1 /*
2 * Copyright (c) 2002, 2023, 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 wraps a value of the primitive
48 * type {@code char} in an object. An object of class
49 * {@code Character} contains a single field whose type is
50 * {@code char}.
51 * <p>
52 * In addition, this class provides a large number of static methods for
53 * determining a character's category (lowercase letter, digit, etc.)
54 * and for converting characters from uppercase to lowercase and vice
55 * versa.
56 *
57 * <h2><a id="conformance">Unicode Conformance</a></h2>
58 * <p>
59 * The fields and methods of class {@code Character} are defined in terms
60 * of character information from the Unicode Standard, specifically the
61 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
62 * This file specifies properties including name and category for every
63 * assigned Unicode code point or character range. The file is available
64 * from the Unicode Consortium at
65 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
66 * <p>
67 * Character information is based on the Unicode Standard, version 15.1.
68 * <p>
69 * The Java platform has supported different versions of the Unicode
70 * Standard over time. Upgrades to newer versions of the Unicode Standard
71 * occurred in the following Java releases, each indicating the new version:
72 * <table class="striped">
73 * <caption style="display:none">Shows Java releases and supported Unicode versions</caption>
74 * <thead>
75 * <tr><th scope="col">Java release</th>
76 * <th scope="col">Unicode version</th></tr>
77 * </thead>
78 * <tbody>
79 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
80 * <td>Unicode 15.1</td></tr>
81 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
82 * <td>Unicode 15.0</td></tr>
83 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
84 * <td>Unicode 14.0</td></tr>
85 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
86 * <td>Unicode 13.0</td></tr>
87 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
88 * <td>Unicode 12.1</td></tr>
89 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
90 * <td>Unicode 11.0</td></tr>
91 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
92 * <td>Unicode 10.0</td></tr>
93 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
94 * <td>Unicode 8.0</td></tr>
95 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
96 * <td>Unicode 6.2</td></tr>
97 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
98 * <td>Unicode 6.0</td></tr>
99 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
100 * <td>Unicode 4.0</td></tr>
101 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
102 * <td>Unicode 3.0</td></tr>
103 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
104 * <td>Unicode 2.0</td></tr>
105 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
106 * <td>Unicode 1.1.5</td></tr>
107 * </tbody>
108 * </table>
109 * Variations from these base Unicode versions, such as recognized appendixes,
110 * are documented elsewhere.
111 * <h2><a id="unicode">Unicode Character Representations</a></h2>
112 *
113 * <p>The {@code char} data type (and therefore the value that a
114 * {@code Character} object encapsulates) are based on the
115 * original Unicode specification, which defined characters as
116 * fixed-width 16-bit entities. The Unicode Standard has since been
117 * changed to allow for characters whose representation requires more
118 * than 16 bits. The range of legal <em>code point</em>s is now
119 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
120 * (Refer to the <a
121 * href="http://www.unicode.org/reports/tr27/#notation"><i>
122 * definition</i></a> of the U+<i>n</i> notation in the Unicode
123 * Standard.)
124 *
125 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
126 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
127 * <a id="supplementary">Characters</a> whose code points are greater
128 * than U+FFFF are called <em>supplementary character</em>s. The Java
129 * platform uses the UTF-16 representation in {@code char} arrays and
130 * in the {@code String} and {@code StringBuffer} classes. In
131 * this representation, supplementary characters are represented as a pair
132 * of {@code char} values, the first from the <em>high-surrogates</em>
133 * range, (\uD800-\uDBFF), the second from the
134 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
135 *
136 * <p>A {@code char} value, therefore, represents Basic
137 * Multilingual Plane (BMP) code points, including the surrogate
138 * code points, or code units of the UTF-16 encoding. An
139 * {@code int} value represents all Unicode code points,
140 * including supplementary code points. The lower (least significant)
141 * 21 bits of {@code int} are used to represent Unicode code
142 * points and the upper (most significant) 11 bits must be zero.
143 * Unless otherwise specified, the behavior with respect to
144 * supplementary characters and surrogate {@code char} values is
145 * as follows:
146 *
147 * <ul>
148 * <li>The methods that only accept a {@code char} value cannot support
149 * supplementary characters. They treat {@code char} values from the
150 * surrogate ranges as undefined characters. For example,
151 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
152 * this specific value if followed by any low-surrogate value in a string
153 * would represent a letter.
154 *
155 * <li>The methods that accept an {@code int} value support all
156 * Unicode characters, including supplementary characters. For
157 * example, {@code Character.isLetter(0x2F81A)} returns
158 * {@code true} because the code point value represents a letter
159 * (a CJK ideograph).
160 * </ul>
161 *
162 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
163 * used for character values in the range between U+0000 and U+10FFFF,
164 * and <em>Unicode code unit</em> is used for 16-bit
165 * {@code char} values that are code units of the <em>UTF-16</em>
166 * encoding. For more information on Unicode terminology, refer to the
167 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
168 *
169 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
170 * class; programmers should treat instances that are
171 * {@linkplain #equals(Object) equal} as interchangeable and should not
172 * use instances for synchronization, or unpredictable behavior may
173 * occur. For example, in a future release, synchronization may fail.
174 *
175 * @spec https://www.unicode.org/reports/tr27 Unicode 3.1.0
176 * @author Lee Boynton
177 * @author Guy Steele
178 * @author Akira Tanaka
179 * @author Martin Buchholz
180 * @author Ulf Zibis
181 * @since 1.0
182 */
183 @jdk.internal.MigratedValueClass
184 @jdk.internal.ValueBased
185 public final class Character implements java.io.Serializable, Comparable<Character>, Constable {
186 /**
187 * The minimum radix available for conversion to and from strings.
188 * The constant value of this field is the smallest value permitted
189 * for the radix argument in radix-conversion methods such as the
190 * {@code digit} method, the {@code forDigit} method, and the
191 * {@code toString} method of class {@code Integer}.
192 *
193 * @see Character#digit(char, int)
194 * @see Character#forDigit(int, int)
195 * @see Integer#toString(int, int)
196 * @see Integer#valueOf(String)
197 */
198 public static final int MIN_RADIX = 2;
199
200 /**
201 * The maximum radix available for conversion to and from strings.
202 * The constant value of this field is the largest value permitted
203 * for the radix argument in radix-conversion methods such as the
204 * {@code digit} method, the {@code forDigit} method, and the
205 * {@code toString} method of class {@code Integer}.
206 *
207 * @see Character#digit(char, int)
208 * @see Character#forDigit(int, int)
209 * @see Integer#toString(int, int)
210 * @see Integer#valueOf(String)
211 */
212 public static final int MAX_RADIX = 36;
213
214 /**
215 * The constant value of this field is the smallest value of type
216 * {@code char}, {@code '\u005Cu0000'}.
217 *
218 * @since 1.0.2
219 */
220 public static final char MIN_VALUE = '\u0000';
221
222 /**
223 * The constant value of this field is the largest value of type
224 * {@code char}, {@code '\u005CuFFFF'}.
225 *
226 * @since 1.0.2
227 */
228 public static final char MAX_VALUE = '\uFFFF';
229
230 /**
231 * The {@code Class} instance representing the primitive type
232 * {@code char}.
233 *
234 * @since 1.1
235 */
236 @SuppressWarnings("unchecked")
237 public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char");
238
239 /*
240 * Normative general types
241 */
242
243 /*
244 * General character types
245 */
246
247 /**
248 * General category "Cn" in the Unicode specification.
249 * @since 1.1
250 */
251 public static final byte UNASSIGNED = 0;
252
253 /**
254 * General category "Lu" in the Unicode specification.
255 * @since 1.1
256 */
257 public static final byte UPPERCASE_LETTER = 1;
258
259 /**
260 * General category "Ll" in the Unicode specification.
261 * @since 1.1
262 */
263 public static final byte LOWERCASE_LETTER = 2;
264
265 /**
266 * General category "Lt" in the Unicode specification.
267 * @since 1.1
268 */
269 public static final byte TITLECASE_LETTER = 3;
270
271 /**
272 * General category "Lm" in the Unicode specification.
273 * @since 1.1
274 */
275 public static final byte MODIFIER_LETTER = 4;
276
277 /**
278 * General category "Lo" in the Unicode specification.
279 * @since 1.1
280 */
281 public static final byte OTHER_LETTER = 5;
282
283 /**
284 * General category "Mn" in the Unicode specification.
285 * @since 1.1
286 */
287 public static final byte NON_SPACING_MARK = 6;
288
289 /**
290 * General category "Me" in the Unicode specification.
291 * @since 1.1
292 */
293 public static final byte ENCLOSING_MARK = 7;
294
295 /**
296 * General category "Mc" in the Unicode specification.
297 * @since 1.1
298 */
299 public static final byte COMBINING_SPACING_MARK = 8;
300
301 /**
302 * General category "Nd" in the Unicode specification.
303 * @since 1.1
304 */
305 public static final byte DECIMAL_DIGIT_NUMBER = 9;
306
307 /**
308 * General category "Nl" in the Unicode specification.
309 * @since 1.1
310 */
311 public static final byte LETTER_NUMBER = 10;
312
313 /**
314 * General category "No" in the Unicode specification.
315 * @since 1.1
316 */
317 public static final byte OTHER_NUMBER = 11;
318
319 /**
320 * General category "Zs" in the Unicode specification.
321 * @since 1.1
322 */
323 public static final byte SPACE_SEPARATOR = 12;
324
325 /**
326 * General category "Zl" in the Unicode specification.
327 * @since 1.1
328 */
329 public static final byte LINE_SEPARATOR = 13;
330
331 /**
332 * General category "Zp" in the Unicode specification.
333 * @since 1.1
334 */
335 public static final byte PARAGRAPH_SEPARATOR = 14;
336
337 /**
338 * General category "Cc" in the Unicode specification.
339 * @since 1.1
340 */
341 public static final byte CONTROL = 15;
342
343 /**
344 * General category "Cf" in the Unicode specification.
345 * @since 1.1
346 */
347 public static final byte FORMAT = 16;
348
349 /**
350 * General category "Co" in the Unicode specification.
351 * @since 1.1
352 */
353 public static final byte PRIVATE_USE = 18;
354
355 /**
356 * General category "Cs" in the Unicode specification.
357 * @since 1.1
358 */
359 public static final byte SURROGATE = 19;
360
361 /**
362 * General category "Pd" in the Unicode specification.
363 * @since 1.1
364 */
365 public static final byte DASH_PUNCTUATION = 20;
366
367 /**
368 * General category "Ps" in the Unicode specification.
369 * @since 1.1
370 */
371 public static final byte START_PUNCTUATION = 21;
372
373 /**
374 * General category "Pe" in the Unicode specification.
375 * @since 1.1
376 */
377 public static final byte END_PUNCTUATION = 22;
378
379 /**
380 * General category "Pc" in the Unicode specification.
381 * @since 1.1
382 */
383 public static final byte CONNECTOR_PUNCTUATION = 23;
384
385 /**
386 * General category "Po" in the Unicode specification.
387 * @since 1.1
388 */
389 public static final byte OTHER_PUNCTUATION = 24;
390
391 /**
392 * General category "Sm" in the Unicode specification.
393 * @since 1.1
394 */
395 public static final byte MATH_SYMBOL = 25;
396
397 /**
398 * General category "Sc" in the Unicode specification.
399 * @since 1.1
400 */
401 public static final byte CURRENCY_SYMBOL = 26;
402
403 /**
404 * General category "Sk" in the Unicode specification.
405 * @since 1.1
406 */
407 public static final byte MODIFIER_SYMBOL = 27;
408
409 /**
410 * General category "So" in the Unicode specification.
411 * @since 1.1
412 */
413 public static final byte OTHER_SYMBOL = 28;
414
415 /**
416 * General category "Pi" in the Unicode specification.
417 * @since 1.4
418 */
419 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
420
421 /**
422 * General category "Pf" in the Unicode specification.
423 * @since 1.4
424 */
425 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
426
427 /**
428 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
429 */
430 static final int ERROR = 0xFFFFFFFF;
431
432
433 /**
434 * Undefined bidirectional character type. Undefined {@code char}
435 * values have undefined directionality in the Unicode specification.
436 * @since 1.4
437 */
438 public static final byte DIRECTIONALITY_UNDEFINED = -1;
439
440 /**
441 * Strong bidirectional character type "L" in the Unicode specification.
442 * @since 1.4
443 */
444 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
445
446 /**
447 * Strong bidirectional character type "R" in the Unicode specification.
448 * @since 1.4
449 */
450 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
451
452 /**
453 * Strong bidirectional character type "AL" in the Unicode specification.
454 * @since 1.4
455 */
456 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
457
458 /**
459 * Weak bidirectional character type "EN" in the Unicode specification.
460 * @since 1.4
461 */
462 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
463
464 /**
465 * Weak bidirectional character type "ES" in the Unicode specification.
466 * @since 1.4
467 */
468 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
469
470 /**
471 * Weak bidirectional character type "ET" in the Unicode specification.
472 * @since 1.4
473 */
474 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
475
476 /**
477 * Weak bidirectional character type "AN" in the Unicode specification.
478 * @since 1.4
479 */
480 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
481
482 /**
483 * Weak bidirectional character type "CS" in the Unicode specification.
484 * @since 1.4
485 */
486 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
487
488 /**
489 * Weak bidirectional character type "NSM" in the Unicode specification.
490 * @since 1.4
491 */
492 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
493
494 /**
495 * Weak bidirectional character type "BN" in the Unicode specification.
496 * @since 1.4
497 */
498 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
499
500 /**
501 * Neutral bidirectional character type "B" in the Unicode specification.
502 * @since 1.4
503 */
504 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
505
506 /**
507 * Neutral bidirectional character type "S" in the Unicode specification.
508 * @since 1.4
509 */
510 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
511
512 /**
513 * Neutral bidirectional character type "WS" in the Unicode specification.
514 * @since 1.4
515 */
516 public static final byte DIRECTIONALITY_WHITESPACE = 12;
517
518 /**
519 * Neutral bidirectional character type "ON" in the Unicode specification.
520 * @since 1.4
521 */
522 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
523
524 /**
525 * Strong bidirectional character type "LRE" in the Unicode specification.
526 * @since 1.4
527 */
528 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
529
530 /**
531 * Strong bidirectional character type "LRO" in the Unicode specification.
532 * @since 1.4
533 */
534 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
535
536 /**
537 * Strong bidirectional character type "RLE" in the Unicode specification.
538 * @since 1.4
539 */
540 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
541
542 /**
543 * Strong bidirectional character type "RLO" in the Unicode specification.
544 * @since 1.4
545 */
546 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
547
548 /**
549 * Weak bidirectional character type "PDF" in the Unicode specification.
550 * @since 1.4
551 */
552 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
553
554 /**
555 * Weak bidirectional character type "LRI" in the Unicode specification.
556 * @since 9
557 */
558 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
559
560 /**
561 * Weak bidirectional character type "RLI" in the Unicode specification.
562 * @since 9
563 */
564 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
565
566 /**
567 * Weak bidirectional character type "FSI" in the Unicode specification.
568 * @since 9
569 */
570 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
571
572 /**
573 * Weak bidirectional character type "PDI" in the Unicode specification.
574 * @since 9
575 */
576 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
577
578 /**
579 * The minimum value of a
580 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
581 * Unicode high-surrogate code unit</a>
582 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
583 * A high-surrogate is also known as a <i>leading-surrogate</i>.
584 *
585 * @since 1.5
586 */
587 public static final char MIN_HIGH_SURROGATE = '\uD800';
588
589 /**
590 * The maximum value of a
591 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
592 * Unicode high-surrogate code unit</a>
593 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
594 * A high-surrogate is also known as a <i>leading-surrogate</i>.
595 *
596 * @since 1.5
597 */
598 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
599
600 /**
601 * The minimum value of a
602 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
603 * Unicode low-surrogate code unit</a>
604 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
605 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
606 *
607 * @since 1.5
608 */
609 public static final char MIN_LOW_SURROGATE = '\uDC00';
610
611 /**
612 * The maximum value of a
613 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
614 * Unicode low-surrogate code unit</a>
615 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
616 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
617 *
618 * @since 1.5
619 */
620 public static final char MAX_LOW_SURROGATE = '\uDFFF';
621
622 /**
623 * The minimum value of a Unicode surrogate code unit in the
624 * UTF-16 encoding, constant {@code '\u005CuD800'}.
625 *
626 * @since 1.5
627 */
628 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
629
630 /**
631 * The maximum value of a Unicode surrogate code unit in the
632 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
633 *
634 * @since 1.5
635 */
636 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
637
638 /**
639 * The minimum value of a
640 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
641 * Unicode supplementary code point</a>, constant {@code U+10000}.
642 *
643 * @since 1.5
644 */
645 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
646
647 /**
648 * The minimum value of a
649 * <a href="http://www.unicode.org/glossary/#code_point">
650 * Unicode code point</a>, constant {@code U+0000}.
651 *
652 * @since 1.5
653 */
654 public static final int MIN_CODE_POINT = 0x000000;
655
656 /**
657 * The maximum value of a
658 * <a href="http://www.unicode.org/glossary/#code_point">
659 * Unicode code point</a>, constant {@code U+10FFFF}.
660 *
661 * @since 1.5
662 */
663 public static final int MAX_CODE_POINT = 0X10FFFF;
664
665 /**
666 * Returns an {@link Optional} containing the nominal descriptor for this
667 * instance.
668 *
669 * @return an {@link Optional} describing the {@linkplain Character} instance
670 * @since 15
671 */
672 @Override
673 public Optional<DynamicConstantDesc<Character>> describeConstable() {
674 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
675 }
676
677 /**
678 * Instances of this class represent particular subsets of the Unicode
679 * character set. The only family of subsets defined in the
680 * {@code Character} class is {@link Character.UnicodeBlock}.
681 * Other portions of the Java API may define other subsets for their
682 * own purposes.
683 *
684 * @since 1.2
685 */
686 public static class Subset {
687
688 private String name;
689
690 /**
691 * Constructs a new {@code Subset} instance.
692 *
693 * @param name The name of this subset
694 * @throws NullPointerException if name is {@code null}
695 */
696 protected Subset(String name) {
697 if (name == null) {
698 throw new NullPointerException("name");
699 }
700 this.name = name;
701 }
702
703 /**
704 * Compares two {@code Subset} objects for equality.
705 * This method returns {@code true} if and only if
706 * {@code this} and the argument refer to the same
707 * object; since this method is {@code final}, this
708 * guarantee holds for all subclasses.
709 */
710 public final boolean equals(Object obj) {
711 return (this == obj);
712 }
713
714 /**
715 * Returns the standard hash code as defined by the
716 * {@link Object#hashCode} method. This method
717 * is {@code final} in order to ensure that the
718 * {@code equals} and {@code hashCode} methods will
719 * be consistent in all subclasses.
720 */
721 public final int hashCode() {
722 return super.hashCode();
723 }
724
725 /**
726 * Returns the name of this subset.
727 */
728 public final String toString() {
729 return name;
730 }
731 }
732
733 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
734 // for the latest specification of Unicode Blocks.
735
736 /**
737 * A family of character subsets representing the character blocks in the
738 * Unicode specification. Character blocks generally define characters
739 * used for a specific script or purpose. A character is contained by
740 * at most one Unicode block.
741 *
742 * @since 1.2
743 */
744 public static final class UnicodeBlock extends Subset {
745 /**
746 * NUM_ENTITIES should match the total number of UnicodeBlocks.
747 * It should be adjusted whenever the Unicode Character Database
748 * is upgraded.
749 */
750 private static final int NUM_ENTITIES = 759;
751 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
752
753 /**
754 * Creates a UnicodeBlock with the given identifier name.
755 * This name must be the same as the block identifier.
756 */
757 private UnicodeBlock(String idName) {
758 super(idName);
759 map.put(idName, this);
760 }
761
762 /**
763 * Creates a UnicodeBlock with the given identifier name and
764 * alias name.
765 */
766 private UnicodeBlock(String idName, String alias) {
767 this(idName);
768 map.put(alias, this);
769 }
770
771 /**
772 * Creates a UnicodeBlock with the given identifier name and
773 * alias names.
774 */
775 private UnicodeBlock(String idName, String... aliases) {
776 this(idName);
777 for (String alias : aliases)
778 map.put(alias, this);
779 }
780
781 /**
782 * Constant for the "Basic Latin" Unicode character block.
783 * @since 1.2
784 */
785 public static final UnicodeBlock BASIC_LATIN =
786 new UnicodeBlock("BASIC_LATIN",
787 "BASIC LATIN",
788 "BASICLATIN");
789
790 /**
791 * Constant for the "Latin-1 Supplement" Unicode character block.
792 * @since 1.2
793 */
794 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
795 new UnicodeBlock("LATIN_1_SUPPLEMENT",
796 "LATIN-1 SUPPLEMENT",
797 "LATIN-1SUPPLEMENT");
798
799 /**
800 * Constant for the "Latin Extended-A" Unicode character block.
801 * @since 1.2
802 */
803 public static final UnicodeBlock LATIN_EXTENDED_A =
804 new UnicodeBlock("LATIN_EXTENDED_A",
805 "LATIN EXTENDED-A",
806 "LATINEXTENDED-A");
807
808 /**
809 * Constant for the "Latin Extended-B" Unicode character block.
810 * @since 1.2
811 */
812 public static final UnicodeBlock LATIN_EXTENDED_B =
813 new UnicodeBlock("LATIN_EXTENDED_B",
814 "LATIN EXTENDED-B",
815 "LATINEXTENDED-B");
816
817 /**
818 * Constant for the "IPA Extensions" Unicode character block.
819 * @since 1.2
820 */
821 public static final UnicodeBlock IPA_EXTENSIONS =
822 new UnicodeBlock("IPA_EXTENSIONS",
823 "IPA EXTENSIONS",
824 "IPAEXTENSIONS");
825
826 /**
827 * Constant for the "Spacing Modifier Letters" Unicode character block.
828 * @since 1.2
829 */
830 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
831 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
832 "SPACING MODIFIER LETTERS",
833 "SPACINGMODIFIERLETTERS");
834
835 /**
836 * Constant for the "Combining Diacritical Marks" Unicode character block.
837 * @since 1.2
838 */
839 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
840 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
841 "COMBINING DIACRITICAL MARKS",
842 "COMBININGDIACRITICALMARKS");
843
844 /**
845 * Constant for the "Greek and Coptic" Unicode character block.
846 * <p>
847 * This block was previously known as the "Greek" block.
848 *
849 * @since 1.2
850 */
851 public static final UnicodeBlock GREEK =
852 new UnicodeBlock("GREEK",
853 "GREEK AND COPTIC",
854 "GREEKANDCOPTIC");
855
856 /**
857 * Constant for the "Cyrillic" Unicode character block.
858 * @since 1.2
859 */
860 public static final UnicodeBlock CYRILLIC =
861 new UnicodeBlock("CYRILLIC");
862
863 /**
864 * Constant for the "Armenian" Unicode character block.
865 * @since 1.2
866 */
867 public static final UnicodeBlock ARMENIAN =
868 new UnicodeBlock("ARMENIAN");
869
870 /**
871 * Constant for the "Hebrew" Unicode character block.
872 * @since 1.2
873 */
874 public static final UnicodeBlock HEBREW =
875 new UnicodeBlock("HEBREW");
876
877 /**
878 * Constant for the "Arabic" Unicode character block.
879 * @since 1.2
880 */
881 public static final UnicodeBlock ARABIC =
882 new UnicodeBlock("ARABIC");
883
884 /**
885 * Constant for the "Devanagari" Unicode character block.
886 * @since 1.2
887 */
888 public static final UnicodeBlock DEVANAGARI =
889 new UnicodeBlock("DEVANAGARI");
890
891 /**
892 * Constant for the "Bengali" Unicode character block.
893 * @since 1.2
894 */
895 public static final UnicodeBlock BENGALI =
896 new UnicodeBlock("BENGALI");
897
898 /**
899 * Constant for the "Gurmukhi" Unicode character block.
900 * @since 1.2
901 */
902 public static final UnicodeBlock GURMUKHI =
903 new UnicodeBlock("GURMUKHI");
904
905 /**
906 * Constant for the "Gujarati" Unicode character block.
907 * @since 1.2
908 */
909 public static final UnicodeBlock GUJARATI =
910 new UnicodeBlock("GUJARATI");
911
912 /**
913 * Constant for the "Oriya" Unicode character block.
914 * @since 1.2
915 */
916 public static final UnicodeBlock ORIYA =
917 new UnicodeBlock("ORIYA");
918
919 /**
920 * Constant for the "Tamil" Unicode character block.
921 * @since 1.2
922 */
923 public static final UnicodeBlock TAMIL =
924 new UnicodeBlock("TAMIL");
925
926 /**
927 * Constant for the "Telugu" Unicode character block.
928 * @since 1.2
929 */
930 public static final UnicodeBlock TELUGU =
931 new UnicodeBlock("TELUGU");
932
933 /**
934 * Constant for the "Kannada" Unicode character block.
935 * @since 1.2
936 */
937 public static final UnicodeBlock KANNADA =
938 new UnicodeBlock("KANNADA");
939
940 /**
941 * Constant for the "Malayalam" Unicode character block.
942 * @since 1.2
943 */
944 public static final UnicodeBlock MALAYALAM =
945 new UnicodeBlock("MALAYALAM");
946
947 /**
948 * Constant for the "Thai" Unicode character block.
949 * @since 1.2
950 */
951 public static final UnicodeBlock THAI =
952 new UnicodeBlock("THAI");
953
954 /**
955 * Constant for the "Lao" Unicode character block.
956 * @since 1.2
957 */
958 public static final UnicodeBlock LAO =
959 new UnicodeBlock("LAO");
960
961 /**
962 * Constant for the "Tibetan" Unicode character block.
963 * @since 1.2
964 */
965 public static final UnicodeBlock TIBETAN =
966 new UnicodeBlock("TIBETAN");
967
968 /**
969 * Constant for the "Georgian" Unicode character block.
970 * @since 1.2
971 */
972 public static final UnicodeBlock GEORGIAN =
973 new UnicodeBlock("GEORGIAN");
974
975 /**
976 * Constant for the "Hangul Jamo" Unicode character block.
977 * @since 1.2
978 */
979 public static final UnicodeBlock HANGUL_JAMO =
980 new UnicodeBlock("HANGUL_JAMO",
981 "HANGUL JAMO",
982 "HANGULJAMO");
983
984 /**
985 * Constant for the "Latin Extended Additional" Unicode character block.
986 * @since 1.2
987 */
988 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
989 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
990 "LATIN EXTENDED ADDITIONAL",
991 "LATINEXTENDEDADDITIONAL");
992
993 /**
994 * Constant for the "Greek Extended" Unicode character block.
995 * @since 1.2
996 */
997 public static final UnicodeBlock GREEK_EXTENDED =
998 new UnicodeBlock("GREEK_EXTENDED",
999 "GREEK EXTENDED",
1000 "GREEKEXTENDED");
1001
1002 /**
1003 * Constant for the "General Punctuation" Unicode character block.
1004 * @since 1.2
1005 */
1006 public static final UnicodeBlock GENERAL_PUNCTUATION =
1007 new UnicodeBlock("GENERAL_PUNCTUATION",
1008 "GENERAL PUNCTUATION",
1009 "GENERALPUNCTUATION");
1010
1011 /**
1012 * Constant for the "Superscripts and Subscripts" Unicode character
1013 * block.
1014 * @since 1.2
1015 */
1016 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1017 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1018 "SUPERSCRIPTS AND SUBSCRIPTS",
1019 "SUPERSCRIPTSANDSUBSCRIPTS");
1020
1021 /**
1022 * Constant for the "Currency Symbols" Unicode character block.
1023 * @since 1.2
1024 */
1025 public static final UnicodeBlock CURRENCY_SYMBOLS =
1026 new UnicodeBlock("CURRENCY_SYMBOLS",
1027 "CURRENCY SYMBOLS",
1028 "CURRENCYSYMBOLS");
1029
1030 /**
1031 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1032 * character block.
1033 * <p>
1034 * This block was previously known as "Combining Marks for Symbols".
1035 * @since 1.2
1036 */
1037 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1038 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1039 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1040 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1041 "COMBINING MARKS FOR SYMBOLS",
1042 "COMBININGMARKSFORSYMBOLS");
1043
1044 /**
1045 * Constant for the "Letterlike Symbols" Unicode character block.
1046 * @since 1.2
1047 */
1048 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1049 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1050 "LETTERLIKE SYMBOLS",
1051 "LETTERLIKESYMBOLS");
1052
1053 /**
1054 * Constant for the "Number Forms" Unicode character block.
1055 * @since 1.2
1056 */
1057 public static final UnicodeBlock NUMBER_FORMS =
1058 new UnicodeBlock("NUMBER_FORMS",
1059 "NUMBER FORMS",
1060 "NUMBERFORMS");
1061
1062 /**
1063 * Constant for the "Arrows" Unicode character block.
1064 * @since 1.2
1065 */
1066 public static final UnicodeBlock ARROWS =
1067 new UnicodeBlock("ARROWS");
1068
1069 /**
1070 * Constant for the "Mathematical Operators" Unicode character block.
1071 * @since 1.2
1072 */
1073 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1074 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1075 "MATHEMATICAL OPERATORS",
1076 "MATHEMATICALOPERATORS");
1077
1078 /**
1079 * Constant for the "Miscellaneous Technical" Unicode character block.
1080 * @since 1.2
1081 */
1082 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1083 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1084 "MISCELLANEOUS TECHNICAL",
1085 "MISCELLANEOUSTECHNICAL");
1086
1087 /**
1088 * Constant for the "Control Pictures" Unicode character block.
1089 * @since 1.2
1090 */
1091 public static final UnicodeBlock CONTROL_PICTURES =
1092 new UnicodeBlock("CONTROL_PICTURES",
1093 "CONTROL PICTURES",
1094 "CONTROLPICTURES");
1095
1096 /**
1097 * Constant for the "Optical Character Recognition" Unicode character block.
1098 * @since 1.2
1099 */
1100 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1101 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1102 "OPTICAL CHARACTER RECOGNITION",
1103 "OPTICALCHARACTERRECOGNITION");
1104
1105 /**
1106 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1107 * @since 1.2
1108 */
1109 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1110 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1111 "ENCLOSED ALPHANUMERICS",
1112 "ENCLOSEDALPHANUMERICS");
1113
1114 /**
1115 * Constant for the "Box Drawing" Unicode character block.
1116 * @since 1.2
1117 */
1118 public static final UnicodeBlock BOX_DRAWING =
1119 new UnicodeBlock("BOX_DRAWING",
1120 "BOX DRAWING",
1121 "BOXDRAWING");
1122
1123 /**
1124 * Constant for the "Block Elements" Unicode character block.
1125 * @since 1.2
1126 */
1127 public static final UnicodeBlock BLOCK_ELEMENTS =
1128 new UnicodeBlock("BLOCK_ELEMENTS",
1129 "BLOCK ELEMENTS",
1130 "BLOCKELEMENTS");
1131
1132 /**
1133 * Constant for the "Geometric Shapes" Unicode character block.
1134 * @since 1.2
1135 */
1136 public static final UnicodeBlock GEOMETRIC_SHAPES =
1137 new UnicodeBlock("GEOMETRIC_SHAPES",
1138 "GEOMETRIC SHAPES",
1139 "GEOMETRICSHAPES");
1140
1141 /**
1142 * Constant for the "Miscellaneous Symbols" Unicode character block.
1143 * @since 1.2
1144 */
1145 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1146 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1147 "MISCELLANEOUS SYMBOLS",
1148 "MISCELLANEOUSSYMBOLS");
1149
1150 /**
1151 * Constant for the "Dingbats" Unicode character block.
1152 * @since 1.2
1153 */
1154 public static final UnicodeBlock DINGBATS =
1155 new UnicodeBlock("DINGBATS");
1156
1157 /**
1158 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1159 * @since 1.2
1160 */
1161 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1162 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1163 "CJK SYMBOLS AND PUNCTUATION",
1164 "CJKSYMBOLSANDPUNCTUATION");
1165
1166 /**
1167 * Constant for the "Hiragana" Unicode character block.
1168 * @since 1.2
1169 */
1170 public static final UnicodeBlock HIRAGANA =
1171 new UnicodeBlock("HIRAGANA");
1172
1173 /**
1174 * Constant for the "Katakana" Unicode character block.
1175 * @since 1.2
1176 */
1177 public static final UnicodeBlock KATAKANA =
1178 new UnicodeBlock("KATAKANA");
1179
1180 /**
1181 * Constant for the "Bopomofo" Unicode character block.
1182 * @since 1.2
1183 */
1184 public static final UnicodeBlock BOPOMOFO =
1185 new UnicodeBlock("BOPOMOFO");
1186
1187 /**
1188 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1189 * @since 1.2
1190 */
1191 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1192 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1193 "HANGUL COMPATIBILITY JAMO",
1194 "HANGULCOMPATIBILITYJAMO");
1195
1196 /**
1197 * Constant for the "Kanbun" Unicode character block.
1198 * @since 1.2
1199 */
1200 public static final UnicodeBlock KANBUN =
1201 new UnicodeBlock("KANBUN");
1202
1203 /**
1204 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1205 * @since 1.2
1206 */
1207 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1208 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1209 "ENCLOSED CJK LETTERS AND MONTHS",
1210 "ENCLOSEDCJKLETTERSANDMONTHS");
1211
1212 /**
1213 * Constant for the "CJK Compatibility" Unicode character block.
1214 * @since 1.2
1215 */
1216 public static final UnicodeBlock CJK_COMPATIBILITY =
1217 new UnicodeBlock("CJK_COMPATIBILITY",
1218 "CJK COMPATIBILITY",
1219 "CJKCOMPATIBILITY");
1220
1221 /**
1222 * Constant for the "CJK Unified Ideographs" Unicode character block.
1223 * @since 1.2
1224 */
1225 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1226 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1227 "CJK UNIFIED IDEOGRAPHS",
1228 "CJKUNIFIEDIDEOGRAPHS");
1229
1230 /**
1231 * Constant for the "Hangul Syllables" Unicode character block.
1232 * @since 1.2
1233 */
1234 public static final UnicodeBlock HANGUL_SYLLABLES =
1235 new UnicodeBlock("HANGUL_SYLLABLES",
1236 "HANGUL SYLLABLES",
1237 "HANGULSYLLABLES");
1238
1239 /**
1240 * Constant for the "Private Use Area" Unicode character block.
1241 * @since 1.2
1242 */
1243 public static final UnicodeBlock PRIVATE_USE_AREA =
1244 new UnicodeBlock("PRIVATE_USE_AREA",
1245 "PRIVATE USE AREA",
1246 "PRIVATEUSEAREA");
1247
1248 /**
1249 * Constant for the "CJK Compatibility Ideographs" Unicode character
1250 * block.
1251 * @since 1.2
1252 */
1253 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1254 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1255 "CJK COMPATIBILITY IDEOGRAPHS",
1256 "CJKCOMPATIBILITYIDEOGRAPHS");
1257
1258 /**
1259 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1260 * @since 1.2
1261 */
1262 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1263 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1264 "ALPHABETIC PRESENTATION FORMS",
1265 "ALPHABETICPRESENTATIONFORMS");
1266
1267 /**
1268 * Constant for the "Arabic Presentation Forms-A" Unicode character
1269 * block.
1270 * @since 1.2
1271 */
1272 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1273 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1274 "ARABIC PRESENTATION FORMS-A",
1275 "ARABICPRESENTATIONFORMS-A");
1276
1277 /**
1278 * Constant for the "Combining Half Marks" Unicode character block.
1279 * @since 1.2
1280 */
1281 public static final UnicodeBlock COMBINING_HALF_MARKS =
1282 new UnicodeBlock("COMBINING_HALF_MARKS",
1283 "COMBINING HALF MARKS",
1284 "COMBININGHALFMARKS");
1285
1286 /**
1287 * Constant for the "CJK Compatibility Forms" Unicode character block.
1288 * @since 1.2
1289 */
1290 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1291 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1292 "CJK COMPATIBILITY FORMS",
1293 "CJKCOMPATIBILITYFORMS");
1294
1295 /**
1296 * Constant for the "Small Form Variants" Unicode character block.
1297 * @since 1.2
1298 */
1299 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1300 new UnicodeBlock("SMALL_FORM_VARIANTS",
1301 "SMALL FORM VARIANTS",
1302 "SMALLFORMVARIANTS");
1303
1304 /**
1305 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1306 * @since 1.2
1307 */
1308 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1309 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1310 "ARABIC PRESENTATION FORMS-B",
1311 "ARABICPRESENTATIONFORMS-B");
1312
1313 /**
1314 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1315 * block.
1316 * @since 1.2
1317 */
1318 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1319 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1320 "HALFWIDTH AND FULLWIDTH FORMS",
1321 "HALFWIDTHANDFULLWIDTHFORMS");
1322
1323 /**
1324 * Constant for the "Specials" Unicode character block.
1325 * @since 1.2
1326 */
1327 public static final UnicodeBlock SPECIALS =
1328 new UnicodeBlock("SPECIALS");
1329
1330 /**
1331 * @deprecated
1332 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1333 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1334 * These constants match the block definitions of the Unicode Standard.
1335 * The {@link #of(char)} and {@link #of(int)} methods return the
1336 * standard constants.
1337 */
1338 @Deprecated(since="1.5")
1339 public static final UnicodeBlock SURROGATES_AREA =
1340 new UnicodeBlock("SURROGATES_AREA");
1341
1342 /**
1343 * Constant for the "Syriac" Unicode character block.
1344 * @since 1.4
1345 */
1346 public static final UnicodeBlock SYRIAC =
1347 new UnicodeBlock("SYRIAC");
1348
1349 /**
1350 * Constant for the "Thaana" Unicode character block.
1351 * @since 1.4
1352 */
1353 public static final UnicodeBlock THAANA =
1354 new UnicodeBlock("THAANA");
1355
1356 /**
1357 * Constant for the "Sinhala" Unicode character block.
1358 * @since 1.4
1359 */
1360 public static final UnicodeBlock SINHALA =
1361 new UnicodeBlock("SINHALA");
1362
1363 /**
1364 * Constant for the "Myanmar" Unicode character block.
1365 * @since 1.4
1366 */
1367 public static final UnicodeBlock MYANMAR =
1368 new UnicodeBlock("MYANMAR");
1369
1370 /**
1371 * Constant for the "Ethiopic" Unicode character block.
1372 * @since 1.4
1373 */
1374 public static final UnicodeBlock ETHIOPIC =
1375 new UnicodeBlock("ETHIOPIC");
1376
1377 /**
1378 * Constant for the "Cherokee" Unicode character block.
1379 * @since 1.4
1380 */
1381 public static final UnicodeBlock CHEROKEE =
1382 new UnicodeBlock("CHEROKEE");
1383
1384 /**
1385 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1386 * @since 1.4
1387 */
1388 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1389 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1390 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1391 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1392
1393 /**
1394 * Constant for the "Ogham" Unicode character block.
1395 * @since 1.4
1396 */
1397 public static final UnicodeBlock OGHAM =
1398 new UnicodeBlock("OGHAM");
1399
1400 /**
1401 * Constant for the "Runic" Unicode character block.
1402 * @since 1.4
1403 */
1404 public static final UnicodeBlock RUNIC =
1405 new UnicodeBlock("RUNIC");
1406
1407 /**
1408 * Constant for the "Khmer" Unicode character block.
1409 * @since 1.4
1410 */
1411 public static final UnicodeBlock KHMER =
1412 new UnicodeBlock("KHMER");
1413
1414 /**
1415 * Constant for the "Mongolian" Unicode character block.
1416 * @since 1.4
1417 */
1418 public static final UnicodeBlock MONGOLIAN =
1419 new UnicodeBlock("MONGOLIAN");
1420
1421 /**
1422 * Constant for the "Braille Patterns" Unicode character block.
1423 * @since 1.4
1424 */
1425 public static final UnicodeBlock BRAILLE_PATTERNS =
1426 new UnicodeBlock("BRAILLE_PATTERNS",
1427 "BRAILLE PATTERNS",
1428 "BRAILLEPATTERNS");
1429
1430 /**
1431 * Constant for the "CJK Radicals Supplement" Unicode character block.
1432 * @since 1.4
1433 */
1434 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1435 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1436 "CJK RADICALS SUPPLEMENT",
1437 "CJKRADICALSSUPPLEMENT");
1438
1439 /**
1440 * Constant for the "Kangxi Radicals" Unicode character block.
1441 * @since 1.4
1442 */
1443 public static final UnicodeBlock KANGXI_RADICALS =
1444 new UnicodeBlock("KANGXI_RADICALS",
1445 "KANGXI RADICALS",
1446 "KANGXIRADICALS");
1447
1448 /**
1449 * Constant for the "Ideographic Description Characters" Unicode character block.
1450 * @since 1.4
1451 */
1452 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1453 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1454 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1455 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1456
1457 /**
1458 * Constant for the "Bopomofo Extended" Unicode character block.
1459 * @since 1.4
1460 */
1461 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1462 new UnicodeBlock("BOPOMOFO_EXTENDED",
1463 "BOPOMOFO EXTENDED",
1464 "BOPOMOFOEXTENDED");
1465
1466 /**
1467 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1468 * @since 1.4
1469 */
1470 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1471 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1472 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1473 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1474
1475 /**
1476 * Constant for the "Yi Syllables" Unicode character block.
1477 * @since 1.4
1478 */
1479 public static final UnicodeBlock YI_SYLLABLES =
1480 new UnicodeBlock("YI_SYLLABLES",
1481 "YI SYLLABLES",
1482 "YISYLLABLES");
1483
1484 /**
1485 * Constant for the "Yi Radicals" Unicode character block.
1486 * @since 1.4
1487 */
1488 public static final UnicodeBlock YI_RADICALS =
1489 new UnicodeBlock("YI_RADICALS",
1490 "YI RADICALS",
1491 "YIRADICALS");
1492
1493 /**
1494 * Constant for the "Cyrillic Supplement" Unicode character block.
1495 * This block was previously known as the "Cyrillic Supplementary" block.
1496 * @since 1.5
1497 */
1498 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1499 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1500 "CYRILLIC SUPPLEMENTARY",
1501 "CYRILLICSUPPLEMENTARY",
1502 "CYRILLIC SUPPLEMENT",
1503 "CYRILLICSUPPLEMENT");
1504
1505 /**
1506 * Constant for the "Tagalog" Unicode character block.
1507 * @since 1.5
1508 */
1509 public static final UnicodeBlock TAGALOG =
1510 new UnicodeBlock("TAGALOG");
1511
1512 /**
1513 * Constant for the "Hanunoo" Unicode character block.
1514 * @since 1.5
1515 */
1516 public static final UnicodeBlock HANUNOO =
1517 new UnicodeBlock("HANUNOO");
1518
1519 /**
1520 * Constant for the "Buhid" Unicode character block.
1521 * @since 1.5
1522 */
1523 public static final UnicodeBlock BUHID =
1524 new UnicodeBlock("BUHID");
1525
1526 /**
1527 * Constant for the "Tagbanwa" Unicode character block.
1528 * @since 1.5
1529 */
1530 public static final UnicodeBlock TAGBANWA =
1531 new UnicodeBlock("TAGBANWA");
1532
1533 /**
1534 * Constant for the "Limbu" Unicode character block.
1535 * @since 1.5
1536 */
1537 public static final UnicodeBlock LIMBU =
1538 new UnicodeBlock("LIMBU");
1539
1540 /**
1541 * Constant for the "Tai Le" Unicode character block.
1542 * @since 1.5
1543 */
1544 public static final UnicodeBlock TAI_LE =
1545 new UnicodeBlock("TAI_LE",
1546 "TAI LE",
1547 "TAILE");
1548
1549 /**
1550 * Constant for the "Khmer Symbols" Unicode character block.
1551 * @since 1.5
1552 */
1553 public static final UnicodeBlock KHMER_SYMBOLS =
1554 new UnicodeBlock("KHMER_SYMBOLS",
1555 "KHMER SYMBOLS",
1556 "KHMERSYMBOLS");
1557
1558 /**
1559 * Constant for the "Phonetic Extensions" Unicode character block.
1560 * @since 1.5
1561 */
1562 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1563 new UnicodeBlock("PHONETIC_EXTENSIONS",
1564 "PHONETIC EXTENSIONS",
1565 "PHONETICEXTENSIONS");
1566
1567 /**
1568 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1569 * @since 1.5
1570 */
1571 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1572 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1573 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1574 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1575
1576 /**
1577 * Constant for the "Supplemental Arrows-A" Unicode character block.
1578 * @since 1.5
1579 */
1580 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1581 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1582 "SUPPLEMENTAL ARROWS-A",
1583 "SUPPLEMENTALARROWS-A");
1584
1585 /**
1586 * Constant for the "Supplemental Arrows-B" Unicode character block.
1587 * @since 1.5
1588 */
1589 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1590 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1591 "SUPPLEMENTAL ARROWS-B",
1592 "SUPPLEMENTALARROWS-B");
1593
1594 /**
1595 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1596 * character block.
1597 * @since 1.5
1598 */
1599 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1600 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1601 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1602 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1603
1604 /**
1605 * Constant for the "Supplemental Mathematical Operators" Unicode
1606 * character block.
1607 * @since 1.5
1608 */
1609 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1610 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1611 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1612 "SUPPLEMENTALMATHEMATICALOPERATORS");
1613
1614 /**
1615 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1616 * block.
1617 * @since 1.5
1618 */
1619 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1620 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1621 "MISCELLANEOUS SYMBOLS AND ARROWS",
1622 "MISCELLANEOUSSYMBOLSANDARROWS");
1623
1624 /**
1625 * Constant for the "Katakana Phonetic Extensions" Unicode character
1626 * block.
1627 * @since 1.5
1628 */
1629 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1630 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1631 "KATAKANA PHONETIC EXTENSIONS",
1632 "KATAKANAPHONETICEXTENSIONS");
1633
1634 /**
1635 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1636 * @since 1.5
1637 */
1638 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1639 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1640 "YIJING HEXAGRAM SYMBOLS",
1641 "YIJINGHEXAGRAMSYMBOLS");
1642
1643 /**
1644 * Constant for the "Variation Selectors" Unicode character block.
1645 * @since 1.5
1646 */
1647 public static final UnicodeBlock VARIATION_SELECTORS =
1648 new UnicodeBlock("VARIATION_SELECTORS",
1649 "VARIATION SELECTORS",
1650 "VARIATIONSELECTORS");
1651
1652 /**
1653 * Constant for the "Linear B Syllabary" Unicode character block.
1654 * @since 1.5
1655 */
1656 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1657 new UnicodeBlock("LINEAR_B_SYLLABARY",
1658 "LINEAR B SYLLABARY",
1659 "LINEARBSYLLABARY");
1660
1661 /**
1662 * Constant for the "Linear B Ideograms" Unicode character block.
1663 * @since 1.5
1664 */
1665 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1666 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1667 "LINEAR B IDEOGRAMS",
1668 "LINEARBIDEOGRAMS");
1669
1670 /**
1671 * Constant for the "Aegean Numbers" Unicode character block.
1672 * @since 1.5
1673 */
1674 public static final UnicodeBlock AEGEAN_NUMBERS =
1675 new UnicodeBlock("AEGEAN_NUMBERS",
1676 "AEGEAN NUMBERS",
1677 "AEGEANNUMBERS");
1678
1679 /**
1680 * Constant for the "Old Italic" Unicode character block.
1681 * @since 1.5
1682 */
1683 public static final UnicodeBlock OLD_ITALIC =
1684 new UnicodeBlock("OLD_ITALIC",
1685 "OLD ITALIC",
1686 "OLDITALIC");
1687
1688 /**
1689 * Constant for the "Gothic" Unicode character block.
1690 * @since 1.5
1691 */
1692 public static final UnicodeBlock GOTHIC =
1693 new UnicodeBlock("GOTHIC");
1694
1695 /**
1696 * Constant for the "Ugaritic" Unicode character block.
1697 * @since 1.5
1698 */
1699 public static final UnicodeBlock UGARITIC =
1700 new UnicodeBlock("UGARITIC");
1701
1702 /**
1703 * Constant for the "Deseret" Unicode character block.
1704 * @since 1.5
1705 */
1706 public static final UnicodeBlock DESERET =
1707 new UnicodeBlock("DESERET");
1708
1709 /**
1710 * Constant for the "Shavian" Unicode character block.
1711 * @since 1.5
1712 */
1713 public static final UnicodeBlock SHAVIAN =
1714 new UnicodeBlock("SHAVIAN");
1715
1716 /**
1717 * Constant for the "Osmanya" Unicode character block.
1718 * @since 1.5
1719 */
1720 public static final UnicodeBlock OSMANYA =
1721 new UnicodeBlock("OSMANYA");
1722
1723 /**
1724 * Constant for the "Cypriot Syllabary" Unicode character block.
1725 * @since 1.5
1726 */
1727 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1728 new UnicodeBlock("CYPRIOT_SYLLABARY",
1729 "CYPRIOT SYLLABARY",
1730 "CYPRIOTSYLLABARY");
1731
1732 /**
1733 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1734 * @since 1.5
1735 */
1736 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1737 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1738 "BYZANTINE MUSICAL SYMBOLS",
1739 "BYZANTINEMUSICALSYMBOLS");
1740
1741 /**
1742 * Constant for the "Musical Symbols" Unicode character block.
1743 * @since 1.5
1744 */
1745 public static final UnicodeBlock MUSICAL_SYMBOLS =
1746 new UnicodeBlock("MUSICAL_SYMBOLS",
1747 "MUSICAL SYMBOLS",
1748 "MUSICALSYMBOLS");
1749
1750 /**
1751 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1752 * @since 1.5
1753 */
1754 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1755 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1756 "TAI XUAN JING SYMBOLS",
1757 "TAIXUANJINGSYMBOLS");
1758
1759 /**
1760 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1761 * character block.
1762 * @since 1.5
1763 */
1764 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1765 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1766 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1767 "MATHEMATICALALPHANUMERICSYMBOLS");
1768
1769 /**
1770 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1771 * character block.
1772 * @since 1.5
1773 */
1774 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1775 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1776 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1777 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1778
1779 /**
1780 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1781 * @since 1.5
1782 */
1783 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1784 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1785 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1786 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1787
1788 /**
1789 * Constant for the "Tags" Unicode character block.
1790 * @since 1.5
1791 */
1792 public static final UnicodeBlock TAGS =
1793 new UnicodeBlock("TAGS");
1794
1795 /**
1796 * Constant for the "Variation Selectors Supplement" Unicode character
1797 * block.
1798 * @since 1.5
1799 */
1800 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1801 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1802 "VARIATION SELECTORS SUPPLEMENT",
1803 "VARIATIONSELECTORSSUPPLEMENT");
1804
1805 /**
1806 * Constant for the "Supplementary Private Use Area-A" Unicode character
1807 * block.
1808 * @since 1.5
1809 */
1810 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1811 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1812 "SUPPLEMENTARY PRIVATE USE AREA-A",
1813 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1814
1815 /**
1816 * Constant for the "Supplementary Private Use Area-B" Unicode character
1817 * block.
1818 * @since 1.5
1819 */
1820 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1821 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1822 "SUPPLEMENTARY PRIVATE USE AREA-B",
1823 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1824
1825 /**
1826 * Constant for the "High Surrogates" Unicode character block.
1827 * This block represents codepoint values in the high surrogate
1828 * range: U+D800 through U+DB7F
1829 *
1830 * @since 1.5
1831 */
1832 public static final UnicodeBlock HIGH_SURROGATES =
1833 new UnicodeBlock("HIGH_SURROGATES",
1834 "HIGH SURROGATES",
1835 "HIGHSURROGATES");
1836
1837 /**
1838 * Constant for the "High Private Use Surrogates" Unicode character
1839 * block.
1840 * This block represents codepoint values in the private use high
1841 * surrogate range: U+DB80 through U+DBFF
1842 *
1843 * @since 1.5
1844 */
1845 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1846 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1847 "HIGH PRIVATE USE SURROGATES",
1848 "HIGHPRIVATEUSESURROGATES");
1849
1850 /**
1851 * Constant for the "Low Surrogates" Unicode character block.
1852 * This block represents codepoint values in the low surrogate
1853 * range: U+DC00 through U+DFFF
1854 *
1855 * @since 1.5
1856 */
1857 public static final UnicodeBlock LOW_SURROGATES =
1858 new UnicodeBlock("LOW_SURROGATES",
1859 "LOW SURROGATES",
1860 "LOWSURROGATES");
1861
1862 /**
1863 * Constant for the "Arabic Supplement" Unicode character block.
1864 * @since 1.7
1865 */
1866 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1867 new UnicodeBlock("ARABIC_SUPPLEMENT",
1868 "ARABIC SUPPLEMENT",
1869 "ARABICSUPPLEMENT");
1870
1871 /**
1872 * Constant for the "NKo" Unicode character block.
1873 * @since 1.7
1874 */
1875 public static final UnicodeBlock NKO =
1876 new UnicodeBlock("NKO");
1877
1878 /**
1879 * Constant for the "Samaritan" Unicode character block.
1880 * @since 1.7
1881 */
1882 public static final UnicodeBlock SAMARITAN =
1883 new UnicodeBlock("SAMARITAN");
1884
1885 /**
1886 * Constant for the "Mandaic" Unicode character block.
1887 * @since 1.7
1888 */
1889 public static final UnicodeBlock MANDAIC =
1890 new UnicodeBlock("MANDAIC");
1891
1892 /**
1893 * Constant for the "Ethiopic Supplement" Unicode character block.
1894 * @since 1.7
1895 */
1896 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1897 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1898 "ETHIOPIC SUPPLEMENT",
1899 "ETHIOPICSUPPLEMENT");
1900
1901 /**
1902 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1903 * Unicode character block.
1904 * @since 1.7
1905 */
1906 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1907 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1908 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1909 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1910
1911 /**
1912 * Constant for the "New Tai Lue" Unicode character block.
1913 * @since 1.7
1914 */
1915 public static final UnicodeBlock NEW_TAI_LUE =
1916 new UnicodeBlock("NEW_TAI_LUE",
1917 "NEW TAI LUE",
1918 "NEWTAILUE");
1919
1920 /**
1921 * Constant for the "Buginese" Unicode character block.
1922 * @since 1.7
1923 */
1924 public static final UnicodeBlock BUGINESE =
1925 new UnicodeBlock("BUGINESE");
1926
1927 /**
1928 * Constant for the "Tai Tham" Unicode character block.
1929 * @since 1.7
1930 */
1931 public static final UnicodeBlock TAI_THAM =
1932 new UnicodeBlock("TAI_THAM",
1933 "TAI THAM",
1934 "TAITHAM");
1935
1936 /**
1937 * Constant for the "Balinese" Unicode character block.
1938 * @since 1.7
1939 */
1940 public static final UnicodeBlock BALINESE =
1941 new UnicodeBlock("BALINESE");
1942
1943 /**
1944 * Constant for the "Sundanese" Unicode character block.
1945 * @since 1.7
1946 */
1947 public static final UnicodeBlock SUNDANESE =
1948 new UnicodeBlock("SUNDANESE");
1949
1950 /**
1951 * Constant for the "Batak" Unicode character block.
1952 * @since 1.7
1953 */
1954 public static final UnicodeBlock BATAK =
1955 new UnicodeBlock("BATAK");
1956
1957 /**
1958 * Constant for the "Lepcha" Unicode character block.
1959 * @since 1.7
1960 */
1961 public static final UnicodeBlock LEPCHA =
1962 new UnicodeBlock("LEPCHA");
1963
1964 /**
1965 * Constant for the "Ol Chiki" Unicode character block.
1966 * @since 1.7
1967 */
1968 public static final UnicodeBlock OL_CHIKI =
1969 new UnicodeBlock("OL_CHIKI",
1970 "OL CHIKI",
1971 "OLCHIKI");
1972
1973 /**
1974 * Constant for the "Vedic Extensions" Unicode character block.
1975 * @since 1.7
1976 */
1977 public static final UnicodeBlock VEDIC_EXTENSIONS =
1978 new UnicodeBlock("VEDIC_EXTENSIONS",
1979 "VEDIC EXTENSIONS",
1980 "VEDICEXTENSIONS");
1981
1982 /**
1983 * Constant for the "Phonetic Extensions Supplement" Unicode character
1984 * block.
1985 * @since 1.7
1986 */
1987 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1988 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1989 "PHONETIC EXTENSIONS SUPPLEMENT",
1990 "PHONETICEXTENSIONSSUPPLEMENT");
1991
1992 /**
1993 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1994 * character block.
