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.value.DeserializeConstructor;
30 import jdk.internal.vm.annotation.IntrinsicCandidate;
31 import jdk.internal.vm.annotation.Stable;
32
33 import java.lang.constant.Constable;
34 import java.lang.constant.DynamicConstantDesc;
35 import java.util.Arrays;
36 import java.util.HashMap;
37 import java.util.Locale;
38 import java.util.Map;
39 import java.util.Objects;
40 import java.util.Optional;
41
42 import static java.lang.constant.ConstantDescs.BSM_EXPLICIT_CAST;
43 import static java.lang.constant.ConstantDescs.CD_char;
44 import static java.lang.constant.ConstantDescs.DEFAULT_NAME;
45
46 /**
47 * The {@code Character} class is the {@linkplain
48 * java.lang##wrapperClass wrapper class} for values of the primitive
49 * type {@code char}. An object of type {@code Character} contains a
50 * single field whose type is {@code char}.
51 *
52 * <p>In addition, this class provides a large number of static methods for
53 * determining a character's category (lowercase letter, digit, etc.)
54 * and for converting characters from uppercase to lowercase and vice
55 * versa.
56 *
57 * <h2><a id="conformance">Unicode Conformance</a></h2>
58 * <p>
59 * The fields and methods of class {@code Character} are defined in terms
60 * of character information from the Unicode Standard, specifically the
61 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
62 * This file specifies properties including name and category for every
63 * assigned Unicode code point or character range. The file is available
64 * from the Unicode Consortium at
65 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
66 * <p>
67 * Character information is based on the Unicode Standard, version 16.0.
68 * <p>
69 * The Java platform has supported different versions of the Unicode
70 * Standard over time. Upgrades to newer versions of the Unicode Standard
71 * occurred in the following Java releases, each indicating the new version:
72 * <table class="striped">
73 * <caption style="display:none">Shows Java releases and supported Unicode versions</caption>
74 * <thead>
75 * <tr><th scope="col">Java release</th>
76 * <th scope="col">Unicode version</th></tr>
77 * </thead>
78 * <tbody>
79 * <tr><th scope="row" style="text-align:left">Java SE 24</th>
80 * <td>Unicode 16.0</td></tr>
81 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
82 * <td>Unicode 15.1</td></tr>
83 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
84 * <td>Unicode 15.0</td></tr>
85 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
86 * <td>Unicode 14.0</td></tr>
87 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
88 * <td>Unicode 13.0</td></tr>
89 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
90 * <td>Unicode 12.1</td></tr>
91 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
92 * <td>Unicode 11.0</td></tr>
93 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
94 * <td>Unicode 10.0</td></tr>
95 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
96 * <td>Unicode 8.0</td></tr>
97 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
98 * <td>Unicode 6.2</td></tr>
99 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
100 * <td>Unicode 6.0</td></tr>
101 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
102 * <td>Unicode 4.0</td></tr>
103 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
104 * <td>Unicode 3.0</td></tr>
105 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
106 * <td>Unicode 2.0</td></tr>
107 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
108 * <td>Unicode 1.1.5</td></tr>
109 * </tbody>
110 * </table>
111 * Variations from these base Unicode versions, such as recognized appendixes,
112 * are documented elsewhere.
113 * <h2><a id="unicode">Unicode Character Representations</a></h2>
114 *
115 * <p>The {@code char} data type (and therefore the value that a
116 * {@code Character} object encapsulates) are based on the
117 * original Unicode specification, which defined characters as
118 * fixed-width 16-bit entities. The Unicode Standard has since been
119 * changed to allow for characters whose representation requires more
120 * than 16 bits. The range of legal <em>code point</em>s is now
121 * U+0000 to U+10FFFF, known as
122 * <em><a href="https://www.unicode.org/glossary/#unicode_scalar_value">
123 * Unicode scalar value</a></em>.
124 *
125 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
126 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
127 * <a id="supplementary">Characters</a> whose code points are greater
128 * than U+FFFF are called <em>supplementary character</em>s. The Java
129 * platform uses the UTF-16 representation in {@code char} arrays and
130 * in the {@code String} and {@code StringBuffer} classes. In
131 * this representation, supplementary characters are represented as a pair
132 * of {@code char} values, the first from the <em>high-surrogates</em>
133 * range, (\uD800-\uDBFF), the second from the
134 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
135 *
136 * <p>A {@code char} value, therefore, represents Basic
137 * Multilingual Plane (BMP) code points, including the surrogate
138 * code points, or code units of the UTF-16 encoding. An
139 * {@code int} value represents all Unicode code points,
140 * including supplementary code points. The lower (least significant)
141 * 21 bits of {@code int} are used to represent Unicode code
142 * points and the upper (most significant) 11 bits must be zero.
143 * Unless otherwise specified, the behavior with respect to
144 * supplementary characters and surrogate {@code char} values is
145 * as follows:
146 *
147 * <ul>
148 * <li>The methods that only accept a {@code char} value cannot support
149 * supplementary characters. They treat {@code char} values from the
150 * surrogate ranges as undefined characters. For example,
151 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
152 * this specific value if followed by any low-surrogate value in a string
153 * would represent a letter.
154 *
155 * <li>The methods that accept an {@code int} value support all
156 * Unicode characters, including supplementary characters. For
157 * example, {@code Character.isLetter(0x2F81A)} returns
158 * {@code true} because the code point value represents a letter
159 * (a CJK ideograph).
160 * </ul>
161 *
162 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
163 * used for character values in the range between U+0000 and U+10FFFF,
164 * and <em>Unicode code unit</em> is used for 16-bit
165 * {@code char} values that are code units of the <em>UTF-16</em>
166 * encoding. For more information on Unicode terminology, refer to the
167 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
168 *
169 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
170 * class; programmers should treat instances that are {@linkplain #equals(Object) equal}
171 * as interchangeable and should not use instances for synchronization, mutexes, or
172 * with {@linkplain java.lang.ref.Reference object references}.
173 *
174 * <div class="preview-block">
175 * <div class="preview-comment">
176 * When preview features are enabled, {@code Character} is a {@linkplain Class#isValue value class}.
177 * Use of value class instances for synchronization, mutexes, or with
178 * {@linkplain java.lang.ref.Reference object references} result in
179 * {@link IdentityException}.
180 * </div>
181 * </div>
182 *
183 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
184 * @author Lee Boynton
185 * @author Guy Steele
186 * @author Akira Tanaka
187 * @author Martin Buchholz
188 * @author Ulf Zibis
189 * @since 1.0
190 */
191 @jdk.internal.MigratedValueClass
192 @jdk.internal.ValueBased
193 public final class Character implements java.io.Serializable, Comparable<Character>, Constable {
194 /**
195 * The minimum radix available for conversion to and from strings.
196 * The constant value of this field is the smallest value permitted
197 * for the radix argument in radix-conversion methods such as the
198 * {@code digit} method, the {@code forDigit} method, and the
199 * {@code toString} method of class {@code Integer}.
200 *
201 * @see Character#digit(char, int)
202 * @see Character#forDigit(int, int)
203 * @see Integer#toString(int, int)
204 * @see Integer#valueOf(String)
205 */
206 public static final int MIN_RADIX = 2;
207
208 /**
209 * The maximum radix available for conversion to and from strings.
210 * The constant value of this field is the largest value permitted
211 * for the radix argument in radix-conversion methods such as the
212 * {@code digit} method, the {@code forDigit} method, and the
213 * {@code toString} method of class {@code Integer}.
214 *
215 * @see Character#digit(char, int)
216 * @see Character#forDigit(int, int)
217 * @see Integer#toString(int, int)
218 * @see Integer#valueOf(String)
219 */
220 public static final int MAX_RADIX = 36;
221
222 /**
223 * The constant value of this field is the smallest value of type
224 * {@code char}, {@code '\u005Cu0000'}.
225 *
226 * @since 1.0.2
227 */
228 public static final char MIN_VALUE = '\u0000';
229
230 /**
231 * The constant value of this field is the largest value of type
232 * {@code char}, {@code '\u005CuFFFF'}.
233 *
234 * @since 1.0.2
235 */
236 public static final char MAX_VALUE = '\uFFFF';
237
238 /**
239 * The {@code Class} instance representing the primitive type
240 * {@code char}.
241 *
242 * @since 1.1
243 */
244 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
245
246 /*
247 * Normative general types
248 */
249
250 /*
251 * General character types
252 */
253
254 /**
255 * General category "Cn" in the Unicode specification.
256 * @since 1.1
257 */
258 public static final byte UNASSIGNED = 0;
259
260 /**
261 * General category "Lu" in the Unicode specification.
262 * @since 1.1
263 */
264 public static final byte UPPERCASE_LETTER = 1;
265
266 /**
267 * General category "Ll" in the Unicode specification.
268 * @since 1.1
269 */
270 public static final byte LOWERCASE_LETTER = 2;
271
272 /**
273 * General category "Lt" in the Unicode specification.
274 * @since 1.1
275 */
276 public static final byte TITLECASE_LETTER = 3;
277
278 /**
279 * General category "Lm" in the Unicode specification.
280 * @since 1.1
281 */
282 public static final byte MODIFIER_LETTER = 4;
283
284 /**
285 * General category "Lo" in the Unicode specification.
286 * @since 1.1
287 */
288 public static final byte OTHER_LETTER = 5;
289
290 /**
291 * General category "Mn" in the Unicode specification.
292 * @since 1.1
293 */
294 public static final byte NON_SPACING_MARK = 6;
295
296 /**
297 * General category "Me" in the Unicode specification.
298 * @since 1.1
299 */
300 public static final byte ENCLOSING_MARK = 7;
301
302 /**
303 * General category "Mc" in the Unicode specification.
304 * @since 1.1
305 */
306 public static final byte COMBINING_SPACING_MARK = 8;
307
308 /**
309 * General category "Nd" in the Unicode specification.
310 * @since 1.1
311 */
312 public static final byte DECIMAL_DIGIT_NUMBER = 9;
313
314 /**
315 * General category "Nl" in the Unicode specification.
316 * @since 1.1
317 */
318 public static final byte LETTER_NUMBER = 10;
319
320 /**
321 * General category "No" in the Unicode specification.
322 * @since 1.1
323 */
324 public static final byte OTHER_NUMBER = 11;
325
326 /**
327 * General category "Zs" in the Unicode specification.
328 * @since 1.1
329 */
330 public static final byte SPACE_SEPARATOR = 12;
331
332 /**
333 * General category "Zl" in the Unicode specification.
334 * @since 1.1
335 */
336 public static final byte LINE_SEPARATOR = 13;
337
338 /**
339 * General category "Zp" in the Unicode specification.
340 * @since 1.1
341 */
342 public static final byte PARAGRAPH_SEPARATOR = 14;
343
344 /**
345 * General category "Cc" in the Unicode specification.
346 * @since 1.1
347 */
348 public static final byte CONTROL = 15;
349
350 /**
351 * General category "Cf" in the Unicode specification.
352 * @since 1.1
353 */
354 public static final byte FORMAT = 16;
355
356 /**
357 * General category "Co" in the Unicode specification.
358 * @since 1.1
359 */
360 public static final byte PRIVATE_USE = 18;
361
362 /**
363 * General category "Cs" in the Unicode specification.
364 * @since 1.1
365 */
366 public static final byte SURROGATE = 19;
367
368 /**
369 * General category "Pd" in the Unicode specification.
370 * @since 1.1
371 */
372 public static final byte DASH_PUNCTUATION = 20;
373
374 /**
375 * General category "Ps" in the Unicode specification.
376 * @since 1.1
377 */
378 public static final byte START_PUNCTUATION = 21;
379
380 /**
381 * General category "Pe" in the Unicode specification.
382 * @since 1.1
383 */
384 public static final byte END_PUNCTUATION = 22;
385
386 /**
387 * General category "Pc" in the Unicode specification.
388 * @since 1.1
389 */
390 public static final byte CONNECTOR_PUNCTUATION = 23;
391
392 /**
393 * General category "Po" in the Unicode specification.
394 * @since 1.1
395 */
396 public static final byte OTHER_PUNCTUATION = 24;
397
398 /**
399 * General category "Sm" in the Unicode specification.
400 * @since 1.1
401 */
402 public static final byte MATH_SYMBOL = 25;
403
404 /**
405 * General category "Sc" in the Unicode specification.
406 * @since 1.1
407 */
408 public static final byte CURRENCY_SYMBOL = 26;
409
410 /**
411 * General category "Sk" in the Unicode specification.
412 * @since 1.1
413 */
414 public static final byte MODIFIER_SYMBOL = 27;
415
416 /**
417 * General category "So" in the Unicode specification.
418 * @since 1.1
419 */
420 public static final byte OTHER_SYMBOL = 28;
421
422 /**
423 * General category "Pi" in the Unicode specification.
424 * @since 1.4
425 */
426 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
427
428 /**
429 * General category "Pf" in the Unicode specification.
430 * @since 1.4
431 */
432 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
433
434 /**
435 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
436 */
437 static final int ERROR = 0xFFFFFFFF;
438
439
440 /**
441 * Undefined bidirectional character type. Undefined {@code char}
442 * values have undefined directionality in the Unicode specification.
443 * @since 1.4
444 */
445 public static final byte DIRECTIONALITY_UNDEFINED = -1;
446
447 /**
448 * Strong bidirectional character type "L" in the Unicode specification.
449 * @since 1.4
450 */
451 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
452
453 /**
454 * Strong bidirectional character type "R" in the Unicode specification.
455 * @since 1.4
456 */
457 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
458
459 /**
460 * Strong bidirectional character type "AL" in the Unicode specification.
461 * @since 1.4
462 */
463 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
464
465 /**
466 * Weak bidirectional character type "EN" in the Unicode specification.
467 * @since 1.4
468 */
469 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
470
471 /**
472 * Weak bidirectional character type "ES" in the Unicode specification.
473 * @since 1.4
474 */
475 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
476
477 /**
478 * Weak bidirectional character type "ET" in the Unicode specification.
479 * @since 1.4
480 */
481 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
482
483 /**
484 * Weak bidirectional character type "AN" in the Unicode specification.
485 * @since 1.4
486 */
487 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
488
489 /**
490 * Weak bidirectional character type "CS" in the Unicode specification.
491 * @since 1.4
492 */
493 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
494
495 /**
496 * Weak bidirectional character type "NSM" in the Unicode specification.
497 * @since 1.4
498 */
499 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
500
501 /**
502 * Weak bidirectional character type "BN" in the Unicode specification.
503 * @since 1.4
504 */
505 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
506
507 /**
508 * Neutral bidirectional character type "B" in the Unicode specification.
509 * @since 1.4
510 */
511 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
512
513 /**
514 * Neutral bidirectional character type "S" in the Unicode specification.
515 * @since 1.4
516 */
517 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
518
519 /**
520 * Neutral bidirectional character type "WS" in the Unicode specification.
521 * @since 1.4
522 */
523 public static final byte DIRECTIONALITY_WHITESPACE = 12;
524
525 /**
526 * Neutral bidirectional character type "ON" in the Unicode specification.
527 * @since 1.4
528 */
529 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
530
531 /**
532 * Strong bidirectional character type "LRE" in the Unicode specification.
533 * @since 1.4
534 */
535 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
536
537 /**
538 * Strong bidirectional character type "LRO" in the Unicode specification.
539 * @since 1.4
540 */
541 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
542
543 /**
544 * Strong bidirectional character type "RLE" in the Unicode specification.
545 * @since 1.4
546 */
547 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
548
549 /**
550 * Strong bidirectional character type "RLO" in the Unicode specification.
551 * @since 1.4
552 */
553 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
554
555 /**
556 * Weak bidirectional character type "PDF" in the Unicode specification.
557 * @since 1.4
558 */
559 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
560
561 /**
562 * Weak bidirectional character type "LRI" in the Unicode specification.
563 * @since 9
564 */
565 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
566
567 /**
568 * Weak bidirectional character type "RLI" in the Unicode specification.
569 * @since 9
570 */
571 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
572
573 /**
574 * Weak bidirectional character type "FSI" in the Unicode specification.
575 * @since 9
576 */
577 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
578
579 /**
580 * Weak bidirectional character type "PDI" in the Unicode specification.
581 * @since 9
582 */
583 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
584
585 /**
586 * The minimum value of a
587 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
588 * Unicode high-surrogate code unit</a>
589 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
590 * A high-surrogate is also known as a <i>leading-surrogate</i>.
591 *
592 * @since 1.5
593 */
594 public static final char MIN_HIGH_SURROGATE = '\uD800';
595
596 /**
597 * The maximum value of a
598 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
599 * Unicode high-surrogate code unit</a>
600 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
601 * A high-surrogate is also known as a <i>leading-surrogate</i>.
602 *
603 * @since 1.5
604 */
605 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
606
607 /**
608 * The minimum value of a
609 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
610 * Unicode low-surrogate code unit</a>
611 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
612 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
613 *
614 * @since 1.5
615 */
616 public static final char MIN_LOW_SURROGATE = '\uDC00';
617
618 /**
619 * The maximum value of a
620 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
621 * Unicode low-surrogate code unit</a>
622 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
623 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
624 *
625 * @since 1.5
626 */
627 public static final char MAX_LOW_SURROGATE = '\uDFFF';
628
629 /**
630 * The minimum value of a Unicode surrogate code unit in the
631 * UTF-16 encoding, constant {@code '\u005CuD800'}.
632 *
633 * @since 1.5
634 */
635 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
636
637 /**
638 * The maximum value of a Unicode surrogate code unit in the
639 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
640 *
641 * @since 1.5
642 */
643 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
644
645 /**
646 * The minimum value of a
647 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
648 * Unicode supplementary code point</a>, constant {@code U+10000}.
649 *
650 * @since 1.5
651 */
652 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
653
654 /**
655 * The minimum value of a
656 * <a href="http://www.unicode.org/glossary/#code_point">
657 * Unicode code point</a>, constant {@code U+0000}.
658 *
659 * @since 1.5
660 */
661 public static final int MIN_CODE_POINT = 0x000000;
662
663 /**
664 * The maximum value of a
665 * <a href="http://www.unicode.org/glossary/#code_point">
666 * Unicode code point</a>, constant {@code U+10FFFF}.
667 *
668 * @since 1.5
669 */
670 public static final int MAX_CODE_POINT = 0X10FFFF;
671
672 /**
673 * Returns an {@link Optional} containing the nominal descriptor for this
674 * instance.
675 *
676 * @return an {@link Optional} describing the {@linkplain Character} instance
677 * @since 15
678 */
679 @Override
680 public Optional<DynamicConstantDesc<Character>> describeConstable() {
681 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
682 }
683
684 /**
685 * Instances of this class represent particular subsets of the Unicode
686 * character set. The only family of subsets defined in the
687 * {@code Character} class is {@link Character.UnicodeBlock}.
688 * Other portions of the Java API may define other subsets for their
689 * own purposes.
690 *
691 * @since 1.2
692 */
693 public static class Subset {
694
695 private String name;
696
697 /**
698 * Constructs a new {@code Subset} instance.
699 *
700 * @param name The name of this subset
701 * @throws NullPointerException if name is {@code null}
702 */
703 protected Subset(String name) {
704 if (name == null) {
705 throw new NullPointerException("name");
706 }
707 this.name = name;
708 }
709
710 /**
711 * Compares two {@code Subset} objects for equality.
712 * This method returns {@code true} if and only if
713 * {@code this} and the argument refer to the same
714 * object; since this method is {@code final}, this
715 * guarantee holds for all subclasses.
716 */
717 public final boolean equals(Object obj) {
718 return (this == obj);
719 }
720
721 /**
722 * Returns the standard hash code as defined by the
723 * {@link Object#hashCode} method. This method
724 * is {@code final} in order to ensure that the
725 * {@code equals} and {@code hashCode} methods will
726 * be consistent in all subclasses.
727 */
728 public final int hashCode() {
729 return super.hashCode();
730 }
731
732 /**
733 * Returns the name of this subset.
734 */
735 public final String toString() {
736 return name;
737 }
738 }
739
740 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
741 // for the latest specification of Unicode Blocks.
742
743 /**
744 * A family of character subsets representing the character blocks in the
745 * Unicode specification. Character blocks generally define characters
746 * used for a specific script or purpose. A character is contained by
747 * at most one Unicode block.
748 *
749 * @since 1.2
750 */
751 public static final class UnicodeBlock extends Subset {
752 /**
753 * NUM_ENTITIES should match the total number of UnicodeBlocks.
754 * It should be adjusted whenever the Unicode Character Database
755 * is upgraded.
756 */
757 private static final int NUM_ENTITIES = 782;
758 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
759
760 /**
761 * Creates a UnicodeBlock with the given identifier name.
762 * This name must be the same as the block identifier.
763 */
764 private UnicodeBlock(String idName) {
765 super(idName);
766 map.put(idName, this);
767 }
768
769 /**
770 * Creates a UnicodeBlock with the given identifier name and
771 * alias name.
772 */
773 private UnicodeBlock(String idName, String alias) {
774 this(idName);
775 map.put(alias, this);
776 }
777
778 /**
779 * Creates a UnicodeBlock with the given identifier name and
780 * alias names.
781 */
782 private UnicodeBlock(String idName, String... aliases) {
783 this(idName);
784 for (String alias : aliases)
785 map.put(alias, this);
786 }
787
788 /**
789 * Constant for the "Basic Latin" Unicode character block.
790 * @since 1.2
791 */
792 public static final UnicodeBlock BASIC_LATIN =
793 new UnicodeBlock("BASIC_LATIN",
794 "BASIC LATIN",
795 "BASICLATIN");
796
797 /**
798 * Constant for the "Latin-1 Supplement" Unicode character block.
799 * @since 1.2
800 */
801 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
802 new UnicodeBlock("LATIN_1_SUPPLEMENT",
803 "LATIN-1 SUPPLEMENT",
804 "LATIN-1SUPPLEMENT");
805
806 /**
807 * Constant for the "Latin Extended-A" Unicode character block.
808 * @since 1.2
809 */
810 public static final UnicodeBlock LATIN_EXTENDED_A =
811 new UnicodeBlock("LATIN_EXTENDED_A",
812 "LATIN EXTENDED-A",
813 "LATINEXTENDED-A");
814
815 /**
816 * Constant for the "Latin Extended-B" Unicode character block.
817 * @since 1.2
818 */
819 public static final UnicodeBlock LATIN_EXTENDED_B =
820 new UnicodeBlock("LATIN_EXTENDED_B",
821 "LATIN EXTENDED-B",
822 "LATINEXTENDED-B");
823
824 /**
825 * Constant for the "IPA Extensions" Unicode character block.
826 * @since 1.2
827 */
828 public static final UnicodeBlock IPA_EXTENSIONS =
829 new UnicodeBlock("IPA_EXTENSIONS",
830 "IPA EXTENSIONS",
831 "IPAEXTENSIONS");
832
833 /**
834 * Constant for the "Spacing Modifier Letters" Unicode character block.
835 * @since 1.2
836 */
837 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
838 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
839 "SPACING MODIFIER LETTERS",
840 "SPACINGMODIFIERLETTERS");
841
842 /**
843 * Constant for the "Combining Diacritical Marks" Unicode character block.
844 * @since 1.2
845 */
846 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
847 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
848 "COMBINING DIACRITICAL MARKS",
849 "COMBININGDIACRITICALMARKS");
850
851 /**
852 * Constant for the "Greek and Coptic" Unicode character block.
853 * <p>
854 * This block was previously known as the "Greek" block.
855 *
856 * @since 1.2
857 */
858 public static final UnicodeBlock GREEK =
859 new UnicodeBlock("GREEK",
860 "GREEK AND COPTIC",
861 "GREEKANDCOPTIC");
862
863 /**
864 * Constant for the "Cyrillic" Unicode character block.
865 * @since 1.2
866 */
867 public static final UnicodeBlock CYRILLIC =
868 new UnicodeBlock("CYRILLIC");
869
870 /**
871 * Constant for the "Armenian" Unicode character block.
872 * @since 1.2
873 */
874 public static final UnicodeBlock ARMENIAN =
875 new UnicodeBlock("ARMENIAN");
876
877 /**
878 * Constant for the "Hebrew" Unicode character block.
879 * @since 1.2
880 */
881 public static final UnicodeBlock HEBREW =
882 new UnicodeBlock("HEBREW");
883
884 /**
885 * Constant for the "Arabic" Unicode character block.
886 * @since 1.2
887 */
888 public static final UnicodeBlock ARABIC =
889 new UnicodeBlock("ARABIC");
890
891 /**
892 * Constant for the "Devanagari" Unicode character block.
893 * @since 1.2
894 */
895 public static final UnicodeBlock DEVANAGARI =
896 new UnicodeBlock("DEVANAGARI");
897
898 /**
899 * Constant for the "Bengali" Unicode character block.
900 * @since 1.2
901 */
902 public static final UnicodeBlock BENGALI =
903 new UnicodeBlock("BENGALI");
904
905 /**
906 * Constant for the "Gurmukhi" Unicode character block.
907 * @since 1.2
908 */
909 public static final UnicodeBlock GURMUKHI =
910 new UnicodeBlock("GURMUKHI");
911
912 /**
913 * Constant for the "Gujarati" Unicode character block.
914 * @since 1.2
915 */
916 public static final UnicodeBlock GUJARATI =
917 new UnicodeBlock("GUJARATI");
918
919 /**
920 * Constant for the "Oriya" Unicode character block.
921 * @since 1.2
922 */
923 public static final UnicodeBlock ORIYA =
924 new UnicodeBlock("ORIYA");
925
926 /**
927 * Constant for the "Tamil" Unicode character block.
928 * @since 1.2
929 */
930 public static final UnicodeBlock TAMIL =
931 new UnicodeBlock("TAMIL");
932
933 /**
934 * Constant for the "Telugu" Unicode character block.
935 * @since 1.2
936 */
937 public static final UnicodeBlock TELUGU =
938 new UnicodeBlock("TELUGU");
939
940 /**
941 * Constant for the "Kannada" Unicode character block.
942 * @since 1.2
943 */
944 public static final UnicodeBlock KANNADA =
945 new UnicodeBlock("KANNADA");
946
947 /**
948 * Constant for the "Malayalam" Unicode character block.
949 * @since 1.2
950 */
951 public static final UnicodeBlock MALAYALAM =
952 new UnicodeBlock("MALAYALAM");
953
954 /**
955 * Constant for the "Thai" Unicode character block.
956 * @since 1.2
957 */
958 public static final UnicodeBlock THAI =
959 new UnicodeBlock("THAI");
960
961 /**
962 * Constant for the "Lao" Unicode character block.
963 * @since 1.2
964 */
965 public static final UnicodeBlock LAO =
966 new UnicodeBlock("LAO");
967
968 /**
969 * Constant for the "Tibetan" Unicode character block.
970 * @since 1.2
971 */
972 public static final UnicodeBlock TIBETAN =
973 new UnicodeBlock("TIBETAN");
974
975 /**
976 * Constant for the "Georgian" Unicode character block.
977 * @since 1.2
978 */
979 public static final UnicodeBlock GEORGIAN =
980 new UnicodeBlock("GEORGIAN");
981
982 /**
983 * Constant for the "Hangul Jamo" Unicode character block.
984 * @since 1.2
985 */
986 public static final UnicodeBlock HANGUL_JAMO =
987 new UnicodeBlock("HANGUL_JAMO",
988 "HANGUL JAMO",
989 "HANGULJAMO");
990
991 /**
992 * Constant for the "Latin Extended Additional" Unicode character block.
993 * @since 1.2
994 */
995 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
996 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
997 "LATIN EXTENDED ADDITIONAL",
998 "LATINEXTENDEDADDITIONAL");
999
1000 /**
1001 * Constant for the "Greek Extended" Unicode character block.
1002 * @since 1.2
1003 */
1004 public static final UnicodeBlock GREEK_EXTENDED =
1005 new UnicodeBlock("GREEK_EXTENDED",
1006 "GREEK EXTENDED",
1007 "GREEKEXTENDED");
1008
1009 /**
1010 * Constant for the "General Punctuation" Unicode character block.
1011 * @since 1.2
1012 */
1013 public static final UnicodeBlock GENERAL_PUNCTUATION =
1014 new UnicodeBlock("GENERAL_PUNCTUATION",
1015 "GENERAL PUNCTUATION",
1016 "GENERALPUNCTUATION");
1017
1018 /**
1019 * Constant for the "Superscripts and Subscripts" Unicode character
1020 * block.
1021 * @since 1.2
1022 */
1023 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1024 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1025 "SUPERSCRIPTS AND SUBSCRIPTS",
1026 "SUPERSCRIPTSANDSUBSCRIPTS");
1027
1028 /**
1029 * Constant for the "Currency Symbols" Unicode character block.
1030 * @since 1.2
1031 */
1032 public static final UnicodeBlock CURRENCY_SYMBOLS =
1033 new UnicodeBlock("CURRENCY_SYMBOLS",
1034 "CURRENCY SYMBOLS",
1035 "CURRENCYSYMBOLS");
1036
1037 /**
1038 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1039 * character block.
1040 * <p>
1041 * This block was previously known as "Combining Marks for Symbols".
1042 * @since 1.2
1043 */
1044 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1045 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1046 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1047 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1048 "COMBINING MARKS FOR SYMBOLS",
1049 "COMBININGMARKSFORSYMBOLS");
1050
1051 /**
1052 * Constant for the "Letterlike Symbols" Unicode character block.
1053 * @since 1.2
1054 */
1055 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1056 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1057 "LETTERLIKE SYMBOLS",
1058 "LETTERLIKESYMBOLS");
1059
1060 /**
1061 * Constant for the "Number Forms" Unicode character block.
1062 * @since 1.2
1063 */
1064 public static final UnicodeBlock NUMBER_FORMS =
1065 new UnicodeBlock("NUMBER_FORMS",
1066 "NUMBER FORMS",
1067 "NUMBERFORMS");
1068
1069 /**
1070 * Constant for the "Arrows" Unicode character block.
1071 * @since 1.2
1072 */
1073 public static final UnicodeBlock ARROWS =
1074 new UnicodeBlock("ARROWS");
1075
1076 /**
1077 * Constant for the "Mathematical Operators" Unicode character block.
1078 * @since 1.2
1079 */
1080 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1081 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1082 "MATHEMATICAL OPERATORS",
1083 "MATHEMATICALOPERATORS");
1084
1085 /**
1086 * Constant for the "Miscellaneous Technical" Unicode character block.
1087 * @since 1.2
1088 */
1089 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1090 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1091 "MISCELLANEOUS TECHNICAL",
1092 "MISCELLANEOUSTECHNICAL");
1093
1094 /**
1095 * Constant for the "Control Pictures" Unicode character block.
1096 * @since 1.2
1097 */
1098 public static final UnicodeBlock CONTROL_PICTURES =
1099 new UnicodeBlock("CONTROL_PICTURES",
1100 "CONTROL PICTURES",
1101 "CONTROLPICTURES");
1102
1103 /**
1104 * Constant for the "Optical Character Recognition" Unicode character block.
1105 * @since 1.2
1106 */
1107 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1108 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1109 "OPTICAL CHARACTER RECOGNITION",
1110 "OPTICALCHARACTERRECOGNITION");
1111
1112 /**
1113 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1114 * @since 1.2
1115 */
1116 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1117 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1118 "ENCLOSED ALPHANUMERICS",
1119 "ENCLOSEDALPHANUMERICS");
1120
1121 /**
1122 * Constant for the "Box Drawing" Unicode character block.
1123 * @since 1.2
1124 */
1125 public static final UnicodeBlock BOX_DRAWING =
1126 new UnicodeBlock("BOX_DRAWING",
1127 "BOX DRAWING",
1128 "BOXDRAWING");
1129
1130 /**
1131 * Constant for the "Block Elements" Unicode character block.
1132 * @since 1.2
1133 */
1134 public static final UnicodeBlock BLOCK_ELEMENTS =
1135 new UnicodeBlock("BLOCK_ELEMENTS",
1136 "BLOCK ELEMENTS",
1137 "BLOCKELEMENTS");
1138
1139 /**
1140 * Constant for the "Geometric Shapes" Unicode character block.
1141 * @since 1.2
1142 */
1143 public static final UnicodeBlock GEOMETRIC_SHAPES =
1144 new UnicodeBlock("GEOMETRIC_SHAPES",
1145 "GEOMETRIC SHAPES",
1146 "GEOMETRICSHAPES");
1147
1148 /**
1149 * Constant for the "Miscellaneous Symbols" Unicode character block.
1150 * @since 1.2
1151 */
1152 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1153 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1154 "MISCELLANEOUS SYMBOLS",
1155 "MISCELLANEOUSSYMBOLS");
1156
1157 /**
1158 * Constant for the "Dingbats" Unicode character block.
1159 * @since 1.2
1160 */
1161 public static final UnicodeBlock DINGBATS =
1162 new UnicodeBlock("DINGBATS");
1163
1164 /**
1165 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1166 * @since 1.2
1167 */
1168 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1169 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1170 "CJK SYMBOLS AND PUNCTUATION",
1171 "CJKSYMBOLSANDPUNCTUATION");
1172
1173 /**
1174 * Constant for the "Hiragana" Unicode character block.
1175 * @since 1.2
1176 */
1177 public static final UnicodeBlock HIRAGANA =
1178 new UnicodeBlock("HIRAGANA");
1179
1180 /**
1181 * Constant for the "Katakana" Unicode character block.
1182 * @since 1.2
1183 */
1184 public static final UnicodeBlock KATAKANA =
1185 new UnicodeBlock("KATAKANA");
1186
1187 /**
1188 * Constant for the "Bopomofo" Unicode character block.
1189 * @since 1.2
1190 */
1191 public static final UnicodeBlock BOPOMOFO =
1192 new UnicodeBlock("BOPOMOFO");
1193
1194 /**
1195 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1196 * @since 1.2
1197 */
1198 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1199 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1200 "HANGUL COMPATIBILITY JAMO",
1201 "HANGULCOMPATIBILITYJAMO");
1202
1203 /**
1204 * Constant for the "Kanbun" Unicode character block.
1205 * @since 1.2
1206 */
1207 public static final UnicodeBlock KANBUN =
1208 new UnicodeBlock("KANBUN");
1209
1210 /**
1211 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1212 * @since 1.2
1213 */
1214 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1215 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1216 "ENCLOSED CJK LETTERS AND MONTHS",
1217 "ENCLOSEDCJKLETTERSANDMONTHS");
1218
1219 /**
1220 * Constant for the "CJK Compatibility" Unicode character block.
1221 * @since 1.2
1222 */
1223 public static final UnicodeBlock CJK_COMPATIBILITY =
1224 new UnicodeBlock("CJK_COMPATIBILITY",
1225 "CJK COMPATIBILITY",
1226 "CJKCOMPATIBILITY");
1227
1228 /**
1229 * Constant for the "CJK Unified Ideographs" Unicode character block.
1230 * @since 1.2
1231 */
1232 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1233 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1234 "CJK UNIFIED IDEOGRAPHS",
1235 "CJKUNIFIEDIDEOGRAPHS");
1236
1237 /**
1238 * Constant for the "Hangul Syllables" Unicode character block.
1239 * @since 1.2
1240 */
1241 public static final UnicodeBlock HANGUL_SYLLABLES =
1242 new UnicodeBlock("HANGUL_SYLLABLES",
1243 "HANGUL SYLLABLES",
1244 "HANGULSYLLABLES");
1245
1246 /**
1247 * Constant for the "Private Use Area" Unicode character block.
1248 * @since 1.2
1249 */
1250 public static final UnicodeBlock PRIVATE_USE_AREA =
1251 new UnicodeBlock("PRIVATE_USE_AREA",
1252 "PRIVATE USE AREA",
1253 "PRIVATEUSEAREA");
1254
1255 /**
1256 * Constant for the "CJK Compatibility Ideographs" Unicode character
1257 * block.
1258 * @since 1.2
1259 */
1260 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1261 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1262 "CJK COMPATIBILITY IDEOGRAPHS",
1263 "CJKCOMPATIBILITYIDEOGRAPHS");
1264
1265 /**
1266 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1267 * @since 1.2
1268 */
1269 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1270 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1271 "ALPHABETIC PRESENTATION FORMS",
1272 "ALPHABETICPRESENTATIONFORMS");
1273
1274 /**
1275 * Constant for the "Arabic Presentation Forms-A" Unicode character
1276 * block.
1277 * @since 1.2
1278 */
1279 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1280 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1281 "ARABIC PRESENTATION FORMS-A",
1282 "ARABICPRESENTATIONFORMS-A");
1283
1284 /**
1285 * Constant for the "Combining Half Marks" Unicode character block.
1286 * @since 1.2
1287 */
1288 public static final UnicodeBlock COMBINING_HALF_MARKS =
1289 new UnicodeBlock("COMBINING_HALF_MARKS",
1290 "COMBINING HALF MARKS",
1291 "COMBININGHALFMARKS");
1292
1293 /**
1294 * Constant for the "CJK Compatibility Forms" Unicode character block.
1295 * @since 1.2
1296 */
1297 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1298 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1299 "CJK COMPATIBILITY FORMS",
1300 "CJKCOMPATIBILITYFORMS");
1301
1302 /**
1303 * Constant for the "Small Form Variants" Unicode character block.
1304 * @since 1.2
1305 */
1306 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1307 new UnicodeBlock("SMALL_FORM_VARIANTS",
1308 "SMALL FORM VARIANTS",
1309 "SMALLFORMVARIANTS");
1310
1311 /**
1312 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1313 * @since 1.2
1314 */
1315 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1316 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1317 "ARABIC PRESENTATION FORMS-B",
1318 "ARABICPRESENTATIONFORMS-B");
1319
1320 /**
1321 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1322 * block.
1323 * @since 1.2
1324 */
1325 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1326 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1327 "HALFWIDTH AND FULLWIDTH FORMS",
1328 "HALFWIDTHANDFULLWIDTHFORMS");
1329
1330 /**
1331 * Constant for the "Specials" Unicode character block.
1332 * @since 1.2
1333 */
1334 public static final UnicodeBlock SPECIALS =
1335 new UnicodeBlock("SPECIALS");
1336
1337 /**
1338 * @deprecated
1339 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1340 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1341 * These constants match the block definitions of the Unicode Standard.
1342 * The {@link #of(char)} and {@link #of(int)} methods return the
1343 * standard constants.
1344 */
1345 @Deprecated(since="1.5")
1346 public static final UnicodeBlock SURROGATES_AREA =
1347 new UnicodeBlock("SURROGATES_AREA");
1348
1349 /**
1350 * Constant for the "Syriac" Unicode character block.
1351 * @since 1.4
1352 */
1353 public static final UnicodeBlock SYRIAC =
1354 new UnicodeBlock("SYRIAC");
1355
1356 /**
1357 * Constant for the "Thaana" Unicode character block.
1358 * @since 1.4
1359 */
1360 public static final UnicodeBlock THAANA =
1361 new UnicodeBlock("THAANA");
1362
1363 /**
1364 * Constant for the "Sinhala" Unicode character block.
1365 * @since 1.4
1366 */
1367 public static final UnicodeBlock SINHALA =
1368 new UnicodeBlock("SINHALA");
1369
1370 /**
1371 * Constant for the "Myanmar" Unicode character block.
1372 * @since 1.4
1373 */
1374 public static final UnicodeBlock MYANMAR =
1375 new UnicodeBlock("MYANMAR");
1376
1377 /**
1378 * Constant for the "Ethiopic" Unicode character block.
1379 * @since 1.4
1380 */
1381 public static final UnicodeBlock ETHIOPIC =
1382 new UnicodeBlock("ETHIOPIC");
1383
1384 /**
1385 * Constant for the "Cherokee" Unicode character block.
1386 * @since 1.4
1387 */
1388 public static final UnicodeBlock CHEROKEE =
1389 new UnicodeBlock("CHEROKEE");
1390
1391 /**
1392 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1393 * @since 1.4
1394 */
1395 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1396 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1397 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1398 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1399
1400 /**
1401 * Constant for the "Ogham" Unicode character block.
1402 * @since 1.4
1403 */
1404 public static final UnicodeBlock OGHAM =
1405 new UnicodeBlock("OGHAM");
1406
1407 /**
1408 * Constant for the "Runic" Unicode character block.
1409 * @since 1.4
1410 */
1411 public static final UnicodeBlock RUNIC =
1412 new UnicodeBlock("RUNIC");
1413
1414 /**
1415 * Constant for the "Khmer" Unicode character block.
1416 * @since 1.4
1417 */
1418 public static final UnicodeBlock KHMER =
1419 new UnicodeBlock("KHMER");
1420
1421 /**
1422 * Constant for the "Mongolian" Unicode character block.
1423 * @since 1.4
1424 */
1425 public static final UnicodeBlock MONGOLIAN =
1426 new UnicodeBlock("MONGOLIAN");
1427
1428 /**
1429 * Constant for the "Braille Patterns" Unicode character block.
1430 * @since 1.4
1431 */
1432 public static final UnicodeBlock BRAILLE_PATTERNS =
1433 new UnicodeBlock("BRAILLE_PATTERNS",
1434 "BRAILLE PATTERNS",
1435 "BRAILLEPATTERNS");
1436
1437 /**
1438 * Constant for the "CJK Radicals Supplement" Unicode character block.
1439 * @since 1.4
1440 */
1441 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1442 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1443 "CJK RADICALS SUPPLEMENT",
1444 "CJKRADICALSSUPPLEMENT");
1445
1446 /**
1447 * Constant for the "Kangxi Radicals" Unicode character block.
1448 * @since 1.4
1449 */
1450 public static final UnicodeBlock KANGXI_RADICALS =
1451 new UnicodeBlock("KANGXI_RADICALS",
1452 "KANGXI RADICALS",
1453 "KANGXIRADICALS");
1454
1455 /**
1456 * Constant for the "Ideographic Description Characters" Unicode character block.
1457 * @since 1.4
1458 */
1459 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1460 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1461 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1462 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1463
1464 /**
1465 * Constant for the "Bopomofo Extended" Unicode character block.
1466 * @since 1.4
1467 */
1468 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1469 new UnicodeBlock("BOPOMOFO_EXTENDED",
1470 "BOPOMOFO EXTENDED",
1471 "BOPOMOFOEXTENDED");
1472
1473 /**
1474 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1475 * @since 1.4
1476 */
1477 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1478 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1479 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1480 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1481
1482 /**
1483 * Constant for the "Yi Syllables" Unicode character block.
1484 * @since 1.4
1485 */
1486 public static final UnicodeBlock YI_SYLLABLES =
1487 new UnicodeBlock("YI_SYLLABLES",
1488 "YI SYLLABLES",
1489 "YISYLLABLES");
1490
1491 /**
1492 * Constant for the "Yi Radicals" Unicode character block.
1493 * @since 1.4
1494 */
1495 public static final UnicodeBlock YI_RADICALS =
1496 new UnicodeBlock("YI_RADICALS",
1497 "YI RADICALS",
1498 "YIRADICALS");
1499
1500 /**
1501 * Constant for the "Cyrillic Supplement" Unicode character block.
1502 * This block was previously known as the "Cyrillic Supplementary" block.
1503 * @since 1.5
1504 */
1505 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1506 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1507 "CYRILLIC SUPPLEMENTARY",
1508 "CYRILLICSUPPLEMENTARY",
1509 "CYRILLIC SUPPLEMENT",
1510 "CYRILLICSUPPLEMENT");
1511
1512 /**
1513 * Constant for the "Tagalog" Unicode character block.
1514 * @since 1.5
1515 */
1516 public static final UnicodeBlock TAGALOG =
1517 new UnicodeBlock("TAGALOG");
1518
1519 /**
1520 * Constant for the "Hanunoo" Unicode character block.
1521 * @since 1.5
1522 */
1523 public static final UnicodeBlock HANUNOO =
1524 new UnicodeBlock("HANUNOO");
1525
1526 /**
1527 * Constant for the "Buhid" Unicode character block.
1528 * @since 1.5
1529 */
1530 public static final UnicodeBlock BUHID =
1531 new UnicodeBlock("BUHID");
1532
1533 /**
1534 * Constant for the "Tagbanwa" Unicode character block.
1535 * @since 1.5
1536 */
1537 public static final UnicodeBlock TAGBANWA =
1538 new UnicodeBlock("TAGBANWA");
1539
1540 /**
1541 * Constant for the "Limbu" Unicode character block.
1542 * @since 1.5
1543 */
1544 public static final UnicodeBlock LIMBU =
1545 new UnicodeBlock("LIMBU");
1546
1547 /**
1548 * Constant for the "Tai Le" Unicode character block.
1549 * @since 1.5
1550 */
1551 public static final UnicodeBlock TAI_LE =
1552 new UnicodeBlock("TAI_LE",
1553 "TAI LE",
1554 "TAILE");
1555
1556 /**
1557 * Constant for the "Khmer Symbols" Unicode character block.
1558 * @since 1.5
1559 */
1560 public static final UnicodeBlock KHMER_SYMBOLS =
1561 new UnicodeBlock("KHMER_SYMBOLS",
1562 "KHMER SYMBOLS",
1563 "KHMERSYMBOLS");
1564
1565 /**
1566 * Constant for the "Phonetic Extensions" Unicode character block.
1567 * @since 1.5
1568 */
1569 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1570 new UnicodeBlock("PHONETIC_EXTENSIONS",
1571 "PHONETIC EXTENSIONS",
1572 "PHONETICEXTENSIONS");
1573
1574 /**
1575 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1576 * @since 1.5
1577 */
1578 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1579 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1580 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1581 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1582
1583 /**
1584 * Constant for the "Supplemental Arrows-A" Unicode character block.
1585 * @since 1.5
1586 */
1587 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1588 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1589 "SUPPLEMENTAL ARROWS-A",
1590 "SUPPLEMENTALARROWS-A");
1591
1592 /**
1593 * Constant for the "Supplemental Arrows-B" Unicode character block.
1594 * @since 1.5
1595 */
1596 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1597 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1598 "SUPPLEMENTAL ARROWS-B",
1599 "SUPPLEMENTALARROWS-B");
1600
1601 /**
1602 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1603 * character block.
1604 * @since 1.5
1605 */
1606 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1607 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1608 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1609 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1610
1611 /**
1612 * Constant for the "Supplemental Mathematical Operators" Unicode
1613 * character block.
1614 * @since 1.5
1615 */
1616 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1617 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1618 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1619 "SUPPLEMENTALMATHEMATICALOPERATORS");
1620
1621 /**
1622 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1623 * block.
1624 * @since 1.5
1625 */
1626 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1627 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1628 "MISCELLANEOUS SYMBOLS AND ARROWS",
1629 "MISCELLANEOUSSYMBOLSANDARROWS");
1630
1631 /**
1632 * Constant for the "Katakana Phonetic Extensions" Unicode character
1633 * block.
1634 * @since 1.5
1635 */
1636 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1637 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1638 "KATAKANA PHONETIC EXTENSIONS",
1639 "KATAKANAPHONETICEXTENSIONS");
1640
1641 /**
1642 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1643 * @since 1.5
1644 */
1645 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1646 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1647 "YIJING HEXAGRAM SYMBOLS",
1648 "YIJINGHEXAGRAMSYMBOLS");
1649
1650 /**
1651 * Constant for the "Variation Selectors" Unicode character block.
1652 * @since 1.5
1653 */
1654 public static final UnicodeBlock VARIATION_SELECTORS =
1655 new UnicodeBlock("VARIATION_SELECTORS",
1656 "VARIATION SELECTORS",
1657 "VARIATIONSELECTORS");
1658
1659 /**
1660 * Constant for the "Linear B Syllabary" Unicode character block.
1661 * @since 1.5
1662 */
1663 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1664 new UnicodeBlock("LINEAR_B_SYLLABARY",
1665 "LINEAR B SYLLABARY",
1666 "LINEARBSYLLABARY");
1667
1668 /**
1669 * Constant for the "Linear B Ideograms" Unicode character block.
1670 * @since 1.5
1671 */
1672 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1673 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1674 "LINEAR B IDEOGRAMS",
1675 "LINEARBIDEOGRAMS");
1676
1677 /**
1678 * Constant for the "Aegean Numbers" Unicode character block.
1679 * @since 1.5
1680 */
1681 public static final UnicodeBlock AEGEAN_NUMBERS =
1682 new UnicodeBlock("AEGEAN_NUMBERS",
1683 "AEGEAN NUMBERS",
1684 "AEGEANNUMBERS");
1685
1686 /**
1687 * Constant for the "Old Italic" Unicode character block.
1688 * @since 1.5
1689 */
1690 public static final UnicodeBlock OLD_ITALIC =
1691 new UnicodeBlock("OLD_ITALIC",
1692 "OLD ITALIC",
1693 "OLDITALIC");
1694
1695 /**
1696 * Constant for the "Gothic" Unicode character block.
1697 * @since 1.5
1698 */
1699 public static final UnicodeBlock GOTHIC =
1700 new UnicodeBlock("GOTHIC");
1701
1702 /**
1703 * Constant for the "Ugaritic" Unicode character block.
1704 * @since 1.5
1705 */
1706 public static final UnicodeBlock UGARITIC =
1707 new UnicodeBlock("UGARITIC");
1708
1709 /**
1710 * Constant for the "Deseret" Unicode character block.
1711 * @since 1.5
1712 */
1713 public static final UnicodeBlock DESERET =
1714 new UnicodeBlock("DESERET");
1715
1716 /**
1717 * Constant for the "Shavian" Unicode character block.
1718 * @since 1.5
1719 */
1720 public static final UnicodeBlock SHAVIAN =
1721 new UnicodeBlock("SHAVIAN");
1722
1723 /**
1724 * Constant for the "Osmanya" Unicode character block.
1725 * @since 1.5
1726 */
1727 public static final UnicodeBlock OSMANYA =
1728 new UnicodeBlock("OSMANYA");
1729
1730 /**
1731 * Constant for the "Cypriot Syllabary" Unicode character block.
1732 * @since 1.5
1733 */
1734 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1735 new UnicodeBlock("CYPRIOT_SYLLABARY",
1736 "CYPRIOT SYLLABARY",
1737 "CYPRIOTSYLLABARY");
1738
1739 /**
1740 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1741 * @since 1.5
1742 */
1743 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1744 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1745 "BYZANTINE MUSICAL SYMBOLS",
1746 "BYZANTINEMUSICALSYMBOLS");
1747
1748 /**
1749 * Constant for the "Musical Symbols" Unicode character block.
1750 * @since 1.5
1751 */
1752 public static final UnicodeBlock MUSICAL_SYMBOLS =
1753 new UnicodeBlock("MUSICAL_SYMBOLS",
1754 "MUSICAL SYMBOLS",
1755 "MUSICALSYMBOLS");
1756
1757 /**
1758 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1759 * @since 1.5
1760 */
1761 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1762 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1763 "TAI XUAN JING SYMBOLS",
1764 "TAIXUANJINGSYMBOLS");
1765
1766 /**
1767 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1768 * character block.
1769 * @since 1.5
1770 */
1771 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1772 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1773 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1774 "MATHEMATICALALPHANUMERICSYMBOLS");
1775
1776 /**
1777 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1778 * character block.
1779 * @since 1.5
1780 */
1781 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1782 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1783 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1784 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1785
1786 /**
1787 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1788 * @since 1.5
1789 */
1790 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1791 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1792 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1793 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1794
1795 /**
1796 * Constant for the "Tags" Unicode character block.
1797 * @since 1.5
1798 */
1799 public static final UnicodeBlock TAGS =
1800 new UnicodeBlock("TAGS");
1801
1802 /**
1803 * Constant for the "Variation Selectors Supplement" Unicode character
1804 * block.
1805 * @since 1.5
1806 */
1807 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1808 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1809 "VARIATION SELECTORS SUPPLEMENT",
1810 "VARIATIONSELECTORSSUPPLEMENT");
1811
1812 /**
1813 * Constant for the "Supplementary Private Use Area-A" Unicode character
1814 * block.
1815 * @since 1.5
1816 */
1817 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1818 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1819 "SUPPLEMENTARY PRIVATE USE AREA-A",
1820 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1821
1822 /**
1823 * Constant for the "Supplementary Private Use Area-B" Unicode character
1824 * block.
1825 * @since 1.5
1826 */
1827 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1828 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1829 "SUPPLEMENTARY PRIVATE USE AREA-B",
1830 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1831
1832 /**
1833 * Constant for the "High Surrogates" Unicode character block.
1834 * This block represents codepoint values in the high surrogate
1835 * range: U+D800 through U+DB7F
1836 *
1837 * @since 1.5
1838 */
1839 public static final UnicodeBlock HIGH_SURROGATES =
1840 new UnicodeBlock("HIGH_SURROGATES",
1841 "HIGH SURROGATES",
1842 "HIGHSURROGATES");
1843
1844 /**
1845 * Constant for the "High Private Use Surrogates" Unicode character
1846 * block.
1847 * This block represents codepoint values in the private use high
1848 * surrogate range: U+DB80 through U+DBFF
1849 *
1850 * @since 1.5
1851 */
1852 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1853 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1854 "HIGH PRIVATE USE SURROGATES",
1855 "HIGHPRIVATEUSESURROGATES");
1856
1857 /**
1858 * Constant for the "Low Surrogates" Unicode character block.
1859 * This block represents codepoint values in the low surrogate
1860 * range: U+DC00 through U+DFFF
1861 *
1862 * @since 1.5
1863 */
1864 public static final UnicodeBlock LOW_SURROGATES =
1865 new UnicodeBlock("LOW_SURROGATES",
1866 "LOW SURROGATES",
1867 "LOWSURROGATES");
1868
1869 /**
1870 * Constant for the "Arabic Supplement" Unicode character block.
1871 * @since 1.7
1872 */
1873 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1874 new UnicodeBlock("ARABIC_SUPPLEMENT",
1875 "ARABIC SUPPLEMENT",
1876 "ARABICSUPPLEMENT");
1877
1878 /**
1879 * Constant for the "NKo" Unicode character block.
1880 * @since 1.7
1881 */
1882 public static final UnicodeBlock NKO =
1883 new UnicodeBlock("NKO");
1884
1885 /**
1886 * Constant for the "Samaritan" Unicode character block.
1887 * @since 1.7
1888 */
1889 public static final UnicodeBlock SAMARITAN =
1890 new UnicodeBlock("SAMARITAN");
1891
1892 /**
1893 * Constant for the "Mandaic" Unicode character block.
1894 * @since 1.7
1895 */
1896 public static final UnicodeBlock MANDAIC =
1897 new UnicodeBlock("MANDAIC");
1898
1899 /**
1900 * Constant for the "Ethiopic Supplement" Unicode character block.
1901 * @since 1.7
1902 */
1903 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1904 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1905 "ETHIOPIC SUPPLEMENT",
1906 "ETHIOPICSUPPLEMENT");
1907
1908 /**
1909 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1910 * Unicode character block.
1911 * @since 1.7
1912 */
1913 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1914 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1915 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1916 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1917
1918 /**
1919 * Constant for the "New Tai Lue" Unicode character block.
1920 * @since 1.7
1921 */
1922 public static final UnicodeBlock NEW_TAI_LUE =
1923 new UnicodeBlock("NEW_TAI_LUE",
1924 "NEW TAI LUE",
1925 "NEWTAILUE");
1926
1927 /**
1928 * Constant for the "Buginese" Unicode character block.
1929 * @since 1.7
1930 */
1931 public static final UnicodeBlock BUGINESE =
1932 new UnicodeBlock("BUGINESE");
1933
1934 /**
1935 * Constant for the "Tai Tham" Unicode character block.
1936 * @since 1.7
1937 */
1938 public static final UnicodeBlock TAI_THAM =
1939 new UnicodeBlock("TAI_THAM",
1940 "TAI THAM",
1941 "TAITHAM");
1942
1943 /**
1944 * Constant for the "Balinese" Unicode character block.
1945 * @since 1.7
1946 */
1947 public static final UnicodeBlock BALINESE =
1948 new UnicodeBlock("BALINESE");
1949
1950 /**
1951 * Constant for the "Sundanese" Unicode character block.
1952 * @since 1.7
1953 */
1954 public static final UnicodeBlock SUNDANESE =
1955 new UnicodeBlock("SUNDANESE");
1956
1957 /**
1958 * Constant for the "Batak" Unicode character block.
1959 * @since 1.7
1960 */
1961 public static final UnicodeBlock BATAK =
1962 new UnicodeBlock("BATAK");
1963
1964 /**
1965 * Constant for the "Lepcha" Unicode character block.
1966 * @since 1.7
1967 */
1968 public static final UnicodeBlock LEPCHA =
1969 new UnicodeBlock("LEPCHA");
1970
1971 /**
1972 * Constant for the "Ol Chiki" Unicode character block.
1973 * @since 1.7
1974 */
1975 public static final UnicodeBlock OL_CHIKI =
1976 new UnicodeBlock("OL_CHIKI",
1977 "OL CHIKI",
1978 "OLCHIKI");
1979
1980 /**
1981 * Constant for the "Vedic Extensions" Unicode character block.
1982 * @since 1.7
1983 */
1984 public static final UnicodeBlock VEDIC_EXTENSIONS =
1985 new UnicodeBlock("VEDIC_EXTENSIONS",
1986 "VEDIC EXTENSIONS",
1987 "VEDICEXTENSIONS");
1988
1989 /**
1990 * Constant for the "Phonetic Extensions Supplement" Unicode character
1991 * block.
1992 * @since 1.7
1993 */
1994 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1995 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1996 "PHONETIC EXTENSIONS SUPPLEMENT",
1997 "PHONETICEXTENSIONSSUPPLEMENT");
1998
1999 /**
2000 * Constant for the "Combining Diacritical Marks Supplement" Unicode
2001 * character block.
2002 * @since 1.7
2003 */
2004 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
2005 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
2006 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
2007 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2008
2009 /**
2010 * Constant for the "Glagolitic" Unicode character block.
2011 * @since 1.7
2012 */
2013 public static final UnicodeBlock GLAGOLITIC =
2014 new UnicodeBlock("GLAGOLITIC");
2015
2016 /**
2017 * Constant for the "Latin Extended-C" Unicode character block.
