322 public static final byte LETTER_NUMBER = 10;
323
324 /**
325 * General category "No" in the Unicode specification.
326 * @since 1.1
327 */
328 public static final byte OTHER_NUMBER = 11;
329
330 /**
331 * General category "Zs" in the Unicode specification.
332 * @since 1.1
333 */
334 public static final byte SPACE_SEPARATOR = 12;
335
336 /**
337 * General category "Zl" in the Unicode specification.
338 * @since 1.1
339 */
340 public static final byte LINE_SEPARATOR = 13;
341
342 /**
343 * General category "Zp" in the Unicode specification.
344 * @since 1.1
345 */
346 public static final byte PARAGRAPH_SEPARATOR = 14;
347
348 /**
349 * General category "Cc" in the Unicode specification.
350 * @since 1.1
351 */
352 public static final byte CONTROL = 15;
353
354 /**
355 * General category "Cf" in the Unicode specification.
356 * @since 1.1
357 */
358 public static final byte FORMAT = 16;
359
360 /**
361 * General category "Co" in the Unicode specification.
362 * @since 1.1
363 */
364 public static final byte PRIVATE_USE = 18;
365
366 /**
367 * General category "Cs" in the Unicode specification.
368 * @since 1.1
369 */
370 public static final byte SURROGATE = 19;
371
372 /**
373 * General category "Pd" in the Unicode specification.
374 * @since 1.1
375 */
376 public static final byte DASH_PUNCTUATION = 20;
377
378 /**
379 * General category "Ps" in the Unicode specification.
380 * @since 1.1
381 */
382 public static final byte START_PUNCTUATION = 21;
383
384 /**
385 * General category "Pe" in the Unicode specification.
386 * @since 1.1
387 */
388 public static final byte END_PUNCTUATION = 22;
389
390 /**
391 * General category "Pc" in the Unicode specification.
392 * @since 1.1
393 */
394 public static final byte CONNECTOR_PUNCTUATION = 23;
395
396 /**
397 * General category "Po" in the Unicode specification.
398 * @since 1.1
399 */
400 public static final byte OTHER_PUNCTUATION = 24;
401
402 /**
403 * General category "Sm" in the Unicode specification.
404 * @since 1.1
405 */
406 public static final byte MATH_SYMBOL = 25;
407
408 /**
409 * General category "Sc" in the Unicode specification.
410 * @since 1.1
411 */
412 public static final byte CURRENCY_SYMBOL = 26;
413
414 /**
415 * General category "Sk" in the Unicode specification.
416 * @since 1.1
417 */
418 public static final byte MODIFIER_SYMBOL = 27;
419
420 /**
421 * General category "So" in the Unicode specification.
422 * @since 1.1
423 */
424 public static final byte OTHER_SYMBOL = 28;
425
426 /**
427 * General category "Pi" in the Unicode specification.
428 * @since 1.4
429 */
430 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
431
432 /**
433 * General category "Pf" in the Unicode specification.
434 * @since 1.4
435 */
436 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
437
438 /**
439 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
440 */
441 static final int ERROR = 0xFFFFFFFF;
442
443
444 /**
445 * Undefined bidirectional character type. Undefined {@code char}
446 * values have undefined directionality in the Unicode specification.
447 * @since 1.4
448 */
449 public static final byte DIRECTIONALITY_UNDEFINED = -1;
450
451 /**
452 * Strong bidirectional character type "L" in the Unicode specification.
453 * @since 1.4
454 */
455 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
456
457 /**
458 * Strong bidirectional character type "R" in the Unicode specification.
459 * @since 1.4
460 */
461 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
462
463 /**
464 * Strong bidirectional character type "AL" in the Unicode specification.
465 * @since 1.4
466 */
467 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
468
469 /**
470 * Weak bidirectional character type "EN" in the Unicode specification.
471 * @since 1.4
472 */
473 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
474
475 /**
476 * Weak bidirectional character type "ES" in the Unicode specification.
477 * @since 1.4
478 */
479 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
480
481 /**
482 * Weak bidirectional character type "ET" in the Unicode specification.
483 * @since 1.4
484 */
485 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
486
487 /**
488 * Weak bidirectional character type "AN" in the Unicode specification.
489 * @since 1.4
490 */
491 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
492
493 /**
494 * Weak bidirectional character type "CS" in the Unicode specification.
495 * @since 1.4
496 */
497 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
498
499 /**
500 * Weak bidirectional character type "NSM" in the Unicode specification.
501 * @since 1.4
502 */
503 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
504
505 /**
506 * Weak bidirectional character type "BN" in the Unicode specification.
507 * @since 1.4
508 */
509 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
510
511 /**
512 * Neutral bidirectional character type "B" in the Unicode specification.
513 * @since 1.4
514 */
515 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
516
517 /**
518 * Neutral bidirectional character type "S" in the Unicode specification.
519 * @since 1.4
520 */
521 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
522
523 /**
524 * Neutral bidirectional character type "WS" in the Unicode specification.
525 * @since 1.4
526 */
527 public static final byte DIRECTIONALITY_WHITESPACE = 12;
528
529 /**
530 * Neutral bidirectional character type "ON" in the Unicode specification.
531 * @since 1.4
532 */
533 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
534
535 /**
536 * Strong bidirectional character type "LRE" in the Unicode specification.
537 * @since 1.4
538 */
539 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
540
541 /**
542 * Strong bidirectional character type "LRO" in the Unicode specification.
543 * @since 1.4
544 */
545 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
546
547 /**
548 * Strong bidirectional character type "RLE" in the Unicode specification.
549 * @since 1.4
550 */
551 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
552
553 /**
554 * Strong bidirectional character type "RLO" in the Unicode specification.
555 * @since 1.4
556 */
557 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
558
559 /**
560 * Weak bidirectional character type "PDF" in the Unicode specification.
561 * @since 1.4
562 */
563 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
564
565 /**
566 * Weak bidirectional character type "LRI" in the Unicode specification.
567 * @since 9
568 */
569 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
570
571 /**
572 * Weak bidirectional character type "RLI" in the Unicode specification.
573 * @since 9
574 */
575 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
576
577 /**
578 * Weak bidirectional character type "FSI" in the Unicode specification.
579 * @since 9
580 */
581 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
582
583 /**
584 * Weak bidirectional character type "PDI" in the Unicode specification.
585 * @since 9
586 */
587 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
588
589 /**
590 * The minimum value of a
591 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
592 * Unicode high-surrogate code unit</a>
593 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
594 * A high-surrogate is also known as a <i>leading-surrogate</i>.
595 *
596 * @since 1.5
597 */
598 public static final char MIN_HIGH_SURROGATE = '\uD800';
599
600 /**
601 * The maximum value of a
602 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
603 * Unicode high-surrogate code unit</a>
604 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
605 * A high-surrogate is also known as a <i>leading-surrogate</i>.
606 *
607 * @since 1.5
608 */
609 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
610
611 /**
612 * The minimum value of a
613 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
614 * Unicode low-surrogate code unit</a>
615 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
616 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
617 *
618 * @since 1.5
619 */
620 public static final char MIN_LOW_SURROGATE = '\uDC00';
621
622 /**
623 * The maximum value of a
624 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
625 * Unicode low-surrogate code unit</a>
626 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
627 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
628 *
629 * @since 1.5
630 */
631 public static final char MAX_LOW_SURROGATE = '\uDFFF';
632
633 /**
634 * The minimum value of a Unicode surrogate code unit in the
635 * UTF-16 encoding, constant {@code '\u005CuD800'}.
636 *
637 * @since 1.5
638 */
639 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
640
641 /**
642 * The maximum value of a Unicode surrogate code unit in the
643 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
644 *
645 * @since 1.5
646 */
647 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
648
649 /**
650 * The minimum value of a
651 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
652 * Unicode supplementary code point</a>, constant {@code U+10000}.
653 *
654 * @since 1.5
655 */
656 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
657
658 /**
659 * The minimum value of a
660 * <a href="http://www.unicode.org/glossary/#code_point">
661 * Unicode code point</a>, constant {@code U+0000}.
662 *
663 * @since 1.5
664 */
665 public static final int MIN_CODE_POINT = 0x000000;
666
667 /**
668 * The maximum value of a
669 * <a href="http://www.unicode.org/glossary/#code_point">
670 * Unicode code point</a>, constant {@code U+10FFFF}.
671 *
672 * @since 1.5
673 */
674 public static final int MAX_CODE_POINT = 0X10FFFF;
675
676 /**
677 * Returns an {@link Optional} containing the nominal descriptor for this
678 * instance.
679 *
680 * @return an {@link Optional} describing the {@linkplain Character} instance
681 * @since 15
682 */
683 @Override
684 public Optional<DynamicConstantDesc<Character>> describeConstable() {
685 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
686 }
687
688 /**
689 * Instances of this class represent particular subsets of the Unicode
690 * character set. The only family of subsets defined in the
691 * {@code Character} class is {@link Character.UnicodeBlock}.
692 * Other portions of the Java API may define other subsets for their
693 * own purposes.
694 *
695 * @since 1.2
696 */
697 public static class Subset {
698
699 private String name;
700
701 /**
702 * Constructs a new {@code Subset} instance.
703 *
704 * @param name The name of this subset
705 * @throws NullPointerException if name is {@code null}
706 */
707 protected Subset(String name) {
708 if (name == null) {
709 throw new NullPointerException("name");
710 }
711 this.name = name;
712 }
713
714 /**
715 * Compares two {@code Subset} objects for equality.
716 * This method returns {@code true} if and only if
717 * {@code this} and the argument refer to the same
718 * object; since this method is {@code final}, this
719 * guarantee holds for all subclasses.
720 */
721 public final boolean equals(Object obj) {
722 return (this == obj);
723 }
724
725 /**
726 * Returns the standard hash code as defined by the
727 * {@link Object#hashCode} method. This method
728 * is {@code final} in order to ensure that the
729 * {@code equals} and {@code hashCode} methods will
730 * be consistent in all subclasses.
731 */
732 public final int hashCode() {
733 return super.hashCode();
734 }
735
736 /**
737 * Returns the name of this subset.
738 */
739 public final String toString() {
740 return name;
741 }
742 }
743
744 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
745 // for the latest specification of Unicode Blocks.
746
747 /**
748 * A family of character subsets representing the character blocks in the
749 * Unicode specification. Character blocks generally define characters
750 * used for a specific script or purpose. A character is contained by
751 * at most one Unicode block.
752 *
753 * @since 1.2
754 */
755 public static final class UnicodeBlock extends Subset {
756 /**
757 * NUM_ENTITIES should match the total number of UnicodeBlock identifier
758 * names plus their aliases.
759 * It should be adjusted whenever the Unicode Character Database
760 * is upgraded.
761 */
762 private static final int NUM_ENTITIES = 804;
763 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
764
765 /**
766 * Creates a UnicodeBlock with the given identifier name.
767 * This name must be the same as the block identifier.
768 */
769 private UnicodeBlock(String idName) {
770 super(idName);
771 map.put(idName, this);
772 }
773
774 /**
775 * Creates a UnicodeBlock with the given identifier name and
776 * alias name.
777 */
778 private UnicodeBlock(String idName, String alias) {
779 this(idName);
780 map.put(alias, this);
781 }
782
783 /**
784 * Creates a UnicodeBlock with the given identifier name and
785 * alias names.
786 */
787 private UnicodeBlock(String idName, String... aliases) {
788 this(idName);
789 for (String alias : aliases)
790 map.put(alias, this);
791 }
792
793 /**
794 * Constant for the "Basic Latin" Unicode character block.
795 * @since 1.2
796 */
797 public static final UnicodeBlock BASIC_LATIN =
798 new UnicodeBlock("BASIC_LATIN",
799 "BASIC LATIN",
800 "BASICLATIN");
801
802 /**
803 * Constant for the "Latin-1 Supplement" Unicode character block.
804 * @since 1.2
805 */
806 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
807 new UnicodeBlock("LATIN_1_SUPPLEMENT",
808 "LATIN-1 SUPPLEMENT",
809 "LATIN-1SUPPLEMENT");
810
811 /**
812 * Constant for the "Latin Extended-A" Unicode character block.
813 * @since 1.2
814 */
815 public static final UnicodeBlock LATIN_EXTENDED_A =
816 new UnicodeBlock("LATIN_EXTENDED_A",
817 "LATIN EXTENDED-A",
818 "LATINEXTENDED-A");
819
820 /**
821 * Constant for the "Latin Extended-B" Unicode character block.
822 * @since 1.2
823 */
824 public static final UnicodeBlock LATIN_EXTENDED_B =
825 new UnicodeBlock("LATIN_EXTENDED_B",
826 "LATIN EXTENDED-B",
827 "LATINEXTENDED-B");
828
829 /**
830 * Constant for the "IPA Extensions" Unicode character block.
831 * @since 1.2
832 */
833 public static final UnicodeBlock IPA_EXTENSIONS =
834 new UnicodeBlock("IPA_EXTENSIONS",
835 "IPA EXTENSIONS",
836 "IPAEXTENSIONS");
837
838 /**
839 * Constant for the "Spacing Modifier Letters" Unicode character block.
840 * @since 1.2
841 */
842 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
843 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
844 "SPACING MODIFIER LETTERS",
845 "SPACINGMODIFIERLETTERS");
846
847 /**
848 * Constant for the "Combining Diacritical Marks" Unicode character block.
849 * @since 1.2
850 */
851 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
852 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
853 "COMBINING DIACRITICAL MARKS",
854 "COMBININGDIACRITICALMARKS");
855
856 /**
857 * Constant for the "Greek and Coptic" Unicode character block.
858 * <p>
859 * This block was previously known as the "Greek" block.
860 *
861 * @since 1.2
862 */
863 public static final UnicodeBlock GREEK =
864 new UnicodeBlock("GREEK",
865 "GREEK AND COPTIC",
866 "GREEKANDCOPTIC");
867
868 /**
869 * Constant for the "Cyrillic" Unicode character block.
870 * @since 1.2
871 */
872 public static final UnicodeBlock CYRILLIC =
873 new UnicodeBlock("CYRILLIC");
874
875 /**
876 * Constant for the "Armenian" Unicode character block.
877 * @since 1.2
878 */
879 public static final UnicodeBlock ARMENIAN =
880 new UnicodeBlock("ARMENIAN");
881
882 /**
883 * Constant for the "Hebrew" Unicode character block.
884 * @since 1.2
885 */
886 public static final UnicodeBlock HEBREW =
887 new UnicodeBlock("HEBREW");
888
889 /**
890 * Constant for the "Arabic" Unicode character block.
891 * @since 1.2
892 */
893 public static final UnicodeBlock ARABIC =
894 new UnicodeBlock("ARABIC");
895
896 /**
897 * Constant for the "Devanagari" Unicode character block.
898 * @since 1.2
899 */
900 public static final UnicodeBlock DEVANAGARI =
901 new UnicodeBlock("DEVANAGARI");
902
903 /**
904 * Constant for the "Bengali" Unicode character block.
905 * @since 1.2
906 */
907 public static final UnicodeBlock BENGALI =
908 new UnicodeBlock("BENGALI");
909
910 /**
911 * Constant for the "Gurmukhi" Unicode character block.
912 * @since 1.2
913 */
914 public static final UnicodeBlock GURMUKHI =
915 new UnicodeBlock("GURMUKHI");
916
917 /**
918 * Constant for the "Gujarati" Unicode character block.
919 * @since 1.2
920 */
921 public static final UnicodeBlock GUJARATI =
922 new UnicodeBlock("GUJARATI");
923
924 /**
925 * Constant for the "Oriya" Unicode character block.
926 * @since 1.2
927 */
928 public static final UnicodeBlock ORIYA =
929 new UnicodeBlock("ORIYA");
930
931 /**
932 * Constant for the "Tamil" Unicode character block.
933 * @since 1.2
934 */
935 public static final UnicodeBlock TAMIL =
936 new UnicodeBlock("TAMIL");
937
938 /**
939 * Constant for the "Telugu" Unicode character block.
940 * @since 1.2
941 */
942 public static final UnicodeBlock TELUGU =
943 new UnicodeBlock("TELUGU");
944
945 /**
946 * Constant for the "Kannada" Unicode character block.
947 * @since 1.2
948 */
949 public static final UnicodeBlock KANNADA =
950 new UnicodeBlock("KANNADA");
951
952 /**
953 * Constant for the "Malayalam" Unicode character block.
954 * @since 1.2
955 */
956 public static final UnicodeBlock MALAYALAM =
957 new UnicodeBlock("MALAYALAM");
958
959 /**
960 * Constant for the "Thai" Unicode character block.
961 * @since 1.2
962 */
963 public static final UnicodeBlock THAI =
964 new UnicodeBlock("THAI");
965
966 /**
967 * Constant for the "Lao" Unicode character block.
968 * @since 1.2
969 */
970 public static final UnicodeBlock LAO =
971 new UnicodeBlock("LAO");
972
973 /**
974 * Constant for the "Tibetan" Unicode character block.
975 * @since 1.2
976 */
977 public static final UnicodeBlock TIBETAN =
978 new UnicodeBlock("TIBETAN");
979
980 /**
981 * Constant for the "Georgian" Unicode character block.
982 * @since 1.2
983 */
984 public static final UnicodeBlock GEORGIAN =
985 new UnicodeBlock("GEORGIAN");
986
987 /**
988 * Constant for the "Hangul Jamo" Unicode character block.
989 * @since 1.2
990 */
991 public static final UnicodeBlock HANGUL_JAMO =
992 new UnicodeBlock("HANGUL_JAMO",
993 "HANGUL JAMO",
994 "HANGULJAMO");
995
996 /**
997 * Constant for the "Latin Extended Additional" Unicode character block.
998 * @since 1.2
999 */
1000 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
1001 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
1002 "LATIN EXTENDED ADDITIONAL",
1003 "LATINEXTENDEDADDITIONAL");
1004
1005 /**
1006 * Constant for the "Greek Extended" Unicode character block.
1007 * @since 1.2
1008 */
1009 public static final UnicodeBlock GREEK_EXTENDED =
1010 new UnicodeBlock("GREEK_EXTENDED",
1011 "GREEK EXTENDED",
1012 "GREEKEXTENDED");
1013
1014 /**
1015 * Constant for the "General Punctuation" Unicode character block.
1016 * @since 1.2
1017 */
1018 public static final UnicodeBlock GENERAL_PUNCTUATION =
1019 new UnicodeBlock("GENERAL_PUNCTUATION",
1020 "GENERAL PUNCTUATION",
1021 "GENERALPUNCTUATION");
1022
1023 /**
1024 * Constant for the "Superscripts and Subscripts" Unicode character
1025 * block.
1026 * @since 1.2
1027 */
1028 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1029 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1030 "SUPERSCRIPTS AND SUBSCRIPTS",
1031 "SUPERSCRIPTSANDSUBSCRIPTS");
1032
1033 /**
1034 * Constant for the "Currency Symbols" Unicode character block.
1035 * @since 1.2
1036 */
1037 public static final UnicodeBlock CURRENCY_SYMBOLS =
1038 new UnicodeBlock("CURRENCY_SYMBOLS",
1039 "CURRENCY SYMBOLS",
1040 "CURRENCYSYMBOLS");
1041
1042 /**
1043 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1044 * character block.
1045 * <p>
1046 * This block was previously known as "Combining Marks for Symbols".
1047 * @since 1.2
1048 */
1049 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1050 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1051 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1052 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1053 "COMBINING MARKS FOR SYMBOLS",
1054 "COMBININGMARKSFORSYMBOLS");
1055
1056 /**
1057 * Constant for the "Letterlike Symbols" Unicode character block.
1058 * @since 1.2
1059 */
1060 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1061 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1062 "LETTERLIKE SYMBOLS",
1063 "LETTERLIKESYMBOLS");
1064
1065 /**
1066 * Constant for the "Number Forms" Unicode character block.
1067 * @since 1.2
1068 */
1069 public static final UnicodeBlock NUMBER_FORMS =
1070 new UnicodeBlock("NUMBER_FORMS",
1071 "NUMBER FORMS",
1072 "NUMBERFORMS");
1073
1074 /**
1075 * Constant for the "Arrows" Unicode character block.
1076 * @since 1.2
1077 */
1078 public static final UnicodeBlock ARROWS =
1079 new UnicodeBlock("ARROWS");
1080
1081 /**
1082 * Constant for the "Mathematical Operators" Unicode character block.
1083 * @since 1.2
1084 */
1085 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1086 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1087 "MATHEMATICAL OPERATORS",
1088 "MATHEMATICALOPERATORS");
1089
1090 /**
1091 * Constant for the "Miscellaneous Technical" Unicode character block.
1092 * @since 1.2
1093 */
1094 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1095 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1096 "MISCELLANEOUS TECHNICAL",
1097 "MISCELLANEOUSTECHNICAL");
1098
1099 /**
1100 * Constant for the "Control Pictures" Unicode character block.
1101 * @since 1.2
1102 */
1103 public static final UnicodeBlock CONTROL_PICTURES =
1104 new UnicodeBlock("CONTROL_PICTURES",
1105 "CONTROL PICTURES",
1106 "CONTROLPICTURES");
1107
1108 /**
1109 * Constant for the "Optical Character Recognition" Unicode character block.
1110 * @since 1.2
1111 */
1112 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1113 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1114 "OPTICAL CHARACTER RECOGNITION",
1115 "OPTICALCHARACTERRECOGNITION");
1116
1117 /**
1118 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1119 * @since 1.2
1120 */
1121 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1122 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1123 "ENCLOSED ALPHANUMERICS",
1124 "ENCLOSEDALPHANUMERICS");
1125
1126 /**
1127 * Constant for the "Box Drawing" Unicode character block.
1128 * @since 1.2
1129 */
1130 public static final UnicodeBlock BOX_DRAWING =
1131 new UnicodeBlock("BOX_DRAWING",
1132 "BOX DRAWING",
1133 "BOXDRAWING");
1134
1135 /**
1136 * Constant for the "Block Elements" Unicode character block.
1137 * @since 1.2
1138 */
1139 public static final UnicodeBlock BLOCK_ELEMENTS =
1140 new UnicodeBlock("BLOCK_ELEMENTS",
1141 "BLOCK ELEMENTS",
1142 "BLOCKELEMENTS");
1143
1144 /**
1145 * Constant for the "Geometric Shapes" Unicode character block.
1146 * @since 1.2
1147 */
1148 public static final UnicodeBlock GEOMETRIC_SHAPES =
1149 new UnicodeBlock("GEOMETRIC_SHAPES",
1150 "GEOMETRIC SHAPES",
1151 "GEOMETRICSHAPES");
1152
1153 /**
1154 * Constant for the "Miscellaneous Symbols" Unicode character block.
1155 * @since 1.2
1156 */
1157 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1158 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1159 "MISCELLANEOUS SYMBOLS",
1160 "MISCELLANEOUSSYMBOLS");
1161
1162 /**
1163 * Constant for the "Dingbats" Unicode character block.
1164 * @since 1.2
1165 */
1166 public static final UnicodeBlock DINGBATS =
1167 new UnicodeBlock("DINGBATS");
1168
1169 /**
1170 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1171 * @since 1.2
1172 */
1173 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1174 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1175 "CJK SYMBOLS AND PUNCTUATION",
1176 "CJKSYMBOLSANDPUNCTUATION");
1177
1178 /**
1179 * Constant for the "Hiragana" Unicode character block.
1180 * @since 1.2
1181 */
1182 public static final UnicodeBlock HIRAGANA =
1183 new UnicodeBlock("HIRAGANA");
1184
1185 /**
1186 * Constant for the "Katakana" Unicode character block.
1187 * @since 1.2
1188 */
1189 public static final UnicodeBlock KATAKANA =
1190 new UnicodeBlock("KATAKANA");
1191
1192 /**
1193 * Constant for the "Bopomofo" Unicode character block.
1194 * @since 1.2
1195 */
1196 public static final UnicodeBlock BOPOMOFO =
1197 new UnicodeBlock("BOPOMOFO");
1198
1199 /**
1200 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1201 * @since 1.2
1202 */
1203 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1204 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1205 "HANGUL COMPATIBILITY JAMO",
1206 "HANGULCOMPATIBILITYJAMO");
1207
1208 /**
1209 * Constant for the "Kanbun" Unicode character block.
1210 * @since 1.2
1211 */
1212 public static final UnicodeBlock KANBUN =
1213 new UnicodeBlock("KANBUN");
1214
1215 /**
1216 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1217 * @since 1.2
1218 */
1219 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1220 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1221 "ENCLOSED CJK LETTERS AND MONTHS",
1222 "ENCLOSEDCJKLETTERSANDMONTHS");
1223
1224 /**
1225 * Constant for the "CJK Compatibility" Unicode character block.
1226 * @since 1.2
1227 */
1228 public static final UnicodeBlock CJK_COMPATIBILITY =
1229 new UnicodeBlock("CJK_COMPATIBILITY",
1230 "CJK COMPATIBILITY",
1231 "CJKCOMPATIBILITY");
1232
1233 /**
1234 * Constant for the "CJK Unified Ideographs" Unicode character block.
1235 * @since 1.2
1236 */
1237 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1238 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1239 "CJK UNIFIED IDEOGRAPHS",
1240 "CJKUNIFIEDIDEOGRAPHS");
1241
1242 /**
1243 * Constant for the "Hangul Syllables" Unicode character block.
1244 * @since 1.2
1245 */
1246 public static final UnicodeBlock HANGUL_SYLLABLES =
1247 new UnicodeBlock("HANGUL_SYLLABLES",
1248 "HANGUL SYLLABLES",
1249 "HANGULSYLLABLES");
1250
1251 /**
1252 * Constant for the "Private Use Area" Unicode character block.
1253 * @since 1.2
1254 */
1255 public static final UnicodeBlock PRIVATE_USE_AREA =
1256 new UnicodeBlock("PRIVATE_USE_AREA",
1257 "PRIVATE USE AREA",
1258 "PRIVATEUSEAREA");
1259
1260 /**
1261 * Constant for the "CJK Compatibility Ideographs" Unicode character
1262 * block.
1263 * @since 1.2
1264 */
1265 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1266 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1267 "CJK COMPATIBILITY IDEOGRAPHS",
1268 "CJKCOMPATIBILITYIDEOGRAPHS");
1269
1270 /**
1271 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1272 * @since 1.2
1273 */
1274 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1275 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1276 "ALPHABETIC PRESENTATION FORMS",
1277 "ALPHABETICPRESENTATIONFORMS");
1278
1279 /**
1280 * Constant for the "Arabic Presentation Forms-A" Unicode character
1281 * block.
1282 * @since 1.2
1283 */
1284 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1285 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1286 "ARABIC PRESENTATION FORMS-A",
1287 "ARABICPRESENTATIONFORMS-A");
1288
1289 /**
1290 * Constant for the "Combining Half Marks" Unicode character block.
1291 * @since 1.2
1292 */
1293 public static final UnicodeBlock COMBINING_HALF_MARKS =
1294 new UnicodeBlock("COMBINING_HALF_MARKS",
1295 "COMBINING HALF MARKS",
1296 "COMBININGHALFMARKS");
1297
1298 /**
1299 * Constant for the "CJK Compatibility Forms" Unicode character block.
1300 * @since 1.2
1301 */
1302 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1303 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1304 "CJK COMPATIBILITY FORMS",
1305 "CJKCOMPATIBILITYFORMS");
1306
1307 /**
1308 * Constant for the "Small Form Variants" Unicode character block.
1309 * @since 1.2
1310 */
1311 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1312 new UnicodeBlock("SMALL_FORM_VARIANTS",
1313 "SMALL FORM VARIANTS",
1314 "SMALLFORMVARIANTS");
1315
1316 /**
1317 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1318 * @since 1.2
1319 */
1320 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1321 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1322 "ARABIC PRESENTATION FORMS-B",
1323 "ARABICPRESENTATIONFORMS-B");
1324
1325 /**
1326 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1327 * block.
1328 * @since 1.2
1329 */
1330 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1331 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1332 "HALFWIDTH AND FULLWIDTH FORMS",
1333 "HALFWIDTHANDFULLWIDTHFORMS");
1334
1335 /**
1336 * Constant for the "Specials" Unicode character block.
1337 * @since 1.2
1338 */
1339 public static final UnicodeBlock SPECIALS =
1340 new UnicodeBlock("SPECIALS");
1341
1342 /**
1343 * @deprecated
1344 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1345 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1346 * These constants match the block definitions of the Unicode Standard.
1347 * The {@link #of(char)} and {@link #of(int)} methods return the
1348 * standard constants.
1349 */
1350 @Deprecated(since="1.5")
1351 public static final UnicodeBlock SURROGATES_AREA =
1352 new UnicodeBlock("SURROGATES_AREA");
1353
1354 /**
1355 * Constant for the "Syriac" Unicode character block.
1356 * @since 1.4
1357 */
1358 public static final UnicodeBlock SYRIAC =
1359 new UnicodeBlock("SYRIAC");
1360
1361 /**
1362 * Constant for the "Thaana" Unicode character block.
1363 * @since 1.4
1364 */
1365 public static final UnicodeBlock THAANA =
1366 new UnicodeBlock("THAANA");
1367
1368 /**
1369 * Constant for the "Sinhala" Unicode character block.
1370 * @since 1.4
1371 */
1372 public static final UnicodeBlock SINHALA =
1373 new UnicodeBlock("SINHALA");
1374
1375 /**
1376 * Constant for the "Myanmar" Unicode character block.
1377 * @since 1.4
1378 */
1379 public static final UnicodeBlock MYANMAR =
1380 new UnicodeBlock("MYANMAR");
1381
1382 /**
1383 * Constant for the "Ethiopic" Unicode character block.
1384 * @since 1.4
1385 */
1386 public static final UnicodeBlock ETHIOPIC =
1387 new UnicodeBlock("ETHIOPIC");
1388
1389 /**
1390 * Constant for the "Cherokee" Unicode character block.
1391 * @since 1.4
1392 */
1393 public static final UnicodeBlock CHEROKEE =
1394 new UnicodeBlock("CHEROKEE");
1395
1396 /**
1397 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1398 * @since 1.4
1399 */
1400 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1401 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1402 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1403 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1404
1405 /**
1406 * Constant for the "Ogham" Unicode character block.
1407 * @since 1.4
1408 */
1409 public static final UnicodeBlock OGHAM =
1410 new UnicodeBlock("OGHAM");
1411
1412 /**
1413 * Constant for the "Runic" Unicode character block.
1414 * @since 1.4
1415 */
1416 public static final UnicodeBlock RUNIC =
1417 new UnicodeBlock("RUNIC");
1418
1419 /**
1420 * Constant for the "Khmer" Unicode character block.
1421 * @since 1.4
1422 */
1423 public static final UnicodeBlock KHMER =
1424 new UnicodeBlock("KHMER");
1425
1426 /**
1427 * Constant for the "Mongolian" Unicode character block.
1428 * @since 1.4
1429 */
1430 public static final UnicodeBlock MONGOLIAN =
1431 new UnicodeBlock("MONGOLIAN");
1432
1433 /**
1434 * Constant for the "Braille Patterns" Unicode character block.
1435 * @since 1.4
1436 */
1437 public static final UnicodeBlock BRAILLE_PATTERNS =
1438 new UnicodeBlock("BRAILLE_PATTERNS",
1439 "BRAILLE PATTERNS",
1440 "BRAILLEPATTERNS");
1441
1442 /**
1443 * Constant for the "CJK Radicals Supplement" Unicode character block.
1444 * @since 1.4
1445 */
1446 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1447 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1448 "CJK RADICALS SUPPLEMENT",
1449 "CJKRADICALSSUPPLEMENT");
1450
1451 /**
1452 * Constant for the "Kangxi Radicals" Unicode character block.
1453 * @since 1.4
1454 */
1455 public static final UnicodeBlock KANGXI_RADICALS =
1456 new UnicodeBlock("KANGXI_RADICALS",
1457 "KANGXI RADICALS",
1458 "KANGXIRADICALS");
1459
1460 /**
1461 * Constant for the "Ideographic Description Characters" Unicode character block.
1462 * @since 1.4
1463 */
1464 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1465 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1466 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1467 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1468
1469 /**
1470 * Constant for the "Bopomofo Extended" Unicode character block.
1471 * @since 1.4
1472 */
1473 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1474 new UnicodeBlock("BOPOMOFO_EXTENDED",
1475 "BOPOMOFO EXTENDED",
1476 "BOPOMOFOEXTENDED");
1477
1478 /**
1479 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1480 * @since 1.4
1481 */
1482 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1483 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1484 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1485 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1486
1487 /**
1488 * Constant for the "Yi Syllables" Unicode character block.
1489 * @since 1.4
1490 */
1491 public static final UnicodeBlock YI_SYLLABLES =
1492 new UnicodeBlock("YI_SYLLABLES",
1493 "YI SYLLABLES",
1494 "YISYLLABLES");
1495
1496 /**
1497 * Constant for the "Yi Radicals" Unicode character block.
1498 * @since 1.4
1499 */
1500 public static final UnicodeBlock YI_RADICALS =
1501 new UnicodeBlock("YI_RADICALS",
1502 "YI RADICALS",
1503 "YIRADICALS");
1504
1505 /**
1506 * Constant for the "Cyrillic Supplement" Unicode character block.
1507 * This block was previously known as the "Cyrillic Supplementary" block.
1508 * @since 1.5
1509 */
1510 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1511 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1512 "CYRILLIC SUPPLEMENTARY",
1513 "CYRILLICSUPPLEMENTARY",
1514 "CYRILLIC SUPPLEMENT",
1515 "CYRILLICSUPPLEMENT");
1516
1517 /**
1518 * Constant for the "Tagalog" Unicode character block.
1519 * @since 1.5
1520 */
1521 public static final UnicodeBlock TAGALOG =
1522 new UnicodeBlock("TAGALOG");
1523
1524 /**
1525 * Constant for the "Hanunoo" Unicode character block.
1526 * @since 1.5
1527 */
1528 public static final UnicodeBlock HANUNOO =
1529 new UnicodeBlock("HANUNOO");
1530
1531 /**
1532 * Constant for the "Buhid" Unicode character block.
1533 * @since 1.5
1534 */
1535 public static final UnicodeBlock BUHID =
1536 new UnicodeBlock("BUHID");
1537
1538 /**
1539 * Constant for the "Tagbanwa" Unicode character block.
1540 * @since 1.5
1541 */
1542 public static final UnicodeBlock TAGBANWA =
1543 new UnicodeBlock("TAGBANWA");
1544
1545 /**
1546 * Constant for the "Limbu" Unicode character block.
1547 * @since 1.5
1548 */
1549 public static final UnicodeBlock LIMBU =
1550 new UnicodeBlock("LIMBU");
1551
1552 /**
1553 * Constant for the "Tai Le" Unicode character block.
1554 * @since 1.5
1555 */
1556 public static final UnicodeBlock TAI_LE =
1557 new UnicodeBlock("TAI_LE",
1558 "TAI LE",
1559 "TAILE");
1560
1561 /**
1562 * Constant for the "Khmer Symbols" Unicode character block.
1563 * @since 1.5
1564 */
1565 public static final UnicodeBlock KHMER_SYMBOLS =
1566 new UnicodeBlock("KHMER_SYMBOLS",
1567 "KHMER SYMBOLS",
1568 "KHMERSYMBOLS");
1569
1570 /**
1571 * Constant for the "Phonetic Extensions" Unicode character block.
1572 * @since 1.5
1573 */
1574 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1575 new UnicodeBlock("PHONETIC_EXTENSIONS",
1576 "PHONETIC EXTENSIONS",
1577 "PHONETICEXTENSIONS");
1578
1579 /**
1580 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1581 * @since 1.5
1582 */
1583 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1584 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1585 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1586 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1587
1588 /**
1589 * Constant for the "Supplemental Arrows-A" Unicode character block.
1590 * @since 1.5
1591 */
1592 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1593 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1594 "SUPPLEMENTAL ARROWS-A",
1595 "SUPPLEMENTALARROWS-A");
1596
1597 /**
1598 * Constant for the "Supplemental Arrows-B" Unicode character block.
1599 * @since 1.5
1600 */
1601 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1602 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1603 "SUPPLEMENTAL ARROWS-B",
1604 "SUPPLEMENTALARROWS-B");
1605
1606 /**
1607 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1608 * character block.
1609 * @since 1.5
1610 */
1611 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1612 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1613 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1614 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1615
1616 /**
1617 * Constant for the "Supplemental Mathematical Operators" Unicode
1618 * character block.
1619 * @since 1.5
1620 */
1621 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1622 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1623 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1624 "SUPPLEMENTALMATHEMATICALOPERATORS");
1625
1626 /**
1627 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1628 * block.
1629 * @since 1.5
1630 */
1631 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1632 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1633 "MISCELLANEOUS SYMBOLS AND ARROWS",
1634 "MISCELLANEOUSSYMBOLSANDARROWS");
1635
1636 /**
1637 * Constant for the "Katakana Phonetic Extensions" Unicode character
1638 * block.
1639 * @since 1.5
1640 */
1641 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1642 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1643 "KATAKANA PHONETIC EXTENSIONS",
1644 "KATAKANAPHONETICEXTENSIONS");
1645
1646 /**
1647 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1648 * @since 1.5
1649 */
1650 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1651 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1652 "YIJING HEXAGRAM SYMBOLS",
1653 "YIJINGHEXAGRAMSYMBOLS");
1654
1655 /**
1656 * Constant for the "Variation Selectors" Unicode character block.
1657 * @since 1.5
1658 */
1659 public static final UnicodeBlock VARIATION_SELECTORS =
1660 new UnicodeBlock("VARIATION_SELECTORS",
1661 "VARIATION SELECTORS",
1662 "VARIATIONSELECTORS");
1663
1664 /**
1665 * Constant for the "Linear B Syllabary" Unicode character block.
1666 * @since 1.5
1667 */
1668 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1669 new UnicodeBlock("LINEAR_B_SYLLABARY",
1670 "LINEAR B SYLLABARY",
1671 "LINEARBSYLLABARY");
1672
1673 /**
1674 * Constant for the "Linear B Ideograms" Unicode character block.
1675 * @since 1.5
1676 */
1677 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1678 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1679 "LINEAR B IDEOGRAMS",
1680 "LINEARBIDEOGRAMS");
1681
1682 /**
1683 * Constant for the "Aegean Numbers" Unicode character block.
1684 * @since 1.5
1685 */
1686 public static final UnicodeBlock AEGEAN_NUMBERS =
1687 new UnicodeBlock("AEGEAN_NUMBERS",
1688 "AEGEAN NUMBERS",
1689 "AEGEANNUMBERS");
1690
1691 /**
1692 * Constant for the "Old Italic" Unicode character block.
1693 * @since 1.5
1694 */
1695 public static final UnicodeBlock OLD_ITALIC =
1696 new UnicodeBlock("OLD_ITALIC",
1697 "OLD ITALIC",
1698 "OLDITALIC");
1699
1700 /**
1701 * Constant for the "Gothic" Unicode character block.
1702 * @since 1.5
1703 */
1704 public static final UnicodeBlock GOTHIC =
1705 new UnicodeBlock("GOTHIC");
1706
1707 /**
1708 * Constant for the "Ugaritic" Unicode character block.
1709 * @since 1.5
1710 */
1711 public static final UnicodeBlock UGARITIC =
1712 new UnicodeBlock("UGARITIC");
1713
1714 /**
1715 * Constant for the "Deseret" Unicode character block.
1716 * @since 1.5
1717 */
1718 public static final UnicodeBlock DESERET =
1719 new UnicodeBlock("DESERET");
1720
1721 /**
1722 * Constant for the "Shavian" Unicode character block.
1723 * @since 1.5
1724 */
1725 public static final UnicodeBlock SHAVIAN =
1726 new UnicodeBlock("SHAVIAN");
1727
1728 /**
1729 * Constant for the "Osmanya" Unicode character block.
1730 * @since 1.5
1731 */
1732 public static final UnicodeBlock OSMANYA =
1733 new UnicodeBlock("OSMANYA");
1734
1735 /**
1736 * Constant for the "Cypriot Syllabary" Unicode character block.
1737 * @since 1.5
1738 */
1739 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1740 new UnicodeBlock("CYPRIOT_SYLLABARY",
1741 "CYPRIOT SYLLABARY",
1742 "CYPRIOTSYLLABARY");
1743
1744 /**
1745 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1746 * @since 1.5
1747 */
1748 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1749 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1750 "BYZANTINE MUSICAL SYMBOLS",
1751 "BYZANTINEMUSICALSYMBOLS");
1752
1753 /**
1754 * Constant for the "Musical Symbols" Unicode character block.
1755 * @since 1.5
1756 */
1757 public static final UnicodeBlock MUSICAL_SYMBOLS =
1758 new UnicodeBlock("MUSICAL_SYMBOLS",
1759 "MUSICAL SYMBOLS",
1760 "MUSICALSYMBOLS");
1761
1762 /**
1763 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1764 * @since 1.5
1765 */
1766 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1767 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1768 "TAI XUAN JING SYMBOLS",
1769 "TAIXUANJINGSYMBOLS");
1770
1771 /**
1772 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1773 * character block.
1774 * @since 1.5
1775 */
1776 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1777 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1778 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1779 "MATHEMATICALALPHANUMERICSYMBOLS");
1780
1781 /**
1782 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1783 * character block.
1784 * @since 1.5
1785 */
1786 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1787 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1788 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1789 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1790
1791 /**
1792 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1793 * @since 1.5
1794 */
1795 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1796 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1797 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1798 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1799
1800 /**
1801 * Constant for the "Tags" Unicode character block.
1802 * @since 1.5
1803 */
1804 public static final UnicodeBlock TAGS =
1805 new UnicodeBlock("TAGS");
1806
1807 /**
1808 * Constant for the "Variation Selectors Supplement" Unicode character
1809 * block.
1810 * @since 1.5
1811 */
1812 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1813 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1814 "VARIATION SELECTORS SUPPLEMENT",
1815 "VARIATIONSELECTORSSUPPLEMENT");
1816
1817 /**
1818 * Constant for the "Supplementary Private Use Area-A" Unicode character
1819 * block.
1820 * @since 1.5
1821 */
1822 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1823 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1824 "SUPPLEMENTARY PRIVATE USE AREA-A",
1825 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1826
1827 /**
1828 * Constant for the "Supplementary Private Use Area-B" Unicode character
1829 * block.
1830 * @since 1.5
1831 */
1832 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1833 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1834 "SUPPLEMENTARY PRIVATE USE AREA-B",
1835 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1836
1837 /**
1838 * Constant for the "High Surrogates" Unicode character block.
1839 * This block represents codepoint values in the high surrogate
1840 * range: U+D800 through U+DB7F
1841 *
1842 * @since 1.5
1843 */
1844 public static final UnicodeBlock HIGH_SURROGATES =
1845 new UnicodeBlock("HIGH_SURROGATES",
1846 "HIGH SURROGATES",
1847 "HIGHSURROGATES");
1848
1849 /**
1850 * Constant for the "High Private Use Surrogates" Unicode character
1851 * block.
1852 * This block represents codepoint values in the private use high
1853 * surrogate range: U+DB80 through U+DBFF
1854 *
1855 * @since 1.5
1856 */
1857 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1858 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1859 "HIGH PRIVATE USE SURROGATES",
1860 "HIGHPRIVATEUSESURROGATES");
1861
1862 /**
1863 * Constant for the "Low Surrogates" Unicode character block.
1864 * This block represents codepoint values in the low surrogate
1865 * range: U+DC00 through U+DFFF
1866 *
1867 * @since 1.5
1868 */
1869 public static final UnicodeBlock LOW_SURROGATES =
1870 new UnicodeBlock("LOW_SURROGATES",
1871 "LOW SURROGATES",
1872 "LOWSURROGATES");
1873
1874 /**
1875 * Constant for the "Arabic Supplement" Unicode character block.
1876 * @since 1.7
1877 */
1878 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1879 new UnicodeBlock("ARABIC_SUPPLEMENT",
1880 "ARABIC SUPPLEMENT",
1881 "ARABICSUPPLEMENT");
1882
1883 /**
1884 * Constant for the "NKo" Unicode character block.
1885 * @since 1.7
1886 */
1887 public static final UnicodeBlock NKO =
1888 new UnicodeBlock("NKO");
1889
1890 /**
1891 * Constant for the "Samaritan" Unicode character block.
1892 * @since 1.7
1893 */
1894 public static final UnicodeBlock SAMARITAN =
1895 new UnicodeBlock("SAMARITAN");
1896
1897 /**
1898 * Constant for the "Mandaic" Unicode character block.
1899 * @since 1.7
1900 */
1901 public static final UnicodeBlock MANDAIC =
1902 new UnicodeBlock("MANDAIC");
1903
1904 /**
1905 * Constant for the "Ethiopic Supplement" Unicode character block.
1906 * @since 1.7
1907 */
1908 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1909 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1910 "ETHIOPIC SUPPLEMENT",
1911 "ETHIOPICSUPPLEMENT");
1912
1913 /**
1914 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1915 * Unicode character block.
1916 * @since 1.7
1917 */
1918 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1919 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1920 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1921 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1922
1923 /**
1924 * Constant for the "New Tai Lue" Unicode character block.
1925 * @since 1.7
1926 */
1927 public static final UnicodeBlock NEW_TAI_LUE =
1928 new UnicodeBlock("NEW_TAI_LUE",
1929 "NEW TAI LUE",
1930 "NEWTAILUE");
1931
1932 /**
1933 * Constant for the "Buginese" Unicode character block.
1934 * @since 1.7
1935 */
1936 public static final UnicodeBlock BUGINESE =
1937 new UnicodeBlock("BUGINESE");
1938
1939 /**
1940 * Constant for the "Tai Tham" Unicode character block.
1941 * @since 1.7
1942 */
1943 public static final UnicodeBlock TAI_THAM =
1944 new UnicodeBlock("TAI_THAM",
1945 "TAI THAM",
1946 "TAITHAM");
1947
1948 /**
1949 * Constant for the "Balinese" Unicode character block.
1950 * @since 1.7
1951 */
1952 public static final UnicodeBlock BALINESE =
1953 new UnicodeBlock("BALINESE");
1954
1955 /**
1956 * Constant for the "Sundanese" Unicode character block.
1957 * @since 1.7
1958 */
1959 public static final UnicodeBlock SUNDANESE =
1960 new UnicodeBlock("SUNDANESE");
1961
1962 /**
1963 * Constant for the "Batak" Unicode character block.
1964 * @since 1.7
1965 */
1966 public static final UnicodeBlock BATAK =
1967 new UnicodeBlock("BATAK");
1968
1969 /**
1970 * Constant for the "Lepcha" Unicode character block.
1971 * @since 1.7
1972 */
1973 public static final UnicodeBlock LEPCHA =
1974 new UnicodeBlock("LEPCHA");
1975
1976 /**
1977 * Constant for the "Ol Chiki" Unicode character block.
1978 * @since 1.7
1979 */
1980 public static final UnicodeBlock OL_CHIKI =
1981 new UnicodeBlock("OL_CHIKI",
1982 "OL CHIKI",
1983 "OLCHIKI");
1984
1985 /**
1986 * Constant for the "Vedic Extensions" Unicode character block.
1987 * @since 1.7
1988 */
1989 public static final UnicodeBlock VEDIC_EXTENSIONS =
1990 new UnicodeBlock("VEDIC_EXTENSIONS",
1991 "VEDIC EXTENSIONS",
1992 "VEDICEXTENSIONS");
1993
1994 /**
1995 * Constant for the "Phonetic Extensions Supplement" Unicode character
1996 * block.
1997 * @since 1.7
1998 */
1999 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
2000 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
2001 "PHONETIC EXTENSIONS SUPPLEMENT",
2002 "PHONETICEXTENSIONSSUPPLEMENT");
2003
2004 /**
2005 * Constant for the "Combining Diacritical Marks Supplement" Unicode
2006 * character block.
2007 * @since 1.7
2008 */
2009 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
2010 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
2011 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
2012 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2013
2014 /**
2015 * Constant for the "Glagolitic" Unicode character block.
2016 * @since 1.7
2017 */
2018 public static final UnicodeBlock GLAGOLITIC =
2019 new UnicodeBlock("GLAGOLITIC");
2020
2021 /**
2022 * Constant for the "Latin Extended-C" Unicode character block.
2023 * @since 1.7
2024 */
2025 public static final UnicodeBlock LATIN_EXTENDED_C =
2026 new UnicodeBlock("LATIN_EXTENDED_C",
2027 "LATIN EXTENDED-C",
2028 "LATINEXTENDED-C");
2029
2030 /**
2031 * Constant for the "Coptic" Unicode character block.
2032 * @since 1.7
2033 */
2034 public static final UnicodeBlock COPTIC =
2035 new UnicodeBlock("COPTIC");
2036
2037 /**
2038 * Constant for the "Georgian Supplement" Unicode character block.
2039 * @since 1.7
2040 */
2041 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2042 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2043 "GEORGIAN SUPPLEMENT",
2044 "GEORGIANSUPPLEMENT");
2045
2046 /**
2047 * Constant for the "Tifinagh" Unicode character block.
2048 * @since 1.7
2049 */
2050 public static final UnicodeBlock TIFINAGH =
2051 new UnicodeBlock("TIFINAGH");
2052
2053 /**
2054 * Constant for the "Ethiopic Extended" Unicode character block.
2055 * @since 1.7
2056 */
2057 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2058 new UnicodeBlock("ETHIOPIC_EXTENDED",
2059 "ETHIOPIC EXTENDED",
2060 "ETHIOPICEXTENDED");
2061
2062 /**
2063 * Constant for the "Cyrillic Extended-A" Unicode character block.
2064 * @since 1.7
2065 */
2066 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2067 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2068 "CYRILLIC EXTENDED-A",
2069 "CYRILLICEXTENDED-A");
2070
2071 /**
2072 * Constant for the "Supplemental Punctuation" Unicode character block.
2073 * @since 1.7
2074 */
2075 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2076 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2077 "SUPPLEMENTAL PUNCTUATION",
2078 "SUPPLEMENTALPUNCTUATION");
2079
2080 /**
2081 * Constant for the "CJK Strokes" Unicode character block.
2082 * @since 1.7
2083 */
2084 public static final UnicodeBlock CJK_STROKES =
2085 new UnicodeBlock("CJK_STROKES",
2086 "CJK STROKES",
2087 "CJKSTROKES");
2088
2089 /**
2090 * Constant for the "Lisu" Unicode character block.
2091 * @since 1.7
2092 */
2093 public static final UnicodeBlock LISU =
2094 new UnicodeBlock("LISU");
2095
2096 /**
2097 * Constant for the "Vai" Unicode character block.
2098 * @since 1.7
2099 */
2100 public static final UnicodeBlock VAI =
2101 new UnicodeBlock("VAI");
2102
2103 /**
2104 * Constant for the "Cyrillic Extended-B" Unicode character block.
2105 * @since 1.7
2106 */
2107 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2108 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2109 "CYRILLIC EXTENDED-B",
2110 "CYRILLICEXTENDED-B");
2111
2112 /**
2113 * Constant for the "Bamum" Unicode character block.
2114 * @since 1.7
2115 */
2116 public static final UnicodeBlock BAMUM =
2117 new UnicodeBlock("BAMUM");
2118
2119 /**
2120 * Constant for the "Modifier Tone Letters" Unicode character block.
2121 * @since 1.7
2122 */
2123 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2124 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2125 "MODIFIER TONE LETTERS",
2126 "MODIFIERTONELETTERS");
2127
2128 /**
2129 * Constant for the "Latin Extended-D" Unicode character block.
2130 * @since 1.7
2131 */
2132 public static final UnicodeBlock LATIN_EXTENDED_D =
2133 new UnicodeBlock("LATIN_EXTENDED_D",
2134 "LATIN EXTENDED-D",
2135 "LATINEXTENDED-D");
2136
2137 /**
2138 * Constant for the "Syloti Nagri" Unicode character block.
2139 * @since 1.7
2140 */
2141 public static final UnicodeBlock SYLOTI_NAGRI =
2142 new UnicodeBlock("SYLOTI_NAGRI",
2143 "SYLOTI NAGRI",
2144 "SYLOTINAGRI");
2145
2146 /**
2147 * Constant for the "Common Indic Number Forms" Unicode character block.
2148 * @since 1.7
2149 */
2150 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2151 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2152 "COMMON INDIC NUMBER FORMS",
2153 "COMMONINDICNUMBERFORMS");
2154
2155 /**
2156 * Constant for the "Phags-pa" Unicode character block.
2157 * @since 1.7
2158 */
2159 public static final UnicodeBlock PHAGS_PA =
2160 new UnicodeBlock("PHAGS_PA",
2161 "PHAGS-PA");
2162
2163 /**
2164 * Constant for the "Saurashtra" Unicode character block.
2165 * @since 1.7
2166 */
2167 public static final UnicodeBlock SAURASHTRA =
2168 new UnicodeBlock("SAURASHTRA");
2169
2170 /**
2171 * Constant for the "Devanagari Extended" Unicode character block.
2172 * @since 1.7
2173 */
2174 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2175 new UnicodeBlock("DEVANAGARI_EXTENDED",
2176 "DEVANAGARI EXTENDED",
2177 "DEVANAGARIEXTENDED");
2178
2179 /**
2180 * Constant for the "Kayah Li" Unicode character block.
2181 * @since 1.7
2182 */
2183 public static final UnicodeBlock KAYAH_LI =
2184 new UnicodeBlock("KAYAH_LI",
2185 "KAYAH LI",
2186 "KAYAHLI");
2187
2188 /**
2189 * Constant for the "Rejang" Unicode character block.
2190 * @since 1.7
2191 */
2192 public static final UnicodeBlock REJANG =
2193 new UnicodeBlock("REJANG");
2194
2195 /**
2196 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2197 * @since 1.7
2198 */
2199 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2200 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2201 "HANGUL JAMO EXTENDED-A",
2202 "HANGULJAMOEXTENDED-A");
2203
2204 /**
2205 * Constant for the "Javanese" Unicode character block.
2206 * @since 1.7
2207 */
2208 public static final UnicodeBlock JAVANESE =
2209 new UnicodeBlock("JAVANESE");
2210
2211 /**
2212 * Constant for the "Cham" Unicode character block.
2213 * @since 1.7
2214 */
2215 public static final UnicodeBlock CHAM =
2216 new UnicodeBlock("CHAM");
2217
2218 /**
2219 * Constant for the "Myanmar Extended-A" Unicode character block.
2220 * @since 1.7
2221 */
2222 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2223 new UnicodeBlock("MYANMAR_EXTENDED_A",
2224 "MYANMAR EXTENDED-A",
2225 "MYANMAREXTENDED-A");
2226
2227 /**
2228 * Constant for the "Tai Viet" Unicode character block.
2229 * @since 1.7
2230 */
2231 public static final UnicodeBlock TAI_VIET =
2232 new UnicodeBlock("TAI_VIET",
2233 "TAI VIET",
2234 "TAIVIET");
2235
2236 /**
2237 * Constant for the "Ethiopic Extended-A" Unicode character block.
2238 * @since 1.7
2239 */
2240 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2241 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2242 "ETHIOPIC EXTENDED-A",
2243 "ETHIOPICEXTENDED-A");
2244
2245 /**
2246 * Constant for the "Meetei Mayek" Unicode character block.
2247 * @since 1.7
2248 */
2249 public static final UnicodeBlock MEETEI_MAYEK =
2250 new UnicodeBlock("MEETEI_MAYEK",
2251 "MEETEI MAYEK",
2252 "MEETEIMAYEK");
2253
2254 /**
2255 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2256 * @since 1.7
2257 */
2258 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2259 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2260 "HANGUL JAMO EXTENDED-B",
2261 "HANGULJAMOEXTENDED-B");
2262
2263 /**
2264 * Constant for the "Vertical Forms" Unicode character block.
2265 * @since 1.7
2266 */
2267 public static final UnicodeBlock VERTICAL_FORMS =
2268 new UnicodeBlock("VERTICAL_FORMS",
2269 "VERTICAL FORMS",
2270 "VERTICALFORMS");
2271
2272 /**
2273 * Constant for the "Ancient Greek Numbers" Unicode character block.
2274 * @since 1.7
2275 */
2276 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2277 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2278 "ANCIENT GREEK NUMBERS",
2279 "ANCIENTGREEKNUMBERS");
2280
2281 /**
2282 * Constant for the "Ancient Symbols" Unicode character block.
2283 * @since 1.7
2284 */
2285 public static final UnicodeBlock ANCIENT_SYMBOLS =
2286 new UnicodeBlock("ANCIENT_SYMBOLS",
2287 "ANCIENT SYMBOLS",
2288 "ANCIENTSYMBOLS");
2289
2290 /**
2291 * Constant for the "Phaistos Disc" Unicode character block.
2292 * @since 1.7
2293 */
2294 public static final UnicodeBlock PHAISTOS_DISC =
2295 new UnicodeBlock("PHAISTOS_DISC",
2296 "PHAISTOS DISC",
2297 "PHAISTOSDISC");
2298
2299 /**
2300 * Constant for the "Lycian" Unicode character block.
2301 * @since 1.7
2302 */
2303 public static final UnicodeBlock LYCIAN =
2304 new UnicodeBlock("LYCIAN");
2305
2306 /**
2307 * Constant for the "Carian" Unicode character block.
2308 * @since 1.7
2309 */
2310 public static final UnicodeBlock CARIAN =
2311 new UnicodeBlock("CARIAN");
2312
2313 /**
2314 * Constant for the "Old Persian" Unicode character block.
2315 * @since 1.7
2316 */
2317 public static final UnicodeBlock OLD_PERSIAN =
2318 new UnicodeBlock("OLD_PERSIAN",
2319 "OLD PERSIAN",
2320 "OLDPERSIAN");
2321
2322 /**
2323 * Constant for the "Imperial Aramaic" Unicode character block.