1995 * @since 1.7
1996 */
1997 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1998 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1999 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
2000 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2001
2002 /**
2003 * Constant for the "Glagolitic" Unicode character block.
2004 * @since 1.7
2005 */
2006 public static final UnicodeBlock GLAGOLITIC =
2007 new UnicodeBlock("GLAGOLITIC");
2008
2009 /**
2010 * Constant for the "Latin Extended-C" Unicode character block.
2011 * @since 1.7
2012 */
2013 public static final UnicodeBlock LATIN_EXTENDED_C =
2014 new UnicodeBlock("LATIN_EXTENDED_C",
2015 "LATIN EXTENDED-C",
2016 "LATINEXTENDED-C");
2017
2018 /**
2019 * Constant for the "Coptic" Unicode character block.
2020 * @since 1.7
2021 */
2022 public static final UnicodeBlock COPTIC =
2023 new UnicodeBlock("COPTIC");
2024
2025 /**
2026 * Constant for the "Georgian Supplement" Unicode character block.
2027 * @since 1.7
2028 */
2029 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2030 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2031 "GEORGIAN SUPPLEMENT",
2032 "GEORGIANSUPPLEMENT");
2033
2034 /**
2035 * Constant for the "Tifinagh" Unicode character block.
2036 * @since 1.7
2037 */
2038 public static final UnicodeBlock TIFINAGH =
2039 new UnicodeBlock("TIFINAGH");
2040
2041 /**
2042 * Constant for the "Ethiopic Extended" Unicode character block.
2043 * @since 1.7
2044 */
2045 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2046 new UnicodeBlock("ETHIOPIC_EXTENDED",
2047 "ETHIOPIC EXTENDED",
2048 "ETHIOPICEXTENDED");
2049
2050 /**
2051 * Constant for the "Cyrillic Extended-A" Unicode character block.
2052 * @since 1.7
2053 */
2054 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2055 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2056 "CYRILLIC EXTENDED-A",
2057 "CYRILLICEXTENDED-A");
2058
2059 /**
2060 * Constant for the "Supplemental Punctuation" Unicode character block.
2061 * @since 1.7
2062 */
2063 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2064 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2065 "SUPPLEMENTAL PUNCTUATION",
2066 "SUPPLEMENTALPUNCTUATION");
2067
2068 /**
2069 * Constant for the "CJK Strokes" Unicode character block.
2070 * @since 1.7
2071 */
2072 public static final UnicodeBlock CJK_STROKES =
2073 new UnicodeBlock("CJK_STROKES",
2074 "CJK STROKES",
2075 "CJKSTROKES");
2076
2077 /**
2078 * Constant for the "Lisu" Unicode character block.
2079 * @since 1.7
2080 */
2081 public static final UnicodeBlock LISU =
2082 new UnicodeBlock("LISU");
2083
2084 /**
2085 * Constant for the "Vai" Unicode character block.
2086 * @since 1.7
2087 */
2088 public static final UnicodeBlock VAI =
2089 new UnicodeBlock("VAI");
2090
2091 /**
2092 * Constant for the "Cyrillic Extended-B" Unicode character block.
2093 * @since 1.7
2094 */
2095 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2096 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2097 "CYRILLIC EXTENDED-B",
2098 "CYRILLICEXTENDED-B");
2099
2100 /**
2101 * Constant for the "Bamum" Unicode character block.
2102 * @since 1.7
2103 */
2104 public static final UnicodeBlock BAMUM =
2105 new UnicodeBlock("BAMUM");
2106
2107 /**
2108 * Constant for the "Modifier Tone Letters" Unicode character block.
2109 * @since 1.7
2110 */
2111 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2112 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2113 "MODIFIER TONE LETTERS",
2114 "MODIFIERTONELETTERS");
2115
2116 /**
2117 * Constant for the "Latin Extended-D" Unicode character block.
2118 * @since 1.7
2119 */
2120 public static final UnicodeBlock LATIN_EXTENDED_D =
2121 new UnicodeBlock("LATIN_EXTENDED_D",
2122 "LATIN EXTENDED-D",
2123 "LATINEXTENDED-D");
2124
2125 /**
2126 * Constant for the "Syloti Nagri" Unicode character block.
2127 * @since 1.7
2128 */
2129 public static final UnicodeBlock SYLOTI_NAGRI =
2130 new UnicodeBlock("SYLOTI_NAGRI",
2131 "SYLOTI NAGRI",
2132 "SYLOTINAGRI");
2133
2134 /**
2135 * Constant for the "Common Indic Number Forms" Unicode character block.
2136 * @since 1.7
2137 */
2138 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2139 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2140 "COMMON INDIC NUMBER FORMS",
2141 "COMMONINDICNUMBERFORMS");
2142
2143 /**
2144 * Constant for the "Phags-pa" Unicode character block.
2145 * @since 1.7
2146 */
2147 public static final UnicodeBlock PHAGS_PA =
2148 new UnicodeBlock("PHAGS_PA",
2149 "PHAGS-PA");
2150
2151 /**
2152 * Constant for the "Saurashtra" Unicode character block.
2153 * @since 1.7
2154 */
2155 public static final UnicodeBlock SAURASHTRA =
2156 new UnicodeBlock("SAURASHTRA");
2157
2158 /**
2159 * Constant for the "Devanagari Extended" Unicode character block.
2160 * @since 1.7
2161 */
2162 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2163 new UnicodeBlock("DEVANAGARI_EXTENDED",
2164 "DEVANAGARI EXTENDED",
2165 "DEVANAGARIEXTENDED");
2166
2167 /**
2168 * Constant for the "Kayah Li" Unicode character block.
2169 * @since 1.7
2170 */
2171 public static final UnicodeBlock KAYAH_LI =
2172 new UnicodeBlock("KAYAH_LI",
2173 "KAYAH LI",
2174 "KAYAHLI");
2175
2176 /**
2177 * Constant for the "Rejang" Unicode character block.
2178 * @since 1.7
2179 */
2180 public static final UnicodeBlock REJANG =
2181 new UnicodeBlock("REJANG");
2182
2183 /**
2184 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2185 * @since 1.7
2186 */
2187 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2188 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2189 "HANGUL JAMO EXTENDED-A",
2190 "HANGULJAMOEXTENDED-A");
2191
2192 /**
2193 * Constant for the "Javanese" Unicode character block.
2194 * @since 1.7
2195 */
2196 public static final UnicodeBlock JAVANESE =
2197 new UnicodeBlock("JAVANESE");
2198
2199 /**
2200 * Constant for the "Cham" Unicode character block.
2201 * @since 1.7
2202 */
2203 public static final UnicodeBlock CHAM =
2204 new UnicodeBlock("CHAM");
2205
2206 /**
2207 * Constant for the "Myanmar Extended-A" Unicode character block.
2208 * @since 1.7
2209 */
2210 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2211 new UnicodeBlock("MYANMAR_EXTENDED_A",
2212 "MYANMAR EXTENDED-A",
2213 "MYANMAREXTENDED-A");
2214
2215 /**
2216 * Constant for the "Tai Viet" Unicode character block.
2217 * @since 1.7
2218 */
2219 public static final UnicodeBlock TAI_VIET =
2220 new UnicodeBlock("TAI_VIET",
2221 "TAI VIET",
2222 "TAIVIET");
2223
2224 /**
2225 * Constant for the "Ethiopic Extended-A" Unicode character block.
2226 * @since 1.7
2227 */
2228 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2229 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2230 "ETHIOPIC EXTENDED-A",
2231 "ETHIOPICEXTENDED-A");
2232
2233 /**
2234 * Constant for the "Meetei Mayek" Unicode character block.
2235 * @since 1.7
2236 */
2237 public static final UnicodeBlock MEETEI_MAYEK =
2238 new UnicodeBlock("MEETEI_MAYEK",
2239 "MEETEI MAYEK",
2240 "MEETEIMAYEK");
2241
2242 /**
2243 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2244 * @since 1.7
2245 */
2246 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2247 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2248 "HANGUL JAMO EXTENDED-B",
2249 "HANGULJAMOEXTENDED-B");
2250
2251 /**
2252 * Constant for the "Vertical Forms" Unicode character block.
2253 * @since 1.7
2254 */
2255 public static final UnicodeBlock VERTICAL_FORMS =
2256 new UnicodeBlock("VERTICAL_FORMS",
2257 "VERTICAL FORMS",
2258 "VERTICALFORMS");
2259
2260 /**
2261 * Constant for the "Ancient Greek Numbers" Unicode character block.
2262 * @since 1.7
2263 */
2264 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2265 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2266 "ANCIENT GREEK NUMBERS",
2267 "ANCIENTGREEKNUMBERS");
2268
2269 /**
2270 * Constant for the "Ancient Symbols" Unicode character block.
2271 * @since 1.7
2272 */
2273 public static final UnicodeBlock ANCIENT_SYMBOLS =
2274 new UnicodeBlock("ANCIENT_SYMBOLS",
2275 "ANCIENT SYMBOLS",
2276 "ANCIENTSYMBOLS");
2277
2278 /**
2279 * Constant for the "Phaistos Disc" Unicode character block.
2280 * @since 1.7
2281 */
2282 public static final UnicodeBlock PHAISTOS_DISC =
2283 new UnicodeBlock("PHAISTOS_DISC",
2284 "PHAISTOS DISC",
2285 "PHAISTOSDISC");
2286
2287 /**
2288 * Constant for the "Lycian" Unicode character block.
2289 * @since 1.7
2290 */
2291 public static final UnicodeBlock LYCIAN =
2292 new UnicodeBlock("LYCIAN");
2293
2294 /**
2295 * Constant for the "Carian" Unicode character block.
2296 * @since 1.7
2297 */
2298 public static final UnicodeBlock CARIAN =
2299 new UnicodeBlock("CARIAN");
2300
2301 /**
2302 * Constant for the "Old Persian" Unicode character block.
2303 * @since 1.7
2304 */
2305 public static final UnicodeBlock OLD_PERSIAN =
2306 new UnicodeBlock("OLD_PERSIAN",
2307 "OLD PERSIAN",
2308 "OLDPERSIAN");
2309
2310 /**
2311 * Constant for the "Imperial Aramaic" Unicode character block.
2312 * @since 1.7
2313 */
2314 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2315 new UnicodeBlock("IMPERIAL_ARAMAIC",
2316 "IMPERIAL ARAMAIC",
2317 "IMPERIALARAMAIC");
2318
2319 /**
2320 * Constant for the "Phoenician" Unicode character block.
2321 * @since 1.7
2322 */
2323 public static final UnicodeBlock PHOENICIAN =
2324 new UnicodeBlock("PHOENICIAN");
2325
2326 /**
2327 * Constant for the "Lydian" Unicode character block.
2328 * @since 1.7
2329 */
2330 public static final UnicodeBlock LYDIAN =
2331 new UnicodeBlock("LYDIAN");
2332
2333 /**
2334 * Constant for the "Kharoshthi" Unicode character block.
2335 * @since 1.7
2336 */
2337 public static final UnicodeBlock KHAROSHTHI =
2338 new UnicodeBlock("KHAROSHTHI");
2339
2340 /**
2341 * Constant for the "Old South Arabian" Unicode character block.
2342 * @since 1.7
2343 */
2344 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2345 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2346 "OLD SOUTH ARABIAN",
2347 "OLDSOUTHARABIAN");
2348
2349 /**
2350 * Constant for the "Avestan" Unicode character block.
2351 * @since 1.7
2352 */
2353 public static final UnicodeBlock AVESTAN =
2354 new UnicodeBlock("AVESTAN");
2355
2356 /**
2357 * Constant for the "Inscriptional Parthian" Unicode character block.
2358 * @since 1.7
2359 */
2360 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2361 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2362 "INSCRIPTIONAL PARTHIAN",
2363 "INSCRIPTIONALPARTHIAN");
2364
2365 /**
2366 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2367 * @since 1.7
2368 */
2369 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2370 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2371 "INSCRIPTIONAL PAHLAVI",
2372 "INSCRIPTIONALPAHLAVI");
2373
2374 /**
2375 * Constant for the "Old Turkic" Unicode character block.
2376 * @since 1.7
2377 */
2378 public static final UnicodeBlock OLD_TURKIC =
2379 new UnicodeBlock("OLD_TURKIC",
2380 "OLD TURKIC",
2381 "OLDTURKIC");
2382
2383 /**
2384 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2385 * @since 1.7
2386 */
2387 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2388 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2389 "RUMI NUMERAL SYMBOLS",
2390 "RUMINUMERALSYMBOLS");
2391
2392 /**
2393 * Constant for the "Brahmi" Unicode character block.
2394 * @since 1.7
2395 */
2396 public static final UnicodeBlock BRAHMI =
2397 new UnicodeBlock("BRAHMI");
2398
2399 /**
2400 * Constant for the "Kaithi" Unicode character block.
2401 * @since 1.7
2402 */
2403 public static final UnicodeBlock KAITHI =
2404 new UnicodeBlock("KAITHI");
2405
2406 /**
2407 * Constant for the "Cuneiform" Unicode character block.
2408 * @since 1.7
2409 */
2410 public static final UnicodeBlock CUNEIFORM =
2411 new UnicodeBlock("CUNEIFORM");
2412
2413 /**
2414 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2415 * character block.
2416 * @since 1.7
2417 */
2418 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2419 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2420 "CUNEIFORM NUMBERS AND PUNCTUATION",
2421 "CUNEIFORMNUMBERSANDPUNCTUATION");
2422
2423 /**
2424 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2425 * @since 1.7
2426 */
2427 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2428 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2429 "EGYPTIAN HIEROGLYPHS",
2430 "EGYPTIANHIEROGLYPHS");
2431
2432 /**
2433 * Constant for the "Bamum Supplement" Unicode character block.
2434 * @since 1.7
2435 */
2436 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2437 new UnicodeBlock("BAMUM_SUPPLEMENT",
2438 "BAMUM SUPPLEMENT",
2439 "BAMUMSUPPLEMENT");
2440
2441 /**
2442 * Constant for the "Kana Supplement" Unicode character block.
2443 * @since 1.7
2444 */
2445 public static final UnicodeBlock KANA_SUPPLEMENT =
2446 new UnicodeBlock("KANA_SUPPLEMENT",
2447 "KANA SUPPLEMENT",
2448 "KANASUPPLEMENT");
2449
2450 /**
2451 * Constant for the "Ancient Greek Musical Notation" Unicode character
2452 * block.
2453 * @since 1.7
2454 */
2455 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2456 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2457 "ANCIENT GREEK MUSICAL NOTATION",
2458 "ANCIENTGREEKMUSICALNOTATION");
2459
2460 /**
2461 * Constant for the "Counting Rod Numerals" Unicode character block.
2462 * @since 1.7
2463 */
2464 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2465 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2466 "COUNTING ROD NUMERALS",
2467 "COUNTINGRODNUMERALS");
2468
2469 /**
2470 * Constant for the "Mahjong Tiles" Unicode character block.
2471 * @since 1.7
2472 */
2473 public static final UnicodeBlock MAHJONG_TILES =
2474 new UnicodeBlock("MAHJONG_TILES",
2475 "MAHJONG TILES",
2476 "MAHJONGTILES");
2477
2478 /**
2479 * Constant for the "Domino Tiles" Unicode character block.
2480 * @since 1.7
2481 */
2482 public static final UnicodeBlock DOMINO_TILES =
2483 new UnicodeBlock("DOMINO_TILES",
2484 "DOMINO TILES",
2485 "DOMINOTILES");
2486
2487 /**
2488 * Constant for the "Playing Cards" Unicode character block.
2489 * @since 1.7
2490 */
2491 public static final UnicodeBlock PLAYING_CARDS =
2492 new UnicodeBlock("PLAYING_CARDS",
2493 "PLAYING CARDS",
2494 "PLAYINGCARDS");
2495
2496 /**
2497 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2498 * block.
2499 * @since 1.7
2500 */
2501 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2502 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2503 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2504 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2505
2506 /**
2507 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2508 * block.
2509 * @since 1.7
2510 */
2511 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2512 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2513 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2514 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2515
2516 /**
2517 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2518 * character block.
2519 * @since 1.7
2520 */
2521 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2522 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2523 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2524 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2525
2526 /**
2527 * Constant for the "Emoticons" Unicode character block.
2528 * @since 1.7
2529 */
2530 public static final UnicodeBlock EMOTICONS =
2531 new UnicodeBlock("EMOTICONS");
2532
2533 /**
2534 * Constant for the "Transport And Map Symbols" Unicode character block.
2535 * @since 1.7
2536 */
2537 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2538 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2539 "TRANSPORT AND MAP SYMBOLS",
2540 "TRANSPORTANDMAPSYMBOLS");
2541
2542 /**
2543 * Constant for the "Alchemical Symbols" Unicode character block.
2544 * @since 1.7
2545 */
2546 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2547 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2548 "ALCHEMICAL SYMBOLS",
2549 "ALCHEMICALSYMBOLS");
2550
2551 /**
2552 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2553 * character block.
2554 * @since 1.7
2555 */
2556 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2557 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2558 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2559 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2560
2561 /**
2562 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2563 * character block.
2564 * @since 1.7
2565 */
2566 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2567 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2568 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2569 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2570
2571 /**
2572 * Constant for the "Arabic Extended-A" Unicode character block.
2573 * @since 1.8
2574 */
2575 public static final UnicodeBlock ARABIC_EXTENDED_A =
2576 new UnicodeBlock("ARABIC_EXTENDED_A",
2577 "ARABIC EXTENDED-A",
2578 "ARABICEXTENDED-A");
2579
2580 /**
2581 * Constant for the "Sundanese Supplement" Unicode character block.
2582 * @since 1.8
2583 */
2584 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2585 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2586 "SUNDANESE SUPPLEMENT",
2587 "SUNDANESESUPPLEMENT");
2588
2589 /**
2590 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2591 * @since 1.8
2592 */
2593 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2594 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2595 "MEETEI MAYEK EXTENSIONS",
2596 "MEETEIMAYEKEXTENSIONS");
2597
2598 /**
2599 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2600 * @since 1.8
2601 */
2602 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2603 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2604 "MEROITIC HIEROGLYPHS",
2605 "MEROITICHIEROGLYPHS");
2606
2607 /**
2608 * Constant for the "Meroitic Cursive" Unicode character block.
2609 * @since 1.8
2610 */
2611 public static final UnicodeBlock MEROITIC_CURSIVE =
2612 new UnicodeBlock("MEROITIC_CURSIVE",
2613 "MEROITIC CURSIVE",
2614 "MEROITICCURSIVE");
2615
2616 /**
2617 * Constant for the "Sora Sompeng" Unicode character block.
2618 * @since 1.8
2619 */
2620 public static final UnicodeBlock SORA_SOMPENG =
2621 new UnicodeBlock("SORA_SOMPENG",
2622 "SORA SOMPENG",
2623 "SORASOMPENG");
2624
2625 /**
2626 * Constant for the "Chakma" Unicode character block.
2627 * @since 1.8
2628 */
2629 public static final UnicodeBlock CHAKMA =
2630 new UnicodeBlock("CHAKMA");
2631
2632 /**
2633 * Constant for the "Sharada" Unicode character block.
2634 * @since 1.8
2635 */
2636 public static final UnicodeBlock SHARADA =
2637 new UnicodeBlock("SHARADA");
2638
2639 /**
2640 * Constant for the "Takri" Unicode character block.
2641 * @since 1.8
2642 */
2643 public static final UnicodeBlock TAKRI =
2644 new UnicodeBlock("TAKRI");
2645
2646 /**
2647 * Constant for the "Miao" Unicode character block.
2648 * @since 1.8
2649 */
2650 public static final UnicodeBlock MIAO =
2651 new UnicodeBlock("MIAO");
2652
2653 /**
2654 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2655 * character block.
2656 * @since 1.8
2657 */
2658 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2659 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2660 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2661 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2662
2663 /**
2664 * Constant for the "Combining Diacritical Marks Extended" Unicode
2665 * character block.
2666 * @since 9
2667 */
2668 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2669 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2670 "COMBINING DIACRITICAL MARKS EXTENDED",
2671 "COMBININGDIACRITICALMARKSEXTENDED");
2672
2673 /**
2674 * Constant for the "Myanmar Extended-B" Unicode character block.
2675 * @since 9
2676 */
2677 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2678 new UnicodeBlock("MYANMAR_EXTENDED_B",
2679 "MYANMAR EXTENDED-B",
2680 "MYANMAREXTENDED-B");
2681
2682 /**
2683 * Constant for the "Latin Extended-E" Unicode character block.
2684 * @since 9
2685 */
2686 public static final UnicodeBlock LATIN_EXTENDED_E =
2687 new UnicodeBlock("LATIN_EXTENDED_E",
2688 "LATIN EXTENDED-E",
2689 "LATINEXTENDED-E");
2690
2691 /**
2692 * Constant for the "Coptic Epact Numbers" Unicode character block.
2693 * @since 9
2694 */
2695 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2696 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2697 "COPTIC EPACT NUMBERS",
2698 "COPTICEPACTNUMBERS");
2699
2700 /**
2701 * Constant for the "Old Permic" Unicode character block.
2702 * @since 9
2703 */
2704 public static final UnicodeBlock OLD_PERMIC =
2705 new UnicodeBlock("OLD_PERMIC",
2706 "OLD PERMIC",
2707 "OLDPERMIC");
2708
2709 /**
2710 * Constant for the "Elbasan" Unicode character block.
2711 * @since 9
2712 */
2713 public static final UnicodeBlock ELBASAN =
2714 new UnicodeBlock("ELBASAN");
2715
2716 /**
2717 * Constant for the "Caucasian Albanian" Unicode character block.
2718 * @since 9
2719 */
2720 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2721 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2722 "CAUCASIAN ALBANIAN",
2723 "CAUCASIANALBANIAN");
2724
2725 /**
2726 * Constant for the "Linear A" Unicode character block.
2727 * @since 9
2728 */
2729 public static final UnicodeBlock LINEAR_A =
2730 new UnicodeBlock("LINEAR_A",
2731 "LINEAR A",
2732 "LINEARA");
2733
2734 /**
2735 * Constant for the "Palmyrene" Unicode character block.
2736 * @since 9
2737 */
2738 public static final UnicodeBlock PALMYRENE =
2739 new UnicodeBlock("PALMYRENE");
2740
2741 /**
2742 * Constant for the "Nabataean" Unicode character block.
2743 * @since 9
2744 */
2745 public static final UnicodeBlock NABATAEAN =
2746 new UnicodeBlock("NABATAEAN");
2747
2748 /**
2749 * Constant for the "Old North Arabian" Unicode character block.
2750 * @since 9
2751 */
2752 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2753 new UnicodeBlock("OLD_NORTH_ARABIAN",
2754 "OLD NORTH ARABIAN",
2755 "OLDNORTHARABIAN");
2756
2757 /**
2758 * Constant for the "Manichaean" Unicode character block.
2759 * @since 9
2760 */
2761 public static final UnicodeBlock MANICHAEAN =
2762 new UnicodeBlock("MANICHAEAN");
2763
2764 /**
2765 * Constant for the "Psalter Pahlavi" Unicode character block.
2766 * @since 9
2767 */
2768 public static final UnicodeBlock PSALTER_PAHLAVI =
2769 new UnicodeBlock("PSALTER_PAHLAVI",
2770 "PSALTER PAHLAVI",
2771 "PSALTERPAHLAVI");
2772
2773 /**
2774 * Constant for the "Mahajani" Unicode character block.
2775 * @since 9
2776 */
2777 public static final UnicodeBlock MAHAJANI =
2778 new UnicodeBlock("MAHAJANI");
2779
2780 /**
2781 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2782 * @since 9
2783 */
2784 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2785 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2786 "SINHALA ARCHAIC NUMBERS",
2787 "SINHALAARCHAICNUMBERS");
2788
2789 /**
2790 * Constant for the "Khojki" Unicode character block.
2791 * @since 9
2792 */
2793 public static final UnicodeBlock KHOJKI =
2794 new UnicodeBlock("KHOJKI");
2795
2796 /**
2797 * Constant for the "Khudawadi" Unicode character block.
2798 * @since 9
2799 */
2800 public static final UnicodeBlock KHUDAWADI =
2801 new UnicodeBlock("KHUDAWADI");
2802
2803 /**
2804 * Constant for the "Grantha" Unicode character block.
2805 * @since 9
2806 */
2807 public static final UnicodeBlock GRANTHA =
2808 new UnicodeBlock("GRANTHA");
2809
2810 /**
2811 * Constant for the "Tirhuta" Unicode character block.
2812 * @since 9
2813 */
2814 public static final UnicodeBlock TIRHUTA =
2815 new UnicodeBlock("TIRHUTA");
2816
2817 /**
2818 * Constant for the "Siddham" Unicode character block.
2819 * @since 9
2820 */
2821 public static final UnicodeBlock SIDDHAM =
2822 new UnicodeBlock("SIDDHAM");
2823
2824 /**
2825 * Constant for the "Modi" Unicode character block.
2826 * @since 9
2827 */
2828 public static final UnicodeBlock MODI =
2829 new UnicodeBlock("MODI");
2830
2831 /**
2832 * Constant for the "Warang Citi" Unicode character block.
2833 * @since 9
2834 */
2835 public static final UnicodeBlock WARANG_CITI =
2836 new UnicodeBlock("WARANG_CITI",
2837 "WARANG CITI",
2838 "WARANGCITI");
2839
2840 /**
2841 * Constant for the "Pau Cin Hau" Unicode character block.
2842 * @since 9
2843 */
2844 public static final UnicodeBlock PAU_CIN_HAU =
2845 new UnicodeBlock("PAU_CIN_HAU",
2846 "PAU CIN HAU",
2847 "PAUCINHAU");
2848
2849 /**
2850 * Constant for the "Mro" Unicode character block.
2851 * @since 9
2852 */
2853 public static final UnicodeBlock MRO =
2854 new UnicodeBlock("MRO");
2855
2856 /**
2857 * Constant for the "Bassa Vah" Unicode character block.
2858 * @since 9
2859 */
2860 public static final UnicodeBlock BASSA_VAH =
2861 new UnicodeBlock("BASSA_VAH",
2862 "BASSA VAH",
2863 "BASSAVAH");
2864
2865 /**
2866 * Constant for the "Pahawh Hmong" Unicode character block.
2867 * @since 9
2868 */
2869 public static final UnicodeBlock PAHAWH_HMONG =
2870 new UnicodeBlock("PAHAWH_HMONG",
2871 "PAHAWH HMONG",
2872 "PAHAWHHMONG");
2873
2874 /**
2875 * Constant for the "Duployan" Unicode character block.
2876 * @since 9
2877 */
2878 public static final UnicodeBlock DUPLOYAN =
2879 new UnicodeBlock("DUPLOYAN");
2880
2881 /**
2882 * Constant for the "Shorthand Format Controls" Unicode character block.
2883 * @since 9
2884 */
2885 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2886 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2887 "SHORTHAND FORMAT CONTROLS",
2888 "SHORTHANDFORMATCONTROLS");
2889
2890 /**
2891 * Constant for the "Mende Kikakui" Unicode character block.
2892 * @since 9
2893 */
2894 public static final UnicodeBlock MENDE_KIKAKUI =
2895 new UnicodeBlock("MENDE_KIKAKUI",
2896 "MENDE KIKAKUI",
2897 "MENDEKIKAKUI");
2898
2899 /**
2900 * Constant for the "Ornamental Dingbats" Unicode character block.
2901 * @since 9
2902 */
2903 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2904 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2905 "ORNAMENTAL DINGBATS",
2906 "ORNAMENTALDINGBATS");
2907
2908 /**
2909 * Constant for the "Geometric Shapes Extended" Unicode character block.
2910 * @since 9
2911 */
2912 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2913 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2914 "GEOMETRIC SHAPES EXTENDED",
2915 "GEOMETRICSHAPESEXTENDED");
2916
2917 /**
2918 * Constant for the "Supplemental Arrows-C" Unicode character block.
2919 * @since 9
2920 */
2921 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2922 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2923 "SUPPLEMENTAL ARROWS-C",
2924 "SUPPLEMENTALARROWS-C");
2925
2926 /**
2927 * Constant for the "Cherokee Supplement" Unicode character block.
2928 * @since 9
2929 */
2930 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2931 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2932 "CHEROKEE SUPPLEMENT",
2933 "CHEROKEESUPPLEMENT");
2934
2935 /**
2936 * Constant for the "Hatran" Unicode character block.
2937 * @since 9
2938 */
2939 public static final UnicodeBlock HATRAN =
2940 new UnicodeBlock("HATRAN");
2941
2942 /**
2943 * Constant for the "Old Hungarian" Unicode character block.
2944 * @since 9
2945 */
2946 public static final UnicodeBlock OLD_HUNGARIAN =
2947 new UnicodeBlock("OLD_HUNGARIAN",
2948 "OLD HUNGARIAN",
2949 "OLDHUNGARIAN");
2950
2951 /**
2952 * Constant for the "Multani" Unicode character block.
2953 * @since 9
2954 */
2955 public static final UnicodeBlock MULTANI =
2956 new UnicodeBlock("MULTANI");
2957
2958 /**
2959 * Constant for the "Ahom" Unicode character block.
2960 * @since 9
2961 */
2962 public static final UnicodeBlock AHOM =
2963 new UnicodeBlock("AHOM");
2964
2965 /**
2966 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2967 * @since 9
2968 */
2969 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2970 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2971 "EARLY DYNASTIC CUNEIFORM",
2972 "EARLYDYNASTICCUNEIFORM");
2973
2974 /**
2975 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2976 * @since 9
2977 */
2978 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2979 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2980 "ANATOLIAN HIEROGLYPHS",
2981 "ANATOLIANHIEROGLYPHS");
2982
2983 /**
2984 * Constant for the "Sutton SignWriting" Unicode character block.
2985 * @since 9
2986 */
2987 public static final UnicodeBlock SUTTON_SIGNWRITING =
2988 new UnicodeBlock("SUTTON_SIGNWRITING",
2989 "SUTTON SIGNWRITING",
2990 "SUTTONSIGNWRITING");
2991
2992 /**
2993 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2994 * character block.
2995 * @since 9
2996 */
2997 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2998 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2999 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
3000 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3001
3002 /**
3003 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3004 * character block.
3005 * @since 9
3006 */
3007 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3008 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3009 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3010 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3011
3012 /**
3013 * Constant for the "Syriac Supplement" Unicode
3014 * character block.
3015 * @since 11
3016 */
3017 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3018 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3019 "SYRIAC SUPPLEMENT",
3020 "SYRIACSUPPLEMENT");
3021
3022 /**
3023 * Constant for the "Cyrillic Extended-C" Unicode
3024 * character block.
3025 * @since 11
3026 */
3027 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3028 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3029 "CYRILLIC EXTENDED-C",
3030 "CYRILLICEXTENDED-C");
3031
3032 /**
3033 * Constant for the "Osage" Unicode
3034 * character block.
3035 * @since 11
3036 */
3037 public static final UnicodeBlock OSAGE =
3038 new UnicodeBlock("OSAGE");
3039
3040 /**
3041 * Constant for the "Newa" Unicode
3042 * character block.
3043 * @since 11
3044 */
3045 public static final UnicodeBlock NEWA =
3046 new UnicodeBlock("NEWA");
3047
3048 /**
3049 * Constant for the "Mongolian Supplement" Unicode
3050 * character block.
3051 * @since 11
3052 */
3053 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3054 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3055 "MONGOLIAN SUPPLEMENT",
3056 "MONGOLIANSUPPLEMENT");
3057
3058 /**
3059 * Constant for the "Marchen" Unicode
3060 * character block.
3061 * @since 11
3062 */
3063 public static final UnicodeBlock MARCHEN =
3064 new UnicodeBlock("MARCHEN");
3065
3066 /**
3067 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3068 * character block.
3069 * @since 11
3070 */
3071 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3072 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3073 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3074 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3075
3076 /**
3077 * Constant for the "Tangut" Unicode
3078 * character block.
3079 * @since 11
3080 */
3081 public static final UnicodeBlock TANGUT =
3082 new UnicodeBlock("TANGUT");
3083
3084 /**
3085 * Constant for the "Tangut Components" Unicode
3086 * character block.
3087 * @since 11
3088 */
3089 public static final UnicodeBlock TANGUT_COMPONENTS =
3090 new UnicodeBlock("TANGUT_COMPONENTS",
3091 "TANGUT COMPONENTS",
3092 "TANGUTCOMPONENTS");
3093
3094 /**
3095 * Constant for the "Kana Extended-A" Unicode
3096 * character block.
3097 * @since 11
3098 */
3099 public static final UnicodeBlock KANA_EXTENDED_A =
3100 new UnicodeBlock("KANA_EXTENDED_A",
3101 "KANA EXTENDED-A",
3102 "KANAEXTENDED-A");
3103 /**
3104 * Constant for the "Glagolitic Supplement" Unicode
3105 * character block.
3106 * @since 11
3107 */
3108 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3109 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3110 "GLAGOLITIC SUPPLEMENT",
3111 "GLAGOLITICSUPPLEMENT");
3112 /**
3113 * Constant for the "Adlam" Unicode
3114 * character block.
3115 * @since 11
3116 */
3117 public static final UnicodeBlock ADLAM =
3118 new UnicodeBlock("ADLAM");
3119
3120 /**
3121 * Constant for the "Masaram Gondi" Unicode
3122 * character block.
3123 * @since 11
3124 */
3125 public static final UnicodeBlock MASARAM_GONDI =
3126 new UnicodeBlock("MASARAM_GONDI",
3127 "MASARAM GONDI",
3128 "MASARAMGONDI");
3129
3130 /**
3131 * Constant for the "Zanabazar Square" Unicode
3132 * character block.
3133 * @since 11
3134 */
3135 public static final UnicodeBlock ZANABAZAR_SQUARE =
3136 new UnicodeBlock("ZANABAZAR_SQUARE",
3137 "ZANABAZAR SQUARE",
3138 "ZANABAZARSQUARE");
3139
3140 /**
3141 * Constant for the "Nushu" Unicode
3142 * character block.
3143 * @since 11
3144 */
3145 public static final UnicodeBlock NUSHU =
3146 new UnicodeBlock("NUSHU");
3147
3148 /**
3149 * Constant for the "Soyombo" Unicode
3150 * character block.
3151 * @since 11
3152 */
3153 public static final UnicodeBlock SOYOMBO =
3154 new UnicodeBlock("SOYOMBO");
3155
3156 /**
3157 * Constant for the "Bhaiksuki" Unicode
3158 * character block.
3159 * @since 11
3160 */
3161 public static final UnicodeBlock BHAIKSUKI =
3162 new UnicodeBlock("BHAIKSUKI");
3163
3164 /**
3165 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3166 * character block.
3167 * @since 11
3168 */
3169 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3170 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3171 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3172 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3173 /**
3174 * Constant for the "Georgian Extended" Unicode
3175 * character block.
3176 * @since 12
3177 */
3178 public static final UnicodeBlock GEORGIAN_EXTENDED =
3179 new UnicodeBlock("GEORGIAN_EXTENDED",
3180 "GEORGIAN EXTENDED",
3181 "GEORGIANEXTENDED");
3182
3183 /**
3184 * Constant for the "Hanifi Rohingya" Unicode
3185 * character block.
3186 * @since 12
3187 */
3188 public static final UnicodeBlock HANIFI_ROHINGYA =
3189 new UnicodeBlock("HANIFI_ROHINGYA",
3190 "HANIFI ROHINGYA",
3191 "HANIFIROHINGYA");
3192
3193 /**
3194 * Constant for the "Old Sogdian" Unicode
3195 * character block.
3196 * @since 12
3197 */
3198 public static final UnicodeBlock OLD_SOGDIAN =
3199 new UnicodeBlock("OLD_SOGDIAN",
3200 "OLD SOGDIAN",
3201 "OLDSOGDIAN");
3202
3203 /**
3204 * Constant for the "Sogdian" Unicode
3205 * character block.
3206 * @since 12
3207 */
3208 public static final UnicodeBlock SOGDIAN =
3209 new UnicodeBlock("SOGDIAN");
3210
3211 /**
3212 * Constant for the "Dogra" Unicode
3213 * character block.
3214 * @since 12
3215 */
3216 public static final UnicodeBlock DOGRA =
3217 new UnicodeBlock("DOGRA");
3218
3219 /**
3220 * Constant for the "Gunjala Gondi" Unicode
3221 * character block.
3222 * @since 12
3223 */
3224 public static final UnicodeBlock GUNJALA_GONDI =
3225 new UnicodeBlock("GUNJALA_GONDI",
3226 "GUNJALA GONDI",
3227 "GUNJALAGONDI");
3228
3229 /**
3230 * Constant for the "Makasar" Unicode
3231 * character block.
3232 * @since 12
3233 */
3234 public static final UnicodeBlock MAKASAR =
3235 new UnicodeBlock("MAKASAR");
3236
3237 /**
3238 * Constant for the "Medefaidrin" Unicode
3239 * character block.
3240 * @since 12
3241 */
3242 public static final UnicodeBlock MEDEFAIDRIN =
3243 new UnicodeBlock("MEDEFAIDRIN");
3244
3245 /**
3246 * Constant for the "Mayan Numerals" Unicode
3247 * character block.
3248 * @since 12
3249 */
3250 public static final UnicodeBlock MAYAN_NUMERALS =
3251 new UnicodeBlock("MAYAN_NUMERALS",
3252 "MAYAN NUMERALS",
3253 "MAYANNUMERALS");
3254
3255 /**
3256 * Constant for the "Indic Siyaq Numbers" Unicode
3257 * character block.
3258 * @since 12
3259 */
3260 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3261 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3262 "INDIC SIYAQ NUMBERS",
3263 "INDICSIYAQNUMBERS");
3264
3265 /**
3266 * Constant for the "Chess Symbols" Unicode
3267 * character block.
3268 * @since 12
3269 */
3270 public static final UnicodeBlock CHESS_SYMBOLS =
3271 new UnicodeBlock("CHESS_SYMBOLS",
3272 "CHESS SYMBOLS",
3273 "CHESSSYMBOLS");
3274
3275 /**
3276 * Constant for the "Elymaic" Unicode
3277 * character block.
3278 * @since 13
3279 */
3280 public static final UnicodeBlock ELYMAIC =
3281 new UnicodeBlock("ELYMAIC");
3282
3283 /**
3284 * Constant for the "Nandinagari" Unicode
3285 * character block.
3286 * @since 13
3287 */
3288 public static final UnicodeBlock NANDINAGARI =
3289 new UnicodeBlock("NANDINAGARI");
3290
3291 /**
3292 * Constant for the "Tamil Supplement" Unicode
3293 * character block.
3294 * @since 13
3295 */
3296 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3297 new UnicodeBlock("TAMIL_SUPPLEMENT",
3298 "TAMIL SUPPLEMENT",
3299 "TAMILSUPPLEMENT");
3300
3301 /**
3302 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3303 * character block.
3304 * @since 13
3305 */
3306 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3307 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3308 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3309 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3310
3311 /**
3312 * Constant for the "Small Kana Extension" Unicode
3313 * character block.
3314 * @since 13
3315 */
3316 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3317 new UnicodeBlock("SMALL_KANA_EXTENSION",
3318 "SMALL KANA EXTENSION",
3319 "SMALLKANAEXTENSION");
3320
3321 /**
3322 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3323 * character block.
3324 * @since 13
3325 */
3326 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3327 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3328 "NYIAKENG PUACHUE HMONG",
3329 "NYIAKENGPUACHUEHMONG");
3330
3331 /**
3332 * Constant for the "Wancho" Unicode
3333 * character block.
3334 * @since 13
3335 */
3336 public static final UnicodeBlock WANCHO =
3337 new UnicodeBlock("WANCHO");
3338
3339 /**
3340 * Constant for the "Ottoman Siyaq Numbers" Unicode
3341 * character block.
3342 * @since 13
3343 */
3344 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3345 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3346 "OTTOMAN SIYAQ NUMBERS",
3347 "OTTOMANSIYAQNUMBERS");
3348
3349 /**
3350 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3351 * character block.
3352 * @since 13
3353 */
3354 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3355 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3356 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3357 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3358
3359 /**
3360 * Constant for the "Yezidi" Unicode
3361 * character block.
3362 * @since 15
3363 */
3364 public static final UnicodeBlock YEZIDI =
3365 new UnicodeBlock("YEZIDI");
3366
3367 /**
3368 * Constant for the "Chorasmian" Unicode
3369 * character block.
3370 * @since 15
3371 */
3372 public static final UnicodeBlock CHORASMIAN =
3373 new UnicodeBlock("CHORASMIAN");
3374
3375 /**
3376 * Constant for the "Dives Akuru" Unicode
3377 * character block.
3378 * @since 15
3379 */
3380 public static final UnicodeBlock DIVES_AKURU =
3381 new UnicodeBlock("DIVES_AKURU",
3382 "DIVES AKURU",
3383 "DIVESAKURU");
3384
3385 /**
3386 * Constant for the "Lisu Supplement" Unicode
3387 * character block.
3388 * @since 15
3389 */
3390 public static final UnicodeBlock LISU_SUPPLEMENT =
3391 new UnicodeBlock("LISU_SUPPLEMENT",
3392 "LISU SUPPLEMENT",
3393 "LISUSUPPLEMENT");
3394
3395 /**
3396 * Constant for the "Khitan Small Script" Unicode
3397 * character block.
3398 * @since 15
3399 */
3400 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3401 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3402 "KHITAN SMALL SCRIPT",
3403 "KHITANSMALLSCRIPT");
3404
3405 /**
3406 * Constant for the "Tangut Supplement" Unicode
3407 * character block.
3408 * @since 15
3409 */
3410 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3411 new UnicodeBlock("TANGUT_SUPPLEMENT",
3412 "TANGUT SUPPLEMENT",
3413 "TANGUTSUPPLEMENT");
3414
3415 /**
3416 * Constant for the "Symbols for Legacy Computing" Unicode
3417 * character block.
3418 * @since 15
3419 */
3420 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3421 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3422 "SYMBOLS FOR LEGACY COMPUTING",
3423 "SYMBOLSFORLEGACYCOMPUTING");
3424
3425 /**
3426 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3427 * character block.
3428 * @since 15
3429 */
3430 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3431 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3432 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3433 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3434
3435 /**
3436 * Constant for the "Arabic Extended-B" Unicode
3437 * character block.
3438 * @since 19
3439 */
3440 public static final UnicodeBlock ARABIC_EXTENDED_B =
3441 new UnicodeBlock("ARABIC_EXTENDED_B",
3442 "ARABIC EXTENDED-B",
3443 "ARABICEXTENDED-B");
3444
3445 /**
3446 * Constant for the "Vithkuqi" Unicode
3447 * character block.
3448 * @since 19
3449 */
3450 public static final UnicodeBlock VITHKUQI =
3451 new UnicodeBlock("VITHKUQI");
3452
3453 /**
3454 * Constant for the "Latin Extended-F" Unicode
3455 * character block.
3456 * @since 19
3457 */
3458 public static final UnicodeBlock LATIN_EXTENDED_F =
3459 new UnicodeBlock("LATIN_EXTENDED_F",
3460 "LATIN EXTENDED-F",
3461 "LATINEXTENDED-F");
3462
3463 /**
3464 * Constant for the "Old Uyghur" Unicode
3465 * character block.
3466 * @since 19
3467 */
3468 public static final UnicodeBlock OLD_UYGHUR =
3469 new UnicodeBlock("OLD_UYGHUR",
3470 "OLD UYGHUR",
3471 "OLDUYGHUR");
3472
3473 /**
3474 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3475 * character block.
3476 * @since 19
3477 */
3478 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3479 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3480 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3481 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3482
3483 /**
3484 * Constant for the "Cypro-Minoan" Unicode
3485 * character block.
3486 * @since 19
3487 */
3488 public static final UnicodeBlock CYPRO_MINOAN =
3489 new UnicodeBlock("CYPRO_MINOAN",
3490 "CYPRO-MINOAN",
3491 "CYPRO-MINOAN");
3492
3493 /**
3494 * Constant for the "Tangsa" Unicode
3495 * character block.
3496 * @since 19
3497 */
3498 public static final UnicodeBlock TANGSA =
3499 new UnicodeBlock("TANGSA");
3500
3501 /**
3502 * Constant for the "Kana Extended-B" Unicode
3503 * character block.
3504 * @since 19
3505 */
3506 public static final UnicodeBlock KANA_EXTENDED_B =
3507 new UnicodeBlock("KANA_EXTENDED_B",
3508 "KANA EXTENDED-B",
3509 "KANAEXTENDED-B");
3510
3511 /**
3512 * Constant for the "Znamenny Musical Notation" Unicode
3513 * character block.
3514 * @since 19
3515 */
3516 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3517 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3518 "ZNAMENNY MUSICAL NOTATION",
3519 "ZNAMENNYMUSICALNOTATION");
3520
3521 /**
3522 * Constant for the "Latin Extended-G" Unicode
3523 * character block.
3524 * @since 19
3525 */
3526 public static final UnicodeBlock LATIN_EXTENDED_G =
3527 new UnicodeBlock("LATIN_EXTENDED_G",
3528 "LATIN EXTENDED-G",
3529 "LATINEXTENDED-G");
3530
3531 /**
3532 * Constant for the "Toto" Unicode
3533 * character block.
3534 * @since 19
3535 */
3536 public static final UnicodeBlock TOTO =
3537 new UnicodeBlock("TOTO");
3538
3539 /**
3540 * Constant for the "Ethiopic Extended-B" Unicode
3541 * character block.
3542 * @since 19
3543 */
3544 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3545 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3546 "ETHIOPIC EXTENDED-B",
3547 "ETHIOPICEXTENDED-B");
3548
3549 /**
3550 * Constant for the "Arabic Extended-C" Unicode
3551 * character block.
3552 * @since 20
3553 */
3554 public static final UnicodeBlock ARABIC_EXTENDED_C =
3555 new UnicodeBlock("ARABIC_EXTENDED_C",
3556 "ARABIC EXTENDED-C",
3557 "ARABICEXTENDED-C");
3558
3559 /**
3560 * Constant for the "Devanagari Extended-A" Unicode
3561 * character block.
3562 * @since 20
3563 */
3564 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3565 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3566 "DEVANAGARI EXTENDED-A",
3567 "DEVANAGARIEXTENDED-A");
3568
3569 /**
3570 * Constant for the "Kawi" Unicode
3571 * character block.
3572 * @since 20
3573 */
3574 public static final UnicodeBlock KAWI =
3575 new UnicodeBlock("KAWI");
3576
3577 /**
3578 * Constant for the "Kaktovik Numerals" Unicode
3579 * character block.
3580 * @since 20
3581 */
3582 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3583 new UnicodeBlock("KAKTOVIK_NUMERALS",
3584 "KAKTOVIK NUMERALS",
3585 "KAKTOVIKNUMERALS");
3586
3587 /**
3588 * Constant for the "Cyrillic Extended-D" Unicode
3589 * character block.
3590 * @since 20
3591 */
3592 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3593 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3594 "CYRILLIC EXTENDED-D",
3595 "CYRILLICEXTENDED-D");
3596
3597 /**
3598 * Constant for the "Nag Mundari" Unicode
3599 * character block.
3600 * @since 20
3601 */
3602 public static final UnicodeBlock NAG_MUNDARI =
3603 new UnicodeBlock("NAG_MUNDARI",
3604 "NAG MUNDARI",
3605 "NAGMUNDARI");
3606
3607 /**
3608 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3609 * character block.
3610 * @since 20
3611 */
3612 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3613 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3614 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3615 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3616
3617 /**
3618 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3619 * character block.