2018 * @since 1.7
2019 */
2020 public static final UnicodeBlock LATIN_EXTENDED_C =
2021 new UnicodeBlock("LATIN_EXTENDED_C",
2022 "LATIN EXTENDED-C",
2023 "LATINEXTENDED-C");
2024
2025 /**
2026 * Constant for the "Coptic" Unicode character block.
2027 * @since 1.7
2028 */
2029 public static final UnicodeBlock COPTIC =
2030 new UnicodeBlock("COPTIC");
2031
2032 /**
2033 * Constant for the "Georgian Supplement" Unicode character block.
2034 * @since 1.7
2035 */
2036 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2037 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2038 "GEORGIAN SUPPLEMENT",
2039 "GEORGIANSUPPLEMENT");
2040
2041 /**
2042 * Constant for the "Tifinagh" Unicode character block.
2043 * @since 1.7
2044 */
2045 public static final UnicodeBlock TIFINAGH =
2046 new UnicodeBlock("TIFINAGH");
2047
2048 /**
2049 * Constant for the "Ethiopic Extended" Unicode character block.
2050 * @since 1.7
2051 */
2052 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2053 new UnicodeBlock("ETHIOPIC_EXTENDED",
2054 "ETHIOPIC EXTENDED",
2055 "ETHIOPICEXTENDED");
2056
2057 /**
2058 * Constant for the "Cyrillic Extended-A" Unicode character block.
2059 * @since 1.7
2060 */
2061 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2062 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2063 "CYRILLIC EXTENDED-A",
2064 "CYRILLICEXTENDED-A");
2065
2066 /**
2067 * Constant for the "Supplemental Punctuation" Unicode character block.
2068 * @since 1.7
2069 */
2070 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2071 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2072 "SUPPLEMENTAL PUNCTUATION",
2073 "SUPPLEMENTALPUNCTUATION");
2074
2075 /**
2076 * Constant for the "CJK Strokes" Unicode character block.
2077 * @since 1.7
2078 */
2079 public static final UnicodeBlock CJK_STROKES =
2080 new UnicodeBlock("CJK_STROKES",
2081 "CJK STROKES",
2082 "CJKSTROKES");
2083
2084 /**
2085 * Constant for the "Lisu" Unicode character block.
2086 * @since 1.7
2087 */
2088 public static final UnicodeBlock LISU =
2089 new UnicodeBlock("LISU");
2090
2091 /**
2092 * Constant for the "Vai" Unicode character block.
2093 * @since 1.7
2094 */
2095 public static final UnicodeBlock VAI =
2096 new UnicodeBlock("VAI");
2097
2098 /**
2099 * Constant for the "Cyrillic Extended-B" Unicode character block.
2100 * @since 1.7
2101 */
2102 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2103 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2104 "CYRILLIC EXTENDED-B",
2105 "CYRILLICEXTENDED-B");
2106
2107 /**
2108 * Constant for the "Bamum" Unicode character block.
2109 * @since 1.7
2110 */
2111 public static final UnicodeBlock BAMUM =
2112 new UnicodeBlock("BAMUM");
2113
2114 /**
2115 * Constant for the "Modifier Tone Letters" Unicode character block.
2116 * @since 1.7
2117 */
2118 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2119 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2120 "MODIFIER TONE LETTERS",
2121 "MODIFIERTONELETTERS");
2122
2123 /**
2124 * Constant for the "Latin Extended-D" Unicode character block.
2125 * @since 1.7
2126 */
2127 public static final UnicodeBlock LATIN_EXTENDED_D =
2128 new UnicodeBlock("LATIN_EXTENDED_D",
2129 "LATIN EXTENDED-D",
2130 "LATINEXTENDED-D");
2131
2132 /**
2133 * Constant for the "Syloti Nagri" Unicode character block.
2134 * @since 1.7
2135 */
2136 public static final UnicodeBlock SYLOTI_NAGRI =
2137 new UnicodeBlock("SYLOTI_NAGRI",
2138 "SYLOTI NAGRI",
2139 "SYLOTINAGRI");
2140
2141 /**
2142 * Constant for the "Common Indic Number Forms" Unicode character block.
2143 * @since 1.7
2144 */
2145 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2146 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2147 "COMMON INDIC NUMBER FORMS",
2148 "COMMONINDICNUMBERFORMS");
2149
2150 /**
2151 * Constant for the "Phags-pa" Unicode character block.
2152 * @since 1.7
2153 */
2154 public static final UnicodeBlock PHAGS_PA =
2155 new UnicodeBlock("PHAGS_PA",
2156 "PHAGS-PA");
2157
2158 /**
2159 * Constant for the "Saurashtra" Unicode character block.
2160 * @since 1.7
2161 */
2162 public static final UnicodeBlock SAURASHTRA =
2163 new UnicodeBlock("SAURASHTRA");
2164
2165 /**
2166 * Constant for the "Devanagari Extended" Unicode character block.
2167 * @since 1.7
2168 */
2169 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2170 new UnicodeBlock("DEVANAGARI_EXTENDED",
2171 "DEVANAGARI EXTENDED",
2172 "DEVANAGARIEXTENDED");
2173
2174 /**
2175 * Constant for the "Kayah Li" Unicode character block.
2176 * @since 1.7
2177 */
2178 public static final UnicodeBlock KAYAH_LI =
2179 new UnicodeBlock("KAYAH_LI",
2180 "KAYAH LI",
2181 "KAYAHLI");
2182
2183 /**
2184 * Constant for the "Rejang" Unicode character block.
2185 * @since 1.7
2186 */
2187 public static final UnicodeBlock REJANG =
2188 new UnicodeBlock("REJANG");
2189
2190 /**
2191 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2192 * @since 1.7
2193 */
2194 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2195 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2196 "HANGUL JAMO EXTENDED-A",
2197 "HANGULJAMOEXTENDED-A");
2198
2199 /**
2200 * Constant for the "Javanese" Unicode character block.
2201 * @since 1.7
2202 */
2203 public static final UnicodeBlock JAVANESE =
2204 new UnicodeBlock("JAVANESE");
2205
2206 /**
2207 * Constant for the "Cham" Unicode character block.
2208 * @since 1.7
2209 */
2210 public static final UnicodeBlock CHAM =
2211 new UnicodeBlock("CHAM");
2212
2213 /**
2214 * Constant for the "Myanmar Extended-A" Unicode character block.
2215 * @since 1.7
2216 */
2217 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2218 new UnicodeBlock("MYANMAR_EXTENDED_A",
2219 "MYANMAR EXTENDED-A",
2220 "MYANMAREXTENDED-A");
2221
2222 /**
2223 * Constant for the "Tai Viet" Unicode character block.
2224 * @since 1.7
2225 */
2226 public static final UnicodeBlock TAI_VIET =
2227 new UnicodeBlock("TAI_VIET",
2228 "TAI VIET",
2229 "TAIVIET");
2230
2231 /**
2232 * Constant for the "Ethiopic Extended-A" Unicode character block.
2233 * @since 1.7
2234 */
2235 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2236 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2237 "ETHIOPIC EXTENDED-A",
2238 "ETHIOPICEXTENDED-A");
2239
2240 /**
2241 * Constant for the "Meetei Mayek" Unicode character block.
2242 * @since 1.7
2243 */
2244 public static final UnicodeBlock MEETEI_MAYEK =
2245 new UnicodeBlock("MEETEI_MAYEK",
2246 "MEETEI MAYEK",
2247 "MEETEIMAYEK");
2248
2249 /**
2250 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2251 * @since 1.7
2252 */
2253 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2254 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2255 "HANGUL JAMO EXTENDED-B",
2256 "HANGULJAMOEXTENDED-B");
2257
2258 /**
2259 * Constant for the "Vertical Forms" Unicode character block.
2260 * @since 1.7
2261 */
2262 public static final UnicodeBlock VERTICAL_FORMS =
2263 new UnicodeBlock("VERTICAL_FORMS",
2264 "VERTICAL FORMS",
2265 "VERTICALFORMS");
2266
2267 /**
2268 * Constant for the "Ancient Greek Numbers" Unicode character block.
2269 * @since 1.7
2270 */
2271 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2272 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2273 "ANCIENT GREEK NUMBERS",
2274 "ANCIENTGREEKNUMBERS");
2275
2276 /**
2277 * Constant for the "Ancient Symbols" Unicode character block.
2278 * @since 1.7
2279 */
2280 public static final UnicodeBlock ANCIENT_SYMBOLS =
2281 new UnicodeBlock("ANCIENT_SYMBOLS",
2282 "ANCIENT SYMBOLS",
2283 "ANCIENTSYMBOLS");
2284
2285 /**
2286 * Constant for the "Phaistos Disc" Unicode character block.
2287 * @since 1.7
2288 */
2289 public static final UnicodeBlock PHAISTOS_DISC =
2290 new UnicodeBlock("PHAISTOS_DISC",
2291 "PHAISTOS DISC",
2292 "PHAISTOSDISC");
2293
2294 /**
2295 * Constant for the "Lycian" Unicode character block.
2296 * @since 1.7
2297 */
2298 public static final UnicodeBlock LYCIAN =
2299 new UnicodeBlock("LYCIAN");
2300
2301 /**
2302 * Constant for the "Carian" Unicode character block.
2303 * @since 1.7
2304 */
2305 public static final UnicodeBlock CARIAN =
2306 new UnicodeBlock("CARIAN");
2307
2308 /**
2309 * Constant for the "Old Persian" Unicode character block.
2310 * @since 1.7
2311 */
2312 public static final UnicodeBlock OLD_PERSIAN =
2313 new UnicodeBlock("OLD_PERSIAN",
2314 "OLD PERSIAN",
2315 "OLDPERSIAN");
2316
2317 /**
2318 * Constant for the "Imperial Aramaic" Unicode character block.
2319 * @since 1.7
2320 */
2321 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2322 new UnicodeBlock("IMPERIAL_ARAMAIC",
2323 "IMPERIAL ARAMAIC",
2324 "IMPERIALARAMAIC");
2325
2326 /**
2327 * Constant for the "Phoenician" Unicode character block.
2328 * @since 1.7
2329 */
2330 public static final UnicodeBlock PHOENICIAN =
2331 new UnicodeBlock("PHOENICIAN");
2332
2333 /**
2334 * Constant for the "Lydian" Unicode character block.
2335 * @since 1.7
2336 */
2337 public static final UnicodeBlock LYDIAN =
2338 new UnicodeBlock("LYDIAN");
2339
2340 /**
2341 * Constant for the "Kharoshthi" Unicode character block.
2342 * @since 1.7
2343 */
2344 public static final UnicodeBlock KHAROSHTHI =
2345 new UnicodeBlock("KHAROSHTHI");
2346
2347 /**
2348 * Constant for the "Old South Arabian" Unicode character block.
2349 * @since 1.7
2350 */
2351 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2352 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2353 "OLD SOUTH ARABIAN",
2354 "OLDSOUTHARABIAN");
2355
2356 /**
2357 * Constant for the "Avestan" Unicode character block.
2358 * @since 1.7
2359 */
2360 public static final UnicodeBlock AVESTAN =
2361 new UnicodeBlock("AVESTAN");
2362
2363 /**
2364 * Constant for the "Inscriptional Parthian" Unicode character block.
2365 * @since 1.7
2366 */
2367 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2368 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2369 "INSCRIPTIONAL PARTHIAN",
2370 "INSCRIPTIONALPARTHIAN");
2371
2372 /**
2373 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2374 * @since 1.7
2375 */
2376 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2377 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2378 "INSCRIPTIONAL PAHLAVI",
2379 "INSCRIPTIONALPAHLAVI");
2380
2381 /**
2382 * Constant for the "Old Turkic" Unicode character block.
2383 * @since 1.7
2384 */
2385 public static final UnicodeBlock OLD_TURKIC =
2386 new UnicodeBlock("OLD_TURKIC",
2387 "OLD TURKIC",
2388 "OLDTURKIC");
2389
2390 /**
2391 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2392 * @since 1.7
2393 */
2394 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2395 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2396 "RUMI NUMERAL SYMBOLS",
2397 "RUMINUMERALSYMBOLS");
2398
2399 /**
2400 * Constant for the "Brahmi" Unicode character block.
2401 * @since 1.7
2402 */
2403 public static final UnicodeBlock BRAHMI =
2404 new UnicodeBlock("BRAHMI");
2405
2406 /**
2407 * Constant for the "Kaithi" Unicode character block.
2408 * @since 1.7
2409 */
2410 public static final UnicodeBlock KAITHI =
2411 new UnicodeBlock("KAITHI");
2412
2413 /**
2414 * Constant for the "Cuneiform" Unicode character block.
2415 * @since 1.7
2416 */
2417 public static final UnicodeBlock CUNEIFORM =
2418 new UnicodeBlock("CUNEIFORM");
2419
2420 /**
2421 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2422 * character block.
2423 * @since 1.7
2424 */
2425 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2426 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2427 "CUNEIFORM NUMBERS AND PUNCTUATION",
2428 "CUNEIFORMNUMBERSANDPUNCTUATION");
2429
2430 /**
2431 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2432 * @since 1.7
2433 */
2434 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2435 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2436 "EGYPTIAN HIEROGLYPHS",
2437 "EGYPTIANHIEROGLYPHS");
2438
2439 /**
2440 * Constant for the "Bamum Supplement" Unicode character block.
2441 * @since 1.7
2442 */
2443 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2444 new UnicodeBlock("BAMUM_SUPPLEMENT",
2445 "BAMUM SUPPLEMENT",
2446 "BAMUMSUPPLEMENT");
2447
2448 /**
2449 * Constant for the "Kana Supplement" Unicode character block.
2450 * @since 1.7
2451 */
2452 public static final UnicodeBlock KANA_SUPPLEMENT =
2453 new UnicodeBlock("KANA_SUPPLEMENT",
2454 "KANA SUPPLEMENT",
2455 "KANASUPPLEMENT");
2456
2457 /**
2458 * Constant for the "Ancient Greek Musical Notation" Unicode character
2459 * block.
2460 * @since 1.7
2461 */
2462 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2463 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2464 "ANCIENT GREEK MUSICAL NOTATION",
2465 "ANCIENTGREEKMUSICALNOTATION");
2466
2467 /**
2468 * Constant for the "Counting Rod Numerals" Unicode character block.
2469 * @since 1.7
2470 */
2471 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2472 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2473 "COUNTING ROD NUMERALS",
2474 "COUNTINGRODNUMERALS");
2475
2476 /**
2477 * Constant for the "Mahjong Tiles" Unicode character block.
2478 * @since 1.7
2479 */
2480 public static final UnicodeBlock MAHJONG_TILES =
2481 new UnicodeBlock("MAHJONG_TILES",
2482 "MAHJONG TILES",
2483 "MAHJONGTILES");
2484
2485 /**
2486 * Constant for the "Domino Tiles" Unicode character block.
2487 * @since 1.7
2488 */
2489 public static final UnicodeBlock DOMINO_TILES =
2490 new UnicodeBlock("DOMINO_TILES",
2491 "DOMINO TILES",
2492 "DOMINOTILES");
2493
2494 /**
2495 * Constant for the "Playing Cards" Unicode character block.
2496 * @since 1.7
2497 */
2498 public static final UnicodeBlock PLAYING_CARDS =
2499 new UnicodeBlock("PLAYING_CARDS",
2500 "PLAYING CARDS",
2501 "PLAYINGCARDS");
2502
2503 /**
2504 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2505 * block.
2506 * @since 1.7
2507 */
2508 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2509 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2510 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2511 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2512
2513 /**
2514 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2515 * block.
2516 * @since 1.7
2517 */
2518 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2519 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2520 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2521 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2522
2523 /**
2524 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2525 * character block.
2526 * @since 1.7
2527 */
2528 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2529 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2530 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2531 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2532
2533 /**
2534 * Constant for the "Emoticons" Unicode character block.
2535 * @since 1.7
2536 */
2537 public static final UnicodeBlock EMOTICONS =
2538 new UnicodeBlock("EMOTICONS");
2539
2540 /**
2541 * Constant for the "Transport And Map Symbols" Unicode character block.
2542 * @since 1.7
2543 */
2544 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2545 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2546 "TRANSPORT AND MAP SYMBOLS",
2547 "TRANSPORTANDMAPSYMBOLS");
2548
2549 /**
2550 * Constant for the "Alchemical Symbols" Unicode character block.
2551 * @since 1.7
2552 */
2553 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2554 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2555 "ALCHEMICAL SYMBOLS",
2556 "ALCHEMICALSYMBOLS");
2557
2558 /**
2559 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2560 * character block.
2561 * @since 1.7
2562 */
2563 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2564 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2565 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2566 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2567
2568 /**
2569 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2570 * character block.
2571 * @since 1.7
2572 */
2573 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2574 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2575 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2576 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2577
2578 /**
2579 * Constant for the "Arabic Extended-A" Unicode character block.
2580 * @since 1.8
2581 */
2582 public static final UnicodeBlock ARABIC_EXTENDED_A =
2583 new UnicodeBlock("ARABIC_EXTENDED_A",
2584 "ARABIC EXTENDED-A",
2585 "ARABICEXTENDED-A");
2586
2587 /**
2588 * Constant for the "Sundanese Supplement" Unicode character block.
2589 * @since 1.8
2590 */
2591 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2592 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2593 "SUNDANESE SUPPLEMENT",
2594 "SUNDANESESUPPLEMENT");
2595
2596 /**
2597 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2598 * @since 1.8
2599 */
2600 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2601 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2602 "MEETEI MAYEK EXTENSIONS",
2603 "MEETEIMAYEKEXTENSIONS");
2604
2605 /**
2606 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2607 * @since 1.8
2608 */
2609 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2610 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2611 "MEROITIC HIEROGLYPHS",
2612 "MEROITICHIEROGLYPHS");
2613
2614 /**
2615 * Constant for the "Meroitic Cursive" Unicode character block.
2616 * @since 1.8
2617 */
2618 public static final UnicodeBlock MEROITIC_CURSIVE =
2619 new UnicodeBlock("MEROITIC_CURSIVE",
2620 "MEROITIC CURSIVE",
2621 "MEROITICCURSIVE");
2622
2623 /**
2624 * Constant for the "Sora Sompeng" Unicode character block.
2625 * @since 1.8
2626 */
2627 public static final UnicodeBlock SORA_SOMPENG =
2628 new UnicodeBlock("SORA_SOMPENG",
2629 "SORA SOMPENG",
2630 "SORASOMPENG");
2631
2632 /**
2633 * Constant for the "Chakma" Unicode character block.
2634 * @since 1.8
2635 */
2636 public static final UnicodeBlock CHAKMA =
2637 new UnicodeBlock("CHAKMA");
2638
2639 /**
2640 * Constant for the "Sharada" Unicode character block.
2641 * @since 1.8
2642 */
2643 public static final UnicodeBlock SHARADA =
2644 new UnicodeBlock("SHARADA");
2645
2646 /**
2647 * Constant for the "Takri" Unicode character block.
2648 * @since 1.8
2649 */
2650 public static final UnicodeBlock TAKRI =
2651 new UnicodeBlock("TAKRI");
2652
2653 /**
2654 * Constant for the "Miao" Unicode character block.
2655 * @since 1.8
2656 */
2657 public static final UnicodeBlock MIAO =
2658 new UnicodeBlock("MIAO");
2659
2660 /**
2661 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2662 * character block.
2663 * @since 1.8
2664 */
2665 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2666 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2667 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2668 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2669
2670 /**
2671 * Constant for the "Combining Diacritical Marks Extended" Unicode
2672 * character block.
2673 * @since 9
2674 */
2675 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2676 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2677 "COMBINING DIACRITICAL MARKS EXTENDED",
2678 "COMBININGDIACRITICALMARKSEXTENDED");
2679
2680 /**
2681 * Constant for the "Myanmar Extended-B" Unicode character block.
2682 * @since 9
2683 */
2684 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2685 new UnicodeBlock("MYANMAR_EXTENDED_B",
2686 "MYANMAR EXTENDED-B",
2687 "MYANMAREXTENDED-B");
2688
2689 /**
2690 * Constant for the "Latin Extended-E" Unicode character block.
2691 * @since 9
2692 */
2693 public static final UnicodeBlock LATIN_EXTENDED_E =
2694 new UnicodeBlock("LATIN_EXTENDED_E",
2695 "LATIN EXTENDED-E",
2696 "LATINEXTENDED-E");
2697
2698 /**
2699 * Constant for the "Coptic Epact Numbers" Unicode character block.
2700 * @since 9
2701 */
2702 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2703 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2704 "COPTIC EPACT NUMBERS",
2705 "COPTICEPACTNUMBERS");
2706
2707 /**
2708 * Constant for the "Old Permic" Unicode character block.
2709 * @since 9
2710 */
2711 public static final UnicodeBlock OLD_PERMIC =
2712 new UnicodeBlock("OLD_PERMIC",
2713 "OLD PERMIC",
2714 "OLDPERMIC");
2715
2716 /**
2717 * Constant for the "Elbasan" Unicode character block.
2718 * @since 9
2719 */
2720 public static final UnicodeBlock ELBASAN =
2721 new UnicodeBlock("ELBASAN");
2722
2723 /**
2724 * Constant for the "Caucasian Albanian" Unicode character block.
2725 * @since 9
2726 */
2727 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2728 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2729 "CAUCASIAN ALBANIAN",
2730 "CAUCASIANALBANIAN");
2731
2732 /**
2733 * Constant for the "Linear A" Unicode character block.
2734 * @since 9
2735 */
2736 public static final UnicodeBlock LINEAR_A =
2737 new UnicodeBlock("LINEAR_A",
2738 "LINEAR A",
2739 "LINEARA");
2740
2741 /**
2742 * Constant for the "Palmyrene" Unicode character block.
2743 * @since 9
2744 */
2745 public static final UnicodeBlock PALMYRENE =
2746 new UnicodeBlock("PALMYRENE");
2747
2748 /**
2749 * Constant for the "Nabataean" Unicode character block.
2750 * @since 9
2751 */
2752 public static final UnicodeBlock NABATAEAN =
2753 new UnicodeBlock("NABATAEAN");
2754
2755 /**
2756 * Constant for the "Old North Arabian" Unicode character block.
2757 * @since 9
2758 */
2759 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2760 new UnicodeBlock("OLD_NORTH_ARABIAN",
2761 "OLD NORTH ARABIAN",
2762 "OLDNORTHARABIAN");
2763
2764 /**
2765 * Constant for the "Manichaean" Unicode character block.
2766 * @since 9
2767 */
2768 public static final UnicodeBlock MANICHAEAN =
2769 new UnicodeBlock("MANICHAEAN");
2770
2771 /**
2772 * Constant for the "Psalter Pahlavi" Unicode character block.
2773 * @since 9
2774 */
2775 public static final UnicodeBlock PSALTER_PAHLAVI =
2776 new UnicodeBlock("PSALTER_PAHLAVI",
2777 "PSALTER PAHLAVI",
2778 "PSALTERPAHLAVI");
2779
2780 /**
2781 * Constant for the "Mahajani" Unicode character block.
2782 * @since 9
2783 */
2784 public static final UnicodeBlock MAHAJANI =
2785 new UnicodeBlock("MAHAJANI");
2786
2787 /**
2788 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2789 * @since 9
2790 */
2791 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2792 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2793 "SINHALA ARCHAIC NUMBERS",
2794 "SINHALAARCHAICNUMBERS");
2795
2796 /**
2797 * Constant for the "Khojki" Unicode character block.
2798 * @since 9
2799 */
2800 public static final UnicodeBlock KHOJKI =
2801 new UnicodeBlock("KHOJKI");
2802
2803 /**
2804 * Constant for the "Khudawadi" Unicode character block.
2805 * @since 9
2806 */
2807 public static final UnicodeBlock KHUDAWADI =
2808 new UnicodeBlock("KHUDAWADI");
2809
2810 /**
2811 * Constant for the "Grantha" Unicode character block.
2812 * @since 9
2813 */
2814 public static final UnicodeBlock GRANTHA =
2815 new UnicodeBlock("GRANTHA");
2816
2817 /**
2818 * Constant for the "Tirhuta" Unicode character block.
2819 * @since 9
2820 */
2821 public static final UnicodeBlock TIRHUTA =
2822 new UnicodeBlock("TIRHUTA");
2823
2824 /**
2825 * Constant for the "Siddham" Unicode character block.
2826 * @since 9
2827 */
2828 public static final UnicodeBlock SIDDHAM =
2829 new UnicodeBlock("SIDDHAM");
2830
2831 /**
2832 * Constant for the "Modi" Unicode character block.
2833 * @since 9
2834 */
2835 public static final UnicodeBlock MODI =
2836 new UnicodeBlock("MODI");
2837
2838 /**
2839 * Constant for the "Warang Citi" Unicode character block.
2840 * @since 9
2841 */
2842 public static final UnicodeBlock WARANG_CITI =
2843 new UnicodeBlock("WARANG_CITI",
2844 "WARANG CITI",
2845 "WARANGCITI");
2846
2847 /**
2848 * Constant for the "Pau Cin Hau" Unicode character block.
2849 * @since 9
2850 */
2851 public static final UnicodeBlock PAU_CIN_HAU =
2852 new UnicodeBlock("PAU_CIN_HAU",
2853 "PAU CIN HAU",
2854 "PAUCINHAU");
2855
2856 /**
2857 * Constant for the "Mro" Unicode character block.
2858 * @since 9
2859 */
2860 public static final UnicodeBlock MRO =
2861 new UnicodeBlock("MRO");
2862
2863 /**
2864 * Constant for the "Bassa Vah" Unicode character block.
2865 * @since 9
2866 */
2867 public static final UnicodeBlock BASSA_VAH =
2868 new UnicodeBlock("BASSA_VAH",
2869 "BASSA VAH",
2870 "BASSAVAH");
2871
2872 /**
2873 * Constant for the "Pahawh Hmong" Unicode character block.
2874 * @since 9
2875 */
2876 public static final UnicodeBlock PAHAWH_HMONG =
2877 new UnicodeBlock("PAHAWH_HMONG",
2878 "PAHAWH HMONG",
2879 "PAHAWHHMONG");
2880
2881 /**
2882 * Constant for the "Duployan" Unicode character block.
2883 * @since 9
2884 */
2885 public static final UnicodeBlock DUPLOYAN =
2886 new UnicodeBlock("DUPLOYAN");
2887
2888 /**
2889 * Constant for the "Shorthand Format Controls" Unicode character block.
2890 * @since 9
2891 */
2892 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2893 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2894 "SHORTHAND FORMAT CONTROLS",
2895 "SHORTHANDFORMATCONTROLS");
2896
2897 /**
2898 * Constant for the "Mende Kikakui" Unicode character block.
2899 * @since 9
2900 */
2901 public static final UnicodeBlock MENDE_KIKAKUI =
2902 new UnicodeBlock("MENDE_KIKAKUI",
2903 "MENDE KIKAKUI",
2904 "MENDEKIKAKUI");
2905
2906 /**
2907 * Constant for the "Ornamental Dingbats" Unicode character block.
2908 * @since 9
2909 */
2910 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2911 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2912 "ORNAMENTAL DINGBATS",
2913 "ORNAMENTALDINGBATS");
2914
2915 /**
2916 * Constant for the "Geometric Shapes Extended" Unicode character block.
2917 * @since 9
2918 */
2919 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2920 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2921 "GEOMETRIC SHAPES EXTENDED",
2922 "GEOMETRICSHAPESEXTENDED");
2923
2924 /**
2925 * Constant for the "Supplemental Arrows-C" Unicode character block.
2926 * @since 9
2927 */
2928 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2929 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2930 "SUPPLEMENTAL ARROWS-C",
2931 "SUPPLEMENTALARROWS-C");
2932
2933 /**
2934 * Constant for the "Cherokee Supplement" Unicode character block.
2935 * @since 9
2936 */
2937 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2938 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2939 "CHEROKEE SUPPLEMENT",
2940 "CHEROKEESUPPLEMENT");
2941
2942 /**
2943 * Constant for the "Hatran" Unicode character block.
2944 * @since 9
2945 */
2946 public static final UnicodeBlock HATRAN =
2947 new UnicodeBlock("HATRAN");
2948
2949 /**
2950 * Constant for the "Old Hungarian" Unicode character block.
2951 * @since 9
2952 */
2953 public static final UnicodeBlock OLD_HUNGARIAN =
2954 new UnicodeBlock("OLD_HUNGARIAN",
2955 "OLD HUNGARIAN",
2956 "OLDHUNGARIAN");
2957
2958 /**
2959 * Constant for the "Multani" Unicode character block.
2960 * @since 9
2961 */
2962 public static final UnicodeBlock MULTANI =
2963 new UnicodeBlock("MULTANI");
2964
2965 /**
2966 * Constant for the "Ahom" Unicode character block.
2967 * @since 9
2968 */
2969 public static final UnicodeBlock AHOM =
2970 new UnicodeBlock("AHOM");
2971
2972 /**
2973 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2974 * @since 9
2975 */
2976 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2977 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2978 "EARLY DYNASTIC CUNEIFORM",
2979 "EARLYDYNASTICCUNEIFORM");
2980
2981 /**
2982 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2983 * @since 9
2984 */
2985 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2986 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2987 "ANATOLIAN HIEROGLYPHS",
2988 "ANATOLIANHIEROGLYPHS");
2989
2990 /**
2991 * Constant for the "Sutton SignWriting" Unicode character block.
2992 * @since 9
2993 */
2994 public static final UnicodeBlock SUTTON_SIGNWRITING =
2995 new UnicodeBlock("SUTTON_SIGNWRITING",
2996 "SUTTON SIGNWRITING",
2997 "SUTTONSIGNWRITING");
2998
2999 /**
3000 * Constant for the "Supplemental Symbols and Pictographs" Unicode
3001 * character block.
3002 * @since 9
3003 */
3004 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
3005 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
3006 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
3007 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3008
3009 /**
3010 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3011 * character block.
3012 * @since 9
3013 */
3014 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3015 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3016 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3017 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3018
3019 /**
3020 * Constant for the "Syriac Supplement" Unicode
3021 * character block.
3022 * @since 11
3023 */
3024 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3025 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3026 "SYRIAC SUPPLEMENT",
3027 "SYRIACSUPPLEMENT");
3028
3029 /**
3030 * Constant for the "Cyrillic Extended-C" Unicode
3031 * character block.
3032 * @since 11
3033 */
3034 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3035 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3036 "CYRILLIC EXTENDED-C",
3037 "CYRILLICEXTENDED-C");
3038
3039 /**
3040 * Constant for the "Osage" Unicode
3041 * character block.
3042 * @since 11
3043 */
3044 public static final UnicodeBlock OSAGE =
3045 new UnicodeBlock("OSAGE");
3046
3047 /**
3048 * Constant for the "Newa" Unicode
3049 * character block.
3050 * @since 11
3051 */
3052 public static final UnicodeBlock NEWA =
3053 new UnicodeBlock("NEWA");
3054
3055 /**
3056 * Constant for the "Mongolian Supplement" Unicode
3057 * character block.
3058 * @since 11
3059 */
3060 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3061 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3062 "MONGOLIAN SUPPLEMENT",
3063 "MONGOLIANSUPPLEMENT");
3064
3065 /**
3066 * Constant for the "Marchen" Unicode
3067 * character block.
3068 * @since 11
3069 */
3070 public static final UnicodeBlock MARCHEN =
3071 new UnicodeBlock("MARCHEN");
3072
3073 /**
3074 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3075 * character block.
3076 * @since 11
3077 */
3078 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3079 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3080 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3081 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3082
3083 /**
3084 * Constant for the "Tangut" Unicode
3085 * character block.
3086 * @since 11
3087 */
3088 public static final UnicodeBlock TANGUT =
3089 new UnicodeBlock("TANGUT");
3090
3091 /**
3092 * Constant for the "Tangut Components" Unicode
3093 * character block.
3094 * @since 11
3095 */
3096 public static final UnicodeBlock TANGUT_COMPONENTS =
3097 new UnicodeBlock("TANGUT_COMPONENTS",
3098 "TANGUT COMPONENTS",
3099 "TANGUTCOMPONENTS");
3100
3101 /**
3102 * Constant for the "Kana Extended-A" Unicode
3103 * character block.
3104 * @since 11
3105 */
3106 public static final UnicodeBlock KANA_EXTENDED_A =
3107 new UnicodeBlock("KANA_EXTENDED_A",
3108 "KANA EXTENDED-A",
3109 "KANAEXTENDED-A");
3110 /**
3111 * Constant for the "Glagolitic Supplement" Unicode
3112 * character block.
3113 * @since 11
3114 */
3115 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3116 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3117 "GLAGOLITIC SUPPLEMENT",
3118 "GLAGOLITICSUPPLEMENT");
3119 /**
3120 * Constant for the "Adlam" Unicode
3121 * character block.
3122 * @since 11
3123 */
3124 public static final UnicodeBlock ADLAM =
3125 new UnicodeBlock("ADLAM");
3126
3127 /**
3128 * Constant for the "Masaram Gondi" Unicode
3129 * character block.
3130 * @since 11
3131 */
3132 public static final UnicodeBlock MASARAM_GONDI =
3133 new UnicodeBlock("MASARAM_GONDI",
3134 "MASARAM GONDI",
3135 "MASARAMGONDI");
3136
3137 /**
3138 * Constant for the "Zanabazar Square" Unicode
3139 * character block.
3140 * @since 11
3141 */
3142 public static final UnicodeBlock ZANABAZAR_SQUARE =
3143 new UnicodeBlock("ZANABAZAR_SQUARE",
3144 "ZANABAZAR SQUARE",
3145 "ZANABAZARSQUARE");
3146
3147 /**
3148 * Constant for the "Nushu" Unicode
3149 * character block.
3150 * @since 11
3151 */
3152 public static final UnicodeBlock NUSHU =
3153 new UnicodeBlock("NUSHU");
3154
3155 /**
3156 * Constant for the "Soyombo" Unicode
3157 * character block.
3158 * @since 11
3159 */
3160 public static final UnicodeBlock SOYOMBO =
3161 new UnicodeBlock("SOYOMBO");
3162
3163 /**
3164 * Constant for the "Bhaiksuki" Unicode
3165 * character block.
3166 * @since 11
3167 */
3168 public static final UnicodeBlock BHAIKSUKI =
3169 new UnicodeBlock("BHAIKSUKI");
3170
3171 /**
3172 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3173 * character block.
3174 * @since 11
3175 */
3176 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3177 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3178 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3179 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3180 /**
3181 * Constant for the "Georgian Extended" Unicode
3182 * character block.
3183 * @since 12
3184 */
3185 public static final UnicodeBlock GEORGIAN_EXTENDED =
3186 new UnicodeBlock("GEORGIAN_EXTENDED",
3187 "GEORGIAN EXTENDED",
3188 "GEORGIANEXTENDED");
3189
3190 /**
3191 * Constant for the "Hanifi Rohingya" Unicode
3192 * character block.
3193 * @since 12
3194 */
3195 public static final UnicodeBlock HANIFI_ROHINGYA =
3196 new UnicodeBlock("HANIFI_ROHINGYA",
3197 "HANIFI ROHINGYA",
3198 "HANIFIROHINGYA");
3199
3200 /**
3201 * Constant for the "Old Sogdian" Unicode
3202 * character block.
3203 * @since 12
3204 */
3205 public static final UnicodeBlock OLD_SOGDIAN =
3206 new UnicodeBlock("OLD_SOGDIAN",
3207 "OLD SOGDIAN",
3208 "OLDSOGDIAN");
3209
3210 /**
3211 * Constant for the "Sogdian" Unicode
3212 * character block.
3213 * @since 12
3214 */
3215 public static final UnicodeBlock SOGDIAN =
3216 new UnicodeBlock("SOGDIAN");
3217
3218 /**
3219 * Constant for the "Dogra" Unicode
3220 * character block.
3221 * @since 12
3222 */
3223 public static final UnicodeBlock DOGRA =
3224 new UnicodeBlock("DOGRA");
3225
3226 /**
3227 * Constant for the "Gunjala Gondi" Unicode
3228 * character block.
3229 * @since 12
3230 */
3231 public static final UnicodeBlock GUNJALA_GONDI =
3232 new UnicodeBlock("GUNJALA_GONDI",
3233 "GUNJALA GONDI",
3234 "GUNJALAGONDI");
3235
3236 /**
3237 * Constant for the "Makasar" Unicode
3238 * character block.
3239 * @since 12
3240 */
3241 public static final UnicodeBlock MAKASAR =
3242 new UnicodeBlock("MAKASAR");
3243
3244 /**
3245 * Constant for the "Medefaidrin" Unicode
3246 * character block.
3247 * @since 12
3248 */
3249 public static final UnicodeBlock MEDEFAIDRIN =
3250 new UnicodeBlock("MEDEFAIDRIN");
3251
3252 /**
3253 * Constant for the "Mayan Numerals" Unicode
3254 * character block.
3255 * @since 12
3256 */
3257 public static final UnicodeBlock MAYAN_NUMERALS =
3258 new UnicodeBlock("MAYAN_NUMERALS",
3259 "MAYAN NUMERALS",
3260 "MAYANNUMERALS");
3261
3262 /**
3263 * Constant for the "Indic Siyaq Numbers" Unicode
3264 * character block.
3265 * @since 12
3266 */
3267 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3268 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3269 "INDIC SIYAQ NUMBERS",
3270 "INDICSIYAQNUMBERS");
3271
3272 /**
3273 * Constant for the "Chess Symbols" Unicode
3274 * character block.
3275 * @since 12
3276 */
3277 public static final UnicodeBlock CHESS_SYMBOLS =
3278 new UnicodeBlock("CHESS_SYMBOLS",
3279 "CHESS SYMBOLS",
3280 "CHESSSYMBOLS");
3281
3282 /**
3283 * Constant for the "Elymaic" Unicode
3284 * character block.
3285 * @since 13
3286 */
3287 public static final UnicodeBlock ELYMAIC =
3288 new UnicodeBlock("ELYMAIC");
3289
3290 /**
3291 * Constant for the "Nandinagari" Unicode
3292 * character block.
3293 * @since 13
3294 */
3295 public static final UnicodeBlock NANDINAGARI =
3296 new UnicodeBlock("NANDINAGARI");
3297
3298 /**
3299 * Constant for the "Tamil Supplement" Unicode
3300 * character block.
3301 * @since 13
3302 */
3303 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3304 new UnicodeBlock("TAMIL_SUPPLEMENT",
3305 "TAMIL SUPPLEMENT",
3306 "TAMILSUPPLEMENT");
3307
3308 /**
3309 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3310 * character block.
3311 * @since 13
3312 */
3313 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3314 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3315 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3316 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3317
3318 /**
3319 * Constant for the "Small Kana Extension" Unicode
3320 * character block.
3321 * @since 13
3322 */
3323 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3324 new UnicodeBlock("SMALL_KANA_EXTENSION",
3325 "SMALL KANA EXTENSION",
3326 "SMALLKANAEXTENSION");
3327
3328 /**
3329 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3330 * character block.
3331 * @since 13
3332 */
3333 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3334 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3335 "NYIAKENG PUACHUE HMONG",
3336 "NYIAKENGPUACHUEHMONG");
3337
3338 /**
3339 * Constant for the "Wancho" Unicode
3340 * character block.
3341 * @since 13
3342 */
3343 public static final UnicodeBlock WANCHO =
3344 new UnicodeBlock("WANCHO");
3345
3346 /**
3347 * Constant for the "Ottoman Siyaq Numbers" Unicode
3348 * character block.
3349 * @since 13
3350 */
3351 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3352 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3353 "OTTOMAN SIYAQ NUMBERS",
3354 "OTTOMANSIYAQNUMBERS");
3355
3356 /**
3357 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3358 * character block.
3359 * @since 13
3360 */
3361 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3362 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3363 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3364 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3365
3366 /**
3367 * Constant for the "Yezidi" Unicode
3368 * character block.
3369 * @since 15
3370 */
3371 public static final UnicodeBlock YEZIDI =
3372 new UnicodeBlock("YEZIDI");
3373
3374 /**
3375 * Constant for the "Chorasmian" Unicode
3376 * character block.
3377 * @since 15
3378 */
3379 public static final UnicodeBlock CHORASMIAN =
3380 new UnicodeBlock("CHORASMIAN");
3381
3382 /**
3383 * Constant for the "Dives Akuru" Unicode
3384 * character block.
3385 * @since 15
3386 */
3387 public static final UnicodeBlock DIVES_AKURU =
3388 new UnicodeBlock("DIVES_AKURU",
3389 "DIVES AKURU",
3390 "DIVESAKURU");
3391
3392 /**
3393 * Constant for the "Lisu Supplement" Unicode
3394 * character block.
3395 * @since 15
3396 */
3397 public static final UnicodeBlock LISU_SUPPLEMENT =
3398 new UnicodeBlock("LISU_SUPPLEMENT",
3399 "LISU SUPPLEMENT",
3400 "LISUSUPPLEMENT");
3401
3402 /**
3403 * Constant for the "Khitan Small Script" Unicode
3404 * character block.
3405 * @since 15
3406 */
3407 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3408 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3409 "KHITAN SMALL SCRIPT",
3410 "KHITANSMALLSCRIPT");
3411
3412 /**
3413 * Constant for the "Tangut Supplement" Unicode
3414 * character block.
3415 * @since 15
3416 */
3417 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3418 new UnicodeBlock("TANGUT_SUPPLEMENT",
3419 "TANGUT SUPPLEMENT",
3420 "TANGUTSUPPLEMENT");
3421
3422 /**
3423 * Constant for the "Symbols for Legacy Computing" Unicode
3424 * character block.
3425 * @since 15
3426 */
3427 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3428 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3429 "SYMBOLS FOR LEGACY COMPUTING",
3430 "SYMBOLSFORLEGACYCOMPUTING");
3431
3432 /**
3433 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3434 * character block.
3435 * @since 15
3436 */
3437 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3438 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3439 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3440 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3441
3442 /**
3443 * Constant for the "Arabic Extended-B" Unicode
3444 * character block.
3445 * @since 19
3446 */
3447 public static final UnicodeBlock ARABIC_EXTENDED_B =
3448 new UnicodeBlock("ARABIC_EXTENDED_B",
3449 "ARABIC EXTENDED-B",
3450 "ARABICEXTENDED-B");
3451
3452 /**
3453 * Constant for the "Vithkuqi" Unicode
3454 * character block.
3455 * @since 19
3456 */
3457 public static final UnicodeBlock VITHKUQI =
3458 new UnicodeBlock("VITHKUQI");
3459
3460 /**
3461 * Constant for the "Latin Extended-F" Unicode
3462 * character block.
3463 * @since 19
3464 */
3465 public static final UnicodeBlock LATIN_EXTENDED_F =
3466 new UnicodeBlock("LATIN_EXTENDED_F",
3467 "LATIN EXTENDED-F",
3468 "LATINEXTENDED-F");
3469
3470 /**
3471 * Constant for the "Old Uyghur" Unicode
3472 * character block.
3473 * @since 19
3474 */
3475 public static final UnicodeBlock OLD_UYGHUR =
3476 new UnicodeBlock("OLD_UYGHUR",
3477 "OLD UYGHUR",
3478 "OLDUYGHUR");
3479
3480 /**
3481 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3482 * character block.
3483 * @since 19
3484 */
3485 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3486 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3487 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3488 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3489
3490 /**
3491 * Constant for the "Cypro-Minoan" Unicode
3492 * character block.
3493 * @since 19
3494 */
3495 public static final UnicodeBlock CYPRO_MINOAN =
3496 new UnicodeBlock("CYPRO_MINOAN",
3497 "CYPRO-MINOAN",
3498 "CYPRO-MINOAN");
3499
3500 /**
3501 * Constant for the "Tangsa" Unicode
3502 * character block.
3503 * @since 19
3504 */
3505 public static final UnicodeBlock TANGSA =
3506 new UnicodeBlock("TANGSA");
3507
3508 /**
3509 * Constant for the "Kana Extended-B" Unicode
3510 * character block.
3511 * @since 19
3512 */
3513 public static final UnicodeBlock KANA_EXTENDED_B =
3514 new UnicodeBlock("KANA_EXTENDED_B",
3515 "KANA EXTENDED-B",
3516 "KANAEXTENDED-B");
3517
3518 /**
3519 * Constant for the "Znamenny Musical Notation" Unicode
3520 * character block.
3521 * @since 19
3522 */
3523 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3524 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3525 "ZNAMENNY MUSICAL NOTATION",
3526 "ZNAMENNYMUSICALNOTATION");
3527
3528 /**
3529 * Constant for the "Latin Extended-G" Unicode
3530 * character block.
3531 * @since 19
3532 */
3533 public static final UnicodeBlock LATIN_EXTENDED_G =
3534 new UnicodeBlock("LATIN_EXTENDED_G",
3535 "LATIN EXTENDED-G",
3536 "LATINEXTENDED-G");
3537
3538 /**
3539 * Constant for the "Toto" Unicode
3540 * character block.
3541 * @since 19
3542 */
3543 public static final UnicodeBlock TOTO =
3544 new UnicodeBlock("TOTO");
3545
3546 /**
3547 * Constant for the "Ethiopic Extended-B" Unicode
3548 * character block.
3549 * @since 19
3550 */
3551 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3552 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3553 "ETHIOPIC EXTENDED-B",
3554 "ETHIOPICEXTENDED-B");
3555
3556 /**
3557 * Constant for the "Arabic Extended-C" Unicode
3558 * character block.
3559 * @since 20
3560 */
3561 public static final UnicodeBlock ARABIC_EXTENDED_C =
3562 new UnicodeBlock("ARABIC_EXTENDED_C",
3563 "ARABIC EXTENDED-C",
3564 "ARABICEXTENDED-C");
3565
3566 /**
3567 * Constant for the "Devanagari Extended-A" Unicode
3568 * character block.
3569 * @since 20
3570 */
3571 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3572 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3573 "DEVANAGARI EXTENDED-A",
3574 "DEVANAGARIEXTENDED-A");
3575
3576 /**
3577 * Constant for the "Kawi" Unicode
3578 * character block.
3579 * @since 20
3580 */
3581 public static final UnicodeBlock KAWI =
3582 new UnicodeBlock("KAWI");
3583
3584 /**
3585 * Constant for the "Kaktovik Numerals" Unicode
3586 * character block.
3587 * @since 20
3588 */
3589 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3590 new UnicodeBlock("KAKTOVIK_NUMERALS",
3591 "KAKTOVIK NUMERALS",
3592 "KAKTOVIKNUMERALS");
3593
3594 /**
3595 * Constant for the "Cyrillic Extended-D" Unicode
3596 * character block.
3597 * @since 20
3598 */
3599 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3600 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3601 "CYRILLIC EXTENDED-D",
3602 "CYRILLICEXTENDED-D");
3603
3604 /**
3605 * Constant for the "Nag Mundari" Unicode
3606 * character block.
3607 * @since 20
3608 */
3609 public static final UnicodeBlock NAG_MUNDARI =
3610 new UnicodeBlock("NAG_MUNDARI",
3611 "NAG MUNDARI",
3612 "NAGMUNDARI");
3613
3614 /**
3615 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3616 * character block.
3617 * @since 20
3618 */
3619 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3620 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3621 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3622 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3623
3624 /**
3625 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3626 * character block.
3627 * @since 22
3628 */
3629 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3630 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3631 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3632 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3633
3634 /**
3635 * Constant for the "Todhri" Unicode
3636 * character block.
3637 * @since 24
3638 */
3639 public static final UnicodeBlock TODHRI =
3640 new UnicodeBlock("TODHRI");
3641
3642 /**
3643 * Constant for the "Garay" Unicode
3644 * character block.
3645 * @since 24
3646 */
3647 public static final UnicodeBlock GARAY =
3648 new UnicodeBlock("GARAY");
3649
3650 /**
3651 * Constant for the "Tulu-Tigalari" Unicode
3652 * character block.
3653 * @since 24
3654 */
3655 public static final UnicodeBlock TULU_TIGALARI =
3656 new UnicodeBlock("TULU_TIGALARI",
3657 "TULU-TIGALARI");
3658
3659 /**
3660 * Constant for the "Myanmar Extended-C" Unicode
3661 * character block.
3662 * @since 24
3663 */
3664 public static final UnicodeBlock MYANMAR_EXTENDED_C =
3665 new UnicodeBlock("MYANMAR_EXTENDED_C",
3666 "MYANMAR EXTENDED-C",
3667 "MYANMAREXTENDED-C");
3668
3669 /**
3670 * Constant for the "Sunuwar" Unicode
3671 * character block.
3672 * @since 24
3673 */
3674 public static final UnicodeBlock SUNUWAR =
3675 new UnicodeBlock("SUNUWAR");
3676
3677 /**
3678 * Constant for the "Egyptian Hieroglyphs Extended-A" Unicode
3679 * character block.
3680 * @since 24
3681 */
3682 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS_EXTENDED_A =
3683 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS_EXTENDED_A",
3684 "EGYPTIAN HIEROGLYPHS EXTENDED-A",
3685 "EGYPTIANHIEROGLYPHSEXTENDED-A");
3686
3687 /**
3688 * Constant for the "Gurung Khema" Unicode
3689 * character block.
3690 * @since 24
3691 */
3692 public static final UnicodeBlock GURUNG_KHEMA =
3693 new UnicodeBlock("GURUNG_KHEMA",
3694 "GURUNG KHEMA",
3695 "GURUNGKHEMA");
3696
3697 /**
3698 * Constant for the "Kirat Rai" Unicode
3699 * character block.
3700 * @since 24
3701 */
3702 public static final UnicodeBlock KIRAT_RAI =
3703 new UnicodeBlock("KIRAT_RAI",
3704 "KIRAT RAI",
3705 "KIRATRAI");
3706
3707 /**
3708 * Constant for the "Symbols for Legacy Computing Supplement" Unicode
3709 * character block.
3710 * @since 24
3711 */
3712 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT =
3713 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT",
3714 "SYMBOLS FOR LEGACY COMPUTING SUPPLEMENT",
3715 "SYMBOLSFORLEGACYCOMPUTINGSUPPLEMENT");
3716
3717 /**
3718 * Constant for the "Ol Onal" Unicode
3719 * character block.