2324 * @since 1.7
2325 */
2326 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2327 new UnicodeBlock("IMPERIAL_ARAMAIC",
2328 "IMPERIAL ARAMAIC",
2329 "IMPERIALARAMAIC");
2330
2331 /**
2332 * Constant for the "Phoenician" Unicode character block.
2333 * @since 1.7
2334 */
2335 public static final UnicodeBlock PHOENICIAN =
2336 new UnicodeBlock("PHOENICIAN");
2337
2338 /**
2339 * Constant for the "Lydian" Unicode character block.
2340 * @since 1.7
2341 */
2342 public static final UnicodeBlock LYDIAN =
2343 new UnicodeBlock("LYDIAN");
2344
2345 /**
2346 * Constant for the "Kharoshthi" Unicode character block.
2347 * @since 1.7
2348 */
2349 public static final UnicodeBlock KHAROSHTHI =
2350 new UnicodeBlock("KHAROSHTHI");
2351
2352 /**
2353 * Constant for the "Old South Arabian" Unicode character block.
2354 * @since 1.7
2355 */
2356 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2357 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2358 "OLD SOUTH ARABIAN",
2359 "OLDSOUTHARABIAN");
2360
2361 /**
2362 * Constant for the "Avestan" Unicode character block.
2363 * @since 1.7
2364 */
2365 public static final UnicodeBlock AVESTAN =
2366 new UnicodeBlock("AVESTAN");
2367
2368 /**
2369 * Constant for the "Inscriptional Parthian" Unicode character block.
2370 * @since 1.7
2371 */
2372 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2373 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2374 "INSCRIPTIONAL PARTHIAN",
2375 "INSCRIPTIONALPARTHIAN");
2376
2377 /**
2378 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2379 * @since 1.7
2380 */
2381 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2382 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2383 "INSCRIPTIONAL PAHLAVI",
2384 "INSCRIPTIONALPAHLAVI");
2385
2386 /**
2387 * Constant for the "Old Turkic" Unicode character block.
2388 * @since 1.7
2389 */
2390 public static final UnicodeBlock OLD_TURKIC =
2391 new UnicodeBlock("OLD_TURKIC",
2392 "OLD TURKIC",
2393 "OLDTURKIC");
2394
2395 /**
2396 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2397 * @since 1.7
2398 */
2399 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2400 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2401 "RUMI NUMERAL SYMBOLS",
2402 "RUMINUMERALSYMBOLS");
2403
2404 /**
2405 * Constant for the "Brahmi" Unicode character block.
2406 * @since 1.7
2407 */
2408 public static final UnicodeBlock BRAHMI =
2409 new UnicodeBlock("BRAHMI");
2410
2411 /**
2412 * Constant for the "Kaithi" Unicode character block.
2413 * @since 1.7
2414 */
2415 public static final UnicodeBlock KAITHI =
2416 new UnicodeBlock("KAITHI");
2417
2418 /**
2419 * Constant for the "Cuneiform" Unicode character block.
2420 * @since 1.7
2421 */
2422 public static final UnicodeBlock CUNEIFORM =
2423 new UnicodeBlock("CUNEIFORM");
2424
2425 /**
2426 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2427 * character block.
2428 * @since 1.7
2429 */
2430 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2431 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2432 "CUNEIFORM NUMBERS AND PUNCTUATION",
2433 "CUNEIFORMNUMBERSANDPUNCTUATION");
2434
2435 /**
2436 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2437 * @since 1.7
2438 */
2439 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2440 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2441 "EGYPTIAN HIEROGLYPHS",
2442 "EGYPTIANHIEROGLYPHS");
2443
2444 /**
2445 * Constant for the "Bamum Supplement" Unicode character block.
2446 * @since 1.7
2447 */
2448 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2449 new UnicodeBlock("BAMUM_SUPPLEMENT",
2450 "BAMUM SUPPLEMENT",
2451 "BAMUMSUPPLEMENT");
2452
2453 /**
2454 * Constant for the "Kana Supplement" Unicode character block.
2455 * @since 1.7
2456 */
2457 public static final UnicodeBlock KANA_SUPPLEMENT =
2458 new UnicodeBlock("KANA_SUPPLEMENT",
2459 "KANA SUPPLEMENT",
2460 "KANASUPPLEMENT");
2461
2462 /**
2463 * Constant for the "Ancient Greek Musical Notation" Unicode character
2464 * block.
2465 * @since 1.7
2466 */
2467 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2468 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2469 "ANCIENT GREEK MUSICAL NOTATION",
2470 "ANCIENTGREEKMUSICALNOTATION");
2471
2472 /**
2473 * Constant for the "Counting Rod Numerals" Unicode character block.
2474 * @since 1.7
2475 */
2476 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2477 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2478 "COUNTING ROD NUMERALS",
2479 "COUNTINGRODNUMERALS");
2480
2481 /**
2482 * Constant for the "Mahjong Tiles" Unicode character block.
2483 * @since 1.7
2484 */
2485 public static final UnicodeBlock MAHJONG_TILES =
2486 new UnicodeBlock("MAHJONG_TILES",
2487 "MAHJONG TILES",
2488 "MAHJONGTILES");
2489
2490 /**
2491 * Constant for the "Domino Tiles" Unicode character block.
2492 * @since 1.7
2493 */
2494 public static final UnicodeBlock DOMINO_TILES =
2495 new UnicodeBlock("DOMINO_TILES",
2496 "DOMINO TILES",
2497 "DOMINOTILES");
2498
2499 /**
2500 * Constant for the "Playing Cards" Unicode character block.
2501 * @since 1.7
2502 */
2503 public static final UnicodeBlock PLAYING_CARDS =
2504 new UnicodeBlock("PLAYING_CARDS",
2505 "PLAYING CARDS",
2506 "PLAYINGCARDS");
2507
2508 /**
2509 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2510 * block.
2511 * @since 1.7
2512 */
2513 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2514 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2515 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2516 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2517
2518 /**
2519 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2520 * block.
2521 * @since 1.7
2522 */
2523 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2524 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2525 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2526 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2527
2528 /**
2529 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2530 * character block.
2531 * @since 1.7
2532 */
2533 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2534 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2535 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2536 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2537
2538 /**
2539 * Constant for the "Emoticons" Unicode character block.
2540 * @since 1.7
2541 */
2542 public static final UnicodeBlock EMOTICONS =
2543 new UnicodeBlock("EMOTICONS");
2544
2545 /**
2546 * Constant for the "Transport And Map Symbols" Unicode character block.
2547 * @since 1.7
2548 */
2549 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2550 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2551 "TRANSPORT AND MAP SYMBOLS",
2552 "TRANSPORTANDMAPSYMBOLS");
2553
2554 /**
2555 * Constant for the "Alchemical Symbols" Unicode character block.
2556 * @since 1.7
2557 */
2558 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2559 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2560 "ALCHEMICAL SYMBOLS",
2561 "ALCHEMICALSYMBOLS");
2562
2563 /**
2564 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2565 * character block.
2566 * @since 1.7
2567 */
2568 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2569 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2570 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2571 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2572
2573 /**
2574 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2575 * character block.
2576 * @since 1.7
2577 */
2578 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2579 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2580 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2581 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2582
2583 /**
2584 * Constant for the "Arabic Extended-A" Unicode character block.
2585 * @since 1.8
2586 */
2587 public static final UnicodeBlock ARABIC_EXTENDED_A =
2588 new UnicodeBlock("ARABIC_EXTENDED_A",
2589 "ARABIC EXTENDED-A",
2590 "ARABICEXTENDED-A");
2591
2592 /**
2593 * Constant for the "Sundanese Supplement" Unicode character block.
2594 * @since 1.8
2595 */
2596 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2597 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2598 "SUNDANESE SUPPLEMENT",
2599 "SUNDANESESUPPLEMENT");
2600
2601 /**
2602 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2603 * @since 1.8
2604 */
2605 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2606 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2607 "MEETEI MAYEK EXTENSIONS",
2608 "MEETEIMAYEKEXTENSIONS");
2609
2610 /**
2611 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2612 * @since 1.8
2613 */
2614 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2615 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2616 "MEROITIC HIEROGLYPHS",
2617 "MEROITICHIEROGLYPHS");
2618
2619 /**
2620 * Constant for the "Meroitic Cursive" Unicode character block.
2621 * @since 1.8
2622 */
2623 public static final UnicodeBlock MEROITIC_CURSIVE =
2624 new UnicodeBlock("MEROITIC_CURSIVE",
2625 "MEROITIC CURSIVE",
2626 "MEROITICCURSIVE");
2627
2628 /**
2629 * Constant for the "Sora Sompeng" Unicode character block.
2630 * @since 1.8
2631 */
2632 public static final UnicodeBlock SORA_SOMPENG =
2633 new UnicodeBlock("SORA_SOMPENG",
2634 "SORA SOMPENG",
2635 "SORASOMPENG");
2636
2637 /**
2638 * Constant for the "Chakma" Unicode character block.
2639 * @since 1.8
2640 */
2641 public static final UnicodeBlock CHAKMA =
2642 new UnicodeBlock("CHAKMA");
2643
2644 /**
2645 * Constant for the "Sharada" Unicode character block.
2646 * @since 1.8
2647 */
2648 public static final UnicodeBlock SHARADA =
2649 new UnicodeBlock("SHARADA");
2650
2651 /**
2652 * Constant for the "Takri" Unicode character block.
2653 * @since 1.8
2654 */
2655 public static final UnicodeBlock TAKRI =
2656 new UnicodeBlock("TAKRI");
2657
2658 /**
2659 * Constant for the "Miao" Unicode character block.
2660 * @since 1.8
2661 */
2662 public static final UnicodeBlock MIAO =
2663 new UnicodeBlock("MIAO");
2664
2665 /**
2666 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2667 * character block.
2668 * @since 1.8
2669 */
2670 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2671 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2672 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2673 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2674
2675 /**
2676 * Constant for the "Combining Diacritical Marks Extended" Unicode
2677 * character block.
2678 * @since 9
2679 */
2680 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2681 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2682 "COMBINING DIACRITICAL MARKS EXTENDED",
2683 "COMBININGDIACRITICALMARKSEXTENDED");
2684
2685 /**
2686 * Constant for the "Myanmar Extended-B" Unicode character block.
2687 * @since 9
2688 */
2689 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2690 new UnicodeBlock("MYANMAR_EXTENDED_B",
2691 "MYANMAR EXTENDED-B",
2692 "MYANMAREXTENDED-B");
2693
2694 /**
2695 * Constant for the "Latin Extended-E" Unicode character block.
2696 * @since 9
2697 */
2698 public static final UnicodeBlock LATIN_EXTENDED_E =
2699 new UnicodeBlock("LATIN_EXTENDED_E",
2700 "LATIN EXTENDED-E",
2701 "LATINEXTENDED-E");
2702
2703 /**
2704 * Constant for the "Coptic Epact Numbers" Unicode character block.
2705 * @since 9
2706 */
2707 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2708 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2709 "COPTIC EPACT NUMBERS",
2710 "COPTICEPACTNUMBERS");
2711
2712 /**
2713 * Constant for the "Old Permic" Unicode character block.
2714 * @since 9
2715 */
2716 public static final UnicodeBlock OLD_PERMIC =
2717 new UnicodeBlock("OLD_PERMIC",
2718 "OLD PERMIC",
2719 "OLDPERMIC");
2720
2721 /**
2722 * Constant for the "Elbasan" Unicode character block.
2723 * @since 9
2724 */
2725 public static final UnicodeBlock ELBASAN =
2726 new UnicodeBlock("ELBASAN");
2727
2728 /**
2729 * Constant for the "Caucasian Albanian" Unicode character block.
2730 * @since 9
2731 */
2732 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2733 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2734 "CAUCASIAN ALBANIAN",
2735 "CAUCASIANALBANIAN");
2736
2737 /**
2738 * Constant for the "Linear A" Unicode character block.
2739 * @since 9
2740 */
2741 public static final UnicodeBlock LINEAR_A =
2742 new UnicodeBlock("LINEAR_A",
2743 "LINEAR A",
2744 "LINEARA");
2745
2746 /**
2747 * Constant for the "Palmyrene" Unicode character block.
2748 * @since 9
2749 */
2750 public static final UnicodeBlock PALMYRENE =
2751 new UnicodeBlock("PALMYRENE");
2752
2753 /**
2754 * Constant for the "Nabataean" Unicode character block.
2755 * @since 9
2756 */
2757 public static final UnicodeBlock NABATAEAN =
2758 new UnicodeBlock("NABATAEAN");
2759
2760 /**
2761 * Constant for the "Old North Arabian" Unicode character block.
2762 * @since 9
2763 */
2764 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2765 new UnicodeBlock("OLD_NORTH_ARABIAN",
2766 "OLD NORTH ARABIAN",
2767 "OLDNORTHARABIAN");
2768
2769 /**
2770 * Constant for the "Manichaean" Unicode character block.
2771 * @since 9
2772 */
2773 public static final UnicodeBlock MANICHAEAN =
2774 new UnicodeBlock("MANICHAEAN");
2775
2776 /**
2777 * Constant for the "Psalter Pahlavi" Unicode character block.
2778 * @since 9
2779 */
2780 public static final UnicodeBlock PSALTER_PAHLAVI =
2781 new UnicodeBlock("PSALTER_PAHLAVI",
2782 "PSALTER PAHLAVI",
2783 "PSALTERPAHLAVI");
2784
2785 /**
2786 * Constant for the "Mahajani" Unicode character block.
2787 * @since 9
2788 */
2789 public static final UnicodeBlock MAHAJANI =
2790 new UnicodeBlock("MAHAJANI");
2791
2792 /**
2793 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2794 * @since 9
2795 */
2796 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2797 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2798 "SINHALA ARCHAIC NUMBERS",
2799 "SINHALAARCHAICNUMBERS");
2800
2801 /**
2802 * Constant for the "Khojki" Unicode character block.
2803 * @since 9
2804 */
2805 public static final UnicodeBlock KHOJKI =
2806 new UnicodeBlock("KHOJKI");
2807
2808 /**
2809 * Constant for the "Khudawadi" Unicode character block.
2810 * @since 9
2811 */
2812 public static final UnicodeBlock KHUDAWADI =
2813 new UnicodeBlock("KHUDAWADI");
2814
2815 /**
2816 * Constant for the "Grantha" Unicode character block.
2817 * @since 9
2818 */
2819 public static final UnicodeBlock GRANTHA =
2820 new UnicodeBlock("GRANTHA");
2821
2822 /**
2823 * Constant for the "Tirhuta" Unicode character block.
2824 * @since 9
2825 */
2826 public static final UnicodeBlock TIRHUTA =
2827 new UnicodeBlock("TIRHUTA");
2828
2829 /**
2830 * Constant for the "Siddham" Unicode character block.
2831 * @since 9
2832 */
2833 public static final UnicodeBlock SIDDHAM =
2834 new UnicodeBlock("SIDDHAM");
2835
2836 /**
2837 * Constant for the "Modi" Unicode character block.
2838 * @since 9
2839 */
2840 public static final UnicodeBlock MODI =
2841 new UnicodeBlock("MODI");
2842
2843 /**
2844 * Constant for the "Warang Citi" Unicode character block.
2845 * @since 9
2846 */
2847 public static final UnicodeBlock WARANG_CITI =
2848 new UnicodeBlock("WARANG_CITI",
2849 "WARANG CITI",
2850 "WARANGCITI");
2851
2852 /**
2853 * Constant for the "Pau Cin Hau" Unicode character block.
2854 * @since 9
2855 */
2856 public static final UnicodeBlock PAU_CIN_HAU =
2857 new UnicodeBlock("PAU_CIN_HAU",
2858 "PAU CIN HAU",
2859 "PAUCINHAU");
2860
2861 /**
2862 * Constant for the "Mro" Unicode character block.
2863 * @since 9
2864 */
2865 public static final UnicodeBlock MRO =
2866 new UnicodeBlock("MRO");
2867
2868 /**
2869 * Constant for the "Bassa Vah" Unicode character block.
2870 * @since 9
2871 */
2872 public static final UnicodeBlock BASSA_VAH =
2873 new UnicodeBlock("BASSA_VAH",
2874 "BASSA VAH",
2875 "BASSAVAH");
2876
2877 /**
2878 * Constant for the "Pahawh Hmong" Unicode character block.
2879 * @since 9
2880 */
2881 public static final UnicodeBlock PAHAWH_HMONG =
2882 new UnicodeBlock("PAHAWH_HMONG",
2883 "PAHAWH HMONG",
2884 "PAHAWHHMONG");
2885
2886 /**
2887 * Constant for the "Duployan" Unicode character block.
2888 * @since 9
2889 */
2890 public static final UnicodeBlock DUPLOYAN =
2891 new UnicodeBlock("DUPLOYAN");
2892
2893 /**
2894 * Constant for the "Shorthand Format Controls" Unicode character block.
2895 * @since 9
2896 */
2897 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2898 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2899 "SHORTHAND FORMAT CONTROLS",
2900 "SHORTHANDFORMATCONTROLS");
2901
2902 /**
2903 * Constant for the "Mende Kikakui" Unicode character block.
2904 * @since 9
2905 */
2906 public static final UnicodeBlock MENDE_KIKAKUI =
2907 new UnicodeBlock("MENDE_KIKAKUI",
2908 "MENDE KIKAKUI",
2909 "MENDEKIKAKUI");
2910
2911 /**
2912 * Constant for the "Ornamental Dingbats" Unicode character block.
2913 * @since 9
2914 */
2915 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2916 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2917 "ORNAMENTAL DINGBATS",
2918 "ORNAMENTALDINGBATS");
2919
2920 /**
2921 * Constant for the "Geometric Shapes Extended" Unicode character block.
2922 * @since 9
2923 */
2924 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2925 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2926 "GEOMETRIC SHAPES EXTENDED",
2927 "GEOMETRICSHAPESEXTENDED");
2928
2929 /**
2930 * Constant for the "Supplemental Arrows-C" Unicode character block.
2931 * @since 9
2932 */
2933 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2934 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2935 "SUPPLEMENTAL ARROWS-C",
2936 "SUPPLEMENTALARROWS-C");
2937
2938 /**
2939 * Constant for the "Cherokee Supplement" Unicode character block.
2940 * @since 9
2941 */
2942 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2943 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2944 "CHEROKEE SUPPLEMENT",
2945 "CHEROKEESUPPLEMENT");
2946
2947 /**
2948 * Constant for the "Hatran" Unicode character block.
2949 * @since 9
2950 */
2951 public static final UnicodeBlock HATRAN =
2952 new UnicodeBlock("HATRAN");
2953
2954 /**
2955 * Constant for the "Old Hungarian" Unicode character block.
2956 * @since 9
2957 */
2958 public static final UnicodeBlock OLD_HUNGARIAN =
2959 new UnicodeBlock("OLD_HUNGARIAN",
2960 "OLD HUNGARIAN",
2961 "OLDHUNGARIAN");
2962
2963 /**
2964 * Constant for the "Multani" Unicode character block.
2965 * @since 9
2966 */
2967 public static final UnicodeBlock MULTANI =
2968 new UnicodeBlock("MULTANI");
2969
2970 /**
2971 * Constant for the "Ahom" Unicode character block.
2972 * @since 9
2973 */
2974 public static final UnicodeBlock AHOM =
2975 new UnicodeBlock("AHOM");
2976
2977 /**
2978 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2979 * @since 9
2980 */
2981 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2982 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2983 "EARLY DYNASTIC CUNEIFORM",
2984 "EARLYDYNASTICCUNEIFORM");
2985
2986 /**
2987 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2988 * @since 9
2989 */
2990 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2991 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2992 "ANATOLIAN HIEROGLYPHS",
2993 "ANATOLIANHIEROGLYPHS");
2994
2995 /**
2996 * Constant for the "Sutton SignWriting" Unicode character block.
2997 * @since 9
2998 */
2999 public static final UnicodeBlock SUTTON_SIGNWRITING =
3000 new UnicodeBlock("SUTTON_SIGNWRITING",
3001 "SUTTON SIGNWRITING",
3002 "SUTTONSIGNWRITING");
3003
3004 /**
3005 * Constant for the "Supplemental Symbols and Pictographs" Unicode
3006 * character block.
3007 * @since 9
3008 */
3009 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
3010 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
3011 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
3012 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3013
3014 /**
3015 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3016 * character block.
3017 * @since 9
3018 */
3019 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3020 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3021 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3022 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3023
3024 /**
3025 * Constant for the "Syriac Supplement" Unicode
3026 * character block.
3027 * @since 11
3028 */
3029 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3030 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3031 "SYRIAC SUPPLEMENT",
3032 "SYRIACSUPPLEMENT");
3033
3034 /**
3035 * Constant for the "Cyrillic Extended-C" Unicode
3036 * character block.
3037 * @since 11
3038 */
3039 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3040 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3041 "CYRILLIC EXTENDED-C",
3042 "CYRILLICEXTENDED-C");
3043
3044 /**
3045 * Constant for the "Osage" Unicode
3046 * character block.
3047 * @since 11
3048 */
3049 public static final UnicodeBlock OSAGE =
3050 new UnicodeBlock("OSAGE");
3051
3052 /**
3053 * Constant for the "Newa" Unicode
3054 * character block.
3055 * @since 11
3056 */
3057 public static final UnicodeBlock NEWA =
3058 new UnicodeBlock("NEWA");
3059
3060 /**
3061 * Constant for the "Mongolian Supplement" Unicode
3062 * character block.
3063 * @since 11
3064 */
3065 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3066 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3067 "MONGOLIAN SUPPLEMENT",
3068 "MONGOLIANSUPPLEMENT");
3069
3070 /**
3071 * Constant for the "Marchen" Unicode
3072 * character block.
3073 * @since 11
3074 */
3075 public static final UnicodeBlock MARCHEN =
3076 new UnicodeBlock("MARCHEN");
3077
3078 /**
3079 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3080 * character block.
3081 * @since 11
3082 */
3083 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3084 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3085 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3086 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3087
3088 /**
3089 * Constant for the "Tangut" Unicode
3090 * character block.
3091 * @since 11
3092 */
3093 public static final UnicodeBlock TANGUT =
3094 new UnicodeBlock("TANGUT");
3095
3096 /**
3097 * Constant for the "Tangut Components" Unicode
3098 * character block.
3099 * @since 11
3100 */
3101 public static final UnicodeBlock TANGUT_COMPONENTS =
3102 new UnicodeBlock("TANGUT_COMPONENTS",
3103 "TANGUT COMPONENTS",
3104 "TANGUTCOMPONENTS");
3105
3106 /**
3107 * Constant for the "Kana Extended-A" Unicode
3108 * character block.
3109 * @since 11
3110 */
3111 public static final UnicodeBlock KANA_EXTENDED_A =
3112 new UnicodeBlock("KANA_EXTENDED_A",
3113 "KANA EXTENDED-A",
3114 "KANAEXTENDED-A");
3115 /**
3116 * Constant for the "Glagolitic Supplement" Unicode
3117 * character block.
3118 * @since 11
3119 */
3120 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3121 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3122 "GLAGOLITIC SUPPLEMENT",
3123 "GLAGOLITICSUPPLEMENT");
3124 /**
3125 * Constant for the "Adlam" Unicode
3126 * character block.
3127 * @since 11
3128 */
3129 public static final UnicodeBlock ADLAM =
3130 new UnicodeBlock("ADLAM");
3131
3132 /**
3133 * Constant for the "Masaram Gondi" Unicode
3134 * character block.
3135 * @since 11
3136 */
3137 public static final UnicodeBlock MASARAM_GONDI =
3138 new UnicodeBlock("MASARAM_GONDI",
3139 "MASARAM GONDI",
3140 "MASARAMGONDI");
3141
3142 /**
3143 * Constant for the "Zanabazar Square" Unicode
3144 * character block.
3145 * @since 11
3146 */
3147 public static final UnicodeBlock ZANABAZAR_SQUARE =
3148 new UnicodeBlock("ZANABAZAR_SQUARE",
3149 "ZANABAZAR SQUARE",
3150 "ZANABAZARSQUARE");
3151
3152 /**
3153 * Constant for the "Nushu" Unicode
3154 * character block.
3155 * @since 11
3156 */
3157 public static final UnicodeBlock NUSHU =
3158 new UnicodeBlock("NUSHU");
3159
3160 /**
3161 * Constant for the "Soyombo" Unicode
3162 * character block.
3163 * @since 11
3164 */
3165 public static final UnicodeBlock SOYOMBO =
3166 new UnicodeBlock("SOYOMBO");
3167
3168 /**
3169 * Constant for the "Bhaiksuki" Unicode
3170 * character block.
3171 * @since 11
3172 */
3173 public static final UnicodeBlock BHAIKSUKI =
3174 new UnicodeBlock("BHAIKSUKI");
3175
3176 /**
3177 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3178 * character block.
3179 * @since 11
3180 */
3181 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3182 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3183 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3184 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3185 /**
3186 * Constant for the "Georgian Extended" Unicode
3187 * character block.
3188 * @since 12
3189 */
3190 public static final UnicodeBlock GEORGIAN_EXTENDED =
3191 new UnicodeBlock("GEORGIAN_EXTENDED",
3192 "GEORGIAN EXTENDED",
3193 "GEORGIANEXTENDED");
3194
3195 /**
3196 * Constant for the "Hanifi Rohingya" Unicode
3197 * character block.
3198 * @since 12
3199 */
3200 public static final UnicodeBlock HANIFI_ROHINGYA =
3201 new UnicodeBlock("HANIFI_ROHINGYA",
3202 "HANIFI ROHINGYA",
3203 "HANIFIROHINGYA");
3204
3205 /**
3206 * Constant for the "Old Sogdian" Unicode
3207 * character block.
3208 * @since 12
3209 */
3210 public static final UnicodeBlock OLD_SOGDIAN =
3211 new UnicodeBlock("OLD_SOGDIAN",
3212 "OLD SOGDIAN",
3213 "OLDSOGDIAN");
3214
3215 /**
3216 * Constant for the "Sogdian" Unicode
3217 * character block.
3218 * @since 12
3219 */
3220 public static final UnicodeBlock SOGDIAN =
3221 new UnicodeBlock("SOGDIAN");
3222
3223 /**
3224 * Constant for the "Dogra" Unicode
3225 * character block.
3226 * @since 12
3227 */
3228 public static final UnicodeBlock DOGRA =
3229 new UnicodeBlock("DOGRA");
3230
3231 /**
3232 * Constant for the "Gunjala Gondi" Unicode
3233 * character block.
3234 * @since 12
3235 */
3236 public static final UnicodeBlock GUNJALA_GONDI =
3237 new UnicodeBlock("GUNJALA_GONDI",
3238 "GUNJALA GONDI",
3239 "GUNJALAGONDI");
3240
3241 /**
3242 * Constant for the "Makasar" Unicode
3243 * character block.
3244 * @since 12
3245 */
3246 public static final UnicodeBlock MAKASAR =
3247 new UnicodeBlock("MAKASAR");
3248
3249 /**
3250 * Constant for the "Medefaidrin" Unicode
3251 * character block.
3252 * @since 12
3253 */
3254 public static final UnicodeBlock MEDEFAIDRIN =
3255 new UnicodeBlock("MEDEFAIDRIN");
3256
3257 /**
3258 * Constant for the "Mayan Numerals" Unicode
3259 * character block.
3260 * @since 12
3261 */
3262 public static final UnicodeBlock MAYAN_NUMERALS =
3263 new UnicodeBlock("MAYAN_NUMERALS",
3264 "MAYAN NUMERALS",
3265 "MAYANNUMERALS");
3266
3267 /**
3268 * Constant for the "Indic Siyaq Numbers" Unicode
3269 * character block.
3270 * @since 12
3271 */
3272 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3273 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3274 "INDIC SIYAQ NUMBERS",
3275 "INDICSIYAQNUMBERS");
3276
3277 /**
3278 * Constant for the "Chess Symbols" Unicode
3279 * character block.
3280 * @since 12
3281 */
3282 public static final UnicodeBlock CHESS_SYMBOLS =
3283 new UnicodeBlock("CHESS_SYMBOLS",
3284 "CHESS SYMBOLS",
3285 "CHESSSYMBOLS");
3286
3287 /**
3288 * Constant for the "Elymaic" Unicode
3289 * character block.
3290 * @since 13
3291 */
3292 public static final UnicodeBlock ELYMAIC =
3293 new UnicodeBlock("ELYMAIC");
3294
3295 /**
3296 * Constant for the "Nandinagari" Unicode
3297 * character block.
3298 * @since 13
3299 */
3300 public static final UnicodeBlock NANDINAGARI =
3301 new UnicodeBlock("NANDINAGARI");
3302
3303 /**
3304 * Constant for the "Tamil Supplement" Unicode
3305 * character block.
3306 * @since 13
3307 */
3308 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3309 new UnicodeBlock("TAMIL_SUPPLEMENT",
3310 "TAMIL SUPPLEMENT",
3311 "TAMILSUPPLEMENT");
3312
3313 /**
3314 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3315 * character block.
3316 * @since 13
3317 */
3318 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3319 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3320 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3321 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3322
3323 /**
3324 * Constant for the "Small Kana Extension" Unicode
3325 * character block.
3326 * @since 13
3327 */
3328 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3329 new UnicodeBlock("SMALL_KANA_EXTENSION",
3330 "SMALL KANA EXTENSION",
3331 "SMALLKANAEXTENSION");
3332
3333 /**
3334 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3335 * character block.
3336 * @since 13
3337 */
3338 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3339 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3340 "NYIAKENG PUACHUE HMONG",
3341 "NYIAKENGPUACHUEHMONG");
3342
3343 /**
3344 * Constant for the "Wancho" Unicode
3345 * character block.
3346 * @since 13
3347 */
3348 public static final UnicodeBlock WANCHO =
3349 new UnicodeBlock("WANCHO");
3350
3351 /**
3352 * Constant for the "Ottoman Siyaq Numbers" Unicode
3353 * character block.
3354 * @since 13
3355 */
3356 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3357 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3358 "OTTOMAN SIYAQ NUMBERS",
3359 "OTTOMANSIYAQNUMBERS");
3360
3361 /**
3362 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3363 * character block.
3364 * @since 13
3365 */
3366 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3367 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3368 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3369 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3370
3371 /**
3372 * Constant for the "Yezidi" Unicode
3373 * character block.
3374 * @since 15
3375 */
3376 public static final UnicodeBlock YEZIDI =
3377 new UnicodeBlock("YEZIDI");
3378
3379 /**
3380 * Constant for the "Chorasmian" Unicode
3381 * character block.
3382 * @since 15
3383 */
3384 public static final UnicodeBlock CHORASMIAN =
3385 new UnicodeBlock("CHORASMIAN");
3386
3387 /**
3388 * Constant for the "Dives Akuru" Unicode
3389 * character block.
3390 * @since 15
3391 */
3392 public static final UnicodeBlock DIVES_AKURU =
3393 new UnicodeBlock("DIVES_AKURU",
3394 "DIVES AKURU",
3395 "DIVESAKURU");
3396
3397 /**
3398 * Constant for the "Lisu Supplement" Unicode
3399 * character block.
3400 * @since 15
3401 */
3402 public static final UnicodeBlock LISU_SUPPLEMENT =
3403 new UnicodeBlock("LISU_SUPPLEMENT",
3404 "LISU SUPPLEMENT",
3405 "LISUSUPPLEMENT");
3406
3407 /**
3408 * Constant for the "Khitan Small Script" Unicode
3409 * character block.
3410 * @since 15
3411 */
3412 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3413 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3414 "KHITAN SMALL SCRIPT",
3415 "KHITANSMALLSCRIPT");
3416
3417 /**
3418 * Constant for the "Tangut Supplement" Unicode
3419 * character block.
3420 * @since 15
3421 */
3422 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3423 new UnicodeBlock("TANGUT_SUPPLEMENT",
3424 "TANGUT SUPPLEMENT",
3425 "TANGUTSUPPLEMENT");
3426
3427 /**
3428 * Constant for the "Symbols for Legacy Computing" Unicode
3429 * character block.
3430 * @since 15
3431 */
3432 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3433 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3434 "SYMBOLS FOR LEGACY COMPUTING",
3435 "SYMBOLSFORLEGACYCOMPUTING");
3436
3437 /**
3438 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3439 * character block.
3440 * @since 15
3441 */
3442 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3443 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3444 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3445 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3446
3447 /**
3448 * Constant for the "Arabic Extended-B" Unicode
3449 * character block.
3450 * @since 19
3451 */
3452 public static final UnicodeBlock ARABIC_EXTENDED_B =
3453 new UnicodeBlock("ARABIC_EXTENDED_B",
3454 "ARABIC EXTENDED-B",
3455 "ARABICEXTENDED-B");
3456
3457 /**
3458 * Constant for the "Vithkuqi" Unicode
3459 * character block.
3460 * @since 19
3461 */
3462 public static final UnicodeBlock VITHKUQI =
3463 new UnicodeBlock("VITHKUQI");
3464
3465 /**
3466 * Constant for the "Latin Extended-F" Unicode
3467 * character block.
3468 * @since 19
3469 */
3470 public static final UnicodeBlock LATIN_EXTENDED_F =
3471 new UnicodeBlock("LATIN_EXTENDED_F",
3472 "LATIN EXTENDED-F",
3473 "LATINEXTENDED-F");
3474
3475 /**
3476 * Constant for the "Old Uyghur" Unicode
3477 * character block.
3478 * @since 19
3479 */
3480 public static final UnicodeBlock OLD_UYGHUR =
3481 new UnicodeBlock("OLD_UYGHUR",
3482 "OLD UYGHUR",
3483 "OLDUYGHUR");
3484
3485 /**
3486 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3487 * character block.
3488 * @since 19
3489 */
3490 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3491 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3492 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3493 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3494
3495 /**
3496 * Constant for the "Cypro-Minoan" Unicode
3497 * character block.
3498 * @since 19
3499 */
3500 public static final UnicodeBlock CYPRO_MINOAN =
3501 new UnicodeBlock("CYPRO_MINOAN",
3502 "CYPRO-MINOAN",
3503 "CYPRO-MINOAN");
3504
3505 /**
3506 * Constant for the "Tangsa" Unicode
3507 * character block.
3508 * @since 19
3509 */
3510 public static final UnicodeBlock TANGSA =
3511 new UnicodeBlock("TANGSA");
3512
3513 /**
3514 * Constant for the "Kana Extended-B" Unicode
3515 * character block.
3516 * @since 19
3517 */
3518 public static final UnicodeBlock KANA_EXTENDED_B =
3519 new UnicodeBlock("KANA_EXTENDED_B",
3520 "KANA EXTENDED-B",
3521 "KANAEXTENDED-B");
3522
3523 /**
3524 * Constant for the "Znamenny Musical Notation" Unicode
3525 * character block.
3526 * @since 19
3527 */
3528 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3529 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3530 "ZNAMENNY MUSICAL NOTATION",
3531 "ZNAMENNYMUSICALNOTATION");
3532
3533 /**
3534 * Constant for the "Latin Extended-G" Unicode
3535 * character block.
3536 * @since 19
3537 */
3538 public static final UnicodeBlock LATIN_EXTENDED_G =
3539 new UnicodeBlock("LATIN_EXTENDED_G",
3540 "LATIN EXTENDED-G",
3541 "LATINEXTENDED-G");
3542
3543 /**
3544 * Constant for the "Toto" Unicode
3545 * character block.
3546 * @since 19
3547 */
3548 public static final UnicodeBlock TOTO =
3549 new UnicodeBlock("TOTO");
3550
3551 /**
3552 * Constant for the "Ethiopic Extended-B" Unicode
3553 * character block.
3554 * @since 19
3555 */
3556 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3557 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3558 "ETHIOPIC EXTENDED-B",
3559 "ETHIOPICEXTENDED-B");
3560
3561 /**
3562 * Constant for the "Arabic Extended-C" Unicode
3563 * character block.
3564 * @since 20
3565 */
3566 public static final UnicodeBlock ARABIC_EXTENDED_C =
3567 new UnicodeBlock("ARABIC_EXTENDED_C",
3568 "ARABIC EXTENDED-C",
3569 "ARABICEXTENDED-C");
3570
3571 /**
3572 * Constant for the "Devanagari Extended-A" Unicode
3573 * character block.
3574 * @since 20
3575 */
3576 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3577 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3578 "DEVANAGARI EXTENDED-A",
3579 "DEVANAGARIEXTENDED-A");
3580
3581 /**
3582 * Constant for the "Kawi" Unicode
3583 * character block.
3584 * @since 20
3585 */
3586 public static final UnicodeBlock KAWI =
3587 new UnicodeBlock("KAWI");
3588
3589 /**
3590 * Constant for the "Kaktovik Numerals" Unicode
3591 * character block.
3592 * @since 20
3593 */
3594 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3595 new UnicodeBlock("KAKTOVIK_NUMERALS",
3596 "KAKTOVIK NUMERALS",
3597 "KAKTOVIKNUMERALS");
3598
3599 /**
3600 * Constant for the "Cyrillic Extended-D" Unicode
3601 * character block.
3602 * @since 20
3603 */
3604 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3605 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3606 "CYRILLIC EXTENDED-D",
3607 "CYRILLICEXTENDED-D");
3608
3609 /**
3610 * Constant for the "Nag Mundari" Unicode
3611 * character block.
3612 * @since 20
3613 */
3614 public static final UnicodeBlock NAG_MUNDARI =
3615 new UnicodeBlock("NAG_MUNDARI",
3616 "NAG MUNDARI",
3617 "NAGMUNDARI");
3618
3619 /**
3620 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3621 * character block.
3622 * @since 20
3623 */
3624 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3625 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3626 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3627 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3628
3629 /**
3630 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3631 * character block.
3632 * @since 22
3633 */
3634 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3635 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3636 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3637 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3638
3639 /**
3640 * Constant for the "Todhri" Unicode
3641 * character block.
3642 * @since 24
3643 */
3644 public static final UnicodeBlock TODHRI =
3645 new UnicodeBlock("TODHRI");
3646
3647 /**
3648 * Constant for the "Garay" Unicode
3649 * character block.
3650 * @since 24
3651 */
3652 public static final UnicodeBlock GARAY =
3653 new UnicodeBlock("GARAY");
3654
3655 /**
3656 * Constant for the "Tulu-Tigalari" Unicode
3657 * character block.
3658 * @since 24
3659 */
3660 public static final UnicodeBlock TULU_TIGALARI =
3661 new UnicodeBlock("TULU_TIGALARI",
3662 "TULU-TIGALARI");
3663
3664 /**
3665 * Constant for the "Myanmar Extended-C" Unicode
3666 * character block.
3667 * @since 24
3668 */
3669 public static final UnicodeBlock MYANMAR_EXTENDED_C =
3670 new UnicodeBlock("MYANMAR_EXTENDED_C",
3671 "MYANMAR EXTENDED-C",
3672 "MYANMAREXTENDED-C");
3673
3674 /**
3675 * Constant for the "Sunuwar" Unicode
3676 * character block.
3677 * @since 24
3678 */
3679 public static final UnicodeBlock SUNUWAR =
3680 new UnicodeBlock("SUNUWAR");
3681
3682 /**
3683 * Constant for the "Egyptian Hieroglyphs Extended-A" Unicode
3684 * character block.
3685 * @since 24
3686 */
3687 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS_EXTENDED_A =
3688 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS_EXTENDED_A",
3689 "EGYPTIAN HIEROGLYPHS EXTENDED-A",
3690 "EGYPTIANHIEROGLYPHSEXTENDED-A");
3691
3692 /**
3693 * Constant for the "Gurung Khema" Unicode
3694 * character block.
3695 * @since 24
3696 */
3697 public static final UnicodeBlock GURUNG_KHEMA =
3698 new UnicodeBlock("GURUNG_KHEMA",
3699 "GURUNG KHEMA",
3700 "GURUNGKHEMA");
3701
3702 /**
3703 * Constant for the "Kirat Rai" Unicode
3704 * character block.
3705 * @since 24
3706 */
3707 public static final UnicodeBlock KIRAT_RAI =
3708 new UnicodeBlock("KIRAT_RAI",
3709 "KIRAT RAI",
3710 "KIRATRAI");
3711
3712 /**
3713 * Constant for the "Symbols for Legacy Computing Supplement" Unicode
3714 * character block.
3715 * @since 24
3716 */
3717 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT =
3718 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT",
3719 "SYMBOLS FOR LEGACY COMPUTING SUPPLEMENT",
3720 "SYMBOLSFORLEGACYCOMPUTINGSUPPLEMENT");
3721
3722 /**
3723 * Constant for the "Ol Onal" Unicode
3724 * character block.
3725 * @since 24
3726 */
3727 public static final UnicodeBlock OL_ONAL =
3728 new UnicodeBlock("OL_ONAL",
3729 "OL ONAL",
3730 "OLONAL");
3731
3732 /**
3733 * Constant for the "Sidetic" Unicode
3734 * character block.
3735 * @since 26
3736 */
3737 public static final UnicodeBlock SIDETIC =
3738 new UnicodeBlock("SIDETIC");
3739
3740 /**
3741 * Constant for the "Sharada Supplement" Unicode
3742 * character block.
3743 * @since 26
3744 */
3745 public static final UnicodeBlock SHARADA_SUPPLEMENT =
3746 new UnicodeBlock("SHARADA_SUPPLEMENT",
3747 "SHARADA SUPPLEMENT",
3748 "SHARADASUPPLEMENT");
3749
3750 /**
3751 * Constant for the "Tolong Siki" Unicode
3752 * character block.
3753 * @since 26
3754 */
3755 public static final UnicodeBlock TOLONG_SIKI =
3756 new UnicodeBlock("TOLONG_SIKI",
3757 "TOLONG SIKI",
3758 "TOLONGSIKI");
3759
3760 /**
3761 * Constant for the "Beria Erfe" Unicode
3762 * character block.
3763 * @since 26
3764 */
3765 public static final UnicodeBlock BERIA_ERFE =
3766 new UnicodeBlock("BERIA_ERFE",
3767 "BERIA ERFE",
3768 "BERIAERFE");
3769
3770 /**
3771 * Constant for the "Tangut Components Supplement" Unicode
3772 * character block.
3773 * @since 26
3774 */
3775 public static final UnicodeBlock TANGUT_COMPONENTS_SUPPLEMENT =
3776 new UnicodeBlock("TANGUT_COMPONENTS_SUPPLEMENT",
3777 "TANGUT COMPONENTS SUPPLEMENT",
3778 "TANGUTCOMPONENTSSUPPLEMENT");
3779
3780 /**
3781 * Constant for the "Miscellaneous Symbols Supplement" Unicode
3782 * character block.
3783 * @since 26
3784 */
3785 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_SUPPLEMENT =
3786 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_SUPPLEMENT",
3787 "MISCELLANEOUS SYMBOLS SUPPLEMENT",
3788 "MISCELLANEOUSSYMBOLSSUPPLEMENT");
3789
3790 /**
3791 * Constant for the "Tai Yo" Unicode
3792 * character block.
3793 * @since 26
3794 */
3795 public static final UnicodeBlock TAI_YO =
3796 new UnicodeBlock("TAI_YO",
3797 "TAI YO",
3798 "TAIYO");
3799
3800 /**
3801 * Constant for the "CJK Unified Ideographs Extension J" Unicode
3802 * character block.
