1 /*
2 * Copyright (c) 2002, 2025, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import jdk.internal.misc.CDS;
29 import jdk.internal.vm.annotation.AOTSafeClassInitializer;
30 import jdk.internal.vm.annotation.IntrinsicCandidate;
31 import jdk.internal.vm.annotation.Stable;
32
33 import java.lang.constant.Constable;
34 import java.lang.constant.DynamicConstantDesc;
35 import java.util.Arrays;
36 import java.util.HashMap;
37 import java.util.Locale;
38 import java.util.Map;
39 import java.util.Objects;
40 import java.util.Optional;
41
42 import static java.lang.constant.ConstantDescs.BSM_EXPLICIT_CAST;
43 import static java.lang.constant.ConstantDescs.CD_char;
44 import static java.lang.constant.ConstantDescs.DEFAULT_NAME;
45
46 /**
47 * The {@code Character} class is the {@linkplain
48 * java.lang##wrapperClass wrapper class} for values of the primitive
49 * type {@code char}. An object of type {@code Character} contains a
50 * single field whose type is {@code char}.
51 *
52 * <p>In addition, this class provides a large number of static methods for
53 * determining a character's category (lowercase letter, digit, etc.)
54 * and for converting characters from uppercase to lowercase and vice
55 * versa.
56 *
57 * <h2><a id="conformance">Unicode Conformance</a></h2>
58 * <p>
59 * The fields and methods of class {@code Character} are defined in terms
60 * of character information from the Unicode Standard, specifically the
61 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
62 * This file specifies properties including name and category for every
63 * assigned Unicode code point or character range. The file is available
64 * from the Unicode Consortium at
65 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
66 * <p>
67 * Character information is based on the Unicode Standard, version 17.0.
68 * <p>
69 * The Java platform has supported different versions of the Unicode
70 * Standard over time. Upgrades to newer versions of the Unicode Standard
71 * occurred in the following Java releases, each indicating the new version:
72 * <table class="striped">
73 * <caption style="display:none">Shows Java releases and supported Unicode versions</caption>
74 * <thead>
75 * <tr><th scope="col">Java release</th>
76 * <th scope="col">Unicode version</th></tr>
77 * </thead>
78 * <tbody>
79 * <tr><th scope="row" style="text-align:left">Java SE 26</th>
80 * <td>Unicode 17.0</td></tr>
81 * <tr><th scope="row" style="text-align:left">Java SE 24</th>
82 * <td>Unicode 16.0</td></tr>
83 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
84 * <td>Unicode 15.1</td></tr>
85 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
86 * <td>Unicode 15.0</td></tr>
87 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
88 * <td>Unicode 14.0</td></tr>
89 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
90 * <td>Unicode 13.0</td></tr>
91 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
92 * <td>Unicode 12.1</td></tr>
93 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
94 * <td>Unicode 11.0</td></tr>
95 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
96 * <td>Unicode 10.0</td></tr>
97 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
98 * <td>Unicode 8.0</td></tr>
99 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
100 * <td>Unicode 6.2</td></tr>
101 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
102 * <td>Unicode 6.0</td></tr>
103 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
104 * <td>Unicode 4.0</td></tr>
105 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
106 * <td>Unicode 3.0</td></tr>
107 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
108 * <td>Unicode 2.0</td></tr>
109 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
110 * <td>Unicode 1.1.5</td></tr>
111 * </tbody>
112 * </table>
113 * Variations from these base Unicode versions, such as recognized appendixes,
114 * are documented elsewhere.
115 * <h2><a id="unicode">Unicode Character Representations</a></h2>
116 *
117 * <p>The {@code char} data type (and therefore the value that a
118 * {@code Character} object encapsulates) are based on the
119 * original Unicode specification, which defined characters as
120 * fixed-width 16-bit entities. The Unicode Standard has since been
121 * changed to allow for characters whose representation requires more
122 * than 16 bits. The range of legal <em>code point</em>s is now
123 * U+0000 to U+10FFFF, known as
124 * <em><a href="https://www.unicode.org/glossary/#unicode_scalar_value">
125 * Unicode scalar value</a></em>.
126 *
127 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
128 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
129 * <a id="supplementary">Characters</a> whose code points are greater
130 * than U+FFFF are called <em>supplementary character</em>s. The Java
131 * platform uses the UTF-16 representation in {@code char} arrays and
132 * in the {@code String} and {@code StringBuffer} classes. In
133 * this representation, supplementary characters are represented as a pair
134 * of {@code char} values, the first from the <em>high-surrogates</em>
135 * range, (\uD800-\uDBFF), the second from the
136 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
137 *
138 * <p>A {@code char} value, therefore, represents Basic
139 * Multilingual Plane (BMP) code points, including the surrogate
140 * code points, or code units of the UTF-16 encoding. An
141 * {@code int} value represents all Unicode code points,
142 * including supplementary code points. The lower (least significant)
143 * 21 bits of {@code int} are used to represent Unicode code
144 * points and the upper (most significant) 11 bits must be zero.
145 * Unless otherwise specified, the behavior with respect to
146 * supplementary characters and surrogate {@code char} values is
147 * as follows:
148 *
149 * <ul>
150 * <li>The methods that only accept a {@code char} value cannot support
151 * supplementary characters. They treat {@code char} values from the
152 * surrogate ranges as undefined characters. For example,
153 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
154 * this specific value if followed by any low-surrogate value in a string
155 * would represent a letter.
156 *
157 * <li>The methods that accept an {@code int} value support all
158 * Unicode characters, including supplementary characters. For
159 * example, {@code Character.isLetter(0x2F81A)} returns
160 * {@code true} because the code point value represents a letter
161 * (a CJK ideograph).
162 * </ul>
163 *
164 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
165 * used for character values in the range between U+0000 and U+10FFFF,
166 * and <em>Unicode code unit</em> is used for 16-bit
167 * {@code char} values that are code units of the <em>UTF-16</em>
168 * encoding. For more information on Unicode terminology, refer to the
169 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
170 *
171 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
172 * class; programmers should treat instances that are
173 * {@linkplain #equals(Object) equal} as interchangeable and should not
174 * use instances for synchronization, or unpredictable behavior may
175 * occur. For example, in a future release, synchronization may fail.
176 *
177 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
178 * @author Lee Boynton
179 * @author Guy Steele
180 * @author Akira Tanaka
181 * @author Martin Buchholz
182 * @author Ulf Zibis
183 * @since 1.0
184 */
185 @jdk.internal.ValueBased
186 public final
187 class Character implements java.io.Serializable, Comparable<Character>, Constable {
188 /**
189 * The minimum radix available for conversion to and from strings.
190 * The constant value of this field is the smallest value permitted
191 * for the radix argument in radix-conversion methods such as the
192 * {@code digit} method, the {@code forDigit} method, and the
193 * {@code toString} method of class {@code Integer}.
194 *
195 * @see Character#digit(char, int)
196 * @see Character#forDigit(int, int)
197 * @see Integer#toString(int, int)
198 * @see Integer#valueOf(String)
199 */
200 public static final int MIN_RADIX = 2;
201
202 /**
203 * The maximum radix available for conversion to and from strings.
204 * The constant value of this field is the largest value permitted
205 * for the radix argument in radix-conversion methods such as the
206 * {@code digit} method, the {@code forDigit} method, and the
207 * {@code toString} method of class {@code Integer}.
208 *
209 * @see Character#digit(char, int)
210 * @see Character#forDigit(int, int)
211 * @see Integer#toString(int, int)
212 * @see Integer#valueOf(String)
213 */
214 public static final int MAX_RADIX = 36;
215
216 /**
217 * The constant value of this field is the smallest value of type
218 * {@code char}, {@code '\u005Cu0000'}.
219 *
220 * @since 1.0.2
221 */
222 public static final char MIN_VALUE = '\u0000';
223
224 /**
225 * The constant value of this field is the largest value of type
226 * {@code char}, {@code '\u005CuFFFF'}.
227 *
228 * @since 1.0.2
229 */
230 public static final char MAX_VALUE = '\uFFFF';
231
232 /**
233 * The {@code Class} instance representing the primitive type
234 * {@code char}.
235 *
236 * @since 1.1
237 */
238 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
239
240 /*
241 * Normative general types
242 */
243
244 /*
245 * General character types
246 */
247
248 /**
249 * General category "Cn" in the Unicode specification.
250 * @since 1.1
251 */
252 public static final byte UNASSIGNED = 0;
253
254 /**
255 * General category "Lu" in the Unicode specification.
256 * @since 1.1
257 */
258 public static final byte UPPERCASE_LETTER = 1;
259
260 /**
261 * General category "Ll" in the Unicode specification.
262 * @since 1.1
263 */
264 public static final byte LOWERCASE_LETTER = 2;
265
266 /**
267 * General category "Lt" in the Unicode specification.
268 * @since 1.1
269 */
270 public static final byte TITLECASE_LETTER = 3;
271
272 /**
273 * General category "Lm" in the Unicode specification.
274 * @since 1.1
275 */
276 public static final byte MODIFIER_LETTER = 4;
277
278 /**
279 * General category "Lo" in the Unicode specification.
280 * @since 1.1
281 */
282 public static final byte OTHER_LETTER = 5;
283
284 /**
285 * General category "Mn" in the Unicode specification.
286 * @since 1.1
287 */
288 public static final byte NON_SPACING_MARK = 6;
289
290 /**
291 * General category "Me" in the Unicode specification.
292 * @since 1.1
293 */
294 public static final byte ENCLOSING_MARK = 7;
295
296 /**
297 * General category "Mc" in the Unicode specification.
298 * @since 1.1
299 */
300 public static final byte COMBINING_SPACING_MARK = 8;
301
302 /**
303 * General category "Nd" in the Unicode specification.
304 * @since 1.1
305 */
306 public static final byte DECIMAL_DIGIT_NUMBER = 9;
307
308 /**
309 * General category "Nl" in the Unicode specification.
310 * @since 1.1
311 */
312 public static final byte LETTER_NUMBER = 10;
313
314 /**
315 * General category "No" in the Unicode specification.
316 * @since 1.1
317 */
318 public static final byte OTHER_NUMBER = 11;
319
320 /**
321 * General category "Zs" in the Unicode specification.
322 * @since 1.1
323 */
324 public static final byte SPACE_SEPARATOR = 12;
325
326 /**
327 * General category "Zl" in the Unicode specification.
328 * @since 1.1
329 */
330 public static final byte LINE_SEPARATOR = 13;
331
332 /**
333 * General category "Zp" in the Unicode specification.
334 * @since 1.1
335 */
336 public static final byte PARAGRAPH_SEPARATOR = 14;
337
338 /**
339 * General category "Cc" in the Unicode specification.
340 * @since 1.1
341 */
342 public static final byte CONTROL = 15;
343
344 /**
345 * General category "Cf" in the Unicode specification.
346 * @since 1.1
347 */
348 public static final byte FORMAT = 16;
349
350 /**
351 * General category "Co" in the Unicode specification.
352 * @since 1.1
353 */
354 public static final byte PRIVATE_USE = 18;
355
356 /**
357 * General category "Cs" in the Unicode specification.
358 * @since 1.1
359 */
360 public static final byte SURROGATE = 19;
361
362 /**
363 * General category "Pd" in the Unicode specification.
364 * @since 1.1
365 */
366 public static final byte DASH_PUNCTUATION = 20;
367
368 /**
369 * General category "Ps" in the Unicode specification.
370 * @since 1.1
371 */
372 public static final byte START_PUNCTUATION = 21;
373
374 /**
375 * General category "Pe" in the Unicode specification.
376 * @since 1.1
377 */
378 public static final byte END_PUNCTUATION = 22;
379
380 /**
381 * General category "Pc" in the Unicode specification.
382 * @since 1.1
383 */
384 public static final byte CONNECTOR_PUNCTUATION = 23;
385
386 /**
387 * General category "Po" in the Unicode specification.
388 * @since 1.1
389 */
390 public static final byte OTHER_PUNCTUATION = 24;
391
392 /**
393 * General category "Sm" in the Unicode specification.
394 * @since 1.1
395 */
396 public static final byte MATH_SYMBOL = 25;
397
398 /**
399 * General category "Sc" in the Unicode specification.
400 * @since 1.1
401 */
402 public static final byte CURRENCY_SYMBOL = 26;
403
404 /**
405 * General category "Sk" in the Unicode specification.
406 * @since 1.1
407 */
408 public static final byte MODIFIER_SYMBOL = 27;
409
410 /**
411 * General category "So" in the Unicode specification.
412 * @since 1.1
413 */
414 public static final byte OTHER_SYMBOL = 28;
415
416 /**
417 * General category "Pi" in the Unicode specification.
418 * @since 1.4
419 */
420 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
421
422 /**
423 * General category "Pf" in the Unicode specification.
424 * @since 1.4
425 */
426 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
427
428 /**
429 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
430 */
431 static final int ERROR = 0xFFFFFFFF;
432
433
434 /**
435 * Undefined bidirectional character type. Undefined {@code char}
436 * values have undefined directionality in the Unicode specification.
437 * @since 1.4
438 */
439 public static final byte DIRECTIONALITY_UNDEFINED = -1;
440
441 /**
442 * Strong bidirectional character type "L" in the Unicode specification.
443 * @since 1.4
444 */
445 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
446
447 /**
448 * Strong bidirectional character type "R" in the Unicode specification.
449 * @since 1.4
450 */
451 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
452
453 /**
454 * Strong bidirectional character type "AL" in the Unicode specification.
455 * @since 1.4
456 */
457 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
458
459 /**
460 * Weak bidirectional character type "EN" in the Unicode specification.
461 * @since 1.4
462 */
463 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
464
465 /**
466 * Weak bidirectional character type "ES" in the Unicode specification.
467 * @since 1.4
468 */
469 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
470
471 /**
472 * Weak bidirectional character type "ET" in the Unicode specification.
473 * @since 1.4
474 */
475 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
476
477 /**
478 * Weak bidirectional character type "AN" in the Unicode specification.
479 * @since 1.4
480 */
481 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
482
483 /**
484 * Weak bidirectional character type "CS" in the Unicode specification.
485 * @since 1.4
486 */
487 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
488
489 /**
490 * Weak bidirectional character type "NSM" in the Unicode specification.
491 * @since 1.4
492 */
493 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
494
495 /**
496 * Weak bidirectional character type "BN" in the Unicode specification.
497 * @since 1.4
498 */
499 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
500
501 /**
502 * Neutral bidirectional character type "B" in the Unicode specification.
503 * @since 1.4
504 */
505 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
506
507 /**
508 * Neutral bidirectional character type "S" in the Unicode specification.
509 * @since 1.4
510 */
511 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
512
513 /**
514 * Neutral bidirectional character type "WS" in the Unicode specification.
515 * @since 1.4
516 */
517 public static final byte DIRECTIONALITY_WHITESPACE = 12;
518
519 /**
520 * Neutral bidirectional character type "ON" in the Unicode specification.
521 * @since 1.4
522 */
523 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
524
525 /**
526 * Strong bidirectional character type "LRE" in the Unicode specification.
527 * @since 1.4
528 */
529 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
530
531 /**
532 * Strong bidirectional character type "LRO" in the Unicode specification.
533 * @since 1.4
534 */
535 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
536
537 /**
538 * Strong bidirectional character type "RLE" in the Unicode specification.
539 * @since 1.4
540 */
541 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
542
543 /**
544 * Strong bidirectional character type "RLO" in the Unicode specification.
545 * @since 1.4
546 */
547 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
548
549 /**
550 * Weak bidirectional character type "PDF" in the Unicode specification.
551 * @since 1.4
552 */
553 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
554
555 /**
556 * Weak bidirectional character type "LRI" in the Unicode specification.
557 * @since 9
558 */
559 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
560
561 /**
562 * Weak bidirectional character type "RLI" in the Unicode specification.
563 * @since 9
564 */
565 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
566
567 /**
568 * Weak bidirectional character type "FSI" in the Unicode specification.
569 * @since 9
570 */
571 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
572
573 /**
574 * Weak bidirectional character type "PDI" in the Unicode specification.
575 * @since 9
576 */
577 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
578
579 /**
580 * The minimum value of a
581 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
582 * Unicode high-surrogate code unit</a>
583 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
584 * A high-surrogate is also known as a <i>leading-surrogate</i>.
585 *
586 * @since 1.5
587 */
588 public static final char MIN_HIGH_SURROGATE = '\uD800';
589
590 /**
591 * The maximum value of a
592 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
593 * Unicode high-surrogate code unit</a>
594 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
595 * A high-surrogate is also known as a <i>leading-surrogate</i>.
596 *
597 * @since 1.5
598 */
599 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
600
601 /**
602 * The minimum value of a
603 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
604 * Unicode low-surrogate code unit</a>
605 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
606 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
607 *
608 * @since 1.5
609 */
610 public static final char MIN_LOW_SURROGATE = '\uDC00';
611
612 /**
613 * The maximum value of a
614 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
615 * Unicode low-surrogate code unit</a>
616 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
617 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
618 *
619 * @since 1.5
620 */
621 public static final char MAX_LOW_SURROGATE = '\uDFFF';
622
623 /**
624 * The minimum value of a Unicode surrogate code unit in the
625 * UTF-16 encoding, constant {@code '\u005CuD800'}.
626 *
627 * @since 1.5
628 */
629 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
630
631 /**
632 * The maximum value of a Unicode surrogate code unit in the
633 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
634 *
635 * @since 1.5
636 */
637 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
638
639 /**
640 * The minimum value of a
641 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
642 * Unicode supplementary code point</a>, constant {@code U+10000}.
643 *
644 * @since 1.5
645 */
646 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
647
648 /**
649 * The minimum value of a
650 * <a href="http://www.unicode.org/glossary/#code_point">
651 * Unicode code point</a>, constant {@code U+0000}.
652 *
653 * @since 1.5
654 */
655 public static final int MIN_CODE_POINT = 0x000000;
656
657 /**
658 * The maximum value of a
659 * <a href="http://www.unicode.org/glossary/#code_point">
660 * Unicode code point</a>, constant {@code U+10FFFF}.
661 *
662 * @since 1.5
663 */
664 public static final int MAX_CODE_POINT = 0X10FFFF;
665
666 /**
667 * Returns an {@link Optional} containing the nominal descriptor for this
668 * instance.
669 *
670 * @return an {@link Optional} describing the {@linkplain Character} instance
671 * @since 15
672 */
673 @Override
674 public Optional<DynamicConstantDesc<Character>> describeConstable() {
675 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
676 }
677
678 /**
679 * Instances of this class represent particular subsets of the Unicode
680 * character set. The only family of subsets defined in the
681 * {@code Character} class is {@link Character.UnicodeBlock}.
682 * Other portions of the Java API may define other subsets for their
683 * own purposes.
684 *
685 * @since 1.2
686 */
687 public static class Subset {
688
689 private String name;
690
691 /**
692 * Constructs a new {@code Subset} instance.
693 *
694 * @param name The name of this subset
695 * @throws NullPointerException if name is {@code null}
696 */
697 protected Subset(String name) {
698 if (name == null) {
699 throw new NullPointerException("name");
700 }
701 this.name = name;
702 }
703
704 /**
705 * Compares two {@code Subset} objects for equality.
706 * This method returns {@code true} if and only if
707 * {@code this} and the argument refer to the same
708 * object; since this method is {@code final}, this
709 * guarantee holds for all subclasses.
710 */
711 public final boolean equals(Object obj) {
712 return (this == obj);
713 }
714
715 /**
716 * Returns the standard hash code as defined by the
717 * {@link Object#hashCode} method. This method
718 * is {@code final} in order to ensure that the
719 * {@code equals} and {@code hashCode} methods will
720 * be consistent in all subclasses.
721 */
722 public final int hashCode() {
723 return super.hashCode();
724 }
725
726 /**
727 * Returns the name of this subset.
728 */
729 public final String toString() {
730 return name;
731 }
732 }
733
734 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
735 // for the latest specification of Unicode Blocks.
736
737 /**
738 * A family of character subsets representing the character blocks in the
739 * Unicode specification. Character blocks generally define characters
740 * used for a specific script or purpose. A character is contained by
741 * at most one Unicode block.
742 *
743 * @since 1.2
744 */
745 public static final class UnicodeBlock extends Subset {
746 /**
747 * NUM_ENTITIES should match the total number of UnicodeBlock identifier
748 * names plus their aliases.
749 * It should be adjusted whenever the Unicode Character Database
750 * is upgraded.
751 */
752 private static final int NUM_ENTITIES = 804;
753 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
754
755 /**
756 * Creates a UnicodeBlock with the given identifier name.
757 * This name must be the same as the block identifier.
758 */
759 private UnicodeBlock(String idName) {
760 super(idName);
761 map.put(idName, this);
762 }
763
764 /**
765 * Creates a UnicodeBlock with the given identifier name and
766 * alias name.
767 */
768 private UnicodeBlock(String idName, String alias) {
769 this(idName);
770 map.put(alias, this);
771 }
772
773 /**
774 * Creates a UnicodeBlock with the given identifier name and
775 * alias names.
776 */
777 private UnicodeBlock(String idName, String... aliases) {
778 this(idName);
779 for (String alias : aliases)
780 map.put(alias, this);
781 }
782
783 /**
784 * Constant for the "Basic Latin" Unicode character block.
785 * @since 1.2
786 */
787 public static final UnicodeBlock BASIC_LATIN =
788 new UnicodeBlock("BASIC_LATIN",
789 "BASIC LATIN",
790 "BASICLATIN");
791
792 /**
793 * Constant for the "Latin-1 Supplement" Unicode character block.
794 * @since 1.2
795 */
796 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
797 new UnicodeBlock("LATIN_1_SUPPLEMENT",
798 "LATIN-1 SUPPLEMENT",
799 "LATIN-1SUPPLEMENT");
800
801 /**
802 * Constant for the "Latin Extended-A" Unicode character block.
803 * @since 1.2
804 */
805 public static final UnicodeBlock LATIN_EXTENDED_A =
806 new UnicodeBlock("LATIN_EXTENDED_A",
807 "LATIN EXTENDED-A",
808 "LATINEXTENDED-A");
809
810 /**
811 * Constant for the "Latin Extended-B" Unicode character block.
812 * @since 1.2
813 */
814 public static final UnicodeBlock LATIN_EXTENDED_B =
815 new UnicodeBlock("LATIN_EXTENDED_B",
816 "LATIN EXTENDED-B",
817 "LATINEXTENDED-B");
818
819 /**
820 * Constant for the "IPA Extensions" Unicode character block.
821 * @since 1.2
822 */
823 public static final UnicodeBlock IPA_EXTENSIONS =
824 new UnicodeBlock("IPA_EXTENSIONS",
825 "IPA EXTENSIONS",
826 "IPAEXTENSIONS");
827
828 /**
829 * Constant for the "Spacing Modifier Letters" Unicode character block.
830 * @since 1.2
831 */
832 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
833 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
834 "SPACING MODIFIER LETTERS",
835 "SPACINGMODIFIERLETTERS");
836
837 /**
838 * Constant for the "Combining Diacritical Marks" Unicode character block.
839 * @since 1.2
840 */
841 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
842 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
843 "COMBINING DIACRITICAL MARKS",
844 "COMBININGDIACRITICALMARKS");
845
846 /**
847 * Constant for the "Greek and Coptic" Unicode character block.
848 * <p>
849 * This block was previously known as the "Greek" block.
850 *
851 * @since 1.2
852 */
853 public static final UnicodeBlock GREEK =
854 new UnicodeBlock("GREEK",
855 "GREEK AND COPTIC",
856 "GREEKANDCOPTIC");
857
858 /**
859 * Constant for the "Cyrillic" Unicode character block.
860 * @since 1.2
861 */
862 public static final UnicodeBlock CYRILLIC =
863 new UnicodeBlock("CYRILLIC");
864
865 /**
866 * Constant for the "Armenian" Unicode character block.
867 * @since 1.2
868 */
869 public static final UnicodeBlock ARMENIAN =
870 new UnicodeBlock("ARMENIAN");
871
872 /**
873 * Constant for the "Hebrew" Unicode character block.
874 * @since 1.2
875 */
876 public static final UnicodeBlock HEBREW =
877 new UnicodeBlock("HEBREW");
878
879 /**
880 * Constant for the "Arabic" Unicode character block.
881 * @since 1.2
882 */
883 public static final UnicodeBlock ARABIC =
884 new UnicodeBlock("ARABIC");
885
886 /**
887 * Constant for the "Devanagari" Unicode character block.
888 * @since 1.2
889 */
890 public static final UnicodeBlock DEVANAGARI =
891 new UnicodeBlock("DEVANAGARI");
892
893 /**
894 * Constant for the "Bengali" Unicode character block.
895 * @since 1.2
896 */
897 public static final UnicodeBlock BENGALI =
898 new UnicodeBlock("BENGALI");
899
900 /**
901 * Constant for the "Gurmukhi" Unicode character block.
902 * @since 1.2
903 */
904 public static final UnicodeBlock GURMUKHI =
905 new UnicodeBlock("GURMUKHI");
906
907 /**
908 * Constant for the "Gujarati" Unicode character block.
909 * @since 1.2
910 */
911 public static final UnicodeBlock GUJARATI =
912 new UnicodeBlock("GUJARATI");
913
914 /**
915 * Constant for the "Oriya" Unicode character block.
916 * @since 1.2
917 */
918 public static final UnicodeBlock ORIYA =
919 new UnicodeBlock("ORIYA");
920
921 /**
922 * Constant for the "Tamil" Unicode character block.
923 * @since 1.2
924 */
925 public static final UnicodeBlock TAMIL =
926 new UnicodeBlock("TAMIL");
927
928 /**
929 * Constant for the "Telugu" Unicode character block.
930 * @since 1.2
931 */
932 public static final UnicodeBlock TELUGU =
933 new UnicodeBlock("TELUGU");
934
935 /**
936 * Constant for the "Kannada" Unicode character block.
937 * @since 1.2
938 */
939 public static final UnicodeBlock KANNADA =
940 new UnicodeBlock("KANNADA");
941
942 /**
943 * Constant for the "Malayalam" Unicode character block.
944 * @since 1.2
945 */
946 public static final UnicodeBlock MALAYALAM =
947 new UnicodeBlock("MALAYALAM");
948
949 /**
950 * Constant for the "Thai" Unicode character block.
951 * @since 1.2
952 */
953 public static final UnicodeBlock THAI =
954 new UnicodeBlock("THAI");
955
956 /**
957 * Constant for the "Lao" Unicode character block.
958 * @since 1.2
959 */
960 public static final UnicodeBlock LAO =
961 new UnicodeBlock("LAO");
962
963 /**
964 * Constant for the "Tibetan" Unicode character block.
965 * @since 1.2
966 */
967 public static final UnicodeBlock TIBETAN =
968 new UnicodeBlock("TIBETAN");
969
970 /**
971 * Constant for the "Georgian" Unicode character block.
972 * @since 1.2
973 */
974 public static final UnicodeBlock GEORGIAN =
975 new UnicodeBlock("GEORGIAN");
976
977 /**
978 * Constant for the "Hangul Jamo" Unicode character block.
979 * @since 1.2
980 */
981 public static final UnicodeBlock HANGUL_JAMO =
982 new UnicodeBlock("HANGUL_JAMO",
983 "HANGUL JAMO",
984 "HANGULJAMO");
985
986 /**
987 * Constant for the "Latin Extended Additional" Unicode character block.
988 * @since 1.2
989 */
990 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
991 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
992 "LATIN EXTENDED ADDITIONAL",
993 "LATINEXTENDEDADDITIONAL");
994
995 /**
996 * Constant for the "Greek Extended" Unicode character block.
997 * @since 1.2
998 */
999 public static final UnicodeBlock GREEK_EXTENDED =
1000 new UnicodeBlock("GREEK_EXTENDED",
1001 "GREEK EXTENDED",
1002 "GREEKEXTENDED");
1003
1004 /**
1005 * Constant for the "General Punctuation" Unicode character block.
1006 * @since 1.2
1007 */
1008 public static final UnicodeBlock GENERAL_PUNCTUATION =
1009 new UnicodeBlock("GENERAL_PUNCTUATION",
1010 "GENERAL PUNCTUATION",
1011 "GENERALPUNCTUATION");
1012
1013 /**
1014 * Constant for the "Superscripts and Subscripts" Unicode character
1015 * block.
1016 * @since 1.2
1017 */
1018 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1019 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1020 "SUPERSCRIPTS AND SUBSCRIPTS",
1021 "SUPERSCRIPTSANDSUBSCRIPTS");
1022
1023 /**
1024 * Constant for the "Currency Symbols" Unicode character block.
1025 * @since 1.2
1026 */
1027 public static final UnicodeBlock CURRENCY_SYMBOLS =
1028 new UnicodeBlock("CURRENCY_SYMBOLS",
1029 "CURRENCY SYMBOLS",
1030 "CURRENCYSYMBOLS");
1031
1032 /**
1033 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1034 * character block.
1035 * <p>
1036 * This block was previously known as "Combining Marks for Symbols".
1037 * @since 1.2
1038 */
1039 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1040 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1041 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1042 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1043 "COMBINING MARKS FOR SYMBOLS",
1044 "COMBININGMARKSFORSYMBOLS");
1045
1046 /**
1047 * Constant for the "Letterlike Symbols" Unicode character block.
1048 * @since 1.2
1049 */
1050 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1051 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1052 "LETTERLIKE SYMBOLS",
1053 "LETTERLIKESYMBOLS");
1054
1055 /**
1056 * Constant for the "Number Forms" Unicode character block.
1057 * @since 1.2
1058 */
1059 public static final UnicodeBlock NUMBER_FORMS =
1060 new UnicodeBlock("NUMBER_FORMS",
1061 "NUMBER FORMS",
1062 "NUMBERFORMS");
1063
1064 /**
1065 * Constant for the "Arrows" Unicode character block.
1066 * @since 1.2
1067 */
1068 public static final UnicodeBlock ARROWS =
1069 new UnicodeBlock("ARROWS");
1070
1071 /**
1072 * Constant for the "Mathematical Operators" Unicode character block.
1073 * @since 1.2
1074 */
1075 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1076 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1077 "MATHEMATICAL OPERATORS",
1078 "MATHEMATICALOPERATORS");
1079
1080 /**
1081 * Constant for the "Miscellaneous Technical" Unicode character block.
1082 * @since 1.2
1083 */
1084 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1085 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1086 "MISCELLANEOUS TECHNICAL",
1087 "MISCELLANEOUSTECHNICAL");
1088
1089 /**
1090 * Constant for the "Control Pictures" Unicode character block.
1091 * @since 1.2
1092 */
1093 public static final UnicodeBlock CONTROL_PICTURES =
1094 new UnicodeBlock("CONTROL_PICTURES",
1095 "CONTROL PICTURES",
1096 "CONTROLPICTURES");
1097
1098 /**
1099 * Constant for the "Optical Character Recognition" Unicode character block.
1100 * @since 1.2
1101 */
1102 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1103 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1104 "OPTICAL CHARACTER RECOGNITION",
1105 "OPTICALCHARACTERRECOGNITION");
1106
1107 /**
1108 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1109 * @since 1.2
1110 */
1111 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1112 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1113 "ENCLOSED ALPHANUMERICS",
1114 "ENCLOSEDALPHANUMERICS");
1115
1116 /**
1117 * Constant for the "Box Drawing" Unicode character block.
1118 * @since 1.2
1119 */
1120 public static final UnicodeBlock BOX_DRAWING =
1121 new UnicodeBlock("BOX_DRAWING",
1122 "BOX DRAWING",
1123 "BOXDRAWING");
1124
1125 /**
1126 * Constant for the "Block Elements" Unicode character block.
1127 * @since 1.2
1128 */
1129 public static final UnicodeBlock BLOCK_ELEMENTS =
1130 new UnicodeBlock("BLOCK_ELEMENTS",
1131 "BLOCK ELEMENTS",
1132 "BLOCKELEMENTS");
1133
1134 /**
1135 * Constant for the "Geometric Shapes" Unicode character block.
1136 * @since 1.2
1137 */
1138 public static final UnicodeBlock GEOMETRIC_SHAPES =
1139 new UnicodeBlock("GEOMETRIC_SHAPES",
1140 "GEOMETRIC SHAPES",
1141 "GEOMETRICSHAPES");
1142
1143 /**
1144 * Constant for the "Miscellaneous Symbols" Unicode character block.
1145 * @since 1.2
1146 */
1147 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1148 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1149 "MISCELLANEOUS SYMBOLS",
1150 "MISCELLANEOUSSYMBOLS");
1151
1152 /**
1153 * Constant for the "Dingbats" Unicode character block.
1154 * @since 1.2
1155 */
1156 public static final UnicodeBlock DINGBATS =
1157 new UnicodeBlock("DINGBATS");
1158
1159 /**
1160 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1161 * @since 1.2
1162 */
1163 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1164 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1165 "CJK SYMBOLS AND PUNCTUATION",
1166 "CJKSYMBOLSANDPUNCTUATION");
1167
1168 /**
1169 * Constant for the "Hiragana" Unicode character block.
1170 * @since 1.2
1171 */
1172 public static final UnicodeBlock HIRAGANA =
1173 new UnicodeBlock("HIRAGANA");
1174
1175 /**
1176 * Constant for the "Katakana" Unicode character block.
1177 * @since 1.2
1178 */
1179 public static final UnicodeBlock KATAKANA =
1180 new UnicodeBlock("KATAKANA");
1181
1182 /**
1183 * Constant for the "Bopomofo" Unicode character block.