3720 * @since 24
3721 */
3722 public static final UnicodeBlock OL_ONAL =
3723 new UnicodeBlock("OL_ONAL",
3724 "OL ONAL",
3725 "OLONAL");
3726
3727 private static final int[] blockStarts = {
3728 0x0000, // 0000..007F; Basic Latin
3729 0x0080, // 0080..00FF; Latin-1 Supplement
3730 0x0100, // 0100..017F; Latin Extended-A
3731 0x0180, // 0180..024F; Latin Extended-B
3732 0x0250, // 0250..02AF; IPA Extensions
3733 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3734 0x0300, // 0300..036F; Combining Diacritical Marks
3735 0x0370, // 0370..03FF; Greek and Coptic
3736 0x0400, // 0400..04FF; Cyrillic
3737 0x0500, // 0500..052F; Cyrillic Supplement
3738 0x0530, // 0530..058F; Armenian
3739 0x0590, // 0590..05FF; Hebrew
3740 0x0600, // 0600..06FF; Arabic
3741 0x0700, // 0700..074F; Syriac
3742 0x0750, // 0750..077F; Arabic Supplement
3743 0x0780, // 0780..07BF; Thaana
3744 0x07C0, // 07C0..07FF; NKo
3745 0x0800, // 0800..083F; Samaritan
3746 0x0840, // 0840..085F; Mandaic
3747 0x0860, // 0860..086F; Syriac Supplement
3748 0x0870, // 0870..089F; Arabic Extended-B
3749 0x08A0, // 08A0..08FF; Arabic Extended-A
3750 0x0900, // 0900..097F; Devanagari
3751 0x0980, // 0980..09FF; Bengali
3752 0x0A00, // 0A00..0A7F; Gurmukhi
3753 0x0A80, // 0A80..0AFF; Gujarati
3754 0x0B00, // 0B00..0B7F; Oriya
3755 0x0B80, // 0B80..0BFF; Tamil
3756 0x0C00, // 0C00..0C7F; Telugu
3757 0x0C80, // 0C80..0CFF; Kannada
3758 0x0D00, // 0D00..0D7F; Malayalam
3759 0x0D80, // 0D80..0DFF; Sinhala
3760 0x0E00, // 0E00..0E7F; Thai
3761 0x0E80, // 0E80..0EFF; Lao
3762 0x0F00, // 0F00..0FFF; Tibetan
3763 0x1000, // 1000..109F; Myanmar
3764 0x10A0, // 10A0..10FF; Georgian
3765 0x1100, // 1100..11FF; Hangul Jamo
3766 0x1200, // 1200..137F; Ethiopic
3767 0x1380, // 1380..139F; Ethiopic Supplement
3768 0x13A0, // 13A0..13FF; Cherokee
3769 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3770 0x1680, // 1680..169F; Ogham
3771 0x16A0, // 16A0..16FF; Runic
3772 0x1700, // 1700..171F; Tagalog
3773 0x1720, // 1720..173F; Hanunoo
3774 0x1740, // 1740..175F; Buhid
3775 0x1760, // 1760..177F; Tagbanwa
3776 0x1780, // 1780..17FF; Khmer
3777 0x1800, // 1800..18AF; Mongolian
3778 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3779 0x1900, // 1900..194F; Limbu
3780 0x1950, // 1950..197F; Tai Le
3781 0x1980, // 1980..19DF; New Tai Lue
3782 0x19E0, // 19E0..19FF; Khmer Symbols
3783 0x1A00, // 1A00..1A1F; Buginese
3784 0x1A20, // 1A20..1AAF; Tai Tham
3785 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3786 0x1B00, // 1B00..1B7F; Balinese
3787 0x1B80, // 1B80..1BBF; Sundanese
3788 0x1BC0, // 1BC0..1BFF; Batak
3789 0x1C00, // 1C00..1C4F; Lepcha
3790 0x1C50, // 1C50..1C7F; Ol Chiki
3791 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3792 0x1C90, // 1C90..1CBF; Georgian Extended
3793 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3794 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3795 0x1D00, // 1D00..1D7F; Phonetic Extensions
3796 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3797 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3798 0x1E00, // 1E00..1EFF; Latin Extended Additional
3799 0x1F00, // 1F00..1FFF; Greek Extended
3800 0x2000, // 2000..206F; General Punctuation
3801 0x2070, // 2070..209F; Superscripts and Subscripts
3802 0x20A0, // 20A0..20CF; Currency Symbols
3803 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3804 0x2100, // 2100..214F; Letterlike Symbols
3805 0x2150, // 2150..218F; Number Forms
3806 0x2190, // 2190..21FF; Arrows
3807 0x2200, // 2200..22FF; Mathematical Operators
3808 0x2300, // 2300..23FF; Miscellaneous Technical
3809 0x2400, // 2400..243F; Control Pictures
3810 0x2440, // 2440..245F; Optical Character Recognition
3811 0x2460, // 2460..24FF; Enclosed Alphanumerics
3812 0x2500, // 2500..257F; Box Drawing
3813 0x2580, // 2580..259F; Block Elements
3814 0x25A0, // 25A0..25FF; Geometric Shapes
3815 0x2600, // 2600..26FF; Miscellaneous Symbols
3816 0x2700, // 2700..27BF; Dingbats
3817 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3818 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3819 0x2800, // 2800..28FF; Braille Patterns
3820 0x2900, // 2900..297F; Supplemental Arrows-B
3821 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3822 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3823 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3824 0x2C00, // 2C00..2C5F; Glagolitic
3825 0x2C60, // 2C60..2C7F; Latin Extended-C
3826 0x2C80, // 2C80..2CFF; Coptic
3827 0x2D00, // 2D00..2D2F; Georgian Supplement
3828 0x2D30, // 2D30..2D7F; Tifinagh
3829 0x2D80, // 2D80..2DDF; Ethiopic Extended
3830 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3831 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3832 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3833 0x2F00, // 2F00..2FDF; Kangxi Radicals
3834 0x2FE0, // unassigned
3835 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3836 0x3000, // 3000..303F; CJK Symbols and Punctuation
3837 0x3040, // 3040..309F; Hiragana
3838 0x30A0, // 30A0..30FF; Katakana
3839 0x3100, // 3100..312F; Bopomofo
3840 0x3130, // 3130..318F; Hangul Compatibility Jamo
3841 0x3190, // 3190..319F; Kanbun
3842 0x31A0, // 31A0..31BF; Bopomofo Extended
3843 0x31C0, // 31C0..31EF; CJK Strokes
3844 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3845 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3846 0x3300, // 3300..33FF; CJK Compatibility
3847 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3848 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3849 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3850 0xA000, // A000..A48F; Yi Syllables
3851 0xA490, // A490..A4CF; Yi Radicals
3852 0xA4D0, // A4D0..A4FF; Lisu
3853 0xA500, // A500..A63F; Vai
3854 0xA640, // A640..A69F; Cyrillic Extended-B
3855 0xA6A0, // A6A0..A6FF; Bamum
3856 0xA700, // A700..A71F; Modifier Tone Letters
3857 0xA720, // A720..A7FF; Latin Extended-D
3858 0xA800, // A800..A82F; Syloti Nagri
3859 0xA830, // A830..A83F; Common Indic Number Forms
3860 0xA840, // A840..A87F; Phags-pa
3861 0xA880, // A880..A8DF; Saurashtra
3862 0xA8E0, // A8E0..A8FF; Devanagari Extended
3863 0xA900, // A900..A92F; Kayah Li
3864 0xA930, // A930..A95F; Rejang
3865 0xA960, // A960..A97F; Hangul Jamo Extended-A
3866 0xA980, // A980..A9DF; Javanese
3867 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3868 0xAA00, // AA00..AA5F; Cham
3869 0xAA60, // AA60..AA7F; Myanmar Extended-A
3870 0xAA80, // AA80..AADF; Tai Viet
3871 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3872 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3873 0xAB30, // AB30..AB6F; Latin Extended-E
3874 0xAB70, // AB70..ABBF; Cherokee Supplement
3875 0xABC0, // ABC0..ABFF; Meetei Mayek
3876 0xAC00, // AC00..D7AF; Hangul Syllables
3877 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3878 0xD800, // D800..DB7F; High Surrogates
3879 0xDB80, // DB80..DBFF; High Private Use Surrogates
3880 0xDC00, // DC00..DFFF; Low Surrogates
3881 0xE000, // E000..F8FF; Private Use Area
3882 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3883 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3884 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3885 0xFE00, // FE00..FE0F; Variation Selectors
3886 0xFE10, // FE10..FE1F; Vertical Forms
3887 0xFE20, // FE20..FE2F; Combining Half Marks
3888 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3889 0xFE50, // FE50..FE6F; Small Form Variants
3890 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3891 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3892 0xFFF0, // FFF0..FFFF; Specials
3893 0x10000, // 10000..1007F; Linear B Syllabary
3894 0x10080, // 10080..100FF; Linear B Ideograms
3895 0x10100, // 10100..1013F; Aegean Numbers
3896 0x10140, // 10140..1018F; Ancient Greek Numbers
3897 0x10190, // 10190..101CF; Ancient Symbols
3898 0x101D0, // 101D0..101FF; Phaistos Disc
3899 0x10200, // unassigned
3900 0x10280, // 10280..1029F; Lycian
3901 0x102A0, // 102A0..102DF; Carian
3902 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3903 0x10300, // 10300..1032F; Old Italic
3904 0x10330, // 10330..1034F; Gothic
3905 0x10350, // 10350..1037F; Old Permic
3906 0x10380, // 10380..1039F; Ugaritic
3907 0x103A0, // 103A0..103DF; Old Persian
3908 0x103E0, // unassigned
3909 0x10400, // 10400..1044F; Deseret
3910 0x10450, // 10450..1047F; Shavian
3911 0x10480, // 10480..104AF; Osmanya
3912 0x104B0, // 104B0..104FF; Osage
3913 0x10500, // 10500..1052F; Elbasan
3914 0x10530, // 10530..1056F; Caucasian Albanian
3915 0x10570, // 10570..105BF; Vithkuqi
3916 0x105C0, // 105C0..105FF; Todhri
3917 0x10600, // 10600..1077F; Linear A
3918 0x10780, // 10780..107BF; Latin Extended-F
3919 0x107C0, // unassigned
3920 0x10800, // 10800..1083F; Cypriot Syllabary
3921 0x10840, // 10840..1085F; Imperial Aramaic
3922 0x10860, // 10860..1087F; Palmyrene
3923 0x10880, // 10880..108AF; Nabataean
3924 0x108B0, // unassigned
3925 0x108E0, // 108E0..108FF; Hatran
3926 0x10900, // 10900..1091F; Phoenician
3927 0x10920, // 10920..1093F; Lydian
3928 0x10940, // unassigned
3929 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3930 0x109A0, // 109A0..109FF; Meroitic Cursive
3931 0x10A00, // 10A00..10A5F; Kharoshthi
3932 0x10A60, // 10A60..10A7F; Old South Arabian
3933 0x10A80, // 10A80..10A9F; Old North Arabian
3934 0x10AA0, // unassigned
3935 0x10AC0, // 10AC0..10AFF; Manichaean
3936 0x10B00, // 10B00..10B3F; Avestan
3937 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3938 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3939 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3940 0x10BB0, // unassigned
3941 0x10C00, // 10C00..10C4F; Old Turkic
3942 0x10C50, // unassigned
3943 0x10C80, // 10C80..10CFF; Old Hungarian
3944 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3945 0x10D40, // 10D40..10D8F; Garay
3946 0x10D90, // unassigned
3947 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3948 0x10E80, // 10E80..10EBF; Yezidi
3949 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
3950 0x10F00, // 10F00..10F2F; Old Sogdian
3951 0x10F30, // 10F30..10F6F; Sogdian
3952 0x10F70, // 10F70..10FAF; Old Uyghur
3953 0x10FB0, // 10FB0..10FDF; Chorasmian
3954 0x10FE0, // 10FE0..10FFF; Elymaic
3955 0x11000, // 11000..1107F; Brahmi
3956 0x11080, // 11080..110CF; Kaithi
3957 0x110D0, // 110D0..110FF; Sora Sompeng
3958 0x11100, // 11100..1114F; Chakma
3959 0x11150, // 11150..1117F; Mahajani
3960 0x11180, // 11180..111DF; Sharada
3961 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3962 0x11200, // 11200..1124F; Khojki
3963 0x11250, // unassigned
3964 0x11280, // 11280..112AF; Multani
3965 0x112B0, // 112B0..112FF; Khudawadi
3966 0x11300, // 11300..1137F; Grantha
3967 0x11380, // 11380..113FF; Tulu-Tigalari
3968 0x11400, // 11400..1147F; Newa
3969 0x11480, // 11480..114DF; Tirhuta
3970 0x114E0, // unassigned
3971 0x11580, // 11580..115FF; Siddham
3972 0x11600, // 11600..1165F; Modi
3973 0x11660, // 11660..1167F; Mongolian Supplement
3974 0x11680, // 11680..116CF; Takri
3975 0x116D0, // 116D0..116FF; Myanmar Extended-C
3976 0x11700, // 11700..1174F; Ahom
3977 0x11750, // unassigned
3978 0x11800, // 11800..1184F; Dogra
3979 0x11850, // unassigned
3980 0x118A0, // 118A0..118FF; Warang Citi
3981 0x11900, // 11900..1195F; Dives Akuru
3982 0x11960, // unassigned
3983 0x119A0, // 119A0..119FF; Nandinagari
3984 0x11A00, // 11A00..11A4F; Zanabazar Square
3985 0x11A50, // 11A50..11AAF; Soyombo
3986 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
3987 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3988 0x11B00, // 11B00..11B5F; Devanagari Extended-A
3989 0x11B60, // unassigned
3990 0x11BC0, // 11BC0..11BFF; Sunuwar
3991 0x11C00, // 11C00..11C6F; Bhaiksuki
3992 0x11C70, // 11C70..11CBF; Marchen
3993 0x11CC0, // unassigned
3994 0x11D00, // 11D00..11D5F; Masaram Gondi
3995 0x11D60, // 11D60..11DAF; Gunjala Gondi
3996 0x11DB0, // unassigned
3997 0x11EE0, // 11EE0..11EFF; Makasar
3998 0x11F00, // 11F00..11F5F; Kawi
3999 0x11F60, // unassigned
4000 0x11FB0, // 11FB0..11FBF; Lisu Supplement
4001 0x11FC0, // 11FC0..11FFF; Tamil Supplement
4002 0x12000, // 12000..123FF; Cuneiform
4003 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
4004 0x12480, // 12480..1254F; Early Dynastic Cuneiform
4005 0x12550, // unassigned
4006 0x12F90, // 12F90..12FFF; Cypro-Minoan
4007 0x13000, // 13000..1342F; Egyptian Hieroglyphs
4008 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
4009 0x13460, // 13460..143FF; Egyptian Hieroglyphs Extended-A
4010 0x14400, // 14400..1467F; Anatolian Hieroglyphs
4011 0x14680, // unassigned
4012 0x16100, // 16100..1613F; Gurung Khema
4013 0x16140, // unassigned
4014 0x16800, // 16800..16A3F; Bamum Supplement
4015 0x16A40, // 16A40..16A6F; Mro
4016 0x16A70, // 16A70..16ACF; Tangsa
4017 0x16AD0, // 16AD0..16AFF; Bassa Vah
4018 0x16B00, // 16B00..16B8F; Pahawh Hmong
4019 0x16B90, // unassigned
4020 0x16D40, // 16D40..16D7F; Kirat Rai
4021 0x16D80, // unassigned
4022 0x16E40, // 16E40..16E9F; Medefaidrin
4023 0x16EA0, // unassigned
4024 0x16F00, // 16F00..16F9F; Miao
4025 0x16FA0, // unassigned
4026 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
4027 0x17000, // 17000..187FF; Tangut
4028 0x18800, // 18800..18AFF; Tangut Components
4029 0x18B00, // 18B00..18CFF; Khitan Small Script
4030 0x18D00, // 18D00..18D7F; Tangut Supplement
4031 0x18D80, // unassigned
4032 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
4033 0x1B000, // 1B000..1B0FF; Kana Supplement
4034 0x1B100, // 1B100..1B12F; Kana Extended-A
4035 0x1B130, // 1B130..1B16F; Small Kana Extension
4036 0x1B170, // 1B170..1B2FF; Nushu
4037 0x1B300, // unassigned
4038 0x1BC00, // 1BC00..1BC9F; Duployan
4039 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
4040 0x1BCB0, // unassigned
4041 0x1CC00, // 1CC00..1CEBF; Symbols for Legacy Computing Supplement
4042 0x1CEC0, // unassigned
4043 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
4044 0x1CFD0, // unassigned
4045 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
4046 0x1D100, // 1D100..1D1FF; Musical Symbols
4047 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
4048 0x1D250, // unassigned
4049 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
4050 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
4051 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
4052 0x1D360, // 1D360..1D37F; Counting Rod Numerals
4053 0x1D380, // unassigned
4054 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
4055 0x1D800, // 1D800..1DAAF; Sutton SignWriting
4056 0x1DAB0, // unassigned
4057 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
4058 0x1E000, // 1E000..1E02F; Glagolitic Supplement
4059 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
4060 0x1E090, // unassigned
4061 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
4062 0x1E150, // unassigned
4063 0x1E290, // 1E290..1E2BF; Toto
4064 0x1E2C0, // 1E2C0..1E2FF; Wancho
4065 0x1E300, // unassigned
4066 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
4067 0x1E500, // unassigned
4068 0x1E5D0, // 1E5D0..1E5FF; Ol Onal
4069 0x1E600, // unassigned
4070 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
4071 0x1E800, // 1E800..1E8DF; Mende Kikakui
4072 0x1E8E0, // unassigned
4073 0x1E900, // 1E900..1E95F; Adlam
4074 0x1E960, // unassigned
4075 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
4076 0x1ECC0, // unassigned
4077 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
4078 0x1ED50, // unassigned
4079 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
4080 0x1EF00, // unassigned
4081 0x1F000, // 1F000..1F02F; Mahjong Tiles
4082 0x1F030, // 1F030..1F09F; Domino Tiles
4083 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
4084 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
4085 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
4086 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
4087 0x1F600, // 1F600..1F64F; Emoticons
4088 0x1F650, // 1F650..1F67F; Ornamental Dingbats
4089 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
4090 0x1F700, // 1F700..1F77F; Alchemical Symbols
4091 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
4092 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
4093 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
4094 0x1FA00, // 1FA00..1FA6F; Chess Symbols
4095 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
4096 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
4097 0x1FC00, // unassigned
4098 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
4099 0x2A6E0, // unassigned
4100 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
4101 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
4102 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
4103 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
4104 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
4105 0x2EE60, // unassigned
4106 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
4107 0x2FA20, // unassigned
4108 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
4109 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4110 0x323B0, // unassigned
4111 0xE0000, // E0000..E007F; Tags
4112 0xE0080, // unassigned
4113 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4114 0xE01F0, // unassigned
4115 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4116 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4117 };
4118
4119 private static final UnicodeBlock[] blocks = {
4120 BASIC_LATIN,
4121 LATIN_1_SUPPLEMENT,
4122 LATIN_EXTENDED_A,
4123 LATIN_EXTENDED_B,
4124 IPA_EXTENSIONS,
4125 SPACING_MODIFIER_LETTERS,
4126 COMBINING_DIACRITICAL_MARKS,
4127 GREEK,
4128 CYRILLIC,
4129 CYRILLIC_SUPPLEMENTARY,
4130 ARMENIAN,
4131 HEBREW,
4132 ARABIC,
4133 SYRIAC,
4134 ARABIC_SUPPLEMENT,
4135 THAANA,
4136 NKO,
4137 SAMARITAN,
4138 MANDAIC,
4139 SYRIAC_SUPPLEMENT,
4140 ARABIC_EXTENDED_B,
4141 ARABIC_EXTENDED_A,
4142 DEVANAGARI,
4143 BENGALI,
4144 GURMUKHI,
4145 GUJARATI,
4146 ORIYA,
4147 TAMIL,
4148 TELUGU,
4149 KANNADA,
4150 MALAYALAM,
4151 SINHALA,
4152 THAI,
4153 LAO,
4154 TIBETAN,
4155 MYANMAR,
4156 GEORGIAN,
4157 HANGUL_JAMO,
4158 ETHIOPIC,
4159 ETHIOPIC_SUPPLEMENT,
4160 CHEROKEE,
4161 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4162 OGHAM,
4163 RUNIC,
4164 TAGALOG,
4165 HANUNOO,
4166 BUHID,
4167 TAGBANWA,
4168 KHMER,
4169 MONGOLIAN,
4170 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4171 LIMBU,
4172 TAI_LE,
4173 NEW_TAI_LUE,
4174 KHMER_SYMBOLS,
4175 BUGINESE,
4176 TAI_THAM,
4177 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4178 BALINESE,
4179 SUNDANESE,
4180 BATAK,
4181 LEPCHA,
4182 OL_CHIKI,
4183 CYRILLIC_EXTENDED_C,
4184 GEORGIAN_EXTENDED,
4185 SUNDANESE_SUPPLEMENT,
4186 VEDIC_EXTENSIONS,
4187 PHONETIC_EXTENSIONS,
4188 PHONETIC_EXTENSIONS_SUPPLEMENT,
4189 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4190 LATIN_EXTENDED_ADDITIONAL,
4191 GREEK_EXTENDED,
4192 GENERAL_PUNCTUATION,
4193 SUPERSCRIPTS_AND_SUBSCRIPTS,
4194 CURRENCY_SYMBOLS,
4195 COMBINING_MARKS_FOR_SYMBOLS,
4196 LETTERLIKE_SYMBOLS,
4197 NUMBER_FORMS,
4198 ARROWS,
4199 MATHEMATICAL_OPERATORS,
4200 MISCELLANEOUS_TECHNICAL,
4201 CONTROL_PICTURES,
4202 OPTICAL_CHARACTER_RECOGNITION,
4203 ENCLOSED_ALPHANUMERICS,
4204 BOX_DRAWING,
4205 BLOCK_ELEMENTS,
4206 GEOMETRIC_SHAPES,
4207 MISCELLANEOUS_SYMBOLS,
4208 DINGBATS,
4209 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4210 SUPPLEMENTAL_ARROWS_A,
4211 BRAILLE_PATTERNS,
4212 SUPPLEMENTAL_ARROWS_B,
4213 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4214 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4215 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4216 GLAGOLITIC,
4217 LATIN_EXTENDED_C,
4218 COPTIC,
4219 GEORGIAN_SUPPLEMENT,
4220 TIFINAGH,
4221 ETHIOPIC_EXTENDED,
4222 CYRILLIC_EXTENDED_A,
4223 SUPPLEMENTAL_PUNCTUATION,
4224 CJK_RADICALS_SUPPLEMENT,
4225 KANGXI_RADICALS,
4226 null,
4227 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4228 CJK_SYMBOLS_AND_PUNCTUATION,
4229 HIRAGANA,
4230 KATAKANA,
4231 BOPOMOFO,
4232 HANGUL_COMPATIBILITY_JAMO,
4233 KANBUN,
4234 BOPOMOFO_EXTENDED,
4235 CJK_STROKES,
4236 KATAKANA_PHONETIC_EXTENSIONS,
4237 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4238 CJK_COMPATIBILITY,
4239 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4240 YIJING_HEXAGRAM_SYMBOLS,
4241 CJK_UNIFIED_IDEOGRAPHS,
4242 YI_SYLLABLES,
4243 YI_RADICALS,
4244 LISU,
4245 VAI,
4246 CYRILLIC_EXTENDED_B,
4247 BAMUM,
4248 MODIFIER_TONE_LETTERS,
4249 LATIN_EXTENDED_D,
4250 SYLOTI_NAGRI,
4251 COMMON_INDIC_NUMBER_FORMS,
4252 PHAGS_PA,
4253 SAURASHTRA,
4254 DEVANAGARI_EXTENDED,
4255 KAYAH_LI,
4256 REJANG,
4257 HANGUL_JAMO_EXTENDED_A,
4258 JAVANESE,
4259 MYANMAR_EXTENDED_B,
4260 CHAM,
4261 MYANMAR_EXTENDED_A,
4262 TAI_VIET,
4263 MEETEI_MAYEK_EXTENSIONS,
4264 ETHIOPIC_EXTENDED_A,
4265 LATIN_EXTENDED_E,
4266 CHEROKEE_SUPPLEMENT,
4267 MEETEI_MAYEK,
4268 HANGUL_SYLLABLES,
4269 HANGUL_JAMO_EXTENDED_B,
4270 HIGH_SURROGATES,
4271 HIGH_PRIVATE_USE_SURROGATES,
4272 LOW_SURROGATES,
4273 PRIVATE_USE_AREA,
4274 CJK_COMPATIBILITY_IDEOGRAPHS,
4275 ALPHABETIC_PRESENTATION_FORMS,
4276 ARABIC_PRESENTATION_FORMS_A,
4277 VARIATION_SELECTORS,
4278 VERTICAL_FORMS,
4279 COMBINING_HALF_MARKS,
4280 CJK_COMPATIBILITY_FORMS,
4281 SMALL_FORM_VARIANTS,
4282 ARABIC_PRESENTATION_FORMS_B,
4283 HALFWIDTH_AND_FULLWIDTH_FORMS,
4284 SPECIALS,
4285 LINEAR_B_SYLLABARY,
4286 LINEAR_B_IDEOGRAMS,
4287 AEGEAN_NUMBERS,
4288 ANCIENT_GREEK_NUMBERS,
4289 ANCIENT_SYMBOLS,
4290 PHAISTOS_DISC,
4291 null,
4292 LYCIAN,
4293 CARIAN,
4294 COPTIC_EPACT_NUMBERS,
4295 OLD_ITALIC,
4296 GOTHIC,
4297 OLD_PERMIC,
4298 UGARITIC,
4299 OLD_PERSIAN,
4300 null,
4301 DESERET,
4302 SHAVIAN,
4303 OSMANYA,
4304 OSAGE,
4305 ELBASAN,
4306 CAUCASIAN_ALBANIAN,
4307 VITHKUQI,
4308 TODHRI,
4309 LINEAR_A,
4310 LATIN_EXTENDED_F,
4311 null,
4312 CYPRIOT_SYLLABARY,
4313 IMPERIAL_ARAMAIC,
4314 PALMYRENE,
4315 NABATAEAN,
4316 null,
4317 HATRAN,
4318 PHOENICIAN,
4319 LYDIAN,
4320 null,
4321 MEROITIC_HIEROGLYPHS,
4322 MEROITIC_CURSIVE,
4323 KHAROSHTHI,
4324 OLD_SOUTH_ARABIAN,
4325 OLD_NORTH_ARABIAN,
4326 null,
4327 MANICHAEAN,
4328 AVESTAN,
4329 INSCRIPTIONAL_PARTHIAN,
4330 INSCRIPTIONAL_PAHLAVI,
4331 PSALTER_PAHLAVI,
4332 null,
4333 OLD_TURKIC,
4334 null,
4335 OLD_HUNGARIAN,
4336 HANIFI_ROHINGYA,
4337 GARAY,
4338 null,
4339 RUMI_NUMERAL_SYMBOLS,
4340 YEZIDI,
4341 ARABIC_EXTENDED_C,
4342 OLD_SOGDIAN,
4343 SOGDIAN,
4344 OLD_UYGHUR,
4345 CHORASMIAN,
4346 ELYMAIC,
4347 BRAHMI,
4348 KAITHI,
4349 SORA_SOMPENG,
4350 CHAKMA,
4351 MAHAJANI,
4352 SHARADA,
4353 SINHALA_ARCHAIC_NUMBERS,
4354 KHOJKI,
4355 null,
4356 MULTANI,
4357 KHUDAWADI,
4358 GRANTHA,
4359 TULU_TIGALARI,
4360 NEWA,
4361 TIRHUTA,
4362 null,
4363 SIDDHAM,
4364 MODI,
4365 MONGOLIAN_SUPPLEMENT,
4366 TAKRI,
4367 MYANMAR_EXTENDED_C,
4368 AHOM,
4369 null,
4370 DOGRA,
4371 null,
4372 WARANG_CITI,
4373 DIVES_AKURU,
4374 null,
4375 NANDINAGARI,
4376 ZANABAZAR_SQUARE,
4377 SOYOMBO,
4378 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4379 PAU_CIN_HAU,
4380 DEVANAGARI_EXTENDED_A,
4381 null,
4382 SUNUWAR,
4383 BHAIKSUKI,
4384 MARCHEN,
4385 null,
4386 MASARAM_GONDI,
4387 GUNJALA_GONDI,
4388 null,
4389 MAKASAR,
4390 KAWI,
4391 null,
4392 LISU_SUPPLEMENT,
4393 TAMIL_SUPPLEMENT,
4394 CUNEIFORM,
4395 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4396 EARLY_DYNASTIC_CUNEIFORM,
4397 null,
4398 CYPRO_MINOAN,
4399 EGYPTIAN_HIEROGLYPHS,
4400 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4401 EGYPTIAN_HIEROGLYPHS_EXTENDED_A,
4402 ANATOLIAN_HIEROGLYPHS,
4403 null,
4404 GURUNG_KHEMA,
4405 null,
4406 BAMUM_SUPPLEMENT,
4407 MRO,
4408 TANGSA,
4409 BASSA_VAH,
4410 PAHAWH_HMONG,
4411 null,
4412 KIRAT_RAI,
4413 null,
4414 MEDEFAIDRIN,
4415 null,
4416 MIAO,
4417 null,
4418 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4419 TANGUT,
4420 TANGUT_COMPONENTS,
4421 KHITAN_SMALL_SCRIPT,
4422 TANGUT_SUPPLEMENT,
4423 null,
4424 KANA_EXTENDED_B,
4425 KANA_SUPPLEMENT,
4426 KANA_EXTENDED_A,
4427 SMALL_KANA_EXTENSION,
4428 NUSHU,
4429 null,
4430 DUPLOYAN,
4431 SHORTHAND_FORMAT_CONTROLS,
4432 null,
4433 SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT,
4434 null,
4435 ZNAMENNY_MUSICAL_NOTATION,
4436 null,
4437 BYZANTINE_MUSICAL_SYMBOLS,
4438 MUSICAL_SYMBOLS,
4439 ANCIENT_GREEK_MUSICAL_NOTATION,
4440 null,
4441 KAKTOVIK_NUMERALS,
4442 MAYAN_NUMERALS,
4443 TAI_XUAN_JING_SYMBOLS,
4444 COUNTING_ROD_NUMERALS,
4445 null,
4446 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4447 SUTTON_SIGNWRITING,
4448 null,
4449 LATIN_EXTENDED_G,
4450 GLAGOLITIC_SUPPLEMENT,
4451 CYRILLIC_EXTENDED_D,
4452 null,
4453 NYIAKENG_PUACHUE_HMONG,
4454 null,
4455 TOTO,
4456 WANCHO,
4457 null,
4458 NAG_MUNDARI,
4459 null,
4460 OL_ONAL,
4461 null,
4462 ETHIOPIC_EXTENDED_B,
4463 MENDE_KIKAKUI,
4464 null,
4465 ADLAM,
4466 null,
4467 INDIC_SIYAQ_NUMBERS,
4468 null,
4469 OTTOMAN_SIYAQ_NUMBERS,
4470 null,
4471 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4472 null,
4473 MAHJONG_TILES,
4474 DOMINO_TILES,
4475 PLAYING_CARDS,
4476 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4477 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4478 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4479 EMOTICONS,
4480 ORNAMENTAL_DINGBATS,
4481 TRANSPORT_AND_MAP_SYMBOLS,
4482 ALCHEMICAL_SYMBOLS,
4483 GEOMETRIC_SHAPES_EXTENDED,
4484 SUPPLEMENTAL_ARROWS_C,
4485 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4486 CHESS_SYMBOLS,
4487 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4488 SYMBOLS_FOR_LEGACY_COMPUTING,
4489 null,
4490 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4491 null,
4492 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4493 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4494 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4495 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4496 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4497 null,
4498 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4499 null,
4500 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4501 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4502 null,
4503 TAGS,
4504 null,
4505 VARIATION_SELECTORS_SUPPLEMENT,
4506 null,
4507 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4508 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4509 };
4510
4511
4512 /**
4513 * Returns the object representing the Unicode block containing the
4514 * given character, or {@code null} if the character is not a
4515 * member of a defined block.
4516 *
4517 * <p><b>Note:</b> This method cannot handle
4518 * <a href="Character.html#supplementary"> supplementary
4519 * characters</a>. To support all Unicode characters, including
4520 * supplementary characters, use the {@link #of(int)} method.
4521 *
4522 * @param c The character in question
4523 * @return The {@code UnicodeBlock} instance representing the
4524 * Unicode block of which this character is a member, or
4525 * {@code null} if the character is not a member of any
4526 * Unicode block
4527 */
4528 public static UnicodeBlock of(char c) {
4529 return of((int)c);
4530 }
4531
4532 /**
4533 * Returns the object representing the Unicode block
4534 * containing the given character (Unicode code point), or
4535 * {@code null} if the character is not a member of a
4536 * defined block.
4537 *
4538 * @param codePoint the character (Unicode code point) in question.
4539 * @return The {@code UnicodeBlock} instance representing the
4540 * Unicode block of which this character is a member, or
4541 * {@code null} if the character is not a member of any
4542 * Unicode block
4543 * @throws IllegalArgumentException if the specified
4544 * {@code codePoint} is an invalid Unicode code point.
4545 * @see Character#isValidCodePoint(int)
4546 * @since 1.5
4547 */
4548 public static UnicodeBlock of(int codePoint) {
4549 if (!isValidCodePoint(codePoint)) {
4550 throw new IllegalArgumentException(
4551 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4552 }
4553
4554 int top, bottom, current;
4555 bottom = 0;
4556 top = blockStarts.length;
4557 current = top/2;
4558
4559 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4560 while (top - bottom > 1) {
4561 if (codePoint >= blockStarts[current]) {
4562 bottom = current;
4563 } else {
4564 top = current;
4565 }
4566 current = (top + bottom) / 2;
4567 }
4568 return blocks[current];
4569 }
4570
4571 /**
4572 * Returns the UnicodeBlock with the given name. Block
4573 * names are determined by The Unicode Standard. The file
4574 * {@code Blocks.txt} defines blocks for a particular
4575 * version of the standard. The {@link Character} class specifies
4576 * the version of the standard that it supports.
4577 * <p>
4578 * This method accepts block names in the following forms:
4579 * <ol>
4580 * <li> Canonical block names as defined by the Unicode Standard.
4581 * For example, the standard defines a "Basic Latin" block. Therefore, this
4582 * method accepts "Basic Latin" as a valid block name. The documentation of
4583 * each UnicodeBlock provides the canonical name.
4584 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4585 * is a valid block name for the "Basic Latin" block.
4586 * <li>The text representation of each constant UnicodeBlock identifier.
4587 * For example, this method will return the {@link #BASIC_LATIN} block if
4588 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4589 * hyphens in the canonical name with underscores.
4590 * </ol>
4591 * Finally, character case is ignored for all of the valid block name forms.
4592 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4593 * The en_US locale's case mapping rules are used to provide case-insensitive
4594 * string comparisons for block name validation.
4595 * <p>
4596 * If the Unicode Standard changes block names, both the previous and
4597 * current names will be accepted.
4598 *
4599 * @param blockName A {@code UnicodeBlock} name.
4600 * @return The {@code UnicodeBlock} instance identified
4601 * by {@code blockName}
4602 * @throws IllegalArgumentException if {@code blockName} is an
4603 * invalid name
4604 * @throws NullPointerException if {@code blockName} is null
4605 * @since 1.5
4606 */
4607 public static final UnicodeBlock forName(String blockName) {
4608 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4609 if (block == null) {
4610 throw new IllegalArgumentException("Not a valid block name: "
4611 + blockName);
4612 }
4613 return block;
4614 }
4615 }
4616
4617
4618 /**
4619 * A family of character subsets representing the character scripts
4620 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4621 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4622 * character is assigned to a single Unicode script, either a specific
4623 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4624 * one of the following three special values,
4625 * {@link Character.UnicodeScript#INHERITED Inherited},
4626 * {@link Character.UnicodeScript#COMMON Common} or
4627 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4628 *
4629 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4630 * @since 1.7
4631 */
4632 public static enum UnicodeScript {
4633
4634 /**
4635 * Unicode script "Common".
4636 */
4637 COMMON,
4638
4639 /**
4640 * Unicode script "Latin".
4641 */
4642 LATIN,
4643
4644 /**
4645 * Unicode script "Greek".
4646 */
4647 GREEK,
4648
4649 /**
4650 * Unicode script "Cyrillic".
4651 */
4652 CYRILLIC,
4653
4654 /**
4655 * Unicode script "Armenian".
4656 */
4657 ARMENIAN,
4658
4659 /**
4660 * Unicode script "Hebrew".
4661 */
4662 HEBREW,
4663
4664 /**
4665 * Unicode script "Arabic".
4666 */
4667 ARABIC,
4668
4669 /**
4670 * Unicode script "Syriac".
4671 */
4672 SYRIAC,
4673
4674 /**
4675 * Unicode script "Thaana".
4676 */
4677 THAANA,
4678
4679 /**
4680 * Unicode script "Devanagari".
4681 */
4682 DEVANAGARI,
4683
4684 /**
4685 * Unicode script "Bengali".
4686 */
4687 BENGALI,
4688
4689 /**
4690 * Unicode script "Gurmukhi".
4691 */
4692 GURMUKHI,
4693
4694 /**
4695 * Unicode script "Gujarati".
4696 */
4697 GUJARATI,
4698
4699 /**
4700 * Unicode script "Oriya".
4701 */
4702 ORIYA,
4703
4704 /**
4705 * Unicode script "Tamil".
4706 */
4707 TAMIL,
4708
4709 /**
4710 * Unicode script "Telugu".
4711 */
4712 TELUGU,
4713
4714 /**
4715 * Unicode script "Kannada".
4716 */
4717 KANNADA,
4718
4719 /**
4720 * Unicode script "Malayalam".
4721 */
4722 MALAYALAM,
4723
4724 /**
4725 * Unicode script "Sinhala".
4726 */
4727 SINHALA,
4728
4729 /**
4730 * Unicode script "Thai".
4731 */
4732 THAI,
4733
4734 /**
4735 * Unicode script "Lao".
4736 */
4737 LAO,
4738
4739 /**
4740 * Unicode script "Tibetan".
4741 */
4742 TIBETAN,
4743
4744 /**
4745 * Unicode script "Myanmar".
4746 */
4747 MYANMAR,
4748
4749 /**
4750 * Unicode script "Georgian".
4751 */
4752 GEORGIAN,
4753
4754 /**
4755 * Unicode script "Hangul".
4756 */
4757 HANGUL,
4758
4759 /**
4760 * Unicode script "Ethiopic".
4761 */
4762 ETHIOPIC,
4763
4764 /**
4765 * Unicode script "Cherokee".
4766 */
4767 CHEROKEE,
4768
4769 /**
4770 * Unicode script "Canadian_Aboriginal".
4771 */
4772 CANADIAN_ABORIGINAL,
4773
4774 /**
4775 * Unicode script "Ogham".
4776 */
4777 OGHAM,
4778
4779 /**
4780 * Unicode script "Runic".
4781 */
4782 RUNIC,
4783
4784 /**
4785 * Unicode script "Khmer".
4786 */
4787 KHMER,
4788
4789 /**
4790 * Unicode script "Mongolian".
4791 */
4792 MONGOLIAN,
4793
4794 /**
4795 * Unicode script "Hiragana".
4796 */
4797 HIRAGANA,
4798
4799 /**
4800 * Unicode script "Katakana".
4801 */
4802 KATAKANA,
4803
4804 /**
4805 * Unicode script "Bopomofo".
4806 */
4807 BOPOMOFO,
4808
4809 /**
4810 * Unicode script "Han".
4811 */
4812 HAN,
4813
4814 /**
4815 * Unicode script "Yi".
4816 */
4817 YI,
4818
4819 /**
4820 * Unicode script "Old_Italic".
4821 */
4822 OLD_ITALIC,
4823
4824 /**
4825 * Unicode script "Gothic".
4826 */
4827 GOTHIC,
4828
4829 /**
4830 * Unicode script "Deseret".
4831 */
4832 DESERET,
4833
4834 /**
4835 * Unicode script "Inherited".
4836 */
4837 INHERITED,
4838
4839 /**
4840 * Unicode script "Tagalog".
4841 */
4842 TAGALOG,
4843
4844 /**
4845 * Unicode script "Hanunoo".
4846 */
4847 HANUNOO,
4848
4849 /**
4850 * Unicode script "Buhid".
4851 */
4852 BUHID,
4853
4854 /**
4855 * Unicode script "Tagbanwa".
4856 */
4857 TAGBANWA,
4858
4859 /**
4860 * Unicode script "Limbu".
4861 */
4862 LIMBU,
4863
4864 /**
4865 * Unicode script "Tai_Le".
4866 */
4867 TAI_LE,
4868
4869 /**
4870 * Unicode script "Linear_B".
4871 */
4872 LINEAR_B,
4873
4874 /**
4875 * Unicode script "Ugaritic".
4876 */
4877 UGARITIC,
4878
4879 /**
4880 * Unicode script "Shavian".
4881 */
4882 SHAVIAN,
4883
4884 /**
4885 * Unicode script "Osmanya".
4886 */
4887 OSMANYA,
4888
4889 /**
4890 * Unicode script "Cypriot".
4891 */
4892 CYPRIOT,
4893
4894 /**
4895 * Unicode script "Braille".
4896 */
4897 BRAILLE,
4898
4899 /**
4900 * Unicode script "Buginese".
4901 */
4902 BUGINESE,
4903
4904 /**
4905 * Unicode script "Coptic".
4906 */
4907 COPTIC,
4908
4909 /**
4910 * Unicode script "New_Tai_Lue".
4911 */
4912 NEW_TAI_LUE,
4913
4914 /**
4915 * Unicode script "Glagolitic".
4916 */
4917 GLAGOLITIC,
4918
4919 /**
4920 * Unicode script "Tifinagh".
4921 */
4922 TIFINAGH,
4923
4924 /**
4925 * Unicode script "Syloti_Nagri".
4926 */
4927 SYLOTI_NAGRI,
4928
4929 /**
4930 * Unicode script "Old_Persian".
4931 */
4932 OLD_PERSIAN,
4933
4934 /**
4935 * Unicode script "Kharoshthi".
4936 */
4937 KHAROSHTHI,
4938
4939 /**
4940 * Unicode script "Balinese".
4941 */
4942 BALINESE,
4943
4944 /**
4945 * Unicode script "Cuneiform".
4946 */
4947 CUNEIFORM,
4948
4949 /**
4950 * Unicode script "Phoenician".
4951 */
4952 PHOENICIAN,
4953
4954 /**
4955 * Unicode script "Phags_Pa".
4956 */
4957 PHAGS_PA,
4958
4959 /**
4960 * Unicode script "Nko".
4961 */
4962 NKO,
4963
4964 /**
4965 * Unicode script "Sundanese".
4966 */
4967 SUNDANESE,
4968
4969 /**
4970 * Unicode script "Batak".
4971 */
4972 BATAK,
4973
4974 /**
4975 * Unicode script "Lepcha".
4976 */
4977 LEPCHA,
4978
4979 /**
4980 * Unicode script "Ol_Chiki".
4981 */
4982 OL_CHIKI,
4983
4984 /**
4985 * Unicode script "Vai".
4986 */
4987 VAI,
4988
4989 /**
4990 * Unicode script "Saurashtra".
4991 */
4992 SAURASHTRA,
4993
4994 /**
4995 * Unicode script "Kayah_Li".
4996 */
4997 KAYAH_LI,
4998
4999 /**
5000 * Unicode script "Rejang".
5001 */
5002 REJANG,
5003
5004 /**
5005 * Unicode script "Lycian".
5006 */
5007 LYCIAN,
5008
5009 /**
5010 * Unicode script "Carian".
5011 */
5012 CARIAN,
5013
5014 /**
5015 * Unicode script "Lydian".
5016 */
5017 LYDIAN,
5018
5019 /**
5020 * Unicode script "Cham".
5021 */
5022 CHAM,
5023
5024 /**
5025 * Unicode script "Tai_Tham".
5026 */
5027 TAI_THAM,
5028
5029 /**
5030 * Unicode script "Tai_Viet".
5031 */
5032 TAI_VIET,
5033
5034 /**
5035 * Unicode script "Avestan".
5036 */
5037 AVESTAN,
5038
5039 /**
5040 * Unicode script "Egyptian_Hieroglyphs".
5041 */
5042 EGYPTIAN_HIEROGLYPHS,
5043
5044 /**
5045 * Unicode script "Samaritan".
5046 */
5047 SAMARITAN,
5048
5049 /**
5050 * Unicode script "Mandaic".
5051 */
5052 MANDAIC,
5053
5054 /**
5055 * Unicode script "Lisu".
5056 */
5057 LISU,
5058
5059 /**
5060 * Unicode script "Bamum".
5061 */
5062 BAMUM,
5063
5064 /**
5065 * Unicode script "Javanese".
5066 */
5067 JAVANESE,
5068
5069 /**
5070 * Unicode script "Meetei_Mayek".
5071 */
5072 MEETEI_MAYEK,
5073
5074 /**
5075 * Unicode script "Imperial_Aramaic".
5076 */
5077 IMPERIAL_ARAMAIC,
5078
5079 /**
5080 * Unicode script "Old_South_Arabian".
5081 */
5082 OLD_SOUTH_ARABIAN,
5083
5084 /**
5085 * Unicode script "Inscriptional_Parthian".
5086 */
5087 INSCRIPTIONAL_PARTHIAN,
5088
5089 /**
5090 * Unicode script "Inscriptional_Pahlavi".
5091 */
5092 INSCRIPTIONAL_PAHLAVI,
5093
5094 /**
5095 * Unicode script "Old_Turkic".
5096 */
5097 OLD_TURKIC,
5098
5099 /**
5100 * Unicode script "Brahmi".
5101 */
5102 BRAHMI,
5103
5104 /**
5105 * Unicode script "Kaithi".
5106 */
5107 KAITHI,
5108
5109 /**
5110 * Unicode script "Meroitic Hieroglyphs".
5111 * @since 1.8
5112 */
5113 MEROITIC_HIEROGLYPHS,
5114
5115 /**
5116 * Unicode script "Meroitic Cursive".
5117 * @since 1.8
5118 */
5119 MEROITIC_CURSIVE,
5120
5121 /**
5122 * Unicode script "Sora Sompeng".
5123 * @since 1.8
5124 */
5125 SORA_SOMPENG,
5126
5127 /**
5128 * Unicode script "Chakma".
5129 * @since 1.8
5130 */
5131 CHAKMA,
5132
5133 /**
5134 * Unicode script "Sharada".
5135 * @since 1.8
5136 */
5137 SHARADA,
5138
5139 /**
5140 * Unicode script "Takri".
5141 * @since 1.8
5142 */
5143 TAKRI,
5144
5145 /**
5146 * Unicode script "Miao".
5147 * @since 1.8
5148 */
5149 MIAO,
5150
5151 /**
5152 * Unicode script "Caucasian Albanian".
5153 * @since 9
5154 */
5155 CAUCASIAN_ALBANIAN,
5156
5157 /**
5158 * Unicode script "Bassa Vah".
5159 * @since 9
5160 */
5161 BASSA_VAH,
5162
5163 /**
5164 * Unicode script "Duployan".
5165 * @since 9
5166 */
5167 DUPLOYAN,
5168
5169 /**
5170 * Unicode script "Elbasan".
5171 * @since 9
5172 */
5173 ELBASAN,
5174
5175 /**
5176 * Unicode script "Grantha".
5177 * @since 9
5178 */
5179 GRANTHA,
5180
5181 /**
5182 * Unicode script "Pahawh Hmong".
5183 * @since 9
5184 */
5185 PAHAWH_HMONG,
5186
5187 /**
5188 * Unicode script "Khojki".
5189 * @since 9
5190 */
5191 KHOJKI,
5192
5193 /**
5194 * Unicode script "Linear A".
5195 * @since 9
5196 */
5197 LINEAR_A,
5198
5199 /**
5200 * Unicode script "Mahajani".
5201 * @since 9
5202 */
5203 MAHAJANI,
5204
5205 /**
5206 * Unicode script "Manichaean".
5207 * @since 9
5208 */
5209 MANICHAEAN,
5210
5211 /**
5212 * Unicode script "Mende Kikakui".
5213 * @since 9
5214 */
5215 MENDE_KIKAKUI,
5216
5217 /**
5218 * Unicode script "Modi".
5219 * @since 9
5220 */
5221 MODI,
5222
5223 /**
5224 * Unicode script "Mro".
5225 * @since 9
5226 */
5227 MRO,
5228
5229 /**
5230 * Unicode script "Old North Arabian".
5231 * @since 9
5232 */
5233 OLD_NORTH_ARABIAN,
5234
5235 /**
5236 * Unicode script "Nabataean".
5237 * @since 9
5238 */
5239 NABATAEAN,
5240
5241 /**
5242 * Unicode script "Palmyrene".
5243 * @since 9
5244 */
5245 PALMYRENE,
5246
5247 /**
5248 * Unicode script "Pau Cin Hau".
5249 * @since 9
5250 */
5251 PAU_CIN_HAU,
5252
5253 /**
5254 * Unicode script "Old Permic".
5255 * @since 9
5256 */
5257 OLD_PERMIC,
5258
5259 /**
5260 * Unicode script "Psalter Pahlavi".
5261 * @since 9
5262 */
5263 PSALTER_PAHLAVI,
5264
5265 /**
5266 * Unicode script "Siddham".
5267 * @since 9
5268 */
5269 SIDDHAM,
5270
5271 /**
5272 * Unicode script "Khudawadi".
5273 * @since 9
5274 */
5275 KHUDAWADI,
5276
5277 /**
5278 * Unicode script "Tirhuta".
5279 * @since 9
5280 */
5281 TIRHUTA,
5282
5283 /**
5284 * Unicode script "Warang Citi".
5285 * @since 9
5286 */
5287 WARANG_CITI,
5288
5289 /**
5290 * Unicode script "Ahom".
5291 * @since 9
5292 */
5293 AHOM,
5294
5295 /**
5296 * Unicode script "Anatolian Hieroglyphs".
5297 * @since 9
5298 */
5299 ANATOLIAN_HIEROGLYPHS,
5300
5301 /**
5302 * Unicode script "Hatran".
5303 * @since 9
5304 */
5305 HATRAN,
5306
5307 /**
5308 * Unicode script "Multani".
5309 * @since 9
5310 */
5311 MULTANI,
5312
5313 /**
5314 * Unicode script "Old Hungarian".
5315 * @since 9
5316 */
5317 OLD_HUNGARIAN,
5318
5319 /**
5320 * Unicode script "SignWriting".
5321 * @since 9
5322 */
5323 SIGNWRITING,
5324
5325 /**
5326 * Unicode script "Adlam".
5327 * @since 11
5328 */
5329 ADLAM,
5330
5331 /**
5332 * Unicode script "Bhaiksuki".
5333 * @since 11
5334 */
5335 BHAIKSUKI,
5336
5337 /**
5338 * Unicode script "Marchen".
5339 * @since 11
5340 */
5341 MARCHEN,
5342
5343 /**
5344 * Unicode script "Newa".
5345 * @since 11
5346 */
5347 NEWA,
5348
5349 /**
5350 * Unicode script "Osage".
5351 * @since 11
5352 */
5353 OSAGE,
5354
5355 /**
5356 * Unicode script "Tangut".
5357 * @since 11
5358 */
5359 TANGUT,
5360
5361 /**
5362 * Unicode script "Masaram Gondi".
5363 * @since 11
5364 */
5365 MASARAM_GONDI,
5366
5367 /**
5368 * Unicode script "Nushu".
5369 * @since 11
5370 */
5371 NUSHU,
5372
5373 /**
5374 * Unicode script "Soyombo".
5375 * @since 11
5376 */
5377 SOYOMBO,
5378
5379 /**
5380 * Unicode script "Zanabazar Square".
5381 * @since 11
5382 */
5383 ZANABAZAR_SQUARE,
5384
5385 /**
5386 * Unicode script "Hanifi Rohingya".
5387 * @since 12
5388 */
5389 HANIFI_ROHINGYA,
5390
5391 /**
5392 * Unicode script "Old Sogdian".
5393 * @since 12
5394 */
5395 OLD_SOGDIAN,
5396
5397 /**
5398 * Unicode script "Sogdian".
5399 * @since 12
5400 */
5401 SOGDIAN,
5402
5403 /**
5404 * Unicode script "Dogra".
5405 * @since 12
5406 */
5407 DOGRA,
5408
5409 /**
5410 * Unicode script "Gunjala Gondi".
5411 * @since 12
5412 */
5413 GUNJALA_GONDI,
5414
5415 /**
5416 * Unicode script "Makasar".
5417 * @since 12
5418 */
5419 MAKASAR,
5420
5421 /**
5422 * Unicode script "Medefaidrin".
5423 * @since 12
5424 */
5425 MEDEFAIDRIN,
5426
5427 /**
5428 * Unicode script "Elymaic".
5429 * @since 13
5430 */
5431 ELYMAIC,
5432
5433 /**
5434 * Unicode script "Nandinagari".
5435 * @since 13
5436 */
5437 NANDINAGARI,
5438
5439 /**
5440 * Unicode script "Nyiakeng Puachue Hmong".
5441 * @since 13
5442 */
5443 NYIAKENG_PUACHUE_HMONG,
5444
5445 /**
5446 * Unicode script "Wancho".
5447 * @since 13
5448 */
5449 WANCHO,
5450
5451 /**
5452 * Unicode script "Yezidi".
5453 * @since 15
5454 */
5455 YEZIDI,
5456
5457 /**
5458 * Unicode script "Chorasmian".
5459 * @since 15
5460 */
5461 CHORASMIAN,
5462
5463 /**
5464 * Unicode script "Dives Akuru".
5465 * @since 15
5466 */
5467 DIVES_AKURU,
5468
5469 /**
5470 * Unicode script "Khitan Small Script".
5471 * @since 15
5472 */
5473 KHITAN_SMALL_SCRIPT,
5474
5475 /**
5476 * Unicode script "Vithkuqi".
5477 * @since 19
5478 */
5479 VITHKUQI,
5480
5481 /**
5482 * Unicode script "Old Uyghur".
5483 * @since 19
5484 */
5485 OLD_UYGHUR,
5486
5487 /**
5488 * Unicode script "Cypro Minoan".
5489 * @since 19
5490 */
5491 CYPRO_MINOAN,
5492
5493 /**
5494 * Unicode script "Tangsa".
5495 * @since 19
5496 */
5497 TANGSA,
5498
5499 /**
5500 * Unicode script "Toto".
5501 * @since 19
5502 */
5503 TOTO,
5504
5505 /**
5506 * Unicode script "Kawi".
5507 * @since 20
5508 */
5509 KAWI,
5510
5511 /**
5512 * Unicode script "Nag Mundari".
5513 * @since 20
5514 */
5515 NAG_MUNDARI,
5516
5517 /**
5518 * Unicode script "Todhri".
5519 * @since 24
5520 */
5521 TODHRI,
5522
5523 /**
5524 * Unicode script "Garay".
5525 * @since 24
5526 */
5527 GARAY,
5528
5529 /**
5530 * Unicode script "Tulu Tigalari".
5531 * @since 24
5532 */
5533 TULU_TIGALARI,
5534
5535 /**
5536 * Unicode script "Sunuwar".
5537 * @since 24
5538 */
5539 SUNUWAR,
5540
5541 /**
5542 * Unicode script "Gurung Khema".
5543 * @since 24
5544 */
5545 GURUNG_KHEMA,
5546
5547 /**
5548 * Unicode script "Kirat Rai".
5549 * @since 24
5550 */
5551 KIRAT_RAI,
5552
5553 /**
5554 * Unicode script "Ol Onal".
5555 * @since 24
5556 */
5557 OL_ONAL,
5558
5559 /**
5560 * Unicode script "Unknown".