3803 * @since 26
3804 */
3805 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J =
3806 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J",
3807 "CJK UNIFIED IDEOGRAPHS EXTENSION J",
3808 "CJKUNIFIEDIDEOGRAPHSEXTENSIONJ");
3809
3810
3811 private static final int[] blockStarts = {
3812 0x0000, // 0000..007F; Basic Latin
3813 0x0080, // 0080..00FF; Latin-1 Supplement
3814 0x0100, // 0100..017F; Latin Extended-A
3815 0x0180, // 0180..024F; Latin Extended-B
3816 0x0250, // 0250..02AF; IPA Extensions
3817 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3818 0x0300, // 0300..036F; Combining Diacritical Marks
3819 0x0370, // 0370..03FF; Greek and Coptic
3820 0x0400, // 0400..04FF; Cyrillic
3821 0x0500, // 0500..052F; Cyrillic Supplement
3822 0x0530, // 0530..058F; Armenian
3823 0x0590, // 0590..05FF; Hebrew
3824 0x0600, // 0600..06FF; Arabic
3825 0x0700, // 0700..074F; Syriac
3826 0x0750, // 0750..077F; Arabic Supplement
3827 0x0780, // 0780..07BF; Thaana
3828 0x07C0, // 07C0..07FF; NKo
3829 0x0800, // 0800..083F; Samaritan
3830 0x0840, // 0840..085F; Mandaic
3831 0x0860, // 0860..086F; Syriac Supplement
3832 0x0870, // 0870..089F; Arabic Extended-B
3833 0x08A0, // 08A0..08FF; Arabic Extended-A
3834 0x0900, // 0900..097F; Devanagari
3835 0x0980, // 0980..09FF; Bengali
3836 0x0A00, // 0A00..0A7F; Gurmukhi
3837 0x0A80, // 0A80..0AFF; Gujarati
3838 0x0B00, // 0B00..0B7F; Oriya
3839 0x0B80, // 0B80..0BFF; Tamil
3840 0x0C00, // 0C00..0C7F; Telugu
3841 0x0C80, // 0C80..0CFF; Kannada
3842 0x0D00, // 0D00..0D7F; Malayalam
3843 0x0D80, // 0D80..0DFF; Sinhala
3844 0x0E00, // 0E00..0E7F; Thai
3845 0x0E80, // 0E80..0EFF; Lao
3846 0x0F00, // 0F00..0FFF; Tibetan
3847 0x1000, // 1000..109F; Myanmar
3848 0x10A0, // 10A0..10FF; Georgian
3849 0x1100, // 1100..11FF; Hangul Jamo
3850 0x1200, // 1200..137F; Ethiopic
3851 0x1380, // 1380..139F; Ethiopic Supplement
3852 0x13A0, // 13A0..13FF; Cherokee
3853 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3854 0x1680, // 1680..169F; Ogham
3855 0x16A0, // 16A0..16FF; Runic
3856 0x1700, // 1700..171F; Tagalog
3857 0x1720, // 1720..173F; Hanunoo
3858 0x1740, // 1740..175F; Buhid
3859 0x1760, // 1760..177F; Tagbanwa
3860 0x1780, // 1780..17FF; Khmer
3861 0x1800, // 1800..18AF; Mongolian
3862 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3863 0x1900, // 1900..194F; Limbu
3864 0x1950, // 1950..197F; Tai Le
3865 0x1980, // 1980..19DF; New Tai Lue
3866 0x19E0, // 19E0..19FF; Khmer Symbols
3867 0x1A00, // 1A00..1A1F; Buginese
3868 0x1A20, // 1A20..1AAF; Tai Tham
3869 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3870 0x1B00, // 1B00..1B7F; Balinese
3871 0x1B80, // 1B80..1BBF; Sundanese
3872 0x1BC0, // 1BC0..1BFF; Batak
3873 0x1C00, // 1C00..1C4F; Lepcha
3874 0x1C50, // 1C50..1C7F; Ol Chiki
3875 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3876 0x1C90, // 1C90..1CBF; Georgian Extended
3877 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3878 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3879 0x1D00, // 1D00..1D7F; Phonetic Extensions
3880 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3881 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3882 0x1E00, // 1E00..1EFF; Latin Extended Additional
3883 0x1F00, // 1F00..1FFF; Greek Extended
3884 0x2000, // 2000..206F; General Punctuation
3885 0x2070, // 2070..209F; Superscripts and Subscripts
3886 0x20A0, // 20A0..20CF; Currency Symbols
3887 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3888 0x2100, // 2100..214F; Letterlike Symbols
3889 0x2150, // 2150..218F; Number Forms
3890 0x2190, // 2190..21FF; Arrows
3891 0x2200, // 2200..22FF; Mathematical Operators
3892 0x2300, // 2300..23FF; Miscellaneous Technical
3893 0x2400, // 2400..243F; Control Pictures
3894 0x2440, // 2440..245F; Optical Character Recognition
3895 0x2460, // 2460..24FF; Enclosed Alphanumerics
3896 0x2500, // 2500..257F; Box Drawing
3897 0x2580, // 2580..259F; Block Elements
3898 0x25A0, // 25A0..25FF; Geometric Shapes
3899 0x2600, // 2600..26FF; Miscellaneous Symbols
3900 0x2700, // 2700..27BF; Dingbats
3901 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3902 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3903 0x2800, // 2800..28FF; Braille Patterns
3904 0x2900, // 2900..297F; Supplemental Arrows-B
3905 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3906 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3907 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3908 0x2C00, // 2C00..2C5F; Glagolitic
3909 0x2C60, // 2C60..2C7F; Latin Extended-C
3910 0x2C80, // 2C80..2CFF; Coptic
3911 0x2D00, // 2D00..2D2F; Georgian Supplement
3912 0x2D30, // 2D30..2D7F; Tifinagh
3913 0x2D80, // 2D80..2DDF; Ethiopic Extended
3914 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3915 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3916 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3917 0x2F00, // 2F00..2FDF; Kangxi Radicals
3918 0x2FE0, // unassigned
3919 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3920 0x3000, // 3000..303F; CJK Symbols and Punctuation
3921 0x3040, // 3040..309F; Hiragana
3922 0x30A0, // 30A0..30FF; Katakana
3923 0x3100, // 3100..312F; Bopomofo
3924 0x3130, // 3130..318F; Hangul Compatibility Jamo
3925 0x3190, // 3190..319F; Kanbun
3926 0x31A0, // 31A0..31BF; Bopomofo Extended
3927 0x31C0, // 31C0..31EF; CJK Strokes
3928 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3929 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3930 0x3300, // 3300..33FF; CJK Compatibility
3931 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3932 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3933 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3934 0xA000, // A000..A48F; Yi Syllables
3935 0xA490, // A490..A4CF; Yi Radicals
3936 0xA4D0, // A4D0..A4FF; Lisu
3937 0xA500, // A500..A63F; Vai
3938 0xA640, // A640..A69F; Cyrillic Extended-B
3939 0xA6A0, // A6A0..A6FF; Bamum
3940 0xA700, // A700..A71F; Modifier Tone Letters
3941 0xA720, // A720..A7FF; Latin Extended-D
3942 0xA800, // A800..A82F; Syloti Nagri
3943 0xA830, // A830..A83F; Common Indic Number Forms
3944 0xA840, // A840..A87F; Phags-pa
3945 0xA880, // A880..A8DF; Saurashtra
3946 0xA8E0, // A8E0..A8FF; Devanagari Extended
3947 0xA900, // A900..A92F; Kayah Li
3948 0xA930, // A930..A95F; Rejang
3949 0xA960, // A960..A97F; Hangul Jamo Extended-A
3950 0xA980, // A980..A9DF; Javanese
3951 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3952 0xAA00, // AA00..AA5F; Cham
3953 0xAA60, // AA60..AA7F; Myanmar Extended-A
3954 0xAA80, // AA80..AADF; Tai Viet
3955 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3956 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3957 0xAB30, // AB30..AB6F; Latin Extended-E
3958 0xAB70, // AB70..ABBF; Cherokee Supplement
3959 0xABC0, // ABC0..ABFF; Meetei Mayek
3960 0xAC00, // AC00..D7AF; Hangul Syllables
3961 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3962 0xD800, // D800..DB7F; High Surrogates
3963 0xDB80, // DB80..DBFF; High Private Use Surrogates
3964 0xDC00, // DC00..DFFF; Low Surrogates
3965 0xE000, // E000..F8FF; Private Use Area
3966 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3967 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3968 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3969 0xFE00, // FE00..FE0F; Variation Selectors
3970 0xFE10, // FE10..FE1F; Vertical Forms
3971 0xFE20, // FE20..FE2F; Combining Half Marks
3972 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3973 0xFE50, // FE50..FE6F; Small Form Variants
3974 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3975 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3976 0xFFF0, // FFF0..FFFF; Specials
3977 0x10000, // 10000..1007F; Linear B Syllabary
3978 0x10080, // 10080..100FF; Linear B Ideograms
3979 0x10100, // 10100..1013F; Aegean Numbers
3980 0x10140, // 10140..1018F; Ancient Greek Numbers
3981 0x10190, // 10190..101CF; Ancient Symbols
3982 0x101D0, // 101D0..101FF; Phaistos Disc
3983 0x10200, // unassigned
3984 0x10280, // 10280..1029F; Lycian
3985 0x102A0, // 102A0..102DF; Carian
3986 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3987 0x10300, // 10300..1032F; Old Italic
3988 0x10330, // 10330..1034F; Gothic
3989 0x10350, // 10350..1037F; Old Permic
3990 0x10380, // 10380..1039F; Ugaritic
3991 0x103A0, // 103A0..103DF; Old Persian
3992 0x103E0, // unassigned
3993 0x10400, // 10400..1044F; Deseret
3994 0x10450, // 10450..1047F; Shavian
3995 0x10480, // 10480..104AF; Osmanya
3996 0x104B0, // 104B0..104FF; Osage
3997 0x10500, // 10500..1052F; Elbasan
3998 0x10530, // 10530..1056F; Caucasian Albanian
3999 0x10570, // 10570..105BF; Vithkuqi
4000 0x105C0, // 105C0..105FF; Todhri
4001 0x10600, // 10600..1077F; Linear A
4002 0x10780, // 10780..107BF; Latin Extended-F
4003 0x107C0, // unassigned
4004 0x10800, // 10800..1083F; Cypriot Syllabary
4005 0x10840, // 10840..1085F; Imperial Aramaic
4006 0x10860, // 10860..1087F; Palmyrene
4007 0x10880, // 10880..108AF; Nabataean
4008 0x108B0, // unassigned
4009 0x108E0, // 108E0..108FF; Hatran
4010 0x10900, // 10900..1091F; Phoenician
4011 0x10920, // 10920..1093F; Lydian
4012 0x10940, // 10940..1095F; Sidetic
4013 0x10960, // unassigned
4014 0x10980, // 10980..1099F; Meroitic Hieroglyphs
4015 0x109A0, // 109A0..109FF; Meroitic Cursive
4016 0x10A00, // 10A00..10A5F; Kharoshthi
4017 0x10A60, // 10A60..10A7F; Old South Arabian
4018 0x10A80, // 10A80..10A9F; Old North Arabian
4019 0x10AA0, // unassigned
4020 0x10AC0, // 10AC0..10AFF; Manichaean
4021 0x10B00, // 10B00..10B3F; Avestan
4022 0x10B40, // 10B40..10B5F; Inscriptional Parthian
4023 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
4024 0x10B80, // 10B80..10BAF; Psalter Pahlavi
4025 0x10BB0, // unassigned
4026 0x10C00, // 10C00..10C4F; Old Turkic
4027 0x10C50, // unassigned
4028 0x10C80, // 10C80..10CFF; Old Hungarian
4029 0x10D00, // 10D00..10D3F; Hanifi Rohingya
4030 0x10D40, // 10D40..10D8F; Garay
4031 0x10D90, // unassigned
4032 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
4033 0x10E80, // 10E80..10EBF; Yezidi
4034 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
4035 0x10F00, // 10F00..10F2F; Old Sogdian
4036 0x10F30, // 10F30..10F6F; Sogdian
4037 0x10F70, // 10F70..10FAF; Old Uyghur
4038 0x10FB0, // 10FB0..10FDF; Chorasmian
4039 0x10FE0, // 10FE0..10FFF; Elymaic
4040 0x11000, // 11000..1107F; Brahmi
4041 0x11080, // 11080..110CF; Kaithi
4042 0x110D0, // 110D0..110FF; Sora Sompeng
4043 0x11100, // 11100..1114F; Chakma
4044 0x11150, // 11150..1117F; Mahajani
4045 0x11180, // 11180..111DF; Sharada
4046 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
4047 0x11200, // 11200..1124F; Khojki
4048 0x11250, // unassigned
4049 0x11280, // 11280..112AF; Multani
4050 0x112B0, // 112B0..112FF; Khudawadi
4051 0x11300, // 11300..1137F; Grantha
4052 0x11380, // 11380..113FF; Tulu-Tigalari
4053 0x11400, // 11400..1147F; Newa
4054 0x11480, // 11480..114DF; Tirhuta
4055 0x114E0, // unassigned
4056 0x11580, // 11580..115FF; Siddham
4057 0x11600, // 11600..1165F; Modi
4058 0x11660, // 11660..1167F; Mongolian Supplement
4059 0x11680, // 11680..116CF; Takri
4060 0x116D0, // 116D0..116FF; Myanmar Extended-C
4061 0x11700, // 11700..1174F; Ahom
4062 0x11750, // unassigned
4063 0x11800, // 11800..1184F; Dogra
4064 0x11850, // unassigned
4065 0x118A0, // 118A0..118FF; Warang Citi
4066 0x11900, // 11900..1195F; Dives Akuru
4067 0x11960, // unassigned
4068 0x119A0, // 119A0..119FF; Nandinagari
4069 0x11A00, // 11A00..11A4F; Zanabazar Square
4070 0x11A50, // 11A50..11AAF; Soyombo
4071 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
4072 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
4073 0x11B00, // 11B00..11B5F; Devanagari Extended-A
4074 0x11B60, // 11B60..11B7F; Sharada Supplement
4075 0x11B80, // unassigned
4076 0x11BC0, // 11BC0..11BFF; Sunuwar
4077 0x11C00, // 11C00..11C6F; Bhaiksuki
4078 0x11C70, // 11C70..11CBF; Marchen
4079 0x11CC0, // unassigned
4080 0x11D00, // 11D00..11D5F; Masaram Gondi
4081 0x11D60, // 11D60..11DAF; Gunjala Gondi
4082 0x11DB0, // 11DB0..11DEF; Tolong Siki
4083 0x11DF0, // unassigned
4084 0x11EE0, // 11EE0..11EFF; Makasar
4085 0x11F00, // 11F00..11F5F; Kawi
4086 0x11F60, // unassigned
4087 0x11FB0, // 11FB0..11FBF; Lisu Supplement
4088 0x11FC0, // 11FC0..11FFF; Tamil Supplement
4089 0x12000, // 12000..123FF; Cuneiform
4090 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
4091 0x12480, // 12480..1254F; Early Dynastic Cuneiform
4092 0x12550, // unassigned
4093 0x12F90, // 12F90..12FFF; Cypro-Minoan
4094 0x13000, // 13000..1342F; Egyptian Hieroglyphs
4095 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
4096 0x13460, // 13460..143FF; Egyptian Hieroglyphs Extended-A
4097 0x14400, // 14400..1467F; Anatolian Hieroglyphs
4098 0x14680, // unassigned
4099 0x16100, // 16100..1613F; Gurung Khema
4100 0x16140, // unassigned
4101 0x16800, // 16800..16A3F; Bamum Supplement
4102 0x16A40, // 16A40..16A6F; Mro
4103 0x16A70, // 16A70..16ACF; Tangsa
4104 0x16AD0, // 16AD0..16AFF; Bassa Vah
4105 0x16B00, // 16B00..16B8F; Pahawh Hmong
4106 0x16B90, // unassigned
4107 0x16D40, // 16D40..16D7F; Kirat Rai
4108 0x16D80, // unassigned
4109 0x16E40, // 16E40..16E9F; Medefaidrin
4110 0x16EA0, // 16EA0..16EDF; Beria Erfe
4111 0x16EE0, // unassigned
4112 0x16F00, // 16F00..16F9F; Miao
4113 0x16FA0, // unassigned
4114 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
4115 0x17000, // 17000..187FF; Tangut
4116 0x18800, // 18800..18AFF; Tangut Components
4117 0x18B00, // 18B00..18CFF; Khitan Small Script
4118 0x18D00, // 18D00..18D7F; Tangut Supplement
4119 0x18D80, // 18D80..18DFF; Tangut Components Supplement
4120 0x18E00, // unassigned
4121 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
4122 0x1B000, // 1B000..1B0FF; Kana Supplement
4123 0x1B100, // 1B100..1B12F; Kana Extended-A
4124 0x1B130, // 1B130..1B16F; Small Kana Extension
4125 0x1B170, // 1B170..1B2FF; Nushu
4126 0x1B300, // unassigned
4127 0x1BC00, // 1BC00..1BC9F; Duployan
4128 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
4129 0x1BCB0, // unassigned
4130 0x1CC00, // 1CC00..1CEBF; Symbols for Legacy Computing Supplement
4131 0x1CEC0, // 1CEC0..1CEFF; Miscellaneous Symbols Supplement
4132 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
4133 0x1CFD0, // unassigned
4134 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
4135 0x1D100, // 1D100..1D1FF; Musical Symbols
4136 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
4137 0x1D250, // unassigned
4138 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
4139 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
4140 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
4141 0x1D360, // 1D360..1D37F; Counting Rod Numerals
4142 0x1D380, // unassigned
4143 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
4144 0x1D800, // 1D800..1DAAF; Sutton SignWriting
4145 0x1DAB0, // unassigned
4146 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
4147 0x1E000, // 1E000..1E02F; Glagolitic Supplement
4148 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
4149 0x1E090, // unassigned
4150 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
4151 0x1E150, // unassigned
4152 0x1E290, // 1E290..1E2BF; Toto
4153 0x1E2C0, // 1E2C0..1E2FF; Wancho
4154 0x1E300, // unassigned
4155 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
4156 0x1E500, // unassigned
4157 0x1E5D0, // 1E5D0..1E5FF; Ol Onal
4158 0x1E600, // unassigned
4159 0x1E6C0, // 1E6C0..1E6FF; Tai Yo
4160 0x1E700, // unassigned
4161 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
4162 0x1E800, // 1E800..1E8DF; Mende Kikakui
4163 0x1E8E0, // unassigned
4164 0x1E900, // 1E900..1E95F; Adlam
4165 0x1E960, // unassigned
4166 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
4167 0x1ECC0, // unassigned
4168 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
4169 0x1ED50, // unassigned
4170 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
4171 0x1EF00, // unassigned
4172 0x1F000, // 1F000..1F02F; Mahjong Tiles
4173 0x1F030, // 1F030..1F09F; Domino Tiles
4174 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
4175 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
4176 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
4177 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
4178 0x1F600, // 1F600..1F64F; Emoticons
4179 0x1F650, // 1F650..1F67F; Ornamental Dingbats
4180 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
4181 0x1F700, // 1F700..1F77F; Alchemical Symbols
4182 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
4183 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
4184 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
4185 0x1FA00, // 1FA00..1FA6F; Chess Symbols
4186 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
4187 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
4188 0x1FC00, // unassigned
4189 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
4190 0x2A6E0, // unassigned
4191 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
4192 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
4193 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
4194 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
4195 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
4196 0x2EE60, // unassigned
4197 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
4198 0x2FA20, // unassigned
4199 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
4200 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4201 0x323B0, // 323B0..3347F; CJK Unified Ideographs Extension J
4202 0x33480, // unassigned
4203 0xE0000, // E0000..E007F; Tags
4204 0xE0080, // unassigned
4205 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4206 0xE01F0, // unassigned
4207 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4208 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4209 };
4210
4211 private static final UnicodeBlock[] blocks = {
4212 BASIC_LATIN,
4213 LATIN_1_SUPPLEMENT,
4214 LATIN_EXTENDED_A,
4215 LATIN_EXTENDED_B,
4216 IPA_EXTENSIONS,
4217 SPACING_MODIFIER_LETTERS,
4218 COMBINING_DIACRITICAL_MARKS,
4219 GREEK,
4220 CYRILLIC,
4221 CYRILLIC_SUPPLEMENTARY,
4222 ARMENIAN,
4223 HEBREW,
4224 ARABIC,
4225 SYRIAC,
4226 ARABIC_SUPPLEMENT,
4227 THAANA,
4228 NKO,
4229 SAMARITAN,
4230 MANDAIC,
4231 SYRIAC_SUPPLEMENT,
4232 ARABIC_EXTENDED_B,
4233 ARABIC_EXTENDED_A,
4234 DEVANAGARI,
4235 BENGALI,
4236 GURMUKHI,
4237 GUJARATI,
4238 ORIYA,
4239 TAMIL,
4240 TELUGU,
4241 KANNADA,
4242 MALAYALAM,
4243 SINHALA,
4244 THAI,
4245 LAO,
4246 TIBETAN,
4247 MYANMAR,
4248 GEORGIAN,
4249 HANGUL_JAMO,
4250 ETHIOPIC,
4251 ETHIOPIC_SUPPLEMENT,
4252 CHEROKEE,
4253 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4254 OGHAM,
4255 RUNIC,
4256 TAGALOG,
4257 HANUNOO,
4258 BUHID,
4259 TAGBANWA,
4260 KHMER,
4261 MONGOLIAN,
4262 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4263 LIMBU,
4264 TAI_LE,
4265 NEW_TAI_LUE,
4266 KHMER_SYMBOLS,
4267 BUGINESE,
4268 TAI_THAM,
4269 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4270 BALINESE,
4271 SUNDANESE,
4272 BATAK,
4273 LEPCHA,
4274 OL_CHIKI,
4275 CYRILLIC_EXTENDED_C,
4276 GEORGIAN_EXTENDED,
4277 SUNDANESE_SUPPLEMENT,
4278 VEDIC_EXTENSIONS,
4279 PHONETIC_EXTENSIONS,
4280 PHONETIC_EXTENSIONS_SUPPLEMENT,
4281 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4282 LATIN_EXTENDED_ADDITIONAL,
4283 GREEK_EXTENDED,
4284 GENERAL_PUNCTUATION,
4285 SUPERSCRIPTS_AND_SUBSCRIPTS,
4286 CURRENCY_SYMBOLS,
4287 COMBINING_MARKS_FOR_SYMBOLS,
4288 LETTERLIKE_SYMBOLS,
4289 NUMBER_FORMS,
4290 ARROWS,
4291 MATHEMATICAL_OPERATORS,
4292 MISCELLANEOUS_TECHNICAL,
4293 CONTROL_PICTURES,
4294 OPTICAL_CHARACTER_RECOGNITION,
4295 ENCLOSED_ALPHANUMERICS,
4296 BOX_DRAWING,
4297 BLOCK_ELEMENTS,
4298 GEOMETRIC_SHAPES,
4299 MISCELLANEOUS_SYMBOLS,
4300 DINGBATS,
4301 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4302 SUPPLEMENTAL_ARROWS_A,
4303 BRAILLE_PATTERNS,
4304 SUPPLEMENTAL_ARROWS_B,
4305 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4306 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4307 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4308 GLAGOLITIC,
4309 LATIN_EXTENDED_C,
4310 COPTIC,
4311 GEORGIAN_SUPPLEMENT,
4312 TIFINAGH,
4313 ETHIOPIC_EXTENDED,
4314 CYRILLIC_EXTENDED_A,
4315 SUPPLEMENTAL_PUNCTUATION,
4316 CJK_RADICALS_SUPPLEMENT,
4317 KANGXI_RADICALS,
4318 null,
4319 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4320 CJK_SYMBOLS_AND_PUNCTUATION,
4321 HIRAGANA,
4322 KATAKANA,
4323 BOPOMOFO,
4324 HANGUL_COMPATIBILITY_JAMO,
4325 KANBUN,
4326 BOPOMOFO_EXTENDED,
4327 CJK_STROKES,
4328 KATAKANA_PHONETIC_EXTENSIONS,
4329 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4330 CJK_COMPATIBILITY,
4331 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4332 YIJING_HEXAGRAM_SYMBOLS,
4333 CJK_UNIFIED_IDEOGRAPHS,
4334 YI_SYLLABLES,
4335 YI_RADICALS,
4336 LISU,
4337 VAI,
4338 CYRILLIC_EXTENDED_B,
4339 BAMUM,
4340 MODIFIER_TONE_LETTERS,
4341 LATIN_EXTENDED_D,
4342 SYLOTI_NAGRI,
4343 COMMON_INDIC_NUMBER_FORMS,
4344 PHAGS_PA,
4345 SAURASHTRA,
4346 DEVANAGARI_EXTENDED,
4347 KAYAH_LI,
4348 REJANG,
4349 HANGUL_JAMO_EXTENDED_A,
4350 JAVANESE,
4351 MYANMAR_EXTENDED_B,
4352 CHAM,
4353 MYANMAR_EXTENDED_A,
4354 TAI_VIET,
4355 MEETEI_MAYEK_EXTENSIONS,
4356 ETHIOPIC_EXTENDED_A,
4357 LATIN_EXTENDED_E,
4358 CHEROKEE_SUPPLEMENT,
4359 MEETEI_MAYEK,
4360 HANGUL_SYLLABLES,
4361 HANGUL_JAMO_EXTENDED_B,
4362 HIGH_SURROGATES,
4363 HIGH_PRIVATE_USE_SURROGATES,
4364 LOW_SURROGATES,
4365 PRIVATE_USE_AREA,
4366 CJK_COMPATIBILITY_IDEOGRAPHS,
4367 ALPHABETIC_PRESENTATION_FORMS,
4368 ARABIC_PRESENTATION_FORMS_A,
4369 VARIATION_SELECTORS,
4370 VERTICAL_FORMS,
4371 COMBINING_HALF_MARKS,
4372 CJK_COMPATIBILITY_FORMS,
4373 SMALL_FORM_VARIANTS,
4374 ARABIC_PRESENTATION_FORMS_B,
4375 HALFWIDTH_AND_FULLWIDTH_FORMS,
4376 SPECIALS,
4377 LINEAR_B_SYLLABARY,
4378 LINEAR_B_IDEOGRAMS,
4379 AEGEAN_NUMBERS,
4380 ANCIENT_GREEK_NUMBERS,
4381 ANCIENT_SYMBOLS,
4382 PHAISTOS_DISC,
4383 null,
4384 LYCIAN,
4385 CARIAN,
4386 COPTIC_EPACT_NUMBERS,
4387 OLD_ITALIC,
4388 GOTHIC,
4389 OLD_PERMIC,
4390 UGARITIC,
4391 OLD_PERSIAN,
4392 null,
4393 DESERET,
4394 SHAVIAN,
4395 OSMANYA,
4396 OSAGE,
4397 ELBASAN,
4398 CAUCASIAN_ALBANIAN,
4399 VITHKUQI,
4400 TODHRI,
4401 LINEAR_A,
4402 LATIN_EXTENDED_F,
4403 null,
4404 CYPRIOT_SYLLABARY,
4405 IMPERIAL_ARAMAIC,
4406 PALMYRENE,
4407 NABATAEAN,
4408 null,
4409 HATRAN,
4410 PHOENICIAN,
4411 LYDIAN,
4412 SIDETIC,
4413 null,
4414 MEROITIC_HIEROGLYPHS,
4415 MEROITIC_CURSIVE,
4416 KHAROSHTHI,
4417 OLD_SOUTH_ARABIAN,
4418 OLD_NORTH_ARABIAN,
4419 null,
4420 MANICHAEAN,
4421 AVESTAN,
4422 INSCRIPTIONAL_PARTHIAN,
4423 INSCRIPTIONAL_PAHLAVI,
4424 PSALTER_PAHLAVI,
4425 null,
4426 OLD_TURKIC,
4427 null,
4428 OLD_HUNGARIAN,
4429 HANIFI_ROHINGYA,
4430 GARAY,
4431 null,
4432 RUMI_NUMERAL_SYMBOLS,
4433 YEZIDI,
4434 ARABIC_EXTENDED_C,
4435 OLD_SOGDIAN,
4436 SOGDIAN,
4437 OLD_UYGHUR,
4438 CHORASMIAN,
4439 ELYMAIC,
4440 BRAHMI,
4441 KAITHI,
4442 SORA_SOMPENG,
4443 CHAKMA,
4444 MAHAJANI,
4445 SHARADA,
4446 SINHALA_ARCHAIC_NUMBERS,
4447 KHOJKI,
4448 null,
4449 MULTANI,
4450 KHUDAWADI,
4451 GRANTHA,
4452 TULU_TIGALARI,
4453 NEWA,
4454 TIRHUTA,
4455 null,
4456 SIDDHAM,
4457 MODI,
4458 MONGOLIAN_SUPPLEMENT,
4459 TAKRI,
4460 MYANMAR_EXTENDED_C,
4461 AHOM,
4462 null,
4463 DOGRA,
4464 null,
4465 WARANG_CITI,
4466 DIVES_AKURU,
4467 null,
4468 NANDINAGARI,
4469 ZANABAZAR_SQUARE,
4470 SOYOMBO,
4471 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4472 PAU_CIN_HAU,
4473 DEVANAGARI_EXTENDED_A,
4474 SHARADA_SUPPLEMENT,
4475 null,
4476 SUNUWAR,
4477 BHAIKSUKI,
4478 MARCHEN,
4479 null,
4480 MASARAM_GONDI,
4481 GUNJALA_GONDI,
4482 TOLONG_SIKI,
4483 null,
4484 MAKASAR,
4485 KAWI,
4486 null,
4487 LISU_SUPPLEMENT,
4488 TAMIL_SUPPLEMENT,
4489 CUNEIFORM,
4490 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4491 EARLY_DYNASTIC_CUNEIFORM,
4492 null,
4493 CYPRO_MINOAN,
4494 EGYPTIAN_HIEROGLYPHS,
4495 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4496 EGYPTIAN_HIEROGLYPHS_EXTENDED_A,
4497 ANATOLIAN_HIEROGLYPHS,
4498 null,
4499 GURUNG_KHEMA,
4500 null,
4501 BAMUM_SUPPLEMENT,
4502 MRO,
4503 TANGSA,
4504 BASSA_VAH,
4505 PAHAWH_HMONG,
4506 null,
4507 KIRAT_RAI,
4508 null,
4509 MEDEFAIDRIN,
4510 BERIA_ERFE,
4511 null,
4512 MIAO,
4513 null,
4514 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4515 TANGUT,
4516 TANGUT_COMPONENTS,
4517 KHITAN_SMALL_SCRIPT,
4518 TANGUT_SUPPLEMENT,
4519 TANGUT_COMPONENTS_SUPPLEMENT,
4520 null,
4521 KANA_EXTENDED_B,
4522 KANA_SUPPLEMENT,
4523 KANA_EXTENDED_A,
4524 SMALL_KANA_EXTENSION,
4525 NUSHU,
4526 null,
4527 DUPLOYAN,
4528 SHORTHAND_FORMAT_CONTROLS,
4529 null,
4530 SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT,
4531 MISCELLANEOUS_SYMBOLS_SUPPLEMENT,
4532 ZNAMENNY_MUSICAL_NOTATION,
4533 null,
4534 BYZANTINE_MUSICAL_SYMBOLS,
4535 MUSICAL_SYMBOLS,
4536 ANCIENT_GREEK_MUSICAL_NOTATION,
4537 null,
4538 KAKTOVIK_NUMERALS,
4539 MAYAN_NUMERALS,
4540 TAI_XUAN_JING_SYMBOLS,
4541 COUNTING_ROD_NUMERALS,
4542 null,
4543 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4544 SUTTON_SIGNWRITING,
4545 null,
4546 LATIN_EXTENDED_G,
4547 GLAGOLITIC_SUPPLEMENT,
4548 CYRILLIC_EXTENDED_D,
4549 null,
4550 NYIAKENG_PUACHUE_HMONG,
4551 null,
4552 TOTO,
4553 WANCHO,
4554 null,
4555 NAG_MUNDARI,
4556 null,
4557 OL_ONAL,
4558 null,
4559 TAI_YO,
4560 null,
4561 ETHIOPIC_EXTENDED_B,
4562 MENDE_KIKAKUI,
4563 null,
4564 ADLAM,
4565 null,
4566 INDIC_SIYAQ_NUMBERS,
4567 null,
4568 OTTOMAN_SIYAQ_NUMBERS,
4569 null,
4570 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4571 null,
4572 MAHJONG_TILES,
4573 DOMINO_TILES,
4574 PLAYING_CARDS,
4575 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4576 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4577 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4578 EMOTICONS,
4579 ORNAMENTAL_DINGBATS,
4580 TRANSPORT_AND_MAP_SYMBOLS,
4581 ALCHEMICAL_SYMBOLS,
4582 GEOMETRIC_SHAPES_EXTENDED,
4583 SUPPLEMENTAL_ARROWS_C,
4584 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4585 CHESS_SYMBOLS,
4586 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4587 SYMBOLS_FOR_LEGACY_COMPUTING,
4588 null,
4589 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4590 null,
4591 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4592 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4593 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4594 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4595 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4596 null,
4597 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4598 null,
4599 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4600 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4601 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J,
4602 null,
4603 TAGS,
4604 null,
4605 VARIATION_SELECTORS_SUPPLEMENT,
4606 null,
4607 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4608 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4609 };
4610
4611
4612 /**
4613 * Returns the object representing the Unicode block containing the
4614 * given character, or {@code null} if the character is not a
4615 * member of a defined block.
4616 *
4617 * <p><b>Note:</b> This method cannot handle
4618 * <a href="Character.html#supplementary"> supplementary
4619 * characters</a>. To support all Unicode characters, including
4620 * supplementary characters, use the {@link #of(int)} method.
4621 *
4622 * @param c The character in question
4623 * @return The {@code UnicodeBlock} instance representing the
4624 * Unicode block of which this character is a member, or
4625 * {@code null} if the character is not a member of any
4626 * Unicode block
4627 */
4628 public static UnicodeBlock of(char c) {
4629 return of((int)c);
4630 }
4631
4632 /**
4633 * Returns the object representing the Unicode block
4634 * containing the given character (Unicode code point), or
4635 * {@code null} if the character is not a member of a
4636 * defined block.
4637 *
4638 * @param codePoint the character (Unicode code point) in question.
4639 * @return The {@code UnicodeBlock} instance representing the
4640 * Unicode block of which this character is a member, or
4641 * {@code null} if the character is not a member of any
4642 * Unicode block
4643 * @throws IllegalArgumentException if the specified
4644 * {@code codePoint} is an invalid Unicode code point.
4645 * @see Character#isValidCodePoint(int)
4646 * @since 1.5
4647 */
4648 public static UnicodeBlock of(int codePoint) {
4649 if (!isValidCodePoint(codePoint)) {
4650 throw new IllegalArgumentException(
4651 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4652 }
4653
4654 int top, bottom, current;
4655 bottom = 0;
4656 top = blockStarts.length;
4657 current = top/2;
4658
4659 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4660 while (top - bottom > 1) {
4661 if (codePoint >= blockStarts[current]) {
4662 bottom = current;
4663 } else {
4664 top = current;
4665 }
4666 current = (top + bottom) / 2;
4667 }
4668 return blocks[current];
4669 }
4670
4671 /**
4672 * Returns the UnicodeBlock with the given name. Block
4673 * names are determined by The Unicode Standard. The file
4674 * {@code Blocks.txt} defines blocks for a particular
4675 * version of the standard. The {@link Character} class specifies
4676 * the version of the standard that it supports.
4677 * <p>
4678 * This method accepts block names in the following forms:
4679 * <ol>
4680 * <li> Canonical block names as defined by the Unicode Standard.
4681 * For example, the standard defines a "Basic Latin" block. Therefore, this
4682 * method accepts "Basic Latin" as a valid block name. The documentation of
4683 * each UnicodeBlock provides the canonical name.
4684 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4685 * is a valid block name for the "Basic Latin" block.
4686 * <li>The text representation of each constant UnicodeBlock identifier.
4687 * For example, this method will return the {@link #BASIC_LATIN} block if
4688 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4689 * hyphens in the canonical name with underscores.
4690 * </ol>
4691 * Finally, character case is ignored for all of the valid block name forms.
4692 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4693 * The en_US locale's case mapping rules are used to provide case-insensitive
4694 * string comparisons for block name validation.
4695 * <p>
4696 * If the Unicode Standard changes block names, both the previous and
4697 * current names will be accepted.
4698 *
4699 * @param blockName A {@code UnicodeBlock} name.
4700 * @return The {@code UnicodeBlock} instance identified
4701 * by {@code blockName}
4702 * @throws IllegalArgumentException if {@code blockName} is an
4703 * invalid name
4704 * @throws NullPointerException if {@code blockName} is null
4705 * @since 1.5
4706 */
4707 public static final UnicodeBlock forName(String blockName) {
4708 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4709 if (block == null) {
4710 throw new IllegalArgumentException("Not a valid block name: "
4711 + blockName);
4712 }
4713 return block;
4714 }
4715 }
4716
4717
4718 /**
4719 * A family of character subsets representing the character scripts
4720 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4721 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4722 * character is assigned to a single Unicode script, either a specific
4723 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4724 * one of the following three special values,
4725 * {@link Character.UnicodeScript#INHERITED Inherited},
4726 * {@link Character.UnicodeScript#COMMON Common} or
4727 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4728 *
4729 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4730 * @since 1.7
4731 */
4732 public static enum UnicodeScript {
4733
4734 /**
4735 * Unicode script "Common".
4736 */
4737 COMMON,
4738
4739 /**
4740 * Unicode script "Latin".
4741 */
4742 LATIN,
4743
4744 /**
4745 * Unicode script "Greek".
4746 */
4747 GREEK,
4748
4749 /**
4750 * Unicode script "Cyrillic".
4751 */
4752 CYRILLIC,
4753
4754 /**
4755 * Unicode script "Armenian".
4756 */
4757 ARMENIAN,
4758
4759 /**
4760 * Unicode script "Hebrew".
4761 */
4762 HEBREW,
4763
4764 /**
4765 * Unicode script "Arabic".
4766 */
4767 ARABIC,
4768
4769 /**
4770 * Unicode script "Syriac".
4771 */
4772 SYRIAC,
4773
4774 /**
4775 * Unicode script "Thaana".
4776 */
4777 THAANA,
4778
4779 /**
4780 * Unicode script "Devanagari".
4781 */
4782 DEVANAGARI,
4783
4784 /**
4785 * Unicode script "Bengali".
4786 */
4787 BENGALI,
4788
4789 /**
4790 * Unicode script "Gurmukhi".
4791 */
4792 GURMUKHI,
4793
4794 /**
4795 * Unicode script "Gujarati".
4796 */
4797 GUJARATI,
4798
4799 /**
4800 * Unicode script "Oriya".
4801 */
4802 ORIYA,
4803
4804 /**
4805 * Unicode script "Tamil".
4806 */
4807 TAMIL,
4808
4809 /**
4810 * Unicode script "Telugu".
4811 */
4812 TELUGU,
4813
4814 /**
4815 * Unicode script "Kannada".
4816 */
4817 KANNADA,
4818
4819 /**
4820 * Unicode script "Malayalam".
4821 */
4822 MALAYALAM,
4823
4824 /**
4825 * Unicode script "Sinhala".
4826 */
4827 SINHALA,
4828
4829 /**
4830 * Unicode script "Thai".
4831 */
4832 THAI,
4833
4834 /**
4835 * Unicode script "Lao".
4836 */
4837 LAO,
4838
4839 /**
4840 * Unicode script "Tibetan".
4841 */
4842 TIBETAN,
4843
4844 /**
4845 * Unicode script "Myanmar".
4846 */
4847 MYANMAR,
4848
4849 /**
4850 * Unicode script "Georgian".
4851 */
4852 GEORGIAN,
4853
4854 /**
4855 * Unicode script "Hangul".
4856 */
4857 HANGUL,
4858
4859 /**
4860 * Unicode script "Ethiopic".
4861 */
4862 ETHIOPIC,
4863
4864 /**
4865 * Unicode script "Cherokee".
4866 */
4867 CHEROKEE,
4868
4869 /**
4870 * Unicode script "Canadian_Aboriginal".
4871 */
4872 CANADIAN_ABORIGINAL,
4873
4874 /**
4875 * Unicode script "Ogham".
4876 */
4877 OGHAM,
4878
4879 /**
4880 * Unicode script "Runic".
4881 */
4882 RUNIC,
4883
4884 /**
4885 * Unicode script "Khmer".
4886 */
4887 KHMER,
4888
4889 /**
4890 * Unicode script "Mongolian".
4891 */
4892 MONGOLIAN,
4893
4894 /**
4895 * Unicode script "Hiragana".
4896 */
4897 HIRAGANA,
4898
4899 /**
4900 * Unicode script "Katakana".
4901 */
4902 KATAKANA,
4903
4904 /**
4905 * Unicode script "Bopomofo".
4906 */
4907 BOPOMOFO,
4908
4909 /**
4910 * Unicode script "Han".
4911 */
4912 HAN,
4913
4914 /**
4915 * Unicode script "Yi".
4916 */
4917 YI,
4918
4919 /**
4920 * Unicode script "Old_Italic".
4921 */
4922 OLD_ITALIC,
4923
4924 /**
4925 * Unicode script "Gothic".
4926 */
4927 GOTHIC,
4928
4929 /**
4930 * Unicode script "Deseret".
4931 */
4932 DESERET,
4933
4934 /**
4935 * Unicode script "Inherited".
4936 */
4937 INHERITED,
4938
4939 /**
4940 * Unicode script "Tagalog".
4941 */
4942 TAGALOG,
4943
4944 /**
4945 * Unicode script "Hanunoo".
4946 */
4947 HANUNOO,
4948
4949 /**
4950 * Unicode script "Buhid".
4951 */
4952 BUHID,
4953
4954 /**
4955 * Unicode script "Tagbanwa".
4956 */
4957 TAGBANWA,
4958
4959 /**
4960 * Unicode script "Limbu".
4961 */
4962 LIMBU,
4963
4964 /**
4965 * Unicode script "Tai_Le".
4966 */
4967 TAI_LE,
4968
4969 /**
4970 * Unicode script "Linear_B".
4971 */
4972 LINEAR_B,
4973
4974 /**
4975 * Unicode script "Ugaritic".
4976 */
4977 UGARITIC,
4978
4979 /**
4980 * Unicode script "Shavian".
4981 */
4982 SHAVIAN,
4983
4984 /**
4985 * Unicode script "Osmanya".
4986 */
4987 OSMANYA,
4988
4989 /**
4990 * Unicode script "Cypriot".
4991 */
4992 CYPRIOT,
4993
4994 /**
4995 * Unicode script "Braille".
4996 */
4997 BRAILLE,
4998
4999 /**
5000 * Unicode script "Buginese".
5001 */
5002 BUGINESE,
5003
5004 /**
5005 * Unicode script "Coptic".
5006 */
5007 COPTIC,
5008
5009 /**
5010 * Unicode script "New_Tai_Lue".
5011 */
5012 NEW_TAI_LUE,
5013
5014 /**
5015 * Unicode script "Glagolitic".
5016 */
5017 GLAGOLITIC,
5018
5019 /**
5020 * Unicode script "Tifinagh".
5021 */
5022 TIFINAGH,
5023
5024 /**
5025 * Unicode script "Syloti_Nagri".
5026 */
5027 SYLOTI_NAGRI,
5028
5029 /**
5030 * Unicode script "Old_Persian".
5031 */
5032 OLD_PERSIAN,
5033
5034 /**
5035 * Unicode script "Kharoshthi".
5036 */
5037 KHAROSHTHI,
5038
5039 /**
5040 * Unicode script "Balinese".
5041 */
5042 BALINESE,
5043
5044 /**
5045 * Unicode script "Cuneiform".
5046 */
5047 CUNEIFORM,
5048
5049 /**
5050 * Unicode script "Phoenician".
5051 */
5052 PHOENICIAN,
5053
5054 /**
5055 * Unicode script "Phags_Pa".
5056 */
5057 PHAGS_PA,
5058
5059 /**
5060 * Unicode script "Nko".
5061 */
5062 NKO,
5063
5064 /**
5065 * Unicode script "Sundanese".
5066 */
5067 SUNDANESE,
5068
5069 /**
5070 * Unicode script "Batak".
5071 */
5072 BATAK,
5073
5074 /**
5075 * Unicode script "Lepcha".
5076 */
5077 LEPCHA,
5078
5079 /**
5080 * Unicode script "Ol_Chiki".
5081 */
5082 OL_CHIKI,
5083
5084 /**
5085 * Unicode script "Vai".
5086 */
5087 VAI,
5088
5089 /**
5090 * Unicode script "Saurashtra".
5091 */
5092 SAURASHTRA,
5093
5094 /**
5095 * Unicode script "Kayah_Li".
5096 */
5097 KAYAH_LI,
5098
5099 /**
5100 * Unicode script "Rejang".
5101 */
5102 REJANG,
5103
5104 /**
5105 * Unicode script "Lycian".
5106 */
5107 LYCIAN,
5108
5109 /**
5110 * Unicode script "Carian".
5111 */
5112 CARIAN,
5113
5114 /**
5115 * Unicode script "Lydian".
5116 */
5117 LYDIAN,
5118
5119 /**
5120 * Unicode script "Cham".
5121 */
5122 CHAM,
5123
5124 /**
5125 * Unicode script "Tai_Tham".
5126 */
5127 TAI_THAM,
5128
5129 /**
5130 * Unicode script "Tai_Viet".
5131 */
5132 TAI_VIET,
5133
5134 /**
5135 * Unicode script "Avestan".
5136 */
5137 AVESTAN,
5138
5139 /**
5140 * Unicode script "Egyptian_Hieroglyphs".
5141 */
5142 EGYPTIAN_HIEROGLYPHS,
5143
5144 /**
5145 * Unicode script "Samaritan".
5146 */
5147 SAMARITAN,
5148
5149 /**
5150 * Unicode script "Mandaic".
5151 */
5152 MANDAIC,
5153
5154 /**
5155 * Unicode script "Lisu".
5156 */
5157 LISU,
5158
5159 /**
5160 * Unicode script "Bamum".
5161 */
5162 BAMUM,
5163
5164 /**
5165 * Unicode script "Javanese".
5166 */
5167 JAVANESE,
5168
5169 /**
5170 * Unicode script "Meetei_Mayek".
5171 */
5172 MEETEI_MAYEK,
5173
5174 /**
5175 * Unicode script "Imperial_Aramaic".
5176 */
5177 IMPERIAL_ARAMAIC,
5178
5179 /**
5180 * Unicode script "Old_South_Arabian".
5181 */
5182 OLD_SOUTH_ARABIAN,
5183
5184 /**
5185 * Unicode script "Inscriptional_Parthian".
5186 */
5187 INSCRIPTIONAL_PARTHIAN,
5188
5189 /**
5190 * Unicode script "Inscriptional_Pahlavi".
5191 */
5192 INSCRIPTIONAL_PAHLAVI,
5193
5194 /**
5195 * Unicode script "Old_Turkic".
5196 */
5197 OLD_TURKIC,
5198
5199 /**
5200 * Unicode script "Brahmi".
5201 */
5202 BRAHMI,
5203
5204 /**
5205 * Unicode script "Kaithi".
5206 */
5207 KAITHI,
5208
5209 /**
5210 * Unicode script "Meroitic Hieroglyphs".
5211 * @since 1.8
5212 */
5213 MEROITIC_HIEROGLYPHS,
5214
5215 /**
5216 * Unicode script "Meroitic Cursive".
5217 * @since 1.8
5218 */
5219 MEROITIC_CURSIVE,
5220
5221 /**
5222 * Unicode script "Sora Sompeng".
5223 * @since 1.8
5224 */
5225 SORA_SOMPENG,
5226
5227 /**
5228 * Unicode script "Chakma".
5229 * @since 1.8
5230 */
5231 CHAKMA,
5232
5233 /**
5234 * Unicode script "Sharada".
5235 * @since 1.8
5236 */
5237 SHARADA,
5238
5239 /**
5240 * Unicode script "Takri".
5241 * @since 1.8
5242 */
5243 TAKRI,
5244
5245 /**
5246 * Unicode script "Miao".
5247 * @since 1.8
5248 */
5249 MIAO,
5250
5251 /**
5252 * Unicode script "Caucasian Albanian".
5253 * @since 9
5254 */
5255 CAUCASIAN_ALBANIAN,
5256
5257 /**
5258 * Unicode script "Bassa Vah".
5259 * @since 9
5260 */
5261 BASSA_VAH,
5262
5263 /**
5264 * Unicode script "Duployan".
5265 * @since 9
5266 */
5267 DUPLOYAN,
5268
5269 /**
5270 * Unicode script "Elbasan".
5271 * @since 9
5272 */
5273 ELBASAN,
5274
5275 /**
5276 * Unicode script "Grantha".
5277 * @since 9
5278 */
5279 GRANTHA,
5280
5281 /**
5282 * Unicode script "Pahawh Hmong".
5283 * @since 9
5284 */
5285 PAHAWH_HMONG,
5286
5287 /**
5288 * Unicode script "Khojki".
5289 * @since 9
5290 */
5291 KHOJKI,
5292
5293 /**
5294 * Unicode script "Linear A".
5295 * @since 9
5296 */
5297 LINEAR_A,
5298
5299 /**
5300 * Unicode script "Mahajani".
5301 * @since 9
5302 */
5303 MAHAJANI,
5304
5305 /**
5306 * Unicode script "Manichaean".
5307 * @since 9
5308 */
5309 MANICHAEAN,
5310
5311 /**
5312 * Unicode script "Mende Kikakui".
5313 * @since 9
5314 */
5315 MENDE_KIKAKUI,
5316
5317 /**
5318 * Unicode script "Modi".
5319 * @since 9
5320 */
5321 MODI,
5322
5323 /**
5324 * Unicode script "Mro".
5325 * @since 9
5326 */
5327 MRO,
5328
5329 /**
5330 * Unicode script "Old North Arabian".
5331 * @since 9
5332 */
5333 OLD_NORTH_ARABIAN,
5334
5335 /**
5336 * Unicode script "Nabataean".
5337 * @since 9
5338 */
5339 NABATAEAN,
5340
5341 /**
5342 * Unicode script "Palmyrene".
5343 * @since 9
5344 */
5345 PALMYRENE,
5346
5347 /**
5348 * Unicode script "Pau Cin Hau".
5349 * @since 9
5350 */
5351 PAU_CIN_HAU,
5352
5353 /**
5354 * Unicode script "Old Permic".
5355 * @since 9
5356 */
5357 OLD_PERMIC,
5358
5359 /**
5360 * Unicode script "Psalter Pahlavi".
5361 * @since 9
5362 */
5363 PSALTER_PAHLAVI,
5364
5365 /**
5366 * Unicode script "Siddham".
5367 * @since 9
5368 */
5369 SIDDHAM,
5370
5371 /**
5372 * Unicode script "Khudawadi".
5373 * @since 9
5374 */
5375 KHUDAWADI,
5376
5377 /**
5378 * Unicode script "Tirhuta".
5379 * @since 9
5380 */
5381 TIRHUTA,
5382
5383 /**
5384 * Unicode script "Warang Citi".
5385 * @since 9
5386 */
5387 WARANG_CITI,
5388
5389 /**
5390 * Unicode script "Ahom".
5391 * @since 9
5392 */
5393 AHOM,
5394
5395 /**
5396 * Unicode script "Anatolian Hieroglyphs".
5397 * @since 9
5398 */
5399 ANATOLIAN_HIEROGLYPHS,
5400
5401 /**
5402 * Unicode script "Hatran".
5403 * @since 9
5404 */
5405 HATRAN,
5406
5407 /**
5408 * Unicode script "Multani".
5409 * @since 9
5410 */
5411 MULTANI,
5412
5413 /**
5414 * Unicode script "Old Hungarian".
5415 * @since 9
5416 */
5417 OLD_HUNGARIAN,
5418
5419 /**
5420 * Unicode script "SignWriting".
5421 * @since 9
5422 */
5423 SIGNWRITING,
5424
5425 /**
5426 * Unicode script "Adlam".
5427 * @since 11
5428 */
5429 ADLAM,
5430
5431 /**
5432 * Unicode script "Bhaiksuki".
5433 * @since 11
5434 */
5435 BHAIKSUKI,
5436
5437 /**
5438 * Unicode script "Marchen".
5439 * @since 11
5440 */
5441 MARCHEN,
5442
5443 /**
5444 * Unicode script "Newa".
5445 * @since 11
5446 */
5447 NEWA,
5448
5449 /**
5450 * Unicode script "Osage".
5451 * @since 11
5452 */
5453 OSAGE,
5454
5455 /**
5456 * Unicode script "Tangut".
5457 * @since 11
5458 */
5459 TANGUT,
5460
5461 /**
5462 * Unicode script "Masaram Gondi".
5463 * @since 11
5464 */
5465 MASARAM_GONDI,
5466
5467 /**
5468 * Unicode script "Nushu".
5469 * @since 11
5470 */
5471 NUSHU,
5472
5473 /**
5474 * Unicode script "Soyombo".
5475 * @since 11
5476 */
5477 SOYOMBO,
5478
5479 /**
5480 * Unicode script "Zanabazar Square".
5481 * @since 11
5482 */
5483 ZANABAZAR_SQUARE,
5484
5485 /**
5486 * Unicode script "Hanifi Rohingya".
5487 * @since 12
5488 */
5489 HANIFI_ROHINGYA,
5490
5491 /**
5492 * Unicode script "Old Sogdian".
5493 * @since 12
5494 */
5495 OLD_SOGDIAN,
5496
5497 /**
5498 * Unicode script "Sogdian".
5499 * @since 12
5500 */
5501 SOGDIAN,
5502
5503 /**
5504 * Unicode script "Dogra".
5505 * @since 12
5506 */
5507 DOGRA,
5508
5509 /**
5510 * Unicode script "Gunjala Gondi".
5511 * @since 12
5512 */
5513 GUNJALA_GONDI,
5514
5515 /**
5516 * Unicode script "Makasar".
5517 * @since 12
5518 */
5519 MAKASAR,
5520
5521 /**
5522 * Unicode script "Medefaidrin".
5523 * @since 12
5524 */
5525 MEDEFAIDRIN,
5526
5527 /**
5528 * Unicode script "Elymaic".
5529 * @since 13
5530 */
5531 ELYMAIC,
5532
5533 /**
5534 * Unicode script "Nandinagari".
5535 * @since 13
5536 */
5537 NANDINAGARI,
5538
5539 /**
5540 * Unicode script "Nyiakeng Puachue Hmong".
5541 * @since 13
5542 */
5543 NYIAKENG_PUACHUE_HMONG,
5544
5545 /**
5546 * Unicode script "Wancho".
5547 * @since 13
5548 */
5549 WANCHO,
5550
5551 /**
5552 * Unicode script "Yezidi".
5553 * @since 15
5554 */
5555 YEZIDI,
5556
5557 /**
5558 * Unicode script "Chorasmian".
5559 * @since 15
5560 */
5561 CHORASMIAN,
5562
5563 /**
5564 * Unicode script "Dives Akuru".
5565 * @since 15
5566 */
5567 DIVES_AKURU,
5568
5569 /**
5570 * Unicode script "Khitan Small Script".
5571 * @since 15
5572 */
5573 KHITAN_SMALL_SCRIPT,
5574
5575 /**
5576 * Unicode script "Vithkuqi".
5577 * @since 19
5578 */
5579 VITHKUQI,
5580
5581 /**
5582 * Unicode script "Old Uyghur".
5583 * @since 19
5584 */
5585 OLD_UYGHUR,
5586
5587 /**
5588 * Unicode script "Cypro Minoan".
5589 * @since 19
5590 */
5591 CYPRO_MINOAN,
5592
5593 /**
5594 * Unicode script "Tangsa".
5595 * @since 19
5596 */
5597 TANGSA,
5598
5599 /**
5600 * Unicode script "Toto".
5601 * @since 19
5602 */
5603 TOTO,
5604
5605 /**
5606 * Unicode script "Kawi".
5607 * @since 20
5608 */
5609 KAWI,
5610
5611 /**
5612 * Unicode script "Nag Mundari".
5613 * @since 20
5614 */
5615 NAG_MUNDARI,
5616
5617 /**
5618 * Unicode script "Todhri".
5619 * @since 24
5620 */
5621 TODHRI,
5622
5623 /**
5624 * Unicode script "Garay".
5625 * @since 24
5626 */
5627 GARAY,
5628
5629 /**
5630 * Unicode script "Tulu Tigalari".
5631 * @since 24
5632 */
5633 TULU_TIGALARI,
5634
5635 /**
5636 * Unicode script "Sunuwar".
5637 * @since 24
5638 */
5639 SUNUWAR,
5640
5641 /**
5642 * Unicode script "Gurung Khema".
5643 * @since 24
5644 */
5645 GURUNG_KHEMA,
5646
5647 /**
5648 * Unicode script "Kirat Rai".
5649 * @since 24
5650 */
5651 KIRAT_RAI,
5652
5653 /**
5654 * Unicode script "Ol Onal".
5655 * @since 24
5656 */
5657 OL_ONAL,
5658
5659 /**
5660 * Unicode script "Sidetic".
5661 * @since 26
5662 */
5663 SIDETIC,
5664
5665 /**
5666 * Unicode script "Tolong Siki".
5667 * @since 26
5668 */
5669 TOLONG_SIKI,
5670
5671 /**
5672 * Unicode script "Beria Erfe".
5673 * @since 26
5674 */
5675 BERIA_ERFE,
5676
5677 /**
5678 * Unicode script "Tai Yo".
5679 * @since 26
5680 */
5681 TAI_YO,
5682
5683 /**
5684 * Unicode script "Unknown".