1184 * @since 1.2
1185 */
1186 public static final UnicodeBlock BOPOMOFO =
1187 new UnicodeBlock("BOPOMOFO");
1188
1189 /**
1190 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1191 * @since 1.2
1192 */
1193 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1194 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1195 "HANGUL COMPATIBILITY JAMO",
1196 "HANGULCOMPATIBILITYJAMO");
1197
1198 /**
1199 * Constant for the "Kanbun" Unicode character block.
1200 * @since 1.2
1201 */
1202 public static final UnicodeBlock KANBUN =
1203 new UnicodeBlock("KANBUN");
1204
1205 /**
1206 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1207 * @since 1.2
1208 */
1209 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1210 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1211 "ENCLOSED CJK LETTERS AND MONTHS",
1212 "ENCLOSEDCJKLETTERSANDMONTHS");
1213
1214 /**
1215 * Constant for the "CJK Compatibility" Unicode character block.
1216 * @since 1.2
1217 */
1218 public static final UnicodeBlock CJK_COMPATIBILITY =
1219 new UnicodeBlock("CJK_COMPATIBILITY",
1220 "CJK COMPATIBILITY",
1221 "CJKCOMPATIBILITY");
1222
1223 /**
1224 * Constant for the "CJK Unified Ideographs" Unicode character block.
1225 * @since 1.2
1226 */
1227 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1228 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1229 "CJK UNIFIED IDEOGRAPHS",
1230 "CJKUNIFIEDIDEOGRAPHS");
1231
1232 /**
1233 * Constant for the "Hangul Syllables" Unicode character block.
1234 * @since 1.2
1235 */
1236 public static final UnicodeBlock HANGUL_SYLLABLES =
1237 new UnicodeBlock("HANGUL_SYLLABLES",
1238 "HANGUL SYLLABLES",
1239 "HANGULSYLLABLES");
1240
1241 /**
1242 * Constant for the "Private Use Area" Unicode character block.
1243 * @since 1.2
1244 */
1245 public static final UnicodeBlock PRIVATE_USE_AREA =
1246 new UnicodeBlock("PRIVATE_USE_AREA",
1247 "PRIVATE USE AREA",
1248 "PRIVATEUSEAREA");
1249
1250 /**
1251 * Constant for the "CJK Compatibility Ideographs" Unicode character
1252 * block.
1253 * @since 1.2
1254 */
1255 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1256 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1257 "CJK COMPATIBILITY IDEOGRAPHS",
1258 "CJKCOMPATIBILITYIDEOGRAPHS");
1259
1260 /**
1261 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1262 * @since 1.2
1263 */
1264 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1265 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1266 "ALPHABETIC PRESENTATION FORMS",
1267 "ALPHABETICPRESENTATIONFORMS");
1268
1269 /**
1270 * Constant for the "Arabic Presentation Forms-A" Unicode character
1271 * block.
1272 * @since 1.2
1273 */
1274 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1275 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1276 "ARABIC PRESENTATION FORMS-A",
1277 "ARABICPRESENTATIONFORMS-A");
1278
1279 /**
1280 * Constant for the "Combining Half Marks" Unicode character block.
1281 * @since 1.2
1282 */
1283 public static final UnicodeBlock COMBINING_HALF_MARKS =
1284 new UnicodeBlock("COMBINING_HALF_MARKS",
1285 "COMBINING HALF MARKS",
1286 "COMBININGHALFMARKS");
1287
1288 /**
1289 * Constant for the "CJK Compatibility Forms" Unicode character block.
1290 * @since 1.2
1291 */
1292 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1293 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1294 "CJK COMPATIBILITY FORMS",
1295 "CJKCOMPATIBILITYFORMS");
1296
1297 /**
1298 * Constant for the "Small Form Variants" Unicode character block.
1299 * @since 1.2
1300 */
1301 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1302 new UnicodeBlock("SMALL_FORM_VARIANTS",
1303 "SMALL FORM VARIANTS",
1304 "SMALLFORMVARIANTS");
1305
1306 /**
1307 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1308 * @since 1.2
1309 */
1310 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1311 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1312 "ARABIC PRESENTATION FORMS-B",
1313 "ARABICPRESENTATIONFORMS-B");
1314
1315 /**
1316 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1317 * block.
1318 * @since 1.2
1319 */
1320 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1321 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1322 "HALFWIDTH AND FULLWIDTH FORMS",
1323 "HALFWIDTHANDFULLWIDTHFORMS");
1324
1325 /**
1326 * Constant for the "Specials" Unicode character block.
1327 * @since 1.2
1328 */
1329 public static final UnicodeBlock SPECIALS =
1330 new UnicodeBlock("SPECIALS");
1331
1332 /**
1333 * @deprecated
1334 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1335 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1336 * These constants match the block definitions of the Unicode Standard.
1337 * The {@link #of(char)} and {@link #of(int)} methods return the
1338 * standard constants.
1339 */
1340 @Deprecated(since="1.5")
1341 public static final UnicodeBlock SURROGATES_AREA =
1342 new UnicodeBlock("SURROGATES_AREA");
1343
1344 /**
1345 * Constant for the "Syriac" Unicode character block.
1346 * @since 1.4
1347 */
1348 public static final UnicodeBlock SYRIAC =
1349 new UnicodeBlock("SYRIAC");
1350
1351 /**
1352 * Constant for the "Thaana" Unicode character block.
1353 * @since 1.4
1354 */
1355 public static final UnicodeBlock THAANA =
1356 new UnicodeBlock("THAANA");
1357
1358 /**
1359 * Constant for the "Sinhala" Unicode character block.
1360 * @since 1.4
1361 */
1362 public static final UnicodeBlock SINHALA =
1363 new UnicodeBlock("SINHALA");
1364
1365 /**
1366 * Constant for the "Myanmar" Unicode character block.
1367 * @since 1.4
1368 */
1369 public static final UnicodeBlock MYANMAR =
1370 new UnicodeBlock("MYANMAR");
1371
1372 /**
1373 * Constant for the "Ethiopic" Unicode character block.
1374 * @since 1.4
1375 */
1376 public static final UnicodeBlock ETHIOPIC =
1377 new UnicodeBlock("ETHIOPIC");
1378
1379 /**
1380 * Constant for the "Cherokee" Unicode character block.
1381 * @since 1.4
1382 */
1383 public static final UnicodeBlock CHEROKEE =
1384 new UnicodeBlock("CHEROKEE");
1385
1386 /**
1387 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1388 * @since 1.4
1389 */
1390 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1391 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1392 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1393 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1394
1395 /**
1396 * Constant for the "Ogham" Unicode character block.
1397 * @since 1.4
1398 */
1399 public static final UnicodeBlock OGHAM =
1400 new UnicodeBlock("OGHAM");
1401
1402 /**
1403 * Constant for the "Runic" Unicode character block.
1404 * @since 1.4
1405 */
1406 public static final UnicodeBlock RUNIC =
1407 new UnicodeBlock("RUNIC");
1408
1409 /**
1410 * Constant for the "Khmer" Unicode character block.
1411 * @since 1.4
1412 */
1413 public static final UnicodeBlock KHMER =
1414 new UnicodeBlock("KHMER");
1415
1416 /**
1417 * Constant for the "Mongolian" Unicode character block.
1418 * @since 1.4
1419 */
1420 public static final UnicodeBlock MONGOLIAN =
1421 new UnicodeBlock("MONGOLIAN");
1422
1423 /**
1424 * Constant for the "Braille Patterns" Unicode character block.
1425 * @since 1.4
1426 */
1427 public static final UnicodeBlock BRAILLE_PATTERNS =
1428 new UnicodeBlock("BRAILLE_PATTERNS",
1429 "BRAILLE PATTERNS",
1430 "BRAILLEPATTERNS");
1431
1432 /**
1433 * Constant for the "CJK Radicals Supplement" Unicode character block.
1434 * @since 1.4
1435 */
1436 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1437 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1438 "CJK RADICALS SUPPLEMENT",
1439 "CJKRADICALSSUPPLEMENT");
1440
1441 /**
1442 * Constant for the "Kangxi Radicals" Unicode character block.
1443 * @since 1.4
1444 */
1445 public static final UnicodeBlock KANGXI_RADICALS =
1446 new UnicodeBlock("KANGXI_RADICALS",
1447 "KANGXI RADICALS",
1448 "KANGXIRADICALS");
1449
1450 /**
1451 * Constant for the "Ideographic Description Characters" Unicode character block.
1452 * @since 1.4
1453 */
1454 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1455 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1456 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1457 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1458
1459 /**
1460 * Constant for the "Bopomofo Extended" Unicode character block.
1461 * @since 1.4
1462 */
1463 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1464 new UnicodeBlock("BOPOMOFO_EXTENDED",
1465 "BOPOMOFO EXTENDED",
1466 "BOPOMOFOEXTENDED");
1467
1468 /**
1469 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1470 * @since 1.4
1471 */
1472 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1473 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1474 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1475 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1476
1477 /**
1478 * Constant for the "Yi Syllables" Unicode character block.
1479 * @since 1.4
1480 */
1481 public static final UnicodeBlock YI_SYLLABLES =
1482 new UnicodeBlock("YI_SYLLABLES",
1483 "YI SYLLABLES",
1484 "YISYLLABLES");
1485
1486 /**
1487 * Constant for the "Yi Radicals" Unicode character block.
1488 * @since 1.4
1489 */
1490 public static final UnicodeBlock YI_RADICALS =
1491 new UnicodeBlock("YI_RADICALS",
1492 "YI RADICALS",
1493 "YIRADICALS");
1494
1495 /**
1496 * Constant for the "Cyrillic Supplement" Unicode character block.
1497 * This block was previously known as the "Cyrillic Supplementary" block.
1498 * @since 1.5
1499 */
1500 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1501 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1502 "CYRILLIC SUPPLEMENTARY",
1503 "CYRILLICSUPPLEMENTARY",
1504 "CYRILLIC SUPPLEMENT",
1505 "CYRILLICSUPPLEMENT");
1506
1507 /**
1508 * Constant for the "Tagalog" Unicode character block.
1509 * @since 1.5
1510 */
1511 public static final UnicodeBlock TAGALOG =
1512 new UnicodeBlock("TAGALOG");
1513
1514 /**
1515 * Constant for the "Hanunoo" Unicode character block.
1516 * @since 1.5
1517 */
1518 public static final UnicodeBlock HANUNOO =
1519 new UnicodeBlock("HANUNOO");
1520
1521 /**
1522 * Constant for the "Buhid" Unicode character block.
1523 * @since 1.5
1524 */
1525 public static final UnicodeBlock BUHID =
1526 new UnicodeBlock("BUHID");
1527
1528 /**
1529 * Constant for the "Tagbanwa" Unicode character block.
1530 * @since 1.5
1531 */
1532 public static final UnicodeBlock TAGBANWA =
1533 new UnicodeBlock("TAGBANWA");
1534
1535 /**
1536 * Constant for the "Limbu" Unicode character block.
1537 * @since 1.5
1538 */
1539 public static final UnicodeBlock LIMBU =
1540 new UnicodeBlock("LIMBU");
1541
1542 /**
1543 * Constant for the "Tai Le" Unicode character block.
1544 * @since 1.5
1545 */
1546 public static final UnicodeBlock TAI_LE =
1547 new UnicodeBlock("TAI_LE",
1548 "TAI LE",
1549 "TAILE");
1550
1551 /**
1552 * Constant for the "Khmer Symbols" Unicode character block.
1553 * @since 1.5
1554 */
1555 public static final UnicodeBlock KHMER_SYMBOLS =
1556 new UnicodeBlock("KHMER_SYMBOLS",
1557 "KHMER SYMBOLS",
1558 "KHMERSYMBOLS");
1559
1560 /**
1561 * Constant for the "Phonetic Extensions" Unicode character block.
1562 * @since 1.5
1563 */
1564 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1565 new UnicodeBlock("PHONETIC_EXTENSIONS",
1566 "PHONETIC EXTENSIONS",
1567 "PHONETICEXTENSIONS");
1568
1569 /**
1570 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1571 * @since 1.5
1572 */
1573 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1574 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1575 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1576 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1577
1578 /**
1579 * Constant for the "Supplemental Arrows-A" Unicode character block.
1580 * @since 1.5
1581 */
1582 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1583 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1584 "SUPPLEMENTAL ARROWS-A",
1585 "SUPPLEMENTALARROWS-A");
1586
1587 /**
1588 * Constant for the "Supplemental Arrows-B" Unicode character block.
1589 * @since 1.5
1590 */
1591 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1592 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1593 "SUPPLEMENTAL ARROWS-B",
1594 "SUPPLEMENTALARROWS-B");
1595
1596 /**
1597 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1598 * character block.
1599 * @since 1.5
1600 */
1601 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1602 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1603 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1604 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1605
1606 /**
1607 * Constant for the "Supplemental Mathematical Operators" Unicode
1608 * character block.
1609 * @since 1.5
1610 */
1611 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1612 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1613 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1614 "SUPPLEMENTALMATHEMATICALOPERATORS");
1615
1616 /**
1617 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1618 * block.
1619 * @since 1.5
1620 */
1621 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1622 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1623 "MISCELLANEOUS SYMBOLS AND ARROWS",
1624 "MISCELLANEOUSSYMBOLSANDARROWS");
1625
1626 /**
1627 * Constant for the "Katakana Phonetic Extensions" Unicode character
1628 * block.
1629 * @since 1.5
1630 */
1631 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1632 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1633 "KATAKANA PHONETIC EXTENSIONS",
1634 "KATAKANAPHONETICEXTENSIONS");
1635
1636 /**
1637 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1638 * @since 1.5
1639 */
1640 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1641 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1642 "YIJING HEXAGRAM SYMBOLS",
1643 "YIJINGHEXAGRAMSYMBOLS");
1644
1645 /**
1646 * Constant for the "Variation Selectors" Unicode character block.
1647 * @since 1.5
1648 */
1649 public static final UnicodeBlock VARIATION_SELECTORS =
1650 new UnicodeBlock("VARIATION_SELECTORS",
1651 "VARIATION SELECTORS",
1652 "VARIATIONSELECTORS");
1653
1654 /**
1655 * Constant for the "Linear B Syllabary" Unicode character block.
1656 * @since 1.5
1657 */
1658 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1659 new UnicodeBlock("LINEAR_B_SYLLABARY",
1660 "LINEAR B SYLLABARY",
1661 "LINEARBSYLLABARY");
1662
1663 /**
1664 * Constant for the "Linear B Ideograms" Unicode character block.
1665 * @since 1.5
1666 */
1667 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1668 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1669 "LINEAR B IDEOGRAMS",
1670 "LINEARBIDEOGRAMS");
1671
1672 /**
1673 * Constant for the "Aegean Numbers" Unicode character block.
1674 * @since 1.5
1675 */
1676 public static final UnicodeBlock AEGEAN_NUMBERS =
1677 new UnicodeBlock("AEGEAN_NUMBERS",
1678 "AEGEAN NUMBERS",
1679 "AEGEANNUMBERS");
1680
1681 /**
1682 * Constant for the "Old Italic" Unicode character block.
1683 * @since 1.5
1684 */
1685 public static final UnicodeBlock OLD_ITALIC =
1686 new UnicodeBlock("OLD_ITALIC",
1687 "OLD ITALIC",
1688 "OLDITALIC");
1689
1690 /**
1691 * Constant for the "Gothic" Unicode character block.
1692 * @since 1.5
1693 */
1694 public static final UnicodeBlock GOTHIC =
1695 new UnicodeBlock("GOTHIC");
1696
1697 /**
1698 * Constant for the "Ugaritic" Unicode character block.
1699 * @since 1.5
1700 */
1701 public static final UnicodeBlock UGARITIC =
1702 new UnicodeBlock("UGARITIC");
1703
1704 /**
1705 * Constant for the "Deseret" Unicode character block.
1706 * @since 1.5
1707 */
1708 public static final UnicodeBlock DESERET =
1709 new UnicodeBlock("DESERET");
1710
1711 /**
1712 * Constant for the "Shavian" Unicode character block.
1713 * @since 1.5
1714 */
1715 public static final UnicodeBlock SHAVIAN =
1716 new UnicodeBlock("SHAVIAN");
1717
1718 /**
1719 * Constant for the "Osmanya" Unicode character block.
1720 * @since 1.5
1721 */
1722 public static final UnicodeBlock OSMANYA =
1723 new UnicodeBlock("OSMANYA");
1724
1725 /**
1726 * Constant for the "Cypriot Syllabary" Unicode character block.
1727 * @since 1.5
1728 */
1729 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1730 new UnicodeBlock("CYPRIOT_SYLLABARY",
1731 "CYPRIOT SYLLABARY",
1732 "CYPRIOTSYLLABARY");
1733
1734 /**
1735 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1736 * @since 1.5
1737 */
1738 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1739 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1740 "BYZANTINE MUSICAL SYMBOLS",
1741 "BYZANTINEMUSICALSYMBOLS");
1742
1743 /**
1744 * Constant for the "Musical Symbols" Unicode character block.
1745 * @since 1.5
1746 */
1747 public static final UnicodeBlock MUSICAL_SYMBOLS =
1748 new UnicodeBlock("MUSICAL_SYMBOLS",
1749 "MUSICAL SYMBOLS",
1750 "MUSICALSYMBOLS");
1751
1752 /**
1753 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1754 * @since 1.5
1755 */
1756 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1757 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1758 "TAI XUAN JING SYMBOLS",
1759 "TAIXUANJINGSYMBOLS");
1760
1761 /**
1762 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1763 * character block.
1764 * @since 1.5
1765 */
1766 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1767 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1768 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1769 "MATHEMATICALALPHANUMERICSYMBOLS");
1770
1771 /**
1772 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1773 * character block.
1774 * @since 1.5
1775 */
1776 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1777 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1778 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1779 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1780
1781 /**
1782 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1783 * @since 1.5
1784 */
1785 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1786 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1787 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1788 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1789
1790 /**
1791 * Constant for the "Tags" Unicode character block.
1792 * @since 1.5
1793 */
1794 public static final UnicodeBlock TAGS =
1795 new UnicodeBlock("TAGS");
1796
1797 /**
1798 * Constant for the "Variation Selectors Supplement" Unicode character
1799 * block.
1800 * @since 1.5
1801 */
1802 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1803 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1804 "VARIATION SELECTORS SUPPLEMENT",
1805 "VARIATIONSELECTORSSUPPLEMENT");
1806
1807 /**
1808 * Constant for the "Supplementary Private Use Area-A" Unicode character
1809 * block.
1810 * @since 1.5
1811 */
1812 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1813 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1814 "SUPPLEMENTARY PRIVATE USE AREA-A",
1815 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1816
1817 /**
1818 * Constant for the "Supplementary Private Use Area-B" Unicode character
1819 * block.
1820 * @since 1.5
1821 */
1822 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1823 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1824 "SUPPLEMENTARY PRIVATE USE AREA-B",
1825 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1826
1827 /**
1828 * Constant for the "High Surrogates" Unicode character block.
1829 * This block represents codepoint values in the high surrogate
1830 * range: U+D800 through U+DB7F
1831 *
1832 * @since 1.5
1833 */
1834 public static final UnicodeBlock HIGH_SURROGATES =
1835 new UnicodeBlock("HIGH_SURROGATES",
1836 "HIGH SURROGATES",
1837 "HIGHSURROGATES");
1838
1839 /**
1840 * Constant for the "High Private Use Surrogates" Unicode character
1841 * block.
1842 * This block represents codepoint values in the private use high
1843 * surrogate range: U+DB80 through U+DBFF
1844 *
1845 * @since 1.5
1846 */
1847 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1848 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1849 "HIGH PRIVATE USE SURROGATES",
1850 "HIGHPRIVATEUSESURROGATES");
1851
1852 /**
1853 * Constant for the "Low Surrogates" Unicode character block.
1854 * This block represents codepoint values in the low surrogate
1855 * range: U+DC00 through U+DFFF
1856 *
1857 * @since 1.5
1858 */
1859 public static final UnicodeBlock LOW_SURROGATES =
1860 new UnicodeBlock("LOW_SURROGATES",
1861 "LOW SURROGATES",
1862 "LOWSURROGATES");
1863
1864 /**
1865 * Constant for the "Arabic Supplement" Unicode character block.
1866 * @since 1.7
1867 */
1868 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1869 new UnicodeBlock("ARABIC_SUPPLEMENT",
1870 "ARABIC SUPPLEMENT",
1871 "ARABICSUPPLEMENT");
1872
1873 /**
1874 * Constant for the "NKo" Unicode character block.
1875 * @since 1.7
1876 */
1877 public static final UnicodeBlock NKO =
1878 new UnicodeBlock("NKO");
1879
1880 /**
1881 * Constant for the "Samaritan" Unicode character block.
1882 * @since 1.7
1883 */
1884 public static final UnicodeBlock SAMARITAN =
1885 new UnicodeBlock("SAMARITAN");
1886
1887 /**
1888 * Constant for the "Mandaic" Unicode character block.
1889 * @since 1.7
1890 */
1891 public static final UnicodeBlock MANDAIC =
1892 new UnicodeBlock("MANDAIC");
1893
1894 /**
1895 * Constant for the "Ethiopic Supplement" Unicode character block.
1896 * @since 1.7
1897 */
1898 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1899 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1900 "ETHIOPIC SUPPLEMENT",
1901 "ETHIOPICSUPPLEMENT");
1902
1903 /**
1904 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1905 * Unicode character block.
1906 * @since 1.7
1907 */
1908 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1909 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1910 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1911 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1912
1913 /**
1914 * Constant for the "New Tai Lue" Unicode character block.
1915 * @since 1.7
1916 */
1917 public static final UnicodeBlock NEW_TAI_LUE =
1918 new UnicodeBlock("NEW_TAI_LUE",
1919 "NEW TAI LUE",
1920 "NEWTAILUE");
1921
1922 /**
1923 * Constant for the "Buginese" Unicode character block.
1924 * @since 1.7
1925 */
1926 public static final UnicodeBlock BUGINESE =
1927 new UnicodeBlock("BUGINESE");
1928
1929 /**
1930 * Constant for the "Tai Tham" Unicode character block.
1931 * @since 1.7
1932 */
1933 public static final UnicodeBlock TAI_THAM =
1934 new UnicodeBlock("TAI_THAM",
1935 "TAI THAM",
1936 "TAITHAM");
1937
1938 /**
1939 * Constant for the "Balinese" Unicode character block.
1940 * @since 1.7
1941 */
1942 public static final UnicodeBlock BALINESE =
1943 new UnicodeBlock("BALINESE");
1944
1945 /**
1946 * Constant for the "Sundanese" Unicode character block.
1947 * @since 1.7
1948 */
1949 public static final UnicodeBlock SUNDANESE =
1950 new UnicodeBlock("SUNDANESE");
1951
1952 /**
1953 * Constant for the "Batak" Unicode character block.
1954 * @since 1.7
1955 */
1956 public static final UnicodeBlock BATAK =
1957 new UnicodeBlock("BATAK");
1958
1959 /**
1960 * Constant for the "Lepcha" Unicode character block.
1961 * @since 1.7
1962 */
1963 public static final UnicodeBlock LEPCHA =
1964 new UnicodeBlock("LEPCHA");
1965
1966 /**
1967 * Constant for the "Ol Chiki" Unicode character block.
1968 * @since 1.7
1969 */
1970 public static final UnicodeBlock OL_CHIKI =
1971 new UnicodeBlock("OL_CHIKI",
1972 "OL CHIKI",
1973 "OLCHIKI");
1974
1975 /**
1976 * Constant for the "Vedic Extensions" Unicode character block.
1977 * @since 1.7
1978 */
1979 public static final UnicodeBlock VEDIC_EXTENSIONS =
1980 new UnicodeBlock("VEDIC_EXTENSIONS",
1981 "VEDIC EXTENSIONS",
1982 "VEDICEXTENSIONS");
1983
1984 /**
1985 * Constant for the "Phonetic Extensions Supplement" Unicode character
1986 * block.
1987 * @since 1.7
1988 */
1989 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1990 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1991 "PHONETIC EXTENSIONS SUPPLEMENT",
1992 "PHONETICEXTENSIONSSUPPLEMENT");
1993
1994 /**
1995 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1996 * character block.
1997 * @since 1.7
1998 */
1999 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
2000 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
2001 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
2002 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2003
2004 /**
2005 * Constant for the "Glagolitic" Unicode character block.
2006 * @since 1.7
2007 */
2008 public static final UnicodeBlock GLAGOLITIC =
2009 new UnicodeBlock("GLAGOLITIC");
2010
2011 /**
2012 * Constant for the "Latin Extended-C" Unicode character block.
2013 * @since 1.7
2014 */
2015 public static final UnicodeBlock LATIN_EXTENDED_C =
2016 new UnicodeBlock("LATIN_EXTENDED_C",
2017 "LATIN EXTENDED-C",
2018 "LATINEXTENDED-C");
2019
2020 /**
2021 * Constant for the "Coptic" Unicode character block.
2022 * @since 1.7
2023 */
2024 public static final UnicodeBlock COPTIC =
2025 new UnicodeBlock("COPTIC");
2026
2027 /**
2028 * Constant for the "Georgian Supplement" Unicode character block.
2029 * @since 1.7
2030 */
2031 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2032 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2033 "GEORGIAN SUPPLEMENT",
2034 "GEORGIANSUPPLEMENT");
2035
2036 /**
2037 * Constant for the "Tifinagh" Unicode character block.
2038 * @since 1.7
2039 */
2040 public static final UnicodeBlock TIFINAGH =
2041 new UnicodeBlock("TIFINAGH");
2042
2043 /**
2044 * Constant for the "Ethiopic Extended" Unicode character block.
2045 * @since 1.7
2046 */
2047 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2048 new UnicodeBlock("ETHIOPIC_EXTENDED",
2049 "ETHIOPIC EXTENDED",
2050 "ETHIOPICEXTENDED");
2051
2052 /**
2053 * Constant for the "Cyrillic Extended-A" Unicode character block.
2054 * @since 1.7
2055 */
2056 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2057 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2058 "CYRILLIC EXTENDED-A",
2059 "CYRILLICEXTENDED-A");
2060
2061 /**
2062 * Constant for the "Supplemental Punctuation" Unicode character block.
2063 * @since 1.7
2064 */
2065 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2066 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2067 "SUPPLEMENTAL PUNCTUATION",
2068 "SUPPLEMENTALPUNCTUATION");
2069
2070 /**
2071 * Constant for the "CJK Strokes" Unicode character block.
2072 * @since 1.7
2073 */
2074 public static final UnicodeBlock CJK_STROKES =
2075 new UnicodeBlock("CJK_STROKES",
2076 "CJK STROKES",
2077 "CJKSTROKES");
2078
2079 /**
2080 * Constant for the "Lisu" Unicode character block.
2081 * @since 1.7
2082 */
2083 public static final UnicodeBlock LISU =
2084 new UnicodeBlock("LISU");
2085
2086 /**
2087 * Constant for the "Vai" Unicode character block.
2088 * @since 1.7
2089 */
2090 public static final UnicodeBlock VAI =
2091 new UnicodeBlock("VAI");
2092
2093 /**
2094 * Constant for the "Cyrillic Extended-B" Unicode character block.
2095 * @since 1.7
2096 */
2097 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2098 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2099 "CYRILLIC EXTENDED-B",
2100 "CYRILLICEXTENDED-B");
2101
2102 /**
2103 * Constant for the "Bamum" Unicode character block.
2104 * @since 1.7
2105 */
2106 public static final UnicodeBlock BAMUM =
2107 new UnicodeBlock("BAMUM");
2108
2109 /**
2110 * Constant for the "Modifier Tone Letters" Unicode character block.
2111 * @since 1.7
2112 */
2113 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2114 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2115 "MODIFIER TONE LETTERS",
2116 "MODIFIERTONELETTERS");
2117
2118 /**
2119 * Constant for the "Latin Extended-D" Unicode character block.
2120 * @since 1.7
2121 */
2122 public static final UnicodeBlock LATIN_EXTENDED_D =
2123 new UnicodeBlock("LATIN_EXTENDED_D",
2124 "LATIN EXTENDED-D",
2125 "LATINEXTENDED-D");
2126
2127 /**
2128 * Constant for the "Syloti Nagri" Unicode character block.
2129 * @since 1.7
2130 */
2131 public static final UnicodeBlock SYLOTI_NAGRI =
2132 new UnicodeBlock("SYLOTI_NAGRI",
2133 "SYLOTI NAGRI",
2134 "SYLOTINAGRI");
2135
2136 /**
2137 * Constant for the "Common Indic Number Forms" Unicode character block.
2138 * @since 1.7
2139 */
2140 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2141 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2142 "COMMON INDIC NUMBER FORMS",
2143 "COMMONINDICNUMBERFORMS");
2144
2145 /**
2146 * Constant for the "Phags-pa" Unicode character block.
2147 * @since 1.7
2148 */
2149 public static final UnicodeBlock PHAGS_PA =
2150 new UnicodeBlock("PHAGS_PA",
2151 "PHAGS-PA");
2152
2153 /**
2154 * Constant for the "Saurashtra" Unicode character block.
2155 * @since 1.7
2156 */
2157 public static final UnicodeBlock SAURASHTRA =
2158 new UnicodeBlock("SAURASHTRA");
2159
2160 /**
2161 * Constant for the "Devanagari Extended" Unicode character block.
2162 * @since 1.7
2163 */
2164 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2165 new UnicodeBlock("DEVANAGARI_EXTENDED",
2166 "DEVANAGARI EXTENDED",
2167 "DEVANAGARIEXTENDED");
2168
2169 /**
2170 * Constant for the "Kayah Li" Unicode character block.
2171 * @since 1.7
2172 */
2173 public static final UnicodeBlock KAYAH_LI =
2174 new UnicodeBlock("KAYAH_LI",
2175 "KAYAH LI",
2176 "KAYAHLI");
2177
2178 /**
2179 * Constant for the "Rejang" Unicode character block.
2180 * @since 1.7
2181 */
2182 public static final UnicodeBlock REJANG =
2183 new UnicodeBlock("REJANG");
2184
2185 /**
2186 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2187 * @since 1.7
2188 */
2189 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2190 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2191 "HANGUL JAMO EXTENDED-A",
2192 "HANGULJAMOEXTENDED-A");
2193
2194 /**
2195 * Constant for the "Javanese" Unicode character block.
2196 * @since 1.7
2197 */
2198 public static final UnicodeBlock JAVANESE =
2199 new UnicodeBlock("JAVANESE");
2200
2201 /**
2202 * Constant for the "Cham" Unicode character block.
2203 * @since 1.7
2204 */
2205 public static final UnicodeBlock CHAM =
2206 new UnicodeBlock("CHAM");
2207
2208 /**
2209 * Constant for the "Myanmar Extended-A" Unicode character block.
2210 * @since 1.7
2211 */
2212 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2213 new UnicodeBlock("MYANMAR_EXTENDED_A",
2214 "MYANMAR EXTENDED-A",
2215 "MYANMAREXTENDED-A");
2216
2217 /**
2218 * Constant for the "Tai Viet" Unicode character block.
2219 * @since 1.7
2220 */
2221 public static final UnicodeBlock TAI_VIET =
2222 new UnicodeBlock("TAI_VIET",
2223 "TAI VIET",
2224 "TAIVIET");
2225
2226 /**
2227 * Constant for the "Ethiopic Extended-A" Unicode character block.
2228 * @since 1.7
2229 */
2230 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2231 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2232 "ETHIOPIC EXTENDED-A",
2233 "ETHIOPICEXTENDED-A");
2234
2235 /**
2236 * Constant for the "Meetei Mayek" Unicode character block.
2237 * @since 1.7
2238 */
2239 public static final UnicodeBlock MEETEI_MAYEK =
2240 new UnicodeBlock("MEETEI_MAYEK",
2241 "MEETEI MAYEK",
2242 "MEETEIMAYEK");
2243
2244 /**
2245 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2246 * @since 1.7
2247 */
2248 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2249 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2250 "HANGUL JAMO EXTENDED-B",
2251 "HANGULJAMOEXTENDED-B");
2252
2253 /**
2254 * Constant for the "Vertical Forms" Unicode character block.
2255 * @since 1.7
2256 */
2257 public static final UnicodeBlock VERTICAL_FORMS =
2258 new UnicodeBlock("VERTICAL_FORMS",
2259 "VERTICAL FORMS",
2260 "VERTICALFORMS");
2261
2262 /**
2263 * Constant for the "Ancient Greek Numbers" Unicode character block.
2264 * @since 1.7
2265 */
2266 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2267 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2268 "ANCIENT GREEK NUMBERS",
2269 "ANCIENTGREEKNUMBERS");
2270
2271 /**
2272 * Constant for the "Ancient Symbols" Unicode character block.
2273 * @since 1.7
2274 */
2275 public static final UnicodeBlock ANCIENT_SYMBOLS =
2276 new UnicodeBlock("ANCIENT_SYMBOLS",
2277 "ANCIENT SYMBOLS",
2278 "ANCIENTSYMBOLS");
2279
2280 /**
2281 * Constant for the "Phaistos Disc" Unicode character block.
2282 * @since 1.7
2283 */
2284 public static final UnicodeBlock PHAISTOS_DISC =
2285 new UnicodeBlock("PHAISTOS_DISC",
2286 "PHAISTOS DISC",
2287 "PHAISTOSDISC");
2288
2289 /**
2290 * Constant for the "Lycian" Unicode character block.
2291 * @since 1.7
2292 */
2293 public static final UnicodeBlock LYCIAN =
2294 new UnicodeBlock("LYCIAN");
2295
2296 /**
2297 * Constant for the "Carian" Unicode character block.
2298 * @since 1.7
2299 */
2300 public static final UnicodeBlock CARIAN =
2301 new UnicodeBlock("CARIAN");
2302
2303 /**
2304 * Constant for the "Old Persian" Unicode character block.