5561 */
5562 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5563
5564 private static final int[] scriptStarts = {
5565 0x0000, // 0000..0040; COMMON
5566 0x0041, // 0041..005A; LATIN
5567 0x005B, // 005B..0060; COMMON
5568 0x0061, // 0061..007A; LATIN
5569 0x007B, // 007B..00A9; COMMON
5570 0x00AA, // 00AA ; LATIN
5571 0x00AB, // 00AB..00B9; COMMON
5572 0x00BA, // 00BA ; LATIN
5573 0x00BB, // 00BB..00BF; COMMON
5574 0x00C0, // 00C0..00D6; LATIN
5575 0x00D7, // 00D7 ; COMMON
5576 0x00D8, // 00D8..00F6; LATIN
5577 0x00F7, // 00F7 ; COMMON
5578 0x00F8, // 00F8..02B8; LATIN
5579 0x02B9, // 02B9..02DF; COMMON
5580 0x02E0, // 02E0..02E4; LATIN
5581 0x02E5, // 02E5..02E9; COMMON
5582 0x02EA, // 02EA..02EB; BOPOMOFO
5583 0x02EC, // 02EC..02FF; COMMON
5584 0x0300, // 0300..036F; INHERITED
5585 0x0370, // 0370..0373; GREEK
5586 0x0374, // 0374 ; COMMON
5587 0x0375, // 0375..0377; GREEK
5588 0x0378, // 0378..0379; UNKNOWN
5589 0x037A, // 037A..037D; GREEK
5590 0x037E, // 037E ; COMMON
5591 0x037F, // 037F ; GREEK
5592 0x0380, // 0380..0383; UNKNOWN
5593 0x0384, // 0384 ; GREEK
5594 0x0385, // 0385 ; COMMON
5595 0x0386, // 0386 ; GREEK
5596 0x0387, // 0387 ; COMMON
5597 0x0388, // 0388..038A; GREEK
5598 0x038B, // 038B ; UNKNOWN
5599 0x038C, // 038C ; GREEK
5600 0x038D, // 038D ; UNKNOWN
5601 0x038E, // 038E..03A1; GREEK
5602 0x03A2, // 03A2 ; UNKNOWN
5603 0x03A3, // 03A3..03E1; GREEK
5604 0x03E2, // 03E2..03EF; COPTIC
5605 0x03F0, // 03F0..03FF; GREEK
5606 0x0400, // 0400..0484; CYRILLIC
5607 0x0485, // 0485..0486; INHERITED
5608 0x0487, // 0487..052F; CYRILLIC
5609 0x0530, // 0530 ; UNKNOWN
5610 0x0531, // 0531..0556; ARMENIAN
5611 0x0557, // 0557..0558; UNKNOWN
5612 0x0559, // 0559..058A; ARMENIAN
5613 0x058B, // 058B..058C; UNKNOWN
5614 0x058D, // 058D..058F; ARMENIAN
5615 0x0590, // 0590 ; UNKNOWN
5616 0x0591, // 0591..05C7; HEBREW
5617 0x05C8, // 05C8..05CF; UNKNOWN
5618 0x05D0, // 05D0..05EA; HEBREW
5619 0x05EB, // 05EB..05EE; UNKNOWN
5620 0x05EF, // 05EF..05F4; HEBREW
5621 0x05F5, // 05F5..05FF; UNKNOWN
5622 0x0600, // 0600..0604; ARABIC
5623 0x0605, // 0605 ; COMMON
5624 0x0606, // 0606..060B; ARABIC
5625 0x060C, // 060C ; COMMON
5626 0x060D, // 060D..061A; ARABIC
5627 0x061B, // 061B ; COMMON
5628 0x061C, // 061C..061E; ARABIC
5629 0x061F, // 061F ; COMMON
5630 0x0620, // 0620..063F; ARABIC
5631 0x0640, // 0640 ; COMMON
5632 0x0641, // 0641..064A; ARABIC
5633 0x064B, // 064B..0655; INHERITED
5634 0x0656, // 0656..066F; ARABIC
5635 0x0670, // 0670 ; INHERITED
5636 0x0671, // 0671..06DC; ARABIC
5637 0x06DD, // 06DD ; COMMON
5638 0x06DE, // 06DE..06FF; ARABIC
5639 0x0700, // 0700..070D; SYRIAC
5640 0x070E, // 070E ; UNKNOWN
5641 0x070F, // 070F..074A; SYRIAC
5642 0x074B, // 074B..074C; UNKNOWN
5643 0x074D, // 074D..074F; SYRIAC
5644 0x0750, // 0750..077F; ARABIC
5645 0x0780, // 0780..07B1; THAANA
5646 0x07B2, // 07B2..07BF; UNKNOWN
5647 0x07C0, // 07C0..07FA; NKO
5648 0x07FB, // 07FB..07FC; UNKNOWN
5649 0x07FD, // 07FD..07FF; NKO
5650 0x0800, // 0800..082D; SAMARITAN
5651 0x082E, // 082E..082F; UNKNOWN
5652 0x0830, // 0830..083E; SAMARITAN
5653 0x083F, // 083F ; UNKNOWN
5654 0x0840, // 0840..085B; MANDAIC
5655 0x085C, // 085C..085D; UNKNOWN
5656 0x085E, // 085E ; MANDAIC
5657 0x085F, // 085F ; UNKNOWN
5658 0x0860, // 0860..086A; SYRIAC
5659 0x086B, // 086B..086F; UNKNOWN
5660 0x0870, // 0870..088E; ARABIC
5661 0x088F, // 088F ; UNKNOWN
5662 0x0890, // 0890..0891; ARABIC
5663 0x0892, // 0892..0896; UNKNOWN
5664 0x0897, // 0897..08E1; ARABIC
5665 0x08E2, // 08E2 ; COMMON
5666 0x08E3, // 08E3..08FF; ARABIC
5667 0x0900, // 0900..0950; DEVANAGARI
5668 0x0951, // 0951..0954; INHERITED
5669 0x0955, // 0955..0963; DEVANAGARI
5670 0x0964, // 0964..0965; COMMON
5671 0x0966, // 0966..097F; DEVANAGARI
5672 0x0980, // 0980..0983; BENGALI
5673 0x0984, // 0984 ; UNKNOWN
5674 0x0985, // 0985..098C; BENGALI
5675 0x098D, // 098D..098E; UNKNOWN
5676 0x098F, // 098F..0990; BENGALI
5677 0x0991, // 0991..0992; UNKNOWN
5678 0x0993, // 0993..09A8; BENGALI
5679 0x09A9, // 09A9 ; UNKNOWN
5680 0x09AA, // 09AA..09B0; BENGALI
5681 0x09B1, // 09B1 ; UNKNOWN
5682 0x09B2, // 09B2 ; BENGALI
5683 0x09B3, // 09B3..09B5; UNKNOWN
5684 0x09B6, // 09B6..09B9; BENGALI
5685 0x09BA, // 09BA..09BB; UNKNOWN
5686 0x09BC, // 09BC..09C4; BENGALI
5687 0x09C5, // 09C5..09C6; UNKNOWN
5688 0x09C7, // 09C7..09C8; BENGALI
5689 0x09C9, // 09C9..09CA; UNKNOWN
5690 0x09CB, // 09CB..09CE; BENGALI
5691 0x09CF, // 09CF..09D6; UNKNOWN
5692 0x09D7, // 09D7 ; BENGALI
5693 0x09D8, // 09D8..09DB; UNKNOWN
5694 0x09DC, // 09DC..09DD; BENGALI
5695 0x09DE, // 09DE ; UNKNOWN
5696 0x09DF, // 09DF..09E3; BENGALI
5697 0x09E4, // 09E4..09E5; UNKNOWN
5698 0x09E6, // 09E6..09FE; BENGALI
5699 0x09FF, // 09FF..0A00; UNKNOWN
5700 0x0A01, // 0A01..0A03; GURMUKHI
5701 0x0A04, // 0A04 ; UNKNOWN
5702 0x0A05, // 0A05..0A0A; GURMUKHI
5703 0x0A0B, // 0A0B..0A0E; UNKNOWN
5704 0x0A0F, // 0A0F..0A10; GURMUKHI
5705 0x0A11, // 0A11..0A12; UNKNOWN
5706 0x0A13, // 0A13..0A28; GURMUKHI
5707 0x0A29, // 0A29 ; UNKNOWN
5708 0x0A2A, // 0A2A..0A30; GURMUKHI
5709 0x0A31, // 0A31 ; UNKNOWN
5710 0x0A32, // 0A32..0A33; GURMUKHI
5711 0x0A34, // 0A34 ; UNKNOWN
5712 0x0A35, // 0A35..0A36; GURMUKHI
5713 0x0A37, // 0A37 ; UNKNOWN
5714 0x0A38, // 0A38..0A39; GURMUKHI
5715 0x0A3A, // 0A3A..0A3B; UNKNOWN
5716 0x0A3C, // 0A3C ; GURMUKHI
5717 0x0A3D, // 0A3D ; UNKNOWN
5718 0x0A3E, // 0A3E..0A42; GURMUKHI
5719 0x0A43, // 0A43..0A46; UNKNOWN
5720 0x0A47, // 0A47..0A48; GURMUKHI
5721 0x0A49, // 0A49..0A4A; UNKNOWN
5722 0x0A4B, // 0A4B..0A4D; GURMUKHI
5723 0x0A4E, // 0A4E..0A50; UNKNOWN
5724 0x0A51, // 0A51 ; GURMUKHI
5725 0x0A52, // 0A52..0A58; UNKNOWN
5726 0x0A59, // 0A59..0A5C; GURMUKHI
5727 0x0A5D, // 0A5D ; UNKNOWN
5728 0x0A5E, // 0A5E ; GURMUKHI
5729 0x0A5F, // 0A5F..0A65; UNKNOWN
5730 0x0A66, // 0A66..0A76; GURMUKHI
5731 0x0A77, // 0A77..0A80; UNKNOWN
5732 0x0A81, // 0A81..0A83; GUJARATI
5733 0x0A84, // 0A84 ; UNKNOWN
5734 0x0A85, // 0A85..0A8D; GUJARATI
5735 0x0A8E, // 0A8E ; UNKNOWN
5736 0x0A8F, // 0A8F..0A91; GUJARATI
5737 0x0A92, // 0A92 ; UNKNOWN
5738 0x0A93, // 0A93..0AA8; GUJARATI
5739 0x0AA9, // 0AA9 ; UNKNOWN
5740 0x0AAA, // 0AAA..0AB0; GUJARATI
5741 0x0AB1, // 0AB1 ; UNKNOWN
5742 0x0AB2, // 0AB2..0AB3; GUJARATI
5743 0x0AB4, // 0AB4 ; UNKNOWN
5744 0x0AB5, // 0AB5..0AB9; GUJARATI
5745 0x0ABA, // 0ABA..0ABB; UNKNOWN
5746 0x0ABC, // 0ABC..0AC5; GUJARATI
5747 0x0AC6, // 0AC6 ; UNKNOWN
5748 0x0AC7, // 0AC7..0AC9; GUJARATI
5749 0x0ACA, // 0ACA ; UNKNOWN
5750 0x0ACB, // 0ACB..0ACD; GUJARATI
5751 0x0ACE, // 0ACE..0ACF; UNKNOWN
5752 0x0AD0, // 0AD0 ; GUJARATI
5753 0x0AD1, // 0AD1..0ADF; UNKNOWN
5754 0x0AE0, // 0AE0..0AE3; GUJARATI
5755 0x0AE4, // 0AE4..0AE5; UNKNOWN
5756 0x0AE6, // 0AE6..0AF1; GUJARATI
5757 0x0AF2, // 0AF2..0AF8; UNKNOWN
5758 0x0AF9, // 0AF9..0AFF; GUJARATI
5759 0x0B00, // 0B00 ; UNKNOWN
5760 0x0B01, // 0B01..0B03; ORIYA
5761 0x0B04, // 0B04 ; UNKNOWN
5762 0x0B05, // 0B05..0B0C; ORIYA
5763 0x0B0D, // 0B0D..0B0E; UNKNOWN
5764 0x0B0F, // 0B0F..0B10; ORIYA
5765 0x0B11, // 0B11..0B12; UNKNOWN
5766 0x0B13, // 0B13..0B28; ORIYA
5767 0x0B29, // 0B29 ; UNKNOWN
5768 0x0B2A, // 0B2A..0B30; ORIYA
5769 0x0B31, // 0B31 ; UNKNOWN
5770 0x0B32, // 0B32..0B33; ORIYA
5771 0x0B34, // 0B34 ; UNKNOWN
5772 0x0B35, // 0B35..0B39; ORIYA
5773 0x0B3A, // 0B3A..0B3B; UNKNOWN
5774 0x0B3C, // 0B3C..0B44; ORIYA
5775 0x0B45, // 0B45..0B46; UNKNOWN
5776 0x0B47, // 0B47..0B48; ORIYA
5777 0x0B49, // 0B49..0B4A; UNKNOWN
5778 0x0B4B, // 0B4B..0B4D; ORIYA
5779 0x0B4E, // 0B4E..0B54; UNKNOWN
5780 0x0B55, // 0B55..0B57; ORIYA
5781 0x0B58, // 0B58..0B5B; UNKNOWN
5782 0x0B5C, // 0B5C..0B5D; ORIYA
5783 0x0B5E, // 0B5E ; UNKNOWN
5784 0x0B5F, // 0B5F..0B63; ORIYA
5785 0x0B64, // 0B64..0B65; UNKNOWN
5786 0x0B66, // 0B66..0B77; ORIYA
5787 0x0B78, // 0B78..0B81; UNKNOWN
5788 0x0B82, // 0B82..0B83; TAMIL
5789 0x0B84, // 0B84 ; UNKNOWN
5790 0x0B85, // 0B85..0B8A; TAMIL
5791 0x0B8B, // 0B8B..0B8D; UNKNOWN
5792 0x0B8E, // 0B8E..0B90; TAMIL
5793 0x0B91, // 0B91 ; UNKNOWN
5794 0x0B92, // 0B92..0B95; TAMIL
5795 0x0B96, // 0B96..0B98; UNKNOWN
5796 0x0B99, // 0B99..0B9A; TAMIL
5797 0x0B9B, // 0B9B ; UNKNOWN
5798 0x0B9C, // 0B9C ; TAMIL
5799 0x0B9D, // 0B9D ; UNKNOWN
5800 0x0B9E, // 0B9E..0B9F; TAMIL
5801 0x0BA0, // 0BA0..0BA2; UNKNOWN
5802 0x0BA3, // 0BA3..0BA4; TAMIL
5803 0x0BA5, // 0BA5..0BA7; UNKNOWN
5804 0x0BA8, // 0BA8..0BAA; TAMIL
5805 0x0BAB, // 0BAB..0BAD; UNKNOWN
5806 0x0BAE, // 0BAE..0BB9; TAMIL
5807 0x0BBA, // 0BBA..0BBD; UNKNOWN
5808 0x0BBE, // 0BBE..0BC2; TAMIL
5809 0x0BC3, // 0BC3..0BC5; UNKNOWN
5810 0x0BC6, // 0BC6..0BC8; TAMIL
5811 0x0BC9, // 0BC9 ; UNKNOWN
5812 0x0BCA, // 0BCA..0BCD; TAMIL
5813 0x0BCE, // 0BCE..0BCF; UNKNOWN
5814 0x0BD0, // 0BD0 ; TAMIL
5815 0x0BD1, // 0BD1..0BD6; UNKNOWN
5816 0x0BD7, // 0BD7 ; TAMIL
5817 0x0BD8, // 0BD8..0BE5; UNKNOWN
5818 0x0BE6, // 0BE6..0BFA; TAMIL
5819 0x0BFB, // 0BFB..0BFF; UNKNOWN
5820 0x0C00, // 0C00..0C0C; TELUGU
5821 0x0C0D, // 0C0D ; UNKNOWN
5822 0x0C0E, // 0C0E..0C10; TELUGU
5823 0x0C11, // 0C11 ; UNKNOWN
5824 0x0C12, // 0C12..0C28; TELUGU
5825 0x0C29, // 0C29 ; UNKNOWN
5826 0x0C2A, // 0C2A..0C39; TELUGU
5827 0x0C3A, // 0C3A..0C3B; UNKNOWN
5828 0x0C3C, // 0C3C..0C44; TELUGU
5829 0x0C45, // 0C45 ; UNKNOWN
5830 0x0C46, // 0C46..0C48; TELUGU
5831 0x0C49, // 0C49 ; UNKNOWN
5832 0x0C4A, // 0C4A..0C4D; TELUGU
5833 0x0C4E, // 0C4E..0C54; UNKNOWN
5834 0x0C55, // 0C55..0C56; TELUGU
5835 0x0C57, // 0C57 ; UNKNOWN
5836 0x0C58, // 0C58..0C5A; TELUGU
5837 0x0C5B, // 0C5B..0C5C; UNKNOWN
5838 0x0C5D, // 0C5D ; TELUGU
5839 0x0C5E, // 0C5E..0C5F; UNKNOWN
5840 0x0C60, // 0C60..0C63; TELUGU
5841 0x0C64, // 0C64..0C65; UNKNOWN
5842 0x0C66, // 0C66..0C6F; TELUGU
5843 0x0C70, // 0C70..0C76; UNKNOWN
5844 0x0C77, // 0C77..0C7F; TELUGU
5845 0x0C80, // 0C80..0C8C; KANNADA
5846 0x0C8D, // 0C8D ; UNKNOWN
5847 0x0C8E, // 0C8E..0C90; KANNADA
5848 0x0C91, // 0C91 ; UNKNOWN
5849 0x0C92, // 0C92..0CA8; KANNADA
5850 0x0CA9, // 0CA9 ; UNKNOWN
5851 0x0CAA, // 0CAA..0CB3; KANNADA
5852 0x0CB4, // 0CB4 ; UNKNOWN
5853 0x0CB5, // 0CB5..0CB9; KANNADA
5854 0x0CBA, // 0CBA..0CBB; UNKNOWN
5855 0x0CBC, // 0CBC..0CC4; KANNADA
5856 0x0CC5, // 0CC5 ; UNKNOWN
5857 0x0CC6, // 0CC6..0CC8; KANNADA
5858 0x0CC9, // 0CC9 ; UNKNOWN
5859 0x0CCA, // 0CCA..0CCD; KANNADA
5860 0x0CCE, // 0CCE..0CD4; UNKNOWN
5861 0x0CD5, // 0CD5..0CD6; KANNADA
5862 0x0CD7, // 0CD7..0CDC; UNKNOWN
5863 0x0CDD, // 0CDD..0CDE; KANNADA
5864 0x0CDF, // 0CDF ; UNKNOWN
5865 0x0CE0, // 0CE0..0CE3; KANNADA
5866 0x0CE4, // 0CE4..0CE5; UNKNOWN
5867 0x0CE6, // 0CE6..0CEF; KANNADA
5868 0x0CF0, // 0CF0 ; UNKNOWN
5869 0x0CF1, // 0CF1..0CF3; KANNADA
5870 0x0CF4, // 0CF4..0CFF; UNKNOWN
5871 0x0D00, // 0D00..0D0C; MALAYALAM
5872 0x0D0D, // 0D0D ; UNKNOWN
5873 0x0D0E, // 0D0E..0D10; MALAYALAM
5874 0x0D11, // 0D11 ; UNKNOWN
5875 0x0D12, // 0D12..0D44; MALAYALAM
5876 0x0D45, // 0D45 ; UNKNOWN
5877 0x0D46, // 0D46..0D48; MALAYALAM
5878 0x0D49, // 0D49 ; UNKNOWN
5879 0x0D4A, // 0D4A..0D4F; MALAYALAM
5880 0x0D50, // 0D50..0D53; UNKNOWN
5881 0x0D54, // 0D54..0D63; MALAYALAM
5882 0x0D64, // 0D64..0D65; UNKNOWN
5883 0x0D66, // 0D66..0D7F; MALAYALAM
5884 0x0D80, // 0D80 ; UNKNOWN
5885 0x0D81, // 0D81..0D83; SINHALA
5886 0x0D84, // 0D84 ; UNKNOWN
5887 0x0D85, // 0D85..0D96; SINHALA
5888 0x0D97, // 0D97..0D99; UNKNOWN
5889 0x0D9A, // 0D9A..0DB1; SINHALA
5890 0x0DB2, // 0DB2 ; UNKNOWN
5891 0x0DB3, // 0DB3..0DBB; SINHALA
5892 0x0DBC, // 0DBC ; UNKNOWN
5893 0x0DBD, // 0DBD ; SINHALA
5894 0x0DBE, // 0DBE..0DBF; UNKNOWN
5895 0x0DC0, // 0DC0..0DC6; SINHALA
5896 0x0DC7, // 0DC7..0DC9; UNKNOWN
5897 0x0DCA, // 0DCA ; SINHALA
5898 0x0DCB, // 0DCB..0DCE; UNKNOWN
5899 0x0DCF, // 0DCF..0DD4; SINHALA
5900 0x0DD5, // 0DD5 ; UNKNOWN
5901 0x0DD6, // 0DD6 ; SINHALA
5902 0x0DD7, // 0DD7 ; UNKNOWN
5903 0x0DD8, // 0DD8..0DDF; SINHALA
5904 0x0DE0, // 0DE0..0DE5; UNKNOWN
5905 0x0DE6, // 0DE6..0DEF; SINHALA
5906 0x0DF0, // 0DF0..0DF1; UNKNOWN
5907 0x0DF2, // 0DF2..0DF4; SINHALA
5908 0x0DF5, // 0DF5..0E00; UNKNOWN
5909 0x0E01, // 0E01..0E3A; THAI
5910 0x0E3B, // 0E3B..0E3E; UNKNOWN
5911 0x0E3F, // 0E3F ; COMMON
5912 0x0E40, // 0E40..0E5B; THAI
5913 0x0E5C, // 0E5C..0E80; UNKNOWN
5914 0x0E81, // 0E81..0E82; LAO
5915 0x0E83, // 0E83 ; UNKNOWN
5916 0x0E84, // 0E84 ; LAO
5917 0x0E85, // 0E85 ; UNKNOWN
5918 0x0E86, // 0E86..0E8A; LAO
5919 0x0E8B, // 0E8B ; UNKNOWN
5920 0x0E8C, // 0E8C..0EA3; LAO
5921 0x0EA4, // 0EA4 ; UNKNOWN
5922 0x0EA5, // 0EA5 ; LAO
5923 0x0EA6, // 0EA6 ; UNKNOWN
5924 0x0EA7, // 0EA7..0EBD; LAO
5925 0x0EBE, // 0EBE..0EBF; UNKNOWN
5926 0x0EC0, // 0EC0..0EC4; LAO
5927 0x0EC5, // 0EC5 ; UNKNOWN
5928 0x0EC6, // 0EC6 ; LAO
5929 0x0EC7, // 0EC7 ; UNKNOWN
5930 0x0EC8, // 0EC8..0ECE; LAO
5931 0x0ECF, // 0ECF ; UNKNOWN
5932 0x0ED0, // 0ED0..0ED9; LAO
5933 0x0EDA, // 0EDA..0EDB; UNKNOWN
5934 0x0EDC, // 0EDC..0EDF; LAO
5935 0x0EE0, // 0EE0..0EFF; UNKNOWN
5936 0x0F00, // 0F00..0F47; TIBETAN
5937 0x0F48, // 0F48 ; UNKNOWN
5938 0x0F49, // 0F49..0F6C; TIBETAN
5939 0x0F6D, // 0F6D..0F70; UNKNOWN
5940 0x0F71, // 0F71..0F97; TIBETAN
5941 0x0F98, // 0F98 ; UNKNOWN
5942 0x0F99, // 0F99..0FBC; TIBETAN
5943 0x0FBD, // 0FBD ; UNKNOWN
5944 0x0FBE, // 0FBE..0FCC; TIBETAN
5945 0x0FCD, // 0FCD ; UNKNOWN
5946 0x0FCE, // 0FCE..0FD4; TIBETAN
5947 0x0FD5, // 0FD5..0FD8; COMMON
5948 0x0FD9, // 0FD9..0FDA; TIBETAN
5949 0x0FDB, // 0FDB..0FFF; UNKNOWN
5950 0x1000, // 1000..109F; MYANMAR
5951 0x10A0, // 10A0..10C5; GEORGIAN
5952 0x10C6, // 10C6 ; UNKNOWN
5953 0x10C7, // 10C7 ; GEORGIAN
5954 0x10C8, // 10C8..10CC; UNKNOWN
5955 0x10CD, // 10CD ; GEORGIAN
5956 0x10CE, // 10CE..10CF; UNKNOWN
5957 0x10D0, // 10D0..10FA; GEORGIAN
5958 0x10FB, // 10FB ; COMMON
5959 0x10FC, // 10FC..10FF; GEORGIAN
5960 0x1100, // 1100..11FF; HANGUL
5961 0x1200, // 1200..1248; ETHIOPIC
5962 0x1249, // 1249 ; UNKNOWN
5963 0x124A, // 124A..124D; ETHIOPIC
5964 0x124E, // 124E..124F; UNKNOWN
5965 0x1250, // 1250..1256; ETHIOPIC
5966 0x1257, // 1257 ; UNKNOWN
5967 0x1258, // 1258 ; ETHIOPIC
5968 0x1259, // 1259 ; UNKNOWN
5969 0x125A, // 125A..125D; ETHIOPIC
5970 0x125E, // 125E..125F; UNKNOWN
5971 0x1260, // 1260..1288; ETHIOPIC
5972 0x1289, // 1289 ; UNKNOWN
5973 0x128A, // 128A..128D; ETHIOPIC
5974 0x128E, // 128E..128F; UNKNOWN
5975 0x1290, // 1290..12B0; ETHIOPIC
5976 0x12B1, // 12B1 ; UNKNOWN
5977 0x12B2, // 12B2..12B5; ETHIOPIC
5978 0x12B6, // 12B6..12B7; UNKNOWN
5979 0x12B8, // 12B8..12BE; ETHIOPIC
5980 0x12BF, // 12BF ; UNKNOWN
5981 0x12C0, // 12C0 ; ETHIOPIC
5982 0x12C1, // 12C1 ; UNKNOWN
5983 0x12C2, // 12C2..12C5; ETHIOPIC
5984 0x12C6, // 12C6..12C7; UNKNOWN
5985 0x12C8, // 12C8..12D6; ETHIOPIC
5986 0x12D7, // 12D7 ; UNKNOWN
5987 0x12D8, // 12D8..1310; ETHIOPIC
5988 0x1311, // 1311 ; UNKNOWN
5989 0x1312, // 1312..1315; ETHIOPIC
5990 0x1316, // 1316..1317; UNKNOWN
5991 0x1318, // 1318..135A; ETHIOPIC
5992 0x135B, // 135B..135C; UNKNOWN
5993 0x135D, // 135D..137C; ETHIOPIC
5994 0x137D, // 137D..137F; UNKNOWN
5995 0x1380, // 1380..1399; ETHIOPIC
5996 0x139A, // 139A..139F; UNKNOWN
5997 0x13A0, // 13A0..13F5; CHEROKEE
5998 0x13F6, // 13F6..13F7; UNKNOWN
5999 0x13F8, // 13F8..13FD; CHEROKEE
6000 0x13FE, // 13FE..13FF; UNKNOWN
6001 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
6002 0x1680, // 1680..169C; OGHAM
6003 0x169D, // 169D..169F; UNKNOWN
6004 0x16A0, // 16A0..16EA; RUNIC
6005 0x16EB, // 16EB..16ED; COMMON
6006 0x16EE, // 16EE..16F8; RUNIC
6007 0x16F9, // 16F9..16FF; UNKNOWN
6008 0x1700, // 1700..1715; TAGALOG
6009 0x1716, // 1716..171E; UNKNOWN
6010 0x171F, // 171F ; TAGALOG
6011 0x1720, // 1720..1734; HANUNOO
6012 0x1735, // 1735..1736; COMMON
6013 0x1737, // 1737..173F; UNKNOWN
6014 0x1740, // 1740..1753; BUHID
6015 0x1754, // 1754..175F; UNKNOWN
6016 0x1760, // 1760..176C; TAGBANWA
6017 0x176D, // 176D ; UNKNOWN
6018 0x176E, // 176E..1770; TAGBANWA
6019 0x1771, // 1771 ; UNKNOWN
6020 0x1772, // 1772..1773; TAGBANWA
6021 0x1774, // 1774..177F; UNKNOWN
6022 0x1780, // 1780..17DD; KHMER
6023 0x17DE, // 17DE..17DF; UNKNOWN
6024 0x17E0, // 17E0..17E9; KHMER
6025 0x17EA, // 17EA..17EF; UNKNOWN
6026 0x17F0, // 17F0..17F9; KHMER
6027 0x17FA, // 17FA..17FF; UNKNOWN
6028 0x1800, // 1800..1801; MONGOLIAN
6029 0x1802, // 1802..1803; COMMON
6030 0x1804, // 1804 ; MONGOLIAN
6031 0x1805, // 1805 ; COMMON
6032 0x1806, // 1806..1819; MONGOLIAN
6033 0x181A, // 181A..181F; UNKNOWN
6034 0x1820, // 1820..1878; MONGOLIAN
6035 0x1879, // 1879..187F; UNKNOWN
6036 0x1880, // 1880..18AA; MONGOLIAN
6037 0x18AB, // 18AB..18AF; UNKNOWN
6038 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
6039 0x18F6, // 18F6..18FF; UNKNOWN
6040 0x1900, // 1900..191E; LIMBU
6041 0x191F, // 191F ; UNKNOWN
6042 0x1920, // 1920..192B; LIMBU
6043 0x192C, // 192C..192F; UNKNOWN
6044 0x1930, // 1930..193B; LIMBU
6045 0x193C, // 193C..193F; UNKNOWN
6046 0x1940, // 1940 ; LIMBU
6047 0x1941, // 1941..1943; UNKNOWN
6048 0x1944, // 1944..194F; LIMBU
6049 0x1950, // 1950..196D; TAI_LE
6050 0x196E, // 196E..196F; UNKNOWN
6051 0x1970, // 1970..1974; TAI_LE
6052 0x1975, // 1975..197F; UNKNOWN
6053 0x1980, // 1980..19AB; NEW_TAI_LUE
6054 0x19AC, // 19AC..19AF; UNKNOWN
6055 0x19B0, // 19B0..19C9; NEW_TAI_LUE
6056 0x19CA, // 19CA..19CF; UNKNOWN
6057 0x19D0, // 19D0..19DA; NEW_TAI_LUE
6058 0x19DB, // 19DB..19DD; UNKNOWN
6059 0x19DE, // 19DE..19DF; NEW_TAI_LUE
6060 0x19E0, // 19E0..19FF; KHMER
6061 0x1A00, // 1A00..1A1B; BUGINESE
6062 0x1A1C, // 1A1C..1A1D; UNKNOWN
6063 0x1A1E, // 1A1E..1A1F; BUGINESE
6064 0x1A20, // 1A20..1A5E; TAI_THAM
6065 0x1A5F, // 1A5F ; UNKNOWN
6066 0x1A60, // 1A60..1A7C; TAI_THAM
6067 0x1A7D, // 1A7D..1A7E; UNKNOWN
6068 0x1A7F, // 1A7F..1A89; TAI_THAM
6069 0x1A8A, // 1A8A..1A8F; UNKNOWN
6070 0x1A90, // 1A90..1A99; TAI_THAM
6071 0x1A9A, // 1A9A..1A9F; UNKNOWN
6072 0x1AA0, // 1AA0..1AAD; TAI_THAM
6073 0x1AAE, // 1AAE..1AAF; UNKNOWN
6074 0x1AB0, // 1AB0..1ACE; INHERITED
6075 0x1ACF, // 1ACF..1AFF; UNKNOWN
6076 0x1B00, // 1B00..1B4C; BALINESE
6077 0x1B4D, // 1B4D ; UNKNOWN
6078 0x1B4E, // 1B4E..1B7F; BALINESE
6079 0x1B80, // 1B80..1BBF; SUNDANESE
6080 0x1BC0, // 1BC0..1BF3; BATAK
6081 0x1BF4, // 1BF4..1BFB; UNKNOWN
6082 0x1BFC, // 1BFC..1BFF; BATAK
6083 0x1C00, // 1C00..1C37; LEPCHA
6084 0x1C38, // 1C38..1C3A; UNKNOWN
6085 0x1C3B, // 1C3B..1C49; LEPCHA
6086 0x1C4A, // 1C4A..1C4C; UNKNOWN
6087 0x1C4D, // 1C4D..1C4F; LEPCHA
6088 0x1C50, // 1C50..1C7F; OL_CHIKI
6089 0x1C80, // 1C80..1C8A; CYRILLIC
6090 0x1C8B, // 1C8B..1C8F; UNKNOWN
6091 0x1C90, // 1C90..1CBA; GEORGIAN
6092 0x1CBB, // 1CBB..1CBC; UNKNOWN
6093 0x1CBD, // 1CBD..1CBF; GEORGIAN
6094 0x1CC0, // 1CC0..1CC7; SUNDANESE
6095 0x1CC8, // 1CC8..1CCF; UNKNOWN
6096 0x1CD0, // 1CD0..1CD2; INHERITED
6097 0x1CD3, // 1CD3 ; COMMON
6098 0x1CD4, // 1CD4..1CE0; INHERITED
6099 0x1CE1, // 1CE1 ; COMMON
6100 0x1CE2, // 1CE2..1CE8; INHERITED
6101 0x1CE9, // 1CE9..1CEC; COMMON
6102 0x1CED, // 1CED ; INHERITED
6103 0x1CEE, // 1CEE..1CF3; COMMON
6104 0x1CF4, // 1CF4 ; INHERITED
6105 0x1CF5, // 1CF5..1CF7; COMMON
6106 0x1CF8, // 1CF8..1CF9; INHERITED
6107 0x1CFA, // 1CFA ; COMMON
6108 0x1CFB, // 1CFB..1CFF; UNKNOWN
6109 0x1D00, // 1D00..1D25; LATIN
6110 0x1D26, // 1D26..1D2A; GREEK
6111 0x1D2B, // 1D2B ; CYRILLIC
6112 0x1D2C, // 1D2C..1D5C; LATIN
6113 0x1D5D, // 1D5D..1D61; GREEK
6114 0x1D62, // 1D62..1D65; LATIN
6115 0x1D66, // 1D66..1D6A; GREEK
6116 0x1D6B, // 1D6B..1D77; LATIN
6117 0x1D78, // 1D78 ; CYRILLIC
6118 0x1D79, // 1D79..1DBE; LATIN
6119 0x1DBF, // 1DBF ; GREEK
6120 0x1DC0, // 1DC0..1DFF; INHERITED
6121 0x1E00, // 1E00..1EFF; LATIN
6122 0x1F00, // 1F00..1F15; GREEK
6123 0x1F16, // 1F16..1F17; UNKNOWN
6124 0x1F18, // 1F18..1F1D; GREEK
6125 0x1F1E, // 1F1E..1F1F; UNKNOWN
6126 0x1F20, // 1F20..1F45; GREEK
6127 0x1F46, // 1F46..1F47; UNKNOWN
6128 0x1F48, // 1F48..1F4D; GREEK
6129 0x1F4E, // 1F4E..1F4F; UNKNOWN
6130 0x1F50, // 1F50..1F57; GREEK
6131 0x1F58, // 1F58 ; UNKNOWN
6132 0x1F59, // 1F59 ; GREEK
6133 0x1F5A, // 1F5A ; UNKNOWN
6134 0x1F5B, // 1F5B ; GREEK
6135 0x1F5C, // 1F5C ; UNKNOWN
6136 0x1F5D, // 1F5D ; GREEK
6137 0x1F5E, // 1F5E ; UNKNOWN
6138 0x1F5F, // 1F5F..1F7D; GREEK
6139 0x1F7E, // 1F7E..1F7F; UNKNOWN
6140 0x1F80, // 1F80..1FB4; GREEK
6141 0x1FB5, // 1FB5 ; UNKNOWN
6142 0x1FB6, // 1FB6..1FC4; GREEK
6143 0x1FC5, // 1FC5 ; UNKNOWN
6144 0x1FC6, // 1FC6..1FD3; GREEK
6145 0x1FD4, // 1FD4..1FD5; UNKNOWN
6146 0x1FD6, // 1FD6..1FDB; GREEK
6147 0x1FDC, // 1FDC ; UNKNOWN
6148 0x1FDD, // 1FDD..1FEF; GREEK
6149 0x1FF0, // 1FF0..1FF1; UNKNOWN
6150 0x1FF2, // 1FF2..1FF4; GREEK
6151 0x1FF5, // 1FF5 ; UNKNOWN
6152 0x1FF6, // 1FF6..1FFE; GREEK
6153 0x1FFF, // 1FFF ; UNKNOWN
6154 0x2000, // 2000..200B; COMMON
6155 0x200C, // 200C..200D; INHERITED
6156 0x200E, // 200E..2064; COMMON
6157 0x2065, // 2065 ; UNKNOWN
6158 0x2066, // 2066..2070; COMMON
6159 0x2071, // 2071 ; LATIN
6160 0x2072, // 2072..2073; UNKNOWN
6161 0x2074, // 2074..207E; COMMON
6162 0x207F, // 207F ; LATIN
6163 0x2080, // 2080..208E; COMMON
6164 0x208F, // 208F ; UNKNOWN
6165 0x2090, // 2090..209C; LATIN
6166 0x209D, // 209D..209F; UNKNOWN
6167 0x20A0, // 20A0..20C0; COMMON
6168 0x20C1, // 20C1..20CF; UNKNOWN
6169 0x20D0, // 20D0..20F0; INHERITED
6170 0x20F1, // 20F1..20FF; UNKNOWN
6171 0x2100, // 2100..2125; COMMON
6172 0x2126, // 2126 ; GREEK
6173 0x2127, // 2127..2129; COMMON
6174 0x212A, // 212A..212B; LATIN
6175 0x212C, // 212C..2131; COMMON
6176 0x2132, // 2132 ; LATIN
6177 0x2133, // 2133..214D; COMMON
6178 0x214E, // 214E ; LATIN
6179 0x214F, // 214F..215F; COMMON
6180 0x2160, // 2160..2188; LATIN
6181 0x2189, // 2189..218B; COMMON
6182 0x218C, // 218C..218F; UNKNOWN
6183 0x2190, // 2190..2429; COMMON
6184 0x242A, // 242A..243F; UNKNOWN
6185 0x2440, // 2440..244A; COMMON
6186 0x244B, // 244B..245F; UNKNOWN
6187 0x2460, // 2460..27FF; COMMON
6188 0x2800, // 2800..28FF; BRAILLE
6189 0x2900, // 2900..2B73; COMMON
6190 0x2B74, // 2B74..2B75; UNKNOWN
6191 0x2B76, // 2B76..2B95; COMMON
6192 0x2B96, // 2B96 ; UNKNOWN
6193 0x2B97, // 2B97..2BFF; COMMON
6194 0x2C00, // 2C00..2C5F; GLAGOLITIC
6195 0x2C60, // 2C60..2C7F; LATIN
6196 0x2C80, // 2C80..2CF3; COPTIC
6197 0x2CF4, // 2CF4..2CF8; UNKNOWN
6198 0x2CF9, // 2CF9..2CFF; COPTIC
6199 0x2D00, // 2D00..2D25; GEORGIAN
6200 0x2D26, // 2D26 ; UNKNOWN
6201 0x2D27, // 2D27 ; GEORGIAN
6202 0x2D28, // 2D28..2D2C; UNKNOWN
6203 0x2D2D, // 2D2D ; GEORGIAN
6204 0x2D2E, // 2D2E..2D2F; UNKNOWN
6205 0x2D30, // 2D30..2D67; TIFINAGH
6206 0x2D68, // 2D68..2D6E; UNKNOWN
6207 0x2D6F, // 2D6F..2D70; TIFINAGH
6208 0x2D71, // 2D71..2D7E; UNKNOWN
6209 0x2D7F, // 2D7F ; TIFINAGH
6210 0x2D80, // 2D80..2D96; ETHIOPIC
6211 0x2D97, // 2D97..2D9F; UNKNOWN
6212 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6213 0x2DA7, // 2DA7 ; UNKNOWN
6214 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6215 0x2DAF, // 2DAF ; UNKNOWN
6216 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6217 0x2DB7, // 2DB7 ; UNKNOWN
6218 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6219 0x2DBF, // 2DBF ; UNKNOWN
6220 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6221 0x2DC7, // 2DC7 ; UNKNOWN
6222 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6223 0x2DCF, // 2DCF ; UNKNOWN
6224 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6225 0x2DD7, // 2DD7 ; UNKNOWN
6226 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6227 0x2DDF, // 2DDF ; UNKNOWN
6228 0x2DE0, // 2DE0..2DFF; CYRILLIC
6229 0x2E00, // 2E00..2E5D; COMMON
6230 0x2E5E, // 2E5E..2E7F; UNKNOWN
6231 0x2E80, // 2E80..2E99; HAN
6232 0x2E9A, // 2E9A ; UNKNOWN
6233 0x2E9B, // 2E9B..2EF3; HAN
6234 0x2EF4, // 2EF4..2EFF; UNKNOWN
6235 0x2F00, // 2F00..2FD5; HAN
6236 0x2FD6, // 2FD6..2FEF; UNKNOWN
6237 0x2FF0, // 2FF0..3004; COMMON
6238 0x3005, // 3005 ; HAN
6239 0x3006, // 3006 ; COMMON
6240 0x3007, // 3007 ; HAN
6241 0x3008, // 3008..3020; COMMON
6242 0x3021, // 3021..3029; HAN
6243 0x302A, // 302A..302D; INHERITED
6244 0x302E, // 302E..302F; HANGUL
6245 0x3030, // 3030..3037; COMMON
6246 0x3038, // 3038..303B; HAN
6247 0x303C, // 303C..303F; COMMON
6248 0x3040, // 3040 ; UNKNOWN
6249 0x3041, // 3041..3096; HIRAGANA
6250 0x3097, // 3097..3098; UNKNOWN
6251 0x3099, // 3099..309A; INHERITED
6252 0x309B, // 309B..309C; COMMON
6253 0x309D, // 309D..309F; HIRAGANA
6254 0x30A0, // 30A0 ; COMMON
6255 0x30A1, // 30A1..30FA; KATAKANA
6256 0x30FB, // 30FB..30FC; COMMON
6257 0x30FD, // 30FD..30FF; KATAKANA
6258 0x3100, // 3100..3104; UNKNOWN
6259 0x3105, // 3105..312F; BOPOMOFO
6260 0x3130, // 3130 ; UNKNOWN
6261 0x3131, // 3131..318E; HANGUL
6262 0x318F, // 318F ; UNKNOWN
6263 0x3190, // 3190..319F; COMMON
6264 0x31A0, // 31A0..31BF; BOPOMOFO
6265 0x31C0, // 31C0..31E5; COMMON
6266 0x31E6, // 31E6..31EE; UNKNOWN
6267 0x31EF, // 31EF ; COMMON
6268 0x31F0, // 31F0..31FF; KATAKANA
6269 0x3200, // 3200..321E; HANGUL
6270 0x321F, // 321F ; UNKNOWN
6271 0x3220, // 3220..325F; COMMON
6272 0x3260, // 3260..327E; HANGUL
6273 0x327F, // 327F..32CF; COMMON
6274 0x32D0, // 32D0..32FE; KATAKANA
6275 0x32FF, // 32FF ; COMMON
6276 0x3300, // 3300..3357; KATAKANA
6277 0x3358, // 3358..33FF; COMMON
6278 0x3400, // 3400..4DBF; HAN
6279 0x4DC0, // 4DC0..4DFF; COMMON
6280 0x4E00, // 4E00..9FFF; HAN
6281 0xA000, // A000..A48C; YI
6282 0xA48D, // A48D..A48F; UNKNOWN
6283 0xA490, // A490..A4C6; YI
6284 0xA4C7, // A4C7..A4CF; UNKNOWN
6285 0xA4D0, // A4D0..A4FF; LISU
6286 0xA500, // A500..A62B; VAI
6287 0xA62C, // A62C..A63F; UNKNOWN
6288 0xA640, // A640..A69F; CYRILLIC
6289 0xA6A0, // A6A0..A6F7; BAMUM
6290 0xA6F8, // A6F8..A6FF; UNKNOWN
6291 0xA700, // A700..A721; COMMON
6292 0xA722, // A722..A787; LATIN
6293 0xA788, // A788..A78A; COMMON
6294 0xA78B, // A78B..A7CD; LATIN
6295 0xA7CE, // A7CE..A7CF; UNKNOWN
6296 0xA7D0, // A7D0..A7D1; LATIN
6297 0xA7D2, // A7D2 ; UNKNOWN
6298 0xA7D3, // A7D3 ; LATIN
6299 0xA7D4, // A7D4 ; UNKNOWN
6300 0xA7D5, // A7D5..A7DC; LATIN
6301 0xA7DD, // A7DD..A7F1; UNKNOWN
6302 0xA7F2, // A7F2..A7FF; LATIN
6303 0xA800, // A800..A82C; SYLOTI_NAGRI
6304 0xA82D, // A82D..A82F; UNKNOWN
6305 0xA830, // A830..A839; COMMON
6306 0xA83A, // A83A..A83F; UNKNOWN
6307 0xA840, // A840..A877; PHAGS_PA
6308 0xA878, // A878..A87F; UNKNOWN
6309 0xA880, // A880..A8C5; SAURASHTRA
6310 0xA8C6, // A8C6..A8CD; UNKNOWN
6311 0xA8CE, // A8CE..A8D9; SAURASHTRA
6312 0xA8DA, // A8DA..A8DF; UNKNOWN
6313 0xA8E0, // A8E0..A8FF; DEVANAGARI
6314 0xA900, // A900..A92D; KAYAH_LI
6315 0xA92E, // A92E ; COMMON
6316 0xA92F, // A92F ; KAYAH_LI
6317 0xA930, // A930..A953; REJANG
6318 0xA954, // A954..A95E; UNKNOWN
6319 0xA95F, // A95F ; REJANG
6320 0xA960, // A960..A97C; HANGUL
6321 0xA97D, // A97D..A97F; UNKNOWN
6322 0xA980, // A980..A9CD; JAVANESE
6323 0xA9CE, // A9CE ; UNKNOWN
6324 0xA9CF, // A9CF ; COMMON
6325 0xA9D0, // A9D0..A9D9; JAVANESE
6326 0xA9DA, // A9DA..A9DD; UNKNOWN
6327 0xA9DE, // A9DE..A9DF; JAVANESE
6328 0xA9E0, // A9E0..A9FE; MYANMAR
6329 0xA9FF, // A9FF ; UNKNOWN
6330 0xAA00, // AA00..AA36; CHAM
6331 0xAA37, // AA37..AA3F; UNKNOWN
6332 0xAA40, // AA40..AA4D; CHAM
6333 0xAA4E, // AA4E..AA4F; UNKNOWN
6334 0xAA50, // AA50..AA59; CHAM
6335 0xAA5A, // AA5A..AA5B; UNKNOWN
6336 0xAA5C, // AA5C..AA5F; CHAM
6337 0xAA60, // AA60..AA7F; MYANMAR
6338 0xAA80, // AA80..AAC2; TAI_VIET
6339 0xAAC3, // AAC3..AADA; UNKNOWN
6340 0xAADB, // AADB..AADF; TAI_VIET
6341 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6342 0xAAF7, // AAF7..AB00; UNKNOWN
6343 0xAB01, // AB01..AB06; ETHIOPIC
6344 0xAB07, // AB07..AB08; UNKNOWN
6345 0xAB09, // AB09..AB0E; ETHIOPIC
6346 0xAB0F, // AB0F..AB10; UNKNOWN
6347 0xAB11, // AB11..AB16; ETHIOPIC
6348 0xAB17, // AB17..AB1F; UNKNOWN
6349 0xAB20, // AB20..AB26; ETHIOPIC
6350 0xAB27, // AB27 ; UNKNOWN
6351 0xAB28, // AB28..AB2E; ETHIOPIC
6352 0xAB2F, // AB2F ; UNKNOWN
6353 0xAB30, // AB30..AB5A; LATIN
6354 0xAB5B, // AB5B ; COMMON
6355 0xAB5C, // AB5C..AB64; LATIN
6356 0xAB65, // AB65 ; GREEK
6357 0xAB66, // AB66..AB69; LATIN
6358 0xAB6A, // AB6A..AB6B; COMMON
6359 0xAB6C, // AB6C..AB6F; UNKNOWN
6360 0xAB70, // AB70..ABBF; CHEROKEE
6361 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6362 0xABEE, // ABEE..ABEF; UNKNOWN
6363 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6364 0xABFA, // ABFA..ABFF; UNKNOWN
6365 0xAC00, // AC00..D7A3; HANGUL
6366 0xD7A4, // D7A4..D7AF; UNKNOWN
6367 0xD7B0, // D7B0..D7C6; HANGUL
6368 0xD7C7, // D7C7..D7CA; UNKNOWN
6369 0xD7CB, // D7CB..D7FB; HANGUL
6370 0xD7FC, // D7FC..F8FF; UNKNOWN
6371 0xF900, // F900..FA6D; HAN
6372 0xFA6E, // FA6E..FA6F; UNKNOWN
6373 0xFA70, // FA70..FAD9; HAN
6374 0xFADA, // FADA..FAFF; UNKNOWN
6375 0xFB00, // FB00..FB06; LATIN
6376 0xFB07, // FB07..FB12; UNKNOWN
6377 0xFB13, // FB13..FB17; ARMENIAN
6378 0xFB18, // FB18..FB1C; UNKNOWN
6379 0xFB1D, // FB1D..FB36; HEBREW
6380 0xFB37, // FB37 ; UNKNOWN
6381 0xFB38, // FB38..FB3C; HEBREW
6382 0xFB3D, // FB3D ; UNKNOWN
6383 0xFB3E, // FB3E ; HEBREW
6384 0xFB3F, // FB3F ; UNKNOWN
6385 0xFB40, // FB40..FB41; HEBREW
6386 0xFB42, // FB42 ; UNKNOWN
6387 0xFB43, // FB43..FB44; HEBREW
6388 0xFB45, // FB45 ; UNKNOWN
6389 0xFB46, // FB46..FB4F; HEBREW
6390 0xFB50, // FB50..FBC2; ARABIC
6391 0xFBC3, // FBC3..FBD2; UNKNOWN
6392 0xFBD3, // FBD3..FD3D; ARABIC
6393 0xFD3E, // FD3E..FD3F; COMMON
6394 0xFD40, // FD40..FD8F; ARABIC
6395 0xFD90, // FD90..FD91; UNKNOWN
6396 0xFD92, // FD92..FDC7; ARABIC
6397 0xFDC8, // FDC8..FDCE; UNKNOWN
6398 0xFDCF, // FDCF ; ARABIC
6399 0xFDD0, // FDD0..FDEF; UNKNOWN
6400 0xFDF0, // FDF0..FDFF; ARABIC
6401 0xFE00, // FE00..FE0F; INHERITED
6402 0xFE10, // FE10..FE19; COMMON
6403 0xFE1A, // FE1A..FE1F; UNKNOWN
6404 0xFE20, // FE20..FE2D; INHERITED
6405 0xFE2E, // FE2E..FE2F; CYRILLIC
6406 0xFE30, // FE30..FE52; COMMON
6407 0xFE53, // FE53 ; UNKNOWN
6408 0xFE54, // FE54..FE66; COMMON
6409 0xFE67, // FE67 ; UNKNOWN
6410 0xFE68, // FE68..FE6B; COMMON
6411 0xFE6C, // FE6C..FE6F; UNKNOWN
6412 0xFE70, // FE70..FE74; ARABIC
6413 0xFE75, // FE75 ; UNKNOWN
6414 0xFE76, // FE76..FEFC; ARABIC
6415 0xFEFD, // FEFD..FEFE; UNKNOWN
6416 0xFEFF, // FEFF ; COMMON
6417 0xFF00, // FF00 ; UNKNOWN
6418 0xFF01, // FF01..FF20; COMMON
6419 0xFF21, // FF21..FF3A; LATIN
6420 0xFF3B, // FF3B..FF40; COMMON
6421 0xFF41, // FF41..FF5A; LATIN
6422 0xFF5B, // FF5B..FF65; COMMON
6423 0xFF66, // FF66..FF6F; KATAKANA
6424 0xFF70, // FF70 ; COMMON
6425 0xFF71, // FF71..FF9D; KATAKANA
6426 0xFF9E, // FF9E..FF9F; COMMON
6427 0xFFA0, // FFA0..FFBE; HANGUL
6428 0xFFBF, // FFBF..FFC1; UNKNOWN
6429 0xFFC2, // FFC2..FFC7; HANGUL
6430 0xFFC8, // FFC8..FFC9; UNKNOWN
6431 0xFFCA, // FFCA..FFCF; HANGUL
6432 0xFFD0, // FFD0..FFD1; UNKNOWN
6433 0xFFD2, // FFD2..FFD7; HANGUL
6434 0xFFD8, // FFD8..FFD9; UNKNOWN
6435 0xFFDA, // FFDA..FFDC; HANGUL
6436 0xFFDD, // FFDD..FFDF; UNKNOWN
6437 0xFFE0, // FFE0..FFE6; COMMON
6438 0xFFE7, // FFE7 ; UNKNOWN
6439 0xFFE8, // FFE8..FFEE; COMMON
6440 0xFFEF, // FFEF..FFF8; UNKNOWN
6441 0xFFF9, // FFF9..FFFD; COMMON
6442 0xFFFE, // FFFE..FFFF; UNKNOWN
6443 0x10000, // 10000..1000B; LINEAR_B
6444 0x1000C, // 1000C ; UNKNOWN
6445 0x1000D, // 1000D..10026; LINEAR_B
6446 0x10027, // 10027 ; UNKNOWN
6447 0x10028, // 10028..1003A; LINEAR_B
6448 0x1003B, // 1003B ; UNKNOWN
6449 0x1003C, // 1003C..1003D; LINEAR_B
6450 0x1003E, // 1003E ; UNKNOWN
6451 0x1003F, // 1003F..1004D; LINEAR_B
6452 0x1004E, // 1004E..1004F; UNKNOWN
6453 0x10050, // 10050..1005D; LINEAR_B
6454 0x1005E, // 1005E..1007F; UNKNOWN
6455 0x10080, // 10080..100FA; LINEAR_B
6456 0x100FB, // 100FB..100FF; UNKNOWN
6457 0x10100, // 10100..10102; COMMON
6458 0x10103, // 10103..10106; UNKNOWN
6459 0x10107, // 10107..10133; COMMON
6460 0x10134, // 10134..10136; UNKNOWN
6461 0x10137, // 10137..1013F; COMMON
6462 0x10140, // 10140..1018E; GREEK
6463 0x1018F, // 1018F ; UNKNOWN
6464 0x10190, // 10190..1019C; COMMON
6465 0x1019D, // 1019D..1019F; UNKNOWN
6466 0x101A0, // 101A0 ; GREEK
6467 0x101A1, // 101A1..101CF; UNKNOWN
6468 0x101D0, // 101D0..101FC; COMMON
6469 0x101FD, // 101FD ; INHERITED
6470 0x101FE, // 101FE..1027F; UNKNOWN
6471 0x10280, // 10280..1029C; LYCIAN
6472 0x1029D, // 1029D..1029F; UNKNOWN
6473 0x102A0, // 102A0..102D0; CARIAN
6474 0x102D1, // 102D1..102DF; UNKNOWN
6475 0x102E0, // 102E0 ; INHERITED
6476 0x102E1, // 102E1..102FB; COMMON
6477 0x102FC, // 102FC..102FF; UNKNOWN
6478 0x10300, // 10300..10323; OLD_ITALIC
6479 0x10324, // 10324..1032C; UNKNOWN
6480 0x1032D, // 1032D..1032F; OLD_ITALIC
6481 0x10330, // 10330..1034A; GOTHIC
6482 0x1034B, // 1034B..1034F; UNKNOWN
6483 0x10350, // 10350..1037A; OLD_PERMIC
6484 0x1037B, // 1037B..1037F; UNKNOWN
6485 0x10380, // 10380..1039D; UGARITIC
6486 0x1039E, // 1039E ; UNKNOWN
6487 0x1039F, // 1039F ; UGARITIC
6488 0x103A0, // 103A0..103C3; OLD_PERSIAN
6489 0x103C4, // 103C4..103C7; UNKNOWN
6490 0x103C8, // 103C8..103D5; OLD_PERSIAN
6491 0x103D6, // 103D6..103FF; UNKNOWN
6492 0x10400, // 10400..1044F; DESERET
6493 0x10450, // 10450..1047F; SHAVIAN
6494 0x10480, // 10480..1049D; OSMANYA
6495 0x1049E, // 1049E..1049F; UNKNOWN
6496 0x104A0, // 104A0..104A9; OSMANYA
6497 0x104AA, // 104AA..104AF; UNKNOWN
6498 0x104B0, // 104B0..104D3; OSAGE
6499 0x104D4, // 104D4..104D7; UNKNOWN
6500 0x104D8, // 104D8..104FB; OSAGE
6501 0x104FC, // 104FC..104FF; UNKNOWN
6502 0x10500, // 10500..10527; ELBASAN
6503 0x10528, // 10528..1052F; UNKNOWN
6504 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6505 0x10564, // 10564..1056E; UNKNOWN
6506 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6507 0x10570, // 10570..1057A; VITHKUQI
6508 0x1057B, // 1057B ; UNKNOWN
6509 0x1057C, // 1057C..1058A; VITHKUQI
6510 0x1058B, // 1058B ; UNKNOWN
6511 0x1058C, // 1058C..10592; VITHKUQI
6512 0x10593, // 10593 ; UNKNOWN
6513 0x10594, // 10594..10595; VITHKUQI
6514 0x10596, // 10596 ; UNKNOWN
6515 0x10597, // 10597..105A1; VITHKUQI
6516 0x105A2, // 105A2 ; UNKNOWN
6517 0x105A3, // 105A3..105B1; VITHKUQI
6518 0x105B2, // 105B2 ; UNKNOWN
6519 0x105B3, // 105B3..105B9; VITHKUQI
6520 0x105BA, // 105BA ; UNKNOWN
6521 0x105BB, // 105BB..105BC; VITHKUQI
6522 0x105BD, // 105BD..105BF; UNKNOWN
6523 0x105C0, // 105C0..105F3; TODHRI
6524 0x105F4, // 105F4..105FF; UNKNOWN
6525 0x10600, // 10600..10736; LINEAR_A
6526 0x10737, // 10737..1073F; UNKNOWN
6527 0x10740, // 10740..10755; LINEAR_A
6528 0x10756, // 10756..1075F; UNKNOWN
6529 0x10760, // 10760..10767; LINEAR_A
6530 0x10768, // 10768..1077F; UNKNOWN
6531 0x10780, // 10780..10785; LATIN
6532 0x10786, // 10786 ; UNKNOWN
6533 0x10787, // 10787..107B0; LATIN
6534 0x107B1, // 107B1 ; UNKNOWN
6535 0x107B2, // 107B2..107BA; LATIN
6536 0x107BB, // 107BB..107FF; UNKNOWN
6537 0x10800, // 10800..10805; CYPRIOT
6538 0x10806, // 10806..10807; UNKNOWN
6539 0x10808, // 10808 ; CYPRIOT
6540 0x10809, // 10809 ; UNKNOWN
6541 0x1080A, // 1080A..10835; CYPRIOT
6542 0x10836, // 10836 ; UNKNOWN
6543 0x10837, // 10837..10838; CYPRIOT
6544 0x10839, // 10839..1083B; UNKNOWN
6545 0x1083C, // 1083C ; CYPRIOT
6546 0x1083D, // 1083D..1083E; UNKNOWN
6547 0x1083F, // 1083F ; CYPRIOT
6548 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6549 0x10856, // 10856 ; UNKNOWN
6550 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6551 0x10860, // 10860..1087F; PALMYRENE
6552 0x10880, // 10880..1089E; NABATAEAN
6553 0x1089F, // 1089F..108A6; UNKNOWN
6554 0x108A7, // 108A7..108AF; NABATAEAN
6555 0x108B0, // 108B0..108DF; UNKNOWN
6556 0x108E0, // 108E0..108F2; HATRAN
6557 0x108F3, // 108F3 ; UNKNOWN
6558 0x108F4, // 108F4..108F5; HATRAN
6559 0x108F6, // 108F6..108FA; UNKNOWN
6560 0x108FB, // 108FB..108FF; HATRAN
6561 0x10900, // 10900..1091B; PHOENICIAN
6562 0x1091C, // 1091C..1091E; UNKNOWN
6563 0x1091F, // 1091F ; PHOENICIAN
6564 0x10920, // 10920..10939; LYDIAN
6565 0x1093A, // 1093A..1093E; UNKNOWN
6566 0x1093F, // 1093F ; LYDIAN
6567 0x10940, // 10940..1097F; UNKNOWN
6568 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6569 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6570 0x109B8, // 109B8..109BB; UNKNOWN
6571 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6572 0x109D0, // 109D0..109D1; UNKNOWN
6573 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6574 0x10A00, // 10A00..10A03; KHAROSHTHI
6575 0x10A04, // 10A04 ; UNKNOWN
6576 0x10A05, // 10A05..10A06; KHAROSHTHI
6577 0x10A07, // 10A07..10A0B; UNKNOWN
6578 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6579 0x10A14, // 10A14 ; UNKNOWN
6580 0x10A15, // 10A15..10A17; KHAROSHTHI
6581 0x10A18, // 10A18 ; UNKNOWN
6582 0x10A19, // 10A19..10A35; KHAROSHTHI
6583 0x10A36, // 10A36..10A37; UNKNOWN
6584 0x10A38, // 10A38..10A3A; KHAROSHTHI
6585 0x10A3B, // 10A3B..10A3E; UNKNOWN
6586 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6587 0x10A49, // 10A49..10A4F; UNKNOWN
6588 0x10A50, // 10A50..10A58; KHAROSHTHI
6589 0x10A59, // 10A59..10A5F; UNKNOWN
6590 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6591 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6592 0x10AA0, // 10AA0..10ABF; UNKNOWN
6593 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6594 0x10AE7, // 10AE7..10AEA; UNKNOWN
6595 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6596 0x10AF7, // 10AF7..10AFF; UNKNOWN
6597 0x10B00, // 10B00..10B35; AVESTAN
6598 0x10B36, // 10B36..10B38; UNKNOWN
6599 0x10B39, // 10B39..10B3F; AVESTAN
6600 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6601 0x10B56, // 10B56..10B57; UNKNOWN
6602 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6603 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6604 0x10B73, // 10B73..10B77; UNKNOWN
6605 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6606 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6607 0x10B92, // 10B92..10B98; UNKNOWN
6608 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6609 0x10B9D, // 10B9D..10BA8; UNKNOWN
6610 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6611 0x10BB0, // 10BB0..10BFF; UNKNOWN
6612 0x10C00, // 10C00..10C48; OLD_TURKIC
6613 0x10C49, // 10C49..10C7F; UNKNOWN
6614 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6615 0x10CB3, // 10CB3..10CBF; UNKNOWN
6616 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6617 0x10CF3, // 10CF3..10CF9; UNKNOWN
6618 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6619 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6620 0x10D28, // 10D28..10D2F; UNKNOWN
6621 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6622 0x10D3A, // 10D3A..10D3F; UNKNOWN
6623 0x10D40, // 10D40..10D65; GARAY
6624 0x10D66, // 10D66..10D68; UNKNOWN
6625 0x10D69, // 10D69..10D85; GARAY
6626 0x10D86, // 10D86..10D8D; UNKNOWN
6627 0x10D8E, // 10D8E..10D8F; GARAY
6628 0x10D90, // 10D90..10E5F; UNKNOWN
6629 0x10E60, // 10E60..10E7E; ARABIC
6630 0x10E7F, // 10E7F ; UNKNOWN
6631 0x10E80, // 10E80..10EA9; YEZIDI
6632 0x10EAA, // 10EAA ; UNKNOWN
6633 0x10EAB, // 10EAB..10EAD; YEZIDI
6634 0x10EAE, // 10EAE..10EAF; UNKNOWN
6635 0x10EB0, // 10EB0..10EB1; YEZIDI
6636 0x10EB2, // 10EB2..10EC1; UNKNOWN
6637 0x10EC2, // 10EC2..10EC4; ARABIC
6638 0x10EC5, // 10EC5..10EFB; UNKNOWN
6639 0x10EFC, // 10EFC..10EFF; ARABIC
6640 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6641 0x10F28, // 10F28..10F2F; UNKNOWN
6642 0x10F30, // 10F30..10F59; SOGDIAN
6643 0x10F5A, // 10F5A..10F6F; UNKNOWN
6644 0x10F70, // 10F70..10F89; OLD_UYGHUR
6645 0x10F8A, // 10F8A..10FAF; UNKNOWN
6646 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6647 0x10FCC, // 10FCC..10FDF; UNKNOWN
6648 0x10FE0, // 10FE0..10FF6; ELYMAIC
6649 0x10FF7, // 10FF7..10FFF; UNKNOWN
6650 0x11000, // 11000..1104D; BRAHMI
6651 0x1104E, // 1104E..11051; UNKNOWN
6652 0x11052, // 11052..11075; BRAHMI
6653 0x11076, // 11076..1107E; UNKNOWN
6654 0x1107F, // 1107F ; BRAHMI
6655 0x11080, // 11080..110C2; KAITHI
6656 0x110C3, // 110C3..110CC; UNKNOWN
6657 0x110CD, // 110CD ; KAITHI
6658 0x110CE, // 110CE..110CF; UNKNOWN
6659 0x110D0, // 110D0..110E8; SORA_SOMPENG
6660 0x110E9, // 110E9..110EF; UNKNOWN