5685 */
5686 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5687
5688 private static final int[] scriptStarts = {
5689 0x0000, // 0000..0040; COMMON
5690 0x0041, // 0041..005A; LATIN
5691 0x005B, // 005B..0060; COMMON
5692 0x0061, // 0061..007A; LATIN
5693 0x007B, // 007B..00A9; COMMON
5694 0x00AA, // 00AA ; LATIN
5695 0x00AB, // 00AB..00B9; COMMON
5696 0x00BA, // 00BA ; LATIN
5697 0x00BB, // 00BB..00BF; COMMON
5698 0x00C0, // 00C0..00D6; LATIN
5699 0x00D7, // 00D7 ; COMMON
5700 0x00D8, // 00D8..00F6; LATIN
5701 0x00F7, // 00F7 ; COMMON
5702 0x00F8, // 00F8..02B8; LATIN
5703 0x02B9, // 02B9..02DF; COMMON
5704 0x02E0, // 02E0..02E4; LATIN
5705 0x02E5, // 02E5..02E9; COMMON
5706 0x02EA, // 02EA..02EB; BOPOMOFO
5707 0x02EC, // 02EC..02FF; COMMON
5708 0x0300, // 0300..036F; INHERITED
5709 0x0370, // 0370..0373; GREEK
5710 0x0374, // 0374 ; COMMON
5711 0x0375, // 0375..0377; GREEK
5712 0x0378, // 0378..0379; UNKNOWN
5713 0x037A, // 037A..037D; GREEK
5714 0x037E, // 037E ; COMMON
5715 0x037F, // 037F ; GREEK
5716 0x0380, // 0380..0383; UNKNOWN
5717 0x0384, // 0384 ; GREEK
5718 0x0385, // 0385 ; COMMON
5719 0x0386, // 0386 ; GREEK
5720 0x0387, // 0387 ; COMMON
5721 0x0388, // 0388..038A; GREEK
5722 0x038B, // 038B ; UNKNOWN
5723 0x038C, // 038C ; GREEK
5724 0x038D, // 038D ; UNKNOWN
5725 0x038E, // 038E..03A1; GREEK
5726 0x03A2, // 03A2 ; UNKNOWN
5727 0x03A3, // 03A3..03E1; GREEK
5728 0x03E2, // 03E2..03EF; COPTIC
5729 0x03F0, // 03F0..03FF; GREEK
5730 0x0400, // 0400..0484; CYRILLIC
5731 0x0485, // 0485..0486; INHERITED
5732 0x0487, // 0487..052F; CYRILLIC
5733 0x0530, // 0530 ; UNKNOWN
5734 0x0531, // 0531..0556; ARMENIAN
5735 0x0557, // 0557..0558; UNKNOWN
5736 0x0559, // 0559..058A; ARMENIAN
5737 0x058B, // 058B..058C; UNKNOWN
5738 0x058D, // 058D..058F; ARMENIAN
5739 0x0590, // 0590 ; UNKNOWN
5740 0x0591, // 0591..05C7; HEBREW
5741 0x05C8, // 05C8..05CF; UNKNOWN
5742 0x05D0, // 05D0..05EA; HEBREW
5743 0x05EB, // 05EB..05EE; UNKNOWN
5744 0x05EF, // 05EF..05F4; HEBREW
5745 0x05F5, // 05F5..05FF; UNKNOWN
5746 0x0600, // 0600..0604; ARABIC
5747 0x0605, // 0605 ; COMMON
5748 0x0606, // 0606..060B; ARABIC
5749 0x060C, // 060C ; COMMON
5750 0x060D, // 060D..061A; ARABIC
5751 0x061B, // 061B ; COMMON
5752 0x061C, // 061C..061E; ARABIC
5753 0x061F, // 061F ; COMMON
5754 0x0620, // 0620..063F; ARABIC
5755 0x0640, // 0640 ; COMMON
5756 0x0641, // 0641..064A; ARABIC
5757 0x064B, // 064B..0655; INHERITED
5758 0x0656, // 0656..066F; ARABIC
5759 0x0670, // 0670 ; INHERITED
5760 0x0671, // 0671..06DC; ARABIC
5761 0x06DD, // 06DD ; COMMON
5762 0x06DE, // 06DE..06FF; ARABIC
5763 0x0700, // 0700..070D; SYRIAC
5764 0x070E, // 070E ; UNKNOWN
5765 0x070F, // 070F..074A; SYRIAC
5766 0x074B, // 074B..074C; UNKNOWN
5767 0x074D, // 074D..074F; SYRIAC
5768 0x0750, // 0750..077F; ARABIC
5769 0x0780, // 0780..07B1; THAANA
5770 0x07B2, // 07B2..07BF; UNKNOWN
5771 0x07C0, // 07C0..07FA; NKO
5772 0x07FB, // 07FB..07FC; UNKNOWN
5773 0x07FD, // 07FD..07FF; NKO
5774 0x0800, // 0800..082D; SAMARITAN
5775 0x082E, // 082E..082F; UNKNOWN
5776 0x0830, // 0830..083E; SAMARITAN
5777 0x083F, // 083F ; UNKNOWN
5778 0x0840, // 0840..085B; MANDAIC
5779 0x085C, // 085C..085D; UNKNOWN
5780 0x085E, // 085E ; MANDAIC
5781 0x085F, // 085F ; UNKNOWN
5782 0x0860, // 0860..086A; SYRIAC
5783 0x086B, // 086B..086F; UNKNOWN
5784 0x0870, // 0870..0891; ARABIC
5785 0x0892, // 0892..0896; UNKNOWN
5786 0x0897, // 0897..08E1; ARABIC
5787 0x08E2, // 08E2 ; COMMON
5788 0x08E3, // 08E3..08FF; ARABIC
5789 0x0900, // 0900..0950; DEVANAGARI
5790 0x0951, // 0951..0954; INHERITED
5791 0x0955, // 0955..0963; DEVANAGARI
5792 0x0964, // 0964..0965; COMMON
5793 0x0966, // 0966..097F; DEVANAGARI
5794 0x0980, // 0980..0983; BENGALI
5795 0x0984, // 0984 ; UNKNOWN
5796 0x0985, // 0985..098C; BENGALI
5797 0x098D, // 098D..098E; UNKNOWN
5798 0x098F, // 098F..0990; BENGALI
5799 0x0991, // 0991..0992; UNKNOWN
5800 0x0993, // 0993..09A8; BENGALI
5801 0x09A9, // 09A9 ; UNKNOWN
5802 0x09AA, // 09AA..09B0; BENGALI
5803 0x09B1, // 09B1 ; UNKNOWN
5804 0x09B2, // 09B2 ; BENGALI
5805 0x09B3, // 09B3..09B5; UNKNOWN
5806 0x09B6, // 09B6..09B9; BENGALI
5807 0x09BA, // 09BA..09BB; UNKNOWN
5808 0x09BC, // 09BC..09C4; BENGALI
5809 0x09C5, // 09C5..09C6; UNKNOWN
5810 0x09C7, // 09C7..09C8; BENGALI
5811 0x09C9, // 09C9..09CA; UNKNOWN
5812 0x09CB, // 09CB..09CE; BENGALI
5813 0x09CF, // 09CF..09D6; UNKNOWN
5814 0x09D7, // 09D7 ; BENGALI
5815 0x09D8, // 09D8..09DB; UNKNOWN
5816 0x09DC, // 09DC..09DD; BENGALI
5817 0x09DE, // 09DE ; UNKNOWN
5818 0x09DF, // 09DF..09E3; BENGALI
5819 0x09E4, // 09E4..09E5; UNKNOWN
5820 0x09E6, // 09E6..09FE; BENGALI
5821 0x09FF, // 09FF..0A00; UNKNOWN
5822 0x0A01, // 0A01..0A03; GURMUKHI
5823 0x0A04, // 0A04 ; UNKNOWN
5824 0x0A05, // 0A05..0A0A; GURMUKHI
5825 0x0A0B, // 0A0B..0A0E; UNKNOWN
5826 0x0A0F, // 0A0F..0A10; GURMUKHI
5827 0x0A11, // 0A11..0A12; UNKNOWN
5828 0x0A13, // 0A13..0A28; GURMUKHI
5829 0x0A29, // 0A29 ; UNKNOWN
5830 0x0A2A, // 0A2A..0A30; GURMUKHI
5831 0x0A31, // 0A31 ; UNKNOWN
5832 0x0A32, // 0A32..0A33; GURMUKHI
5833 0x0A34, // 0A34 ; UNKNOWN
5834 0x0A35, // 0A35..0A36; GURMUKHI
5835 0x0A37, // 0A37 ; UNKNOWN
5836 0x0A38, // 0A38..0A39; GURMUKHI
5837 0x0A3A, // 0A3A..0A3B; UNKNOWN
5838 0x0A3C, // 0A3C ; GURMUKHI
5839 0x0A3D, // 0A3D ; UNKNOWN
5840 0x0A3E, // 0A3E..0A42; GURMUKHI
5841 0x0A43, // 0A43..0A46; UNKNOWN
5842 0x0A47, // 0A47..0A48; GURMUKHI
5843 0x0A49, // 0A49..0A4A; UNKNOWN
5844 0x0A4B, // 0A4B..0A4D; GURMUKHI
5845 0x0A4E, // 0A4E..0A50; UNKNOWN
5846 0x0A51, // 0A51 ; GURMUKHI
5847 0x0A52, // 0A52..0A58; UNKNOWN
5848 0x0A59, // 0A59..0A5C; GURMUKHI
5849 0x0A5D, // 0A5D ; UNKNOWN
5850 0x0A5E, // 0A5E ; GURMUKHI
5851 0x0A5F, // 0A5F..0A65; UNKNOWN
5852 0x0A66, // 0A66..0A76; GURMUKHI
5853 0x0A77, // 0A77..0A80; UNKNOWN
5854 0x0A81, // 0A81..0A83; GUJARATI
5855 0x0A84, // 0A84 ; UNKNOWN
5856 0x0A85, // 0A85..0A8D; GUJARATI
5857 0x0A8E, // 0A8E ; UNKNOWN
5858 0x0A8F, // 0A8F..0A91; GUJARATI
5859 0x0A92, // 0A92 ; UNKNOWN
5860 0x0A93, // 0A93..0AA8; GUJARATI
5861 0x0AA9, // 0AA9 ; UNKNOWN
5862 0x0AAA, // 0AAA..0AB0; GUJARATI
5863 0x0AB1, // 0AB1 ; UNKNOWN
5864 0x0AB2, // 0AB2..0AB3; GUJARATI
5865 0x0AB4, // 0AB4 ; UNKNOWN
5866 0x0AB5, // 0AB5..0AB9; GUJARATI
5867 0x0ABA, // 0ABA..0ABB; UNKNOWN
5868 0x0ABC, // 0ABC..0AC5; GUJARATI
5869 0x0AC6, // 0AC6 ; UNKNOWN
5870 0x0AC7, // 0AC7..0AC9; GUJARATI
5871 0x0ACA, // 0ACA ; UNKNOWN
5872 0x0ACB, // 0ACB..0ACD; GUJARATI
5873 0x0ACE, // 0ACE..0ACF; UNKNOWN
5874 0x0AD0, // 0AD0 ; GUJARATI
5875 0x0AD1, // 0AD1..0ADF; UNKNOWN
5876 0x0AE0, // 0AE0..0AE3; GUJARATI
5877 0x0AE4, // 0AE4..0AE5; UNKNOWN
5878 0x0AE6, // 0AE6..0AF1; GUJARATI
5879 0x0AF2, // 0AF2..0AF8; UNKNOWN
5880 0x0AF9, // 0AF9..0AFF; GUJARATI
5881 0x0B00, // 0B00 ; UNKNOWN
5882 0x0B01, // 0B01..0B03; ORIYA
5883 0x0B04, // 0B04 ; UNKNOWN
5884 0x0B05, // 0B05..0B0C; ORIYA
5885 0x0B0D, // 0B0D..0B0E; UNKNOWN
5886 0x0B0F, // 0B0F..0B10; ORIYA
5887 0x0B11, // 0B11..0B12; UNKNOWN
5888 0x0B13, // 0B13..0B28; ORIYA
5889 0x0B29, // 0B29 ; UNKNOWN
5890 0x0B2A, // 0B2A..0B30; ORIYA
5891 0x0B31, // 0B31 ; UNKNOWN
5892 0x0B32, // 0B32..0B33; ORIYA
5893 0x0B34, // 0B34 ; UNKNOWN
5894 0x0B35, // 0B35..0B39; ORIYA
5895 0x0B3A, // 0B3A..0B3B; UNKNOWN
5896 0x0B3C, // 0B3C..0B44; ORIYA
5897 0x0B45, // 0B45..0B46; UNKNOWN
5898 0x0B47, // 0B47..0B48; ORIYA
5899 0x0B49, // 0B49..0B4A; UNKNOWN
5900 0x0B4B, // 0B4B..0B4D; ORIYA
5901 0x0B4E, // 0B4E..0B54; UNKNOWN
5902 0x0B55, // 0B55..0B57; ORIYA
5903 0x0B58, // 0B58..0B5B; UNKNOWN
5904 0x0B5C, // 0B5C..0B5D; ORIYA
5905 0x0B5E, // 0B5E ; UNKNOWN
5906 0x0B5F, // 0B5F..0B63; ORIYA
5907 0x0B64, // 0B64..0B65; UNKNOWN
5908 0x0B66, // 0B66..0B77; ORIYA
5909 0x0B78, // 0B78..0B81; UNKNOWN
5910 0x0B82, // 0B82..0B83; TAMIL
5911 0x0B84, // 0B84 ; UNKNOWN
5912 0x0B85, // 0B85..0B8A; TAMIL
5913 0x0B8B, // 0B8B..0B8D; UNKNOWN
5914 0x0B8E, // 0B8E..0B90; TAMIL
5915 0x0B91, // 0B91 ; UNKNOWN
5916 0x0B92, // 0B92..0B95; TAMIL
5917 0x0B96, // 0B96..0B98; UNKNOWN
5918 0x0B99, // 0B99..0B9A; TAMIL
5919 0x0B9B, // 0B9B ; UNKNOWN
5920 0x0B9C, // 0B9C ; TAMIL
5921 0x0B9D, // 0B9D ; UNKNOWN
5922 0x0B9E, // 0B9E..0B9F; TAMIL
5923 0x0BA0, // 0BA0..0BA2; UNKNOWN
5924 0x0BA3, // 0BA3..0BA4; TAMIL
5925 0x0BA5, // 0BA5..0BA7; UNKNOWN
5926 0x0BA8, // 0BA8..0BAA; TAMIL
5927 0x0BAB, // 0BAB..0BAD; UNKNOWN
5928 0x0BAE, // 0BAE..0BB9; TAMIL
5929 0x0BBA, // 0BBA..0BBD; UNKNOWN
5930 0x0BBE, // 0BBE..0BC2; TAMIL
5931 0x0BC3, // 0BC3..0BC5; UNKNOWN
5932 0x0BC6, // 0BC6..0BC8; TAMIL
5933 0x0BC9, // 0BC9 ; UNKNOWN
5934 0x0BCA, // 0BCA..0BCD; TAMIL
5935 0x0BCE, // 0BCE..0BCF; UNKNOWN
5936 0x0BD0, // 0BD0 ; TAMIL
5937 0x0BD1, // 0BD1..0BD6; UNKNOWN
5938 0x0BD7, // 0BD7 ; TAMIL
5939 0x0BD8, // 0BD8..0BE5; UNKNOWN
5940 0x0BE6, // 0BE6..0BFA; TAMIL
5941 0x0BFB, // 0BFB..0BFF; UNKNOWN
5942 0x0C00, // 0C00..0C0C; TELUGU
5943 0x0C0D, // 0C0D ; UNKNOWN
5944 0x0C0E, // 0C0E..0C10; TELUGU
5945 0x0C11, // 0C11 ; UNKNOWN
5946 0x0C12, // 0C12..0C28; TELUGU
5947 0x0C29, // 0C29 ; UNKNOWN
5948 0x0C2A, // 0C2A..0C39; TELUGU
5949 0x0C3A, // 0C3A..0C3B; UNKNOWN
5950 0x0C3C, // 0C3C..0C44; TELUGU
5951 0x0C45, // 0C45 ; UNKNOWN
5952 0x0C46, // 0C46..0C48; TELUGU
5953 0x0C49, // 0C49 ; UNKNOWN
5954 0x0C4A, // 0C4A..0C4D; TELUGU
5955 0x0C4E, // 0C4E..0C54; UNKNOWN
5956 0x0C55, // 0C55..0C56; TELUGU
5957 0x0C57, // 0C57 ; UNKNOWN
5958 0x0C58, // 0C58..0C5A; TELUGU
5959 0x0C5B, // 0C5B ; UNKNOWN
5960 0x0C5C, // 0C5C..0C5D; TELUGU
5961 0x0C5E, // 0C5E..0C5F; UNKNOWN
5962 0x0C60, // 0C60..0C63; TELUGU
5963 0x0C64, // 0C64..0C65; UNKNOWN
5964 0x0C66, // 0C66..0C6F; TELUGU
5965 0x0C70, // 0C70..0C76; UNKNOWN
5966 0x0C77, // 0C77..0C7F; TELUGU
5967 0x0C80, // 0C80..0C8C; KANNADA
5968 0x0C8D, // 0C8D ; UNKNOWN
5969 0x0C8E, // 0C8E..0C90; KANNADA
5970 0x0C91, // 0C91 ; UNKNOWN
5971 0x0C92, // 0C92..0CA8; KANNADA
5972 0x0CA9, // 0CA9 ; UNKNOWN
5973 0x0CAA, // 0CAA..0CB3; KANNADA
5974 0x0CB4, // 0CB4 ; UNKNOWN
5975 0x0CB5, // 0CB5..0CB9; KANNADA
5976 0x0CBA, // 0CBA..0CBB; UNKNOWN
5977 0x0CBC, // 0CBC..0CC4; KANNADA
5978 0x0CC5, // 0CC5 ; UNKNOWN
5979 0x0CC6, // 0CC6..0CC8; KANNADA
5980 0x0CC9, // 0CC9 ; UNKNOWN
5981 0x0CCA, // 0CCA..0CCD; KANNADA
5982 0x0CCE, // 0CCE..0CD4; UNKNOWN
5983 0x0CD5, // 0CD5..0CD6; KANNADA
5984 0x0CD7, // 0CD7..0CDB; UNKNOWN
5985 0x0CDC, // 0CDC..0CDE; KANNADA
5986 0x0CDF, // 0CDF ; UNKNOWN
5987 0x0CE0, // 0CE0..0CE3; KANNADA
5988 0x0CE4, // 0CE4..0CE5; UNKNOWN
5989 0x0CE6, // 0CE6..0CEF; KANNADA
5990 0x0CF0, // 0CF0 ; UNKNOWN
5991 0x0CF1, // 0CF1..0CF3; KANNADA
5992 0x0CF4, // 0CF4..0CFF; UNKNOWN
5993 0x0D00, // 0D00..0D0C; MALAYALAM
5994 0x0D0D, // 0D0D ; UNKNOWN
5995 0x0D0E, // 0D0E..0D10; MALAYALAM
5996 0x0D11, // 0D11 ; UNKNOWN
5997 0x0D12, // 0D12..0D44; MALAYALAM
5998 0x0D45, // 0D45 ; UNKNOWN
5999 0x0D46, // 0D46..0D48; MALAYALAM
6000 0x0D49, // 0D49 ; UNKNOWN
6001 0x0D4A, // 0D4A..0D4F; MALAYALAM
6002 0x0D50, // 0D50..0D53; UNKNOWN
6003 0x0D54, // 0D54..0D63; MALAYALAM
6004 0x0D64, // 0D64..0D65; UNKNOWN
6005 0x0D66, // 0D66..0D7F; MALAYALAM
6006 0x0D80, // 0D80 ; UNKNOWN
6007 0x0D81, // 0D81..0D83; SINHALA
6008 0x0D84, // 0D84 ; UNKNOWN
6009 0x0D85, // 0D85..0D96; SINHALA
6010 0x0D97, // 0D97..0D99; UNKNOWN
6011 0x0D9A, // 0D9A..0DB1; SINHALA
6012 0x0DB2, // 0DB2 ; UNKNOWN
6013 0x0DB3, // 0DB3..0DBB; SINHALA
6014 0x0DBC, // 0DBC ; UNKNOWN
6015 0x0DBD, // 0DBD ; SINHALA
6016 0x0DBE, // 0DBE..0DBF; UNKNOWN
6017 0x0DC0, // 0DC0..0DC6; SINHALA
6018 0x0DC7, // 0DC7..0DC9; UNKNOWN
6019 0x0DCA, // 0DCA ; SINHALA
6020 0x0DCB, // 0DCB..0DCE; UNKNOWN
6021 0x0DCF, // 0DCF..0DD4; SINHALA
6022 0x0DD5, // 0DD5 ; UNKNOWN
6023 0x0DD6, // 0DD6 ; SINHALA
6024 0x0DD7, // 0DD7 ; UNKNOWN
6025 0x0DD8, // 0DD8..0DDF; SINHALA
6026 0x0DE0, // 0DE0..0DE5; UNKNOWN
6027 0x0DE6, // 0DE6..0DEF; SINHALA
6028 0x0DF0, // 0DF0..0DF1; UNKNOWN
6029 0x0DF2, // 0DF2..0DF4; SINHALA
6030 0x0DF5, // 0DF5..0E00; UNKNOWN
6031 0x0E01, // 0E01..0E3A; THAI
6032 0x0E3B, // 0E3B..0E3E; UNKNOWN
6033 0x0E3F, // 0E3F ; COMMON
6034 0x0E40, // 0E40..0E5B; THAI
6035 0x0E5C, // 0E5C..0E80; UNKNOWN
6036 0x0E81, // 0E81..0E82; LAO
6037 0x0E83, // 0E83 ; UNKNOWN
6038 0x0E84, // 0E84 ; LAO
6039 0x0E85, // 0E85 ; UNKNOWN
6040 0x0E86, // 0E86..0E8A; LAO
6041 0x0E8B, // 0E8B ; UNKNOWN
6042 0x0E8C, // 0E8C..0EA3; LAO
6043 0x0EA4, // 0EA4 ; UNKNOWN
6044 0x0EA5, // 0EA5 ; LAO
6045 0x0EA6, // 0EA6 ; UNKNOWN
6046 0x0EA7, // 0EA7..0EBD; LAO
6047 0x0EBE, // 0EBE..0EBF; UNKNOWN
6048 0x0EC0, // 0EC0..0EC4; LAO
6049 0x0EC5, // 0EC5 ; UNKNOWN
6050 0x0EC6, // 0EC6 ; LAO
6051 0x0EC7, // 0EC7 ; UNKNOWN
6052 0x0EC8, // 0EC8..0ECE; LAO
6053 0x0ECF, // 0ECF ; UNKNOWN
6054 0x0ED0, // 0ED0..0ED9; LAO
6055 0x0EDA, // 0EDA..0EDB; UNKNOWN
6056 0x0EDC, // 0EDC..0EDF; LAO
6057 0x0EE0, // 0EE0..0EFF; UNKNOWN
6058 0x0F00, // 0F00..0F47; TIBETAN
6059 0x0F48, // 0F48 ; UNKNOWN
6060 0x0F49, // 0F49..0F6C; TIBETAN
6061 0x0F6D, // 0F6D..0F70; UNKNOWN
6062 0x0F71, // 0F71..0F97; TIBETAN
6063 0x0F98, // 0F98 ; UNKNOWN
6064 0x0F99, // 0F99..0FBC; TIBETAN
6065 0x0FBD, // 0FBD ; UNKNOWN
6066 0x0FBE, // 0FBE..0FCC; TIBETAN
6067 0x0FCD, // 0FCD ; UNKNOWN
6068 0x0FCE, // 0FCE..0FD4; TIBETAN
6069 0x0FD5, // 0FD5..0FD8; COMMON
6070 0x0FD9, // 0FD9..0FDA; TIBETAN
6071 0x0FDB, // 0FDB..0FFF; UNKNOWN
6072 0x1000, // 1000..109F; MYANMAR
6073 0x10A0, // 10A0..10C5; GEORGIAN
6074 0x10C6, // 10C6 ; UNKNOWN
6075 0x10C7, // 10C7 ; GEORGIAN
6076 0x10C8, // 10C8..10CC; UNKNOWN
6077 0x10CD, // 10CD ; GEORGIAN
6078 0x10CE, // 10CE..10CF; UNKNOWN
6079 0x10D0, // 10D0..10FA; GEORGIAN
6080 0x10FB, // 10FB ; COMMON
6081 0x10FC, // 10FC..10FF; GEORGIAN
6082 0x1100, // 1100..11FF; HANGUL
6083 0x1200, // 1200..1248; ETHIOPIC
6084 0x1249, // 1249 ; UNKNOWN
6085 0x124A, // 124A..124D; ETHIOPIC
6086 0x124E, // 124E..124F; UNKNOWN
6087 0x1250, // 1250..1256; ETHIOPIC
6088 0x1257, // 1257 ; UNKNOWN
6089 0x1258, // 1258 ; ETHIOPIC
6090 0x1259, // 1259 ; UNKNOWN
6091 0x125A, // 125A..125D; ETHIOPIC
6092 0x125E, // 125E..125F; UNKNOWN
6093 0x1260, // 1260..1288; ETHIOPIC
6094 0x1289, // 1289 ; UNKNOWN
6095 0x128A, // 128A..128D; ETHIOPIC
6096 0x128E, // 128E..128F; UNKNOWN
6097 0x1290, // 1290..12B0; ETHIOPIC
6098 0x12B1, // 12B1 ; UNKNOWN
6099 0x12B2, // 12B2..12B5; ETHIOPIC
6100 0x12B6, // 12B6..12B7; UNKNOWN
6101 0x12B8, // 12B8..12BE; ETHIOPIC
6102 0x12BF, // 12BF ; UNKNOWN
6103 0x12C0, // 12C0 ; ETHIOPIC
6104 0x12C1, // 12C1 ; UNKNOWN
6105 0x12C2, // 12C2..12C5; ETHIOPIC
6106 0x12C6, // 12C6..12C7; UNKNOWN
6107 0x12C8, // 12C8..12D6; ETHIOPIC
6108 0x12D7, // 12D7 ; UNKNOWN
6109 0x12D8, // 12D8..1310; ETHIOPIC
6110 0x1311, // 1311 ; UNKNOWN
6111 0x1312, // 1312..1315; ETHIOPIC
6112 0x1316, // 1316..1317; UNKNOWN
6113 0x1318, // 1318..135A; ETHIOPIC
6114 0x135B, // 135B..135C; UNKNOWN
6115 0x135D, // 135D..137C; ETHIOPIC
6116 0x137D, // 137D..137F; UNKNOWN
6117 0x1380, // 1380..1399; ETHIOPIC
6118 0x139A, // 139A..139F; UNKNOWN
6119 0x13A0, // 13A0..13F5; CHEROKEE
6120 0x13F6, // 13F6..13F7; UNKNOWN
6121 0x13F8, // 13F8..13FD; CHEROKEE
6122 0x13FE, // 13FE..13FF; UNKNOWN
6123 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
6124 0x1680, // 1680..169C; OGHAM
6125 0x169D, // 169D..169F; UNKNOWN
6126 0x16A0, // 16A0..16EA; RUNIC
6127 0x16EB, // 16EB..16ED; COMMON
6128 0x16EE, // 16EE..16F8; RUNIC
6129 0x16F9, // 16F9..16FF; UNKNOWN
6130 0x1700, // 1700..1715; TAGALOG
6131 0x1716, // 1716..171E; UNKNOWN
6132 0x171F, // 171F ; TAGALOG
6133 0x1720, // 1720..1734; HANUNOO
6134 0x1735, // 1735..1736; COMMON
6135 0x1737, // 1737..173F; UNKNOWN
6136 0x1740, // 1740..1753; BUHID
6137 0x1754, // 1754..175F; UNKNOWN
6138 0x1760, // 1760..176C; TAGBANWA
6139 0x176D, // 176D ; UNKNOWN
6140 0x176E, // 176E..1770; TAGBANWA
6141 0x1771, // 1771 ; UNKNOWN
6142 0x1772, // 1772..1773; TAGBANWA
6143 0x1774, // 1774..177F; UNKNOWN
6144 0x1780, // 1780..17DD; KHMER
6145 0x17DE, // 17DE..17DF; UNKNOWN
6146 0x17E0, // 17E0..17E9; KHMER
6147 0x17EA, // 17EA..17EF; UNKNOWN
6148 0x17F0, // 17F0..17F9; KHMER
6149 0x17FA, // 17FA..17FF; UNKNOWN
6150 0x1800, // 1800..1801; MONGOLIAN
6151 0x1802, // 1802..1803; COMMON
6152 0x1804, // 1804 ; MONGOLIAN
6153 0x1805, // 1805 ; COMMON
6154 0x1806, // 1806..1819; MONGOLIAN
6155 0x181A, // 181A..181F; UNKNOWN
6156 0x1820, // 1820..1878; MONGOLIAN
6157 0x1879, // 1879..187F; UNKNOWN
6158 0x1880, // 1880..18AA; MONGOLIAN
6159 0x18AB, // 18AB..18AF; UNKNOWN
6160 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
6161 0x18F6, // 18F6..18FF; UNKNOWN
6162 0x1900, // 1900..191E; LIMBU
6163 0x191F, // 191F ; UNKNOWN
6164 0x1920, // 1920..192B; LIMBU
6165 0x192C, // 192C..192F; UNKNOWN
6166 0x1930, // 1930..193B; LIMBU
6167 0x193C, // 193C..193F; UNKNOWN
6168 0x1940, // 1940 ; LIMBU
6169 0x1941, // 1941..1943; UNKNOWN
6170 0x1944, // 1944..194F; LIMBU
6171 0x1950, // 1950..196D; TAI_LE
6172 0x196E, // 196E..196F; UNKNOWN
6173 0x1970, // 1970..1974; TAI_LE
6174 0x1975, // 1975..197F; UNKNOWN
6175 0x1980, // 1980..19AB; NEW_TAI_LUE
6176 0x19AC, // 19AC..19AF; UNKNOWN
6177 0x19B0, // 19B0..19C9; NEW_TAI_LUE
6178 0x19CA, // 19CA..19CF; UNKNOWN
6179 0x19D0, // 19D0..19DA; NEW_TAI_LUE
6180 0x19DB, // 19DB..19DD; UNKNOWN
6181 0x19DE, // 19DE..19DF; NEW_TAI_LUE
6182 0x19E0, // 19E0..19FF; KHMER
6183 0x1A00, // 1A00..1A1B; BUGINESE
6184 0x1A1C, // 1A1C..1A1D; UNKNOWN
6185 0x1A1E, // 1A1E..1A1F; BUGINESE
6186 0x1A20, // 1A20..1A5E; TAI_THAM
6187 0x1A5F, // 1A5F ; UNKNOWN
6188 0x1A60, // 1A60..1A7C; TAI_THAM
6189 0x1A7D, // 1A7D..1A7E; UNKNOWN
6190 0x1A7F, // 1A7F..1A89; TAI_THAM
6191 0x1A8A, // 1A8A..1A8F; UNKNOWN
6192 0x1A90, // 1A90..1A99; TAI_THAM
6193 0x1A9A, // 1A9A..1A9F; UNKNOWN
6194 0x1AA0, // 1AA0..1AAD; TAI_THAM
6195 0x1AAE, // 1AAE..1AAF; UNKNOWN
6196 0x1AB0, // 1AB0..1ADD; INHERITED
6197 0x1ADE, // 1ADE..1ADF; UNKNOWN
6198 0x1AE0, // 1AE0..1AEB; INHERITED
6199 0x1AEC, // 1AEC..1AFF; UNKNOWN
6200 0x1B00, // 1B00..1B4C; BALINESE
6201 0x1B4D, // 1B4D ; UNKNOWN
6202 0x1B4E, // 1B4E..1B7F; BALINESE
6203 0x1B80, // 1B80..1BBF; SUNDANESE
6204 0x1BC0, // 1BC0..1BF3; BATAK
6205 0x1BF4, // 1BF4..1BFB; UNKNOWN
6206 0x1BFC, // 1BFC..1BFF; BATAK
6207 0x1C00, // 1C00..1C37; LEPCHA
6208 0x1C38, // 1C38..1C3A; UNKNOWN
6209 0x1C3B, // 1C3B..1C49; LEPCHA
6210 0x1C4A, // 1C4A..1C4C; UNKNOWN
6211 0x1C4D, // 1C4D..1C4F; LEPCHA
6212 0x1C50, // 1C50..1C7F; OL_CHIKI
6213 0x1C80, // 1C80..1C8A; CYRILLIC
6214 0x1C8B, // 1C8B..1C8F; UNKNOWN
6215 0x1C90, // 1C90..1CBA; GEORGIAN
6216 0x1CBB, // 1CBB..1CBC; UNKNOWN
6217 0x1CBD, // 1CBD..1CBF; GEORGIAN
6218 0x1CC0, // 1CC0..1CC7; SUNDANESE
6219 0x1CC8, // 1CC8..1CCF; UNKNOWN
6220 0x1CD0, // 1CD0..1CD2; INHERITED
6221 0x1CD3, // 1CD3 ; COMMON
6222 0x1CD4, // 1CD4..1CE0; INHERITED
6223 0x1CE1, // 1CE1 ; COMMON
6224 0x1CE2, // 1CE2..1CE8; INHERITED
6225 0x1CE9, // 1CE9..1CEC; COMMON
6226 0x1CED, // 1CED ; INHERITED
6227 0x1CEE, // 1CEE..1CF3; COMMON
6228 0x1CF4, // 1CF4 ; INHERITED
6229 0x1CF5, // 1CF5..1CF7; COMMON
6230 0x1CF8, // 1CF8..1CF9; INHERITED
6231 0x1CFA, // 1CFA ; COMMON
6232 0x1CFB, // 1CFB..1CFF; UNKNOWN
6233 0x1D00, // 1D00..1D25; LATIN
6234 0x1D26, // 1D26..1D2A; GREEK
6235 0x1D2B, // 1D2B ; CYRILLIC
6236 0x1D2C, // 1D2C..1D5C; LATIN
6237 0x1D5D, // 1D5D..1D61; GREEK
6238 0x1D62, // 1D62..1D65; LATIN
6239 0x1D66, // 1D66..1D6A; GREEK
6240 0x1D6B, // 1D6B..1D77; LATIN
6241 0x1D78, // 1D78 ; CYRILLIC
6242 0x1D79, // 1D79..1DBE; LATIN
6243 0x1DBF, // 1DBF ; GREEK
6244 0x1DC0, // 1DC0..1DFF; INHERITED
6245 0x1E00, // 1E00..1EFF; LATIN
6246 0x1F00, // 1F00..1F15; GREEK
6247 0x1F16, // 1F16..1F17; UNKNOWN
6248 0x1F18, // 1F18..1F1D; GREEK
6249 0x1F1E, // 1F1E..1F1F; UNKNOWN
6250 0x1F20, // 1F20..1F45; GREEK
6251 0x1F46, // 1F46..1F47; UNKNOWN
6252 0x1F48, // 1F48..1F4D; GREEK
6253 0x1F4E, // 1F4E..1F4F; UNKNOWN
6254 0x1F50, // 1F50..1F57; GREEK
6255 0x1F58, // 1F58 ; UNKNOWN
6256 0x1F59, // 1F59 ; GREEK
6257 0x1F5A, // 1F5A ; UNKNOWN
6258 0x1F5B, // 1F5B ; GREEK
6259 0x1F5C, // 1F5C ; UNKNOWN
6260 0x1F5D, // 1F5D ; GREEK
6261 0x1F5E, // 1F5E ; UNKNOWN
6262 0x1F5F, // 1F5F..1F7D; GREEK
6263 0x1F7E, // 1F7E..1F7F; UNKNOWN
6264 0x1F80, // 1F80..1FB4; GREEK
6265 0x1FB5, // 1FB5 ; UNKNOWN
6266 0x1FB6, // 1FB6..1FC4; GREEK
6267 0x1FC5, // 1FC5 ; UNKNOWN
6268 0x1FC6, // 1FC6..1FD3; GREEK
6269 0x1FD4, // 1FD4..1FD5; UNKNOWN
6270 0x1FD6, // 1FD6..1FDB; GREEK
6271 0x1FDC, // 1FDC ; UNKNOWN
6272 0x1FDD, // 1FDD..1FEF; GREEK
6273 0x1FF0, // 1FF0..1FF1; UNKNOWN
6274 0x1FF2, // 1FF2..1FF4; GREEK
6275 0x1FF5, // 1FF5 ; UNKNOWN
6276 0x1FF6, // 1FF6..1FFE; GREEK
6277 0x1FFF, // 1FFF ; UNKNOWN
6278 0x2000, // 2000..200B; COMMON
6279 0x200C, // 200C..200D; INHERITED
6280 0x200E, // 200E..2064; COMMON
6281 0x2065, // 2065 ; UNKNOWN
6282 0x2066, // 2066..2070; COMMON
6283 0x2071, // 2071 ; LATIN
6284 0x2072, // 2072..2073; UNKNOWN
6285 0x2074, // 2074..207E; COMMON
6286 0x207F, // 207F ; LATIN
6287 0x2080, // 2080..208E; COMMON
6288 0x208F, // 208F ; UNKNOWN
6289 0x2090, // 2090..209C; LATIN
6290 0x209D, // 209D..209F; UNKNOWN
6291 0x20A0, // 20A0..20C1; COMMON
6292 0x20C2, // 20C2..20CF; UNKNOWN
6293 0x20D0, // 20D0..20F0; INHERITED
6294 0x20F1, // 20F1..20FF; UNKNOWN
6295 0x2100, // 2100..2125; COMMON
6296 0x2126, // 2126 ; GREEK
6297 0x2127, // 2127..2129; COMMON
6298 0x212A, // 212A..212B; LATIN
6299 0x212C, // 212C..2131; COMMON
6300 0x2132, // 2132 ; LATIN
6301 0x2133, // 2133..214D; COMMON
6302 0x214E, // 214E ; LATIN
6303 0x214F, // 214F..215F; COMMON
6304 0x2160, // 2160..2188; LATIN
6305 0x2189, // 2189..218B; COMMON
6306 0x218C, // 218C..218F; UNKNOWN
6307 0x2190, // 2190..2429; COMMON
6308 0x242A, // 242A..243F; UNKNOWN
6309 0x2440, // 2440..244A; COMMON
6310 0x244B, // 244B..245F; UNKNOWN
6311 0x2460, // 2460..27FF; COMMON
6312 0x2800, // 2800..28FF; BRAILLE
6313 0x2900, // 2900..2B73; COMMON
6314 0x2B74, // 2B74..2B75; UNKNOWN
6315 0x2B76, // 2B76..2BFF; COMMON
6316 0x2C00, // 2C00..2C5F; GLAGOLITIC
6317 0x2C60, // 2C60..2C7F; LATIN
6318 0x2C80, // 2C80..2CF3; COPTIC
6319 0x2CF4, // 2CF4..2CF8; UNKNOWN
6320 0x2CF9, // 2CF9..2CFF; COPTIC
6321 0x2D00, // 2D00..2D25; GEORGIAN
6322 0x2D26, // 2D26 ; UNKNOWN
6323 0x2D27, // 2D27 ; GEORGIAN
6324 0x2D28, // 2D28..2D2C; UNKNOWN
6325 0x2D2D, // 2D2D ; GEORGIAN
6326 0x2D2E, // 2D2E..2D2F; UNKNOWN
6327 0x2D30, // 2D30..2D67; TIFINAGH
6328 0x2D68, // 2D68..2D6E; UNKNOWN
6329 0x2D6F, // 2D6F..2D70; TIFINAGH
6330 0x2D71, // 2D71..2D7E; UNKNOWN
6331 0x2D7F, // 2D7F ; TIFINAGH
6332 0x2D80, // 2D80..2D96; ETHIOPIC
6333 0x2D97, // 2D97..2D9F; UNKNOWN
6334 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6335 0x2DA7, // 2DA7 ; UNKNOWN
6336 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6337 0x2DAF, // 2DAF ; UNKNOWN
6338 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6339 0x2DB7, // 2DB7 ; UNKNOWN
6340 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6341 0x2DBF, // 2DBF ; UNKNOWN
6342 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6343 0x2DC7, // 2DC7 ; UNKNOWN
6344 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6345 0x2DCF, // 2DCF ; UNKNOWN
6346 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6347 0x2DD7, // 2DD7 ; UNKNOWN
6348 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6349 0x2DDF, // 2DDF ; UNKNOWN
6350 0x2DE0, // 2DE0..2DFF; CYRILLIC
6351 0x2E00, // 2E00..2E5D; COMMON
6352 0x2E5E, // 2E5E..2E7F; UNKNOWN
6353 0x2E80, // 2E80..2E99; HAN
6354 0x2E9A, // 2E9A ; UNKNOWN
6355 0x2E9B, // 2E9B..2EF3; HAN
6356 0x2EF4, // 2EF4..2EFF; UNKNOWN
6357 0x2F00, // 2F00..2FD5; HAN
6358 0x2FD6, // 2FD6..2FEF; UNKNOWN
6359 0x2FF0, // 2FF0..3004; COMMON
6360 0x3005, // 3005 ; HAN
6361 0x3006, // 3006 ; COMMON
6362 0x3007, // 3007 ; HAN
6363 0x3008, // 3008..3020; COMMON
6364 0x3021, // 3021..3029; HAN
6365 0x302A, // 302A..302D; INHERITED
6366 0x302E, // 302E..302F; HANGUL
6367 0x3030, // 3030..3037; COMMON
6368 0x3038, // 3038..303B; HAN
6369 0x303C, // 303C..303F; COMMON
6370 0x3040, // 3040 ; UNKNOWN
6371 0x3041, // 3041..3096; HIRAGANA
6372 0x3097, // 3097..3098; UNKNOWN
6373 0x3099, // 3099..309A; INHERITED
6374 0x309B, // 309B..309C; COMMON
6375 0x309D, // 309D..309F; HIRAGANA
6376 0x30A0, // 30A0 ; COMMON
6377 0x30A1, // 30A1..30FA; KATAKANA
6378 0x30FB, // 30FB..30FC; COMMON
6379 0x30FD, // 30FD..30FF; KATAKANA
6380 0x3100, // 3100..3104; UNKNOWN
6381 0x3105, // 3105..312F; BOPOMOFO
6382 0x3130, // 3130 ; UNKNOWN
6383 0x3131, // 3131..318E; HANGUL
6384 0x318F, // 318F ; UNKNOWN
6385 0x3190, // 3190..319F; COMMON
6386 0x31A0, // 31A0..31BF; BOPOMOFO
6387 0x31C0, // 31C0..31E5; COMMON
6388 0x31E6, // 31E6..31EE; UNKNOWN
6389 0x31EF, // 31EF ; COMMON
6390 0x31F0, // 31F0..31FF; KATAKANA
6391 0x3200, // 3200..321E; HANGUL
6392 0x321F, // 321F ; UNKNOWN
6393 0x3220, // 3220..325F; COMMON
6394 0x3260, // 3260..327E; HANGUL
6395 0x327F, // 327F..32CF; COMMON
6396 0x32D0, // 32D0..32FE; KATAKANA
6397 0x32FF, // 32FF ; COMMON
6398 0x3300, // 3300..3357; KATAKANA
6399 0x3358, // 3358..33FF; COMMON
6400 0x3400, // 3400..4DBF; HAN
6401 0x4DC0, // 4DC0..4DFF; COMMON
6402 0x4E00, // 4E00..9FFF; HAN
6403 0xA000, // A000..A48C; YI
6404 0xA48D, // A48D..A48F; UNKNOWN
6405 0xA490, // A490..A4C6; YI
6406 0xA4C7, // A4C7..A4CF; UNKNOWN
6407 0xA4D0, // A4D0..A4FF; LISU
6408 0xA500, // A500..A62B; VAI
6409 0xA62C, // A62C..A63F; UNKNOWN
6410 0xA640, // A640..A69F; CYRILLIC
6411 0xA6A0, // A6A0..A6F7; BAMUM
6412 0xA6F8, // A6F8..A6FF; UNKNOWN
6413 0xA700, // A700..A721; COMMON
6414 0xA722, // A722..A787; LATIN
6415 0xA788, // A788..A78A; COMMON
6416 0xA78B, // A78B..A7DC; LATIN
6417 0xA7DD, // A7DD..A7F0; UNKNOWN
6418 0xA7F1, // A7F1..A7FF; LATIN
6419 0xA800, // A800..A82C; SYLOTI_NAGRI
6420 0xA82D, // A82D..A82F; UNKNOWN
6421 0xA830, // A830..A839; COMMON
6422 0xA83A, // A83A..A83F; UNKNOWN
6423 0xA840, // A840..A877; PHAGS_PA
6424 0xA878, // A878..A87F; UNKNOWN
6425 0xA880, // A880..A8C5; SAURASHTRA
6426 0xA8C6, // A8C6..A8CD; UNKNOWN
6427 0xA8CE, // A8CE..A8D9; SAURASHTRA
6428 0xA8DA, // A8DA..A8DF; UNKNOWN
6429 0xA8E0, // A8E0..A8FF; DEVANAGARI
6430 0xA900, // A900..A92D; KAYAH_LI
6431 0xA92E, // A92E ; COMMON
6432 0xA92F, // A92F ; KAYAH_LI
6433 0xA930, // A930..A953; REJANG
6434 0xA954, // A954..A95E; UNKNOWN
6435 0xA95F, // A95F ; REJANG
6436 0xA960, // A960..A97C; HANGUL
6437 0xA97D, // A97D..A97F; UNKNOWN
6438 0xA980, // A980..A9CD; JAVANESE
6439 0xA9CE, // A9CE ; UNKNOWN
6440 0xA9CF, // A9CF ; COMMON
6441 0xA9D0, // A9D0..A9D9; JAVANESE
6442 0xA9DA, // A9DA..A9DD; UNKNOWN
6443 0xA9DE, // A9DE..A9DF; JAVANESE
6444 0xA9E0, // A9E0..A9FE; MYANMAR
6445 0xA9FF, // A9FF ; UNKNOWN
6446 0xAA00, // AA00..AA36; CHAM
6447 0xAA37, // AA37..AA3F; UNKNOWN
6448 0xAA40, // AA40..AA4D; CHAM
6449 0xAA4E, // AA4E..AA4F; UNKNOWN
6450 0xAA50, // AA50..AA59; CHAM
6451 0xAA5A, // AA5A..AA5B; UNKNOWN
6452 0xAA5C, // AA5C..AA5F; CHAM
6453 0xAA60, // AA60..AA7F; MYANMAR
6454 0xAA80, // AA80..AAC2; TAI_VIET
6455 0xAAC3, // AAC3..AADA; UNKNOWN
6456 0xAADB, // AADB..AADF; TAI_VIET
6457 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6458 0xAAF7, // AAF7..AB00; UNKNOWN
6459 0xAB01, // AB01..AB06; ETHIOPIC
6460 0xAB07, // AB07..AB08; UNKNOWN
6461 0xAB09, // AB09..AB0E; ETHIOPIC
6462 0xAB0F, // AB0F..AB10; UNKNOWN
6463 0xAB11, // AB11..AB16; ETHIOPIC
6464 0xAB17, // AB17..AB1F; UNKNOWN
6465 0xAB20, // AB20..AB26; ETHIOPIC
6466 0xAB27, // AB27 ; UNKNOWN
6467 0xAB28, // AB28..AB2E; ETHIOPIC
6468 0xAB2F, // AB2F ; UNKNOWN
6469 0xAB30, // AB30..AB5A; LATIN
6470 0xAB5B, // AB5B ; COMMON
6471 0xAB5C, // AB5C..AB64; LATIN
6472 0xAB65, // AB65 ; GREEK
6473 0xAB66, // AB66..AB69; LATIN
6474 0xAB6A, // AB6A..AB6B; COMMON
6475 0xAB6C, // AB6C..AB6F; UNKNOWN
6476 0xAB70, // AB70..ABBF; CHEROKEE
6477 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6478 0xABEE, // ABEE..ABEF; UNKNOWN
6479 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6480 0xABFA, // ABFA..ABFF; UNKNOWN
6481 0xAC00, // AC00..D7A3; HANGUL
6482 0xD7A4, // D7A4..D7AF; UNKNOWN
6483 0xD7B0, // D7B0..D7C6; HANGUL
6484 0xD7C7, // D7C7..D7CA; UNKNOWN
6485 0xD7CB, // D7CB..D7FB; HANGUL
6486 0xD7FC, // D7FC..F8FF; UNKNOWN
6487 0xF900, // F900..FA6D; HAN
6488 0xFA6E, // FA6E..FA6F; UNKNOWN
6489 0xFA70, // FA70..FAD9; HAN
6490 0xFADA, // FADA..FAFF; UNKNOWN
6491 0xFB00, // FB00..FB06; LATIN
6492 0xFB07, // FB07..FB12; UNKNOWN
6493 0xFB13, // FB13..FB17; ARMENIAN
6494 0xFB18, // FB18..FB1C; UNKNOWN
6495 0xFB1D, // FB1D..FB36; HEBREW
6496 0xFB37, // FB37 ; UNKNOWN
6497 0xFB38, // FB38..FB3C; HEBREW
6498 0xFB3D, // FB3D ; UNKNOWN
6499 0xFB3E, // FB3E ; HEBREW
6500 0xFB3F, // FB3F ; UNKNOWN
6501 0xFB40, // FB40..FB41; HEBREW
6502 0xFB42, // FB42 ; UNKNOWN
6503 0xFB43, // FB43..FB44; HEBREW
6504 0xFB45, // FB45 ; UNKNOWN
6505 0xFB46, // FB46..FB4F; HEBREW
6506 0xFB50, // FB50..FD3D; ARABIC
6507 0xFD3E, // FD3E..FD3F; COMMON
6508 0xFD40, // FD40..FDCF; ARABIC
6509 0xFDD0, // FDD0..FDEF; UNKNOWN
6510 0xFDF0, // FDF0..FDFF; ARABIC
6511 0xFE00, // FE00..FE0F; INHERITED
6512 0xFE10, // FE10..FE19; COMMON
6513 0xFE1A, // FE1A..FE1F; UNKNOWN
6514 0xFE20, // FE20..FE2D; INHERITED
6515 0xFE2E, // FE2E..FE2F; CYRILLIC
6516 0xFE30, // FE30..FE52; COMMON
6517 0xFE53, // FE53 ; UNKNOWN
6518 0xFE54, // FE54..FE66; COMMON
6519 0xFE67, // FE67 ; UNKNOWN
6520 0xFE68, // FE68..FE6B; COMMON
6521 0xFE6C, // FE6C..FE6F; UNKNOWN
6522 0xFE70, // FE70..FE74; ARABIC
6523 0xFE75, // FE75 ; UNKNOWN
6524 0xFE76, // FE76..FEFC; ARABIC
6525 0xFEFD, // FEFD..FEFE; UNKNOWN
6526 0xFEFF, // FEFF ; COMMON
6527 0xFF00, // FF00 ; UNKNOWN
6528 0xFF01, // FF01..FF20; COMMON
6529 0xFF21, // FF21..FF3A; LATIN
6530 0xFF3B, // FF3B..FF40; COMMON
6531 0xFF41, // FF41..FF5A; LATIN
6532 0xFF5B, // FF5B..FF65; COMMON
6533 0xFF66, // FF66..FF6F; KATAKANA
6534 0xFF70, // FF70 ; COMMON
6535 0xFF71, // FF71..FF9D; KATAKANA
6536 0xFF9E, // FF9E..FF9F; COMMON
6537 0xFFA0, // FFA0..FFBE; HANGUL
6538 0xFFBF, // FFBF..FFC1; UNKNOWN
6539 0xFFC2, // FFC2..FFC7; HANGUL
6540 0xFFC8, // FFC8..FFC9; UNKNOWN
6541 0xFFCA, // FFCA..FFCF; HANGUL
6542 0xFFD0, // FFD0..FFD1; UNKNOWN
6543 0xFFD2, // FFD2..FFD7; HANGUL
6544 0xFFD8, // FFD8..FFD9; UNKNOWN
6545 0xFFDA, // FFDA..FFDC; HANGUL
6546 0xFFDD, // FFDD..FFDF; UNKNOWN
6547 0xFFE0, // FFE0..FFE6; COMMON
6548 0xFFE7, // FFE7 ; UNKNOWN
6549 0xFFE8, // FFE8..FFEE; COMMON
6550 0xFFEF, // FFEF..FFF8; UNKNOWN
6551 0xFFF9, // FFF9..FFFD; COMMON
6552 0xFFFE, // FFFE..FFFF; UNKNOWN
6553 0x10000, // 10000..1000B; LINEAR_B
6554 0x1000C, // 1000C ; UNKNOWN
6555 0x1000D, // 1000D..10026; LINEAR_B
6556 0x10027, // 10027 ; UNKNOWN
6557 0x10028, // 10028..1003A; LINEAR_B
6558 0x1003B, // 1003B ; UNKNOWN
6559 0x1003C, // 1003C..1003D; LINEAR_B
6560 0x1003E, // 1003E ; UNKNOWN
6561 0x1003F, // 1003F..1004D; LINEAR_B
6562 0x1004E, // 1004E..1004F; UNKNOWN
6563 0x10050, // 10050..1005D; LINEAR_B
6564 0x1005E, // 1005E..1007F; UNKNOWN
6565 0x10080, // 10080..100FA; LINEAR_B
6566 0x100FB, // 100FB..100FF; UNKNOWN
6567 0x10100, // 10100..10102; COMMON
6568 0x10103, // 10103..10106; UNKNOWN
6569 0x10107, // 10107..10133; COMMON
6570 0x10134, // 10134..10136; UNKNOWN
6571 0x10137, // 10137..1013F; COMMON
6572 0x10140, // 10140..1018E; GREEK
6573 0x1018F, // 1018F ; UNKNOWN
6574 0x10190, // 10190..1019C; COMMON
6575 0x1019D, // 1019D..1019F; UNKNOWN
6576 0x101A0, // 101A0 ; GREEK
6577 0x101A1, // 101A1..101CF; UNKNOWN
6578 0x101D0, // 101D0..101FC; COMMON
6579 0x101FD, // 101FD ; INHERITED
6580 0x101FE, // 101FE..1027F; UNKNOWN
6581 0x10280, // 10280..1029C; LYCIAN
6582 0x1029D, // 1029D..1029F; UNKNOWN
6583 0x102A0, // 102A0..102D0; CARIAN
6584 0x102D1, // 102D1..102DF; UNKNOWN
6585 0x102E0, // 102E0 ; INHERITED
6586 0x102E1, // 102E1..102FB; COMMON
6587 0x102FC, // 102FC..102FF; UNKNOWN
6588 0x10300, // 10300..10323; OLD_ITALIC
6589 0x10324, // 10324..1032C; UNKNOWN
6590 0x1032D, // 1032D..1032F; OLD_ITALIC
6591 0x10330, // 10330..1034A; GOTHIC
6592 0x1034B, // 1034B..1034F; UNKNOWN
6593 0x10350, // 10350..1037A; OLD_PERMIC
6594 0x1037B, // 1037B..1037F; UNKNOWN
6595 0x10380, // 10380..1039D; UGARITIC
6596 0x1039E, // 1039E ; UNKNOWN
6597 0x1039F, // 1039F ; UGARITIC
6598 0x103A0, // 103A0..103C3; OLD_PERSIAN
6599 0x103C4, // 103C4..103C7; UNKNOWN
6600 0x103C8, // 103C8..103D5; OLD_PERSIAN
6601 0x103D6, // 103D6..103FF; UNKNOWN
6602 0x10400, // 10400..1044F; DESERET
6603 0x10450, // 10450..1047F; SHAVIAN
6604 0x10480, // 10480..1049D; OSMANYA
6605 0x1049E, // 1049E..1049F; UNKNOWN
6606 0x104A0, // 104A0..104A9; OSMANYA
6607 0x104AA, // 104AA..104AF; UNKNOWN
6608 0x104B0, // 104B0..104D3; OSAGE
6609 0x104D4, // 104D4..104D7; UNKNOWN
6610 0x104D8, // 104D8..104FB; OSAGE
6611 0x104FC, // 104FC..104FF; UNKNOWN
6612 0x10500, // 10500..10527; ELBASAN
6613 0x10528, // 10528..1052F; UNKNOWN
6614 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6615 0x10564, // 10564..1056E; UNKNOWN
6616 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6617 0x10570, // 10570..1057A; VITHKUQI
6618 0x1057B, // 1057B ; UNKNOWN
6619 0x1057C, // 1057C..1058A; VITHKUQI
6620 0x1058B, // 1058B ; UNKNOWN
6621 0x1058C, // 1058C..10592; VITHKUQI
6622 0x10593, // 10593 ; UNKNOWN
6623 0x10594, // 10594..10595; VITHKUQI
6624 0x10596, // 10596 ; UNKNOWN
6625 0x10597, // 10597..105A1; VITHKUQI
6626 0x105A2, // 105A2 ; UNKNOWN
6627 0x105A3, // 105A3..105B1; VITHKUQI
6628 0x105B2, // 105B2 ; UNKNOWN
6629 0x105B3, // 105B3..105B9; VITHKUQI
6630 0x105BA, // 105BA ; UNKNOWN
6631 0x105BB, // 105BB..105BC; VITHKUQI
6632 0x105BD, // 105BD..105BF; UNKNOWN
6633 0x105C0, // 105C0..105F3; TODHRI
6634 0x105F4, // 105F4..105FF; UNKNOWN
6635 0x10600, // 10600..10736; LINEAR_A
6636 0x10737, // 10737..1073F; UNKNOWN
6637 0x10740, // 10740..10755; LINEAR_A
6638 0x10756, // 10756..1075F; UNKNOWN
6639 0x10760, // 10760..10767; LINEAR_A
6640 0x10768, // 10768..1077F; UNKNOWN
6641 0x10780, // 10780..10785; LATIN
6642 0x10786, // 10786 ; UNKNOWN
6643 0x10787, // 10787..107B0; LATIN
6644 0x107B1, // 107B1 ; UNKNOWN
6645 0x107B2, // 107B2..107BA; LATIN
6646 0x107BB, // 107BB..107FF; UNKNOWN
6647 0x10800, // 10800..10805; CYPRIOT
6648 0x10806, // 10806..10807; UNKNOWN
6649 0x10808, // 10808 ; CYPRIOT
6650 0x10809, // 10809 ; UNKNOWN
6651 0x1080A, // 1080A..10835; CYPRIOT
6652 0x10836, // 10836 ; UNKNOWN
6653 0x10837, // 10837..10838; CYPRIOT
6654 0x10839, // 10839..1083B; UNKNOWN
6655 0x1083C, // 1083C ; CYPRIOT
6656 0x1083D, // 1083D..1083E; UNKNOWN
6657 0x1083F, // 1083F ; CYPRIOT
6658 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6659 0x10856, // 10856 ; UNKNOWN
6660 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6661 0x10860, // 10860..1087F; PALMYRENE
6662 0x10880, // 10880..1089E; NABATAEAN
6663 0x1089F, // 1089F..108A6; UNKNOWN
6664 0x108A7, // 108A7..108AF; NABATAEAN
6665 0x108B0, // 108B0..108DF; UNKNOWN
6666 0x108E0, // 108E0..108F2; HATRAN
6667 0x108F3, // 108F3 ; UNKNOWN
6668 0x108F4, // 108F4..108F5; HATRAN
6669 0x108F6, // 108F6..108FA; UNKNOWN
6670 0x108FB, // 108FB..108FF; HATRAN
6671 0x10900, // 10900..1091B; PHOENICIAN
6672 0x1091C, // 1091C..1091E; UNKNOWN
6673 0x1091F, // 1091F ; PHOENICIAN
6674 0x10920, // 10920..10939; LYDIAN
6675 0x1093A, // 1093A..1093E; UNKNOWN
6676 0x1093F, // 1093F ; LYDIAN
6677 0x10940, // 10940..10959; SIDETIC
6678 0x1095A, // 1095A..1097F; UNKNOWN
6679 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6680 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6681 0x109B8, // 109B8..109BB; UNKNOWN
6682 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6683 0x109D0, // 109D0..109D1; UNKNOWN
6684 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6685 0x10A00, // 10A00..10A03; KHAROSHTHI
6686 0x10A04, // 10A04 ; UNKNOWN
6687 0x10A05, // 10A05..10A06; KHAROSHTHI
6688 0x10A07, // 10A07..10A0B; UNKNOWN
6689 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6690 0x10A14, // 10A14 ; UNKNOWN
6691 0x10A15, // 10A15..10A17; KHAROSHTHI
6692 0x10A18, // 10A18 ; UNKNOWN
6693 0x10A19, // 10A19..10A35; KHAROSHTHI
6694 0x10A36, // 10A36..10A37; UNKNOWN
6695 0x10A38, // 10A38..10A3A; KHAROSHTHI
6696 0x10A3B, // 10A3B..10A3E; UNKNOWN
6697 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6698 0x10A49, // 10A49..10A4F; UNKNOWN
6699 0x10A50, // 10A50..10A58; KHAROSHTHI
6700 0x10A59, // 10A59..10A5F; UNKNOWN
6701 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6702 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6703 0x10AA0, // 10AA0..10ABF; UNKNOWN
6704 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6705 0x10AE7, // 10AE7..10AEA; UNKNOWN
6706 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6707 0x10AF7, // 10AF7..10AFF; UNKNOWN
6708 0x10B00, // 10B00..10B35; AVESTAN
6709 0x10B36, // 10B36..10B38; UNKNOWN
6710 0x10B39, // 10B39..10B3F; AVESTAN
6711 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6712 0x10B56, // 10B56..10B57; UNKNOWN
6713 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6714 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6715 0x10B73, // 10B73..10B77; UNKNOWN
6716 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6717 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6718 0x10B92, // 10B92..10B98; UNKNOWN
6719 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6720 0x10B9D, // 10B9D..10BA8; UNKNOWN
6721 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6722 0x10BB0, // 10BB0..10BFF; UNKNOWN
6723 0x10C00, // 10C00..10C48; OLD_TURKIC
6724 0x10C49, // 10C49..10C7F; UNKNOWN
6725 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6726 0x10CB3, // 10CB3..10CBF; UNKNOWN
6727 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6728 0x10CF3, // 10CF3..10CF9; UNKNOWN
6729 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6730 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6731 0x10D28, // 10D28..10D2F; UNKNOWN
6732 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6733 0x10D3A, // 10D3A..10D3F; UNKNOWN
6734 0x10D40, // 10D40..10D65; GARAY
6735 0x10D66, // 10D66..10D68; UNKNOWN
6736 0x10D69, // 10D69..10D85; GARAY
6737 0x10D86, // 10D86..10D8D; UNKNOWN
6738 0x10D8E, // 10D8E..10D8F; GARAY
6739 0x10D90, // 10D90..10E5F; UNKNOWN
6740 0x10E60, // 10E60..10E7E; ARABIC
6741 0x10E7F, // 10E7F ; UNKNOWN
6742 0x10E80, // 10E80..10EA9; YEZIDI
6743 0x10EAA, // 10EAA ; UNKNOWN
6744 0x10EAB, // 10EAB..10EAD; YEZIDI
6745 0x10EAE, // 10EAE..10EAF; UNKNOWN
6746 0x10EB0, // 10EB0..10EB1; YEZIDI
6747 0x10EB2, // 10EB2..10EC1; UNKNOWN
6748 0x10EC2, // 10EC2..10EC7; ARABIC
6749 0x10EC8, // 10EC8..10ECF; UNKNOWN
6750 0x10ED0, // 10ED0..10ED8; ARABIC
6751 0x10ED9, // 10ED9..10EF9; UNKNOWN
6752 0x10EFA, // 10EFA..10EFF; ARABIC
6753 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6754 0x10F28, // 10F28..10F2F; UNKNOWN
6755 0x10F30, // 10F30..10F59; SOGDIAN
6756 0x10F5A, // 10F5A..10F6F; UNKNOWN
6757 0x10F70, // 10F70..10F89; OLD_UYGHUR
6758 0x10F8A, // 10F8A..10FAF; UNKNOWN
6759 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6760 0x10FCC, // 10FCC..10FDF; UNKNOWN
6761 0x10FE0, // 10FE0..10FF6; ELYMAIC
6762 0x10FF7, // 10FF7..10FFF; UNKNOWN
6763 0x11000, // 11000..1104D; BRAHMI
6764 0x1104E, // 1104E..11051; UNKNOWN
6765 0x11052, // 11052..11075; BRAHMI
6766 0x11076, // 11076..1107E; UNKNOWN
6767 0x1107F, // 1107F ; BRAHMI
6768 0x11080, // 11080..110C2; KAITHI
6769 0x110C3, // 110C3..110CC; UNKNOWN
6770 0x110CD, // 110CD ; KAITHI
6771 0x110CE, // 110CE..110CF; UNKNOWN
6772 0x110D0, // 110D0..110E8; SORA_SOMPENG
6773 0x110E9, // 110E9..110EF; UNKNOWN
6774 0x110F0, // 110F0..110F9; SORA_SOMPENG
6775 0x110FA, // 110FA..110FF; UNKNOWN
6776 0x11100, // 11100..11134; CHAKMA
6777 0x11135, // 11135 ; UNKNOWN
6778 0x11136, // 11136..11147; CHAKMA
6779 0x11148, // 11148..1114F; UNKNOWN
6780 0x11150, // 11150..11176; MAHAJANI
6781 0x11177, // 11177..1117F; UNKNOWN
6782 0x11180, // 11180..111DF; SHARADA
6783 0x111E0, // 111E0 ; UNKNOWN
6784 0x111E1, // 111E1..111F4; SINHALA
6785 0x111F5, // 111F5..111FF; UNKNOWN
6786 0x11200, // 11200..11211; KHOJKI
6787 0x11212, // 11212 ; UNKNOWN
6788 0x11213, // 11213..11241; KHOJKI
6789 0x11242, // 11242..1127F; UNKNOWN