2305 * @since 1.7
2306 */
2307 public static final UnicodeBlock OLD_PERSIAN =
2308 new UnicodeBlock("OLD_PERSIAN",
2309 "OLD PERSIAN",
2310 "OLDPERSIAN");
2311
2312 /**
2313 * Constant for the "Imperial Aramaic" Unicode character block.
2314 * @since 1.7
2315 */
2316 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2317 new UnicodeBlock("IMPERIAL_ARAMAIC",
2318 "IMPERIAL ARAMAIC",
2319 "IMPERIALARAMAIC");
2320
2321 /**
2322 * Constant for the "Phoenician" Unicode character block.
2323 * @since 1.7
2324 */
2325 public static final UnicodeBlock PHOENICIAN =
2326 new UnicodeBlock("PHOENICIAN");
2327
2328 /**
2329 * Constant for the "Lydian" Unicode character block.
2330 * @since 1.7
2331 */
2332 public static final UnicodeBlock LYDIAN =
2333 new UnicodeBlock("LYDIAN");
2334
2335 /**
2336 * Constant for the "Kharoshthi" Unicode character block.
2337 * @since 1.7
2338 */
2339 public static final UnicodeBlock KHAROSHTHI =
2340 new UnicodeBlock("KHAROSHTHI");
2341
2342 /**
2343 * Constant for the "Old South Arabian" Unicode character block.
2344 * @since 1.7
2345 */
2346 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2347 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2348 "OLD SOUTH ARABIAN",
2349 "OLDSOUTHARABIAN");
2350
2351 /**
2352 * Constant for the "Avestan" Unicode character block.
2353 * @since 1.7
2354 */
2355 public static final UnicodeBlock AVESTAN =
2356 new UnicodeBlock("AVESTAN");
2357
2358 /**
2359 * Constant for the "Inscriptional Parthian" Unicode character block.
2360 * @since 1.7
2361 */
2362 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2363 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2364 "INSCRIPTIONAL PARTHIAN",
2365 "INSCRIPTIONALPARTHIAN");
2366
2367 /**
2368 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2369 * @since 1.7
2370 */
2371 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2372 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2373 "INSCRIPTIONAL PAHLAVI",
2374 "INSCRIPTIONALPAHLAVI");
2375
2376 /**
2377 * Constant for the "Old Turkic" Unicode character block.
2378 * @since 1.7
2379 */
2380 public static final UnicodeBlock OLD_TURKIC =
2381 new UnicodeBlock("OLD_TURKIC",
2382 "OLD TURKIC",
2383 "OLDTURKIC");
2384
2385 /**
2386 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2387 * @since 1.7
2388 */
2389 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2390 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2391 "RUMI NUMERAL SYMBOLS",
2392 "RUMINUMERALSYMBOLS");
2393
2394 /**
2395 * Constant for the "Brahmi" Unicode character block.
2396 * @since 1.7
2397 */
2398 public static final UnicodeBlock BRAHMI =
2399 new UnicodeBlock("BRAHMI");
2400
2401 /**
2402 * Constant for the "Kaithi" Unicode character block.
2403 * @since 1.7
2404 */
2405 public static final UnicodeBlock KAITHI =
2406 new UnicodeBlock("KAITHI");
2407
2408 /**
2409 * Constant for the "Cuneiform" Unicode character block.
2410 * @since 1.7
2411 */
2412 public static final UnicodeBlock CUNEIFORM =
2413 new UnicodeBlock("CUNEIFORM");
2414
2415 /**
2416 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2417 * character block.
2418 * @since 1.7
2419 */
2420 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2421 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2422 "CUNEIFORM NUMBERS AND PUNCTUATION",
2423 "CUNEIFORMNUMBERSANDPUNCTUATION");
2424
2425 /**
2426 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2427 * @since 1.7
2428 */
2429 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2430 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2431 "EGYPTIAN HIEROGLYPHS",
2432 "EGYPTIANHIEROGLYPHS");
2433
2434 /**
2435 * Constant for the "Bamum Supplement" Unicode character block.
2436 * @since 1.7
2437 */
2438 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2439 new UnicodeBlock("BAMUM_SUPPLEMENT",
2440 "BAMUM SUPPLEMENT",
2441 "BAMUMSUPPLEMENT");
2442
2443 /**
2444 * Constant for the "Kana Supplement" Unicode character block.
2445 * @since 1.7
2446 */
2447 public static final UnicodeBlock KANA_SUPPLEMENT =
2448 new UnicodeBlock("KANA_SUPPLEMENT",
2449 "KANA SUPPLEMENT",
2450 "KANASUPPLEMENT");
2451
2452 /**
2453 * Constant for the "Ancient Greek Musical Notation" Unicode character
2454 * block.
2455 * @since 1.7
2456 */
2457 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2458 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2459 "ANCIENT GREEK MUSICAL NOTATION",
2460 "ANCIENTGREEKMUSICALNOTATION");
2461
2462 /**
2463 * Constant for the "Counting Rod Numerals" Unicode character block.
2464 * @since 1.7
2465 */
2466 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2467 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2468 "COUNTING ROD NUMERALS",
2469 "COUNTINGRODNUMERALS");
2470
2471 /**
2472 * Constant for the "Mahjong Tiles" Unicode character block.
2473 * @since 1.7
2474 */
2475 public static final UnicodeBlock MAHJONG_TILES =
2476 new UnicodeBlock("MAHJONG_TILES",
2477 "MAHJONG TILES",
2478 "MAHJONGTILES");
2479
2480 /**
2481 * Constant for the "Domino Tiles" Unicode character block.
2482 * @since 1.7
2483 */
2484 public static final UnicodeBlock DOMINO_TILES =
2485 new UnicodeBlock("DOMINO_TILES",
2486 "DOMINO TILES",
2487 "DOMINOTILES");
2488
2489 /**
2490 * Constant for the "Playing Cards" Unicode character block.
2491 * @since 1.7
2492 */
2493 public static final UnicodeBlock PLAYING_CARDS =
2494 new UnicodeBlock("PLAYING_CARDS",
2495 "PLAYING CARDS",
2496 "PLAYINGCARDS");
2497
2498 /**
2499 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2500 * block.
2501 * @since 1.7
2502 */
2503 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2504 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2505 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2506 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2507
2508 /**
2509 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2510 * block.
2511 * @since 1.7
2512 */
2513 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2514 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2515 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2516 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2517
2518 /**
2519 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2520 * character block.
2521 * @since 1.7
2522 */
2523 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2524 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2525 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2526 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2527
2528 /**
2529 * Constant for the "Emoticons" Unicode character block.
2530 * @since 1.7
2531 */
2532 public static final UnicodeBlock EMOTICONS =
2533 new UnicodeBlock("EMOTICONS");
2534
2535 /**
2536 * Constant for the "Transport And Map Symbols" Unicode character block.
2537 * @since 1.7
2538 */
2539 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2540 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2541 "TRANSPORT AND MAP SYMBOLS",
2542 "TRANSPORTANDMAPSYMBOLS");
2543
2544 /**
2545 * Constant for the "Alchemical Symbols" Unicode character block.
2546 * @since 1.7
2547 */
2548 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2549 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2550 "ALCHEMICAL SYMBOLS",
2551 "ALCHEMICALSYMBOLS");
2552
2553 /**
2554 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2555 * character block.
2556 * @since 1.7
2557 */
2558 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2559 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2560 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2561 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2562
2563 /**
2564 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2565 * character block.
2566 * @since 1.7
2567 */
2568 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2569 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2570 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2571 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2572
2573 /**
2574 * Constant for the "Arabic Extended-A" Unicode character block.
2575 * @since 1.8
2576 */
2577 public static final UnicodeBlock ARABIC_EXTENDED_A =
2578 new UnicodeBlock("ARABIC_EXTENDED_A",
2579 "ARABIC EXTENDED-A",
2580 "ARABICEXTENDED-A");
2581
2582 /**
2583 * Constant for the "Sundanese Supplement" Unicode character block.
2584 * @since 1.8
2585 */
2586 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2587 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2588 "SUNDANESE SUPPLEMENT",
2589 "SUNDANESESUPPLEMENT");
2590
2591 /**
2592 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2593 * @since 1.8
2594 */
2595 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2596 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2597 "MEETEI MAYEK EXTENSIONS",
2598 "MEETEIMAYEKEXTENSIONS");
2599
2600 /**
2601 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2602 * @since 1.8
2603 */
2604 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2605 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2606 "MEROITIC HIEROGLYPHS",
2607 "MEROITICHIEROGLYPHS");
2608
2609 /**
2610 * Constant for the "Meroitic Cursive" Unicode character block.
2611 * @since 1.8
2612 */
2613 public static final UnicodeBlock MEROITIC_CURSIVE =
2614 new UnicodeBlock("MEROITIC_CURSIVE",
2615 "MEROITIC CURSIVE",
2616 "MEROITICCURSIVE");
2617
2618 /**
2619 * Constant for the "Sora Sompeng" Unicode character block.
2620 * @since 1.8
2621 */
2622 public static final UnicodeBlock SORA_SOMPENG =
2623 new UnicodeBlock("SORA_SOMPENG",
2624 "SORA SOMPENG",
2625 "SORASOMPENG");
2626
2627 /**
2628 * Constant for the "Chakma" Unicode character block.
2629 * @since 1.8
2630 */
2631 public static final UnicodeBlock CHAKMA =
2632 new UnicodeBlock("CHAKMA");
2633
2634 /**
2635 * Constant for the "Sharada" Unicode character block.
2636 * @since 1.8
2637 */
2638 public static final UnicodeBlock SHARADA =
2639 new UnicodeBlock("SHARADA");
2640
2641 /**
2642 * Constant for the "Takri" Unicode character block.
2643 * @since 1.8
2644 */
2645 public static final UnicodeBlock TAKRI =
2646 new UnicodeBlock("TAKRI");
2647
2648 /**
2649 * Constant for the "Miao" Unicode character block.
2650 * @since 1.8
2651 */
2652 public static final UnicodeBlock MIAO =
2653 new UnicodeBlock("MIAO");
2654
2655 /**
2656 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2657 * character block.
2658 * @since 1.8
2659 */
2660 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2661 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2662 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2663 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2664
2665 /**
2666 * Constant for the "Combining Diacritical Marks Extended" Unicode
2667 * character block.
2668 * @since 9
2669 */
2670 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2671 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2672 "COMBINING DIACRITICAL MARKS EXTENDED",
2673 "COMBININGDIACRITICALMARKSEXTENDED");
2674
2675 /**
2676 * Constant for the "Myanmar Extended-B" Unicode character block.
2677 * @since 9
2678 */
2679 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2680 new UnicodeBlock("MYANMAR_EXTENDED_B",
2681 "MYANMAR EXTENDED-B",
2682 "MYANMAREXTENDED-B");
2683
2684 /**
2685 * Constant for the "Latin Extended-E" Unicode character block.
2686 * @since 9
2687 */
2688 public static final UnicodeBlock LATIN_EXTENDED_E =
2689 new UnicodeBlock("LATIN_EXTENDED_E",
2690 "LATIN EXTENDED-E",
2691 "LATINEXTENDED-E");
2692
2693 /**
2694 * Constant for the "Coptic Epact Numbers" Unicode character block.
2695 * @since 9
2696 */
2697 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2698 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2699 "COPTIC EPACT NUMBERS",
2700 "COPTICEPACTNUMBERS");
2701
2702 /**
2703 * Constant for the "Old Permic" Unicode character block.
2704 * @since 9
2705 */
2706 public static final UnicodeBlock OLD_PERMIC =
2707 new UnicodeBlock("OLD_PERMIC",
2708 "OLD PERMIC",
2709 "OLDPERMIC");
2710
2711 /**
2712 * Constant for the "Elbasan" Unicode character block.
2713 * @since 9
2714 */
2715 public static final UnicodeBlock ELBASAN =
2716 new UnicodeBlock("ELBASAN");
2717
2718 /**
2719 * Constant for the "Caucasian Albanian" Unicode character block.
2720 * @since 9
2721 */
2722 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2723 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2724 "CAUCASIAN ALBANIAN",
2725 "CAUCASIANALBANIAN");
2726
2727 /**
2728 * Constant for the "Linear A" Unicode character block.
2729 * @since 9
2730 */
2731 public static final UnicodeBlock LINEAR_A =
2732 new UnicodeBlock("LINEAR_A",
2733 "LINEAR A",
2734 "LINEARA");
2735
2736 /**
2737 * Constant for the "Palmyrene" Unicode character block.
2738 * @since 9
2739 */
2740 public static final UnicodeBlock PALMYRENE =
2741 new UnicodeBlock("PALMYRENE");
2742
2743 /**
2744 * Constant for the "Nabataean" Unicode character block.
2745 * @since 9
2746 */
2747 public static final UnicodeBlock NABATAEAN =
2748 new UnicodeBlock("NABATAEAN");
2749
2750 /**
2751 * Constant for the "Old North Arabian" Unicode character block.
2752 * @since 9
2753 */
2754 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2755 new UnicodeBlock("OLD_NORTH_ARABIAN",
2756 "OLD NORTH ARABIAN",
2757 "OLDNORTHARABIAN");
2758
2759 /**
2760 * Constant for the "Manichaean" Unicode character block.
2761 * @since 9
2762 */
2763 public static final UnicodeBlock MANICHAEAN =
2764 new UnicodeBlock("MANICHAEAN");
2765
2766 /**
2767 * Constant for the "Psalter Pahlavi" Unicode character block.
2768 * @since 9
2769 */
2770 public static final UnicodeBlock PSALTER_PAHLAVI =
2771 new UnicodeBlock("PSALTER_PAHLAVI",
2772 "PSALTER PAHLAVI",
2773 "PSALTERPAHLAVI");
2774
2775 /**
2776 * Constant for the "Mahajani" Unicode character block.
2777 * @since 9
2778 */
2779 public static final UnicodeBlock MAHAJANI =
2780 new UnicodeBlock("MAHAJANI");
2781
2782 /**
2783 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2784 * @since 9
2785 */
2786 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2787 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2788 "SINHALA ARCHAIC NUMBERS",
2789 "SINHALAARCHAICNUMBERS");
2790
2791 /**
2792 * Constant for the "Khojki" Unicode character block.
2793 * @since 9
2794 */
2795 public static final UnicodeBlock KHOJKI =
2796 new UnicodeBlock("KHOJKI");
2797
2798 /**
2799 * Constant for the "Khudawadi" Unicode character block.
2800 * @since 9
2801 */
2802 public static final UnicodeBlock KHUDAWADI =
2803 new UnicodeBlock("KHUDAWADI");
2804
2805 /**
2806 * Constant for the "Grantha" Unicode character block.
2807 * @since 9
2808 */
2809 public static final UnicodeBlock GRANTHA =
2810 new UnicodeBlock("GRANTHA");
2811
2812 /**
2813 * Constant for the "Tirhuta" Unicode character block.
2814 * @since 9
2815 */
2816 public static final UnicodeBlock TIRHUTA =
2817 new UnicodeBlock("TIRHUTA");
2818
2819 /**
2820 * Constant for the "Siddham" Unicode character block.
2821 * @since 9
2822 */
2823 public static final UnicodeBlock SIDDHAM =
2824 new UnicodeBlock("SIDDHAM");
2825
2826 /**
2827 * Constant for the "Modi" Unicode character block.
2828 * @since 9
2829 */
2830 public static final UnicodeBlock MODI =
2831 new UnicodeBlock("MODI");
2832
2833 /**
2834 * Constant for the "Warang Citi" Unicode character block.
2835 * @since 9
2836 */
2837 public static final UnicodeBlock WARANG_CITI =
2838 new UnicodeBlock("WARANG_CITI",
2839 "WARANG CITI",
2840 "WARANGCITI");
2841
2842 /**
2843 * Constant for the "Pau Cin Hau" Unicode character block.
2844 * @since 9
2845 */
2846 public static final UnicodeBlock PAU_CIN_HAU =
2847 new UnicodeBlock("PAU_CIN_HAU",
2848 "PAU CIN HAU",
2849 "PAUCINHAU");
2850
2851 /**
2852 * Constant for the "Mro" Unicode character block.
2853 * @since 9
2854 */
2855 public static final UnicodeBlock MRO =
2856 new UnicodeBlock("MRO");
2857
2858 /**
2859 * Constant for the "Bassa Vah" Unicode character block.
2860 * @since 9
2861 */
2862 public static final UnicodeBlock BASSA_VAH =
2863 new UnicodeBlock("BASSA_VAH",
2864 "BASSA VAH",
2865 "BASSAVAH");
2866
2867 /**
2868 * Constant for the "Pahawh Hmong" Unicode character block.
2869 * @since 9
2870 */
2871 public static final UnicodeBlock PAHAWH_HMONG =
2872 new UnicodeBlock("PAHAWH_HMONG",
2873 "PAHAWH HMONG",
2874 "PAHAWHHMONG");
2875
2876 /**
2877 * Constant for the "Duployan" Unicode character block.
2878 * @since 9
2879 */
2880 public static final UnicodeBlock DUPLOYAN =
2881 new UnicodeBlock("DUPLOYAN");
2882
2883 /**
2884 * Constant for the "Shorthand Format Controls" Unicode character block.
2885 * @since 9
2886 */
2887 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2888 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2889 "SHORTHAND FORMAT CONTROLS",
2890 "SHORTHANDFORMATCONTROLS");
2891
2892 /**
2893 * Constant for the "Mende Kikakui" Unicode character block.
2894 * @since 9
2895 */
2896 public static final UnicodeBlock MENDE_KIKAKUI =
2897 new UnicodeBlock("MENDE_KIKAKUI",
2898 "MENDE KIKAKUI",
2899 "MENDEKIKAKUI");
2900
2901 /**
2902 * Constant for the "Ornamental Dingbats" Unicode character block.
2903 * @since 9
2904 */
2905 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2906 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2907 "ORNAMENTAL DINGBATS",
2908 "ORNAMENTALDINGBATS");
2909
2910 /**
2911 * Constant for the "Geometric Shapes Extended" Unicode character block.
2912 * @since 9
2913 */
2914 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2915 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2916 "GEOMETRIC SHAPES EXTENDED",
2917 "GEOMETRICSHAPESEXTENDED");
2918
2919 /**
2920 * Constant for the "Supplemental Arrows-C" Unicode character block.
2921 * @since 9
2922 */
2923 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2924 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2925 "SUPPLEMENTAL ARROWS-C",
2926 "SUPPLEMENTALARROWS-C");
2927
2928 /**
2929 * Constant for the "Cherokee Supplement" Unicode character block.
2930 * @since 9
2931 */
2932 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2933 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2934 "CHEROKEE SUPPLEMENT",
2935 "CHEROKEESUPPLEMENT");
2936
2937 /**
2938 * Constant for the "Hatran" Unicode character block.
2939 * @since 9
2940 */
2941 public static final UnicodeBlock HATRAN =
2942 new UnicodeBlock("HATRAN");
2943
2944 /**
2945 * Constant for the "Old Hungarian" Unicode character block.
2946 * @since 9
2947 */
2948 public static final UnicodeBlock OLD_HUNGARIAN =
2949 new UnicodeBlock("OLD_HUNGARIAN",
2950 "OLD HUNGARIAN",
2951 "OLDHUNGARIAN");
2952
2953 /**
2954 * Constant for the "Multani" Unicode character block.
2955 * @since 9
2956 */
2957 public static final UnicodeBlock MULTANI =
2958 new UnicodeBlock("MULTANI");
2959
2960 /**
2961 * Constant for the "Ahom" Unicode character block.
2962 * @since 9
2963 */
2964 public static final UnicodeBlock AHOM =
2965 new UnicodeBlock("AHOM");
2966
2967 /**
2968 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2969 * @since 9
2970 */
2971 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2972 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2973 "EARLY DYNASTIC CUNEIFORM",
2974 "EARLYDYNASTICCUNEIFORM");
2975
2976 /**
2977 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2978 * @since 9
2979 */
2980 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2981 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2982 "ANATOLIAN HIEROGLYPHS",
2983 "ANATOLIANHIEROGLYPHS");
2984
2985 /**
2986 * Constant for the "Sutton SignWriting" Unicode character block.
2987 * @since 9
2988 */
2989 public static final UnicodeBlock SUTTON_SIGNWRITING =
2990 new UnicodeBlock("SUTTON_SIGNWRITING",
2991 "SUTTON SIGNWRITING",
2992 "SUTTONSIGNWRITING");
2993
2994 /**
2995 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2996 * character block.
2997 * @since 9
2998 */
2999 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
3000 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
3001 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
3002 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3003
3004 /**
3005 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3006 * character block.
3007 * @since 9
3008 */
3009 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3010 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3011 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3012 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3013
3014 /**
3015 * Constant for the "Syriac Supplement" Unicode
3016 * character block.
3017 * @since 11
3018 */
3019 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3020 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3021 "SYRIAC SUPPLEMENT",
3022 "SYRIACSUPPLEMENT");
3023
3024 /**
3025 * Constant for the "Cyrillic Extended-C" Unicode
3026 * character block.
3027 * @since 11
3028 */
3029 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3030 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3031 "CYRILLIC EXTENDED-C",
3032 "CYRILLICEXTENDED-C");
3033
3034 /**
3035 * Constant for the "Osage" Unicode
3036 * character block.
3037 * @since 11
3038 */
3039 public static final UnicodeBlock OSAGE =
3040 new UnicodeBlock("OSAGE");
3041
3042 /**
3043 * Constant for the "Newa" Unicode
3044 * character block.
3045 * @since 11
3046 */
3047 public static final UnicodeBlock NEWA =
3048 new UnicodeBlock("NEWA");
3049
3050 /**
3051 * Constant for the "Mongolian Supplement" Unicode
3052 * character block.
3053 * @since 11
3054 */
3055 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3056 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3057 "MONGOLIAN SUPPLEMENT",
3058 "MONGOLIANSUPPLEMENT");
3059
3060 /**
3061 * Constant for the "Marchen" Unicode
3062 * character block.
3063 * @since 11
3064 */
3065 public static final UnicodeBlock MARCHEN =
3066 new UnicodeBlock("MARCHEN");
3067
3068 /**
3069 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3070 * character block.
3071 * @since 11
3072 */
3073 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3074 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3075 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3076 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3077
3078 /**
3079 * Constant for the "Tangut" Unicode
3080 * character block.
3081 * @since 11
3082 */
3083 public static final UnicodeBlock TANGUT =
3084 new UnicodeBlock("TANGUT");
3085
3086 /**
3087 * Constant for the "Tangut Components" Unicode
3088 * character block.
3089 * @since 11
3090 */
3091 public static final UnicodeBlock TANGUT_COMPONENTS =
3092 new UnicodeBlock("TANGUT_COMPONENTS",
3093 "TANGUT COMPONENTS",
3094 "TANGUTCOMPONENTS");
3095
3096 /**
3097 * Constant for the "Kana Extended-A" Unicode
3098 * character block.
3099 * @since 11
3100 */
3101 public static final UnicodeBlock KANA_EXTENDED_A =
3102 new UnicodeBlock("KANA_EXTENDED_A",
3103 "KANA EXTENDED-A",
3104 "KANAEXTENDED-A");
3105 /**
3106 * Constant for the "Glagolitic Supplement" Unicode
3107 * character block.
3108 * @since 11
3109 */
3110 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3111 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3112 "GLAGOLITIC SUPPLEMENT",
3113 "GLAGOLITICSUPPLEMENT");
3114 /**
3115 * Constant for the "Adlam" Unicode
3116 * character block.
3117 * @since 11
3118 */
3119 public static final UnicodeBlock ADLAM =
3120 new UnicodeBlock("ADLAM");
3121
3122 /**
3123 * Constant for the "Masaram Gondi" Unicode
3124 * character block.
3125 * @since 11
3126 */
3127 public static final UnicodeBlock MASARAM_GONDI =
3128 new UnicodeBlock("MASARAM_GONDI",
3129 "MASARAM GONDI",
3130 "MASARAMGONDI");
3131
3132 /**
3133 * Constant for the "Zanabazar Square" Unicode
3134 * character block.
3135 * @since 11
3136 */
3137 public static final UnicodeBlock ZANABAZAR_SQUARE =
3138 new UnicodeBlock("ZANABAZAR_SQUARE",
3139 "ZANABAZAR SQUARE",
3140 "ZANABAZARSQUARE");
3141
3142 /**
3143 * Constant for the "Nushu" Unicode
3144 * character block.
3145 * @since 11
3146 */
3147 public static final UnicodeBlock NUSHU =
3148 new UnicodeBlock("NUSHU");
3149
3150 /**
3151 * Constant for the "Soyombo" Unicode
3152 * character block.
3153 * @since 11
3154 */
3155 public static final UnicodeBlock SOYOMBO =
3156 new UnicodeBlock("SOYOMBO");
3157
3158 /**
3159 * Constant for the "Bhaiksuki" Unicode
3160 * character block.
3161 * @since 11
3162 */
3163 public static final UnicodeBlock BHAIKSUKI =
3164 new UnicodeBlock("BHAIKSUKI");
3165
3166 /**
3167 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3168 * character block.
3169 * @since 11
3170 */
3171 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3172 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3173 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3174 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3175 /**
3176 * Constant for the "Georgian Extended" Unicode
3177 * character block.
3178 * @since 12
3179 */
3180 public static final UnicodeBlock GEORGIAN_EXTENDED =
3181 new UnicodeBlock("GEORGIAN_EXTENDED",
3182 "GEORGIAN EXTENDED",
3183 "GEORGIANEXTENDED");
3184
3185 /**
3186 * Constant for the "Hanifi Rohingya" Unicode
3187 * character block.
3188 * @since 12
3189 */
3190 public static final UnicodeBlock HANIFI_ROHINGYA =
3191 new UnicodeBlock("HANIFI_ROHINGYA",
3192 "HANIFI ROHINGYA",
3193 "HANIFIROHINGYA");
3194
3195 /**
3196 * Constant for the "Old Sogdian" Unicode
3197 * character block.
3198 * @since 12
3199 */
3200 public static final UnicodeBlock OLD_SOGDIAN =
3201 new UnicodeBlock("OLD_SOGDIAN",
3202 "OLD SOGDIAN",
3203 "OLDSOGDIAN");
3204
3205 /**
3206 * Constant for the "Sogdian" Unicode
3207 * character block.
3208 * @since 12
3209 */
3210 public static final UnicodeBlock SOGDIAN =
3211 new UnicodeBlock("SOGDIAN");
3212
3213 /**
3214 * Constant for the "Dogra" Unicode
3215 * character block.
3216 * @since 12
3217 */
3218 public static final UnicodeBlock DOGRA =
3219 new UnicodeBlock("DOGRA");
3220
3221 /**
3222 * Constant for the "Gunjala Gondi" Unicode
3223 * character block.
3224 * @since 12
3225 */
3226 public static final UnicodeBlock GUNJALA_GONDI =
3227 new UnicodeBlock("GUNJALA_GONDI",
3228 "GUNJALA GONDI",
3229 "GUNJALAGONDI");
3230
3231 /**
3232 * Constant for the "Makasar" Unicode
3233 * character block.
3234 * @since 12
3235 */
3236 public static final UnicodeBlock MAKASAR =
3237 new UnicodeBlock("MAKASAR");
3238
3239 /**
3240 * Constant for the "Medefaidrin" Unicode
3241 * character block.
3242 * @since 12
3243 */
3244 public static final UnicodeBlock MEDEFAIDRIN =
3245 new UnicodeBlock("MEDEFAIDRIN");
3246
3247 /**
3248 * Constant for the "Mayan Numerals" Unicode
3249 * character block.
3250 * @since 12
3251 */
3252 public static final UnicodeBlock MAYAN_NUMERALS =
3253 new UnicodeBlock("MAYAN_NUMERALS",
3254 "MAYAN NUMERALS",
3255 "MAYANNUMERALS");
3256
3257 /**
3258 * Constant for the "Indic Siyaq Numbers" Unicode
3259 * character block.
3260 * @since 12
3261 */
3262 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3263 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3264 "INDIC SIYAQ NUMBERS",
3265 "INDICSIYAQNUMBERS");
3266
3267 /**
3268 * Constant for the "Chess Symbols" Unicode
3269 * character block.
3270 * @since 12
3271 */
3272 public static final UnicodeBlock CHESS_SYMBOLS =
3273 new UnicodeBlock("CHESS_SYMBOLS",
3274 "CHESS SYMBOLS",
3275 "CHESSSYMBOLS");
3276
3277 /**
3278 * Constant for the "Elymaic" Unicode
3279 * character block.
3280 * @since 13
3281 */
3282 public static final UnicodeBlock ELYMAIC =
3283 new UnicodeBlock("ELYMAIC");
3284
3285 /**
3286 * Constant for the "Nandinagari" Unicode
3287 * character block.
3288 * @since 13
3289 */
3290 public static final UnicodeBlock NANDINAGARI =
3291 new UnicodeBlock("NANDINAGARI");
3292
3293 /**
3294 * Constant for the "Tamil Supplement" Unicode
3295 * character block.
3296 * @since 13
3297 */
3298 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3299 new UnicodeBlock("TAMIL_SUPPLEMENT",
3300 "TAMIL SUPPLEMENT",
3301 "TAMILSUPPLEMENT");
3302
3303 /**
3304 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3305 * character block.
3306 * @since 13
3307 */
3308 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3309 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3310 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3311 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3312
3313 /**
3314 * Constant for the "Small Kana Extension" Unicode
3315 * character block.
3316 * @since 13
3317 */
3318 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3319 new UnicodeBlock("SMALL_KANA_EXTENSION",
3320 "SMALL KANA EXTENSION",
3321 "SMALLKANAEXTENSION");
3322
3323 /**
3324 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3325 * character block.
3326 * @since 13
3327 */
3328 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3329 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3330 "NYIAKENG PUACHUE HMONG",
3331 "NYIAKENGPUACHUEHMONG");
3332
3333 /**
3334 * Constant for the "Wancho" Unicode
3335 * character block.
3336 * @since 13
3337 */
3338 public static final UnicodeBlock WANCHO =
3339 new UnicodeBlock("WANCHO");
3340
3341 /**
3342 * Constant for the "Ottoman Siyaq Numbers" Unicode
3343 * character block.
3344 * @since 13
3345 */
3346 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3347 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3348 "OTTOMAN SIYAQ NUMBERS",
3349 "OTTOMANSIYAQNUMBERS");
3350
3351 /**
3352 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3353 * character block.
3354 * @since 13
3355 */
3356 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3357 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3358 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3359 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3360
3361 /**
3362 * Constant for the "Yezidi" Unicode
3363 * character block.
3364 * @since 15
3365 */
3366 public static final UnicodeBlock YEZIDI =
3367 new UnicodeBlock("YEZIDI");
3368
3369 /**
3370 * Constant for the "Chorasmian" Unicode
3371 * character block.
3372 * @since 15
3373 */
3374 public static final UnicodeBlock CHORASMIAN =
3375 new UnicodeBlock("CHORASMIAN");
3376
3377 /**
3378 * Constant for the "Dives Akuru" Unicode
3379 * character block.
3380 * @since 15
3381 */
3382 public static final UnicodeBlock DIVES_AKURU =
3383 new UnicodeBlock("DIVES_AKURU",
3384 "DIVES AKURU",
3385 "DIVESAKURU");
3386
3387 /**
3388 * Constant for the "Lisu Supplement" Unicode
3389 * character block.
3390 * @since 15
3391 */
3392 public static final UnicodeBlock LISU_SUPPLEMENT =
3393 new UnicodeBlock("LISU_SUPPLEMENT",
3394 "LISU SUPPLEMENT",
3395 "LISUSUPPLEMENT");
3396
3397 /**
3398 * Constant for the "Khitan Small Script" Unicode
3399 * character block.
3400 * @since 15
3401 */
3402 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3403 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3404 "KHITAN SMALL SCRIPT",
3405 "KHITANSMALLSCRIPT");
3406
3407 /**
3408 * Constant for the "Tangut Supplement" Unicode
3409 * character block.
3410 * @since 15
3411 */
3412 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3413 new UnicodeBlock("TANGUT_SUPPLEMENT",
3414 "TANGUT SUPPLEMENT",
3415 "TANGUTSUPPLEMENT");
3416
3417 /**
3418 * Constant for the "Symbols for Legacy Computing" Unicode
3419 * character block.
3420 * @since 15
3421 */
3422 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3423 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3424 "SYMBOLS FOR LEGACY COMPUTING",
3425 "SYMBOLSFORLEGACYCOMPUTING");
3426
3427 /**
3428 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3429 * character block.
3430 * @since 15
3431 */
3432 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3433 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3434 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3435 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3436
3437 /**
3438 * Constant for the "Arabic Extended-B" Unicode
3439 * character block.
3440 * @since 19
3441 */
3442 public static final UnicodeBlock ARABIC_EXTENDED_B =
3443 new UnicodeBlock("ARABIC_EXTENDED_B",
3444 "ARABIC EXTENDED-B",
3445 "ARABICEXTENDED-B");
3446
3447 /**
3448 * Constant for the "Vithkuqi" Unicode
3449 * character block.
3450 * @since 19
3451 */
3452 public static final UnicodeBlock VITHKUQI =
3453 new UnicodeBlock("VITHKUQI");
3454
3455 /**
3456 * Constant for the "Latin Extended-F" Unicode
3457 * character block.
3458 * @since 19
3459 */
3460 public static final UnicodeBlock LATIN_EXTENDED_F =
3461 new UnicodeBlock("LATIN_EXTENDED_F",
3462 "LATIN EXTENDED-F",
3463 "LATINEXTENDED-F");
3464
3465 /**
3466 * Constant for the "Old Uyghur" Unicode
3467 * character block.