6661 0x110F0, // 110F0..110F9; SORA_SOMPENG
6662 0x110FA, // 110FA..110FF; UNKNOWN
6663 0x11100, // 11100..11134; CHAKMA
6664 0x11135, // 11135 ; UNKNOWN
6665 0x11136, // 11136..11147; CHAKMA
6666 0x11148, // 11148..1114F; UNKNOWN
6667 0x11150, // 11150..11176; MAHAJANI
6668 0x11177, // 11177..1117F; UNKNOWN
6669 0x11180, // 11180..111DF; SHARADA
6670 0x111E0, // 111E0 ; UNKNOWN
6671 0x111E1, // 111E1..111F4; SINHALA
6672 0x111F5, // 111F5..111FF; UNKNOWN
6673 0x11200, // 11200..11211; KHOJKI
6674 0x11212, // 11212 ; UNKNOWN
6675 0x11213, // 11213..11241; KHOJKI
6676 0x11242, // 11242..1127F; UNKNOWN
6677 0x11280, // 11280..11286; MULTANI
6678 0x11287, // 11287 ; UNKNOWN
6679 0x11288, // 11288 ; MULTANI
6680 0x11289, // 11289 ; UNKNOWN
6681 0x1128A, // 1128A..1128D; MULTANI
6682 0x1128E, // 1128E ; UNKNOWN
6683 0x1128F, // 1128F..1129D; MULTANI
6684 0x1129E, // 1129E ; UNKNOWN
6685 0x1129F, // 1129F..112A9; MULTANI
6686 0x112AA, // 112AA..112AF; UNKNOWN
6687 0x112B0, // 112B0..112EA; KHUDAWADI
6688 0x112EB, // 112EB..112EF; UNKNOWN
6689 0x112F0, // 112F0..112F9; KHUDAWADI
6690 0x112FA, // 112FA..112FF; UNKNOWN
6691 0x11300, // 11300..11303; GRANTHA
6692 0x11304, // 11304 ; UNKNOWN
6693 0x11305, // 11305..1130C; GRANTHA
6694 0x1130D, // 1130D..1130E; UNKNOWN
6695 0x1130F, // 1130F..11310; GRANTHA
6696 0x11311, // 11311..11312; UNKNOWN
6697 0x11313, // 11313..11328; GRANTHA
6698 0x11329, // 11329 ; UNKNOWN
6699 0x1132A, // 1132A..11330; GRANTHA
6700 0x11331, // 11331 ; UNKNOWN
6701 0x11332, // 11332..11333; GRANTHA
6702 0x11334, // 11334 ; UNKNOWN
6703 0x11335, // 11335..11339; GRANTHA
6704 0x1133A, // 1133A ; UNKNOWN
6705 0x1133B, // 1133B ; INHERITED
6706 0x1133C, // 1133C..11344; GRANTHA
6707 0x11345, // 11345..11346; UNKNOWN
6708 0x11347, // 11347..11348; GRANTHA
6709 0x11349, // 11349..1134A; UNKNOWN
6710 0x1134B, // 1134B..1134D; GRANTHA
6711 0x1134E, // 1134E..1134F; UNKNOWN
6712 0x11350, // 11350 ; GRANTHA
6713 0x11351, // 11351..11356; UNKNOWN
6714 0x11357, // 11357 ; GRANTHA
6715 0x11358, // 11358..1135C; UNKNOWN
6716 0x1135D, // 1135D..11363; GRANTHA
6717 0x11364, // 11364..11365; UNKNOWN
6718 0x11366, // 11366..1136C; GRANTHA
6719 0x1136D, // 1136D..1136F; UNKNOWN
6720 0x11370, // 11370..11374; GRANTHA
6721 0x11375, // 11375..1137F; UNKNOWN
6722 0x11380, // 11380..11389; TULU_TIGALARI
6723 0x1138A, // 1138A ; UNKNOWN
6724 0x1138B, // 1138B ; TULU_TIGALARI
6725 0x1138C, // 1138C..1138D; UNKNOWN
6726 0x1138E, // 1138E ; TULU_TIGALARI
6727 0x1138F, // 1138F ; UNKNOWN
6728 0x11390, // 11390..113B5; TULU_TIGALARI
6729 0x113B6, // 113B6 ; UNKNOWN
6730 0x113B7, // 113B7..113C0; TULU_TIGALARI
6731 0x113C1, // 113C1 ; UNKNOWN
6732 0x113C2, // 113C2 ; TULU_TIGALARI
6733 0x113C3, // 113C3..113C4; UNKNOWN
6734 0x113C5, // 113C5 ; TULU_TIGALARI
6735 0x113C6, // 113C6 ; UNKNOWN
6736 0x113C7, // 113C7..113CA; TULU_TIGALARI
6737 0x113CB, // 113CB ; UNKNOWN
6738 0x113CC, // 113CC..113D5; TULU_TIGALARI
6739 0x113D6, // 113D6 ; UNKNOWN
6740 0x113D7, // 113D7..113D8; TULU_TIGALARI
6741 0x113D9, // 113D9..113E0; UNKNOWN
6742 0x113E1, // 113E1..113E2; TULU_TIGALARI
6743 0x113E3, // 113E3..113FF; UNKNOWN
6744 0x11400, // 11400..1145B; NEWA
6745 0x1145C, // 1145C ; UNKNOWN
6746 0x1145D, // 1145D..11461; NEWA
6747 0x11462, // 11462..1147F; UNKNOWN
6748 0x11480, // 11480..114C7; TIRHUTA
6749 0x114C8, // 114C8..114CF; UNKNOWN
6750 0x114D0, // 114D0..114D9; TIRHUTA
6751 0x114DA, // 114DA..1157F; UNKNOWN
6752 0x11580, // 11580..115B5; SIDDHAM
6753 0x115B6, // 115B6..115B7; UNKNOWN
6754 0x115B8, // 115B8..115DD; SIDDHAM
6755 0x115DE, // 115DE..115FF; UNKNOWN
6756 0x11600, // 11600..11644; MODI
6757 0x11645, // 11645..1164F; UNKNOWN
6758 0x11650, // 11650..11659; MODI
6759 0x1165A, // 1165A..1165F; UNKNOWN
6760 0x11660, // 11660..1166C; MONGOLIAN
6761 0x1166D, // 1166D..1167F; UNKNOWN
6762 0x11680, // 11680..116B9; TAKRI
6763 0x116BA, // 116BA..116BF; UNKNOWN
6764 0x116C0, // 116C0..116C9; TAKRI
6765 0x116CA, // 116CA..116CF; UNKNOWN
6766 0x116D0, // 116D0..116E3; MYANMAR
6767 0x116E4, // 116E4..116FF; UNKNOWN
6768 0x11700, // 11700..1171A; AHOM
6769 0x1171B, // 1171B..1171C; UNKNOWN
6770 0x1171D, // 1171D..1172B; AHOM
6771 0x1172C, // 1172C..1172F; UNKNOWN
6772 0x11730, // 11730..11746; AHOM
6773 0x11747, // 11747..117FF; UNKNOWN
6774 0x11800, // 11800..1183B; DOGRA
6775 0x1183C, // 1183C..1189F; UNKNOWN
6776 0x118A0, // 118A0..118F2; WARANG_CITI
6777 0x118F3, // 118F3..118FE; UNKNOWN
6778 0x118FF, // 118FF ; WARANG_CITI
6779 0x11900, // 11900..11906; DIVES_AKURU
6780 0x11907, // 11907..11908; UNKNOWN
6781 0x11909, // 11909 ; DIVES_AKURU
6782 0x1190A, // 1190A..1190B; UNKNOWN
6783 0x1190C, // 1190C..11913; DIVES_AKURU
6784 0x11914, // 11914 ; UNKNOWN
6785 0x11915, // 11915..11916; DIVES_AKURU
6786 0x11917, // 11917 ; UNKNOWN
6787 0x11918, // 11918..11935; DIVES_AKURU
6788 0x11936, // 11936 ; UNKNOWN
6789 0x11937, // 11937..11938; DIVES_AKURU
6790 0x11939, // 11939..1193A; UNKNOWN
6791 0x1193B, // 1193B..11946; DIVES_AKURU
6792 0x11947, // 11947..1194F; UNKNOWN
6793 0x11950, // 11950..11959; DIVES_AKURU
6794 0x1195A, // 1195A..1199F; UNKNOWN
6795 0x119A0, // 119A0..119A7; NANDINAGARI
6796 0x119A8, // 119A8..119A9; UNKNOWN
6797 0x119AA, // 119AA..119D7; NANDINAGARI
6798 0x119D8, // 119D8..119D9; UNKNOWN
6799 0x119DA, // 119DA..119E4; NANDINAGARI
6800 0x119E5, // 119E5..119FF; UNKNOWN
6801 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6802 0x11A48, // 11A48..11A4F; UNKNOWN
6803 0x11A50, // 11A50..11AA2; SOYOMBO
6804 0x11AA3, // 11AA3..11AAF; UNKNOWN
6805 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6806 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6807 0x11AF9, // 11AF9..11AFF; UNKNOWN
6808 0x11B00, // 11B00..11B09; DEVANAGARI
6809 0x11B0A, // 11B0A..11BBF; UNKNOWN
6810 0x11BC0, // 11BC0..11BE1; SUNUWAR
6811 0x11BE2, // 11BE2..11BEF; UNKNOWN
6812 0x11BF0, // 11BF0..11BF9; SUNUWAR
6813 0x11BFA, // 11BFA..11BFF; UNKNOWN
6814 0x11C00, // 11C00..11C08; BHAIKSUKI
6815 0x11C09, // 11C09 ; UNKNOWN
6816 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6817 0x11C37, // 11C37 ; UNKNOWN
6818 0x11C38, // 11C38..11C45; BHAIKSUKI
6819 0x11C46, // 11C46..11C4F; UNKNOWN
6820 0x11C50, // 11C50..11C6C; BHAIKSUKI
6821 0x11C6D, // 11C6D..11C6F; UNKNOWN
6822 0x11C70, // 11C70..11C8F; MARCHEN
6823 0x11C90, // 11C90..11C91; UNKNOWN
6824 0x11C92, // 11C92..11CA7; MARCHEN
6825 0x11CA8, // 11CA8 ; UNKNOWN
6826 0x11CA9, // 11CA9..11CB6; MARCHEN
6827 0x11CB7, // 11CB7..11CFF; UNKNOWN
6828 0x11D00, // 11D00..11D06; MASARAM_GONDI
6829 0x11D07, // 11D07 ; UNKNOWN
6830 0x11D08, // 11D08..11D09; MASARAM_GONDI
6831 0x11D0A, // 11D0A ; UNKNOWN
6832 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6833 0x11D37, // 11D37..11D39; UNKNOWN
6834 0x11D3A, // 11D3A ; MASARAM_GONDI
6835 0x11D3B, // 11D3B ; UNKNOWN
6836 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6837 0x11D3E, // 11D3E ; UNKNOWN
6838 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6839 0x11D48, // 11D48..11D4F; UNKNOWN
6840 0x11D50, // 11D50..11D59; MASARAM_GONDI
6841 0x11D5A, // 11D5A..11D5F; UNKNOWN
6842 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6843 0x11D66, // 11D66 ; UNKNOWN
6844 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6845 0x11D69, // 11D69 ; UNKNOWN
6846 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6847 0x11D8F, // 11D8F ; UNKNOWN
6848 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6849 0x11D92, // 11D92 ; UNKNOWN
6850 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6851 0x11D99, // 11D99..11D9F; UNKNOWN
6852 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6853 0x11DAA, // 11DAA..11EDF; UNKNOWN
6854 0x11EE0, // 11EE0..11EF8; MAKASAR
6855 0x11EF9, // 11EF9..11EFF; UNKNOWN
6856 0x11F00, // 11F00..11F10; KAWI
6857 0x11F11, // 11F11 ; UNKNOWN
6858 0x11F12, // 11F12..11F3A; KAWI
6859 0x11F3B, // 11F3B..11F3D; UNKNOWN
6860 0x11F3E, // 11F3E..11F5A; KAWI
6861 0x11F5B, // 11F5B..11FAF; UNKNOWN
6862 0x11FB0, // 11FB0 ; LISU
6863 0x11FB1, // 11FB1..11FBF; UNKNOWN
6864 0x11FC0, // 11FC0..11FF1; TAMIL
6865 0x11FF2, // 11FF2..11FFE; UNKNOWN
6866 0x11FFF, // 11FFF ; TAMIL
6867 0x12000, // 12000..12399; CUNEIFORM
6868 0x1239A, // 1239A..123FF; UNKNOWN
6869 0x12400, // 12400..1246E; CUNEIFORM
6870 0x1246F, // 1246F ; UNKNOWN
6871 0x12470, // 12470..12474; CUNEIFORM
6872 0x12475, // 12475..1247F; UNKNOWN
6873 0x12480, // 12480..12543; CUNEIFORM
6874 0x12544, // 12544..12F8F; UNKNOWN
6875 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6876 0x12FF3, // 12FF3..12FFF; UNKNOWN
6877 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6878 0x13456, // 13456..1345F; UNKNOWN
6879 0x13460, // 13460..143FA; EGYPTIAN_HIEROGLYPHS
6880 0x143FB, // 143FB..143FF; UNKNOWN
6881 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6882 0x14647, // 14647..160FF; UNKNOWN
6883 0x16100, // 16100..16139; GURUNG_KHEMA
6884 0x1613A, // 1613A..167FF; UNKNOWN
6885 0x16800, // 16800..16A38; BAMUM
6886 0x16A39, // 16A39..16A3F; UNKNOWN
6887 0x16A40, // 16A40..16A5E; MRO
6888 0x16A5F, // 16A5F ; UNKNOWN
6889 0x16A60, // 16A60..16A69; MRO
6890 0x16A6A, // 16A6A..16A6D; UNKNOWN
6891 0x16A6E, // 16A6E..16A6F; MRO
6892 0x16A70, // 16A70..16ABE; TANGSA
6893 0x16ABF, // 16ABF ; UNKNOWN
6894 0x16AC0, // 16AC0..16AC9; TANGSA
6895 0x16ACA, // 16ACA..16ACF; UNKNOWN
6896 0x16AD0, // 16AD0..16AED; BASSA_VAH
6897 0x16AEE, // 16AEE..16AEF; UNKNOWN
6898 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6899 0x16AF6, // 16AF6..16AFF; UNKNOWN
6900 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6901 0x16B46, // 16B46..16B4F; UNKNOWN
6902 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6903 0x16B5A, // 16B5A ; UNKNOWN
6904 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6905 0x16B62, // 16B62 ; UNKNOWN
6906 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6907 0x16B78, // 16B78..16B7C; UNKNOWN
6908 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6909 0x16B90, // 16B90..16D3F; UNKNOWN
6910 0x16D40, // 16D40..16D79; KIRAT_RAI
6911 0x16D7A, // 16D7A..16E3F; UNKNOWN
6912 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6913 0x16E9B, // 16E9B..16EFF; UNKNOWN
6914 0x16F00, // 16F00..16F4A; MIAO
6915 0x16F4B, // 16F4B..16F4E; UNKNOWN
6916 0x16F4F, // 16F4F..16F87; MIAO
6917 0x16F88, // 16F88..16F8E; UNKNOWN
6918 0x16F8F, // 16F8F..16F9F; MIAO
6919 0x16FA0, // 16FA0..16FDF; UNKNOWN
6920 0x16FE0, // 16FE0 ; TANGUT
6921 0x16FE1, // 16FE1 ; NUSHU
6922 0x16FE2, // 16FE2..16FE3; HAN
6923 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
6924 0x16FE5, // 16FE5..16FEF; UNKNOWN
6925 0x16FF0, // 16FF0..16FF1; HAN
6926 0x16FF2, // 16FF2..16FFF; UNKNOWN
6927 0x17000, // 17000..187F7; TANGUT
6928 0x187F8, // 187F8..187FF; UNKNOWN
6929 0x18800, // 18800..18AFF; TANGUT
6930 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
6931 0x18CD6, // 18CD6..18CFE; UNKNOWN
6932 0x18CFF, // 18CFF ; KHITAN_SMALL_SCRIPT
6933 0x18D00, // 18D00..18D08; TANGUT
6934 0x18D09, // 18D09..1AFEF; UNKNOWN
6935 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
6936 0x1AFF4, // 1AFF4 ; UNKNOWN
6937 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
6938 0x1AFFC, // 1AFFC ; UNKNOWN
6939 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
6940 0x1AFFF, // 1AFFF ; UNKNOWN
6941 0x1B000, // 1B000 ; KATAKANA
6942 0x1B001, // 1B001..1B11F; HIRAGANA
6943 0x1B120, // 1B120..1B122; KATAKANA
6944 0x1B123, // 1B123..1B131; UNKNOWN
6945 0x1B132, // 1B132 ; HIRAGANA
6946 0x1B133, // 1B133..1B14F; UNKNOWN
6947 0x1B150, // 1B150..1B152; HIRAGANA
6948 0x1B153, // 1B153..1B154; UNKNOWN
6949 0x1B155, // 1B155 ; KATAKANA
6950 0x1B156, // 1B156..1B163; UNKNOWN
6951 0x1B164, // 1B164..1B167; KATAKANA
6952 0x1B168, // 1B168..1B16F; UNKNOWN
6953 0x1B170, // 1B170..1B2FB; NUSHU
6954 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6955 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6956 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6957 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6958 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6959 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6960 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6961 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6962 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6963 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6964 0x1BCA0, // 1BCA0..1BCA3; COMMON
6965 0x1BCA4, // 1BCA4..1CBFF; UNKNOWN
6966 0x1CC00, // 1CC00..1CCF9; COMMON
6967 0x1CCFA, // 1CCFA..1CCFF; UNKNOWN
6968 0x1CD00, // 1CD00..1CEB3; COMMON
6969 0x1CEB4, // 1CEB4..1CEFF; UNKNOWN
6970 0x1CF00, // 1CF00..1CF2D; INHERITED
6971 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
6972 0x1CF30, // 1CF30..1CF46; INHERITED
6973 0x1CF47, // 1CF47..1CF4F; UNKNOWN
6974 0x1CF50, // 1CF50..1CFC3; COMMON
6975 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
6976 0x1D000, // 1D000..1D0F5; COMMON
6977 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6978 0x1D100, // 1D100..1D126; COMMON
6979 0x1D127, // 1D127..1D128; UNKNOWN
6980 0x1D129, // 1D129..1D166; COMMON
6981 0x1D167, // 1D167..1D169; INHERITED
6982 0x1D16A, // 1D16A..1D17A; COMMON
6983 0x1D17B, // 1D17B..1D182; INHERITED
6984 0x1D183, // 1D183..1D184; COMMON
6985 0x1D185, // 1D185..1D18B; INHERITED
6986 0x1D18C, // 1D18C..1D1A9; COMMON
6987 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6988 0x1D1AE, // 1D1AE..1D1EA; COMMON
6989 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
6990 0x1D200, // 1D200..1D245; GREEK
6991 0x1D246, // 1D246..1D2BF; UNKNOWN
6992 0x1D2C0, // 1D2C0..1D2D3; COMMON
6993 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
6994 0x1D2E0, // 1D2E0..1D2F3; COMMON
6995 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6996 0x1D300, // 1D300..1D356; COMMON
6997 0x1D357, // 1D357..1D35F; UNKNOWN
6998 0x1D360, // 1D360..1D378; COMMON
6999 0x1D379, // 1D379..1D3FF; UNKNOWN
7000 0x1D400, // 1D400..1D454; COMMON
7001 0x1D455, // 1D455 ; UNKNOWN
7002 0x1D456, // 1D456..1D49C; COMMON
7003 0x1D49D, // 1D49D ; UNKNOWN
7004 0x1D49E, // 1D49E..1D49F; COMMON
7005 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
7006 0x1D4A2, // 1D4A2 ; COMMON
7007 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
7008 0x1D4A5, // 1D4A5..1D4A6; COMMON
7009 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
7010 0x1D4A9, // 1D4A9..1D4AC; COMMON
7011 0x1D4AD, // 1D4AD ; UNKNOWN
7012 0x1D4AE, // 1D4AE..1D4B9; COMMON
7013 0x1D4BA, // 1D4BA ; UNKNOWN
7014 0x1D4BB, // 1D4BB ; COMMON
7015 0x1D4BC, // 1D4BC ; UNKNOWN
7016 0x1D4BD, // 1D4BD..1D4C3; COMMON
7017 0x1D4C4, // 1D4C4 ; UNKNOWN
7018 0x1D4C5, // 1D4C5..1D505; COMMON
7019 0x1D506, // 1D506 ; UNKNOWN
7020 0x1D507, // 1D507..1D50A; COMMON
7021 0x1D50B, // 1D50B..1D50C; UNKNOWN
7022 0x1D50D, // 1D50D..1D514; COMMON
7023 0x1D515, // 1D515 ; UNKNOWN
7024 0x1D516, // 1D516..1D51C; COMMON
7025 0x1D51D, // 1D51D ; UNKNOWN
7026 0x1D51E, // 1D51E..1D539; COMMON
7027 0x1D53A, // 1D53A ; UNKNOWN
7028 0x1D53B, // 1D53B..1D53E; COMMON
7029 0x1D53F, // 1D53F ; UNKNOWN
7030 0x1D540, // 1D540..1D544; COMMON
7031 0x1D545, // 1D545 ; UNKNOWN
7032 0x1D546, // 1D546 ; COMMON
7033 0x1D547, // 1D547..1D549; UNKNOWN
7034 0x1D54A, // 1D54A..1D550; COMMON
7035 0x1D551, // 1D551 ; UNKNOWN
7036 0x1D552, // 1D552..1D6A5; COMMON
7037 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
7038 0x1D6A8, // 1D6A8..1D7CB; COMMON
7039 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
7040 0x1D7CE, // 1D7CE..1D7FF; COMMON
7041 0x1D800, // 1D800..1DA8B; SIGNWRITING
7042 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
7043 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
7044 0x1DAA0, // 1DAA0 ; UNKNOWN
7045 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
7046 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
7047 0x1DF00, // 1DF00..1DF1E; LATIN
7048 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
7049 0x1DF25, // 1DF25..1DF2A; LATIN
7050 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
7051 0x1E000, // 1E000..1E006; GLAGOLITIC
7052 0x1E007, // 1E007 ; UNKNOWN
7053 0x1E008, // 1E008..1E018; GLAGOLITIC
7054 0x1E019, // 1E019..1E01A; UNKNOWN
7055 0x1E01B, // 1E01B..1E021; GLAGOLITIC
7056 0x1E022, // 1E022 ; UNKNOWN
7057 0x1E023, // 1E023..1E024; GLAGOLITIC
7058 0x1E025, // 1E025 ; UNKNOWN
7059 0x1E026, // 1E026..1E02A; GLAGOLITIC
7060 0x1E02B, // 1E02B..1E02F; UNKNOWN
7061 0x1E030, // 1E030..1E06D; CYRILLIC
7062 0x1E06E, // 1E06E..1E08E; UNKNOWN
7063 0x1E08F, // 1E08F ; CYRILLIC
7064 0x1E090, // 1E090..1E0FF; UNKNOWN
7065 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
7066 0x1E12D, // 1E12D..1E12F; UNKNOWN
7067 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
7068 0x1E13E, // 1E13E..1E13F; UNKNOWN
7069 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
7070 0x1E14A, // 1E14A..1E14D; UNKNOWN
7071 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
7072 0x1E150, // 1E150..1E28F; UNKNOWN
7073 0x1E290, // 1E290..1E2AE; TOTO
7074 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
7075 0x1E2C0, // 1E2C0..1E2F9; WANCHO
7076 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
7077 0x1E2FF, // 1E2FF ; WANCHO
7078 0x1E300, // 1E300..1E4CF; UNKNOWN
7079 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
7080 0x1E4FA, // 1E4FA..1E5CF; UNKNOWN
7081 0x1E5D0, // 1E5D0..1E5FA; OL_ONAL
7082 0x1E5FB, // 1E5FB..1E5FE; UNKNOWN
7083 0x1E5FF, // 1E5FF ; OL_ONAL
7084 0x1E600, // 1E600..1E7DF; UNKNOWN
7085 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
7086 0x1E7E7, // 1E7E7 ; UNKNOWN
7087 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
7088 0x1E7EC, // 1E7EC ; UNKNOWN
7089 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
7090 0x1E7EF, // 1E7EF ; UNKNOWN
7091 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
7092 0x1E7FF, // 1E7FF ; UNKNOWN
7093 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
7094 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
7095 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
7096 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
7097 0x1E900, // 1E900..1E94B; ADLAM
7098 0x1E94C, // 1E94C..1E94F; UNKNOWN
7099 0x1E950, // 1E950..1E959; ADLAM
7100 0x1E95A, // 1E95A..1E95D; UNKNOWN
7101 0x1E95E, // 1E95E..1E95F; ADLAM
7102 0x1E960, // 1E960..1EC70; UNKNOWN
7103 0x1EC71, // 1EC71..1ECB4; COMMON
7104 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
7105 0x1ED01, // 1ED01..1ED3D; COMMON
7106 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
7107 0x1EE00, // 1EE00..1EE03; ARABIC
7108 0x1EE04, // 1EE04 ; UNKNOWN
7109 0x1EE05, // 1EE05..1EE1F; ARABIC
7110 0x1EE20, // 1EE20 ; UNKNOWN
7111 0x1EE21, // 1EE21..1EE22; ARABIC
7112 0x1EE23, // 1EE23 ; UNKNOWN
7113 0x1EE24, // 1EE24 ; ARABIC
7114 0x1EE25, // 1EE25..1EE26; UNKNOWN
7115 0x1EE27, // 1EE27 ; ARABIC
7116 0x1EE28, // 1EE28 ; UNKNOWN
7117 0x1EE29, // 1EE29..1EE32; ARABIC
7118 0x1EE33, // 1EE33 ; UNKNOWN
7119 0x1EE34, // 1EE34..1EE37; ARABIC
7120 0x1EE38, // 1EE38 ; UNKNOWN
7121 0x1EE39, // 1EE39 ; ARABIC
7122 0x1EE3A, // 1EE3A ; UNKNOWN
7123 0x1EE3B, // 1EE3B ; ARABIC
7124 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
7125 0x1EE42, // 1EE42 ; ARABIC
7126 0x1EE43, // 1EE43..1EE46; UNKNOWN
7127 0x1EE47, // 1EE47 ; ARABIC
7128 0x1EE48, // 1EE48 ; UNKNOWN
7129 0x1EE49, // 1EE49 ; ARABIC
7130 0x1EE4A, // 1EE4A ; UNKNOWN
7131 0x1EE4B, // 1EE4B ; ARABIC
7132 0x1EE4C, // 1EE4C ; UNKNOWN
7133 0x1EE4D, // 1EE4D..1EE4F; ARABIC
7134 0x1EE50, // 1EE50 ; UNKNOWN
7135 0x1EE51, // 1EE51..1EE52; ARABIC
7136 0x1EE53, // 1EE53 ; UNKNOWN
7137 0x1EE54, // 1EE54 ; ARABIC
7138 0x1EE55, // 1EE55..1EE56; UNKNOWN
7139 0x1EE57, // 1EE57 ; ARABIC
7140 0x1EE58, // 1EE58 ; UNKNOWN
7141 0x1EE59, // 1EE59 ; ARABIC
7142 0x1EE5A, // 1EE5A ; UNKNOWN
7143 0x1EE5B, // 1EE5B ; ARABIC
7144 0x1EE5C, // 1EE5C ; UNKNOWN
7145 0x1EE5D, // 1EE5D ; ARABIC
7146 0x1EE5E, // 1EE5E ; UNKNOWN
7147 0x1EE5F, // 1EE5F ; ARABIC
7148 0x1EE60, // 1EE60 ; UNKNOWN
7149 0x1EE61, // 1EE61..1EE62; ARABIC
7150 0x1EE63, // 1EE63 ; UNKNOWN
7151 0x1EE64, // 1EE64 ; ARABIC
7152 0x1EE65, // 1EE65..1EE66; UNKNOWN
7153 0x1EE67, // 1EE67..1EE6A; ARABIC
7154 0x1EE6B, // 1EE6B ; UNKNOWN
7155 0x1EE6C, // 1EE6C..1EE72; ARABIC
7156 0x1EE73, // 1EE73 ; UNKNOWN
7157 0x1EE74, // 1EE74..1EE77; ARABIC
7158 0x1EE78, // 1EE78 ; UNKNOWN
7159 0x1EE79, // 1EE79..1EE7C; ARABIC
7160 0x1EE7D, // 1EE7D ; UNKNOWN
7161 0x1EE7E, // 1EE7E ; ARABIC
7162 0x1EE7F, // 1EE7F ; UNKNOWN
7163 0x1EE80, // 1EE80..1EE89; ARABIC
7164 0x1EE8A, // 1EE8A ; UNKNOWN
7165 0x1EE8B, // 1EE8B..1EE9B; ARABIC
7166 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
7167 0x1EEA1, // 1EEA1..1EEA3; ARABIC
7168 0x1EEA4, // 1EEA4 ; UNKNOWN
7169 0x1EEA5, // 1EEA5..1EEA9; ARABIC
7170 0x1EEAA, // 1EEAA ; UNKNOWN
7171 0x1EEAB, // 1EEAB..1EEBB; ARABIC
7172 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
7173 0x1EEF0, // 1EEF0..1EEF1; ARABIC
7174 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
7175 0x1F000, // 1F000..1F02B; COMMON
7176 0x1F02C, // 1F02C..1F02F; UNKNOWN
7177 0x1F030, // 1F030..1F093; COMMON
7178 0x1F094, // 1F094..1F09F; UNKNOWN
7179 0x1F0A0, // 1F0A0..1F0AE; COMMON
7180 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
7181 0x1F0B1, // 1F0B1..1F0BF; COMMON
7182 0x1F0C0, // 1F0C0 ; UNKNOWN
7183 0x1F0C1, // 1F0C1..1F0CF; COMMON
7184 0x1F0D0, // 1F0D0 ; UNKNOWN
7185 0x1F0D1, // 1F0D1..1F0F5; COMMON
7186 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
7187 0x1F100, // 1F100..1F1AD; COMMON
7188 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
7189 0x1F1E6, // 1F1E6..1F1FF; COMMON
7190 0x1F200, // 1F200 ; HIRAGANA
7191 0x1F201, // 1F201..1F202; COMMON
7192 0x1F203, // 1F203..1F20F; UNKNOWN
7193 0x1F210, // 1F210..1F23B; COMMON
7194 0x1F23C, // 1F23C..1F23F; UNKNOWN
7195 0x1F240, // 1F240..1F248; COMMON
7196 0x1F249, // 1F249..1F24F; UNKNOWN
7197 0x1F250, // 1F250..1F251; COMMON
7198 0x1F252, // 1F252..1F25F; UNKNOWN
7199 0x1F260, // 1F260..1F265; COMMON
7200 0x1F266, // 1F266..1F2FF; UNKNOWN
7201 0x1F300, // 1F300..1F6D7; COMMON
7202 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN
7203 0x1F6DC, // 1F6DC..1F6EC; COMMON
7204 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
7205 0x1F6F0, // 1F6F0..1F6FC; COMMON
7206 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
7207 0x1F700, // 1F700..1F776; COMMON
7208 0x1F777, // 1F777..1F77A; UNKNOWN
7209 0x1F77B, // 1F77B..1F7D9; COMMON
7210 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
7211 0x1F7E0, // 1F7E0..1F7EB; COMMON
7212 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
7213 0x1F7F0, // 1F7F0 ; COMMON
7214 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7215 0x1F800, // 1F800..1F80B; COMMON
7216 0x1F80C, // 1F80C..1F80F; UNKNOWN
7217 0x1F810, // 1F810..1F847; COMMON
7218 0x1F848, // 1F848..1F84F; UNKNOWN
7219 0x1F850, // 1F850..1F859; COMMON
7220 0x1F85A, // 1F85A..1F85F; UNKNOWN
7221 0x1F860, // 1F860..1F887; COMMON
7222 0x1F888, // 1F888..1F88F; UNKNOWN
7223 0x1F890, // 1F890..1F8AD; COMMON
7224 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7225 0x1F8B0, // 1F8B0..1F8BB; COMMON
7226 0x1F8BC, // 1F8BC..1F8BF; UNKNOWN
7227 0x1F8C0, // 1F8C0..1F8C1; COMMON
7228 0x1F8C2, // 1F8C2..1F8FF; UNKNOWN
7229 0x1F900, // 1F900..1FA53; COMMON
7230 0x1FA54, // 1FA54..1FA5F; UNKNOWN
7231 0x1FA60, // 1FA60..1FA6D; COMMON
7232 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7233 0x1FA70, // 1FA70..1FA7C; COMMON
7234 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7235 0x1FA80, // 1FA80..1FA89; COMMON
7236 0x1FA8A, // 1FA8A..1FA8E; UNKNOWN
7237 0x1FA8F, // 1FA8F..1FAC6; COMMON
7238 0x1FAC7, // 1FAC7..1FACD; UNKNOWN
7239 0x1FACE, // 1FACE..1FADC; COMMON
7240 0x1FADD, // 1FADD..1FADE; UNKNOWN
7241 0x1FADF, // 1FADF..1FAE9; COMMON
7242 0x1FAEA, // 1FAEA..1FAEF; UNKNOWN
7243 0x1FAF0, // 1FAF0..1FAF8; COMMON
7244 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7245 0x1FB00, // 1FB00..1FB92; COMMON
7246 0x1FB93, // 1FB93 ; UNKNOWN
7247 0x1FB94, // 1FB94..1FBF9; COMMON
7248 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN
7249 0x20000, // 20000..2A6DF; HAN
7250 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7251 0x2A700, // 2A700..2B739; HAN
7252 0x2B73A, // 2B73A..2B73F; UNKNOWN
7253 0x2B740, // 2B740..2B81D; HAN
7254 0x2B81E, // 2B81E..2B81F; UNKNOWN
7255 0x2B820, // 2B820..2CEA1; HAN
7256 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
7257 0x2CEB0, // 2CEB0..2EBE0; HAN
7258 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7259 0x2EBF0, // 2EBF0..2EE5D; HAN
7260 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7261 0x2F800, // 2F800..2FA1D; HAN
7262 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7263 0x30000, // 30000..3134A; HAN
7264 0x3134B, // 3134B..3134F; UNKNOWN
7265 0x31350, // 31350..323AF; HAN
7266 0x323B0, // 323B0..E0000; UNKNOWN
7267 0xE0001, // E0001 ; COMMON
7268 0xE0002, // E0002..E001F; UNKNOWN
7269 0xE0020, // E0020..E007F; COMMON
7270 0xE0080, // E0080..E00FF; UNKNOWN
7271 0xE0100, // E0100..E01EF; INHERITED
7272 0xE01F0, // E01F0..10FFFF; UNKNOWN
7273 };
7274
7275 private static final UnicodeScript[] scripts = {
7276 COMMON, // 0000..0040
7277 LATIN, // 0041..005A
7278 COMMON, // 005B..0060
7279 LATIN, // 0061..007A
7280 COMMON, // 007B..00A9
7281 LATIN, // 00AA
7282 COMMON, // 00AB..00B9
7283 LATIN, // 00BA
7284 COMMON, // 00BB..00BF
7285 LATIN, // 00C0..00D6
7286 COMMON, // 00D7
7287 LATIN, // 00D8..00F6
7288 COMMON, // 00F7
7289 LATIN, // 00F8..02B8
7290 COMMON, // 02B9..02DF
7291 LATIN, // 02E0..02E4
7292 COMMON, // 02E5..02E9
7293 BOPOMOFO, // 02EA..02EB
7294 COMMON, // 02EC..02FF
7295 INHERITED, // 0300..036F
7296 GREEK, // 0370..0373
7297 COMMON, // 0374
7298 GREEK, // 0375..0377
7299 UNKNOWN, // 0378..0379
7300 GREEK, // 037A..037D
7301 COMMON, // 037E
7302 GREEK, // 037F
7303 UNKNOWN, // 0380..0383
7304 GREEK, // 0384
7305 COMMON, // 0385
7306 GREEK, // 0386
7307 COMMON, // 0387
7308 GREEK, // 0388..038A
7309 UNKNOWN, // 038B
7310 GREEK, // 038C
7311 UNKNOWN, // 038D
7312 GREEK, // 038E..03A1
7313 UNKNOWN, // 03A2
7314 GREEK, // 03A3..03E1
7315 COPTIC, // 03E2..03EF
7316 GREEK, // 03F0..03FF
7317 CYRILLIC, // 0400..0484
7318 INHERITED, // 0485..0486
7319 CYRILLIC, // 0487..052F
7320 UNKNOWN, // 0530
7321 ARMENIAN, // 0531..0556
7322 UNKNOWN, // 0557..0558
7323 ARMENIAN, // 0559..058A
7324 UNKNOWN, // 058B..058C
7325 ARMENIAN, // 058D..058F
7326 UNKNOWN, // 0590
7327 HEBREW, // 0591..05C7
7328 UNKNOWN, // 05C8..05CF
7329 HEBREW, // 05D0..05EA
7330 UNKNOWN, // 05EB..05EE
7331 HEBREW, // 05EF..05F4
7332 UNKNOWN, // 05F5..05FF
7333 ARABIC, // 0600..0604
7334 COMMON, // 0605
7335 ARABIC, // 0606..060B
7336 COMMON, // 060C
7337 ARABIC, // 060D..061A
7338 COMMON, // 061B
7339 ARABIC, // 061C..061E
7340 COMMON, // 061F
7341 ARABIC, // 0620..063F
7342 COMMON, // 0640
7343 ARABIC, // 0641..064A
7344 INHERITED, // 064B..0655
7345 ARABIC, // 0656..066F
7346 INHERITED, // 0670
7347 ARABIC, // 0671..06DC
7348 COMMON, // 06DD
7349 ARABIC, // 06DE..06FF
7350 SYRIAC, // 0700..070D
7351 UNKNOWN, // 070E
7352 SYRIAC, // 070F..074A
7353 UNKNOWN, // 074B..074C
7354 SYRIAC, // 074D..074F
7355 ARABIC, // 0750..077F
7356 THAANA, // 0780..07B1
7357 UNKNOWN, // 07B2..07BF
7358 NKO, // 07C0..07FA
7359 UNKNOWN, // 07FB..07FC
7360 NKO, // 07FD..07FF
7361 SAMARITAN, // 0800..082D
7362 UNKNOWN, // 082E..082F
7363 SAMARITAN, // 0830..083E
7364 UNKNOWN, // 083F
7365 MANDAIC, // 0840..085B
7366 UNKNOWN, // 085C..085D
7367 MANDAIC, // 085E
7368 UNKNOWN, // 085F
7369 SYRIAC, // 0860..086A
7370 UNKNOWN, // 086B..086F
7371 ARABIC, // 0870..088E
7372 UNKNOWN, // 088F
7373 ARABIC, // 0890..0891
7374 UNKNOWN, // 0892..0896
7375 ARABIC, // 0897..08E1
7376 COMMON, // 08E2
7377 ARABIC, // 08E3..08FF
7378 DEVANAGARI, // 0900..0950
7379 INHERITED, // 0951..0954
7380 DEVANAGARI, // 0955..0963
7381 COMMON, // 0964..0965
7382 DEVANAGARI, // 0966..097F
7383 BENGALI, // 0980..0983
7384 UNKNOWN, // 0984
7385 BENGALI, // 0985..098C
7386 UNKNOWN, // 098D..098E
7387 BENGALI, // 098F..0990
7388 UNKNOWN, // 0991..0992
7389 BENGALI, // 0993..09A8
7390 UNKNOWN, // 09A9
7391 BENGALI, // 09AA..09B0
7392 UNKNOWN, // 09B1
7393 BENGALI, // 09B2
7394 UNKNOWN, // 09B3..09B5
7395 BENGALI, // 09B6..09B9
7396 UNKNOWN, // 09BA..09BB
7397 BENGALI, // 09BC..09C4
7398 UNKNOWN, // 09C5..09C6
7399 BENGALI, // 09C7..09C8
7400 UNKNOWN, // 09C9..09CA
7401 BENGALI, // 09CB..09CE
7402 UNKNOWN, // 09CF..09D6
7403 BENGALI, // 09D7
7404 UNKNOWN, // 09D8..09DB
7405 BENGALI, // 09DC..09DD
7406 UNKNOWN, // 09DE
7407 BENGALI, // 09DF..09E3
7408 UNKNOWN, // 09E4..09E5
7409 BENGALI, // 09E6..09FE
7410 UNKNOWN, // 09FF..0A00
7411 GURMUKHI, // 0A01..0A03
7412 UNKNOWN, // 0A04
7413 GURMUKHI, // 0A05..0A0A
7414 UNKNOWN, // 0A0B..0A0E
7415 GURMUKHI, // 0A0F..0A10
7416 UNKNOWN, // 0A11..0A12
7417 GURMUKHI, // 0A13..0A28
7418 UNKNOWN, // 0A29
7419 GURMUKHI, // 0A2A..0A30
7420 UNKNOWN, // 0A31
7421 GURMUKHI, // 0A32..0A33
7422 UNKNOWN, // 0A34
7423 GURMUKHI, // 0A35..0A36
7424 UNKNOWN, // 0A37
7425 GURMUKHI, // 0A38..0A39
7426 UNKNOWN, // 0A3A..0A3B
7427 GURMUKHI, // 0A3C
7428 UNKNOWN, // 0A3D
7429 GURMUKHI, // 0A3E..0A42
7430 UNKNOWN, // 0A43..0A46
7431 GURMUKHI, // 0A47..0A48
7432 UNKNOWN, // 0A49..0A4A
7433 GURMUKHI, // 0A4B..0A4D
7434 UNKNOWN, // 0A4E..0A50
7435 GURMUKHI, // 0A51
7436 UNKNOWN, // 0A52..0A58
7437 GURMUKHI, // 0A59..0A5C
7438 UNKNOWN, // 0A5D
7439 GURMUKHI, // 0A5E
7440 UNKNOWN, // 0A5F..0A65
7441 GURMUKHI, // 0A66..0A76
7442 UNKNOWN, // 0A77..0A80
7443 GUJARATI, // 0A81..0A83
7444 UNKNOWN, // 0A84
7445 GUJARATI, // 0A85..0A8D
7446 UNKNOWN, // 0A8E
7447 GUJARATI, // 0A8F..0A91
7448 UNKNOWN, // 0A92
7449 GUJARATI, // 0A93..0AA8
7450 UNKNOWN, // 0AA9
7451 GUJARATI, // 0AAA..0AB0
7452 UNKNOWN, // 0AB1
7453 GUJARATI, // 0AB2..0AB3
7454 UNKNOWN, // 0AB4
7455 GUJARATI, // 0AB5..0AB9
7456 UNKNOWN, // 0ABA..0ABB
7457 GUJARATI, // 0ABC..0AC5
7458 UNKNOWN, // 0AC6
7459 GUJARATI, // 0AC7..0AC9
7460 UNKNOWN, // 0ACA
7461 GUJARATI, // 0ACB..0ACD
7462 UNKNOWN, // 0ACE..0ACF
7463 GUJARATI, // 0AD0
7464 UNKNOWN, // 0AD1..0ADF
7465 GUJARATI, // 0AE0..0AE3
7466 UNKNOWN, // 0AE4..0AE5
7467 GUJARATI, // 0AE6..0AF1
7468 UNKNOWN, // 0AF2..0AF8
7469 GUJARATI, // 0AF9..0AFF
7470 UNKNOWN, // 0B00
7471 ORIYA, // 0B01..0B03
7472 UNKNOWN, // 0B04
7473 ORIYA, // 0B05..0B0C
7474 UNKNOWN, // 0B0D..0B0E
7475 ORIYA, // 0B0F..0B10
7476 UNKNOWN, // 0B11..0B12
7477 ORIYA, // 0B13..0B28
7478 UNKNOWN, // 0B29
7479 ORIYA, // 0B2A..0B30
7480 UNKNOWN, // 0B31
7481 ORIYA, // 0B32..0B33
7482 UNKNOWN, // 0B34
7483 ORIYA, // 0B35..0B39
7484 UNKNOWN, // 0B3A..0B3B
7485 ORIYA, // 0B3C..0B44
7486 UNKNOWN, // 0B45..0B46
7487 ORIYA, // 0B47..0B48
7488 UNKNOWN, // 0B49..0B4A
7489 ORIYA, // 0B4B..0B4D
7490 UNKNOWN, // 0B4E..0B54
7491 ORIYA, // 0B55..0B57
7492 UNKNOWN, // 0B58..0B5B
7493 ORIYA, // 0B5C..0B5D
7494 UNKNOWN, // 0B5E
7495 ORIYA, // 0B5F..0B63
7496 UNKNOWN, // 0B64..0B65
7497 ORIYA, // 0B66..0B77
7498 UNKNOWN, // 0B78..0B81
7499 TAMIL, // 0B82..0B83
7500 UNKNOWN, // 0B84
7501 TAMIL, // 0B85..0B8A
7502 UNKNOWN, // 0B8B..0B8D
7503 TAMIL, // 0B8E..0B90
7504 UNKNOWN, // 0B91
7505 TAMIL, // 0B92..0B95
7506 UNKNOWN, // 0B96..0B98
7507 TAMIL, // 0B99..0B9A
7508 UNKNOWN, // 0B9B
7509 TAMIL, // 0B9C
7510 UNKNOWN, // 0B9D
7511 TAMIL, // 0B9E..0B9F
7512 UNKNOWN, // 0BA0..0BA2
7513 TAMIL, // 0BA3..0BA4
7514 UNKNOWN, // 0BA5..0BA7
7515 TAMIL, // 0BA8..0BAA
7516 UNKNOWN, // 0BAB..0BAD
7517 TAMIL, // 0BAE..0BB9
7518 UNKNOWN, // 0BBA..0BBD
7519 TAMIL, // 0BBE..0BC2
7520 UNKNOWN, // 0BC3..0BC5
7521 TAMIL, // 0BC6..0BC8
7522 UNKNOWN, // 0BC9
7523 TAMIL, // 0BCA..0BCD
7524 UNKNOWN, // 0BCE..0BCF
7525 TAMIL, // 0BD0
7526 UNKNOWN, // 0BD1..0BD6
7527 TAMIL, // 0BD7
7528 UNKNOWN, // 0BD8..0BE5
7529 TAMIL, // 0BE6..0BFA
7530 UNKNOWN, // 0BFB..0BFF
7531 TELUGU, // 0C00..0C0C
7532 UNKNOWN, // 0C0D
7533 TELUGU, // 0C0E..0C10
7534 UNKNOWN, // 0C11
7535 TELUGU, // 0C12..0C28
7536 UNKNOWN, // 0C29
7537 TELUGU, // 0C2A..0C39
7538 UNKNOWN, // 0C3A..0C3B
7539 TELUGU, // 0C3C..0C44
7540 UNKNOWN, // 0C45
7541 TELUGU, // 0C46..0C48
7542 UNKNOWN, // 0C49
7543 TELUGU, // 0C4A..0C4D
7544 UNKNOWN, // 0C4E..0C54
7545 TELUGU, // 0C55..0C56
7546 UNKNOWN, // 0C57
7547 TELUGU, // 0C58..0C5A
7548 UNKNOWN, // 0C5B..0C5C
7549 TELUGU, // 0C5D
7550 UNKNOWN, // 0C5E..0C5F
7551 TELUGU, // 0C60..0C63
7552 UNKNOWN, // 0C64..0C65
7553 TELUGU, // 0C66..0C6F
7554 UNKNOWN, // 0C70..0C76
7555 TELUGU, // 0C77..0C7F
7556 KANNADA, // 0C80..0C8C
7557 UNKNOWN, // 0C8D
7558 KANNADA, // 0C8E..0C90
7559 UNKNOWN, // 0C91
7560 KANNADA, // 0C92..0CA8
7561 UNKNOWN, // 0CA9
7562 KANNADA, // 0CAA..0CB3
7563 UNKNOWN, // 0CB4
7564 KANNADA, // 0CB5..0CB9
7565 UNKNOWN, // 0CBA..0CBB
7566 KANNADA, // 0CBC..0CC4
7567 UNKNOWN, // 0CC5
7568 KANNADA, // 0CC6..0CC8
7569 UNKNOWN, // 0CC9
7570 KANNADA, // 0CCA..0CCD
7571 UNKNOWN, // 0CCE..0CD4
7572 KANNADA, // 0CD5..0CD6
7573 UNKNOWN, // 0CD7..0CDC
7574 KANNADA, // 0CDD..0CDE
7575 UNKNOWN, // 0CDF
7576 KANNADA, // 0CE0..0CE3
7577 UNKNOWN, // 0CE4..0CE5
7578 KANNADA, // 0CE6..0CEF
7579 UNKNOWN, // 0CF0
7580 KANNADA, // 0CF1..0CF3
7581 UNKNOWN, // 0CF4..0CFF
7582 MALAYALAM, // 0D00..0D0C
7583 UNKNOWN, // 0D0D
7584 MALAYALAM, // 0D0E..0D10
7585 UNKNOWN, // 0D11
7586 MALAYALAM, // 0D12..0D44
7587 UNKNOWN, // 0D45
7588 MALAYALAM, // 0D46..0D48
7589 UNKNOWN, // 0D49
7590 MALAYALAM, // 0D4A..0D4F
7591 UNKNOWN, // 0D50..0D53
7592 MALAYALAM, // 0D54..0D63
7593 UNKNOWN, // 0D64..0D65
7594 MALAYALAM, // 0D66..0D7F
7595 UNKNOWN, // 0D80
7596 SINHALA, // 0D81..0D83
7597 UNKNOWN, // 0D84
7598 SINHALA, // 0D85..0D96
7599 UNKNOWN, // 0D97..0D99
7600 SINHALA, // 0D9A..0DB1
7601 UNKNOWN, // 0DB2
7602 SINHALA, // 0DB3..0DBB
7603 UNKNOWN, // 0DBC
7604 SINHALA, // 0DBD
7605 UNKNOWN, // 0DBE..0DBF
7606 SINHALA, // 0DC0..0DC6
7607 UNKNOWN, // 0DC7..0DC9
7608 SINHALA, // 0DCA
7609 UNKNOWN, // 0DCB..0DCE
7610 SINHALA, // 0DCF..0DD4
7611 UNKNOWN, // 0DD5
7612 SINHALA, // 0DD6
7613 UNKNOWN, // 0DD7
7614 SINHALA, // 0DD8..0DDF
7615 UNKNOWN, // 0DE0..0DE5
7616 SINHALA, // 0DE6..0DEF
7617 UNKNOWN, // 0DF0..0DF1
7618 SINHALA, // 0DF2..0DF4
7619 UNKNOWN, // 0DF5..0E00
7620 THAI, // 0E01..0E3A
7621 UNKNOWN, // 0E3B..0E3E
7622 COMMON, // 0E3F
7623 THAI, // 0E40..0E5B
7624 UNKNOWN, // 0E5C..0E80
7625 LAO, // 0E81..0E82
7626 UNKNOWN, // 0E83
7627 LAO, // 0E84
7628 UNKNOWN, // 0E85
7629 LAO, // 0E86..0E8A
7630 UNKNOWN, // 0E8B
7631 LAO, // 0E8C..0EA3
7632 UNKNOWN, // 0EA4
7633 LAO, // 0EA5
7634 UNKNOWN, // 0EA6
7635 LAO, // 0EA7..0EBD
7636 UNKNOWN, // 0EBE..0EBF
7637 LAO, // 0EC0..0EC4
7638 UNKNOWN, // 0EC5
7639 LAO, // 0EC6
7640 UNKNOWN, // 0EC7
7641 LAO, // 0EC8..0ECE
7642 UNKNOWN, // 0ECF
7643 LAO, // 0ED0..0ED9
7644 UNKNOWN, // 0EDA..0EDB
7645 LAO, // 0EDC..0EDF
7646 UNKNOWN, // 0EE0..0EFF
7647 TIBETAN, // 0F00..0F47
7648 UNKNOWN, // 0F48
7649 TIBETAN, // 0F49..0F6C
7650 UNKNOWN, // 0F6D..0F70
7651 TIBETAN, // 0F71..0F97
7652 UNKNOWN, // 0F98
7653 TIBETAN, // 0F99..0FBC
7654 UNKNOWN, // 0FBD
7655 TIBETAN, // 0FBE..0FCC
7656 UNKNOWN, // 0FCD
7657 TIBETAN, // 0FCE..0FD4
7658 COMMON, // 0FD5..0FD8
7659 TIBETAN, // 0FD9..0FDA
7660 UNKNOWN, // 0FDB..0FFF
7661 MYANMAR, // 1000..109F
7662 GEORGIAN, // 10A0..10C5
7663 UNKNOWN, // 10C6
7664 GEORGIAN, // 10C7
7665 UNKNOWN, // 10C8..10CC
7666 GEORGIAN, // 10CD
7667 UNKNOWN, // 10CE..10CF
7668 GEORGIAN, // 10D0..10FA
7669 COMMON, // 10FB
7670 GEORGIAN, // 10FC..10FF
7671 HANGUL, // 1100..11FF
7672 ETHIOPIC, // 1200..1248
7673 UNKNOWN, // 1249
7674 ETHIOPIC, // 124A..124D
7675 UNKNOWN, // 124E..124F
7676 ETHIOPIC, // 1250..1256
7677 UNKNOWN, // 1257
7678 ETHIOPIC, // 1258
7679 UNKNOWN, // 1259
7680 ETHIOPIC, // 125A..125D
7681 UNKNOWN, // 125E..125F
7682 ETHIOPIC, // 1260..1288
7683 UNKNOWN, // 1289
7684 ETHIOPIC, // 128A..128D
7685 UNKNOWN, // 128E..128F
7686 ETHIOPIC, // 1290..12B0
7687 UNKNOWN, // 12B1
7688 ETHIOPIC, // 12B2..12B5
7689 UNKNOWN, // 12B6..12B7
7690 ETHIOPIC, // 12B8..12BE
7691 UNKNOWN, // 12BF
7692 ETHIOPIC, // 12C0
7693 UNKNOWN, // 12C1
7694 ETHIOPIC, // 12C2..12C5
7695 UNKNOWN, // 12C6..12C7
7696 ETHIOPIC, // 12C8..12D6
7697 UNKNOWN, // 12D7
7698 ETHIOPIC, // 12D8..1310
7699 UNKNOWN, // 1311
7700 ETHIOPIC, // 1312..1315
7701 UNKNOWN, // 1316..1317
7702 ETHIOPIC, // 1318..135A
7703 UNKNOWN, // 135B..135C
7704 ETHIOPIC, // 135D..137C
7705 UNKNOWN, // 137D..137F
7706 ETHIOPIC, // 1380..1399
7707 UNKNOWN, // 139A..139F
7708 CHEROKEE, // 13A0..13F5
7709 UNKNOWN, // 13F6..13F7
7710 CHEROKEE, // 13F8..13FD
7711 UNKNOWN, // 13FE..13FF
7712 CANADIAN_ABORIGINAL, // 1400..167F
7713 OGHAM, // 1680..169C
7714 UNKNOWN, // 169D..169F
7715 RUNIC, // 16A0..16EA
7716 COMMON, // 16EB..16ED
7717 RUNIC, // 16EE..16F8
7718 UNKNOWN, // 16F9..16FF
7719 TAGALOG, // 1700..1715
7720 UNKNOWN, // 1716..171E
7721 TAGALOG, // 171F
7722 HANUNOO, // 1720..1734
7723 COMMON, // 1735..1736
7724 UNKNOWN, // 1737..173F
7725 BUHID, // 1740..1753
7726 UNKNOWN, // 1754..175F
7727 TAGBANWA, // 1760..176C
7728 UNKNOWN, // 176D
7729 TAGBANWA, // 176E..1770
7730 UNKNOWN, // 1771
7731 TAGBANWA, // 1772..1773
7732 UNKNOWN, // 1774..177F
7733 KHMER, // 1780..17DD
7734 UNKNOWN, // 17DE..17DF
7735 KHMER, // 17E0..17E9
7736 UNKNOWN, // 17EA..17EF
7737 KHMER, // 17F0..17F9
7738 UNKNOWN, // 17FA..17FF
7739 MONGOLIAN, // 1800..1801
7740 COMMON, // 1802..1803
7741 MONGOLIAN, // 1804
7742 COMMON, // 1805
7743 MONGOLIAN, // 1806..1819
7744 UNKNOWN, // 181A..181F
7745 MONGOLIAN, // 1820..1878
7746 UNKNOWN, // 1879..187F
7747 MONGOLIAN, // 1880..18AA
7748 UNKNOWN, // 18AB..18AF
7749 CANADIAN_ABORIGINAL, // 18B0..18F5
7750 UNKNOWN, // 18F6..18FF
7751 LIMBU, // 1900..191E
7752 UNKNOWN, // 191F
7753 LIMBU, // 1920..192B
7754 UNKNOWN, // 192C..192F
7755 LIMBU, // 1930..193B
7756 UNKNOWN, // 193C..193F
7757 LIMBU, // 1940
7758 UNKNOWN, // 1941..1943
7759 LIMBU, // 1944..194F
7760 TAI_LE, // 1950..196D
7761 UNKNOWN, // 196E..196F
7762 TAI_LE, // 1970..1974
7763 UNKNOWN, // 1975..197F
7764 NEW_TAI_LUE, // 1980..19AB
7765 UNKNOWN, // 19AC..19AF
7766 NEW_TAI_LUE, // 19B0..19C9
7767 UNKNOWN, // 19CA..19CF
7768 NEW_TAI_LUE, // 19D0..19DA
7769 UNKNOWN, // 19DB..19DD
7770 NEW_TAI_LUE, // 19DE..19DF
7771 KHMER, // 19E0..19FF
7772 BUGINESE, // 1A00..1A1B
7773 UNKNOWN, // 1A1C..1A1D
7774 BUGINESE, // 1A1E..1A1F
7775 TAI_THAM, // 1A20..1A5E
7776 UNKNOWN, // 1A5F
7777 TAI_THAM, // 1A60..1A7C
7778 UNKNOWN, // 1A7D..1A7E
7779 TAI_THAM, // 1A7F..1A89
7780 UNKNOWN, // 1A8A..1A8F
7781 TAI_THAM, // 1A90..1A99
7782 UNKNOWN, // 1A9A..1A9F
7783 TAI_THAM, // 1AA0..1AAD
7784 UNKNOWN, // 1AAE..1AAF
7785 INHERITED, // 1AB0..1ACE
7786 UNKNOWN, // 1ACF..1AFF
7787 BALINESE, // 1B00..1B4C
7788 UNKNOWN, // 1B4D
7789 BALINESE, // 1B4E..1B7F
7790 SUNDANESE, // 1B80..1BBF
7791 BATAK, // 1BC0..1BF3
7792 UNKNOWN, // 1BF4..1BFB
7793 BATAK, // 1BFC..1BFF
7794 LEPCHA, // 1C00..1C37
7795 UNKNOWN, // 1C38..1C3A
7796 LEPCHA, // 1C3B..1C49
7797 UNKNOWN, // 1C4A..1C4C
7798 LEPCHA, // 1C4D..1C4F
7799 OL_CHIKI, // 1C50..1C7F
7800 CYRILLIC, // 1C80..1C8A
7801 UNKNOWN, // 1C8B..1C8F
7802 GEORGIAN, // 1C90..1CBA
7803 UNKNOWN, // 1CBB..1CBC
7804 GEORGIAN, // 1CBD..1CBF
7805 SUNDANESE, // 1CC0..1CC7
7806 UNKNOWN, // 1CC8..1CCF
7807 INHERITED, // 1CD0..1CD2
7808 COMMON, // 1CD3
7809 INHERITED, // 1CD4..1CE0
7810 COMMON, // 1CE1
7811 INHERITED, // 1CE2..1CE8
7812 COMMON, // 1CE9..1CEC
7813 INHERITED, // 1CED
7814 COMMON, // 1CEE..1CF3
7815 INHERITED, // 1CF4
7816 COMMON, // 1CF5..1CF7
7817 INHERITED, // 1CF8..1CF9
7818 COMMON, // 1CFA
7819 UNKNOWN, // 1CFB..1CFF
7820 LATIN, // 1D00..1D25
7821 GREEK, // 1D26..1D2A
7822 CYRILLIC, // 1D2B
7823 LATIN, // 1D2C..1D5C
7824 GREEK, // 1D5D..1D61
7825 LATIN, // 1D62..1D65
7826 GREEK, // 1D66..1D6A
7827 LATIN, // 1D6B..1D77
7828 CYRILLIC, // 1D78
7829 LATIN, // 1D79..1DBE
7830 GREEK, // 1DBF