6790 0x11280, // 11280..11286; MULTANI
6791 0x11287, // 11287 ; UNKNOWN
6792 0x11288, // 11288 ; MULTANI
6793 0x11289, // 11289 ; UNKNOWN
6794 0x1128A, // 1128A..1128D; MULTANI
6795 0x1128E, // 1128E ; UNKNOWN
6796 0x1128F, // 1128F..1129D; MULTANI
6797 0x1129E, // 1129E ; UNKNOWN
6798 0x1129F, // 1129F..112A9; MULTANI
6799 0x112AA, // 112AA..112AF; UNKNOWN
6800 0x112B0, // 112B0..112EA; KHUDAWADI
6801 0x112EB, // 112EB..112EF; UNKNOWN
6802 0x112F0, // 112F0..112F9; KHUDAWADI
6803 0x112FA, // 112FA..112FF; UNKNOWN
6804 0x11300, // 11300..11303; GRANTHA
6805 0x11304, // 11304 ; UNKNOWN
6806 0x11305, // 11305..1130C; GRANTHA
6807 0x1130D, // 1130D..1130E; UNKNOWN
6808 0x1130F, // 1130F..11310; GRANTHA
6809 0x11311, // 11311..11312; UNKNOWN
6810 0x11313, // 11313..11328; GRANTHA
6811 0x11329, // 11329 ; UNKNOWN
6812 0x1132A, // 1132A..11330; GRANTHA
6813 0x11331, // 11331 ; UNKNOWN
6814 0x11332, // 11332..11333; GRANTHA
6815 0x11334, // 11334 ; UNKNOWN
6816 0x11335, // 11335..11339; GRANTHA
6817 0x1133A, // 1133A ; UNKNOWN
6818 0x1133B, // 1133B ; INHERITED
6819 0x1133C, // 1133C..11344; GRANTHA
6820 0x11345, // 11345..11346; UNKNOWN
6821 0x11347, // 11347..11348; GRANTHA
6822 0x11349, // 11349..1134A; UNKNOWN
6823 0x1134B, // 1134B..1134D; GRANTHA
6824 0x1134E, // 1134E..1134F; UNKNOWN
6825 0x11350, // 11350 ; GRANTHA
6826 0x11351, // 11351..11356; UNKNOWN
6827 0x11357, // 11357 ; GRANTHA
6828 0x11358, // 11358..1135C; UNKNOWN
6829 0x1135D, // 1135D..11363; GRANTHA
6830 0x11364, // 11364..11365; UNKNOWN
6831 0x11366, // 11366..1136C; GRANTHA
6832 0x1136D, // 1136D..1136F; UNKNOWN
6833 0x11370, // 11370..11374; GRANTHA
6834 0x11375, // 11375..1137F; UNKNOWN
6835 0x11380, // 11380..11389; TULU_TIGALARI
6836 0x1138A, // 1138A ; UNKNOWN
6837 0x1138B, // 1138B ; TULU_TIGALARI
6838 0x1138C, // 1138C..1138D; UNKNOWN
6839 0x1138E, // 1138E ; TULU_TIGALARI
6840 0x1138F, // 1138F ; UNKNOWN
6841 0x11390, // 11390..113B5; TULU_TIGALARI
6842 0x113B6, // 113B6 ; UNKNOWN
6843 0x113B7, // 113B7..113C0; TULU_TIGALARI
6844 0x113C1, // 113C1 ; UNKNOWN
6845 0x113C2, // 113C2 ; TULU_TIGALARI
6846 0x113C3, // 113C3..113C4; UNKNOWN
6847 0x113C5, // 113C5 ; TULU_TIGALARI
6848 0x113C6, // 113C6 ; UNKNOWN
6849 0x113C7, // 113C7..113CA; TULU_TIGALARI
6850 0x113CB, // 113CB ; UNKNOWN
6851 0x113CC, // 113CC..113D5; TULU_TIGALARI
6852 0x113D6, // 113D6 ; UNKNOWN
6853 0x113D7, // 113D7..113D8; TULU_TIGALARI
6854 0x113D9, // 113D9..113E0; UNKNOWN
6855 0x113E1, // 113E1..113E2; TULU_TIGALARI
6856 0x113E3, // 113E3..113FF; UNKNOWN
6857 0x11400, // 11400..1145B; NEWA
6858 0x1145C, // 1145C ; UNKNOWN
6859 0x1145D, // 1145D..11461; NEWA
6860 0x11462, // 11462..1147F; UNKNOWN
6861 0x11480, // 11480..114C7; TIRHUTA
6862 0x114C8, // 114C8..114CF; UNKNOWN
6863 0x114D0, // 114D0..114D9; TIRHUTA
6864 0x114DA, // 114DA..1157F; UNKNOWN
6865 0x11580, // 11580..115B5; SIDDHAM
6866 0x115B6, // 115B6..115B7; UNKNOWN
6867 0x115B8, // 115B8..115DD; SIDDHAM
6868 0x115DE, // 115DE..115FF; UNKNOWN
6869 0x11600, // 11600..11644; MODI
6870 0x11645, // 11645..1164F; UNKNOWN
6871 0x11650, // 11650..11659; MODI
6872 0x1165A, // 1165A..1165F; UNKNOWN
6873 0x11660, // 11660..1166C; MONGOLIAN
6874 0x1166D, // 1166D..1167F; UNKNOWN
6875 0x11680, // 11680..116B9; TAKRI
6876 0x116BA, // 116BA..116BF; UNKNOWN
6877 0x116C0, // 116C0..116C9; TAKRI
6878 0x116CA, // 116CA..116CF; UNKNOWN
6879 0x116D0, // 116D0..116E3; MYANMAR
6880 0x116E4, // 116E4..116FF; UNKNOWN
6881 0x11700, // 11700..1171A; AHOM
6882 0x1171B, // 1171B..1171C; UNKNOWN
6883 0x1171D, // 1171D..1172B; AHOM
6884 0x1172C, // 1172C..1172F; UNKNOWN
6885 0x11730, // 11730..11746; AHOM
6886 0x11747, // 11747..117FF; UNKNOWN
6887 0x11800, // 11800..1183B; DOGRA
6888 0x1183C, // 1183C..1189F; UNKNOWN
6889 0x118A0, // 118A0..118F2; WARANG_CITI
6890 0x118F3, // 118F3..118FE; UNKNOWN
6891 0x118FF, // 118FF ; WARANG_CITI
6892 0x11900, // 11900..11906; DIVES_AKURU
6893 0x11907, // 11907..11908; UNKNOWN
6894 0x11909, // 11909 ; DIVES_AKURU
6895 0x1190A, // 1190A..1190B; UNKNOWN
6896 0x1190C, // 1190C..11913; DIVES_AKURU
6897 0x11914, // 11914 ; UNKNOWN
6898 0x11915, // 11915..11916; DIVES_AKURU
6899 0x11917, // 11917 ; UNKNOWN
6900 0x11918, // 11918..11935; DIVES_AKURU
6901 0x11936, // 11936 ; UNKNOWN
6902 0x11937, // 11937..11938; DIVES_AKURU
6903 0x11939, // 11939..1193A; UNKNOWN
6904 0x1193B, // 1193B..11946; DIVES_AKURU
6905 0x11947, // 11947..1194F; UNKNOWN
6906 0x11950, // 11950..11959; DIVES_AKURU
6907 0x1195A, // 1195A..1199F; UNKNOWN
6908 0x119A0, // 119A0..119A7; NANDINAGARI
6909 0x119A8, // 119A8..119A9; UNKNOWN
6910 0x119AA, // 119AA..119D7; NANDINAGARI
6911 0x119D8, // 119D8..119D9; UNKNOWN
6912 0x119DA, // 119DA..119E4; NANDINAGARI
6913 0x119E5, // 119E5..119FF; UNKNOWN
6914 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6915 0x11A48, // 11A48..11A4F; UNKNOWN
6916 0x11A50, // 11A50..11AA2; SOYOMBO
6917 0x11AA3, // 11AA3..11AAF; UNKNOWN
6918 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6919 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6920 0x11AF9, // 11AF9..11AFF; UNKNOWN
6921 0x11B00, // 11B00..11B09; DEVANAGARI
6922 0x11B0A, // 11B0A..11B5F; UNKNOWN
6923 0x11B60, // 11B60..11B67; SHARADA
6924 0x11B68, // 11B68..11BBF; UNKNOWN
6925 0x11BC0, // 11BC0..11BE1; SUNUWAR
6926 0x11BE2, // 11BE2..11BEF; UNKNOWN
6927 0x11BF0, // 11BF0..11BF9; SUNUWAR
6928 0x11BFA, // 11BFA..11BFF; UNKNOWN
6929 0x11C00, // 11C00..11C08; BHAIKSUKI
6930 0x11C09, // 11C09 ; UNKNOWN
6931 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6932 0x11C37, // 11C37 ; UNKNOWN
6933 0x11C38, // 11C38..11C45; BHAIKSUKI
6934 0x11C46, // 11C46..11C4F; UNKNOWN
6935 0x11C50, // 11C50..11C6C; BHAIKSUKI
6936 0x11C6D, // 11C6D..11C6F; UNKNOWN
6937 0x11C70, // 11C70..11C8F; MARCHEN
6938 0x11C90, // 11C90..11C91; UNKNOWN
6939 0x11C92, // 11C92..11CA7; MARCHEN
6940 0x11CA8, // 11CA8 ; UNKNOWN
6941 0x11CA9, // 11CA9..11CB6; MARCHEN
6942 0x11CB7, // 11CB7..11CFF; UNKNOWN
6943 0x11D00, // 11D00..11D06; MASARAM_GONDI
6944 0x11D07, // 11D07 ; UNKNOWN
6945 0x11D08, // 11D08..11D09; MASARAM_GONDI
6946 0x11D0A, // 11D0A ; UNKNOWN
6947 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6948 0x11D37, // 11D37..11D39; UNKNOWN
6949 0x11D3A, // 11D3A ; MASARAM_GONDI
6950 0x11D3B, // 11D3B ; UNKNOWN
6951 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6952 0x11D3E, // 11D3E ; UNKNOWN
6953 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6954 0x11D48, // 11D48..11D4F; UNKNOWN
6955 0x11D50, // 11D50..11D59; MASARAM_GONDI
6956 0x11D5A, // 11D5A..11D5F; UNKNOWN
6957 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6958 0x11D66, // 11D66 ; UNKNOWN
6959 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6960 0x11D69, // 11D69 ; UNKNOWN
6961 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6962 0x11D8F, // 11D8F ; UNKNOWN
6963 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6964 0x11D92, // 11D92 ; UNKNOWN
6965 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6966 0x11D99, // 11D99..11D9F; UNKNOWN
6967 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6968 0x11DAA, // 11DAA..11DAF; UNKNOWN
6969 0x11DB0, // 11DB0..11DDB; TOLONG_SIKI
6970 0x11DDC, // 11DDC..11DDF; UNKNOWN
6971 0x11DE0, // 11DE0..11DE9; TOLONG_SIKI
6972 0x11DEA, // 11DEA..11EDF; UNKNOWN
6973 0x11EE0, // 11EE0..11EF8; MAKASAR
6974 0x11EF9, // 11EF9..11EFF; UNKNOWN
6975 0x11F00, // 11F00..11F10; KAWI
6976 0x11F11, // 11F11 ; UNKNOWN
6977 0x11F12, // 11F12..11F3A; KAWI
6978 0x11F3B, // 11F3B..11F3D; UNKNOWN
6979 0x11F3E, // 11F3E..11F5A; KAWI
6980 0x11F5B, // 11F5B..11FAF; UNKNOWN
6981 0x11FB0, // 11FB0 ; LISU
6982 0x11FB1, // 11FB1..11FBF; UNKNOWN
6983 0x11FC0, // 11FC0..11FF1; TAMIL
6984 0x11FF2, // 11FF2..11FFE; UNKNOWN
6985 0x11FFF, // 11FFF ; TAMIL
6986 0x12000, // 12000..12399; CUNEIFORM
6987 0x1239A, // 1239A..123FF; UNKNOWN
6988 0x12400, // 12400..1246E; CUNEIFORM
6989 0x1246F, // 1246F ; UNKNOWN
6990 0x12470, // 12470..12474; CUNEIFORM
6991 0x12475, // 12475..1247F; UNKNOWN
6992 0x12480, // 12480..12543; CUNEIFORM
6993 0x12544, // 12544..12F8F; UNKNOWN
6994 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6995 0x12FF3, // 12FF3..12FFF; UNKNOWN
6996 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6997 0x13456, // 13456..1345F; UNKNOWN
6998 0x13460, // 13460..143FA; EGYPTIAN_HIEROGLYPHS
6999 0x143FB, // 143FB..143FF; UNKNOWN
7000 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
7001 0x14647, // 14647..160FF; UNKNOWN
7002 0x16100, // 16100..16139; GURUNG_KHEMA
7003 0x1613A, // 1613A..167FF; UNKNOWN
7004 0x16800, // 16800..16A38; BAMUM
7005 0x16A39, // 16A39..16A3F; UNKNOWN
7006 0x16A40, // 16A40..16A5E; MRO
7007 0x16A5F, // 16A5F ; UNKNOWN
7008 0x16A60, // 16A60..16A69; MRO
7009 0x16A6A, // 16A6A..16A6D; UNKNOWN
7010 0x16A6E, // 16A6E..16A6F; MRO
7011 0x16A70, // 16A70..16ABE; TANGSA
7012 0x16ABF, // 16ABF ; UNKNOWN
7013 0x16AC0, // 16AC0..16AC9; TANGSA
7014 0x16ACA, // 16ACA..16ACF; UNKNOWN
7015 0x16AD0, // 16AD0..16AED; BASSA_VAH
7016 0x16AEE, // 16AEE..16AEF; UNKNOWN
7017 0x16AF0, // 16AF0..16AF5; BASSA_VAH
7018 0x16AF6, // 16AF6..16AFF; UNKNOWN
7019 0x16B00, // 16B00..16B45; PAHAWH_HMONG
7020 0x16B46, // 16B46..16B4F; UNKNOWN
7021 0x16B50, // 16B50..16B59; PAHAWH_HMONG
7022 0x16B5A, // 16B5A ; UNKNOWN
7023 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
7024 0x16B62, // 16B62 ; UNKNOWN
7025 0x16B63, // 16B63..16B77; PAHAWH_HMONG
7026 0x16B78, // 16B78..16B7C; UNKNOWN
7027 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
7028 0x16B90, // 16B90..16D3F; UNKNOWN
7029 0x16D40, // 16D40..16D79; KIRAT_RAI
7030 0x16D7A, // 16D7A..16E3F; UNKNOWN
7031 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
7032 0x16E9B, // 16E9B..16E9F; UNKNOWN
7033 0x16EA0, // 16EA0..16EB8; BERIA_ERFE
7034 0x16EB9, // 16EB9..16EBA; UNKNOWN
7035 0x16EBB, // 16EBB..16ED3; BERIA_ERFE
7036 0x16ED4, // 16ED4..16EFF; UNKNOWN
7037 0x16F00, // 16F00..16F4A; MIAO
7038 0x16F4B, // 16F4B..16F4E; UNKNOWN
7039 0x16F4F, // 16F4F..16F87; MIAO
7040 0x16F88, // 16F88..16F8E; UNKNOWN
7041 0x16F8F, // 16F8F..16F9F; MIAO
7042 0x16FA0, // 16FA0..16FDF; UNKNOWN
7043 0x16FE0, // 16FE0 ; TANGUT
7044 0x16FE1, // 16FE1 ; NUSHU
7045 0x16FE2, // 16FE2..16FE3; HAN
7046 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
7047 0x16FE5, // 16FE5..16FEF; UNKNOWN
7048 0x16FF0, // 16FF0..16FF6; HAN
7049 0x16FF7, // 16FF7..16FFF; UNKNOWN
7050 0x17000, // 17000..18AFF; TANGUT
7051 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
7052 0x18CD6, // 18CD6..18CFE; UNKNOWN
7053 0x18CFF, // 18CFF ; KHITAN_SMALL_SCRIPT
7054 0x18D00, // 18D00..18D1E; TANGUT
7055 0x18D1F, // 18D1F..18D7F; UNKNOWN
7056 0x18D80, // 18D80..18DF2; TANGUT
7057 0x18DF3, // 18DF3..1AFEF; UNKNOWN
7058 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
7059 0x1AFF4, // 1AFF4 ; UNKNOWN
7060 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
7061 0x1AFFC, // 1AFFC ; UNKNOWN
7062 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
7063 0x1AFFF, // 1AFFF ; UNKNOWN
7064 0x1B000, // 1B000 ; KATAKANA
7065 0x1B001, // 1B001..1B11F; HIRAGANA
7066 0x1B120, // 1B120..1B122; KATAKANA
7067 0x1B123, // 1B123..1B131; UNKNOWN
7068 0x1B132, // 1B132 ; HIRAGANA
7069 0x1B133, // 1B133..1B14F; UNKNOWN
7070 0x1B150, // 1B150..1B152; HIRAGANA
7071 0x1B153, // 1B153..1B154; UNKNOWN
7072 0x1B155, // 1B155 ; KATAKANA
7073 0x1B156, // 1B156..1B163; UNKNOWN
7074 0x1B164, // 1B164..1B167; KATAKANA
7075 0x1B168, // 1B168..1B16F; UNKNOWN
7076 0x1B170, // 1B170..1B2FB; NUSHU
7077 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
7078 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
7079 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
7080 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
7081 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
7082 0x1BC80, // 1BC80..1BC88; DUPLOYAN
7083 0x1BC89, // 1BC89..1BC8F; UNKNOWN
7084 0x1BC90, // 1BC90..1BC99; DUPLOYAN
7085 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
7086 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
7087 0x1BCA0, // 1BCA0..1BCA3; COMMON
7088 0x1BCA4, // 1BCA4..1CBFF; UNKNOWN
7089 0x1CC00, // 1CC00..1CCFC; COMMON
7090 0x1CCFD, // 1CCFD..1CCFF; UNKNOWN
7091 0x1CD00, // 1CD00..1CEB3; COMMON
7092 0x1CEB4, // 1CEB4..1CEB9; UNKNOWN
7093 0x1CEBA, // 1CEBA..1CED0; COMMON
7094 0x1CED1, // 1CED1..1CEDF; UNKNOWN
7095 0x1CEE0, // 1CEE0..1CEF0; COMMON
7096 0x1CEF1, // 1CEF1..1CEFF; UNKNOWN
7097 0x1CF00, // 1CF00..1CF2D; INHERITED
7098 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
7099 0x1CF30, // 1CF30..1CF46; INHERITED
7100 0x1CF47, // 1CF47..1CF4F; UNKNOWN
7101 0x1CF50, // 1CF50..1CFC3; COMMON
7102 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
7103 0x1D000, // 1D000..1D0F5; COMMON
7104 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
7105 0x1D100, // 1D100..1D126; COMMON
7106 0x1D127, // 1D127..1D128; UNKNOWN
7107 0x1D129, // 1D129..1D166; COMMON
7108 0x1D167, // 1D167..1D169; INHERITED
7109 0x1D16A, // 1D16A..1D17A; COMMON
7110 0x1D17B, // 1D17B..1D182; INHERITED
7111 0x1D183, // 1D183..1D184; COMMON
7112 0x1D185, // 1D185..1D18B; INHERITED
7113 0x1D18C, // 1D18C..1D1A9; COMMON
7114 0x1D1AA, // 1D1AA..1D1AD; INHERITED
7115 0x1D1AE, // 1D1AE..1D1EA; COMMON
7116 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
7117 0x1D200, // 1D200..1D245; GREEK
7118 0x1D246, // 1D246..1D2BF; UNKNOWN
7119 0x1D2C0, // 1D2C0..1D2D3; COMMON
7120 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
7121 0x1D2E0, // 1D2E0..1D2F3; COMMON
7122 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
7123 0x1D300, // 1D300..1D356; COMMON
7124 0x1D357, // 1D357..1D35F; UNKNOWN
7125 0x1D360, // 1D360..1D378; COMMON
7126 0x1D379, // 1D379..1D3FF; UNKNOWN
7127 0x1D400, // 1D400..1D454; COMMON
7128 0x1D455, // 1D455 ; UNKNOWN
7129 0x1D456, // 1D456..1D49C; COMMON
7130 0x1D49D, // 1D49D ; UNKNOWN
7131 0x1D49E, // 1D49E..1D49F; COMMON
7132 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
7133 0x1D4A2, // 1D4A2 ; COMMON
7134 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
7135 0x1D4A5, // 1D4A5..1D4A6; COMMON
7136 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
7137 0x1D4A9, // 1D4A9..1D4AC; COMMON
7138 0x1D4AD, // 1D4AD ; UNKNOWN
7139 0x1D4AE, // 1D4AE..1D4B9; COMMON
7140 0x1D4BA, // 1D4BA ; UNKNOWN
7141 0x1D4BB, // 1D4BB ; COMMON
7142 0x1D4BC, // 1D4BC ; UNKNOWN
7143 0x1D4BD, // 1D4BD..1D4C3; COMMON
7144 0x1D4C4, // 1D4C4 ; UNKNOWN
7145 0x1D4C5, // 1D4C5..1D505; COMMON
7146 0x1D506, // 1D506 ; UNKNOWN
7147 0x1D507, // 1D507..1D50A; COMMON
7148 0x1D50B, // 1D50B..1D50C; UNKNOWN
7149 0x1D50D, // 1D50D..1D514; COMMON
7150 0x1D515, // 1D515 ; UNKNOWN
7151 0x1D516, // 1D516..1D51C; COMMON
7152 0x1D51D, // 1D51D ; UNKNOWN
7153 0x1D51E, // 1D51E..1D539; COMMON
7154 0x1D53A, // 1D53A ; UNKNOWN
7155 0x1D53B, // 1D53B..1D53E; COMMON
7156 0x1D53F, // 1D53F ; UNKNOWN
7157 0x1D540, // 1D540..1D544; COMMON
7158 0x1D545, // 1D545 ; UNKNOWN
7159 0x1D546, // 1D546 ; COMMON
7160 0x1D547, // 1D547..1D549; UNKNOWN
7161 0x1D54A, // 1D54A..1D550; COMMON
7162 0x1D551, // 1D551 ; UNKNOWN
7163 0x1D552, // 1D552..1D6A5; COMMON
7164 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
7165 0x1D6A8, // 1D6A8..1D7CB; COMMON
7166 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
7167 0x1D7CE, // 1D7CE..1D7FF; COMMON
7168 0x1D800, // 1D800..1DA8B; SIGNWRITING
7169 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
7170 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
7171 0x1DAA0, // 1DAA0 ; UNKNOWN
7172 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
7173 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
7174 0x1DF00, // 1DF00..1DF1E; LATIN
7175 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
7176 0x1DF25, // 1DF25..1DF2A; LATIN
7177 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
7178 0x1E000, // 1E000..1E006; GLAGOLITIC
7179 0x1E007, // 1E007 ; UNKNOWN
7180 0x1E008, // 1E008..1E018; GLAGOLITIC
7181 0x1E019, // 1E019..1E01A; UNKNOWN
7182 0x1E01B, // 1E01B..1E021; GLAGOLITIC
7183 0x1E022, // 1E022 ; UNKNOWN
7184 0x1E023, // 1E023..1E024; GLAGOLITIC
7185 0x1E025, // 1E025 ; UNKNOWN
7186 0x1E026, // 1E026..1E02A; GLAGOLITIC
7187 0x1E02B, // 1E02B..1E02F; UNKNOWN
7188 0x1E030, // 1E030..1E06D; CYRILLIC
7189 0x1E06E, // 1E06E..1E08E; UNKNOWN
7190 0x1E08F, // 1E08F ; CYRILLIC
7191 0x1E090, // 1E090..1E0FF; UNKNOWN
7192 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
7193 0x1E12D, // 1E12D..1E12F; UNKNOWN
7194 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
7195 0x1E13E, // 1E13E..1E13F; UNKNOWN
7196 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
7197 0x1E14A, // 1E14A..1E14D; UNKNOWN
7198 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
7199 0x1E150, // 1E150..1E28F; UNKNOWN
7200 0x1E290, // 1E290..1E2AE; TOTO
7201 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
7202 0x1E2C0, // 1E2C0..1E2F9; WANCHO
7203 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
7204 0x1E2FF, // 1E2FF ; WANCHO
7205 0x1E300, // 1E300..1E4CF; UNKNOWN
7206 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
7207 0x1E4FA, // 1E4FA..1E5CF; UNKNOWN
7208 0x1E5D0, // 1E5D0..1E5FA; OL_ONAL
7209 0x1E5FB, // 1E5FB..1E5FE; UNKNOWN
7210 0x1E5FF, // 1E5FF ; OL_ONAL
7211 0x1E600, // 1E600..1E6BF; UNKNOWN
7212 0x1E6C0, // 1E6C0..1E6DE; TAI_YO
7213 0x1E6DF, // 1E6DF ; UNKNOWN
7214 0x1E6E0, // 1E6E0..1E6F5; TAI_YO
7215 0x1E6F6, // 1E6F6..1E6FD; UNKNOWN
7216 0x1E6FE, // 1E6FE..1E6FF; TAI_YO
7217 0x1E700, // 1E700..1E7DF; UNKNOWN
7218 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
7219 0x1E7E7, // 1E7E7 ; UNKNOWN
7220 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
7221 0x1E7EC, // 1E7EC ; UNKNOWN
7222 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
7223 0x1E7EF, // 1E7EF ; UNKNOWN
7224 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
7225 0x1E7FF, // 1E7FF ; UNKNOWN
7226 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
7227 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
7228 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
7229 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
7230 0x1E900, // 1E900..1E94B; ADLAM
7231 0x1E94C, // 1E94C..1E94F; UNKNOWN
7232 0x1E950, // 1E950..1E959; ADLAM
7233 0x1E95A, // 1E95A..1E95D; UNKNOWN
7234 0x1E95E, // 1E95E..1E95F; ADLAM
7235 0x1E960, // 1E960..1EC70; UNKNOWN
7236 0x1EC71, // 1EC71..1ECB4; COMMON
7237 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
7238 0x1ED01, // 1ED01..1ED3D; COMMON
7239 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
7240 0x1EE00, // 1EE00..1EE03; ARABIC
7241 0x1EE04, // 1EE04 ; UNKNOWN
7242 0x1EE05, // 1EE05..1EE1F; ARABIC
7243 0x1EE20, // 1EE20 ; UNKNOWN
7244 0x1EE21, // 1EE21..1EE22; ARABIC
7245 0x1EE23, // 1EE23 ; UNKNOWN
7246 0x1EE24, // 1EE24 ; ARABIC
7247 0x1EE25, // 1EE25..1EE26; UNKNOWN
7248 0x1EE27, // 1EE27 ; ARABIC
7249 0x1EE28, // 1EE28 ; UNKNOWN
7250 0x1EE29, // 1EE29..1EE32; ARABIC
7251 0x1EE33, // 1EE33 ; UNKNOWN
7252 0x1EE34, // 1EE34..1EE37; ARABIC
7253 0x1EE38, // 1EE38 ; UNKNOWN
7254 0x1EE39, // 1EE39 ; ARABIC
7255 0x1EE3A, // 1EE3A ; UNKNOWN
7256 0x1EE3B, // 1EE3B ; ARABIC
7257 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
7258 0x1EE42, // 1EE42 ; ARABIC
7259 0x1EE43, // 1EE43..1EE46; UNKNOWN
7260 0x1EE47, // 1EE47 ; ARABIC
7261 0x1EE48, // 1EE48 ; UNKNOWN
7262 0x1EE49, // 1EE49 ; ARABIC
7263 0x1EE4A, // 1EE4A ; UNKNOWN
7264 0x1EE4B, // 1EE4B ; ARABIC
7265 0x1EE4C, // 1EE4C ; UNKNOWN
7266 0x1EE4D, // 1EE4D..1EE4F; ARABIC
7267 0x1EE50, // 1EE50 ; UNKNOWN
7268 0x1EE51, // 1EE51..1EE52; ARABIC
7269 0x1EE53, // 1EE53 ; UNKNOWN
7270 0x1EE54, // 1EE54 ; ARABIC
7271 0x1EE55, // 1EE55..1EE56; UNKNOWN
7272 0x1EE57, // 1EE57 ; ARABIC
7273 0x1EE58, // 1EE58 ; UNKNOWN
7274 0x1EE59, // 1EE59 ; ARABIC
7275 0x1EE5A, // 1EE5A ; UNKNOWN
7276 0x1EE5B, // 1EE5B ; ARABIC
7277 0x1EE5C, // 1EE5C ; UNKNOWN
7278 0x1EE5D, // 1EE5D ; ARABIC
7279 0x1EE5E, // 1EE5E ; UNKNOWN
7280 0x1EE5F, // 1EE5F ; ARABIC
7281 0x1EE60, // 1EE60 ; UNKNOWN
7282 0x1EE61, // 1EE61..1EE62; ARABIC
7283 0x1EE63, // 1EE63 ; UNKNOWN
7284 0x1EE64, // 1EE64 ; ARABIC
7285 0x1EE65, // 1EE65..1EE66; UNKNOWN
7286 0x1EE67, // 1EE67..1EE6A; ARABIC
7287 0x1EE6B, // 1EE6B ; UNKNOWN
7288 0x1EE6C, // 1EE6C..1EE72; ARABIC
7289 0x1EE73, // 1EE73 ; UNKNOWN
7290 0x1EE74, // 1EE74..1EE77; ARABIC
7291 0x1EE78, // 1EE78 ; UNKNOWN
7292 0x1EE79, // 1EE79..1EE7C; ARABIC
7293 0x1EE7D, // 1EE7D ; UNKNOWN
7294 0x1EE7E, // 1EE7E ; ARABIC
7295 0x1EE7F, // 1EE7F ; UNKNOWN
7296 0x1EE80, // 1EE80..1EE89; ARABIC
7297 0x1EE8A, // 1EE8A ; UNKNOWN
7298 0x1EE8B, // 1EE8B..1EE9B; ARABIC
7299 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
7300 0x1EEA1, // 1EEA1..1EEA3; ARABIC
7301 0x1EEA4, // 1EEA4 ; UNKNOWN
7302 0x1EEA5, // 1EEA5..1EEA9; ARABIC
7303 0x1EEAA, // 1EEAA ; UNKNOWN
7304 0x1EEAB, // 1EEAB..1EEBB; ARABIC
7305 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
7306 0x1EEF0, // 1EEF0..1EEF1; ARABIC
7307 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
7308 0x1F000, // 1F000..1F02B; COMMON
7309 0x1F02C, // 1F02C..1F02F; UNKNOWN
7310 0x1F030, // 1F030..1F093; COMMON
7311 0x1F094, // 1F094..1F09F; UNKNOWN
7312 0x1F0A0, // 1F0A0..1F0AE; COMMON
7313 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
7314 0x1F0B1, // 1F0B1..1F0BF; COMMON
7315 0x1F0C0, // 1F0C0 ; UNKNOWN
7316 0x1F0C1, // 1F0C1..1F0CF; COMMON
7317 0x1F0D0, // 1F0D0 ; UNKNOWN
7318 0x1F0D1, // 1F0D1..1F0F5; COMMON
7319 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
7320 0x1F100, // 1F100..1F1AD; COMMON
7321 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
7322 0x1F1E6, // 1F1E6..1F1FF; COMMON
7323 0x1F200, // 1F200 ; HIRAGANA
7324 0x1F201, // 1F201..1F202; COMMON
7325 0x1F203, // 1F203..1F20F; UNKNOWN
7326 0x1F210, // 1F210..1F23B; COMMON
7327 0x1F23C, // 1F23C..1F23F; UNKNOWN
7328 0x1F240, // 1F240..1F248; COMMON
7329 0x1F249, // 1F249..1F24F; UNKNOWN
7330 0x1F250, // 1F250..1F251; COMMON
7331 0x1F252, // 1F252..1F25F; UNKNOWN
7332 0x1F260, // 1F260..1F265; COMMON
7333 0x1F266, // 1F266..1F2FF; UNKNOWN
7334 0x1F300, // 1F300..1F6D8; COMMON
7335 0x1F6D9, // 1F6D9..1F6DB; UNKNOWN
7336 0x1F6DC, // 1F6DC..1F6EC; COMMON
7337 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
7338 0x1F6F0, // 1F6F0..1F6FC; COMMON
7339 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
7340 0x1F700, // 1F700..1F7D9; COMMON
7341 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
7342 0x1F7E0, // 1F7E0..1F7EB; COMMON
7343 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
7344 0x1F7F0, // 1F7F0 ; COMMON
7345 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7346 0x1F800, // 1F800..1F80B; COMMON
7347 0x1F80C, // 1F80C..1F80F; UNKNOWN
7348 0x1F810, // 1F810..1F847; COMMON
7349 0x1F848, // 1F848..1F84F; UNKNOWN
7350 0x1F850, // 1F850..1F859; COMMON
7351 0x1F85A, // 1F85A..1F85F; UNKNOWN
7352 0x1F860, // 1F860..1F887; COMMON
7353 0x1F888, // 1F888..1F88F; UNKNOWN
7354 0x1F890, // 1F890..1F8AD; COMMON
7355 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7356 0x1F8B0, // 1F8B0..1F8BB; COMMON
7357 0x1F8BC, // 1F8BC..1F8BF; UNKNOWN
7358 0x1F8C0, // 1F8C0..1F8C1; COMMON
7359 0x1F8C2, // 1F8C2..1F8CF; UNKNOWN
7360 0x1F8D0, // 1F8D0..1F8D8; COMMON
7361 0x1F8D9, // 1F8D9..1F8FF; UNKNOWN
7362 0x1F900, // 1F900..1FA57; COMMON
7363 0x1FA58, // 1FA58..1FA5F; UNKNOWN
7364 0x1FA60, // 1FA60..1FA6D; COMMON
7365 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7366 0x1FA70, // 1FA70..1FA7C; COMMON
7367 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7368 0x1FA80, // 1FA80..1FA8A; COMMON
7369 0x1FA8B, // 1FA8B..1FA8D; UNKNOWN
7370 0x1FA8E, // 1FA8E..1FAC6; COMMON
7371 0x1FAC7, // 1FAC7 ; UNKNOWN
7372 0x1FAC8, // 1FAC8 ; COMMON
7373 0x1FAC9, // 1FAC9..1FACC; UNKNOWN
7374 0x1FACD, // 1FACD..1FADC; COMMON
7375 0x1FADD, // 1FADD..1FADE; UNKNOWN
7376 0x1FADF, // 1FADF..1FAEA; COMMON
7377 0x1FAEB, // 1FAEB..1FAEE; UNKNOWN
7378 0x1FAEF, // 1FAEF..1FAF8; COMMON
7379 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7380 0x1FB00, // 1FB00..1FB92; COMMON
7381 0x1FB93, // 1FB93 ; UNKNOWN
7382 0x1FB94, // 1FB94..1FBFA; COMMON
7383 0x1FBFB, // 1FBFB..1FFFF; UNKNOWN
7384 0x20000, // 20000..2A6DF; HAN
7385 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7386 0x2A700, // 2A700..2B81D; HAN
7387 0x2B81E, // 2B81E..2B81F; UNKNOWN
7388 0x2B820, // 2B820..2CEAD; HAN
7389 0x2CEAE, // 2CEAE..2CEAF; UNKNOWN
7390 0x2CEB0, // 2CEB0..2EBE0; HAN
7391 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7392 0x2EBF0, // 2EBF0..2EE5D; HAN
7393 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7394 0x2F800, // 2F800..2FA1D; HAN
7395 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7396 0x30000, // 30000..3134A; HAN
7397 0x3134B, // 3134B..3134F; UNKNOWN
7398 0x31350, // 31350..33479; HAN
7399 0x3347A, // 3347A..E0000; UNKNOWN
7400 0xE0001, // E0001 ; COMMON
7401 0xE0002, // E0002..E001F; UNKNOWN
7402 0xE0020, // E0020..E007F; COMMON
7403 0xE0080, // E0080..E00FF; UNKNOWN
7404 0xE0100, // E0100..E01EF; INHERITED
7405 0xE01F0, // E01F0..10FFFF; UNKNOWN
7406 };
7407
7408 private static final UnicodeScript[] scripts = {
7409 COMMON, // 0000..0040
7410 LATIN, // 0041..005A
7411 COMMON, // 005B..0060
7412 LATIN, // 0061..007A
7413 COMMON, // 007B..00A9
7414 LATIN, // 00AA
7415 COMMON, // 00AB..00B9
7416 LATIN, // 00BA
7417 COMMON, // 00BB..00BF
7418 LATIN, // 00C0..00D6
7419 COMMON, // 00D7
7420 LATIN, // 00D8..00F6
7421 COMMON, // 00F7
7422 LATIN, // 00F8..02B8
7423 COMMON, // 02B9..02DF
7424 LATIN, // 02E0..02E4
7425 COMMON, // 02E5..02E9
7426 BOPOMOFO, // 02EA..02EB
7427 COMMON, // 02EC..02FF
7428 INHERITED, // 0300..036F
7429 GREEK, // 0370..0373
7430 COMMON, // 0374
7431 GREEK, // 0375..0377
7432 UNKNOWN, // 0378..0379
7433 GREEK, // 037A..037D
7434 COMMON, // 037E
7435 GREEK, // 037F
7436 UNKNOWN, // 0380..0383
7437 GREEK, // 0384
7438 COMMON, // 0385
7439 GREEK, // 0386
7440 COMMON, // 0387
7441 GREEK, // 0388..038A
7442 UNKNOWN, // 038B
7443 GREEK, // 038C
7444 UNKNOWN, // 038D
7445 GREEK, // 038E..03A1
7446 UNKNOWN, // 03A2
7447 GREEK, // 03A3..03E1
7448 COPTIC, // 03E2..03EF
7449 GREEK, // 03F0..03FF
7450 CYRILLIC, // 0400..0484
7451 INHERITED, // 0485..0486
7452 CYRILLIC, // 0487..052F
7453 UNKNOWN, // 0530
7454 ARMENIAN, // 0531..0556
7455 UNKNOWN, // 0557..0558
7456 ARMENIAN, // 0559..058A
7457 UNKNOWN, // 058B..058C
7458 ARMENIAN, // 058D..058F
7459 UNKNOWN, // 0590
7460 HEBREW, // 0591..05C7
7461 UNKNOWN, // 05C8..05CF
7462 HEBREW, // 05D0..05EA
7463 UNKNOWN, // 05EB..05EE
7464 HEBREW, // 05EF..05F4
7465 UNKNOWN, // 05F5..05FF
7466 ARABIC, // 0600..0604
7467 COMMON, // 0605
7468 ARABIC, // 0606..060B
7469 COMMON, // 060C
7470 ARABIC, // 060D..061A
7471 COMMON, // 061B
7472 ARABIC, // 061C..061E
7473 COMMON, // 061F
7474 ARABIC, // 0620..063F
7475 COMMON, // 0640
7476 ARABIC, // 0641..064A
7477 INHERITED, // 064B..0655
7478 ARABIC, // 0656..066F
7479 INHERITED, // 0670
7480 ARABIC, // 0671..06DC
7481 COMMON, // 06DD
7482 ARABIC, // 06DE..06FF
7483 SYRIAC, // 0700..070D
7484 UNKNOWN, // 070E
7485 SYRIAC, // 070F..074A
7486 UNKNOWN, // 074B..074C
7487 SYRIAC, // 074D..074F
7488 ARABIC, // 0750..077F
7489 THAANA, // 0780..07B1
7490 UNKNOWN, // 07B2..07BF
7491 NKO, // 07C0..07FA
7492 UNKNOWN, // 07FB..07FC
7493 NKO, // 07FD..07FF
7494 SAMARITAN, // 0800..082D
7495 UNKNOWN, // 082E..082F
7496 SAMARITAN, // 0830..083E
7497 UNKNOWN, // 083F
7498 MANDAIC, // 0840..085B
7499 UNKNOWN, // 085C..085D
7500 MANDAIC, // 085E
7501 UNKNOWN, // 085F
7502 SYRIAC, // 0860..086A
7503 UNKNOWN, // 086B..086F
7504 ARABIC, // 0870..0891
7505 UNKNOWN, // 0892..0896
7506 ARABIC, // 0897..08E1
7507 COMMON, // 08E2
7508 ARABIC, // 08E3..08FF
7509 DEVANAGARI, // 0900..0950
7510 INHERITED, // 0951..0954
7511 DEVANAGARI, // 0955..0963
7512 COMMON, // 0964..0965
7513 DEVANAGARI, // 0966..097F
7514 BENGALI, // 0980..0983
7515 UNKNOWN, // 0984
7516 BENGALI, // 0985..098C
7517 UNKNOWN, // 098D..098E
7518 BENGALI, // 098F..0990
7519 UNKNOWN, // 0991..0992
7520 BENGALI, // 0993..09A8
7521 UNKNOWN, // 09A9
7522 BENGALI, // 09AA..09B0
7523 UNKNOWN, // 09B1
7524 BENGALI, // 09B2
7525 UNKNOWN, // 09B3..09B5
7526 BENGALI, // 09B6..09B9
7527 UNKNOWN, // 09BA..09BB
7528 BENGALI, // 09BC..09C4
7529 UNKNOWN, // 09C5..09C6
7530 BENGALI, // 09C7..09C8
7531 UNKNOWN, // 09C9..09CA
7532 BENGALI, // 09CB..09CE
7533 UNKNOWN, // 09CF..09D6
7534 BENGALI, // 09D7
7535 UNKNOWN, // 09D8..09DB
7536 BENGALI, // 09DC..09DD
7537 UNKNOWN, // 09DE
7538 BENGALI, // 09DF..09E3
7539 UNKNOWN, // 09E4..09E5
7540 BENGALI, // 09E6..09FE
7541 UNKNOWN, // 09FF..0A00
7542 GURMUKHI, // 0A01..0A03
7543 UNKNOWN, // 0A04
7544 GURMUKHI, // 0A05..0A0A
7545 UNKNOWN, // 0A0B..0A0E
7546 GURMUKHI, // 0A0F..0A10
7547 UNKNOWN, // 0A11..0A12
7548 GURMUKHI, // 0A13..0A28
7549 UNKNOWN, // 0A29
7550 GURMUKHI, // 0A2A..0A30
7551 UNKNOWN, // 0A31
7552 GURMUKHI, // 0A32..0A33
7553 UNKNOWN, // 0A34
7554 GURMUKHI, // 0A35..0A36
7555 UNKNOWN, // 0A37
7556 GURMUKHI, // 0A38..0A39
7557 UNKNOWN, // 0A3A..0A3B
7558 GURMUKHI, // 0A3C
7559 UNKNOWN, // 0A3D
7560 GURMUKHI, // 0A3E..0A42
7561 UNKNOWN, // 0A43..0A46
7562 GURMUKHI, // 0A47..0A48
7563 UNKNOWN, // 0A49..0A4A
7564 GURMUKHI, // 0A4B..0A4D
7565 UNKNOWN, // 0A4E..0A50
7566 GURMUKHI, // 0A51
7567 UNKNOWN, // 0A52..0A58
7568 GURMUKHI, // 0A59..0A5C
7569 UNKNOWN, // 0A5D
7570 GURMUKHI, // 0A5E
7571 UNKNOWN, // 0A5F..0A65
7572 GURMUKHI, // 0A66..0A76
7573 UNKNOWN, // 0A77..0A80
7574 GUJARATI, // 0A81..0A83
7575 UNKNOWN, // 0A84
7576 GUJARATI, // 0A85..0A8D
7577 UNKNOWN, // 0A8E
7578 GUJARATI, // 0A8F..0A91
7579 UNKNOWN, // 0A92
7580 GUJARATI, // 0A93..0AA8
7581 UNKNOWN, // 0AA9
7582 GUJARATI, // 0AAA..0AB0
7583 UNKNOWN, // 0AB1
7584 GUJARATI, // 0AB2..0AB3
7585 UNKNOWN, // 0AB4
7586 GUJARATI, // 0AB5..0AB9
7587 UNKNOWN, // 0ABA..0ABB
7588 GUJARATI, // 0ABC..0AC5
7589 UNKNOWN, // 0AC6
7590 GUJARATI, // 0AC7..0AC9
7591 UNKNOWN, // 0ACA
7592 GUJARATI, // 0ACB..0ACD
7593 UNKNOWN, // 0ACE..0ACF
7594 GUJARATI, // 0AD0
7595 UNKNOWN, // 0AD1..0ADF
7596 GUJARATI, // 0AE0..0AE3
7597 UNKNOWN, // 0AE4..0AE5
7598 GUJARATI, // 0AE6..0AF1
7599 UNKNOWN, // 0AF2..0AF8
7600 GUJARATI, // 0AF9..0AFF
7601 UNKNOWN, // 0B00
7602 ORIYA, // 0B01..0B03
7603 UNKNOWN, // 0B04
7604 ORIYA, // 0B05..0B0C
7605 UNKNOWN, // 0B0D..0B0E
7606 ORIYA, // 0B0F..0B10
7607 UNKNOWN, // 0B11..0B12
7608 ORIYA, // 0B13..0B28
7609 UNKNOWN, // 0B29
7610 ORIYA, // 0B2A..0B30
7611 UNKNOWN, // 0B31
7612 ORIYA, // 0B32..0B33
7613 UNKNOWN, // 0B34
7614 ORIYA, // 0B35..0B39
7615 UNKNOWN, // 0B3A..0B3B
7616 ORIYA, // 0B3C..0B44
7617 UNKNOWN, // 0B45..0B46
7618 ORIYA, // 0B47..0B48
7619 UNKNOWN, // 0B49..0B4A
7620 ORIYA, // 0B4B..0B4D
7621 UNKNOWN, // 0B4E..0B54
7622 ORIYA, // 0B55..0B57
7623 UNKNOWN, // 0B58..0B5B
7624 ORIYA, // 0B5C..0B5D
7625 UNKNOWN, // 0B5E
7626 ORIYA, // 0B5F..0B63
7627 UNKNOWN, // 0B64..0B65
7628 ORIYA, // 0B66..0B77
7629 UNKNOWN, // 0B78..0B81
7630 TAMIL, // 0B82..0B83
7631 UNKNOWN, // 0B84
7632 TAMIL, // 0B85..0B8A
7633 UNKNOWN, // 0B8B..0B8D
7634 TAMIL, // 0B8E..0B90
7635 UNKNOWN, // 0B91
7636 TAMIL, // 0B92..0B95
7637 UNKNOWN, // 0B96..0B98
7638 TAMIL, // 0B99..0B9A
7639 UNKNOWN, // 0B9B
7640 TAMIL, // 0B9C
7641 UNKNOWN, // 0B9D
7642 TAMIL, // 0B9E..0B9F
7643 UNKNOWN, // 0BA0..0BA2
7644 TAMIL, // 0BA3..0BA4
7645 UNKNOWN, // 0BA5..0BA7
7646 TAMIL, // 0BA8..0BAA
7647 UNKNOWN, // 0BAB..0BAD
7648 TAMIL, // 0BAE..0BB9
7649 UNKNOWN, // 0BBA..0BBD
7650 TAMIL, // 0BBE..0BC2
7651 UNKNOWN, // 0BC3..0BC5
7652 TAMIL, // 0BC6..0BC8
7653 UNKNOWN, // 0BC9
7654 TAMIL, // 0BCA..0BCD
7655 UNKNOWN, // 0BCE..0BCF
7656 TAMIL, // 0BD0
7657 UNKNOWN, // 0BD1..0BD6
7658 TAMIL, // 0BD7
7659 UNKNOWN, // 0BD8..0BE5
7660 TAMIL, // 0BE6..0BFA
7661 UNKNOWN, // 0BFB..0BFF
7662 TELUGU, // 0C00..0C0C
7663 UNKNOWN, // 0C0D
7664 TELUGU, // 0C0E..0C10
7665 UNKNOWN, // 0C11
7666 TELUGU, // 0C12..0C28
7667 UNKNOWN, // 0C29
7668 TELUGU, // 0C2A..0C39
7669 UNKNOWN, // 0C3A..0C3B
7670 TELUGU, // 0C3C..0C44
7671 UNKNOWN, // 0C45
7672 TELUGU, // 0C46..0C48
7673 UNKNOWN, // 0C49
7674 TELUGU, // 0C4A..0C4D
7675 UNKNOWN, // 0C4E..0C54
7676 TELUGU, // 0C55..0C56
7677 UNKNOWN, // 0C57
7678 TELUGU, // 0C58..0C5A
7679 UNKNOWN, // 0C5B
7680 TELUGU, // 0C5C..0C5D
7681 UNKNOWN, // 0C5E..0C5F
7682 TELUGU, // 0C60..0C63
7683 UNKNOWN, // 0C64..0C65
7684 TELUGU, // 0C66..0C6F
7685 UNKNOWN, // 0C70..0C76
7686 TELUGU, // 0C77..0C7F
7687 KANNADA, // 0C80..0C8C
7688 UNKNOWN, // 0C8D
7689 KANNADA, // 0C8E..0C90
7690 UNKNOWN, // 0C91
7691 KANNADA, // 0C92..0CA8
7692 UNKNOWN, // 0CA9
7693 KANNADA, // 0CAA..0CB3
7694 UNKNOWN, // 0CB4
7695 KANNADA, // 0CB5..0CB9
7696 UNKNOWN, // 0CBA..0CBB
7697 KANNADA, // 0CBC..0CC4
7698 UNKNOWN, // 0CC5
7699 KANNADA, // 0CC6..0CC8
7700 UNKNOWN, // 0CC9
7701 KANNADA, // 0CCA..0CCD
7702 UNKNOWN, // 0CCE..0CD4
7703 KANNADA, // 0CD5..0CD6
7704 UNKNOWN, // 0CD7..0CDB
7705 KANNADA, // 0CDC..0CDE
7706 UNKNOWN, // 0CDF
7707 KANNADA, // 0CE0..0CE3
7708 UNKNOWN, // 0CE4..0CE5
7709 KANNADA, // 0CE6..0CEF
7710 UNKNOWN, // 0CF0
7711 KANNADA, // 0CF1..0CF3
7712 UNKNOWN, // 0CF4..0CFF
7713 MALAYALAM, // 0D00..0D0C
7714 UNKNOWN, // 0D0D
7715 MALAYALAM, // 0D0E..0D10
7716 UNKNOWN, // 0D11
7717 MALAYALAM, // 0D12..0D44
7718 UNKNOWN, // 0D45
7719 MALAYALAM, // 0D46..0D48
7720 UNKNOWN, // 0D49
7721 MALAYALAM, // 0D4A..0D4F
7722 UNKNOWN, // 0D50..0D53
7723 MALAYALAM, // 0D54..0D63
7724 UNKNOWN, // 0D64..0D65
7725 MALAYALAM, // 0D66..0D7F
7726 UNKNOWN, // 0D80
7727 SINHALA, // 0D81..0D83
7728 UNKNOWN, // 0D84
7729 SINHALA, // 0D85..0D96
7730 UNKNOWN, // 0D97..0D99
7731 SINHALA, // 0D9A..0DB1
7732 UNKNOWN, // 0DB2
7733 SINHALA, // 0DB3..0DBB
7734 UNKNOWN, // 0DBC
7735 SINHALA, // 0DBD
7736 UNKNOWN, // 0DBE..0DBF
7737 SINHALA, // 0DC0..0DC6
7738 UNKNOWN, // 0DC7..0DC9
7739 SINHALA, // 0DCA
7740 UNKNOWN, // 0DCB..0DCE
7741 SINHALA, // 0DCF..0DD4
7742 UNKNOWN, // 0DD5
7743 SINHALA, // 0DD6
7744 UNKNOWN, // 0DD7
7745 SINHALA, // 0DD8..0DDF
7746 UNKNOWN, // 0DE0..0DE5
7747 SINHALA, // 0DE6..0DEF
7748 UNKNOWN, // 0DF0..0DF1
7749 SINHALA, // 0DF2..0DF4
7750 UNKNOWN, // 0DF5..0E00
7751 THAI, // 0E01..0E3A
7752 UNKNOWN, // 0E3B..0E3E
7753 COMMON, // 0E3F
7754 THAI, // 0E40..0E5B
7755 UNKNOWN, // 0E5C..0E80
7756 LAO, // 0E81..0E82
7757 UNKNOWN, // 0E83
7758 LAO, // 0E84
7759 UNKNOWN, // 0E85
7760 LAO, // 0E86..0E8A
7761 UNKNOWN, // 0E8B
7762 LAO, // 0E8C..0EA3
7763 UNKNOWN, // 0EA4
7764 LAO, // 0EA5
7765 UNKNOWN, // 0EA6
7766 LAO, // 0EA7..0EBD
7767 UNKNOWN, // 0EBE..0EBF
7768 LAO, // 0EC0..0EC4
7769 UNKNOWN, // 0EC5
7770 LAO, // 0EC6
7771 UNKNOWN, // 0EC7
7772 LAO, // 0EC8..0ECE
7773 UNKNOWN, // 0ECF
7774 LAO, // 0ED0..0ED9
7775 UNKNOWN, // 0EDA..0EDB
7776 LAO, // 0EDC..0EDF
7777 UNKNOWN, // 0EE0..0EFF
7778 TIBETAN, // 0F00..0F47
7779 UNKNOWN, // 0F48
7780 TIBETAN, // 0F49..0F6C
7781 UNKNOWN, // 0F6D..0F70
7782 TIBETAN, // 0F71..0F97
7783 UNKNOWN, // 0F98
7784 TIBETAN, // 0F99..0FBC
7785 UNKNOWN, // 0FBD
7786 TIBETAN, // 0FBE..0FCC
7787 UNKNOWN, // 0FCD
7788 TIBETAN, // 0FCE..0FD4
7789 COMMON, // 0FD5..0FD8
7790 TIBETAN, // 0FD9..0FDA
7791 UNKNOWN, // 0FDB..0FFF
7792 MYANMAR, // 1000..109F
7793 GEORGIAN, // 10A0..10C5
7794 UNKNOWN, // 10C6
7795 GEORGIAN, // 10C7
7796 UNKNOWN, // 10C8..10CC
7797 GEORGIAN, // 10CD
7798 UNKNOWN, // 10CE..10CF
7799 GEORGIAN, // 10D0..10FA
7800 COMMON, // 10FB
7801 GEORGIAN, // 10FC..10FF
7802 HANGUL, // 1100..11FF
7803 ETHIOPIC, // 1200..1248
7804 UNKNOWN, // 1249
7805 ETHIOPIC, // 124A..124D
7806 UNKNOWN, // 124E..124F
7807 ETHIOPIC, // 1250..1256
7808 UNKNOWN, // 1257
7809 ETHIOPIC, // 1258
7810 UNKNOWN, // 1259
7811 ETHIOPIC, // 125A..125D
7812 UNKNOWN, // 125E..125F
7813 ETHIOPIC, // 1260..1288
7814 UNKNOWN, // 1289
7815 ETHIOPIC, // 128A..128D
7816 UNKNOWN, // 128E..128F
7817 ETHIOPIC, // 1290..12B0
7818 UNKNOWN, // 12B1
7819 ETHIOPIC, // 12B2..12B5
7820 UNKNOWN, // 12B6..12B7
7821 ETHIOPIC, // 12B8..12BE
7822 UNKNOWN, // 12BF
7823 ETHIOPIC, // 12C0
7824 UNKNOWN, // 12C1
7825 ETHIOPIC, // 12C2..12C5
7826 UNKNOWN, // 12C6..12C7
7827 ETHIOPIC, // 12C8..12D6
7828 UNKNOWN, // 12D7
7829 ETHIOPIC, // 12D8..1310
7830 UNKNOWN, // 1311
7831 ETHIOPIC, // 1312..1315
7832 UNKNOWN, // 1316..1317
7833 ETHIOPIC, // 1318..135A
7834 UNKNOWN, // 135B..135C
7835 ETHIOPIC, // 135D..137C
7836 UNKNOWN, // 137D..137F
7837 ETHIOPIC, // 1380..1399
7838 UNKNOWN, // 139A..139F
7839 CHEROKEE, // 13A0..13F5
7840 UNKNOWN, // 13F6..13F7
7841 CHEROKEE, // 13F8..13FD
7842 UNKNOWN, // 13FE..13FF
7843 CANADIAN_ABORIGINAL, // 1400..167F
7844 OGHAM, // 1680..169C
7845 UNKNOWN, // 169D..169F
7846 RUNIC, // 16A0..16EA
7847 COMMON, // 16EB..16ED
7848 RUNIC, // 16EE..16F8
7849 UNKNOWN, // 16F9..16FF
7850 TAGALOG, // 1700..1715
7851 UNKNOWN, // 1716..171E
7852 TAGALOG, // 171F
7853 HANUNOO, // 1720..1734
7854 COMMON, // 1735..1736
7855 UNKNOWN, // 1737..173F
7856 BUHID, // 1740..1753
7857 UNKNOWN, // 1754..175F
7858 TAGBANWA, // 1760..176C
7859 UNKNOWN, // 176D
7860 TAGBANWA, // 176E..1770
7861 UNKNOWN, // 1771
7862 TAGBANWA, // 1772..1773
7863 UNKNOWN, // 1774..177F
7864 KHMER, // 1780..17DD
7865 UNKNOWN, // 17DE..17DF
7866 KHMER, // 17E0..17E9
7867 UNKNOWN, // 17EA..17EF
7868 KHMER, // 17F0..17F9
7869 UNKNOWN, // 17FA..17FF
7870 MONGOLIAN, // 1800..1801
7871 COMMON, // 1802..1803
7872 MONGOLIAN, // 1804
7873 COMMON, // 1805
7874 MONGOLIAN, // 1806..1819
7875 UNKNOWN, // 181A..181F
7876 MONGOLIAN, // 1820..1878
7877 UNKNOWN, // 1879..187F
7878 MONGOLIAN, // 1880..18AA
7879 UNKNOWN, // 18AB..18AF
7880 CANADIAN_ABORIGINAL, // 18B0..18F5
7881 UNKNOWN, // 18F6..18FF
7882 LIMBU, // 1900..191E
7883 UNKNOWN, // 191F
7884 LIMBU, // 1920..192B
7885 UNKNOWN, // 192C..192F
7886 LIMBU, // 1930..193B
7887 UNKNOWN, // 193C..193F
7888 LIMBU, // 1940
7889 UNKNOWN, // 1941..1943
7890 LIMBU, // 1944..194F
7891 TAI_LE, // 1950..196D
7892 UNKNOWN, // 196E..196F
7893 TAI_LE, // 1970..1974
7894 UNKNOWN, // 1975..197F
7895 NEW_TAI_LUE, // 1980..19AB
7896 UNKNOWN, // 19AC..19AF
7897 NEW_TAI_LUE, // 19B0..19C9
7898 UNKNOWN, // 19CA..19CF
7899 NEW_TAI_LUE, // 19D0..19DA
7900 UNKNOWN, // 19DB..19DD
7901 NEW_TAI_LUE, // 19DE..19DF
7902 KHMER, // 19E0..19FF
7903 BUGINESE, // 1A00..1A1B
7904 UNKNOWN, // 1A1C..1A1D
7905 BUGINESE, // 1A1E..1A1F
7906 TAI_THAM, // 1A20..1A5E
7907 UNKNOWN, // 1A5F
7908 TAI_THAM, // 1A60..1A7C
7909 UNKNOWN, // 1A7D..1A7E
7910 TAI_THAM, // 1A7F..1A89
7911 UNKNOWN, // 1A8A..1A8F
7912 TAI_THAM, // 1A90..1A99
7913 UNKNOWN, // 1A9A..1A9F
7914 TAI_THAM, // 1AA0..1AAD
7915 UNKNOWN, // 1AAE..1AAF
7916 INHERITED, // 1AB0..1ADD
7917 UNKNOWN, // 1ADE..1ADF
7918 INHERITED, // 1AE0..1AEB
7919 UNKNOWN, // 1AEC..1AFF
7920 BALINESE, // 1B00..1B4C
7921 UNKNOWN, // 1B4D
7922 BALINESE, // 1B4E..1B7F
7923 SUNDANESE, // 1B80..1BBF
7924 BATAK, // 1BC0..1BF3
7925 UNKNOWN, // 1BF4..1BFB
7926 BATAK, // 1BFC..1BFF
7927 LEPCHA, // 1C00..1C37
7928 UNKNOWN, // 1C38..1C3A
7929 LEPCHA, // 1C3B..1C49
7930 UNKNOWN, // 1C4A..1C4C
7931 LEPCHA, // 1C4D..1C4F
7932 OL_CHIKI, // 1C50..1C7F
7933 CYRILLIC, // 1C80..1C8A
7934 UNKNOWN, // 1C8B..1C8F
7935 GEORGIAN, // 1C90..1CBA
7936 UNKNOWN, // 1CBB..1CBC
7937 GEORGIAN, // 1CBD..1CBF
7938 SUNDANESE, // 1CC0..1CC7
7939 UNKNOWN, // 1CC8..1CCF
7940 INHERITED, // 1CD0..1CD2
7941 COMMON, // 1CD3
7942 INHERITED, // 1CD4..1CE0
7943 COMMON, // 1CE1
7944 INHERITED, // 1CE2..1CE8
7945 COMMON, // 1CE9..1CEC
7946 INHERITED, // 1CED
7947 COMMON, // 1CEE..1CF3
7948 INHERITED, // 1CF4
7949 COMMON, // 1CF5..1CF7
7950 INHERITED, // 1CF8..1CF9
7951 COMMON, // 1CFA
7952 UNKNOWN, // 1CFB..1CFF
7953 LATIN, // 1D00..1D25
7954 GREEK, // 1D26..1D2A
7955 CYRILLIC, // 1D2B
7956 LATIN, // 1D2C..1D5C
7957 GREEK, // 1D5D..1D61
7958 LATIN, // 1D62..1D65
7959 GREEK, // 1D66..1D6A
7960 LATIN, // 1D6B..1D77
7961 CYRILLIC, // 1D78
7962 LATIN, // 1D79..1DBE
7963 GREEK, // 1DBF
7964 INHERITED, // 1DC0..1DFF
7965 LATIN, // 1E00..1EFF
7966 GREEK, // 1F00..1F15
7967 UNKNOWN, // 1F16..1F17
7968 GREEK, // 1F18..1F1D
7969 UNKNOWN, // 1F1E..1F1F
7970 GREEK, // 1F20..1F45
7971 UNKNOWN, // 1F46..1F47