3468 * @since 19
3469 */
3470 public static final UnicodeBlock OLD_UYGHUR =
3471 new UnicodeBlock("OLD_UYGHUR",
3472 "OLD UYGHUR",
3473 "OLDUYGHUR");
3474
3475 /**
3476 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3477 * character block.
3478 * @since 19
3479 */
3480 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3481 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3482 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3483 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3484
3485 /**
3486 * Constant for the "Cypro-Minoan" Unicode
3487 * character block.
3488 * @since 19
3489 */
3490 public static final UnicodeBlock CYPRO_MINOAN =
3491 new UnicodeBlock("CYPRO_MINOAN",
3492 "CYPRO-MINOAN",
3493 "CYPRO-MINOAN");
3494
3495 /**
3496 * Constant for the "Tangsa" Unicode
3497 * character block.
3498 * @since 19
3499 */
3500 public static final UnicodeBlock TANGSA =
3501 new UnicodeBlock("TANGSA");
3502
3503 /**
3504 * Constant for the "Kana Extended-B" Unicode
3505 * character block.
3506 * @since 19
3507 */
3508 public static final UnicodeBlock KANA_EXTENDED_B =
3509 new UnicodeBlock("KANA_EXTENDED_B",
3510 "KANA EXTENDED-B",
3511 "KANAEXTENDED-B");
3512
3513 /**
3514 * Constant for the "Znamenny Musical Notation" Unicode
3515 * character block.
3516 * @since 19
3517 */
3518 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3519 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3520 "ZNAMENNY MUSICAL NOTATION",
3521 "ZNAMENNYMUSICALNOTATION");
3522
3523 /**
3524 * Constant for the "Latin Extended-G" Unicode
3525 * character block.
3526 * @since 19
3527 */
3528 public static final UnicodeBlock LATIN_EXTENDED_G =
3529 new UnicodeBlock("LATIN_EXTENDED_G",
3530 "LATIN EXTENDED-G",
3531 "LATINEXTENDED-G");
3532
3533 /**
3534 * Constant for the "Toto" Unicode
3535 * character block.
3536 * @since 19
3537 */
3538 public static final UnicodeBlock TOTO =
3539 new UnicodeBlock("TOTO");
3540
3541 /**
3542 * Constant for the "Ethiopic Extended-B" Unicode
3543 * character block.
3544 * @since 19
3545 */
3546 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3547 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3548 "ETHIOPIC EXTENDED-B",
3549 "ETHIOPICEXTENDED-B");
3550
3551 /**
3552 * Constant for the "Arabic Extended-C" Unicode
3553 * character block.
3554 * @since 20
3555 */
3556 public static final UnicodeBlock ARABIC_EXTENDED_C =
3557 new UnicodeBlock("ARABIC_EXTENDED_C",
3558 "ARABIC EXTENDED-C",
3559 "ARABICEXTENDED-C");
3560
3561 /**
3562 * Constant for the "Devanagari Extended-A" Unicode
3563 * character block.
3564 * @since 20
3565 */
3566 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3567 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3568 "DEVANAGARI EXTENDED-A",
3569 "DEVANAGARIEXTENDED-A");
3570
3571 /**
3572 * Constant for the "Kawi" Unicode
3573 * character block.
3574 * @since 20
3575 */
3576 public static final UnicodeBlock KAWI =
3577 new UnicodeBlock("KAWI");
3578
3579 /**
3580 * Constant for the "Kaktovik Numerals" Unicode
3581 * character block.
3582 * @since 20
3583 */
3584 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3585 new UnicodeBlock("KAKTOVIK_NUMERALS",
3586 "KAKTOVIK NUMERALS",
3587 "KAKTOVIKNUMERALS");
3588
3589 /**
3590 * Constant for the "Cyrillic Extended-D" Unicode
3591 * character block.
3592 * @since 20
3593 */
3594 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3595 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3596 "CYRILLIC EXTENDED-D",
3597 "CYRILLICEXTENDED-D");
3598
3599 /**
3600 * Constant for the "Nag Mundari" Unicode
3601 * character block.
3602 * @since 20
3603 */
3604 public static final UnicodeBlock NAG_MUNDARI =
3605 new UnicodeBlock("NAG_MUNDARI",
3606 "NAG MUNDARI",
3607 "NAGMUNDARI");
3608
3609 /**
3610 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3611 * character block.
3612 * @since 20
3613 */
3614 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3615 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3616 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3617 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3618
3619 /**
3620 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3621 * character block.
3622 * @since 22
3623 */
3624 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3625 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3626 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3627 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3628
3629 /**
3630 * Constant for the "Todhri" Unicode
3631 * character block.
3632 * @since 24
3633 */
3634 public static final UnicodeBlock TODHRI =
3635 new UnicodeBlock("TODHRI");
3636
3637 /**
3638 * Constant for the "Garay" Unicode
3639 * character block.
3640 * @since 24
3641 */
3642 public static final UnicodeBlock GARAY =
3643 new UnicodeBlock("GARAY");
3644
3645 /**
3646 * Constant for the "Tulu-Tigalari" Unicode
3647 * character block.
3648 * @since 24
3649 */
3650 public static final UnicodeBlock TULU_TIGALARI =
3651 new UnicodeBlock("TULU_TIGALARI",
3652 "TULU-TIGALARI");
3653
3654 /**
3655 * Constant for the "Myanmar Extended-C" Unicode
3656 * character block.
3657 * @since 24
3658 */
3659 public static final UnicodeBlock MYANMAR_EXTENDED_C =
3660 new UnicodeBlock("MYANMAR_EXTENDED_C",
3661 "MYANMAR EXTENDED-C",
3662 "MYANMAREXTENDED-C");
3663
3664 /**
3665 * Constant for the "Sunuwar" Unicode
3666 * character block.
3667 * @since 24
3668 */
3669 public static final UnicodeBlock SUNUWAR =
3670 new UnicodeBlock("SUNUWAR");
3671
3672 /**
3673 * Constant for the "Egyptian Hieroglyphs Extended-A" Unicode
3674 * character block.
3675 * @since 24
3676 */
3677 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS_EXTENDED_A =
3678 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS_EXTENDED_A",
3679 "EGYPTIAN HIEROGLYPHS EXTENDED-A",
3680 "EGYPTIANHIEROGLYPHSEXTENDED-A");
3681
3682 /**
3683 * Constant for the "Gurung Khema" Unicode
3684 * character block.
3685 * @since 24
3686 */
3687 public static final UnicodeBlock GURUNG_KHEMA =
3688 new UnicodeBlock("GURUNG_KHEMA",
3689 "GURUNG KHEMA",
3690 "GURUNGKHEMA");
3691
3692 /**
3693 * Constant for the "Kirat Rai" Unicode
3694 * character block.
3695 * @since 24
3696 */
3697 public static final UnicodeBlock KIRAT_RAI =
3698 new UnicodeBlock("KIRAT_RAI",
3699 "KIRAT RAI",
3700 "KIRATRAI");
3701
3702 /**
3703 * Constant for the "Symbols for Legacy Computing Supplement" Unicode
3704 * character block.
3705 * @since 24
3706 */
3707 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT =
3708 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT",
3709 "SYMBOLS FOR LEGACY COMPUTING SUPPLEMENT",
3710 "SYMBOLSFORLEGACYCOMPUTINGSUPPLEMENT");
3711
3712 /**
3713 * Constant for the "Ol Onal" Unicode
3714 * character block.
3715 * @since 24
3716 */
3717 public static final UnicodeBlock OL_ONAL =
3718 new UnicodeBlock("OL_ONAL",
3719 "OL ONAL",
3720 "OLONAL");
3721
3722 /**
3723 * Constant for the "Sidetic" Unicode
3724 * character block.
3725 * @since 26
3726 */
3727 public static final UnicodeBlock SIDETIC =
3728 new UnicodeBlock("SIDETIC");
3729
3730 /**
3731 * Constant for the "Sharada Supplement" Unicode
3732 * character block.
3733 * @since 26
3734 */
3735 public static final UnicodeBlock SHARADA_SUPPLEMENT =
3736 new UnicodeBlock("SHARADA_SUPPLEMENT",
3737 "SHARADA SUPPLEMENT",
3738 "SHARADASUPPLEMENT");
3739
3740 /**
3741 * Constant for the "Tolong Siki" Unicode
3742 * character block.
3743 * @since 26
3744 */
3745 public static final UnicodeBlock TOLONG_SIKI =
3746 new UnicodeBlock("TOLONG_SIKI",
3747 "TOLONG SIKI",
3748 "TOLONGSIKI");
3749
3750 /**
3751 * Constant for the "Beria Erfe" Unicode
3752 * character block.
3753 * @since 26
3754 */
3755 public static final UnicodeBlock BERIA_ERFE =
3756 new UnicodeBlock("BERIA_ERFE",
3757 "BERIA ERFE",
3758 "BERIAERFE");
3759
3760 /**
3761 * Constant for the "Tangut Components Supplement" Unicode
3762 * character block.
3763 * @since 26
3764 */
3765 public static final UnicodeBlock TANGUT_COMPONENTS_SUPPLEMENT =
3766 new UnicodeBlock("TANGUT_COMPONENTS_SUPPLEMENT",
3767 "TANGUT COMPONENTS SUPPLEMENT",
3768 "TANGUTCOMPONENTSSUPPLEMENT");
3769
3770 /**
3771 * Constant for the "Miscellaneous Symbols Supplement" Unicode
3772 * character block.
3773 * @since 26
3774 */
3775 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_SUPPLEMENT =
3776 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_SUPPLEMENT",
3777 "MISCELLANEOUS SYMBOLS SUPPLEMENT",
3778 "MISCELLANEOUSSYMBOLSSUPPLEMENT");
3779
3780 /**
3781 * Constant for the "Tai Yo" Unicode
3782 * character block.
3783 * @since 26
3784 */
3785 public static final UnicodeBlock TAI_YO =
3786 new UnicodeBlock("TAI_YO",
3787 "TAI YO",
3788 "TAIYO");
3789
3790 /**
3791 * Constant for the "CJK Unified Ideographs Extension J" Unicode
3792 * character block.
3793 * @since 26
3794 */
3795 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J =
3796 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J",
3797 "CJK UNIFIED IDEOGRAPHS EXTENSION J",
3798 "CJKUNIFIEDIDEOGRAPHSEXTENSIONJ");
3799
3800
3801 private static final int[] blockStarts = {
3802 0x0000, // 0000..007F; Basic Latin
3803 0x0080, // 0080..00FF; Latin-1 Supplement
3804 0x0100, // 0100..017F; Latin Extended-A
3805 0x0180, // 0180..024F; Latin Extended-B
3806 0x0250, // 0250..02AF; IPA Extensions
3807 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3808 0x0300, // 0300..036F; Combining Diacritical Marks
3809 0x0370, // 0370..03FF; Greek and Coptic
3810 0x0400, // 0400..04FF; Cyrillic
3811 0x0500, // 0500..052F; Cyrillic Supplement
3812 0x0530, // 0530..058F; Armenian
3813 0x0590, // 0590..05FF; Hebrew
3814 0x0600, // 0600..06FF; Arabic
3815 0x0700, // 0700..074F; Syriac
3816 0x0750, // 0750..077F; Arabic Supplement
3817 0x0780, // 0780..07BF; Thaana
3818 0x07C0, // 07C0..07FF; NKo
3819 0x0800, // 0800..083F; Samaritan
3820 0x0840, // 0840..085F; Mandaic
3821 0x0860, // 0860..086F; Syriac Supplement
3822 0x0870, // 0870..089F; Arabic Extended-B
3823 0x08A0, // 08A0..08FF; Arabic Extended-A
3824 0x0900, // 0900..097F; Devanagari
3825 0x0980, // 0980..09FF; Bengali
3826 0x0A00, // 0A00..0A7F; Gurmukhi
3827 0x0A80, // 0A80..0AFF; Gujarati
3828 0x0B00, // 0B00..0B7F; Oriya
3829 0x0B80, // 0B80..0BFF; Tamil
3830 0x0C00, // 0C00..0C7F; Telugu
3831 0x0C80, // 0C80..0CFF; Kannada
3832 0x0D00, // 0D00..0D7F; Malayalam
3833 0x0D80, // 0D80..0DFF; Sinhala
3834 0x0E00, // 0E00..0E7F; Thai
3835 0x0E80, // 0E80..0EFF; Lao
3836 0x0F00, // 0F00..0FFF; Tibetan
3837 0x1000, // 1000..109F; Myanmar
3838 0x10A0, // 10A0..10FF; Georgian
3839 0x1100, // 1100..11FF; Hangul Jamo
3840 0x1200, // 1200..137F; Ethiopic
3841 0x1380, // 1380..139F; Ethiopic Supplement
3842 0x13A0, // 13A0..13FF; Cherokee
3843 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3844 0x1680, // 1680..169F; Ogham
3845 0x16A0, // 16A0..16FF; Runic
3846 0x1700, // 1700..171F; Tagalog
3847 0x1720, // 1720..173F; Hanunoo
3848 0x1740, // 1740..175F; Buhid
3849 0x1760, // 1760..177F; Tagbanwa
3850 0x1780, // 1780..17FF; Khmer
3851 0x1800, // 1800..18AF; Mongolian
3852 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3853 0x1900, // 1900..194F; Limbu
3854 0x1950, // 1950..197F; Tai Le
3855 0x1980, // 1980..19DF; New Tai Lue
3856 0x19E0, // 19E0..19FF; Khmer Symbols
3857 0x1A00, // 1A00..1A1F; Buginese
3858 0x1A20, // 1A20..1AAF; Tai Tham
3859 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3860 0x1B00, // 1B00..1B7F; Balinese
3861 0x1B80, // 1B80..1BBF; Sundanese
3862 0x1BC0, // 1BC0..1BFF; Batak
3863 0x1C00, // 1C00..1C4F; Lepcha
3864 0x1C50, // 1C50..1C7F; Ol Chiki
3865 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3866 0x1C90, // 1C90..1CBF; Georgian Extended
3867 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3868 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3869 0x1D00, // 1D00..1D7F; Phonetic Extensions
3870 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3871 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3872 0x1E00, // 1E00..1EFF; Latin Extended Additional
3873 0x1F00, // 1F00..1FFF; Greek Extended
3874 0x2000, // 2000..206F; General Punctuation
3875 0x2070, // 2070..209F; Superscripts and Subscripts
3876 0x20A0, // 20A0..20CF; Currency Symbols
3877 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3878 0x2100, // 2100..214F; Letterlike Symbols
3879 0x2150, // 2150..218F; Number Forms
3880 0x2190, // 2190..21FF; Arrows
3881 0x2200, // 2200..22FF; Mathematical Operators
3882 0x2300, // 2300..23FF; Miscellaneous Technical
3883 0x2400, // 2400..243F; Control Pictures
3884 0x2440, // 2440..245F; Optical Character Recognition
3885 0x2460, // 2460..24FF; Enclosed Alphanumerics
3886 0x2500, // 2500..257F; Box Drawing
3887 0x2580, // 2580..259F; Block Elements
3888 0x25A0, // 25A0..25FF; Geometric Shapes
3889 0x2600, // 2600..26FF; Miscellaneous Symbols
3890 0x2700, // 2700..27BF; Dingbats
3891 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3892 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3893 0x2800, // 2800..28FF; Braille Patterns
3894 0x2900, // 2900..297F; Supplemental Arrows-B
3895 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3896 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3897 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3898 0x2C00, // 2C00..2C5F; Glagolitic
3899 0x2C60, // 2C60..2C7F; Latin Extended-C
3900 0x2C80, // 2C80..2CFF; Coptic
3901 0x2D00, // 2D00..2D2F; Georgian Supplement
3902 0x2D30, // 2D30..2D7F; Tifinagh
3903 0x2D80, // 2D80..2DDF; Ethiopic Extended
3904 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3905 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3906 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3907 0x2F00, // 2F00..2FDF; Kangxi Radicals
3908 0x2FE0, // unassigned
3909 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3910 0x3000, // 3000..303F; CJK Symbols and Punctuation
3911 0x3040, // 3040..309F; Hiragana
3912 0x30A0, // 30A0..30FF; Katakana
3913 0x3100, // 3100..312F; Bopomofo
3914 0x3130, // 3130..318F; Hangul Compatibility Jamo
3915 0x3190, // 3190..319F; Kanbun
3916 0x31A0, // 31A0..31BF; Bopomofo Extended
3917 0x31C0, // 31C0..31EF; CJK Strokes
3918 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3919 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3920 0x3300, // 3300..33FF; CJK Compatibility
3921 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3922 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3923 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3924 0xA000, // A000..A48F; Yi Syllables
3925 0xA490, // A490..A4CF; Yi Radicals
3926 0xA4D0, // A4D0..A4FF; Lisu
3927 0xA500, // A500..A63F; Vai
3928 0xA640, // A640..A69F; Cyrillic Extended-B
3929 0xA6A0, // A6A0..A6FF; Bamum
3930 0xA700, // A700..A71F; Modifier Tone Letters
3931 0xA720, // A720..A7FF; Latin Extended-D
3932 0xA800, // A800..A82F; Syloti Nagri
3933 0xA830, // A830..A83F; Common Indic Number Forms
3934 0xA840, // A840..A87F; Phags-pa
3935 0xA880, // A880..A8DF; Saurashtra
3936 0xA8E0, // A8E0..A8FF; Devanagari Extended
3937 0xA900, // A900..A92F; Kayah Li
3938 0xA930, // A930..A95F; Rejang
3939 0xA960, // A960..A97F; Hangul Jamo Extended-A
3940 0xA980, // A980..A9DF; Javanese
3941 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3942 0xAA00, // AA00..AA5F; Cham
3943 0xAA60, // AA60..AA7F; Myanmar Extended-A
3944 0xAA80, // AA80..AADF; Tai Viet
3945 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3946 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3947 0xAB30, // AB30..AB6F; Latin Extended-E
3948 0xAB70, // AB70..ABBF; Cherokee Supplement
3949 0xABC0, // ABC0..ABFF; Meetei Mayek
3950 0xAC00, // AC00..D7AF; Hangul Syllables
3951 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3952 0xD800, // D800..DB7F; High Surrogates
3953 0xDB80, // DB80..DBFF; High Private Use Surrogates
3954 0xDC00, // DC00..DFFF; Low Surrogates
3955 0xE000, // E000..F8FF; Private Use Area
3956 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3957 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3958 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3959 0xFE00, // FE00..FE0F; Variation Selectors
3960 0xFE10, // FE10..FE1F; Vertical Forms
3961 0xFE20, // FE20..FE2F; Combining Half Marks
3962 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3963 0xFE50, // FE50..FE6F; Small Form Variants
3964 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3965 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3966 0xFFF0, // FFF0..FFFF; Specials
3967 0x10000, // 10000..1007F; Linear B Syllabary
3968 0x10080, // 10080..100FF; Linear B Ideograms
3969 0x10100, // 10100..1013F; Aegean Numbers
3970 0x10140, // 10140..1018F; Ancient Greek Numbers
3971 0x10190, // 10190..101CF; Ancient Symbols
3972 0x101D0, // 101D0..101FF; Phaistos Disc
3973 0x10200, // unassigned
3974 0x10280, // 10280..1029F; Lycian
3975 0x102A0, // 102A0..102DF; Carian
3976 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3977 0x10300, // 10300..1032F; Old Italic
3978 0x10330, // 10330..1034F; Gothic
3979 0x10350, // 10350..1037F; Old Permic
3980 0x10380, // 10380..1039F; Ugaritic
3981 0x103A0, // 103A0..103DF; Old Persian
3982 0x103E0, // unassigned
3983 0x10400, // 10400..1044F; Deseret
3984 0x10450, // 10450..1047F; Shavian
3985 0x10480, // 10480..104AF; Osmanya
3986 0x104B0, // 104B0..104FF; Osage
3987 0x10500, // 10500..1052F; Elbasan
3988 0x10530, // 10530..1056F; Caucasian Albanian
3989 0x10570, // 10570..105BF; Vithkuqi
3990 0x105C0, // 105C0..105FF; Todhri
3991 0x10600, // 10600..1077F; Linear A
3992 0x10780, // 10780..107BF; Latin Extended-F
3993 0x107C0, // unassigned
3994 0x10800, // 10800..1083F; Cypriot Syllabary
3995 0x10840, // 10840..1085F; Imperial Aramaic
3996 0x10860, // 10860..1087F; Palmyrene
3997 0x10880, // 10880..108AF; Nabataean
3998 0x108B0, // unassigned
3999 0x108E0, // 108E0..108FF; Hatran
4000 0x10900, // 10900..1091F; Phoenician
4001 0x10920, // 10920..1093F; Lydian
4002 0x10940, // 10940..1095F; Sidetic
4003 0x10960, // unassigned
4004 0x10980, // 10980..1099F; Meroitic Hieroglyphs
4005 0x109A0, // 109A0..109FF; Meroitic Cursive
4006 0x10A00, // 10A00..10A5F; Kharoshthi
4007 0x10A60, // 10A60..10A7F; Old South Arabian
4008 0x10A80, // 10A80..10A9F; Old North Arabian
4009 0x10AA0, // unassigned
4010 0x10AC0, // 10AC0..10AFF; Manichaean
4011 0x10B00, // 10B00..10B3F; Avestan
4012 0x10B40, // 10B40..10B5F; Inscriptional Parthian
4013 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
4014 0x10B80, // 10B80..10BAF; Psalter Pahlavi
4015 0x10BB0, // unassigned
4016 0x10C00, // 10C00..10C4F; Old Turkic
4017 0x10C50, // unassigned
4018 0x10C80, // 10C80..10CFF; Old Hungarian
4019 0x10D00, // 10D00..10D3F; Hanifi Rohingya
4020 0x10D40, // 10D40..10D8F; Garay
4021 0x10D90, // unassigned
4022 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
4023 0x10E80, // 10E80..10EBF; Yezidi
4024 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
4025 0x10F00, // 10F00..10F2F; Old Sogdian
4026 0x10F30, // 10F30..10F6F; Sogdian
4027 0x10F70, // 10F70..10FAF; Old Uyghur
4028 0x10FB0, // 10FB0..10FDF; Chorasmian
4029 0x10FE0, // 10FE0..10FFF; Elymaic
4030 0x11000, // 11000..1107F; Brahmi
4031 0x11080, // 11080..110CF; Kaithi
4032 0x110D0, // 110D0..110FF; Sora Sompeng
4033 0x11100, // 11100..1114F; Chakma
4034 0x11150, // 11150..1117F; Mahajani
4035 0x11180, // 11180..111DF; Sharada
4036 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
4037 0x11200, // 11200..1124F; Khojki
4038 0x11250, // unassigned
4039 0x11280, // 11280..112AF; Multani
4040 0x112B0, // 112B0..112FF; Khudawadi
4041 0x11300, // 11300..1137F; Grantha
4042 0x11380, // 11380..113FF; Tulu-Tigalari
4043 0x11400, // 11400..1147F; Newa
4044 0x11480, // 11480..114DF; Tirhuta
4045 0x114E0, // unassigned
4046 0x11580, // 11580..115FF; Siddham
4047 0x11600, // 11600..1165F; Modi
4048 0x11660, // 11660..1167F; Mongolian Supplement
4049 0x11680, // 11680..116CF; Takri
4050 0x116D0, // 116D0..116FF; Myanmar Extended-C
4051 0x11700, // 11700..1174F; Ahom
4052 0x11750, // unassigned
4053 0x11800, // 11800..1184F; Dogra
4054 0x11850, // unassigned
4055 0x118A0, // 118A0..118FF; Warang Citi
4056 0x11900, // 11900..1195F; Dives Akuru
4057 0x11960, // unassigned
4058 0x119A0, // 119A0..119FF; Nandinagari
4059 0x11A00, // 11A00..11A4F; Zanabazar Square
4060 0x11A50, // 11A50..11AAF; Soyombo
4061 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
4062 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
4063 0x11B00, // 11B00..11B5F; Devanagari Extended-A
4064 0x11B60, // 11B60..11B7F; Sharada Supplement
4065 0x11B80, // unassigned
4066 0x11BC0, // 11BC0..11BFF; Sunuwar
4067 0x11C00, // 11C00..11C6F; Bhaiksuki
4068 0x11C70, // 11C70..11CBF; Marchen
4069 0x11CC0, // unassigned
4070 0x11D00, // 11D00..11D5F; Masaram Gondi
4071 0x11D60, // 11D60..11DAF; Gunjala Gondi
4072 0x11DB0, // 11DB0..11DEF; Tolong Siki
4073 0x11DF0, // unassigned
4074 0x11EE0, // 11EE0..11EFF; Makasar
4075 0x11F00, // 11F00..11F5F; Kawi
4076 0x11F60, // unassigned
4077 0x11FB0, // 11FB0..11FBF; Lisu Supplement
4078 0x11FC0, // 11FC0..11FFF; Tamil Supplement
4079 0x12000, // 12000..123FF; Cuneiform
4080 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
4081 0x12480, // 12480..1254F; Early Dynastic Cuneiform
4082 0x12550, // unassigned
4083 0x12F90, // 12F90..12FFF; Cypro-Minoan
4084 0x13000, // 13000..1342F; Egyptian Hieroglyphs
4085 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
4086 0x13460, // 13460..143FF; Egyptian Hieroglyphs Extended-A
4087 0x14400, // 14400..1467F; Anatolian Hieroglyphs
4088 0x14680, // unassigned
4089 0x16100, // 16100..1613F; Gurung Khema
4090 0x16140, // unassigned
4091 0x16800, // 16800..16A3F; Bamum Supplement
4092 0x16A40, // 16A40..16A6F; Mro
4093 0x16A70, // 16A70..16ACF; Tangsa
4094 0x16AD0, // 16AD0..16AFF; Bassa Vah
4095 0x16B00, // 16B00..16B8F; Pahawh Hmong
4096 0x16B90, // unassigned
4097 0x16D40, // 16D40..16D7F; Kirat Rai
4098 0x16D80, // unassigned
4099 0x16E40, // 16E40..16E9F; Medefaidrin
4100 0x16EA0, // 16EA0..16EDF; Beria Erfe
4101 0x16EE0, // unassigned
4102 0x16F00, // 16F00..16F9F; Miao
4103 0x16FA0, // unassigned
4104 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
4105 0x17000, // 17000..187FF; Tangut
4106 0x18800, // 18800..18AFF; Tangut Components
4107 0x18B00, // 18B00..18CFF; Khitan Small Script
4108 0x18D00, // 18D00..18D7F; Tangut Supplement
4109 0x18D80, // 18D80..18DFF; Tangut Components Supplement
4110 0x18E00, // unassigned
4111 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
4112 0x1B000, // 1B000..1B0FF; Kana Supplement
4113 0x1B100, // 1B100..1B12F; Kana Extended-A
4114 0x1B130, // 1B130..1B16F; Small Kana Extension
4115 0x1B170, // 1B170..1B2FF; Nushu
4116 0x1B300, // unassigned
4117 0x1BC00, // 1BC00..1BC9F; Duployan
4118 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
4119 0x1BCB0, // unassigned
4120 0x1CC00, // 1CC00..1CEBF; Symbols for Legacy Computing Supplement
4121 0x1CEC0, // 1CEC0..1CEFF; Miscellaneous Symbols Supplement
4122 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
4123 0x1CFD0, // unassigned
4124 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
4125 0x1D100, // 1D100..1D1FF; Musical Symbols
4126 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
4127 0x1D250, // unassigned
4128 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
4129 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
4130 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
4131 0x1D360, // 1D360..1D37F; Counting Rod Numerals
4132 0x1D380, // unassigned
4133 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
4134 0x1D800, // 1D800..1DAAF; Sutton SignWriting
4135 0x1DAB0, // unassigned
4136 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
4137 0x1E000, // 1E000..1E02F; Glagolitic Supplement
4138 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
4139 0x1E090, // unassigned
4140 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
4141 0x1E150, // unassigned
4142 0x1E290, // 1E290..1E2BF; Toto
4143 0x1E2C0, // 1E2C0..1E2FF; Wancho
4144 0x1E300, // unassigned
4145 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
4146 0x1E500, // unassigned
4147 0x1E5D0, // 1E5D0..1E5FF; Ol Onal
4148 0x1E600, // unassigned
4149 0x1E6C0, // 1E6C0..1E6FF; Tai Yo
4150 0x1E700, // unassigned
4151 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
4152 0x1E800, // 1E800..1E8DF; Mende Kikakui
4153 0x1E8E0, // unassigned
4154 0x1E900, // 1E900..1E95F; Adlam
4155 0x1E960, // unassigned
4156 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
4157 0x1ECC0, // unassigned
4158 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
4159 0x1ED50, // unassigned
4160 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
4161 0x1EF00, // unassigned
4162 0x1F000, // 1F000..1F02F; Mahjong Tiles
4163 0x1F030, // 1F030..1F09F; Domino Tiles
4164 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
4165 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
4166 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
4167 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
4168 0x1F600, // 1F600..1F64F; Emoticons
4169 0x1F650, // 1F650..1F67F; Ornamental Dingbats
4170 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
4171 0x1F700, // 1F700..1F77F; Alchemical Symbols
4172 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
4173 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
4174 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
4175 0x1FA00, // 1FA00..1FA6F; Chess Symbols
4176 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
4177 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
4178 0x1FC00, // unassigned
4179 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
4180 0x2A6E0, // unassigned
4181 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
4182 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
4183 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
4184 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
4185 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
4186 0x2EE60, // unassigned
4187 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
4188 0x2FA20, // unassigned
4189 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
4190 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4191 0x323B0, // 323B0..3347F; CJK Unified Ideographs Extension J
4192 0x33480, // unassigned
4193 0xE0000, // E0000..E007F; Tags
4194 0xE0080, // unassigned
4195 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4196 0xE01F0, // unassigned
4197 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4198 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4199 };
4200
4201 private static final UnicodeBlock[] blocks = {
4202 BASIC_LATIN,
4203 LATIN_1_SUPPLEMENT,
4204 LATIN_EXTENDED_A,
4205 LATIN_EXTENDED_B,
4206 IPA_EXTENSIONS,
4207 SPACING_MODIFIER_LETTERS,
4208 COMBINING_DIACRITICAL_MARKS,
4209 GREEK,
4210 CYRILLIC,
4211 CYRILLIC_SUPPLEMENTARY,
4212 ARMENIAN,
4213 HEBREW,
4214 ARABIC,
4215 SYRIAC,
4216 ARABIC_SUPPLEMENT,
4217 THAANA,
4218 NKO,
4219 SAMARITAN,
4220 MANDAIC,
4221 SYRIAC_SUPPLEMENT,
4222 ARABIC_EXTENDED_B,
4223 ARABIC_EXTENDED_A,
4224 DEVANAGARI,
4225 BENGALI,
4226 GURMUKHI,
4227 GUJARATI,
4228 ORIYA,
4229 TAMIL,
4230 TELUGU,
4231 KANNADA,
4232 MALAYALAM,
4233 SINHALA,
4234 THAI,
4235 LAO,
4236 TIBETAN,
4237 MYANMAR,
4238 GEORGIAN,
4239 HANGUL_JAMO,
4240 ETHIOPIC,
4241 ETHIOPIC_SUPPLEMENT,
4242 CHEROKEE,
4243 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4244 OGHAM,
4245 RUNIC,
4246 TAGALOG,
4247 HANUNOO,
4248 BUHID,
4249 TAGBANWA,
4250 KHMER,
4251 MONGOLIAN,
4252 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4253 LIMBU,
4254 TAI_LE,
4255 NEW_TAI_LUE,
4256 KHMER_SYMBOLS,
4257 BUGINESE,
4258 TAI_THAM,
4259 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4260 BALINESE,
4261 SUNDANESE,
4262 BATAK,
4263 LEPCHA,
4264 OL_CHIKI,
4265 CYRILLIC_EXTENDED_C,
4266 GEORGIAN_EXTENDED,
4267 SUNDANESE_SUPPLEMENT,
4268 VEDIC_EXTENSIONS,
4269 PHONETIC_EXTENSIONS,
4270 PHONETIC_EXTENSIONS_SUPPLEMENT,
4271 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4272 LATIN_EXTENDED_ADDITIONAL,
4273 GREEK_EXTENDED,
4274 GENERAL_PUNCTUATION,
4275 SUPERSCRIPTS_AND_SUBSCRIPTS,
4276 CURRENCY_SYMBOLS,
4277 COMBINING_MARKS_FOR_SYMBOLS,
4278 LETTERLIKE_SYMBOLS,
4279 NUMBER_FORMS,
4280 ARROWS,
4281 MATHEMATICAL_OPERATORS,
4282 MISCELLANEOUS_TECHNICAL,
4283 CONTROL_PICTURES,
4284 OPTICAL_CHARACTER_RECOGNITION,
4285 ENCLOSED_ALPHANUMERICS,
4286 BOX_DRAWING,
4287 BLOCK_ELEMENTS,
4288 GEOMETRIC_SHAPES,
4289 MISCELLANEOUS_SYMBOLS,
4290 DINGBATS,
4291 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4292 SUPPLEMENTAL_ARROWS_A,
4293 BRAILLE_PATTERNS,
4294 SUPPLEMENTAL_ARROWS_B,
4295 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4296 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4297 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4298 GLAGOLITIC,
4299 LATIN_EXTENDED_C,
4300 COPTIC,
4301 GEORGIAN_SUPPLEMENT,
4302 TIFINAGH,
4303 ETHIOPIC_EXTENDED,
4304 CYRILLIC_EXTENDED_A,
4305 SUPPLEMENTAL_PUNCTUATION,
4306 CJK_RADICALS_SUPPLEMENT,
4307 KANGXI_RADICALS,
4308 null,
4309 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4310 CJK_SYMBOLS_AND_PUNCTUATION,
4311 HIRAGANA,
4312 KATAKANA,
4313 BOPOMOFO,
4314 HANGUL_COMPATIBILITY_JAMO,
4315 KANBUN,
4316 BOPOMOFO_EXTENDED,
4317 CJK_STROKES,
4318 KATAKANA_PHONETIC_EXTENSIONS,
4319 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4320 CJK_COMPATIBILITY,
4321 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4322 YIJING_HEXAGRAM_SYMBOLS,
4323 CJK_UNIFIED_IDEOGRAPHS,
4324 YI_SYLLABLES,
4325 YI_RADICALS,
4326 LISU,
4327 VAI,
4328 CYRILLIC_EXTENDED_B,
4329 BAMUM,
4330 MODIFIER_TONE_LETTERS,
4331 LATIN_EXTENDED_D,
4332 SYLOTI_NAGRI,
4333 COMMON_INDIC_NUMBER_FORMS,
4334 PHAGS_PA,
4335 SAURASHTRA,
4336 DEVANAGARI_EXTENDED,
4337 KAYAH_LI,
4338 REJANG,
4339 HANGUL_JAMO_EXTENDED_A,
4340 JAVANESE,
4341 MYANMAR_EXTENDED_B,
4342 CHAM,
4343 MYANMAR_EXTENDED_A,
4344 TAI_VIET,
4345 MEETEI_MAYEK_EXTENSIONS,
4346 ETHIOPIC_EXTENDED_A,
4347 LATIN_EXTENDED_E,
4348 CHEROKEE_SUPPLEMENT,
4349 MEETEI_MAYEK,
4350 HANGUL_SYLLABLES,
4351 HANGUL_JAMO_EXTENDED_B,
4352 HIGH_SURROGATES,
4353 HIGH_PRIVATE_USE_SURROGATES,
4354 LOW_SURROGATES,
4355 PRIVATE_USE_AREA,
4356 CJK_COMPATIBILITY_IDEOGRAPHS,
4357 ALPHABETIC_PRESENTATION_FORMS,
4358 ARABIC_PRESENTATION_FORMS_A,
4359 VARIATION_SELECTORS,
4360 VERTICAL_FORMS,
4361 COMBINING_HALF_MARKS,
4362 CJK_COMPATIBILITY_FORMS,
4363 SMALL_FORM_VARIANTS,
4364 ARABIC_PRESENTATION_FORMS_B,
4365 HALFWIDTH_AND_FULLWIDTH_FORMS,
4366 SPECIALS,
4367 LINEAR_B_SYLLABARY,
4368 LINEAR_B_IDEOGRAMS,
4369 AEGEAN_NUMBERS,
4370 ANCIENT_GREEK_NUMBERS,
4371 ANCIENT_SYMBOLS,
4372 PHAISTOS_DISC,
4373 null,
4374 LYCIAN,
4375 CARIAN,
4376 COPTIC_EPACT_NUMBERS,
4377 OLD_ITALIC,
4378 GOTHIC,
4379 OLD_PERMIC,
4380 UGARITIC,
4381 OLD_PERSIAN,
4382 null,
4383 DESERET,
4384 SHAVIAN,
4385 OSMANYA,
4386 OSAGE,
4387 ELBASAN,
4388 CAUCASIAN_ALBANIAN,
4389 VITHKUQI,
4390 TODHRI,
4391 LINEAR_A,
4392 LATIN_EXTENDED_F,
4393 null,
4394 CYPRIOT_SYLLABARY,
4395 IMPERIAL_ARAMAIC,
4396 PALMYRENE,
4397 NABATAEAN,
4398 null,
4399 HATRAN,
4400 PHOENICIAN,
4401 LYDIAN,
4402 SIDETIC,
4403 null,
4404 MEROITIC_HIEROGLYPHS,
4405 MEROITIC_CURSIVE,
4406 KHAROSHTHI,
4407 OLD_SOUTH_ARABIAN,
4408 OLD_NORTH_ARABIAN,
4409 null,
4410 MANICHAEAN,
4411 AVESTAN,
4412 INSCRIPTIONAL_PARTHIAN,
4413 INSCRIPTIONAL_PAHLAVI,
4414 PSALTER_PAHLAVI,
4415 null,
4416 OLD_TURKIC,
4417 null,
4418 OLD_HUNGARIAN,
4419 HANIFI_ROHINGYA,
4420 GARAY,
4421 null,
4422 RUMI_NUMERAL_SYMBOLS,
4423 YEZIDI,
4424 ARABIC_EXTENDED_C,
4425 OLD_SOGDIAN,
4426 SOGDIAN,
4427 OLD_UYGHUR,
4428 CHORASMIAN,
4429 ELYMAIC,
4430 BRAHMI,
4431 KAITHI,
4432 SORA_SOMPENG,
4433 CHAKMA,
4434 MAHAJANI,
4435 SHARADA,
4436 SINHALA_ARCHAIC_NUMBERS,
4437 KHOJKI,
4438 null,
4439 MULTANI,
4440 KHUDAWADI,
4441 GRANTHA,
4442 TULU_TIGALARI,
4443 NEWA,
4444 TIRHUTA,
4445 null,
4446 SIDDHAM,
4447 MODI,
4448 MONGOLIAN_SUPPLEMENT,
4449 TAKRI,
4450 MYANMAR_EXTENDED_C,
4451 AHOM,
4452 null,
4453 DOGRA,
4454 null,
4455 WARANG_CITI,
4456 DIVES_AKURU,
4457 null,
4458 NANDINAGARI,
4459 ZANABAZAR_SQUARE,
4460 SOYOMBO,
4461 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4462 PAU_CIN_HAU,
4463 DEVANAGARI_EXTENDED_A,
4464 SHARADA_SUPPLEMENT,
4465 null,
4466 SUNUWAR,
4467 BHAIKSUKI,
4468 MARCHEN,
4469 null,
4470 MASARAM_GONDI,
4471 GUNJALA_GONDI,
4472 TOLONG_SIKI,
4473 null,
4474 MAKASAR,
4475 KAWI,
4476 null,
4477 LISU_SUPPLEMENT,
4478 TAMIL_SUPPLEMENT,
4479 CUNEIFORM,
4480 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4481 EARLY_DYNASTIC_CUNEIFORM,
4482 null,
4483 CYPRO_MINOAN,
4484 EGYPTIAN_HIEROGLYPHS,
4485 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4486 EGYPTIAN_HIEROGLYPHS_EXTENDED_A,
4487 ANATOLIAN_HIEROGLYPHS,
4488 null,
4489 GURUNG_KHEMA,
4490 null,
4491 BAMUM_SUPPLEMENT,
4492 MRO,
4493 TANGSA,
4494 BASSA_VAH,
4495 PAHAWH_HMONG,
4496 null,
4497 KIRAT_RAI,
4498 null,
4499 MEDEFAIDRIN,
4500 BERIA_ERFE,
4501 null,
4502 MIAO,
4503 null,
4504 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4505 TANGUT,
4506 TANGUT_COMPONENTS,
4507 KHITAN_SMALL_SCRIPT,
4508 TANGUT_SUPPLEMENT,
4509 TANGUT_COMPONENTS_SUPPLEMENT,
4510 null,
4511 KANA_EXTENDED_B,
4512 KANA_SUPPLEMENT,
4513 KANA_EXTENDED_A,
4514 SMALL_KANA_EXTENSION,
4515 NUSHU,
4516 null,
4517 DUPLOYAN,
4518 SHORTHAND_FORMAT_CONTROLS,
4519 null,
4520 SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT,
4521 MISCELLANEOUS_SYMBOLS_SUPPLEMENT,
4522 ZNAMENNY_MUSICAL_NOTATION,
4523 null,
4524 BYZANTINE_MUSICAL_SYMBOLS,
4525 MUSICAL_SYMBOLS,
4526 ANCIENT_GREEK_MUSICAL_NOTATION,
4527 null,
4528 KAKTOVIK_NUMERALS,
4529 MAYAN_NUMERALS,
4530 TAI_XUAN_JING_SYMBOLS,
4531 COUNTING_ROD_NUMERALS,
4532 null,
4533 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4534 SUTTON_SIGNWRITING,
4535 null,
4536 LATIN_EXTENDED_G,
4537 GLAGOLITIC_SUPPLEMENT,
4538 CYRILLIC_EXTENDED_D,
4539 null,
4540 NYIAKENG_PUACHUE_HMONG,
4541 null,
4542 TOTO,
4543 WANCHO,
4544 null,
4545 NAG_MUNDARI,
4546 null,
4547 OL_ONAL,
4548 null,
4549 TAI_YO,
4550 null,
4551 ETHIOPIC_EXTENDED_B,
4552 MENDE_KIKAKUI,
4553 null,
4554 ADLAM,
4555 null,
4556 INDIC_SIYAQ_NUMBERS,
4557 null,
4558 OTTOMAN_SIYAQ_NUMBERS,
4559 null,
4560 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4561 null,
4562 MAHJONG_TILES,
4563 DOMINO_TILES,
4564 PLAYING_CARDS,
4565 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4566 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4567 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4568 EMOTICONS,
4569 ORNAMENTAL_DINGBATS,
4570 TRANSPORT_AND_MAP_SYMBOLS,
4571 ALCHEMICAL_SYMBOLS,
4572 GEOMETRIC_SHAPES_EXTENDED,
4573 SUPPLEMENTAL_ARROWS_C,
4574 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4575 CHESS_SYMBOLS,
4576 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4577 SYMBOLS_FOR_LEGACY_COMPUTING,
4578 null,
4579 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4580 null,
4581 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4582 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4583 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4584 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4585 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4586 null,
4587 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4588 null,
4589 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4590 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4591 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J,
4592 null,
4593 TAGS,
4594 null,
4595 VARIATION_SELECTORS_SUPPLEMENT,
4596 null,
4597 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4598 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4599 };
4600
4601
4602 /**
4603 * Returns the object representing the Unicode block containing the
4604 * given character, or {@code null} if the character is not a
4605 * member of a defined block.