7831 INHERITED, // 1DC0..1DFF
7832 LATIN, // 1E00..1EFF
7833 GREEK, // 1F00..1F15
7834 UNKNOWN, // 1F16..1F17
7835 GREEK, // 1F18..1F1D
7836 UNKNOWN, // 1F1E..1F1F
7837 GREEK, // 1F20..1F45
7838 UNKNOWN, // 1F46..1F47
7839 GREEK, // 1F48..1F4D
7840 UNKNOWN, // 1F4E..1F4F
7841 GREEK, // 1F50..1F57
7842 UNKNOWN, // 1F58
7843 GREEK, // 1F59
7844 UNKNOWN, // 1F5A
7845 GREEK, // 1F5B
7846 UNKNOWN, // 1F5C
7847 GREEK, // 1F5D
7848 UNKNOWN, // 1F5E
7849 GREEK, // 1F5F..1F7D
7850 UNKNOWN, // 1F7E..1F7F
7851 GREEK, // 1F80..1FB4
7852 UNKNOWN, // 1FB5
7853 GREEK, // 1FB6..1FC4
7854 UNKNOWN, // 1FC5
7855 GREEK, // 1FC6..1FD3
7856 UNKNOWN, // 1FD4..1FD5
7857 GREEK, // 1FD6..1FDB
7858 UNKNOWN, // 1FDC
7859 GREEK, // 1FDD..1FEF
7860 UNKNOWN, // 1FF0..1FF1
7861 GREEK, // 1FF2..1FF4
7862 UNKNOWN, // 1FF5
7863 GREEK, // 1FF6..1FFE
7864 UNKNOWN, // 1FFF
7865 COMMON, // 2000..200B
7866 INHERITED, // 200C..200D
7867 COMMON, // 200E..2064
7868 UNKNOWN, // 2065
7869 COMMON, // 2066..2070
7870 LATIN, // 2071
7871 UNKNOWN, // 2072..2073
7872 COMMON, // 2074..207E
7873 LATIN, // 207F
7874 COMMON, // 2080..208E
7875 UNKNOWN, // 208F
7876 LATIN, // 2090..209C
7877 UNKNOWN, // 209D..209F
7878 COMMON, // 20A0..20C0
7879 UNKNOWN, // 20C1..20CF
7880 INHERITED, // 20D0..20F0
7881 UNKNOWN, // 20F1..20FF
7882 COMMON, // 2100..2125
7883 GREEK, // 2126
7884 COMMON, // 2127..2129
7885 LATIN, // 212A..212B
7886 COMMON, // 212C..2131
7887 LATIN, // 2132
7888 COMMON, // 2133..214D
7889 LATIN, // 214E
7890 COMMON, // 214F..215F
7891 LATIN, // 2160..2188
7892 COMMON, // 2189..218B
7893 UNKNOWN, // 218C..218F
7894 COMMON, // 2190..2429
7895 UNKNOWN, // 242A..243F
7896 COMMON, // 2440..244A
7897 UNKNOWN, // 244B..245F
7898 COMMON, // 2460..27FF
7899 BRAILLE, // 2800..28FF
7900 COMMON, // 2900..2B73
7901 UNKNOWN, // 2B74..2B75
7902 COMMON, // 2B76..2B95
7903 UNKNOWN, // 2B96
7904 COMMON, // 2B97..2BFF
7905 GLAGOLITIC, // 2C00..2C5F
7906 LATIN, // 2C60..2C7F
7907 COPTIC, // 2C80..2CF3
7908 UNKNOWN, // 2CF4..2CF8
7909 COPTIC, // 2CF9..2CFF
7910 GEORGIAN, // 2D00..2D25
7911 UNKNOWN, // 2D26
7912 GEORGIAN, // 2D27
7913 UNKNOWN, // 2D28..2D2C
7914 GEORGIAN, // 2D2D
7915 UNKNOWN, // 2D2E..2D2F
7916 TIFINAGH, // 2D30..2D67
7917 UNKNOWN, // 2D68..2D6E
7918 TIFINAGH, // 2D6F..2D70
7919 UNKNOWN, // 2D71..2D7E
7920 TIFINAGH, // 2D7F
7921 ETHIOPIC, // 2D80..2D96
7922 UNKNOWN, // 2D97..2D9F
7923 ETHIOPIC, // 2DA0..2DA6
7924 UNKNOWN, // 2DA7
7925 ETHIOPIC, // 2DA8..2DAE
7926 UNKNOWN, // 2DAF
7927 ETHIOPIC, // 2DB0..2DB6
7928 UNKNOWN, // 2DB7
7929 ETHIOPIC, // 2DB8..2DBE
7930 UNKNOWN, // 2DBF
7931 ETHIOPIC, // 2DC0..2DC6
7932 UNKNOWN, // 2DC7
7933 ETHIOPIC, // 2DC8..2DCE
7934 UNKNOWN, // 2DCF
7935 ETHIOPIC, // 2DD0..2DD6
7936 UNKNOWN, // 2DD7
7937 ETHIOPIC, // 2DD8..2DDE
7938 UNKNOWN, // 2DDF
7939 CYRILLIC, // 2DE0..2DFF
7940 COMMON, // 2E00..2E5D
7941 UNKNOWN, // 2E5E..2E7F
7942 HAN, // 2E80..2E99
7943 UNKNOWN, // 2E9A
7944 HAN, // 2E9B..2EF3
7945 UNKNOWN, // 2EF4..2EFF
7946 HAN, // 2F00..2FD5
7947 UNKNOWN, // 2FD6..2FEF
7948 COMMON, // 2FF0..3004
7949 HAN, // 3005
7950 COMMON, // 3006
7951 HAN, // 3007
7952 COMMON, // 3008..3020
7953 HAN, // 3021..3029
7954 INHERITED, // 302A..302D
7955 HANGUL, // 302E..302F
7956 COMMON, // 3030..3037
7957 HAN, // 3038..303B
7958 COMMON, // 303C..303F
7959 UNKNOWN, // 3040
7960 HIRAGANA, // 3041..3096
7961 UNKNOWN, // 3097..3098
7962 INHERITED, // 3099..309A
7963 COMMON, // 309B..309C
7964 HIRAGANA, // 309D..309F
7965 COMMON, // 30A0
7966 KATAKANA, // 30A1..30FA
7967 COMMON, // 30FB..30FC
7968 KATAKANA, // 30FD..30FF
7969 UNKNOWN, // 3100..3104
7970 BOPOMOFO, // 3105..312F
7971 UNKNOWN, // 3130
7972 HANGUL, // 3131..318E
7973 UNKNOWN, // 318F
7974 COMMON, // 3190..319F
7975 BOPOMOFO, // 31A0..31BF
7976 COMMON, // 31C0..31E5
7977 UNKNOWN, // 31E6..31EE
7978 COMMON, // 31EF
7979 KATAKANA, // 31F0..31FF
7980 HANGUL, // 3200..321E
7981 UNKNOWN, // 321F
7982 COMMON, // 3220..325F
7983 HANGUL, // 3260..327E
7984 COMMON, // 327F..32CF
7985 KATAKANA, // 32D0..32FE
7986 COMMON, // 32FF
7987 KATAKANA, // 3300..3357
7988 COMMON, // 3358..33FF
7989 HAN, // 3400..4DBF
7990 COMMON, // 4DC0..4DFF
7991 HAN, // 4E00..9FFF
7992 YI, // A000..A48C
7993 UNKNOWN, // A48D..A48F
7994 YI, // A490..A4C6
7995 UNKNOWN, // A4C7..A4CF
7996 LISU, // A4D0..A4FF
7997 VAI, // A500..A62B
7998 UNKNOWN, // A62C..A63F
7999 CYRILLIC, // A640..A69F
8000 BAMUM, // A6A0..A6F7
8001 UNKNOWN, // A6F8..A6FF
8002 COMMON, // A700..A721
8003 LATIN, // A722..A787
8004 COMMON, // A788..A78A
8005 LATIN, // A78B..A7CD
8006 UNKNOWN, // A7CE..A7CF
8007 LATIN, // A7D0..A7D1
8008 UNKNOWN, // A7D2
8009 LATIN, // A7D3
8010 UNKNOWN, // A7D4
8011 LATIN, // A7D5..A7DC
8012 UNKNOWN, // A7DD..A7F1
8013 LATIN, // A7F2..A7FF
8014 SYLOTI_NAGRI, // A800..A82C
8015 UNKNOWN, // A82D..A82F
8016 COMMON, // A830..A839
8017 UNKNOWN, // A83A..A83F
8018 PHAGS_PA, // A840..A877
8019 UNKNOWN, // A878..A87F
8020 SAURASHTRA, // A880..A8C5
8021 UNKNOWN, // A8C6..A8CD
8022 SAURASHTRA, // A8CE..A8D9
8023 UNKNOWN, // A8DA..A8DF
8024 DEVANAGARI, // A8E0..A8FF
8025 KAYAH_LI, // A900..A92D
8026 COMMON, // A92E
8027 KAYAH_LI, // A92F
8028 REJANG, // A930..A953
8029 UNKNOWN, // A954..A95E
8030 REJANG, // A95F
8031 HANGUL, // A960..A97C
8032 UNKNOWN, // A97D..A97F
8033 JAVANESE, // A980..A9CD
8034 UNKNOWN, // A9CE
8035 COMMON, // A9CF
8036 JAVANESE, // A9D0..A9D9
8037 UNKNOWN, // A9DA..A9DD
8038 JAVANESE, // A9DE..A9DF
8039 MYANMAR, // A9E0..A9FE
8040 UNKNOWN, // A9FF
8041 CHAM, // AA00..AA36
8042 UNKNOWN, // AA37..AA3F
8043 CHAM, // AA40..AA4D
8044 UNKNOWN, // AA4E..AA4F
8045 CHAM, // AA50..AA59
8046 UNKNOWN, // AA5A..AA5B
8047 CHAM, // AA5C..AA5F
8048 MYANMAR, // AA60..AA7F
8049 TAI_VIET, // AA80..AAC2
8050 UNKNOWN, // AAC3..AADA
8051 TAI_VIET, // AADB..AADF
8052 MEETEI_MAYEK, // AAE0..AAF6
8053 UNKNOWN, // AAF7..AB00
8054 ETHIOPIC, // AB01..AB06
8055 UNKNOWN, // AB07..AB08
8056 ETHIOPIC, // AB09..AB0E
8057 UNKNOWN, // AB0F..AB10
8058 ETHIOPIC, // AB11..AB16
8059 UNKNOWN, // AB17..AB1F
8060 ETHIOPIC, // AB20..AB26
8061 UNKNOWN, // AB27
8062 ETHIOPIC, // AB28..AB2E
8063 UNKNOWN, // AB2F
8064 LATIN, // AB30..AB5A
8065 COMMON, // AB5B
8066 LATIN, // AB5C..AB64
8067 GREEK, // AB65
8068 LATIN, // AB66..AB69
8069 COMMON, // AB6A..AB6B
8070 UNKNOWN, // AB6C..AB6F
8071 CHEROKEE, // AB70..ABBF
8072 MEETEI_MAYEK, // ABC0..ABED
8073 UNKNOWN, // ABEE..ABEF
8074 MEETEI_MAYEK, // ABF0..ABF9
8075 UNKNOWN, // ABFA..ABFF
8076 HANGUL, // AC00..D7A3
8077 UNKNOWN, // D7A4..D7AF
8078 HANGUL, // D7B0..D7C6
8079 UNKNOWN, // D7C7..D7CA
8080 HANGUL, // D7CB..D7FB
8081 UNKNOWN, // D7FC..F8FF
8082 HAN, // F900..FA6D
8083 UNKNOWN, // FA6E..FA6F
8084 HAN, // FA70..FAD9
8085 UNKNOWN, // FADA..FAFF
8086 LATIN, // FB00..FB06
8087 UNKNOWN, // FB07..FB12
8088 ARMENIAN, // FB13..FB17
8089 UNKNOWN, // FB18..FB1C
8090 HEBREW, // FB1D..FB36
8091 UNKNOWN, // FB37
8092 HEBREW, // FB38..FB3C
8093 UNKNOWN, // FB3D
8094 HEBREW, // FB3E
8095 UNKNOWN, // FB3F
8096 HEBREW, // FB40..FB41
8097 UNKNOWN, // FB42
8098 HEBREW, // FB43..FB44
8099 UNKNOWN, // FB45
8100 HEBREW, // FB46..FB4F
8101 ARABIC, // FB50..FBC2
8102 UNKNOWN, // FBC3..FBD2
8103 ARABIC, // FBD3..FD3D
8104 COMMON, // FD3E..FD3F
8105 ARABIC, // FD40..FD8F
8106 UNKNOWN, // FD90..FD91
8107 ARABIC, // FD92..FDC7
8108 UNKNOWN, // FDC8..FDCE
8109 ARABIC, // FDCF
8110 UNKNOWN, // FDD0..FDEF
8111 ARABIC, // FDF0..FDFF
8112 INHERITED, // FE00..FE0F
8113 COMMON, // FE10..FE19
8114 UNKNOWN, // FE1A..FE1F
8115 INHERITED, // FE20..FE2D
8116 CYRILLIC, // FE2E..FE2F
8117 COMMON, // FE30..FE52
8118 UNKNOWN, // FE53
8119 COMMON, // FE54..FE66
8120 UNKNOWN, // FE67
8121 COMMON, // FE68..FE6B
8122 UNKNOWN, // FE6C..FE6F
8123 ARABIC, // FE70..FE74
8124 UNKNOWN, // FE75
8125 ARABIC, // FE76..FEFC
8126 UNKNOWN, // FEFD..FEFE
8127 COMMON, // FEFF
8128 UNKNOWN, // FF00
8129 COMMON, // FF01..FF20
8130 LATIN, // FF21..FF3A
8131 COMMON, // FF3B..FF40
8132 LATIN, // FF41..FF5A
8133 COMMON, // FF5B..FF65
8134 KATAKANA, // FF66..FF6F
8135 COMMON, // FF70
8136 KATAKANA, // FF71..FF9D
8137 COMMON, // FF9E..FF9F
8138 HANGUL, // FFA0..FFBE
8139 UNKNOWN, // FFBF..FFC1
8140 HANGUL, // FFC2..FFC7
8141 UNKNOWN, // FFC8..FFC9
8142 HANGUL, // FFCA..FFCF
8143 UNKNOWN, // FFD0..FFD1
8144 HANGUL, // FFD2..FFD7
8145 UNKNOWN, // FFD8..FFD9
8146 HANGUL, // FFDA..FFDC
8147 UNKNOWN, // FFDD..FFDF
8148 COMMON, // FFE0..FFE6
8149 UNKNOWN, // FFE7
8150 COMMON, // FFE8..FFEE
8151 UNKNOWN, // FFEF..FFF8
8152 COMMON, // FFF9..FFFD
8153 UNKNOWN, // FFFE..FFFF
8154 LINEAR_B, // 10000..1000B
8155 UNKNOWN, // 1000C
8156 LINEAR_B, // 1000D..10026
8157 UNKNOWN, // 10027
8158 LINEAR_B, // 10028..1003A
8159 UNKNOWN, // 1003B
8160 LINEAR_B, // 1003C..1003D
8161 UNKNOWN, // 1003E
8162 LINEAR_B, // 1003F..1004D
8163 UNKNOWN, // 1004E..1004F
8164 LINEAR_B, // 10050..1005D
8165 UNKNOWN, // 1005E..1007F
8166 LINEAR_B, // 10080..100FA
8167 UNKNOWN, // 100FB..100FF
8168 COMMON, // 10100..10102
8169 UNKNOWN, // 10103..10106
8170 COMMON, // 10107..10133
8171 UNKNOWN, // 10134..10136
8172 COMMON, // 10137..1013F
8173 GREEK, // 10140..1018E
8174 UNKNOWN, // 1018F
8175 COMMON, // 10190..1019C
8176 UNKNOWN, // 1019D..1019F
8177 GREEK, // 101A0
8178 UNKNOWN, // 101A1..101CF
8179 COMMON, // 101D0..101FC
8180 INHERITED, // 101FD
8181 UNKNOWN, // 101FE..1027F
8182 LYCIAN, // 10280..1029C
8183 UNKNOWN, // 1029D..1029F
8184 CARIAN, // 102A0..102D0
8185 UNKNOWN, // 102D1..102DF
8186 INHERITED, // 102E0
8187 COMMON, // 102E1..102FB
8188 UNKNOWN, // 102FC..102FF
8189 OLD_ITALIC, // 10300..10323
8190 UNKNOWN, // 10324..1032C
8191 OLD_ITALIC, // 1032D..1032F
8192 GOTHIC, // 10330..1034A
8193 UNKNOWN, // 1034B..1034F
8194 OLD_PERMIC, // 10350..1037A
8195 UNKNOWN, // 1037B..1037F
8196 UGARITIC, // 10380..1039D
8197 UNKNOWN, // 1039E
8198 UGARITIC, // 1039F
8199 OLD_PERSIAN, // 103A0..103C3
8200 UNKNOWN, // 103C4..103C7
8201 OLD_PERSIAN, // 103C8..103D5
8202 UNKNOWN, // 103D6..103FF
8203 DESERET, // 10400..1044F
8204 SHAVIAN, // 10450..1047F
8205 OSMANYA, // 10480..1049D
8206 UNKNOWN, // 1049E..1049F
8207 OSMANYA, // 104A0..104A9
8208 UNKNOWN, // 104AA..104AF
8209 OSAGE, // 104B0..104D3
8210 UNKNOWN, // 104D4..104D7
8211 OSAGE, // 104D8..104FB
8212 UNKNOWN, // 104FC..104FF
8213 ELBASAN, // 10500..10527
8214 UNKNOWN, // 10528..1052F
8215 CAUCASIAN_ALBANIAN, // 10530..10563
8216 UNKNOWN, // 10564..1056E
8217 CAUCASIAN_ALBANIAN, // 1056F
8218 VITHKUQI, // 10570..1057A
8219 UNKNOWN, // 1057B
8220 VITHKUQI, // 1057C..1058A
8221 UNKNOWN, // 1058B
8222 VITHKUQI, // 1058C..10592
8223 UNKNOWN, // 10593
8224 VITHKUQI, // 10594..10595
8225 UNKNOWN, // 10596
8226 VITHKUQI, // 10597..105A1
8227 UNKNOWN, // 105A2
8228 VITHKUQI, // 105A3..105B1
8229 UNKNOWN, // 105B2
8230 VITHKUQI, // 105B3..105B9
8231 UNKNOWN, // 105BA
8232 VITHKUQI, // 105BB..105BC
8233 UNKNOWN, // 105BD..105BF
8234 TODHRI, // 105C0..105F3
8235 UNKNOWN, // 105F4..105FF
8236 LINEAR_A, // 10600..10736
8237 UNKNOWN, // 10737..1073F
8238 LINEAR_A, // 10740..10755
8239 UNKNOWN, // 10756..1075F
8240 LINEAR_A, // 10760..10767
8241 UNKNOWN, // 10768..1077F
8242 LATIN, // 10780..10785
8243 UNKNOWN, // 10786
8244 LATIN, // 10787..107B0
8245 UNKNOWN, // 107B1
8246 LATIN, // 107B2..107BA
8247 UNKNOWN, // 107BB..107FF
8248 CYPRIOT, // 10800..10805
8249 UNKNOWN, // 10806..10807
8250 CYPRIOT, // 10808
8251 UNKNOWN, // 10809
8252 CYPRIOT, // 1080A..10835
8253 UNKNOWN, // 10836
8254 CYPRIOT, // 10837..10838
8255 UNKNOWN, // 10839..1083B
8256 CYPRIOT, // 1083C
8257 UNKNOWN, // 1083D..1083E
8258 CYPRIOT, // 1083F
8259 IMPERIAL_ARAMAIC, // 10840..10855
8260 UNKNOWN, // 10856
8261 IMPERIAL_ARAMAIC, // 10857..1085F
8262 PALMYRENE, // 10860..1087F
8263 NABATAEAN, // 10880..1089E
8264 UNKNOWN, // 1089F..108A6
8265 NABATAEAN, // 108A7..108AF
8266 UNKNOWN, // 108B0..108DF
8267 HATRAN, // 108E0..108F2
8268 UNKNOWN, // 108F3
8269 HATRAN, // 108F4..108F5
8270 UNKNOWN, // 108F6..108FA
8271 HATRAN, // 108FB..108FF
8272 PHOENICIAN, // 10900..1091B
8273 UNKNOWN, // 1091C..1091E
8274 PHOENICIAN, // 1091F
8275 LYDIAN, // 10920..10939
8276 UNKNOWN, // 1093A..1093E
8277 LYDIAN, // 1093F
8278 UNKNOWN, // 10940..1097F
8279 MEROITIC_HIEROGLYPHS, // 10980..1099F
8280 MEROITIC_CURSIVE, // 109A0..109B7
8281 UNKNOWN, // 109B8..109BB
8282 MEROITIC_CURSIVE, // 109BC..109CF
8283 UNKNOWN, // 109D0..109D1
8284 MEROITIC_CURSIVE, // 109D2..109FF
8285 KHAROSHTHI, // 10A00..10A03
8286 UNKNOWN, // 10A04
8287 KHAROSHTHI, // 10A05..10A06
8288 UNKNOWN, // 10A07..10A0B
8289 KHAROSHTHI, // 10A0C..10A13
8290 UNKNOWN, // 10A14
8291 KHAROSHTHI, // 10A15..10A17
8292 UNKNOWN, // 10A18
8293 KHAROSHTHI, // 10A19..10A35
8294 UNKNOWN, // 10A36..10A37
8295 KHAROSHTHI, // 10A38..10A3A
8296 UNKNOWN, // 10A3B..10A3E
8297 KHAROSHTHI, // 10A3F..10A48
8298 UNKNOWN, // 10A49..10A4F
8299 KHAROSHTHI, // 10A50..10A58
8300 UNKNOWN, // 10A59..10A5F
8301 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8302 OLD_NORTH_ARABIAN, // 10A80..10A9F
8303 UNKNOWN, // 10AA0..10ABF
8304 MANICHAEAN, // 10AC0..10AE6
8305 UNKNOWN, // 10AE7..10AEA
8306 MANICHAEAN, // 10AEB..10AF6
8307 UNKNOWN, // 10AF7..10AFF
8308 AVESTAN, // 10B00..10B35
8309 UNKNOWN, // 10B36..10B38
8310 AVESTAN, // 10B39..10B3F
8311 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8312 UNKNOWN, // 10B56..10B57
8313 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8314 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8315 UNKNOWN, // 10B73..10B77
8316 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8317 PSALTER_PAHLAVI, // 10B80..10B91
8318 UNKNOWN, // 10B92..10B98
8319 PSALTER_PAHLAVI, // 10B99..10B9C
8320 UNKNOWN, // 10B9D..10BA8
8321 PSALTER_PAHLAVI, // 10BA9..10BAF
8322 UNKNOWN, // 10BB0..10BFF
8323 OLD_TURKIC, // 10C00..10C48
8324 UNKNOWN, // 10C49..10C7F
8325 OLD_HUNGARIAN, // 10C80..10CB2
8326 UNKNOWN, // 10CB3..10CBF
8327 OLD_HUNGARIAN, // 10CC0..10CF2
8328 UNKNOWN, // 10CF3..10CF9
8329 OLD_HUNGARIAN, // 10CFA..10CFF
8330 HANIFI_ROHINGYA, // 10D00..10D27
8331 UNKNOWN, // 10D28..10D2F
8332 HANIFI_ROHINGYA, // 10D30..10D39
8333 UNKNOWN, // 10D3A..10D3F
8334 GARAY, // 10D40..10D65
8335 UNKNOWN, // 10D66..10D68
8336 GARAY, // 10D69..10D85
8337 UNKNOWN, // 10D86..10D8D
8338 GARAY, // 10D8E..10D8F
8339 UNKNOWN, // 10D90..10E5F
8340 ARABIC, // 10E60..10E7E
8341 UNKNOWN, // 10E7F
8342 YEZIDI, // 10E80..10EA9
8343 UNKNOWN, // 10EAA
8344 YEZIDI, // 10EAB..10EAD
8345 UNKNOWN, // 10EAE..10EAF
8346 YEZIDI, // 10EB0..10EB1
8347 UNKNOWN, // 10EB2..10EC1
8348 ARABIC, // 10EC2..10EC4
8349 UNKNOWN, // 10EC5..10EFB
8350 ARABIC, // 10EFC..10EFF
8351 OLD_SOGDIAN, // 10F00..10F27
8352 UNKNOWN, // 10F28..10F2F
8353 SOGDIAN, // 10F30..10F59
8354 UNKNOWN, // 10F5A..10F6F
8355 OLD_UYGHUR, // 10F70..10F89
8356 UNKNOWN, // 10F8A..10FAF
8357 CHORASMIAN, // 10FB0..10FCB
8358 UNKNOWN, // 10FCC..10FDF
8359 ELYMAIC, // 10FE0..10FF6
8360 UNKNOWN, // 10FF7..10FFF
8361 BRAHMI, // 11000..1104D
8362 UNKNOWN, // 1104E..11051
8363 BRAHMI, // 11052..11075
8364 UNKNOWN, // 11076..1107E
8365 BRAHMI, // 1107F
8366 KAITHI, // 11080..110C2
8367 UNKNOWN, // 110C3..110CC
8368 KAITHI, // 110CD
8369 UNKNOWN, // 110CE..110CF
8370 SORA_SOMPENG, // 110D0..110E8
8371 UNKNOWN, // 110E9..110EF
8372 SORA_SOMPENG, // 110F0..110F9
8373 UNKNOWN, // 110FA..110FF
8374 CHAKMA, // 11100..11134
8375 UNKNOWN, // 11135
8376 CHAKMA, // 11136..11147
8377 UNKNOWN, // 11148..1114F
8378 MAHAJANI, // 11150..11176
8379 UNKNOWN, // 11177..1117F
8380 SHARADA, // 11180..111DF
8381 UNKNOWN, // 111E0
8382 SINHALA, // 111E1..111F4
8383 UNKNOWN, // 111F5..111FF
8384 KHOJKI, // 11200..11211
8385 UNKNOWN, // 11212
8386 KHOJKI, // 11213..11241
8387 UNKNOWN, // 11242..1127F
8388 MULTANI, // 11280..11286
8389 UNKNOWN, // 11287
8390 MULTANI, // 11288
8391 UNKNOWN, // 11289
8392 MULTANI, // 1128A..1128D
8393 UNKNOWN, // 1128E
8394 MULTANI, // 1128F..1129D
8395 UNKNOWN, // 1129E
8396 MULTANI, // 1129F..112A9
8397 UNKNOWN, // 112AA..112AF
8398 KHUDAWADI, // 112B0..112EA
8399 UNKNOWN, // 112EB..112EF
8400 KHUDAWADI, // 112F0..112F9
8401 UNKNOWN, // 112FA..112FF
8402 GRANTHA, // 11300..11303
8403 UNKNOWN, // 11304
8404 GRANTHA, // 11305..1130C
8405 UNKNOWN, // 1130D..1130E
8406 GRANTHA, // 1130F..11310
8407 UNKNOWN, // 11311..11312
8408 GRANTHA, // 11313..11328
8409 UNKNOWN, // 11329
8410 GRANTHA, // 1132A..11330
8411 UNKNOWN, // 11331
8412 GRANTHA, // 11332..11333
8413 UNKNOWN, // 11334
8414 GRANTHA, // 11335..11339
8415 UNKNOWN, // 1133A
8416 INHERITED, // 1133B
8417 GRANTHA, // 1133C..11344
8418 UNKNOWN, // 11345..11346
8419 GRANTHA, // 11347..11348
8420 UNKNOWN, // 11349..1134A
8421 GRANTHA, // 1134B..1134D
8422 UNKNOWN, // 1134E..1134F
8423 GRANTHA, // 11350
8424 UNKNOWN, // 11351..11356
8425 GRANTHA, // 11357
8426 UNKNOWN, // 11358..1135C
8427 GRANTHA, // 1135D..11363
8428 UNKNOWN, // 11364..11365
8429 GRANTHA, // 11366..1136C
8430 UNKNOWN, // 1136D..1136F
8431 GRANTHA, // 11370..11374
8432 UNKNOWN, // 11375..1137F
8433 TULU_TIGALARI, // 11380..11389
8434 UNKNOWN, // 1138A
8435 TULU_TIGALARI, // 1138B
8436 UNKNOWN, // 1138C..1138D
8437 TULU_TIGALARI, // 1138E
8438 UNKNOWN, // 1138F
8439 TULU_TIGALARI, // 11390..113B5
8440 UNKNOWN, // 113B6
8441 TULU_TIGALARI, // 113B7..113C0
8442 UNKNOWN, // 113C1
8443 TULU_TIGALARI, // 113C2
8444 UNKNOWN, // 113C3..113C4
8445 TULU_TIGALARI, // 113C5
8446 UNKNOWN, // 113C6
8447 TULU_TIGALARI, // 113C7..113CA
8448 UNKNOWN, // 113CB
8449 TULU_TIGALARI, // 113CC..113D5
8450 UNKNOWN, // 113D6
8451 TULU_TIGALARI, // 113D7..113D8
8452 UNKNOWN, // 113D9..113E0
8453 TULU_TIGALARI, // 113E1..113E2
8454 UNKNOWN, // 113E3..113FF
8455 NEWA, // 11400..1145B
8456 UNKNOWN, // 1145C
8457 NEWA, // 1145D..11461
8458 UNKNOWN, // 11462..1147F
8459 TIRHUTA, // 11480..114C7
8460 UNKNOWN, // 114C8..114CF
8461 TIRHUTA, // 114D0..114D9
8462 UNKNOWN, // 114DA..1157F
8463 SIDDHAM, // 11580..115B5
8464 UNKNOWN, // 115B6..115B7
8465 SIDDHAM, // 115B8..115DD
8466 UNKNOWN, // 115DE..115FF
8467 MODI, // 11600..11644
8468 UNKNOWN, // 11645..1164F
8469 MODI, // 11650..11659
8470 UNKNOWN, // 1165A..1165F
8471 MONGOLIAN, // 11660..1166C
8472 UNKNOWN, // 1166D..1167F
8473 TAKRI, // 11680..116B9
8474 UNKNOWN, // 116BA..116BF
8475 TAKRI, // 116C0..116C9
8476 UNKNOWN, // 116CA..116CF
8477 MYANMAR, // 116D0..116E3
8478 UNKNOWN, // 116E4..116FF
8479 AHOM, // 11700..1171A
8480 UNKNOWN, // 1171B..1171C
8481 AHOM, // 1171D..1172B
8482 UNKNOWN, // 1172C..1172F
8483 AHOM, // 11730..11746
8484 UNKNOWN, // 11747..117FF
8485 DOGRA, // 11800..1183B
8486 UNKNOWN, // 1183C..1189F
8487 WARANG_CITI, // 118A0..118F2
8488 UNKNOWN, // 118F3..118FE
8489 WARANG_CITI, // 118FF
8490 DIVES_AKURU, // 11900..11906
8491 UNKNOWN, // 11907..11908
8492 DIVES_AKURU, // 11909
8493 UNKNOWN, // 1190A..1190B
8494 DIVES_AKURU, // 1190C..11913
8495 UNKNOWN, // 11914
8496 DIVES_AKURU, // 11915..11916
8497 UNKNOWN, // 11917
8498 DIVES_AKURU, // 11918..11935
8499 UNKNOWN, // 11936
8500 DIVES_AKURU, // 11937..11938
8501 UNKNOWN, // 11939..1193A
8502 DIVES_AKURU, // 1193B..11946
8503 UNKNOWN, // 11947..1194F
8504 DIVES_AKURU, // 11950..11959
8505 UNKNOWN, // 1195A..1199F
8506 NANDINAGARI, // 119A0..119A7
8507 UNKNOWN, // 119A8..119A9
8508 NANDINAGARI, // 119AA..119D7
8509 UNKNOWN, // 119D8..119D9
8510 NANDINAGARI, // 119DA..119E4
8511 UNKNOWN, // 119E5..119FF
8512 ZANABAZAR_SQUARE, // 11A00..11A47
8513 UNKNOWN, // 11A48..11A4F
8514 SOYOMBO, // 11A50..11AA2
8515 UNKNOWN, // 11AA3..11AAF
8516 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8517 PAU_CIN_HAU, // 11AC0..11AF8
8518 UNKNOWN, // 11AF9..11AFF
8519 DEVANAGARI, // 11B00..11B09
8520 UNKNOWN, // 11B0A..11BBF
8521 SUNUWAR, // 11BC0..11BE1
8522 UNKNOWN, // 11BE2..11BEF
8523 SUNUWAR, // 11BF0..11BF9
8524 UNKNOWN, // 11BFA..11BFF
8525 BHAIKSUKI, // 11C00..11C08
8526 UNKNOWN, // 11C09
8527 BHAIKSUKI, // 11C0A..11C36
8528 UNKNOWN, // 11C37
8529 BHAIKSUKI, // 11C38..11C45
8530 UNKNOWN, // 11C46..11C4F
8531 BHAIKSUKI, // 11C50..11C6C
8532 UNKNOWN, // 11C6D..11C6F
8533 MARCHEN, // 11C70..11C8F
8534 UNKNOWN, // 11C90..11C91
8535 MARCHEN, // 11C92..11CA7
8536 UNKNOWN, // 11CA8
8537 MARCHEN, // 11CA9..11CB6
8538 UNKNOWN, // 11CB7..11CFF
8539 MASARAM_GONDI, // 11D00..11D06
8540 UNKNOWN, // 11D07
8541 MASARAM_GONDI, // 11D08..11D09
8542 UNKNOWN, // 11D0A
8543 MASARAM_GONDI, // 11D0B..11D36
8544 UNKNOWN, // 11D37..11D39
8545 MASARAM_GONDI, // 11D3A
8546 UNKNOWN, // 11D3B
8547 MASARAM_GONDI, // 11D3C..11D3D
8548 UNKNOWN, // 11D3E
8549 MASARAM_GONDI, // 11D3F..11D47
8550 UNKNOWN, // 11D48..11D4F
8551 MASARAM_GONDI, // 11D50..11D59
8552 UNKNOWN, // 11D5A..11D5F
8553 GUNJALA_GONDI, // 11D60..11D65
8554 UNKNOWN, // 11D66
8555 GUNJALA_GONDI, // 11D67..11D68
8556 UNKNOWN, // 11D69
8557 GUNJALA_GONDI, // 11D6A..11D8E
8558 UNKNOWN, // 11D8F
8559 GUNJALA_GONDI, // 11D90..11D91
8560 UNKNOWN, // 11D92
8561 GUNJALA_GONDI, // 11D93..11D98
8562 UNKNOWN, // 11D99..11D9F
8563 GUNJALA_GONDI, // 11DA0..11DA9
8564 UNKNOWN, // 11DAA..11EDF
8565 MAKASAR, // 11EE0..11EF8
8566 UNKNOWN, // 11EF9..11EFF
8567 KAWI, // 11F00..11F10
8568 UNKNOWN, // 11F11
8569 KAWI, // 11F12..11F3A
8570 UNKNOWN, // 11F3B..11F3D
8571 KAWI, // 11F3E..11F5A
8572 UNKNOWN, // 11F5B..11FAF
8573 LISU, // 11FB0
8574 UNKNOWN, // 11FB1..11FBF
8575 TAMIL, // 11FC0..11FF1
8576 UNKNOWN, // 11FF2..11FFE
8577 TAMIL, // 11FFF
8578 CUNEIFORM, // 12000..12399
8579 UNKNOWN, // 1239A..123FF
8580 CUNEIFORM, // 12400..1246E
8581 UNKNOWN, // 1246F
8582 CUNEIFORM, // 12470..12474
8583 UNKNOWN, // 12475..1247F
8584 CUNEIFORM, // 12480..12543
8585 UNKNOWN, // 12544..12F8F
8586 CYPRO_MINOAN, // 12F90..12FF2
8587 UNKNOWN, // 12FF3..12FFF
8588 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8589 UNKNOWN, // 13456..1345F
8590 EGYPTIAN_HIEROGLYPHS, // 13460..143FA
8591 UNKNOWN, // 143FB..143FF
8592 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8593 UNKNOWN, // 14647..160FF
8594 GURUNG_KHEMA, // 16100..16139
8595 UNKNOWN, // 1613A..167FF
8596 BAMUM, // 16800..16A38
8597 UNKNOWN, // 16A39..16A3F
8598 MRO, // 16A40..16A5E
8599 UNKNOWN, // 16A5F
8600 MRO, // 16A60..16A69
8601 UNKNOWN, // 16A6A..16A6D
8602 MRO, // 16A6E..16A6F
8603 TANGSA, // 16A70..16ABE
8604 UNKNOWN, // 16ABF
8605 TANGSA, // 16AC0..16AC9
8606 UNKNOWN, // 16ACA..16ACF
8607 BASSA_VAH, // 16AD0..16AED
8608 UNKNOWN, // 16AEE..16AEF
8609 BASSA_VAH, // 16AF0..16AF5
8610 UNKNOWN, // 16AF6..16AFF
8611 PAHAWH_HMONG, // 16B00..16B45
8612 UNKNOWN, // 16B46..16B4F
8613 PAHAWH_HMONG, // 16B50..16B59
8614 UNKNOWN, // 16B5A
8615 PAHAWH_HMONG, // 16B5B..16B61
8616 UNKNOWN, // 16B62
8617 PAHAWH_HMONG, // 16B63..16B77
8618 UNKNOWN, // 16B78..16B7C
8619 PAHAWH_HMONG, // 16B7D..16B8F
8620 UNKNOWN, // 16B90..16D3F
8621 KIRAT_RAI, // 16D40..16D79
8622 UNKNOWN, // 16D7A..16E3F
8623 MEDEFAIDRIN, // 16E40..16E9A
8624 UNKNOWN, // 16E9B..16EFF
8625 MIAO, // 16F00..16F4A
8626 UNKNOWN, // 16F4B..16F4E
8627 MIAO, // 16F4F..16F87
8628 UNKNOWN, // 16F88..16F8E
8629 MIAO, // 16F8F..16F9F
8630 UNKNOWN, // 16FA0..16FDF
8631 TANGUT, // 16FE0
8632 NUSHU, // 16FE1
8633 HAN, // 16FE2..16FE3
8634 KHITAN_SMALL_SCRIPT, // 16FE4
8635 UNKNOWN, // 16FE5..16FEF
8636 HAN, // 16FF0..16FF1
8637 UNKNOWN, // 16FF2..16FFF
8638 TANGUT, // 17000..187F7
8639 UNKNOWN, // 187F8..187FF
8640 TANGUT, // 18800..18AFF
8641 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8642 UNKNOWN, // 18CD6..18CFE
8643 KHITAN_SMALL_SCRIPT, // 18CFF
8644 TANGUT, // 18D00..18D08
8645 UNKNOWN, // 18D09..1AFEF
8646 KATAKANA, // 1AFF0..1AFF3
8647 UNKNOWN, // 1AFF4
8648 KATAKANA, // 1AFF5..1AFFB
8649 UNKNOWN, // 1AFFC
8650 KATAKANA, // 1AFFD..1AFFE
8651 UNKNOWN, // 1AFFF
8652 KATAKANA, // 1B000
8653 HIRAGANA, // 1B001..1B11F
8654 KATAKANA, // 1B120..1B122
8655 UNKNOWN, // 1B123..1B131
8656 HIRAGANA, // 1B132
8657 UNKNOWN, // 1B133..1B14F
8658 HIRAGANA, // 1B150..1B152
8659 UNKNOWN, // 1B153..1B154
8660 KATAKANA, // 1B155
8661 UNKNOWN, // 1B156..1B163
8662 KATAKANA, // 1B164..1B167
8663 UNKNOWN, // 1B168..1B16F
8664 NUSHU, // 1B170..1B2FB
8665 UNKNOWN, // 1B2FC..1BBFF
8666 DUPLOYAN, // 1BC00..1BC6A
8667 UNKNOWN, // 1BC6B..1BC6F
8668 DUPLOYAN, // 1BC70..1BC7C
8669 UNKNOWN, // 1BC7D..1BC7F
8670 DUPLOYAN, // 1BC80..1BC88
8671 UNKNOWN, // 1BC89..1BC8F
8672 DUPLOYAN, // 1BC90..1BC99
8673 UNKNOWN, // 1BC9A..1BC9B
8674 DUPLOYAN, // 1BC9C..1BC9F
8675 COMMON, // 1BCA0..1BCA3
8676 UNKNOWN, // 1BCA4..1CBFF
8677 COMMON, // 1CC00..1CCF9
8678 UNKNOWN, // 1CCFA..1CCFF
8679 COMMON, // 1CD00..1CEB3
8680 UNKNOWN, // 1CEB4..1CEFF
8681 INHERITED, // 1CF00..1CF2D
8682 UNKNOWN, // 1CF2E..1CF2F
8683 INHERITED, // 1CF30..1CF46
8684 UNKNOWN, // 1CF47..1CF4F
8685 COMMON, // 1CF50..1CFC3
8686 UNKNOWN, // 1CFC4..1CFFF
8687 COMMON, // 1D000..1D0F5
8688 UNKNOWN, // 1D0F6..1D0FF
8689 COMMON, // 1D100..1D126
8690 UNKNOWN, // 1D127..1D128
8691 COMMON, // 1D129..1D166
8692 INHERITED, // 1D167..1D169
8693 COMMON, // 1D16A..1D17A
8694 INHERITED, // 1D17B..1D182
8695 COMMON, // 1D183..1D184
8696 INHERITED, // 1D185..1D18B
8697 COMMON, // 1D18C..1D1A9
8698 INHERITED, // 1D1AA..1D1AD
8699 COMMON, // 1D1AE..1D1EA
8700 UNKNOWN, // 1D1EB..1D1FF
8701 GREEK, // 1D200..1D245
8702 UNKNOWN, // 1D246..1D2BF
8703 COMMON, // 1D2C0..1D2D3
8704 UNKNOWN, // 1D2D4..1D2DF
8705 COMMON, // 1D2E0..1D2F3
8706 UNKNOWN, // 1D2F4..1D2FF
8707 COMMON, // 1D300..1D356
8708 UNKNOWN, // 1D357..1D35F
8709 COMMON, // 1D360..1D378
8710 UNKNOWN, // 1D379..1D3FF
8711 COMMON, // 1D400..1D454
8712 UNKNOWN, // 1D455
8713 COMMON, // 1D456..1D49C
8714 UNKNOWN, // 1D49D
8715 COMMON, // 1D49E..1D49F
8716 UNKNOWN, // 1D4A0..1D4A1
8717 COMMON, // 1D4A2
8718 UNKNOWN, // 1D4A3..1D4A4
8719 COMMON, // 1D4A5..1D4A6
8720 UNKNOWN, // 1D4A7..1D4A8
8721 COMMON, // 1D4A9..1D4AC
8722 UNKNOWN, // 1D4AD
8723 COMMON, // 1D4AE..1D4B9
8724 UNKNOWN, // 1D4BA
8725 COMMON, // 1D4BB
8726 UNKNOWN, // 1D4BC
8727 COMMON, // 1D4BD..1D4C3
8728 UNKNOWN, // 1D4C4
8729 COMMON, // 1D4C5..1D505
8730 UNKNOWN, // 1D506
8731 COMMON, // 1D507..1D50A
8732 UNKNOWN, // 1D50B..1D50C
8733 COMMON, // 1D50D..1D514
8734 UNKNOWN, // 1D515
8735 COMMON, // 1D516..1D51C
8736 UNKNOWN, // 1D51D
8737 COMMON, // 1D51E..1D539
8738 UNKNOWN, // 1D53A
8739 COMMON, // 1D53B..1D53E
8740 UNKNOWN, // 1D53F
8741 COMMON, // 1D540..1D544
8742 UNKNOWN, // 1D545
8743 COMMON, // 1D546
8744 UNKNOWN, // 1D547..1D549
8745 COMMON, // 1D54A..1D550
8746 UNKNOWN, // 1D551
8747 COMMON, // 1D552..1D6A5
8748 UNKNOWN, // 1D6A6..1D6A7
8749 COMMON, // 1D6A8..1D7CB
8750 UNKNOWN, // 1D7CC..1D7CD
8751 COMMON, // 1D7CE..1D7FF
8752 SIGNWRITING, // 1D800..1DA8B
8753 UNKNOWN, // 1DA8C..1DA9A
8754 SIGNWRITING, // 1DA9B..1DA9F
8755 UNKNOWN, // 1DAA0
8756 SIGNWRITING, // 1DAA1..1DAAF
8757 UNKNOWN, // 1DAB0..1DEFF
8758 LATIN, // 1DF00..1DF1E
8759 UNKNOWN, // 1DF1F..1DF24
8760 LATIN, // 1DF25..1DF2A
8761 UNKNOWN, // 1DF2B..1DFFF
8762 GLAGOLITIC, // 1E000..1E006
8763 UNKNOWN, // 1E007
8764 GLAGOLITIC, // 1E008..1E018
8765 UNKNOWN, // 1E019..1E01A
8766 GLAGOLITIC, // 1E01B..1E021
8767 UNKNOWN, // 1E022
8768 GLAGOLITIC, // 1E023..1E024
8769 UNKNOWN, // 1E025
8770 GLAGOLITIC, // 1E026..1E02A
8771 UNKNOWN, // 1E02B..1E02F
8772 CYRILLIC, // 1E030..1E06D
8773 UNKNOWN, // 1E06E..1E08E
8774 CYRILLIC, // 1E08F
8775 UNKNOWN, // 1E090..1E0FF
8776 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8777 UNKNOWN, // 1E12D..1E12F
8778 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8779 UNKNOWN, // 1E13E..1E13F
8780 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8781 UNKNOWN, // 1E14A..1E14D
8782 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8783 UNKNOWN, // 1E150..1E28F
8784 TOTO, // 1E290..1E2AE
8785 UNKNOWN, // 1E2AF..1E2BF
8786 WANCHO, // 1E2C0..1E2F9
8787 UNKNOWN, // 1E2FA..1E2FE
8788 WANCHO, // 1E2FF
8789 UNKNOWN, // 1E300..1E4CF
8790 NAG_MUNDARI, // 1E4D0..1E4F9
8791 UNKNOWN, // 1E4FA..1E5CF
8792 OL_ONAL, // 1E5D0..1E5FA
8793 UNKNOWN, // 1E5FB..1E5FE
8794 OL_ONAL, // 1E5FF
8795 UNKNOWN, // 1E600..1E7DF
8796 ETHIOPIC, // 1E7E0..1E7E6
8797 UNKNOWN, // 1E7E7
8798 ETHIOPIC, // 1E7E8..1E7EB
8799 UNKNOWN, // 1E7EC
8800 ETHIOPIC, // 1E7ED..1E7EE
8801 UNKNOWN, // 1E7EF
8802 ETHIOPIC, // 1E7F0..1E7FE
8803 UNKNOWN, // 1E7FF
8804 MENDE_KIKAKUI, // 1E800..1E8C4
8805 UNKNOWN, // 1E8C5..1E8C6
8806 MENDE_KIKAKUI, // 1E8C7..1E8D6
8807 UNKNOWN, // 1E8D7..1E8FF
8808 ADLAM, // 1E900..1E94B
8809 UNKNOWN, // 1E94C..1E94F
8810 ADLAM, // 1E950..1E959
8811 UNKNOWN, // 1E95A..1E95D
8812 ADLAM, // 1E95E..1E95F
8813 UNKNOWN, // 1E960..1EC70
8814 COMMON, // 1EC71..1ECB4
8815 UNKNOWN, // 1ECB5..1ED00
8816 COMMON, // 1ED01..1ED3D
8817 UNKNOWN, // 1ED3E..1EDFF
8818 ARABIC, // 1EE00..1EE03
8819 UNKNOWN, // 1EE04
8820 ARABIC, // 1EE05..1EE1F
8821 UNKNOWN, // 1EE20
8822 ARABIC, // 1EE21..1EE22
8823 UNKNOWN, // 1EE23
8824 ARABIC, // 1EE24
8825 UNKNOWN, // 1EE25..1EE26
8826 ARABIC, // 1EE27
8827 UNKNOWN, // 1EE28
8828 ARABIC, // 1EE29..1EE32
8829 UNKNOWN, // 1EE33
8830 ARABIC, // 1EE34..1EE37
8831 UNKNOWN, // 1EE38
8832 ARABIC, // 1EE39
8833 UNKNOWN, // 1EE3A
8834 ARABIC, // 1EE3B
8835 UNKNOWN, // 1EE3C..1EE41
8836 ARABIC, // 1EE42
8837 UNKNOWN, // 1EE43..1EE46
8838 ARABIC, // 1EE47
8839 UNKNOWN, // 1EE48
8840 ARABIC, // 1EE49
8841 UNKNOWN, // 1EE4A
8842 ARABIC, // 1EE4B
8843 UNKNOWN, // 1EE4C
8844 ARABIC, // 1EE4D..1EE4F
8845 UNKNOWN, // 1EE50
8846 ARABIC, // 1EE51..1EE52
8847 UNKNOWN, // 1EE53
8848 ARABIC, // 1EE54
8849 UNKNOWN, // 1EE55..1EE56
8850 ARABIC, // 1EE57
8851 UNKNOWN, // 1EE58
8852 ARABIC, // 1EE59
8853 UNKNOWN, // 1EE5A
8854 ARABIC, // 1EE5B
8855 UNKNOWN, // 1EE5C
8856 ARABIC, // 1EE5D
8857 UNKNOWN, // 1EE5E
8858 ARABIC, // 1EE5F
8859 UNKNOWN, // 1EE60
8860 ARABIC, // 1EE61..1EE62
8861 UNKNOWN, // 1EE63
8862 ARABIC, // 1EE64
8863 UNKNOWN, // 1EE65..1EE66
8864 ARABIC, // 1EE67..1EE6A
8865 UNKNOWN, // 1EE6B
8866 ARABIC, // 1EE6C..1EE72
8867 UNKNOWN, // 1EE73
8868 ARABIC, // 1EE74..1EE77
8869 UNKNOWN, // 1EE78
8870 ARABIC, // 1EE79..1EE7C
8871 UNKNOWN, // 1EE7D
8872 ARABIC, // 1EE7E
8873 UNKNOWN, // 1EE7F
8874 ARABIC, // 1EE80..1EE89
8875 UNKNOWN, // 1EE8A
8876 ARABIC, // 1EE8B..1EE9B
8877 UNKNOWN, // 1EE9C..1EEA0
8878 ARABIC, // 1EEA1..1EEA3
8879 UNKNOWN, // 1EEA4
8880 ARABIC, // 1EEA5..1EEA9
8881 UNKNOWN, // 1EEAA
8882 ARABIC, // 1EEAB..1EEBB
8883 UNKNOWN, // 1EEBC..1EEEF
8884 ARABIC, // 1EEF0..1EEF1
8885 UNKNOWN, // 1EEF2..1EFFF
8886 COMMON, // 1F000..1F02B
8887 UNKNOWN, // 1F02C..1F02F
8888 COMMON, // 1F030..1F093
8889 UNKNOWN, // 1F094..1F09F
8890 COMMON, // 1F0A0..1F0AE
8891 UNKNOWN, // 1F0AF..1F0B0
8892 COMMON, // 1F0B1..1F0BF
8893 UNKNOWN, // 1F0C0
8894 COMMON, // 1F0C1..1F0CF
8895 UNKNOWN, // 1F0D0
8896 COMMON, // 1F0D1..1F0F5
8897 UNKNOWN, // 1F0F6..1F0FF
8898 COMMON, // 1F100..1F1AD
8899 UNKNOWN, // 1F1AE..1F1E5
8900 COMMON, // 1F1E6..1F1FF
8901 HIRAGANA, // 1F200
8902 COMMON, // 1F201..1F202
8903 UNKNOWN, // 1F203..1F20F
8904 COMMON, // 1F210..1F23B
8905 UNKNOWN, // 1F23C..1F23F
8906 COMMON, // 1F240..1F248
8907 UNKNOWN, // 1F249..1F24F
8908 COMMON, // 1F250..1F251
8909 UNKNOWN, // 1F252..1F25F
8910 COMMON, // 1F260..1F265
8911 UNKNOWN, // 1F266..1F2FF
8912 COMMON, // 1F300..1F6D7
8913 UNKNOWN, // 1F6D8..1F6DB
8914 COMMON, // 1F6DC..1F6EC
8915 UNKNOWN, // 1F6ED..1F6EF
8916 COMMON, // 1F6F0..1F6FC
8917 UNKNOWN, // 1F6FD..1F6FF
8918 COMMON, // 1F700..1F776
8919 UNKNOWN, // 1F777..1F77A
8920 COMMON, // 1F77B..1F7D9
8921 UNKNOWN, // 1F7DA..1F7DF
8922 COMMON, // 1F7E0..1F7EB
8923 UNKNOWN, // 1F7EC..1F7EF
8924 COMMON, // 1F7F0
8925 UNKNOWN, // 1F7F1..1F7FF
8926 COMMON, // 1F800..1F80B
8927 UNKNOWN, // 1F80C..1F80F
8928 COMMON, // 1F810..1F847
8929 UNKNOWN, // 1F848..1F84F
8930 COMMON, // 1F850..1F859
8931 UNKNOWN, // 1F85A..1F85F
8932 COMMON, // 1F860..1F887
8933 UNKNOWN, // 1F888..1F88F
8934 COMMON, // 1F890..1F8AD
8935 UNKNOWN, // 1F8AE..1F8AF
8936 COMMON, // 1F8B0..1F8BB
8937 UNKNOWN, // 1F8BC..1F8BF
8938 COMMON, // 1F8C0..1F8C1
8939 UNKNOWN, // 1F8C2..1F8FF
8940 COMMON, // 1F900..1FA53
8941 UNKNOWN, // 1FA54..1FA5F
8942 COMMON, // 1FA60..1FA6D
8943 UNKNOWN, // 1FA6E..1FA6F
8944 COMMON, // 1FA70..1FA7C
8945 UNKNOWN, // 1FA7D..1FA7F
8946 COMMON, // 1FA80..1FA89
8947 UNKNOWN, // 1FA8A..1FA8E
8948 COMMON, // 1FA8F..1FAC6
8949 UNKNOWN, // 1FAC7..1FACD
8950 COMMON, // 1FACE..1FADC
8951 UNKNOWN, // 1FADD..1FADE
8952 COMMON, // 1FADF..1FAE9
8953 UNKNOWN, // 1FAEA..1FAEF
8954 COMMON, // 1FAF0..1FAF8
8955 UNKNOWN, // 1FAF9..1FAFF
8956 COMMON, // 1FB00..1FB92
8957 UNKNOWN, // 1FB93
8958 COMMON, // 1FB94..1FBF9
8959 UNKNOWN, // 1FBFA..1FFFF
8960 HAN, // 20000..2A6DF
8961 UNKNOWN, // 2A6E0..2A6FF
8962 HAN, // 2A700..2B739
8963 UNKNOWN, // 2B73A..2B73F
8964 HAN, // 2B740..2B81D
8965 UNKNOWN, // 2B81E..2B81F
8966 HAN, // 2B820..2CEA1
8967 UNKNOWN, // 2CEA2..2CEAF
8968 HAN, // 2CEB0..2EBE0
8969 UNKNOWN, // 2EBE1..2EBEF
8970 HAN, // 2EBF0..2EE5D
8971 UNKNOWN, // 2EE5E..2F7FF
8972 HAN, // 2F800..2FA1D
8973 UNKNOWN, // 2FA1E..2FFFF
8974 HAN, // 30000..3134A
8975 UNKNOWN, // 3134B..3134F
8976 HAN, // 31350..323AF
8977 UNKNOWN, // 323B0..E0000
8978 COMMON, // E0001
8979 UNKNOWN, // E0002..E001F
8980 COMMON, // E0020..E007F
8981 UNKNOWN, // E0080..E00FF
8982 INHERITED, // E0100..E01EF
8983 UNKNOWN, // E01F0..10FFFF
8984 };
8985
8986 private static final HashMap<String, Character.UnicodeScript> aliases;
8987 static {
8988 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
8989 aliases.put("ADLM", ADLAM);
8990 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
8991 aliases.put("AHOM", AHOM);
8992 aliases.put("ARAB", ARABIC);
8993 aliases.put("ARMI", IMPERIAL_ARAMAIC);
8994 aliases.put("ARMN", ARMENIAN);
8995 aliases.put("AVST", AVESTAN);
8996 aliases.put("BALI", BALINESE);
8997 aliases.put("BAMU", BAMUM);
8998 aliases.put("BASS", BASSA_VAH);
8999 aliases.put("BATK", BATAK);
9000 aliases.put("BENG", BENGALI);
9001 aliases.put("BHKS", BHAIKSUKI);
9002 aliases.put("BOPO", BOPOMOFO);
9003 aliases.put("BRAH", BRAHMI);
9004 aliases.put("BRAI", BRAILLE);
9005 aliases.put("BUGI", BUGINESE);
9006 aliases.put("BUHD", BUHID);
9007 aliases.put("CAKM", CHAKMA);
9008 aliases.put("CANS", CANADIAN_ABORIGINAL);
9009 aliases.put("CARI", CARIAN);
9010 aliases.put("CHAM", CHAM);
9011 aliases.put("CHER", CHEROKEE);
9012 aliases.put("CHRS", CHORASMIAN);
9013 aliases.put("COPT", COPTIC);
9014 aliases.put("CPMN", CYPRO_MINOAN);
9015 aliases.put("CPRT", CYPRIOT);
9016 aliases.put("CYRL", CYRILLIC);
9017 aliases.put("DEVA", DEVANAGARI);
9018 aliases.put("DIAK", DIVES_AKURU);
9019 aliases.put("DOGR", DOGRA);
9020 aliases.put("DSRT", DESERET);
9021 aliases.put("DUPL", DUPLOYAN);
9022 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
9023 aliases.put("ELBA", ELBASAN);
9024 aliases.put("ELYM", ELYMAIC);
9025 aliases.put("ETHI", ETHIOPIC);
9026 aliases.put("GARA", GARAY);
9027 aliases.put("GEOR", GEORGIAN);
9028 aliases.put("GLAG", GLAGOLITIC);
9029 aliases.put("GONG", GUNJALA_GONDI);
9030 aliases.put("GONM", MASARAM_GONDI);
9031 aliases.put("GOTH", GOTHIC);
9032 aliases.put("GRAN", GRANTHA);
9033 aliases.put("GREK", GREEK);
9034 aliases.put("GUJR", GUJARATI);
9035 aliases.put("GUKH", GURUNG_KHEMA);
9036 aliases.put("GURU", GURMUKHI);
9037 aliases.put("HANG", HANGUL);
9038 aliases.put("HANI", HAN);
9039 aliases.put("HANO", HANUNOO);
9040 aliases.put("HATR", HATRAN);
9041 aliases.put("HEBR", HEBREW);
9042 aliases.put("HIRA", HIRAGANA);
9043 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
9044 aliases.put("HMNG", PAHAWH_HMONG);
9045 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
9046 aliases.put("HUNG", OLD_HUNGARIAN);
9047 aliases.put("ITAL", OLD_ITALIC);
9048 aliases.put("JAVA", JAVANESE);
9049 aliases.put("KALI", KAYAH_LI);
9050 aliases.put("KANA", KATAKANA);
9051 aliases.put("KAWI", KAWI);
9052 aliases.put("KHAR", KHAROSHTHI);
9053 aliases.put("KHMR", KHMER);
9054 aliases.put("KHOJ", KHOJKI);
9055 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
9056 aliases.put("KNDA", KANNADA);
9057 aliases.put("KRAI", KIRAT_RAI);
9058 aliases.put("KTHI", KAITHI);
9059 aliases.put("LANA", TAI_THAM);
9060 aliases.put("LAOO", LAO);
9061 aliases.put("LATN", LATIN);
9062 aliases.put("LEPC", LEPCHA);
9063 aliases.put("LIMB", LIMBU);
9064 aliases.put("LINA", LINEAR_A);
9065 aliases.put("LINB", LINEAR_B);
9066 aliases.put("LISU", LISU);
9067 aliases.put("LYCI", LYCIAN);
9068 aliases.put("LYDI", LYDIAN);
9069 aliases.put("MAHJ", MAHAJANI);
9070 aliases.put("MAKA", MAKASAR);
9071 aliases.put("MAND", MANDAIC);
9072 aliases.put("MANI", MANICHAEAN);
9073 aliases.put("MARC", MARCHEN);
9074 aliases.put("MEDF", MEDEFAIDRIN);
9075 aliases.put("MEND", MENDE_KIKAKUI);
9076 aliases.put("MERC", MEROITIC_CURSIVE);
9077 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
9078 aliases.put("MLYM", MALAYALAM);
9079 aliases.put("MODI", MODI);
9080 aliases.put("MONG", MONGOLIAN);
9081 aliases.put("MROO", MRO);
9082 aliases.put("MTEI", MEETEI_MAYEK);
9083 aliases.put("MULT", MULTANI);
9084 aliases.put("MYMR", MYANMAR);
9085 aliases.put("NAGM", NAG_MUNDARI);
9086 aliases.put("NAND", NANDINAGARI);
9087 aliases.put("NARB", OLD_NORTH_ARABIAN);
9088 aliases.put("NBAT", NABATAEAN);
9089 aliases.put("NEWA", NEWA);
9090 aliases.put("NKOO", NKO);
9091 aliases.put("NSHU", NUSHU);
9092 aliases.put("OGAM", OGHAM);
9093 aliases.put("OLCK", OL_CHIKI);
9094 aliases.put("ONAO", OL_ONAL);
9095 aliases.put("ORKH", OLD_TURKIC);
9096 aliases.put("ORYA", ORIYA);
9097 aliases.put("OSGE", OSAGE);
9098 aliases.put("OSMA", OSMANYA);
9099 aliases.put("OUGR", OLD_UYGHUR);
9100 aliases.put("PALM", PALMYRENE);
9101 aliases.put("PAUC", PAU_CIN_HAU);
9102 aliases.put("PERM", OLD_PERMIC);
9103 aliases.put("PHAG", PHAGS_PA);
9104 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
9105 aliases.put("PHLP", PSALTER_PAHLAVI);
9106 aliases.put("PHNX", PHOENICIAN);
9107 aliases.put("PLRD", MIAO);
9108 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
9109 aliases.put("RJNG", REJANG);
9110 aliases.put("ROHG", HANIFI_ROHINGYA);
9111 aliases.put("RUNR", RUNIC);
9112 aliases.put("SAMR", SAMARITAN);
9113 aliases.put("SARB", OLD_SOUTH_ARABIAN);
9114 aliases.put("SAUR", SAURASHTRA);
9115 aliases.put("SGNW", SIGNWRITING);
9116 aliases.put("SHAW", SHAVIAN);
9117 aliases.put("SHRD", SHARADA);
9118 aliases.put("SIDD", SIDDHAM);
9119 aliases.put("SIND", KHUDAWADI);
9120 aliases.put("SINH", SINHALA);
9121 aliases.put("SOGD", SOGDIAN);
9122 aliases.put("SOGO", OLD_SOGDIAN);
9123 aliases.put("SORA", SORA_SOMPENG);
9124 aliases.put("SOYO", SOYOMBO);
9125 aliases.put("SUND", SUNDANESE);
9126 aliases.put("SUNU", SUNUWAR);
9127 aliases.put("SYLO", SYLOTI_NAGRI);
9128 aliases.put("SYRC", SYRIAC);
9129 aliases.put("TAGB", TAGBANWA);
9130 aliases.put("TAKR", TAKRI);
9131 aliases.put("TALE", TAI_LE);
9132 aliases.put("TALU", NEW_TAI_LUE);
9133 aliases.put("TAML", TAMIL);
9134 aliases.put("TANG", TANGUT);
9135 aliases.put("TAVT", TAI_VIET);
9136 aliases.put("TELU", TELUGU);
9137 aliases.put("TFNG", TIFINAGH);
9138 aliases.put("TGLG", TAGALOG);
9139 aliases.put("THAA", THAANA);
9140 aliases.put("THAI", THAI);
9141 aliases.put("TIBT", TIBETAN);
9142 aliases.put("TIRH", TIRHUTA);
9143 aliases.put("TNSA", TANGSA);
9144 aliases.put("TODR", TODHRI);
9145 aliases.put("TOTO", TOTO);
9146 aliases.put("TUTG", TULU_TIGALARI);
9147 aliases.put("UGAR", UGARITIC);
9148 aliases.put("VAII", VAI);
9149 aliases.put("VITH", VITHKUQI);
9150 aliases.put("WARA", WARANG_CITI);
9151 aliases.put("WCHO", WANCHO);
9152 aliases.put("XPEO", OLD_PERSIAN);
9153 aliases.put("XSUX", CUNEIFORM);
9154 aliases.put("YEZI", YEZIDI);
9155 aliases.put("YIII", YI);
9156 aliases.put("ZANB", ZANABAZAR_SQUARE);
9157 aliases.put("ZINH", INHERITED);
9158 aliases.put("ZYYY", COMMON);
9159 aliases.put("ZZZZ", UNKNOWN);
9160 }
9161
9162 /**
9163 * Returns the enum constant representing the Unicode script of which
9164 * the given character (Unicode code point) is assigned to.