3620 * @since 22
3621 */
3622 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3623 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3624 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3625 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3626
3627 private static final int[] blockStarts = {
3628 0x0000, // 0000..007F; Basic Latin
3629 0x0080, // 0080..00FF; Latin-1 Supplement
3630 0x0100, // 0100..017F; Latin Extended-A
3631 0x0180, // 0180..024F; Latin Extended-B
3632 0x0250, // 0250..02AF; IPA Extensions
3633 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3634 0x0300, // 0300..036F; Combining Diacritical Marks
3635 0x0370, // 0370..03FF; Greek and Coptic
3636 0x0400, // 0400..04FF; Cyrillic
3637 0x0500, // 0500..052F; Cyrillic Supplement
3638 0x0530, // 0530..058F; Armenian
3639 0x0590, // 0590..05FF; Hebrew
3640 0x0600, // 0600..06FF; Arabic
3641 0x0700, // 0700..074F; Syriac
3642 0x0750, // 0750..077F; Arabic Supplement
3643 0x0780, // 0780..07BF; Thaana
3644 0x07C0, // 07C0..07FF; NKo
3645 0x0800, // 0800..083F; Samaritan
3646 0x0840, // 0840..085F; Mandaic
3647 0x0860, // 0860..086F; Syriac Supplement
3648 0x0870, // 0870..089F; Arabic Extended-B
3649 0x08A0, // 08A0..08FF; Arabic Extended-A
3650 0x0900, // 0900..097F; Devanagari
3651 0x0980, // 0980..09FF; Bengali
3652 0x0A00, // 0A00..0A7F; Gurmukhi
3653 0x0A80, // 0A80..0AFF; Gujarati
3654 0x0B00, // 0B00..0B7F; Oriya
3655 0x0B80, // 0B80..0BFF; Tamil
3656 0x0C00, // 0C00..0C7F; Telugu
3657 0x0C80, // 0C80..0CFF; Kannada
3658 0x0D00, // 0D00..0D7F; Malayalam
3659 0x0D80, // 0D80..0DFF; Sinhala
3660 0x0E00, // 0E00..0E7F; Thai
3661 0x0E80, // 0E80..0EFF; Lao
3662 0x0F00, // 0F00..0FFF; Tibetan
3663 0x1000, // 1000..109F; Myanmar
3664 0x10A0, // 10A0..10FF; Georgian
3665 0x1100, // 1100..11FF; Hangul Jamo
3666 0x1200, // 1200..137F; Ethiopic
3667 0x1380, // 1380..139F; Ethiopic Supplement
3668 0x13A0, // 13A0..13FF; Cherokee
3669 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3670 0x1680, // 1680..169F; Ogham
3671 0x16A0, // 16A0..16FF; Runic
3672 0x1700, // 1700..171F; Tagalog
3673 0x1720, // 1720..173F; Hanunoo
3674 0x1740, // 1740..175F; Buhid
3675 0x1760, // 1760..177F; Tagbanwa
3676 0x1780, // 1780..17FF; Khmer
3677 0x1800, // 1800..18AF; Mongolian
3678 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3679 0x1900, // 1900..194F; Limbu
3680 0x1950, // 1950..197F; Tai Le
3681 0x1980, // 1980..19DF; New Tai Lue
3682 0x19E0, // 19E0..19FF; Khmer Symbols
3683 0x1A00, // 1A00..1A1F; Buginese
3684 0x1A20, // 1A20..1AAF; Tai Tham
3685 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3686 0x1B00, // 1B00..1B7F; Balinese
3687 0x1B80, // 1B80..1BBF; Sundanese
3688 0x1BC0, // 1BC0..1BFF; Batak
3689 0x1C00, // 1C00..1C4F; Lepcha
3690 0x1C50, // 1C50..1C7F; Ol Chiki
3691 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3692 0x1C90, // 1C90..1CBF; Georgian Extended
3693 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3694 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3695 0x1D00, // 1D00..1D7F; Phonetic Extensions
3696 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3697 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3698 0x1E00, // 1E00..1EFF; Latin Extended Additional
3699 0x1F00, // 1F00..1FFF; Greek Extended
3700 0x2000, // 2000..206F; General Punctuation
3701 0x2070, // 2070..209F; Superscripts and Subscripts
3702 0x20A0, // 20A0..20CF; Currency Symbols
3703 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3704 0x2100, // 2100..214F; Letterlike Symbols
3705 0x2150, // 2150..218F; Number Forms
3706 0x2190, // 2190..21FF; Arrows
3707 0x2200, // 2200..22FF; Mathematical Operators
3708 0x2300, // 2300..23FF; Miscellaneous Technical
3709 0x2400, // 2400..243F; Control Pictures
3710 0x2440, // 2440..245F; Optical Character Recognition
3711 0x2460, // 2460..24FF; Enclosed Alphanumerics
3712 0x2500, // 2500..257F; Box Drawing
3713 0x2580, // 2580..259F; Block Elements
3714 0x25A0, // 25A0..25FF; Geometric Shapes
3715 0x2600, // 2600..26FF; Miscellaneous Symbols
3716 0x2700, // 2700..27BF; Dingbats
3717 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3718 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3719 0x2800, // 2800..28FF; Braille Patterns
3720 0x2900, // 2900..297F; Supplemental Arrows-B
3721 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3722 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3723 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3724 0x2C00, // 2C00..2C5F; Glagolitic
3725 0x2C60, // 2C60..2C7F; Latin Extended-C
3726 0x2C80, // 2C80..2CFF; Coptic
3727 0x2D00, // 2D00..2D2F; Georgian Supplement
3728 0x2D30, // 2D30..2D7F; Tifinagh
3729 0x2D80, // 2D80..2DDF; Ethiopic Extended
3730 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3731 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3732 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3733 0x2F00, // 2F00..2FDF; Kangxi Radicals
3734 0x2FE0, // unassigned
3735 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3736 0x3000, // 3000..303F; CJK Symbols and Punctuation
3737 0x3040, // 3040..309F; Hiragana
3738 0x30A0, // 30A0..30FF; Katakana
3739 0x3100, // 3100..312F; Bopomofo
3740 0x3130, // 3130..318F; Hangul Compatibility Jamo
3741 0x3190, // 3190..319F; Kanbun
3742 0x31A0, // 31A0..31BF; Bopomofo Extended
3743 0x31C0, // 31C0..31EF; CJK Strokes
3744 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3745 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3746 0x3300, // 3300..33FF; CJK Compatibility
3747 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3748 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3749 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3750 0xA000, // A000..A48F; Yi Syllables
3751 0xA490, // A490..A4CF; Yi Radicals
3752 0xA4D0, // A4D0..A4FF; Lisu
3753 0xA500, // A500..A63F; Vai
3754 0xA640, // A640..A69F; Cyrillic Extended-B
3755 0xA6A0, // A6A0..A6FF; Bamum
3756 0xA700, // A700..A71F; Modifier Tone Letters
3757 0xA720, // A720..A7FF; Latin Extended-D
3758 0xA800, // A800..A82F; Syloti Nagri
3759 0xA830, // A830..A83F; Common Indic Number Forms
3760 0xA840, // A840..A87F; Phags-pa
3761 0xA880, // A880..A8DF; Saurashtra
3762 0xA8E0, // A8E0..A8FF; Devanagari Extended
3763 0xA900, // A900..A92F; Kayah Li
3764 0xA930, // A930..A95F; Rejang
3765 0xA960, // A960..A97F; Hangul Jamo Extended-A
3766 0xA980, // A980..A9DF; Javanese
3767 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3768 0xAA00, // AA00..AA5F; Cham
3769 0xAA60, // AA60..AA7F; Myanmar Extended-A
3770 0xAA80, // AA80..AADF; Tai Viet
3771 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3772 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3773 0xAB30, // AB30..AB6F; Latin Extended-E
3774 0xAB70, // AB70..ABBF; Cherokee Supplement
3775 0xABC0, // ABC0..ABFF; Meetei Mayek
3776 0xAC00, // AC00..D7AF; Hangul Syllables
3777 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3778 0xD800, // D800..DB7F; High Surrogates
3779 0xDB80, // DB80..DBFF; High Private Use Surrogates
3780 0xDC00, // DC00..DFFF; Low Surrogates
3781 0xE000, // E000..F8FF; Private Use Area
3782 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3783 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3784 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3785 0xFE00, // FE00..FE0F; Variation Selectors
3786 0xFE10, // FE10..FE1F; Vertical Forms
3787 0xFE20, // FE20..FE2F; Combining Half Marks
3788 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3789 0xFE50, // FE50..FE6F; Small Form Variants
3790 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3791 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3792 0xFFF0, // FFF0..FFFF; Specials
3793 0x10000, // 10000..1007F; Linear B Syllabary
3794 0x10080, // 10080..100FF; Linear B Ideograms
3795 0x10100, // 10100..1013F; Aegean Numbers
3796 0x10140, // 10140..1018F; Ancient Greek Numbers
3797 0x10190, // 10190..101CF; Ancient Symbols
3798 0x101D0, // 101D0..101FF; Phaistos Disc
3799 0x10200, // unassigned
3800 0x10280, // 10280..1029F; Lycian
3801 0x102A0, // 102A0..102DF; Carian
3802 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3803 0x10300, // 10300..1032F; Old Italic
3804 0x10330, // 10330..1034F; Gothic
3805 0x10350, // 10350..1037F; Old Permic
3806 0x10380, // 10380..1039F; Ugaritic
3807 0x103A0, // 103A0..103DF; Old Persian
3808 0x103E0, // unassigned
3809 0x10400, // 10400..1044F; Deseret
3810 0x10450, // 10450..1047F; Shavian
3811 0x10480, // 10480..104AF; Osmanya
3812 0x104B0, // 104B0..104FF; Osage
3813 0x10500, // 10500..1052F; Elbasan
3814 0x10530, // 10530..1056F; Caucasian Albanian
3815 0x10570, // 10570..105BF; Vithkuqi
3816 0x105C0, // unassigned
3817 0x10600, // 10600..1077F; Linear A
3818 0x10780, // 10780..107BF; Latin Extended-F
3819 0x107C0, // unassigned
3820 0x10800, // 10800..1083F; Cypriot Syllabary
3821 0x10840, // 10840..1085F; Imperial Aramaic
3822 0x10860, // 10860..1087F; Palmyrene
3823 0x10880, // 10880..108AF; Nabataean
3824 0x108B0, // unassigned
3825 0x108E0, // 108E0..108FF; Hatran
3826 0x10900, // 10900..1091F; Phoenician
3827 0x10920, // 10920..1093F; Lydian
3828 0x10940, // unassigned
3829 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3830 0x109A0, // 109A0..109FF; Meroitic Cursive
3831 0x10A00, // 10A00..10A5F; Kharoshthi
3832 0x10A60, // 10A60..10A7F; Old South Arabian
3833 0x10A80, // 10A80..10A9F; Old North Arabian
3834 0x10AA0, // unassigned
3835 0x10AC0, // 10AC0..10AFF; Manichaean
3836 0x10B00, // 10B00..10B3F; Avestan
3837 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3838 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3839 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3840 0x10BB0, // unassigned
3841 0x10C00, // 10C00..10C4F; Old Turkic
3842 0x10C50, // unassigned
3843 0x10C80, // 10C80..10CFF; Old Hungarian
3844 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3845 0x10D40, // unassigned
3846 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3847 0x10E80, // 10E80..10EBF; Yezidi
3848 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
3849 0x10F00, // 10F00..10F2F; Old Sogdian
3850 0x10F30, // 10F30..10F6F; Sogdian
3851 0x10F70, // 10F70..10FAF; Old Uyghur
3852 0x10FB0, // 10FB0..10FDF; Chorasmian
3853 0x10FE0, // 10FE0..10FFF; Elymaic
3854 0x11000, // 11000..1107F; Brahmi
3855 0x11080, // 11080..110CF; Kaithi
3856 0x110D0, // 110D0..110FF; Sora Sompeng
3857 0x11100, // 11100..1114F; Chakma
3858 0x11150, // 11150..1117F; Mahajani
3859 0x11180, // 11180..111DF; Sharada
3860 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3861 0x11200, // 11200..1124F; Khojki
3862 0x11250, // unassigned
3863 0x11280, // 11280..112AF; Multani
3864 0x112B0, // 112B0..112FF; Khudawadi
3865 0x11300, // 11300..1137F; Grantha
3866 0x11380, // unassigned
3867 0x11400, // 11400..1147F; Newa
3868 0x11480, // 11480..114DF; Tirhuta
3869 0x114E0, // unassigned
3870 0x11580, // 11580..115FF; Siddham
3871 0x11600, // 11600..1165F; Modi
3872 0x11660, // 11660..1167F; Mongolian Supplement
3873 0x11680, // 11680..116CF; Takri
3874 0x116D0, // unassigned
3875 0x11700, // 11700..1174F; Ahom
3876 0x11750, // unassigned
3877 0x11800, // 11800..1184F; Dogra
3878 0x11850, // unassigned
3879 0x118A0, // 118A0..118FF; Warang Citi
3880 0x11900, // 11900..1195F; Dives Akuru
3881 0x11960, // unassigned
3882 0x119A0, // 119A0..119FF; Nandinagari
3883 0x11A00, // 11A00..11A4F; Zanabazar Square
3884 0x11A50, // 11A50..11AAF; Soyombo
3885 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
3886 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3887 0x11B00, // 11B00..11B5F; Devanagari Extended-A
3888 0x11B60, // unassigned
3889 0x11C00, // 11C00..11C6F; Bhaiksuki
3890 0x11C70, // 11C70..11CBF; Marchen
3891 0x11CC0, // unassigned
3892 0x11D00, // 11D00..11D5F; Masaram Gondi
3893 0x11D60, // 11D60..11DAF; Gunjala Gondi
3894 0x11DB0, // unassigned
3895 0x11EE0, // 11EE0..11EFF; Makasar
3896 0x11F00, // 11F00..11F5F; Kawi
3897 0x11F60, // unassigned
3898 0x11FB0, // 11FB0..11FBF; Lisu Supplement
3899 0x11FC0, // 11FC0..11FFF; Tamil Supplement
3900 0x12000, // 12000..123FF; Cuneiform
3901 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3902 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3903 0x12550, // unassigned
3904 0x12F90, // 12F90..12FFF; Cypro-Minoan
3905 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3906 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
3907 0x13460, // unassigned
3908 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3909 0x14680, // unassigned
3910 0x16800, // 16800..16A3F; Bamum Supplement
3911 0x16A40, // 16A40..16A6F; Mro
3912 0x16A70, // 16A70..16ACF; Tangsa
3913 0x16AD0, // 16AD0..16AFF; Bassa Vah
3914 0x16B00, // 16B00..16B8F; Pahawh Hmong
3915 0x16B90, // unassigned
3916 0x16E40, // 16E40..16E9F; Medefaidrin
3917 0x16EA0, // unassigned
3918 0x16F00, // 16F00..16F9F; Miao
3919 0x16FA0, // unassigned
3920 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
3921 0x17000, // 17000..187FF; Tangut
3922 0x18800, // 18800..18AFF; Tangut Components
3923 0x18B00, // 18B00..18CFF; Khitan Small Script
3924 0x18D00, // 18D00..18D7F; Tangut Supplement
3925 0x18D80, // unassigned
3926 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
3927 0x1B000, // 1B000..1B0FF; Kana Supplement
3928 0x1B100, // 1B100..1B12F; Kana Extended-A
3929 0x1B130, // 1B130..1B16F; Small Kana Extension
3930 0x1B170, // 1B170..1B2FF; Nushu
3931 0x1B300, // unassigned
3932 0x1BC00, // 1BC00..1BC9F; Duployan
3933 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3934 0x1BCB0, // unassigned
3935 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
3936 0x1CFD0, // unassigned
3937 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3938 0x1D100, // 1D100..1D1FF; Musical Symbols
3939 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3940 0x1D250, // unassigned
3941 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
3942 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
3943 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3944 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3945 0x1D380, // unassigned
3946 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3947 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3948 0x1DAB0, // unassigned
3949 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
3950 0x1E000, // 1E000..1E02F; Glagolitic Supplement
3951 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
3952 0x1E090, // unassigned
3953 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
3954 0x1E150, // unassigned
3955 0x1E290, // 1E290..1E2BF; Toto
3956 0x1E2C0, // 1E2C0..1E2FF; Wancho
3957 0x1E300, // unassigned
3958 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
3959 0x1E500, // unassigned
3960 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
3961 0x1E800, // 1E800..1E8DF; Mende Kikakui
3962 0x1E8E0, // unassigned
3963 0x1E900, // 1E900..1E95F; Adlam
3964 0x1E960, // unassigned
3965 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
3966 0x1ECC0, // unassigned
3967 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
3968 0x1ED50, // unassigned
3969 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3970 0x1EF00, // unassigned
3971 0x1F000, // 1F000..1F02F; Mahjong Tiles
3972 0x1F030, // 1F030..1F09F; Domino Tiles
3973 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3974 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3975 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3976 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3977 0x1F600, // 1F600..1F64F; Emoticons
3978 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3979 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3980 0x1F700, // 1F700..1F77F; Alchemical Symbols
3981 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3982 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3983 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3984 0x1FA00, // 1FA00..1FA6F; Chess Symbols
3985 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
3986 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
3987 0x1FC00, // unassigned
3988 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3989 0x2A6E0, // unassigned
3990 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3991 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3992 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
3993 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
3994 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
3995 0x2EE60, // unassigned
3996 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
3997 0x2FA20, // unassigned
3998 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
3999 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4000 0x323B0, // unassigned
4001 0xE0000, // E0000..E007F; Tags
4002 0xE0080, // unassigned
4003 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4004 0xE01F0, // unassigned
4005 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4006 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4007 };
4008
4009 private static final UnicodeBlock[] blocks = {
4010 BASIC_LATIN,
4011 LATIN_1_SUPPLEMENT,
4012 LATIN_EXTENDED_A,
4013 LATIN_EXTENDED_B,
4014 IPA_EXTENSIONS,
4015 SPACING_MODIFIER_LETTERS,
4016 COMBINING_DIACRITICAL_MARKS,
4017 GREEK,
4018 CYRILLIC,
4019 CYRILLIC_SUPPLEMENTARY,
4020 ARMENIAN,
4021 HEBREW,
4022 ARABIC,
4023 SYRIAC,
4024 ARABIC_SUPPLEMENT,
4025 THAANA,
4026 NKO,
4027 SAMARITAN,
4028 MANDAIC,
4029 SYRIAC_SUPPLEMENT,
4030 ARABIC_EXTENDED_B,
4031 ARABIC_EXTENDED_A,
4032 DEVANAGARI,
4033 BENGALI,
4034 GURMUKHI,
4035 GUJARATI,
4036 ORIYA,
4037 TAMIL,
4038 TELUGU,
4039 KANNADA,
4040 MALAYALAM,
4041 SINHALA,
4042 THAI,
4043 LAO,
4044 TIBETAN,
4045 MYANMAR,
4046 GEORGIAN,
4047 HANGUL_JAMO,
4048 ETHIOPIC,
4049 ETHIOPIC_SUPPLEMENT,
4050 CHEROKEE,
4051 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4052 OGHAM,
4053 RUNIC,
4054 TAGALOG,
4055 HANUNOO,
4056 BUHID,
4057 TAGBANWA,
4058 KHMER,
4059 MONGOLIAN,
4060 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4061 LIMBU,
4062 TAI_LE,
4063 NEW_TAI_LUE,
4064 KHMER_SYMBOLS,
4065 BUGINESE,
4066 TAI_THAM,
4067 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4068 BALINESE,
4069 SUNDANESE,
4070 BATAK,
4071 LEPCHA,
4072 OL_CHIKI,
4073 CYRILLIC_EXTENDED_C,
4074 GEORGIAN_EXTENDED,
4075 SUNDANESE_SUPPLEMENT,
4076 VEDIC_EXTENSIONS,
4077 PHONETIC_EXTENSIONS,
4078 PHONETIC_EXTENSIONS_SUPPLEMENT,
4079 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4080 LATIN_EXTENDED_ADDITIONAL,
4081 GREEK_EXTENDED,
4082 GENERAL_PUNCTUATION,
4083 SUPERSCRIPTS_AND_SUBSCRIPTS,
4084 CURRENCY_SYMBOLS,
4085 COMBINING_MARKS_FOR_SYMBOLS,
4086 LETTERLIKE_SYMBOLS,
4087 NUMBER_FORMS,
4088 ARROWS,
4089 MATHEMATICAL_OPERATORS,
4090 MISCELLANEOUS_TECHNICAL,
4091 CONTROL_PICTURES,
4092 OPTICAL_CHARACTER_RECOGNITION,
4093 ENCLOSED_ALPHANUMERICS,
4094 BOX_DRAWING,
4095 BLOCK_ELEMENTS,
4096 GEOMETRIC_SHAPES,
4097 MISCELLANEOUS_SYMBOLS,
4098 DINGBATS,
4099 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4100 SUPPLEMENTAL_ARROWS_A,
4101 BRAILLE_PATTERNS,
4102 SUPPLEMENTAL_ARROWS_B,
4103 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4104 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4105 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4106 GLAGOLITIC,
4107 LATIN_EXTENDED_C,
4108 COPTIC,
4109 GEORGIAN_SUPPLEMENT,
4110 TIFINAGH,
4111 ETHIOPIC_EXTENDED,
4112 CYRILLIC_EXTENDED_A,
4113 SUPPLEMENTAL_PUNCTUATION,
4114 CJK_RADICALS_SUPPLEMENT,
4115 KANGXI_RADICALS,
4116 null,
4117 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4118 CJK_SYMBOLS_AND_PUNCTUATION,
4119 HIRAGANA,
4120 KATAKANA,
4121 BOPOMOFO,
4122 HANGUL_COMPATIBILITY_JAMO,
4123 KANBUN,
4124 BOPOMOFO_EXTENDED,
4125 CJK_STROKES,
4126 KATAKANA_PHONETIC_EXTENSIONS,
4127 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4128 CJK_COMPATIBILITY,
4129 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4130 YIJING_HEXAGRAM_SYMBOLS,
4131 CJK_UNIFIED_IDEOGRAPHS,
4132 YI_SYLLABLES,
4133 YI_RADICALS,
4134 LISU,
4135 VAI,
4136 CYRILLIC_EXTENDED_B,
4137 BAMUM,
4138 MODIFIER_TONE_LETTERS,
4139 LATIN_EXTENDED_D,
4140 SYLOTI_NAGRI,
4141 COMMON_INDIC_NUMBER_FORMS,
4142 PHAGS_PA,
4143 SAURASHTRA,
4144 DEVANAGARI_EXTENDED,
4145 KAYAH_LI,
4146 REJANG,
4147 HANGUL_JAMO_EXTENDED_A,
4148 JAVANESE,
4149 MYANMAR_EXTENDED_B,
4150 CHAM,
4151 MYANMAR_EXTENDED_A,
4152 TAI_VIET,
4153 MEETEI_MAYEK_EXTENSIONS,
4154 ETHIOPIC_EXTENDED_A,
4155 LATIN_EXTENDED_E,
4156 CHEROKEE_SUPPLEMENT,
4157 MEETEI_MAYEK,
4158 HANGUL_SYLLABLES,
4159 HANGUL_JAMO_EXTENDED_B,
4160 HIGH_SURROGATES,
4161 HIGH_PRIVATE_USE_SURROGATES,
4162 LOW_SURROGATES,
4163 PRIVATE_USE_AREA,
4164 CJK_COMPATIBILITY_IDEOGRAPHS,
4165 ALPHABETIC_PRESENTATION_FORMS,
4166 ARABIC_PRESENTATION_FORMS_A,
4167 VARIATION_SELECTORS,
4168 VERTICAL_FORMS,
4169 COMBINING_HALF_MARKS,
4170 CJK_COMPATIBILITY_FORMS,
4171 SMALL_FORM_VARIANTS,
4172 ARABIC_PRESENTATION_FORMS_B,
4173 HALFWIDTH_AND_FULLWIDTH_FORMS,
4174 SPECIALS,
4175 LINEAR_B_SYLLABARY,
4176 LINEAR_B_IDEOGRAMS,
4177 AEGEAN_NUMBERS,
4178 ANCIENT_GREEK_NUMBERS,
4179 ANCIENT_SYMBOLS,
4180 PHAISTOS_DISC,
4181 null,
4182 LYCIAN,
4183 CARIAN,
4184 COPTIC_EPACT_NUMBERS,
4185 OLD_ITALIC,
4186 GOTHIC,
4187 OLD_PERMIC,
4188 UGARITIC,
4189 OLD_PERSIAN,
4190 null,
4191 DESERET,
4192 SHAVIAN,
4193 OSMANYA,
4194 OSAGE,
4195 ELBASAN,
4196 CAUCASIAN_ALBANIAN,
4197 VITHKUQI,
4198 null,
4199 LINEAR_A,
4200 LATIN_EXTENDED_F,
4201 null,
4202 CYPRIOT_SYLLABARY,
4203 IMPERIAL_ARAMAIC,
4204 PALMYRENE,
4205 NABATAEAN,
4206 null,
4207 HATRAN,
4208 PHOENICIAN,
4209 LYDIAN,
4210 null,
4211 MEROITIC_HIEROGLYPHS,
4212 MEROITIC_CURSIVE,
4213 KHAROSHTHI,
4214 OLD_SOUTH_ARABIAN,
4215 OLD_NORTH_ARABIAN,
4216 null,
4217 MANICHAEAN,
4218 AVESTAN,
4219 INSCRIPTIONAL_PARTHIAN,
4220 INSCRIPTIONAL_PAHLAVI,
4221 PSALTER_PAHLAVI,
4222 null,
4223 OLD_TURKIC,
4224 null,
4225 OLD_HUNGARIAN,
4226 HANIFI_ROHINGYA,
4227 null,
4228 RUMI_NUMERAL_SYMBOLS,
4229 YEZIDI,
4230 ARABIC_EXTENDED_C,
4231 OLD_SOGDIAN,
4232 SOGDIAN,
4233 OLD_UYGHUR,
4234 CHORASMIAN,
4235 ELYMAIC,
4236 BRAHMI,
4237 KAITHI,
4238 SORA_SOMPENG,
4239 CHAKMA,
4240 MAHAJANI,
4241 SHARADA,
4242 SINHALA_ARCHAIC_NUMBERS,
4243 KHOJKI,
4244 null,
4245 MULTANI,
4246 KHUDAWADI,
4247 GRANTHA,
4248 null,
4249 NEWA,
4250 TIRHUTA,
4251 null,
4252 SIDDHAM,
4253 MODI,
4254 MONGOLIAN_SUPPLEMENT,
4255 TAKRI,
4256 null,
4257 AHOM,
4258 null,
4259 DOGRA,
4260 null,
4261 WARANG_CITI,
4262 DIVES_AKURU,
4263 null,
4264 NANDINAGARI,
4265 ZANABAZAR_SQUARE,
4266 SOYOMBO,
4267 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4268 PAU_CIN_HAU,
4269 DEVANAGARI_EXTENDED_A,
4270 null,
4271 BHAIKSUKI,
4272 MARCHEN,
4273 null,
4274 MASARAM_GONDI,
4275 GUNJALA_GONDI,
4276 null,
4277 MAKASAR,
4278 KAWI,
4279 null,
4280 LISU_SUPPLEMENT,
4281 TAMIL_SUPPLEMENT,
4282 CUNEIFORM,
4283 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4284 EARLY_DYNASTIC_CUNEIFORM,
4285 null,
4286 CYPRO_MINOAN,
4287 EGYPTIAN_HIEROGLYPHS,
4288 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4289 null,
4290 ANATOLIAN_HIEROGLYPHS,
4291 null,
4292 BAMUM_SUPPLEMENT,
4293 MRO,
4294 TANGSA,
4295 BASSA_VAH,
4296 PAHAWH_HMONG,
4297 null,
4298 MEDEFAIDRIN,
4299 null,
4300 MIAO,
4301 null,
4302 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4303 TANGUT,
4304 TANGUT_COMPONENTS,
4305 KHITAN_SMALL_SCRIPT,
4306 TANGUT_SUPPLEMENT,
4307 null,
4308 KANA_EXTENDED_B,
4309 KANA_SUPPLEMENT,
4310 KANA_EXTENDED_A,
4311 SMALL_KANA_EXTENSION,
4312 NUSHU,
4313 null,
4314 DUPLOYAN,
4315 SHORTHAND_FORMAT_CONTROLS,
4316 null,
4317 ZNAMENNY_MUSICAL_NOTATION,
4318 null,
4319 BYZANTINE_MUSICAL_SYMBOLS,
4320 MUSICAL_SYMBOLS,
4321 ANCIENT_GREEK_MUSICAL_NOTATION,
4322 null,
4323 KAKTOVIK_NUMERALS,
4324 MAYAN_NUMERALS,
4325 TAI_XUAN_JING_SYMBOLS,
4326 COUNTING_ROD_NUMERALS,
4327 null,
4328 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4329 SUTTON_SIGNWRITING,
4330 null,
4331 LATIN_EXTENDED_G,
4332 GLAGOLITIC_SUPPLEMENT,
4333 CYRILLIC_EXTENDED_D,
4334 null,
4335 NYIAKENG_PUACHUE_HMONG,
4336 null,
4337 TOTO,
4338 WANCHO,
4339 null,
4340 NAG_MUNDARI,
4341 null,
4342 ETHIOPIC_EXTENDED_B,
4343 MENDE_KIKAKUI,
4344 null,
4345 ADLAM,
4346 null,
4347 INDIC_SIYAQ_NUMBERS,
4348 null,
4349 OTTOMAN_SIYAQ_NUMBERS,
4350 null,
4351 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4352 null,
4353 MAHJONG_TILES,
4354 DOMINO_TILES,
4355 PLAYING_CARDS,
4356 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4357 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4358 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4359 EMOTICONS,
4360 ORNAMENTAL_DINGBATS,
4361 TRANSPORT_AND_MAP_SYMBOLS,
4362 ALCHEMICAL_SYMBOLS,
4363 GEOMETRIC_SHAPES_EXTENDED,
4364 SUPPLEMENTAL_ARROWS_C,
4365 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4366 CHESS_SYMBOLS,
4367 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4368 SYMBOLS_FOR_LEGACY_COMPUTING,
4369 null,
4370 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4371 null,
4372 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4373 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4374 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4375 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4376 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4377 null,
4378 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4379 null,
4380 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4381 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4382 null,
4383 TAGS,
4384 null,
4385 VARIATION_SELECTORS_SUPPLEMENT,
4386 null,
4387 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4388 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4389 };
4390
4391
4392 /**
4393 * Returns the object representing the Unicode block containing the
4394 * given character, or {@code null} if the character is not a
4395 * member of a defined block.
4396 *
4397 * <p><b>Note:</b> This method cannot handle
4398 * <a href="Character.html#supplementary"> supplementary
4399 * characters</a>. To support all Unicode characters, including
4400 * supplementary characters, use the {@link #of(int)} method.
4401 *
4402 * @param c The character in question
4403 * @return The {@code UnicodeBlock} instance representing the
4404 * Unicode block of which this character is a member, or
4405 * {@code null} if the character is not a member of any
4406 * Unicode block
4407 */
4408 public static UnicodeBlock of(char c) {
4409 return of((int)c);
4410 }
4411
4412 /**
4413 * Returns the object representing the Unicode block
4414 * containing the given character (Unicode code point), or
4415 * {@code null} if the character is not a member of a
4416 * defined block.
4417 *
4418 * @param codePoint the character (Unicode code point) in question.
4419 * @return The {@code UnicodeBlock} instance representing the
4420 * Unicode block of which this character is a member, or
4421 * {@code null} if the character is not a member of any
4422 * Unicode block
4423 * @throws IllegalArgumentException if the specified
4424 * {@code codePoint} is an invalid Unicode code point.
4425 * @see Character#isValidCodePoint(int)
4426 * @since 1.5
4427 */
4428 public static UnicodeBlock of(int codePoint) {
4429 if (!isValidCodePoint(codePoint)) {
4430 throw new IllegalArgumentException(
4431 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4432 }
4433
4434 int top, bottom, current;
4435 bottom = 0;
4436 top = blockStarts.length;
4437 current = top/2;
4438
4439 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4440 while (top - bottom > 1) {
4441 if (codePoint >= blockStarts[current]) {
4442 bottom = current;
4443 } else {
4444 top = current;
4445 }
4446 current = (top + bottom) / 2;
4447 }
4448 return blocks[current];
4449 }
4450
4451 /**
4452 * Returns the UnicodeBlock with the given name. Block
4453 * names are determined by The Unicode Standard. The file
4454 * {@code Blocks.txt} defines blocks for a particular
4455 * version of the standard. The {@link Character} class specifies
4456 * the version of the standard that it supports.
4457 * <p>
4458 * This method accepts block names in the following forms:
4459 * <ol>
4460 * <li> Canonical block names as defined by the Unicode Standard.
4461 * For example, the standard defines a "Basic Latin" block. Therefore, this
4462 * method accepts "Basic Latin" as a valid block name. The documentation of
4463 * each UnicodeBlock provides the canonical name.
4464 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4465 * is a valid block name for the "Basic Latin" block.
4466 * <li>The text representation of each constant UnicodeBlock identifier.
4467 * For example, this method will return the {@link #BASIC_LATIN} block if
4468 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4469 * hyphens in the canonical name with underscores.
4470 * </ol>
4471 * Finally, character case is ignored for all of the valid block name forms.
4472 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4473 * The en_US locale's case mapping rules are used to provide case-insensitive
4474 * string comparisons for block name validation.
4475 * <p>
4476 * If the Unicode Standard changes block names, both the previous and
4477 * current names will be accepted.
4478 *
4479 * @param blockName A {@code UnicodeBlock} name.
4480 * @return The {@code UnicodeBlock} instance identified
4481 * by {@code blockName}
4482 * @throws IllegalArgumentException if {@code blockName} is an
4483 * invalid name
4484 * @throws NullPointerException if {@code blockName} is null
4485 * @since 1.5
4486 */
4487 public static final UnicodeBlock forName(String blockName) {
4488 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4489 if (block == null) {
4490 throw new IllegalArgumentException("Not a valid block name: "
4491 + blockName);
4492 }
4493 return block;
4494 }
4495 }
4496
4497
4498 /**
4499 * A family of character subsets representing the character scripts
4500 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4501 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4502 * character is assigned to a single Unicode script, either a specific
4503 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4504 * one of the following three special values,
4505 * {@link Character.UnicodeScript#INHERITED Inherited},
4506 * {@link Character.UnicodeScript#COMMON Common} or
4507 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4508 *
4509 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4510 * @since 1.7
4511 */
4512 public static enum UnicodeScript {
4513 /**
4514 * Unicode script "Common".
4515 */
4516 COMMON,
4517
4518 /**
4519 * Unicode script "Latin".
4520 */
4521 LATIN,
4522
4523 /**
4524 * Unicode script "Greek".
4525 */
4526 GREEK,
4527
4528 /**
4529 * Unicode script "Cyrillic".
4530 */
4531 CYRILLIC,
4532
4533 /**
4534 * Unicode script "Armenian".
4535 */
4536 ARMENIAN,
4537
4538 /**
4539 * Unicode script "Hebrew".
4540 */
4541 HEBREW,
4542
4543 /**
4544 * Unicode script "Arabic".
4545 */
4546 ARABIC,
4547
4548 /**
4549 * Unicode script "Syriac".
4550 */
4551 SYRIAC,
4552
4553 /**
4554 * Unicode script "Thaana".
4555 */
4556 THAANA,
4557
4558 /**
4559 * Unicode script "Devanagari".
4560 */
4561 DEVANAGARI,
4562
4563 /**
4564 * Unicode script "Bengali".
4565 */
4566 BENGALI,
4567
4568 /**
4569 * Unicode script "Gurmukhi".
4570 */
4571 GURMUKHI,
4572
4573 /**
4574 * Unicode script "Gujarati".
4575 */
4576 GUJARATI,
4577
4578 /**
4579 * Unicode script "Oriya".
4580 */
4581 ORIYA,
4582
4583 /**
4584 * Unicode script "Tamil".
4585 */
4586 TAMIL,
4587
4588 /**
4589 * Unicode script "Telugu".
4590 */
4591 TELUGU,
4592
4593 /**
4594 * Unicode script "Kannada".
4595 */
4596 KANNADA,
4597
4598 /**
4599 * Unicode script "Malayalam".
4600 */
4601 MALAYALAM,
4602
4603 /**
4604 * Unicode script "Sinhala".
4605 */
4606 SINHALA,
4607
4608 /**
4609 * Unicode script "Thai".
4610 */
4611 THAI,
4612
4613 /**
4614 * Unicode script "Lao".
4615 */
4616 LAO,
4617
4618 /**
4619 * Unicode script "Tibetan".
4620 */
4621 TIBETAN,
4622
4623 /**
4624 * Unicode script "Myanmar".
4625 */
4626 MYANMAR,
4627
4628 /**
4629 * Unicode script "Georgian".
4630 */
4631 GEORGIAN,
4632
4633 /**
4634 * Unicode script "Hangul".
4635 */
4636 HANGUL,
4637
4638 /**
4639 * Unicode script "Ethiopic".
4640 */
4641 ETHIOPIC,
4642
4643 /**
4644 * Unicode script "Cherokee".
4645 */
4646 CHEROKEE,
4647
4648 /**
4649 * Unicode script "Canadian_Aboriginal".
4650 */
4651 CANADIAN_ABORIGINAL,
4652
4653 /**
4654 * Unicode script "Ogham".
4655 */
4656 OGHAM,
4657
4658 /**
4659 * Unicode script "Runic".
4660 */
4661 RUNIC,
4662
4663 /**
4664 * Unicode script "Khmer".
4665 */
4666 KHMER,
4667
4668 /**
4669 * Unicode script "Mongolian".
4670 */
4671 MONGOLIAN,
4672
4673 /**
4674 * Unicode script "Hiragana".
4675 */
4676 HIRAGANA,
4677
4678 /**
4679 * Unicode script "Katakana".
4680 */
4681 KATAKANA,
4682
4683 /**
4684 * Unicode script "Bopomofo".
4685 */
4686 BOPOMOFO,
4687
4688 /**
4689 * Unicode script "Han".
4690 */
4691 HAN,
4692
4693 /**
4694 * Unicode script "Yi".
4695 */
4696 YI,
4697
4698 /**
4699 * Unicode script "Old_Italic".
4700 */
4701 OLD_ITALIC,
4702
4703 /**
4704 * Unicode script "Gothic".
4705 */
4706 GOTHIC,
4707
4708 /**
4709 * Unicode script "Deseret".
4710 */
4711 DESERET,
4712
4713 /**
4714 * Unicode script "Inherited".
4715 */
4716 INHERITED,
4717
4718 /**
4719 * Unicode script "Tagalog".
4720 */
4721 TAGALOG,
4722
4723 /**
4724 * Unicode script "Hanunoo".
4725 */
4726 HANUNOO,
4727
4728 /**
4729 * Unicode script "Buhid".
4730 */
4731 BUHID,
4732
4733 /**
4734 * Unicode script "Tagbanwa".
4735 */
4736 TAGBANWA,
4737
4738 /**
4739 * Unicode script "Limbu".
4740 */
4741 LIMBU,
4742
4743 /**
4744 * Unicode script "Tai_Le".
4745 */
4746 TAI_LE,
4747
4748 /**
4749 * Unicode script "Linear_B".
4750 */
4751 LINEAR_B,
4752
4753 /**
4754 * Unicode script "Ugaritic".
4755 */
4756 UGARITIC,
4757
4758 /**
4759 * Unicode script "Shavian".
4760 */
4761 SHAVIAN,
4762
4763 /**
4764 * Unicode script "Osmanya".
4765 */
4766 OSMANYA,
4767
4768 /**
4769 * Unicode script "Cypriot".
4770 */
4771 CYPRIOT,
4772
4773 /**
4774 * Unicode script "Braille".
4775 */
4776 BRAILLE,
4777
4778 /**
4779 * Unicode script "Buginese".
4780 */
4781 BUGINESE,
4782
4783 /**
4784 * Unicode script "Coptic".
4785 */
4786 COPTIC,
4787
4788 /**
4789 * Unicode script "New_Tai_Lue".
4790 */
4791 NEW_TAI_LUE,
4792
4793 /**
4794 * Unicode script "Glagolitic".
4795 */
4796 GLAGOLITIC,
4797
4798 /**
4799 * Unicode script "Tifinagh".
4800 */
4801 TIFINAGH,
4802
4803 /**
4804 * Unicode script "Syloti_Nagri".
4805 */
4806 SYLOTI_NAGRI,
4807
4808 /**
4809 * Unicode script "Old_Persian".
4810 */
4811 OLD_PERSIAN,
4812
4813 /**
4814 * Unicode script "Kharoshthi".
4815 */
4816 KHAROSHTHI,
4817
4818 /**
4819 * Unicode script "Balinese".
4820 */
4821 BALINESE,
4822
4823 /**
4824 * Unicode script "Cuneiform".
4825 */
4826 CUNEIFORM,
4827
4828 /**
4829 * Unicode script "Phoenician".
4830 */
4831 PHOENICIAN,
4832
4833 /**
4834 * Unicode script "Phags_Pa".
4835 */
4836 PHAGS_PA,
4837
4838 /**
4839 * Unicode script "Nko".
4840 */
4841 NKO,
4842
4843 /**
4844 * Unicode script "Sundanese".
4845 */
4846 SUNDANESE,
4847
4848 /**
4849 * Unicode script "Batak".
4850 */
4851 BATAK,
4852
4853 /**
4854 * Unicode script "Lepcha".
4855 */
4856 LEPCHA,
4857
4858 /**
4859 * Unicode script "Ol_Chiki".
4860 */
4861 OL_CHIKI,
4862
4863 /**
4864 * Unicode script "Vai".
4865 */
4866 VAI,
4867
4868 /**
4869 * Unicode script "Saurashtra".
4870 */
4871 SAURASHTRA,
4872
4873 /**
4874 * Unicode script "Kayah_Li".
4875 */
4876 KAYAH_LI,
4877
4878 /**
4879 * Unicode script "Rejang".
4880 */
4881 REJANG,
4882
4883 /**
4884 * Unicode script "Lycian".
4885 */
4886 LYCIAN,
4887
4888 /**
4889 * Unicode script "Carian".
4890 */
4891 CARIAN,
4892
4893 /**
4894 * Unicode script "Lydian".
4895 */
4896 LYDIAN,
4897
4898 /**
4899 * Unicode script "Cham".
4900 */
4901 CHAM,
4902
4903 /**
4904 * Unicode script "Tai_Tham".
4905 */
4906 TAI_THAM,
4907
4908 /**
4909 * Unicode script "Tai_Viet".
4910 */
4911 TAI_VIET,
4912
4913 /**
4914 * Unicode script "Avestan".
4915 */
4916 AVESTAN,
4917
4918 /**
4919 * Unicode script "Egyptian_Hieroglyphs".
4920 */
4921 EGYPTIAN_HIEROGLYPHS,
4922
4923 /**
4924 * Unicode script "Samaritan".
4925 */
4926 SAMARITAN,
4927
4928 /**
4929 * Unicode script "Mandaic".
4930 */
4931 MANDAIC,
4932
4933 /**
4934 * Unicode script "Lisu".
4935 */
4936 LISU,
4937
4938 /**
4939 * Unicode script "Bamum".
4940 */
4941 BAMUM,
4942
4943 /**
4944 * Unicode script "Javanese".
4945 */
4946 JAVANESE,
4947
4948 /**
4949 * Unicode script "Meetei_Mayek".
4950 */
4951 MEETEI_MAYEK,
4952
4953 /**
4954 * Unicode script "Imperial_Aramaic".
4955 */
4956 IMPERIAL_ARAMAIC,
4957
4958 /**
4959 * Unicode script "Old_South_Arabian".
4960 */
4961 OLD_SOUTH_ARABIAN,
4962
4963 /**
4964 * Unicode script "Inscriptional_Parthian".
4965 */
4966 INSCRIPTIONAL_PARTHIAN,
4967
4968 /**
4969 * Unicode script "Inscriptional_Pahlavi".
4970 */
4971 INSCRIPTIONAL_PAHLAVI,
4972
4973 /**
4974 * Unicode script "Old_Turkic".
4975 */
4976 OLD_TURKIC,
4977
4978 /**
4979 * Unicode script "Brahmi".
4980 */
4981 BRAHMI,
4982
4983 /**
4984 * Unicode script "Kaithi".
4985 */
4986 KAITHI,
4987
4988 /**
4989 * Unicode script "Meroitic Hieroglyphs".
4990 * @since 1.8
4991 */
4992 MEROITIC_HIEROGLYPHS,
4993
4994 /**
4995 * Unicode script "Meroitic Cursive".
4996 * @since 1.8
4997 */
4998 MEROITIC_CURSIVE,
4999
5000 /**
5001 * Unicode script "Sora Sompeng".
5002 * @since 1.8
5003 */
5004 SORA_SOMPENG,
5005
5006 /**
5007 * Unicode script "Chakma".
5008 * @since 1.8
5009 */
5010 CHAKMA,
5011
5012 /**
5013 * Unicode script "Sharada".
5014 * @since 1.8
5015 */
5016 SHARADA,
5017
5018 /**
5019 * Unicode script "Takri".
5020 * @since 1.8
5021 */
5022 TAKRI,
5023
5024 /**
5025 * Unicode script "Miao".
5026 * @since 1.8
5027 */
5028 MIAO,
5029
5030 /**
5031 * Unicode script "Caucasian Albanian".
5032 * @since 9
5033 */
5034 CAUCASIAN_ALBANIAN,
5035
5036 /**
5037 * Unicode script "Bassa Vah".
5038 * @since 9
5039 */
5040 BASSA_VAH,
5041
5042 /**
5043 * Unicode script "Duployan".
5044 * @since 9
5045 */
5046 DUPLOYAN,
5047
5048 /**
5049 * Unicode script "Elbasan".
5050 * @since 9
5051 */
5052 ELBASAN,
5053
5054 /**
5055 * Unicode script "Grantha".
5056 * @since 9
5057 */
5058 GRANTHA,
5059
5060 /**
5061 * Unicode script "Pahawh Hmong".
5062 * @since 9
5063 */
5064 PAHAWH_HMONG,
5065
5066 /**
5067 * Unicode script "Khojki".
5068 * @since 9
5069 */
5070 KHOJKI,
5071
5072 /**
5073 * Unicode script "Linear A".
5074 * @since 9
5075 */
5076 LINEAR_A,
5077
5078 /**
5079 * Unicode script "Mahajani".
5080 * @since 9
5081 */
5082 MAHAJANI,
5083
5084 /**
5085 * Unicode script "Manichaean".
5086 * @since 9
5087 */
5088 MANICHAEAN,
5089
5090 /**
5091 * Unicode script "Mende Kikakui".
5092 * @since 9
5093 */
5094 MENDE_KIKAKUI,
5095
5096 /**
5097 * Unicode script "Modi".
5098 * @since 9
5099 */
5100 MODI,
5101
5102 /**
5103 * Unicode script "Mro".
5104 * @since 9
5105 */
5106 MRO,
5107
5108 /**
5109 * Unicode script "Old North Arabian".
5110 * @since 9
5111 */
5112 OLD_NORTH_ARABIAN,
5113
5114 /**
5115 * Unicode script "Nabataean".
5116 * @since 9
5117 */
5118 NABATAEAN,
5119
5120 /**
5121 * Unicode script "Palmyrene".
5122 * @since 9
5123 */
5124 PALMYRENE,
5125
5126 /**
5127 * Unicode script "Pau Cin Hau".
5128 * @since 9
5129 */
5130 PAU_CIN_HAU,
5131
5132 /**
5133 * Unicode script "Old Permic".
5134 * @since 9
5135 */
5136 OLD_PERMIC,
5137
5138 /**
5139 * Unicode script "Psalter Pahlavi".
5140 * @since 9
5141 */
5142 PSALTER_PAHLAVI,
5143
5144 /**
5145 * Unicode script "Siddham".
5146 * @since 9
5147 */
5148 SIDDHAM,
5149
5150 /**
5151 * Unicode script "Khudawadi".
5152 * @since 9
5153 */
5154 KHUDAWADI,
5155
5156 /**
5157 * Unicode script "Tirhuta".
5158 * @since 9
5159 */
5160 TIRHUTA,
5161
5162 /**
5163 * Unicode script "Warang Citi".
5164 * @since 9
5165 */
5166 WARANG_CITI,
5167
5168 /**
5169 * Unicode script "Ahom".
5170 * @since 9
5171 */
5172 AHOM,
5173
5174 /**
5175 * Unicode script "Anatolian Hieroglyphs".
5176 * @since 9
5177 */
5178 ANATOLIAN_HIEROGLYPHS,
5179
5180 /**
5181 * Unicode script "Hatran".
5182 * @since 9
5183 */
5184 HATRAN,
5185
5186 /**
5187 * Unicode script "Multani".
5188 * @since 9
5189 */
5190 MULTANI,
5191
5192 /**
5193 * Unicode script "Old Hungarian".
5194 * @since 9
5195 */
5196 OLD_HUNGARIAN,
5197
5198 /**
5199 * Unicode script "SignWriting".
5200 * @since 9
5201 */
5202 SIGNWRITING,
5203
5204 /**
5205 * Unicode script "Adlam".
5206 * @since 11
5207 */
5208 ADLAM,
5209
5210 /**
5211 * Unicode script "Bhaiksuki".
5212 * @since 11
5213 */
5214 BHAIKSUKI,
5215
5216 /**
5217 * Unicode script "Marchen".
5218 * @since 11
5219 */
5220 MARCHEN,
5221
5222 /**
5223 * Unicode script "Newa".
5224 * @since 11
5225 */
5226 NEWA,
5227
5228 /**
5229 * Unicode script "Osage".
5230 * @since 11
5231 */
5232 OSAGE,
5233
5234 /**
5235 * Unicode script "Tangut".
5236 * @since 11
5237 */
5238 TANGUT,
5239
5240 /**
5241 * Unicode script "Masaram Gondi".
5242 * @since 11
5243 */
5244 MASARAM_GONDI,
5245
5246 /**
5247 * Unicode script "Nushu".
5248 * @since 11
5249 */
5250 NUSHU,
5251
5252 /**
5253 * Unicode script "Soyombo".
5254 * @since 11
5255 */
5256 SOYOMBO,
5257
5258 /**
5259 * Unicode script "Zanabazar Square".
5260 * @since 11
5261 */
5262 ZANABAZAR_SQUARE,
5263
5264 /**
5265 * Unicode script "Hanifi Rohingya".
5266 * @since 12
5267 */
5268 HANIFI_ROHINGYA,
5269
5270 /**
5271 * Unicode script "Old Sogdian".
5272 * @since 12
5273 */
5274 OLD_SOGDIAN,
5275
5276 /**
5277 * Unicode script "Sogdian".
5278 * @since 12
5279 */
5280 SOGDIAN,
5281
5282 /**
5283 * Unicode script "Dogra".
5284 * @since 12
5285 */
5286 DOGRA,
5287
5288 /**
5289 * Unicode script "Gunjala Gondi".
5290 * @since 12
5291 */
5292 GUNJALA_GONDI,
5293
5294 /**
5295 * Unicode script "Makasar".
5296 * @since 12
5297 */
5298 MAKASAR,
5299
5300 /**
5301 * Unicode script "Medefaidrin".
5302 * @since 12
5303 */
5304 MEDEFAIDRIN,
5305
5306 /**
5307 * Unicode script "Elymaic".
5308 * @since 13
5309 */
5310 ELYMAIC,
5311
5312 /**
5313 * Unicode script "Nandinagari".
5314 * @since 13
5315 */
5316 NANDINAGARI,
5317
5318 /**
5319 * Unicode script "Nyiakeng Puachue Hmong".
5320 * @since 13
5321 */
5322 NYIAKENG_PUACHUE_HMONG,
5323
5324 /**
5325 * Unicode script "Wancho".
5326 * @since 13
5327 */
5328 WANCHO,
5329
5330 /**
5331 * Unicode script "Yezidi".
5332 * @since 15
5333 */
5334 YEZIDI,
5335
5336 /**
5337 * Unicode script "Chorasmian".
5338 * @since 15
5339 */
5340 CHORASMIAN,
5341
5342 /**
5343 * Unicode script "Dives Akuru".
5344 * @since 15
5345 */
5346 DIVES_AKURU,
5347
5348 /**
5349 * Unicode script "Khitan Small Script".
5350 * @since 15
5351 */
5352 KHITAN_SMALL_SCRIPT,
5353
5354 /**
5355 * Unicode script "Vithkuqi".
5356 * @since 19
5357 */
5358 VITHKUQI,
5359
5360 /**
5361 * Unicode script "Old Uyghur".
5362 * @since 19
5363 */
5364 OLD_UYGHUR,
5365
5366 /**
5367 * Unicode script "Cypro Minoan".
5368 * @since 19
5369 */
5370 CYPRO_MINOAN,
5371
5372 /**
5373 * Unicode script "Tangsa".
5374 * @since 19
5375 */
5376 TANGSA,
5377
5378 /**
5379 * Unicode script "Toto".
5380 * @since 19
5381 */
5382 TOTO,
5383
5384 /**
5385 * Unicode script "Kawi".
5386 * @since 20
5387 */
5388 KAWI,
5389
5390 /**
5391 * Unicode script "Nag Mundari".
5392 * @since 20
5393 */
5394 NAG_MUNDARI,
5395
5396 /**
5397 * Unicode script "Unknown".