4606 *
4607 * <p><b>Note:</b> This method cannot handle
4608 * <a href="Character.html#supplementary"> supplementary
4609 * characters</a>. To support all Unicode characters, including
4610 * supplementary characters, use the {@link #of(int)} method.
4611 *
4612 * @param c The character in question
4613 * @return The {@code UnicodeBlock} instance representing the
4614 * Unicode block of which this character is a member, or
4615 * {@code null} if the character is not a member of any
4616 * Unicode block
4617 */
4618 public static UnicodeBlock of(char c) {
4619 return of((int)c);
4620 }
4621
4622 /**
4623 * Returns the object representing the Unicode block
4624 * containing the given character (Unicode code point), or
4625 * {@code null} if the character is not a member of a
4626 * defined block.
4627 *
4628 * @param codePoint the character (Unicode code point) in question.
4629 * @return The {@code UnicodeBlock} instance representing the
4630 * Unicode block of which this character is a member, or
4631 * {@code null} if the character is not a member of any
4632 * Unicode block
4633 * @throws IllegalArgumentException if the specified
4634 * {@code codePoint} is an invalid Unicode code point.
4635 * @see Character#isValidCodePoint(int)
4636 * @since 1.5
4637 */
4638 public static UnicodeBlock of(int codePoint) {
4639 if (!isValidCodePoint(codePoint)) {
4640 throw new IllegalArgumentException(
4641 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4642 }
4643
4644 int top, bottom, current;
4645 bottom = 0;
4646 top = blockStarts.length;
4647 current = top/2;
4648
4649 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4650 while (top - bottom > 1) {
4651 if (codePoint >= blockStarts[current]) {
4652 bottom = current;
4653 } else {
4654 top = current;
4655 }
4656 current = (top + bottom) / 2;
4657 }
4658 return blocks[current];
4659 }
4660
4661 /**
4662 * Returns the UnicodeBlock with the given name. Block
4663 * names are determined by The Unicode Standard. The file
4664 * {@code Blocks.txt} defines blocks for a particular
4665 * version of the standard. The {@link Character} class specifies
4666 * the version of the standard that it supports.
4667 * <p>
4668 * This method accepts block names in the following forms:
4669 * <ol>
4670 * <li> Canonical block names as defined by the Unicode Standard.
4671 * For example, the standard defines a "Basic Latin" block. Therefore, this
4672 * method accepts "Basic Latin" as a valid block name. The documentation of
4673 * each UnicodeBlock provides the canonical name.
4674 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4675 * is a valid block name for the "Basic Latin" block.
4676 * <li>The text representation of each constant UnicodeBlock identifier.
4677 * For example, this method will return the {@link #BASIC_LATIN} block if
4678 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4679 * hyphens in the canonical name with underscores.
4680 * </ol>
4681 * Finally, character case is ignored for all of the valid block name forms.
4682 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4683 * The en_US locale's case mapping rules are used to provide case-insensitive
4684 * string comparisons for block name validation.
4685 * <p>
4686 * If the Unicode Standard changes block names, both the previous and
4687 * current names will be accepted.
4688 *
4689 * @param blockName A {@code UnicodeBlock} name.
4690 * @return The {@code UnicodeBlock} instance identified
4691 * by {@code blockName}
4692 * @throws IllegalArgumentException if {@code blockName} is an
4693 * invalid name
4694 * @throws NullPointerException if {@code blockName} is null
4695 * @since 1.5
4696 */
4697 public static final UnicodeBlock forName(String blockName) {
4698 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4699 if (block == null) {
4700 throw new IllegalArgumentException("Not a valid block name: "
4701 + blockName);
4702 }
4703 return block;
4704 }
4705 }
4706
4707
4708 /**
4709 * A family of character subsets representing the character scripts
4710 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4711 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4712 * character is assigned to a single Unicode script, either a specific
4713 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4714 * one of the following three special values,
4715 * {@link Character.UnicodeScript#INHERITED Inherited},
4716 * {@link Character.UnicodeScript#COMMON Common} or
4717 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4718 *
4719 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4720 * @since 1.7
4721 */
4722 public static enum UnicodeScript {
4723
4724 /**
4725 * Unicode script "Common".
4726 */
4727 COMMON,
4728
4729 /**
4730 * Unicode script "Latin".
4731 */
4732 LATIN,
4733
4734 /**
4735 * Unicode script "Greek".
4736 */
4737 GREEK,
4738
4739 /**
4740 * Unicode script "Cyrillic".
4741 */
4742 CYRILLIC,
4743
4744 /**
4745 * Unicode script "Armenian".
4746 */
4747 ARMENIAN,
4748
4749 /**
4750 * Unicode script "Hebrew".
4751 */
4752 HEBREW,
4753
4754 /**
4755 * Unicode script "Arabic".
4756 */
4757 ARABIC,
4758
4759 /**
4760 * Unicode script "Syriac".
4761 */
4762 SYRIAC,
4763
4764 /**
4765 * Unicode script "Thaana".
4766 */
4767 THAANA,
4768
4769 /**
4770 * Unicode script "Devanagari".
4771 */
4772 DEVANAGARI,
4773
4774 /**
4775 * Unicode script "Bengali".
4776 */
4777 BENGALI,
4778
4779 /**
4780 * Unicode script "Gurmukhi".
4781 */
4782 GURMUKHI,
4783
4784 /**
4785 * Unicode script "Gujarati".
4786 */
4787 GUJARATI,
4788
4789 /**
4790 * Unicode script "Oriya".
4791 */
4792 ORIYA,
4793
4794 /**
4795 * Unicode script "Tamil".
4796 */
4797 TAMIL,
4798
4799 /**
4800 * Unicode script "Telugu".
4801 */
4802 TELUGU,
4803
4804 /**
4805 * Unicode script "Kannada".
4806 */
4807 KANNADA,
4808
4809 /**
4810 * Unicode script "Malayalam".
4811 */
4812 MALAYALAM,
4813
4814 /**
4815 * Unicode script "Sinhala".
4816 */
4817 SINHALA,
4818
4819 /**
4820 * Unicode script "Thai".
4821 */
4822 THAI,
4823
4824 /**
4825 * Unicode script "Lao".
4826 */
4827 LAO,
4828
4829 /**
4830 * Unicode script "Tibetan".
4831 */
4832 TIBETAN,
4833
4834 /**
4835 * Unicode script "Myanmar".
4836 */
4837 MYANMAR,
4838
4839 /**
4840 * Unicode script "Georgian".
4841 */
4842 GEORGIAN,
4843
4844 /**
4845 * Unicode script "Hangul".
4846 */
4847 HANGUL,
4848
4849 /**
4850 * Unicode script "Ethiopic".
4851 */
4852 ETHIOPIC,
4853
4854 /**
4855 * Unicode script "Cherokee".
4856 */
4857 CHEROKEE,
4858
4859 /**
4860 * Unicode script "Canadian_Aboriginal".
4861 */
4862 CANADIAN_ABORIGINAL,
4863
4864 /**
4865 * Unicode script "Ogham".
4866 */
4867 OGHAM,
4868
4869 /**
4870 * Unicode script "Runic".
4871 */
4872 RUNIC,
4873
4874 /**
4875 * Unicode script "Khmer".
4876 */
4877 KHMER,
4878
4879 /**
4880 * Unicode script "Mongolian".
4881 */
4882 MONGOLIAN,
4883
4884 /**
4885 * Unicode script "Hiragana".
4886 */
4887 HIRAGANA,
4888
4889 /**
4890 * Unicode script "Katakana".
4891 */
4892 KATAKANA,
4893
4894 /**
4895 * Unicode script "Bopomofo".
4896 */
4897 BOPOMOFO,
4898
4899 /**
4900 * Unicode script "Han".
4901 */
4902 HAN,
4903
4904 /**
4905 * Unicode script "Yi".
4906 */
4907 YI,
4908
4909 /**
4910 * Unicode script "Old_Italic".
4911 */
4912 OLD_ITALIC,
4913
4914 /**
4915 * Unicode script "Gothic".
4916 */
4917 GOTHIC,
4918
4919 /**
4920 * Unicode script "Deseret".
4921 */
4922 DESERET,
4923
4924 /**
4925 * Unicode script "Inherited".
4926 */
4927 INHERITED,
4928
4929 /**
4930 * Unicode script "Tagalog".
4931 */
4932 TAGALOG,
4933
4934 /**
4935 * Unicode script "Hanunoo".
4936 */
4937 HANUNOO,
4938
4939 /**
4940 * Unicode script "Buhid".
4941 */
4942 BUHID,
4943
4944 /**
4945 * Unicode script "Tagbanwa".
4946 */
4947 TAGBANWA,
4948
4949 /**
4950 * Unicode script "Limbu".
4951 */
4952 LIMBU,
4953
4954 /**
4955 * Unicode script "Tai_Le".
4956 */
4957 TAI_LE,
4958
4959 /**
4960 * Unicode script "Linear_B".
4961 */
4962 LINEAR_B,
4963
4964 /**
4965 * Unicode script "Ugaritic".
4966 */
4967 UGARITIC,
4968
4969 /**
4970 * Unicode script "Shavian".
4971 */
4972 SHAVIAN,
4973
4974 /**
4975 * Unicode script "Osmanya".
4976 */
4977 OSMANYA,
4978
4979 /**
4980 * Unicode script "Cypriot".
4981 */
4982 CYPRIOT,
4983
4984 /**
4985 * Unicode script "Braille".
4986 */
4987 BRAILLE,
4988
4989 /**
4990 * Unicode script "Buginese".
4991 */
4992 BUGINESE,
4993
4994 /**
4995 * Unicode script "Coptic".
4996 */
4997 COPTIC,
4998
4999 /**
5000 * Unicode script "New_Tai_Lue".
5001 */
5002 NEW_TAI_LUE,
5003
5004 /**
5005 * Unicode script "Glagolitic".
5006 */
5007 GLAGOLITIC,
5008
5009 /**
5010 * Unicode script "Tifinagh".
5011 */
5012 TIFINAGH,
5013
5014 /**
5015 * Unicode script "Syloti_Nagri".
5016 */
5017 SYLOTI_NAGRI,
5018
5019 /**
5020 * Unicode script "Old_Persian".
5021 */
5022 OLD_PERSIAN,
5023
5024 /**
5025 * Unicode script "Kharoshthi".
5026 */
5027 KHAROSHTHI,
5028
5029 /**
5030 * Unicode script "Balinese".
5031 */
5032 BALINESE,
5033
5034 /**
5035 * Unicode script "Cuneiform".
5036 */
5037 CUNEIFORM,
5038
5039 /**
5040 * Unicode script "Phoenician".
5041 */
5042 PHOENICIAN,
5043
5044 /**
5045 * Unicode script "Phags_Pa".
5046 */
5047 PHAGS_PA,
5048
5049 /**
5050 * Unicode script "Nko".
5051 */
5052 NKO,
5053
5054 /**
5055 * Unicode script "Sundanese".
5056 */
5057 SUNDANESE,
5058
5059 /**
5060 * Unicode script "Batak".
5061 */
5062 BATAK,
5063
5064 /**
5065 * Unicode script "Lepcha".
5066 */
5067 LEPCHA,
5068
5069 /**
5070 * Unicode script "Ol_Chiki".
5071 */
5072 OL_CHIKI,
5073
5074 /**
5075 * Unicode script "Vai".
5076 */
5077 VAI,
5078
5079 /**
5080 * Unicode script "Saurashtra".
5081 */
5082 SAURASHTRA,
5083
5084 /**
5085 * Unicode script "Kayah_Li".
5086 */
5087 KAYAH_LI,
5088
5089 /**
5090 * Unicode script "Rejang".
5091 */
5092 REJANG,
5093
5094 /**
5095 * Unicode script "Lycian".
5096 */
5097 LYCIAN,
5098
5099 /**
5100 * Unicode script "Carian".
5101 */
5102 CARIAN,
5103
5104 /**
5105 * Unicode script "Lydian".
5106 */
5107 LYDIAN,
5108
5109 /**
5110 * Unicode script "Cham".
5111 */
5112 CHAM,
5113
5114 /**
5115 * Unicode script "Tai_Tham".
5116 */
5117 TAI_THAM,
5118
5119 /**
5120 * Unicode script "Tai_Viet".
5121 */
5122 TAI_VIET,
5123
5124 /**
5125 * Unicode script "Avestan".
5126 */
5127 AVESTAN,
5128
5129 /**
5130 * Unicode script "Egyptian_Hieroglyphs".
5131 */
5132 EGYPTIAN_HIEROGLYPHS,
5133
5134 /**
5135 * Unicode script "Samaritan".
5136 */
5137 SAMARITAN,
5138
5139 /**
5140 * Unicode script "Mandaic".
5141 */
5142 MANDAIC,
5143
5144 /**
5145 * Unicode script "Lisu".
5146 */
5147 LISU,
5148
5149 /**
5150 * Unicode script "Bamum".
5151 */
5152 BAMUM,
5153
5154 /**
5155 * Unicode script "Javanese".
5156 */
5157 JAVANESE,
5158
5159 /**
5160 * Unicode script "Meetei_Mayek".
5161 */
5162 MEETEI_MAYEK,
5163
5164 /**
5165 * Unicode script "Imperial_Aramaic".
5166 */
5167 IMPERIAL_ARAMAIC,
5168
5169 /**
5170 * Unicode script "Old_South_Arabian".
5171 */
5172 OLD_SOUTH_ARABIAN,
5173
5174 /**
5175 * Unicode script "Inscriptional_Parthian".
5176 */
5177 INSCRIPTIONAL_PARTHIAN,
5178
5179 /**
5180 * Unicode script "Inscriptional_Pahlavi".
5181 */
5182 INSCRIPTIONAL_PAHLAVI,
5183
5184 /**
5185 * Unicode script "Old_Turkic".
5186 */
5187 OLD_TURKIC,
5188
5189 /**
5190 * Unicode script "Brahmi".
5191 */
5192 BRAHMI,
5193
5194 /**
5195 * Unicode script "Kaithi".
5196 */
5197 KAITHI,
5198
5199 /**
5200 * Unicode script "Meroitic Hieroglyphs".
5201 * @since 1.8
5202 */
5203 MEROITIC_HIEROGLYPHS,
5204
5205 /**
5206 * Unicode script "Meroitic Cursive".
5207 * @since 1.8
5208 */
5209 MEROITIC_CURSIVE,
5210
5211 /**
5212 * Unicode script "Sora Sompeng".
5213 * @since 1.8
5214 */
5215 SORA_SOMPENG,
5216
5217 /**
5218 * Unicode script "Chakma".
5219 * @since 1.8
5220 */
5221 CHAKMA,
5222
5223 /**
5224 * Unicode script "Sharada".
5225 * @since 1.8
5226 */
5227 SHARADA,
5228
5229 /**
5230 * Unicode script "Takri".
5231 * @since 1.8
5232 */
5233 TAKRI,
5234
5235 /**
5236 * Unicode script "Miao".
5237 * @since 1.8
5238 */
5239 MIAO,
5240
5241 /**
5242 * Unicode script "Caucasian Albanian".
5243 * @since 9
5244 */
5245 CAUCASIAN_ALBANIAN,
5246
5247 /**
5248 * Unicode script "Bassa Vah".
5249 * @since 9
5250 */
5251 BASSA_VAH,
5252
5253 /**
5254 * Unicode script "Duployan".
5255 * @since 9
5256 */
5257 DUPLOYAN,
5258
5259 /**
5260 * Unicode script "Elbasan".
5261 * @since 9
5262 */
5263 ELBASAN,
5264
5265 /**
5266 * Unicode script "Grantha".
5267 * @since 9
5268 */
5269 GRANTHA,
5270
5271 /**
5272 * Unicode script "Pahawh Hmong".
5273 * @since 9
5274 */
5275 PAHAWH_HMONG,
5276
5277 /**
5278 * Unicode script "Khojki".
5279 * @since 9
5280 */
5281 KHOJKI,
5282
5283 /**
5284 * Unicode script "Linear A".
5285 * @since 9
5286 */
5287 LINEAR_A,
5288
5289 /**
5290 * Unicode script "Mahajani".
5291 * @since 9
5292 */
5293 MAHAJANI,
5294
5295 /**
5296 * Unicode script "Manichaean".
5297 * @since 9
5298 */
5299 MANICHAEAN,
5300
5301 /**
5302 * Unicode script "Mende Kikakui".
5303 * @since 9
5304 */
5305 MENDE_KIKAKUI,
5306
5307 /**
5308 * Unicode script "Modi".
5309 * @since 9
5310 */
5311 MODI,
5312
5313 /**
5314 * Unicode script "Mro".
5315 * @since 9
5316 */
5317 MRO,
5318
5319 /**
5320 * Unicode script "Old North Arabian".
5321 * @since 9
5322 */
5323 OLD_NORTH_ARABIAN,
5324
5325 /**
5326 * Unicode script "Nabataean".
5327 * @since 9
5328 */
5329 NABATAEAN,
5330
5331 /**
5332 * Unicode script "Palmyrene".
5333 * @since 9
5334 */
5335 PALMYRENE,
5336
5337 /**
5338 * Unicode script "Pau Cin Hau".
5339 * @since 9
5340 */
5341 PAU_CIN_HAU,
5342
5343 /**
5344 * Unicode script "Old Permic".
5345 * @since 9
5346 */
5347 OLD_PERMIC,
5348
5349 /**
5350 * Unicode script "Psalter Pahlavi".
5351 * @since 9
5352 */
5353 PSALTER_PAHLAVI,
5354
5355 /**
5356 * Unicode script "Siddham".
5357 * @since 9
5358 */
5359 SIDDHAM,
5360
5361 /**
5362 * Unicode script "Khudawadi".
5363 * @since 9
5364 */
5365 KHUDAWADI,
5366
5367 /**
5368 * Unicode script "Tirhuta".
5369 * @since 9
5370 */
5371 TIRHUTA,
5372
5373 /**
5374 * Unicode script "Warang Citi".
5375 * @since 9
5376 */
5377 WARANG_CITI,
5378
5379 /**
5380 * Unicode script "Ahom".
5381 * @since 9
5382 */
5383 AHOM,
5384
5385 /**
5386 * Unicode script "Anatolian Hieroglyphs".
5387 * @since 9
5388 */
5389 ANATOLIAN_HIEROGLYPHS,
5390
5391 /**
5392 * Unicode script "Hatran".
5393 * @since 9
5394 */
5395 HATRAN,
5396
5397 /**
5398 * Unicode script "Multani".
5399 * @since 9
5400 */
5401 MULTANI,
5402
5403 /**
5404 * Unicode script "Old Hungarian".
5405 * @since 9
5406 */
5407 OLD_HUNGARIAN,
5408
5409 /**
5410 * Unicode script "SignWriting".
5411 * @since 9
5412 */
5413 SIGNWRITING,
5414
5415 /**
5416 * Unicode script "Adlam".
5417 * @since 11
5418 */
5419 ADLAM,
5420
5421 /**
5422 * Unicode script "Bhaiksuki".
5423 * @since 11
5424 */
5425 BHAIKSUKI,
5426
5427 /**
5428 * Unicode script "Marchen".
5429 * @since 11
5430 */
5431 MARCHEN,
5432
5433 /**
5434 * Unicode script "Newa".
5435 * @since 11
5436 */
5437 NEWA,
5438
5439 /**
5440 * Unicode script "Osage".
5441 * @since 11
5442 */
5443 OSAGE,
5444
5445 /**
5446 * Unicode script "Tangut".
5447 * @since 11
5448 */
5449 TANGUT,
5450
5451 /**
5452 * Unicode script "Masaram Gondi".
5453 * @since 11
5454 */
5455 MASARAM_GONDI,
5456
5457 /**
5458 * Unicode script "Nushu".
5459 * @since 11
5460 */
5461 NUSHU,
5462
5463 /**
5464 * Unicode script "Soyombo".
5465 * @since 11
5466 */
5467 SOYOMBO,
5468
5469 /**
5470 * Unicode script "Zanabazar Square".
5471 * @since 11
5472 */
5473 ZANABAZAR_SQUARE,
5474
5475 /**
5476 * Unicode script "Hanifi Rohingya".
5477 * @since 12
5478 */
5479 HANIFI_ROHINGYA,
5480
5481 /**
5482 * Unicode script "Old Sogdian".
5483 * @since 12
5484 */
5485 OLD_SOGDIAN,
5486
5487 /**
5488 * Unicode script "Sogdian".
5489 * @since 12
5490 */
5491 SOGDIAN,
5492
5493 /**
5494 * Unicode script "Dogra".
5495 * @since 12
5496 */
5497 DOGRA,
5498
5499 /**
5500 * Unicode script "Gunjala Gondi".
5501 * @since 12
5502 */
5503 GUNJALA_GONDI,
5504
5505 /**
5506 * Unicode script "Makasar".
5507 * @since 12
5508 */
5509 MAKASAR,
5510
5511 /**
5512 * Unicode script "Medefaidrin".
5513 * @since 12
5514 */
5515 MEDEFAIDRIN,
5516
5517 /**
5518 * Unicode script "Elymaic".
5519 * @since 13
5520 */
5521 ELYMAIC,
5522
5523 /**
5524 * Unicode script "Nandinagari".
5525 * @since 13
5526 */
5527 NANDINAGARI,
5528
5529 /**
5530 * Unicode script "Nyiakeng Puachue Hmong".
5531 * @since 13
5532 */
5533 NYIAKENG_PUACHUE_HMONG,
5534
5535 /**
5536 * Unicode script "Wancho".
5537 * @since 13
5538 */
5539 WANCHO,
5540
5541 /**
5542 * Unicode script "Yezidi".
5543 * @since 15
5544 */
5545 YEZIDI,
5546
5547 /**
5548 * Unicode script "Chorasmian".
5549 * @since 15
5550 */
5551 CHORASMIAN,
5552
5553 /**
5554 * Unicode script "Dives Akuru".
5555 * @since 15
5556 */
5557 DIVES_AKURU,
5558
5559 /**
5560 * Unicode script "Khitan Small Script".
5561 * @since 15
5562 */
5563 KHITAN_SMALL_SCRIPT,
5564
5565 /**
5566 * Unicode script "Vithkuqi".
5567 * @since 19
5568 */
5569 VITHKUQI,
5570
5571 /**
5572 * Unicode script "Old Uyghur".
5573 * @since 19
5574 */
5575 OLD_UYGHUR,
5576
5577 /**
5578 * Unicode script "Cypro Minoan".
5579 * @since 19
5580 */
5581 CYPRO_MINOAN,
5582
5583 /**
5584 * Unicode script "Tangsa".
5585 * @since 19
5586 */
5587 TANGSA,
5588
5589 /**
5590 * Unicode script "Toto".
5591 * @since 19
5592 */
5593 TOTO,
5594
5595 /**
5596 * Unicode script "Kawi".
5597 * @since 20
5598 */
5599 KAWI,
5600
5601 /**
5602 * Unicode script "Nag Mundari".
5603 * @since 20
5604 */
5605 NAG_MUNDARI,
5606
5607 /**
5608 * Unicode script "Todhri".
5609 * @since 24
5610 */
5611 TODHRI,
5612
5613 /**
5614 * Unicode script "Garay".
5615 * @since 24
5616 */
5617 GARAY,
5618
5619 /**
5620 * Unicode script "Tulu Tigalari".
5621 * @since 24
5622 */
5623 TULU_TIGALARI,
5624
5625 /**
5626 * Unicode script "Sunuwar".
5627 * @since 24
5628 */
5629 SUNUWAR,
5630
5631 /**
5632 * Unicode script "Gurung Khema".
5633 * @since 24
5634 */
5635 GURUNG_KHEMA,
5636
5637 /**
5638 * Unicode script "Kirat Rai".