7972 GREEK, // 1F48..1F4D
7973 UNKNOWN, // 1F4E..1F4F
7974 GREEK, // 1F50..1F57
7975 UNKNOWN, // 1F58
7976 GREEK, // 1F59
7977 UNKNOWN, // 1F5A
7978 GREEK, // 1F5B
7979 UNKNOWN, // 1F5C
7980 GREEK, // 1F5D
7981 UNKNOWN, // 1F5E
7982 GREEK, // 1F5F..1F7D
7983 UNKNOWN, // 1F7E..1F7F
7984 GREEK, // 1F80..1FB4
7985 UNKNOWN, // 1FB5
7986 GREEK, // 1FB6..1FC4
7987 UNKNOWN, // 1FC5
7988 GREEK, // 1FC6..1FD3
7989 UNKNOWN, // 1FD4..1FD5
7990 GREEK, // 1FD6..1FDB
7991 UNKNOWN, // 1FDC
7992 GREEK, // 1FDD..1FEF
7993 UNKNOWN, // 1FF0..1FF1
7994 GREEK, // 1FF2..1FF4
7995 UNKNOWN, // 1FF5
7996 GREEK, // 1FF6..1FFE
7997 UNKNOWN, // 1FFF
7998 COMMON, // 2000..200B
7999 INHERITED, // 200C..200D
8000 COMMON, // 200E..2064
8001 UNKNOWN, // 2065
8002 COMMON, // 2066..2070
8003 LATIN, // 2071
8004 UNKNOWN, // 2072..2073
8005 COMMON, // 2074..207E
8006 LATIN, // 207F
8007 COMMON, // 2080..208E
8008 UNKNOWN, // 208F
8009 LATIN, // 2090..209C
8010 UNKNOWN, // 209D..209F
8011 COMMON, // 20A0..20C1
8012 UNKNOWN, // 20C2..20CF
8013 INHERITED, // 20D0..20F0
8014 UNKNOWN, // 20F1..20FF
8015 COMMON, // 2100..2125
8016 GREEK, // 2126
8017 COMMON, // 2127..2129
8018 LATIN, // 212A..212B
8019 COMMON, // 212C..2131
8020 LATIN, // 2132
8021 COMMON, // 2133..214D
8022 LATIN, // 214E
8023 COMMON, // 214F..215F
8024 LATIN, // 2160..2188
8025 COMMON, // 2189..218B
8026 UNKNOWN, // 218C..218F
8027 COMMON, // 2190..2429
8028 UNKNOWN, // 242A..243F
8029 COMMON, // 2440..244A
8030 UNKNOWN, // 244B..245F
8031 COMMON, // 2460..27FF
8032 BRAILLE, // 2800..28FF
8033 COMMON, // 2900..2B73
8034 UNKNOWN, // 2B74..2B75
8035 COMMON, // 2B76..2BFF
8036 GLAGOLITIC, // 2C00..2C5F
8037 LATIN, // 2C60..2C7F
8038 COPTIC, // 2C80..2CF3
8039 UNKNOWN, // 2CF4..2CF8
8040 COPTIC, // 2CF9..2CFF
8041 GEORGIAN, // 2D00..2D25
8042 UNKNOWN, // 2D26
8043 GEORGIAN, // 2D27
8044 UNKNOWN, // 2D28..2D2C
8045 GEORGIAN, // 2D2D
8046 UNKNOWN, // 2D2E..2D2F
8047 TIFINAGH, // 2D30..2D67
8048 UNKNOWN, // 2D68..2D6E
8049 TIFINAGH, // 2D6F..2D70
8050 UNKNOWN, // 2D71..2D7E
8051 TIFINAGH, // 2D7F
8052 ETHIOPIC, // 2D80..2D96
8053 UNKNOWN, // 2D97..2D9F
8054 ETHIOPIC, // 2DA0..2DA6
8055 UNKNOWN, // 2DA7
8056 ETHIOPIC, // 2DA8..2DAE
8057 UNKNOWN, // 2DAF
8058 ETHIOPIC, // 2DB0..2DB6
8059 UNKNOWN, // 2DB7
8060 ETHIOPIC, // 2DB8..2DBE
8061 UNKNOWN, // 2DBF
8062 ETHIOPIC, // 2DC0..2DC6
8063 UNKNOWN, // 2DC7
8064 ETHIOPIC, // 2DC8..2DCE
8065 UNKNOWN, // 2DCF
8066 ETHIOPIC, // 2DD0..2DD6
8067 UNKNOWN, // 2DD7
8068 ETHIOPIC, // 2DD8..2DDE
8069 UNKNOWN, // 2DDF
8070 CYRILLIC, // 2DE0..2DFF
8071 COMMON, // 2E00..2E5D
8072 UNKNOWN, // 2E5E..2E7F
8073 HAN, // 2E80..2E99
8074 UNKNOWN, // 2E9A
8075 HAN, // 2E9B..2EF3
8076 UNKNOWN, // 2EF4..2EFF
8077 HAN, // 2F00..2FD5
8078 UNKNOWN, // 2FD6..2FEF
8079 COMMON, // 2FF0..3004
8080 HAN, // 3005
8081 COMMON, // 3006
8082 HAN, // 3007
8083 COMMON, // 3008..3020
8084 HAN, // 3021..3029
8085 INHERITED, // 302A..302D
8086 HANGUL, // 302E..302F
8087 COMMON, // 3030..3037
8088 HAN, // 3038..303B
8089 COMMON, // 303C..303F
8090 UNKNOWN, // 3040
8091 HIRAGANA, // 3041..3096
8092 UNKNOWN, // 3097..3098
8093 INHERITED, // 3099..309A
8094 COMMON, // 309B..309C
8095 HIRAGANA, // 309D..309F
8096 COMMON, // 30A0
8097 KATAKANA, // 30A1..30FA
8098 COMMON, // 30FB..30FC
8099 KATAKANA, // 30FD..30FF
8100 UNKNOWN, // 3100..3104
8101 BOPOMOFO, // 3105..312F
8102 UNKNOWN, // 3130
8103 HANGUL, // 3131..318E
8104 UNKNOWN, // 318F
8105 COMMON, // 3190..319F
8106 BOPOMOFO, // 31A0..31BF
8107 COMMON, // 31C0..31E5
8108 UNKNOWN, // 31E6..31EE
8109 COMMON, // 31EF
8110 KATAKANA, // 31F0..31FF
8111 HANGUL, // 3200..321E
8112 UNKNOWN, // 321F
8113 COMMON, // 3220..325F
8114 HANGUL, // 3260..327E
8115 COMMON, // 327F..32CF
8116 KATAKANA, // 32D0..32FE
8117 COMMON, // 32FF
8118 KATAKANA, // 3300..3357
8119 COMMON, // 3358..33FF
8120 HAN, // 3400..4DBF
8121 COMMON, // 4DC0..4DFF
8122 HAN, // 4E00..9FFF
8123 YI, // A000..A48C
8124 UNKNOWN, // A48D..A48F
8125 YI, // A490..A4C6
8126 UNKNOWN, // A4C7..A4CF
8127 LISU, // A4D0..A4FF
8128 VAI, // A500..A62B
8129 UNKNOWN, // A62C..A63F
8130 CYRILLIC, // A640..A69F
8131 BAMUM, // A6A0..A6F7
8132 UNKNOWN, // A6F8..A6FF
8133 COMMON, // A700..A721
8134 LATIN, // A722..A787
8135 COMMON, // A788..A78A
8136 LATIN, // A78B..A7DC
8137 UNKNOWN, // A7DD..A7F0
8138 LATIN, // A7F1..A7FF
8139 SYLOTI_NAGRI, // A800..A82C
8140 UNKNOWN, // A82D..A82F
8141 COMMON, // A830..A839
8142 UNKNOWN, // A83A..A83F
8143 PHAGS_PA, // A840..A877
8144 UNKNOWN, // A878..A87F
8145 SAURASHTRA, // A880..A8C5
8146 UNKNOWN, // A8C6..A8CD
8147 SAURASHTRA, // A8CE..A8D9
8148 UNKNOWN, // A8DA..A8DF
8149 DEVANAGARI, // A8E0..A8FF
8150 KAYAH_LI, // A900..A92D
8151 COMMON, // A92E
8152 KAYAH_LI, // A92F
8153 REJANG, // A930..A953
8154 UNKNOWN, // A954..A95E
8155 REJANG, // A95F
8156 HANGUL, // A960..A97C
8157 UNKNOWN, // A97D..A97F
8158 JAVANESE, // A980..A9CD
8159 UNKNOWN, // A9CE
8160 COMMON, // A9CF
8161 JAVANESE, // A9D0..A9D9
8162 UNKNOWN, // A9DA..A9DD
8163 JAVANESE, // A9DE..A9DF
8164 MYANMAR, // A9E0..A9FE
8165 UNKNOWN, // A9FF
8166 CHAM, // AA00..AA36
8167 UNKNOWN, // AA37..AA3F
8168 CHAM, // AA40..AA4D
8169 UNKNOWN, // AA4E..AA4F
8170 CHAM, // AA50..AA59
8171 UNKNOWN, // AA5A..AA5B
8172 CHAM, // AA5C..AA5F
8173 MYANMAR, // AA60..AA7F
8174 TAI_VIET, // AA80..AAC2
8175 UNKNOWN, // AAC3..AADA
8176 TAI_VIET, // AADB..AADF
8177 MEETEI_MAYEK, // AAE0..AAF6
8178 UNKNOWN, // AAF7..AB00
8179 ETHIOPIC, // AB01..AB06
8180 UNKNOWN, // AB07..AB08
8181 ETHIOPIC, // AB09..AB0E
8182 UNKNOWN, // AB0F..AB10
8183 ETHIOPIC, // AB11..AB16
8184 UNKNOWN, // AB17..AB1F
8185 ETHIOPIC, // AB20..AB26
8186 UNKNOWN, // AB27
8187 ETHIOPIC, // AB28..AB2E
8188 UNKNOWN, // AB2F
8189 LATIN, // AB30..AB5A
8190 COMMON, // AB5B
8191 LATIN, // AB5C..AB64
8192 GREEK, // AB65
8193 LATIN, // AB66..AB69
8194 COMMON, // AB6A..AB6B
8195 UNKNOWN, // AB6C..AB6F
8196 CHEROKEE, // AB70..ABBF
8197 MEETEI_MAYEK, // ABC0..ABED
8198 UNKNOWN, // ABEE..ABEF
8199 MEETEI_MAYEK, // ABF0..ABF9
8200 UNKNOWN, // ABFA..ABFF
8201 HANGUL, // AC00..D7A3
8202 UNKNOWN, // D7A4..D7AF
8203 HANGUL, // D7B0..D7C6
8204 UNKNOWN, // D7C7..D7CA
8205 HANGUL, // D7CB..D7FB
8206 UNKNOWN, // D7FC..F8FF
8207 HAN, // F900..FA6D
8208 UNKNOWN, // FA6E..FA6F
8209 HAN, // FA70..FAD9
8210 UNKNOWN, // FADA..FAFF
8211 LATIN, // FB00..FB06
8212 UNKNOWN, // FB07..FB12
8213 ARMENIAN, // FB13..FB17
8214 UNKNOWN, // FB18..FB1C
8215 HEBREW, // FB1D..FB36
8216 UNKNOWN, // FB37
8217 HEBREW, // FB38..FB3C
8218 UNKNOWN, // FB3D
8219 HEBREW, // FB3E
8220 UNKNOWN, // FB3F
8221 HEBREW, // FB40..FB41
8222 UNKNOWN, // FB42
8223 HEBREW, // FB43..FB44
8224 UNKNOWN, // FB45
8225 HEBREW, // FB46..FB4F
8226 ARABIC, // FB50..FD3D
8227 COMMON, // FD3E..FD3F
8228 ARABIC, // FD40..FDCF
8229 UNKNOWN, // FDD0..FDEF
8230 ARABIC, // FDF0..FDFF
8231 INHERITED, // FE00..FE0F
8232 COMMON, // FE10..FE19
8233 UNKNOWN, // FE1A..FE1F
8234 INHERITED, // FE20..FE2D
8235 CYRILLIC, // FE2E..FE2F
8236 COMMON, // FE30..FE52
8237 UNKNOWN, // FE53
8238 COMMON, // FE54..FE66
8239 UNKNOWN, // FE67
8240 COMMON, // FE68..FE6B
8241 UNKNOWN, // FE6C..FE6F
8242 ARABIC, // FE70..FE74
8243 UNKNOWN, // FE75
8244 ARABIC, // FE76..FEFC
8245 UNKNOWN, // FEFD..FEFE
8246 COMMON, // FEFF
8247 UNKNOWN, // FF00
8248 COMMON, // FF01..FF20
8249 LATIN, // FF21..FF3A
8250 COMMON, // FF3B..FF40
8251 LATIN, // FF41..FF5A
8252 COMMON, // FF5B..FF65
8253 KATAKANA, // FF66..FF6F
8254 COMMON, // FF70
8255 KATAKANA, // FF71..FF9D
8256 COMMON, // FF9E..FF9F
8257 HANGUL, // FFA0..FFBE
8258 UNKNOWN, // FFBF..FFC1
8259 HANGUL, // FFC2..FFC7
8260 UNKNOWN, // FFC8..FFC9
8261 HANGUL, // FFCA..FFCF
8262 UNKNOWN, // FFD0..FFD1
8263 HANGUL, // FFD2..FFD7
8264 UNKNOWN, // FFD8..FFD9
8265 HANGUL, // FFDA..FFDC
8266 UNKNOWN, // FFDD..FFDF
8267 COMMON, // FFE0..FFE6
8268 UNKNOWN, // FFE7
8269 COMMON, // FFE8..FFEE
8270 UNKNOWN, // FFEF..FFF8
8271 COMMON, // FFF9..FFFD
8272 UNKNOWN, // FFFE..FFFF
8273 LINEAR_B, // 10000..1000B
8274 UNKNOWN, // 1000C
8275 LINEAR_B, // 1000D..10026
8276 UNKNOWN, // 10027
8277 LINEAR_B, // 10028..1003A
8278 UNKNOWN, // 1003B
8279 LINEAR_B, // 1003C..1003D
8280 UNKNOWN, // 1003E
8281 LINEAR_B, // 1003F..1004D
8282 UNKNOWN, // 1004E..1004F
8283 LINEAR_B, // 10050..1005D
8284 UNKNOWN, // 1005E..1007F
8285 LINEAR_B, // 10080..100FA
8286 UNKNOWN, // 100FB..100FF
8287 COMMON, // 10100..10102
8288 UNKNOWN, // 10103..10106
8289 COMMON, // 10107..10133
8290 UNKNOWN, // 10134..10136
8291 COMMON, // 10137..1013F
8292 GREEK, // 10140..1018E
8293 UNKNOWN, // 1018F
8294 COMMON, // 10190..1019C
8295 UNKNOWN, // 1019D..1019F
8296 GREEK, // 101A0
8297 UNKNOWN, // 101A1..101CF
8298 COMMON, // 101D0..101FC
8299 INHERITED, // 101FD
8300 UNKNOWN, // 101FE..1027F
8301 LYCIAN, // 10280..1029C
8302 UNKNOWN, // 1029D..1029F
8303 CARIAN, // 102A0..102D0
8304 UNKNOWN, // 102D1..102DF
8305 INHERITED, // 102E0
8306 COMMON, // 102E1..102FB
8307 UNKNOWN, // 102FC..102FF
8308 OLD_ITALIC, // 10300..10323
8309 UNKNOWN, // 10324..1032C
8310 OLD_ITALIC, // 1032D..1032F
8311 GOTHIC, // 10330..1034A
8312 UNKNOWN, // 1034B..1034F
8313 OLD_PERMIC, // 10350..1037A
8314 UNKNOWN, // 1037B..1037F
8315 UGARITIC, // 10380..1039D
8316 UNKNOWN, // 1039E
8317 UGARITIC, // 1039F
8318 OLD_PERSIAN, // 103A0..103C3
8319 UNKNOWN, // 103C4..103C7
8320 OLD_PERSIAN, // 103C8..103D5
8321 UNKNOWN, // 103D6..103FF
8322 DESERET, // 10400..1044F
8323 SHAVIAN, // 10450..1047F
8324 OSMANYA, // 10480..1049D
8325 UNKNOWN, // 1049E..1049F
8326 OSMANYA, // 104A0..104A9
8327 UNKNOWN, // 104AA..104AF
8328 OSAGE, // 104B0..104D3
8329 UNKNOWN, // 104D4..104D7
8330 OSAGE, // 104D8..104FB
8331 UNKNOWN, // 104FC..104FF
8332 ELBASAN, // 10500..10527
8333 UNKNOWN, // 10528..1052F
8334 CAUCASIAN_ALBANIAN, // 10530..10563
8335 UNKNOWN, // 10564..1056E
8336 CAUCASIAN_ALBANIAN, // 1056F
8337 VITHKUQI, // 10570..1057A
8338 UNKNOWN, // 1057B
8339 VITHKUQI, // 1057C..1058A
8340 UNKNOWN, // 1058B
8341 VITHKUQI, // 1058C..10592
8342 UNKNOWN, // 10593
8343 VITHKUQI, // 10594..10595
8344 UNKNOWN, // 10596
8345 VITHKUQI, // 10597..105A1
8346 UNKNOWN, // 105A2
8347 VITHKUQI, // 105A3..105B1
8348 UNKNOWN, // 105B2
8349 VITHKUQI, // 105B3..105B9
8350 UNKNOWN, // 105BA
8351 VITHKUQI, // 105BB..105BC
8352 UNKNOWN, // 105BD..105BF
8353 TODHRI, // 105C0..105F3
8354 UNKNOWN, // 105F4..105FF
8355 LINEAR_A, // 10600..10736
8356 UNKNOWN, // 10737..1073F
8357 LINEAR_A, // 10740..10755
8358 UNKNOWN, // 10756..1075F
8359 LINEAR_A, // 10760..10767
8360 UNKNOWN, // 10768..1077F
8361 LATIN, // 10780..10785
8362 UNKNOWN, // 10786
8363 LATIN, // 10787..107B0
8364 UNKNOWN, // 107B1
8365 LATIN, // 107B2..107BA
8366 UNKNOWN, // 107BB..107FF
8367 CYPRIOT, // 10800..10805
8368 UNKNOWN, // 10806..10807
8369 CYPRIOT, // 10808
8370 UNKNOWN, // 10809
8371 CYPRIOT, // 1080A..10835
8372 UNKNOWN, // 10836
8373 CYPRIOT, // 10837..10838
8374 UNKNOWN, // 10839..1083B
8375 CYPRIOT, // 1083C
8376 UNKNOWN, // 1083D..1083E
8377 CYPRIOT, // 1083F
8378 IMPERIAL_ARAMAIC, // 10840..10855
8379 UNKNOWN, // 10856
8380 IMPERIAL_ARAMAIC, // 10857..1085F
8381 PALMYRENE, // 10860..1087F
8382 NABATAEAN, // 10880..1089E
8383 UNKNOWN, // 1089F..108A6
8384 NABATAEAN, // 108A7..108AF
8385 UNKNOWN, // 108B0..108DF
8386 HATRAN, // 108E0..108F2
8387 UNKNOWN, // 108F3
8388 HATRAN, // 108F4..108F5
8389 UNKNOWN, // 108F6..108FA
8390 HATRAN, // 108FB..108FF
8391 PHOENICIAN, // 10900..1091B
8392 UNKNOWN, // 1091C..1091E
8393 PHOENICIAN, // 1091F
8394 LYDIAN, // 10920..10939
8395 UNKNOWN, // 1093A..1093E
8396 LYDIAN, // 1093F
8397 SIDETIC, // 10940..10959
8398 UNKNOWN, // 1095A..1097F
8399 MEROITIC_HIEROGLYPHS, // 10980..1099F
8400 MEROITIC_CURSIVE, // 109A0..109B7
8401 UNKNOWN, // 109B8..109BB
8402 MEROITIC_CURSIVE, // 109BC..109CF
8403 UNKNOWN, // 109D0..109D1
8404 MEROITIC_CURSIVE, // 109D2..109FF
8405 KHAROSHTHI, // 10A00..10A03
8406 UNKNOWN, // 10A04
8407 KHAROSHTHI, // 10A05..10A06
8408 UNKNOWN, // 10A07..10A0B
8409 KHAROSHTHI, // 10A0C..10A13
8410 UNKNOWN, // 10A14
8411 KHAROSHTHI, // 10A15..10A17
8412 UNKNOWN, // 10A18
8413 KHAROSHTHI, // 10A19..10A35
8414 UNKNOWN, // 10A36..10A37
8415 KHAROSHTHI, // 10A38..10A3A
8416 UNKNOWN, // 10A3B..10A3E
8417 KHAROSHTHI, // 10A3F..10A48
8418 UNKNOWN, // 10A49..10A4F
8419 KHAROSHTHI, // 10A50..10A58
8420 UNKNOWN, // 10A59..10A5F
8421 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8422 OLD_NORTH_ARABIAN, // 10A80..10A9F
8423 UNKNOWN, // 10AA0..10ABF
8424 MANICHAEAN, // 10AC0..10AE6
8425 UNKNOWN, // 10AE7..10AEA
8426 MANICHAEAN, // 10AEB..10AF6
8427 UNKNOWN, // 10AF7..10AFF
8428 AVESTAN, // 10B00..10B35
8429 UNKNOWN, // 10B36..10B38
8430 AVESTAN, // 10B39..10B3F
8431 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8432 UNKNOWN, // 10B56..10B57
8433 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8434 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8435 UNKNOWN, // 10B73..10B77
8436 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8437 PSALTER_PAHLAVI, // 10B80..10B91
8438 UNKNOWN, // 10B92..10B98
8439 PSALTER_PAHLAVI, // 10B99..10B9C
8440 UNKNOWN, // 10B9D..10BA8
8441 PSALTER_PAHLAVI, // 10BA9..10BAF
8442 UNKNOWN, // 10BB0..10BFF
8443 OLD_TURKIC, // 10C00..10C48
8444 UNKNOWN, // 10C49..10C7F
8445 OLD_HUNGARIAN, // 10C80..10CB2
8446 UNKNOWN, // 10CB3..10CBF
8447 OLD_HUNGARIAN, // 10CC0..10CF2
8448 UNKNOWN, // 10CF3..10CF9
8449 OLD_HUNGARIAN, // 10CFA..10CFF
8450 HANIFI_ROHINGYA, // 10D00..10D27
8451 UNKNOWN, // 10D28..10D2F
8452 HANIFI_ROHINGYA, // 10D30..10D39
8453 UNKNOWN, // 10D3A..10D3F
8454 GARAY, // 10D40..10D65
8455 UNKNOWN, // 10D66..10D68
8456 GARAY, // 10D69..10D85
8457 UNKNOWN, // 10D86..10D8D
8458 GARAY, // 10D8E..10D8F
8459 UNKNOWN, // 10D90..10E5F
8460 ARABIC, // 10E60..10E7E
8461 UNKNOWN, // 10E7F
8462 YEZIDI, // 10E80..10EA9
8463 UNKNOWN, // 10EAA
8464 YEZIDI, // 10EAB..10EAD
8465 UNKNOWN, // 10EAE..10EAF
8466 YEZIDI, // 10EB0..10EB1
8467 UNKNOWN, // 10EB2..10EC1
8468 ARABIC, // 10EC2..10EC7
8469 UNKNOWN, // 10EC8..10ECF
8470 ARABIC, // 10ED0..10ED8
8471 UNKNOWN, // 10ED9..10EF9
8472 ARABIC, // 10EFA..10EFF
8473 OLD_SOGDIAN, // 10F00..10F27
8474 UNKNOWN, // 10F28..10F2F
8475 SOGDIAN, // 10F30..10F59
8476 UNKNOWN, // 10F5A..10F6F
8477 OLD_UYGHUR, // 10F70..10F89
8478 UNKNOWN, // 10F8A..10FAF
8479 CHORASMIAN, // 10FB0..10FCB
8480 UNKNOWN, // 10FCC..10FDF
8481 ELYMAIC, // 10FE0..10FF6
8482 UNKNOWN, // 10FF7..10FFF
8483 BRAHMI, // 11000..1104D
8484 UNKNOWN, // 1104E..11051
8485 BRAHMI, // 11052..11075
8486 UNKNOWN, // 11076..1107E
8487 BRAHMI, // 1107F
8488 KAITHI, // 11080..110C2
8489 UNKNOWN, // 110C3..110CC
8490 KAITHI, // 110CD
8491 UNKNOWN, // 110CE..110CF
8492 SORA_SOMPENG, // 110D0..110E8
8493 UNKNOWN, // 110E9..110EF
8494 SORA_SOMPENG, // 110F0..110F9
8495 UNKNOWN, // 110FA..110FF
8496 CHAKMA, // 11100..11134
8497 UNKNOWN, // 11135
8498 CHAKMA, // 11136..11147
8499 UNKNOWN, // 11148..1114F
8500 MAHAJANI, // 11150..11176
8501 UNKNOWN, // 11177..1117F
8502 SHARADA, // 11180..111DF
8503 UNKNOWN, // 111E0
8504 SINHALA, // 111E1..111F4
8505 UNKNOWN, // 111F5..111FF
8506 KHOJKI, // 11200..11211
8507 UNKNOWN, // 11212
8508 KHOJKI, // 11213..11241
8509 UNKNOWN, // 11242..1127F
8510 MULTANI, // 11280..11286
8511 UNKNOWN, // 11287
8512 MULTANI, // 11288
8513 UNKNOWN, // 11289
8514 MULTANI, // 1128A..1128D
8515 UNKNOWN, // 1128E
8516 MULTANI, // 1128F..1129D
8517 UNKNOWN, // 1129E
8518 MULTANI, // 1129F..112A9
8519 UNKNOWN, // 112AA..112AF
8520 KHUDAWADI, // 112B0..112EA
8521 UNKNOWN, // 112EB..112EF
8522 KHUDAWADI, // 112F0..112F9
8523 UNKNOWN, // 112FA..112FF
8524 GRANTHA, // 11300..11303
8525 UNKNOWN, // 11304
8526 GRANTHA, // 11305..1130C
8527 UNKNOWN, // 1130D..1130E
8528 GRANTHA, // 1130F..11310
8529 UNKNOWN, // 11311..11312
8530 GRANTHA, // 11313..11328
8531 UNKNOWN, // 11329
8532 GRANTHA, // 1132A..11330
8533 UNKNOWN, // 11331
8534 GRANTHA, // 11332..11333
8535 UNKNOWN, // 11334
8536 GRANTHA, // 11335..11339
8537 UNKNOWN, // 1133A
8538 INHERITED, // 1133B
8539 GRANTHA, // 1133C..11344
8540 UNKNOWN, // 11345..11346
8541 GRANTHA, // 11347..11348
8542 UNKNOWN, // 11349..1134A
8543 GRANTHA, // 1134B..1134D
8544 UNKNOWN, // 1134E..1134F
8545 GRANTHA, // 11350
8546 UNKNOWN, // 11351..11356
8547 GRANTHA, // 11357
8548 UNKNOWN, // 11358..1135C
8549 GRANTHA, // 1135D..11363
8550 UNKNOWN, // 11364..11365
8551 GRANTHA, // 11366..1136C
8552 UNKNOWN, // 1136D..1136F
8553 GRANTHA, // 11370..11374
8554 UNKNOWN, // 11375..1137F
8555 TULU_TIGALARI, // 11380..11389
8556 UNKNOWN, // 1138A
8557 TULU_TIGALARI, // 1138B
8558 UNKNOWN, // 1138C..1138D
8559 TULU_TIGALARI, // 1138E
8560 UNKNOWN, // 1138F
8561 TULU_TIGALARI, // 11390..113B5
8562 UNKNOWN, // 113B6
8563 TULU_TIGALARI, // 113B7..113C0
8564 UNKNOWN, // 113C1
8565 TULU_TIGALARI, // 113C2
8566 UNKNOWN, // 113C3..113C4
8567 TULU_TIGALARI, // 113C5
8568 UNKNOWN, // 113C6
8569 TULU_TIGALARI, // 113C7..113CA
8570 UNKNOWN, // 113CB
8571 TULU_TIGALARI, // 113CC..113D5
8572 UNKNOWN, // 113D6
8573 TULU_TIGALARI, // 113D7..113D8
8574 UNKNOWN, // 113D9..113E0
8575 TULU_TIGALARI, // 113E1..113E2
8576 UNKNOWN, // 113E3..113FF
8577 NEWA, // 11400..1145B
8578 UNKNOWN, // 1145C
8579 NEWA, // 1145D..11461
8580 UNKNOWN, // 11462..1147F
8581 TIRHUTA, // 11480..114C7
8582 UNKNOWN, // 114C8..114CF
8583 TIRHUTA, // 114D0..114D9
8584 UNKNOWN, // 114DA..1157F
8585 SIDDHAM, // 11580..115B5
8586 UNKNOWN, // 115B6..115B7
8587 SIDDHAM, // 115B8..115DD
8588 UNKNOWN, // 115DE..115FF
8589 MODI, // 11600..11644
8590 UNKNOWN, // 11645..1164F
8591 MODI, // 11650..11659
8592 UNKNOWN, // 1165A..1165F
8593 MONGOLIAN, // 11660..1166C
8594 UNKNOWN, // 1166D..1167F
8595 TAKRI, // 11680..116B9
8596 UNKNOWN, // 116BA..116BF
8597 TAKRI, // 116C0..116C9
8598 UNKNOWN, // 116CA..116CF
8599 MYANMAR, // 116D0..116E3
8600 UNKNOWN, // 116E4..116FF
8601 AHOM, // 11700..1171A
8602 UNKNOWN, // 1171B..1171C
8603 AHOM, // 1171D..1172B
8604 UNKNOWN, // 1172C..1172F
8605 AHOM, // 11730..11746
8606 UNKNOWN, // 11747..117FF
8607 DOGRA, // 11800..1183B
8608 UNKNOWN, // 1183C..1189F
8609 WARANG_CITI, // 118A0..118F2
8610 UNKNOWN, // 118F3..118FE
8611 WARANG_CITI, // 118FF
8612 DIVES_AKURU, // 11900..11906
8613 UNKNOWN, // 11907..11908
8614 DIVES_AKURU, // 11909
8615 UNKNOWN, // 1190A..1190B
8616 DIVES_AKURU, // 1190C..11913
8617 UNKNOWN, // 11914
8618 DIVES_AKURU, // 11915..11916
8619 UNKNOWN, // 11917
8620 DIVES_AKURU, // 11918..11935
8621 UNKNOWN, // 11936
8622 DIVES_AKURU, // 11937..11938
8623 UNKNOWN, // 11939..1193A
8624 DIVES_AKURU, // 1193B..11946
8625 UNKNOWN, // 11947..1194F
8626 DIVES_AKURU, // 11950..11959
8627 UNKNOWN, // 1195A..1199F
8628 NANDINAGARI, // 119A0..119A7
8629 UNKNOWN, // 119A8..119A9
8630 NANDINAGARI, // 119AA..119D7
8631 UNKNOWN, // 119D8..119D9
8632 NANDINAGARI, // 119DA..119E4
8633 UNKNOWN, // 119E5..119FF
8634 ZANABAZAR_SQUARE, // 11A00..11A47
8635 UNKNOWN, // 11A48..11A4F
8636 SOYOMBO, // 11A50..11AA2
8637 UNKNOWN, // 11AA3..11AAF
8638 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8639 PAU_CIN_HAU, // 11AC0..11AF8
8640 UNKNOWN, // 11AF9..11AFF
8641 DEVANAGARI, // 11B00..11B09
8642 UNKNOWN, // 11B0A..11B5F
8643 SHARADA, // 11B60..11B67
8644 UNKNOWN, // 11B68..11BBF
8645 SUNUWAR, // 11BC0..11BE1
8646 UNKNOWN, // 11BE2..11BEF
8647 SUNUWAR, // 11BF0..11BF9
8648 UNKNOWN, // 11BFA..11BFF
8649 BHAIKSUKI, // 11C00..11C08
8650 UNKNOWN, // 11C09
8651 BHAIKSUKI, // 11C0A..11C36
8652 UNKNOWN, // 11C37
8653 BHAIKSUKI, // 11C38..11C45
8654 UNKNOWN, // 11C46..11C4F
8655 BHAIKSUKI, // 11C50..11C6C
8656 UNKNOWN, // 11C6D..11C6F
8657 MARCHEN, // 11C70..11C8F
8658 UNKNOWN, // 11C90..11C91
8659 MARCHEN, // 11C92..11CA7
8660 UNKNOWN, // 11CA8
8661 MARCHEN, // 11CA9..11CB6
8662 UNKNOWN, // 11CB7..11CFF
8663 MASARAM_GONDI, // 11D00..11D06
8664 UNKNOWN, // 11D07
8665 MASARAM_GONDI, // 11D08..11D09
8666 UNKNOWN, // 11D0A
8667 MASARAM_GONDI, // 11D0B..11D36
8668 UNKNOWN, // 11D37..11D39
8669 MASARAM_GONDI, // 11D3A
8670 UNKNOWN, // 11D3B
8671 MASARAM_GONDI, // 11D3C..11D3D
8672 UNKNOWN, // 11D3E
8673 MASARAM_GONDI, // 11D3F..11D47
8674 UNKNOWN, // 11D48..11D4F
8675 MASARAM_GONDI, // 11D50..11D59
8676 UNKNOWN, // 11D5A..11D5F
8677 GUNJALA_GONDI, // 11D60..11D65
8678 UNKNOWN, // 11D66
8679 GUNJALA_GONDI, // 11D67..11D68
8680 UNKNOWN, // 11D69
8681 GUNJALA_GONDI, // 11D6A..11D8E
8682 UNKNOWN, // 11D8F
8683 GUNJALA_GONDI, // 11D90..11D91
8684 UNKNOWN, // 11D92
8685 GUNJALA_GONDI, // 11D93..11D98
8686 UNKNOWN, // 11D99..11D9F
8687 GUNJALA_GONDI, // 11DA0..11DA9
8688 UNKNOWN, // 11DAA..11DAF
8689 TOLONG_SIKI, // 11DB0..11DDB
8690 UNKNOWN, // 11DDC..11DDF
8691 TOLONG_SIKI, // 11DE0..11DE9
8692 UNKNOWN, // 11DEA..11EDF
8693 MAKASAR, // 11EE0..11EF8
8694 UNKNOWN, // 11EF9..11EFF
8695 KAWI, // 11F00..11F10
8696 UNKNOWN, // 11F11
8697 KAWI, // 11F12..11F3A
8698 UNKNOWN, // 11F3B..11F3D
8699 KAWI, // 11F3E..11F5A
8700 UNKNOWN, // 11F5B..11FAF
8701 LISU, // 11FB0
8702 UNKNOWN, // 11FB1..11FBF
8703 TAMIL, // 11FC0..11FF1
8704 UNKNOWN, // 11FF2..11FFE
8705 TAMIL, // 11FFF
8706 CUNEIFORM, // 12000..12399
8707 UNKNOWN, // 1239A..123FF
8708 CUNEIFORM, // 12400..1246E
8709 UNKNOWN, // 1246F
8710 CUNEIFORM, // 12470..12474
8711 UNKNOWN, // 12475..1247F
8712 CUNEIFORM, // 12480..12543
8713 UNKNOWN, // 12544..12F8F
8714 CYPRO_MINOAN, // 12F90..12FF2
8715 UNKNOWN, // 12FF3..12FFF
8716 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8717 UNKNOWN, // 13456..1345F
8718 EGYPTIAN_HIEROGLYPHS, // 13460..143FA
8719 UNKNOWN, // 143FB..143FF
8720 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8721 UNKNOWN, // 14647..160FF
8722 GURUNG_KHEMA, // 16100..16139
8723 UNKNOWN, // 1613A..167FF
8724 BAMUM, // 16800..16A38
8725 UNKNOWN, // 16A39..16A3F
8726 MRO, // 16A40..16A5E
8727 UNKNOWN, // 16A5F
8728 MRO, // 16A60..16A69
8729 UNKNOWN, // 16A6A..16A6D
8730 MRO, // 16A6E..16A6F
8731 TANGSA, // 16A70..16ABE
8732 UNKNOWN, // 16ABF
8733 TANGSA, // 16AC0..16AC9
8734 UNKNOWN, // 16ACA..16ACF
8735 BASSA_VAH, // 16AD0..16AED
8736 UNKNOWN, // 16AEE..16AEF
8737 BASSA_VAH, // 16AF0..16AF5
8738 UNKNOWN, // 16AF6..16AFF
8739 PAHAWH_HMONG, // 16B00..16B45
8740 UNKNOWN, // 16B46..16B4F
8741 PAHAWH_HMONG, // 16B50..16B59
8742 UNKNOWN, // 16B5A
8743 PAHAWH_HMONG, // 16B5B..16B61
8744 UNKNOWN, // 16B62
8745 PAHAWH_HMONG, // 16B63..16B77
8746 UNKNOWN, // 16B78..16B7C
8747 PAHAWH_HMONG, // 16B7D..16B8F
8748 UNKNOWN, // 16B90..16D3F
8749 KIRAT_RAI, // 16D40..16D79
8750 UNKNOWN, // 16D7A..16E3F
8751 MEDEFAIDRIN, // 16E40..16E9A
8752 UNKNOWN, // 16E9B..16E9F
8753 BERIA_ERFE, // 16EA0..16EB8
8754 UNKNOWN, // 16EB9..16EBA
8755 BERIA_ERFE, // 16EBB..16ED3
8756 UNKNOWN, // 16ED4..16EFF
8757 MIAO, // 16F00..16F4A
8758 UNKNOWN, // 16F4B..16F4E
8759 MIAO, // 16F4F..16F87
8760 UNKNOWN, // 16F88..16F8E
8761 MIAO, // 16F8F..16F9F
8762 UNKNOWN, // 16FA0..16FDF
8763 TANGUT, // 16FE0
8764 NUSHU, // 16FE1
8765 HAN, // 16FE2..16FE3
8766 KHITAN_SMALL_SCRIPT, // 16FE4
8767 UNKNOWN, // 16FE5..16FEF
8768 HAN, // 16FF0..16FF6
8769 UNKNOWN, // 16FF7..16FFF
8770 TANGUT, // 17000..18AFF
8771 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8772 UNKNOWN, // 18CD6..18CFE
8773 KHITAN_SMALL_SCRIPT, // 18CFF
8774 TANGUT, // 18D00..18D1E
8775 UNKNOWN, // 18D1F..18D7F
8776 TANGUT, // 18D80..18DF2
8777 UNKNOWN, // 18DF3..1AFEF
8778 KATAKANA, // 1AFF0..1AFF3
8779 UNKNOWN, // 1AFF4
8780 KATAKANA, // 1AFF5..1AFFB
8781 UNKNOWN, // 1AFFC
8782 KATAKANA, // 1AFFD..1AFFE
8783 UNKNOWN, // 1AFFF
8784 KATAKANA, // 1B000
8785 HIRAGANA, // 1B001..1B11F
8786 KATAKANA, // 1B120..1B122
8787 UNKNOWN, // 1B123..1B131
8788 HIRAGANA, // 1B132
8789 UNKNOWN, // 1B133..1B14F
8790 HIRAGANA, // 1B150..1B152
8791 UNKNOWN, // 1B153..1B154
8792 KATAKANA, // 1B155
8793 UNKNOWN, // 1B156..1B163
8794 KATAKANA, // 1B164..1B167
8795 UNKNOWN, // 1B168..1B16F
8796 NUSHU, // 1B170..1B2FB
8797 UNKNOWN, // 1B2FC..1BBFF
8798 DUPLOYAN, // 1BC00..1BC6A
8799 UNKNOWN, // 1BC6B..1BC6F
8800 DUPLOYAN, // 1BC70..1BC7C
8801 UNKNOWN, // 1BC7D..1BC7F
8802 DUPLOYAN, // 1BC80..1BC88
8803 UNKNOWN, // 1BC89..1BC8F
8804 DUPLOYAN, // 1BC90..1BC99
8805 UNKNOWN, // 1BC9A..1BC9B
8806 DUPLOYAN, // 1BC9C..1BC9F
8807 COMMON, // 1BCA0..1BCA3
8808 UNKNOWN, // 1BCA4..1CBFF
8809 COMMON, // 1CC00..1CCFC
8810 UNKNOWN, // 1CCFD..1CCFF
8811 COMMON, // 1CD00..1CEB3
8812 UNKNOWN, // 1CEB4..1CEB9
8813 COMMON, // 1CEBA..1CED0
8814 UNKNOWN, // 1CED1..1CEDF
8815 COMMON, // 1CEE0..1CEF0
8816 UNKNOWN, // 1CEF1..1CEFF
8817 INHERITED, // 1CF00..1CF2D
8818 UNKNOWN, // 1CF2E..1CF2F
8819 INHERITED, // 1CF30..1CF46
8820 UNKNOWN, // 1CF47..1CF4F
8821 COMMON, // 1CF50..1CFC3
8822 UNKNOWN, // 1CFC4..1CFFF
8823 COMMON, // 1D000..1D0F5
8824 UNKNOWN, // 1D0F6..1D0FF
8825 COMMON, // 1D100..1D126
8826 UNKNOWN, // 1D127..1D128
8827 COMMON, // 1D129..1D166
8828 INHERITED, // 1D167..1D169
8829 COMMON, // 1D16A..1D17A
8830 INHERITED, // 1D17B..1D182
8831 COMMON, // 1D183..1D184
8832 INHERITED, // 1D185..1D18B
8833 COMMON, // 1D18C..1D1A9
8834 INHERITED, // 1D1AA..1D1AD
8835 COMMON, // 1D1AE..1D1EA
8836 UNKNOWN, // 1D1EB..1D1FF
8837 GREEK, // 1D200..1D245
8838 UNKNOWN, // 1D246..1D2BF
8839 COMMON, // 1D2C0..1D2D3
8840 UNKNOWN, // 1D2D4..1D2DF
8841 COMMON, // 1D2E0..1D2F3
8842 UNKNOWN, // 1D2F4..1D2FF
8843 COMMON, // 1D300..1D356
8844 UNKNOWN, // 1D357..1D35F
8845 COMMON, // 1D360..1D378
8846 UNKNOWN, // 1D379..1D3FF
8847 COMMON, // 1D400..1D454
8848 UNKNOWN, // 1D455
8849 COMMON, // 1D456..1D49C
8850 UNKNOWN, // 1D49D
8851 COMMON, // 1D49E..1D49F
8852 UNKNOWN, // 1D4A0..1D4A1
8853 COMMON, // 1D4A2
8854 UNKNOWN, // 1D4A3..1D4A4
8855 COMMON, // 1D4A5..1D4A6
8856 UNKNOWN, // 1D4A7..1D4A8
8857 COMMON, // 1D4A9..1D4AC
8858 UNKNOWN, // 1D4AD
8859 COMMON, // 1D4AE..1D4B9
8860 UNKNOWN, // 1D4BA
8861 COMMON, // 1D4BB
8862 UNKNOWN, // 1D4BC
8863 COMMON, // 1D4BD..1D4C3
8864 UNKNOWN, // 1D4C4
8865 COMMON, // 1D4C5..1D505
8866 UNKNOWN, // 1D506
8867 COMMON, // 1D507..1D50A
8868 UNKNOWN, // 1D50B..1D50C
8869 COMMON, // 1D50D..1D514
8870 UNKNOWN, // 1D515
8871 COMMON, // 1D516..1D51C
8872 UNKNOWN, // 1D51D
8873 COMMON, // 1D51E..1D539
8874 UNKNOWN, // 1D53A
8875 COMMON, // 1D53B..1D53E
8876 UNKNOWN, // 1D53F
8877 COMMON, // 1D540..1D544
8878 UNKNOWN, // 1D545
8879 COMMON, // 1D546
8880 UNKNOWN, // 1D547..1D549
8881 COMMON, // 1D54A..1D550
8882 UNKNOWN, // 1D551
8883 COMMON, // 1D552..1D6A5
8884 UNKNOWN, // 1D6A6..1D6A7
8885 COMMON, // 1D6A8..1D7CB
8886 UNKNOWN, // 1D7CC..1D7CD
8887 COMMON, // 1D7CE..1D7FF
8888 SIGNWRITING, // 1D800..1DA8B
8889 UNKNOWN, // 1DA8C..1DA9A
8890 SIGNWRITING, // 1DA9B..1DA9F
8891 UNKNOWN, // 1DAA0
8892 SIGNWRITING, // 1DAA1..1DAAF
8893 UNKNOWN, // 1DAB0..1DEFF
8894 LATIN, // 1DF00..1DF1E
8895 UNKNOWN, // 1DF1F..1DF24
8896 LATIN, // 1DF25..1DF2A
8897 UNKNOWN, // 1DF2B..1DFFF
8898 GLAGOLITIC, // 1E000..1E006
8899 UNKNOWN, // 1E007
8900 GLAGOLITIC, // 1E008..1E018
8901 UNKNOWN, // 1E019..1E01A
8902 GLAGOLITIC, // 1E01B..1E021
8903 UNKNOWN, // 1E022
8904 GLAGOLITIC, // 1E023..1E024
8905 UNKNOWN, // 1E025
8906 GLAGOLITIC, // 1E026..1E02A
8907 UNKNOWN, // 1E02B..1E02F
8908 CYRILLIC, // 1E030..1E06D
8909 UNKNOWN, // 1E06E..1E08E
8910 CYRILLIC, // 1E08F
8911 UNKNOWN, // 1E090..1E0FF
8912 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8913 UNKNOWN, // 1E12D..1E12F
8914 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8915 UNKNOWN, // 1E13E..1E13F
8916 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8917 UNKNOWN, // 1E14A..1E14D
8918 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8919 UNKNOWN, // 1E150..1E28F
8920 TOTO, // 1E290..1E2AE
8921 UNKNOWN, // 1E2AF..1E2BF
8922 WANCHO, // 1E2C0..1E2F9
8923 UNKNOWN, // 1E2FA..1E2FE
8924 WANCHO, // 1E2FF
8925 UNKNOWN, // 1E300..1E4CF
8926 NAG_MUNDARI, // 1E4D0..1E4F9
8927 UNKNOWN, // 1E4FA..1E5CF
8928 OL_ONAL, // 1E5D0..1E5FA
8929 UNKNOWN, // 1E5FB..1E5FE
8930 OL_ONAL, // 1E5FF
8931 UNKNOWN, // 1E600..1E6BF
8932 TAI_YO, // 1E6C0..1E6DE
8933 UNKNOWN, // 1E6DF
8934 TAI_YO, // 1E6E0..1E6F5
8935 UNKNOWN, // 1E6F6..1E6FD
8936 TAI_YO, // 1E6FE..1E6FF
8937 UNKNOWN, // 1E700..1E7DF
8938 ETHIOPIC, // 1E7E0..1E7E6
8939 UNKNOWN, // 1E7E7
8940 ETHIOPIC, // 1E7E8..1E7EB
8941 UNKNOWN, // 1E7EC
8942 ETHIOPIC, // 1E7ED..1E7EE
8943 UNKNOWN, // 1E7EF
8944 ETHIOPIC, // 1E7F0..1E7FE
8945 UNKNOWN, // 1E7FF
8946 MENDE_KIKAKUI, // 1E800..1E8C4
8947 UNKNOWN, // 1E8C5..1E8C6
8948 MENDE_KIKAKUI, // 1E8C7..1E8D6
8949 UNKNOWN, // 1E8D7..1E8FF
8950 ADLAM, // 1E900..1E94B
8951 UNKNOWN, // 1E94C..1E94F
8952 ADLAM, // 1E950..1E959
8953 UNKNOWN, // 1E95A..1E95D
8954 ADLAM, // 1E95E..1E95F
8955 UNKNOWN, // 1E960..1EC70
8956 COMMON, // 1EC71..1ECB4
8957 UNKNOWN, // 1ECB5..1ED00
8958 COMMON, // 1ED01..1ED3D
8959 UNKNOWN, // 1ED3E..1EDFF
8960 ARABIC, // 1EE00..1EE03
8961 UNKNOWN, // 1EE04
8962 ARABIC, // 1EE05..1EE1F
8963 UNKNOWN, // 1EE20
8964 ARABIC, // 1EE21..1EE22
8965 UNKNOWN, // 1EE23
8966 ARABIC, // 1EE24
8967 UNKNOWN, // 1EE25..1EE26
8968 ARABIC, // 1EE27
8969 UNKNOWN, // 1EE28
8970 ARABIC, // 1EE29..1EE32
8971 UNKNOWN, // 1EE33
8972 ARABIC, // 1EE34..1EE37
8973 UNKNOWN, // 1EE38
8974 ARABIC, // 1EE39
8975 UNKNOWN, // 1EE3A
8976 ARABIC, // 1EE3B
8977 UNKNOWN, // 1EE3C..1EE41
8978 ARABIC, // 1EE42
8979 UNKNOWN, // 1EE43..1EE46
8980 ARABIC, // 1EE47
8981 UNKNOWN, // 1EE48
8982 ARABIC, // 1EE49
8983 UNKNOWN, // 1EE4A
8984 ARABIC, // 1EE4B
8985 UNKNOWN, // 1EE4C
8986 ARABIC, // 1EE4D..1EE4F
8987 UNKNOWN, // 1EE50
8988 ARABIC, // 1EE51..1EE52
8989 UNKNOWN, // 1EE53
8990 ARABIC, // 1EE54
8991 UNKNOWN, // 1EE55..1EE56
8992 ARABIC, // 1EE57
8993 UNKNOWN, // 1EE58
8994 ARABIC, // 1EE59
8995 UNKNOWN, // 1EE5A
8996 ARABIC, // 1EE5B
8997 UNKNOWN, // 1EE5C
8998 ARABIC, // 1EE5D
8999 UNKNOWN, // 1EE5E
9000 ARABIC, // 1EE5F
9001 UNKNOWN, // 1EE60
9002 ARABIC, // 1EE61..1EE62
9003 UNKNOWN, // 1EE63
9004 ARABIC, // 1EE64
9005 UNKNOWN, // 1EE65..1EE66
9006 ARABIC, // 1EE67..1EE6A
9007 UNKNOWN, // 1EE6B
9008 ARABIC, // 1EE6C..1EE72
9009 UNKNOWN, // 1EE73
9010 ARABIC, // 1EE74..1EE77
9011 UNKNOWN, // 1EE78
9012 ARABIC, // 1EE79..1EE7C
9013 UNKNOWN, // 1EE7D
9014 ARABIC, // 1EE7E
9015 UNKNOWN, // 1EE7F
9016 ARABIC, // 1EE80..1EE89
9017 UNKNOWN, // 1EE8A
9018 ARABIC, // 1EE8B..1EE9B
9019 UNKNOWN, // 1EE9C..1EEA0
9020 ARABIC, // 1EEA1..1EEA3
9021 UNKNOWN, // 1EEA4
9022 ARABIC, // 1EEA5..1EEA9
9023 UNKNOWN, // 1EEAA
9024 ARABIC, // 1EEAB..1EEBB
9025 UNKNOWN, // 1EEBC..1EEEF
9026 ARABIC, // 1EEF0..1EEF1
9027 UNKNOWN, // 1EEF2..1EFFF
9028 COMMON, // 1F000..1F02B
9029 UNKNOWN, // 1F02C..1F02F
9030 COMMON, // 1F030..1F093
9031 UNKNOWN, // 1F094..1F09F
9032 COMMON, // 1F0A0..1F0AE
9033 UNKNOWN, // 1F0AF..1F0B0
9034 COMMON, // 1F0B1..1F0BF
9035 UNKNOWN, // 1F0C0
9036 COMMON, // 1F0C1..1F0CF
9037 UNKNOWN, // 1F0D0
9038 COMMON, // 1F0D1..1F0F5
9039 UNKNOWN, // 1F0F6..1F0FF
9040 COMMON, // 1F100..1F1AD
9041 UNKNOWN, // 1F1AE..1F1E5
9042 COMMON, // 1F1E6..1F1FF
9043 HIRAGANA, // 1F200
9044 COMMON, // 1F201..1F202
9045 UNKNOWN, // 1F203..1F20F
9046 COMMON, // 1F210..1F23B
9047 UNKNOWN, // 1F23C..1F23F
9048 COMMON, // 1F240..1F248
9049 UNKNOWN, // 1F249..1F24F
9050 COMMON, // 1F250..1F251
9051 UNKNOWN, // 1F252..1F25F
9052 COMMON, // 1F260..1F265
9053 UNKNOWN, // 1F266..1F2FF
9054 COMMON, // 1F300..1F6D8
9055 UNKNOWN, // 1F6D9..1F6DB
9056 COMMON, // 1F6DC..1F6EC
9057 UNKNOWN, // 1F6ED..1F6EF
9058 COMMON, // 1F6F0..1F6FC
9059 UNKNOWN, // 1F6FD..1F6FF
9060 COMMON, // 1F700..1F7D9
9061 UNKNOWN, // 1F7DA..1F7DF
9062 COMMON, // 1F7E0..1F7EB
9063 UNKNOWN, // 1F7EC..1F7EF
9064 COMMON, // 1F7F0
9065 UNKNOWN, // 1F7F1..1F7FF
9066 COMMON, // 1F800..1F80B
9067 UNKNOWN, // 1F80C..1F80F
9068 COMMON, // 1F810..1F847
9069 UNKNOWN, // 1F848..1F84F
9070 COMMON, // 1F850..1F859
9071 UNKNOWN, // 1F85A..1F85F
9072 COMMON, // 1F860..1F887
9073 UNKNOWN, // 1F888..1F88F
9074 COMMON, // 1F890..1F8AD
9075 UNKNOWN, // 1F8AE..1F8AF
9076 COMMON, // 1F8B0..1F8BB
9077 UNKNOWN, // 1F8BC..1F8BF
9078 COMMON, // 1F8C0..1F8C1
9079 UNKNOWN, // 1F8C2..1F8CF
9080 COMMON, // 1F8D0..1F8D8
9081 UNKNOWN, // 1F8D9..1F8FF
9082 COMMON, // 1F900..1FA57
9083 UNKNOWN, // 1FA58..1FA5F
9084 COMMON, // 1FA60..1FA6D
9085 UNKNOWN, // 1FA6E..1FA6F
9086 COMMON, // 1FA70..1FA7C
9087 UNKNOWN, // 1FA7D..1FA7F
9088 COMMON, // 1FA80..1FA8A
9089 UNKNOWN, // 1FA8B..1FA8D
9090 COMMON, // 1FA8E..1FAC6
9091 UNKNOWN, // 1FAC7
9092 COMMON, // 1FAC8
9093 UNKNOWN, // 1FAC9..1FACC
9094 COMMON, // 1FACD..1FADC
9095 UNKNOWN, // 1FADD..1FADE
9096 COMMON, // 1FADF..1FAEA
9097 UNKNOWN, // 1FAEB..1FAEE
9098 COMMON, // 1FAEF..1FAF8
9099 UNKNOWN, // 1FAF9..1FAFF
9100 COMMON, // 1FB00..1FB92
9101 UNKNOWN, // 1FB93
9102 COMMON, // 1FB94..1FBFA
9103 UNKNOWN, // 1FBFB..1FFFF
9104 HAN, // 20000..2A6DF
9105 UNKNOWN, // 2A6E0..2A6FF
9106 HAN, // 2A700..2B81D
9107 UNKNOWN, // 2B81E..2B81F
9108 HAN, // 2B820..2CEAD
9109 UNKNOWN, // 2CEAE..2CEAF
9110 HAN, // 2CEB0..2EBE0
9111 UNKNOWN, // 2EBE1..2EBEF
9112 HAN, // 2EBF0..2EE5D
9113 UNKNOWN, // 2EE5E..2F7FF
9114 HAN, // 2F800..2FA1D
9115 UNKNOWN, // 2FA1E..2FFFF
9116 HAN, // 30000..3134A
9117 UNKNOWN, // 3134B..3134F
9118 HAN, // 31350..33479
9119 UNKNOWN, // 3347A..E0000
9120 COMMON, // E0001
9121 UNKNOWN, // E0002..E001F
9122 COMMON, // E0020..E007F
9123 UNKNOWN, // E0080..E00FF
9124 INHERITED, // E0100..E01EF
9125 UNKNOWN, // E01F0..10FFFF
9126 };
9127
9128 private static final HashMap<String, Character.UnicodeScript> aliases;
9129 static {
9130 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
9131 aliases.put("ADLM", ADLAM);
9132 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
9133 aliases.put("AHOM", AHOM);
9134 aliases.put("ARAB", ARABIC);
9135 aliases.put("ARMI", IMPERIAL_ARAMAIC);
9136 aliases.put("ARMN", ARMENIAN);
9137 aliases.put("AVST", AVESTAN);
9138 aliases.put("BALI", BALINESE);
9139 aliases.put("BAMU", BAMUM);
9140 aliases.put("BASS", BASSA_VAH);
9141 aliases.put("BATK", BATAK);
9142 aliases.put("BENG", BENGALI);
9143 aliases.put("BERF", BERIA_ERFE);
9144 aliases.put("BHKS", BHAIKSUKI);
9145 aliases.put("BOPO", BOPOMOFO);
9146 aliases.put("BRAH", BRAHMI);
9147 aliases.put("BRAI", BRAILLE);
9148 aliases.put("BUGI", BUGINESE);
9149 aliases.put("BUHD", BUHID);
9150 aliases.put("CAKM", CHAKMA);
9151 aliases.put("CANS", CANADIAN_ABORIGINAL);
9152 aliases.put("CARI", CARIAN);
9153 aliases.put("CHAM", CHAM);
9154 aliases.put("CHER", CHEROKEE);
9155 aliases.put("CHRS", CHORASMIAN);
9156 aliases.put("COPT", COPTIC);
9157 aliases.put("CPMN", CYPRO_MINOAN);
9158 aliases.put("CPRT", CYPRIOT);
9159 aliases.put("CYRL", CYRILLIC);
9160 aliases.put("DEVA", DEVANAGARI);
9161 aliases.put("DIAK", DIVES_AKURU);
9162 aliases.put("DOGR", DOGRA);
9163 aliases.put("DSRT", DESERET);
9164 aliases.put("DUPL", DUPLOYAN);
9165 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
9166 aliases.put("ELBA", ELBASAN);
9167 aliases.put("ELYM", ELYMAIC);
9168 aliases.put("ETHI", ETHIOPIC);
9169 aliases.put("GARA", GARAY);
9170 aliases.put("GEOR", GEORGIAN);
9171 aliases.put("GLAG", GLAGOLITIC);
9172 aliases.put("GONG", GUNJALA_GONDI);
9173 aliases.put("GONM", MASARAM_GONDI);
9174 aliases.put("GOTH", GOTHIC);
9175 aliases.put("GRAN", GRANTHA);
9176 aliases.put("GREK", GREEK);
9177 aliases.put("GUJR", GUJARATI);
9178 aliases.put("GUKH", GURUNG_KHEMA);
9179 aliases.put("GURU", GURMUKHI);
9180 aliases.put("HANG", HANGUL);
9181 aliases.put("HANI", HAN);
9182 aliases.put("HANO", HANUNOO);
9183 aliases.put("HATR", HATRAN);
9184 aliases.put("HEBR", HEBREW);
9185 aliases.put("HIRA", HIRAGANA);
9186 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
9187 aliases.put("HMNG", PAHAWH_HMONG);
9188 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
9189 aliases.put("HUNG", OLD_HUNGARIAN);
9190 aliases.put("ITAL", OLD_ITALIC);
9191 aliases.put("JAVA", JAVANESE);
9192 aliases.put("KALI", KAYAH_LI);
9193 aliases.put("KANA", KATAKANA);
9194 aliases.put("KAWI", KAWI);
9195 aliases.put("KHAR", KHAROSHTHI);
9196 aliases.put("KHMR", KHMER);
9197 aliases.put("KHOJ", KHOJKI);
9198 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
9199 aliases.put("KNDA", KANNADA);
9200 aliases.put("KRAI", KIRAT_RAI);
9201 aliases.put("KTHI", KAITHI);
9202 aliases.put("LANA", TAI_THAM);
9203 aliases.put("LAOO", LAO);
9204 aliases.put("LATN", LATIN);
9205 aliases.put("LEPC", LEPCHA);
9206 aliases.put("LIMB", LIMBU);
9207 aliases.put("LINA", LINEAR_A);
9208 aliases.put("LINB", LINEAR_B);
9209 aliases.put("LISU", LISU);
9210 aliases.put("LYCI", LYCIAN);
9211 aliases.put("LYDI", LYDIAN);
9212 aliases.put("MAHJ", MAHAJANI);
9213 aliases.put("MAKA", MAKASAR);
9214 aliases.put("MAND", MANDAIC);
9215 aliases.put("MANI", MANICHAEAN);
9216 aliases.put("MARC", MARCHEN);
9217 aliases.put("MEDF", MEDEFAIDRIN);
9218 aliases.put("MEND", MENDE_KIKAKUI);
9219 aliases.put("MERC", MEROITIC_CURSIVE);
9220 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
9221 aliases.put("MLYM", MALAYALAM);
9222 aliases.put("MODI", MODI);
9223 aliases.put("MONG", MONGOLIAN);
9224 aliases.put("MROO", MRO);
9225 aliases.put("MTEI", MEETEI_MAYEK);
9226 aliases.put("MULT", MULTANI);
9227 aliases.put("MYMR", MYANMAR);
9228 aliases.put("NAGM", NAG_MUNDARI);
9229 aliases.put("NAND", NANDINAGARI);
9230 aliases.put("NARB", OLD_NORTH_ARABIAN);
9231 aliases.put("NBAT", NABATAEAN);
9232 aliases.put("NEWA", NEWA);
9233 aliases.put("NKOO", NKO);
9234 aliases.put("NSHU", NUSHU);
9235 aliases.put("OGAM", OGHAM);
9236 aliases.put("OLCK", OL_CHIKI);
9237 aliases.put("ONAO", OL_ONAL);
9238 aliases.put("ORKH", OLD_TURKIC);
9239 aliases.put("ORYA", ORIYA);
9240 aliases.put("OSGE", OSAGE);
9241 aliases.put("OSMA", OSMANYA);
9242 aliases.put("OUGR", OLD_UYGHUR);
9243 aliases.put("PALM", PALMYRENE);
9244 aliases.put("PAUC", PAU_CIN_HAU);
9245 aliases.put("PERM", OLD_PERMIC);
9246 aliases.put("PHAG", PHAGS_PA);
9247 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
9248 aliases.put("PHLP", PSALTER_PAHLAVI);
9249 aliases.put("PHNX", PHOENICIAN);
9250 aliases.put("PLRD", MIAO);
9251 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
9252 aliases.put("RJNG", REJANG);
9253 aliases.put("ROHG", HANIFI_ROHINGYA);
9254 aliases.put("RUNR", RUNIC);
9255 aliases.put("SAMR", SAMARITAN);
9256 aliases.put("SARB", OLD_SOUTH_ARABIAN);
9257 aliases.put("SAUR", SAURASHTRA);
9258 aliases.put("SGNW", SIGNWRITING);
9259 aliases.put("SHAW", SHAVIAN);
9260 aliases.put("SHRD", SHARADA);
9261 aliases.put("SIDD", SIDDHAM);
9262 aliases.put("SIDT", SIDETIC);
9263 aliases.put("SIND", KHUDAWADI);
9264 aliases.put("SINH", SINHALA);
9265 aliases.put("SOGD", SOGDIAN);
9266 aliases.put("SOGO", OLD_SOGDIAN);
9267 aliases.put("SORA", SORA_SOMPENG);
9268 aliases.put("SOYO", SOYOMBO);
9269 aliases.put("SUND", SUNDANESE);
9270 aliases.put("SUNU", SUNUWAR);
9271 aliases.put("SYLO", SYLOTI_NAGRI);
9272 aliases.put("SYRC", SYRIAC);
9273 aliases.put("TAGB", TAGBANWA);
9274 aliases.put("TAKR", TAKRI);
9275 aliases.put("TALE", TAI_LE);
9276 aliases.put("TALU", NEW_TAI_LUE);
9277 aliases.put("TAML", TAMIL);
9278 aliases.put("TANG", TANGUT);
9279 aliases.put("TAVT", TAI_VIET);
9280 aliases.put("TAYO", TAI_YO);
9281 aliases.put("TELU", TELUGU);
9282 aliases.put("TFNG", TIFINAGH);
9283 aliases.put("TGLG", TAGALOG);
9284 aliases.put("THAA", THAANA);
9285 aliases.put("THAI", THAI);
9286 aliases.put("TIBT", TIBETAN);
9287 aliases.put("TIRH", TIRHUTA);
9288 aliases.put("TNSA", TANGSA);
9289 aliases.put("TODR", TODHRI);
9290 aliases.put("TOLS", TOLONG_SIKI);
9291 aliases.put("TOTO", TOTO);
9292 aliases.put("TUTG", TULU_TIGALARI);
9293 aliases.put("UGAR", UGARITIC);
9294 aliases.put("VAII", VAI);
9295 aliases.put("VITH", VITHKUQI);
9296 aliases.put("WARA", WARANG_CITI);
9297 aliases.put("WCHO", WANCHO);
9298 aliases.put("XPEO", OLD_PERSIAN);
9299 aliases.put("XSUX", CUNEIFORM);
9300 aliases.put("YEZI", YEZIDI);
9301 aliases.put("YIII", YI);
9302 aliases.put("ZANB", ZANABAZAR_SQUARE);
9303 aliases.put("ZINH", INHERITED);
9304 aliases.put("ZYYY", COMMON);
9305 aliases.put("ZZZZ", UNKNOWN);
9306 }
9307
9308 /**
9309 * Returns the enum constant representing the Unicode script of which
9310 * the given character (Unicode code point) is assigned to.