5398 */
5399 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5400
5401 private static final int[] scriptStarts = {
5402 0x0000, // 0000..0040; COMMON
5403 0x0041, // 0041..005A; LATIN
5404 0x005B, // 005B..0060; COMMON
5405 0x0061, // 0061..007A; LATIN
5406 0x007B, // 007B..00A9; COMMON
5407 0x00AA, // 00AA ; LATIN
5408 0x00AB, // 00AB..00B9; COMMON
5409 0x00BA, // 00BA ; LATIN
5410 0x00BB, // 00BB..00BF; COMMON
5411 0x00C0, // 00C0..00D6; LATIN
5412 0x00D7, // 00D7 ; COMMON
5413 0x00D8, // 00D8..00F6; LATIN
5414 0x00F7, // 00F7 ; COMMON
5415 0x00F8, // 00F8..02B8; LATIN
5416 0x02B9, // 02B9..02DF; COMMON
5417 0x02E0, // 02E0..02E4; LATIN
5418 0x02E5, // 02E5..02E9; COMMON
5419 0x02EA, // 02EA..02EB; BOPOMOFO
5420 0x02EC, // 02EC..02FF; COMMON
5421 0x0300, // 0300..036F; INHERITED
5422 0x0370, // 0370..0373; GREEK
5423 0x0374, // 0374 ; COMMON
5424 0x0375, // 0375..0377; GREEK
5425 0x0378, // 0378..0379; UNKNOWN
5426 0x037A, // 037A..037D; GREEK
5427 0x037E, // 037E ; COMMON
5428 0x037F, // 037F ; GREEK
5429 0x0380, // 0380..0383; UNKNOWN
5430 0x0384, // 0384 ; GREEK
5431 0x0385, // 0385 ; COMMON
5432 0x0386, // 0386 ; GREEK
5433 0x0387, // 0387 ; COMMON
5434 0x0388, // 0388..038A; GREEK
5435 0x038B, // 038B ; UNKNOWN
5436 0x038C, // 038C ; GREEK
5437 0x038D, // 038D ; UNKNOWN
5438 0x038E, // 038E..03A1; GREEK
5439 0x03A2, // 03A2 ; UNKNOWN
5440 0x03A3, // 03A3..03E1; GREEK
5441 0x03E2, // 03E2..03EF; COPTIC
5442 0x03F0, // 03F0..03FF; GREEK
5443 0x0400, // 0400..0484; CYRILLIC
5444 0x0485, // 0485..0486; INHERITED
5445 0x0487, // 0487..052F; CYRILLIC
5446 0x0530, // 0530 ; UNKNOWN
5447 0x0531, // 0531..0556; ARMENIAN
5448 0x0557, // 0557..0558; UNKNOWN
5449 0x0559, // 0559..058A; ARMENIAN
5450 0x058B, // 058B..058C; UNKNOWN
5451 0x058D, // 058D..058F; ARMENIAN
5452 0x0590, // 0590 ; UNKNOWN
5453 0x0591, // 0591..05C7; HEBREW
5454 0x05C8, // 05C8..05CF; UNKNOWN
5455 0x05D0, // 05D0..05EA; HEBREW
5456 0x05EB, // 05EB..05EE; UNKNOWN
5457 0x05EF, // 05EF..05F4; HEBREW
5458 0x05F5, // 05F5..05FF; UNKNOWN
5459 0x0600, // 0600..0604; ARABIC
5460 0x0605, // 0605 ; COMMON
5461 0x0606, // 0606..060B; ARABIC
5462 0x060C, // 060C ; COMMON
5463 0x060D, // 060D..061A; ARABIC
5464 0x061B, // 061B ; COMMON
5465 0x061C, // 061C..061E; ARABIC
5466 0x061F, // 061F ; COMMON
5467 0x0620, // 0620..063F; ARABIC
5468 0x0640, // 0640 ; COMMON
5469 0x0641, // 0641..064A; ARABIC
5470 0x064B, // 064B..0655; INHERITED
5471 0x0656, // 0656..066F; ARABIC
5472 0x0670, // 0670 ; INHERITED
5473 0x0671, // 0671..06DC; ARABIC
5474 0x06DD, // 06DD ; COMMON
5475 0x06DE, // 06DE..06FF; ARABIC
5476 0x0700, // 0700..070D; SYRIAC
5477 0x070E, // 070E ; UNKNOWN
5478 0x070F, // 070F..074A; SYRIAC
5479 0x074B, // 074B..074C; UNKNOWN
5480 0x074D, // 074D..074F; SYRIAC
5481 0x0750, // 0750..077F; ARABIC
5482 0x0780, // 0780..07B1; THAANA
5483 0x07B2, // 07B2..07BF; UNKNOWN
5484 0x07C0, // 07C0..07FA; NKO
5485 0x07FB, // 07FB..07FC; UNKNOWN
5486 0x07FD, // 07FD..07FF; NKO
5487 0x0800, // 0800..082D; SAMARITAN
5488 0x082E, // 082E..082F; UNKNOWN
5489 0x0830, // 0830..083E; SAMARITAN
5490 0x083F, // 083F ; UNKNOWN
5491 0x0840, // 0840..085B; MANDAIC
5492 0x085C, // 085C..085D; UNKNOWN
5493 0x085E, // 085E ; MANDAIC
5494 0x085F, // 085F ; UNKNOWN
5495 0x0860, // 0860..086A; SYRIAC
5496 0x086B, // 086B..086F; UNKNOWN
5497 0x0870, // 0870..088E; ARABIC
5498 0x088F, // 088F ; UNKNOWN
5499 0x0890, // 0890..0891; ARABIC
5500 0x0892, // 0892..0897; UNKNOWN
5501 0x0898, // 0898..08E1; ARABIC
5502 0x08E2, // 08E2 ; COMMON
5503 0x08E3, // 08E3..08FF; ARABIC
5504 0x0900, // 0900..0950; DEVANAGARI
5505 0x0951, // 0951..0954; INHERITED
5506 0x0955, // 0955..0963; DEVANAGARI
5507 0x0964, // 0964..0965; COMMON
5508 0x0966, // 0966..097F; DEVANAGARI
5509 0x0980, // 0980..0983; BENGALI
5510 0x0984, // 0984 ; UNKNOWN
5511 0x0985, // 0985..098C; BENGALI
5512 0x098D, // 098D..098E; UNKNOWN
5513 0x098F, // 098F..0990; BENGALI
5514 0x0991, // 0991..0992; UNKNOWN
5515 0x0993, // 0993..09A8; BENGALI
5516 0x09A9, // 09A9 ; UNKNOWN
5517 0x09AA, // 09AA..09B0; BENGALI
5518 0x09B1, // 09B1 ; UNKNOWN
5519 0x09B2, // 09B2 ; BENGALI
5520 0x09B3, // 09B3..09B5; UNKNOWN
5521 0x09B6, // 09B6..09B9; BENGALI
5522 0x09BA, // 09BA..09BB; UNKNOWN
5523 0x09BC, // 09BC..09C4; BENGALI
5524 0x09C5, // 09C5..09C6; UNKNOWN
5525 0x09C7, // 09C7..09C8; BENGALI
5526 0x09C9, // 09C9..09CA; UNKNOWN
5527 0x09CB, // 09CB..09CE; BENGALI
5528 0x09CF, // 09CF..09D6; UNKNOWN
5529 0x09D7, // 09D7 ; BENGALI
5530 0x09D8, // 09D8..09DB; UNKNOWN
5531 0x09DC, // 09DC..09DD; BENGALI
5532 0x09DE, // 09DE ; UNKNOWN
5533 0x09DF, // 09DF..09E3; BENGALI
5534 0x09E4, // 09E4..09E5; UNKNOWN
5535 0x09E6, // 09E6..09FE; BENGALI
5536 0x09FF, // 09FF..0A00; UNKNOWN
5537 0x0A01, // 0A01..0A03; GURMUKHI
5538 0x0A04, // 0A04 ; UNKNOWN
5539 0x0A05, // 0A05..0A0A; GURMUKHI
5540 0x0A0B, // 0A0B..0A0E; UNKNOWN
5541 0x0A0F, // 0A0F..0A10; GURMUKHI
5542 0x0A11, // 0A11..0A12; UNKNOWN
5543 0x0A13, // 0A13..0A28; GURMUKHI
5544 0x0A29, // 0A29 ; UNKNOWN
5545 0x0A2A, // 0A2A..0A30; GURMUKHI
5546 0x0A31, // 0A31 ; UNKNOWN
5547 0x0A32, // 0A32..0A33; GURMUKHI
5548 0x0A34, // 0A34 ; UNKNOWN
5549 0x0A35, // 0A35..0A36; GURMUKHI
5550 0x0A37, // 0A37 ; UNKNOWN
5551 0x0A38, // 0A38..0A39; GURMUKHI
5552 0x0A3A, // 0A3A..0A3B; UNKNOWN
5553 0x0A3C, // 0A3C ; GURMUKHI
5554 0x0A3D, // 0A3D ; UNKNOWN
5555 0x0A3E, // 0A3E..0A42; GURMUKHI
5556 0x0A43, // 0A43..0A46; UNKNOWN
5557 0x0A47, // 0A47..0A48; GURMUKHI
5558 0x0A49, // 0A49..0A4A; UNKNOWN
5559 0x0A4B, // 0A4B..0A4D; GURMUKHI
5560 0x0A4E, // 0A4E..0A50; UNKNOWN
5561 0x0A51, // 0A51 ; GURMUKHI
5562 0x0A52, // 0A52..0A58; UNKNOWN
5563 0x0A59, // 0A59..0A5C; GURMUKHI
5564 0x0A5D, // 0A5D ; UNKNOWN
5565 0x0A5E, // 0A5E ; GURMUKHI
5566 0x0A5F, // 0A5F..0A65; UNKNOWN
5567 0x0A66, // 0A66..0A76; GURMUKHI
5568 0x0A77, // 0A77..0A80; UNKNOWN
5569 0x0A81, // 0A81..0A83; GUJARATI
5570 0x0A84, // 0A84 ; UNKNOWN
5571 0x0A85, // 0A85..0A8D; GUJARATI
5572 0x0A8E, // 0A8E ; UNKNOWN
5573 0x0A8F, // 0A8F..0A91; GUJARATI
5574 0x0A92, // 0A92 ; UNKNOWN
5575 0x0A93, // 0A93..0AA8; GUJARATI
5576 0x0AA9, // 0AA9 ; UNKNOWN
5577 0x0AAA, // 0AAA..0AB0; GUJARATI
5578 0x0AB1, // 0AB1 ; UNKNOWN
5579 0x0AB2, // 0AB2..0AB3; GUJARATI
5580 0x0AB4, // 0AB4 ; UNKNOWN
5581 0x0AB5, // 0AB5..0AB9; GUJARATI
5582 0x0ABA, // 0ABA..0ABB; UNKNOWN
5583 0x0ABC, // 0ABC..0AC5; GUJARATI
5584 0x0AC6, // 0AC6 ; UNKNOWN
5585 0x0AC7, // 0AC7..0AC9; GUJARATI
5586 0x0ACA, // 0ACA ; UNKNOWN
5587 0x0ACB, // 0ACB..0ACD; GUJARATI
5588 0x0ACE, // 0ACE..0ACF; UNKNOWN
5589 0x0AD0, // 0AD0 ; GUJARATI
5590 0x0AD1, // 0AD1..0ADF; UNKNOWN
5591 0x0AE0, // 0AE0..0AE3; GUJARATI
5592 0x0AE4, // 0AE4..0AE5; UNKNOWN
5593 0x0AE6, // 0AE6..0AF1; GUJARATI
5594 0x0AF2, // 0AF2..0AF8; UNKNOWN
5595 0x0AF9, // 0AF9..0AFF; GUJARATI
5596 0x0B00, // 0B00 ; UNKNOWN
5597 0x0B01, // 0B01..0B03; ORIYA
5598 0x0B04, // 0B04 ; UNKNOWN
5599 0x0B05, // 0B05..0B0C; ORIYA
5600 0x0B0D, // 0B0D..0B0E; UNKNOWN
5601 0x0B0F, // 0B0F..0B10; ORIYA
5602 0x0B11, // 0B11..0B12; UNKNOWN
5603 0x0B13, // 0B13..0B28; ORIYA
5604 0x0B29, // 0B29 ; UNKNOWN
5605 0x0B2A, // 0B2A..0B30; ORIYA
5606 0x0B31, // 0B31 ; UNKNOWN
5607 0x0B32, // 0B32..0B33; ORIYA
5608 0x0B34, // 0B34 ; UNKNOWN
5609 0x0B35, // 0B35..0B39; ORIYA
5610 0x0B3A, // 0B3A..0B3B; UNKNOWN
5611 0x0B3C, // 0B3C..0B44; ORIYA
5612 0x0B45, // 0B45..0B46; UNKNOWN
5613 0x0B47, // 0B47..0B48; ORIYA
5614 0x0B49, // 0B49..0B4A; UNKNOWN
5615 0x0B4B, // 0B4B..0B4D; ORIYA
5616 0x0B4E, // 0B4E..0B54; UNKNOWN
5617 0x0B55, // 0B55..0B57; ORIYA
5618 0x0B58, // 0B58..0B5B; UNKNOWN
5619 0x0B5C, // 0B5C..0B5D; ORIYA
5620 0x0B5E, // 0B5E ; UNKNOWN
5621 0x0B5F, // 0B5F..0B63; ORIYA
5622 0x0B64, // 0B64..0B65; UNKNOWN
5623 0x0B66, // 0B66..0B77; ORIYA
5624 0x0B78, // 0B78..0B81; UNKNOWN
5625 0x0B82, // 0B82..0B83; TAMIL
5626 0x0B84, // 0B84 ; UNKNOWN
5627 0x0B85, // 0B85..0B8A; TAMIL
5628 0x0B8B, // 0B8B..0B8D; UNKNOWN
5629 0x0B8E, // 0B8E..0B90; TAMIL
5630 0x0B91, // 0B91 ; UNKNOWN
5631 0x0B92, // 0B92..0B95; TAMIL
5632 0x0B96, // 0B96..0B98; UNKNOWN
5633 0x0B99, // 0B99..0B9A; TAMIL
5634 0x0B9B, // 0B9B ; UNKNOWN
5635 0x0B9C, // 0B9C ; TAMIL
5636 0x0B9D, // 0B9D ; UNKNOWN
5637 0x0B9E, // 0B9E..0B9F; TAMIL
5638 0x0BA0, // 0BA0..0BA2; UNKNOWN
5639 0x0BA3, // 0BA3..0BA4; TAMIL
5640 0x0BA5, // 0BA5..0BA7; UNKNOWN
5641 0x0BA8, // 0BA8..0BAA; TAMIL
5642 0x0BAB, // 0BAB..0BAD; UNKNOWN
5643 0x0BAE, // 0BAE..0BB9; TAMIL
5644 0x0BBA, // 0BBA..0BBD; UNKNOWN
5645 0x0BBE, // 0BBE..0BC2; TAMIL
5646 0x0BC3, // 0BC3..0BC5; UNKNOWN
5647 0x0BC6, // 0BC6..0BC8; TAMIL
5648 0x0BC9, // 0BC9 ; UNKNOWN
5649 0x0BCA, // 0BCA..0BCD; TAMIL
5650 0x0BCE, // 0BCE..0BCF; UNKNOWN
5651 0x0BD0, // 0BD0 ; TAMIL
5652 0x0BD1, // 0BD1..0BD6; UNKNOWN
5653 0x0BD7, // 0BD7 ; TAMIL
5654 0x0BD8, // 0BD8..0BE5; UNKNOWN
5655 0x0BE6, // 0BE6..0BFA; TAMIL
5656 0x0BFB, // 0BFB..0BFF; UNKNOWN
5657 0x0C00, // 0C00..0C0C; TELUGU
5658 0x0C0D, // 0C0D ; UNKNOWN
5659 0x0C0E, // 0C0E..0C10; TELUGU
5660 0x0C11, // 0C11 ; UNKNOWN
5661 0x0C12, // 0C12..0C28; TELUGU
5662 0x0C29, // 0C29 ; UNKNOWN
5663 0x0C2A, // 0C2A..0C39; TELUGU
5664 0x0C3A, // 0C3A..0C3B; UNKNOWN
5665 0x0C3C, // 0C3C..0C44; TELUGU
5666 0x0C45, // 0C45 ; UNKNOWN
5667 0x0C46, // 0C46..0C48; TELUGU
5668 0x0C49, // 0C49 ; UNKNOWN
5669 0x0C4A, // 0C4A..0C4D; TELUGU
5670 0x0C4E, // 0C4E..0C54; UNKNOWN
5671 0x0C55, // 0C55..0C56; TELUGU
5672 0x0C57, // 0C57 ; UNKNOWN
5673 0x0C58, // 0C58..0C5A; TELUGU
5674 0x0C5B, // 0C5B..0C5C; UNKNOWN
5675 0x0C5D, // 0C5D ; TELUGU
5676 0x0C5E, // 0C5E..0C5F; UNKNOWN
5677 0x0C60, // 0C60..0C63; TELUGU
5678 0x0C64, // 0C64..0C65; UNKNOWN
5679 0x0C66, // 0C66..0C6F; TELUGU
5680 0x0C70, // 0C70..0C76; UNKNOWN
5681 0x0C77, // 0C77..0C7F; TELUGU
5682 0x0C80, // 0C80..0C8C; KANNADA
5683 0x0C8D, // 0C8D ; UNKNOWN
5684 0x0C8E, // 0C8E..0C90; KANNADA
5685 0x0C91, // 0C91 ; UNKNOWN
5686 0x0C92, // 0C92..0CA8; KANNADA
5687 0x0CA9, // 0CA9 ; UNKNOWN
5688 0x0CAA, // 0CAA..0CB3; KANNADA
5689 0x0CB4, // 0CB4 ; UNKNOWN
5690 0x0CB5, // 0CB5..0CB9; KANNADA
5691 0x0CBA, // 0CBA..0CBB; UNKNOWN
5692 0x0CBC, // 0CBC..0CC4; KANNADA
5693 0x0CC5, // 0CC5 ; UNKNOWN
5694 0x0CC6, // 0CC6..0CC8; KANNADA
5695 0x0CC9, // 0CC9 ; UNKNOWN
5696 0x0CCA, // 0CCA..0CCD; KANNADA
5697 0x0CCE, // 0CCE..0CD4; UNKNOWN
5698 0x0CD5, // 0CD5..0CD6; KANNADA
5699 0x0CD7, // 0CD7..0CDC; UNKNOWN
5700 0x0CDD, // 0CDD..0CDE; KANNADA
5701 0x0CDF, // 0CDF ; UNKNOWN
5702 0x0CE0, // 0CE0..0CE3; KANNADA
5703 0x0CE4, // 0CE4..0CE5; UNKNOWN
5704 0x0CE6, // 0CE6..0CEF; KANNADA
5705 0x0CF0, // 0CF0 ; UNKNOWN
5706 0x0CF1, // 0CF1..0CF3; KANNADA
5707 0x0CF4, // 0CF4..0CFF; UNKNOWN
5708 0x0D00, // 0D00..0D0C; MALAYALAM
5709 0x0D0D, // 0D0D ; UNKNOWN
5710 0x0D0E, // 0D0E..0D10; MALAYALAM
5711 0x0D11, // 0D11 ; UNKNOWN
5712 0x0D12, // 0D12..0D44; MALAYALAM
5713 0x0D45, // 0D45 ; UNKNOWN
5714 0x0D46, // 0D46..0D48; MALAYALAM
5715 0x0D49, // 0D49 ; UNKNOWN
5716 0x0D4A, // 0D4A..0D4F; MALAYALAM
5717 0x0D50, // 0D50..0D53; UNKNOWN
5718 0x0D54, // 0D54..0D63; MALAYALAM
5719 0x0D64, // 0D64..0D65; UNKNOWN
5720 0x0D66, // 0D66..0D7F; MALAYALAM
5721 0x0D80, // 0D80 ; UNKNOWN
5722 0x0D81, // 0D81..0D83; SINHALA
5723 0x0D84, // 0D84 ; UNKNOWN
5724 0x0D85, // 0D85..0D96; SINHALA
5725 0x0D97, // 0D97..0D99; UNKNOWN
5726 0x0D9A, // 0D9A..0DB1; SINHALA
5727 0x0DB2, // 0DB2 ; UNKNOWN
5728 0x0DB3, // 0DB3..0DBB; SINHALA
5729 0x0DBC, // 0DBC ; UNKNOWN
5730 0x0DBD, // 0DBD ; SINHALA
5731 0x0DBE, // 0DBE..0DBF; UNKNOWN
5732 0x0DC0, // 0DC0..0DC6; SINHALA
5733 0x0DC7, // 0DC7..0DC9; UNKNOWN
5734 0x0DCA, // 0DCA ; SINHALA
5735 0x0DCB, // 0DCB..0DCE; UNKNOWN
5736 0x0DCF, // 0DCF..0DD4; SINHALA
5737 0x0DD5, // 0DD5 ; UNKNOWN
5738 0x0DD6, // 0DD6 ; SINHALA
5739 0x0DD7, // 0DD7 ; UNKNOWN
5740 0x0DD8, // 0DD8..0DDF; SINHALA
5741 0x0DE0, // 0DE0..0DE5; UNKNOWN
5742 0x0DE6, // 0DE6..0DEF; SINHALA
5743 0x0DF0, // 0DF0..0DF1; UNKNOWN
5744 0x0DF2, // 0DF2..0DF4; SINHALA
5745 0x0DF5, // 0DF5..0E00; UNKNOWN
5746 0x0E01, // 0E01..0E3A; THAI
5747 0x0E3B, // 0E3B..0E3E; UNKNOWN
5748 0x0E3F, // 0E3F ; COMMON
5749 0x0E40, // 0E40..0E5B; THAI
5750 0x0E5C, // 0E5C..0E80; UNKNOWN
5751 0x0E81, // 0E81..0E82; LAO
5752 0x0E83, // 0E83 ; UNKNOWN
5753 0x0E84, // 0E84 ; LAO
5754 0x0E85, // 0E85 ; UNKNOWN
5755 0x0E86, // 0E86..0E8A; LAO
5756 0x0E8B, // 0E8B ; UNKNOWN
5757 0x0E8C, // 0E8C..0EA3; LAO
5758 0x0EA4, // 0EA4 ; UNKNOWN
5759 0x0EA5, // 0EA5 ; LAO
5760 0x0EA6, // 0EA6 ; UNKNOWN
5761 0x0EA7, // 0EA7..0EBD; LAO
5762 0x0EBE, // 0EBE..0EBF; UNKNOWN
5763 0x0EC0, // 0EC0..0EC4; LAO
5764 0x0EC5, // 0EC5 ; UNKNOWN
5765 0x0EC6, // 0EC6 ; LAO
5766 0x0EC7, // 0EC7 ; UNKNOWN
5767 0x0EC8, // 0EC8..0ECE; LAO
5768 0x0ECF, // 0ECF ; UNKNOWN
5769 0x0ED0, // 0ED0..0ED9; LAO
5770 0x0EDA, // 0EDA..0EDB; UNKNOWN
5771 0x0EDC, // 0EDC..0EDF; LAO
5772 0x0EE0, // 0EE0..0EFF; UNKNOWN
5773 0x0F00, // 0F00..0F47; TIBETAN
5774 0x0F48, // 0F48 ; UNKNOWN
5775 0x0F49, // 0F49..0F6C; TIBETAN
5776 0x0F6D, // 0F6D..0F70; UNKNOWN
5777 0x0F71, // 0F71..0F97; TIBETAN
5778 0x0F98, // 0F98 ; UNKNOWN
5779 0x0F99, // 0F99..0FBC; TIBETAN
5780 0x0FBD, // 0FBD ; UNKNOWN
5781 0x0FBE, // 0FBE..0FCC; TIBETAN
5782 0x0FCD, // 0FCD ; UNKNOWN
5783 0x0FCE, // 0FCE..0FD4; TIBETAN
5784 0x0FD5, // 0FD5..0FD8; COMMON
5785 0x0FD9, // 0FD9..0FDA; TIBETAN
5786 0x0FDB, // 0FDB..0FFF; UNKNOWN
5787 0x1000, // 1000..109F; MYANMAR
5788 0x10A0, // 10A0..10C5; GEORGIAN
5789 0x10C6, // 10C6 ; UNKNOWN
5790 0x10C7, // 10C7 ; GEORGIAN
5791 0x10C8, // 10C8..10CC; UNKNOWN
5792 0x10CD, // 10CD ; GEORGIAN
5793 0x10CE, // 10CE..10CF; UNKNOWN
5794 0x10D0, // 10D0..10FA; GEORGIAN
5795 0x10FB, // 10FB ; COMMON
5796 0x10FC, // 10FC..10FF; GEORGIAN
5797 0x1100, // 1100..11FF; HANGUL
5798 0x1200, // 1200..1248; ETHIOPIC
5799 0x1249, // 1249 ; UNKNOWN
5800 0x124A, // 124A..124D; ETHIOPIC
5801 0x124E, // 124E..124F; UNKNOWN
5802 0x1250, // 1250..1256; ETHIOPIC
5803 0x1257, // 1257 ; UNKNOWN
5804 0x1258, // 1258 ; ETHIOPIC
5805 0x1259, // 1259 ; UNKNOWN
5806 0x125A, // 125A..125D; ETHIOPIC
5807 0x125E, // 125E..125F; UNKNOWN
5808 0x1260, // 1260..1288; ETHIOPIC
5809 0x1289, // 1289 ; UNKNOWN
5810 0x128A, // 128A..128D; ETHIOPIC
5811 0x128E, // 128E..128F; UNKNOWN
5812 0x1290, // 1290..12B0; ETHIOPIC
5813 0x12B1, // 12B1 ; UNKNOWN
5814 0x12B2, // 12B2..12B5; ETHIOPIC
5815 0x12B6, // 12B6..12B7; UNKNOWN
5816 0x12B8, // 12B8..12BE; ETHIOPIC
5817 0x12BF, // 12BF ; UNKNOWN
5818 0x12C0, // 12C0 ; ETHIOPIC
5819 0x12C1, // 12C1 ; UNKNOWN
5820 0x12C2, // 12C2..12C5; ETHIOPIC
5821 0x12C6, // 12C6..12C7; UNKNOWN
5822 0x12C8, // 12C8..12D6; ETHIOPIC
5823 0x12D7, // 12D7 ; UNKNOWN
5824 0x12D8, // 12D8..1310; ETHIOPIC
5825 0x1311, // 1311 ; UNKNOWN
5826 0x1312, // 1312..1315; ETHIOPIC
5827 0x1316, // 1316..1317; UNKNOWN
5828 0x1318, // 1318..135A; ETHIOPIC
5829 0x135B, // 135B..135C; UNKNOWN
5830 0x135D, // 135D..137C; ETHIOPIC
5831 0x137D, // 137D..137F; UNKNOWN
5832 0x1380, // 1380..1399; ETHIOPIC
5833 0x139A, // 139A..139F; UNKNOWN
5834 0x13A0, // 13A0..13F5; CHEROKEE
5835 0x13F6, // 13F6..13F7; UNKNOWN
5836 0x13F8, // 13F8..13FD; CHEROKEE
5837 0x13FE, // 13FE..13FF; UNKNOWN
5838 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5839 0x1680, // 1680..169C; OGHAM
5840 0x169D, // 169D..169F; UNKNOWN
5841 0x16A0, // 16A0..16EA; RUNIC
5842 0x16EB, // 16EB..16ED; COMMON
5843 0x16EE, // 16EE..16F8; RUNIC
5844 0x16F9, // 16F9..16FF; UNKNOWN
5845 0x1700, // 1700..1715; TAGALOG
5846 0x1716, // 1716..171E; UNKNOWN
5847 0x171F, // 171F ; TAGALOG
5848 0x1720, // 1720..1734; HANUNOO
5849 0x1735, // 1735..1736; COMMON
5850 0x1737, // 1737..173F; UNKNOWN
5851 0x1740, // 1740..1753; BUHID
5852 0x1754, // 1754..175F; UNKNOWN
5853 0x1760, // 1760..176C; TAGBANWA
5854 0x176D, // 176D ; UNKNOWN
5855 0x176E, // 176E..1770; TAGBANWA
5856 0x1771, // 1771 ; UNKNOWN
5857 0x1772, // 1772..1773; TAGBANWA
5858 0x1774, // 1774..177F; UNKNOWN
5859 0x1780, // 1780..17DD; KHMER
5860 0x17DE, // 17DE..17DF; UNKNOWN
5861 0x17E0, // 17E0..17E9; KHMER
5862 0x17EA, // 17EA..17EF; UNKNOWN
5863 0x17F0, // 17F0..17F9; KHMER
5864 0x17FA, // 17FA..17FF; UNKNOWN
5865 0x1800, // 1800..1801; MONGOLIAN
5866 0x1802, // 1802..1803; COMMON
5867 0x1804, // 1804 ; MONGOLIAN
5868 0x1805, // 1805 ; COMMON
5869 0x1806, // 1806..1819; MONGOLIAN
5870 0x181A, // 181A..181F; UNKNOWN
5871 0x1820, // 1820..1878; MONGOLIAN
5872 0x1879, // 1879..187F; UNKNOWN
5873 0x1880, // 1880..18AA; MONGOLIAN
5874 0x18AB, // 18AB..18AF; UNKNOWN
5875 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
5876 0x18F6, // 18F6..18FF; UNKNOWN
5877 0x1900, // 1900..191E; LIMBU
5878 0x191F, // 191F ; UNKNOWN
5879 0x1920, // 1920..192B; LIMBU
5880 0x192C, // 192C..192F; UNKNOWN
5881 0x1930, // 1930..193B; LIMBU
5882 0x193C, // 193C..193F; UNKNOWN
5883 0x1940, // 1940 ; LIMBU
5884 0x1941, // 1941..1943; UNKNOWN
5885 0x1944, // 1944..194F; LIMBU
5886 0x1950, // 1950..196D; TAI_LE
5887 0x196E, // 196E..196F; UNKNOWN
5888 0x1970, // 1970..1974; TAI_LE
5889 0x1975, // 1975..197F; UNKNOWN
5890 0x1980, // 1980..19AB; NEW_TAI_LUE
5891 0x19AC, // 19AC..19AF; UNKNOWN
5892 0x19B0, // 19B0..19C9; NEW_TAI_LUE
5893 0x19CA, // 19CA..19CF; UNKNOWN
5894 0x19D0, // 19D0..19DA; NEW_TAI_LUE
5895 0x19DB, // 19DB..19DD; UNKNOWN
5896 0x19DE, // 19DE..19DF; NEW_TAI_LUE
5897 0x19E0, // 19E0..19FF; KHMER
5898 0x1A00, // 1A00..1A1B; BUGINESE
5899 0x1A1C, // 1A1C..1A1D; UNKNOWN
5900 0x1A1E, // 1A1E..1A1F; BUGINESE
5901 0x1A20, // 1A20..1A5E; TAI_THAM
5902 0x1A5F, // 1A5F ; UNKNOWN
5903 0x1A60, // 1A60..1A7C; TAI_THAM
5904 0x1A7D, // 1A7D..1A7E; UNKNOWN
5905 0x1A7F, // 1A7F..1A89; TAI_THAM
5906 0x1A8A, // 1A8A..1A8F; UNKNOWN
5907 0x1A90, // 1A90..1A99; TAI_THAM
5908 0x1A9A, // 1A9A..1A9F; UNKNOWN
5909 0x1AA0, // 1AA0..1AAD; TAI_THAM
5910 0x1AAE, // 1AAE..1AAF; UNKNOWN
5911 0x1AB0, // 1AB0..1ACE; INHERITED
5912 0x1ACF, // 1ACF..1AFF; UNKNOWN
5913 0x1B00, // 1B00..1B4C; BALINESE
5914 0x1B4D, // 1B4D..1B4F; UNKNOWN
5915 0x1B50, // 1B50..1B7E; BALINESE
5916 0x1B7F, // 1B7F ; UNKNOWN
5917 0x1B80, // 1B80..1BBF; SUNDANESE
5918 0x1BC0, // 1BC0..1BF3; BATAK
5919 0x1BF4, // 1BF4..1BFB; UNKNOWN
5920 0x1BFC, // 1BFC..1BFF; BATAK
5921 0x1C00, // 1C00..1C37; LEPCHA
5922 0x1C38, // 1C38..1C3A; UNKNOWN
5923 0x1C3B, // 1C3B..1C49; LEPCHA
5924 0x1C4A, // 1C4A..1C4C; UNKNOWN
5925 0x1C4D, // 1C4D..1C4F; LEPCHA
5926 0x1C50, // 1C50..1C7F; OL_CHIKI
5927 0x1C80, // 1C80..1C88; CYRILLIC
5928 0x1C89, // 1C89..1C8F; UNKNOWN
5929 0x1C90, // 1C90..1CBA; GEORGIAN
5930 0x1CBB, // 1CBB..1CBC; UNKNOWN
5931 0x1CBD, // 1CBD..1CBF; GEORGIAN
5932 0x1CC0, // 1CC0..1CC7; SUNDANESE
5933 0x1CC8, // 1CC8..1CCF; UNKNOWN
5934 0x1CD0, // 1CD0..1CD2; INHERITED
5935 0x1CD3, // 1CD3 ; COMMON
5936 0x1CD4, // 1CD4..1CE0; INHERITED
5937 0x1CE1, // 1CE1 ; COMMON
5938 0x1CE2, // 1CE2..1CE8; INHERITED
5939 0x1CE9, // 1CE9..1CEC; COMMON
5940 0x1CED, // 1CED ; INHERITED
5941 0x1CEE, // 1CEE..1CF3; COMMON
5942 0x1CF4, // 1CF4 ; INHERITED
5943 0x1CF5, // 1CF5..1CF7; COMMON
5944 0x1CF8, // 1CF8..1CF9; INHERITED
5945 0x1CFA, // 1CFA ; COMMON
5946 0x1CFB, // 1CFB..1CFF; UNKNOWN
5947 0x1D00, // 1D00..1D25; LATIN
5948 0x1D26, // 1D26..1D2A; GREEK
5949 0x1D2B, // 1D2B ; CYRILLIC
5950 0x1D2C, // 1D2C..1D5C; LATIN
5951 0x1D5D, // 1D5D..1D61; GREEK
5952 0x1D62, // 1D62..1D65; LATIN
5953 0x1D66, // 1D66..1D6A; GREEK
5954 0x1D6B, // 1D6B..1D77; LATIN
5955 0x1D78, // 1D78 ; CYRILLIC
5956 0x1D79, // 1D79..1DBE; LATIN
5957 0x1DBF, // 1DBF ; GREEK
5958 0x1DC0, // 1DC0..1DFF; INHERITED
5959 0x1E00, // 1E00..1EFF; LATIN
5960 0x1F00, // 1F00..1F15; GREEK
5961 0x1F16, // 1F16..1F17; UNKNOWN
5962 0x1F18, // 1F18..1F1D; GREEK
5963 0x1F1E, // 1F1E..1F1F; UNKNOWN
5964 0x1F20, // 1F20..1F45; GREEK
5965 0x1F46, // 1F46..1F47; UNKNOWN
5966 0x1F48, // 1F48..1F4D; GREEK
5967 0x1F4E, // 1F4E..1F4F; UNKNOWN
5968 0x1F50, // 1F50..1F57; GREEK
5969 0x1F58, // 1F58 ; UNKNOWN
5970 0x1F59, // 1F59 ; GREEK
5971 0x1F5A, // 1F5A ; UNKNOWN
5972 0x1F5B, // 1F5B ; GREEK
5973 0x1F5C, // 1F5C ; UNKNOWN
5974 0x1F5D, // 1F5D ; GREEK
5975 0x1F5E, // 1F5E ; UNKNOWN
5976 0x1F5F, // 1F5F..1F7D; GREEK
5977 0x1F7E, // 1F7E..1F7F; UNKNOWN
5978 0x1F80, // 1F80..1FB4; GREEK
5979 0x1FB5, // 1FB5 ; UNKNOWN
5980 0x1FB6, // 1FB6..1FC4; GREEK
5981 0x1FC5, // 1FC5 ; UNKNOWN
5982 0x1FC6, // 1FC6..1FD3; GREEK
5983 0x1FD4, // 1FD4..1FD5; UNKNOWN
5984 0x1FD6, // 1FD6..1FDB; GREEK
5985 0x1FDC, // 1FDC ; UNKNOWN
5986 0x1FDD, // 1FDD..1FEF; GREEK
5987 0x1FF0, // 1FF0..1FF1; UNKNOWN
5988 0x1FF2, // 1FF2..1FF4; GREEK
5989 0x1FF5, // 1FF5 ; UNKNOWN
5990 0x1FF6, // 1FF6..1FFE; GREEK
5991 0x1FFF, // 1FFF ; UNKNOWN
5992 0x2000, // 2000..200B; COMMON
5993 0x200C, // 200C..200D; INHERITED
5994 0x200E, // 200E..2064; COMMON
5995 0x2065, // 2065 ; UNKNOWN
5996 0x2066, // 2066..2070; COMMON
5997 0x2071, // 2071 ; LATIN
5998 0x2072, // 2072..2073; UNKNOWN
5999 0x2074, // 2074..207E; COMMON
6000 0x207F, // 207F ; LATIN
6001 0x2080, // 2080..208E; COMMON
6002 0x208F, // 208F ; UNKNOWN
6003 0x2090, // 2090..209C; LATIN
6004 0x209D, // 209D..209F; UNKNOWN
6005 0x20A0, // 20A0..20C0; COMMON
6006 0x20C1, // 20C1..20CF; UNKNOWN
6007 0x20D0, // 20D0..20F0; INHERITED
6008 0x20F1, // 20F1..20FF; UNKNOWN
6009 0x2100, // 2100..2125; COMMON
6010 0x2126, // 2126 ; GREEK
6011 0x2127, // 2127..2129; COMMON
6012 0x212A, // 212A..212B; LATIN
6013 0x212C, // 212C..2131; COMMON
6014 0x2132, // 2132 ; LATIN
6015 0x2133, // 2133..214D; COMMON
6016 0x214E, // 214E ; LATIN
6017 0x214F, // 214F..215F; COMMON
6018 0x2160, // 2160..2188; LATIN
6019 0x2189, // 2189..218B; COMMON
6020 0x218C, // 218C..218F; UNKNOWN
6021 0x2190, // 2190..2426; COMMON
6022 0x2427, // 2427..243F; UNKNOWN
6023 0x2440, // 2440..244A; COMMON
6024 0x244B, // 244B..245F; UNKNOWN
6025 0x2460, // 2460..27FF; COMMON
6026 0x2800, // 2800..28FF; BRAILLE
6027 0x2900, // 2900..2B73; COMMON
6028 0x2B74, // 2B74..2B75; UNKNOWN
6029 0x2B76, // 2B76..2B95; COMMON
6030 0x2B96, // 2B96 ; UNKNOWN
6031 0x2B97, // 2B97..2BFF; COMMON
6032 0x2C00, // 2C00..2C5F; GLAGOLITIC
6033 0x2C60, // 2C60..2C7F; LATIN
6034 0x2C80, // 2C80..2CF3; COPTIC
6035 0x2CF4, // 2CF4..2CF8; UNKNOWN
6036 0x2CF9, // 2CF9..2CFF; COPTIC
6037 0x2D00, // 2D00..2D25; GEORGIAN
6038 0x2D26, // 2D26 ; UNKNOWN
6039 0x2D27, // 2D27 ; GEORGIAN
6040 0x2D28, // 2D28..2D2C; UNKNOWN
6041 0x2D2D, // 2D2D ; GEORGIAN
6042 0x2D2E, // 2D2E..2D2F; UNKNOWN
6043 0x2D30, // 2D30..2D67; TIFINAGH
6044 0x2D68, // 2D68..2D6E; UNKNOWN
6045 0x2D6F, // 2D6F..2D70; TIFINAGH
6046 0x2D71, // 2D71..2D7E; UNKNOWN
6047 0x2D7F, // 2D7F ; TIFINAGH
6048 0x2D80, // 2D80..2D96; ETHIOPIC
6049 0x2D97, // 2D97..2D9F; UNKNOWN
6050 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6051 0x2DA7, // 2DA7 ; UNKNOWN
6052 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6053 0x2DAF, // 2DAF ; UNKNOWN
6054 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6055 0x2DB7, // 2DB7 ; UNKNOWN
6056 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6057 0x2DBF, // 2DBF ; UNKNOWN
6058 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6059 0x2DC7, // 2DC7 ; UNKNOWN
6060 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6061 0x2DCF, // 2DCF ; UNKNOWN
6062 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6063 0x2DD7, // 2DD7 ; UNKNOWN
6064 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6065 0x2DDF, // 2DDF ; UNKNOWN
6066 0x2DE0, // 2DE0..2DFF; CYRILLIC
6067 0x2E00, // 2E00..2E5D; COMMON
6068 0x2E5E, // 2E5E..2E7F; UNKNOWN
6069 0x2E80, // 2E80..2E99; HAN
6070 0x2E9A, // 2E9A ; UNKNOWN
6071 0x2E9B, // 2E9B..2EF3; HAN
6072 0x2EF4, // 2EF4..2EFF; UNKNOWN
6073 0x2F00, // 2F00..2FD5; HAN
6074 0x2FD6, // 2FD6..2FEF; UNKNOWN
6075 0x2FF0, // 2FF0..3004; COMMON
6076 0x3005, // 3005 ; HAN
6077 0x3006, // 3006 ; COMMON
6078 0x3007, // 3007 ; HAN
6079 0x3008, // 3008..3020; COMMON
6080 0x3021, // 3021..3029; HAN
6081 0x302A, // 302A..302D; INHERITED
6082 0x302E, // 302E..302F; HANGUL
6083 0x3030, // 3030..3037; COMMON
6084 0x3038, // 3038..303B; HAN
6085 0x303C, // 303C..303F; COMMON
6086 0x3040, // 3040 ; UNKNOWN
6087 0x3041, // 3041..3096; HIRAGANA
6088 0x3097, // 3097..3098; UNKNOWN
6089 0x3099, // 3099..309A; INHERITED
6090 0x309B, // 309B..309C; COMMON
6091 0x309D, // 309D..309F; HIRAGANA
6092 0x30A0, // 30A0 ; COMMON
6093 0x30A1, // 30A1..30FA; KATAKANA
6094 0x30FB, // 30FB..30FC; COMMON
6095 0x30FD, // 30FD..30FF; KATAKANA
6096 0x3100, // 3100..3104; UNKNOWN
6097 0x3105, // 3105..312F; BOPOMOFO
6098 0x3130, // 3130 ; UNKNOWN
6099 0x3131, // 3131..318E; HANGUL
6100 0x318F, // 318F ; UNKNOWN
6101 0x3190, // 3190..319F; COMMON
6102 0x31A0, // 31A0..31BF; BOPOMOFO
6103 0x31C0, // 31C0..31E3; COMMON
6104 0x31E4, // 31E4..31EE; UNKNOWN
6105 0x31EF, // 31EF ; COMMON
6106 0x31F0, // 31F0..31FF; KATAKANA
6107 0x3200, // 3200..321E; HANGUL
6108 0x321F, // 321F ; UNKNOWN
6109 0x3220, // 3220..325F; COMMON
6110 0x3260, // 3260..327E; HANGUL
6111 0x327F, // 327F..32CF; COMMON
6112 0x32D0, // 32D0..32FE; KATAKANA
6113 0x32FF, // 32FF ; COMMON
6114 0x3300, // 3300..3357; KATAKANA
6115 0x3358, // 3358..33FF; COMMON
6116 0x3400, // 3400..4DBF; HAN
6117 0x4DC0, // 4DC0..4DFF; COMMON
6118 0x4E00, // 4E00..9FFF; HAN
6119 0xA000, // A000..A48C; YI
6120 0xA48D, // A48D..A48F; UNKNOWN
6121 0xA490, // A490..A4C6; YI
6122 0xA4C7, // A4C7..A4CF; UNKNOWN
6123 0xA4D0, // A4D0..A4FF; LISU
6124 0xA500, // A500..A62B; VAI
6125 0xA62C, // A62C..A63F; UNKNOWN
6126 0xA640, // A640..A69F; CYRILLIC
6127 0xA6A0, // A6A0..A6F7; BAMUM
6128 0xA6F8, // A6F8..A6FF; UNKNOWN
6129 0xA700, // A700..A721; COMMON
6130 0xA722, // A722..A787; LATIN
6131 0xA788, // A788..A78A; COMMON
6132 0xA78B, // A78B..A7CA; LATIN
6133 0xA7CB, // A7CB..A7CF; UNKNOWN
6134 0xA7D0, // A7D0..A7D1; LATIN
6135 0xA7D2, // A7D2 ; UNKNOWN
6136 0xA7D3, // A7D3 ; LATIN
6137 0xA7D4, // A7D4 ; UNKNOWN
6138 0xA7D5, // A7D5..A7D9; LATIN
6139 0xA7DA, // A7DA..A7F1; UNKNOWN
6140 0xA7F2, // A7F2..A7FF; LATIN
6141 0xA800, // A800..A82C; SYLOTI_NAGRI
6142 0xA82D, // A82D..A82F; UNKNOWN
6143 0xA830, // A830..A839; COMMON
6144 0xA83A, // A83A..A83F; UNKNOWN
6145 0xA840, // A840..A877; PHAGS_PA
6146 0xA878, // A878..A87F; UNKNOWN
6147 0xA880, // A880..A8C5; SAURASHTRA
6148 0xA8C6, // A8C6..A8CD; UNKNOWN
6149 0xA8CE, // A8CE..A8D9; SAURASHTRA
6150 0xA8DA, // A8DA..A8DF; UNKNOWN
6151 0xA8E0, // A8E0..A8FF; DEVANAGARI
6152 0xA900, // A900..A92D; KAYAH_LI
6153 0xA92E, // A92E ; COMMON
6154 0xA92F, // A92F ; KAYAH_LI
6155 0xA930, // A930..A953; REJANG
6156 0xA954, // A954..A95E; UNKNOWN
6157 0xA95F, // A95F ; REJANG
6158 0xA960, // A960..A97C; HANGUL
6159 0xA97D, // A97D..A97F; UNKNOWN
6160 0xA980, // A980..A9CD; JAVANESE
6161 0xA9CE, // A9CE ; UNKNOWN
6162 0xA9CF, // A9CF ; COMMON
6163 0xA9D0, // A9D0..A9D9; JAVANESE
6164 0xA9DA, // A9DA..A9DD; UNKNOWN
6165 0xA9DE, // A9DE..A9DF; JAVANESE
6166 0xA9E0, // A9E0..A9FE; MYANMAR
6167 0xA9FF, // A9FF ; UNKNOWN
6168 0xAA00, // AA00..AA36; CHAM
6169 0xAA37, // AA37..AA3F; UNKNOWN
6170 0xAA40, // AA40..AA4D; CHAM
6171 0xAA4E, // AA4E..AA4F; UNKNOWN
6172 0xAA50, // AA50..AA59; CHAM
6173 0xAA5A, // AA5A..AA5B; UNKNOWN
6174 0xAA5C, // AA5C..AA5F; CHAM
6175 0xAA60, // AA60..AA7F; MYANMAR
6176 0xAA80, // AA80..AAC2; TAI_VIET
6177 0xAAC3, // AAC3..AADA; UNKNOWN
6178 0xAADB, // AADB..AADF; TAI_VIET
6179 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6180 0xAAF7, // AAF7..AB00; UNKNOWN
6181 0xAB01, // AB01..AB06; ETHIOPIC
6182 0xAB07, // AB07..AB08; UNKNOWN
6183 0xAB09, // AB09..AB0E; ETHIOPIC
6184 0xAB0F, // AB0F..AB10; UNKNOWN
6185 0xAB11, // AB11..AB16; ETHIOPIC
6186 0xAB17, // AB17..AB1F; UNKNOWN
6187 0xAB20, // AB20..AB26; ETHIOPIC
6188 0xAB27, // AB27 ; UNKNOWN
6189 0xAB28, // AB28..AB2E; ETHIOPIC
6190 0xAB2F, // AB2F ; UNKNOWN
6191 0xAB30, // AB30..AB5A; LATIN
6192 0xAB5B, // AB5B ; COMMON
6193 0xAB5C, // AB5C..AB64; LATIN
6194 0xAB65, // AB65 ; GREEK
6195 0xAB66, // AB66..AB69; LATIN
6196 0xAB6A, // AB6A..AB6B; COMMON
6197 0xAB6C, // AB6C..AB6F; UNKNOWN
6198 0xAB70, // AB70..ABBF; CHEROKEE
6199 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6200 0xABEE, // ABEE..ABEF; UNKNOWN
6201 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6202 0xABFA, // ABFA..ABFF; UNKNOWN
6203 0xAC00, // AC00..D7A3; HANGUL
6204 0xD7A4, // D7A4..D7AF; UNKNOWN
6205 0xD7B0, // D7B0..D7C6; HANGUL
6206 0xD7C7, // D7C7..D7CA; UNKNOWN
6207 0xD7CB, // D7CB..D7FB; HANGUL
6208 0xD7FC, // D7FC..F8FF; UNKNOWN
6209 0xF900, // F900..FA6D; HAN
6210 0xFA6E, // FA6E..FA6F; UNKNOWN
6211 0xFA70, // FA70..FAD9; HAN
6212 0xFADA, // FADA..FAFF; UNKNOWN
6213 0xFB00, // FB00..FB06; LATIN
6214 0xFB07, // FB07..FB12; UNKNOWN
6215 0xFB13, // FB13..FB17; ARMENIAN
6216 0xFB18, // FB18..FB1C; UNKNOWN
6217 0xFB1D, // FB1D..FB36; HEBREW
6218 0xFB37, // FB37 ; UNKNOWN
6219 0xFB38, // FB38..FB3C; HEBREW
6220 0xFB3D, // FB3D ; UNKNOWN
6221 0xFB3E, // FB3E ; HEBREW
6222 0xFB3F, // FB3F ; UNKNOWN
6223 0xFB40, // FB40..FB41; HEBREW
6224 0xFB42, // FB42 ; UNKNOWN
6225 0xFB43, // FB43..FB44; HEBREW
6226 0xFB45, // FB45 ; UNKNOWN
6227 0xFB46, // FB46..FB4F; HEBREW
6228 0xFB50, // FB50..FBC2; ARABIC
6229 0xFBC3, // FBC3..FBD2; UNKNOWN
6230 0xFBD3, // FBD3..FD3D; ARABIC
6231 0xFD3E, // FD3E..FD3F; COMMON
6232 0xFD40, // FD40..FD8F; ARABIC
6233 0xFD90, // FD90..FD91; UNKNOWN
6234 0xFD92, // FD92..FDC7; ARABIC
6235 0xFDC8, // FDC8..FDCE; UNKNOWN
6236 0xFDCF, // FDCF ; ARABIC
6237 0xFDD0, // FDD0..FDEF; UNKNOWN
6238 0xFDF0, // FDF0..FDFF; ARABIC
6239 0xFE00, // FE00..FE0F; INHERITED
6240 0xFE10, // FE10..FE19; COMMON
6241 0xFE1A, // FE1A..FE1F; UNKNOWN
6242 0xFE20, // FE20..FE2D; INHERITED
6243 0xFE2E, // FE2E..FE2F; CYRILLIC
6244 0xFE30, // FE30..FE52; COMMON
6245 0xFE53, // FE53 ; UNKNOWN
6246 0xFE54, // FE54..FE66; COMMON
6247 0xFE67, // FE67 ; UNKNOWN
6248 0xFE68, // FE68..FE6B; COMMON
6249 0xFE6C, // FE6C..FE6F; UNKNOWN
6250 0xFE70, // FE70..FE74; ARABIC
6251 0xFE75, // FE75 ; UNKNOWN
6252 0xFE76, // FE76..FEFC; ARABIC
6253 0xFEFD, // FEFD..FEFE; UNKNOWN
6254 0xFEFF, // FEFF ; COMMON
6255 0xFF00, // FF00 ; UNKNOWN
6256 0xFF01, // FF01..FF20; COMMON
6257 0xFF21, // FF21..FF3A; LATIN
6258 0xFF3B, // FF3B..FF40; COMMON
6259 0xFF41, // FF41..FF5A; LATIN
6260 0xFF5B, // FF5B..FF65; COMMON
6261 0xFF66, // FF66..FF6F; KATAKANA
6262 0xFF70, // FF70 ; COMMON
6263 0xFF71, // FF71..FF9D; KATAKANA
6264 0xFF9E, // FF9E..FF9F; COMMON
6265 0xFFA0, // FFA0..FFBE; HANGUL
6266 0xFFBF, // FFBF..FFC1; UNKNOWN
6267 0xFFC2, // FFC2..FFC7; HANGUL
6268 0xFFC8, // FFC8..FFC9; UNKNOWN
6269 0xFFCA, // FFCA..FFCF; HANGUL
6270 0xFFD0, // FFD0..FFD1; UNKNOWN
6271 0xFFD2, // FFD2..FFD7; HANGUL
6272 0xFFD8, // FFD8..FFD9; UNKNOWN
6273 0xFFDA, // FFDA..FFDC; HANGUL
6274 0xFFDD, // FFDD..FFDF; UNKNOWN
6275 0xFFE0, // FFE0..FFE6; COMMON
6276 0xFFE7, // FFE7 ; UNKNOWN
6277 0xFFE8, // FFE8..FFEE; COMMON
6278 0xFFEF, // FFEF..FFF8; UNKNOWN
6279 0xFFF9, // FFF9..FFFD; COMMON
6280 0xFFFE, // FFFE..FFFF; UNKNOWN
6281 0x10000, // 10000..1000B; LINEAR_B
6282 0x1000C, // 1000C ; UNKNOWN
6283 0x1000D, // 1000D..10026; LINEAR_B
6284 0x10027, // 10027 ; UNKNOWN
6285 0x10028, // 10028..1003A; LINEAR_B
6286 0x1003B, // 1003B ; UNKNOWN
6287 0x1003C, // 1003C..1003D; LINEAR_B
6288 0x1003E, // 1003E ; UNKNOWN
6289 0x1003F, // 1003F..1004D; LINEAR_B
6290 0x1004E, // 1004E..1004F; UNKNOWN
6291 0x10050, // 10050..1005D; LINEAR_B
6292 0x1005E, // 1005E..1007F; UNKNOWN
6293 0x10080, // 10080..100FA; LINEAR_B
6294 0x100FB, // 100FB..100FF; UNKNOWN
6295 0x10100, // 10100..10102; COMMON
6296 0x10103, // 10103..10106; UNKNOWN
6297 0x10107, // 10107..10133; COMMON
6298 0x10134, // 10134..10136; UNKNOWN
6299 0x10137, // 10137..1013F; COMMON
6300 0x10140, // 10140..1018E; GREEK
6301 0x1018F, // 1018F ; UNKNOWN
6302 0x10190, // 10190..1019C; COMMON
6303 0x1019D, // 1019D..1019F; UNKNOWN
6304 0x101A0, // 101A0 ; GREEK
6305 0x101A1, // 101A1..101CF; UNKNOWN
6306 0x101D0, // 101D0..101FC; COMMON
6307 0x101FD, // 101FD ; INHERITED
6308 0x101FE, // 101FE..1027F; UNKNOWN
6309 0x10280, // 10280..1029C; LYCIAN
6310 0x1029D, // 1029D..1029F; UNKNOWN
6311 0x102A0, // 102A0..102D0; CARIAN
6312 0x102D1, // 102D1..102DF; UNKNOWN
6313 0x102E0, // 102E0 ; INHERITED
6314 0x102E1, // 102E1..102FB; COMMON
6315 0x102FC, // 102FC..102FF; UNKNOWN
6316 0x10300, // 10300..10323; OLD_ITALIC
6317 0x10324, // 10324..1032C; UNKNOWN
6318 0x1032D, // 1032D..1032F; OLD_ITALIC
6319 0x10330, // 10330..1034A; GOTHIC
6320 0x1034B, // 1034B..1034F; UNKNOWN
6321 0x10350, // 10350..1037A; OLD_PERMIC
6322 0x1037B, // 1037B..1037F; UNKNOWN
6323 0x10380, // 10380..1039D; UGARITIC
6324 0x1039E, // 1039E ; UNKNOWN
6325 0x1039F, // 1039F ; UGARITIC
6326 0x103A0, // 103A0..103C3; OLD_PERSIAN
6327 0x103C4, // 103C4..103C7; UNKNOWN
6328 0x103C8, // 103C8..103D5; OLD_PERSIAN
6329 0x103D6, // 103D6..103FF; UNKNOWN
6330 0x10400, // 10400..1044F; DESERET
6331 0x10450, // 10450..1047F; SHAVIAN
6332 0x10480, // 10480..1049D; OSMANYA
6333 0x1049E, // 1049E..1049F; UNKNOWN
6334 0x104A0, // 104A0..104A9; OSMANYA
6335 0x104AA, // 104AA..104AF; UNKNOWN
6336 0x104B0, // 104B0..104D3; OSAGE
6337 0x104D4, // 104D4..104D7; UNKNOWN
6338 0x104D8, // 104D8..104FB; OSAGE
6339 0x104FC, // 104FC..104FF; UNKNOWN
6340 0x10500, // 10500..10527; ELBASAN
6341 0x10528, // 10528..1052F; UNKNOWN
6342 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6343 0x10564, // 10564..1056E; UNKNOWN
6344 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6345 0x10570, // 10570..1057A; VITHKUQI
6346 0x1057B, // 1057B ; UNKNOWN
6347 0x1057C, // 1057C..1058A; VITHKUQI
6348 0x1058B, // 1058B ; UNKNOWN
6349 0x1058C, // 1058C..10592; VITHKUQI
6350 0x10593, // 10593 ; UNKNOWN
6351 0x10594, // 10594..10595; VITHKUQI
6352 0x10596, // 10596 ; UNKNOWN
6353 0x10597, // 10597..105A1; VITHKUQI
6354 0x105A2, // 105A2 ; UNKNOWN
6355 0x105A3, // 105A3..105B1; VITHKUQI
6356 0x105B2, // 105B2 ; UNKNOWN
6357 0x105B3, // 105B3..105B9; VITHKUQI
6358 0x105BA, // 105BA ; UNKNOWN
6359 0x105BB, // 105BB..105BC; VITHKUQI
6360 0x105BD, // 105BD..105FF; UNKNOWN
6361 0x10600, // 10600..10736; LINEAR_A
6362 0x10737, // 10737..1073F; UNKNOWN
6363 0x10740, // 10740..10755; LINEAR_A
6364 0x10756, // 10756..1075F; UNKNOWN
6365 0x10760, // 10760..10767; LINEAR_A
6366 0x10768, // 10768..1077F; UNKNOWN
6367 0x10780, // 10780..10785; LATIN
6368 0x10786, // 10786 ; UNKNOWN
6369 0x10787, // 10787..107B0; LATIN
6370 0x107B1, // 107B1 ; UNKNOWN
6371 0x107B2, // 107B2..107BA; LATIN
6372 0x107BB, // 107BB..107FF; UNKNOWN
6373 0x10800, // 10800..10805; CYPRIOT
6374 0x10806, // 10806..10807; UNKNOWN
6375 0x10808, // 10808 ; CYPRIOT
6376 0x10809, // 10809 ; UNKNOWN
6377 0x1080A, // 1080A..10835; CYPRIOT
6378 0x10836, // 10836 ; UNKNOWN
6379 0x10837, // 10837..10838; CYPRIOT
6380 0x10839, // 10839..1083B; UNKNOWN
6381 0x1083C, // 1083C ; CYPRIOT
6382 0x1083D, // 1083D..1083E; UNKNOWN
6383 0x1083F, // 1083F ; CYPRIOT
6384 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6385 0x10856, // 10856 ; UNKNOWN
6386 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6387 0x10860, // 10860..1087F; PALMYRENE
6388 0x10880, // 10880..1089E; NABATAEAN
6389 0x1089F, // 1089F..108A6; UNKNOWN
6390 0x108A7, // 108A7..108AF; NABATAEAN
6391 0x108B0, // 108B0..108DF; UNKNOWN
6392 0x108E0, // 108E0..108F2; HATRAN
6393 0x108F3, // 108F3 ; UNKNOWN
6394 0x108F4, // 108F4..108F5; HATRAN
6395 0x108F6, // 108F6..108FA; UNKNOWN
6396 0x108FB, // 108FB..108FF; HATRAN
6397 0x10900, // 10900..1091B; PHOENICIAN
6398 0x1091C, // 1091C..1091E; UNKNOWN
6399 0x1091F, // 1091F ; PHOENICIAN
6400 0x10920, // 10920..10939; LYDIAN
6401 0x1093A, // 1093A..1093E; UNKNOWN
6402 0x1093F, // 1093F ; LYDIAN
6403 0x10940, // 10940..1097F; UNKNOWN
6404 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6405 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6406 0x109B8, // 109B8..109BB; UNKNOWN
6407 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6408 0x109D0, // 109D0..109D1; UNKNOWN
6409 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6410 0x10A00, // 10A00..10A03; KHAROSHTHI
6411 0x10A04, // 10A04 ; UNKNOWN
6412 0x10A05, // 10A05..10A06; KHAROSHTHI
6413 0x10A07, // 10A07..10A0B; UNKNOWN
6414 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6415 0x10A14, // 10A14 ; UNKNOWN
6416 0x10A15, // 10A15..10A17; KHAROSHTHI
6417 0x10A18, // 10A18 ; UNKNOWN
6418 0x10A19, // 10A19..10A35; KHAROSHTHI
6419 0x10A36, // 10A36..10A37; UNKNOWN
6420 0x10A38, // 10A38..10A3A; KHAROSHTHI
6421 0x10A3B, // 10A3B..10A3E; UNKNOWN
6422 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6423 0x10A49, // 10A49..10A4F; UNKNOWN
6424 0x10A50, // 10A50..10A58; KHAROSHTHI
6425 0x10A59, // 10A59..10A5F; UNKNOWN
6426 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6427 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6428 0x10AA0, // 10AA0..10ABF; UNKNOWN
6429 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6430 0x10AE7, // 10AE7..10AEA; UNKNOWN
6431 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6432 0x10AF7, // 10AF7..10AFF; UNKNOWN
6433 0x10B00, // 10B00..10B35; AVESTAN
6434 0x10B36, // 10B36..10B38; UNKNOWN
6435 0x10B39, // 10B39..10B3F; AVESTAN
6436 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6437 0x10B56, // 10B56..10B57; UNKNOWN
6438 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6439 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6440 0x10B73, // 10B73..10B77; UNKNOWN
6441 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6442 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6443 0x10B92, // 10B92..10B98; UNKNOWN
6444 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6445 0x10B9D, // 10B9D..10BA8; UNKNOWN
6446 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6447 0x10BB0, // 10BB0..10BFF; UNKNOWN
6448 0x10C00, // 10C00..10C48; OLD_TURKIC
6449 0x10C49, // 10C49..10C7F; UNKNOWN
6450 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6451 0x10CB3, // 10CB3..10CBF; UNKNOWN
6452 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6453 0x10CF3, // 10CF3..10CF9; UNKNOWN
6454 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6455 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6456 0x10D28, // 10D28..10D2F; UNKNOWN
6457 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6458 0x10D3A, // 10D3A..10E5F; UNKNOWN
6459 0x10E60, // 10E60..10E7E; ARABIC
6460 0x10E7F, // 10E7F ; UNKNOWN
6461 0x10E80, // 10E80..10EA9; YEZIDI
6462 0x10EAA, // 10EAA ; UNKNOWN
6463 0x10EAB, // 10EAB..10EAD; YEZIDI
6464 0x10EAE, // 10EAE..10EAF; UNKNOWN
6465 0x10EB0, // 10EB0..10EB1; YEZIDI
6466 0x10EB2, // 10EB2..10EFC; UNKNOWN