5639 * @since 24
5640 */
5641 KIRAT_RAI,
5642
5643 /**
5644 * Unicode script "Ol Onal".
5645 * @since 24
5646 */
5647 OL_ONAL,
5648
5649 /**
5650 * Unicode script "Sidetic".
5651 * @since 26
5652 */
5653 SIDETIC,
5654
5655 /**
5656 * Unicode script "Tolong Siki".
5657 * @since 26
5658 */
5659 TOLONG_SIKI,
5660
5661 /**
5662 * Unicode script "Beria Erfe".
5663 * @since 26
5664 */
5665 BERIA_ERFE,
5666
5667 /**
5668 * Unicode script "Tai Yo".
5669 * @since 26
5670 */
5671 TAI_YO,
5672
5673 /**
5674 * Unicode script "Unknown".
5675 */
5676 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5677
5678 private static final int[] scriptStarts = {
5679 0x0000, // 0000..0040; COMMON
5680 0x0041, // 0041..005A; LATIN
5681 0x005B, // 005B..0060; COMMON
5682 0x0061, // 0061..007A; LATIN
5683 0x007B, // 007B..00A9; COMMON
5684 0x00AA, // 00AA ; LATIN
5685 0x00AB, // 00AB..00B9; COMMON
5686 0x00BA, // 00BA ; LATIN
5687 0x00BB, // 00BB..00BF; COMMON
5688 0x00C0, // 00C0..00D6; LATIN
5689 0x00D7, // 00D7 ; COMMON
5690 0x00D8, // 00D8..00F6; LATIN
5691 0x00F7, // 00F7 ; COMMON
5692 0x00F8, // 00F8..02B8; LATIN
5693 0x02B9, // 02B9..02DF; COMMON
5694 0x02E0, // 02E0..02E4; LATIN
5695 0x02E5, // 02E5..02E9; COMMON
5696 0x02EA, // 02EA..02EB; BOPOMOFO
5697 0x02EC, // 02EC..02FF; COMMON
5698 0x0300, // 0300..036F; INHERITED
5699 0x0370, // 0370..0373; GREEK
5700 0x0374, // 0374 ; COMMON
5701 0x0375, // 0375..0377; GREEK
5702 0x0378, // 0378..0379; UNKNOWN
5703 0x037A, // 037A..037D; GREEK
5704 0x037E, // 037E ; COMMON
5705 0x037F, // 037F ; GREEK
5706 0x0380, // 0380..0383; UNKNOWN
5707 0x0384, // 0384 ; GREEK
5708 0x0385, // 0385 ; COMMON
5709 0x0386, // 0386 ; GREEK
5710 0x0387, // 0387 ; COMMON
5711 0x0388, // 0388..038A; GREEK
5712 0x038B, // 038B ; UNKNOWN
5713 0x038C, // 038C ; GREEK
5714 0x038D, // 038D ; UNKNOWN
5715 0x038E, // 038E..03A1; GREEK
5716 0x03A2, // 03A2 ; UNKNOWN
5717 0x03A3, // 03A3..03E1; GREEK
5718 0x03E2, // 03E2..03EF; COPTIC
5719 0x03F0, // 03F0..03FF; GREEK
5720 0x0400, // 0400..0484; CYRILLIC
5721 0x0485, // 0485..0486; INHERITED
5722 0x0487, // 0487..052F; CYRILLIC
5723 0x0530, // 0530 ; UNKNOWN
5724 0x0531, // 0531..0556; ARMENIAN
5725 0x0557, // 0557..0558; UNKNOWN
5726 0x0559, // 0559..058A; ARMENIAN
5727 0x058B, // 058B..058C; UNKNOWN
5728 0x058D, // 058D..058F; ARMENIAN
5729 0x0590, // 0590 ; UNKNOWN
5730 0x0591, // 0591..05C7; HEBREW
5731 0x05C8, // 05C8..05CF; UNKNOWN
5732 0x05D0, // 05D0..05EA; HEBREW
5733 0x05EB, // 05EB..05EE; UNKNOWN
5734 0x05EF, // 05EF..05F4; HEBREW
5735 0x05F5, // 05F5..05FF; UNKNOWN
5736 0x0600, // 0600..0604; ARABIC
5737 0x0605, // 0605 ; COMMON
5738 0x0606, // 0606..060B; ARABIC
5739 0x060C, // 060C ; COMMON
5740 0x060D, // 060D..061A; ARABIC
5741 0x061B, // 061B ; COMMON
5742 0x061C, // 061C..061E; ARABIC
5743 0x061F, // 061F ; COMMON
5744 0x0620, // 0620..063F; ARABIC
5745 0x0640, // 0640 ; COMMON
5746 0x0641, // 0641..064A; ARABIC
5747 0x064B, // 064B..0655; INHERITED
5748 0x0656, // 0656..066F; ARABIC
5749 0x0670, // 0670 ; INHERITED
5750 0x0671, // 0671..06DC; ARABIC
5751 0x06DD, // 06DD ; COMMON
5752 0x06DE, // 06DE..06FF; ARABIC
5753 0x0700, // 0700..070D; SYRIAC
5754 0x070E, // 070E ; UNKNOWN
5755 0x070F, // 070F..074A; SYRIAC
5756 0x074B, // 074B..074C; UNKNOWN
5757 0x074D, // 074D..074F; SYRIAC
5758 0x0750, // 0750..077F; ARABIC
5759 0x0780, // 0780..07B1; THAANA
5760 0x07B2, // 07B2..07BF; UNKNOWN
5761 0x07C0, // 07C0..07FA; NKO
5762 0x07FB, // 07FB..07FC; UNKNOWN
5763 0x07FD, // 07FD..07FF; NKO
5764 0x0800, // 0800..082D; SAMARITAN
5765 0x082E, // 082E..082F; UNKNOWN
5766 0x0830, // 0830..083E; SAMARITAN
5767 0x083F, // 083F ; UNKNOWN
5768 0x0840, // 0840..085B; MANDAIC
5769 0x085C, // 085C..085D; UNKNOWN
5770 0x085E, // 085E ; MANDAIC
5771 0x085F, // 085F ; UNKNOWN
5772 0x0860, // 0860..086A; SYRIAC
5773 0x086B, // 086B..086F; UNKNOWN
5774 0x0870, // 0870..0891; ARABIC
5775 0x0892, // 0892..0896; UNKNOWN
5776 0x0897, // 0897..08E1; ARABIC
5777 0x08E2, // 08E2 ; COMMON
5778 0x08E3, // 08E3..08FF; ARABIC
5779 0x0900, // 0900..0950; DEVANAGARI
5780 0x0951, // 0951..0954; INHERITED
5781 0x0955, // 0955..0963; DEVANAGARI
5782 0x0964, // 0964..0965; COMMON
5783 0x0966, // 0966..097F; DEVANAGARI
5784 0x0980, // 0980..0983; BENGALI
5785 0x0984, // 0984 ; UNKNOWN
5786 0x0985, // 0985..098C; BENGALI
5787 0x098D, // 098D..098E; UNKNOWN
5788 0x098F, // 098F..0990; BENGALI
5789 0x0991, // 0991..0992; UNKNOWN
5790 0x0993, // 0993..09A8; BENGALI
5791 0x09A9, // 09A9 ; UNKNOWN
5792 0x09AA, // 09AA..09B0; BENGALI
5793 0x09B1, // 09B1 ; UNKNOWN
5794 0x09B2, // 09B2 ; BENGALI
5795 0x09B3, // 09B3..09B5; UNKNOWN
5796 0x09B6, // 09B6..09B9; BENGALI
5797 0x09BA, // 09BA..09BB; UNKNOWN
5798 0x09BC, // 09BC..09C4; BENGALI
5799 0x09C5, // 09C5..09C6; UNKNOWN
5800 0x09C7, // 09C7..09C8; BENGALI
5801 0x09C9, // 09C9..09CA; UNKNOWN
5802 0x09CB, // 09CB..09CE; BENGALI
5803 0x09CF, // 09CF..09D6; UNKNOWN
5804 0x09D7, // 09D7 ; BENGALI
5805 0x09D8, // 09D8..09DB; UNKNOWN
5806 0x09DC, // 09DC..09DD; BENGALI
5807 0x09DE, // 09DE ; UNKNOWN
5808 0x09DF, // 09DF..09E3; BENGALI
5809 0x09E4, // 09E4..09E5; UNKNOWN
5810 0x09E6, // 09E6..09FE; BENGALI
5811 0x09FF, // 09FF..0A00; UNKNOWN
5812 0x0A01, // 0A01..0A03; GURMUKHI
5813 0x0A04, // 0A04 ; UNKNOWN
5814 0x0A05, // 0A05..0A0A; GURMUKHI
5815 0x0A0B, // 0A0B..0A0E; UNKNOWN
5816 0x0A0F, // 0A0F..0A10; GURMUKHI
5817 0x0A11, // 0A11..0A12; UNKNOWN
5818 0x0A13, // 0A13..0A28; GURMUKHI
5819 0x0A29, // 0A29 ; UNKNOWN
5820 0x0A2A, // 0A2A..0A30; GURMUKHI
5821 0x0A31, // 0A31 ; UNKNOWN
5822 0x0A32, // 0A32..0A33; GURMUKHI
5823 0x0A34, // 0A34 ; UNKNOWN
5824 0x0A35, // 0A35..0A36; GURMUKHI
5825 0x0A37, // 0A37 ; UNKNOWN
5826 0x0A38, // 0A38..0A39; GURMUKHI
5827 0x0A3A, // 0A3A..0A3B; UNKNOWN
5828 0x0A3C, // 0A3C ; GURMUKHI
5829 0x0A3D, // 0A3D ; UNKNOWN
5830 0x0A3E, // 0A3E..0A42; GURMUKHI
5831 0x0A43, // 0A43..0A46; UNKNOWN
5832 0x0A47, // 0A47..0A48; GURMUKHI
5833 0x0A49, // 0A49..0A4A; UNKNOWN
5834 0x0A4B, // 0A4B..0A4D; GURMUKHI
5835 0x0A4E, // 0A4E..0A50; UNKNOWN
5836 0x0A51, // 0A51 ; GURMUKHI
5837 0x0A52, // 0A52..0A58; UNKNOWN
5838 0x0A59, // 0A59..0A5C; GURMUKHI
5839 0x0A5D, // 0A5D ; UNKNOWN
5840 0x0A5E, // 0A5E ; GURMUKHI
5841 0x0A5F, // 0A5F..0A65; UNKNOWN
5842 0x0A66, // 0A66..0A76; GURMUKHI
5843 0x0A77, // 0A77..0A80; UNKNOWN
5844 0x0A81, // 0A81..0A83; GUJARATI
5845 0x0A84, // 0A84 ; UNKNOWN
5846 0x0A85, // 0A85..0A8D; GUJARATI
5847 0x0A8E, // 0A8E ; UNKNOWN
5848 0x0A8F, // 0A8F..0A91; GUJARATI
5849 0x0A92, // 0A92 ; UNKNOWN
5850 0x0A93, // 0A93..0AA8; GUJARATI
5851 0x0AA9, // 0AA9 ; UNKNOWN
5852 0x0AAA, // 0AAA..0AB0; GUJARATI
5853 0x0AB1, // 0AB1 ; UNKNOWN
5854 0x0AB2, // 0AB2..0AB3; GUJARATI
5855 0x0AB4, // 0AB4 ; UNKNOWN
5856 0x0AB5, // 0AB5..0AB9; GUJARATI
5857 0x0ABA, // 0ABA..0ABB; UNKNOWN
5858 0x0ABC, // 0ABC..0AC5; GUJARATI
5859 0x0AC6, // 0AC6 ; UNKNOWN
5860 0x0AC7, // 0AC7..0AC9; GUJARATI
5861 0x0ACA, // 0ACA ; UNKNOWN
5862 0x0ACB, // 0ACB..0ACD; GUJARATI
5863 0x0ACE, // 0ACE..0ACF; UNKNOWN
5864 0x0AD0, // 0AD0 ; GUJARATI
5865 0x0AD1, // 0AD1..0ADF; UNKNOWN
5866 0x0AE0, // 0AE0..0AE3; GUJARATI
5867 0x0AE4, // 0AE4..0AE5; UNKNOWN
5868 0x0AE6, // 0AE6..0AF1; GUJARATI
5869 0x0AF2, // 0AF2..0AF8; UNKNOWN
5870 0x0AF9, // 0AF9..0AFF; GUJARATI
5871 0x0B00, // 0B00 ; UNKNOWN
5872 0x0B01, // 0B01..0B03; ORIYA
5873 0x0B04, // 0B04 ; UNKNOWN
5874 0x0B05, // 0B05..0B0C; ORIYA
5875 0x0B0D, // 0B0D..0B0E; UNKNOWN
5876 0x0B0F, // 0B0F..0B10; ORIYA
5877 0x0B11, // 0B11..0B12; UNKNOWN
5878 0x0B13, // 0B13..0B28; ORIYA
5879 0x0B29, // 0B29 ; UNKNOWN
5880 0x0B2A, // 0B2A..0B30; ORIYA
5881 0x0B31, // 0B31 ; UNKNOWN
5882 0x0B32, // 0B32..0B33; ORIYA
5883 0x0B34, // 0B34 ; UNKNOWN
5884 0x0B35, // 0B35..0B39; ORIYA
5885 0x0B3A, // 0B3A..0B3B; UNKNOWN
5886 0x0B3C, // 0B3C..0B44; ORIYA
5887 0x0B45, // 0B45..0B46; UNKNOWN
5888 0x0B47, // 0B47..0B48; ORIYA
5889 0x0B49, // 0B49..0B4A; UNKNOWN
5890 0x0B4B, // 0B4B..0B4D; ORIYA
5891 0x0B4E, // 0B4E..0B54; UNKNOWN
5892 0x0B55, // 0B55..0B57; ORIYA
5893 0x0B58, // 0B58..0B5B; UNKNOWN
5894 0x0B5C, // 0B5C..0B5D; ORIYA
5895 0x0B5E, // 0B5E ; UNKNOWN
5896 0x0B5F, // 0B5F..0B63; ORIYA
5897 0x0B64, // 0B64..0B65; UNKNOWN
5898 0x0B66, // 0B66..0B77; ORIYA
5899 0x0B78, // 0B78..0B81; UNKNOWN
5900 0x0B82, // 0B82..0B83; TAMIL
5901 0x0B84, // 0B84 ; UNKNOWN
5902 0x0B85, // 0B85..0B8A; TAMIL
5903 0x0B8B, // 0B8B..0B8D; UNKNOWN
5904 0x0B8E, // 0B8E..0B90; TAMIL
5905 0x0B91, // 0B91 ; UNKNOWN
5906 0x0B92, // 0B92..0B95; TAMIL
5907 0x0B96, // 0B96..0B98; UNKNOWN
5908 0x0B99, // 0B99..0B9A; TAMIL
5909 0x0B9B, // 0B9B ; UNKNOWN
5910 0x0B9C, // 0B9C ; TAMIL
5911 0x0B9D, // 0B9D ; UNKNOWN
5912 0x0B9E, // 0B9E..0B9F; TAMIL
5913 0x0BA0, // 0BA0..0BA2; UNKNOWN
5914 0x0BA3, // 0BA3..0BA4; TAMIL
5915 0x0BA5, // 0BA5..0BA7; UNKNOWN
5916 0x0BA8, // 0BA8..0BAA; TAMIL
5917 0x0BAB, // 0BAB..0BAD; UNKNOWN
5918 0x0BAE, // 0BAE..0BB9; TAMIL
5919 0x0BBA, // 0BBA..0BBD; UNKNOWN
5920 0x0BBE, // 0BBE..0BC2; TAMIL
5921 0x0BC3, // 0BC3..0BC5; UNKNOWN
5922 0x0BC6, // 0BC6..0BC8; TAMIL
5923 0x0BC9, // 0BC9 ; UNKNOWN
5924 0x0BCA, // 0BCA..0BCD; TAMIL
5925 0x0BCE, // 0BCE..0BCF; UNKNOWN
5926 0x0BD0, // 0BD0 ; TAMIL
5927 0x0BD1, // 0BD1..0BD6; UNKNOWN
5928 0x0BD7, // 0BD7 ; TAMIL
5929 0x0BD8, // 0BD8..0BE5; UNKNOWN
5930 0x0BE6, // 0BE6..0BFA; TAMIL
5931 0x0BFB, // 0BFB..0BFF; UNKNOWN
5932 0x0C00, // 0C00..0C0C; TELUGU
5933 0x0C0D, // 0C0D ; UNKNOWN
5934 0x0C0E, // 0C0E..0C10; TELUGU
5935 0x0C11, // 0C11 ; UNKNOWN
5936 0x0C12, // 0C12..0C28; TELUGU
5937 0x0C29, // 0C29 ; UNKNOWN
5938 0x0C2A, // 0C2A..0C39; TELUGU
5939 0x0C3A, // 0C3A..0C3B; UNKNOWN
5940 0x0C3C, // 0C3C..0C44; TELUGU
5941 0x0C45, // 0C45 ; UNKNOWN
5942 0x0C46, // 0C46..0C48; TELUGU
5943 0x0C49, // 0C49 ; UNKNOWN
5944 0x0C4A, // 0C4A..0C4D; TELUGU
5945 0x0C4E, // 0C4E..0C54; UNKNOWN
5946 0x0C55, // 0C55..0C56; TELUGU
5947 0x0C57, // 0C57 ; UNKNOWN
5948 0x0C58, // 0C58..0C5A; TELUGU
5949 0x0C5B, // 0C5B ; UNKNOWN
5950 0x0C5C, // 0C5C..0C5D; TELUGU
5951 0x0C5E, // 0C5E..0C5F; UNKNOWN
5952 0x0C60, // 0C60..0C63; TELUGU
5953 0x0C64, // 0C64..0C65; UNKNOWN
5954 0x0C66, // 0C66..0C6F; TELUGU
5955 0x0C70, // 0C70..0C76; UNKNOWN
5956 0x0C77, // 0C77..0C7F; TELUGU
5957 0x0C80, // 0C80..0C8C; KANNADA
5958 0x0C8D, // 0C8D ; UNKNOWN
5959 0x0C8E, // 0C8E..0C90; KANNADA
5960 0x0C91, // 0C91 ; UNKNOWN
5961 0x0C92, // 0C92..0CA8; KANNADA
5962 0x0CA9, // 0CA9 ; UNKNOWN
5963 0x0CAA, // 0CAA..0CB3; KANNADA
5964 0x0CB4, // 0CB4 ; UNKNOWN
5965 0x0CB5, // 0CB5..0CB9; KANNADA
5966 0x0CBA, // 0CBA..0CBB; UNKNOWN
5967 0x0CBC, // 0CBC..0CC4; KANNADA
5968 0x0CC5, // 0CC5 ; UNKNOWN
5969 0x0CC6, // 0CC6..0CC8; KANNADA
5970 0x0CC9, // 0CC9 ; UNKNOWN
5971 0x0CCA, // 0CCA..0CCD; KANNADA
5972 0x0CCE, // 0CCE..0CD4; UNKNOWN
5973 0x0CD5, // 0CD5..0CD6; KANNADA
5974 0x0CD7, // 0CD7..0CDB; UNKNOWN
5975 0x0CDC, // 0CDC..0CDE; KANNADA
5976 0x0CDF, // 0CDF ; UNKNOWN
5977 0x0CE0, // 0CE0..0CE3; KANNADA
5978 0x0CE4, // 0CE4..0CE5; UNKNOWN
5979 0x0CE6, // 0CE6..0CEF; KANNADA
5980 0x0CF0, // 0CF0 ; UNKNOWN
5981 0x0CF1, // 0CF1..0CF3; KANNADA
5982 0x0CF4, // 0CF4..0CFF; UNKNOWN
5983 0x0D00, // 0D00..0D0C; MALAYALAM
5984 0x0D0D, // 0D0D ; UNKNOWN
5985 0x0D0E, // 0D0E..0D10; MALAYALAM
5986 0x0D11, // 0D11 ; UNKNOWN
5987 0x0D12, // 0D12..0D44; MALAYALAM
5988 0x0D45, // 0D45 ; UNKNOWN
5989 0x0D46, // 0D46..0D48; MALAYALAM
5990 0x0D49, // 0D49 ; UNKNOWN
5991 0x0D4A, // 0D4A..0D4F; MALAYALAM
5992 0x0D50, // 0D50..0D53; UNKNOWN
5993 0x0D54, // 0D54..0D63; MALAYALAM
5994 0x0D64, // 0D64..0D65; UNKNOWN
5995 0x0D66, // 0D66..0D7F; MALAYALAM
5996 0x0D80, // 0D80 ; UNKNOWN
5997 0x0D81, // 0D81..0D83; SINHALA
5998 0x0D84, // 0D84 ; UNKNOWN
5999 0x0D85, // 0D85..0D96; SINHALA
6000 0x0D97, // 0D97..0D99; UNKNOWN
6001 0x0D9A, // 0D9A..0DB1; SINHALA
6002 0x0DB2, // 0DB2 ; UNKNOWN
6003 0x0DB3, // 0DB3..0DBB; SINHALA
6004 0x0DBC, // 0DBC ; UNKNOWN
6005 0x0DBD, // 0DBD ; SINHALA
6006 0x0DBE, // 0DBE..0DBF; UNKNOWN
6007 0x0DC0, // 0DC0..0DC6; SINHALA
6008 0x0DC7, // 0DC7..0DC9; UNKNOWN
6009 0x0DCA, // 0DCA ; SINHALA
6010 0x0DCB, // 0DCB..0DCE; UNKNOWN
6011 0x0DCF, // 0DCF..0DD4; SINHALA
6012 0x0DD5, // 0DD5 ; UNKNOWN
6013 0x0DD6, // 0DD6 ; SINHALA
6014 0x0DD7, // 0DD7 ; UNKNOWN
6015 0x0DD8, // 0DD8..0DDF; SINHALA
6016 0x0DE0, // 0DE0..0DE5; UNKNOWN
6017 0x0DE6, // 0DE6..0DEF; SINHALA
6018 0x0DF0, // 0DF0..0DF1; UNKNOWN
6019 0x0DF2, // 0DF2..0DF4; SINHALA
6020 0x0DF5, // 0DF5..0E00; UNKNOWN
6021 0x0E01, // 0E01..0E3A; THAI
6022 0x0E3B, // 0E3B..0E3E; UNKNOWN
6023 0x0E3F, // 0E3F ; COMMON
6024 0x0E40, // 0E40..0E5B; THAI
6025 0x0E5C, // 0E5C..0E80; UNKNOWN
6026 0x0E81, // 0E81..0E82; LAO
6027 0x0E83, // 0E83 ; UNKNOWN
6028 0x0E84, // 0E84 ; LAO
6029 0x0E85, // 0E85 ; UNKNOWN
6030 0x0E86, // 0E86..0E8A; LAO
6031 0x0E8B, // 0E8B ; UNKNOWN
6032 0x0E8C, // 0E8C..0EA3; LAO
6033 0x0EA4, // 0EA4 ; UNKNOWN
6034 0x0EA5, // 0EA5 ; LAO
6035 0x0EA6, // 0EA6 ; UNKNOWN
6036 0x0EA7, // 0EA7..0EBD; LAO
6037 0x0EBE, // 0EBE..0EBF; UNKNOWN
6038 0x0EC0, // 0EC0..0EC4; LAO
6039 0x0EC5, // 0EC5 ; UNKNOWN
6040 0x0EC6, // 0EC6 ; LAO
6041 0x0EC7, // 0EC7 ; UNKNOWN
6042 0x0EC8, // 0EC8..0ECE; LAO
6043 0x0ECF, // 0ECF ; UNKNOWN
6044 0x0ED0, // 0ED0..0ED9; LAO
6045 0x0EDA, // 0EDA..0EDB; UNKNOWN
6046 0x0EDC, // 0EDC..0EDF; LAO
6047 0x0EE0, // 0EE0..0EFF; UNKNOWN
6048 0x0F00, // 0F00..0F47; TIBETAN
6049 0x0F48, // 0F48 ; UNKNOWN
6050 0x0F49, // 0F49..0F6C; TIBETAN
6051 0x0F6D, // 0F6D..0F70; UNKNOWN
6052 0x0F71, // 0F71..0F97; TIBETAN
6053 0x0F98, // 0F98 ; UNKNOWN
6054 0x0F99, // 0F99..0FBC; TIBETAN
6055 0x0FBD, // 0FBD ; UNKNOWN
6056 0x0FBE, // 0FBE..0FCC; TIBETAN
6057 0x0FCD, // 0FCD ; UNKNOWN
6058 0x0FCE, // 0FCE..0FD4; TIBETAN
6059 0x0FD5, // 0FD5..0FD8; COMMON
6060 0x0FD9, // 0FD9..0FDA; TIBETAN
6061 0x0FDB, // 0FDB..0FFF; UNKNOWN
6062 0x1000, // 1000..109F; MYANMAR
6063 0x10A0, // 10A0..10C5; GEORGIAN
6064 0x10C6, // 10C6 ; UNKNOWN
6065 0x10C7, // 10C7 ; GEORGIAN
6066 0x10C8, // 10C8..10CC; UNKNOWN
6067 0x10CD, // 10CD ; GEORGIAN
6068 0x10CE, // 10CE..10CF; UNKNOWN
6069 0x10D0, // 10D0..10FA; GEORGIAN
6070 0x10FB, // 10FB ; COMMON
6071 0x10FC, // 10FC..10FF; GEORGIAN
6072 0x1100, // 1100..11FF; HANGUL
6073 0x1200, // 1200..1248; ETHIOPIC
6074 0x1249, // 1249 ; UNKNOWN
6075 0x124A, // 124A..124D; ETHIOPIC
6076 0x124E, // 124E..124F; UNKNOWN
6077 0x1250, // 1250..1256; ETHIOPIC
6078 0x1257, // 1257 ; UNKNOWN
6079 0x1258, // 1258 ; ETHIOPIC
6080 0x1259, // 1259 ; UNKNOWN
6081 0x125A, // 125A..125D; ETHIOPIC
6082 0x125E, // 125E..125F; UNKNOWN
6083 0x1260, // 1260..1288; ETHIOPIC
6084 0x1289, // 1289 ; UNKNOWN
6085 0x128A, // 128A..128D; ETHIOPIC
6086 0x128E, // 128E..128F; UNKNOWN
6087 0x1290, // 1290..12B0; ETHIOPIC
6088 0x12B1, // 12B1 ; UNKNOWN
6089 0x12B2, // 12B2..12B5; ETHIOPIC
6090 0x12B6, // 12B6..12B7; UNKNOWN
6091 0x12B8, // 12B8..12BE; ETHIOPIC
6092 0x12BF, // 12BF ; UNKNOWN
6093 0x12C0, // 12C0 ; ETHIOPIC
6094 0x12C1, // 12C1 ; UNKNOWN
6095 0x12C2, // 12C2..12C5; ETHIOPIC
6096 0x12C6, // 12C6..12C7; UNKNOWN
6097 0x12C8, // 12C8..12D6; ETHIOPIC
6098 0x12D7, // 12D7 ; UNKNOWN
6099 0x12D8, // 12D8..1310; ETHIOPIC
6100 0x1311, // 1311 ; UNKNOWN
6101 0x1312, // 1312..1315; ETHIOPIC
6102 0x1316, // 1316..1317; UNKNOWN
6103 0x1318, // 1318..135A; ETHIOPIC
6104 0x135B, // 135B..135C; UNKNOWN
6105 0x135D, // 135D..137C; ETHIOPIC
6106 0x137D, // 137D..137F; UNKNOWN
6107 0x1380, // 1380..1399; ETHIOPIC
6108 0x139A, // 139A..139F; UNKNOWN
6109 0x13A0, // 13A0..13F5; CHEROKEE
6110 0x13F6, // 13F6..13F7; UNKNOWN
6111 0x13F8, // 13F8..13FD; CHEROKEE
6112 0x13FE, // 13FE..13FF; UNKNOWN
6113 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
6114 0x1680, // 1680..169C; OGHAM
6115 0x169D, // 169D..169F; UNKNOWN
6116 0x16A0, // 16A0..16EA; RUNIC
6117 0x16EB, // 16EB..16ED; COMMON
6118 0x16EE, // 16EE..16F8; RUNIC
6119 0x16F9, // 16F9..16FF; UNKNOWN
6120 0x1700, // 1700..1715; TAGALOG
6121 0x1716, // 1716..171E; UNKNOWN
6122 0x171F, // 171F ; TAGALOG
6123 0x1720, // 1720..1734; HANUNOO
6124 0x1735, // 1735..1736; COMMON
6125 0x1737, // 1737..173F; UNKNOWN
6126 0x1740, // 1740..1753; BUHID
6127 0x1754, // 1754..175F; UNKNOWN
6128 0x1760, // 1760..176C; TAGBANWA
6129 0x176D, // 176D ; UNKNOWN
6130 0x176E, // 176E..1770; TAGBANWA
6131 0x1771, // 1771 ; UNKNOWN
6132 0x1772, // 1772..1773; TAGBANWA
6133 0x1774, // 1774..177F; UNKNOWN
6134 0x1780, // 1780..17DD; KHMER
6135 0x17DE, // 17DE..17DF; UNKNOWN
6136 0x17E0, // 17E0..17E9; KHMER
6137 0x17EA, // 17EA..17EF; UNKNOWN
6138 0x17F0, // 17F0..17F9; KHMER
6139 0x17FA, // 17FA..17FF; UNKNOWN
6140 0x1800, // 1800..1801; MONGOLIAN
6141 0x1802, // 1802..1803; COMMON
6142 0x1804, // 1804 ; MONGOLIAN
6143 0x1805, // 1805 ; COMMON
6144 0x1806, // 1806..1819; MONGOLIAN
6145 0x181A, // 181A..181F; UNKNOWN
6146 0x1820, // 1820..1878; MONGOLIAN
6147 0x1879, // 1879..187F; UNKNOWN
6148 0x1880, // 1880..18AA; MONGOLIAN
6149 0x18AB, // 18AB..18AF; UNKNOWN
6150 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
6151 0x18F6, // 18F6..18FF; UNKNOWN
6152 0x1900, // 1900..191E; LIMBU
6153 0x191F, // 191F ; UNKNOWN
6154 0x1920, // 1920..192B; LIMBU
6155 0x192C, // 192C..192F; UNKNOWN
6156 0x1930, // 1930..193B; LIMBU
6157 0x193C, // 193C..193F; UNKNOWN
6158 0x1940, // 1940 ; LIMBU
6159 0x1941, // 1941..1943; UNKNOWN
6160 0x1944, // 1944..194F; LIMBU
6161 0x1950, // 1950..196D; TAI_LE
6162 0x196E, // 196E..196F; UNKNOWN
6163 0x1970, // 1970..1974; TAI_LE
6164 0x1975, // 1975..197F; UNKNOWN
6165 0x1980, // 1980..19AB; NEW_TAI_LUE
6166 0x19AC, // 19AC..19AF; UNKNOWN
6167 0x19B0, // 19B0..19C9; NEW_TAI_LUE
6168 0x19CA, // 19CA..19CF; UNKNOWN
6169 0x19D0, // 19D0..19DA; NEW_TAI_LUE
6170 0x19DB, // 19DB..19DD; UNKNOWN
6171 0x19DE, // 19DE..19DF; NEW_TAI_LUE
6172 0x19E0, // 19E0..19FF; KHMER
6173 0x1A00, // 1A00..1A1B; BUGINESE
6174 0x1A1C, // 1A1C..1A1D; UNKNOWN
6175 0x1A1E, // 1A1E..1A1F; BUGINESE
6176 0x1A20, // 1A20..1A5E; TAI_THAM
6177 0x1A5F, // 1A5F ; UNKNOWN
6178 0x1A60, // 1A60..1A7C; TAI_THAM
6179 0x1A7D, // 1A7D..1A7E; UNKNOWN
6180 0x1A7F, // 1A7F..1A89; TAI_THAM
6181 0x1A8A, // 1A8A..1A8F; UNKNOWN
6182 0x1A90, // 1A90..1A99; TAI_THAM
6183 0x1A9A, // 1A9A..1A9F; UNKNOWN
6184 0x1AA0, // 1AA0..1AAD; TAI_THAM
6185 0x1AAE, // 1AAE..1AAF; UNKNOWN
6186 0x1AB0, // 1AB0..1ADD; INHERITED
6187 0x1ADE, // 1ADE..1ADF; UNKNOWN
6188 0x1AE0, // 1AE0..1AEB; INHERITED
6189 0x1AEC, // 1AEC..1AFF; UNKNOWN
6190 0x1B00, // 1B00..1B4C; BALINESE
6191 0x1B4D, // 1B4D ; UNKNOWN
6192 0x1B4E, // 1B4E..1B7F; BALINESE
6193 0x1B80, // 1B80..1BBF; SUNDANESE
6194 0x1BC0, // 1BC0..1BF3; BATAK
6195 0x1BF4, // 1BF4..1BFB; UNKNOWN
6196 0x1BFC, // 1BFC..1BFF; BATAK
6197 0x1C00, // 1C00..1C37; LEPCHA
6198 0x1C38, // 1C38..1C3A; UNKNOWN
6199 0x1C3B, // 1C3B..1C49; LEPCHA
6200 0x1C4A, // 1C4A..1C4C; UNKNOWN
6201 0x1C4D, // 1C4D..1C4F; LEPCHA
6202 0x1C50, // 1C50..1C7F; OL_CHIKI
6203 0x1C80, // 1C80..1C8A; CYRILLIC
6204 0x1C8B, // 1C8B..1C8F; UNKNOWN
6205 0x1C90, // 1C90..1CBA; GEORGIAN
6206 0x1CBB, // 1CBB..1CBC; UNKNOWN
6207 0x1CBD, // 1CBD..1CBF; GEORGIAN
6208 0x1CC0, // 1CC0..1CC7; SUNDANESE
6209 0x1CC8, // 1CC8..1CCF; UNKNOWN
6210 0x1CD0, // 1CD0..1CD2; INHERITED
6211 0x1CD3, // 1CD3 ; COMMON
6212 0x1CD4, // 1CD4..1CE0; INHERITED
6213 0x1CE1, // 1CE1 ; COMMON
6214 0x1CE2, // 1CE2..1CE8; INHERITED
6215 0x1CE9, // 1CE9..1CEC; COMMON
6216 0x1CED, // 1CED ; INHERITED
6217 0x1CEE, // 1CEE..1CF3; COMMON
6218 0x1CF4, // 1CF4 ; INHERITED
6219 0x1CF5, // 1CF5..1CF7; COMMON
6220 0x1CF8, // 1CF8..1CF9; INHERITED
6221 0x1CFA, // 1CFA ; COMMON
6222 0x1CFB, // 1CFB..1CFF; UNKNOWN
6223 0x1D00, // 1D00..1D25; LATIN
6224 0x1D26, // 1D26..1D2A; GREEK
6225 0x1D2B, // 1D2B ; CYRILLIC
6226 0x1D2C, // 1D2C..1D5C; LATIN
6227 0x1D5D, // 1D5D..1D61; GREEK
6228 0x1D62, // 1D62..1D65; LATIN
6229 0x1D66, // 1D66..1D6A; GREEK
6230 0x1D6B, // 1D6B..1D77; LATIN
6231 0x1D78, // 1D78 ; CYRILLIC
6232 0x1D79, // 1D79..1DBE; LATIN
6233 0x1DBF, // 1DBF ; GREEK
6234 0x1DC0, // 1DC0..1DFF; INHERITED
6235 0x1E00, // 1E00..1EFF; LATIN
6236 0x1F00, // 1F00..1F15; GREEK
6237 0x1F16, // 1F16..1F17; UNKNOWN
6238 0x1F18, // 1F18..1F1D; GREEK
6239 0x1F1E, // 1F1E..1F1F; UNKNOWN
6240 0x1F20, // 1F20..1F45; GREEK
6241 0x1F46, // 1F46..1F47; UNKNOWN
6242 0x1F48, // 1F48..1F4D; GREEK
6243 0x1F4E, // 1F4E..1F4F; UNKNOWN
6244 0x1F50, // 1F50..1F57; GREEK
6245 0x1F58, // 1F58 ; UNKNOWN
6246 0x1F59, // 1F59 ; GREEK
6247 0x1F5A, // 1F5A ; UNKNOWN
6248 0x1F5B, // 1F5B ; GREEK
6249 0x1F5C, // 1F5C ; UNKNOWN
6250 0x1F5D, // 1F5D ; GREEK
6251 0x1F5E, // 1F5E ; UNKNOWN
6252 0x1F5F, // 1F5F..1F7D; GREEK
6253 0x1F7E, // 1F7E..1F7F; UNKNOWN
6254 0x1F80, // 1F80..1FB4; GREEK
6255 0x1FB5, // 1FB5 ; UNKNOWN
6256 0x1FB6, // 1FB6..1FC4; GREEK
6257 0x1FC5, // 1FC5 ; UNKNOWN
6258 0x1FC6, // 1FC6..1FD3; GREEK
6259 0x1FD4, // 1FD4..1FD5; UNKNOWN
6260 0x1FD6, // 1FD6..1FDB; GREEK
6261 0x1FDC, // 1FDC ; UNKNOWN
6262 0x1FDD, // 1FDD..1FEF; GREEK
6263 0x1FF0, // 1FF0..1FF1; UNKNOWN
6264 0x1FF2, // 1FF2..1FF4; GREEK
6265 0x1FF5, // 1FF5 ; UNKNOWN
6266 0x1FF6, // 1FF6..1FFE; GREEK
6267 0x1FFF, // 1FFF ; UNKNOWN
6268 0x2000, // 2000..200B; COMMON
6269 0x200C, // 200C..200D; INHERITED
6270 0x200E, // 200E..2064; COMMON
6271 0x2065, // 2065 ; UNKNOWN
6272 0x2066, // 2066..2070; COMMON
6273 0x2071, // 2071 ; LATIN
6274 0x2072, // 2072..2073; UNKNOWN