9311 *
9312 * @param codePoint the character (Unicode code point) in question.
9313 * @return The {@code UnicodeScript} constant representing the
9314 * Unicode script of which this character is assigned to.
9315 *
9316 * @throws IllegalArgumentException if the specified
9317 * {@code codePoint} is an invalid Unicode code point.
9318 * @see Character#isValidCodePoint(int)
9319 *
9320 */
9321 public static UnicodeScript of(int codePoint) {
9322 if (!isValidCodePoint(codePoint))
9323 throw new IllegalArgumentException(
9324 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9325 int type = getType(codePoint);
9326 // leave SURROGATE and PRIVATE_USE for table lookup
9327 if (type == UNASSIGNED)
9328 return UNKNOWN;
9329 int index = Arrays.binarySearch(scriptStarts, codePoint);
9330 if (index < 0)
9331 index = -index - 2;
9332 return scripts[index];
9333 }
9334
9335 /**
9336 * Returns the UnicodeScript constant with the given Unicode script
9337 * name or the script name alias. Script names and their aliases are
9338 * determined by The Unicode Standard. The files {@code Scripts.txt}
9339 * and {@code PropertyValueAliases.txt} define script names
9340 * and the script name aliases for a particular version of the
9341 * standard. The {@link Character} class specifies the version of
9342 * the standard that it supports.
9343 * <p>
9344 * Character case is ignored for all of the valid script names.
9345 * The en_US locale's case mapping rules are used to provide
9346 * case-insensitive string comparisons for script name validation.
9347 *
9348 * @param scriptName A {@code UnicodeScript} name.
9349 * @return The {@code UnicodeScript} constant identified
9350 * by {@code scriptName}
9351 * @throws IllegalArgumentException if {@code scriptName} is an
9352 * invalid name
9353 * @throws NullPointerException if {@code scriptName} is null
9354 */
9355 public static final UnicodeScript forName(String scriptName) {
9356 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
9357 //.replace(' ', '_'));
9358 UnicodeScript sc = aliases.get(scriptName);
9359 if (sc != null)
9360 return sc;
9361 return valueOf(scriptName);
9362 }
9363 }
9364
9365 /**
9366 * The value of the {@code Character}.
9367 *
9368 * @serial
9369 */
9370 private final char value;
9371
9372 /** use serialVersionUID from JDK 1.0.2 for interoperability */
9373 @java.io.Serial
9374 private static final long serialVersionUID = 3786198910865385080L;
9375
9376 /**
9377 * Constructs a newly allocated {@code Character} object that
9378 * represents the specified {@code char} value.
9379 *
9380 * @param value the value to be represented by the
9381 * {@code Character} object.
9382 *
9383 * @deprecated
9384 * It is rarely appropriate to use this constructor. The static factory
9385 * {@link #valueOf(char)} is generally a better choice, as it is
9386 * likely to yield significantly better space and time performance.
9387 */
9388 @Deprecated(since="9")
9389 public Character(char value) {
9390 this.value = value;
9391 }
9392
9393 @AOTSafeClassInitializer
9394 private static final class CharacterCache {
9395 private CharacterCache(){}
9396
9397 @Stable
9398 static final Character[] cache;
9399 static Character[] archivedCache;
9400
9401 static {
9402 int size = 127 + 1;
9403
9404 // Load and use the archived cache if it exists
9405 CDS.initializeFromArchive(CharacterCache.class);
9406 if (archivedCache == null) {
9407 Character[] c = new Character[size];
9408 for (int i = 0; i < size; i++) {
9409 c[i] = new Character((char) i);
9410 }
9411 archivedCache = c;
9412 }
9413 cache = archivedCache;
9414 assert cache.length == size;
9415 }
9416 }
9417
9418 /**
9419 * Returns a {@code Character} instance representing the specified
9420 * {@code char} value.
9421 * <div class="preview-block">
9422 * <div class="preview-comment">
9423 * <p>
9424 * - When preview features are NOT enabled, {@code Character} is an identity class.
9425 * If a new {@code Character} instance is not required, this method
9426 * should generally be used in preference to the constructor
9427 * {@link #Character(char)}, as this method is likely to yield
9428 * significantly better space and time performance by caching
9429 * frequently requested values.
9430 * This method will always cache values in the range {@code
9431 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9432 * cache other values outside of this range.
9433 * </p>
9434 * <p>
9435 * - When preview features are enabled, {@code Character} is a {@linkplain Class#isValue value class}.
9436 * The {@code valueOf} behavior is the same as invoking the constructor,
9437 * whether cached or not.
9438 * </p>
9439 * </div>
9440 * </div>
9441 *
9442 * @param c a char value.
9443 * @return a {@code Character} instance representing {@code c}.
9444 * @since 1.5
9445 */
9446 @IntrinsicCandidate
9447 @DeserializeConstructor
9448 public static Character valueOf(char c) {
9449 if (c <= 127) { // must cache
9450 return CharacterCache.cache[(int)c];
9451 }
9452 return new Character(c);
9453 }
9454
9455 /**
9456 * Returns the value of this {@code Character} object.
9457 * @return the primitive {@code char} value represented by
9458 * this object.
9459 */
9460 @IntrinsicCandidate
9461 public char charValue() {
9462 return value;
9463 }
9464
9465 /**
9466 * Returns a hash code for this {@code Character}; equal to the result
9467 * of invoking {@code charValue()}.
9468 *
9469 * @return a hash code value for this {@code Character}
9470 */
9471 @Override
9472 public int hashCode() {
9473 return Character.hashCode(value);
9474 }
9475
9476 /**
9477 * Returns a hash code for a {@code char} value; compatible with
9478 * {@code Character.hashCode()}.
9479 *
9480 * @since 1.8
9481 *
9482 * @param value The {@code char} for which to return a hash code.
9483 * @return a hash code value for a {@code char} value.
9484 */
9485 public static int hashCode(char value) {
9486 return (int)value;
9487 }
9488
9489 /**
9490 * Compares this object against the specified object.
9491 * The result is {@code true} if and only if the argument is not
9492 * {@code null} and is a {@code Character} object that
9493 * represents the same {@code char} value as this object.
9494 *
9495 * @param obj the object to compare with.
9496 * @return {@code true} if the objects are the same;
9497 * {@code false} otherwise.
9498 */
9499 public boolean equals(Object obj) {
9500 if (obj instanceof Character c) {
9501 return value == c.charValue();
9502 }
9503 return false;
9504 }
9505
9506 /**
9507 * Returns a {@code String} object representing this
9508 * {@code Character}'s value. The result is a string of
9509 * length 1 whose sole component is the primitive
9510 * {@code char} value represented by this
9511 * {@code Character} object.
9512 *
9513 * @return a string representation of this object.
9514 */
9515 @Override
9516 public String toString() {
9517 return String.valueOf(value);
9518 }
9519
9520 /**
9521 * Returns a {@code String} object representing the
9522 * specified {@code char}. The result is a string of length
9523 * 1 consisting solely of the specified {@code char}.
9524 *
9525 * @apiNote This method cannot handle <a
9526 * href="#supplementary"> supplementary characters</a>. To support
9527 * all Unicode characters, including supplementary characters, use
9528 * the {@link #toString(int)} method.
9529 *
9530 * @param c the {@code char} to be converted
9531 * @return the string representation of the specified {@code char}
9532 * @since 1.4
9533 */
9534 public static String toString(char c) {
9535 return String.valueOf(c);
9536 }
9537
9538 /**
9539 * Returns a {@code String} object representing the
9540 * specified character (Unicode code point). The result is a string of
9541 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9542 *
9543 * @param codePoint the {@code codePoint} to be converted
9544 * @return the string representation of the specified {@code codePoint}
9545 * @throws IllegalArgumentException if the specified
9546 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9547 * valid Unicode code point}.
9548 * @since 11
9549 */
9550 public static String toString(int codePoint) {
9551 return String.valueOfCodePoint(codePoint);
9552 }
9553
9554 /**
9555 * Determines whether the specified code point is a valid
9556 * <a href="http://www.unicode.org/glossary/#code_point">
9557 * Unicode code point value</a>.
9558 *
9559 * @param codePoint the Unicode code point to be tested
9560 * @return {@code true} if the specified code point value is between
9561 * {@link #MIN_CODE_POINT} and
9562 * {@link #MAX_CODE_POINT} inclusive;
9563 * {@code false} otherwise.
9564 * @since 1.5
9565 */
9566 public static boolean isValidCodePoint(int codePoint) {
9567 // Optimized form of:
9568 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9569 int plane = codePoint >>> 16;
9570 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9571 }
9572
9573 /**
9574 * Determines whether the specified character (Unicode code point)
9575 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9576 * Such code points can be represented using a single {@code char}.
9577 *
9578 * @param codePoint the character (Unicode code point) to be tested
9579 * @return {@code true} if the specified code point is between
9580 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9581 * {@code false} otherwise.
9582 * @since 1.7
9583 */
9584 public static boolean isBmpCodePoint(int codePoint) {
9585 return codePoint >>> 16 == 0;
9586 // Optimized form of:
9587 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9588 // We consistently use logical shift (>>>) to facilitate
9589 // additional runtime optimizations.
9590 }
9591
9592 /**
9593 * Determines whether the specified character (Unicode code point)
9594 * is in the <a href="#supplementary">supplementary character</a> range.
9595 *
9596 * @param codePoint the character (Unicode code point) to be tested
9597 * @return {@code true} if the specified code point is between
9598 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9599 * {@link #MAX_CODE_POINT} inclusive;
9600 * {@code false} otherwise.
9601 * @since 1.5
9602 */
9603 public static boolean isSupplementaryCodePoint(int codePoint) {
9604 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9605 && codePoint < MAX_CODE_POINT + 1;
9606 }
9607
9608 /**
9609 * Determines if the given {@code char} value is a
9610 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9611 * Unicode high-surrogate code unit</a>
9612 * (also known as <i>leading-surrogate code unit</i>).
9613 *
9614 * <p>Such values do not represent characters by themselves,
9615 * but are used in the representation of
9616 * <a href="#supplementary">supplementary characters</a>
9617 * in the UTF-16 encoding.
9618 *
9619 * @param ch the {@code char} value to be tested.
9620 * @return {@code true} if the {@code char} value is between
9621 * {@link #MIN_HIGH_SURROGATE} and
9622 * {@link #MAX_HIGH_SURROGATE} inclusive;
9623 * {@code false} otherwise.
9624 * @see Character#isLowSurrogate(char)
9625 * @see Character.UnicodeBlock#of(int)
9626 * @since 1.5
9627 */
9628 public static boolean isHighSurrogate(char ch) {
9629 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9630 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9631 }
9632
9633 /**
9634 * Determines if the given {@code char} value is a
9635 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9636 * Unicode low-surrogate code unit</a>
9637 * (also known as <i>trailing-surrogate code unit</i>).
9638 *
9639 * <p>Such values do not represent characters by themselves,
9640 * but are used in the representation of
9641 * <a href="#supplementary">supplementary characters</a>
9642 * in the UTF-16 encoding.
9643 *
9644 * @param ch the {@code char} value to be tested.
9645 * @return {@code true} if the {@code char} value is between
9646 * {@link #MIN_LOW_SURROGATE} and
9647 * {@link #MAX_LOW_SURROGATE} inclusive;
9648 * {@code false} otherwise.
9649 * @see Character#isHighSurrogate(char)
9650 * @since 1.5
9651 */
9652 public static boolean isLowSurrogate(char ch) {
9653 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9654 }
9655
9656 /**
9657 * Determines if the given {@code char} value is a Unicode
9658 * <i>surrogate code unit</i>.
9659 *
9660 * <p>Such values do not represent characters by themselves,
9661 * but are used in the representation of
9662 * <a href="#supplementary">supplementary characters</a>
9663 * in the UTF-16 encoding.
9664 *
9665 * <p>A char value is a surrogate code unit if and only if it is either
9666 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9667 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9668 *
9669 * @param ch the {@code char} value to be tested.
9670 * @return {@code true} if the {@code char} value is between
9671 * {@link #MIN_SURROGATE} and
9672 * {@link #MAX_SURROGATE} inclusive;
9673 * {@code false} otherwise.
9674 * @since 1.7
9675 */
9676 public static boolean isSurrogate(char ch) {
9677 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9678 }
9679
9680 /**
9681 * Determines whether the specified pair of {@code char}
9682 * values is a valid
9683 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9684 * Unicode surrogate pair</a>.
9685 *
9686 * <p>This method is equivalent to the expression:
9687 * <blockquote><pre>{@code
9688 * isHighSurrogate(high) && isLowSurrogate(low)
9689 * }</pre></blockquote>
9690 *
9691 * @param high the high-surrogate code value to be tested
9692 * @param low the low-surrogate code value to be tested
9693 * @return {@code true} if the specified high and
9694 * low-surrogate code values represent a valid surrogate pair;
9695 * {@code false} otherwise.
9696 * @since 1.5
9697 */
9698 public static boolean isSurrogatePair(char high, char low) {
9699 return isHighSurrogate(high) && isLowSurrogate(low);
9700 }
9701
9702 /**
9703 * Determines the number of {@code char} values needed to
9704 * represent the specified character (Unicode code point). If the
9705 * specified character is equal to or greater than 0x10000, then
9706 * the method returns 2. Otherwise, the method returns 1.
9707 *
9708 * <p>This method doesn't validate the specified character to be a
9709 * valid Unicode code point. The caller must validate the
9710 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9711 * if necessary.
9712 *
9713 * @param codePoint the character (Unicode code point) to be tested.
9714 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9715 * @see Character#isSupplementaryCodePoint(int)
9716 * @since 1.5
9717 */
9718 public static int charCount(int codePoint) {
9719 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9720 }
9721
9722 /**
9723 * Converts the specified surrogate pair to its supplementary code
9724 * point value. This method does not validate the specified
9725 * surrogate pair. The caller must validate it using {@link
9726 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9727 *
9728 * @param high the high-surrogate code unit
9729 * @param low the low-surrogate code unit
9730 * @return the supplementary code point composed from the
9731 * specified surrogate pair.
9732 * @since 1.5
9733 */
9734 public static int toCodePoint(char high, char low) {
9735 // Optimized form of:
9736 // return ((high - MIN_HIGH_SURROGATE) << 10)
9737 // + (low - MIN_LOW_SURROGATE)
9738 // + MIN_SUPPLEMENTARY_CODE_POINT;
9739 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9740 - (MIN_HIGH_SURROGATE << 10)
9741 - MIN_LOW_SURROGATE);
9742 }
9743
9744 /**
9745 * Returns the code point at the given index of the
9746 * {@code CharSequence}. If the {@code char} value at
9747 * the given index in the {@code CharSequence} is in the
9748 * high-surrogate range, the following index is less than the
9749 * length of the {@code CharSequence}, and the
9750 * {@code char} value at the following index is in the
9751 * low-surrogate range, then the supplementary code point
9752 * corresponding to this surrogate pair is returned. Otherwise,
9753 * the {@code char} value at the given index is returned.
9754 *
9755 * @param seq a sequence of {@code char} values (Unicode code
9756 * units)
9757 * @param index the index to the {@code char} values (Unicode
9758 * code units) in {@code seq} to be converted
9759 * @return the Unicode code point at the given index
9760 * @throws NullPointerException if {@code seq} is null.
9761 * @throws IndexOutOfBoundsException if the value
9762 * {@code index} is negative or not less than
9763 * {@link CharSequence#length() seq.length()}.
9764 * @since 1.5
9765 */
9766 public static int codePointAt(CharSequence seq, int index) {
9767 char c1 = seq.charAt(index);
9768 if (isHighSurrogate(c1) && ++index < seq.length()) {
9769 char c2 = seq.charAt(index);
9770 if (isLowSurrogate(c2)) {
9771 return toCodePoint(c1, c2);
9772 }
9773 }
9774 return c1;
9775 }
9776
9777 /**
9778 * Returns the code point at the given index of the
9779 * {@code char} array. If the {@code char} value at
9780 * the given index in the {@code char} array is in the
9781 * high-surrogate range, the following index is less than the
9782 * length of the {@code char} array, and the
9783 * {@code char} value at the following index is in the
9784 * low-surrogate range, then the supplementary code point
9785 * corresponding to this surrogate pair is returned. Otherwise,
9786 * the {@code char} value at the given index is returned.
9787 *
9788 * @param a the {@code char} array
9789 * @param index the index to the {@code char} values (Unicode
9790 * code units) in the {@code char} array to be converted
9791 * @return the Unicode code point at the given index
9792 * @throws NullPointerException if {@code a} is null.
9793 * @throws IndexOutOfBoundsException if the value
9794 * {@code index} is negative or not less than
9795 * the length of the {@code char} array.
9796 * @since 1.5
9797 */
9798 public static int codePointAt(char[] a, int index) {
9799 return codePointAtImpl(a, index, a.length);
9800 }
9801
9802 /**
9803 * Returns the code point at the given index of the
9804 * {@code char} array, where only array elements with
9805 * {@code index} less than {@code limit} can be used. If
9806 * the {@code char} value at the given index in the
9807 * {@code char} array is in the high-surrogate range, the
9808 * following index is less than the {@code limit}, and the
9809 * {@code char} value at the following index is in the
9810 * low-surrogate range, then the supplementary code point
9811 * corresponding to this surrogate pair is returned. Otherwise,
9812 * the {@code char} value at the given index is returned.
9813 *
9814 * @param a the {@code char} array
9815 * @param index the index to the {@code char} values (Unicode
9816 * code units) in the {@code char} array to be converted
9817 * @param limit the index after the last array element that
9818 * can be used in the {@code char} array
9819 * @return the Unicode code point at the given index
9820 * @throws NullPointerException if {@code a} is null.
9821 * @throws IndexOutOfBoundsException if the {@code index}
9822 * argument is negative or not less than the {@code limit}
9823 * argument, or if the {@code limit} argument is negative or
9824 * greater than the length of the {@code char} array.
9825 * @since 1.5
9826 */
9827 public static int codePointAt(char[] a, int index, int limit) {
9828 if (index >= limit || index < 0 || limit > a.length) {
9829 throw new IndexOutOfBoundsException();
9830 }
9831 return codePointAtImpl(a, index, limit);
9832 }
9833
9834 // throws ArrayIndexOutOfBoundsException if index out of bounds
9835 static int codePointAtImpl(char[] a, int index, int limit) {
9836 char c1 = a[index];
9837 if (isHighSurrogate(c1) && ++index < limit) {
9838 char c2 = a[index];
9839 if (isLowSurrogate(c2)) {
9840 return toCodePoint(c1, c2);
9841 }
9842 }
9843 return c1;
9844 }
9845
9846 /**
9847 * Returns the code point preceding the given index of the
9848 * {@code CharSequence}. If the {@code char} value at
9849 * {@code (index - 1)} in the {@code CharSequence} is in
9850 * the low-surrogate range, {@code (index - 2)} is not
9851 * negative, and the {@code char} value at {@code (index - 2)}
9852 * in the {@code CharSequence} is in the
9853 * high-surrogate range, then the supplementary code point
9854 * corresponding to this surrogate pair is returned. Otherwise,
9855 * the {@code char} value at {@code (index - 1)} is
9856 * returned.
9857 *
9858 * @param seq the {@code CharSequence} instance
9859 * @param index the index following the code point that should be returned
9860 * @return the Unicode code point value before the given index.
9861 * @throws NullPointerException if {@code seq} is null.
9862 * @throws IndexOutOfBoundsException if the {@code index}
9863 * argument is less than 1 or greater than {@link
9864 * CharSequence#length() seq.length()}.
9865 * @since 1.5
9866 */
9867 public static int codePointBefore(CharSequence seq, int index) {
9868 char c2 = seq.charAt(--index);
9869 if (isLowSurrogate(c2) && index > 0) {
9870 char c1 = seq.charAt(--index);
9871 if (isHighSurrogate(c1)) {
9872 return toCodePoint(c1, c2);
9873 }
9874 }
9875 return c2;
9876 }
9877
9878 /**
9879 * Returns the code point preceding the given index of the
9880 * {@code char} array. If the {@code char} value at
9881 * {@code (index - 1)} in the {@code char} array is in
9882 * the low-surrogate range, {@code (index - 2)} is not
9883 * negative, and the {@code char} value at {@code (index - 2)}
9884 * in the {@code char} array is in the
9885 * high-surrogate range, then the supplementary code point
9886 * corresponding to this surrogate pair is returned. Otherwise,
9887 * the {@code char} value at {@code (index - 1)} is
9888 * returned.
9889 *
9890 * @param a the {@code char} array
9891 * @param index the index following the code point that should be returned
9892 * @return the Unicode code point value before the given index.
9893 * @throws NullPointerException if {@code a} is null.
9894 * @throws IndexOutOfBoundsException if the {@code index}
9895 * argument is less than 1 or greater than the length of the
9896 * {@code char} array
9897 * @since 1.5
9898 */
9899 public static int codePointBefore(char[] a, int index) {
9900 return codePointBeforeImpl(a, index, 0);
9901 }
9902
9903 /**
9904 * Returns the code point preceding the given index of the
9905 * {@code char} array, where only array elements with
9906 * {@code index} greater than or equal to {@code start}
9907 * can be used. If the {@code char} value at {@code (index - 1)}
9908 * in the {@code char} array is in the
9909 * low-surrogate range, {@code (index - 2)} is not less than
9910 * {@code start}, and the {@code char} value at
9911 * {@code (index - 2)} in the {@code char} array is in
9912 * the high-surrogate range, then the supplementary code point
9913 * corresponding to this surrogate pair is returned. Otherwise,
9914 * the {@code char} value at {@code (index - 1)} is
9915 * returned.
9916 *
9917 * @param a the {@code char} array
9918 * @param index the index following the code point that should be returned
9919 * @param start the index of the first array element in the
9920 * {@code char} array
9921 * @return the Unicode code point value before the given index.
9922 * @throws NullPointerException if {@code a} is null.
9923 * @throws IndexOutOfBoundsException if the {@code index}
9924 * argument is not greater than the {@code start} argument or
9925 * is greater than the length of the {@code char} array, or
9926 * if the {@code start} argument is negative or not less than
9927 * the length of the {@code char} array.
9928 * @since 1.5
9929 */
9930 public static int codePointBefore(char[] a, int index, int start) {
9931 if (index <= start || start < 0 || index > a.length) {
9932 throw new IndexOutOfBoundsException();
9933 }
9934 return codePointBeforeImpl(a, index, start);
9935 }
9936
9937 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9938 static int codePointBeforeImpl(char[] a, int index, int start) {
9939 char c2 = a[--index];
9940 if (isLowSurrogate(c2) && index > start) {
9941 char c1 = a[--index];
9942 if (isHighSurrogate(c1)) {
9943 return toCodePoint(c1, c2);
9944 }
9945 }
9946 return c2;
9947 }
9948
9949 /**
9950 * Returns the leading surrogate (a
9951 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9952 * high surrogate code unit</a>) of the
9953 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9954 * surrogate pair</a>
9955 * representing the specified supplementary character (Unicode
9956 * code point) in the UTF-16 encoding. If the specified character
9957 * is not a
9958 * <a href="Character.html#supplementary">supplementary character</a>,
9959 * an unspecified {@code char} is returned.
9960 *
9961 * <p>If
9962 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9963 * is {@code true}, then
9964 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9965 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9966 * are also always {@code true}.
9967 *
9968 * @param codePoint a supplementary character (Unicode code point)
9969 * @return the leading surrogate code unit used to represent the
9970 * character in the UTF-16 encoding
9971 * @since 1.7
9972 */
9973 public static char highSurrogate(int codePoint) {
9974 return (char) ((codePoint >>> 10)
9975 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9976 }
9977
9978 /**
9979 * Returns the trailing surrogate (a
9980 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9981 * low surrogate code unit</a>) of the
9982 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9983 * surrogate pair</a>
9984 * representing the specified supplementary character (Unicode
9985 * code point) in the UTF-16 encoding. If the specified character
9986 * is not a
9987 * <a href="Character.html#supplementary">supplementary character</a>,
9988 * an unspecified {@code char} is returned.
9989 *
9990 * <p>If
9991 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9992 * is {@code true}, then
9993 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9994 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9995 * are also always {@code true}.
9996 *
9997 * @param codePoint a supplementary character (Unicode code point)
9998 * @return the trailing surrogate code unit used to represent the
9999 * character in the UTF-16 encoding
10000 * @since 1.7
10001 */
10002 public static char lowSurrogate(int codePoint) {
10003 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
10004 }
10005
10006 /**
10007 * Converts the specified character (Unicode code point) to its
10008 * UTF-16 representation. If the specified code point is a BMP
10009 * (Basic Multilingual Plane or Plane 0) value, the same value is
10010 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
10011 * specified code point is a supplementary character, its
10012 * surrogate values are stored in {@code dst[dstIndex]}
10013 * (high-surrogate) and {@code dst[dstIndex+1]}
10014 * (low-surrogate), and 2 is returned.
10015 *
10016 * @param codePoint the character (Unicode code point) to be converted.
10017 * @param dst an array of {@code char} in which the
10018 * {@code codePoint}'s UTF-16 value is stored.
10019 * @param dstIndex the start index into the {@code dst}
10020 * array where the converted value is stored.
10021 * @return 1 if the code point is a BMP code point, 2 if the
10022 * code point is a supplementary code point.
10023 * @throws IllegalArgumentException if the specified
10024 * {@code codePoint} is not a valid Unicode code point.
10025 * @throws NullPointerException if the specified {@code dst} is null.
10026 * @throws IndexOutOfBoundsException if {@code dstIndex}
10027 * is negative or not less than {@code dst.length}, or if
10028 * {@code dst} at {@code dstIndex} doesn't have enough
10029 * array element(s) to store the resulting {@code char}
10030 * value(s). (If {@code dstIndex} is equal to
10031 * {@code dst.length-1} and the specified
10032 * {@code codePoint} is a supplementary character, the
10033 * high-surrogate value is not stored in
10034 * {@code dst[dstIndex]}.)
10035 * @since 1.5
10036 */
10037 public static int toChars(int codePoint, char[] dst, int dstIndex) {
10038 if (isBmpCodePoint(codePoint)) {
10039 dst[dstIndex] = (char) codePoint;
10040 return 1;
10041 } else if (isValidCodePoint(codePoint)) {
10042 toSurrogates(codePoint, dst, dstIndex);
10043 return 2;
10044 } else {
10045 throw new IllegalArgumentException(
10046 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10047 }
10048 }
10049
10050 /**
10051 * Converts the specified character (Unicode code point) to its
10052 * UTF-16 representation stored in a {@code char} array. If
10053 * the specified code point is a BMP (Basic Multilingual Plane or
10054 * Plane 0) value, the resulting {@code char} array has
10055 * the same value as {@code codePoint}. If the specified code
10056 * point is a supplementary code point, the resulting
10057 * {@code char} array has the corresponding surrogate pair.
10058 *
10059 * @param codePoint a Unicode code point
10060 * @return a {@code char} array having
10061 * {@code codePoint}'s UTF-16 representation.
10062 * @throws IllegalArgumentException if the specified
10063 * {@code codePoint} is not a valid Unicode code point.
10064 * @since 1.5
10065 */
10066 public static char[] toChars(int codePoint) {
10067 if (isBmpCodePoint(codePoint)) {
10068 return new char[] { (char) codePoint };
10069 } else if (isValidCodePoint(codePoint)) {
10070 char[] result = new char[2];
10071 toSurrogates(codePoint, result, 0);
10072 return result;
10073 } else {
10074 throw new IllegalArgumentException(
10075 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10076 }
10077 }
10078
10079 static void toSurrogates(int codePoint, char[] dst, int index) {
10080 // We write elements "backwards" to guarantee all-or-nothing
10081 dst[index+1] = lowSurrogate(codePoint);
10082 dst[index] = highSurrogate(codePoint);
10083 }
10084
10085 /**
10086 * Returns the number of Unicode code points in the text range of
10087 * the specified char sequence. The text range begins at the
10088 * specified {@code beginIndex} and extends to the
10089 * {@code char} at index {@code endIndex - 1}. Thus the
10090 * length (in {@code char}s) of the text range is
10091 * {@code endIndex-beginIndex}. Unpaired surrogates within
10092 * the text range count as one code point each.
10093 *
10094 * @param seq the char sequence
10095 * @param beginIndex the index to the first {@code char} of
10096 * the text range.
10097 * @param endIndex the index after the last {@code char} of
10098 * the text range.
10099 * @return the number of Unicode code points in the specified text
10100 * range
10101 * @throws NullPointerException if {@code seq} is null.
10102 * @throws IndexOutOfBoundsException if the
10103 * {@code beginIndex} is negative, or {@code endIndex}
10104 * is larger than the length of the given sequence, or
10105 * {@code beginIndex} is larger than {@code endIndex}.
10106 * @since 1.5
10107 */
10108 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
10109 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
10110 int n = endIndex - beginIndex;
10111 for (int i = beginIndex; i < endIndex; ) {
10112 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
10113 isLowSurrogate(seq.charAt(i))) {
10114 n--;
10115 i++;
10116 }
10117 }
10118 return n;
10119 }
10120
10121 /**
10122 * Returns the number of Unicode code points in a subarray of the
10123 * {@code char} array argument. The {@code offset}
10124 * argument is the index of the first {@code char} of the
10125 * subarray and the {@code count} argument specifies the
10126 * length of the subarray in {@code char}s. Unpaired
10127 * surrogates within the subarray count as one code point each.
10128 *
10129 * @param a the {@code char} array
10130 * @param offset the index of the first {@code char} in the
10131 * given {@code char} array
10132 * @param count the length of the subarray in {@code char}s
10133 * @return the number of Unicode code points in the specified subarray
10134 * @throws NullPointerException if {@code a} is null.
10135 * @throws IndexOutOfBoundsException if {@code offset} or
10136 * {@code count} is negative, or if {@code offset +
10137 * count} is larger than the length of the given array.
10138 * @since 1.5
10139 */
10140 public static int codePointCount(char[] a, int offset, int count) {
10141 Objects.checkFromIndexSize(offset, count, a.length);
10142 return codePointCountImpl(a, offset, count);
10143 }
10144
10145 static int codePointCountImpl(char[] a, int offset, int count) {
10146 int endIndex = offset + count;
10147 int n = count;
10148 for (int i = offset; i < endIndex; ) {
10149 if (isHighSurrogate(a[i++]) && i < endIndex &&
10150 isLowSurrogate(a[i])) {
10151 n--;
10152 i++;
10153 }
10154 }
10155 return n;
10156 }
10157
10158 /**
10159 * Returns the index within the given char sequence that is offset
10160 * from the given {@code index} by {@code codePointOffset}
10161 * code points. Unpaired surrogates within the text range given by
10162 * {@code index} and {@code codePointOffset} count as
10163 * one code point each.
10164 *
10165 * @param seq the char sequence
10166 * @param index the index to be offset
10167 * @param codePointOffset the offset in code points
10168 * @return the index within the char sequence
10169 * @throws NullPointerException if {@code seq} is null.
10170 * @throws IndexOutOfBoundsException if {@code index}
10171 * is negative or larger than the length of the char sequence,
10172 * or if {@code codePointOffset} is positive and the
10173 * subsequence starting with {@code index} has fewer than
10174 * {@code codePointOffset} code points, or if
10175 * {@code codePointOffset} is negative and the subsequence
10176 * before {@code index} has fewer than the absolute value
10177 * of {@code codePointOffset} code points.
10178 * @since 1.5
10179 */
10180 public static int offsetByCodePoints(CharSequence seq, int index,
10181 int codePointOffset) {
10182 int length = seq.length();
10183 if (index < 0 || index > length) {
10184 throw new IndexOutOfBoundsException();
10185 }
10186
10187 int x = index;
10188 if (codePointOffset >= 0) {
10189 int i;
10190 for (i = 0; x < length && i < codePointOffset; i++) {
10191 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
10192 isLowSurrogate(seq.charAt(x))) {
10193 x++;
10194 }
10195 }
10196 if (i < codePointOffset) {
10197 throw new IndexOutOfBoundsException();
10198 }
10199 } else {
10200 int i;
10201 for (i = codePointOffset; x > 0 && i < 0; i++) {
10202 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
10203 isHighSurrogate(seq.charAt(x-1))) {
10204 x--;
10205 }
10206 }
10207 if (i < 0) {
10208 throw new IndexOutOfBoundsException();
10209 }
10210 }
10211 return x;
10212 }
10213
10214 /**
10215 * Returns the index within the given {@code char} subarray
10216 * that is offset from the given {@code index} by
10217 * {@code codePointOffset} code points. The
10218 * {@code start} and {@code count} arguments specify a
10219 * subarray of the {@code char} array. Unpaired surrogates
10220 * within the text range given by {@code index} and
10221 * {@code codePointOffset} count as one code point each.
10222 *
10223 * @param a the {@code char} array
10224 * @param start the index of the first {@code char} of the
10225 * subarray
10226 * @param count the length of the subarray in {@code char}s
10227 * @param index the index to be offset
10228 * @param codePointOffset the offset in code points
10229 * @return the index within the subarray
10230 * @throws NullPointerException if {@code a} is null.
10231 * @throws IndexOutOfBoundsException
10232 * if {@code start} or {@code count} is negative,
10233 * or if {@code start + count} is larger than the length of
10234 * the given array,
10235 * or if {@code index} is less than {@code start} or
10236 * larger then {@code start + count},
10237 * or if {@code codePointOffset} is positive and the text range
10238 * starting with {@code index} and ending with {@code start + count - 1}
10239 * has fewer than {@code codePointOffset} code
10240 * points,
10241 * or if {@code codePointOffset} is negative and the text range
10242 * starting with {@code start} and ending with {@code index - 1}
10243 * has fewer than the absolute value of
10244 * {@code codePointOffset} code points.
10245 * @since 1.5
10246 */
10247 public static int offsetByCodePoints(char[] a, int start, int count,
10248 int index, int codePointOffset) {
10249 if (count > a.length-start || start < 0 || count < 0
10250 || index < start || index > start+count) {
10251 throw new IndexOutOfBoundsException();
10252 }
10253 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
10254 }
10255
10256 static int offsetByCodePointsImpl(char[]a, int start, int count,
10257 int index, int codePointOffset) {
10258 int x = index;
10259 if (codePointOffset >= 0) {
10260 int limit = start + count;
10261 int i;
10262 for (i = 0; x < limit && i < codePointOffset; i++) {
10263 if (isHighSurrogate(a[x++]) && x < limit &&
10264 isLowSurrogate(a[x])) {
10265 x++;
10266 }
10267 }
10268 if (i < codePointOffset) {
10269 throw new IndexOutOfBoundsException();
10270 }
10271 } else {
10272 int i;
10273 for (i = codePointOffset; x > start && i < 0; i++) {
10274 if (isLowSurrogate(a[--x]) && x > start &&
10275 isHighSurrogate(a[x-1])) {
10276 x--;
10277 }
10278 }
10279 if (i < 0) {
10280 throw new IndexOutOfBoundsException();
10281 }
10282 }
10283 return x;
10284 }
10285
10286 /**
10287 * Determines if the specified character is a lowercase character.
10288 * <p>
10289 * A character is lowercase if its general category type, provided
10290 * by {@code Character.getType(ch)}, is
10291 * {@code LOWERCASE_LETTER}, or it has contributory property
10292 * Other_Lowercase as defined by the Unicode Standard.
10293 * <p>
10294 * The following are examples of lowercase characters:
10295 * <blockquote><pre>
10296 * 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
10297 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10298 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10299 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10300 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10301 * </pre></blockquote>
10302 * <p> Many other Unicode characters are lowercase too.
10303 *
10304 * <p><b>Note:</b> This method cannot handle <a
10305 * href="#supplementary"> supplementary characters</a>. To support
10306 * all Unicode characters, including supplementary characters, use
10307 * the {@link #isLowerCase(int)} method.
10308 *
10309 * @param ch the character to be tested.
10310 * @return {@code true} if the character is lowercase;
10311 * {@code false} otherwise.
10312 * @see Character#isLowerCase(char)
10313 * @see Character#isTitleCase(char)
10314 * @see Character#toLowerCase(char)
10315 * @see Character#getType(char)
10316 */
10317 public static boolean isLowerCase(char ch) {
10318 return isLowerCase((int)ch);
10319 }
10320
10321 /**
10322 * Determines if the specified character (Unicode code point) is a
10323 * lowercase character.
10324 * <p>
10325 * A character is lowercase if its general category type, provided
10326 * by {@link Character#getType getType(codePoint)}, is
10327 * {@code LOWERCASE_LETTER}, or it has contributory property
10328 * Other_Lowercase as defined by the Unicode Standard.
10329 * <p>
10330 * The following are examples of lowercase characters:
10331 * <blockquote><pre>
10332 * 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
10333 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10334 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10335 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10336 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10337 * </pre></blockquote>
10338 * <p> Many other Unicode characters are lowercase too.
10339 *
10340 * @param codePoint the character (Unicode code point) to be tested.
10341 * @return {@code true} if the character is lowercase;
10342 * {@code false} otherwise.
10343 * @see Character#isLowerCase(int)
10344 * @see Character#isTitleCase(int)
10345 * @see Character#toLowerCase(int)
10346 * @see Character#getType(int)
10347 * @since 1.5
10348 */
10349 public static boolean isLowerCase(int codePoint) {
10350 return CharacterData.of(codePoint).isLowerCase(codePoint);
10351 }
10352
10353 /**
10354 * Determines if the specified character is an uppercase character.
10355 * <p>
10356 * A character is uppercase if its general category type, provided by
10357 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
10358 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10359 * <p>
10360 * The following are examples of uppercase characters:
10361 * <blockquote><pre>
10362 * 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
10363 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10364 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10365 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10366 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10367 * </pre></blockquote>
10368 * <p> Many other Unicode characters are uppercase too.
10369 *
10370 * <p><b>Note:</b> This method cannot handle <a
10371 * href="#supplementary"> supplementary characters</a>. To support
10372 * all Unicode characters, including supplementary characters, use
10373 * the {@link #isUpperCase(int)} method.
10374 *
10375 * @param ch the character to be tested.
10376 * @return {@code true} if the character is uppercase;
10377 * {@code false} otherwise.
10378 * @see Character#isLowerCase(char)
10379 * @see Character#isTitleCase(char)
10380 * @see Character#toUpperCase(char)
10381 * @see Character#getType(char)
10382 * @since 1.0
10383 */
10384 public static boolean isUpperCase(char ch) {
10385 return isUpperCase((int)ch);
10386 }
10387
10388 /**
10389 * Determines if the specified character (Unicode code point) is an uppercase character.
10390 * <p>
10391 * A character is uppercase if its general category type, provided by
10392 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
10393 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10394 * <p>
10395 * The following are examples of uppercase characters:
10396 * <blockquote><pre>
10397 * 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
10398 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10399 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10400 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10401 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10402 * </pre></blockquote>
10403 * <p> Many other Unicode characters are uppercase too.
10404 *
10405 * @param codePoint the character (Unicode code point) to be tested.
10406 * @return {@code true} if the character is uppercase;
10407 * {@code false} otherwise.
10408 * @see Character#isLowerCase(int)
10409 * @see Character#isTitleCase(int)
10410 * @see Character#toUpperCase(int)
10411 * @see Character#getType(int)
10412 * @since 1.5
10413 */
10414 public static boolean isUpperCase(int codePoint) {
10415 return CharacterData.of(codePoint).isUpperCase(codePoint);
10416 }
10417
10418 /**
10419 * Determines if the specified character is a titlecase character.
10420 * <p>
10421 * A character is a titlecase character if its general
10422 * category type, provided by {@code Character.getType(ch)},
10423 * is {@code TITLECASE_LETTER}.
10424 * <p>
10425 * Some characters look like pairs of Latin letters. For example, there
10426 * is an uppercase letter that looks like "LJ" and has a corresponding
10427 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10428 * is the appropriate form to use when rendering a word in lowercase
10429 * with initial capitals, as for a book title.
10430 * <p>
10431 * These are some of the Unicode characters for which this method returns
10432 * {@code true}:
10433 * <ul>
10434 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10435 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10436 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10437 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10438 * </ul>
10439 * <p> Many other Unicode characters are titlecase too.
10440 *
10441 * <p><b>Note:</b> This method cannot handle <a
10442 * href="#supplementary"> supplementary characters</a>. To support
10443 * all Unicode characters, including supplementary characters, use
10444 * the {@link #isTitleCase(int)} method.
10445 *
10446 * @param ch the character to be tested.
10447 * @return {@code true} if the character is titlecase;
10448 * {@code false} otherwise.
10449 * @see Character#isLowerCase(char)
10450 * @see Character#isUpperCase(char)
10451 * @see Character#toTitleCase(char)
10452 * @see Character#getType(char)
10453 * @since 1.0.2
10454 */
10455 public static boolean isTitleCase(char ch) {
10456 return isTitleCase((int)ch);
10457 }
10458
10459 /**
10460 * Determines if the specified character (Unicode code point) is a titlecase character.
10461 * <p>
10462 * A character is a titlecase character if its general
10463 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10464 * is {@code TITLECASE_LETTER}.
10465 * <p>
10466 * Some characters look like pairs of Latin letters. For example, there
10467 * is an uppercase letter that looks like "LJ" and has a corresponding
10468 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10469 * is the appropriate form to use when rendering a word in lowercase
10470 * with initial capitals, as for a book title.
10471 * <p>
10472 * These are some of the Unicode characters for which this method returns
10473 * {@code true}:
10474 * <ul>
10475 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10476 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10477 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10478 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10479 * </ul>
10480 * <p> Many other Unicode characters are titlecase too.
10481 *
10482 * @param codePoint the character (Unicode code point) to be tested.
10483 * @return {@code true} if the character is titlecase;
10484 * {@code false} otherwise.
10485 * @see Character#isLowerCase(int)
10486 * @see Character#isUpperCase(int)
10487 * @see Character#toTitleCase(int)
10488 * @see Character#getType(int)
10489 * @since 1.5
10490 */
10491 public static boolean isTitleCase(int codePoint) {
10492 return getType(codePoint) == Character.TITLECASE_LETTER;
10493 }
10494
10495 /**
10496 * Determines if the specified character is a digit.
10497 * <p>
10498 * A character is a digit if its general category type, provided
10499 * by {@code Character.getType(ch)}, is
10500 * {@code DECIMAL_DIGIT_NUMBER}.
10501 * <p>
10502 * Some Unicode character ranges that contain digits:
10503 * <ul>
10504 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10505 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10506 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10507 * Arabic-Indic digits
10508 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10509 * Extended Arabic-Indic digits
10510 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10511 * Devanagari digits
10512 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10513 * Fullwidth digits
10514 * </ul>
10515 *
10516 * Many other character ranges contain digits as well.
10517 *
10518 * <p><b>Note:</b> This method cannot handle <a
10519 * href="#supplementary"> supplementary characters</a>. To support
10520 * all Unicode characters, including supplementary characters, use
10521 * the {@link #isDigit(int)} method.
10522 *
10523 * @param ch the character to be tested.
10524 * @return {@code true} if the character is a digit;
10525 * {@code false} otherwise.
10526 * @see Character#digit(char, int)
10527 * @see Character#forDigit(int, int)
10528 * @see Character#getType(char)
10529 */
10530 public static boolean isDigit(char ch) {
10531 return isDigit((int)ch);
10532 }
10533
10534 /**
10535 * Determines if the specified character (Unicode code point) is a digit.
10536 * <p>
10537 * A character is a digit if its general category type, provided
10538 * by {@link Character#getType(int) getType(codePoint)}, is
10539 * {@code DECIMAL_DIGIT_NUMBER}.
10540 * <p>
10541 * Some Unicode character ranges that contain digits:
10542 * <ul>
10543 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10544 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10545 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10546 * Arabic-Indic digits
10547 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10548 * Extended Arabic-Indic digits
10549 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10550 * Devanagari digits
10551 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10552 * Fullwidth digits
10553 * </ul>
10554 *
10555 * Many other character ranges contain digits as well.
10556 *
10557 * @param codePoint the character (Unicode code point) to be tested.
10558 * @return {@code true} if the character is a digit;
10559 * {@code false} otherwise.
10560 * @see Character#forDigit(int, int)
10561 * @see Character#getType(int)
10562 * @since 1.5
10563 */
10564 public static boolean isDigit(int codePoint) {
10565 return CharacterData.of(codePoint).isDigit(codePoint);
10566 }
10567
10568 /**
10569 * Determines if a character is defined in Unicode.
10570 * <p>
10571 * A character is defined if at least one of the following is true:
10572 * <ul>
10573 * <li>It has an entry in the UnicodeData file.
10574 * <li>It has a value in a range defined by the UnicodeData file.
10575 * </ul>
10576 *
10577 * <p><b>Note:</b> This method cannot handle <a
10578 * href="#supplementary"> supplementary characters</a>. To support
10579 * all Unicode characters, including supplementary characters, use
10580 * the {@link #isDefined(int)} method.
10581 *
10582 * @param ch the character to be tested
10583 * @return {@code true} if the character has a defined meaning
10584 * in Unicode; {@code false} otherwise.
10585 * @see Character#isDigit(char)
10586 * @see Character#isLetter(char)
10587 * @see Character#isLetterOrDigit(char)
10588 * @see Character#isLowerCase(char)
10589 * @see Character#isTitleCase(char)
10590 * @see Character#isUpperCase(char)
10591 * @since 1.0.2
10592 */
10593 public static boolean isDefined(char ch) {
10594 return isDefined((int)ch);
10595 }
10596
10597 /**
10598 * Determines if a character (Unicode code point) is defined in Unicode.
10599 * <p>
10600 * A character is defined if at least one of the following is true:
10601 * <ul>
10602 * <li>It has an entry in the UnicodeData file.
10603 * <li>It has a value in a range defined by the UnicodeData file.
10604 * </ul>
10605 *
10606 * @param codePoint the character (Unicode code point) to be tested.
10607 * @return {@code true} if the character has a defined meaning
10608 * in Unicode; {@code false} otherwise.
10609 * @see Character#isDigit(int)
10610 * @see Character#isLetter(int)
10611 * @see Character#isLetterOrDigit(int)
10612 * @see Character#isLowerCase(int)
10613 * @see Character#isTitleCase(int)
10614 * @see Character#isUpperCase(int)
10615 * @since 1.5
10616 */
10617 public static boolean isDefined(int codePoint) {
10618 return getType(codePoint) != Character.UNASSIGNED;
10619 }
10620
10621 /**
10622 * Determines if the specified character is a letter.
10623 * <p>
10624 * A character is considered to be a letter if its general
10625 * category type, provided by {@code Character.getType(ch)},
10626 * is any of the following:
10627 * <ul>
10628 * <li> {@code UPPERCASE_LETTER}
10629 * <li> {@code LOWERCASE_LETTER}
10630 * <li> {@code TITLECASE_LETTER}
10631 * <li> {@code MODIFIER_LETTER}
10632 * <li> {@code OTHER_LETTER}
10633 * </ul>
10634 *
10635 * Not all letters have case. Many characters are
10636 * letters but are neither uppercase nor lowercase nor titlecase.
10637 *
10638 * <p><b>Note:</b> This method cannot handle <a
10639 * href="#supplementary"> supplementary characters</a>. To support
10640 * all Unicode characters, including supplementary characters, use
10641 * the {@link #isLetter(int)} method.
10642 *
10643 * @param ch the character to be tested.
10644 * @return {@code true} if the character is a letter;
10645 * {@code false} otherwise.
10646 * @see Character#isDigit(char)
10647 * @see Character#isJavaIdentifierStart(char)
10648 * @see Character#isJavaLetter(char)
10649 * @see Character#isJavaLetterOrDigit(char)
10650 * @see Character#isLetterOrDigit(char)
10651 * @see Character#isLowerCase(char)
10652 * @see Character#isTitleCase(char)
10653 * @see Character#isUnicodeIdentifierStart(char)
10654 * @see Character#isUpperCase(char)
10655 */
10656 public static boolean isLetter(char ch) {
10657 return isLetter((int)ch);
10658 }
10659
10660 /**
10661 * Determines if the specified character (Unicode code point) is a letter.
10662 * <p>
10663 * A character is considered to be a letter if its general
10664 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10665 * is any of the following:
10666 * <ul>
10667 * <li> {@code UPPERCASE_LETTER}
10668 * <li> {@code LOWERCASE_LETTER}
10669 * <li> {@code TITLECASE_LETTER}
10670 * <li> {@code MODIFIER_LETTER}
10671 * <li> {@code OTHER_LETTER}
10672 * </ul>
10673 *
10674 * Not all letters have case. Many characters are
10675 * letters but are neither uppercase nor lowercase nor titlecase.
10676 *
10677 * @param codePoint the character (Unicode code point) to be tested.
10678 * @return {@code true} if the character is a letter;
10679 * {@code false} otherwise.
10680 * @see Character#isDigit(int)
10681 * @see Character#isJavaIdentifierStart(int)
10682 * @see Character#isLetterOrDigit(int)
10683 * @see Character#isLowerCase(int)
10684 * @see Character#isTitleCase(int)
10685 * @see Character#isUnicodeIdentifierStart(int)
10686 * @see Character#isUpperCase(int)
10687 * @since 1.5
10688 */
10689 public static boolean isLetter(int codePoint) {
10690 return ((((1 << Character.UPPERCASE_LETTER) |
10691 (1 << Character.LOWERCASE_LETTER) |
10692 (1 << Character.TITLECASE_LETTER) |
10693 (1 << Character.MODIFIER_LETTER) |
10694 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10695 != 0;
10696 }
10697
10698 /**
10699 * Determines if the specified character is a letter or digit.
10700 * <p>
10701 * A character is considered to be a letter or digit if either
10702 * {@code Character.isLetter(char ch)} or
10703 * {@code Character.isDigit(char ch)} returns
10704 * {@code true} for the character.
10705 *
10706 * <p><b>Note:</b> This method cannot handle <a
10707 * href="#supplementary"> supplementary characters</a>. To support
10708 * all Unicode characters, including supplementary characters, use
10709 * the {@link #isLetterOrDigit(int)} method.
10710 *
10711 * @param ch the character to be tested.
10712 * @return {@code true} if the character is a letter or digit;
10713 * {@code false} otherwise.
10714 * @see Character#isDigit(char)
10715 * @see Character#isJavaIdentifierPart(char)
10716 * @see Character#isJavaLetter(char)
10717 * @see Character#isJavaLetterOrDigit(char)
10718 * @see Character#isLetter(char)
10719 * @see Character#isUnicodeIdentifierPart(char)
10720 * @since 1.0.2
10721 */
10722 public static boolean isLetterOrDigit(char ch) {
10723 return isLetterOrDigit((int)ch);
10724 }
10725
10726 /**
10727 * Determines if the specified character (Unicode code point) is a letter or digit.
10728 * <p>
10729 * A character is considered to be a letter or digit if either
10730 * {@link #isLetter(int) isLetter(codePoint)} or
10731 * {@link #isDigit(int) isDigit(codePoint)} returns
10732 * {@code true} for the character.
10733 *
10734 * @param codePoint the character (Unicode code point) to be tested.
10735 * @return {@code true} if the character is a letter or digit;
10736 * {@code false} otherwise.
10737 * @see Character#isDigit(int)
10738 * @see Character#isJavaIdentifierPart(int)
10739 * @see Character#isLetter(int)
10740 * @see Character#isUnicodeIdentifierPart(int)
10741 * @since 1.5
10742 */
10743 public static boolean isLetterOrDigit(int codePoint) {
10744 return ((((1 << Character.UPPERCASE_LETTER) |
10745 (1 << Character.LOWERCASE_LETTER) |
10746 (1 << Character.TITLECASE_LETTER) |
10747 (1 << Character.MODIFIER_LETTER) |
10748 (1 << Character.OTHER_LETTER) |
10749 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10750 != 0;
10751 }
10752
10753 /**
10754 * Determines if the specified character is permissible as the first
10755 * character in a Java identifier.