6467 0x10EFD, // 10EFD..10EFF; ARABIC
6468 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6469 0x10F28, // 10F28..10F2F; UNKNOWN
6470 0x10F30, // 10F30..10F59; SOGDIAN
6471 0x10F5A, // 10F5A..10F6F; UNKNOWN
6472 0x10F70, // 10F70..10F89; OLD_UYGHUR
6473 0x10F8A, // 10F8A..10FAF; UNKNOWN
6474 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6475 0x10FCC, // 10FCC..10FDF; UNKNOWN
6476 0x10FE0, // 10FE0..10FF6; ELYMAIC
6477 0x10FF7, // 10FF7..10FFF; UNKNOWN
6478 0x11000, // 11000..1104D; BRAHMI
6479 0x1104E, // 1104E..11051; UNKNOWN
6480 0x11052, // 11052..11075; BRAHMI
6481 0x11076, // 11076..1107E; UNKNOWN
6482 0x1107F, // 1107F ; BRAHMI
6483 0x11080, // 11080..110C2; KAITHI
6484 0x110C3, // 110C3..110CC; UNKNOWN
6485 0x110CD, // 110CD ; KAITHI
6486 0x110CE, // 110CE..110CF; UNKNOWN
6487 0x110D0, // 110D0..110E8; SORA_SOMPENG
6488 0x110E9, // 110E9..110EF; UNKNOWN
6489 0x110F0, // 110F0..110F9; SORA_SOMPENG
6490 0x110FA, // 110FA..110FF; UNKNOWN
6491 0x11100, // 11100..11134; CHAKMA
6492 0x11135, // 11135 ; UNKNOWN
6493 0x11136, // 11136..11147; CHAKMA
6494 0x11148, // 11148..1114F; UNKNOWN
6495 0x11150, // 11150..11176; MAHAJANI
6496 0x11177, // 11177..1117F; UNKNOWN
6497 0x11180, // 11180..111DF; SHARADA
6498 0x111E0, // 111E0 ; UNKNOWN
6499 0x111E1, // 111E1..111F4; SINHALA
6500 0x111F5, // 111F5..111FF; UNKNOWN
6501 0x11200, // 11200..11211; KHOJKI
6502 0x11212, // 11212 ; UNKNOWN
6503 0x11213, // 11213..11241; KHOJKI
6504 0x11242, // 11242..1127F; UNKNOWN
6505 0x11280, // 11280..11286; MULTANI
6506 0x11287, // 11287 ; UNKNOWN
6507 0x11288, // 11288 ; MULTANI
6508 0x11289, // 11289 ; UNKNOWN
6509 0x1128A, // 1128A..1128D; MULTANI
6510 0x1128E, // 1128E ; UNKNOWN
6511 0x1128F, // 1128F..1129D; MULTANI
6512 0x1129E, // 1129E ; UNKNOWN
6513 0x1129F, // 1129F..112A9; MULTANI
6514 0x112AA, // 112AA..112AF; UNKNOWN
6515 0x112B0, // 112B0..112EA; KHUDAWADI
6516 0x112EB, // 112EB..112EF; UNKNOWN
6517 0x112F0, // 112F0..112F9; KHUDAWADI
6518 0x112FA, // 112FA..112FF; UNKNOWN
6519 0x11300, // 11300..11303; GRANTHA
6520 0x11304, // 11304 ; UNKNOWN
6521 0x11305, // 11305..1130C; GRANTHA
6522 0x1130D, // 1130D..1130E; UNKNOWN
6523 0x1130F, // 1130F..11310; GRANTHA
6524 0x11311, // 11311..11312; UNKNOWN
6525 0x11313, // 11313..11328; GRANTHA
6526 0x11329, // 11329 ; UNKNOWN
6527 0x1132A, // 1132A..11330; GRANTHA
6528 0x11331, // 11331 ; UNKNOWN
6529 0x11332, // 11332..11333; GRANTHA
6530 0x11334, // 11334 ; UNKNOWN
6531 0x11335, // 11335..11339; GRANTHA
6532 0x1133A, // 1133A ; UNKNOWN
6533 0x1133B, // 1133B ; INHERITED
6534 0x1133C, // 1133C..11344; GRANTHA
6535 0x11345, // 11345..11346; UNKNOWN
6536 0x11347, // 11347..11348; GRANTHA
6537 0x11349, // 11349..1134A; UNKNOWN
6538 0x1134B, // 1134B..1134D; GRANTHA
6539 0x1134E, // 1134E..1134F; UNKNOWN
6540 0x11350, // 11350 ; GRANTHA
6541 0x11351, // 11351..11356; UNKNOWN
6542 0x11357, // 11357 ; GRANTHA
6543 0x11358, // 11358..1135C; UNKNOWN
6544 0x1135D, // 1135D..11363; GRANTHA
6545 0x11364, // 11364..11365; UNKNOWN
6546 0x11366, // 11366..1136C; GRANTHA
6547 0x1136D, // 1136D..1136F; UNKNOWN
6548 0x11370, // 11370..11374; GRANTHA
6549 0x11375, // 11375..113FF; UNKNOWN
6550 0x11400, // 11400..1145B; NEWA
6551 0x1145C, // 1145C ; UNKNOWN
6552 0x1145D, // 1145D..11461; NEWA
6553 0x11462, // 11462..1147F; UNKNOWN
6554 0x11480, // 11480..114C7; TIRHUTA
6555 0x114C8, // 114C8..114CF; UNKNOWN
6556 0x114D0, // 114D0..114D9; TIRHUTA
6557 0x114DA, // 114DA..1157F; UNKNOWN
6558 0x11580, // 11580..115B5; SIDDHAM
6559 0x115B6, // 115B6..115B7; UNKNOWN
6560 0x115B8, // 115B8..115DD; SIDDHAM
6561 0x115DE, // 115DE..115FF; UNKNOWN
6562 0x11600, // 11600..11644; MODI
6563 0x11645, // 11645..1164F; UNKNOWN
6564 0x11650, // 11650..11659; MODI
6565 0x1165A, // 1165A..1165F; UNKNOWN
6566 0x11660, // 11660..1166C; MONGOLIAN
6567 0x1166D, // 1166D..1167F; UNKNOWN
6568 0x11680, // 11680..116B9; TAKRI
6569 0x116BA, // 116BA..116BF; UNKNOWN
6570 0x116C0, // 116C0..116C9; TAKRI
6571 0x116CA, // 116CA..116FF; UNKNOWN
6572 0x11700, // 11700..1171A; AHOM
6573 0x1171B, // 1171B..1171C; UNKNOWN
6574 0x1171D, // 1171D..1172B; AHOM
6575 0x1172C, // 1172C..1172F; UNKNOWN
6576 0x11730, // 11730..11746; AHOM
6577 0x11747, // 11747..117FF; UNKNOWN
6578 0x11800, // 11800..1183B; DOGRA
6579 0x1183C, // 1183C..1189F; UNKNOWN
6580 0x118A0, // 118A0..118F2; WARANG_CITI
6581 0x118F3, // 118F3..118FE; UNKNOWN
6582 0x118FF, // 118FF ; WARANG_CITI
6583 0x11900, // 11900..11906; DIVES_AKURU
6584 0x11907, // 11907..11908; UNKNOWN
6585 0x11909, // 11909 ; DIVES_AKURU
6586 0x1190A, // 1190A..1190B; UNKNOWN
6587 0x1190C, // 1190C..11913; DIVES_AKURU
6588 0x11914, // 11914 ; UNKNOWN
6589 0x11915, // 11915..11916; DIVES_AKURU
6590 0x11917, // 11917 ; UNKNOWN
6591 0x11918, // 11918..11935; DIVES_AKURU
6592 0x11936, // 11936 ; UNKNOWN
6593 0x11937, // 11937..11938; DIVES_AKURU
6594 0x11939, // 11939..1193A; UNKNOWN
6595 0x1193B, // 1193B..11946; DIVES_AKURU
6596 0x11947, // 11947..1194F; UNKNOWN
6597 0x11950, // 11950..11959; DIVES_AKURU
6598 0x1195A, // 1195A..1199F; UNKNOWN
6599 0x119A0, // 119A0..119A7; NANDINAGARI
6600 0x119A8, // 119A8..119A9; UNKNOWN
6601 0x119AA, // 119AA..119D7; NANDINAGARI
6602 0x119D8, // 119D8..119D9; UNKNOWN
6603 0x119DA, // 119DA..119E4; NANDINAGARI
6604 0x119E5, // 119E5..119FF; UNKNOWN
6605 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6606 0x11A48, // 11A48..11A4F; UNKNOWN
6607 0x11A50, // 11A50..11AA2; SOYOMBO
6608 0x11AA3, // 11AA3..11AAF; UNKNOWN
6609 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6610 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6611 0x11AF9, // 11AF9..11AFF; UNKNOWN
6612 0x11B00, // 11B00..11B09; DEVANAGARI
6613 0x11B0A, // 11B0A..11BFF; UNKNOWN
6614 0x11C00, // 11C00..11C08; BHAIKSUKI
6615 0x11C09, // 11C09 ; UNKNOWN
6616 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6617 0x11C37, // 11C37 ; UNKNOWN
6618 0x11C38, // 11C38..11C45; BHAIKSUKI
6619 0x11C46, // 11C46..11C4F; UNKNOWN
6620 0x11C50, // 11C50..11C6C; BHAIKSUKI
6621 0x11C6D, // 11C6D..11C6F; UNKNOWN
6622 0x11C70, // 11C70..11C8F; MARCHEN
6623 0x11C90, // 11C90..11C91; UNKNOWN
6624 0x11C92, // 11C92..11CA7; MARCHEN
6625 0x11CA8, // 11CA8 ; UNKNOWN
6626 0x11CA9, // 11CA9..11CB6; MARCHEN
6627 0x11CB7, // 11CB7..11CFF; UNKNOWN
6628 0x11D00, // 11D00..11D06; MASARAM_GONDI
6629 0x11D07, // 11D07 ; UNKNOWN
6630 0x11D08, // 11D08..11D09; MASARAM_GONDI
6631 0x11D0A, // 11D0A ; UNKNOWN
6632 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6633 0x11D37, // 11D37..11D39; UNKNOWN
6634 0x11D3A, // 11D3A ; MASARAM_GONDI
6635 0x11D3B, // 11D3B ; UNKNOWN
6636 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6637 0x11D3E, // 11D3E ; UNKNOWN
6638 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6639 0x11D48, // 11D48..11D4F; UNKNOWN
6640 0x11D50, // 11D50..11D59; MASARAM_GONDI
6641 0x11D5A, // 11D5A..11D5F; UNKNOWN
6642 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6643 0x11D66, // 11D66 ; UNKNOWN
6644 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6645 0x11D69, // 11D69 ; UNKNOWN
6646 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6647 0x11D8F, // 11D8F ; UNKNOWN
6648 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6649 0x11D92, // 11D92 ; UNKNOWN
6650 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6651 0x11D99, // 11D99..11D9F; UNKNOWN
6652 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6653 0x11DAA, // 11DAA..11EDF; UNKNOWN
6654 0x11EE0, // 11EE0..11EF8; MAKASAR
6655 0x11EF9, // 11EF9..11EFF; UNKNOWN
6656 0x11F00, // 11F00..11F10; KAWI
6657 0x11F11, // 11F11 ; UNKNOWN
6658 0x11F12, // 11F12..11F3A; KAWI
6659 0x11F3B, // 11F3B..11F3D; UNKNOWN
6660 0x11F3E, // 11F3E..11F59; KAWI
6661 0x11F5A, // 11F5A..11FAF; UNKNOWN
6662 0x11FB0, // 11FB0 ; LISU
6663 0x11FB1, // 11FB1..11FBF; UNKNOWN
6664 0x11FC0, // 11FC0..11FF1; TAMIL
6665 0x11FF2, // 11FF2..11FFE; UNKNOWN
6666 0x11FFF, // 11FFF ; TAMIL
6667 0x12000, // 12000..12399; CUNEIFORM
6668 0x1239A, // 1239A..123FF; UNKNOWN
6669 0x12400, // 12400..1246E; CUNEIFORM
6670 0x1246F, // 1246F ; UNKNOWN
6671 0x12470, // 12470..12474; CUNEIFORM
6672 0x12475, // 12475..1247F; UNKNOWN
6673 0x12480, // 12480..12543; CUNEIFORM
6674 0x12544, // 12544..12F8F; UNKNOWN
6675 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6676 0x12FF3, // 12FF3..12FFF; UNKNOWN
6677 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6678 0x13456, // 13456..143FF; UNKNOWN
6679 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6680 0x14647, // 14647..167FF; UNKNOWN
6681 0x16800, // 16800..16A38; BAMUM
6682 0x16A39, // 16A39..16A3F; UNKNOWN
6683 0x16A40, // 16A40..16A5E; MRO
6684 0x16A5F, // 16A5F ; UNKNOWN
6685 0x16A60, // 16A60..16A69; MRO
6686 0x16A6A, // 16A6A..16A6D; UNKNOWN
6687 0x16A6E, // 16A6E..16A6F; MRO
6688 0x16A70, // 16A70..16ABE; TANGSA
6689 0x16ABF, // 16ABF ; UNKNOWN
6690 0x16AC0, // 16AC0..16AC9; TANGSA
6691 0x16ACA, // 16ACA..16ACF; UNKNOWN
6692 0x16AD0, // 16AD0..16AED; BASSA_VAH
6693 0x16AEE, // 16AEE..16AEF; UNKNOWN
6694 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6695 0x16AF6, // 16AF6..16AFF; UNKNOWN
6696 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6697 0x16B46, // 16B46..16B4F; UNKNOWN
6698 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6699 0x16B5A, // 16B5A ; UNKNOWN
6700 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6701 0x16B62, // 16B62 ; UNKNOWN
6702 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6703 0x16B78, // 16B78..16B7C; UNKNOWN
6704 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6705 0x16B90, // 16B90..16E3F; UNKNOWN
6706 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6707 0x16E9B, // 16E9B..16EFF; UNKNOWN
6708 0x16F00, // 16F00..16F4A; MIAO
6709 0x16F4B, // 16F4B..16F4E; UNKNOWN
6710 0x16F4F, // 16F4F..16F87; MIAO
6711 0x16F88, // 16F88..16F8E; UNKNOWN
6712 0x16F8F, // 16F8F..16F9F; MIAO
6713 0x16FA0, // 16FA0..16FDF; UNKNOWN
6714 0x16FE0, // 16FE0 ; TANGUT
6715 0x16FE1, // 16FE1 ; NUSHU
6716 0x16FE2, // 16FE2..16FE3; HAN
6717 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
6718 0x16FE5, // 16FE5..16FEF; UNKNOWN
6719 0x16FF0, // 16FF0..16FF1; HAN
6720 0x16FF2, // 16FF2..16FFF; UNKNOWN
6721 0x17000, // 17000..187F7; TANGUT
6722 0x187F8, // 187F8..187FF; UNKNOWN
6723 0x18800, // 18800..18AFF; TANGUT
6724 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
6725 0x18CD6, // 18CD6..18CFF; UNKNOWN
6726 0x18D00, // 18D00..18D08; TANGUT
6727 0x18D09, // 18D09..1AFEF; UNKNOWN
6728 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
6729 0x1AFF4, // 1AFF4 ; UNKNOWN
6730 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
6731 0x1AFFC, // 1AFFC ; UNKNOWN
6732 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
6733 0x1AFFF, // 1AFFF ; UNKNOWN
6734 0x1B000, // 1B000 ; KATAKANA
6735 0x1B001, // 1B001..1B11F; HIRAGANA
6736 0x1B120, // 1B120..1B122; KATAKANA
6737 0x1B123, // 1B123..1B131; UNKNOWN
6738 0x1B132, // 1B132 ; HIRAGANA
6739 0x1B133, // 1B133..1B14F; UNKNOWN
6740 0x1B150, // 1B150..1B152; HIRAGANA
6741 0x1B153, // 1B153..1B154; UNKNOWN
6742 0x1B155, // 1B155 ; KATAKANA
6743 0x1B156, // 1B156..1B163; UNKNOWN
6744 0x1B164, // 1B164..1B167; KATAKANA
6745 0x1B168, // 1B168..1B16F; UNKNOWN
6746 0x1B170, // 1B170..1B2FB; NUSHU
6747 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6748 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6749 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6750 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6751 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6752 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6753 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6754 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6755 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6756 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6757 0x1BCA0, // 1BCA0..1BCA3; COMMON
6758 0x1BCA4, // 1BCA4..1CEFF; UNKNOWN
6759 0x1CF00, // 1CF00..1CF2D; INHERITED
6760 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
6761 0x1CF30, // 1CF30..1CF46; INHERITED
6762 0x1CF47, // 1CF47..1CF4F; UNKNOWN
6763 0x1CF50, // 1CF50..1CFC3; COMMON
6764 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
6765 0x1D000, // 1D000..1D0F5; COMMON
6766 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6767 0x1D100, // 1D100..1D126; COMMON
6768 0x1D127, // 1D127..1D128; UNKNOWN
6769 0x1D129, // 1D129..1D166; COMMON
6770 0x1D167, // 1D167..1D169; INHERITED
6771 0x1D16A, // 1D16A..1D17A; COMMON
6772 0x1D17B, // 1D17B..1D182; INHERITED
6773 0x1D183, // 1D183..1D184; COMMON
6774 0x1D185, // 1D185..1D18B; INHERITED
6775 0x1D18C, // 1D18C..1D1A9; COMMON
6776 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6777 0x1D1AE, // 1D1AE..1D1EA; COMMON
6778 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
6779 0x1D200, // 1D200..1D245; GREEK
6780 0x1D246, // 1D246..1D2BF; UNKNOWN
6781 0x1D2C0, // 1D2C0..1D2D3; COMMON
6782 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
6783 0x1D2E0, // 1D2E0..1D2F3; COMMON
6784 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6785 0x1D300, // 1D300..1D356; COMMON
6786 0x1D357, // 1D357..1D35F; UNKNOWN
6787 0x1D360, // 1D360..1D378; COMMON
6788 0x1D379, // 1D379..1D3FF; UNKNOWN
6789 0x1D400, // 1D400..1D454; COMMON
6790 0x1D455, // 1D455 ; UNKNOWN
6791 0x1D456, // 1D456..1D49C; COMMON
6792 0x1D49D, // 1D49D ; UNKNOWN
6793 0x1D49E, // 1D49E..1D49F; COMMON
6794 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
6795 0x1D4A2, // 1D4A2 ; COMMON
6796 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
6797 0x1D4A5, // 1D4A5..1D4A6; COMMON
6798 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
6799 0x1D4A9, // 1D4A9..1D4AC; COMMON
6800 0x1D4AD, // 1D4AD ; UNKNOWN
6801 0x1D4AE, // 1D4AE..1D4B9; COMMON
6802 0x1D4BA, // 1D4BA ; UNKNOWN
6803 0x1D4BB, // 1D4BB ; COMMON
6804 0x1D4BC, // 1D4BC ; UNKNOWN
6805 0x1D4BD, // 1D4BD..1D4C3; COMMON
6806 0x1D4C4, // 1D4C4 ; UNKNOWN
6807 0x1D4C5, // 1D4C5..1D505; COMMON
6808 0x1D506, // 1D506 ; UNKNOWN
6809 0x1D507, // 1D507..1D50A; COMMON
6810 0x1D50B, // 1D50B..1D50C; UNKNOWN
6811 0x1D50D, // 1D50D..1D514; COMMON
6812 0x1D515, // 1D515 ; UNKNOWN
6813 0x1D516, // 1D516..1D51C; COMMON
6814 0x1D51D, // 1D51D ; UNKNOWN
6815 0x1D51E, // 1D51E..1D539; COMMON
6816 0x1D53A, // 1D53A ; UNKNOWN
6817 0x1D53B, // 1D53B..1D53E; COMMON
6818 0x1D53F, // 1D53F ; UNKNOWN
6819 0x1D540, // 1D540..1D544; COMMON
6820 0x1D545, // 1D545 ; UNKNOWN
6821 0x1D546, // 1D546 ; COMMON
6822 0x1D547, // 1D547..1D549; UNKNOWN
6823 0x1D54A, // 1D54A..1D550; COMMON
6824 0x1D551, // 1D551 ; UNKNOWN
6825 0x1D552, // 1D552..1D6A5; COMMON
6826 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
6827 0x1D6A8, // 1D6A8..1D7CB; COMMON
6828 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
6829 0x1D7CE, // 1D7CE..1D7FF; COMMON
6830 0x1D800, // 1D800..1DA8B; SIGNWRITING
6831 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
6832 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
6833 0x1DAA0, // 1DAA0 ; UNKNOWN
6834 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
6835 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
6836 0x1DF00, // 1DF00..1DF1E; LATIN
6837 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
6838 0x1DF25, // 1DF25..1DF2A; LATIN
6839 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
6840 0x1E000, // 1E000..1E006; GLAGOLITIC
6841 0x1E007, // 1E007 ; UNKNOWN
6842 0x1E008, // 1E008..1E018; GLAGOLITIC
6843 0x1E019, // 1E019..1E01A; UNKNOWN
6844 0x1E01B, // 1E01B..1E021; GLAGOLITIC
6845 0x1E022, // 1E022 ; UNKNOWN
6846 0x1E023, // 1E023..1E024; GLAGOLITIC
6847 0x1E025, // 1E025 ; UNKNOWN
6848 0x1E026, // 1E026..1E02A; GLAGOLITIC
6849 0x1E02B, // 1E02B..1E02F; UNKNOWN
6850 0x1E030, // 1E030..1E06D; CYRILLIC
6851 0x1E06E, // 1E06E..1E08E; UNKNOWN
6852 0x1E08F, // 1E08F ; CYRILLIC
6853 0x1E090, // 1E090..1E0FF; UNKNOWN
6854 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
6855 0x1E12D, // 1E12D..1E12F; UNKNOWN
6856 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
6857 0x1E13E, // 1E13E..1E13F; UNKNOWN
6858 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
6859 0x1E14A, // 1E14A..1E14D; UNKNOWN
6860 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
6861 0x1E150, // 1E150..1E28F; UNKNOWN
6862 0x1E290, // 1E290..1E2AE; TOTO
6863 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
6864 0x1E2C0, // 1E2C0..1E2F9; WANCHO
6865 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
6866 0x1E2FF, // 1E2FF ; WANCHO
6867 0x1E300, // 1E300..1E4CF; UNKNOWN
6868 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
6869 0x1E4FA, // 1E4FA..1E7DF; UNKNOWN
6870 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
6871 0x1E7E7, // 1E7E7 ; UNKNOWN
6872 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
6873 0x1E7EC, // 1E7EC ; UNKNOWN
6874 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
6875 0x1E7EF, // 1E7EF ; UNKNOWN
6876 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
6877 0x1E7FF, // 1E7FF ; UNKNOWN
6878 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
6879 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
6880 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
6881 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
6882 0x1E900, // 1E900..1E94B; ADLAM
6883 0x1E94C, // 1E94C..1E94F; UNKNOWN
6884 0x1E950, // 1E950..1E959; ADLAM
6885 0x1E95A, // 1E95A..1E95D; UNKNOWN
6886 0x1E95E, // 1E95E..1E95F; ADLAM
6887 0x1E960, // 1E960..1EC70; UNKNOWN
6888 0x1EC71, // 1EC71..1ECB4; COMMON
6889 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
6890 0x1ED01, // 1ED01..1ED3D; COMMON
6891 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
6892 0x1EE00, // 1EE00..1EE03; ARABIC
6893 0x1EE04, // 1EE04 ; UNKNOWN
6894 0x1EE05, // 1EE05..1EE1F; ARABIC
6895 0x1EE20, // 1EE20 ; UNKNOWN
6896 0x1EE21, // 1EE21..1EE22; ARABIC
6897 0x1EE23, // 1EE23 ; UNKNOWN
6898 0x1EE24, // 1EE24 ; ARABIC
6899 0x1EE25, // 1EE25..1EE26; UNKNOWN
6900 0x1EE27, // 1EE27 ; ARABIC
6901 0x1EE28, // 1EE28 ; UNKNOWN
6902 0x1EE29, // 1EE29..1EE32; ARABIC
6903 0x1EE33, // 1EE33 ; UNKNOWN
6904 0x1EE34, // 1EE34..1EE37; ARABIC
6905 0x1EE38, // 1EE38 ; UNKNOWN
6906 0x1EE39, // 1EE39 ; ARABIC
6907 0x1EE3A, // 1EE3A ; UNKNOWN
6908 0x1EE3B, // 1EE3B ; ARABIC
6909 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
6910 0x1EE42, // 1EE42 ; ARABIC
6911 0x1EE43, // 1EE43..1EE46; UNKNOWN
6912 0x1EE47, // 1EE47 ; ARABIC
6913 0x1EE48, // 1EE48 ; UNKNOWN
6914 0x1EE49, // 1EE49 ; ARABIC
6915 0x1EE4A, // 1EE4A ; UNKNOWN
6916 0x1EE4B, // 1EE4B ; ARABIC
6917 0x1EE4C, // 1EE4C ; UNKNOWN
6918 0x1EE4D, // 1EE4D..1EE4F; ARABIC
6919 0x1EE50, // 1EE50 ; UNKNOWN
6920 0x1EE51, // 1EE51..1EE52; ARABIC
6921 0x1EE53, // 1EE53 ; UNKNOWN
6922 0x1EE54, // 1EE54 ; ARABIC
6923 0x1EE55, // 1EE55..1EE56; UNKNOWN
6924 0x1EE57, // 1EE57 ; ARABIC
6925 0x1EE58, // 1EE58 ; UNKNOWN
6926 0x1EE59, // 1EE59 ; ARABIC
6927 0x1EE5A, // 1EE5A ; UNKNOWN
6928 0x1EE5B, // 1EE5B ; ARABIC
6929 0x1EE5C, // 1EE5C ; UNKNOWN
6930 0x1EE5D, // 1EE5D ; ARABIC
6931 0x1EE5E, // 1EE5E ; UNKNOWN
6932 0x1EE5F, // 1EE5F ; ARABIC
6933 0x1EE60, // 1EE60 ; UNKNOWN
6934 0x1EE61, // 1EE61..1EE62; ARABIC
6935 0x1EE63, // 1EE63 ; UNKNOWN
6936 0x1EE64, // 1EE64 ; ARABIC
6937 0x1EE65, // 1EE65..1EE66; UNKNOWN
6938 0x1EE67, // 1EE67..1EE6A; ARABIC
6939 0x1EE6B, // 1EE6B ; UNKNOWN
6940 0x1EE6C, // 1EE6C..1EE72; ARABIC
6941 0x1EE73, // 1EE73 ; UNKNOWN
6942 0x1EE74, // 1EE74..1EE77; ARABIC
6943 0x1EE78, // 1EE78 ; UNKNOWN
6944 0x1EE79, // 1EE79..1EE7C; ARABIC
6945 0x1EE7D, // 1EE7D ; UNKNOWN
6946 0x1EE7E, // 1EE7E ; ARABIC
6947 0x1EE7F, // 1EE7F ; UNKNOWN
6948 0x1EE80, // 1EE80..1EE89; ARABIC
6949 0x1EE8A, // 1EE8A ; UNKNOWN
6950 0x1EE8B, // 1EE8B..1EE9B; ARABIC
6951 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
6952 0x1EEA1, // 1EEA1..1EEA3; ARABIC
6953 0x1EEA4, // 1EEA4 ; UNKNOWN
6954 0x1EEA5, // 1EEA5..1EEA9; ARABIC
6955 0x1EEAA, // 1EEAA ; UNKNOWN
6956 0x1EEAB, // 1EEAB..1EEBB; ARABIC
6957 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
6958 0x1EEF0, // 1EEF0..1EEF1; ARABIC
6959 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
6960 0x1F000, // 1F000..1F02B; COMMON
6961 0x1F02C, // 1F02C..1F02F; UNKNOWN
6962 0x1F030, // 1F030..1F093; COMMON
6963 0x1F094, // 1F094..1F09F; UNKNOWN
6964 0x1F0A0, // 1F0A0..1F0AE; COMMON
6965 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
6966 0x1F0B1, // 1F0B1..1F0BF; COMMON
6967 0x1F0C0, // 1F0C0 ; UNKNOWN
6968 0x1F0C1, // 1F0C1..1F0CF; COMMON
6969 0x1F0D0, // 1F0D0 ; UNKNOWN
6970 0x1F0D1, // 1F0D1..1F0F5; COMMON
6971 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
6972 0x1F100, // 1F100..1F1AD; COMMON
6973 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
6974 0x1F1E6, // 1F1E6..1F1FF; COMMON
6975 0x1F200, // 1F200 ; HIRAGANA
6976 0x1F201, // 1F201..1F202; COMMON
6977 0x1F203, // 1F203..1F20F; UNKNOWN
6978 0x1F210, // 1F210..1F23B; COMMON
6979 0x1F23C, // 1F23C..1F23F; UNKNOWN
6980 0x1F240, // 1F240..1F248; COMMON
6981 0x1F249, // 1F249..1F24F; UNKNOWN
6982 0x1F250, // 1F250..1F251; COMMON
6983 0x1F252, // 1F252..1F25F; UNKNOWN
6984 0x1F260, // 1F260..1F265; COMMON
6985 0x1F266, // 1F266..1F2FF; UNKNOWN
6986 0x1F300, // 1F300..1F6D7; COMMON
6987 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN
6988 0x1F6DC, // 1F6DC..1F6EC; COMMON
6989 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
6990 0x1F6F0, // 1F6F0..1F6FC; COMMON
6991 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
6992 0x1F700, // 1F700..1F776; COMMON
6993 0x1F777, // 1F777..1F77A; UNKNOWN
6994 0x1F77B, // 1F77B..1F7D9; COMMON
6995 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
6996 0x1F7E0, // 1F7E0..1F7EB; COMMON
6997 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
6998 0x1F7F0, // 1F7F0 ; COMMON
6999 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7000 0x1F800, // 1F800..1F80B; COMMON
7001 0x1F80C, // 1F80C..1F80F; UNKNOWN
7002 0x1F810, // 1F810..1F847; COMMON
7003 0x1F848, // 1F848..1F84F; UNKNOWN
7004 0x1F850, // 1F850..1F859; COMMON
7005 0x1F85A, // 1F85A..1F85F; UNKNOWN
7006 0x1F860, // 1F860..1F887; COMMON
7007 0x1F888, // 1F888..1F88F; UNKNOWN
7008 0x1F890, // 1F890..1F8AD; COMMON
7009 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7010 0x1F8B0, // 1F8B0..1F8B1; COMMON
7011 0x1F8B2, // 1F8B2..1F8FF; UNKNOWN
7012 0x1F900, // 1F900..1FA53; COMMON
7013 0x1FA54, // 1FA54..1FA5F; UNKNOWN
7014 0x1FA60, // 1FA60..1FA6D; COMMON
7015 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7016 0x1FA70, // 1FA70..1FA7C; COMMON
7017 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7018 0x1FA80, // 1FA80..1FA88; COMMON
7019 0x1FA89, // 1FA89..1FA8F; UNKNOWN
7020 0x1FA90, // 1FA90..1FABD; COMMON
7021 0x1FABE, // 1FABE ; UNKNOWN
7022 0x1FABF, // 1FABF..1FAC5; COMMON
7023 0x1FAC6, // 1FAC6..1FACD; UNKNOWN
7024 0x1FACE, // 1FACE..1FADB; COMMON
7025 0x1FADC, // 1FADC..1FADF; UNKNOWN
7026 0x1FAE0, // 1FAE0..1FAE8; COMMON
7027 0x1FAE9, // 1FAE9..1FAEF; UNKNOWN
7028 0x1FAF0, // 1FAF0..1FAF8; COMMON
7029 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7030 0x1FB00, // 1FB00..1FB92; COMMON
7031 0x1FB93, // 1FB93 ; UNKNOWN
7032 0x1FB94, // 1FB94..1FBCA; COMMON
7033 0x1FBCB, // 1FBCB..1FBEF; UNKNOWN
7034 0x1FBF0, // 1FBF0..1FBF9; COMMON
7035 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN
7036 0x20000, // 20000..2A6DF; HAN
7037 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7038 0x2A700, // 2A700..2B739; HAN
7039 0x2B73A, // 2B73A..2B73F; UNKNOWN
7040 0x2B740, // 2B740..2B81D; HAN
7041 0x2B81E, // 2B81E..2B81F; UNKNOWN
7042 0x2B820, // 2B820..2CEA1; HAN
7043 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
7044 0x2CEB0, // 2CEB0..2EBE0; HAN
7045 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7046 0x2EBF0, // 2EBF0..2EE5D; HAN
7047 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7048 0x2F800, // 2F800..2FA1D; HAN
7049 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7050 0x30000, // 30000..3134A; HAN
7051 0x3134B, // 3134B..3134F; UNKNOWN
7052 0x31350, // 31350..323AF; HAN
7053 0x323B0, // 323B0..E0000; UNKNOWN
7054 0xE0001, // E0001 ; COMMON
7055 0xE0002, // E0002..E001F; UNKNOWN
7056 0xE0020, // E0020..E007F; COMMON
7057 0xE0080, // E0080..E00FF; UNKNOWN
7058 0xE0100, // E0100..E01EF; INHERITED
7059 0xE01F0, // E01F0..10FFFF; UNKNOWN
7060 };
7061
7062 private static final UnicodeScript[] scripts = {
7063 COMMON, // 0000..0040
7064 LATIN, // 0041..005A
7065 COMMON, // 005B..0060
7066 LATIN, // 0061..007A
7067 COMMON, // 007B..00A9
7068 LATIN, // 00AA
7069 COMMON, // 00AB..00B9
7070 LATIN, // 00BA
7071 COMMON, // 00BB..00BF
7072 LATIN, // 00C0..00D6
7073 COMMON, // 00D7
7074 LATIN, // 00D8..00F6
7075 COMMON, // 00F7
7076 LATIN, // 00F8..02B8
7077 COMMON, // 02B9..02DF
7078 LATIN, // 02E0..02E4
7079 COMMON, // 02E5..02E9
7080 BOPOMOFO, // 02EA..02EB
7081 COMMON, // 02EC..02FF
7082 INHERITED, // 0300..036F
7083 GREEK, // 0370..0373
7084 COMMON, // 0374
7085 GREEK, // 0375..0377
7086 UNKNOWN, // 0378..0379
7087 GREEK, // 037A..037D
7088 COMMON, // 037E
7089 GREEK, // 037F
7090 UNKNOWN, // 0380..0383
7091 GREEK, // 0384
7092 COMMON, // 0385
7093 GREEK, // 0386
7094 COMMON, // 0387
7095 GREEK, // 0388..038A
7096 UNKNOWN, // 038B
7097 GREEK, // 038C
7098 UNKNOWN, // 038D
7099 GREEK, // 038E..03A1
7100 UNKNOWN, // 03A2
7101 GREEK, // 03A3..03E1
7102 COPTIC, // 03E2..03EF
7103 GREEK, // 03F0..03FF
7104 CYRILLIC, // 0400..0484
7105 INHERITED, // 0485..0486
7106 CYRILLIC, // 0487..052F
7107 UNKNOWN, // 0530
7108 ARMENIAN, // 0531..0556
7109 UNKNOWN, // 0557..0558
7110 ARMENIAN, // 0559..058A
7111 UNKNOWN, // 058B..058C
7112 ARMENIAN, // 058D..058F
7113 UNKNOWN, // 0590
7114 HEBREW, // 0591..05C7
7115 UNKNOWN, // 05C8..05CF
7116 HEBREW, // 05D0..05EA
7117 UNKNOWN, // 05EB..05EE
7118 HEBREW, // 05EF..05F4
7119 UNKNOWN, // 05F5..05FF
7120 ARABIC, // 0600..0604
7121 COMMON, // 0605
7122 ARABIC, // 0606..060B
7123 COMMON, // 060C
7124 ARABIC, // 060D..061A
7125 COMMON, // 061B
7126 ARABIC, // 061C..061E
7127 COMMON, // 061F
7128 ARABIC, // 0620..063F
7129 COMMON, // 0640
7130 ARABIC, // 0641..064A
7131 INHERITED, // 064B..0655
7132 ARABIC, // 0656..066F
7133 INHERITED, // 0670
7134 ARABIC, // 0671..06DC
7135 COMMON, // 06DD
7136 ARABIC, // 06DE..06FF
7137 SYRIAC, // 0700..070D
7138 UNKNOWN, // 070E
7139 SYRIAC, // 070F..074A
7140 UNKNOWN, // 074B..074C
7141 SYRIAC, // 074D..074F
7142 ARABIC, // 0750..077F
7143 THAANA, // 0780..07B1
7144 UNKNOWN, // 07B2..07BF
7145 NKO, // 07C0..07FA
7146 UNKNOWN, // 07FB..07FC
7147 NKO, // 07FD..07FF
7148 SAMARITAN, // 0800..082D
7149 UNKNOWN, // 082E..082F
7150 SAMARITAN, // 0830..083E
7151 UNKNOWN, // 083F
7152 MANDAIC, // 0840..085B
7153 UNKNOWN, // 085C..085D
7154 MANDAIC, // 085E
7155 UNKNOWN, // 085F
7156 SYRIAC, // 0860..086A
7157 UNKNOWN, // 086B..086F
7158 ARABIC, // 0870..088E
7159 UNKNOWN, // 088F
7160 ARABIC, // 0890..0891
7161 UNKNOWN, // 0892..0897
7162 ARABIC, // 0898..08E1
7163 COMMON, // 08E2
7164 ARABIC, // 08E3..08FF
7165 DEVANAGARI, // 0900..0950
7166 INHERITED, // 0951..0954
7167 DEVANAGARI, // 0955..0963
7168 COMMON, // 0964..0965
7169 DEVANAGARI, // 0966..097F
7170 BENGALI, // 0980..0983
7171 UNKNOWN, // 0984
7172 BENGALI, // 0985..098C
7173 UNKNOWN, // 098D..098E
7174 BENGALI, // 098F..0990
7175 UNKNOWN, // 0991..0992
7176 BENGALI, // 0993..09A8
7177 UNKNOWN, // 09A9
7178 BENGALI, // 09AA..09B0
7179 UNKNOWN, // 09B1
7180 BENGALI, // 09B2
7181 UNKNOWN, // 09B3..09B5
7182 BENGALI, // 09B6..09B9
7183 UNKNOWN, // 09BA..09BB
7184 BENGALI, // 09BC..09C4
7185 UNKNOWN, // 09C5..09C6
7186 BENGALI, // 09C7..09C8
7187 UNKNOWN, // 09C9..09CA
7188 BENGALI, // 09CB..09CE
7189 UNKNOWN, // 09CF..09D6
7190 BENGALI, // 09D7
7191 UNKNOWN, // 09D8..09DB
7192 BENGALI, // 09DC..09DD
7193 UNKNOWN, // 09DE
7194 BENGALI, // 09DF..09E3
7195 UNKNOWN, // 09E4..09E5
7196 BENGALI, // 09E6..09FE
7197 UNKNOWN, // 09FF..0A00
7198 GURMUKHI, // 0A01..0A03
7199 UNKNOWN, // 0A04
7200 GURMUKHI, // 0A05..0A0A
7201 UNKNOWN, // 0A0B..0A0E
7202 GURMUKHI, // 0A0F..0A10
7203 UNKNOWN, // 0A11..0A12
7204 GURMUKHI, // 0A13..0A28
7205 UNKNOWN, // 0A29
7206 GURMUKHI, // 0A2A..0A30
7207 UNKNOWN, // 0A31
7208 GURMUKHI, // 0A32..0A33
7209 UNKNOWN, // 0A34
7210 GURMUKHI, // 0A35..0A36
7211 UNKNOWN, // 0A37
7212 GURMUKHI, // 0A38..0A39
7213 UNKNOWN, // 0A3A..0A3B
7214 GURMUKHI, // 0A3C
7215 UNKNOWN, // 0A3D
7216 GURMUKHI, // 0A3E..0A42
7217 UNKNOWN, // 0A43..0A46
7218 GURMUKHI, // 0A47..0A48
7219 UNKNOWN, // 0A49..0A4A
7220 GURMUKHI, // 0A4B..0A4D
7221 UNKNOWN, // 0A4E..0A50
7222 GURMUKHI, // 0A51
7223 UNKNOWN, // 0A52..0A58
7224 GURMUKHI, // 0A59..0A5C
7225 UNKNOWN, // 0A5D
7226 GURMUKHI, // 0A5E
7227 UNKNOWN, // 0A5F..0A65
7228 GURMUKHI, // 0A66..0A76
7229 UNKNOWN, // 0A77..0A80
7230 GUJARATI, // 0A81..0A83
7231 UNKNOWN, // 0A84
7232 GUJARATI, // 0A85..0A8D
7233 UNKNOWN, // 0A8E
7234 GUJARATI, // 0A8F..0A91
7235 UNKNOWN, // 0A92
7236 GUJARATI, // 0A93..0AA8
7237 UNKNOWN, // 0AA9
7238 GUJARATI, // 0AAA..0AB0
7239 UNKNOWN, // 0AB1
7240 GUJARATI, // 0AB2..0AB3
7241 UNKNOWN, // 0AB4
7242 GUJARATI, // 0AB5..0AB9
7243 UNKNOWN, // 0ABA..0ABB
7244 GUJARATI, // 0ABC..0AC5
7245 UNKNOWN, // 0AC6
7246 GUJARATI, // 0AC7..0AC9
7247 UNKNOWN, // 0ACA
7248 GUJARATI, // 0ACB..0ACD
7249 UNKNOWN, // 0ACE..0ACF
7250 GUJARATI, // 0AD0
7251 UNKNOWN, // 0AD1..0ADF
7252 GUJARATI, // 0AE0..0AE3
7253 UNKNOWN, // 0AE4..0AE5
7254 GUJARATI, // 0AE6..0AF1
7255 UNKNOWN, // 0AF2..0AF8
7256 GUJARATI, // 0AF9..0AFF
7257 UNKNOWN, // 0B00
7258 ORIYA, // 0B01..0B03
7259 UNKNOWN, // 0B04
7260 ORIYA, // 0B05..0B0C
7261 UNKNOWN, // 0B0D..0B0E
7262 ORIYA, // 0B0F..0B10
7263 UNKNOWN, // 0B11..0B12
7264 ORIYA, // 0B13..0B28
7265 UNKNOWN, // 0B29
7266 ORIYA, // 0B2A..0B30
7267 UNKNOWN, // 0B31
7268 ORIYA, // 0B32..0B33
7269 UNKNOWN, // 0B34
7270 ORIYA, // 0B35..0B39
7271 UNKNOWN, // 0B3A..0B3B
7272 ORIYA, // 0B3C..0B44
7273 UNKNOWN, // 0B45..0B46
7274 ORIYA, // 0B47..0B48
7275 UNKNOWN, // 0B49..0B4A
7276 ORIYA, // 0B4B..0B4D
7277 UNKNOWN, // 0B4E..0B54
7278 ORIYA, // 0B55..0B57
7279 UNKNOWN, // 0B58..0B5B
7280 ORIYA, // 0B5C..0B5D
7281 UNKNOWN, // 0B5E
7282 ORIYA, // 0B5F..0B63
7283 UNKNOWN, // 0B64..0B65
7284 ORIYA, // 0B66..0B77
7285 UNKNOWN, // 0B78..0B81
7286 TAMIL, // 0B82..0B83
7287 UNKNOWN, // 0B84
7288 TAMIL, // 0B85..0B8A
7289 UNKNOWN, // 0B8B..0B8D
7290 TAMIL, // 0B8E..0B90
7291 UNKNOWN, // 0B91
7292 TAMIL, // 0B92..0B95
7293 UNKNOWN, // 0B96..0B98
7294 TAMIL, // 0B99..0B9A
7295 UNKNOWN, // 0B9B
7296 TAMIL, // 0B9C
7297 UNKNOWN, // 0B9D
7298 TAMIL, // 0B9E..0B9F
7299 UNKNOWN, // 0BA0..0BA2
7300 TAMIL, // 0BA3..0BA4
7301 UNKNOWN, // 0BA5..0BA7
7302 TAMIL, // 0BA8..0BAA
7303 UNKNOWN, // 0BAB..0BAD
7304 TAMIL, // 0BAE..0BB9
7305 UNKNOWN, // 0BBA..0BBD
7306 TAMIL, // 0BBE..0BC2
7307 UNKNOWN, // 0BC3..0BC5
7308 TAMIL, // 0BC6..0BC8
7309 UNKNOWN, // 0BC9
7310 TAMIL, // 0BCA..0BCD
7311 UNKNOWN, // 0BCE..0BCF
7312 TAMIL, // 0BD0
7313 UNKNOWN, // 0BD1..0BD6
7314 TAMIL, // 0BD7
7315 UNKNOWN, // 0BD8..0BE5
7316 TAMIL, // 0BE6..0BFA
7317 UNKNOWN, // 0BFB..0BFF
7318 TELUGU, // 0C00..0C0C
7319 UNKNOWN, // 0C0D
7320 TELUGU, // 0C0E..0C10
7321 UNKNOWN, // 0C11
7322 TELUGU, // 0C12..0C28
7323 UNKNOWN, // 0C29
7324 TELUGU, // 0C2A..0C39
7325 UNKNOWN, // 0C3A..0C3B
7326 TELUGU, // 0C3C..0C44
7327 UNKNOWN, // 0C45
7328 TELUGU, // 0C46..0C48
7329 UNKNOWN, // 0C49
7330 TELUGU, // 0C4A..0C4D
7331 UNKNOWN, // 0C4E..0C54
7332 TELUGU, // 0C55..0C56
7333 UNKNOWN, // 0C57
7334 TELUGU, // 0C58..0C5A
7335 UNKNOWN, // 0C5B..0C5C
7336 TELUGU, // 0C5D
7337 UNKNOWN, // 0C5E..0C5F
7338 TELUGU, // 0C60..0C63
7339 UNKNOWN, // 0C64..0C65
7340 TELUGU, // 0C66..0C6F
7341 UNKNOWN, // 0C70..0C76
7342 TELUGU, // 0C77..0C7F
7343 KANNADA, // 0C80..0C8C
7344 UNKNOWN, // 0C8D
7345 KANNADA, // 0C8E..0C90
7346 UNKNOWN, // 0C91
7347 KANNADA, // 0C92..0CA8
7348 UNKNOWN, // 0CA9
7349 KANNADA, // 0CAA..0CB3
7350 UNKNOWN, // 0CB4
7351 KANNADA, // 0CB5..0CB9
7352 UNKNOWN, // 0CBA..0CBB
7353 KANNADA, // 0CBC..0CC4
7354 UNKNOWN, // 0CC5
7355 KANNADA, // 0CC6..0CC8
7356 UNKNOWN, // 0CC9
7357 KANNADA, // 0CCA..0CCD
7358 UNKNOWN, // 0CCE..0CD4
7359 KANNADA, // 0CD5..0CD6
7360 UNKNOWN, // 0CD7..0CDC
7361 KANNADA, // 0CDD..0CDE
7362 UNKNOWN, // 0CDF
7363 KANNADA, // 0CE0..0CE3
7364 UNKNOWN, // 0CE4..0CE5
7365 KANNADA, // 0CE6..0CEF
7366 UNKNOWN, // 0CF0
7367 KANNADA, // 0CF1..0CF3
7368 UNKNOWN, // 0CF4..0CFF
7369 MALAYALAM, // 0D00..0D0C
7370 UNKNOWN, // 0D0D
7371 MALAYALAM, // 0D0E..0D10
7372 UNKNOWN, // 0D11
7373 MALAYALAM, // 0D12..0D44
7374 UNKNOWN, // 0D45
7375 MALAYALAM, // 0D46..0D48
7376 UNKNOWN, // 0D49
7377 MALAYALAM, // 0D4A..0D4F
7378 UNKNOWN, // 0D50..0D53
7379 MALAYALAM, // 0D54..0D63
7380 UNKNOWN, // 0D64..0D65
7381 MALAYALAM, // 0D66..0D7F
7382 UNKNOWN, // 0D80
7383 SINHALA, // 0D81..0D83
7384 UNKNOWN, // 0D84
7385 SINHALA, // 0D85..0D96
7386 UNKNOWN, // 0D97..0D99
7387 SINHALA, // 0D9A..0DB1
7388 UNKNOWN, // 0DB2
7389 SINHALA, // 0DB3..0DBB
7390 UNKNOWN, // 0DBC
7391 SINHALA, // 0DBD
7392 UNKNOWN, // 0DBE..0DBF
7393 SINHALA, // 0DC0..0DC6
7394 UNKNOWN, // 0DC7..0DC9
7395 SINHALA, // 0DCA
7396 UNKNOWN, // 0DCB..0DCE
7397 SINHALA, // 0DCF..0DD4
7398 UNKNOWN, // 0DD5
7399 SINHALA, // 0DD6
7400 UNKNOWN, // 0DD7
7401 SINHALA, // 0DD8..0DDF
7402 UNKNOWN, // 0DE0..0DE5
7403 SINHALA, // 0DE6..0DEF
7404 UNKNOWN, // 0DF0..0DF1
7405 SINHALA, // 0DF2..0DF4
7406 UNKNOWN, // 0DF5..0E00
7407 THAI, // 0E01..0E3A
7408 UNKNOWN, // 0E3B..0E3E
7409 COMMON, // 0E3F
7410 THAI, // 0E40..0E5B
7411 UNKNOWN, // 0E5C..0E80
7412 LAO, // 0E81..0E82
7413 UNKNOWN, // 0E83
7414 LAO, // 0E84
7415 UNKNOWN, // 0E85
7416 LAO, // 0E86..0E8A
7417 UNKNOWN, // 0E8B
7418 LAO, // 0E8C..0EA3
7419 UNKNOWN, // 0EA4
7420 LAO, // 0EA5
7421 UNKNOWN, // 0EA6
7422 LAO, // 0EA7..0EBD
7423 UNKNOWN, // 0EBE..0EBF
7424 LAO, // 0EC0..0EC4
7425 UNKNOWN, // 0EC5
7426 LAO, // 0EC6
7427 UNKNOWN, // 0EC7
7428 LAO, // 0EC8..0ECE
7429 UNKNOWN, // 0ECF
7430 LAO, // 0ED0..0ED9
7431 UNKNOWN, // 0EDA..0EDB
7432 LAO, // 0EDC..0EDF
7433 UNKNOWN, // 0EE0..0EFF
7434 TIBETAN, // 0F00..0F47
7435 UNKNOWN, // 0F48
7436 TIBETAN, // 0F49..0F6C
7437 UNKNOWN, // 0F6D..0F70
7438 TIBETAN, // 0F71..0F97
7439 UNKNOWN, // 0F98
7440 TIBETAN, // 0F99..0FBC
7441 UNKNOWN, // 0FBD
7442 TIBETAN, // 0FBE..0FCC
7443 UNKNOWN, // 0FCD
7444 TIBETAN, // 0FCE..0FD4
7445 COMMON, // 0FD5..0FD8
7446 TIBETAN, // 0FD9..0FDA
7447 UNKNOWN, // 0FDB..0FFF
7448 MYANMAR, // 1000..109F
7449 GEORGIAN, // 10A0..10C5
7450 UNKNOWN, // 10C6
7451 GEORGIAN, // 10C7
7452 UNKNOWN, // 10C8..10CC
7453 GEORGIAN, // 10CD
7454 UNKNOWN, // 10CE..10CF
7455 GEORGIAN, // 10D0..10FA
7456 COMMON, // 10FB
7457 GEORGIAN, // 10FC..10FF
7458 HANGUL, // 1100..11FF
7459 ETHIOPIC, // 1200..1248
7460 UNKNOWN, // 1249
7461 ETHIOPIC, // 124A..124D
7462 UNKNOWN, // 124E..124F
7463 ETHIOPIC, // 1250..1256
7464 UNKNOWN, // 1257
7465 ETHIOPIC, // 1258
7466 UNKNOWN, // 1259
7467 ETHIOPIC, // 125A..125D
7468 UNKNOWN, // 125E..125F
7469 ETHIOPIC, // 1260..1288
7470 UNKNOWN, // 1289
7471 ETHIOPIC, // 128A..128D
7472 UNKNOWN, // 128E..128F
7473 ETHIOPIC, // 1290..12B0
7474 UNKNOWN, // 12B1
7475 ETHIOPIC, // 12B2..12B5
7476 UNKNOWN, // 12B6..12B7
7477 ETHIOPIC, // 12B8..12BE
7478 UNKNOWN, // 12BF
7479 ETHIOPIC, // 12C0
7480 UNKNOWN, // 12C1
7481 ETHIOPIC, // 12C2..12C5
7482 UNKNOWN, // 12C6..12C7
7483 ETHIOPIC, // 12C8..12D6
7484 UNKNOWN, // 12D7
7485 ETHIOPIC, // 12D8..1310
7486 UNKNOWN, // 1311
7487 ETHIOPIC, // 1312..1315
7488 UNKNOWN, // 1316..1317
7489 ETHIOPIC, // 1318..135A
7490 UNKNOWN, // 135B..135C
7491 ETHIOPIC, // 135D..137C
7492 UNKNOWN, // 137D..137F
7493 ETHIOPIC, // 1380..1399
7494 UNKNOWN, // 139A..139F
7495 CHEROKEE, // 13A0..13F5
7496 UNKNOWN, // 13F6..13F7
7497 CHEROKEE, // 13F8..13FD
7498 UNKNOWN, // 13FE..13FF
7499 CANADIAN_ABORIGINAL, // 1400..167F
7500 OGHAM, // 1680..169C
7501 UNKNOWN, // 169D..169F
7502 RUNIC, // 16A0..16EA
7503 COMMON, // 16EB..16ED
7504 RUNIC, // 16EE..16F8
7505 UNKNOWN, // 16F9..16FF
7506 TAGALOG, // 1700..1715
7507 UNKNOWN, // 1716..171E
7508 TAGALOG, // 171F
7509 HANUNOO, // 1720..1734
7510 COMMON, // 1735..1736
7511 UNKNOWN, // 1737..173F
7512 BUHID, // 1740..1753
7513 UNKNOWN, // 1754..175F
7514 TAGBANWA, // 1760..176C
7515 UNKNOWN, // 176D
7516 TAGBANWA, // 176E..1770
7517 UNKNOWN, // 1771
7518 TAGBANWA, // 1772..1773
7519 UNKNOWN, // 1774..177F
7520 KHMER, // 1780..17DD
7521 UNKNOWN, // 17DE..17DF
7522 KHMER, // 17E0..17E9
7523 UNKNOWN, // 17EA..17EF
7524 KHMER, // 17F0..17F9
7525 UNKNOWN, // 17FA..17FF
7526 MONGOLIAN, // 1800..1801
7527 COMMON, // 1802..1803
7528 MONGOLIAN, // 1804
7529 COMMON, // 1805
7530 MONGOLIAN, // 1806..1819
7531 UNKNOWN, // 181A..181F
7532 MONGOLIAN, // 1820..1878
7533 UNKNOWN, // 1879..187F
7534 MONGOLIAN, // 1880..18AA
7535 UNKNOWN, // 18AB..18AF
7536 CANADIAN_ABORIGINAL, // 18B0..18F5
7537 UNKNOWN, // 18F6..18FF
7538 LIMBU, // 1900..191E
7539 UNKNOWN, // 191F
7540 LIMBU, // 1920..192B
7541 UNKNOWN, // 192C..192F
7542 LIMBU, // 1930..193B
7543 UNKNOWN, // 193C..193F
7544 LIMBU, // 1940
7545 UNKNOWN, // 1941..1943
7546 LIMBU, // 1944..194F
7547 TAI_LE, // 1950..196D
7548 UNKNOWN, // 196E..196F
7549 TAI_LE, // 1970..1974
7550 UNKNOWN, // 1975..197F
7551 NEW_TAI_LUE, // 1980..19AB
7552 UNKNOWN, // 19AC..19AF
7553 NEW_TAI_LUE, // 19B0..19C9
7554 UNKNOWN, // 19CA..19CF
7555 NEW_TAI_LUE, // 19D0..19DA
7556 UNKNOWN, // 19DB..19DD
7557 NEW_TAI_LUE, // 19DE..19DF
7558 KHMER, // 19E0..19FF
7559 BUGINESE, // 1A00..1A1B
7560 UNKNOWN, // 1A1C..1A1D
7561 BUGINESE, // 1A1E..1A1F
7562 TAI_THAM, // 1A20..1A5E
7563 UNKNOWN, // 1A5F
7564 TAI_THAM, // 1A60..1A7C
7565 UNKNOWN, // 1A7D..1A7E
7566 TAI_THAM, // 1A7F..1A89
7567 UNKNOWN, // 1A8A..1A8F
7568 TAI_THAM, // 1A90..1A99
7569 UNKNOWN, // 1A9A..1A9F
7570 TAI_THAM, // 1AA0..1AAD
7571 UNKNOWN, // 1AAE..1AAF
7572 INHERITED, // 1AB0..1ACE
7573 UNKNOWN, // 1ACF..1AFF
7574 BALINESE, // 1B00..1B4C
7575 UNKNOWN, // 1B4D..1B4F
7576 BALINESE, // 1B50..1B7E
7577 UNKNOWN, // 1B7F
7578 SUNDANESE, // 1B80..1BBF
7579 BATAK, // 1BC0..1BF3
7580 UNKNOWN, // 1BF4..1BFB
7581 BATAK, // 1BFC..1BFF
7582 LEPCHA, // 1C00..1C37
7583 UNKNOWN, // 1C38..1C3A
7584 LEPCHA, // 1C3B..1C49
7585 UNKNOWN, // 1C4A..1C4C
7586 LEPCHA, // 1C4D..1C4F
7587 OL_CHIKI, // 1C50..1C7F
7588 CYRILLIC, // 1C80..1C88
7589 UNKNOWN, // 1C89..1C8F
7590 GEORGIAN, // 1C90..1CBA
7591 UNKNOWN, // 1CBB..1CBC
7592 GEORGIAN, // 1CBD..1CBF
7593 SUNDANESE, // 1CC0..1CC7
7594 UNKNOWN, // 1CC8..1CCF
7595 INHERITED, // 1CD0..1CD2
7596 COMMON, // 1CD3