9165 *
9166 * @param codePoint the character (Unicode code point) in question.
9167 * @return The {@code UnicodeScript} constant representing the
9168 * Unicode script of which this character is assigned to.
9169 *
9170 * @throws IllegalArgumentException if the specified
9171 * {@code codePoint} is an invalid Unicode code point.
9172 * @see Character#isValidCodePoint(int)
9173 *
9174 */
9175 public static UnicodeScript of(int codePoint) {
9176 if (!isValidCodePoint(codePoint))
9177 throw new IllegalArgumentException(
9178 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9179 int type = getType(codePoint);
9180 // leave SURROGATE and PRIVATE_USE for table lookup
9181 if (type == UNASSIGNED)
9182 return UNKNOWN;
9183 int index = Arrays.binarySearch(scriptStarts, codePoint);
9184 if (index < 0)
9185 index = -index - 2;
9186 return scripts[index];
9187 }
9188
9189 /**
9190 * Returns the UnicodeScript constant with the given Unicode script
9191 * name or the script name alias. Script names and their aliases are
9192 * determined by The Unicode Standard. The files {@code Scripts.txt}
9193 * and {@code PropertyValueAliases.txt} define script names
9194 * and the script name aliases for a particular version of the
9195 * standard. The {@link Character} class specifies the version of
9196 * the standard that it supports.
9197 * <p>
9198 * Character case is ignored for all of the valid script names.
9199 * The en_US locale's case mapping rules are used to provide
9200 * case-insensitive string comparisons for script name validation.
9201 *
9202 * @param scriptName A {@code UnicodeScript} name.
9203 * @return The {@code UnicodeScript} constant identified
9204 * by {@code scriptName}
9205 * @throws IllegalArgumentException if {@code scriptName} is an
9206 * invalid name
9207 * @throws NullPointerException if {@code scriptName} is null
9208 */
9209 public static final UnicodeScript forName(String scriptName) {
9210 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
9211 //.replace(' ', '_'));
9212 UnicodeScript sc = aliases.get(scriptName);
9213 if (sc != null)
9214 return sc;
9215 return valueOf(scriptName);
9216 }
9217 }
9218
9219 /**
9220 * The value of the {@code Character}.
9221 *
9222 * @serial
9223 */
9224 private final char value;
9225
9226 /** use serialVersionUID from JDK 1.0.2 for interoperability */
9227 @java.io.Serial
9228 private static final long serialVersionUID = 3786198910865385080L;
9229
9230 /**
9231 * Constructs a newly allocated {@code Character} object that
9232 * represents the specified {@code char} value.
9233 *
9234 * @param value the value to be represented by the
9235 * {@code Character} object.
9236 *
9237 * @deprecated
9238 * It is rarely appropriate to use this constructor. The static factory
9239 * {@link #valueOf(char)} is generally a better choice, as it is
9240 * likely to yield significantly better space and time performance.
9241 */
9242 @Deprecated(since="9")
9243 public Character(char value) {
9244 this.value = value;
9245 }
9246
9247 private static final class CharacterCache {
9248 private CharacterCache(){}
9249
9250 @Stable
9251 static final Character[] cache;
9252 static Character[] archivedCache;
9253
9254 static {
9255 int size = 127 + 1;
9256
9257 // Load and use the archived cache if it exists
9258 CDS.initializeFromArchive(CharacterCache.class);
9259 if (archivedCache == null) {
9260 Character[] c = new Character[size];
9261 for (int i = 0; i < size; i++) {
9262 c[i] = new Character((char) i);
9263 }
9264 archivedCache = c;
9265 }
9266 cache = archivedCache;
9267 assert cache.length == size;
9268 }
9269 }
9270
9271 /**
9272 * Returns a {@code Character} instance representing the specified
9273 * {@code char} value.
9274 * If a new {@code Character} instance is not required, this method
9275 * should generally be used in preference to the constructor
9276 * {@link #Character(char)}, as this method is likely to yield
9277 * significantly better space and time performance by caching
9278 * frequently requested values.
9279 *
9280 * This method will always cache values in the range {@code
9281 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9282 * cache other values outside of this range.
9283 *
9284 * @param c a char value.
9285 * @return a {@code Character} instance representing {@code c}.
9286 * @since 1.5
9287 */
9288 @IntrinsicCandidate
9289 @DeserializeConstructor
9290 public static Character valueOf(char c) {
9291 if (c <= 127) { // must cache
9292 return CharacterCache.cache[(int)c];
9293 }
9294 return new Character(c);
9295 }
9296
9297 /**
9298 * Returns the value of this {@code Character} object.
9299 * @return the primitive {@code char} value represented by
9300 * this object.
9301 */
9302 @IntrinsicCandidate
9303 public char charValue() {
9304 return value;
9305 }
9306
9307 /**
9308 * Returns a hash code for this {@code Character}; equal to the result
9309 * of invoking {@code charValue()}.
9310 *
9311 * @return a hash code value for this {@code Character}
9312 */
9313 @Override
9314 public int hashCode() {
9315 return Character.hashCode(value);
9316 }
9317
9318 /**
9319 * Returns a hash code for a {@code char} value; compatible with
9320 * {@code Character.hashCode()}.
9321 *
9322 * @since 1.8
9323 *
9324 * @param value The {@code char} for which to return a hash code.
9325 * @return a hash code value for a {@code char} value.
9326 */
9327 public static int hashCode(char value) {
9328 return (int)value;
9329 }
9330
9331 /**
9332 * Compares this object against the specified object.
9333 * The result is {@code true} if and only if the argument is not
9334 * {@code null} and is a {@code Character} object that
9335 * represents the same {@code char} value as this object.
9336 *
9337 * @param obj the object to compare with.
9338 * @return {@code true} if the objects are the same;
9339 * {@code false} otherwise.
9340 */
9341 public boolean equals(Object obj) {
9342 if (obj instanceof Character c) {
9343 return value == c.charValue();
9344 }
9345 return false;
9346 }
9347
9348 /**
9349 * Returns a {@code String} object representing this
9350 * {@code Character}'s value. The result is a string of
9351 * length 1 whose sole component is the primitive
9352 * {@code char} value represented by this
9353 * {@code Character} object.
9354 *
9355 * @return a string representation of this object.
9356 */
9357 @Override
9358 public String toString() {
9359 return String.valueOf(value);
9360 }
9361
9362 /**
9363 * Returns a {@code String} object representing the
9364 * specified {@code char}. The result is a string of length
9365 * 1 consisting solely of the specified {@code char}.
9366 *
9367 * @apiNote This method cannot handle <a
9368 * href="#supplementary"> supplementary characters</a>. To support
9369 * all Unicode characters, including supplementary characters, use
9370 * the {@link #toString(int)} method.
9371 *
9372 * @param c the {@code char} to be converted
9373 * @return the string representation of the specified {@code char}
9374 * @since 1.4
9375 */
9376 public static String toString(char c) {
9377 return String.valueOf(c);
9378 }
9379
9380 /**
9381 * Returns a {@code String} object representing the
9382 * specified character (Unicode code point). The result is a string of
9383 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9384 *
9385 * @param codePoint the {@code codePoint} to be converted
9386 * @return the string representation of the specified {@code codePoint}
9387 * @throws IllegalArgumentException if the specified
9388 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9389 * valid Unicode code point}.
9390 * @since 11
9391 */
9392 public static String toString(int codePoint) {
9393 return String.valueOfCodePoint(codePoint);
9394 }
9395
9396 /**
9397 * Determines whether the specified code point is a valid
9398 * <a href="http://www.unicode.org/glossary/#code_point">
9399 * Unicode code point value</a>.
9400 *
9401 * @param codePoint the Unicode code point to be tested
9402 * @return {@code true} if the specified code point value is between
9403 * {@link #MIN_CODE_POINT} and
9404 * {@link #MAX_CODE_POINT} inclusive;
9405 * {@code false} otherwise.
9406 * @since 1.5
9407 */
9408 public static boolean isValidCodePoint(int codePoint) {
9409 // Optimized form of:
9410 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9411 int plane = codePoint >>> 16;
9412 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9413 }
9414
9415 /**
9416 * Determines whether the specified character (Unicode code point)
9417 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9418 * Such code points can be represented using a single {@code char}.
9419 *
9420 * @param codePoint the character (Unicode code point) to be tested
9421 * @return {@code true} if the specified code point is between
9422 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9423 * {@code false} otherwise.
9424 * @since 1.7
9425 */
9426 public static boolean isBmpCodePoint(int codePoint) {
9427 return codePoint >>> 16 == 0;
9428 // Optimized form of:
9429 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9430 // We consistently use logical shift (>>>) to facilitate
9431 // additional runtime optimizations.
9432 }
9433
9434 /**
9435 * Determines whether the specified character (Unicode code point)
9436 * is in the <a href="#supplementary">supplementary character</a> range.
9437 *
9438 * @param codePoint the character (Unicode code point) to be tested
9439 * @return {@code true} if the specified code point is between
9440 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9441 * {@link #MAX_CODE_POINT} inclusive;
9442 * {@code false} otherwise.
9443 * @since 1.5
9444 */
9445 public static boolean isSupplementaryCodePoint(int codePoint) {
9446 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9447 && codePoint < MAX_CODE_POINT + 1;
9448 }
9449
9450 /**
9451 * Determines if the given {@code char} value is a
9452 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9453 * Unicode high-surrogate code unit</a>
9454 * (also known as <i>leading-surrogate code unit</i>).
9455 *
9456 * <p>Such values do not represent characters by themselves,
9457 * but are used in the representation of
9458 * <a href="#supplementary">supplementary characters</a>
9459 * in the UTF-16 encoding.
9460 *
9461 * @param ch the {@code char} value to be tested.
9462 * @return {@code true} if the {@code char} value is between
9463 * {@link #MIN_HIGH_SURROGATE} and
9464 * {@link #MAX_HIGH_SURROGATE} inclusive;
9465 * {@code false} otherwise.
9466 * @see Character#isLowSurrogate(char)
9467 * @see Character.UnicodeBlock#of(int)
9468 * @since 1.5
9469 */
9470 public static boolean isHighSurrogate(char ch) {
9471 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9472 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9473 }
9474
9475 /**
9476 * Determines if the given {@code char} value is a
9477 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9478 * Unicode low-surrogate code unit</a>
9479 * (also known as <i>trailing-surrogate code unit</i>).
9480 *
9481 * <p>Such values do not represent characters by themselves,
9482 * but are used in the representation of
9483 * <a href="#supplementary">supplementary characters</a>
9484 * in the UTF-16 encoding.
9485 *
9486 * @param ch the {@code char} value to be tested.
9487 * @return {@code true} if the {@code char} value is between
9488 * {@link #MIN_LOW_SURROGATE} and
9489 * {@link #MAX_LOW_SURROGATE} inclusive;
9490 * {@code false} otherwise.
9491 * @see Character#isHighSurrogate(char)
9492 * @since 1.5
9493 */
9494 public static boolean isLowSurrogate(char ch) {
9495 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9496 }
9497
9498 /**
9499 * Determines if the given {@code char} value is a Unicode
9500 * <i>surrogate code unit</i>.
9501 *
9502 * <p>Such values do not represent characters by themselves,
9503 * but are used in the representation of
9504 * <a href="#supplementary">supplementary characters</a>
9505 * in the UTF-16 encoding.
9506 *
9507 * <p>A char value is a surrogate code unit if and only if it is either
9508 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9509 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9510 *
9511 * @param ch the {@code char} value to be tested.
9512 * @return {@code true} if the {@code char} value is between
9513 * {@link #MIN_SURROGATE} and
9514 * {@link #MAX_SURROGATE} inclusive;
9515 * {@code false} otherwise.
9516 * @since 1.7
9517 */
9518 public static boolean isSurrogate(char ch) {
9519 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9520 }
9521
9522 /**
9523 * Determines whether the specified pair of {@code char}
9524 * values is a valid
9525 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9526 * Unicode surrogate pair</a>.
9527 *
9528 * <p>This method is equivalent to the expression:
9529 * <blockquote><pre>{@code
9530 * isHighSurrogate(high) && isLowSurrogate(low)
9531 * }</pre></blockquote>
9532 *
9533 * @param high the high-surrogate code value to be tested
9534 * @param low the low-surrogate code value to be tested
9535 * @return {@code true} if the specified high and
9536 * low-surrogate code values represent a valid surrogate pair;
9537 * {@code false} otherwise.
9538 * @since 1.5
9539 */
9540 public static boolean isSurrogatePair(char high, char low) {
9541 return isHighSurrogate(high) && isLowSurrogate(low);
9542 }
9543
9544 /**
9545 * Determines the number of {@code char} values needed to
9546 * represent the specified character (Unicode code point). If the
9547 * specified character is equal to or greater than 0x10000, then
9548 * the method returns 2. Otherwise, the method returns 1.
9549 *
9550 * <p>This method doesn't validate the specified character to be a
9551 * valid Unicode code point. The caller must validate the
9552 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9553 * if necessary.
9554 *
9555 * @param codePoint the character (Unicode code point) to be tested.
9556 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9557 * @see Character#isSupplementaryCodePoint(int)
9558 * @since 1.5
9559 */
9560 public static int charCount(int codePoint) {
9561 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9562 }
9563
9564 /**
9565 * Converts the specified surrogate pair to its supplementary code
9566 * point value. This method does not validate the specified
9567 * surrogate pair. The caller must validate it using {@link
9568 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9569 *
9570 * @param high the high-surrogate code unit
9571 * @param low the low-surrogate code unit
9572 * @return the supplementary code point composed from the
9573 * specified surrogate pair.
9574 * @since 1.5
9575 */
9576 public static int toCodePoint(char high, char low) {
9577 // Optimized form of:
9578 // return ((high - MIN_HIGH_SURROGATE) << 10)
9579 // + (low - MIN_LOW_SURROGATE)
9580 // + MIN_SUPPLEMENTARY_CODE_POINT;
9581 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9582 - (MIN_HIGH_SURROGATE << 10)
9583 - MIN_LOW_SURROGATE);
9584 }
9585
9586 /**
9587 * Returns the code point at the given index of the
9588 * {@code CharSequence}. If the {@code char} value at
9589 * the given index in the {@code CharSequence} is in the
9590 * high-surrogate range, the following index is less than the
9591 * length of the {@code CharSequence}, and the
9592 * {@code char} value at the following index is in the
9593 * low-surrogate range, then the supplementary code point
9594 * corresponding to this surrogate pair is returned. Otherwise,
9595 * the {@code char} value at the given index is returned.
9596 *
9597 * @param seq a sequence of {@code char} values (Unicode code
9598 * units)
9599 * @param index the index to the {@code char} values (Unicode
9600 * code units) in {@code seq} to be converted
9601 * @return the Unicode code point at the given index
9602 * @throws NullPointerException if {@code seq} is null.
9603 * @throws IndexOutOfBoundsException if the value
9604 * {@code index} is negative or not less than
9605 * {@link CharSequence#length() seq.length()}.
9606 * @since 1.5
9607 */
9608 public static int codePointAt(CharSequence seq, int index) {
9609 char c1 = seq.charAt(index);
9610 if (isHighSurrogate(c1) && ++index < seq.length()) {
9611 char c2 = seq.charAt(index);
9612 if (isLowSurrogate(c2)) {
9613 return toCodePoint(c1, c2);
9614 }
9615 }
9616 return c1;
9617 }
9618
9619 /**
9620 * Returns the code point at the given index of the
9621 * {@code char} array. If the {@code char} value at
9622 * the given index in the {@code char} array is in the
9623 * high-surrogate range, the following index is less than the
9624 * length of the {@code char} array, and the
9625 * {@code char} value at the following index is in the
9626 * low-surrogate range, then the supplementary code point
9627 * corresponding to this surrogate pair is returned. Otherwise,
9628 * the {@code char} value at the given index is returned.
9629 *
9630 * @param a the {@code char} array
9631 * @param index the index to the {@code char} values (Unicode
9632 * code units) in the {@code char} array to be converted
9633 * @return the Unicode code point at the given index
9634 * @throws NullPointerException if {@code a} is null.
9635 * @throws IndexOutOfBoundsException if the value
9636 * {@code index} is negative or not less than
9637 * the length of the {@code char} array.
9638 * @since 1.5
9639 */
9640 public static int codePointAt(char[] a, int index) {
9641 return codePointAtImpl(a, index, a.length);
9642 }
9643
9644 /**
9645 * Returns the code point at the given index of the
9646 * {@code char} array, where only array elements with
9647 * {@code index} less than {@code limit} can be used. If
9648 * the {@code char} value at the given index in the
9649 * {@code char} array is in the high-surrogate range, the
9650 * following index is less than the {@code limit}, and the
9651 * {@code char} value at the following index is in the
9652 * low-surrogate range, then the supplementary code point
9653 * corresponding to this surrogate pair is returned. Otherwise,
9654 * the {@code char} value at the given index is returned.
9655 *
9656 * @param a the {@code char} array
9657 * @param index the index to the {@code char} values (Unicode
9658 * code units) in the {@code char} array to be converted
9659 * @param limit the index after the last array element that
9660 * can be used in the {@code char} array
9661 * @return the Unicode code point at the given index
9662 * @throws NullPointerException if {@code a} is null.
9663 * @throws IndexOutOfBoundsException if the {@code index}
9664 * argument is negative or not less than the {@code limit}
9665 * argument, or if the {@code limit} argument is negative or
9666 * greater than the length of the {@code char} array.
9667 * @since 1.5
9668 */
9669 public static int codePointAt(char[] a, int index, int limit) {
9670 if (index >= limit || index < 0 || limit > a.length) {
9671 throw new IndexOutOfBoundsException();
9672 }
9673 return codePointAtImpl(a, index, limit);
9674 }
9675
9676 // throws ArrayIndexOutOfBoundsException if index out of bounds
9677 static int codePointAtImpl(char[] a, int index, int limit) {
9678 char c1 = a[index];
9679 if (isHighSurrogate(c1) && ++index < limit) {
9680 char c2 = a[index];
9681 if (isLowSurrogate(c2)) {
9682 return toCodePoint(c1, c2);
9683 }
9684 }
9685 return c1;
9686 }
9687
9688 /**
9689 * Returns the code point preceding the given index of the
9690 * {@code CharSequence}. If the {@code char} value at
9691 * {@code (index - 1)} in the {@code CharSequence} is in
9692 * the low-surrogate range, {@code (index - 2)} is not
9693 * negative, and the {@code char} value at {@code (index - 2)}
9694 * in the {@code CharSequence} is in the
9695 * high-surrogate range, then the supplementary code point
9696 * corresponding to this surrogate pair is returned. Otherwise,
9697 * the {@code char} value at {@code (index - 1)} is
9698 * returned.
9699 *
9700 * @param seq the {@code CharSequence} instance
9701 * @param index the index following the code point that should be returned
9702 * @return the Unicode code point value before the given index.
9703 * @throws NullPointerException if {@code seq} is null.
9704 * @throws IndexOutOfBoundsException if the {@code index}
9705 * argument is less than 1 or greater than {@link
9706 * CharSequence#length() seq.length()}.
9707 * @since 1.5
9708 */
9709 public static int codePointBefore(CharSequence seq, int index) {
9710 char c2 = seq.charAt(--index);
9711 if (isLowSurrogate(c2) && index > 0) {
9712 char c1 = seq.charAt(--index);
9713 if (isHighSurrogate(c1)) {
9714 return toCodePoint(c1, c2);
9715 }
9716 }
9717 return c2;
9718 }
9719
9720 /**
9721 * Returns the code point preceding the given index of the
9722 * {@code char} array. If the {@code char} value at
9723 * {@code (index - 1)} in the {@code char} array is in
9724 * the low-surrogate range, {@code (index - 2)} is not
9725 * negative, and the {@code char} value at {@code (index - 2)}
9726 * in the {@code char} array is in the
9727 * high-surrogate range, then the supplementary code point
9728 * corresponding to this surrogate pair is returned. Otherwise,
9729 * the {@code char} value at {@code (index - 1)} is
9730 * returned.
9731 *
9732 * @param a the {@code char} array
9733 * @param index the index following the code point that should be returned
9734 * @return the Unicode code point value before the given index.
9735 * @throws NullPointerException if {@code a} is null.
9736 * @throws IndexOutOfBoundsException if the {@code index}
9737 * argument is less than 1 or greater than the length of the
9738 * {@code char} array
9739 * @since 1.5
9740 */
9741 public static int codePointBefore(char[] a, int index) {
9742 return codePointBeforeImpl(a, index, 0);
9743 }
9744
9745 /**
9746 * Returns the code point preceding the given index of the
9747 * {@code char} array, where only array elements with
9748 * {@code index} greater than or equal to {@code start}
9749 * can be used. If the {@code char} value at {@code (index - 1)}
9750 * in the {@code char} array is in the
9751 * low-surrogate range, {@code (index - 2)} is not less than
9752 * {@code start}, and the {@code char} value at
9753 * {@code (index - 2)} in the {@code char} array is in
9754 * the high-surrogate range, then the supplementary code point
9755 * corresponding to this surrogate pair is returned. Otherwise,
9756 * the {@code char} value at {@code (index - 1)} is
9757 * returned.
9758 *
9759 * @param a the {@code char} array
9760 * @param index the index following the code point that should be returned
9761 * @param start the index of the first array element in the
9762 * {@code char} array
9763 * @return the Unicode code point value before the given index.
9764 * @throws NullPointerException if {@code a} is null.
9765 * @throws IndexOutOfBoundsException if the {@code index}
9766 * argument is not greater than the {@code start} argument or
9767 * is greater than the length of the {@code char} array, or
9768 * if the {@code start} argument is negative or not less than
9769 * the length of the {@code char} array.
9770 * @since 1.5
9771 */
9772 public static int codePointBefore(char[] a, int index, int start) {
9773 if (index <= start || start < 0 || index > a.length) {
9774 throw new IndexOutOfBoundsException();
9775 }
9776 return codePointBeforeImpl(a, index, start);
9777 }
9778
9779 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9780 static int codePointBeforeImpl(char[] a, int index, int start) {
9781 char c2 = a[--index];
9782 if (isLowSurrogate(c2) && index > start) {
9783 char c1 = a[--index];
9784 if (isHighSurrogate(c1)) {
9785 return toCodePoint(c1, c2);
9786 }
9787 }
9788 return c2;
9789 }
9790
9791 /**
9792 * Returns the leading surrogate (a
9793 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9794 * high surrogate code unit</a>) of the
9795 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9796 * surrogate pair</a>
9797 * representing the specified supplementary character (Unicode
9798 * code point) in the UTF-16 encoding. If the specified character
9799 * is not a
9800 * <a href="Character.html#supplementary">supplementary character</a>,
9801 * an unspecified {@code char} is returned.
9802 *
9803 * <p>If
9804 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9805 * is {@code true}, then
9806 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9807 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9808 * are also always {@code true}.
9809 *
9810 * @param codePoint a supplementary character (Unicode code point)
9811 * @return the leading surrogate code unit used to represent the
9812 * character in the UTF-16 encoding
9813 * @since 1.7
9814 */
9815 public static char highSurrogate(int codePoint) {
9816 return (char) ((codePoint >>> 10)
9817 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9818 }
9819
9820 /**
9821 * Returns the trailing surrogate (a
9822 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9823 * low surrogate code unit</a>) of the
9824 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9825 * surrogate pair</a>
9826 * representing the specified supplementary character (Unicode
9827 * code point) in the UTF-16 encoding. If the specified character
9828 * is not a
9829 * <a href="Character.html#supplementary">supplementary character</a>,
9830 * an unspecified {@code char} is returned.
9831 *
9832 * <p>If
9833 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9834 * is {@code true}, then
9835 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9836 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9837 * are also always {@code true}.
9838 *
9839 * @param codePoint a supplementary character (Unicode code point)
9840 * @return the trailing surrogate code unit used to represent the
9841 * character in the UTF-16 encoding
9842 * @since 1.7
9843 */
9844 public static char lowSurrogate(int codePoint) {
9845 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
9846 }
9847
9848 /**
9849 * Converts the specified character (Unicode code point) to its
9850 * UTF-16 representation. If the specified code point is a BMP
9851 * (Basic Multilingual Plane or Plane 0) value, the same value is
9852 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
9853 * specified code point is a supplementary character, its
9854 * surrogate values are stored in {@code dst[dstIndex]}
9855 * (high-surrogate) and {@code dst[dstIndex+1]}
9856 * (low-surrogate), and 2 is returned.
9857 *
9858 * @param codePoint the character (Unicode code point) to be converted.
9859 * @param dst an array of {@code char} in which the
9860 * {@code codePoint}'s UTF-16 value is stored.
9861 * @param dstIndex the start index into the {@code dst}
9862 * array where the converted value is stored.
9863 * @return 1 if the code point is a BMP code point, 2 if the
9864 * code point is a supplementary code point.
9865 * @throws IllegalArgumentException if the specified
9866 * {@code codePoint} is not a valid Unicode code point.
9867 * @throws NullPointerException if the specified {@code dst} is null.
9868 * @throws IndexOutOfBoundsException if {@code dstIndex}
9869 * is negative or not less than {@code dst.length}, or if
9870 * {@code dst} at {@code dstIndex} doesn't have enough
9871 * array element(s) to store the resulting {@code char}
9872 * value(s). (If {@code dstIndex} is equal to
9873 * {@code dst.length-1} and the specified
9874 * {@code codePoint} is a supplementary character, the
9875 * high-surrogate value is not stored in
9876 * {@code dst[dstIndex]}.)
9877 * @since 1.5
9878 */
9879 public static int toChars(int codePoint, char[] dst, int dstIndex) {
9880 if (isBmpCodePoint(codePoint)) {
9881 dst[dstIndex] = (char) codePoint;
9882 return 1;
9883 } else if (isValidCodePoint(codePoint)) {
9884 toSurrogates(codePoint, dst, dstIndex);
9885 return 2;
9886 } else {
9887 throw new IllegalArgumentException(
9888 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9889 }
9890 }
9891
9892 /**
9893 * Converts the specified character (Unicode code point) to its
9894 * UTF-16 representation stored in a {@code char} array. If
9895 * the specified code point is a BMP (Basic Multilingual Plane or
9896 * Plane 0) value, the resulting {@code char} array has
9897 * the same value as {@code codePoint}. If the specified code
9898 * point is a supplementary code point, the resulting
9899 * {@code char} array has the corresponding surrogate pair.
9900 *
9901 * @param codePoint a Unicode code point
9902 * @return a {@code char} array having
9903 * {@code codePoint}'s UTF-16 representation.
9904 * @throws IllegalArgumentException if the specified
9905 * {@code codePoint} is not a valid Unicode code point.
9906 * @since 1.5
9907 */
9908 public static char[] toChars(int codePoint) {
9909 if (isBmpCodePoint(codePoint)) {
9910 return new char[] { (char) codePoint };
9911 } else if (isValidCodePoint(codePoint)) {
9912 char[] result = new char[2];
9913 toSurrogates(codePoint, result, 0);
9914 return result;
9915 } else {
9916 throw new IllegalArgumentException(
9917 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9918 }
9919 }
9920
9921 static void toSurrogates(int codePoint, char[] dst, int index) {
9922 // We write elements "backwards" to guarantee all-or-nothing
9923 dst[index+1] = lowSurrogate(codePoint);
9924 dst[index] = highSurrogate(codePoint);
9925 }
9926
9927 /**
9928 * Returns the number of Unicode code points in the text range of
9929 * the specified char sequence. The text range begins at the
9930 * specified {@code beginIndex} and extends to the
9931 * {@code char} at index {@code endIndex - 1}. Thus the
9932 * length (in {@code char}s) of the text range is
9933 * {@code endIndex-beginIndex}. Unpaired surrogates within
9934 * the text range count as one code point each.
9935 *
9936 * @param seq the char sequence
9937 * @param beginIndex the index to the first {@code char} of
9938 * the text range.
9939 * @param endIndex the index after the last {@code char} of
9940 * the text range.
9941 * @return the number of Unicode code points in the specified text
9942 * range
9943 * @throws NullPointerException if {@code seq} is null.
9944 * @throws IndexOutOfBoundsException if the
9945 * {@code beginIndex} is negative, or {@code endIndex}
9946 * is larger than the length of the given sequence, or
9947 * {@code beginIndex} is larger than {@code endIndex}.
9948 * @since 1.5
9949 */
9950 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
9951 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
9952 int n = endIndex - beginIndex;
9953 for (int i = beginIndex; i < endIndex; ) {
9954 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
9955 isLowSurrogate(seq.charAt(i))) {
9956 n--;
9957 i++;
9958 }
9959 }
9960 return n;
9961 }
9962
9963 /**
9964 * Returns the number of Unicode code points in a subarray of the
9965 * {@code char} array argument. The {@code offset}
9966 * argument is the index of the first {@code char} of the
9967 * subarray and the {@code count} argument specifies the
9968 * length of the subarray in {@code char}s. Unpaired
9969 * surrogates within the subarray count as one code point each.
9970 *
9971 * @param a the {@code char} array
9972 * @param offset the index of the first {@code char} in the
9973 * given {@code char} array
9974 * @param count the length of the subarray in {@code char}s
9975 * @return the number of Unicode code points in the specified subarray
9976 * @throws NullPointerException if {@code a} is null.
9977 * @throws IndexOutOfBoundsException if {@code offset} or
9978 * {@code count} is negative, or if {@code offset +
9979 * count} is larger than the length of the given array.
9980 * @since 1.5
9981 */
9982 public static int codePointCount(char[] a, int offset, int count) {
9983 Objects.checkFromIndexSize(offset, count, a.length);
9984 return codePointCountImpl(a, offset, count);
9985 }
9986
9987 static int codePointCountImpl(char[] a, int offset, int count) {
9988 int endIndex = offset + count;
9989 int n = count;
9990 for (int i = offset; i < endIndex; ) {
9991 if (isHighSurrogate(a[i++]) && i < endIndex &&
9992 isLowSurrogate(a[i])) {
9993 n--;
9994 i++;
9995 }
9996 }
9997 return n;
9998 }
9999
10000 /**
10001 * Returns the index within the given char sequence that is offset
10002 * from the given {@code index} by {@code codePointOffset}
10003 * code points. Unpaired surrogates within the text range given by
10004 * {@code index} and {@code codePointOffset} count as
10005 * one code point each.
10006 *
10007 * @param seq the char sequence
10008 * @param index the index to be offset
10009 * @param codePointOffset the offset in code points
10010 * @return the index within the char sequence
10011 * @throws NullPointerException if {@code seq} is null.
10012 * @throws IndexOutOfBoundsException if {@code index}
10013 * is negative or larger than the length of the char sequence,
10014 * or if {@code codePointOffset} is positive and the
10015 * subsequence starting with {@code index} has fewer than
10016 * {@code codePointOffset} code points, or if
10017 * {@code codePointOffset} is negative and the subsequence
10018 * before {@code index} has fewer than the absolute value
10019 * of {@code codePointOffset} code points.
10020 * @since 1.5
10021 */
10022 public static int offsetByCodePoints(CharSequence seq, int index,
10023 int codePointOffset) {
10024 int length = seq.length();
10025 if (index < 0 || index > length) {
10026 throw new IndexOutOfBoundsException();
10027 }
10028
10029 int x = index;
10030 if (codePointOffset >= 0) {
10031 int i;
10032 for (i = 0; x < length && i < codePointOffset; i++) {
10033 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
10034 isLowSurrogate(seq.charAt(x))) {
10035 x++;
10036 }
10037 }
10038 if (i < codePointOffset) {
10039 throw new IndexOutOfBoundsException();
10040 }
10041 } else {
10042 int i;
10043 for (i = codePointOffset; x > 0 && i < 0; i++) {
10044 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
10045 isHighSurrogate(seq.charAt(x-1))) {
10046 x--;
10047 }
10048 }
10049 if (i < 0) {
10050 throw new IndexOutOfBoundsException();
10051 }
10052 }
10053 return x;
10054 }
10055
10056 /**
10057 * Returns the index within the given {@code char} subarray
10058 * that is offset from the given {@code index} by
10059 * {@code codePointOffset} code points. The
10060 * {@code start} and {@code count} arguments specify a
10061 * subarray of the {@code char} array. Unpaired surrogates
10062 * within the text range given by {@code index} and
10063 * {@code codePointOffset} count as one code point each.
10064 *
10065 * @param a the {@code char} array
10066 * @param start the index of the first {@code char} of the
10067 * subarray
10068 * @param count the length of the subarray in {@code char}s
10069 * @param index the index to be offset
10070 * @param codePointOffset the offset in code points
10071 * @return the index within the subarray
10072 * @throws NullPointerException if {@code a} is null.
10073 * @throws IndexOutOfBoundsException
10074 * if {@code start} or {@code count} is negative,
10075 * or if {@code start + count} is larger than the length of
10076 * the given array,
10077 * or if {@code index} is less than {@code start} or
10078 * larger then {@code start + count},
10079 * or if {@code codePointOffset} is positive and the text range
10080 * starting with {@code index} and ending with {@code start + count - 1}
10081 * has fewer than {@code codePointOffset} code
10082 * points,
10083 * or if {@code codePointOffset} is negative and the text range
10084 * starting with {@code start} and ending with {@code index - 1}
10085 * has fewer than the absolute value of
10086 * {@code codePointOffset} code points.
10087 * @since 1.5
10088 */
10089 public static int offsetByCodePoints(char[] a, int start, int count,
10090 int index, int codePointOffset) {
10091 if (count > a.length-start || start < 0 || count < 0
10092 || index < start || index > start+count) {
10093 throw new IndexOutOfBoundsException();
10094 }
10095 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
10096 }
10097
10098 static int offsetByCodePointsImpl(char[]a, int start, int count,
10099 int index, int codePointOffset) {
10100 int x = index;
10101 if (codePointOffset >= 0) {
10102 int limit = start + count;
10103 int i;
10104 for (i = 0; x < limit && i < codePointOffset; i++) {
10105 if (isHighSurrogate(a[x++]) && x < limit &&
10106 isLowSurrogate(a[x])) {
10107 x++;
10108 }
10109 }
10110 if (i < codePointOffset) {
10111 throw new IndexOutOfBoundsException();
10112 }
10113 } else {
10114 int i;
10115 for (i = codePointOffset; x > start && i < 0; i++) {
10116 if (isLowSurrogate(a[--x]) && x > start &&
10117 isHighSurrogate(a[x-1])) {
10118 x--;
10119 }
10120 }
10121 if (i < 0) {
10122 throw new IndexOutOfBoundsException();
10123 }
10124 }
10125 return x;
10126 }
10127
10128 /**
10129 * Determines if the specified character is a lowercase character.
10130 * <p>
10131 * A character is lowercase if its general category type, provided
10132 * by {@code Character.getType(ch)}, is
10133 * {@code LOWERCASE_LETTER}, or it has contributory property
10134 * Other_Lowercase as defined by the Unicode Standard.
10135 * <p>
10136 * The following are examples of lowercase characters:
10137 * <blockquote><pre>
10138 * 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
10139 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10140 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10141 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10142 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10143 * </pre></blockquote>
10144 * <p> Many other Unicode characters are lowercase too.
10145 *
10146 * <p><b>Note:</b> This method cannot handle <a
10147 * href="#supplementary"> supplementary characters</a>. To support
10148 * all Unicode characters, including supplementary characters, use
10149 * the {@link #isLowerCase(int)} method.
10150 *
10151 * @param ch the character to be tested.
10152 * @return {@code true} if the character is lowercase;
10153 * {@code false} otherwise.
10154 * @see Character#isLowerCase(char)
10155 * @see Character#isTitleCase(char)
10156 * @see Character#toLowerCase(char)
10157 * @see Character#getType(char)
10158 */
10159 public static boolean isLowerCase(char ch) {
10160 return isLowerCase((int)ch);
10161 }
10162
10163 /**
10164 * Determines if the specified character (Unicode code point) is a
10165 * lowercase character.
10166 * <p>
10167 * A character is lowercase if its general category type, provided
10168 * by {@link Character#getType getType(codePoint)}, is
10169 * {@code LOWERCASE_LETTER}, or it has contributory property
10170 * Other_Lowercase as defined by the Unicode Standard.
10171 * <p>
10172 * The following are examples of lowercase characters:
10173 * <blockquote><pre>
10174 * 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
10175 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10176 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10177 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10178 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10179 * </pre></blockquote>
10180 * <p> Many other Unicode characters are lowercase too.
10181 *
10182 * @param codePoint the character (Unicode code point) to be tested.
10183 * @return {@code true} if the character is lowercase;
10184 * {@code false} otherwise.
10185 * @see Character#isLowerCase(int)
10186 * @see Character#isTitleCase(int)
10187 * @see Character#toLowerCase(int)
10188 * @see Character#getType(int)
10189 * @since 1.5
10190 */
10191 public static boolean isLowerCase(int codePoint) {
10192 return CharacterData.of(codePoint).isLowerCase(codePoint);
10193 }
10194
10195 /**
10196 * Determines if the specified character is an uppercase character.
10197 * <p>
10198 * A character is uppercase if its general category type, provided by
10199 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
10200 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10201 * <p>
10202 * The following are examples of uppercase characters:
10203 * <blockquote><pre>
10204 * 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
10205 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10206 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10207 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10208 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10209 * </pre></blockquote>
10210 * <p> Many other Unicode characters are uppercase too.
10211 *
10212 * <p><b>Note:</b> This method cannot handle <a
10213 * href="#supplementary"> supplementary characters</a>. To support
10214 * all Unicode characters, including supplementary characters, use
10215 * the {@link #isUpperCase(int)} method.
10216 *
10217 * @param ch the character to be tested.
10218 * @return {@code true} if the character is uppercase;
10219 * {@code false} otherwise.
10220 * @see Character#isLowerCase(char)
10221 * @see Character#isTitleCase(char)
10222 * @see Character#toUpperCase(char)
10223 * @see Character#getType(char)
10224 * @since 1.0
10225 */
10226 public static boolean isUpperCase(char ch) {
10227 return isUpperCase((int)ch);
10228 }
10229
10230 /**
10231 * Determines if the specified character (Unicode code point) is an uppercase character.
10232 * <p>
10233 * A character is uppercase if its general category type, provided by
10234 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
10235 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10236 * <p>
10237 * The following are examples of uppercase characters:
10238 * <blockquote><pre>
10239 * 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
10240 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10241 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10242 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10243 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10244 * </pre></blockquote>
10245 * <p> Many other Unicode characters are uppercase too.
10246 *
10247 * @param codePoint the character (Unicode code point) to be tested.
10248 * @return {@code true} if the character is uppercase;
10249 * {@code false} otherwise.
10250 * @see Character#isLowerCase(int)
10251 * @see Character#isTitleCase(int)
10252 * @see Character#toUpperCase(int)
10253 * @see Character#getType(int)
10254 * @since 1.5
10255 */
10256 public static boolean isUpperCase(int codePoint) {
10257 return CharacterData.of(codePoint).isUpperCase(codePoint);
10258 }
10259
10260 /**
10261 * Determines if the specified character is a titlecase character.
10262 * <p>
10263 * A character is a titlecase character if its general
10264 * category type, provided by {@code Character.getType(ch)},
10265 * is {@code TITLECASE_LETTER}.
10266 * <p>
10267 * Some characters look like pairs of Latin letters. For example, there
10268 * is an uppercase letter that looks like "LJ" and has a corresponding
10269 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10270 * is the appropriate form to use when rendering a word in lowercase
10271 * with initial capitals, as for a book title.
10272 * <p>
10273 * These are some of the Unicode characters for which this method returns
10274 * {@code true}:
10275 * <ul>
10276 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10277 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10278 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10279 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10280 * </ul>
10281 * <p> Many other Unicode characters are titlecase too.
10282 *
10283 * <p><b>Note:</b> This method cannot handle <a
10284 * href="#supplementary"> supplementary characters</a>. To support
10285 * all Unicode characters, including supplementary characters, use
10286 * the {@link #isTitleCase(int)} method.
10287 *
10288 * @param ch the character to be tested.
10289 * @return {@code true} if the character is titlecase;
10290 * {@code false} otherwise.
10291 * @see Character#isLowerCase(char)
10292 * @see Character#isUpperCase(char)
10293 * @see Character#toTitleCase(char)
10294 * @see Character#getType(char)
10295 * @since 1.0.2
10296 */
10297 public static boolean isTitleCase(char ch) {
10298 return isTitleCase((int)ch);
10299 }
10300
10301 /**
10302 * Determines if the specified character (Unicode code point) is a titlecase character.
10303 * <p>
10304 * A character is a titlecase character if its general
10305 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10306 * is {@code TITLECASE_LETTER}.
10307 * <p>
10308 * Some characters look like pairs of Latin letters. For example, there
10309 * is an uppercase letter that looks like "LJ" and has a corresponding
10310 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10311 * is the appropriate form to use when rendering a word in lowercase
10312 * with initial capitals, as for a book title.
10313 * <p>
10314 * These are some of the Unicode characters for which this method returns
10315 * {@code true}:
10316 * <ul>
10317 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10318 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10319 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10320 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10321 * </ul>
10322 * <p> Many other Unicode characters are titlecase too.
10323 *
10324 * @param codePoint the character (Unicode code point) to be tested.
10325 * @return {@code true} if the character is titlecase;
10326 * {@code false} otherwise.
10327 * @see Character#isLowerCase(int)
10328 * @see Character#isUpperCase(int)
10329 * @see Character#toTitleCase(int)
10330 * @see Character#getType(int)
10331 * @since 1.5
10332 */
10333 public static boolean isTitleCase(int codePoint) {
10334 return getType(codePoint) == Character.TITLECASE_LETTER;
10335 }
10336
10337 /**
10338 * Determines if the specified character is a digit.
10339 * <p>
10340 * A character is a digit if its general category type, provided
10341 * by {@code Character.getType(ch)}, is
10342 * {@code DECIMAL_DIGIT_NUMBER}.
10343 * <p>
10344 * Some Unicode character ranges that contain digits:
10345 * <ul>
10346 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10347 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10348 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10349 * Arabic-Indic digits
10350 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10351 * Extended Arabic-Indic digits
10352 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10353 * Devanagari digits
10354 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10355 * Fullwidth digits
10356 * </ul>
10357 *
10358 * Many other character ranges contain digits as well.
10359 *
10360 * <p><b>Note:</b> This method cannot handle <a
10361 * href="#supplementary"> supplementary characters</a>. To support
10362 * all Unicode characters, including supplementary characters, use
10363 * the {@link #isDigit(int)} method.
10364 *
10365 * @param ch the character to be tested.
10366 * @return {@code true} if the character is a digit;
10367 * {@code false} otherwise.
10368 * @see Character#digit(char, int)
10369 * @see Character#forDigit(int, int)
10370 * @see Character#getType(char)
10371 */
10372 public static boolean isDigit(char ch) {
10373 return isDigit((int)ch);
10374 }
10375
10376 /**
10377 * Determines if the specified character (Unicode code point) is a digit.
10378 * <p>
10379 * A character is a digit if its general category type, provided
10380 * by {@link Character#getType(int) getType(codePoint)}, is
10381 * {@code DECIMAL_DIGIT_NUMBER}.
10382 * <p>
10383 * Some Unicode character ranges that contain digits:
10384 * <ul>
10385 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10386 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10387 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10388 * Arabic-Indic digits
10389 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10390 * Extended Arabic-Indic digits
10391 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10392 * Devanagari digits
10393 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10394 * Fullwidth digits
10395 * </ul>
10396 *
10397 * Many other character ranges contain digits as well.
10398 *
10399 * @param codePoint the character (Unicode code point) to be tested.
10400 * @return {@code true} if the character is a digit;
10401 * {@code false} otherwise.
10402 * @see Character#forDigit(int, int)
10403 * @see Character#getType(int)
10404 * @since 1.5
10405 */
10406 public static boolean isDigit(int codePoint) {
10407 return CharacterData.of(codePoint).isDigit(codePoint);
10408 }
10409
10410 /**
10411 * Determines if a character is defined in Unicode.
10412 * <p>
10413 * A character is defined if at least one of the following is true:
10414 * <ul>
10415 * <li>It has an entry in the UnicodeData file.
10416 * <li>It has a value in a range defined by the UnicodeData file.
10417 * </ul>
10418 *
10419 * <p><b>Note:</b> This method cannot handle <a
10420 * href="#supplementary"> supplementary characters</a>. To support
10421 * all Unicode characters, including supplementary characters, use
10422 * the {@link #isDefined(int)} method.
10423 *
10424 * @param ch the character to be tested
10425 * @return {@code true} if the character has a defined meaning
10426 * in Unicode; {@code false} otherwise.
10427 * @see Character#isDigit(char)
10428 * @see Character#isLetter(char)
10429 * @see Character#isLetterOrDigit(char)
10430 * @see Character#isLowerCase(char)
10431 * @see Character#isTitleCase(char)
10432 * @see Character#isUpperCase(char)
10433 * @since 1.0.2
10434 */
10435 public static boolean isDefined(char ch) {
10436 return isDefined((int)ch);
10437 }
10438
10439 /**
10440 * Determines if a character (Unicode code point) is defined in Unicode.
10441 * <p>
10442 * A character is defined if at least one of the following is true:
10443 * <ul>
10444 * <li>It has an entry in the UnicodeData file.
10445 * <li>It has a value in a range defined by the UnicodeData file.
10446 * </ul>
10447 *
10448 * @param codePoint the character (Unicode code point) to be tested.
10449 * @return {@code true} if the character has a defined meaning
10450 * in Unicode; {@code false} otherwise.
10451 * @see Character#isDigit(int)
10452 * @see Character#isLetter(int)
10453 * @see Character#isLetterOrDigit(int)
10454 * @see Character#isLowerCase(int)
10455 * @see Character#isTitleCase(int)
10456 * @see Character#isUpperCase(int)
10457 * @since 1.5
10458 */
10459 public static boolean isDefined(int codePoint) {
10460 return getType(codePoint) != Character.UNASSIGNED;
10461 }
10462
10463 /**
10464 * Determines if the specified character is a letter.
10465 * <p>
10466 * A character is considered to be a letter if its general
10467 * category type, provided by {@code Character.getType(ch)},
10468 * is any of the following:
10469 * <ul>
10470 * <li> {@code UPPERCASE_LETTER}
10471 * <li> {@code LOWERCASE_LETTER}
10472 * <li> {@code TITLECASE_LETTER}
10473 * <li> {@code MODIFIER_LETTER}
10474 * <li> {@code OTHER_LETTER}
10475 * </ul>
10476 *
10477 * Not all letters have case. Many characters are
10478 * letters but are neither uppercase nor lowercase nor titlecase.
10479 *
10480 * <p><b>Note:</b> This method cannot handle <a
10481 * href="#supplementary"> supplementary characters</a>. To support
10482 * all Unicode characters, including supplementary characters, use
10483 * the {@link #isLetter(int)} method.
10484 *
10485 * @param ch the character to be tested.
10486 * @return {@code true} if the character is a letter;
10487 * {@code false} otherwise.
10488 * @see Character#isDigit(char)
10489 * @see Character#isJavaIdentifierStart(char)
10490 * @see Character#isJavaLetter(char)
10491 * @see Character#isJavaLetterOrDigit(char)
10492 * @see Character#isLetterOrDigit(char)
10493 * @see Character#isLowerCase(char)
10494 * @see Character#isTitleCase(char)
10495 * @see Character#isUnicodeIdentifierStart(char)
10496 * @see Character#isUpperCase(char)
10497 */
10498 public static boolean isLetter(char ch) {
10499 return isLetter((int)ch);
10500 }
10501
10502 /**
10503 * Determines if the specified character (Unicode code point) is a letter.
10504 * <p>
10505 * A character is considered to be a letter if its general
10506 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10507 * is any of the following:
10508 * <ul>
10509 * <li> {@code UPPERCASE_LETTER}
10510 * <li> {@code LOWERCASE_LETTER}
10511 * <li> {@code TITLECASE_LETTER}
10512 * <li> {@code MODIFIER_LETTER}
10513 * <li> {@code OTHER_LETTER}
10514 * </ul>
10515 *
10516 * Not all letters have case. Many characters are
10517 * letters but are neither uppercase nor lowercase nor titlecase.
10518 *
10519 * @param codePoint the character (Unicode code point) to be tested.
10520 * @return {@code true} if the character is a letter;
10521 * {@code false} otherwise.
10522 * @see Character#isDigit(int)
10523 * @see Character#isJavaIdentifierStart(int)
10524 * @see Character#isLetterOrDigit(int)
10525 * @see Character#isLowerCase(int)
10526 * @see Character#isTitleCase(int)
10527 * @see Character#isUnicodeIdentifierStart(int)
10528 * @see Character#isUpperCase(int)
10529 * @since 1.5
10530 */
10531 public static boolean isLetter(int codePoint) {
10532 return ((((1 << Character.UPPERCASE_LETTER) |
10533 (1 << Character.LOWERCASE_LETTER) |
10534 (1 << Character.TITLECASE_LETTER) |
10535 (1 << Character.MODIFIER_LETTER) |
10536 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10537 != 0;
10538 }
10539
10540 /**
10541 * Determines if the specified character is a letter or digit.
10542 * <p>
10543 * A character is considered to be a letter or digit if either
10544 * {@code Character.isLetter(char ch)} or
10545 * {@code Character.isDigit(char ch)} returns
10546 * {@code true} for the character.
10547 *
10548 * <p><b>Note:</b> This method cannot handle <a
10549 * href="#supplementary"> supplementary characters</a>. To support
10550 * all Unicode characters, including supplementary characters, use
10551 * the {@link #isLetterOrDigit(int)} method.
10552 *
10553 * @param ch the character to be tested.
10554 * @return {@code true} if the character is a letter or digit;
10555 * {@code false} otherwise.
10556 * @see Character#isDigit(char)
10557 * @see Character#isJavaIdentifierPart(char)
10558 * @see Character#isJavaLetter(char)
10559 * @see Character#isJavaLetterOrDigit(char)
10560 * @see Character#isLetter(char)
10561 * @see Character#isUnicodeIdentifierPart(char)
10562 * @since 1.0.2
10563 */
10564 public static boolean isLetterOrDigit(char ch) {
10565 return isLetterOrDigit((int)ch);
10566 }
10567
10568 /**
10569 * Determines if the specified character (Unicode code point) is a letter or digit.
10570 * <p>
10571 * A character is considered to be a letter or digit if either
10572 * {@link #isLetter(int) isLetter(codePoint)} or
10573 * {@link #isDigit(int) isDigit(codePoint)} returns
10574 * {@code true} for the character.
10575 *
10576 * @param codePoint the character (Unicode code point) to be tested.
10577 * @return {@code true} if the character is a letter or digit;
10578 * {@code false} otherwise.
10579 * @see Character#isDigit(int)
10580 * @see Character#isJavaIdentifierPart(int)
10581 * @see Character#isLetter(int)
10582 * @see Character#isUnicodeIdentifierPart(int)
10583 * @since 1.5
10584 */
10585 public static boolean isLetterOrDigit(int codePoint) {
10586 return ((((1 << Character.UPPERCASE_LETTER) |
10587 (1 << Character.LOWERCASE_LETTER) |
10588 (1 << Character.TITLECASE_LETTER) |
10589 (1 << Character.MODIFIER_LETTER) |
10590 (1 << Character.OTHER_LETTER) |
10591 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10592 != 0;
10593 }
10594
10595 /**
10596 * Determines if the specified character is permissible as the first
10597 * character in a Java identifier.