6275 0x2074, // 2074..207E; COMMON
6276 0x207F, // 207F ; LATIN
6277 0x2080, // 2080..208E; COMMON
6278 0x208F, // 208F ; UNKNOWN
6279 0x2090, // 2090..209C; LATIN
6280 0x209D, // 209D..209F; UNKNOWN
6281 0x20A0, // 20A0..20C1; COMMON
6282 0x20C2, // 20C2..20CF; UNKNOWN
6283 0x20D0, // 20D0..20F0; INHERITED
6284 0x20F1, // 20F1..20FF; UNKNOWN
6285 0x2100, // 2100..2125; COMMON
6286 0x2126, // 2126 ; GREEK
6287 0x2127, // 2127..2129; COMMON
6288 0x212A, // 212A..212B; LATIN
6289 0x212C, // 212C..2131; COMMON
6290 0x2132, // 2132 ; LATIN
6291 0x2133, // 2133..214D; COMMON
6292 0x214E, // 214E ; LATIN
6293 0x214F, // 214F..215F; COMMON
6294 0x2160, // 2160..2188; LATIN
6295 0x2189, // 2189..218B; COMMON
6296 0x218C, // 218C..218F; UNKNOWN
6297 0x2190, // 2190..2429; COMMON
6298 0x242A, // 242A..243F; UNKNOWN
6299 0x2440, // 2440..244A; COMMON
6300 0x244B, // 244B..245F; UNKNOWN
6301 0x2460, // 2460..27FF; COMMON
6302 0x2800, // 2800..28FF; BRAILLE
6303 0x2900, // 2900..2B73; COMMON
6304 0x2B74, // 2B74..2B75; UNKNOWN
6305 0x2B76, // 2B76..2BFF; COMMON
6306 0x2C00, // 2C00..2C5F; GLAGOLITIC
6307 0x2C60, // 2C60..2C7F; LATIN
6308 0x2C80, // 2C80..2CF3; COPTIC
6309 0x2CF4, // 2CF4..2CF8; UNKNOWN
6310 0x2CF9, // 2CF9..2CFF; COPTIC
6311 0x2D00, // 2D00..2D25; GEORGIAN
6312 0x2D26, // 2D26 ; UNKNOWN
6313 0x2D27, // 2D27 ; GEORGIAN
6314 0x2D28, // 2D28..2D2C; UNKNOWN
6315 0x2D2D, // 2D2D ; GEORGIAN
6316 0x2D2E, // 2D2E..2D2F; UNKNOWN
6317 0x2D30, // 2D30..2D67; TIFINAGH
6318 0x2D68, // 2D68..2D6E; UNKNOWN
6319 0x2D6F, // 2D6F..2D70; TIFINAGH
6320 0x2D71, // 2D71..2D7E; UNKNOWN
6321 0x2D7F, // 2D7F ; TIFINAGH
6322 0x2D80, // 2D80..2D96; ETHIOPIC
6323 0x2D97, // 2D97..2D9F; UNKNOWN
6324 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6325 0x2DA7, // 2DA7 ; UNKNOWN
6326 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6327 0x2DAF, // 2DAF ; UNKNOWN
6328 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6329 0x2DB7, // 2DB7 ; UNKNOWN
6330 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6331 0x2DBF, // 2DBF ; UNKNOWN
6332 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6333 0x2DC7, // 2DC7 ; UNKNOWN
6334 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6335 0x2DCF, // 2DCF ; UNKNOWN
6336 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6337 0x2DD7, // 2DD7 ; UNKNOWN
6338 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6339 0x2DDF, // 2DDF ; UNKNOWN
6340 0x2DE0, // 2DE0..2DFF; CYRILLIC
6341 0x2E00, // 2E00..2E5D; COMMON
6342 0x2E5E, // 2E5E..2E7F; UNKNOWN
6343 0x2E80, // 2E80..2E99; HAN
6344 0x2E9A, // 2E9A ; UNKNOWN
6345 0x2E9B, // 2E9B..2EF3; HAN
6346 0x2EF4, // 2EF4..2EFF; UNKNOWN
6347 0x2F00, // 2F00..2FD5; HAN
6348 0x2FD6, // 2FD6..2FEF; UNKNOWN
6349 0x2FF0, // 2FF0..3004; COMMON
6350 0x3005, // 3005 ; HAN
6351 0x3006, // 3006 ; COMMON
6352 0x3007, // 3007 ; HAN
6353 0x3008, // 3008..3020; COMMON
6354 0x3021, // 3021..3029; HAN
6355 0x302A, // 302A..302D; INHERITED
6356 0x302E, // 302E..302F; HANGUL
6357 0x3030, // 3030..3037; COMMON
6358 0x3038, // 3038..303B; HAN
6359 0x303C, // 303C..303F; COMMON
6360 0x3040, // 3040 ; UNKNOWN
6361 0x3041, // 3041..3096; HIRAGANA
6362 0x3097, // 3097..3098; UNKNOWN
6363 0x3099, // 3099..309A; INHERITED
6364 0x309B, // 309B..309C; COMMON
6365 0x309D, // 309D..309F; HIRAGANA
6366 0x30A0, // 30A0 ; COMMON
6367 0x30A1, // 30A1..30FA; KATAKANA
6368 0x30FB, // 30FB..30FC; COMMON
6369 0x30FD, // 30FD..30FF; KATAKANA
6370 0x3100, // 3100..3104; UNKNOWN
6371 0x3105, // 3105..312F; BOPOMOFO
6372 0x3130, // 3130 ; UNKNOWN
6373 0x3131, // 3131..318E; HANGUL
6374 0x318F, // 318F ; UNKNOWN
6375 0x3190, // 3190..319F; COMMON
6376 0x31A0, // 31A0..31BF; BOPOMOFO
6377 0x31C0, // 31C0..31E5; COMMON
6378 0x31E6, // 31E6..31EE; UNKNOWN
6379 0x31EF, // 31EF ; COMMON
6380 0x31F0, // 31F0..31FF; KATAKANA
6381 0x3200, // 3200..321E; HANGUL
6382 0x321F, // 321F ; UNKNOWN
6383 0x3220, // 3220..325F; COMMON
6384 0x3260, // 3260..327E; HANGUL
6385 0x327F, // 327F..32CF; COMMON
6386 0x32D0, // 32D0..32FE; KATAKANA
6387 0x32FF, // 32FF ; COMMON
6388 0x3300, // 3300..3357; KATAKANA
6389 0x3358, // 3358..33FF; COMMON
6390 0x3400, // 3400..4DBF; HAN
6391 0x4DC0, // 4DC0..4DFF; COMMON
6392 0x4E00, // 4E00..9FFF; HAN
6393 0xA000, // A000..A48C; YI
6394 0xA48D, // A48D..A48F; UNKNOWN
6395 0xA490, // A490..A4C6; YI
6396 0xA4C7, // A4C7..A4CF; UNKNOWN
6397 0xA4D0, // A4D0..A4FF; LISU
6398 0xA500, // A500..A62B; VAI
6399 0xA62C, // A62C..A63F; UNKNOWN
6400 0xA640, // A640..A69F; CYRILLIC
6401 0xA6A0, // A6A0..A6F7; BAMUM
6402 0xA6F8, // A6F8..A6FF; UNKNOWN
6403 0xA700, // A700..A721; COMMON
6404 0xA722, // A722..A787; LATIN
6405 0xA788, // A788..A78A; COMMON
6406 0xA78B, // A78B..A7DC; LATIN
6407 0xA7DD, // A7DD..A7F0; UNKNOWN
6408 0xA7F1, // A7F1..A7FF; LATIN
6409 0xA800, // A800..A82C; SYLOTI_NAGRI
6410 0xA82D, // A82D..A82F; UNKNOWN
6411 0xA830, // A830..A839; COMMON
6412 0xA83A, // A83A..A83F; UNKNOWN
6413 0xA840, // A840..A877; PHAGS_PA
6414 0xA878, // A878..A87F; UNKNOWN
6415 0xA880, // A880..A8C5; SAURASHTRA
6416 0xA8C6, // A8C6..A8CD; UNKNOWN
6417 0xA8CE, // A8CE..A8D9; SAURASHTRA
6418 0xA8DA, // A8DA..A8DF; UNKNOWN
6419 0xA8E0, // A8E0..A8FF; DEVANAGARI
6420 0xA900, // A900..A92D; KAYAH_LI
6421 0xA92E, // A92E ; COMMON
6422 0xA92F, // A92F ; KAYAH_LI
6423 0xA930, // A930..A953; REJANG
6424 0xA954, // A954..A95E; UNKNOWN
6425 0xA95F, // A95F ; REJANG
6426 0xA960, // A960..A97C; HANGUL
6427 0xA97D, // A97D..A97F; UNKNOWN
6428 0xA980, // A980..A9CD; JAVANESE
6429 0xA9CE, // A9CE ; UNKNOWN
6430 0xA9CF, // A9CF ; COMMON
6431 0xA9D0, // A9D0..A9D9; JAVANESE
6432 0xA9DA, // A9DA..A9DD; UNKNOWN
6433 0xA9DE, // A9DE..A9DF; JAVANESE
6434 0xA9E0, // A9E0..A9FE; MYANMAR
6435 0xA9FF, // A9FF ; UNKNOWN
6436 0xAA00, // AA00..AA36; CHAM
6437 0xAA37, // AA37..AA3F; UNKNOWN
6438 0xAA40, // AA40..AA4D; CHAM
6439 0xAA4E, // AA4E..AA4F; UNKNOWN
6440 0xAA50, // AA50..AA59; CHAM
6441 0xAA5A, // AA5A..AA5B; UNKNOWN
6442 0xAA5C, // AA5C..AA5F; CHAM
6443 0xAA60, // AA60..AA7F; MYANMAR
6444 0xAA80, // AA80..AAC2; TAI_VIET
6445 0xAAC3, // AAC3..AADA; UNKNOWN
6446 0xAADB, // AADB..AADF; TAI_VIET
6447 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6448 0xAAF7, // AAF7..AB00; UNKNOWN
6449 0xAB01, // AB01..AB06; ETHIOPIC
6450 0xAB07, // AB07..AB08; UNKNOWN
6451 0xAB09, // AB09..AB0E; ETHIOPIC
6452 0xAB0F, // AB0F..AB10; UNKNOWN
6453 0xAB11, // AB11..AB16; ETHIOPIC
6454 0xAB17, // AB17..AB1F; UNKNOWN
6455 0xAB20, // AB20..AB26; ETHIOPIC
6456 0xAB27, // AB27 ; UNKNOWN
6457 0xAB28, // AB28..AB2E; ETHIOPIC
6458 0xAB2F, // AB2F ; UNKNOWN
6459 0xAB30, // AB30..AB5A; LATIN
6460 0xAB5B, // AB5B ; COMMON
6461 0xAB5C, // AB5C..AB64; LATIN
6462 0xAB65, // AB65 ; GREEK
6463 0xAB66, // AB66..AB69; LATIN
6464 0xAB6A, // AB6A..AB6B; COMMON
6465 0xAB6C, // AB6C..AB6F; UNKNOWN
6466 0xAB70, // AB70..ABBF; CHEROKEE
6467 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6468 0xABEE, // ABEE..ABEF; UNKNOWN
6469 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6470 0xABFA, // ABFA..ABFF; UNKNOWN
6471 0xAC00, // AC00..D7A3; HANGUL
6472 0xD7A4, // D7A4..D7AF; UNKNOWN
6473 0xD7B0, // D7B0..D7C6; HANGUL
6474 0xD7C7, // D7C7..D7CA; UNKNOWN
6475 0xD7CB, // D7CB..D7FB; HANGUL
6476 0xD7FC, // D7FC..F8FF; UNKNOWN
6477 0xF900, // F900..FA6D; HAN
6478 0xFA6E, // FA6E..FA6F; UNKNOWN
6479 0xFA70, // FA70..FAD9; HAN
6480 0xFADA, // FADA..FAFF; UNKNOWN
6481 0xFB00, // FB00..FB06; LATIN
6482 0xFB07, // FB07..FB12; UNKNOWN
6483 0xFB13, // FB13..FB17; ARMENIAN
6484 0xFB18, // FB18..FB1C; UNKNOWN
6485 0xFB1D, // FB1D..FB36; HEBREW
6486 0xFB37, // FB37 ; UNKNOWN
6487 0xFB38, // FB38..FB3C; HEBREW
6488 0xFB3D, // FB3D ; UNKNOWN
6489 0xFB3E, // FB3E ; HEBREW
6490 0xFB3F, // FB3F ; UNKNOWN
6491 0xFB40, // FB40..FB41; HEBREW
6492 0xFB42, // FB42 ; UNKNOWN
6493 0xFB43, // FB43..FB44; HEBREW
6494 0xFB45, // FB45 ; UNKNOWN
6495 0xFB46, // FB46..FB4F; HEBREW
6496 0xFB50, // FB50..FD3D; ARABIC
6497 0xFD3E, // FD3E..FD3F; COMMON
6498 0xFD40, // FD40..FDCF; ARABIC
6499 0xFDD0, // FDD0..FDEF; UNKNOWN
6500 0xFDF0, // FDF0..FDFF; ARABIC
6501 0xFE00, // FE00..FE0F; INHERITED
6502 0xFE10, // FE10..FE19; COMMON
6503 0xFE1A, // FE1A..FE1F; UNKNOWN
6504 0xFE20, // FE20..FE2D; INHERITED
6505 0xFE2E, // FE2E..FE2F; CYRILLIC
6506 0xFE30, // FE30..FE52; COMMON
6507 0xFE53, // FE53 ; UNKNOWN
6508 0xFE54, // FE54..FE66; COMMON
6509 0xFE67, // FE67 ; UNKNOWN
6510 0xFE68, // FE68..FE6B; COMMON
6511 0xFE6C, // FE6C..FE6F; UNKNOWN
6512 0xFE70, // FE70..FE74; ARABIC
6513 0xFE75, // FE75 ; UNKNOWN
6514 0xFE76, // FE76..FEFC; ARABIC
6515 0xFEFD, // FEFD..FEFE; UNKNOWN
6516 0xFEFF, // FEFF ; COMMON
6517 0xFF00, // FF00 ; UNKNOWN
6518 0xFF01, // FF01..FF20; COMMON
6519 0xFF21, // FF21..FF3A; LATIN
6520 0xFF3B, // FF3B..FF40; COMMON
6521 0xFF41, // FF41..FF5A; LATIN
6522 0xFF5B, // FF5B..FF65; COMMON
6523 0xFF66, // FF66..FF6F; KATAKANA
6524 0xFF70, // FF70 ; COMMON
6525 0xFF71, // FF71..FF9D; KATAKANA
6526 0xFF9E, // FF9E..FF9F; COMMON
6527 0xFFA0, // FFA0..FFBE; HANGUL
6528 0xFFBF, // FFBF..FFC1; UNKNOWN
6529 0xFFC2, // FFC2..FFC7; HANGUL
6530 0xFFC8, // FFC8..FFC9; UNKNOWN
6531 0xFFCA, // FFCA..FFCF; HANGUL
6532 0xFFD0, // FFD0..FFD1; UNKNOWN
6533 0xFFD2, // FFD2..FFD7; HANGUL
6534 0xFFD8, // FFD8..FFD9; UNKNOWN
6535 0xFFDA, // FFDA..FFDC; HANGUL
6536 0xFFDD, // FFDD..FFDF; UNKNOWN
6537 0xFFE0, // FFE0..FFE6; COMMON
6538 0xFFE7, // FFE7 ; UNKNOWN
6539 0xFFE8, // FFE8..FFEE; COMMON
6540 0xFFEF, // FFEF..FFF8; UNKNOWN
6541 0xFFF9, // FFF9..FFFD; COMMON
6542 0xFFFE, // FFFE..FFFF; UNKNOWN
6543 0x10000, // 10000..1000B; LINEAR_B
6544 0x1000C, // 1000C ; UNKNOWN
6545 0x1000D, // 1000D..10026; LINEAR_B
6546 0x10027, // 10027 ; UNKNOWN
6547 0x10028, // 10028..1003A; LINEAR_B
6548 0x1003B, // 1003B ; UNKNOWN
6549 0x1003C, // 1003C..1003D; LINEAR_B
6550 0x1003E, // 1003E ; UNKNOWN
6551 0x1003F, // 1003F..1004D; LINEAR_B
6552 0x1004E, // 1004E..1004F; UNKNOWN
6553 0x10050, // 10050..1005D; LINEAR_B
6554 0x1005E, // 1005E..1007F; UNKNOWN
6555 0x10080, // 10080..100FA; LINEAR_B
6556 0x100FB, // 100FB..100FF; UNKNOWN
6557 0x10100, // 10100..10102; COMMON
6558 0x10103, // 10103..10106; UNKNOWN
6559 0x10107, // 10107..10133; COMMON
6560 0x10134, // 10134..10136; UNKNOWN
6561 0x10137, // 10137..1013F; COMMON
6562 0x10140, // 10140..1018E; GREEK
6563 0x1018F, // 1018F ; UNKNOWN
6564 0x10190, // 10190..1019C; COMMON
6565 0x1019D, // 1019D..1019F; UNKNOWN
6566 0x101A0, // 101A0 ; GREEK
6567 0x101A1, // 101A1..101CF; UNKNOWN
6568 0x101D0, // 101D0..101FC; COMMON
6569 0x101FD, // 101FD ; INHERITED
6570 0x101FE, // 101FE..1027F; UNKNOWN
6571 0x10280, // 10280..1029C; LYCIAN
6572 0x1029D, // 1029D..1029F; UNKNOWN
6573 0x102A0, // 102A0..102D0; CARIAN
6574 0x102D1, // 102D1..102DF; UNKNOWN
6575 0x102E0, // 102E0 ; INHERITED
6576 0x102E1, // 102E1..102FB; COMMON
6577 0x102FC, // 102FC..102FF; UNKNOWN
6578 0x10300, // 10300..10323; OLD_ITALIC
6579 0x10324, // 10324..1032C; UNKNOWN
6580 0x1032D, // 1032D..1032F; OLD_ITALIC
6581 0x10330, // 10330..1034A; GOTHIC
6582 0x1034B, // 1034B..1034F; UNKNOWN
6583 0x10350, // 10350..1037A; OLD_PERMIC
6584 0x1037B, // 1037B..1037F; UNKNOWN
6585 0x10380, // 10380..1039D; UGARITIC
6586 0x1039E, // 1039E ; UNKNOWN
6587 0x1039F, // 1039F ; UGARITIC
6588 0x103A0, // 103A0..103C3; OLD_PERSIAN
6589 0x103C4, // 103C4..103C7; UNKNOWN
6590 0x103C8, // 103C8..103D5; OLD_PERSIAN
6591 0x103D6, // 103D6..103FF; UNKNOWN
6592 0x10400, // 10400..1044F; DESERET
6593 0x10450, // 10450..1047F; SHAVIAN
6594 0x10480, // 10480..1049D; OSMANYA
6595 0x1049E, // 1049E..1049F; UNKNOWN
6596 0x104A0, // 104A0..104A9; OSMANYA
6597 0x104AA, // 104AA..104AF; UNKNOWN
6598 0x104B0, // 104B0..104D3; OSAGE
6599 0x104D4, // 104D4..104D7; UNKNOWN
6600 0x104D8, // 104D8..104FB; OSAGE
6601 0x104FC, // 104FC..104FF; UNKNOWN
6602 0x10500, // 10500..10527; ELBASAN
6603 0x10528, // 10528..1052F; UNKNOWN
6604 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6605 0x10564, // 10564..1056E; UNKNOWN
6606 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6607 0x10570, // 10570..1057A; VITHKUQI
6608 0x1057B, // 1057B ; UNKNOWN
6609 0x1057C, // 1057C..1058A; VITHKUQI
6610 0x1058B, // 1058B ; UNKNOWN
6611 0x1058C, // 1058C..10592; VITHKUQI
6612 0x10593, // 10593 ; UNKNOWN
6613 0x10594, // 10594..10595; VITHKUQI
6614 0x10596, // 10596 ; UNKNOWN
6615 0x10597, // 10597..105A1; VITHKUQI
6616 0x105A2, // 105A2 ; UNKNOWN
6617 0x105A3, // 105A3..105B1; VITHKUQI
6618 0x105B2, // 105B2 ; UNKNOWN
6619 0x105B3, // 105B3..105B9; VITHKUQI
6620 0x105BA, // 105BA ; UNKNOWN
6621 0x105BB, // 105BB..105BC; VITHKUQI
6622 0x105BD, // 105BD..105BF; UNKNOWN
6623 0x105C0, // 105C0..105F3; TODHRI
6624 0x105F4, // 105F4..105FF; UNKNOWN
6625 0x10600, // 10600..10736; LINEAR_A
6626 0x10737, // 10737..1073F; UNKNOWN
6627 0x10740, // 10740..10755; LINEAR_A
6628 0x10756, // 10756..1075F; UNKNOWN
6629 0x10760, // 10760..10767; LINEAR_A
6630 0x10768, // 10768..1077F; UNKNOWN
6631 0x10780, // 10780..10785; LATIN
6632 0x10786, // 10786 ; UNKNOWN
6633 0x10787, // 10787..107B0; LATIN
6634 0x107B1, // 107B1 ; UNKNOWN
6635 0x107B2, // 107B2..107BA; LATIN
6636 0x107BB, // 107BB..107FF; UNKNOWN
6637 0x10800, // 10800..10805; CYPRIOT
6638 0x10806, // 10806..10807; UNKNOWN
6639 0x10808, // 10808 ; CYPRIOT
6640 0x10809, // 10809 ; UNKNOWN
6641 0x1080A, // 1080A..10835; CYPRIOT
6642 0x10836, // 10836 ; UNKNOWN
6643 0x10837, // 10837..10838; CYPRIOT
6644 0x10839, // 10839..1083B; UNKNOWN
6645 0x1083C, // 1083C ; CYPRIOT
6646 0x1083D, // 1083D..1083E; UNKNOWN
6647 0x1083F, // 1083F ; CYPRIOT
6648 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6649 0x10856, // 10856 ; UNKNOWN
6650 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6651 0x10860, // 10860..1087F; PALMYRENE
6652 0x10880, // 10880..1089E; NABATAEAN
6653 0x1089F, // 1089F..108A6; UNKNOWN
6654 0x108A7, // 108A7..108AF; NABATAEAN
6655 0x108B0, // 108B0..108DF; UNKNOWN
6656 0x108E0, // 108E0..108F2; HATRAN
6657 0x108F3, // 108F3 ; UNKNOWN
6658 0x108F4, // 108F4..108F5; HATRAN
6659 0x108F6, // 108F6..108FA; UNKNOWN
6660 0x108FB, // 108FB..108FF; HATRAN
6661 0x10900, // 10900..1091B; PHOENICIAN
6662 0x1091C, // 1091C..1091E; UNKNOWN
6663 0x1091F, // 1091F ; PHOENICIAN
6664 0x10920, // 10920..10939; LYDIAN
6665 0x1093A, // 1093A..1093E; UNKNOWN
6666 0x1093F, // 1093F ; LYDIAN
6667 0x10940, // 10940..10959; SIDETIC
6668 0x1095A, // 1095A..1097F; UNKNOWN
6669 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6670 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6671 0x109B8, // 109B8..109BB; UNKNOWN
6672 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6673 0x109D0, // 109D0..109D1; UNKNOWN
6674 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6675 0x10A00, // 10A00..10A03; KHAROSHTHI
6676 0x10A04, // 10A04 ; UNKNOWN
6677 0x10A05, // 10A05..10A06; KHAROSHTHI
6678 0x10A07, // 10A07..10A0B; UNKNOWN
6679 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6680 0x10A14, // 10A14 ; UNKNOWN
6681 0x10A15, // 10A15..10A17; KHAROSHTHI
6682 0x10A18, // 10A18 ; UNKNOWN
6683 0x10A19, // 10A19..10A35; KHAROSHTHI
6684 0x10A36, // 10A36..10A37; UNKNOWN
6685 0x10A38, // 10A38..10A3A; KHAROSHTHI
6686 0x10A3B, // 10A3B..10A3E; UNKNOWN
6687 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6688 0x10A49, // 10A49..10A4F; UNKNOWN
6689 0x10A50, // 10A50..10A58; KHAROSHTHI
6690 0x10A59, // 10A59..10A5F; UNKNOWN
6691 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6692 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6693 0x10AA0, // 10AA0..10ABF; UNKNOWN
6694 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6695 0x10AE7, // 10AE7..10AEA; UNKNOWN
6696 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6697 0x10AF7, // 10AF7..10AFF; UNKNOWN
6698 0x10B00, // 10B00..10B35; AVESTAN
6699 0x10B36, // 10B36..10B38; UNKNOWN
6700 0x10B39, // 10B39..10B3F; AVESTAN
6701 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6702 0x10B56, // 10B56..10B57; UNKNOWN
6703 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6704 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6705 0x10B73, // 10B73..10B77; UNKNOWN
6706 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6707 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6708 0x10B92, // 10B92..10B98; UNKNOWN
6709 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6710 0x10B9D, // 10B9D..10BA8; UNKNOWN
6711 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6712 0x10BB0, // 10BB0..10BFF; UNKNOWN
6713 0x10C00, // 10C00..10C48; OLD_TURKIC
6714 0x10C49, // 10C49..10C7F; UNKNOWN
6715 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6716 0x10CB3, // 10CB3..10CBF; UNKNOWN
6717 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6718 0x10CF3, // 10CF3..10CF9; UNKNOWN
6719 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6720 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6721 0x10D28, // 10D28..10D2F; UNKNOWN
6722 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6723 0x10D3A, // 10D3A..10D3F; UNKNOWN
6724 0x10D40, // 10D40..10D65; GARAY
6725 0x10D66, // 10D66..10D68; UNKNOWN
6726 0x10D69, // 10D69..10D85; GARAY
6727 0x10D86, // 10D86..10D8D; UNKNOWN
6728 0x10D8E, // 10D8E..10D8F; GARAY
6729 0x10D90, // 10D90..10E5F; UNKNOWN
6730 0x10E60, // 10E60..10E7E; ARABIC
6731 0x10E7F, // 10E7F ; UNKNOWN
6732 0x10E80, // 10E80..10EA9; YEZIDI
6733 0x10EAA, // 10EAA ; UNKNOWN
6734 0x10EAB, // 10EAB..10EAD; YEZIDI
6735 0x10EAE, // 10EAE..10EAF; UNKNOWN
6736 0x10EB0, // 10EB0..10EB1; YEZIDI
6737 0x10EB2, // 10EB2..10EC1; UNKNOWN
6738 0x10EC2, // 10EC2..10EC7; ARABIC
6739 0x10EC8, // 10EC8..10ECF; UNKNOWN
6740 0x10ED0, // 10ED0..10ED8; ARABIC
6741 0x10ED9, // 10ED9..10EF9; UNKNOWN
6742 0x10EFA, // 10EFA..10EFF; ARABIC
6743 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6744 0x10F28, // 10F28..10F2F; UNKNOWN
6745 0x10F30, // 10F30..10F59; SOGDIAN
6746 0x10F5A, // 10F5A..10F6F; UNKNOWN
6747 0x10F70, // 10F70..10F89; OLD_UYGHUR
6748 0x10F8A, // 10F8A..10FAF; UNKNOWN
6749 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6750 0x10FCC, // 10FCC..10FDF; UNKNOWN
6751 0x10FE0, // 10FE0..10FF6; ELYMAIC
6752 0x10FF7, // 10FF7..10FFF; UNKNOWN
6753 0x11000, // 11000..1104D; BRAHMI
6754 0x1104E, // 1104E..11051; UNKNOWN
6755 0x11052, // 11052..11075; BRAHMI
6756 0x11076, // 11076..1107E; UNKNOWN
6757 0x1107F, // 1107F ; BRAHMI
6758 0x11080, // 11080..110C2; KAITHI
6759 0x110C3, // 110C3..110CC; UNKNOWN
6760 0x110CD, // 110CD ; KAITHI
6761 0x110CE, // 110CE..110CF; UNKNOWN
6762 0x110D0, // 110D0..110E8; SORA_SOMPENG
6763 0x110E9, // 110E9..110EF; UNKNOWN
6764 0x110F0, // 110F0..110F9; SORA_SOMPENG
6765 0x110FA, // 110FA..110FF; UNKNOWN
6766 0x11100, // 11100..11134; CHAKMA
6767 0x11135, // 11135 ; UNKNOWN
6768 0x11136, // 11136..11147; CHAKMA
6769 0x11148, // 11148..1114F; UNKNOWN
6770 0x11150, // 11150..11176; MAHAJANI
6771 0x11177, // 11177..1117F; UNKNOWN
6772 0x11180, // 11180..111DF; SHARADA
6773 0x111E0, // 111E0 ; UNKNOWN
6774 0x111E1, // 111E1..111F4; SINHALA
6775 0x111F5, // 111F5..111FF; UNKNOWN
6776 0x11200, // 11200..11211; KHOJKI
6777 0x11212, // 11212 ; UNKNOWN
6778 0x11213, // 11213..11241; KHOJKI
6779 0x11242, // 11242..1127F; UNKNOWN
6780 0x11280, // 11280..11286; MULTANI
6781 0x11287, // 11287 ; UNKNOWN
6782 0x11288, // 11288 ; MULTANI
6783 0x11289, // 11289 ; UNKNOWN
6784 0x1128A, // 1128A..1128D; MULTANI
6785 0x1128E, // 1128E ; UNKNOWN
6786 0x1128F, // 1128F..1129D; MULTANI
6787 0x1129E, // 1129E ; UNKNOWN
6788 0x1129F, // 1129F..112A9; MULTANI
6789 0x112AA, // 112AA..112AF; UNKNOWN
6790 0x112B0, // 112B0..112EA; KHUDAWADI
6791 0x112EB, // 112EB..112EF; UNKNOWN
6792 0x112F0, // 112F0..112F9; KHUDAWADI
6793 0x112FA, // 112FA..112FF; UNKNOWN
6794 0x11300, // 11300..11303; GRANTHA
6795 0x11304, // 11304 ; UNKNOWN
6796 0x11305, // 11305..1130C; GRANTHA
6797 0x1130D, // 1130D..1130E; UNKNOWN
6798 0x1130F, // 1130F..11310; GRANTHA
6799 0x11311, // 11311..11312; UNKNOWN
6800 0x11313, // 11313..11328; GRANTHA
6801 0x11329, // 11329 ; UNKNOWN
6802 0x1132A, // 1132A..11330; GRANTHA
6803 0x11331, // 11331 ; UNKNOWN
6804 0x11332, // 11332..11333; GRANTHA
6805 0x11334, // 11334 ; UNKNOWN
6806 0x11335, // 11335..11339; GRANTHA
6807 0x1133A, // 1133A ; UNKNOWN
6808 0x1133B, // 1133B ; INHERITED
6809 0x1133C, // 1133C..11344; GRANTHA
6810 0x11345, // 11345..11346; UNKNOWN
6811 0x11347, // 11347..11348; GRANTHA
6812 0x11349, // 11349..1134A; UNKNOWN
6813 0x1134B, // 1134B..1134D; GRANTHA
6814 0x1134E, // 1134E..1134F; UNKNOWN
6815 0x11350, // 11350 ; GRANTHA
6816 0x11351, // 11351..11356; UNKNOWN
6817 0x11357, // 11357 ; GRANTHA
6818 0x11358, // 11358..1135C; UNKNOWN
6819 0x1135D, // 1135D..11363; GRANTHA
6820 0x11364, // 11364..11365; UNKNOWN
6821 0x11366, // 11366..1136C; GRANTHA
6822 0x1136D, // 1136D..1136F; UNKNOWN
6823 0x11370, // 11370..11374; GRANTHA
6824 0x11375, // 11375..1137F; UNKNOWN
6825 0x11380, // 11380..11389; TULU_TIGALARI
6826 0x1138A, // 1138A ; UNKNOWN
6827 0x1138B, // 1138B ; TULU_TIGALARI
6828 0x1138C, // 1138C..1138D; UNKNOWN
6829 0x1138E, // 1138E ; TULU_TIGALARI
6830 0x1138F, // 1138F ; UNKNOWN
6831 0x11390, // 11390..113B5; TULU_TIGALARI
6832 0x113B6, // 113B6 ; UNKNOWN
6833 0x113B7, // 113B7..113C0; TULU_TIGALARI
6834 0x113C1, // 113C1 ; UNKNOWN
6835 0x113C2, // 113C2 ; TULU_TIGALARI