7597 INHERITED, // 1CD4..1CE0
7598 COMMON, // 1CE1
7599 INHERITED, // 1CE2..1CE8
7600 COMMON, // 1CE9..1CEC
7601 INHERITED, // 1CED
7602 COMMON, // 1CEE..1CF3
7603 INHERITED, // 1CF4
7604 COMMON, // 1CF5..1CF7
7605 INHERITED, // 1CF8..1CF9
7606 COMMON, // 1CFA
7607 UNKNOWN, // 1CFB..1CFF
7608 LATIN, // 1D00..1D25
7609 GREEK, // 1D26..1D2A
7610 CYRILLIC, // 1D2B
7611 LATIN, // 1D2C..1D5C
7612 GREEK, // 1D5D..1D61
7613 LATIN, // 1D62..1D65
7614 GREEK, // 1D66..1D6A
7615 LATIN, // 1D6B..1D77
7616 CYRILLIC, // 1D78
7617 LATIN, // 1D79..1DBE
7618 GREEK, // 1DBF
7619 INHERITED, // 1DC0..1DFF
7620 LATIN, // 1E00..1EFF
7621 GREEK, // 1F00..1F15
7622 UNKNOWN, // 1F16..1F17
7623 GREEK, // 1F18..1F1D
7624 UNKNOWN, // 1F1E..1F1F
7625 GREEK, // 1F20..1F45
7626 UNKNOWN, // 1F46..1F47
7627 GREEK, // 1F48..1F4D
7628 UNKNOWN, // 1F4E..1F4F
7629 GREEK, // 1F50..1F57
7630 UNKNOWN, // 1F58
7631 GREEK, // 1F59
7632 UNKNOWN, // 1F5A
7633 GREEK, // 1F5B
7634 UNKNOWN, // 1F5C
7635 GREEK, // 1F5D
7636 UNKNOWN, // 1F5E
7637 GREEK, // 1F5F..1F7D
7638 UNKNOWN, // 1F7E..1F7F
7639 GREEK, // 1F80..1FB4
7640 UNKNOWN, // 1FB5
7641 GREEK, // 1FB6..1FC4
7642 UNKNOWN, // 1FC5
7643 GREEK, // 1FC6..1FD3
7644 UNKNOWN, // 1FD4..1FD5
7645 GREEK, // 1FD6..1FDB
7646 UNKNOWN, // 1FDC
7647 GREEK, // 1FDD..1FEF
7648 UNKNOWN, // 1FF0..1FF1
7649 GREEK, // 1FF2..1FF4
7650 UNKNOWN, // 1FF5
7651 GREEK, // 1FF6..1FFE
7652 UNKNOWN, // 1FFF
7653 COMMON, // 2000..200B
7654 INHERITED, // 200C..200D
7655 COMMON, // 200E..2064
7656 UNKNOWN, // 2065
7657 COMMON, // 2066..2070
7658 LATIN, // 2071
7659 UNKNOWN, // 2072..2073
7660 COMMON, // 2074..207E
7661 LATIN, // 207F
7662 COMMON, // 2080..208E
7663 UNKNOWN, // 208F
7664 LATIN, // 2090..209C
7665 UNKNOWN, // 209D..209F
7666 COMMON, // 20A0..20C0
7667 UNKNOWN, // 20C1..20CF
7668 INHERITED, // 20D0..20F0
7669 UNKNOWN, // 20F1..20FF
7670 COMMON, // 2100..2125
7671 GREEK, // 2126
7672 COMMON, // 2127..2129
7673 LATIN, // 212A..212B
7674 COMMON, // 212C..2131
7675 LATIN, // 2132
7676 COMMON, // 2133..214D
7677 LATIN, // 214E
7678 COMMON, // 214F..215F
7679 LATIN, // 2160..2188
7680 COMMON, // 2189..218B
7681 UNKNOWN, // 218C..218F
7682 COMMON, // 2190..2426
7683 UNKNOWN, // 2427..243F
7684 COMMON, // 2440..244A
7685 UNKNOWN, // 244B..245F
7686 COMMON, // 2460..27FF
7687 BRAILLE, // 2800..28FF
7688 COMMON, // 2900..2B73
7689 UNKNOWN, // 2B74..2B75
7690 COMMON, // 2B76..2B95
7691 UNKNOWN, // 2B96
7692 COMMON, // 2B97..2BFF
7693 GLAGOLITIC, // 2C00..2C5F
7694 LATIN, // 2C60..2C7F
7695 COPTIC, // 2C80..2CF3
7696 UNKNOWN, // 2CF4..2CF8
7697 COPTIC, // 2CF9..2CFF
7698 GEORGIAN, // 2D00..2D25
7699 UNKNOWN, // 2D26
7700 GEORGIAN, // 2D27
7701 UNKNOWN, // 2D28..2D2C
7702 GEORGIAN, // 2D2D
7703 UNKNOWN, // 2D2E..2D2F
7704 TIFINAGH, // 2D30..2D67
7705 UNKNOWN, // 2D68..2D6E
7706 TIFINAGH, // 2D6F..2D70
7707 UNKNOWN, // 2D71..2D7E
7708 TIFINAGH, // 2D7F
7709 ETHIOPIC, // 2D80..2D96
7710 UNKNOWN, // 2D97..2D9F
7711 ETHIOPIC, // 2DA0..2DA6
7712 UNKNOWN, // 2DA7
7713 ETHIOPIC, // 2DA8..2DAE
7714 UNKNOWN, // 2DAF
7715 ETHIOPIC, // 2DB0..2DB6
7716 UNKNOWN, // 2DB7
7717 ETHIOPIC, // 2DB8..2DBE
7718 UNKNOWN, // 2DBF
7719 ETHIOPIC, // 2DC0..2DC6
7720 UNKNOWN, // 2DC7
7721 ETHIOPIC, // 2DC8..2DCE
7722 UNKNOWN, // 2DCF
7723 ETHIOPIC, // 2DD0..2DD6
7724 UNKNOWN, // 2DD7
7725 ETHIOPIC, // 2DD8..2DDE
7726 UNKNOWN, // 2DDF
7727 CYRILLIC, // 2DE0..2DFF
7728 COMMON, // 2E00..2E5D
7729 UNKNOWN, // 2E5E..2E7F
7730 HAN, // 2E80..2E99
7731 UNKNOWN, // 2E9A
7732 HAN, // 2E9B..2EF3
7733 UNKNOWN, // 2EF4..2EFF
7734 HAN, // 2F00..2FD5
7735 UNKNOWN, // 2FD6..2FEF
7736 COMMON, // 2FF0..3004
7737 HAN, // 3005
7738 COMMON, // 3006
7739 HAN, // 3007
7740 COMMON, // 3008..3020
7741 HAN, // 3021..3029
7742 INHERITED, // 302A..302D
7743 HANGUL, // 302E..302F
7744 COMMON, // 3030..3037
7745 HAN, // 3038..303B
7746 COMMON, // 303C..303F
7747 UNKNOWN, // 3040
7748 HIRAGANA, // 3041..3096
7749 UNKNOWN, // 3097..3098
7750 INHERITED, // 3099..309A
7751 COMMON, // 309B..309C
7752 HIRAGANA, // 309D..309F
7753 COMMON, // 30A0
7754 KATAKANA, // 30A1..30FA
7755 COMMON, // 30FB..30FC
7756 KATAKANA, // 30FD..30FF
7757 UNKNOWN, // 3100..3104
7758 BOPOMOFO, // 3105..312F
7759 UNKNOWN, // 3130
7760 HANGUL, // 3131..318E
7761 UNKNOWN, // 318F
7762 COMMON, // 3190..319F
7763 BOPOMOFO, // 31A0..31BF
7764 COMMON, // 31C0..31E3
7765 UNKNOWN, // 31E4..31EE
7766 COMMON, // 31EF
7767 KATAKANA, // 31F0..31FF
7768 HANGUL, // 3200..321E
7769 UNKNOWN, // 321F
7770 COMMON, // 3220..325F
7771 HANGUL, // 3260..327E
7772 COMMON, // 327F..32CF
7773 KATAKANA, // 32D0..32FE
7774 COMMON, // 32FF
7775 KATAKANA, // 3300..3357
7776 COMMON, // 3358..33FF
7777 HAN, // 3400..4DBF
7778 COMMON, // 4DC0..4DFF
7779 HAN, // 4E00..9FFF
7780 YI, // A000..A48C
7781 UNKNOWN, // A48D..A48F
7782 YI, // A490..A4C6
7783 UNKNOWN, // A4C7..A4CF
7784 LISU, // A4D0..A4FF
7785 VAI, // A500..A62B
7786 UNKNOWN, // A62C..A63F
7787 CYRILLIC, // A640..A69F
7788 BAMUM, // A6A0..A6F7
7789 UNKNOWN, // A6F8..A6FF
7790 COMMON, // A700..A721
7791 LATIN, // A722..A787
7792 COMMON, // A788..A78A
7793 LATIN, // A78B..A7CA
7794 UNKNOWN, // A7CB..A7CF
7795 LATIN, // A7D0..A7D1
7796 UNKNOWN, // A7D2
7797 LATIN, // A7D3
7798 UNKNOWN, // A7D4
7799 LATIN, // A7D5..A7D9
7800 UNKNOWN, // A7DA..A7F1
7801 LATIN, // A7F2..A7FF
7802 SYLOTI_NAGRI, // A800..A82C
7803 UNKNOWN, // A82D..A82F
7804 COMMON, // A830..A839
7805 UNKNOWN, // A83A..A83F
7806 PHAGS_PA, // A840..A877
7807 UNKNOWN, // A878..A87F
7808 SAURASHTRA, // A880..A8C5
7809 UNKNOWN, // A8C6..A8CD
7810 SAURASHTRA, // A8CE..A8D9
7811 UNKNOWN, // A8DA..A8DF
7812 DEVANAGARI, // A8E0..A8FF
7813 KAYAH_LI, // A900..A92D
7814 COMMON, // A92E
7815 KAYAH_LI, // A92F
7816 REJANG, // A930..A953
7817 UNKNOWN, // A954..A95E
7818 REJANG, // A95F
7819 HANGUL, // A960..A97C
7820 UNKNOWN, // A97D..A97F
7821 JAVANESE, // A980..A9CD
7822 UNKNOWN, // A9CE
7823 COMMON, // A9CF
7824 JAVANESE, // A9D0..A9D9
7825 UNKNOWN, // A9DA..A9DD
7826 JAVANESE, // A9DE..A9DF
7827 MYANMAR, // A9E0..A9FE
7828 UNKNOWN, // A9FF
7829 CHAM, // AA00..AA36
7830 UNKNOWN, // AA37..AA3F
7831 CHAM, // AA40..AA4D
7832 UNKNOWN, // AA4E..AA4F
7833 CHAM, // AA50..AA59
7834 UNKNOWN, // AA5A..AA5B
7835 CHAM, // AA5C..AA5F
7836 MYANMAR, // AA60..AA7F
7837 TAI_VIET, // AA80..AAC2
7838 UNKNOWN, // AAC3..AADA
7839 TAI_VIET, // AADB..AADF
7840 MEETEI_MAYEK, // AAE0..AAF6
7841 UNKNOWN, // AAF7..AB00
7842 ETHIOPIC, // AB01..AB06
7843 UNKNOWN, // AB07..AB08
7844 ETHIOPIC, // AB09..AB0E
7845 UNKNOWN, // AB0F..AB10
7846 ETHIOPIC, // AB11..AB16
7847 UNKNOWN, // AB17..AB1F
7848 ETHIOPIC, // AB20..AB26
7849 UNKNOWN, // AB27
7850 ETHIOPIC, // AB28..AB2E
7851 UNKNOWN, // AB2F
7852 LATIN, // AB30..AB5A
7853 COMMON, // AB5B
7854 LATIN, // AB5C..AB64
7855 GREEK, // AB65
7856 LATIN, // AB66..AB69
7857 COMMON, // AB6A..AB6B
7858 UNKNOWN, // AB6C..AB6F
7859 CHEROKEE, // AB70..ABBF
7860 MEETEI_MAYEK, // ABC0..ABED
7861 UNKNOWN, // ABEE..ABEF
7862 MEETEI_MAYEK, // ABF0..ABF9
7863 UNKNOWN, // ABFA..ABFF
7864 HANGUL, // AC00..D7A3
7865 UNKNOWN, // D7A4..D7AF
7866 HANGUL, // D7B0..D7C6
7867 UNKNOWN, // D7C7..D7CA
7868 HANGUL, // D7CB..D7FB
7869 UNKNOWN, // D7FC..F8FF
7870 HAN, // F900..FA6D
7871 UNKNOWN, // FA6E..FA6F
7872 HAN, // FA70..FAD9
7873 UNKNOWN, // FADA..FAFF
7874 LATIN, // FB00..FB06
7875 UNKNOWN, // FB07..FB12
7876 ARMENIAN, // FB13..FB17
7877 UNKNOWN, // FB18..FB1C
7878 HEBREW, // FB1D..FB36
7879 UNKNOWN, // FB37
7880 HEBREW, // FB38..FB3C
7881 UNKNOWN, // FB3D
7882 HEBREW, // FB3E
7883 UNKNOWN, // FB3F
7884 HEBREW, // FB40..FB41
7885 UNKNOWN, // FB42
7886 HEBREW, // FB43..FB44
7887 UNKNOWN, // FB45
7888 HEBREW, // FB46..FB4F
7889 ARABIC, // FB50..FBC2
7890 UNKNOWN, // FBC3..FBD2
7891 ARABIC, // FBD3..FD3D
7892 COMMON, // FD3E..FD3F
7893 ARABIC, // FD40..FD8F
7894 UNKNOWN, // FD90..FD91
7895 ARABIC, // FD92..FDC7
7896 UNKNOWN, // FDC8..FDCE
7897 ARABIC, // FDCF
7898 UNKNOWN, // FDD0..FDEF
7899 ARABIC, // FDF0..FDFF
7900 INHERITED, // FE00..FE0F
7901 COMMON, // FE10..FE19
7902 UNKNOWN, // FE1A..FE1F
7903 INHERITED, // FE20..FE2D
7904 CYRILLIC, // FE2E..FE2F
7905 COMMON, // FE30..FE52
7906 UNKNOWN, // FE53
7907 COMMON, // FE54..FE66
7908 UNKNOWN, // FE67
7909 COMMON, // FE68..FE6B
7910 UNKNOWN, // FE6C..FE6F
7911 ARABIC, // FE70..FE74
7912 UNKNOWN, // FE75
7913 ARABIC, // FE76..FEFC
7914 UNKNOWN, // FEFD..FEFE
7915 COMMON, // FEFF
7916 UNKNOWN, // FF00
7917 COMMON, // FF01..FF20
7918 LATIN, // FF21..FF3A
7919 COMMON, // FF3B..FF40
7920 LATIN, // FF41..FF5A
7921 COMMON, // FF5B..FF65
7922 KATAKANA, // FF66..FF6F
7923 COMMON, // FF70
7924 KATAKANA, // FF71..FF9D
7925 COMMON, // FF9E..FF9F
7926 HANGUL, // FFA0..FFBE
7927 UNKNOWN, // FFBF..FFC1
7928 HANGUL, // FFC2..FFC7
7929 UNKNOWN, // FFC8..FFC9
7930 HANGUL, // FFCA..FFCF
7931 UNKNOWN, // FFD0..FFD1
7932 HANGUL, // FFD2..FFD7
7933 UNKNOWN, // FFD8..FFD9
7934 HANGUL, // FFDA..FFDC
7935 UNKNOWN, // FFDD..FFDF
7936 COMMON, // FFE0..FFE6
7937 UNKNOWN, // FFE7
7938 COMMON, // FFE8..FFEE
7939 UNKNOWN, // FFEF..FFF8
7940 COMMON, // FFF9..FFFD
7941 UNKNOWN, // FFFE..FFFF
7942 LINEAR_B, // 10000..1000B
7943 UNKNOWN, // 1000C
7944 LINEAR_B, // 1000D..10026
7945 UNKNOWN, // 10027
7946 LINEAR_B, // 10028..1003A
7947 UNKNOWN, // 1003B
7948 LINEAR_B, // 1003C..1003D
7949 UNKNOWN, // 1003E
7950 LINEAR_B, // 1003F..1004D
7951 UNKNOWN, // 1004E..1004F
7952 LINEAR_B, // 10050..1005D
7953 UNKNOWN, // 1005E..1007F
7954 LINEAR_B, // 10080..100FA
7955 UNKNOWN, // 100FB..100FF
7956 COMMON, // 10100..10102
7957 UNKNOWN, // 10103..10106
7958 COMMON, // 10107..10133
7959 UNKNOWN, // 10134..10136
7960 COMMON, // 10137..1013F
7961 GREEK, // 10140..1018E
7962 UNKNOWN, // 1018F
7963 COMMON, // 10190..1019C
7964 UNKNOWN, // 1019D..1019F
7965 GREEK, // 101A0
7966 UNKNOWN, // 101A1..101CF
7967 COMMON, // 101D0..101FC
7968 INHERITED, // 101FD
7969 UNKNOWN, // 101FE..1027F
7970 LYCIAN, // 10280..1029C
7971 UNKNOWN, // 1029D..1029F
7972 CARIAN, // 102A0..102D0
7973 UNKNOWN, // 102D1..102DF
7974 INHERITED, // 102E0
7975 COMMON, // 102E1..102FB
7976 UNKNOWN, // 102FC..102FF
7977 OLD_ITALIC, // 10300..10323
7978 UNKNOWN, // 10324..1032C
7979 OLD_ITALIC, // 1032D..1032F
7980 GOTHIC, // 10330..1034A
7981 UNKNOWN, // 1034B..1034F
7982 OLD_PERMIC, // 10350..1037A
7983 UNKNOWN, // 1037B..1037F
7984 UGARITIC, // 10380..1039D
7985 UNKNOWN, // 1039E
7986 UGARITIC, // 1039F
7987 OLD_PERSIAN, // 103A0..103C3
7988 UNKNOWN, // 103C4..103C7
7989 OLD_PERSIAN, // 103C8..103D5
7990 UNKNOWN, // 103D6..103FF
7991 DESERET, // 10400..1044F
7992 SHAVIAN, // 10450..1047F
7993 OSMANYA, // 10480..1049D
7994 UNKNOWN, // 1049E..1049F
7995 OSMANYA, // 104A0..104A9
7996 UNKNOWN, // 104AA..104AF
7997 OSAGE, // 104B0..104D3
7998 UNKNOWN, // 104D4..104D7
7999 OSAGE, // 104D8..104FB
8000 UNKNOWN, // 104FC..104FF
8001 ELBASAN, // 10500..10527
8002 UNKNOWN, // 10528..1052F
8003 CAUCASIAN_ALBANIAN, // 10530..10563
8004 UNKNOWN, // 10564..1056E
8005 CAUCASIAN_ALBANIAN, // 1056F
8006 VITHKUQI, // 10570..1057A
8007 UNKNOWN, // 1057B
8008 VITHKUQI, // 1057C..1058A
8009 UNKNOWN, // 1058B
8010 VITHKUQI, // 1058C..10592
8011 UNKNOWN, // 10593
8012 VITHKUQI, // 10594..10595
8013 UNKNOWN, // 10596
8014 VITHKUQI, // 10597..105A1
8015 UNKNOWN, // 105A2
8016 VITHKUQI, // 105A3..105B1
8017 UNKNOWN, // 105B2
8018 VITHKUQI, // 105B3..105B9
8019 UNKNOWN, // 105BA
8020 VITHKUQI, // 105BB..105BC
8021 UNKNOWN, // 105BD..105FF
8022 LINEAR_A, // 10600..10736
8023 UNKNOWN, // 10737..1073F
8024 LINEAR_A, // 10740..10755
8025 UNKNOWN, // 10756..1075F
8026 LINEAR_A, // 10760..10767
8027 UNKNOWN, // 10768..1077F
8028 LATIN, // 10780..10785
8029 UNKNOWN, // 10786
8030 LATIN, // 10787..107B0
8031 UNKNOWN, // 107B1
8032 LATIN, // 107B2..107BA
8033 UNKNOWN, // 107BB..107FF
8034 CYPRIOT, // 10800..10805
8035 UNKNOWN, // 10806..10807
8036 CYPRIOT, // 10808
8037 UNKNOWN, // 10809
8038 CYPRIOT, // 1080A..10835
8039 UNKNOWN, // 10836
8040 CYPRIOT, // 10837..10838
8041 UNKNOWN, // 10839..1083B
8042 CYPRIOT, // 1083C
8043 UNKNOWN, // 1083D..1083E
8044 CYPRIOT, // 1083F
8045 IMPERIAL_ARAMAIC, // 10840..10855
8046 UNKNOWN, // 10856
8047 IMPERIAL_ARAMAIC, // 10857..1085F
8048 PALMYRENE, // 10860..1087F
8049 NABATAEAN, // 10880..1089E
8050 UNKNOWN, // 1089F..108A6
8051 NABATAEAN, // 108A7..108AF
8052 UNKNOWN, // 108B0..108DF
8053 HATRAN, // 108E0..108F2
8054 UNKNOWN, // 108F3
8055 HATRAN, // 108F4..108F5
8056 UNKNOWN, // 108F6..108FA
8057 HATRAN, // 108FB..108FF
8058 PHOENICIAN, // 10900..1091B
8059 UNKNOWN, // 1091C..1091E
8060 PHOENICIAN, // 1091F
8061 LYDIAN, // 10920..10939
8062 UNKNOWN, // 1093A..1093E
8063 LYDIAN, // 1093F
8064 UNKNOWN, // 10940..1097F
8065 MEROITIC_HIEROGLYPHS, // 10980..1099F
8066 MEROITIC_CURSIVE, // 109A0..109B7
8067 UNKNOWN, // 109B8..109BB
8068 MEROITIC_CURSIVE, // 109BC..109CF
8069 UNKNOWN, // 109D0..109D1
8070 MEROITIC_CURSIVE, // 109D2..109FF
8071 KHAROSHTHI, // 10A00..10A03
8072 UNKNOWN, // 10A04
8073 KHAROSHTHI, // 10A05..10A06
8074 UNKNOWN, // 10A07..10A0B
8075 KHAROSHTHI, // 10A0C..10A13
8076 UNKNOWN, // 10A14
8077 KHAROSHTHI, // 10A15..10A17
8078 UNKNOWN, // 10A18
8079 KHAROSHTHI, // 10A19..10A35
8080 UNKNOWN, // 10A36..10A37
8081 KHAROSHTHI, // 10A38..10A3A
8082 UNKNOWN, // 10A3B..10A3E
8083 KHAROSHTHI, // 10A3F..10A48
8084 UNKNOWN, // 10A49..10A4F
8085 KHAROSHTHI, // 10A50..10A58
8086 UNKNOWN, // 10A59..10A5F
8087 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8088 OLD_NORTH_ARABIAN, // 10A80..10A9F
8089 UNKNOWN, // 10AA0..10ABF
8090 MANICHAEAN, // 10AC0..10AE6
8091 UNKNOWN, // 10AE7..10AEA
8092 MANICHAEAN, // 10AEB..10AF6
8093 UNKNOWN, // 10AF7..10AFF
8094 AVESTAN, // 10B00..10B35
8095 UNKNOWN, // 10B36..10B38
8096 AVESTAN, // 10B39..10B3F
8097 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8098 UNKNOWN, // 10B56..10B57
8099 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8100 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8101 UNKNOWN, // 10B73..10B77
8102 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8103 PSALTER_PAHLAVI, // 10B80..10B91
8104 UNKNOWN, // 10B92..10B98
8105 PSALTER_PAHLAVI, // 10B99..10B9C
8106 UNKNOWN, // 10B9D..10BA8
8107 PSALTER_PAHLAVI, // 10BA9..10BAF
8108 UNKNOWN, // 10BB0..10BFF
8109 OLD_TURKIC, // 10C00..10C48
8110 UNKNOWN, // 10C49..10C7F
8111 OLD_HUNGARIAN, // 10C80..10CB2
8112 UNKNOWN, // 10CB3..10CBF
8113 OLD_HUNGARIAN, // 10CC0..10CF2
8114 UNKNOWN, // 10CF3..10CF9
8115 OLD_HUNGARIAN, // 10CFA..10CFF
8116 HANIFI_ROHINGYA, // 10D00..10D27
8117 UNKNOWN, // 10D28..10D2F
8118 HANIFI_ROHINGYA, // 10D30..10D39
8119 UNKNOWN, // 10D3A..10E5F
8120 ARABIC, // 10E60..10E7E
8121 UNKNOWN, // 10E7F
8122 YEZIDI, // 10E80..10EA9
8123 UNKNOWN, // 10EAA
8124 YEZIDI, // 10EAB..10EAD
8125 UNKNOWN, // 10EAE..10EAF
8126 YEZIDI, // 10EB0..10EB1
8127 UNKNOWN, // 10EB2..10EFC
8128 ARABIC, // 10EFD..10EFF
8129 OLD_SOGDIAN, // 10F00..10F27
8130 UNKNOWN, // 10F28..10F2F
8131 SOGDIAN, // 10F30..10F59
8132 UNKNOWN, // 10F5A..10F6F
8133 OLD_UYGHUR, // 10F70..10F89
8134 UNKNOWN, // 10F8A..10FAF
8135 CHORASMIAN, // 10FB0..10FCB
8136 UNKNOWN, // 10FCC..10FDF
8137 ELYMAIC, // 10FE0..10FF6
8138 UNKNOWN, // 10FF7..10FFF
8139 BRAHMI, // 11000..1104D
8140 UNKNOWN, // 1104E..11051
8141 BRAHMI, // 11052..11075
8142 UNKNOWN, // 11076..1107E
8143 BRAHMI, // 1107F
8144 KAITHI, // 11080..110C2
8145 UNKNOWN, // 110C3..110CC
8146 KAITHI, // 110CD
8147 UNKNOWN, // 110CE..110CF
8148 SORA_SOMPENG, // 110D0..110E8
8149 UNKNOWN, // 110E9..110EF
8150 SORA_SOMPENG, // 110F0..110F9
8151 UNKNOWN, // 110FA..110FF
8152 CHAKMA, // 11100..11134
8153 UNKNOWN, // 11135
8154 CHAKMA, // 11136..11147
8155 UNKNOWN, // 11148..1114F
8156 MAHAJANI, // 11150..11176
8157 UNKNOWN, // 11177..1117F
8158 SHARADA, // 11180..111DF
8159 UNKNOWN, // 111E0
8160 SINHALA, // 111E1..111F4
8161 UNKNOWN, // 111F5..111FF
8162 KHOJKI, // 11200..11211
8163 UNKNOWN, // 11212
8164 KHOJKI, // 11213..11241
8165 UNKNOWN, // 11242..1127F
8166 MULTANI, // 11280..11286
8167 UNKNOWN, // 11287
8168 MULTANI, // 11288
8169 UNKNOWN, // 11289
8170 MULTANI, // 1128A..1128D
8171 UNKNOWN, // 1128E
8172 MULTANI, // 1128F..1129D
8173 UNKNOWN, // 1129E
8174 MULTANI, // 1129F..112A9
8175 UNKNOWN, // 112AA..112AF
8176 KHUDAWADI, // 112B0..112EA
8177 UNKNOWN, // 112EB..112EF
8178 KHUDAWADI, // 112F0..112F9
8179 UNKNOWN, // 112FA..112FF
8180 GRANTHA, // 11300..11303
8181 UNKNOWN, // 11304
8182 GRANTHA, // 11305..1130C
8183 UNKNOWN, // 1130D..1130E
8184 GRANTHA, // 1130F..11310
8185 UNKNOWN, // 11311..11312
8186 GRANTHA, // 11313..11328
8187 UNKNOWN, // 11329
8188 GRANTHA, // 1132A..11330
8189 UNKNOWN, // 11331
8190 GRANTHA, // 11332..11333
8191 UNKNOWN, // 11334
8192 GRANTHA, // 11335..11339
8193 UNKNOWN, // 1133A
8194 INHERITED, // 1133B
8195 GRANTHA, // 1133C..11344
8196 UNKNOWN, // 11345..11346
8197 GRANTHA, // 11347..11348
8198 UNKNOWN, // 11349..1134A
8199 GRANTHA, // 1134B..1134D
8200 UNKNOWN, // 1134E..1134F
8201 GRANTHA, // 11350
8202 UNKNOWN, // 11351..11356
8203 GRANTHA, // 11357
8204 UNKNOWN, // 11358..1135C
8205 GRANTHA, // 1135D..11363
8206 UNKNOWN, // 11364..11365
8207 GRANTHA, // 11366..1136C
8208 UNKNOWN, // 1136D..1136F
8209 GRANTHA, // 11370..11374
8210 UNKNOWN, // 11375..113FF
8211 NEWA, // 11400..1145B
8212 UNKNOWN, // 1145C
8213 NEWA, // 1145D..11461
8214 UNKNOWN, // 11462..1147F
8215 TIRHUTA, // 11480..114C7
8216 UNKNOWN, // 114C8..114CF
8217 TIRHUTA, // 114D0..114D9
8218 UNKNOWN, // 114DA..1157F
8219 SIDDHAM, // 11580..115B5
8220 UNKNOWN, // 115B6..115B7
8221 SIDDHAM, // 115B8..115DD
8222 UNKNOWN, // 115DE..115FF
8223 MODI, // 11600..11644
8224 UNKNOWN, // 11645..1164F
8225 MODI, // 11650..11659
8226 UNKNOWN, // 1165A..1165F
8227 MONGOLIAN, // 11660..1166C
8228 UNKNOWN, // 1166D..1167F
8229 TAKRI, // 11680..116B9
8230 UNKNOWN, // 116BA..116BF
8231 TAKRI, // 116C0..116C9
8232 UNKNOWN, // 116CA..116FF
8233 AHOM, // 11700..1171A
8234 UNKNOWN, // 1171B..1171C
8235 AHOM, // 1171D..1172B
8236 UNKNOWN, // 1172C..1172F
8237 AHOM, // 11730..11746
8238 UNKNOWN, // 11747..117FF
8239 DOGRA, // 11800..1183B
8240 UNKNOWN, // 1183C..1189F
8241 WARANG_CITI, // 118A0..118F2
8242 UNKNOWN, // 118F3..118FE
8243 WARANG_CITI, // 118FF
8244 DIVES_AKURU, // 11900..11906
8245 UNKNOWN, // 11907..11908
8246 DIVES_AKURU, // 11909
8247 UNKNOWN, // 1190A..1190B
8248 DIVES_AKURU, // 1190C..11913
8249 UNKNOWN, // 11914
8250 DIVES_AKURU, // 11915..11916
8251 UNKNOWN, // 11917
8252 DIVES_AKURU, // 11918..11935
8253 UNKNOWN, // 11936
8254 DIVES_AKURU, // 11937..11938
8255 UNKNOWN, // 11939..1193A
8256 DIVES_AKURU, // 1193B..11946
8257 UNKNOWN, // 11947..1194F
8258 DIVES_AKURU, // 11950..11959
8259 UNKNOWN, // 1195A..1199F
8260 NANDINAGARI, // 119A0..119A7
8261 UNKNOWN, // 119A8..119A9
8262 NANDINAGARI, // 119AA..119D7
8263 UNKNOWN, // 119D8..119D9
8264 NANDINAGARI, // 119DA..119E4
8265 UNKNOWN, // 119E5..119FF
8266 ZANABAZAR_SQUARE, // 11A00..11A47
8267 UNKNOWN, // 11A48..11A4F
8268 SOYOMBO, // 11A50..11AA2
8269 UNKNOWN, // 11AA3..11AAF
8270 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8271 PAU_CIN_HAU, // 11AC0..11AF8
8272 UNKNOWN, // 11AF9..11AFF
8273 DEVANAGARI, // 11B00..11B09
8274 UNKNOWN, // 11B0A..11BFF
8275 BHAIKSUKI, // 11C00..11C08
8276 UNKNOWN, // 11C09
8277 BHAIKSUKI, // 11C0A..11C36
8278 UNKNOWN, // 11C37
8279 BHAIKSUKI, // 11C38..11C45
8280 UNKNOWN, // 11C46..11C4F
8281 BHAIKSUKI, // 11C50..11C6C
8282 UNKNOWN, // 11C6D..11C6F
8283 MARCHEN, // 11C70..11C8F
8284 UNKNOWN, // 11C90..11C91
8285 MARCHEN, // 11C92..11CA7
8286 UNKNOWN, // 11CA8
8287 MARCHEN, // 11CA9..11CB6
8288 UNKNOWN, // 11CB7..11CFF
8289 MASARAM_GONDI, // 11D00..11D06
8290 UNKNOWN, // 11D07
8291 MASARAM_GONDI, // 11D08..11D09
8292 UNKNOWN, // 11D0A
8293 MASARAM_GONDI, // 11D0B..11D36
8294 UNKNOWN, // 11D37..11D39
8295 MASARAM_GONDI, // 11D3A
8296 UNKNOWN, // 11D3B
8297 MASARAM_GONDI, // 11D3C..11D3D
8298 UNKNOWN, // 11D3E
8299 MASARAM_GONDI, // 11D3F..11D47
8300 UNKNOWN, // 11D48..11D4F
8301 MASARAM_GONDI, // 11D50..11D59
8302 UNKNOWN, // 11D5A..11D5F
8303 GUNJALA_GONDI, // 11D60..11D65
8304 UNKNOWN, // 11D66
8305 GUNJALA_GONDI, // 11D67..11D68
8306 UNKNOWN, // 11D69
8307 GUNJALA_GONDI, // 11D6A..11D8E
8308 UNKNOWN, // 11D8F
8309 GUNJALA_GONDI, // 11D90..11D91
8310 UNKNOWN, // 11D92
8311 GUNJALA_GONDI, // 11D93..11D98
8312 UNKNOWN, // 11D99..11D9F
8313 GUNJALA_GONDI, // 11DA0..11DA9
8314 UNKNOWN, // 11DAA..11EDF
8315 MAKASAR, // 11EE0..11EF8
8316 UNKNOWN, // 11EF9..11EFF
8317 KAWI, // 11F00..11F10
8318 UNKNOWN, // 11F11
8319 KAWI, // 11F12..11F3A
8320 UNKNOWN, // 11F3B..11F3D
8321 KAWI, // 11F3E..11F59
8322 UNKNOWN, // 11F5A..11FAF
8323 LISU, // 11FB0
8324 UNKNOWN, // 11FB1..11FBF
8325 TAMIL, // 11FC0..11FF1
8326 UNKNOWN, // 11FF2..11FFE
8327 TAMIL, // 11FFF
8328 CUNEIFORM, // 12000..12399
8329 UNKNOWN, // 1239A..123FF
8330 CUNEIFORM, // 12400..1246E
8331 UNKNOWN, // 1246F
8332 CUNEIFORM, // 12470..12474
8333 UNKNOWN, // 12475..1247F
8334 CUNEIFORM, // 12480..12543
8335 UNKNOWN, // 12544..12F8F
8336 CYPRO_MINOAN, // 12F90..12FF2
8337 UNKNOWN, // 12FF3..12FFF
8338 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8339 UNKNOWN, // 13456..143FF
8340 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8341 UNKNOWN, // 14647..167FF
8342 BAMUM, // 16800..16A38
8343 UNKNOWN, // 16A39..16A3F
8344 MRO, // 16A40..16A5E
8345 UNKNOWN, // 16A5F
8346 MRO, // 16A60..16A69
8347 UNKNOWN, // 16A6A..16A6D
8348 MRO, // 16A6E..16A6F
8349 TANGSA, // 16A70..16ABE
8350 UNKNOWN, // 16ABF
8351 TANGSA, // 16AC0..16AC9
8352 UNKNOWN, // 16ACA..16ACF
8353 BASSA_VAH, // 16AD0..16AED
8354 UNKNOWN, // 16AEE..16AEF
8355 BASSA_VAH, // 16AF0..16AF5
8356 UNKNOWN, // 16AF6..16AFF
8357 PAHAWH_HMONG, // 16B00..16B45
8358 UNKNOWN, // 16B46..16B4F
8359 PAHAWH_HMONG, // 16B50..16B59
8360 UNKNOWN, // 16B5A
8361 PAHAWH_HMONG, // 16B5B..16B61
8362 UNKNOWN, // 16B62
8363 PAHAWH_HMONG, // 16B63..16B77
8364 UNKNOWN, // 16B78..16B7C
8365 PAHAWH_HMONG, // 16B7D..16B8F
8366 UNKNOWN, // 16B90..16E3F
8367 MEDEFAIDRIN, // 16E40..16E9A
8368 UNKNOWN, // 16E9B..16EFF
8369 MIAO, // 16F00..16F4A
8370 UNKNOWN, // 16F4B..16F4E
8371 MIAO, // 16F4F..16F87
8372 UNKNOWN, // 16F88..16F8E
8373 MIAO, // 16F8F..16F9F
8374 UNKNOWN, // 16FA0..16FDF
8375 TANGUT, // 16FE0
8376 NUSHU, // 16FE1
8377 HAN, // 16FE2..16FE3
8378 KHITAN_SMALL_SCRIPT, // 16FE4
8379 UNKNOWN, // 16FE5..16FEF
8380 HAN, // 16FF0..16FF1
8381 UNKNOWN, // 16FF2..16FFF
8382 TANGUT, // 17000..187F7
8383 UNKNOWN, // 187F8..187FF
8384 TANGUT, // 18800..18AFF
8385 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8386 UNKNOWN, // 18CD6..18CFF
8387 TANGUT, // 18D00..18D08
8388 UNKNOWN, // 18D09..1AFEF
8389 KATAKANA, // 1AFF0..1AFF3
8390 UNKNOWN, // 1AFF4
8391 KATAKANA, // 1AFF5..1AFFB
8392 UNKNOWN, // 1AFFC
8393 KATAKANA, // 1AFFD..1AFFE
8394 UNKNOWN, // 1AFFF
8395 KATAKANA, // 1B000
8396 HIRAGANA, // 1B001..1B11F
8397 KATAKANA, // 1B120..1B122
8398 UNKNOWN, // 1B123..1B131
8399 HIRAGANA, // 1B132
8400 UNKNOWN, // 1B133..1B14F
8401 HIRAGANA, // 1B150..1B152
8402 UNKNOWN, // 1B153..1B154
8403 KATAKANA, // 1B155
8404 UNKNOWN, // 1B156..1B163
8405 KATAKANA, // 1B164..1B167
8406 UNKNOWN, // 1B168..1B16F
8407 NUSHU, // 1B170..1B2FB
8408 UNKNOWN, // 1B2FC..1BBFF
8409 DUPLOYAN, // 1BC00..1BC6A
8410 UNKNOWN, // 1BC6B..1BC6F
8411 DUPLOYAN, // 1BC70..1BC7C
8412 UNKNOWN, // 1BC7D..1BC7F
8413 DUPLOYAN, // 1BC80..1BC88
8414 UNKNOWN, // 1BC89..1BC8F
8415 DUPLOYAN, // 1BC90..1BC99
8416 UNKNOWN, // 1BC9A..1BC9B
8417 DUPLOYAN, // 1BC9C..1BC9F
8418 COMMON, // 1BCA0..1BCA3
8419 UNKNOWN, // 1BCA4..1CEFF
8420 INHERITED, // 1CF00..1CF2D
8421 UNKNOWN, // 1CF2E..1CF2F
8422 INHERITED, // 1CF30..1CF46
8423 UNKNOWN, // 1CF47..1CF4F
8424 COMMON, // 1CF50..1CFC3
8425 UNKNOWN, // 1CFC4..1CFFF
8426 COMMON, // 1D000..1D0F5
8427 UNKNOWN, // 1D0F6..1D0FF
8428 COMMON, // 1D100..1D126
8429 UNKNOWN, // 1D127..1D128
8430 COMMON, // 1D129..1D166
8431 INHERITED, // 1D167..1D169
8432 COMMON, // 1D16A..1D17A
8433 INHERITED, // 1D17B..1D182
8434 COMMON, // 1D183..1D184
8435 INHERITED, // 1D185..1D18B
8436 COMMON, // 1D18C..1D1A9
8437 INHERITED, // 1D1AA..1D1AD
8438 COMMON, // 1D1AE..1D1EA
8439 UNKNOWN, // 1D1EB..1D1FF
8440 GREEK, // 1D200..1D245
8441 UNKNOWN, // 1D246..1D2BF
8442 COMMON, // 1D2C0..1D2D3
8443 UNKNOWN, // 1D2D4..1D2DF
8444 COMMON, // 1D2E0..1D2F3
8445 UNKNOWN, // 1D2F4..1D2FF
8446 COMMON, // 1D300..1D356
8447 UNKNOWN, // 1D357..1D35F
8448 COMMON, // 1D360..1D378
8449 UNKNOWN, // 1D379..1D3FF
8450 COMMON, // 1D400..1D454
8451 UNKNOWN, // 1D455
8452 COMMON, // 1D456..1D49C
8453 UNKNOWN, // 1D49D
8454 COMMON, // 1D49E..1D49F
8455 UNKNOWN, // 1D4A0..1D4A1
8456 COMMON, // 1D4A2
8457 UNKNOWN, // 1D4A3..1D4A4
8458 COMMON, // 1D4A5..1D4A6
8459 UNKNOWN, // 1D4A7..1D4A8
8460 COMMON, // 1D4A9..1D4AC
8461 UNKNOWN, // 1D4AD
8462 COMMON, // 1D4AE..1D4B9
8463 UNKNOWN, // 1D4BA
8464 COMMON, // 1D4BB
8465 UNKNOWN, // 1D4BC
8466 COMMON, // 1D4BD..1D4C3
8467 UNKNOWN, // 1D4C4
8468 COMMON, // 1D4C5..1D505
8469 UNKNOWN, // 1D506
8470 COMMON, // 1D507..1D50A
8471 UNKNOWN, // 1D50B..1D50C
8472 COMMON, // 1D50D..1D514
8473 UNKNOWN, // 1D515
8474 COMMON, // 1D516..1D51C
8475 UNKNOWN, // 1D51D
8476 COMMON, // 1D51E..1D539
8477 UNKNOWN, // 1D53A
8478 COMMON, // 1D53B..1D53E
8479 UNKNOWN, // 1D53F
8480 COMMON, // 1D540..1D544
8481 UNKNOWN, // 1D545
8482 COMMON, // 1D546
8483 UNKNOWN, // 1D547..1D549
8484 COMMON, // 1D54A..1D550
8485 UNKNOWN, // 1D551
8486 COMMON, // 1D552..1D6A5
8487 UNKNOWN, // 1D6A6..1D6A7
8488 COMMON, // 1D6A8..1D7CB
8489 UNKNOWN, // 1D7CC..1D7CD
8490 COMMON, // 1D7CE..1D7FF
8491 SIGNWRITING, // 1D800..1DA8B
8492 UNKNOWN, // 1DA8C..1DA9A
8493 SIGNWRITING, // 1DA9B..1DA9F
8494 UNKNOWN, // 1DAA0
8495 SIGNWRITING, // 1DAA1..1DAAF
8496 UNKNOWN, // 1DAB0..1DEFF
8497 LATIN, // 1DF00..1DF1E
8498 UNKNOWN, // 1DF1F..1DF24
8499 LATIN, // 1DF25..1DF2A
8500 UNKNOWN, // 1DF2B..1DFFF
8501 GLAGOLITIC, // 1E000..1E006
8502 UNKNOWN, // 1E007
8503 GLAGOLITIC, // 1E008..1E018
8504 UNKNOWN, // 1E019..1E01A
8505 GLAGOLITIC, // 1E01B..1E021
8506 UNKNOWN, // 1E022
8507 GLAGOLITIC, // 1E023..1E024
8508 UNKNOWN, // 1E025
8509 GLAGOLITIC, // 1E026..1E02A
8510 UNKNOWN, // 1E02B..1E02F
8511 CYRILLIC, // 1E030..1E06D
8512 UNKNOWN, // 1E06E..1E08E
8513 CYRILLIC, // 1E08F
8514 UNKNOWN, // 1E090..1E0FF
8515 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8516 UNKNOWN, // 1E12D..1E12F
8517 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8518 UNKNOWN, // 1E13E..1E13F
8519 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8520 UNKNOWN, // 1E14A..1E14D
8521 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8522 UNKNOWN, // 1E150..1E28F
8523 TOTO, // 1E290..1E2AE
8524 UNKNOWN, // 1E2AF..1E2BF
8525 WANCHO, // 1E2C0..1E2F9
8526 UNKNOWN, // 1E2FA..1E2FE
8527 WANCHO, // 1E2FF
8528 UNKNOWN, // 1E300..1E4CF
8529 NAG_MUNDARI, // 1E4D0..1E4F9
8530 UNKNOWN, // 1E4FA..1E7DF
8531 ETHIOPIC, // 1E7E0..1E7E6
8532 UNKNOWN, // 1E7E7
8533 ETHIOPIC, // 1E7E8..1E7EB
8534 UNKNOWN, // 1E7EC
8535 ETHIOPIC, // 1E7ED..1E7EE
8536 UNKNOWN, // 1E7EF
8537 ETHIOPIC, // 1E7F0..1E7FE
8538 UNKNOWN, // 1E7FF
8539 MENDE_KIKAKUI, // 1E800..1E8C4
8540 UNKNOWN, // 1E8C5..1E8C6
8541 MENDE_KIKAKUI, // 1E8C7..1E8D6
8542 UNKNOWN, // 1E8D7..1E8FF
8543 ADLAM, // 1E900..1E94B
8544 UNKNOWN, // 1E94C..1E94F
8545 ADLAM, // 1E950..1E959
8546 UNKNOWN, // 1E95A..1E95D
8547 ADLAM, // 1E95E..1E95F
8548 UNKNOWN, // 1E960..1EC70
8549 COMMON, // 1EC71..1ECB4
8550 UNKNOWN, // 1ECB5..1ED00
8551 COMMON, // 1ED01..1ED3D
8552 UNKNOWN, // 1ED3E..1EDFF
8553 ARABIC, // 1EE00..1EE03
8554 UNKNOWN, // 1EE04
8555 ARABIC, // 1EE05..1EE1F
8556 UNKNOWN, // 1EE20
8557 ARABIC, // 1EE21..1EE22
8558 UNKNOWN, // 1EE23
8559 ARABIC, // 1EE24
8560 UNKNOWN, // 1EE25..1EE26
8561 ARABIC, // 1EE27
8562 UNKNOWN, // 1EE28
8563 ARABIC, // 1EE29..1EE32
8564 UNKNOWN, // 1EE33
8565 ARABIC, // 1EE34..1EE37
8566 UNKNOWN, // 1EE38
8567 ARABIC, // 1EE39
8568 UNKNOWN, // 1EE3A
8569 ARABIC, // 1EE3B
8570 UNKNOWN, // 1EE3C..1EE41
8571 ARABIC, // 1EE42
8572 UNKNOWN, // 1EE43..1EE46
8573 ARABIC, // 1EE47
8574 UNKNOWN, // 1EE48
8575 ARABIC, // 1EE49
8576 UNKNOWN, // 1EE4A
8577 ARABIC, // 1EE4B
8578 UNKNOWN, // 1EE4C
8579 ARABIC, // 1EE4D..1EE4F
8580 UNKNOWN, // 1EE50
8581 ARABIC, // 1EE51..1EE52
8582 UNKNOWN, // 1EE53
8583 ARABIC, // 1EE54
8584 UNKNOWN, // 1EE55..1EE56
8585 ARABIC, // 1EE57
8586 UNKNOWN, // 1EE58
8587 ARABIC, // 1EE59
8588 UNKNOWN, // 1EE5A
8589 ARABIC, // 1EE5B
8590 UNKNOWN, // 1EE5C
8591 ARABIC, // 1EE5D
8592 UNKNOWN, // 1EE5E
8593 ARABIC, // 1EE5F
8594 UNKNOWN, // 1EE60
8595 ARABIC, // 1EE61..1EE62
8596 UNKNOWN, // 1EE63
8597 ARABIC, // 1EE64
8598 UNKNOWN, // 1EE65..1EE66
8599 ARABIC, // 1EE67..1EE6A
8600 UNKNOWN, // 1EE6B
8601 ARABIC, // 1EE6C..1EE72
8602 UNKNOWN, // 1EE73
8603 ARABIC, // 1EE74..1EE77
8604 UNKNOWN, // 1EE78
8605 ARABIC, // 1EE79..1EE7C
8606 UNKNOWN, // 1EE7D
8607 ARABIC, // 1EE7E
8608 UNKNOWN, // 1EE7F
8609 ARABIC, // 1EE80..1EE89
8610 UNKNOWN, // 1EE8A
8611 ARABIC, // 1EE8B..1EE9B
8612 UNKNOWN, // 1EE9C..1EEA0
8613 ARABIC, // 1EEA1..1EEA3
8614 UNKNOWN, // 1EEA4
8615 ARABIC, // 1EEA5..1EEA9
8616 UNKNOWN, // 1EEAA
8617 ARABIC, // 1EEAB..1EEBB
8618 UNKNOWN, // 1EEBC..1EEEF
8619 ARABIC, // 1EEF0..1EEF1
8620 UNKNOWN, // 1EEF2..1EFFF
8621 COMMON, // 1F000..1F02B
8622 UNKNOWN, // 1F02C..1F02F
8623 COMMON, // 1F030..1F093
8624 UNKNOWN, // 1F094..1F09F
8625 COMMON, // 1F0A0..1F0AE
8626 UNKNOWN, // 1F0AF..1F0B0
8627 COMMON, // 1F0B1..1F0BF
8628 UNKNOWN, // 1F0C0
8629 COMMON, // 1F0C1..1F0CF
8630 UNKNOWN, // 1F0D0
8631 COMMON, // 1F0D1..1F0F5
8632 UNKNOWN, // 1F0F6..1F0FF
8633 COMMON, // 1F100..1F1AD
8634 UNKNOWN, // 1F1AE..1F1E5
8635 COMMON, // 1F1E6..1F1FF
8636 HIRAGANA, // 1F200
8637 COMMON, // 1F201..1F202
8638 UNKNOWN, // 1F203..1F20F
8639 COMMON, // 1F210..1F23B
8640 UNKNOWN, // 1F23C..1F23F
8641 COMMON, // 1F240..1F248
8642 UNKNOWN, // 1F249..1F24F
8643 COMMON, // 1F250..1F251
8644 UNKNOWN, // 1F252..1F25F
8645 COMMON, // 1F260..1F265
8646 UNKNOWN, // 1F266..1F2FF
8647 COMMON, // 1F300..1F6D7
8648 UNKNOWN, // 1F6D8..1F6DB
8649 COMMON, // 1F6DC..1F6EC
8650 UNKNOWN, // 1F6ED..1F6EF
8651 COMMON, // 1F6F0..1F6FC
8652 UNKNOWN, // 1F6FD..1F6FF
8653 COMMON, // 1F700..1F776
8654 UNKNOWN, // 1F777..1F77A
8655 COMMON, // 1F77B..1F7D9
8656 UNKNOWN, // 1F7DA..1F7DF
8657 COMMON, // 1F7E0..1F7EB
8658 UNKNOWN, // 1F7EC..1F7EF
8659 COMMON, // 1F7F0
8660 UNKNOWN, // 1F7F1..1F7FF
8661 COMMON, // 1F800..1F80B
8662 UNKNOWN, // 1F80C..1F80F
8663 COMMON, // 1F810..1F847
8664 UNKNOWN, // 1F848..1F84F
8665 COMMON, // 1F850..1F859
8666 UNKNOWN, // 1F85A..1F85F
8667 COMMON, // 1F860..1F887
8668 UNKNOWN, // 1F888..1F88F
8669 COMMON, // 1F890..1F8AD
8670 UNKNOWN, // 1F8AE..1F8AF
8671 COMMON, // 1F8B0..1F8B1
8672 UNKNOWN, // 1F8B2..1F8FF
8673 COMMON, // 1F900..1FA53
8674 UNKNOWN, // 1FA54..1FA5F
8675 COMMON, // 1FA60..1FA6D
8676 UNKNOWN, // 1FA6E..1FA6F
8677 COMMON, // 1FA70..1FA7C
8678 UNKNOWN, // 1FA7D..1FA7F
8679 COMMON, // 1FA80..1FA88
8680 UNKNOWN, // 1FA89..1FA8F
8681 COMMON, // 1FA90..1FABD
8682 UNKNOWN, // 1FABE
8683 COMMON, // 1FABF..1FAC5
8684 UNKNOWN, // 1FAC6..1FACD
8685 COMMON, // 1FACE..1FADB
8686 UNKNOWN, // 1FADC..1FADF
8687 COMMON, // 1FAE0..1FAE8
8688 UNKNOWN, // 1FAE9..1FAEF
8689 COMMON, // 1FAF0..1FAF8
8690 UNKNOWN, // 1FAF9..1FAFF
8691 COMMON, // 1FB00..1FB92
8692 UNKNOWN, // 1FB93
8693 COMMON, // 1FB94..1FBCA
8694 UNKNOWN, // 1FBCB..1FBEF
8695 COMMON, // 1FBF0..1FBF9
8696 UNKNOWN, // 1FBFA..1FFFF
8697 HAN, // 20000..2A6DF
8698 UNKNOWN, // 2A6E0..2A6FF
8699 HAN, // 2A700..2B739
8700 UNKNOWN, // 2B73A..2B73F
8701 HAN, // 2B740..2B81D
8702 UNKNOWN, // 2B81E..2B81F
8703 HAN, // 2B820..2CEA1
8704 UNKNOWN, // 2CEA2..2CEAF
8705 HAN, // 2CEB0..2EBE0
8706 UNKNOWN, // 2EBE1..2EBEF
8707 HAN, // 2EBF0..2EE5D
8708 UNKNOWN, // 2EE5E..2F7FF
8709 HAN, // 2F800..2FA1D
8710 UNKNOWN, // 2FA1E..2FFFF
8711 HAN, // 30000..3134A
8712 UNKNOWN, // 3134B..3134F
8713 HAN, // 31350..323AF
8714 UNKNOWN, // 323B0..E0000
8715 COMMON, // E0001
8716 UNKNOWN, // E0002..E001F
8717 COMMON, // E0020..E007F
8718 UNKNOWN, // E0080..E00FF
8719 INHERITED, // E0100..E01EF
8720 UNKNOWN, // E01F0..10FFFF
8721 };
8722
8723 private static final HashMap<String, Character.UnicodeScript> aliases;
8724 static {
8725 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
8726 aliases.put("ADLM", ADLAM);
8727 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
8728 aliases.put("AHOM", AHOM);
8729 aliases.put("ARAB", ARABIC);
8730 aliases.put("ARMI", IMPERIAL_ARAMAIC);
8731 aliases.put("ARMN", ARMENIAN);
8732 aliases.put("AVST", AVESTAN);
8733 aliases.put("BALI", BALINESE);
8734 aliases.put("BAMU", BAMUM);
8735 aliases.put("BASS", BASSA_VAH);
8736 aliases.put("BATK", BATAK);
8737 aliases.put("BENG", BENGALI);
8738 aliases.put("BHKS", BHAIKSUKI);
8739 aliases.put("BOPO", BOPOMOFO);
8740 aliases.put("BRAH", BRAHMI);
8741 aliases.put("BRAI", BRAILLE);
8742 aliases.put("BUGI", BUGINESE);
8743 aliases.put("BUHD", BUHID);
8744 aliases.put("CAKM", CHAKMA);
8745 aliases.put("CANS", CANADIAN_ABORIGINAL);
8746 aliases.put("CARI", CARIAN);
8747 aliases.put("CHAM", CHAM);
8748 aliases.put("CHER", CHEROKEE);
8749 aliases.put("CHRS", CHORASMIAN);
8750 aliases.put("COPT", COPTIC);
8751 aliases.put("CPMN", CYPRO_MINOAN);
8752 aliases.put("CPRT", CYPRIOT);
8753 aliases.put("CYRL", CYRILLIC);
8754 aliases.put("DEVA", DEVANAGARI);
8755 aliases.put("DIAK", DIVES_AKURU);
8756 aliases.put("DOGR", DOGRA);
8757 aliases.put("DSRT", DESERET);
8758 aliases.put("DUPL", DUPLOYAN);
8759 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
8760 aliases.put("ELBA", ELBASAN);
8761 aliases.put("ELYM", ELYMAIC);
8762 aliases.put("ETHI", ETHIOPIC);
8763 aliases.put("GEOR", GEORGIAN);
8764 aliases.put("GLAG", GLAGOLITIC);
8765 aliases.put("GONG", GUNJALA_GONDI);
8766 aliases.put("GONM", MASARAM_GONDI);
8767 aliases.put("GOTH", GOTHIC);
8768 aliases.put("GRAN", GRANTHA);
8769 aliases.put("GREK", GREEK);
8770 aliases.put("GUJR", GUJARATI);
8771 aliases.put("GURU", GURMUKHI);
8772 aliases.put("HANG", HANGUL);
8773 aliases.put("HANI", HAN);
8774 aliases.put("HANO", HANUNOO);
8775 aliases.put("HATR", HATRAN);
8776 aliases.put("HEBR", HEBREW);
8777 aliases.put("HIRA", HIRAGANA);
8778 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
8779 aliases.put("HMNG", PAHAWH_HMONG);
8780 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
8781 aliases.put("HUNG", OLD_HUNGARIAN);
8782 aliases.put("ITAL", OLD_ITALIC);
8783 aliases.put("JAVA", JAVANESE);
8784 aliases.put("KALI", KAYAH_LI);
8785 aliases.put("KANA", KATAKANA);
8786 aliases.put("KAWI", KAWI);
8787 aliases.put("KHAR", KHAROSHTHI);
8788 aliases.put("KHMR", KHMER);
8789 aliases.put("KHOJ", KHOJKI);
8790 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
8791 aliases.put("KNDA", KANNADA);
8792 aliases.put("KTHI", KAITHI);
8793 aliases.put("LANA", TAI_THAM);
8794 aliases.put("LAOO", LAO);
8795 aliases.put("LATN", LATIN);
8796 aliases.put("LEPC", LEPCHA);
8797 aliases.put("LIMB", LIMBU);
8798 aliases.put("LINA", LINEAR_A);
8799 aliases.put("LINB", LINEAR_B);
8800 aliases.put("LISU", LISU);
8801 aliases.put("LYCI", LYCIAN);
8802 aliases.put("LYDI", LYDIAN);
8803 aliases.put("MAHJ", MAHAJANI);
8804 aliases.put("MAKA", MAKASAR);
8805 aliases.put("MAND", MANDAIC);
8806 aliases.put("MANI", MANICHAEAN);
8807 aliases.put("MARC", MARCHEN);
8808 aliases.put("MEDF", MEDEFAIDRIN);
8809 aliases.put("MEND", MENDE_KIKAKUI);
8810 aliases.put("MERC", MEROITIC_CURSIVE);
8811 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
8812 aliases.put("MLYM", MALAYALAM);
8813 aliases.put("MODI", MODI);
8814 aliases.put("MONG", MONGOLIAN);
8815 aliases.put("MROO", MRO);
8816 aliases.put("MTEI", MEETEI_MAYEK);
8817 aliases.put("MULT", MULTANI);
8818 aliases.put("MYMR", MYANMAR);
8819 aliases.put("NAGM", NAG_MUNDARI);
8820 aliases.put("NAND", NANDINAGARI);
8821 aliases.put("NARB", OLD_NORTH_ARABIAN);
8822 aliases.put("NBAT", NABATAEAN);
8823 aliases.put("NEWA", NEWA);
8824 aliases.put("NKOO", NKO);
8825 aliases.put("NSHU", NUSHU);
8826 aliases.put("OGAM", OGHAM);
8827 aliases.put("OLCK", OL_CHIKI);
8828 aliases.put("ORKH", OLD_TURKIC);
8829 aliases.put("ORYA", ORIYA);
8830 aliases.put("OSGE", OSAGE);
8831 aliases.put("OSMA", OSMANYA);
8832 aliases.put("OUGR", OLD_UYGHUR);
8833 aliases.put("PALM", PALMYRENE);
8834 aliases.put("PAUC", PAU_CIN_HAU);
8835 aliases.put("PERM", OLD_PERMIC);
8836 aliases.put("PHAG", PHAGS_PA);
8837 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
8838 aliases.put("PHLP", PSALTER_PAHLAVI);
8839 aliases.put("PHNX", PHOENICIAN);
8840 aliases.put("PLRD", MIAO);
8841 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
8842 aliases.put("RJNG", REJANG);
8843 aliases.put("ROHG", HANIFI_ROHINGYA);
8844 aliases.put("RUNR", RUNIC);
8845 aliases.put("SAMR", SAMARITAN);
8846 aliases.put("SARB", OLD_SOUTH_ARABIAN);
8847 aliases.put("SAUR", SAURASHTRA);
8848 aliases.put("SGNW", SIGNWRITING);
8849 aliases.put("SHAW", SHAVIAN);
8850 aliases.put("SHRD", SHARADA);
8851 aliases.put("SIDD", SIDDHAM);
8852 aliases.put("SIND", KHUDAWADI);
8853 aliases.put("SINH", SINHALA);
8854 aliases.put("SOGD", SOGDIAN);
8855 aliases.put("SOGO", OLD_SOGDIAN);
8856 aliases.put("SORA", SORA_SOMPENG);
8857 aliases.put("SOYO", SOYOMBO);
8858 aliases.put("SUND", SUNDANESE);
8859 aliases.put("SYLO", SYLOTI_NAGRI);
8860 aliases.put("SYRC", SYRIAC);
8861 aliases.put("TAGB", TAGBANWA);
8862 aliases.put("TAKR", TAKRI);
8863 aliases.put("TALE", TAI_LE);
8864 aliases.put("TALU", NEW_TAI_LUE);
8865 aliases.put("TAML", TAMIL);
8866 aliases.put("TANG", TANGUT);
8867 aliases.put("TAVT", TAI_VIET);
8868 aliases.put("TELU", TELUGU);
8869 aliases.put("TFNG", TIFINAGH);
8870 aliases.put("TGLG", TAGALOG);
8871 aliases.put("THAA", THAANA);
8872 aliases.put("THAI", THAI);
8873 aliases.put("TIBT", TIBETAN);
8874 aliases.put("TIRH", TIRHUTA);
8875 aliases.put("TNSA", TANGSA);
8876 aliases.put("TOTO", TOTO);
8877 aliases.put("UGAR", UGARITIC);
8878 aliases.put("VAII", VAI);
8879 aliases.put("VITH", VITHKUQI);
8880 aliases.put("WARA", WARANG_CITI);
8881 aliases.put("WCHO", WANCHO);
8882 aliases.put("XPEO", OLD_PERSIAN);
8883 aliases.put("XSUX", CUNEIFORM);
8884 aliases.put("YEZI", YEZIDI);
8885 aliases.put("YIII", YI);
8886 aliases.put("ZANB", ZANABAZAR_SQUARE);
8887 aliases.put("ZINH", INHERITED);
8888 aliases.put("ZYYY", COMMON);
8889 aliases.put("ZZZZ", UNKNOWN);
8890 }
8891
8892 /**
8893 * Returns the enum constant representing the Unicode script of which
8894 * the given character (Unicode code point) is assigned to.