10756 * <p>
10757 * A character may start a Java identifier if and only if
10758 * one of the following conditions is true:
10759 * <ul>
10760 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10761 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10762 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10763 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10764 * </ul>
10765 *
10766 * @param ch the character to be tested.
10767 * @return {@code true} if the character may start a Java
10768 * identifier; {@code false} otherwise.
10769 * @see Character#isJavaLetterOrDigit(char)
10770 * @see Character#isJavaIdentifierStart(char)
10771 * @see Character#isJavaIdentifierPart(char)
10772 * @see Character#isLetter(char)
10773 * @see Character#isLetterOrDigit(char)
10774 * @see Character#isUnicodeIdentifierStart(char)
10775 * @since 1.0.2
10776 * @deprecated Replaced by isJavaIdentifierStart(char).
10777 */
10778 @Deprecated(since="1.1")
10779 public static boolean isJavaLetter(char ch) {
10780 return isJavaIdentifierStart(ch);
10781 }
10782
10783 /**
10784 * Determines if the specified character may be part of a Java
10785 * identifier as other than the first character.
10786 * <p>
10787 * A character may be part of a Java identifier if and only if one
10788 * of the following conditions is true:
10789 * <ul>
10790 * <li> it is a letter
10791 * <li> it is a currency symbol (such as {@code '$'})
10792 * <li> it is a connecting punctuation character (such as {@code '_'})
10793 * <li> it is a digit
10794 * <li> it is a numeric letter (such as a Roman numeral character)
10795 * <li> it is a combining mark
10796 * <li> it is a non-spacing mark
10797 * <li> {@code isIdentifierIgnorable} returns
10798 * {@code true} for the character.
10799 * </ul>
10800 *
10801 * @param ch the character to be tested.
10802 * @return {@code true} if the character may be part of a
10803 * Java identifier; {@code false} otherwise.
10804 * @see Character#isJavaLetter(char)
10805 * @see Character#isJavaIdentifierStart(char)
10806 * @see Character#isJavaIdentifierPart(char)
10807 * @see Character#isLetter(char)
10808 * @see Character#isLetterOrDigit(char)
10809 * @see Character#isUnicodeIdentifierPart(char)
10810 * @see Character#isIdentifierIgnorable(char)
10811 * @since 1.0.2
10812 * @deprecated Replaced by isJavaIdentifierPart(char).
10813 */
10814 @Deprecated(since="1.1")
10815 public static boolean isJavaLetterOrDigit(char ch) {
10816 return isJavaIdentifierPart(ch);
10817 }
10818
10819 /**
10820 * Determines if the specified character (Unicode code point) is alphabetic.
10821 * <p>
10822 * A character is considered to be alphabetic if its general category type,
10823 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10824 * the following:
10825 * <ul>
10826 * <li> {@code UPPERCASE_LETTER}
10827 * <li> {@code LOWERCASE_LETTER}
10828 * <li> {@code TITLECASE_LETTER}
10829 * <li> {@code MODIFIER_LETTER}
10830 * <li> {@code OTHER_LETTER}
10831 * <li> {@code LETTER_NUMBER}
10832 * </ul>
10833 * or it has contributory property Other_Alphabetic as defined by the
10834 * Unicode Standard.
10835 *
10836 * @param codePoint the character (Unicode code point) to be tested.
10837 * @return {@code true} if the character is a Unicode alphabet
10838 * character, {@code false} otherwise.
10839 * @since 1.7
10840 */
10841 public static boolean isAlphabetic(int codePoint) {
10842 return (((((1 << Character.UPPERCASE_LETTER) |
10843 (1 << Character.LOWERCASE_LETTER) |
10844 (1 << Character.TITLECASE_LETTER) |
10845 (1 << Character.MODIFIER_LETTER) |
10846 (1 << Character.OTHER_LETTER) |
10847 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10848 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10849 }
10850
10851 /**
10852 * Determines if the specified character (Unicode code point) is a CJKV
10853 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10854 * the Unicode Standard.
10855 *
10856 * @param codePoint the character (Unicode code point) to be tested.
10857 * @return {@code true} if the character is a Unicode ideograph
10858 * character, {@code false} otherwise.
10859 * @since 1.7
10860 */
10861 public static boolean isIdeographic(int codePoint) {
10862 return CharacterData.of(codePoint).isIdeographic(codePoint);
10863 }
10864
10865 /**
10866 * Determines if the specified character is
10867 * permissible as the first character in a Java identifier.
10868 * <p>
10869 * A character may start a Java identifier if and only if
10870 * one of the following conditions is true:
10871 * <ul>
10872 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10873 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10874 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10875 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10876 * </ul>
10877 *
10878 * <p><b>Note:</b> This method cannot handle <a
10879 * href="#supplementary"> supplementary characters</a>. To support
10880 * all Unicode characters, including supplementary characters, use
10881 * the {@link #isJavaIdentifierStart(int)} method.
10882 *
10883 * @param ch the character to be tested.
10884 * @return {@code true} if the character may start a Java identifier;
10885 * {@code false} otherwise.
10886 * @see Character#isJavaIdentifierPart(char)
10887 * @see Character#isLetter(char)
10888 * @see Character#isUnicodeIdentifierStart(char)
10889 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10890 * @since 1.1
10891 */
10892 @SuppressWarnings("doclint:reference") // cross-module links
10893 public static boolean isJavaIdentifierStart(char ch) {
10894 return isJavaIdentifierStart((int)ch);
10895 }
10896
10897 /**
10898 * Determines if the character (Unicode code point) is
10899 * permissible as the first character in a Java identifier.
10900 * <p>
10901 * A character may start a Java identifier if and only if
10902 * one of the following conditions is true:
10903 * <ul>
10904 * <li> {@link #isLetter(int) isLetter(codePoint)}
10905 * returns {@code true}
10906 * <li> {@link #getType(int) getType(codePoint)}
10907 * returns {@code LETTER_NUMBER}
10908 * <li> the referenced character is a currency symbol (such as {@code '$'})
10909 * <li> the referenced character is a connecting punctuation character
10910 * (such as {@code '_'}).
10911 * </ul>
10912 *
10913 * @param codePoint the character (Unicode code point) to be tested.
10914 * @return {@code true} if the character may start a Java identifier;
10915 * {@code false} otherwise.
10916 * @see Character#isJavaIdentifierPart(int)
10917 * @see Character#isLetter(int)
10918 * @see Character#isUnicodeIdentifierStart(int)
10919 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10920 * @since 1.5
10921 */
10922 @SuppressWarnings("doclint:reference") // cross-module links
10923 public static boolean isJavaIdentifierStart(int codePoint) {
10924 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10925 }
10926
10927 /**
10928 * Determines if the specified character may be part of a Java
10929 * identifier as other than the first character.
10930 * <p>
10931 * A character may be part of a Java identifier if any of the following
10932 * conditions are true:
10933 * <ul>
10934 * <li> it is a letter
10935 * <li> it is a currency symbol (such as {@code '$'})
10936 * <li> it is a connecting punctuation character (such as {@code '_'})
10937 * <li> it is a digit
10938 * <li> it is a numeric letter (such as a Roman numeral character)
10939 * <li> it is a combining mark
10940 * <li> it is a non-spacing mark
10941 * <li> {@code isIdentifierIgnorable} returns
10942 * {@code true} for the character
10943 * </ul>
10944 *
10945 * <p><b>Note:</b> This method cannot handle <a
10946 * href="#supplementary"> supplementary characters</a>. To support
10947 * all Unicode characters, including supplementary characters, use
10948 * the {@link #isJavaIdentifierPart(int)} method.
10949 *
10950 * @param ch the character to be tested.
10951 * @return {@code true} if the character may be part of a
10952 * Java identifier; {@code false} otherwise.
10953 * @see Character#isIdentifierIgnorable(char)
10954 * @see Character#isJavaIdentifierStart(char)
10955 * @see Character#isLetterOrDigit(char)
10956 * @see Character#isUnicodeIdentifierPart(char)
10957 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10958 * @since 1.1
10959 */
10960 @SuppressWarnings("doclint:reference") // cross-module links
10961 public static boolean isJavaIdentifierPart(char ch) {
10962 return isJavaIdentifierPart((int)ch);
10963 }
10964
10965 /**
10966 * Determines if the character (Unicode code point) may be part of a Java
10967 * identifier as other than the first character.
10968 * <p>
10969 * A character may be part of a Java identifier if any of the following
10970 * conditions are true:
10971 * <ul>
10972 * <li> it is a letter
10973 * <li> it is a currency symbol (such as {@code '$'})
10974 * <li> it is a connecting punctuation character (such as {@code '_'})
10975 * <li> it is a digit
10976 * <li> it is a numeric letter (such as a Roman numeral character)
10977 * <li> it is a combining mark
10978 * <li> it is a non-spacing mark
10979 * <li> {@link #isIdentifierIgnorable(int)
10980 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10981 * the code point
10982 * </ul>
10983 *
10984 * @param codePoint the character (Unicode code point) to be tested.
10985 * @return {@code true} if the character may be part of a
10986 * Java identifier; {@code false} otherwise.
10987 * @see Character#isIdentifierIgnorable(int)
10988 * @see Character#isJavaIdentifierStart(int)
10989 * @see Character#isLetterOrDigit(int)
10990 * @see Character#isUnicodeIdentifierPart(int)
10991 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10992 * @since 1.5
10993 */
10994 @SuppressWarnings("doclint:reference") // cross-module links
10995 public static boolean isJavaIdentifierPart(int codePoint) {
10996 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10997 }
10998
10999 /**
11000 * Determines if the specified character is permissible as the
11001 * first character in a Unicode identifier.
11002 * <p>
11003 * A character may start a Unicode identifier if and only if
11004 * one of the following conditions is true:
11005 * <ul>
11006 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
11007 * <li> {@link #getType(char) getType(ch)} returns
11008 * {@code LETTER_NUMBER}.
11009 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11010 * {@code Other_ID_Start}</a> character.
11011 * </ul>
11012 * <p>
11013 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11014 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11015 * with the following profile of UAX31:
11016 * <pre>
11017 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
11018 * </pre>
11019 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
11020 * compatibility.
11021 *
11022 * <p><b>Note:</b> This method cannot handle <a
11023 * href="#supplementary"> supplementary characters</a>. To support
11024 * all Unicode characters, including supplementary characters, use
11025 * the {@link #isUnicodeIdentifierStart(int)} method.
11026 *
11027 * @param ch the character to be tested.
11028 * @return {@code true} if the character may start a Unicode
11029 * identifier; {@code false} otherwise.
11030 *
11031 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11032 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11033 * @see Character#isJavaIdentifierStart(char)
11034 * @see Character#isLetter(char)
11035 * @see Character#isUnicodeIdentifierPart(char)
11036 * @since 1.1
11037 */
11038 public static boolean isUnicodeIdentifierStart(char ch) {
11039 return isUnicodeIdentifierStart((int)ch);
11040 }
11041
11042 /**
11043 * Determines if the specified character (Unicode code point) is permissible as the
11044 * first character in a Unicode identifier.
11045 * <p>
11046 * A character may start a Unicode identifier if and only if
11047 * one of the following conditions is true:
11048 * <ul>
11049 * <li> {@link #isLetter(int) isLetter(codePoint)}
11050 * returns {@code true}
11051 * <li> {@link #getType(int) getType(codePoint)}
11052 * returns {@code LETTER_NUMBER}.
11053 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11054 * {@code Other_ID_Start}</a> character.
11055 * </ul>
11056 * <p>
11057 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11058 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11059 * with the following profile of UAX31:
11060 * <pre>
11061 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
11062 * </pre>
11063 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
11064 * compatibility.
11065 *
11066 * @param codePoint the character (Unicode code point) to be tested.
11067 * @return {@code true} if the character may start a Unicode
11068 * identifier; {@code false} otherwise.
11069 *
11070 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11071 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11072 * @see Character#isJavaIdentifierStart(int)
11073 * @see Character#isLetter(int)
11074 * @see Character#isUnicodeIdentifierPart(int)
11075 * @since 1.5
11076 */
11077 public static boolean isUnicodeIdentifierStart(int codePoint) {
11078 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
11079 }
11080
11081 /**
11082 * Determines if the specified character may be part of a Unicode
11083 * identifier as other than the first character.
11084 * <p>
11085 * A character may be part of a Unicode identifier if and only if
11086 * one of the following statements is true:
11087 * <ul>
11088 * <li> it is a letter
11089 * <li> it is a connecting punctuation character (such as {@code '_'})
11090 * <li> it is a digit
11091 * <li> it is a numeric letter (such as a Roman numeral character)
11092 * <li> it is a combining mark
11093 * <li> it is a non-spacing mark
11094 * <li> {@code isIdentifierIgnorable} returns
11095 * {@code true} for this character.
11096 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11097 * {@code Other_ID_Start}</a> character.
11098 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
11099 * {@code Other_ID_Continue}</a> character.
11100 * </ul>
11101 * <p>
11102 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11103 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11104 * with the following profile of UAX31:
11105 * <pre>
11106 * Continue := Start + ID_Continue + ignorable
11107 * Medial := empty
11108 * ignorable := isIdentifierIgnorable(char) returns true for the character
11109 * </pre>
11110 * {@code ignorable} is added to {@code Continue} for backward
11111 * compatibility.
11112 *
11113 * <p><b>Note:</b> This method cannot handle <a
11114 * href="#supplementary"> supplementary characters</a>. To support
11115 * all Unicode characters, including supplementary characters, use
11116 * the {@link #isUnicodeIdentifierPart(int)} method.
11117 *
11118 * @param ch the character to be tested.
11119 * @return {@code true} if the character may be part of a
11120 * Unicode identifier; {@code false} otherwise.
11121 *
11122 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11123 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11124 * @see Character#isIdentifierIgnorable(char)
11125 * @see Character#isJavaIdentifierPart(char)
11126 * @see Character#isLetterOrDigit(char)
11127 * @see Character#isUnicodeIdentifierStart(char)
11128 * @since 1.1
11129 */
11130 public static boolean isUnicodeIdentifierPart(char ch) {
11131 return isUnicodeIdentifierPart((int)ch);
11132 }
11133
11134 /**
11135 * Determines if the specified character (Unicode code point) may be part of a Unicode
11136 * identifier as other than the first character.
11137 * <p>
11138 * A character may be part of a Unicode identifier if and only if
11139 * one of the following statements is true:
11140 * <ul>
11141 * <li> it is a letter
11142 * <li> it is a connecting punctuation character (such as {@code '_'})
11143 * <li> it is a digit
11144 * <li> it is a numeric letter (such as a Roman numeral character)
11145 * <li> it is a combining mark
11146 * <li> it is a non-spacing mark
11147 * <li> {@code isIdentifierIgnorable} returns
11148 * {@code true} for this character.
11149 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11150 * {@code Other_ID_Start}</a> character.
11151 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
11152 * {@code Other_ID_Continue}</a> character.
11153 * </ul>
11154 * <p>
11155 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11156 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11157 * with the following profile of UAX31:
11158 * <pre>
11159 * Continue := Start + ID_Continue + ignorable
11160 * Medial := empty
11161 * ignorable := isIdentifierIgnorable(int) returns true for the character
11162 * </pre>
11163 * {@code ignorable} is added to {@code Continue} for backward
11164 * compatibility.
11165 *
11166 * @param codePoint the character (Unicode code point) to be tested.
11167 * @return {@code true} if the character may be part of a
11168 * Unicode identifier; {@code false} otherwise.
11169 *
11170 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11171 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11172 * @see Character#isIdentifierIgnorable(int)
11173 * @see Character#isJavaIdentifierPart(int)
11174 * @see Character#isLetterOrDigit(int)
11175 * @see Character#isUnicodeIdentifierStart(int)
11176 * @since 1.5
11177 */
11178 public static boolean isUnicodeIdentifierPart(int codePoint) {
11179 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
11180 }
11181
11182 /**
11183 * Determines if the specified character should be regarded as
11184 * an ignorable character in a Java identifier or a Unicode identifier.
11185 * <p>
11186 * The following Unicode characters are ignorable in a Java identifier
11187 * or a Unicode identifier:
11188 * <ul>
11189 * <li>ISO control characters that are not whitespace
11190 * <ul>
11191 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11192 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11193 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11194 * </ul>
11195 *
11196 * <li>all characters that have the {@code FORMAT} general
11197 * category value
11198 * </ul>
11199 *
11200 * <p><b>Note:</b> This method cannot handle <a
11201 * href="#supplementary"> supplementary characters</a>. To support
11202 * all Unicode characters, including supplementary characters, use
11203 * the {@link #isIdentifierIgnorable(int)} method.
11204 *
11205 * @param ch the character to be tested.
11206 * @return {@code true} if the character is an ignorable control
11207 * character that may be part of a Java or Unicode identifier;
11208 * {@code false} otherwise.
11209 * @see Character#isJavaIdentifierPart(char)
11210 * @see Character#isUnicodeIdentifierPart(char)
11211 * @since 1.1
11212 */
11213 public static boolean isIdentifierIgnorable(char ch) {
11214 return isIdentifierIgnorable((int)ch);
11215 }
11216
11217 /**
11218 * Determines if the specified character (Unicode code point) should be regarded as
11219 * an ignorable character in a Java identifier or a Unicode identifier.
11220 * <p>
11221 * The following Unicode characters are ignorable in a Java identifier
11222 * or a Unicode identifier:
11223 * <ul>
11224 * <li>ISO control characters that are not whitespace
11225 * <ul>
11226 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11227 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11228 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11229 * </ul>
11230 *
11231 * <li>all characters that have the {@code FORMAT} general
11232 * category value
11233 * </ul>
11234 *
11235 * @param codePoint the character (Unicode code point) to be tested.
11236 * @return {@code true} if the character is an ignorable control
11237 * character that may be part of a Java or Unicode identifier;
11238 * {@code false} otherwise.
11239 * @see Character#isJavaIdentifierPart(int)
11240 * @see Character#isUnicodeIdentifierPart(int)
11241 * @since 1.5
11242 */
11243 public static boolean isIdentifierIgnorable(int codePoint) {
11244 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
11245 }
11246
11247 /**
11248 * Determines if the specified character (Unicode code point) is an Emoji.
11249 * <p>
11250 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
11251 * property, defined in
11252 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11253 * Unicode Emoji (Technical Standard #51)</a>.
11254 *
11255 * @param codePoint the character (Unicode code point) to be tested.
11256 * @return {@code true} if the character is an Emoji;
11257 * {@code false} otherwise.
11258 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11259 * @since 21
11260 */
11261 public static boolean isEmoji(int codePoint) {
11262 return CharacterData.of(codePoint).isEmoji(codePoint);
11263 }
11264
11265 /**
11266 * Determines if the specified character (Unicode code point) has the
11267 * Emoji Presentation property by default.
11268 * <p>
11269 * A character is considered to have the Emoji Presentation property if and
11270 * only if it has the {@code Emoji_Presentation} property, defined in
11271 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11272 * Unicode Emoji (Technical Standard #51)</a>.
11273 *
11274 * @param codePoint the character (Unicode code point) to be tested.
11275 * @return {@code true} if the character has the Emoji Presentation
11276 * property; {@code false} otherwise.
11277 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11278 * @since 21
11279 */
11280 public static boolean isEmojiPresentation(int codePoint) {
11281 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
11282 }
11283
11284 /**
11285 * Determines if the specified character (Unicode code point) is an
11286 * Emoji Modifier.
11287 * <p>
11288 * A character is considered to be an Emoji Modifier if and only if it has
11289 * the {@code Emoji_Modifier} property, defined in
11290 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11291 * Unicode Emoji (Technical Standard #51)</a>.
11292 *
11293 * @param codePoint the character (Unicode code point) to be tested.
11294 * @return {@code true} if the character is an Emoji Modifier;
11295 * {@code false} otherwise.
11296 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11297 * @since 21
11298 */
11299 public static boolean isEmojiModifier(int codePoint) {
11300 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
11301 }
11302
11303 /**
11304 * Determines if the specified character (Unicode code point) is an
11305 * Emoji Modifier Base.
11306 * <p>
11307 * A character is considered to be an Emoji Modifier Base if and only if it has
11308 * the {@code Emoji_Modifier_Base} property, defined in
11309 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11310 * Unicode Emoji (Technical Standard #51)</a>.
11311 *
11312 * @param codePoint the character (Unicode code point) to be tested.
11313 * @return {@code true} if the character is an Emoji Modifier Base;
11314 * {@code false} otherwise.
11315 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11316 * @since 21
11317 */
11318 public static boolean isEmojiModifierBase(int codePoint) {
11319 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
11320 }
11321
11322 /**
11323 * Determines if the specified character (Unicode code point) is an
11324 * Emoji Component.
11325 * <p>
11326 * A character is considered to be an Emoji Component if and only if it has
11327 * the {@code Emoji_Component} property, defined in
11328 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11329 * Unicode Emoji (Technical Standard #51)</a>.
11330 *
11331 * @param codePoint the character (Unicode code point) to be tested.
11332 * @return {@code true} if the character is an Emoji Component;
11333 * {@code false} otherwise.
11334 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11335 * @since 21
11336 */
11337 public static boolean isEmojiComponent(int codePoint) {
11338 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
11339 }
11340
11341 /**
11342 * Determines if the specified character (Unicode code point) is
11343 * an Extended Pictographic.
11344 * <p>
11345 * A character is considered to be an Extended Pictographic if and only if it has
11346 * the {@code Extended_Pictographic} property, defined in
11347 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11348 * Unicode Emoji (Technical Standard #51)</a>.
11349 *
11350 * @param codePoint the character (Unicode code point) to be tested.
11351 * @return {@code true} if the character is an Extended Pictographic;
11352 * {@code false} otherwise.
11353 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11354 * @since 21
11355 */
11356 public static boolean isExtendedPictographic(int codePoint) {
11357 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
11358 }
11359
11360 /**
11361 * Converts the character argument to lowercase using case
11362 * mapping information from the UnicodeData file.
11363 * <p>
11364 * Note that
11365 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
11366 * does not always return {@code true} for some ranges of
11367 * characters, particularly those that are symbols or ideographs.
11368 *
11369 * <p>In general, {@link String#toLowerCase()} should be used to map
11370 * characters to lowercase. {@code String} case mapping methods
11371 * have several benefits over {@code Character} case mapping methods.
11372 * {@code String} case mapping methods can perform locale-sensitive
11373 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11374 * the {@code Character} case mapping methods cannot.
11375 *
11376 * <p><b>Note:</b> This method cannot handle <a
11377 * href="#supplementary"> supplementary characters</a>. To support
11378 * all Unicode characters, including supplementary characters, use
11379 * the {@link #toLowerCase(int)} method.
11380 *
11381 * @param ch the character to be converted.
11382 * @return the lowercase equivalent of the character, if any;
11383 * otherwise, the character itself.
11384 * @see Character#isLowerCase(char)
11385 * @see String#toLowerCase()
11386 */
11387 public static char toLowerCase(char ch) {
11388 return (char)toLowerCase((int)ch);
11389 }
11390
11391 /**
11392 * Converts the character (Unicode code point) argument to
11393 * lowercase using case mapping information from the UnicodeData
11394 * file.
11395 *
11396 * <p> Note that
11397 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
11398 * does not always return {@code true} for some ranges of
11399 * characters, particularly those that are symbols or ideographs.
11400 *
11401 * <p>In general, {@link String#toLowerCase()} should be used to map
11402 * characters to lowercase. {@code String} case mapping methods
11403 * have several benefits over {@code Character} case mapping methods.
11404 * {@code String} case mapping methods can perform locale-sensitive
11405 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11406 * the {@code Character} case mapping methods cannot.
11407 *
11408 * @param codePoint the character (Unicode code point) to be converted.
11409 * @return the lowercase equivalent of the character (Unicode code
11410 * point), if any; otherwise, the character itself.
11411 * @see Character#isLowerCase(int)
11412 * @see String#toLowerCase()
11413 *
11414 * @since 1.5
11415 */
11416 public static int toLowerCase(int codePoint) {
11417 return CharacterData.of(codePoint).toLowerCase(codePoint);
11418 }
11419
11420 /**
11421 * Converts the character argument to uppercase using case mapping
11422 * information from the UnicodeData file.
11423 * <p>
11424 * Note that
11425 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
11426 * does not always return {@code true} for some ranges of
11427 * characters, particularly those that are symbols or ideographs.
11428 *
11429 * <p>In general, {@link String#toUpperCase()} should be used to map
11430 * characters to uppercase. {@code String} case mapping methods
11431 * have several benefits over {@code Character} case mapping methods.
11432 * {@code String} case mapping methods can perform locale-sensitive
11433 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11434 * the {@code Character} case mapping methods cannot.
11435 *
11436 * <p><b>Note:</b> This method cannot handle <a
11437 * href="#supplementary"> supplementary characters</a>. To support
11438 * all Unicode characters, including supplementary characters, use
11439 * the {@link #toUpperCase(int)} method.
11440 *
11441 * @param ch the character to be converted.
11442 * @return the uppercase equivalent of the character, if any;
11443 * otherwise, the character itself.
11444 * @see Character#isUpperCase(char)
11445 * @see String#toUpperCase()
11446 */
11447 public static char toUpperCase(char ch) {
11448 return (char)toUpperCase((int)ch);
11449 }
11450
11451 /**
11452 * Converts the character (Unicode code point) argument to
11453 * uppercase using case mapping information from the UnicodeData
11454 * file.
11455 *
11456 * <p>Note that
11457 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11458 * does not always return {@code true} for some ranges of
11459 * characters, particularly those that are symbols or ideographs.
11460 *
11461 * <p>In general, {@link String#toUpperCase()} should be used to map
11462 * characters to uppercase. {@code String} case mapping methods
11463 * have several benefits over {@code Character} case mapping methods.
11464 * {@code String} case mapping methods can perform locale-sensitive
11465 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11466 * the {@code Character} case mapping methods cannot.
11467 *
11468 * @param codePoint the character (Unicode code point) to be converted.
11469 * @return the uppercase equivalent of the character, if any;
11470 * otherwise, the character itself.
11471 * @see Character#isUpperCase(int)
11472 * @see String#toUpperCase()
11473 *
11474 * @since 1.5
11475 */
11476 public static int toUpperCase(int codePoint) {
11477 return CharacterData.of(codePoint).toUpperCase(codePoint);
11478 }
11479
11480 /**
11481 * Converts the character argument to titlecase using case mapping
11482 * information from the UnicodeData file. If a character has no
11483 * explicit titlecase mapping and is not itself a titlecase char
11484 * according to UnicodeData, then the uppercase mapping is
11485 * returned as an equivalent titlecase mapping. If the
11486 * {@code char} argument is already a titlecase
11487 * {@code char}, the same {@code char} value will be
11488 * returned.
11489 * <p>
11490 * Note that
11491 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11492 * does not always return {@code true} for some ranges of
11493 * characters.
11494 *
11495 * <p><b>Note:</b> This method cannot handle <a
11496 * href="#supplementary"> supplementary characters</a>. To support
11497 * all Unicode characters, including supplementary characters, use
11498 * the {@link #toTitleCase(int)} method.
11499 *
11500 * @param ch the character to be converted.
11501 * @return the titlecase equivalent of the character, if any;
11502 * otherwise, the character itself.
11503 * @see Character#isTitleCase(char)
11504 * @see Character#toLowerCase(char)
11505 * @see Character#toUpperCase(char)
11506 * @since 1.0.2
11507 */
11508 public static char toTitleCase(char ch) {
11509 return (char)toTitleCase((int)ch);
11510 }
11511
11512 /**
11513 * Converts the character (Unicode code point) argument to titlecase using case mapping
11514 * information from the UnicodeData file. If a character has no
11515 * explicit titlecase mapping and is not itself a titlecase char
11516 * according to UnicodeData, then the uppercase mapping is
11517 * returned as an equivalent titlecase mapping. If the
11518 * character argument is already a titlecase
11519 * character, the same character value will be
11520 * returned.
11521 *
11522 * <p>Note that
11523 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11524 * does not always return {@code true} for some ranges of
11525 * characters.
11526 *
11527 * @param codePoint the character (Unicode code point) to be converted.
11528 * @return the titlecase equivalent of the character, if any;
11529 * otherwise, the character itself.
11530 * @see Character#isTitleCase(int)
11531 * @see Character#toLowerCase(int)
11532 * @see Character#toUpperCase(int)
11533 * @since 1.5
11534 */
11535 public static int toTitleCase(int codePoint) {
11536 return CharacterData.of(codePoint).toTitleCase(codePoint);
11537 }
11538
11539 /**
11540 * Returns the numeric value of the character {@code ch} in the
11541 * specified radix.
11542 * <p>
11543 * If the radix is not in the range {@code MIN_RADIX} ≤
11544 * {@code radix} ≤ {@code MAX_RADIX} or if the
11545 * value of {@code ch} is not a valid digit in the specified
11546 * radix, {@code -1} is returned. A character is a valid digit
11547 * if at least one of the following is true:
11548 * <ul>
11549 * <li>The method {@code isDigit} is {@code true} of the character
11550 * and the Unicode decimal digit value of the character (or its
11551 * single-character decomposition) is less than the specified radix.
11552 * In this case the decimal digit value is returned.
11553 * <li>The character is one of the uppercase Latin letters
11554 * {@code 'A'} through {@code 'Z'} and its code is less than
11555 * {@code radix + 'A' - 10}.
11556 * In this case, {@code ch - 'A' + 10}
11557 * is returned.
11558 * <li>The character is one of the lowercase Latin letters
11559 * {@code 'a'} through {@code 'z'} and its code is less than
11560 * {@code radix + 'a' - 10}.
11561 * In this case, {@code ch - 'a' + 10}
11562 * is returned.
11563 * <li>The character is one of the fullwidth uppercase Latin letters A
11564 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11565 * and its code is less than
11566 * {@code radix + '\u005CuFF21' - 10}.
11567 * In this case, {@code ch - '\u005CuFF21' + 10}
11568 * is returned.
11569 * <li>The character is one of the fullwidth lowercase Latin letters a
11570 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11571 * and its code is less than
11572 * {@code radix + '\u005CuFF41' - 10}.
11573 * In this case, {@code ch - '\u005CuFF41' + 10}
11574 * is returned.
11575 * </ul>
11576 *
11577 * <p><b>Note:</b> This method cannot handle <a
11578 * href="#supplementary"> supplementary characters</a>. To support
11579 * all Unicode characters, including supplementary characters, use
11580 * the {@link #digit(int, int)} method.
11581 *
11582 * @param ch the character to be converted.
11583 * @param radix the radix.
11584 * @return the numeric value represented by the character in the
11585 * specified radix.
11586 * @see Character#forDigit(int, int)
11587 * @see Character#isDigit(char)
11588 */
11589 public static int digit(char ch, int radix) {
11590 return digit((int)ch, radix);
11591 }
11592
11593 /**
11594 * Returns the numeric value of the specified character (Unicode
11595 * code point) in the specified radix.
11596 *
11597 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11598 * {@code radix} ≤ {@code MAX_RADIX} or if the
11599 * character is not a valid digit in the specified
11600 * radix, {@code -1} is returned. A character is a valid digit
11601 * if at least one of the following is true:
11602 * <ul>
11603 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11604 * and the Unicode decimal digit value of the character (or its
11605 * single-character decomposition) is less than the specified radix.
11606 * In this case the decimal digit value is returned.
11607 * <li>The character is one of the uppercase Latin letters
11608 * {@code 'A'} through {@code 'Z'} and its code is less than
11609 * {@code radix + 'A' - 10}.
11610 * In this case, {@code codePoint - 'A' + 10}
11611 * is returned.
11612 * <li>The character is one of the lowercase Latin letters
11613 * {@code 'a'} through {@code 'z'} and its code is less than
11614 * {@code radix + 'a' - 10}.
11615 * In this case, {@code codePoint - 'a' + 10}
11616 * is returned.
11617 * <li>The character is one of the fullwidth uppercase Latin letters A
11618 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11619 * and its code is less than
11620 * {@code radix + '\u005CuFF21' - 10}.
11621 * In this case,
11622 * {@code codePoint - '\u005CuFF21' + 10}
11623 * is returned.
11624 * <li>The character is one of the fullwidth lowercase Latin letters a
11625 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11626 * and its code is less than
11627 * {@code radix + '\u005CuFF41'- 10}.
11628 * In this case,
11629 * {@code codePoint - '\u005CuFF41' + 10}
11630 * is returned.
11631 * </ul>
11632 *
11633 * @param codePoint the character (Unicode code point) to be converted.
11634 * @param radix the radix.
11635 * @return the numeric value represented by the character in the
11636 * specified radix.
11637 * @see Character#forDigit(int, int)
11638 * @see Character#isDigit(int)
11639 * @since 1.5
11640 */
11641 public static int digit(int codePoint, int radix) {
11642 return CharacterData.of(codePoint).digit(codePoint, radix);
11643 }
11644
11645 /**
11646 * Returns the {@code int} value that the specified Unicode
11647 * character represents. For example, the character
11648 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11649 * an int with a value of 50.
11650 * <p>
11651 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11652 * {@code '\u005Cu005A'}), lowercase
11653 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11654 * full width variant ({@code '\u005CuFF21'} through
11655 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11656 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11657 * through 35. This is independent of the Unicode specification,
11658 * which does not assign numeric values to these {@code char}
11659 * values.
11660 * <p>
11661 * If the character does not have a numeric value, then -1 is returned.
11662 * If the character has a numeric value that cannot be represented as a
11663 * nonnegative integer (for example, a fractional value), then -2
11664 * is returned.
11665 *
11666 * <p><b>Note:</b> This method cannot handle <a
11667 * href="#supplementary"> supplementary characters</a>. To support
11668 * all Unicode characters, including supplementary characters, use
11669 * the {@link #getNumericValue(int)} method.
11670 *
11671 * @param ch the character to be converted.
11672 * @return the numeric value of the character, as a nonnegative {@code int}
11673 * value; -2 if the character has a numeric value but the value
11674 * can not be represented as a nonnegative {@code int} value;
11675 * -1 if the character has no numeric value.
11676 * @see Character#forDigit(int, int)
11677 * @see Character#isDigit(char)
11678 * @since 1.1
11679 */
11680 public static int getNumericValue(char ch) {
11681 return getNumericValue((int)ch);
11682 }
11683
11684 /**
11685 * Returns the {@code int} value that the specified
11686 * character (Unicode code point) represents. For example, the character
11687 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11688 * an {@code int} with a value of 50.
11689 * <p>
11690 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11691 * {@code '\u005Cu005A'}), lowercase
11692 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11693 * full width variant ({@code '\u005CuFF21'} through
11694 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11695 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11696 * through 35. This is independent of the Unicode specification,
11697 * which does not assign numeric values to these {@code char}
11698 * values.
11699 * <p>
11700 * If the character does not have a numeric value, then -1 is returned.
11701 * If the character has a numeric value that cannot be represented as a
11702 * nonnegative integer (for example, a fractional value), then -2
11703 * is returned.
11704 *
11705 * @param codePoint the character (Unicode code point) to be converted.
11706 * @return the numeric value of the character, as a nonnegative {@code int}
11707 * value; -2 if the character has a numeric value but the value
11708 * can not be represented as a nonnegative {@code int} value;
11709 * -1 if the character has no numeric value.
11710 * @see Character#forDigit(int, int)
11711 * @see Character#isDigit(int)
11712 * @since 1.5
11713 */
11714 public static int getNumericValue(int codePoint) {
11715 return CharacterData.of(codePoint).getNumericValue(codePoint);
11716 }
11717
11718 /**
11719 * Determines if the specified character is ISO-LATIN-1 white space.
11720 * This method returns {@code true} for the following five
11721 * characters only:
11722 * <table class="striped">
11723 * <caption style="display:none">truechars</caption>
11724 * <thead>
11725 * <tr><th scope="col">Character
11726 * <th scope="col">Code
11727 * <th scope="col">Name
11728 * </thead>
11729 * <tbody>
11730 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11731 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11732 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11733 * <td>{@code NEW LINE}</td></tr>
11734 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11735 * <td>{@code FORM FEED}</td></tr>
11736 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11737 * <td>{@code CARRIAGE RETURN}</td></tr>
11738 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11739 * <td>{@code SPACE}</td></tr>
11740 * </tbody>
11741 * </table>
11742 *
11743 * @param ch the character to be tested.
11744 * @return {@code true} if the character is ISO-LATIN-1 white
11745 * space; {@code false} otherwise.
11746 * @see Character#isSpaceChar(char)
11747 * @see Character#isWhitespace(char)
11748 * @deprecated Replaced by isWhitespace(char).
11749 */
11750 @Deprecated(since="1.1")
11751 public static boolean isSpace(char ch) {
11752 return (ch <= 0x0020) &&
11753 (((((1L << 0x0009) |
11754 (1L << 0x000A) |
11755 (1L << 0x000C) |
11756 (1L << 0x000D) |
11757 (1L << 0x0020)) >> ch) & 1L) != 0);
11758 }
11759
11760
11761 /**
11762 * Determines if the specified character is a Unicode space character.
11763 * A character is considered to be a space character if and only if
11764 * it is specified to be a space character by the Unicode Standard. This
11765 * method returns true if the character's general category type is any of
11766 * the following:
11767 * <ul>
11768 * <li> {@code SPACE_SEPARATOR}
11769 * <li> {@code LINE_SEPARATOR}
11770 * <li> {@code PARAGRAPH_SEPARATOR}
11771 * </ul>
11772 *
11773 * <p><b>Note:</b> This method cannot handle <a
11774 * href="#supplementary"> supplementary characters</a>. To support
11775 * all Unicode characters, including supplementary characters, use
11776 * the {@link #isSpaceChar(int)} method.
11777 *
11778 * @param ch the character to be tested.
11779 * @return {@code true} if the character is a space character;
11780 * {@code false} otherwise.
11781 * @see Character#isWhitespace(char)
11782 * @since 1.1
11783 */
11784 public static boolean isSpaceChar(char ch) {
11785 return isSpaceChar((int)ch);
11786 }
11787
11788 /**
11789 * Determines if the specified character (Unicode code point) is a
11790 * Unicode space character. A character is considered to be a
11791 * space character if and only if it is specified to be a space
11792 * character by the Unicode Standard. This method returns true if
11793 * the character's general category type is any of the following:
11794 *
11795 * <ul>
11796 * <li> {@link #SPACE_SEPARATOR}
11797 * <li> {@link #LINE_SEPARATOR}
11798 * <li> {@link #PARAGRAPH_SEPARATOR}
11799 * </ul>
11800 *
11801 * @param codePoint the character (Unicode code point) to be tested.
11802 * @return {@code true} if the character is a space character;
11803 * {@code false} otherwise.
11804 * @see Character#isWhitespace(int)
11805 * @since 1.5
11806 */
11807 public static boolean isSpaceChar(int codePoint) {
11808 return ((((1 << Character.SPACE_SEPARATOR) |
11809 (1 << Character.LINE_SEPARATOR) |
11810 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11811 != 0;
11812 }
11813
11814 /**
11815 * Determines if the specified character is white space according to Java.
11816 * A character is a Java whitespace character if and only if it satisfies
11817 * one of the following criteria:
11818 * <ul>
11819 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11820 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11821 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11822 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11823 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11824 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11825 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11826 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11827 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11828 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11829 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11830 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11831 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11832 * </ul>
11833 *
11834 * <p><b>Note:</b> This method cannot handle <a
11835 * href="#supplementary"> supplementary characters</a>. To support
11836 * all Unicode characters, including supplementary characters, use
11837 * the {@link #isWhitespace(int)} method.
11838 *
11839 * @param ch the character to be tested.
11840 * @return {@code true} if the character is a Java whitespace
11841 * character; {@code false} otherwise.
11842 * @see Character#isSpaceChar(char)
11843 * @since 1.1
11844 */
11845 public static boolean isWhitespace(char ch) {
11846 return isWhitespace((int)ch);
11847 }
11848
11849 /**
11850 * Determines if the specified character (Unicode code point) is
11851 * white space according to Java. A character is a Java
11852 * whitespace character if and only if it satisfies one of the
11853 * following criteria:
11854 * <ul>
11855 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11856 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11857 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11858 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11859 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11860 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11861 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11862 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11863 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11864 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11865 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11866 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11867 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11868 * </ul>
11869 *
11870 * @param codePoint the character (Unicode code point) to be tested.
11871 * @return {@code true} if the character is a Java whitespace
11872 * character; {@code false} otherwise.
11873 * @see Character#isSpaceChar(int)
11874 * @since 1.5
11875 */
11876 public static boolean isWhitespace(int codePoint) {
11877 return CharacterData.of(codePoint).isWhitespace(codePoint);
11878 }
11879
11880 /**
11881 * Determines if the specified character is an ISO control
11882 * character. A character is considered to be an ISO control
11883 * character if its code is in the range {@code '\u005Cu0000'}
11884 * through {@code '\u005Cu001F'} or in the range
11885 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11886 *
11887 * <p><b>Note:</b> This method cannot handle <a
11888 * href="#supplementary"> supplementary characters</a>. To support
11889 * all Unicode characters, including supplementary characters, use
11890 * the {@link #isISOControl(int)} method.
11891 *
11892 * @param ch the character to be tested.
11893 * @return {@code true} if the character is an ISO control character;
11894 * {@code false} otherwise.
11895 *
11896 * @see Character#isSpaceChar(char)
11897 * @see Character#isWhitespace(char)
11898 * @since 1.1
11899 */
11900 public static boolean isISOControl(char ch) {
11901 return isISOControl((int)ch);
11902 }
11903
11904 /**
11905 * Determines if the referenced character (Unicode code point) is an ISO control
11906 * character. A character is considered to be an ISO control
11907 * character if its code is in the range {@code '\u005Cu0000'}
11908 * through {@code '\u005Cu001F'} or in the range
11909 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11910 *
11911 * @param codePoint the character (Unicode code point) to be tested.
11912 * @return {@code true} if the character is an ISO control character;
11913 * {@code false} otherwise.
11914 * @see Character#isSpaceChar(int)
11915 * @see Character#isWhitespace(int)
11916 * @since 1.5
11917 */
11918 public static boolean isISOControl(int codePoint) {
11919 // Optimized form of:
11920 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11921 // (codePoint >= 0x7F && codePoint <= 0x9F);
11922 return codePoint <= 0x9F &&
11923 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11924 }
11925
11926 /**
11927 * Returns a value indicating a character's general category.
11928 *
11929 * <p><b>Note:</b> This method cannot handle <a
11930 * href="#supplementary"> supplementary characters</a>. To support
11931 * all Unicode characters, including supplementary characters, use
11932 * the {@link #getType(int)} method.
11933 *
11934 * @param ch the character to be tested.
11935 * @return a value of type {@code int} representing the
11936 * character's general category.
11937 * @see Character#COMBINING_SPACING_MARK
11938 * @see Character#CONNECTOR_PUNCTUATION
11939 * @see Character#CONTROL
11940 * @see Character#CURRENCY_SYMBOL
11941 * @see Character#DASH_PUNCTUATION
11942 * @see Character#DECIMAL_DIGIT_NUMBER
11943 * @see Character#ENCLOSING_MARK
11944 * @see Character#END_PUNCTUATION
11945 * @see Character#FINAL_QUOTE_PUNCTUATION
11946 * @see Character#FORMAT
11947 * @see Character#INITIAL_QUOTE_PUNCTUATION
11948 * @see Character#LETTER_NUMBER
11949 * @see Character#LINE_SEPARATOR
11950 * @see Character#LOWERCASE_LETTER
11951 * @see Character#MATH_SYMBOL
11952 * @see Character#MODIFIER_LETTER
11953 * @see Character#MODIFIER_SYMBOL
11954 * @see Character#NON_SPACING_MARK
11955 * @see Character#OTHER_LETTER
11956 * @see Character#OTHER_NUMBER
11957 * @see Character#OTHER_PUNCTUATION
11958 * @see Character#OTHER_SYMBOL
11959 * @see Character#PARAGRAPH_SEPARATOR
11960 * @see Character#PRIVATE_USE
11961 * @see Character#SPACE_SEPARATOR
11962 * @see Character#START_PUNCTUATION
11963 * @see Character#SURROGATE
11964 * @see Character#TITLECASE_LETTER
11965 * @see Character#UNASSIGNED
11966 * @see Character#UPPERCASE_LETTER
11967 * @since 1.1
11968 */
11969 public static int getType(char ch) {
11970 return getType((int)ch);
11971 }
11972
11973 /**
11974 * Returns a value indicating a character's general category.
11975 *
11976 * @param codePoint the character (Unicode code point) to be tested.
11977 * @return a value of type {@code int} representing the
11978 * character's general category.
11979 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11980 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11981 * @see Character#CONTROL CONTROL
11982 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11983 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11984 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11985 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11986 * @see Character#END_PUNCTUATION END_PUNCTUATION
11987 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11988 * @see Character#FORMAT FORMAT
11989 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11990 * @see Character#LETTER_NUMBER LETTER_NUMBER
11991 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11992 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11993 * @see Character#MATH_SYMBOL MATH_SYMBOL
11994 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11995 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11996 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11997 * @see Character#OTHER_LETTER OTHER_LETTER
11998 * @see Character#OTHER_NUMBER OTHER_NUMBER
11999 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
12000 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
12001 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
12002 * @see Character#PRIVATE_USE PRIVATE_USE
12003 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
12004 * @see Character#START_PUNCTUATION START_PUNCTUATION
12005 * @see Character#SURROGATE SURROGATE
12006 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
12007 * @see Character#UNASSIGNED UNASSIGNED
12008 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
12009 * @since 1.5
12010 */
12011 public static int getType(int codePoint) {
12012 return CharacterData.of(codePoint).getType(codePoint);
12013 }
12014
12015 /**
12016 * Determines the character representation for a specific digit in
12017 * the specified radix. If the value of {@code radix} is not a
12018 * valid radix, or the value of {@code digit} is not a valid
12019 * digit in the specified radix, the null character
12020 * ({@code '\u005Cu0000'}) is returned.
12021 * <p>
12022 * The {@code radix} argument is valid if it is greater than or
12023 * equal to {@code MIN_RADIX} and less than or equal to
12024 * {@code MAX_RADIX}. The {@code digit} argument is valid if
12025 * {@code 0 <= digit < radix}.
12026 * <p>
12027 * If the digit is less than 10, then
12028 * {@code '0' + digit} is returned. Otherwise, the value
12029 * {@code 'a' + digit - 10} is returned.
12030 *
12031 * @param digit the number to convert to a character.
12032 * @param radix the radix.
12033 * @return the {@code char} representation of the specified digit
12034 * in the specified radix.
12035 * @see Character#MIN_RADIX
12036 * @see Character#MAX_RADIX
12037 * @see Character#digit(char, int)
12038 */
12039 public static char forDigit(int digit, int radix) {
12040 if ((digit >= radix) || (digit < 0)) {
12041 return '\0';
12042 }
12043 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
12044 return '\0';
12045 }
12046 if (digit < 10) {
12047 return (char)('0' + digit);
12048 }
12049 return (char)('a' - 10 + digit);
12050 }
12051
12052 /**
12053 * Returns the Unicode directionality property for the given
12054 * character. Character directionality is used to calculate the
12055 * visual ordering of text. The directionality value of undefined
12056 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
12057 *
12058 * <p><b>Note:</b> This method cannot handle <a
12059 * href="#supplementary"> supplementary characters</a>. To support
12060 * all Unicode characters, including supplementary characters, use
12061 * the {@link #getDirectionality(int)} method.
12062 *
12063 * @param ch {@code char} for which the directionality property
12064 * is requested.
12065 * @return the directionality property of the {@code char} value.
12066 *
12067 * @see Character#DIRECTIONALITY_UNDEFINED
12068 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
12069 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
12070 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
12071 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
12072 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
12073 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
12074 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
12075 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
12076 * @see Character#DIRECTIONALITY_NONSPACING_MARK
12077 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
12078 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
12079 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
12080 * @see Character#DIRECTIONALITY_WHITESPACE
12081 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
12082 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
12083 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
12084 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
12085 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
12086 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
12087 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
12088 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
12089 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
12090 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
12091 * @since 1.4
12092 */
12093 public static byte getDirectionality(char ch) {
12094 return getDirectionality((int)ch);
12095 }
12096
12097 /**
12098 * Returns the Unicode directionality property for the given
12099 * character (Unicode code point). Character directionality is
12100 * used to calculate the visual ordering of text. The
12101 * directionality value of undefined character is {@link
12102 * #DIRECTIONALITY_UNDEFINED}.
12103 *
12104 * @param codePoint the character (Unicode code point) for which
12105 * the directionality property is requested.
12106 * @return the directionality property of the character.
12107 *
12108 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
12109 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
12110 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
12111 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
12112 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
12113 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
12114 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
12115 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
12116 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
12117 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
12118 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
12119 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
12120 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
12121 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
12122 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
12123 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
12124 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
12125 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
12126 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
12127 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
12128 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
12129 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
12130 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
12131 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
12132 * @since 1.5
12133 */
12134 public static byte getDirectionality(int codePoint) {
12135 return CharacterData.of(codePoint).getDirectionality(codePoint);
12136 }
12137
12138 /**
12139 * Determines whether the character is mirrored according to the
12140 * Unicode specification. Mirrored characters should have their
12141 * glyphs horizontally mirrored when displayed in text that is
12142 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
12143 * PARENTHESIS is semantically defined to be an <i>opening
12144 * parenthesis</i>. This will appear as a "(" in text that is
12145 * left-to-right but as a ")" in text that is right-to-left.
12146 *
12147 * <p><b>Note:</b> This method cannot handle <a
12148 * href="#supplementary"> supplementary characters</a>. To support
12149 * all Unicode characters, including supplementary characters, use
12150 * the {@link #isMirrored(int)} method.
12151 *
12152 * @param ch {@code char} for which the mirrored property is requested
12153 * @return {@code true} if the char is mirrored, {@code false}
12154 * if the {@code char} is not mirrored or is not defined.
12155 * @since 1.4
12156 */
12157 public static boolean isMirrored(char ch) {
12158 return isMirrored((int)ch);
12159 }
12160
12161 /**
12162 * Determines whether the specified character (Unicode code point)
12163 * is mirrored according to the Unicode specification. Mirrored
12164 * characters should have their glyphs horizontally mirrored when
12165 * displayed in text that is right-to-left. For example,
12166 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
12167 * defined to be an <i>opening parenthesis</i>. This will appear
12168 * as a "(" in text that is left-to-right but as a ")" in text
12169 * that is right-to-left.
12170 *
12171 * @param codePoint the character (Unicode code point) to be tested.
12172 * @return {@code true} if the character is mirrored, {@code false}
12173 * if the character is not mirrored or is not defined.
12174 * @since 1.5
12175 */
12176 public static boolean isMirrored(int codePoint) {
12177 return CharacterData.of(codePoint).isMirrored(codePoint);
12178 }
12179
12180 /**
12181 * Compares two {@code Character} objects numerically.
12182 *
12183 * @param anotherCharacter the {@code Character} to be compared.
12184 * @return the value {@code 0} if the argument {@code Character}
12185 * is equal to this {@code Character}; a value less than
12186 * {@code 0} if this {@code Character} is numerically less
12187 * than the {@code Character} argument; and a value greater than
12188 * {@code 0} if this {@code Character} is numerically greater
12189 * than the {@code Character} argument (unsigned comparison).
12190 * Note that this is strictly a numerical comparison; it is not
12191 * locale-dependent.
12192 * @since 1.2
12193 */
12194 public int compareTo(Character anotherCharacter) {
12195 return compare(this.value, anotherCharacter.value);
12196 }
12197
12198 /**
12199 * Compares two {@code char} values numerically.
12200 * The value returned is identical to what would be returned by:
12201 * <pre>
12202 * Character.valueOf(x).compareTo(Character.valueOf(y))
12203 * </pre>
12204 *
12205 * @param x the first {@code char} to compare
12206 * @param y the second {@code char} to compare
12207 * @return the value {@code 0} if {@code x == y};
12208 * a value less than {@code 0} if {@code x < y}; and
12209 * a value greater than {@code 0} if {@code x > y}
12210 * @since 1.7
12211 */
12212 public static int compare(char x, char y) {
12213 return x - y;
12214 }
12215
12216 /**
12217 * Converts the character (Unicode code point) argument to uppercase using
12218 * information from the UnicodeData file.
12219 *
12220 * @param codePoint the character (Unicode code point) to be converted.
12221 * @return either the uppercase equivalent of the character, if
12222 * any, or an error flag ({@code Character.ERROR})
12223 * that indicates that a 1:M {@code char} mapping exists.
12224 * @see Character#isLowerCase(char)
12225 * @see Character#isUpperCase(char)
12226 * @see Character#toLowerCase(char)
12227 * @see Character#toTitleCase(char)
12228 * @since 1.4
12229 */
12230 static int toUpperCaseEx(int codePoint) {
12231 assert isValidCodePoint(codePoint);
12232 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
12233 }
12234
12235 /**
12236 * Converts the character (Unicode code point) argument to uppercase using case
12237 * mapping information from the SpecialCasing file in the Unicode
12238 * specification. If a character has no explicit uppercase
12239 * mapping, then the {@code char} itself is returned in the
12240 * {@code char[]}.
12241 *
12242 * @param codePoint the character (Unicode code point) to be converted.
12243 * @return a {@code char[]} with the uppercased character.
12244 * @since 1.4
12245 */
12246 static char[] toUpperCaseCharArray(int codePoint) {
12247 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
12248 assert isBmpCodePoint(codePoint);
12249 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
12250 }
12251
12252 /**
12253 * The number of bits used to represent a {@code char} value in unsigned
12254 * binary form, constant {@code 16}.
12255 *
12256 * @since 1.5
12257 */
12258 public static final int SIZE = 16;
12259
12260 /**
12261 * The number of bytes used to represent a {@code char} value in unsigned
12262 * binary form.
12263 *
12264 * @since 1.8
12265 */
12266 public static final int BYTES = SIZE / Byte.SIZE;
12267
12268 /**
12269 * Returns the value obtained by reversing the order of the bytes in the
12270 * specified {@code char} value.
12271 *
12272 * @param ch The {@code char} of which to reverse the byte order.
12273 * @return the value obtained by reversing (or, equivalently, swapping)
12274 * the bytes in the specified {@code char} value.
12275 * @since 1.5
12276 */
12277 @IntrinsicCandidate
12278 public static char reverseBytes(char ch) {
12279 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
12280 }
12281
12282 /**
12283 * Returns the name of the specified character
12284 * {@code codePoint}, or null if the code point is
12285 * {@link #UNASSIGNED unassigned}.
12286 * <p>
12287 * If the specified character is not assigned a name by
12288 * the <i>UnicodeData</i> file (part of the Unicode Character
12289 * Database maintained by the Unicode Consortium), the returned
12290 * name is the same as the result of the expression:
12291 *
12292 * <blockquote>{@code
12293 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12294 * + " "
12295 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12296 *
12297 * }</blockquote>
12298 *
12299 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
12300 * returned by this method follows the naming scheme in the
12301 * "Unicode Name Property" section of the Unicode Standard. For other
12302 * code points, such as Hangul/Ideographs, The name generation rule above
12303 * differs from the one defined in the Unicode Standard.
12304 *
12305 * @param codePoint the character (Unicode code point)
12306 *
12307 * @return the name of the specified character, or null if
12308 * the code point is unassigned.
12309 *
12310 * @throws IllegalArgumentException if the specified
12311 * {@code codePoint} is not a valid Unicode
12312 * code point.
12313 *
12314 * @since 1.7
12315 */
12316 public static String getName(int codePoint) {
12317 if (!isValidCodePoint(codePoint)) {
12318 throw new IllegalArgumentException(
12319 String.format("Not a valid Unicode code point: 0x%X", codePoint));
12320 }
12321 String name = CharacterName.getInstance().getName(codePoint);
12322 if (name != null)
12323 return name;
12324 if (getType(codePoint) == UNASSIGNED)
12325 return null;
12326 UnicodeBlock block = UnicodeBlock.of(codePoint);
12327 if (block != null)
12328 return block.toString().replace('_', ' ') + " "
12329 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12330 // should never come here
12331 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12332 }
12333
12334 /**
12335 * Returns the code point value of the Unicode character specified by
12336 * the given character name.
12337 * <p>
12338 * If a character is not assigned a name by the <i>UnicodeData</i>
12339 * file (part of the Unicode Character Database maintained by the Unicode
12340 * Consortium), its name is defined as the result of the expression:
12341 *
12342 * <blockquote>{@code
12343 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12344 * + " "
12345 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12346 *
12347 * }</blockquote>
12348 * <p>
12349 * The {@code name} matching is case insensitive, with any leading and
12350 * trailing whitespace character removed.
12351 *
12352 * For the code points in the <i>UnicodeData</i> file, this method
12353 * recognizes the name which conforms to the name defined in the
12354 * "Unicode Name Property" section in the Unicode Standard. For other
12355 * code points, this method recognizes the name generated with
12356 * {@link #getName(int)} method.
12357 *
12358 * @param name the character name
12359 *
12360 * @return the code point value of the character specified by its name.
12361 *
12362 * @throws IllegalArgumentException if the specified {@code name}
12363 * is not a valid character name.
12364 * @throws NullPointerException if {@code name} is {@code null}
12365 *
12366 * @since 9
12367 */
12368 public static int codePointOf(String name) {
12369 name = name.trim().toUpperCase(Locale.ROOT);
12370 int cp = CharacterName.getInstance().getCodePoint(name);
12371 if (cp != -1)
12372 return cp;
12373 try {
12374 int off = name.lastIndexOf(' ');
12375 if (off != -1) {
12376 cp = Integer.parseInt(name, off + 1, name.length(), 16);
12377 if (isValidCodePoint(cp) && name.equals(getName(cp)))
12378 return cp;
12379 }
12380 } catch (Exception x) {}
12381 throw new IllegalArgumentException("Unrecognized character name :" + name);
12382 }
12383 }