10598 * <p>
10599 * A character may start a Java identifier if and only if
10600 * one of the following conditions is true:
10601 * <ul>
10602 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10603 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10604 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10605 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10606 * </ul>
10607 *
10608 * @param ch the character to be tested.
10609 * @return {@code true} if the character may start a Java
10610 * identifier; {@code false} otherwise.
10611 * @see Character#isJavaLetterOrDigit(char)
10612 * @see Character#isJavaIdentifierStart(char)
10613 * @see Character#isJavaIdentifierPart(char)
10614 * @see Character#isLetter(char)
10615 * @see Character#isLetterOrDigit(char)
10616 * @see Character#isUnicodeIdentifierStart(char)
10617 * @since 1.0.2
10618 * @deprecated Replaced by isJavaIdentifierStart(char).
10619 */
10620 @Deprecated(since="1.1")
10621 public static boolean isJavaLetter(char ch) {
10622 return isJavaIdentifierStart(ch);
10623 }
10624
10625 /**
10626 * Determines if the specified character may be part of a Java
10627 * identifier as other than the first character.
10628 * <p>
10629 * A character may be part of a Java identifier if and only if one
10630 * of the following conditions is true:
10631 * <ul>
10632 * <li> it is a letter
10633 * <li> it is a currency symbol (such as {@code '$'})
10634 * <li> it is a connecting punctuation character (such as {@code '_'})
10635 * <li> it is a digit
10636 * <li> it is a numeric letter (such as a Roman numeral character)
10637 * <li> it is a combining mark
10638 * <li> it is a non-spacing mark
10639 * <li> {@code isIdentifierIgnorable} returns
10640 * {@code true} for the character.
10641 * </ul>
10642 *
10643 * @param ch the character to be tested.
10644 * @return {@code true} if the character may be part of a
10645 * Java identifier; {@code false} otherwise.
10646 * @see Character#isJavaLetter(char)
10647 * @see Character#isJavaIdentifierStart(char)
10648 * @see Character#isJavaIdentifierPart(char)
10649 * @see Character#isLetter(char)
10650 * @see Character#isLetterOrDigit(char)
10651 * @see Character#isUnicodeIdentifierPart(char)
10652 * @see Character#isIdentifierIgnorable(char)
10653 * @since 1.0.2
10654 * @deprecated Replaced by isJavaIdentifierPart(char).
10655 */
10656 @Deprecated(since="1.1")
10657 public static boolean isJavaLetterOrDigit(char ch) {
10658 return isJavaIdentifierPart(ch);
10659 }
10660
10661 /**
10662 * Determines if the specified character (Unicode code point) is alphabetic.
10663 * <p>
10664 * A character is considered to be alphabetic if its general category type,
10665 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10666 * the following:
10667 * <ul>
10668 * <li> {@code UPPERCASE_LETTER}
10669 * <li> {@code LOWERCASE_LETTER}
10670 * <li> {@code TITLECASE_LETTER}
10671 * <li> {@code MODIFIER_LETTER}
10672 * <li> {@code OTHER_LETTER}
10673 * <li> {@code LETTER_NUMBER}
10674 * </ul>
10675 * or it has contributory property Other_Alphabetic as defined by the
10676 * Unicode Standard.
10677 *
10678 * @param codePoint the character (Unicode code point) to be tested.
10679 * @return {@code true} if the character is a Unicode alphabet
10680 * character, {@code false} otherwise.
10681 * @since 1.7
10682 */
10683 public static boolean isAlphabetic(int codePoint) {
10684 return (((((1 << Character.UPPERCASE_LETTER) |
10685 (1 << Character.LOWERCASE_LETTER) |
10686 (1 << Character.TITLECASE_LETTER) |
10687 (1 << Character.MODIFIER_LETTER) |
10688 (1 << Character.OTHER_LETTER) |
10689 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10690 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10691 }
10692
10693 /**
10694 * Determines if the specified character (Unicode code point) is a CJKV
10695 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10696 * the Unicode Standard.
10697 *
10698 * @param codePoint the character (Unicode code point) to be tested.
10699 * @return {@code true} if the character is a Unicode ideograph
10700 * character, {@code false} otherwise.
10701 * @since 1.7
10702 */
10703 public static boolean isIdeographic(int codePoint) {
10704 return CharacterData.of(codePoint).isIdeographic(codePoint);
10705 }
10706
10707 /**
10708 * Determines if the specified character is
10709 * permissible as the first character in a Java identifier.
10710 * <p>
10711 * A character may start a Java identifier if and only if
10712 * one of the following conditions is true:
10713 * <ul>
10714 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10715 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10716 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10717 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10718 * </ul>
10719 *
10720 * <p><b>Note:</b> This method cannot handle <a
10721 * href="#supplementary"> supplementary characters</a>. To support
10722 * all Unicode characters, including supplementary characters, use
10723 * the {@link #isJavaIdentifierStart(int)} method.
10724 *
10725 * @param ch the character to be tested.
10726 * @return {@code true} if the character may start a Java identifier;
10727 * {@code false} otherwise.
10728 * @see Character#isJavaIdentifierPart(char)
10729 * @see Character#isLetter(char)
10730 * @see Character#isUnicodeIdentifierStart(char)
10731 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10732 * @since 1.1
10733 */
10734 @SuppressWarnings("doclint:reference") // cross-module links
10735 public static boolean isJavaIdentifierStart(char ch) {
10736 return isJavaIdentifierStart((int)ch);
10737 }
10738
10739 /**
10740 * Determines if the character (Unicode code point) is
10741 * permissible as the first character in a Java identifier.
10742 * <p>
10743 * A character may start a Java identifier if and only if
10744 * one of the following conditions is true:
10745 * <ul>
10746 * <li> {@link #isLetter(int) isLetter(codePoint)}
10747 * returns {@code true}
10748 * <li> {@link #getType(int) getType(codePoint)}
10749 * returns {@code LETTER_NUMBER}
10750 * <li> the referenced character is a currency symbol (such as {@code '$'})
10751 * <li> the referenced character is a connecting punctuation character
10752 * (such as {@code '_'}).
10753 * </ul>
10754 *
10755 * @param codePoint the character (Unicode code point) to be tested.
10756 * @return {@code true} if the character may start a Java identifier;
10757 * {@code false} otherwise.
10758 * @see Character#isJavaIdentifierPart(int)
10759 * @see Character#isLetter(int)
10760 * @see Character#isUnicodeIdentifierStart(int)
10761 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10762 * @since 1.5
10763 */
10764 @SuppressWarnings("doclint:reference") // cross-module links
10765 public static boolean isJavaIdentifierStart(int codePoint) {
10766 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10767 }
10768
10769 /**
10770 * Determines if the specified character may be part of a Java
10771 * identifier as other than the first character.
10772 * <p>
10773 * A character may be part of a Java identifier if any of the following
10774 * conditions are true:
10775 * <ul>
10776 * <li> it is a letter
10777 * <li> it is a currency symbol (such as {@code '$'})
10778 * <li> it is a connecting punctuation character (such as {@code '_'})
10779 * <li> it is a digit
10780 * <li> it is a numeric letter (such as a Roman numeral character)
10781 * <li> it is a combining mark
10782 * <li> it is a non-spacing mark
10783 * <li> {@code isIdentifierIgnorable} returns
10784 * {@code true} for the character
10785 * </ul>
10786 *
10787 * <p><b>Note:</b> This method cannot handle <a
10788 * href="#supplementary"> supplementary characters</a>. To support
10789 * all Unicode characters, including supplementary characters, use
10790 * the {@link #isJavaIdentifierPart(int)} method.
10791 *
10792 * @param ch the character to be tested.
10793 * @return {@code true} if the character may be part of a
10794 * Java identifier; {@code false} otherwise.
10795 * @see Character#isIdentifierIgnorable(char)
10796 * @see Character#isJavaIdentifierStart(char)
10797 * @see Character#isLetterOrDigit(char)
10798 * @see Character#isUnicodeIdentifierPart(char)
10799 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10800 * @since 1.1
10801 */
10802 @SuppressWarnings("doclint:reference") // cross-module links
10803 public static boolean isJavaIdentifierPart(char ch) {
10804 return isJavaIdentifierPart((int)ch);
10805 }
10806
10807 /**
10808 * Determines if the character (Unicode code point) may be part of a Java
10809 * identifier as other than the first character.
10810 * <p>
10811 * A character may be part of a Java identifier if any of the following
10812 * conditions are true:
10813 * <ul>
10814 * <li> it is a letter
10815 * <li> it is a currency symbol (such as {@code '$'})
10816 * <li> it is a connecting punctuation character (such as {@code '_'})
10817 * <li> it is a digit
10818 * <li> it is a numeric letter (such as a Roman numeral character)
10819 * <li> it is a combining mark
10820 * <li> it is a non-spacing mark
10821 * <li> {@link #isIdentifierIgnorable(int)
10822 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10823 * the code point
10824 * </ul>
10825 *
10826 * @param codePoint the character (Unicode code point) to be tested.
10827 * @return {@code true} if the character may be part of a
10828 * Java identifier; {@code false} otherwise.
10829 * @see Character#isIdentifierIgnorable(int)
10830 * @see Character#isJavaIdentifierStart(int)
10831 * @see Character#isLetterOrDigit(int)
10832 * @see Character#isUnicodeIdentifierPart(int)
10833 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10834 * @since 1.5
10835 */
10836 @SuppressWarnings("doclint:reference") // cross-module links
10837 public static boolean isJavaIdentifierPart(int codePoint) {
10838 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10839 }
10840
10841 /**
10842 * Determines if the specified character is permissible as the
10843 * first character in a Unicode identifier.
10844 * <p>
10845 * A character may start a Unicode identifier if and only if
10846 * one of the following conditions is true:
10847 * <ul>
10848 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10849 * <li> {@link #getType(char) getType(ch)} returns
10850 * {@code LETTER_NUMBER}.
10851 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10852 * {@code Other_ID_Start}</a> character.
10853 * </ul>
10854 * <p>
10855 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10856 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10857 * with the following profile of UAX31:
10858 * <pre>
10859 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10860 * </pre>
10861 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10862 * compatibility.
10863 *
10864 * <p><b>Note:</b> This method cannot handle <a
10865 * href="#supplementary"> supplementary characters</a>. To support
10866 * all Unicode characters, including supplementary characters, use
10867 * the {@link #isUnicodeIdentifierStart(int)} method.
10868 *
10869 * @param ch the character to be tested.
10870 * @return {@code true} if the character may start a Unicode
10871 * identifier; {@code false} otherwise.
10872 *
10873 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10874 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10875 * @see Character#isJavaIdentifierStart(char)
10876 * @see Character#isLetter(char)
10877 * @see Character#isUnicodeIdentifierPart(char)
10878 * @since 1.1
10879 */
10880 public static boolean isUnicodeIdentifierStart(char ch) {
10881 return isUnicodeIdentifierStart((int)ch);
10882 }
10883
10884 /**
10885 * Determines if the specified character (Unicode code point) is permissible as the
10886 * first character in a Unicode identifier.
10887 * <p>
10888 * A character may start a Unicode identifier if and only if
10889 * one of the following conditions is true:
10890 * <ul>
10891 * <li> {@link #isLetter(int) isLetter(codePoint)}
10892 * returns {@code true}
10893 * <li> {@link #getType(int) getType(codePoint)}
10894 * returns {@code LETTER_NUMBER}.
10895 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10896 * {@code Other_ID_Start}</a> character.
10897 * </ul>
10898 * <p>
10899 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10900 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10901 * with the following profile of UAX31:
10902 * <pre>
10903 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10904 * </pre>
10905 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10906 * compatibility.
10907 *
10908 * @param codePoint the character (Unicode code point) to be tested.
10909 * @return {@code true} if the character may start a Unicode
10910 * identifier; {@code false} otherwise.
10911 *
10912 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10913 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10914 * @see Character#isJavaIdentifierStart(int)
10915 * @see Character#isLetter(int)
10916 * @see Character#isUnicodeIdentifierPart(int)
10917 * @since 1.5
10918 */
10919 public static boolean isUnicodeIdentifierStart(int codePoint) {
10920 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
10921 }
10922
10923 /**
10924 * Determines if the specified character may be part of a Unicode
10925 * identifier as other than the first character.
10926 * <p>
10927 * A character may be part of a Unicode identifier if and only if
10928 * one of the following statements is true:
10929 * <ul>
10930 * <li> it is a letter
10931 * <li> it is a connecting punctuation character (such as {@code '_'})
10932 * <li> it is a digit
10933 * <li> it is a numeric letter (such as a Roman numeral character)
10934 * <li> it is a combining mark
10935 * <li> it is a non-spacing mark
10936 * <li> {@code isIdentifierIgnorable} returns
10937 * {@code true} for this character.
10938 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10939 * {@code Other_ID_Start}</a> character.
10940 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10941 * {@code Other_ID_Continue}</a> character.
10942 * </ul>
10943 * <p>
10944 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10945 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10946 * with the following profile of UAX31:
10947 * <pre>
10948 * Continue := Start + ID_Continue + ignorable
10949 * Medial := empty
10950 * ignorable := isIdentifierIgnorable(char) returns true for the character
10951 * </pre>
10952 * {@code ignorable} is added to {@code Continue} for backward
10953 * compatibility.
10954 *
10955 * <p><b>Note:</b> This method cannot handle <a
10956 * href="#supplementary"> supplementary characters</a>. To support
10957 * all Unicode characters, including supplementary characters, use
10958 * the {@link #isUnicodeIdentifierPart(int)} method.
10959 *
10960 * @param ch the character to be tested.
10961 * @return {@code true} if the character may be part of a
10962 * Unicode identifier; {@code false} otherwise.
10963 *
10964 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10965 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10966 * @see Character#isIdentifierIgnorable(char)
10967 * @see Character#isJavaIdentifierPart(char)
10968 * @see Character#isLetterOrDigit(char)
10969 * @see Character#isUnicodeIdentifierStart(char)
10970 * @since 1.1
10971 */
10972 public static boolean isUnicodeIdentifierPart(char ch) {
10973 return isUnicodeIdentifierPart((int)ch);
10974 }
10975
10976 /**
10977 * Determines if the specified character (Unicode code point) may be part of a Unicode
10978 * identifier as other than the first character.
10979 * <p>
10980 * A character may be part of a Unicode identifier if and only if
10981 * one of the following statements is true:
10982 * <ul>
10983 * <li> it is a letter
10984 * <li> it is a connecting punctuation character (such as {@code '_'})
10985 * <li> it is a digit
10986 * <li> it is a numeric letter (such as a Roman numeral character)
10987 * <li> it is a combining mark
10988 * <li> it is a non-spacing mark
10989 * <li> {@code isIdentifierIgnorable} returns
10990 * {@code true} for this character.
10991 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10992 * {@code Other_ID_Start}</a> character.
10993 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10994 * {@code Other_ID_Continue}</a> character.
10995 * </ul>
10996 * <p>
10997 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10998 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10999 * with the following profile of UAX31:
11000 * <pre>
11001 * Continue := Start + ID_Continue + ignorable
11002 * Medial := empty
11003 * ignorable := isIdentifierIgnorable(int) returns true for the character
11004 * </pre>
11005 * {@code ignorable} is added to {@code Continue} for backward
11006 * compatibility.
11007 *
11008 * @param codePoint the character (Unicode code point) to be tested.
11009 * @return {@code true} if the character may be part of a
11010 * Unicode identifier; {@code false} otherwise.
11011 *
11012 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11013 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11014 * @see Character#isIdentifierIgnorable(int)
11015 * @see Character#isJavaIdentifierPart(int)
11016 * @see Character#isLetterOrDigit(int)
11017 * @see Character#isUnicodeIdentifierStart(int)
11018 * @since 1.5
11019 */
11020 public static boolean isUnicodeIdentifierPart(int codePoint) {
11021 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
11022 }
11023
11024 /**
11025 * Determines if the specified character should be regarded as
11026 * an ignorable character in a Java identifier or a Unicode identifier.
11027 * <p>
11028 * The following Unicode characters are ignorable in a Java identifier
11029 * or a Unicode identifier:
11030 * <ul>
11031 * <li>ISO control characters that are not whitespace
11032 * <ul>
11033 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11034 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11035 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11036 * </ul>
11037 *
11038 * <li>all characters that have the {@code FORMAT} general
11039 * category value
11040 * </ul>
11041 *
11042 * <p><b>Note:</b> This method cannot handle <a
11043 * href="#supplementary"> supplementary characters</a>. To support
11044 * all Unicode characters, including supplementary characters, use
11045 * the {@link #isIdentifierIgnorable(int)} method.
11046 *
11047 * @param ch the character to be tested.
11048 * @return {@code true} if the character is an ignorable control
11049 * character that may be part of a Java or Unicode identifier;
11050 * {@code false} otherwise.
11051 * @see Character#isJavaIdentifierPart(char)
11052 * @see Character#isUnicodeIdentifierPart(char)
11053 * @since 1.1
11054 */
11055 public static boolean isIdentifierIgnorable(char ch) {
11056 return isIdentifierIgnorable((int)ch);
11057 }
11058
11059 /**
11060 * Determines if the specified character (Unicode code point) should be regarded as
11061 * an ignorable character in a Java identifier or a Unicode identifier.
11062 * <p>
11063 * The following Unicode characters are ignorable in a Java identifier
11064 * or a Unicode identifier:
11065 * <ul>
11066 * <li>ISO control characters that are not whitespace
11067 * <ul>
11068 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11069 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11070 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11071 * </ul>
11072 *
11073 * <li>all characters that have the {@code FORMAT} general
11074 * category value
11075 * </ul>
11076 *
11077 * @param codePoint the character (Unicode code point) to be tested.
11078 * @return {@code true} if the character is an ignorable control
11079 * character that may be part of a Java or Unicode identifier;
11080 * {@code false} otherwise.
11081 * @see Character#isJavaIdentifierPart(int)
11082 * @see Character#isUnicodeIdentifierPart(int)
11083 * @since 1.5
11084 */
11085 public static boolean isIdentifierIgnorable(int codePoint) {
11086 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
11087 }
11088
11089 /**
11090 * Determines if the specified character (Unicode code point) is an Emoji.
11091 * <p>
11092 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
11093 * property, defined in
11094 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11095 * Unicode Emoji (Technical Standard #51)</a>.
11096 *
11097 * @param codePoint the character (Unicode code point) to be tested.
11098 * @return {@code true} if the character is an Emoji;
11099 * {@code false} otherwise.
11100 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11101 * @since 21
11102 */
11103 public static boolean isEmoji(int codePoint) {
11104 return CharacterData.of(codePoint).isEmoji(codePoint);
11105 }
11106
11107 /**
11108 * Determines if the specified character (Unicode code point) has the
11109 * Emoji Presentation property by default.
11110 * <p>
11111 * A character is considered to have the Emoji Presentation property if and
11112 * only if it has the {@code Emoji_Presentation} property, defined in
11113 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11114 * Unicode Emoji (Technical Standard #51)</a>.
11115 *
11116 * @param codePoint the character (Unicode code point) to be tested.
11117 * @return {@code true} if the character has the Emoji Presentation
11118 * property; {@code false} otherwise.
11119 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11120 * @since 21
11121 */
11122 public static boolean isEmojiPresentation(int codePoint) {
11123 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
11124 }
11125
11126 /**
11127 * Determines if the specified character (Unicode code point) is an
11128 * Emoji Modifier.
11129 * <p>
11130 * A character is considered to be an Emoji Modifier if and only if it has
11131 * the {@code Emoji_Modifier} property, defined in
11132 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11133 * Unicode Emoji (Technical Standard #51)</a>.
11134 *
11135 * @param codePoint the character (Unicode code point) to be tested.
11136 * @return {@code true} if the character is an Emoji Modifier;
11137 * {@code false} otherwise.
11138 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11139 * @since 21
11140 */
11141 public static boolean isEmojiModifier(int codePoint) {
11142 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
11143 }
11144
11145 /**
11146 * Determines if the specified character (Unicode code point) is an
11147 * Emoji Modifier Base.
11148 * <p>
11149 * A character is considered to be an Emoji Modifier Base if and only if it has
11150 * the {@code Emoji_Modifier_Base} property, defined in
11151 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11152 * Unicode Emoji (Technical Standard #51)</a>.
11153 *
11154 * @param codePoint the character (Unicode code point) to be tested.
11155 * @return {@code true} if the character is an Emoji Modifier Base;
11156 * {@code false} otherwise.
11157 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11158 * @since 21
11159 */
11160 public static boolean isEmojiModifierBase(int codePoint) {
11161 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
11162 }
11163
11164 /**
11165 * Determines if the specified character (Unicode code point) is an
11166 * Emoji Component.
11167 * <p>
11168 * A character is considered to be an Emoji Component if and only if it has
11169 * the {@code Emoji_Component} property, defined in
11170 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11171 * Unicode Emoji (Technical Standard #51)</a>.
11172 *
11173 * @param codePoint the character (Unicode code point) to be tested.
11174 * @return {@code true} if the character is an Emoji Component;
11175 * {@code false} otherwise.
11176 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11177 * @since 21
11178 */
11179 public static boolean isEmojiComponent(int codePoint) {
11180 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
11181 }
11182
11183 /**
11184 * Determines if the specified character (Unicode code point) is
11185 * an Extended Pictographic.
11186 * <p>
11187 * A character is considered to be an Extended Pictographic if and only if it has
11188 * the {@code Extended_Pictographic} property, defined in
11189 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11190 * Unicode Emoji (Technical Standard #51)</a>.
11191 *
11192 * @param codePoint the character (Unicode code point) to be tested.
11193 * @return {@code true} if the character is an Extended Pictographic;
11194 * {@code false} otherwise.
11195 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11196 * @since 21
11197 */
11198 public static boolean isExtendedPictographic(int codePoint) {
11199 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
11200 }
11201
11202 /**
11203 * Converts the character argument to lowercase using case
11204 * mapping information from the UnicodeData file.
11205 * <p>
11206 * Note that
11207 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
11208 * does not always return {@code true} for some ranges of
11209 * characters, particularly those that are symbols or ideographs.
11210 *
11211 * <p>In general, {@link String#toLowerCase()} should be used to map
11212 * characters to lowercase. {@code String} case mapping methods
11213 * have several benefits over {@code Character} case mapping methods.
11214 * {@code String} case mapping methods can perform locale-sensitive
11215 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11216 * the {@code Character} case mapping methods cannot.
11217 *
11218 * <p><b>Note:</b> This method cannot handle <a
11219 * href="#supplementary"> supplementary characters</a>. To support
11220 * all Unicode characters, including supplementary characters, use
11221 * the {@link #toLowerCase(int)} method.
11222 *
11223 * @param ch the character to be converted.
11224 * @return the lowercase equivalent of the character, if any;
11225 * otherwise, the character itself.
11226 * @see Character#isLowerCase(char)
11227 * @see String#toLowerCase()
11228 */
11229 public static char toLowerCase(char ch) {
11230 return (char)toLowerCase((int)ch);
11231 }
11232
11233 /**
11234 * Converts the character (Unicode code point) argument to
11235 * lowercase using case mapping information from the UnicodeData
11236 * file.
11237 *
11238 * <p> Note that
11239 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
11240 * does not always return {@code true} for some ranges of
11241 * characters, particularly those that are symbols or ideographs.
11242 *
11243 * <p>In general, {@link String#toLowerCase()} should be used to map
11244 * characters to lowercase. {@code String} case mapping methods
11245 * have several benefits over {@code Character} case mapping methods.
11246 * {@code String} case mapping methods can perform locale-sensitive
11247 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11248 * the {@code Character} case mapping methods cannot.
11249 *
11250 * @param codePoint the character (Unicode code point) to be converted.
11251 * @return the lowercase equivalent of the character (Unicode code
11252 * point), if any; otherwise, the character itself.
11253 * @see Character#isLowerCase(int)
11254 * @see String#toLowerCase()
11255 *
11256 * @since 1.5
11257 */
11258 public static int toLowerCase(int codePoint) {
11259 return CharacterData.of(codePoint).toLowerCase(codePoint);
11260 }
11261
11262 /**
11263 * Converts the character argument to uppercase using case mapping
11264 * information from the UnicodeData file.
11265 * <p>
11266 * Note that
11267 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
11268 * does not always return {@code true} for some ranges of
11269 * characters, particularly those that are symbols or ideographs.
11270 *
11271 * <p>In general, {@link String#toUpperCase()} should be used to map
11272 * characters to uppercase. {@code String} case mapping methods
11273 * have several benefits over {@code Character} case mapping methods.
11274 * {@code String} case mapping methods can perform locale-sensitive
11275 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11276 * the {@code Character} case mapping methods cannot.
11277 *
11278 * <p><b>Note:</b> This method cannot handle <a
11279 * href="#supplementary"> supplementary characters</a>. To support
11280 * all Unicode characters, including supplementary characters, use
11281 * the {@link #toUpperCase(int)} method.
11282 *
11283 * @param ch the character to be converted.
11284 * @return the uppercase equivalent of the character, if any;
11285 * otherwise, the character itself.
11286 * @see Character#isUpperCase(char)
11287 * @see String#toUpperCase()
11288 */
11289 public static char toUpperCase(char ch) {
11290 return (char)toUpperCase((int)ch);
11291 }
11292
11293 /**
11294 * Converts the character (Unicode code point) argument to
11295 * uppercase using case mapping information from the UnicodeData
11296 * file.
11297 *
11298 * <p>Note that
11299 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11300 * does not always return {@code true} for some ranges of
11301 * characters, particularly those that are symbols or ideographs.
11302 *
11303 * <p>In general, {@link String#toUpperCase()} should be used to map
11304 * characters to uppercase. {@code String} case mapping methods
11305 * have several benefits over {@code Character} case mapping methods.
11306 * {@code String} case mapping methods can perform locale-sensitive
11307 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11308 * the {@code Character} case mapping methods cannot.
11309 *
11310 * @param codePoint the character (Unicode code point) to be converted.
11311 * @return the uppercase equivalent of the character, if any;
11312 * otherwise, the character itself.
11313 * @see Character#isUpperCase(int)
11314 * @see String#toUpperCase()
11315 *
11316 * @since 1.5
11317 */
11318 public static int toUpperCase(int codePoint) {
11319 return CharacterData.of(codePoint).toUpperCase(codePoint);
11320 }
11321
11322 /**
11323 * Converts the character argument to titlecase using case mapping
11324 * information from the UnicodeData file. If a character has no
11325 * explicit titlecase mapping and is not itself a titlecase char
11326 * according to UnicodeData, then the uppercase mapping is
11327 * returned as an equivalent titlecase mapping. If the
11328 * {@code char} argument is already a titlecase
11329 * {@code char}, the same {@code char} value will be
11330 * returned.
11331 * <p>
11332 * Note that
11333 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11334 * does not always return {@code true} for some ranges of
11335 * characters.
11336 *
11337 * <p><b>Note:</b> This method cannot handle <a
11338 * href="#supplementary"> supplementary characters</a>. To support
11339 * all Unicode characters, including supplementary characters, use
11340 * the {@link #toTitleCase(int)} method.
11341 *
11342 * @param ch the character to be converted.
11343 * @return the titlecase equivalent of the character, if any;
11344 * otherwise, the character itself.
11345 * @see Character#isTitleCase(char)
11346 * @see Character#toLowerCase(char)
11347 * @see Character#toUpperCase(char)
11348 * @since 1.0.2
11349 */
11350 public static char toTitleCase(char ch) {
11351 return (char)toTitleCase((int)ch);
11352 }
11353
11354 /**
11355 * Converts the character (Unicode code point) argument to titlecase using case mapping
11356 * information from the UnicodeData file. If a character has no
11357 * explicit titlecase mapping and is not itself a titlecase char
11358 * according to UnicodeData, then the uppercase mapping is
11359 * returned as an equivalent titlecase mapping. If the
11360 * character argument is already a titlecase
11361 * character, the same character value will be
11362 * returned.
11363 *
11364 * <p>Note that
11365 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11366 * does not always return {@code true} for some ranges of
11367 * characters.
11368 *
11369 * @param codePoint the character (Unicode code point) to be converted.
11370 * @return the titlecase equivalent of the character, if any;
11371 * otherwise, the character itself.
11372 * @see Character#isTitleCase(int)
11373 * @see Character#toLowerCase(int)
11374 * @see Character#toUpperCase(int)
11375 * @since 1.5
11376 */
11377 public static int toTitleCase(int codePoint) {
11378 return CharacterData.of(codePoint).toTitleCase(codePoint);
11379 }
11380
11381 /**
11382 * Returns the numeric value of the character {@code ch} in the
11383 * specified radix.
11384 * <p>
11385 * If the radix is not in the range {@code MIN_RADIX} ≤
11386 * {@code radix} ≤ {@code MAX_RADIX} or if the
11387 * value of {@code ch} is not a valid digit in the specified
11388 * radix, {@code -1} is returned. A character is a valid digit
11389 * if at least one of the following is true:
11390 * <ul>
11391 * <li>The method {@code isDigit} is {@code true} of the character
11392 * and the Unicode decimal digit value of the character (or its
11393 * single-character decomposition) is less than the specified radix.
11394 * In this case the decimal digit value is returned.
11395 * <li>The character is one of the uppercase Latin letters
11396 * {@code 'A'} through {@code 'Z'} and its code is less than
11397 * {@code radix + 'A' - 10}.
11398 * In this case, {@code ch - 'A' + 10}
11399 * is returned.
11400 * <li>The character is one of the lowercase Latin letters
11401 * {@code 'a'} through {@code 'z'} and its code is less than
11402 * {@code radix + 'a' - 10}.
11403 * In this case, {@code ch - 'a' + 10}
11404 * is returned.
11405 * <li>The character is one of the fullwidth uppercase Latin letters A
11406 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11407 * and its code is less than
11408 * {@code radix + '\u005CuFF21' - 10}.
11409 * In this case, {@code ch - '\u005CuFF21' + 10}
11410 * is returned.
11411 * <li>The character is one of the fullwidth lowercase Latin letters a
11412 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11413 * and its code is less than
11414 * {@code radix + '\u005CuFF41' - 10}.
11415 * In this case, {@code ch - '\u005CuFF41' + 10}
11416 * is returned.
11417 * </ul>
11418 *
11419 * <p><b>Note:</b> This method cannot handle <a
11420 * href="#supplementary"> supplementary characters</a>. To support
11421 * all Unicode characters, including supplementary characters, use
11422 * the {@link #digit(int, int)} method.
11423 *
11424 * @param ch the character to be converted.
11425 * @param radix the radix.
11426 * @return the numeric value represented by the character in the
11427 * specified radix.
11428 * @see Character#forDigit(int, int)
11429 * @see Character#isDigit(char)
11430 */
11431 public static int digit(char ch, int radix) {
11432 return digit((int)ch, radix);
11433 }
11434
11435 /**
11436 * Returns the numeric value of the specified character (Unicode
11437 * code point) in the specified radix.
11438 *
11439 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11440 * {@code radix} ≤ {@code MAX_RADIX} or if the
11441 * character is not a valid digit in the specified
11442 * radix, {@code -1} is returned. A character is a valid digit
11443 * if at least one of the following is true:
11444 * <ul>
11445 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11446 * and the Unicode decimal digit value of the character (or its
11447 * single-character decomposition) is less than the specified radix.
11448 * In this case the decimal digit value is returned.
11449 * <li>The character is one of the uppercase Latin letters
11450 * {@code 'A'} through {@code 'Z'} and its code is less than
11451 * {@code radix + 'A' - 10}.
11452 * In this case, {@code codePoint - 'A' + 10}
11453 * is returned.
11454 * <li>The character is one of the lowercase Latin letters
11455 * {@code 'a'} through {@code 'z'} and its code is less than
11456 * {@code radix + 'a' - 10}.
11457 * In this case, {@code codePoint - 'a' + 10}
11458 * is returned.
11459 * <li>The character is one of the fullwidth uppercase Latin letters A
11460 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11461 * and its code is less than
11462 * {@code radix + '\u005CuFF21' - 10}.
11463 * In this case,
11464 * {@code codePoint - '\u005CuFF21' + 10}
11465 * is returned.
11466 * <li>The character is one of the fullwidth lowercase Latin letters a
11467 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11468 * and its code is less than
11469 * {@code radix + '\u005CuFF41'- 10}.
11470 * In this case,
11471 * {@code codePoint - '\u005CuFF41' + 10}
11472 * is returned.
11473 * </ul>
11474 *
11475 * @param codePoint the character (Unicode code point) to be converted.
11476 * @param radix the radix.
11477 * @return the numeric value represented by the character in the
11478 * specified radix.
11479 * @see Character#forDigit(int, int)
11480 * @see Character#isDigit(int)
11481 * @since 1.5
11482 */
11483 public static int digit(int codePoint, int radix) {
11484 return CharacterData.of(codePoint).digit(codePoint, radix);
11485 }
11486
11487 /**
11488 * Returns the {@code int} value that the specified Unicode
11489 * character represents. For example, the character
11490 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11491 * an int with a value of 50.
11492 * <p>
11493 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11494 * {@code '\u005Cu005A'}), lowercase
11495 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11496 * full width variant ({@code '\u005CuFF21'} through
11497 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11498 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11499 * through 35. This is independent of the Unicode specification,
11500 * which does not assign numeric values to these {@code char}
11501 * values.
11502 * <p>
11503 * If the character does not have a numeric value, then -1 is returned.
11504 * If the character has a numeric value that cannot be represented as a
11505 * nonnegative integer (for example, a fractional value), then -2
11506 * is returned.
11507 *
11508 * <p><b>Note:</b> This method cannot handle <a
11509 * href="#supplementary"> supplementary characters</a>. To support
11510 * all Unicode characters, including supplementary characters, use
11511 * the {@link #getNumericValue(int)} method.
11512 *
11513 * @param ch the character to be converted.
11514 * @return the numeric value of the character, as a nonnegative {@code int}
11515 * value; -2 if the character has a numeric value but the value
11516 * can not be represented as a nonnegative {@code int} value;
11517 * -1 if the character has no numeric value.
11518 * @see Character#forDigit(int, int)
11519 * @see Character#isDigit(char)
11520 * @since 1.1
11521 */
11522 public static int getNumericValue(char ch) {
11523 return getNumericValue((int)ch);
11524 }
11525
11526 /**
11527 * Returns the {@code int} value that the specified
11528 * character (Unicode code point) represents. For example, the character
11529 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11530 * an {@code int} with a value of 50.
11531 * <p>
11532 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11533 * {@code '\u005Cu005A'}), lowercase
11534 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11535 * full width variant ({@code '\u005CuFF21'} through
11536 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11537 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11538 * through 35. This is independent of the Unicode specification,
11539 * which does not assign numeric values to these {@code char}
11540 * values.
11541 * <p>
11542 * If the character does not have a numeric value, then -1 is returned.
11543 * If the character has a numeric value that cannot be represented as a
11544 * nonnegative integer (for example, a fractional value), then -2
11545 * is returned.
11546 *
11547 * @param codePoint the character (Unicode code point) to be converted.
11548 * @return the numeric value of the character, as a nonnegative {@code int}
11549 * value; -2 if the character has a numeric value but the value
11550 * can not be represented as a nonnegative {@code int} value;
11551 * -1 if the character has no numeric value.
11552 * @see Character#forDigit(int, int)
11553 * @see Character#isDigit(int)
11554 * @since 1.5
11555 */
11556 public static int getNumericValue(int codePoint) {
11557 return CharacterData.of(codePoint).getNumericValue(codePoint);
11558 }
11559
11560 /**
11561 * Determines if the specified character is ISO-LATIN-1 white space.
11562 * This method returns {@code true} for the following five
11563 * characters only:
11564 * <table class="striped">
11565 * <caption style="display:none">truechars</caption>
11566 * <thead>
11567 * <tr><th scope="col">Character
11568 * <th scope="col">Code
11569 * <th scope="col">Name
11570 * </thead>
11571 * <tbody>
11572 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11573 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11574 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11575 * <td>{@code NEW LINE}</td></tr>
11576 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11577 * <td>{@code FORM FEED}</td></tr>
11578 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11579 * <td>{@code CARRIAGE RETURN}</td></tr>
11580 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11581 * <td>{@code SPACE}</td></tr>
11582 * </tbody>
11583 * </table>
11584 *
11585 * @param ch the character to be tested.
11586 * @return {@code true} if the character is ISO-LATIN-1 white
11587 * space; {@code false} otherwise.
11588 * @see Character#isSpaceChar(char)
11589 * @see Character#isWhitespace(char)
11590 * @deprecated Replaced by isWhitespace(char).
11591 */
11592 @Deprecated(since="1.1")
11593 public static boolean isSpace(char ch) {
11594 return (ch <= 0x0020) &&
11595 (((((1L << 0x0009) |
11596 (1L << 0x000A) |
11597 (1L << 0x000C) |
11598 (1L << 0x000D) |
11599 (1L << 0x0020)) >> ch) & 1L) != 0);
11600 }
11601
11602
11603 /**
11604 * Determines if the specified character is a Unicode space character.
11605 * A character is considered to be a space character if and only if
11606 * it is specified to be a space character by the Unicode Standard. This
11607 * method returns true if the character's general category type is any of
11608 * the following:
11609 * <ul>
11610 * <li> {@code SPACE_SEPARATOR}
11611 * <li> {@code LINE_SEPARATOR}
11612 * <li> {@code PARAGRAPH_SEPARATOR}
11613 * </ul>
11614 *
11615 * <p><b>Note:</b> This method cannot handle <a
11616 * href="#supplementary"> supplementary characters</a>. To support
11617 * all Unicode characters, including supplementary characters, use
11618 * the {@link #isSpaceChar(int)} method.
11619 *
11620 * @param ch the character to be tested.
11621 * @return {@code true} if the character is a space character;
11622 * {@code false} otherwise.
11623 * @see Character#isWhitespace(char)
11624 * @since 1.1
11625 */
11626 public static boolean isSpaceChar(char ch) {
11627 return isSpaceChar((int)ch);
11628 }
11629
11630 /**
11631 * Determines if the specified character (Unicode code point) is a
11632 * Unicode space character. A character is considered to be a
11633 * space character if and only if it is specified to be a space
11634 * character by the Unicode Standard. This method returns true if
11635 * the character's general category type is any of the following:
11636 *
11637 * <ul>
11638 * <li> {@link #SPACE_SEPARATOR}
11639 * <li> {@link #LINE_SEPARATOR}
11640 * <li> {@link #PARAGRAPH_SEPARATOR}
11641 * </ul>
11642 *
11643 * @param codePoint the character (Unicode code point) to be tested.
11644 * @return {@code true} if the character is a space character;
11645 * {@code false} otherwise.
11646 * @see Character#isWhitespace(int)
11647 * @since 1.5
11648 */
11649 public static boolean isSpaceChar(int codePoint) {
11650 return ((((1 << Character.SPACE_SEPARATOR) |
11651 (1 << Character.LINE_SEPARATOR) |
11652 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11653 != 0;
11654 }
11655
11656 /**
11657 * Determines if the specified character is white space according to Java.
11658 * A character is a Java whitespace character if and only if it satisfies
11659 * one of the following criteria:
11660 * <ul>
11661 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11662 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11663 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11664 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11665 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11666 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11667 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11668 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11669 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11670 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11671 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11672 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11673 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11674 * </ul>
11675 *
11676 * <p><b>Note:</b> This method cannot handle <a
11677 * href="#supplementary"> supplementary characters</a>. To support
11678 * all Unicode characters, including supplementary characters, use
11679 * the {@link #isWhitespace(int)} method.
11680 *
11681 * @param ch the character to be tested.
11682 * @return {@code true} if the character is a Java whitespace
11683 * character; {@code false} otherwise.
11684 * @see Character#isSpaceChar(char)
11685 * @since 1.1
11686 */
11687 public static boolean isWhitespace(char ch) {
11688 return isWhitespace((int)ch);
11689 }
11690
11691 /**
11692 * Determines if the specified character (Unicode code point) is
11693 * white space according to Java. A character is a Java
11694 * whitespace character if and only if it satisfies one of the
11695 * following criteria:
11696 * <ul>
11697 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11698 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11699 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11700 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11701 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11702 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11703 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11704 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11705 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11706 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11707 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11708 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11709 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11710 * </ul>
11711 *
11712 * @param codePoint the character (Unicode code point) to be tested.
11713 * @return {@code true} if the character is a Java whitespace
11714 * character; {@code false} otherwise.
11715 * @see Character#isSpaceChar(int)
11716 * @since 1.5
11717 */
11718 public static boolean isWhitespace(int codePoint) {
11719 return CharacterData.of(codePoint).isWhitespace(codePoint);
11720 }
11721
11722 /**
11723 * Determines if the specified character is an ISO control
11724 * character. A character is considered to be an ISO control
11725 * character if its code is in the range {@code '\u005Cu0000'}
11726 * through {@code '\u005Cu001F'} or in the range
11727 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11728 *
11729 * <p><b>Note:</b> This method cannot handle <a
11730 * href="#supplementary"> supplementary characters</a>. To support
11731 * all Unicode characters, including supplementary characters, use
11732 * the {@link #isISOControl(int)} method.
11733 *
11734 * @param ch the character to be tested.
11735 * @return {@code true} if the character is an ISO control character;
11736 * {@code false} otherwise.
11737 *
11738 * @see Character#isSpaceChar(char)
11739 * @see Character#isWhitespace(char)
11740 * @since 1.1
11741 */
11742 public static boolean isISOControl(char ch) {
11743 return isISOControl((int)ch);
11744 }
11745
11746 /**
11747 * Determines if the referenced character (Unicode code point) is an ISO control
11748 * character. A character is considered to be an ISO control
11749 * character if its code is in the range {@code '\u005Cu0000'}
11750 * through {@code '\u005Cu001F'} or in the range
11751 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11752 *
11753 * @param codePoint the character (Unicode code point) to be tested.
11754 * @return {@code true} if the character is an ISO control character;
11755 * {@code false} otherwise.
11756 * @see Character#isSpaceChar(int)
11757 * @see Character#isWhitespace(int)
11758 * @since 1.5
11759 */
11760 public static boolean isISOControl(int codePoint) {
11761 // Optimized form of:
11762 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11763 // (codePoint >= 0x7F && codePoint <= 0x9F);
11764 return codePoint <= 0x9F &&
11765 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11766 }
11767
11768 /**
11769 * Returns a value indicating a character's general category.
11770 *
11771 * <p><b>Note:</b> This method cannot handle <a
11772 * href="#supplementary"> supplementary characters</a>. To support
11773 * all Unicode characters, including supplementary characters, use
11774 * the {@link #getType(int)} method.
11775 *
11776 * @param ch the character to be tested.
11777 * @return a value of type {@code int} representing the
11778 * character's general category.
11779 * @see Character#COMBINING_SPACING_MARK
11780 * @see Character#CONNECTOR_PUNCTUATION
11781 * @see Character#CONTROL
11782 * @see Character#CURRENCY_SYMBOL
11783 * @see Character#DASH_PUNCTUATION
11784 * @see Character#DECIMAL_DIGIT_NUMBER
11785 * @see Character#ENCLOSING_MARK
11786 * @see Character#END_PUNCTUATION
11787 * @see Character#FINAL_QUOTE_PUNCTUATION
11788 * @see Character#FORMAT
11789 * @see Character#INITIAL_QUOTE_PUNCTUATION
11790 * @see Character#LETTER_NUMBER
11791 * @see Character#LINE_SEPARATOR
11792 * @see Character#LOWERCASE_LETTER
11793 * @see Character#MATH_SYMBOL
11794 * @see Character#MODIFIER_LETTER
11795 * @see Character#MODIFIER_SYMBOL
11796 * @see Character#NON_SPACING_MARK
11797 * @see Character#OTHER_LETTER
11798 * @see Character#OTHER_NUMBER
11799 * @see Character#OTHER_PUNCTUATION
11800 * @see Character#OTHER_SYMBOL
11801 * @see Character#PARAGRAPH_SEPARATOR
11802 * @see Character#PRIVATE_USE
11803 * @see Character#SPACE_SEPARATOR
11804 * @see Character#START_PUNCTUATION
11805 * @see Character#SURROGATE
11806 * @see Character#TITLECASE_LETTER
11807 * @see Character#UNASSIGNED
11808 * @see Character#UPPERCASE_LETTER
11809 * @since 1.1
11810 */
11811 public static int getType(char ch) {
11812 return getType((int)ch);
11813 }
11814
11815 /**
11816 * Returns a value indicating a character's general category.
11817 *
11818 * @param codePoint the character (Unicode code point) to be tested.
11819 * @return a value of type {@code int} representing the
11820 * character's general category.
11821 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11822 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11823 * @see Character#CONTROL CONTROL
11824 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11825 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11826 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11827 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11828 * @see Character#END_PUNCTUATION END_PUNCTUATION
11829 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11830 * @see Character#FORMAT FORMAT
11831 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11832 * @see Character#LETTER_NUMBER LETTER_NUMBER
11833 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11834 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11835 * @see Character#MATH_SYMBOL MATH_SYMBOL
11836 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11837 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11838 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11839 * @see Character#OTHER_LETTER OTHER_LETTER
11840 * @see Character#OTHER_NUMBER OTHER_NUMBER
11841 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
11842 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
11843 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
11844 * @see Character#PRIVATE_USE PRIVATE_USE
11845 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
11846 * @see Character#START_PUNCTUATION START_PUNCTUATION
11847 * @see Character#SURROGATE SURROGATE
11848 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
11849 * @see Character#UNASSIGNED UNASSIGNED
11850 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
11851 * @since 1.5
11852 */
11853 public static int getType(int codePoint) {
11854 return CharacterData.of(codePoint).getType(codePoint);
11855 }
11856
11857 /**
11858 * Determines the character representation for a specific digit in
11859 * the specified radix. If the value of {@code radix} is not a
11860 * valid radix, or the value of {@code digit} is not a valid
11861 * digit in the specified radix, the null character
11862 * ({@code '\u005Cu0000'}) is returned.
11863 * <p>
11864 * The {@code radix} argument is valid if it is greater than or
11865 * equal to {@code MIN_RADIX} and less than or equal to
11866 * {@code MAX_RADIX}. The {@code digit} argument is valid if
11867 * {@code 0 <= digit < radix}.
11868 * <p>
11869 * If the digit is less than 10, then
11870 * {@code '0' + digit} is returned. Otherwise, the value
11871 * {@code 'a' + digit - 10} is returned.
11872 *
11873 * @param digit the number to convert to a character.
11874 * @param radix the radix.
11875 * @return the {@code char} representation of the specified digit
11876 * in the specified radix.
11877 * @see Character#MIN_RADIX
11878 * @see Character#MAX_RADIX
11879 * @see Character#digit(char, int)
11880 */
11881 public static char forDigit(int digit, int radix) {
11882 if ((digit >= radix) || (digit < 0)) {
11883 return '\0';
11884 }
11885 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
11886 return '\0';
11887 }
11888 if (digit < 10) {
11889 return (char)('0' + digit);
11890 }
11891 return (char)('a' - 10 + digit);
11892 }
11893
11894 /**
11895 * Returns the Unicode directionality property for the given
11896 * character. Character directionality is used to calculate the
11897 * visual ordering of text. The directionality value of undefined
11898 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
11899 *
11900 * <p><b>Note:</b> This method cannot handle <a
11901 * href="#supplementary"> supplementary characters</a>. To support
11902 * all Unicode characters, including supplementary characters, use
11903 * the {@link #getDirectionality(int)} method.
11904 *
11905 * @param ch {@code char} for which the directionality property
11906 * is requested.
11907 * @return the directionality property of the {@code char} value.
11908 *
11909 * @see Character#DIRECTIONALITY_UNDEFINED
11910 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
11911 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
11912 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11913 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
11914 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11915 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11916 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
11917 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11918 * @see Character#DIRECTIONALITY_NONSPACING_MARK
11919 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
11920 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
11921 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
11922 * @see Character#DIRECTIONALITY_WHITESPACE
11923 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
11924 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11925 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11926 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11927 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11928 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11929 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11930 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11931 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
11932 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11933 * @since 1.4
11934 */
11935 public static byte getDirectionality(char ch) {
11936 return getDirectionality((int)ch);
11937 }
11938
11939 /**
11940 * Returns the Unicode directionality property for the given
11941 * character (Unicode code point). Character directionality is
11942 * used to calculate the visual ordering of text. The
11943 * directionality value of undefined character is {@link
11944 * #DIRECTIONALITY_UNDEFINED}.
11945 *
11946 * @param codePoint the character (Unicode code point) for which
11947 * the directionality property is requested.
11948 * @return the directionality property of the character.
11949 *
11950 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
11951 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
11952 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
11953 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11954 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
11955 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11956 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11957 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
11958 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11959 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
11960 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
11961 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
11962 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
11963 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
11964 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
11965 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11966 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11967 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11968 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11969 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11970 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11971 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11972 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
11973 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11974 * @since 1.5
11975 */
11976 public static byte getDirectionality(int codePoint) {
11977 return CharacterData.of(codePoint).getDirectionality(codePoint);
11978 }
11979
11980 /**
11981 * Determines whether the character is mirrored according to the
11982 * Unicode specification. Mirrored characters should have their
11983 * glyphs horizontally mirrored when displayed in text that is
11984 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
11985 * PARENTHESIS is semantically defined to be an <i>opening
11986 * parenthesis</i>. This will appear as a "(" in text that is
11987 * left-to-right but as a ")" in text that is right-to-left.
11988 *
11989 * <p><b>Note:</b> This method cannot handle <a
11990 * href="#supplementary"> supplementary characters</a>. To support
11991 * all Unicode characters, including supplementary characters, use
11992 * the {@link #isMirrored(int)} method.
11993 *
11994 * @param ch {@code char} for which the mirrored property is requested
11995 * @return {@code true} if the char is mirrored, {@code false}
11996 * if the {@code char} is not mirrored or is not defined.
11997 * @since 1.4
11998 */
11999 public static boolean isMirrored(char ch) {
12000 return isMirrored((int)ch);
12001 }
12002
12003 /**
12004 * Determines whether the specified character (Unicode code point)
12005 * is mirrored according to the Unicode specification. Mirrored
12006 * characters should have their glyphs horizontally mirrored when
12007 * displayed in text that is right-to-left. For example,
12008 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
12009 * defined to be an <i>opening parenthesis</i>. This will appear
12010 * as a "(" in text that is left-to-right but as a ")" in text
12011 * that is right-to-left.
12012 *
12013 * @param codePoint the character (Unicode code point) to be tested.
12014 * @return {@code true} if the character is mirrored, {@code false}
12015 * if the character is not mirrored or is not defined.
12016 * @since 1.5
12017 */
12018 public static boolean isMirrored(int codePoint) {
12019 return CharacterData.of(codePoint).isMirrored(codePoint);
12020 }
12021
12022 /**
12023 * Compares two {@code Character} objects numerically.
12024 *
12025 * @param anotherCharacter the {@code Character} to be compared.
12026 * @return the value {@code 0} if the argument {@code Character}
12027 * is equal to this {@code Character}; a value less than
12028 * {@code 0} if this {@code Character} is numerically less
12029 * than the {@code Character} argument; and a value greater than
12030 * {@code 0} if this {@code Character} is numerically greater
12031 * than the {@code Character} argument (unsigned comparison).
12032 * Note that this is strictly a numerical comparison; it is not
12033 * locale-dependent.
12034 * @since 1.2
12035 */
12036 public int compareTo(Character anotherCharacter) {
12037 return compare(this.value, anotherCharacter.value);
12038 }
12039
12040 /**
12041 * Compares two {@code char} values numerically.
12042 * The value returned is identical to what would be returned by:
12043 * <pre>
12044 * Character.valueOf(x).compareTo(Character.valueOf(y))
12045 * </pre>
12046 *
12047 * @param x the first {@code char} to compare
12048 * @param y the second {@code char} to compare
12049 * @return the value {@code 0} if {@code x == y};
12050 * a value less than {@code 0} if {@code x < y}; and
12051 * a value greater than {@code 0} if {@code x > y}
12052 * @since 1.7
12053 */
12054 public static int compare(char x, char y) {
12055 return x - y;
12056 }
12057
12058 /**
12059 * Converts the character (Unicode code point) argument to uppercase using
12060 * information from the UnicodeData file.
12061 *
12062 * @param codePoint the character (Unicode code point) to be converted.
12063 * @return either the uppercase equivalent of the character, if
12064 * any, or an error flag ({@code Character.ERROR})
12065 * that indicates that a 1:M {@code char} mapping exists.
12066 * @see Character#isLowerCase(char)
12067 * @see Character#isUpperCase(char)
12068 * @see Character#toLowerCase(char)
12069 * @see Character#toTitleCase(char)
12070 * @since 1.4
12071 */
12072 static int toUpperCaseEx(int codePoint) {
12073 assert isValidCodePoint(codePoint);
12074 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
12075 }
12076
12077 /**
12078 * Converts the character (Unicode code point) argument to uppercase using case
12079 * mapping information from the SpecialCasing file in the Unicode
12080 * specification. If a character has no explicit uppercase
12081 * mapping, then the {@code char} itself is returned in the
12082 * {@code char[]}.
12083 *
12084 * @param codePoint the character (Unicode code point) to be converted.
12085 * @return a {@code char[]} with the uppercased character.
12086 * @since 1.4
12087 */
12088 static char[] toUpperCaseCharArray(int codePoint) {
12089 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
12090 assert isBmpCodePoint(codePoint);
12091 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
12092 }
12093
12094 /**
12095 * The number of bits used to represent a {@code char} value in unsigned
12096 * binary form, constant {@code 16}.
12097 *
12098 * @since 1.5
12099 */
12100 public static final int SIZE = 16;
12101
12102 /**
12103 * The number of bytes used to represent a {@code char} value in unsigned
12104 * binary form.
12105 *
12106 * @since 1.8
12107 */
12108 public static final int BYTES = SIZE / Byte.SIZE;
12109
12110 /**
12111 * Returns the value obtained by reversing the order of the bytes in the
12112 * specified {@code char} value.
12113 *
12114 * @param ch The {@code char} of which to reverse the byte order.
12115 * @return the value obtained by reversing (or, equivalently, swapping)
12116 * the bytes in the specified {@code char} value.
12117 * @since 1.5
12118 */
12119 @IntrinsicCandidate
12120 public static char reverseBytes(char ch) {
12121 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
12122 }
12123
12124 /**
12125 * Returns the name of the specified character
12126 * {@code codePoint}, or null if the code point is
12127 * {@link #UNASSIGNED unassigned}.
12128 * <p>
12129 * If the specified character is not assigned a name by
12130 * the <i>UnicodeData</i> file (part of the Unicode Character
12131 * Database maintained by the Unicode Consortium), the returned
12132 * name is the same as the result of the expression:
12133 *
12134 * <blockquote>{@code
12135 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12136 * + " "
12137 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12138 *
12139 * }</blockquote>
12140 *
12141 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
12142 * returned by this method follows the naming scheme in the
12143 * "Unicode Name Property" section of the Unicode Standard. For other
12144 * code points, such as Hangul/Ideographs, The name generation rule above
12145 * differs from the one defined in the Unicode Standard.
12146 *
12147 * @param codePoint the character (Unicode code point)
12148 *
12149 * @return the name of the specified character, or null if
12150 * the code point is unassigned.
12151 *
12152 * @throws IllegalArgumentException if the specified
12153 * {@code codePoint} is not a valid Unicode
12154 * code point.
12155 *
12156 * @since 1.7
12157 */
12158 public static String getName(int codePoint) {
12159 if (!isValidCodePoint(codePoint)) {
12160 throw new IllegalArgumentException(
12161 String.format("Not a valid Unicode code point: 0x%X", codePoint));
12162 }
12163 String name = CharacterName.getInstance().getName(codePoint);
12164 if (name != null)
12165 return name;
12166 if (getType(codePoint) == UNASSIGNED)
12167 return null;
12168 UnicodeBlock block = UnicodeBlock.of(codePoint);
12169 if (block != null)
12170 return block.toString().replace('_', ' ') + " "
12171 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12172 // should never come here
12173 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12174 }
12175
12176 /**
12177 * Returns the code point value of the Unicode character specified by
12178 * the given character name.
12179 * <p>
12180 * If a character is not assigned a name by the <i>UnicodeData</i>
12181 * file (part of the Unicode Character Database maintained by the Unicode
12182 * Consortium), its name is defined as the result of the expression:
12183 *
12184 * <blockquote>{@code
12185 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12186 * + " "
12187 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12188 *
12189 * }</blockquote>
12190 * <p>
12191 * The {@code name} matching is case insensitive, with any leading and
12192 * trailing whitespace character removed.
12193 *
12194 * For the code points in the <i>UnicodeData</i> file, this method
12195 * recognizes the name which conforms to the name defined in the
12196 * "Unicode Name Property" section in the Unicode Standard. For other
12197 * code points, this method recognizes the name generated with
12198 * {@link #getName(int)} method.
12199 *
12200 * @param name the character name
12201 *
12202 * @return the code point value of the character specified by its name.
12203 *
12204 * @throws IllegalArgumentException if the specified {@code name}
12205 * is not a valid character name.
12206 * @throws NullPointerException if {@code name} is {@code null}
12207 *
12208 * @since 9
12209 */
12210 public static int codePointOf(String name) {
12211 name = name.trim().toUpperCase(Locale.ROOT);
12212 int cp = CharacterName.getInstance().getCodePoint(name);
12213 if (cp != -1)
12214 return cp;
12215 try {
12216 int off = name.lastIndexOf(' ');
12217 if (off != -1) {
12218 cp = Integer.parseInt(name, off + 1, name.length(), 16);
12219 if (isValidCodePoint(cp) && name.equals(getName(cp)))
12220 return cp;
12221 }
12222 } catch (Exception x) {}
12223 throw new IllegalArgumentException("Unrecognized character name :" + name);
12224 }
12225 }