8895 *
8896 * @param codePoint the character (Unicode code point) in question.
8897 * @return The {@code UnicodeScript} constant representing the
8898 * Unicode script of which this character is assigned to.
8899 *
8900 * @throws IllegalArgumentException if the specified
8901 * {@code codePoint} is an invalid Unicode code point.
8902 * @see Character#isValidCodePoint(int)
8903 *
8904 */
8905 public static UnicodeScript of(int codePoint) {
8906 if (!isValidCodePoint(codePoint))
8907 throw new IllegalArgumentException(
8908 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8909 int type = getType(codePoint);
8910 // leave SURROGATE and PRIVATE_USE for table lookup
8911 if (type == UNASSIGNED)
8912 return UNKNOWN;
8913 int index = Arrays.binarySearch(scriptStarts, codePoint);
8914 if (index < 0)
8915 index = -index - 2;
8916 return scripts[index];
8917 }
8918
8919 /**
8920 * Returns the UnicodeScript constant with the given Unicode script
8921 * name or the script name alias. Script names and their aliases are
8922 * determined by The Unicode Standard. The files {@code Scripts.txt}
8923 * and {@code PropertyValueAliases.txt} define script names
8924 * and the script name aliases for a particular version of the
8925 * standard. The {@link Character} class specifies the version of
8926 * the standard that it supports.
8927 * <p>
8928 * Character case is ignored for all of the valid script names.
8929 * The en_US locale's case mapping rules are used to provide
8930 * case-insensitive string comparisons for script name validation.
8931 *
8932 * @param scriptName A {@code UnicodeScript} name.
8933 * @return The {@code UnicodeScript} constant identified
8934 * by {@code scriptName}
8935 * @throws IllegalArgumentException if {@code scriptName} is an
8936 * invalid name
8937 * @throws NullPointerException if {@code scriptName} is null
8938 */
8939 public static final UnicodeScript forName(String scriptName) {
8940 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
8941 //.replace(' ', '_'));
8942 UnicodeScript sc = aliases.get(scriptName);
8943 if (sc != null)
8944 return sc;
8945 return valueOf(scriptName);
8946 }
8947 }
8948
8949 /**
8950 * The value of the {@code Character}.
8951 *
8952 * @serial
8953 */
8954 private final char value;
8955
8956 /** use serialVersionUID from JDK 1.0.2 for interoperability */
8957 @java.io.Serial
8958 private static final long serialVersionUID = 3786198910865385080L;
8959
8960 /**
8961 * Constructs a newly allocated {@code Character} object that
8962 * represents the specified {@code char} value.
8963 *
8964 * @param value the value to be represented by the
8965 * {@code Character} object.
8966 *
8967 * @deprecated
8968 * It is rarely appropriate to use this constructor. The static factory
8969 * {@link #valueOf(char)} is generally a better choice, as it is
8970 * likely to yield significantly better space and time performance.
8971 */
8972 @Deprecated(since="9", forRemoval = true)
8973 public Character(char value) {
8974 this.value = value;
8975 }
8976
8977 private static final class CharacterCache {
8978 private CharacterCache(){}
8979
8980 @Stable
8981 static final Character[] cache;
8982 static Character[] archivedCache;
8983
8984 static {
8985 int size = 127 + 1;
8986
8987 // Load and use the archived cache if it exists
8988 CDS.initializeFromArchive(CharacterCache.class);
8989 if (archivedCache == null || archivedCache.length != size) {
8990 Character[] c = new Character[size];
8991 for (int i = 0; i < size; i++) {
8992 c[i] = new Character((char) i);
8993 }
8994 archivedCache = c;
8995 }
8996 cache = archivedCache;
8997 }
8998 }
8999
9000 /**
9001 * Returns a {@code Character} instance representing the specified
9002 * {@code char} value.
9003 * If a new {@code Character} instance is not required, this method
9004 * should generally be used in preference to the constructor
9005 * {@link #Character(char)}, as this method is likely to yield
9006 * significantly better space and time performance by caching
9007 * frequently requested values.
9008 *
9009 * This method will always cache values in the range {@code
9010 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9011 * cache other values outside of this range.
9012 *
9013 * @param c a char value.
9014 * @return a {@code Character} instance representing {@code c}.
9015 * @since 1.5
9016 */
9017 @IntrinsicCandidate
9018 @DeserializeConstructor
9019 public static Character valueOf(char c) {
9020 if (c <= 127) { // must cache
9021 return CharacterCache.cache[(int)c];
9022 }
9023 return new Character(c);
9024 }
9025
9026 /**
9027 * Returns the value of this {@code Character} object.
9028 * @return the primitive {@code char} value represented by
9029 * this object.
9030 */
9031 @IntrinsicCandidate
9032 public char charValue() {
9033 return value;
9034 }
9035
9036 /**
9037 * Returns a hash code for this {@code Character}; equal to the result
9038 * of invoking {@code charValue()}.
9039 *
9040 * @return a hash code value for this {@code Character}
9041 */
9042 @Override
9043 public int hashCode() {
9044 return Character.hashCode(value);
9045 }
9046
9047 /**
9048 * Returns a hash code for a {@code char} value; compatible with
9049 * {@code Character.hashCode()}.
9050 *
9051 * @since 1.8
9052 *
9053 * @param value The {@code char} for which to return a hash code.
9054 * @return a hash code value for a {@code char} value.
9055 */
9056 public static int hashCode(char value) {
9057 return (int)value;
9058 }
9059
9060 /**
9061 * Compares this object against the specified object.
9062 * The result is {@code true} if and only if the argument is not
9063 * {@code null} and is a {@code Character} object that
9064 * represents the same {@code char} value as this object.
9065 *
9066 * @param obj the object to compare with.
9067 * @return {@code true} if the objects are the same;
9068 * {@code false} otherwise.
9069 */
9070 public boolean equals(Object obj) {
9071 if (obj instanceof Character) {
9072 return value == ((Character)obj).charValue();
9073 }
9074 return false;
9075 }
9076
9077 /**
9078 * Returns a {@code String} object representing this
9079 * {@code Character}'s value. The result is a string of
9080 * length 1 whose sole component is the primitive
9081 * {@code char} value represented by this
9082 * {@code Character} object.
9083 *
9084 * @return a string representation of this object.
9085 */
9086 @Override
9087 public String toString() {
9088 return String.valueOf(value);
9089 }
9090
9091 /**
9092 * Returns a {@code String} object representing the
9093 * specified {@code char}. The result is a string of length
9094 * 1 consisting solely of the specified {@code char}.
9095 *
9096 * @apiNote This method cannot handle <a
9097 * href="#supplementary"> supplementary characters</a>. To support
9098 * all Unicode characters, including supplementary characters, use
9099 * the {@link #toString(int)} method.
9100 *
9101 * @param c the {@code char} to be converted
9102 * @return the string representation of the specified {@code char}
9103 * @since 1.4
9104 */
9105 public static String toString(char c) {
9106 return String.valueOf(c);
9107 }
9108
9109 /**
9110 * Returns a {@code String} object representing the
9111 * specified character (Unicode code point). The result is a string of
9112 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9113 *
9114 * @param codePoint the {@code codePoint} to be converted
9115 * @return the string representation of the specified {@code codePoint}
9116 * @throws IllegalArgumentException if the specified
9117 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9118 * valid Unicode code point}.
9119 * @since 11
9120 */
9121 public static String toString(int codePoint) {
9122 return String.valueOfCodePoint(codePoint);
9123 }
9124
9125 /**
9126 * Determines whether the specified code point is a valid
9127 * <a href="http://www.unicode.org/glossary/#code_point">
9128 * Unicode code point value</a>.
9129 *
9130 * @param codePoint the Unicode code point to be tested
9131 * @return {@code true} if the specified code point value is between
9132 * {@link #MIN_CODE_POINT} and
9133 * {@link #MAX_CODE_POINT} inclusive;
9134 * {@code false} otherwise.
9135 * @since 1.5
9136 */
9137 public static boolean isValidCodePoint(int codePoint) {
9138 // Optimized form of:
9139 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9140 int plane = codePoint >>> 16;
9141 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9142 }
9143
9144 /**
9145 * Determines whether the specified character (Unicode code point)
9146 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9147 * Such code points can be represented using a single {@code char}.
9148 *
9149 * @param codePoint the character (Unicode code point) to be tested
9150 * @return {@code true} if the specified code point is between
9151 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9152 * {@code false} otherwise.
9153 * @since 1.7
9154 */
9155 public static boolean isBmpCodePoint(int codePoint) {
9156 return codePoint >>> 16 == 0;
9157 // Optimized form of:
9158 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9159 // We consistently use logical shift (>>>) to facilitate
9160 // additional runtime optimizations.
9161 }
9162
9163 /**
9164 * Determines whether the specified character (Unicode code point)
9165 * is in the <a href="#supplementary">supplementary character</a> range.
9166 *
9167 * @param codePoint the character (Unicode code point) to be tested
9168 * @return {@code true} if the specified code point is between
9169 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9170 * {@link #MAX_CODE_POINT} inclusive;
9171 * {@code false} otherwise.
9172 * @since 1.5
9173 */
9174 public static boolean isSupplementaryCodePoint(int codePoint) {
9175 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9176 && codePoint < MAX_CODE_POINT + 1;
9177 }
9178
9179 /**
9180 * Determines if the given {@code char} value is a
9181 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9182 * Unicode high-surrogate code unit</a>
9183 * (also known as <i>leading-surrogate code unit</i>).
9184 *
9185 * <p>Such values do not represent characters by themselves,
9186 * but are used in the representation of
9187 * <a href="#supplementary">supplementary characters</a>
9188 * in the UTF-16 encoding.
9189 *
9190 * @param ch the {@code char} value to be tested.
9191 * @return {@code true} if the {@code char} value is between
9192 * {@link #MIN_HIGH_SURROGATE} and
9193 * {@link #MAX_HIGH_SURROGATE} inclusive;
9194 * {@code false} otherwise.
9195 * @see Character#isLowSurrogate(char)
9196 * @see Character.UnicodeBlock#of(int)
9197 * @since 1.5
9198 */
9199 public static boolean isHighSurrogate(char ch) {
9200 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9201 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9202 }
9203
9204 /**
9205 * Determines if the given {@code char} value is a
9206 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9207 * Unicode low-surrogate code unit</a>
9208 * (also known as <i>trailing-surrogate code unit</i>).
9209 *
9210 * <p>Such values do not represent characters by themselves,
9211 * but are used in the representation of
9212 * <a href="#supplementary">supplementary characters</a>
9213 * in the UTF-16 encoding.
9214 *
9215 * @param ch the {@code char} value to be tested.
9216 * @return {@code true} if the {@code char} value is between
9217 * {@link #MIN_LOW_SURROGATE} and
9218 * {@link #MAX_LOW_SURROGATE} inclusive;
9219 * {@code false} otherwise.
9220 * @see Character#isHighSurrogate(char)
9221 * @since 1.5
9222 */
9223 public static boolean isLowSurrogate(char ch) {
9224 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9225 }
9226
9227 /**
9228 * Determines if the given {@code char} value is a Unicode
9229 * <i>surrogate code unit</i>.
9230 *
9231 * <p>Such values do not represent characters by themselves,
9232 * but are used in the representation of
9233 * <a href="#supplementary">supplementary characters</a>
9234 * in the UTF-16 encoding.
9235 *
9236 * <p>A char value is a surrogate code unit if and only if it is either
9237 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9238 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9239 *
9240 * @param ch the {@code char} value to be tested.
9241 * @return {@code true} if the {@code char} value is between
9242 * {@link #MIN_SURROGATE} and
9243 * {@link #MAX_SURROGATE} inclusive;
9244 * {@code false} otherwise.
9245 * @since 1.7
9246 */
9247 public static boolean isSurrogate(char ch) {
9248 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9249 }
9250
9251 /**
9252 * Determines whether the specified pair of {@code char}
9253 * values is a valid
9254 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9255 * Unicode surrogate pair</a>.
9256 *
9257 * <p>This method is equivalent to the expression:
9258 * <blockquote><pre>{@code
9259 * isHighSurrogate(high) && isLowSurrogate(low)
9260 * }</pre></blockquote>
9261 *
9262 * @param high the high-surrogate code value to be tested
9263 * @param low the low-surrogate code value to be tested
9264 * @return {@code true} if the specified high and
9265 * low-surrogate code values represent a valid surrogate pair;
9266 * {@code false} otherwise.
9267 * @since 1.5
9268 */
9269 public static boolean isSurrogatePair(char high, char low) {
9270 return isHighSurrogate(high) && isLowSurrogate(low);
9271 }
9272
9273 /**
9274 * Determines the number of {@code char} values needed to
9275 * represent the specified character (Unicode code point). If the
9276 * specified character is equal to or greater than 0x10000, then
9277 * the method returns 2. Otherwise, the method returns 1.
9278 *
9279 * <p>This method doesn't validate the specified character to be a
9280 * valid Unicode code point. The caller must validate the
9281 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9282 * if necessary.
9283 *
9284 * @param codePoint the character (Unicode code point) to be tested.
9285 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9286 * @see Character#isSupplementaryCodePoint(int)
9287 * @since 1.5
9288 */
9289 public static int charCount(int codePoint) {
9290 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9291 }
9292
9293 /**
9294 * Converts the specified surrogate pair to its supplementary code
9295 * point value. This method does not validate the specified
9296 * surrogate pair. The caller must validate it using {@link
9297 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9298 *
9299 * @param high the high-surrogate code unit
9300 * @param low the low-surrogate code unit
9301 * @return the supplementary code point composed from the
9302 * specified surrogate pair.
9303 * @since 1.5
9304 */
9305 public static int toCodePoint(char high, char low) {
9306 // Optimized form of:
9307 // return ((high - MIN_HIGH_SURROGATE) << 10)
9308 // + (low - MIN_LOW_SURROGATE)
9309 // + MIN_SUPPLEMENTARY_CODE_POINT;
9310 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9311 - (MIN_HIGH_SURROGATE << 10)
9312 - MIN_LOW_SURROGATE);
9313 }
9314
9315 /**
9316 * Returns the code point at the given index of the
9317 * {@code CharSequence}. If the {@code char} value at
9318 * the given index in the {@code CharSequence} is in the
9319 * high-surrogate range, the following index is less than the
9320 * length of the {@code CharSequence}, and the
9321 * {@code char} value at the following index is in the
9322 * low-surrogate range, then the supplementary code point
9323 * corresponding to this surrogate pair is returned. Otherwise,
9324 * the {@code char} value at the given index is returned.
9325 *
9326 * @param seq a sequence of {@code char} values (Unicode code
9327 * units)
9328 * @param index the index to the {@code char} values (Unicode
9329 * code units) in {@code seq} to be converted
9330 * @return the Unicode code point at the given index
9331 * @throws NullPointerException if {@code seq} is null.
9332 * @throws IndexOutOfBoundsException if the value
9333 * {@code index} is negative or not less than
9334 * {@link CharSequence#length() seq.length()}.
9335 * @since 1.5
9336 */
9337 public static int codePointAt(CharSequence seq, int index) {
9338 char c1 = seq.charAt(index);
9339 if (isHighSurrogate(c1) && ++index < seq.length()) {
9340 char c2 = seq.charAt(index);
9341 if (isLowSurrogate(c2)) {
9342 return toCodePoint(c1, c2);
9343 }
9344 }
9345 return c1;
9346 }
9347
9348 /**
9349 * Returns the code point at the given index of the
9350 * {@code char} array. If the {@code char} value at
9351 * the given index in the {@code char} array is in the
9352 * high-surrogate range, the following index is less than the
9353 * length of the {@code char} array, and the
9354 * {@code char} value at the following index is in the
9355 * low-surrogate range, then the supplementary code point
9356 * corresponding to this surrogate pair is returned. Otherwise,
9357 * the {@code char} value at the given index is returned.
9358 *
9359 * @param a the {@code char} array
9360 * @param index the index to the {@code char} values (Unicode
9361 * code units) in the {@code char} array to be converted
9362 * @return the Unicode code point at the given index
9363 * @throws NullPointerException if {@code a} is null.
9364 * @throws IndexOutOfBoundsException if the value
9365 * {@code index} is negative or not less than
9366 * the length of the {@code char} array.
9367 * @since 1.5
9368 */
9369 public static int codePointAt(char[] a, int index) {
9370 return codePointAtImpl(a, index, a.length);
9371 }
9372
9373 /**
9374 * Returns the code point at the given index of the
9375 * {@code char} array, where only array elements with
9376 * {@code index} less than {@code limit} can be used. If
9377 * the {@code char} value at the given index in the
9378 * {@code char} array is in the high-surrogate range, the
9379 * following index is less than the {@code limit}, and the
9380 * {@code char} value at the following index is in the
9381 * low-surrogate range, then the supplementary code point
9382 * corresponding to this surrogate pair is returned. Otherwise,
9383 * the {@code char} value at the given index is returned.
9384 *
9385 * @param a the {@code char} array
9386 * @param index the index to the {@code char} values (Unicode
9387 * code units) in the {@code char} array to be converted
9388 * @param limit the index after the last array element that
9389 * can be used in the {@code char} array
9390 * @return the Unicode code point at the given index
9391 * @throws NullPointerException if {@code a} is null.
9392 * @throws IndexOutOfBoundsException if the {@code index}
9393 * argument is negative or not less than the {@code limit}
9394 * argument, or if the {@code limit} argument is negative or
9395 * greater than the length of the {@code char} array.
9396 * @since 1.5
9397 */
9398 public static int codePointAt(char[] a, int index, int limit) {
9399 if (index >= limit || index < 0 || limit > a.length) {
9400 throw new IndexOutOfBoundsException();
9401 }
9402 return codePointAtImpl(a, index, limit);
9403 }
9404
9405 // throws ArrayIndexOutOfBoundsException if index out of bounds
9406 static int codePointAtImpl(char[] a, int index, int limit) {
9407 char c1 = a[index];
9408 if (isHighSurrogate(c1) && ++index < limit) {
9409 char c2 = a[index];
9410 if (isLowSurrogate(c2)) {
9411 return toCodePoint(c1, c2);
9412 }
9413 }
9414 return c1;
9415 }
9416
9417 /**
9418 * Returns the code point preceding the given index of the
9419 * {@code CharSequence}. If the {@code char} value at
9420 * {@code (index - 1)} in the {@code CharSequence} is in
9421 * the low-surrogate range, {@code (index - 2)} is not
9422 * negative, and the {@code char} value at {@code (index - 2)}
9423 * in the {@code CharSequence} is in the
9424 * high-surrogate range, then the supplementary code point
9425 * corresponding to this surrogate pair is returned. Otherwise,
9426 * the {@code char} value at {@code (index - 1)} is
9427 * returned.
9428 *
9429 * @param seq the {@code CharSequence} instance
9430 * @param index the index following the code point that should be returned
9431 * @return the Unicode code point value before the given index.
9432 * @throws NullPointerException if {@code seq} is null.
9433 * @throws IndexOutOfBoundsException if the {@code index}
9434 * argument is less than 1 or greater than {@link
9435 * CharSequence#length() seq.length()}.
9436 * @since 1.5
9437 */
9438 public static int codePointBefore(CharSequence seq, int index) {
9439 char c2 = seq.charAt(--index);
9440 if (isLowSurrogate(c2) && index > 0) {
9441 char c1 = seq.charAt(--index);
9442 if (isHighSurrogate(c1)) {
9443 return toCodePoint(c1, c2);
9444 }
9445 }
9446 return c2;
9447 }
9448
9449 /**
9450 * Returns the code point preceding the given index of the
9451 * {@code char} array. If the {@code char} value at
9452 * {@code (index - 1)} in the {@code char} array is in
9453 * the low-surrogate range, {@code (index - 2)} is not
9454 * negative, and the {@code char} value at {@code (index - 2)}
9455 * in the {@code char} array is in the
9456 * high-surrogate range, then the supplementary code point
9457 * corresponding to this surrogate pair is returned. Otherwise,
9458 * the {@code char} value at {@code (index - 1)} is
9459 * returned.
9460 *
9461 * @param a the {@code char} array
9462 * @param index the index following the code point that should be returned
9463 * @return the Unicode code point value before the given index.
9464 * @throws NullPointerException if {@code a} is null.
9465 * @throws IndexOutOfBoundsException if the {@code index}
9466 * argument is less than 1 or greater than the length of the
9467 * {@code char} array
9468 * @since 1.5
9469 */
9470 public static int codePointBefore(char[] a, int index) {
9471 return codePointBeforeImpl(a, index, 0);
9472 }
9473
9474 /**
9475 * Returns the code point preceding the given index of the
9476 * {@code char} array, where only array elements with
9477 * {@code index} greater than or equal to {@code start}
9478 * can be used. If the {@code char} value at {@code (index - 1)}
9479 * in the {@code char} array is in the
9480 * low-surrogate range, {@code (index - 2)} is not less than
9481 * {@code start}, and the {@code char} value at
9482 * {@code (index - 2)} in the {@code char} array is in
9483 * the high-surrogate range, then the supplementary code point
9484 * corresponding to this surrogate pair is returned. Otherwise,
9485 * the {@code char} value at {@code (index - 1)} is
9486 * returned.
9487 *
9488 * @param a the {@code char} array
9489 * @param index the index following the code point that should be returned
9490 * @param start the index of the first array element in the
9491 * {@code char} array
9492 * @return the Unicode code point value before the given index.
9493 * @throws NullPointerException if {@code a} is null.
9494 * @throws IndexOutOfBoundsException if the {@code index}
9495 * argument is not greater than the {@code start} argument or
9496 * is greater than the length of the {@code char} array, or
9497 * if the {@code start} argument is negative or not less than
9498 * the length of the {@code char} array.
9499 * @since 1.5
9500 */
9501 public static int codePointBefore(char[] a, int index, int start) {
9502 if (index <= start || start < 0 || index > a.length) {
9503 throw new IndexOutOfBoundsException();
9504 }
9505 return codePointBeforeImpl(a, index, start);
9506 }
9507
9508 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9509 static int codePointBeforeImpl(char[] a, int index, int start) {
9510 char c2 = a[--index];
9511 if (isLowSurrogate(c2) && index > start) {
9512 char c1 = a[--index];
9513 if (isHighSurrogate(c1)) {
9514 return toCodePoint(c1, c2);
9515 }
9516 }
9517 return c2;
9518 }
9519
9520 /**
9521 * Returns the leading surrogate (a
9522 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9523 * high surrogate code unit</a>) of the
9524 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9525 * surrogate pair</a>
9526 * representing the specified supplementary character (Unicode
9527 * code point) in the UTF-16 encoding. If the specified character
9528 * is not a
9529 * <a href="Character.html#supplementary">supplementary character</a>,
9530 * an unspecified {@code char} is returned.
9531 *
9532 * <p>If
9533 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9534 * is {@code true}, then
9535 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9536 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9537 * are also always {@code true}.
9538 *
9539 * @param codePoint a supplementary character (Unicode code point)
9540 * @return the leading surrogate code unit used to represent the
9541 * character in the UTF-16 encoding
9542 * @since 1.7
9543 */
9544 public static char highSurrogate(int codePoint) {
9545 return (char) ((codePoint >>> 10)
9546 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9547 }
9548
9549 /**
9550 * Returns the trailing surrogate (a
9551 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9552 * low surrogate code unit</a>) of the
9553 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9554 * surrogate pair</a>
9555 * representing the specified supplementary character (Unicode
9556 * code point) in the UTF-16 encoding. If the specified character
9557 * is not a
9558 * <a href="Character.html#supplementary">supplementary character</a>,
9559 * an unspecified {@code char} is returned.
9560 *
9561 * <p>If
9562 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9563 * is {@code true}, then
9564 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9565 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9566 * are also always {@code true}.
9567 *
9568 * @param codePoint a supplementary character (Unicode code point)
9569 * @return the trailing surrogate code unit used to represent the
9570 * character in the UTF-16 encoding
9571 * @since 1.7
9572 */
9573 public static char lowSurrogate(int codePoint) {
9574 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
9575 }
9576
9577 /**
9578 * Converts the specified character (Unicode code point) to its
9579 * UTF-16 representation. If the specified code point is a BMP
9580 * (Basic Multilingual Plane or Plane 0) value, the same value is
9581 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
9582 * specified code point is a supplementary character, its
9583 * surrogate values are stored in {@code dst[dstIndex]}
9584 * (high-surrogate) and {@code dst[dstIndex+1]}
9585 * (low-surrogate), and 2 is returned.
9586 *
9587 * @param codePoint the character (Unicode code point) to be converted.
9588 * @param dst an array of {@code char} in which the
9589 * {@code codePoint}'s UTF-16 value is stored.
9590 * @param dstIndex the start index into the {@code dst}
9591 * array where the converted value is stored.
9592 * @return 1 if the code point is a BMP code point, 2 if the
9593 * code point is a supplementary code point.
9594 * @throws IllegalArgumentException if the specified
9595 * {@code codePoint} is not a valid Unicode code point.
9596 * @throws NullPointerException if the specified {@code dst} is null.
9597 * @throws IndexOutOfBoundsException if {@code dstIndex}
9598 * is negative or not less than {@code dst.length}, or if
9599 * {@code dst} at {@code dstIndex} doesn't have enough
9600 * array element(s) to store the resulting {@code char}
9601 * value(s). (If {@code dstIndex} is equal to
9602 * {@code dst.length-1} and the specified
9603 * {@code codePoint} is a supplementary character, the
9604 * high-surrogate value is not stored in
9605 * {@code dst[dstIndex]}.)
9606 * @since 1.5
9607 */
9608 public static int toChars(int codePoint, char[] dst, int dstIndex) {
9609 if (isBmpCodePoint(codePoint)) {
9610 dst[dstIndex] = (char) codePoint;
9611 return 1;
9612 } else if (isValidCodePoint(codePoint)) {
9613 toSurrogates(codePoint, dst, dstIndex);
9614 return 2;
9615 } else {
9616 throw new IllegalArgumentException(
9617 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9618 }
9619 }
9620
9621 /**
9622 * Converts the specified character (Unicode code point) to its
9623 * UTF-16 representation stored in a {@code char} array. If
9624 * the specified code point is a BMP (Basic Multilingual Plane or
9625 * Plane 0) value, the resulting {@code char} array has
9626 * the same value as {@code codePoint}. If the specified code
9627 * point is a supplementary code point, the resulting
9628 * {@code char} array has the corresponding surrogate pair.
9629 *
9630 * @param codePoint a Unicode code point
9631 * @return a {@code char} array having
9632 * {@code codePoint}'s UTF-16 representation.
9633 * @throws IllegalArgumentException if the specified
9634 * {@code codePoint} is not a valid Unicode code point.
9635 * @since 1.5
9636 */
9637 public static char[] toChars(int codePoint) {
9638 if (isBmpCodePoint(codePoint)) {
9639 return new char[] { (char) codePoint };
9640 } else if (isValidCodePoint(codePoint)) {
9641 char[] result = new char[2];
9642 toSurrogates(codePoint, result, 0);
9643 return result;
9644 } else {
9645 throw new IllegalArgumentException(
9646 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9647 }
9648 }
9649
9650 static void toSurrogates(int codePoint, char[] dst, int index) {
9651 // We write elements "backwards" to guarantee all-or-nothing
9652 dst[index+1] = lowSurrogate(codePoint);
9653 dst[index] = highSurrogate(codePoint);
9654 }
9655
9656 /**
9657 * Returns the number of Unicode code points in the text range of
9658 * the specified char sequence. The text range begins at the
9659 * specified {@code beginIndex} and extends to the
9660 * {@code char} at index {@code endIndex - 1}. Thus the
9661 * length (in {@code char}s) of the text range is
9662 * {@code endIndex-beginIndex}. Unpaired surrogates within
9663 * the text range count as one code point each.
9664 *
9665 * @param seq the char sequence
9666 * @param beginIndex the index to the first {@code char} of
9667 * the text range.
9668 * @param endIndex the index after the last {@code char} of
9669 * the text range.
9670 * @return the number of Unicode code points in the specified text
9671 * range
9672 * @throws NullPointerException if {@code seq} is null.
9673 * @throws IndexOutOfBoundsException if the
9674 * {@code beginIndex} is negative, or {@code endIndex}
9675 * is larger than the length of the given sequence, or
9676 * {@code beginIndex} is larger than {@code endIndex}.
9677 * @since 1.5
9678 */
9679 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
9680 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
9681 int n = endIndex - beginIndex;
9682 for (int i = beginIndex; i < endIndex; ) {
9683 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
9684 isLowSurrogate(seq.charAt(i))) {
9685 n--;
9686 i++;
9687 }
9688 }
9689 return n;
9690 }
9691
9692 /**
9693 * Returns the number of Unicode code points in a subarray of the
9694 * {@code char} array argument. The {@code offset}
9695 * argument is the index of the first {@code char} of the
9696 * subarray and the {@code count} argument specifies the
9697 * length of the subarray in {@code char}s. Unpaired
9698 * surrogates within the subarray count as one code point each.
9699 *
9700 * @param a the {@code char} array
9701 * @param offset the index of the first {@code char} in the
9702 * given {@code char} array
9703 * @param count the length of the subarray in {@code char}s
9704 * @return the number of Unicode code points in the specified subarray
9705 * @throws NullPointerException if {@code a} is null.
9706 * @throws IndexOutOfBoundsException if {@code offset} or
9707 * {@code count} is negative, or if {@code offset +
9708 * count} is larger than the length of the given array.
9709 * @since 1.5
9710 */
9711 public static int codePointCount(char[] a, int offset, int count) {
9712 Objects.checkFromIndexSize(offset, count, a.length);
9713 return codePointCountImpl(a, offset, count);
9714 }
9715
9716 static int codePointCountImpl(char[] a, int offset, int count) {
9717 int endIndex = offset + count;
9718 int n = count;
9719 for (int i = offset; i < endIndex; ) {
9720 if (isHighSurrogate(a[i++]) && i < endIndex &&
9721 isLowSurrogate(a[i])) {
9722 n--;
9723 i++;
9724 }
9725 }
9726 return n;
9727 }
9728
9729 /**
9730 * Returns the index within the given char sequence that is offset
9731 * from the given {@code index} by {@code codePointOffset}
9732 * code points. Unpaired surrogates within the text range given by
9733 * {@code index} and {@code codePointOffset} count as
9734 * one code point each.
9735 *
9736 * @param seq the char sequence
9737 * @param index the index to be offset
9738 * @param codePointOffset the offset in code points
9739 * @return the index within the char sequence
9740 * @throws NullPointerException if {@code seq} is null.
9741 * @throws IndexOutOfBoundsException if {@code index}
9742 * is negative or larger than the length of the char sequence,
9743 * or if {@code codePointOffset} is positive and the
9744 * subsequence starting with {@code index} has fewer than
9745 * {@code codePointOffset} code points, or if
9746 * {@code codePointOffset} is negative and the subsequence
9747 * before {@code index} has fewer than the absolute value
9748 * of {@code codePointOffset} code points.
9749 * @since 1.5
9750 */
9751 public static int offsetByCodePoints(CharSequence seq, int index,
9752 int codePointOffset) {
9753 int length = seq.length();
9754 if (index < 0 || index > length) {
9755 throw new IndexOutOfBoundsException();
9756 }
9757
9758 int x = index;
9759 if (codePointOffset >= 0) {
9760 int i;
9761 for (i = 0; x < length && i < codePointOffset; i++) {
9762 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
9763 isLowSurrogate(seq.charAt(x))) {
9764 x++;
9765 }
9766 }
9767 if (i < codePointOffset) {
9768 throw new IndexOutOfBoundsException();
9769 }
9770 } else {
9771 int i;
9772 for (i = codePointOffset; x > 0 && i < 0; i++) {
9773 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
9774 isHighSurrogate(seq.charAt(x-1))) {
9775 x--;
9776 }
9777 }
9778 if (i < 0) {
9779 throw new IndexOutOfBoundsException();
9780 }
9781 }
9782 return x;
9783 }
9784
9785 /**
9786 * Returns the index within the given {@code char} subarray
9787 * that is offset from the given {@code index} by
9788 * {@code codePointOffset} code points. The
9789 * {@code start} and {@code count} arguments specify a
9790 * subarray of the {@code char} array. Unpaired surrogates
9791 * within the text range given by {@code index} and
9792 * {@code codePointOffset} count as one code point each.
9793 *
9794 * @param a the {@code char} array
9795 * @param start the index of the first {@code char} of the
9796 * subarray
9797 * @param count the length of the subarray in {@code char}s
9798 * @param index the index to be offset
9799 * @param codePointOffset the offset in code points
9800 * @return the index within the subarray
9801 * @throws NullPointerException if {@code a} is null.
9802 * @throws IndexOutOfBoundsException
9803 * if {@code start} or {@code count} is negative,
9804 * or if {@code start + count} is larger than the length of
9805 * the given array,
9806 * or if {@code index} is less than {@code start} or
9807 * larger then {@code start + count},
9808 * or if {@code codePointOffset} is positive and the text range
9809 * starting with {@code index} and ending with {@code start + count - 1}
9810 * has fewer than {@code codePointOffset} code
9811 * points,
9812 * or if {@code codePointOffset} is negative and the text range
9813 * starting with {@code start} and ending with {@code index - 1}
9814 * has fewer than the absolute value of
9815 * {@code codePointOffset} code points.
9816 * @since 1.5
9817 */
9818 public static int offsetByCodePoints(char[] a, int start, int count,
9819 int index, int codePointOffset) {
9820 if (count > a.length-start || start < 0 || count < 0
9821 || index < start || index > start+count) {
9822 throw new IndexOutOfBoundsException();
9823 }
9824 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
9825 }
9826
9827 static int offsetByCodePointsImpl(char[]a, int start, int count,
9828 int index, int codePointOffset) {
9829 int x = index;
9830 if (codePointOffset >= 0) {
9831 int limit = start + count;
9832 int i;
9833 for (i = 0; x < limit && i < codePointOffset; i++) {
9834 if (isHighSurrogate(a[x++]) && x < limit &&
9835 isLowSurrogate(a[x])) {
9836 x++;
9837 }
9838 }
9839 if (i < codePointOffset) {
9840 throw new IndexOutOfBoundsException();
9841 }
9842 } else {
9843 int i;
9844 for (i = codePointOffset; x > start && i < 0; i++) {
9845 if (isLowSurrogate(a[--x]) && x > start &&
9846 isHighSurrogate(a[x-1])) {
9847 x--;
9848 }
9849 }
9850 if (i < 0) {
9851 throw new IndexOutOfBoundsException();
9852 }
9853 }
9854 return x;
9855 }
9856
9857 /**
9858 * Determines if the specified character is a lowercase character.
9859 * <p>
9860 * A character is lowercase if its general category type, provided
9861 * by {@code Character.getType(ch)}, is
9862 * {@code LOWERCASE_LETTER}, or it has contributory property
9863 * Other_Lowercase as defined by the Unicode Standard.
9864 * <p>
9865 * The following are examples of lowercase characters:
9866 * <blockquote><pre>
9867 * 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
9868 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9869 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9870 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9871 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9872 * </pre></blockquote>
9873 * <p> Many other Unicode characters are lowercase too.
9874 *
9875 * <p><b>Note:</b> This method cannot handle <a
9876 * href="#supplementary"> supplementary characters</a>. To support
9877 * all Unicode characters, including supplementary characters, use
9878 * the {@link #isLowerCase(int)} method.
9879 *
9880 * @param ch the character to be tested.
9881 * @return {@code true} if the character is lowercase;
9882 * {@code false} otherwise.
9883 * @see Character#isLowerCase(char)
9884 * @see Character#isTitleCase(char)
9885 * @see Character#toLowerCase(char)
9886 * @see Character#getType(char)
9887 */
9888 public static boolean isLowerCase(char ch) {
9889 return isLowerCase((int)ch);
9890 }
9891
9892 /**
9893 * Determines if the specified character (Unicode code point) is a
9894 * lowercase character.
9895 * <p>
9896 * A character is lowercase if its general category type, provided
9897 * by {@link Character#getType getType(codePoint)}, is
9898 * {@code LOWERCASE_LETTER}, or it has contributory property
9899 * Other_Lowercase as defined by the Unicode Standard.
9900 * <p>
9901 * The following are examples of lowercase characters:
9902 * <blockquote><pre>
9903 * 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
9904 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9905 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9906 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9907 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9908 * </pre></blockquote>
9909 * <p> Many other Unicode characters are lowercase too.
9910 *
9911 * @param codePoint the character (Unicode code point) to be tested.
9912 * @return {@code true} if the character is lowercase;
9913 * {@code false} otherwise.
9914 * @see Character#isLowerCase(int)
9915 * @see Character#isTitleCase(int)
9916 * @see Character#toLowerCase(int)
9917 * @see Character#getType(int)
9918 * @since 1.5
9919 */
9920 public static boolean isLowerCase(int codePoint) {
9921 return CharacterData.of(codePoint).isLowerCase(codePoint);
9922 }
9923
9924 /**
9925 * Determines if the specified character is an uppercase character.
9926 * <p>
9927 * A character is uppercase if its general category type, provided by
9928 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
9929 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9930 * <p>
9931 * The following are examples of uppercase characters:
9932 * <blockquote><pre>
9933 * 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
9934 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9935 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9936 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9937 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9938 * </pre></blockquote>
9939 * <p> Many other Unicode characters are uppercase too.
9940 *
9941 * <p><b>Note:</b> This method cannot handle <a
9942 * href="#supplementary"> supplementary characters</a>. To support
9943 * all Unicode characters, including supplementary characters, use
9944 * the {@link #isUpperCase(int)} method.
9945 *
9946 * @param ch the character to be tested.
9947 * @return {@code true} if the character is uppercase;
9948 * {@code false} otherwise.
9949 * @see Character#isLowerCase(char)
9950 * @see Character#isTitleCase(char)
9951 * @see Character#toUpperCase(char)
9952 * @see Character#getType(char)
9953 * @since 1.0
9954 */
9955 public static boolean isUpperCase(char ch) {
9956 return isUpperCase((int)ch);
9957 }
9958
9959 /**
9960 * Determines if the specified character (Unicode code point) is an uppercase character.
9961 * <p>
9962 * A character is uppercase if its general category type, provided by
9963 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
9964 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9965 * <p>
9966 * The following are examples of uppercase characters:
9967 * <blockquote><pre>
9968 * 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
9969 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9970 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9971 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9972 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9973 * </pre></blockquote>
9974 * <p> Many other Unicode characters are uppercase too.
9975 *
9976 * @param codePoint the character (Unicode code point) to be tested.
9977 * @return {@code true} if the character is uppercase;
9978 * {@code false} otherwise.
9979 * @see Character#isLowerCase(int)
9980 * @see Character#isTitleCase(int)
9981 * @see Character#toUpperCase(int)
9982 * @see Character#getType(int)
9983 * @since 1.5
9984 */
9985 public static boolean isUpperCase(int codePoint) {
9986 return CharacterData.of(codePoint).isUpperCase(codePoint);
9987 }
9988
9989 /**
9990 * Determines if the specified character is a titlecase character.
9991 * <p>
9992 * A character is a titlecase character if its general
9993 * category type, provided by {@code Character.getType(ch)},
9994 * is {@code TITLECASE_LETTER}.
9995 * <p>
9996 * Some characters look like pairs of Latin letters. For example, there
9997 * is an uppercase letter that looks like "LJ" and has a corresponding
9998 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
9999 * is the appropriate form to use when rendering a word in lowercase
10000 * with initial capitals, as for a book title.
10001 * <p>
10002 * These are some of the Unicode characters for which this method returns
10003 * {@code true}:
10004 * <ul>
10005 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10006 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10007 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10008 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10009 * </ul>
10010 * <p> Many other Unicode characters are titlecase too.
10011 *
10012 * <p><b>Note:</b> This method cannot handle <a
10013 * href="#supplementary"> supplementary characters</a>. To support
10014 * all Unicode characters, including supplementary characters, use
10015 * the {@link #isTitleCase(int)} method.
10016 *
10017 * @param ch the character to be tested.
10018 * @return {@code true} if the character is titlecase;
10019 * {@code false} otherwise.
10020 * @see Character#isLowerCase(char)
10021 * @see Character#isUpperCase(char)
10022 * @see Character#toTitleCase(char)
10023 * @see Character#getType(char)
10024 * @since 1.0.2
10025 */
10026 public static boolean isTitleCase(char ch) {
10027 return isTitleCase((int)ch);
10028 }
10029
10030 /**
10031 * Determines if the specified character (Unicode code point) is a titlecase character.
10032 * <p>
10033 * A character is a titlecase character if its general
10034 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10035 * is {@code TITLECASE_LETTER}.
10036 * <p>
10037 * Some characters look like pairs of Latin letters. For example, there
10038 * is an uppercase letter that looks like "LJ" and has a corresponding
10039 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10040 * is the appropriate form to use when rendering a word in lowercase
10041 * with initial capitals, as for a book title.
10042 * <p>
10043 * These are some of the Unicode characters for which this method returns
10044 * {@code true}:
10045 * <ul>
10046 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10047 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10048 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10049 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10050 * </ul>
10051 * <p> Many other Unicode characters are titlecase too.
10052 *
10053 * @param codePoint the character (Unicode code point) to be tested.
10054 * @return {@code true} if the character is titlecase;
10055 * {@code false} otherwise.
10056 * @see Character#isLowerCase(int)
10057 * @see Character#isUpperCase(int)
10058 * @see Character#toTitleCase(int)
10059 * @see Character#getType(int)
10060 * @since 1.5
10061 */
10062 public static boolean isTitleCase(int codePoint) {
10063 return getType(codePoint) == Character.TITLECASE_LETTER;
10064 }
10065
10066 /**
10067 * Determines if the specified character is a digit.
10068 * <p>
10069 * A character is a digit if its general category type, provided
10070 * by {@code Character.getType(ch)}, is
10071 * {@code DECIMAL_DIGIT_NUMBER}.
10072 * <p>
10073 * Some Unicode character ranges that contain digits:
10074 * <ul>
10075 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10076 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10077 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10078 * Arabic-Indic digits
10079 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10080 * Extended Arabic-Indic digits
10081 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10082 * Devanagari digits
10083 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10084 * Fullwidth digits
10085 * </ul>
10086 *
10087 * Many other character ranges contain digits as well.
10088 *
10089 * <p><b>Note:</b> This method cannot handle <a
10090 * href="#supplementary"> supplementary characters</a>. To support
10091 * all Unicode characters, including supplementary characters, use
10092 * the {@link #isDigit(int)} method.
10093 *
10094 * @param ch the character to be tested.
10095 * @return {@code true} if the character is a digit;
10096 * {@code false} otherwise.
10097 * @see Character#digit(char, int)
10098 * @see Character#forDigit(int, int)
10099 * @see Character#getType(char)
10100 */
10101 public static boolean isDigit(char ch) {
10102 return isDigit((int)ch);
10103 }
10104
10105 /**
10106 * Determines if the specified character (Unicode code point) is a digit.
10107 * <p>
10108 * A character is a digit if its general category type, provided
10109 * by {@link Character#getType(int) getType(codePoint)}, is
10110 * {@code DECIMAL_DIGIT_NUMBER}.
10111 * <p>
10112 * Some Unicode character ranges that contain digits:
10113 * <ul>
10114 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10115 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10116 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10117 * Arabic-Indic digits
10118 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10119 * Extended Arabic-Indic digits
10120 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10121 * Devanagari digits
10122 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10123 * Fullwidth digits
10124 * </ul>
10125 *
10126 * Many other character ranges contain digits as well.
10127 *
10128 * @param codePoint the character (Unicode code point) to be tested.
10129 * @return {@code true} if the character is a digit;
10130 * {@code false} otherwise.
10131 * @see Character#forDigit(int, int)
10132 * @see Character#getType(int)
10133 * @since 1.5
10134 */
10135 public static boolean isDigit(int codePoint) {
10136 return CharacterData.of(codePoint).isDigit(codePoint);
10137 }
10138
10139 /**
10140 * Determines if a character is defined in Unicode.
10141 * <p>
10142 * A character is defined if at least one of the following is true:
10143 * <ul>
10144 * <li>It has an entry in the UnicodeData file.
10145 * <li>It has a value in a range defined by the UnicodeData file.
10146 * </ul>
10147 *
10148 * <p><b>Note:</b> This method cannot handle <a
10149 * href="#supplementary"> supplementary characters</a>. To support
10150 * all Unicode characters, including supplementary characters, use
10151 * the {@link #isDefined(int)} method.
10152 *
10153 * @param ch the character to be tested
10154 * @return {@code true} if the character has a defined meaning
10155 * in Unicode; {@code false} otherwise.
10156 * @see Character#isDigit(char)
10157 * @see Character#isLetter(char)
10158 * @see Character#isLetterOrDigit(char)
10159 * @see Character#isLowerCase(char)
10160 * @see Character#isTitleCase(char)
10161 * @see Character#isUpperCase(char)
10162 * @since 1.0.2
10163 */
10164 public static boolean isDefined(char ch) {
10165 return isDefined((int)ch);
10166 }
10167
10168 /**
10169 * Determines if a character (Unicode code point) is defined in Unicode.
10170 * <p>
10171 * A character is defined if at least one of the following is true:
10172 * <ul>
10173 * <li>It has an entry in the UnicodeData file.
10174 * <li>It has a value in a range defined by the UnicodeData file.
10175 * </ul>
10176 *
10177 * @param codePoint the character (Unicode code point) to be tested.
10178 * @return {@code true} if the character has a defined meaning
10179 * in Unicode; {@code false} otherwise.
10180 * @see Character#isDigit(int)
10181 * @see Character#isLetter(int)
10182 * @see Character#isLetterOrDigit(int)
10183 * @see Character#isLowerCase(int)
10184 * @see Character#isTitleCase(int)
10185 * @see Character#isUpperCase(int)
10186 * @since 1.5
10187 */
10188 public static boolean isDefined(int codePoint) {
10189 return getType(codePoint) != Character.UNASSIGNED;
10190 }
10191
10192 /**
10193 * Determines if the specified character is a letter.
10194 * <p>
10195 * A character is considered to be a letter if its general
10196 * category type, provided by {@code Character.getType(ch)},
10197 * is any of the following:
10198 * <ul>
10199 * <li> {@code UPPERCASE_LETTER}
10200 * <li> {@code LOWERCASE_LETTER}
10201 * <li> {@code TITLECASE_LETTER}
10202 * <li> {@code MODIFIER_LETTER}
10203 * <li> {@code OTHER_LETTER}
10204 * </ul>
10205 *
10206 * Not all letters have case. Many characters are
10207 * letters but are neither uppercase nor lowercase nor titlecase.
10208 *
10209 * <p><b>Note:</b> This method cannot handle <a
10210 * href="#supplementary"> supplementary characters</a>. To support
10211 * all Unicode characters, including supplementary characters, use
10212 * the {@link #isLetter(int)} method.
10213 *
10214 * @param ch the character to be tested.
10215 * @return {@code true} if the character is a letter;
10216 * {@code false} otherwise.
10217 * @see Character#isDigit(char)
10218 * @see Character#isJavaIdentifierStart(char)
10219 * @see Character#isJavaLetter(char)
10220 * @see Character#isJavaLetterOrDigit(char)
10221 * @see Character#isLetterOrDigit(char)
10222 * @see Character#isLowerCase(char)
10223 * @see Character#isTitleCase(char)
10224 * @see Character#isUnicodeIdentifierStart(char)
10225 * @see Character#isUpperCase(char)
10226 */
10227 public static boolean isLetter(char ch) {
10228 return isLetter((int)ch);
10229 }
10230
10231 /**
10232 * Determines if the specified character (Unicode code point) is a letter.
10233 * <p>
10234 * A character is considered to be a letter if its general
10235 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10236 * is any of the following:
10237 * <ul>
10238 * <li> {@code UPPERCASE_LETTER}
10239 * <li> {@code LOWERCASE_LETTER}
10240 * <li> {@code TITLECASE_LETTER}
10241 * <li> {@code MODIFIER_LETTER}
10242 * <li> {@code OTHER_LETTER}
10243 * </ul>
10244 *
10245 * Not all letters have case. Many characters are
10246 * letters but are neither uppercase nor lowercase nor titlecase.
10247 *
10248 * @param codePoint the character (Unicode code point) to be tested.
10249 * @return {@code true} if the character is a letter;
10250 * {@code false} otherwise.
10251 * @see Character#isDigit(int)
10252 * @see Character#isJavaIdentifierStart(int)
10253 * @see Character#isLetterOrDigit(int)
10254 * @see Character#isLowerCase(int)
10255 * @see Character#isTitleCase(int)
10256 * @see Character#isUnicodeIdentifierStart(int)
10257 * @see Character#isUpperCase(int)
10258 * @since 1.5
10259 */
10260 public static boolean isLetter(int codePoint) {
10261 return ((((1 << Character.UPPERCASE_LETTER) |
10262 (1 << Character.LOWERCASE_LETTER) |
10263 (1 << Character.TITLECASE_LETTER) |
10264 (1 << Character.MODIFIER_LETTER) |
10265 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10266 != 0;
10267 }
10268
10269 /**
10270 * Determines if the specified character is a letter or digit.
10271 * <p>
10272 * A character is considered to be a letter or digit if either
10273 * {@code Character.isLetter(char ch)} or
10274 * {@code Character.isDigit(char ch)} returns
10275 * {@code true} for the character.
10276 *
10277 * <p><b>Note:</b> This method cannot handle <a
10278 * href="#supplementary"> supplementary characters</a>. To support
10279 * all Unicode characters, including supplementary characters, use
10280 * the {@link #isLetterOrDigit(int)} method.
10281 *
10282 * @param ch the character to be tested.
10283 * @return {@code true} if the character is a letter or digit;
10284 * {@code false} otherwise.
10285 * @see Character#isDigit(char)
10286 * @see Character#isJavaIdentifierPart(char)
10287 * @see Character#isJavaLetter(char)
10288 * @see Character#isJavaLetterOrDigit(char)
10289 * @see Character#isLetter(char)
10290 * @see Character#isUnicodeIdentifierPart(char)
10291 * @since 1.0.2
10292 */
10293 public static boolean isLetterOrDigit(char ch) {
10294 return isLetterOrDigit((int)ch);
10295 }
10296
10297 /**
10298 * Determines if the specified character (Unicode code point) is a letter or digit.
10299 * <p>
10300 * A character is considered to be a letter or digit if either
10301 * {@link #isLetter(int) isLetter(codePoint)} or
10302 * {@link #isDigit(int) isDigit(codePoint)} returns
10303 * {@code true} for the character.
10304 *
10305 * @param codePoint the character (Unicode code point) to be tested.
10306 * @return {@code true} if the character is a letter or digit;
10307 * {@code false} otherwise.
10308 * @see Character#isDigit(int)
10309 * @see Character#isJavaIdentifierPart(int)
10310 * @see Character#isLetter(int)
10311 * @see Character#isUnicodeIdentifierPart(int)
10312 * @since 1.5
10313 */
10314 public static boolean isLetterOrDigit(int codePoint) {
10315 return ((((1 << Character.UPPERCASE_LETTER) |
10316 (1 << Character.LOWERCASE_LETTER) |
10317 (1 << Character.TITLECASE_LETTER) |
10318 (1 << Character.MODIFIER_LETTER) |
10319 (1 << Character.OTHER_LETTER) |
10320 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10321 != 0;
10322 }
10323
10324 /**
10325 * Determines if the specified character is permissible as the first
10326 * character in a Java identifier.
10327 * <p>
10328 * A character may start a Java identifier if and only if
10329 * one of the following conditions is true:
10330 * <ul>
10331 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10332 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10333 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10334 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10335 * </ul>
10336 *
10337 * @param ch the character to be tested.
10338 * @return {@code true} if the character may start a Java
10339 * identifier; {@code false} otherwise.
10340 * @see Character#isJavaLetterOrDigit(char)
10341 * @see Character#isJavaIdentifierStart(char)
10342 * @see Character#isJavaIdentifierPart(char)
10343 * @see Character#isLetter(char)
10344 * @see Character#isLetterOrDigit(char)
10345 * @see Character#isUnicodeIdentifierStart(char)
10346 * @since 1.0.2
10347 * @deprecated Replaced by isJavaIdentifierStart(char).
10348 */
10349 @Deprecated(since="1.1")
10350 public static boolean isJavaLetter(char ch) {
10351 return isJavaIdentifierStart(ch);
10352 }
10353
10354 /**
10355 * Determines if the specified character may be part of a Java
10356 * identifier as other than the first character.
10357 * <p>
10358 * A character may be part of a Java identifier if and only if one
10359 * of the following conditions is true:
10360 * <ul>
10361 * <li> it is a letter
10362 * <li> it is a currency symbol (such as {@code '$'})
10363 * <li> it is a connecting punctuation character (such as {@code '_'})
10364 * <li> it is a digit
10365 * <li> it is a numeric letter (such as a Roman numeral character)
10366 * <li> it is a combining mark
10367 * <li> it is a non-spacing mark
10368 * <li> {@code isIdentifierIgnorable} returns
10369 * {@code true} for the character.
10370 * </ul>
10371 *
10372 * @param ch the character to be tested.
10373 * @return {@code true} if the character may be part of a
10374 * Java identifier; {@code false} otherwise.
10375 * @see Character#isJavaLetter(char)
10376 * @see Character#isJavaIdentifierStart(char)
10377 * @see Character#isJavaIdentifierPart(char)
10378 * @see Character#isLetter(char)
10379 * @see Character#isLetterOrDigit(char)
10380 * @see Character#isUnicodeIdentifierPart(char)
10381 * @see Character#isIdentifierIgnorable(char)
10382 * @since 1.0.2
10383 * @deprecated Replaced by isJavaIdentifierPart(char).
10384 */
10385 @Deprecated(since="1.1")
10386 public static boolean isJavaLetterOrDigit(char ch) {
10387 return isJavaIdentifierPart(ch);
10388 }
10389
10390 /**
10391 * Determines if the specified character (Unicode code point) is alphabetic.
10392 * <p>
10393 * A character is considered to be alphabetic if its general category type,
10394 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10395 * the following:
10396 * <ul>
10397 * <li> {@code UPPERCASE_LETTER}
10398 * <li> {@code LOWERCASE_LETTER}
10399 * <li> {@code TITLECASE_LETTER}
10400 * <li> {@code MODIFIER_LETTER}
10401 * <li> {@code OTHER_LETTER}
10402 * <li> {@code LETTER_NUMBER}
10403 * </ul>
10404 * or it has contributory property Other_Alphabetic as defined by the
10405 * Unicode Standard.
10406 *
10407 * @param codePoint the character (Unicode code point) to be tested.
10408 * @return {@code true} if the character is a Unicode alphabet
10409 * character, {@code false} otherwise.
10410 * @since 1.7
10411 */
10412 public static boolean isAlphabetic(int codePoint) {
10413 return (((((1 << Character.UPPERCASE_LETTER) |
10414 (1 << Character.LOWERCASE_LETTER) |
10415 (1 << Character.TITLECASE_LETTER) |
10416 (1 << Character.MODIFIER_LETTER) |
10417 (1 << Character.OTHER_LETTER) |
10418 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10419 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10420 }
10421
10422 /**
10423 * Determines if the specified character (Unicode code point) is a CJKV
10424 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10425 * the Unicode Standard.
10426 *
10427 * @param codePoint the character (Unicode code point) to be tested.
10428 * @return {@code true} if the character is a Unicode ideograph
10429 * character, {@code false} otherwise.
10430 * @since 1.7
10431 */
10432 public static boolean isIdeographic(int codePoint) {
10433 return CharacterData.of(codePoint).isIdeographic(codePoint);
10434 }
10435
10436 /**
10437 * Determines if the specified character is
10438 * permissible as the first character in a Java identifier.
10439 * <p>
10440 * A character may start a Java identifier if and only if
10441 * one of the following conditions is true:
10442 * <ul>
10443 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10444 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10445 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10446 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10447 * </ul>
10448 *
10449 * <p><b>Note:</b> This method cannot handle <a
10450 * href="#supplementary"> supplementary characters</a>. To support
10451 * all Unicode characters, including supplementary characters, use
10452 * the {@link #isJavaIdentifierStart(int)} method.
10453 *
10454 * @param ch the character to be tested.
10455 * @return {@code true} if the character may start a Java identifier;
10456 * {@code false} otherwise.
10457 * @see Character#isJavaIdentifierPart(char)
10458 * @see Character#isLetter(char)
10459 * @see Character#isUnicodeIdentifierStart(char)
10460 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10461 * @since 1.1
10462 */
10463 @SuppressWarnings("doclint:reference") // cross-module links
10464 public static boolean isJavaIdentifierStart(char ch) {
10465 return isJavaIdentifierStart((int)ch);
10466 }
10467
10468 /**
10469 * Determines if the character (Unicode code point) is
10470 * permissible as the first character in a Java identifier.
10471 * <p>
10472 * A character may start a Java identifier if and only if
10473 * one of the following conditions is true:
10474 * <ul>
10475 * <li> {@link #isLetter(int) isLetter(codePoint)}
10476 * returns {@code true}
10477 * <li> {@link #getType(int) getType(codePoint)}
10478 * returns {@code LETTER_NUMBER}
10479 * <li> the referenced character is a currency symbol (such as {@code '$'})
10480 * <li> the referenced character is a connecting punctuation character
10481 * (such as {@code '_'}).
10482 * </ul>
10483 *
10484 * @param codePoint the character (Unicode code point) to be tested.
10485 * @return {@code true} if the character may start a Java identifier;
10486 * {@code false} otherwise.
10487 * @see Character#isJavaIdentifierPart(int)
10488 * @see Character#isLetter(int)
10489 * @see Character#isUnicodeIdentifierStart(int)
10490 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10491 * @since 1.5
10492 */
10493 @SuppressWarnings("doclint:reference") // cross-module links
10494 public static boolean isJavaIdentifierStart(int codePoint) {
10495 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10496 }
10497
10498 /**
10499 * Determines if the specified character may be part of a Java
10500 * identifier as other than the first character.
10501 * <p>
10502 * A character may be part of a Java identifier if any of the following
10503 * conditions are true:
10504 * <ul>
10505 * <li> it is a letter
10506 * <li> it is a currency symbol (such as {@code '$'})
10507 * <li> it is a connecting punctuation character (such as {@code '_'})
10508 * <li> it is a digit
10509 * <li> it is a numeric letter (such as a Roman numeral character)
10510 * <li> it is a combining mark
10511 * <li> it is a non-spacing mark
10512 * <li> {@code isIdentifierIgnorable} returns
10513 * {@code true} for the character
10514 * </ul>
10515 *
10516 * <p><b>Note:</b> This method cannot handle <a
10517 * href="#supplementary"> supplementary characters</a>. To support
10518 * all Unicode characters, including supplementary characters, use
10519 * the {@link #isJavaIdentifierPart(int)} method.
10520 *
10521 * @param ch the character to be tested.
10522 * @return {@code true} if the character may be part of a
10523 * Java identifier; {@code false} otherwise.
10524 * @see Character#isIdentifierIgnorable(char)
10525 * @see Character#isJavaIdentifierStart(char)
10526 * @see Character#isLetterOrDigit(char)
10527 * @see Character#isUnicodeIdentifierPart(char)
10528 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10529 * @since 1.1
10530 */
10531 @SuppressWarnings("doclint:reference") // cross-module links
10532 public static boolean isJavaIdentifierPart(char ch) {
10533 return isJavaIdentifierPart((int)ch);
10534 }
10535
10536 /**
10537 * Determines if the character (Unicode code point) may be part of a Java
10538 * identifier as other than the first character.
10539 * <p>
10540 * A character may be part of a Java identifier if any of the following
10541 * conditions are true:
10542 * <ul>
10543 * <li> it is a letter
10544 * <li> it is a currency symbol (such as {@code '$'})
10545 * <li> it is a connecting punctuation character (such as {@code '_'})
10546 * <li> it is a digit
10547 * <li> it is a numeric letter (such as a Roman numeral character)
10548 * <li> it is a combining mark
10549 * <li> it is a non-spacing mark
10550 * <li> {@link #isIdentifierIgnorable(int)
10551 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10552 * the code point
10553 * </ul>
10554 *
10555 * @param codePoint the character (Unicode code point) to be tested.
10556 * @return {@code true} if the character may be part of a
10557 * Java identifier; {@code false} otherwise.
10558 * @see Character#isIdentifierIgnorable(int)
10559 * @see Character#isJavaIdentifierStart(int)
10560 * @see Character#isLetterOrDigit(int)
10561 * @see Character#isUnicodeIdentifierPart(int)
10562 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10563 * @since 1.5
10564 */
10565 @SuppressWarnings("doclint:reference") // cross-module links
10566 public static boolean isJavaIdentifierPart(int codePoint) {
10567 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10568 }
10569
10570 /**
10571 * Determines if the specified character is permissible as the
10572 * first character in a Unicode identifier.
10573 * <p>
10574 * A character may start a Unicode identifier if and only if
10575 * one of the following conditions is true:
10576 * <ul>
10577 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10578 * <li> {@link #getType(char) getType(ch)} returns
10579 * {@code LETTER_NUMBER}.
10580 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10581 * {@code Other_ID_Start}</a> character.
10582 * </ul>
10583 * <p>
10584 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10585 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10586 * with the following profile of UAX31:
10587 * <pre>
10588 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10589 * </pre>
10590 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10591 * compatibility.
10592 *
10593 * <p><b>Note:</b> This method cannot handle <a
10594 * href="#supplementary"> supplementary characters</a>. To support
10595 * all Unicode characters, including supplementary characters, use
10596 * the {@link #isUnicodeIdentifierStart(int)} method.
10597 *
10598 * @param ch the character to be tested.
10599 * @return {@code true} if the character may start a Unicode
10600 * identifier; {@code false} otherwise.
10601 *
10602 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10603 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10604 * @see Character#isJavaIdentifierStart(char)
10605 * @see Character#isLetter(char)
10606 * @see Character#isUnicodeIdentifierPart(char)
10607 * @since 1.1
10608 */
10609 public static boolean isUnicodeIdentifierStart(char ch) {
10610 return isUnicodeIdentifierStart((int)ch);
10611 }
10612
10613 /**
10614 * Determines if the specified character (Unicode code point) is permissible as the
10615 * first character in a Unicode identifier.
10616 * <p>
10617 * A character may start a Unicode identifier if and only if
10618 * one of the following conditions is true:
10619 * <ul>
10620 * <li> {@link #isLetter(int) isLetter(codePoint)}
10621 * returns {@code true}
10622 * <li> {@link #getType(int) getType(codePoint)}
10623 * returns {@code LETTER_NUMBER}.
10624 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10625 * {@code Other_ID_Start}</a> character.
10626 * </ul>
10627 * <p>
10628 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10629 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10630 * with the following profile of UAX31:
10631 * <pre>
10632 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10633 * </pre>
10634 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10635 * compatibility.
10636 *
10637 * @param codePoint the character (Unicode code point) to be tested.
10638 * @return {@code true} if the character may start a Unicode
10639 * identifier; {@code false} otherwise.
10640 *
10641 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10642 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10643 * @see Character#isJavaIdentifierStart(int)
10644 * @see Character#isLetter(int)
10645 * @see Character#isUnicodeIdentifierPart(int)
10646 * @since 1.5
10647 */
10648 public static boolean isUnicodeIdentifierStart(int codePoint) {
10649 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
10650 }
10651
10652 /**
10653 * Determines if the specified character may be part of a Unicode
10654 * identifier as other than the first character.
10655 * <p>
10656 * A character may be part of a Unicode identifier if and only if
10657 * one of the following statements is true:
10658 * <ul>
10659 * <li> it is a letter
10660 * <li> it is a connecting punctuation character (such as {@code '_'})
10661 * <li> it is a digit
10662 * <li> it is a numeric letter (such as a Roman numeral character)
10663 * <li> it is a combining mark
10664 * <li> it is a non-spacing mark
10665 * <li> {@code isIdentifierIgnorable} returns
10666 * {@code true} for this character.
10667 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10668 * {@code Other_ID_Start}</a> character.
10669 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10670 * {@code Other_ID_Continue}</a> character.
10671 * </ul>
10672 * <p>
10673 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10674 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10675 * with the following profile of UAX31:
10676 * <pre>
10677 * Continue := Start + ID_Continue + ignorable
10678 * Medial := empty
10679 * ignorable := isIdentifierIgnorable(char) returns true for the character
10680 * </pre>
10681 * {@code ignorable} is added to {@code Continue} for backward
10682 * compatibility.
10683 *
10684 * <p><b>Note:</b> This method cannot handle <a
10685 * href="#supplementary"> supplementary characters</a>. To support
10686 * all Unicode characters, including supplementary characters, use
10687 * the {@link #isUnicodeIdentifierPart(int)} method.
10688 *
10689 * @param ch the character to be tested.
10690 * @return {@code true} if the character may be part of a
10691 * Unicode identifier; {@code false} otherwise.
10692 *
10693 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10694 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10695 * @see Character#isIdentifierIgnorable(char)
10696 * @see Character#isJavaIdentifierPart(char)
10697 * @see Character#isLetterOrDigit(char)
10698 * @see Character#isUnicodeIdentifierStart(char)
10699 * @since 1.1
10700 */
10701 public static boolean isUnicodeIdentifierPart(char ch) {
10702 return isUnicodeIdentifierPart((int)ch);
10703 }
10704
10705 /**
10706 * Determines if the specified character (Unicode code point) may be part of a Unicode
10707 * identifier as other than the first character.
10708 * <p>
10709 * A character may be part of a Unicode identifier if and only if
10710 * one of the following statements is true:
10711 * <ul>
10712 * <li> it is a letter
10713 * <li> it is a connecting punctuation character (such as {@code '_'})
10714 * <li> it is a digit
10715 * <li> it is a numeric letter (such as a Roman numeral character)
10716 * <li> it is a combining mark
10717 * <li> it is a non-spacing mark
10718 * <li> {@code isIdentifierIgnorable} returns
10719 * {@code true} for this character.
10720 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10721 * {@code Other_ID_Start}</a> character.
10722 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10723 * {@code Other_ID_Continue}</a> character.
10724 * </ul>
10725 * <p>
10726 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10727 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10728 * with the following profile of UAX31:
10729 * <pre>
10730 * Continue := Start + ID_Continue + ignorable
10731 * Medial := empty
10732 * ignorable := isIdentifierIgnorable(int) returns true for the character
10733 * </pre>
10734 * {@code ignorable} is added to {@code Continue} for backward
10735 * compatibility.
10736 *
10737 * @param codePoint the character (Unicode code point) to be tested.
10738 * @return {@code true} if the character may be part of a
10739 * Unicode identifier; {@code false} otherwise.
10740 *
10741 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10742 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10743 * @see Character#isIdentifierIgnorable(int)
10744 * @see Character#isJavaIdentifierPart(int)
10745 * @see Character#isLetterOrDigit(int)
10746 * @see Character#isUnicodeIdentifierStart(int)
10747 * @since 1.5
10748 */
10749 public static boolean isUnicodeIdentifierPart(int codePoint) {
10750 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
10751 }
10752
10753 /**
10754 * Determines if the specified character should be regarded as
10755 * an ignorable character in a Java identifier or a Unicode identifier.
10756 * <p>
10757 * The following Unicode characters are ignorable in a Java identifier
10758 * or a Unicode identifier:
10759 * <ul>
10760 * <li>ISO control characters that are not whitespace
10761 * <ul>
10762 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
10763 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
10764 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
10765 * </ul>
10766 *
10767 * <li>all characters that have the {@code FORMAT} general
10768 * category value
10769 * </ul>
10770 *
10771 * <p><b>Note:</b> This method cannot handle <a
10772 * href="#supplementary"> supplementary characters</a>. To support
10773 * all Unicode characters, including supplementary characters, use
10774 * the {@link #isIdentifierIgnorable(int)} method.
10775 *
10776 * @param ch the character to be tested.
10777 * @return {@code true} if the character is an ignorable control
10778 * character that may be part of a Java or Unicode identifier;
10779 * {@code false} otherwise.
10780 * @see Character#isJavaIdentifierPart(char)
10781 * @see Character#isUnicodeIdentifierPart(char)
10782 * @since 1.1
10783 */
10784 public static boolean isIdentifierIgnorable(char ch) {
10785 return isIdentifierIgnorable((int)ch);
10786 }
10787
10788 /**
10789 * Determines if the specified character (Unicode code point) should be regarded as
10790 * an ignorable character in a Java identifier or a Unicode identifier.
10791 * <p>
10792 * The following Unicode characters are ignorable in a Java identifier
10793 * or a Unicode identifier:
10794 * <ul>
10795 * <li>ISO control characters that are not whitespace
10796 * <ul>
10797 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
10798 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
10799 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
10800 * </ul>
10801 *
10802 * <li>all characters that have the {@code FORMAT} general
10803 * category value
10804 * </ul>
10805 *
10806 * @param codePoint the character (Unicode code point) to be tested.
10807 * @return {@code true} if the character is an ignorable control
10808 * character that may be part of a Java or Unicode identifier;
10809 * {@code false} otherwise.
10810 * @see Character#isJavaIdentifierPart(int)
10811 * @see Character#isUnicodeIdentifierPart(int)
10812 * @since 1.5
10813 */
10814 public static boolean isIdentifierIgnorable(int codePoint) {
10815 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
10816 }
10817
10818 /**
10819 * Determines if the specified character (Unicode code point) is an Emoji.
10820 * <p>
10821 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
10822 * property, defined in
10823 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10824 * Unicode Emoji (Technical Standard #51)</a>.
10825 *
10826 * @param codePoint the character (Unicode code point) to be tested.
10827 * @return {@code true} if the character is an Emoji;
10828 * {@code false} otherwise.
10829 * @since 21
10830 */
10831 public static boolean isEmoji(int codePoint) {
10832 return CharacterData.of(codePoint).isEmoji(codePoint);
10833 }
10834
10835 /**
10836 * Determines if the specified character (Unicode code point) has the
10837 * Emoji Presentation property by default.
10838 * <p>
10839 * A character is considered to have the Emoji Presentation property if and
10840 * only if it has the {@code Emoji_Presentation} property, defined in
10841 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10842 * Unicode Emoji (Technical Standard #51)</a>.
10843 *
10844 * @param codePoint the character (Unicode code point) to be tested.
10845 * @return {@code true} if the character has the Emoji Presentation
10846 * property; {@code false} otherwise.
10847 * @since 21
10848 */
10849 public static boolean isEmojiPresentation(int codePoint) {
10850 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
10851 }
10852
10853 /**
10854 * Determines if the specified character (Unicode code point) is an
10855 * Emoji Modifier.
10856 * <p>
10857 * A character is considered to be an Emoji Modifier if and only if it has
10858 * the {@code Emoji_Modifier} property, defined in
10859 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10860 * Unicode Emoji (Technical Standard #51)</a>.
10861 *
10862 * @param codePoint the character (Unicode code point) to be tested.
10863 * @return {@code true} if the character is an Emoji Modifier;
10864 * {@code false} otherwise.
10865 * @since 21
10866 */
10867 public static boolean isEmojiModifier(int codePoint) {
10868 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
10869 }
10870
10871 /**
10872 * Determines if the specified character (Unicode code point) is an
10873 * Emoji Modifier Base.
10874 * <p>
10875 * A character is considered to be an Emoji Modifier Base if and only if it has
10876 * the {@code Emoji_Modifier_Base} property, defined in
10877 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10878 * Unicode Emoji (Technical Standard #51)</a>.
10879 *
10880 * @param codePoint the character (Unicode code point) to be tested.
10881 * @return {@code true} if the character is an Emoji Modifier Base;
10882 * {@code false} otherwise.
10883 * @since 21
10884 */
10885 public static boolean isEmojiModifierBase(int codePoint) {
10886 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
10887 }
10888
10889 /**
10890 * Determines if the specified character (Unicode code point) is an
10891 * Emoji Component.
10892 * <p>
10893 * A character is considered to be an Emoji Component if and only if it has
10894 * the {@code Emoji_Component} property, defined in
10895 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10896 * Unicode Emoji (Technical Standard #51)</a>.
10897 *
10898 * @param codePoint the character (Unicode code point) to be tested.
10899 * @return {@code true} if the character is an Emoji Component;
10900 * {@code false} otherwise.
10901 * @since 21
10902 */
10903 public static boolean isEmojiComponent(int codePoint) {
10904 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
10905 }
10906
10907 /**
10908 * Determines if the specified character (Unicode code point) is
10909 * an Extended Pictographic.
10910 * <p>
10911 * A character is considered to be an Extended Pictographic if and only if it has
10912 * the {@code Extended_Pictographic} property, defined in
10913 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10914 * Unicode Emoji (Technical Standard #51)</a>.
10915 *
10916 * @param codePoint the character (Unicode code point) to be tested.
10917 * @return {@code true} if the character is an Extended Pictographic;
10918 * {@code false} otherwise.
10919 * @since 21
10920 */
10921 public static boolean isExtendedPictographic(int codePoint) {
10922 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
10923 }
10924
10925 /**
10926 * Converts the character argument to lowercase using case
10927 * mapping information from the UnicodeData file.
10928 * <p>
10929 * Note that
10930 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
10931 * does not always return {@code true} for some ranges of
10932 * characters, particularly those that are symbols or ideographs.
10933 *
10934 * <p>In general, {@link String#toLowerCase()} should be used to map
10935 * characters to lowercase. {@code String} case mapping methods
10936 * have several benefits over {@code Character} case mapping methods.
10937 * {@code String} case mapping methods can perform locale-sensitive
10938 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10939 * the {@code Character} case mapping methods cannot.
10940 *
10941 * <p><b>Note:</b> This method cannot handle <a
10942 * href="#supplementary"> supplementary characters</a>. To support
10943 * all Unicode characters, including supplementary characters, use
10944 * the {@link #toLowerCase(int)} method.
10945 *
10946 * @param ch the character to be converted.
10947 * @return the lowercase equivalent of the character, if any;
10948 * otherwise, the character itself.
10949 * @see Character#isLowerCase(char)
10950 * @see String#toLowerCase()
10951 */
10952 public static char toLowerCase(char ch) {
10953 return (char)toLowerCase((int)ch);
10954 }
10955
10956 /**
10957 * Converts the character (Unicode code point) argument to
10958 * lowercase using case mapping information from the UnicodeData
10959 * file.
10960 *
10961 * <p> Note that
10962 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
10963 * does not always return {@code true} for some ranges of
10964 * characters, particularly those that are symbols or ideographs.
10965 *
10966 * <p>In general, {@link String#toLowerCase()} should be used to map
10967 * characters to lowercase. {@code String} case mapping methods
10968 * have several benefits over {@code Character} case mapping methods.
10969 * {@code String} case mapping methods can perform locale-sensitive
10970 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10971 * the {@code Character} case mapping methods cannot.
10972 *
10973 * @param codePoint the character (Unicode code point) to be converted.
10974 * @return the lowercase equivalent of the character (Unicode code
10975 * point), if any; otherwise, the character itself.
10976 * @see Character#isLowerCase(int)
10977 * @see String#toLowerCase()
10978 *
10979 * @since 1.5
10980 */
10981 public static int toLowerCase(int codePoint) {
10982 return CharacterData.of(codePoint).toLowerCase(codePoint);
10983 }
10984
10985 /**
10986 * Converts the character argument to uppercase using case mapping
10987 * information from the UnicodeData file.
10988 * <p>
10989 * Note that
10990 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
10991 * does not always return {@code true} for some ranges of
10992 * characters, particularly those that are symbols or ideographs.
10993 *
10994 * <p>In general, {@link String#toUpperCase()} should be used to map
10995 * characters to uppercase. {@code String} case mapping methods
10996 * have several benefits over {@code Character} case mapping methods.
10997 * {@code String} case mapping methods can perform locale-sensitive
10998 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10999 * the {@code Character} case mapping methods cannot.
11000 *
11001 * <p><b>Note:</b> This method cannot handle <a
11002 * href="#supplementary"> supplementary characters</a>. To support
11003 * all Unicode characters, including supplementary characters, use
11004 * the {@link #toUpperCase(int)} method.
11005 *
11006 * @param ch the character to be converted.
11007 * @return the uppercase equivalent of the character, if any;
11008 * otherwise, the character itself.
11009 * @see Character#isUpperCase(char)
11010 * @see String#toUpperCase()
11011 */
11012 public static char toUpperCase(char ch) {
11013 return (char)toUpperCase((int)ch);
11014 }
11015
11016 /**
11017 * Converts the character (Unicode code point) argument to
11018 * uppercase using case mapping information from the UnicodeData
11019 * file.
11020 *
11021 * <p>Note that
11022 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11023 * does not always return {@code true} for some ranges of
11024 * characters, particularly those that are symbols or ideographs.
11025 *
11026 * <p>In general, {@link String#toUpperCase()} should be used to map
11027 * characters to uppercase. {@code String} case mapping methods
11028 * have several benefits over {@code Character} case mapping methods.
11029 * {@code String} case mapping methods can perform locale-sensitive
11030 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11031 * the {@code Character} case mapping methods cannot.
11032 *
11033 * @param codePoint the character (Unicode code point) to be converted.
11034 * @return the uppercase equivalent of the character, if any;
11035 * otherwise, the character itself.
11036 * @see Character#isUpperCase(int)
11037 * @see String#toUpperCase()
11038 *
11039 * @since 1.5
11040 */
11041 public static int toUpperCase(int codePoint) {
11042 return CharacterData.of(codePoint).toUpperCase(codePoint);
11043 }
11044
11045 /**
11046 * Converts the character argument to titlecase using case mapping
11047 * information from the UnicodeData file. If a character has no
11048 * explicit titlecase mapping and is not itself a titlecase char
11049 * according to UnicodeData, then the uppercase mapping is
11050 * returned as an equivalent titlecase mapping. If the
11051 * {@code char} argument is already a titlecase
11052 * {@code char}, the same {@code char} value will be
11053 * returned.
11054 * <p>
11055 * Note that
11056 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11057 * does not always return {@code true} for some ranges of
11058 * characters.
11059 *
11060 * <p><b>Note:</b> This method cannot handle <a
11061 * href="#supplementary"> supplementary characters</a>. To support
11062 * all Unicode characters, including supplementary characters, use
11063 * the {@link #toTitleCase(int)} method.
11064 *
11065 * @param ch the character to be converted.
11066 * @return the titlecase equivalent of the character, if any;
11067 * otherwise, the character itself.
11068 * @see Character#isTitleCase(char)
11069 * @see Character#toLowerCase(char)
11070 * @see Character#toUpperCase(char)
11071 * @since 1.0.2
11072 */
11073 public static char toTitleCase(char ch) {
11074 return (char)toTitleCase((int)ch);
11075 }
11076
11077 /**
11078 * Converts the character (Unicode code point) argument to titlecase using case mapping
11079 * information from the UnicodeData file. If a character has no
11080 * explicit titlecase mapping and is not itself a titlecase char
11081 * according to UnicodeData, then the uppercase mapping is
11082 * returned as an equivalent titlecase mapping. If the
11083 * character argument is already a titlecase
11084 * character, the same character value will be
11085 * returned.
11086 *
11087 * <p>Note that
11088 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11089 * does not always return {@code true} for some ranges of
11090 * characters.
11091 *
11092 * @param codePoint the character (Unicode code point) to be converted.
11093 * @return the titlecase equivalent of the character, if any;
11094 * otherwise, the character itself.
11095 * @see Character#isTitleCase(int)
11096 * @see Character#toLowerCase(int)
11097 * @see Character#toUpperCase(int)
11098 * @since 1.5
11099 */
11100 public static int toTitleCase(int codePoint) {
11101 return CharacterData.of(codePoint).toTitleCase(codePoint);
11102 }
11103
11104 /**
11105 * Returns the numeric value of the character {@code ch} in the
11106 * specified radix.
11107 * <p>
11108 * If the radix is not in the range {@code MIN_RADIX} ≤
11109 * {@code radix} ≤ {@code MAX_RADIX} or if the
11110 * value of {@code ch} is not a valid digit in the specified
11111 * radix, {@code -1} is returned. A character is a valid digit
11112 * if at least one of the following is true:
11113 * <ul>
11114 * <li>The method {@code isDigit} is {@code true} of the character
11115 * and the Unicode decimal digit value of the character (or its
11116 * single-character decomposition) is less than the specified radix.
11117 * In this case the decimal digit value is returned.
11118 * <li>The character is one of the uppercase Latin letters
11119 * {@code 'A'} through {@code 'Z'} and its code is less than
11120 * {@code radix + 'A' - 10}.
11121 * In this case, {@code ch - 'A' + 10}
11122 * is returned.
11123 * <li>The character is one of the lowercase Latin letters
11124 * {@code 'a'} through {@code 'z'} and its code is less than
11125 * {@code radix + 'a' - 10}.
11126 * In this case, {@code ch - 'a' + 10}
11127 * is returned.
11128 * <li>The character is one of the fullwidth uppercase Latin letters A
11129 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11130 * and its code is less than
11131 * {@code radix + '\u005CuFF21' - 10}.
11132 * In this case, {@code ch - '\u005CuFF21' + 10}
11133 * is returned.
11134 * <li>The character is one of the fullwidth lowercase Latin letters a
11135 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11136 * and its code is less than
11137 * {@code radix + '\u005CuFF41' - 10}.
11138 * In this case, {@code ch - '\u005CuFF41' + 10}
11139 * is returned.
11140 * </ul>
11141 *
11142 * <p><b>Note:</b> This method cannot handle <a
11143 * href="#supplementary"> supplementary characters</a>. To support
11144 * all Unicode characters, including supplementary characters, use
11145 * the {@link #digit(int, int)} method.
11146 *
11147 * @param ch the character to be converted.
11148 * @param radix the radix.
11149 * @return the numeric value represented by the character in the
11150 * specified radix.
11151 * @see Character#forDigit(int, int)
11152 * @see Character#isDigit(char)
11153 */
11154 public static int digit(char ch, int radix) {
11155 return digit((int)ch, radix);
11156 }
11157
11158 /**
11159 * Returns the numeric value of the specified character (Unicode
11160 * code point) in the specified radix.
11161 *
11162 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11163 * {@code radix} ≤ {@code MAX_RADIX} or if the
11164 * character is not a valid digit in the specified
11165 * radix, {@code -1} is returned. A character is a valid digit
11166 * if at least one of the following is true:
11167 * <ul>
11168 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11169 * and the Unicode decimal digit value of the character (or its
11170 * single-character decomposition) is less than the specified radix.
11171 * In this case the decimal digit value is returned.
11172 * <li>The character is one of the uppercase Latin letters
11173 * {@code 'A'} through {@code 'Z'} and its code is less than
11174 * {@code radix + 'A' - 10}.
11175 * In this case, {@code codePoint - 'A' + 10}
11176 * is returned.
11177 * <li>The character is one of the lowercase Latin letters
11178 * {@code 'a'} through {@code 'z'} and its code is less than
11179 * {@code radix + 'a' - 10}.
11180 * In this case, {@code codePoint - 'a' + 10}
11181 * is returned.
11182 * <li>The character is one of the fullwidth uppercase Latin letters A
11183 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11184 * and its code is less than
11185 * {@code radix + '\u005CuFF21' - 10}.
11186 * In this case,
11187 * {@code codePoint - '\u005CuFF21' + 10}
11188 * is returned.
11189 * <li>The character is one of the fullwidth lowercase Latin letters a
11190 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11191 * and its code is less than
11192 * {@code radix + '\u005CuFF41'- 10}.
11193 * In this case,
11194 * {@code codePoint - '\u005CuFF41' + 10}
11195 * is returned.
11196 * </ul>
11197 *
11198 * @param codePoint the character (Unicode code point) to be converted.
11199 * @param radix the radix.
11200 * @return the numeric value represented by the character in the
11201 * specified radix.
11202 * @see Character#forDigit(int, int)
11203 * @see Character#isDigit(int)
11204 * @since 1.5
11205 */
11206 public static int digit(int codePoint, int radix) {
11207 return CharacterData.of(codePoint).digit(codePoint, radix);
11208 }
11209
11210 /**
11211 * Returns the {@code int} value that the specified Unicode
11212 * character represents. For example, the character
11213 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11214 * an int with a value of 50.
11215 * <p>
11216 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11217 * {@code '\u005Cu005A'}), lowercase
11218 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11219 * full width variant ({@code '\u005CuFF21'} through
11220 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11221 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11222 * through 35. This is independent of the Unicode specification,
11223 * which does not assign numeric values to these {@code char}
11224 * values.
11225 * <p>
11226 * If the character does not have a numeric value, then -1 is returned.
11227 * If the character has a numeric value that cannot be represented as a
11228 * nonnegative integer (for example, a fractional value), then -2
11229 * is returned.
11230 *
11231 * <p><b>Note:</b> This method cannot handle <a
11232 * href="#supplementary"> supplementary characters</a>. To support
11233 * all Unicode characters, including supplementary characters, use
11234 * the {@link #getNumericValue(int)} method.
11235 *
11236 * @param ch the character to be converted.
11237 * @return the numeric value of the character, as a nonnegative {@code int}
11238 * value; -2 if the character has a numeric value but the value
11239 * can not be represented as a nonnegative {@code int} value;
11240 * -1 if the character has no numeric value.
11241 * @see Character#forDigit(int, int)
11242 * @see Character#isDigit(char)
11243 * @since 1.1
11244 */
11245 public static int getNumericValue(char ch) {
11246 return getNumericValue((int)ch);
11247 }
11248
11249 /**
11250 * Returns the {@code int} value that the specified
11251 * character (Unicode code point) represents. For example, the character
11252 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11253 * an {@code int} with a value of 50.
11254 * <p>
11255 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11256 * {@code '\u005Cu005A'}), lowercase
11257 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11258 * full width variant ({@code '\u005CuFF21'} through
11259 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11260 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11261 * through 35. This is independent of the Unicode specification,
11262 * which does not assign numeric values to these {@code char}
11263 * values.
11264 * <p>
11265 * If the character does not have a numeric value, then -1 is returned.
11266 * If the character has a numeric value that cannot be represented as a
11267 * nonnegative integer (for example, a fractional value), then -2
11268 * is returned.
11269 *
11270 * @param codePoint the character (Unicode code point) to be converted.
11271 * @return the numeric value of the character, as a nonnegative {@code int}
11272 * value; -2 if the character has a numeric value but the value
11273 * can not be represented as a nonnegative {@code int} value;
11274 * -1 if the character has no numeric value.
11275 * @see Character#forDigit(int, int)
11276 * @see Character#isDigit(int)
11277 * @since 1.5
11278 */
11279 public static int getNumericValue(int codePoint) {
11280 return CharacterData.of(codePoint).getNumericValue(codePoint);
11281 }
11282
11283 /**
11284 * Determines if the specified character is ISO-LATIN-1 white space.
11285 * This method returns {@code true} for the following five
11286 * characters only:
11287 * <table class="striped">
11288 * <caption style="display:none">truechars</caption>
11289 * <thead>
11290 * <tr><th scope="col">Character
11291 * <th scope="col">Code
11292 * <th scope="col">Name
11293 * </thead>
11294 * <tbody>
11295 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11296 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11297 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11298 * <td>{@code NEW LINE}</td></tr>
11299 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11300 * <td>{@code FORM FEED}</td></tr>
11301 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11302 * <td>{@code CARRIAGE RETURN}</td></tr>
11303 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11304 * <td>{@code SPACE}</td></tr>
11305 * </tbody>
11306 * </table>
11307 *
11308 * @param ch the character to be tested.
11309 * @return {@code true} if the character is ISO-LATIN-1 white
11310 * space; {@code false} otherwise.
11311 * @see Character#isSpaceChar(char)
11312 * @see Character#isWhitespace(char)
11313 * @deprecated Replaced by isWhitespace(char).
11314 */
11315 @Deprecated(since="1.1")
11316 public static boolean isSpace(char ch) {
11317 return (ch <= 0x0020) &&
11318 (((((1L << 0x0009) |
11319 (1L << 0x000A) |
11320 (1L << 0x000C) |
11321 (1L << 0x000D) |
11322 (1L << 0x0020)) >> ch) & 1L) != 0);
11323 }
11324
11325
11326 /**
11327 * Determines if the specified character is a Unicode space character.
11328 * A character is considered to be a space character if and only if
11329 * it is specified to be a space character by the Unicode Standard. This
11330 * method returns true if the character's general category type is any of
11331 * the following:
11332 * <ul>
11333 * <li> {@code SPACE_SEPARATOR}
11334 * <li> {@code LINE_SEPARATOR}
11335 * <li> {@code PARAGRAPH_SEPARATOR}
11336 * </ul>
11337 *
11338 * <p><b>Note:</b> This method cannot handle <a
11339 * href="#supplementary"> supplementary characters</a>. To support
11340 * all Unicode characters, including supplementary characters, use
11341 * the {@link #isSpaceChar(int)} method.
11342 *
11343 * @param ch the character to be tested.
11344 * @return {@code true} if the character is a space character;
11345 * {@code false} otherwise.
11346 * @see Character#isWhitespace(char)
11347 * @since 1.1
11348 */
11349 public static boolean isSpaceChar(char ch) {
11350 return isSpaceChar((int)ch);
11351 }
11352
11353 /**
11354 * Determines if the specified character (Unicode code point) is a
11355 * Unicode space character. A character is considered to be a
11356 * space character if and only if it is specified to be a space
11357 * character by the Unicode Standard. This method returns true if
11358 * the character's general category type is any of the following:
11359 *
11360 * <ul>
11361 * <li> {@link #SPACE_SEPARATOR}
11362 * <li> {@link #LINE_SEPARATOR}
11363 * <li> {@link #PARAGRAPH_SEPARATOR}
11364 * </ul>
11365 *
11366 * @param codePoint the character (Unicode code point) to be tested.
11367 * @return {@code true} if the character is a space character;
11368 * {@code false} otherwise.
11369 * @see Character#isWhitespace(int)
11370 * @since 1.5
11371 */
11372 public static boolean isSpaceChar(int codePoint) {
11373 return ((((1 << Character.SPACE_SEPARATOR) |
11374 (1 << Character.LINE_SEPARATOR) |
11375 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11376 != 0;
11377 }
11378
11379 /**
11380 * Determines if the specified character is white space according to Java.
11381 * A character is a Java whitespace character if and only if it satisfies
11382 * one of the following criteria:
11383 * <ul>
11384 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11385 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11386 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11387 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11388 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11389 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11390 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11391 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11392 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11393 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11394 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11395 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11396 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11397 * </ul>
11398 *
11399 * <p><b>Note:</b> This method cannot handle <a
11400 * href="#supplementary"> supplementary characters</a>. To support
11401 * all Unicode characters, including supplementary characters, use
11402 * the {@link #isWhitespace(int)} method.
11403 *
11404 * @param ch the character to be tested.
11405 * @return {@code true} if the character is a Java whitespace
11406 * character; {@code false} otherwise.
11407 * @see Character#isSpaceChar(char)
11408 * @since 1.1
11409 */
11410 public static boolean isWhitespace(char ch) {
11411 return isWhitespace((int)ch);
11412 }
11413
11414 /**
11415 * Determines if the specified character (Unicode code point) is
11416 * white space according to Java. A character is a Java
11417 * whitespace character if and only if it satisfies one of the
11418 * following criteria:
11419 * <ul>
11420 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11421 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11422 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11423 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11424 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11425 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11426 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11427 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11428 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11429 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11430 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11431 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11432 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11433 * </ul>
11434 *
11435 * @param codePoint the character (Unicode code point) to be tested.
11436 * @return {@code true} if the character is a Java whitespace
11437 * character; {@code false} otherwise.
11438 * @see Character#isSpaceChar(int)
11439 * @since 1.5
11440 */
11441 public static boolean isWhitespace(int codePoint) {
11442 return CharacterData.of(codePoint).isWhitespace(codePoint);
11443 }
11444
11445 /**
11446 * Determines if the specified character is an ISO control
11447 * character. A character is considered to be an ISO control
11448 * character if its code is in the range {@code '\u005Cu0000'}
11449 * through {@code '\u005Cu001F'} or in the range
11450 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11451 *
11452 * <p><b>Note:</b> This method cannot handle <a
11453 * href="#supplementary"> supplementary characters</a>. To support
11454 * all Unicode characters, including supplementary characters, use
11455 * the {@link #isISOControl(int)} method.
11456 *
11457 * @param ch the character to be tested.
11458 * @return {@code true} if the character is an ISO control character;
11459 * {@code false} otherwise.
11460 *
11461 * @see Character#isSpaceChar(char)
11462 * @see Character#isWhitespace(char)
11463 * @since 1.1
11464 */
11465 public static boolean isISOControl(char ch) {
11466 return isISOControl((int)ch);
11467 }
11468
11469 /**
11470 * Determines if the referenced character (Unicode code point) is an ISO control
11471 * character. A character is considered to be an ISO control
11472 * character if its code is in the range {@code '\u005Cu0000'}
11473 * through {@code '\u005Cu001F'} or in the range
11474 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11475 *
11476 * @param codePoint the character (Unicode code point) to be tested.
11477 * @return {@code true} if the character is an ISO control character;
11478 * {@code false} otherwise.
11479 * @see Character#isSpaceChar(int)
11480 * @see Character#isWhitespace(int)
11481 * @since 1.5
11482 */
11483 public static boolean isISOControl(int codePoint) {
11484 // Optimized form of:
11485 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11486 // (codePoint >= 0x7F && codePoint <= 0x9F);
11487 return codePoint <= 0x9F &&
11488 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11489 }
11490
11491 /**
11492 * Returns a value indicating a character's general category.
11493 *
11494 * <p><b>Note:</b> This method cannot handle <a
11495 * href="#supplementary"> supplementary characters</a>. To support
11496 * all Unicode characters, including supplementary characters, use
11497 * the {@link #getType(int)} method.
11498 *
11499 * @param ch the character to be tested.
11500 * @return a value of type {@code int} representing the
11501 * character's general category.
11502 * @see Character#COMBINING_SPACING_MARK
11503 * @see Character#CONNECTOR_PUNCTUATION
11504 * @see Character#CONTROL
11505 * @see Character#CURRENCY_SYMBOL
11506 * @see Character#DASH_PUNCTUATION
11507 * @see Character#DECIMAL_DIGIT_NUMBER
11508 * @see Character#ENCLOSING_MARK
11509 * @see Character#END_PUNCTUATION
11510 * @see Character#FINAL_QUOTE_PUNCTUATION
11511 * @see Character#FORMAT
11512 * @see Character#INITIAL_QUOTE_PUNCTUATION
11513 * @see Character#LETTER_NUMBER
11514 * @see Character#LINE_SEPARATOR
11515 * @see Character#LOWERCASE_LETTER
11516 * @see Character#MATH_SYMBOL
11517 * @see Character#MODIFIER_LETTER
11518 * @see Character#MODIFIER_SYMBOL
11519 * @see Character#NON_SPACING_MARK
11520 * @see Character#OTHER_LETTER
11521 * @see Character#OTHER_NUMBER
11522 * @see Character#OTHER_PUNCTUATION
11523 * @see Character#OTHER_SYMBOL
11524 * @see Character#PARAGRAPH_SEPARATOR
11525 * @see Character#PRIVATE_USE
11526 * @see Character#SPACE_SEPARATOR
11527 * @see Character#START_PUNCTUATION
11528 * @see Character#SURROGATE
11529 * @see Character#TITLECASE_LETTER
11530 * @see Character#UNASSIGNED
11531 * @see Character#UPPERCASE_LETTER
11532 * @since 1.1
11533 */
11534 public static int getType(char ch) {
11535 return getType((int)ch);
11536 }
11537
11538 /**
11539 * Returns a value indicating a character's general category.
11540 *
11541 * @param codePoint the character (Unicode code point) to be tested.
11542 * @return a value of type {@code int} representing the
11543 * character's general category.
11544 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11545 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11546 * @see Character#CONTROL CONTROL
11547 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11548 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11549 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11550 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11551 * @see Character#END_PUNCTUATION END_PUNCTUATION
11552 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11553 * @see Character#FORMAT FORMAT
11554 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11555 * @see Character#LETTER_NUMBER LETTER_NUMBER
11556 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11557 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11558 * @see Character#MATH_SYMBOL MATH_SYMBOL
11559 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11560 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11561 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11562 * @see Character#OTHER_LETTER OTHER_LETTER
11563 * @see Character#OTHER_NUMBER OTHER_NUMBER
11564 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
11565 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
11566 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
11567 * @see Character#PRIVATE_USE PRIVATE_USE
11568 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
11569 * @see Character#START_PUNCTUATION START_PUNCTUATION
11570 * @see Character#SURROGATE SURROGATE
11571 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
11572 * @see Character#UNASSIGNED UNASSIGNED
11573 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
11574 * @since 1.5
11575 */
11576 public static int getType(int codePoint) {
11577 return CharacterData.of(codePoint).getType(codePoint);
11578 }
11579
11580 /**
11581 * Determines the character representation for a specific digit in
11582 * the specified radix. If the value of {@code radix} is not a
11583 * valid radix, or the value of {@code digit} is not a valid
11584 * digit in the specified radix, the null character
11585 * ({@code '\u005Cu0000'}) is returned.
11586 * <p>
11587 * The {@code radix} argument is valid if it is greater than or
11588 * equal to {@code MIN_RADIX} and less than or equal to
11589 * {@code MAX_RADIX}. The {@code digit} argument is valid if
11590 * {@code 0 <= digit < radix}.
11591 * <p>
11592 * If the digit is less than 10, then
11593 * {@code '0' + digit} is returned. Otherwise, the value
11594 * {@code 'a' + digit - 10} is returned.
11595 *
11596 * @param digit the number to convert to a character.
11597 * @param radix the radix.
11598 * @return the {@code char} representation of the specified digit
11599 * in the specified radix.
11600 * @see Character#MIN_RADIX
11601 * @see Character#MAX_RADIX
11602 * @see Character#digit(char, int)
11603 */
11604 public static char forDigit(int digit, int radix) {
11605 if ((digit >= radix) || (digit < 0)) {
11606 return '\0';
11607 }
11608 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
11609 return '\0';
11610 }
11611 if (digit < 10) {
11612 return (char)('0' + digit);
11613 }
11614 return (char)('a' - 10 + digit);
11615 }
11616
11617 /**
11618 * Returns the Unicode directionality property for the given
11619 * character. Character directionality is used to calculate the
11620 * visual ordering of text. The directionality value of undefined
11621 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
11622 *
11623 * <p><b>Note:</b> This method cannot handle <a
11624 * href="#supplementary"> supplementary characters</a>. To support
11625 * all Unicode characters, including supplementary characters, use
11626 * the {@link #getDirectionality(int)} method.
11627 *
11628 * @param ch {@code char} for which the directionality property
11629 * is requested.
11630 * @return the directionality property of the {@code char} value.
11631 *
11632 * @see Character#DIRECTIONALITY_UNDEFINED
11633 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
11634 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
11635 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11636 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
11637 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11638 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11639 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
11640 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11641 * @see Character#DIRECTIONALITY_NONSPACING_MARK
11642 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
11643 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
11644 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
11645 * @see Character#DIRECTIONALITY_WHITESPACE
11646 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
11647 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11648 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11649 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11650 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11651 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11652 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11653 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11654 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
11655 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11656 * @since 1.4
11657 */
11658 public static byte getDirectionality(char ch) {
11659 return getDirectionality((int)ch);
11660 }
11661
11662 /**
11663 * Returns the Unicode directionality property for the given
11664 * character (Unicode code point). Character directionality is
11665 * used to calculate the visual ordering of text. The
11666 * directionality value of undefined character is {@link
11667 * #DIRECTIONALITY_UNDEFINED}.
11668 *
11669 * @param codePoint the character (Unicode code point) for which
11670 * the directionality property is requested.
11671 * @return the directionality property of the character.
11672 *
11673 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
11674 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
11675 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
11676 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11677 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
11678 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11679 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11680 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
11681 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11682 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
11683 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
11684 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
11685 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
11686 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
11687 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
11688 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11689 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11690 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11691 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11692 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11693 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11694 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11695 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
11696 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11697 * @since 1.5
11698 */
11699 public static byte getDirectionality(int codePoint) {
11700 return CharacterData.of(codePoint).getDirectionality(codePoint);
11701 }
11702
11703 /**
11704 * Determines whether the character is mirrored according to the
11705 * Unicode specification. Mirrored characters should have their
11706 * glyphs horizontally mirrored when displayed in text that is
11707 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
11708 * PARENTHESIS is semantically defined to be an <i>opening
11709 * parenthesis</i>. This will appear as a "(" in text that is
11710 * left-to-right but as a ")" in text that is right-to-left.
11711 *
11712 * <p><b>Note:</b> This method cannot handle <a
11713 * href="#supplementary"> supplementary characters</a>. To support
11714 * all Unicode characters, including supplementary characters, use
11715 * the {@link #isMirrored(int)} method.
11716 *
11717 * @param ch {@code char} for which the mirrored property is requested
11718 * @return {@code true} if the char is mirrored, {@code false}
11719 * if the {@code char} is not mirrored or is not defined.
11720 * @since 1.4
11721 */
11722 public static boolean isMirrored(char ch) {
11723 return isMirrored((int)ch);
11724 }
11725
11726 /**
11727 * Determines whether the specified character (Unicode code point)
11728 * is mirrored according to the Unicode specification. Mirrored
11729 * characters should have their glyphs horizontally mirrored when
11730 * displayed in text that is right-to-left. For example,
11731 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
11732 * defined to be an <i>opening parenthesis</i>. This will appear
11733 * as a "(" in text that is left-to-right but as a ")" in text
11734 * that is right-to-left.
11735 *
11736 * @param codePoint the character (Unicode code point) to be tested.
11737 * @return {@code true} if the character is mirrored, {@code false}
11738 * if the character is not mirrored or is not defined.
11739 * @since 1.5
11740 */
11741 public static boolean isMirrored(int codePoint) {
11742 return CharacterData.of(codePoint).isMirrored(codePoint);
11743 }
11744
11745 /**
11746 * Compares two {@code Character} objects numerically.
11747 *
11748 * @param anotherCharacter the {@code Character} to be compared.
11749 * @return the value {@code 0} if the argument {@code Character}
11750 * is equal to this {@code Character}; a value less than
11751 * {@code 0} if this {@code Character} is numerically less
11752 * than the {@code Character} argument; and a value greater than
11753 * {@code 0} if this {@code Character} is numerically greater
11754 * than the {@code Character} argument (unsigned comparison).
11755 * Note that this is strictly a numerical comparison; it is not
11756 * locale-dependent.
11757 * @since 1.2
11758 */
11759 public int compareTo(Character anotherCharacter) {
11760 return compare(this.value, anotherCharacter.value);
11761 }
11762
11763 /**
11764 * Compares two {@code char} values numerically.
11765 * The value returned is identical to what would be returned by:
11766 * <pre>
11767 * Character.valueOf(x).compareTo(Character.valueOf(y))
11768 * </pre>
11769 *
11770 * @param x the first {@code char} to compare
11771 * @param y the second {@code char} to compare
11772 * @return the value {@code 0} if {@code x == y};
11773 * a value less than {@code 0} if {@code x < y}; and
11774 * a value greater than {@code 0} if {@code x > y}
11775 * @since 1.7
11776 */
11777 public static int compare(char x, char y) {
11778 return x - y;
11779 }
11780
11781 /**
11782 * Converts the character (Unicode code point) argument to uppercase using
11783 * information from the UnicodeData file.
11784 *
11785 * @param codePoint the character (Unicode code point) to be converted.
11786 * @return either the uppercase equivalent of the character, if
11787 * any, or an error flag ({@code Character.ERROR})
11788 * that indicates that a 1:M {@code char} mapping exists.
11789 * @see Character#isLowerCase(char)
11790 * @see Character#isUpperCase(char)
11791 * @see Character#toLowerCase(char)
11792 * @see Character#toTitleCase(char)
11793 * @since 1.4
11794 */
11795 static int toUpperCaseEx(int codePoint) {
11796 assert isValidCodePoint(codePoint);
11797 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
11798 }
11799
11800 /**
11801 * Converts the character (Unicode code point) argument to uppercase using case
11802 * mapping information from the SpecialCasing file in the Unicode
11803 * specification. If a character has no explicit uppercase
11804 * mapping, then the {@code char} itself is returned in the
11805 * {@code char[]}.
11806 *
11807 * @param codePoint the character (Unicode code point) to be converted.
11808 * @return a {@code char[]} with the uppercased character.
11809 * @since 1.4
11810 */
11811 static char[] toUpperCaseCharArray(int codePoint) {
11812 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
11813 assert isBmpCodePoint(codePoint);
11814 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
11815 }
11816
11817 /**
11818 * The number of bits used to represent a {@code char} value in unsigned
11819 * binary form, constant {@code 16}.
11820 *
11821 * @since 1.5
11822 */
11823 public static final int SIZE = 16;
11824
11825 /**
11826 * The number of bytes used to represent a {@code char} value in unsigned
11827 * binary form.
11828 *
11829 * @since 1.8
11830 */
11831 public static final int BYTES = SIZE / Byte.SIZE;
11832
11833 /**
11834 * Returns the value obtained by reversing the order of the bytes in the
11835 * specified {@code char} value.
11836 *
11837 * @param ch The {@code char} of which to reverse the byte order.
11838 * @return the value obtained by reversing (or, equivalently, swapping)
11839 * the bytes in the specified {@code char} value.
11840 * @since 1.5
11841 */
11842 @IntrinsicCandidate
11843 public static char reverseBytes(char ch) {
11844 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
11845 }
11846
11847 /**
11848 * Returns the name of the specified character
11849 * {@code codePoint}, or null if the code point is
11850 * {@link #UNASSIGNED unassigned}.
11851 * <p>
11852 * If the specified character is not assigned a name by
11853 * the <i>UnicodeData</i> file (part of the Unicode Character
11854 * Database maintained by the Unicode Consortium), the returned
11855 * name is the same as the result of the expression:
11856 *
11857 * <blockquote>{@code
11858 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
11859 * + " "
11860 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11861 *
11862 * }</blockquote>
11863 *
11864 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
11865 * returned by this method follows the naming scheme in the
11866 * "Unicode Name Property" section of the Unicode Standard. For other
11867 * code points, such as Hangul/Ideographs, The name generation rule above
11868 * differs from the one defined in the Unicode Standard.
11869 *
11870 * @param codePoint the character (Unicode code point)
11871 *
11872 * @return the name of the specified character, or null if
11873 * the code point is unassigned.
11874 *
11875 * @throws IllegalArgumentException if the specified
11876 * {@code codePoint} is not a valid Unicode
11877 * code point.
11878 *
11879 * @since 1.7
11880 */
11881 public static String getName(int codePoint) {
11882 if (!isValidCodePoint(codePoint)) {
11883 throw new IllegalArgumentException(
11884 String.format("Not a valid Unicode code point: 0x%X", codePoint));
11885 }
11886 String name = CharacterName.getInstance().getName(codePoint);
11887 if (name != null)
11888 return name;
11889 if (getType(codePoint) == UNASSIGNED)
11890 return null;
11891 UnicodeBlock block = UnicodeBlock.of(codePoint);
11892 if (block != null)
11893 return block.toString().replace('_', ' ') + " "
11894 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11895 // should never come here
11896 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11897 }
11898
11899 /**
11900 * Returns the code point value of the Unicode character specified by
11901 * the given character name.
11902 * <p>
11903 * If a character is not assigned a name by the <i>UnicodeData</i>
11904 * file (part of the Unicode Character Database maintained by the Unicode
11905 * Consortium), its name is defined as the result of the expression:
11906 *
11907 * <blockquote>{@code
11908 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
11909 * + " "
11910 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11911 *
11912 * }</blockquote>
11913 * <p>
11914 * The {@code name} matching is case insensitive, with any leading and
11915 * trailing whitespace character removed.
11916 *
11917 * For the code points in the <i>UnicodeData</i> file, this method
11918 * recognizes the name which conforms to the name defined in the
11919 * "Unicode Name Property" section in the Unicode Standard. For other
11920 * code points, this method recognizes the name generated with
11921 * {@link #getName(int)} method.
11922 *
11923 * @param name the character name
11924 *
11925 * @return the code point value of the character specified by its name.
11926 *
11927 * @throws IllegalArgumentException if the specified {@code name}
11928 * is not a valid character name.
11929 * @throws NullPointerException if {@code name} is {@code null}
11930 *
11931 * @since 9
11932 */
11933 public static int codePointOf(String name) {
11934 name = name.trim().toUpperCase(Locale.ROOT);
11935 int cp = CharacterName.getInstance().getCodePoint(name);
11936 if (cp != -1)
11937 return cp;
11938 try {
11939 int off = name.lastIndexOf(' ');
11940 if (off != -1) {
11941 cp = Integer.parseInt(name, off + 1, name.length(), 16);
11942 if (isValidCodePoint(cp) && name.equals(getName(cp)))
11943 return cp;
11944 }
11945 } catch (Exception x) {}
11946 throw new IllegalArgumentException("Unrecognized character name :" + name);
11947 }
11948 }