6836 0x113C3, // 113C3..113C4; UNKNOWN
6837 0x113C5, // 113C5 ; TULU_TIGALARI
6838 0x113C6, // 113C6 ; UNKNOWN
6839 0x113C7, // 113C7..113CA; TULU_TIGALARI
6840 0x113CB, // 113CB ; UNKNOWN
6841 0x113CC, // 113CC..113D5; TULU_TIGALARI
6842 0x113D6, // 113D6 ; UNKNOWN
6843 0x113D7, // 113D7..113D8; TULU_TIGALARI
6844 0x113D9, // 113D9..113E0; UNKNOWN
6845 0x113E1, // 113E1..113E2; TULU_TIGALARI
6846 0x113E3, // 113E3..113FF; UNKNOWN
6847 0x11400, // 11400..1145B; NEWA
6848 0x1145C, // 1145C ; UNKNOWN
6849 0x1145D, // 1145D..11461; NEWA
6850 0x11462, // 11462..1147F; UNKNOWN
6851 0x11480, // 11480..114C7; TIRHUTA
6852 0x114C8, // 114C8..114CF; UNKNOWN
6853 0x114D0, // 114D0..114D9; TIRHUTA
6854 0x114DA, // 114DA..1157F; UNKNOWN
6855 0x11580, // 11580..115B5; SIDDHAM
6856 0x115B6, // 115B6..115B7; UNKNOWN
6857 0x115B8, // 115B8..115DD; SIDDHAM
6858 0x115DE, // 115DE..115FF; UNKNOWN
6859 0x11600, // 11600..11644; MODI
6860 0x11645, // 11645..1164F; UNKNOWN
6861 0x11650, // 11650..11659; MODI
6862 0x1165A, // 1165A..1165F; UNKNOWN
6863 0x11660, // 11660..1166C; MONGOLIAN
6864 0x1166D, // 1166D..1167F; UNKNOWN
6865 0x11680, // 11680..116B9; TAKRI
6866 0x116BA, // 116BA..116BF; UNKNOWN
6867 0x116C0, // 116C0..116C9; TAKRI
6868 0x116CA, // 116CA..116CF; UNKNOWN
6869 0x116D0, // 116D0..116E3; MYANMAR
6870 0x116E4, // 116E4..116FF; UNKNOWN
6871 0x11700, // 11700..1171A; AHOM
6872 0x1171B, // 1171B..1171C; UNKNOWN
6873 0x1171D, // 1171D..1172B; AHOM
6874 0x1172C, // 1172C..1172F; UNKNOWN
6875 0x11730, // 11730..11746; AHOM
6876 0x11747, // 11747..117FF; UNKNOWN
6877 0x11800, // 11800..1183B; DOGRA
6878 0x1183C, // 1183C..1189F; UNKNOWN
6879 0x118A0, // 118A0..118F2; WARANG_CITI
6880 0x118F3, // 118F3..118FE; UNKNOWN
6881 0x118FF, // 118FF ; WARANG_CITI
6882 0x11900, // 11900..11906; DIVES_AKURU
6883 0x11907, // 11907..11908; UNKNOWN
6884 0x11909, // 11909 ; DIVES_AKURU
6885 0x1190A, // 1190A..1190B; UNKNOWN
6886 0x1190C, // 1190C..11913; DIVES_AKURU
6887 0x11914, // 11914 ; UNKNOWN
6888 0x11915, // 11915..11916; DIVES_AKURU
6889 0x11917, // 11917 ; UNKNOWN
6890 0x11918, // 11918..11935; DIVES_AKURU
6891 0x11936, // 11936 ; UNKNOWN
6892 0x11937, // 11937..11938; DIVES_AKURU
6893 0x11939, // 11939..1193A; UNKNOWN
6894 0x1193B, // 1193B..11946; DIVES_AKURU
6895 0x11947, // 11947..1194F; UNKNOWN
6896 0x11950, // 11950..11959; DIVES_AKURU
6897 0x1195A, // 1195A..1199F; UNKNOWN
6898 0x119A0, // 119A0..119A7; NANDINAGARI
6899 0x119A8, // 119A8..119A9; UNKNOWN
6900 0x119AA, // 119AA..119D7; NANDINAGARI
6901 0x119D8, // 119D8..119D9; UNKNOWN
6902 0x119DA, // 119DA..119E4; NANDINAGARI
6903 0x119E5, // 119E5..119FF; UNKNOWN
6904 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6905 0x11A48, // 11A48..11A4F; UNKNOWN
6906 0x11A50, // 11A50..11AA2; SOYOMBO
6907 0x11AA3, // 11AA3..11AAF; UNKNOWN
6908 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6909 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6910 0x11AF9, // 11AF9..11AFF; UNKNOWN
6911 0x11B00, // 11B00..11B09; DEVANAGARI
6912 0x11B0A, // 11B0A..11B5F; UNKNOWN
6913 0x11B60, // 11B60..11B67; SHARADA
6914 0x11B68, // 11B68..11BBF; UNKNOWN
6915 0x11BC0, // 11BC0..11BE1; SUNUWAR
6916 0x11BE2, // 11BE2..11BEF; UNKNOWN
6917 0x11BF0, // 11BF0..11BF9; SUNUWAR
6918 0x11BFA, // 11BFA..11BFF; UNKNOWN
6919 0x11C00, // 11C00..11C08; BHAIKSUKI
6920 0x11C09, // 11C09 ; UNKNOWN
6921 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6922 0x11C37, // 11C37 ; UNKNOWN
6923 0x11C38, // 11C38..11C45; BHAIKSUKI
6924 0x11C46, // 11C46..11C4F; UNKNOWN
6925 0x11C50, // 11C50..11C6C; BHAIKSUKI
6926 0x11C6D, // 11C6D..11C6F; UNKNOWN
6927 0x11C70, // 11C70..11C8F; MARCHEN
6928 0x11C90, // 11C90..11C91; UNKNOWN
6929 0x11C92, // 11C92..11CA7; MARCHEN
6930 0x11CA8, // 11CA8 ; UNKNOWN
6931 0x11CA9, // 11CA9..11CB6; MARCHEN
6932 0x11CB7, // 11CB7..11CFF; UNKNOWN
6933 0x11D00, // 11D00..11D06; MASARAM_GONDI
6934 0x11D07, // 11D07 ; UNKNOWN
6935 0x11D08, // 11D08..11D09; MASARAM_GONDI
6936 0x11D0A, // 11D0A ; UNKNOWN
6937 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6938 0x11D37, // 11D37..11D39; UNKNOWN
6939 0x11D3A, // 11D3A ; MASARAM_GONDI
6940 0x11D3B, // 11D3B ; UNKNOWN
6941 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6942 0x11D3E, // 11D3E ; UNKNOWN
6943 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6944 0x11D48, // 11D48..11D4F; UNKNOWN
6945 0x11D50, // 11D50..11D59; MASARAM_GONDI
6946 0x11D5A, // 11D5A..11D5F; UNKNOWN
6947 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6948 0x11D66, // 11D66 ; UNKNOWN
6949 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6950 0x11D69, // 11D69 ; UNKNOWN
6951 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6952 0x11D8F, // 11D8F ; UNKNOWN
6953 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6954 0x11D92, // 11D92 ; UNKNOWN
6955 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6956 0x11D99, // 11D99..11D9F; UNKNOWN
6957 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6958 0x11DAA, // 11DAA..11DAF; UNKNOWN
6959 0x11DB0, // 11DB0..11DDB; TOLONG_SIKI
6960 0x11DDC, // 11DDC..11DDF; UNKNOWN
6961 0x11DE0, // 11DE0..11DE9; TOLONG_SIKI
6962 0x11DEA, // 11DEA..11EDF; UNKNOWN
6963 0x11EE0, // 11EE0..11EF8; MAKASAR
6964 0x11EF9, // 11EF9..11EFF; UNKNOWN
6965 0x11F00, // 11F00..11F10; KAWI
6966 0x11F11, // 11F11 ; UNKNOWN
6967 0x11F12, // 11F12..11F3A; KAWI
6968 0x11F3B, // 11F3B..11F3D; UNKNOWN
6969 0x11F3E, // 11F3E..11F5A; KAWI
6970 0x11F5B, // 11F5B..11FAF; UNKNOWN
6971 0x11FB0, // 11FB0 ; LISU
6972 0x11FB1, // 11FB1..11FBF; UNKNOWN
6973 0x11FC0, // 11FC0..11FF1; TAMIL
6974 0x11FF2, // 11FF2..11FFE; UNKNOWN
6975 0x11FFF, // 11FFF ; TAMIL
6976 0x12000, // 12000..12399; CUNEIFORM
6977 0x1239A, // 1239A..123FF; UNKNOWN
6978 0x12400, // 12400..1246E; CUNEIFORM
6979 0x1246F, // 1246F ; UNKNOWN
6980 0x12470, // 12470..12474; CUNEIFORM
6981 0x12475, // 12475..1247F; UNKNOWN
6982 0x12480, // 12480..12543; CUNEIFORM
6983 0x12544, // 12544..12F8F; UNKNOWN
6984 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6985 0x12FF3, // 12FF3..12FFF; UNKNOWN
6986 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6987 0x13456, // 13456..1345F; UNKNOWN
6988 0x13460, // 13460..143FA; EGYPTIAN_HIEROGLYPHS
6989 0x143FB, // 143FB..143FF; UNKNOWN
6990 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6991 0x14647, // 14647..160FF; UNKNOWN
6992 0x16100, // 16100..16139; GURUNG_KHEMA
6993 0x1613A, // 1613A..167FF; UNKNOWN
6994 0x16800, // 16800..16A38; BAMUM
6995 0x16A39, // 16A39..16A3F; UNKNOWN
6996 0x16A40, // 16A40..16A5E; MRO
6997 0x16A5F, // 16A5F ; UNKNOWN
6998 0x16A60, // 16A60..16A69; MRO
6999 0x16A6A, // 16A6A..16A6D; UNKNOWN
7000 0x16A6E, // 16A6E..16A6F; MRO
7001 0x16A70, // 16A70..16ABE; TANGSA
7002 0x16ABF, // 16ABF ; UNKNOWN
7003 0x16AC0, // 16AC0..16AC9; TANGSA
7004 0x16ACA, // 16ACA..16ACF; UNKNOWN
7005 0x16AD0, // 16AD0..16AED; BASSA_VAH
7006 0x16AEE, // 16AEE..16AEF; UNKNOWN
7007 0x16AF0, // 16AF0..16AF5; BASSA_VAH
7008 0x16AF6, // 16AF6..16AFF; UNKNOWN
7009 0x16B00, // 16B00..16B45; PAHAWH_HMONG
7010 0x16B46, // 16B46..16B4F; UNKNOWN
7011 0x16B50, // 16B50..16B59; PAHAWH_HMONG
7012 0x16B5A, // 16B5A ; UNKNOWN
7013 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
7014 0x16B62, // 16B62 ; UNKNOWN
7015 0x16B63, // 16B63..16B77; PAHAWH_HMONG
7016 0x16B78, // 16B78..16B7C; UNKNOWN
7017 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
7018 0x16B90, // 16B90..16D3F; UNKNOWN
7019 0x16D40, // 16D40..16D79; KIRAT_RAI
7020 0x16D7A, // 16D7A..16E3F; UNKNOWN
7021 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
7022 0x16E9B, // 16E9B..16E9F; UNKNOWN
7023 0x16EA0, // 16EA0..16EB8; BERIA_ERFE
7024 0x16EB9, // 16EB9..16EBA; UNKNOWN
7025 0x16EBB, // 16EBB..16ED3; BERIA_ERFE
7026 0x16ED4, // 16ED4..16EFF; UNKNOWN
7027 0x16F00, // 16F00..16F4A; MIAO
7028 0x16F4B, // 16F4B..16F4E; UNKNOWN
7029 0x16F4F, // 16F4F..16F87; MIAO
7030 0x16F88, // 16F88..16F8E; UNKNOWN
7031 0x16F8F, // 16F8F..16F9F; MIAO
7032 0x16FA0, // 16FA0..16FDF; UNKNOWN
7033 0x16FE0, // 16FE0 ; TANGUT
7034 0x16FE1, // 16FE1 ; NUSHU
7035 0x16FE2, // 16FE2..16FE3; HAN
7036 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
7037 0x16FE5, // 16FE5..16FEF; UNKNOWN
7038 0x16FF0, // 16FF0..16FF6; HAN
7039 0x16FF7, // 16FF7..16FFF; UNKNOWN
7040 0x17000, // 17000..18AFF; TANGUT
7041 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
7042 0x18CD6, // 18CD6..18CFE; UNKNOWN
7043 0x18CFF, // 18CFF ; KHITAN_SMALL_SCRIPT
7044 0x18D00, // 18D00..18D1E; TANGUT
7045 0x18D1F, // 18D1F..18D7F; UNKNOWN
7046 0x18D80, // 18D80..18DF2; TANGUT
7047 0x18DF3, // 18DF3..1AFEF; UNKNOWN
7048 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
7049 0x1AFF4, // 1AFF4 ; UNKNOWN
7050 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
7051 0x1AFFC, // 1AFFC ; UNKNOWN
7052 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
7053 0x1AFFF, // 1AFFF ; UNKNOWN
7054 0x1B000, // 1B000 ; KATAKANA
7055 0x1B001, // 1B001..1B11F; HIRAGANA
7056 0x1B120, // 1B120..1B122; KATAKANA
7057 0x1B123, // 1B123..1B131; UNKNOWN
7058 0x1B132, // 1B132 ; HIRAGANA
7059 0x1B133, // 1B133..1B14F; UNKNOWN
7060 0x1B150, // 1B150..1B152; HIRAGANA
7061 0x1B153, // 1B153..1B154; UNKNOWN
7062 0x1B155, // 1B155 ; KATAKANA
7063 0x1B156, // 1B156..1B163; UNKNOWN
7064 0x1B164, // 1B164..1B167; KATAKANA
7065 0x1B168, // 1B168..1B16F; UNKNOWN
7066 0x1B170, // 1B170..1B2FB; NUSHU
7067 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
7068 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
7069 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
7070 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
7071 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
7072 0x1BC80, // 1BC80..1BC88; DUPLOYAN
7073 0x1BC89, // 1BC89..1BC8F; UNKNOWN
7074 0x1BC90, // 1BC90..1BC99; DUPLOYAN
7075 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
7076 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
7077 0x1BCA0, // 1BCA0..1BCA3; COMMON
7078 0x1BCA4, // 1BCA4..1CBFF; UNKNOWN
7079 0x1CC00, // 1CC00..1CCFC; COMMON
7080 0x1CCFD, // 1CCFD..1CCFF; UNKNOWN
7081 0x1CD00, // 1CD00..1CEB3; COMMON
7082 0x1CEB4, // 1CEB4..1CEB9; UNKNOWN
7083 0x1CEBA, // 1CEBA..1CED0; COMMON
7084 0x1CED1, // 1CED1..1CEDF; UNKNOWN
7085 0x1CEE0, // 1CEE0..1CEF0; COMMON
7086 0x1CEF1, // 1CEF1..1CEFF; UNKNOWN
7087 0x1CF00, // 1CF00..1CF2D; INHERITED
7088 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
7089 0x1CF30, // 1CF30..1CF46; INHERITED
7090 0x1CF47, // 1CF47..1CF4F; UNKNOWN
7091 0x1CF50, // 1CF50..1CFC3; COMMON
7092 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
7093 0x1D000, // 1D000..1D0F5; COMMON
7094 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
7095 0x1D100, // 1D100..1D126; COMMON
7096 0x1D127, // 1D127..1D128; UNKNOWN
7097 0x1D129, // 1D129..1D166; COMMON
7098 0x1D167, // 1D167..1D169; INHERITED
7099 0x1D16A, // 1D16A..1D17A; COMMON
7100 0x1D17B, // 1D17B..1D182; INHERITED
7101 0x1D183, // 1D183..1D184; COMMON
7102 0x1D185, // 1D185..1D18B; INHERITED
7103 0x1D18C, // 1D18C..1D1A9; COMMON
7104 0x1D1AA, // 1D1AA..1D1AD; INHERITED
7105 0x1D1AE, // 1D1AE..1D1EA; COMMON
7106 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
7107 0x1D200, // 1D200..1D245; GREEK
7108 0x1D246, // 1D246..1D2BF; UNKNOWN
7109 0x1D2C0, // 1D2C0..1D2D3; COMMON
7110 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
7111 0x1D2E0, // 1D2E0..1D2F3; COMMON
7112 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
7113 0x1D300, // 1D300..1D356; COMMON
7114 0x1D357, // 1D357..1D35F; UNKNOWN
7115 0x1D360, // 1D360..1D378; COMMON
7116 0x1D379, // 1D379..1D3FF; UNKNOWN
7117 0x1D400, // 1D400..1D454; COMMON
7118 0x1D455, // 1D455 ; UNKNOWN
7119 0x1D456, // 1D456..1D49C; COMMON
7120 0x1D49D, // 1D49D ; UNKNOWN
7121 0x1D49E, // 1D49E..1D49F; COMMON
7122 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
7123 0x1D4A2, // 1D4A2 ; COMMON
7124 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
7125 0x1D4A5, // 1D4A5..1D4A6; COMMON
7126 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
7127 0x1D4A9, // 1D4A9..1D4AC; COMMON
7128 0x1D4AD, // 1D4AD ; UNKNOWN
7129 0x1D4AE, // 1D4AE..1D4B9; COMMON
7130 0x1D4BA, // 1D4BA ; UNKNOWN
7131 0x1D4BB, // 1D4BB ; COMMON
7132 0x1D4BC, // 1D4BC ; UNKNOWN
7133 0x1D4BD, // 1D4BD..1D4C3; COMMON
7134 0x1D4C4, // 1D4C4 ; UNKNOWN
7135 0x1D4C5, // 1D4C5..1D505; COMMON
7136 0x1D506, // 1D506 ; UNKNOWN
7137 0x1D507, // 1D507..1D50A; COMMON
7138 0x1D50B, // 1D50B..1D50C; UNKNOWN
7139 0x1D50D, // 1D50D..1D514; COMMON
7140 0x1D515, // 1D515 ; UNKNOWN
7141 0x1D516, // 1D516..1D51C; COMMON
7142 0x1D51D, // 1D51D ; UNKNOWN
7143 0x1D51E, // 1D51E..1D539; COMMON
7144 0x1D53A, // 1D53A ; UNKNOWN
7145 0x1D53B, // 1D53B..1D53E; COMMON
7146 0x1D53F, // 1D53F ; UNKNOWN
7147 0x1D540, // 1D540..1D544; COMMON
7148 0x1D545, // 1D545 ; UNKNOWN
7149 0x1D546, // 1D546 ; COMMON
7150 0x1D547, // 1D547..1D549; UNKNOWN
7151 0x1D54A, // 1D54A..1D550; COMMON
7152 0x1D551, // 1D551 ; UNKNOWN
7153 0x1D552, // 1D552..1D6A5; COMMON
7154 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
7155 0x1D6A8, // 1D6A8..1D7CB; COMMON
7156 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
7157 0x1D7CE, // 1D7CE..1D7FF; COMMON
7158 0x1D800, // 1D800..1DA8B; SIGNWRITING
7159 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
7160 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
7161 0x1DAA0, // 1DAA0 ; UNKNOWN
7162 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
7163 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
7164 0x1DF00, // 1DF00..1DF1E; LATIN
7165 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
7166 0x1DF25, // 1DF25..1DF2A; LATIN
7167 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
7168 0x1E000, // 1E000..1E006; GLAGOLITIC
7169 0x1E007, // 1E007 ; UNKNOWN
7170 0x1E008, // 1E008..1E018; GLAGOLITIC
7171 0x1E019, // 1E019..1E01A; UNKNOWN
7172 0x1E01B, // 1E01B..1E021; GLAGOLITIC
7173 0x1E022, // 1E022 ; UNKNOWN
7174 0x1E023, // 1E023..1E024; GLAGOLITIC
7175 0x1E025, // 1E025 ; UNKNOWN
7176 0x1E026, // 1E026..1E02A; GLAGOLITIC
7177 0x1E02B, // 1E02B..1E02F; UNKNOWN
7178 0x1E030, // 1E030..1E06D; CYRILLIC
7179 0x1E06E, // 1E06E..1E08E; UNKNOWN
7180 0x1E08F, // 1E08F ; CYRILLIC
7181 0x1E090, // 1E090..1E0FF; UNKNOWN
7182 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
7183 0x1E12D, // 1E12D..1E12F; UNKNOWN
7184 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
7185 0x1E13E, // 1E13E..1E13F; UNKNOWN
7186 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
7187 0x1E14A, // 1E14A..1E14D; UNKNOWN
7188 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
7189 0x1E150, // 1E150..1E28F; UNKNOWN
7190 0x1E290, // 1E290..1E2AE; TOTO
7191 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
7192 0x1E2C0, // 1E2C0..1E2F9; WANCHO
7193 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
7194 0x1E2FF, // 1E2FF ; WANCHO
7195 0x1E300, // 1E300..1E4CF; UNKNOWN
7196 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
7197 0x1E4FA, // 1E4FA..1E5CF; UNKNOWN
7198 0x1E5D0, // 1E5D0..1E5FA; OL_ONAL
7199 0x1E5FB, // 1E5FB..1E5FE; UNKNOWN
7200 0x1E5FF, // 1E5FF ; OL_ONAL
7201 0x1E600, // 1E600..1E6BF; UNKNOWN
7202 0x1E6C0, // 1E6C0..1E6DE; TAI_YO
7203 0x1E6DF, // 1E6DF ; UNKNOWN
7204 0x1E6E0, // 1E6E0..1E6F5; TAI_YO
7205 0x1E6F6, // 1E6F6..1E6FD; UNKNOWN
7206 0x1E6FE, // 1E6FE..1E6FF; TAI_YO
7207 0x1E700, // 1E700..1E7DF; UNKNOWN
7208 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
7209 0x1E7E7, // 1E7E7 ; UNKNOWN
7210 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
7211 0x1E7EC, // 1E7EC ; UNKNOWN
7212 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
7213 0x1E7EF, // 1E7EF ; UNKNOWN
7214 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
7215 0x1E7FF, // 1E7FF ; UNKNOWN
7216 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
7217 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
7218 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
7219 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
7220 0x1E900, // 1E900..1E94B; ADLAM
7221 0x1E94C, // 1E94C..1E94F; UNKNOWN
7222 0x1E950, // 1E950..1E959; ADLAM
7223 0x1E95A, // 1E95A..1E95D; UNKNOWN
7224 0x1E95E, // 1E95E..1E95F; ADLAM
7225 0x1E960, // 1E960..1EC70; UNKNOWN
7226 0x1EC71, // 1EC71..1ECB4; COMMON
7227 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
7228 0x1ED01, // 1ED01..1ED3D; COMMON
7229 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
7230 0x1EE00, // 1EE00..1EE03; ARABIC
7231 0x1EE04, // 1EE04 ; UNKNOWN
7232 0x1EE05, // 1EE05..1EE1F; ARABIC
7233 0x1EE20, // 1EE20 ; UNKNOWN
7234 0x1EE21, // 1EE21..1EE22; ARABIC
7235 0x1EE23, // 1EE23 ; UNKNOWN
7236 0x1EE24, // 1EE24 ; ARABIC
7237 0x1EE25, // 1EE25..1EE26; UNKNOWN
7238 0x1EE27, // 1EE27 ; ARABIC
7239 0x1EE28, // 1EE28 ; UNKNOWN
7240 0x1EE29, // 1EE29..1EE32; ARABIC
7241 0x1EE33, // 1EE33 ; UNKNOWN
7242 0x1EE34, // 1EE34..1EE37; ARABIC
7243 0x1EE38, // 1EE38 ; UNKNOWN
7244 0x1EE39, // 1EE39 ; ARABIC
7245 0x1EE3A, // 1EE3A ; UNKNOWN
7246 0x1EE3B, // 1EE3B ; ARABIC
7247 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
7248 0x1EE42, // 1EE42 ; ARABIC
7249 0x1EE43, // 1EE43..1EE46; UNKNOWN
7250 0x1EE47, // 1EE47 ; ARABIC
7251 0x1EE48, // 1EE48 ; UNKNOWN
7252 0x1EE49, // 1EE49 ; ARABIC
7253 0x1EE4A, // 1EE4A ; UNKNOWN
7254 0x1EE4B, // 1EE4B ; ARABIC
7255 0x1EE4C, // 1EE4C ; UNKNOWN
7256 0x1EE4D, // 1EE4D..1EE4F; ARABIC
7257 0x1EE50, // 1EE50 ; UNKNOWN
7258 0x1EE51, // 1EE51..1EE52; ARABIC
7259 0x1EE53, // 1EE53 ; UNKNOWN
7260 0x1EE54, // 1EE54 ; ARABIC
7261 0x1EE55, // 1EE55..1EE56; UNKNOWN
7262 0x1EE57, // 1EE57 ; ARABIC
7263 0x1EE58, // 1EE58 ; UNKNOWN
7264 0x1EE59, // 1EE59 ; ARABIC
7265 0x1EE5A, // 1EE5A ; UNKNOWN
7266 0x1EE5B, // 1EE5B ; ARABIC
7267 0x1EE5C, // 1EE5C ; UNKNOWN
7268 0x1EE5D, // 1EE5D ; ARABIC
7269 0x1EE5E, // 1EE5E ; UNKNOWN
7270 0x1EE5F, // 1EE5F ; ARABIC
7271 0x1EE60, // 1EE60 ; UNKNOWN
7272 0x1EE61, // 1EE61..1EE62; ARABIC
7273 0x1EE63, // 1EE63 ; UNKNOWN
7274 0x1EE64, // 1EE64 ; ARABIC
7275 0x1EE65, // 1EE65..1EE66; UNKNOWN
7276 0x1EE67, // 1EE67..1EE6A; ARABIC
7277 0x1EE6B, // 1EE6B ; UNKNOWN
7278 0x1EE6C, // 1EE6C..1EE72; ARABIC
7279 0x1EE73, // 1EE73 ; UNKNOWN
7280 0x1EE74, // 1EE74..1EE77; ARABIC
7281 0x1EE78, // 1EE78 ; UNKNOWN
7282 0x1EE79, // 1EE79..1EE7C; ARABIC
7283 0x1EE7D, // 1EE7D ; UNKNOWN
7284 0x1EE7E, // 1EE7E ; ARABIC
7285 0x1EE7F, // 1EE7F ; UNKNOWN
7286 0x1EE80, // 1EE80..1EE89; ARABIC
7287 0x1EE8A, // 1EE8A ; UNKNOWN
7288 0x1EE8B, // 1EE8B..1EE9B; ARABIC
7289 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
7290 0x1EEA1, // 1EEA1..1EEA3; ARABIC
7291 0x1EEA4, // 1EEA4 ; UNKNOWN
7292 0x1EEA5, // 1EEA5..1EEA9; ARABIC
7293 0x1EEAA, // 1EEAA ; UNKNOWN
7294 0x1EEAB, // 1EEAB..1EEBB; ARABIC
7295 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
7296 0x1EEF0, // 1EEF0..1EEF1; ARABIC
7297 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
7298 0x1F000, // 1F000..1F02B; COMMON
7299 0x1F02C, // 1F02C..1F02F; UNKNOWN
7300 0x1F030, // 1F030..1F093; COMMON
7301 0x1F094, // 1F094..1F09F; UNKNOWN
7302 0x1F0A0, // 1F0A0..1F0AE; COMMON
7303 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
7304 0x1F0B1, // 1F0B1..1F0BF; COMMON
7305 0x1F0C0, // 1F0C0 ; UNKNOWN
7306 0x1F0C1, // 1F0C1..1F0CF; COMMON
7307 0x1F0D0, // 1F0D0 ; UNKNOWN
7308 0x1F0D1, // 1F0D1..1F0F5; COMMON
7309 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
7310 0x1F100, // 1F100..1F1AD; COMMON
7311 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
7312 0x1F1E6, // 1F1E6..1F1FF; COMMON
7313 0x1F200, // 1F200 ; HIRAGANA
7314 0x1F201, // 1F201..1F202; COMMON
7315 0x1F203, // 1F203..1F20F; UNKNOWN
7316 0x1F210, // 1F210..1F23B; COMMON
7317 0x1F23C, // 1F23C..1F23F; UNKNOWN
7318 0x1F240, // 1F240..1F248; COMMON
7319 0x1F249, // 1F249..1F24F; UNKNOWN
7320 0x1F250, // 1F250..1F251; COMMON
7321 0x1F252, // 1F252..1F25F; UNKNOWN
7322 0x1F260, // 1F260..1F265; COMMON
7323 0x1F266, // 1F266..1F2FF; UNKNOWN
7324 0x1F300, // 1F300..1F6D8; COMMON
7325 0x1F6D9, // 1F6D9..1F6DB; UNKNOWN
7326 0x1F6DC, // 1F6DC..1F6EC; COMMON
7327 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
7328 0x1F6F0, // 1F6F0..1F6FC; COMMON
7329 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
7330 0x1F700, // 1F700..1F7D9; COMMON
7331 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
7332 0x1F7E0, // 1F7E0..1F7EB; COMMON
7333 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
7334 0x1F7F0, // 1F7F0 ; COMMON
7335 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7336 0x1F800, // 1F800..1F80B; COMMON
7337 0x1F80C, // 1F80C..1F80F; UNKNOWN
7338 0x1F810, // 1F810..1F847; COMMON
7339 0x1F848, // 1F848..1F84F; UNKNOWN
7340 0x1F850, // 1F850..1F859; COMMON
7341 0x1F85A, // 1F85A..1F85F; UNKNOWN
7342 0x1F860, // 1F860..1F887; COMMON
7343 0x1F888, // 1F888..1F88F; UNKNOWN
7344 0x1F890, // 1F890..1F8AD; COMMON
7345 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7346 0x1F8B0, // 1F8B0..1F8BB; COMMON
7347 0x1F8BC, // 1F8BC..1F8BF; UNKNOWN
7348 0x1F8C0, // 1F8C0..1F8C1; COMMON
7349 0x1F8C2, // 1F8C2..1F8CF; UNKNOWN
7350 0x1F8D0, // 1F8D0..1F8D8; COMMON
7351 0x1F8D9, // 1F8D9..1F8FF; UNKNOWN
7352 0x1F900, // 1F900..1FA57; COMMON
7353 0x1FA58, // 1FA58..1FA5F; UNKNOWN
7354 0x1FA60, // 1FA60..1FA6D; COMMON
7355 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7356 0x1FA70, // 1FA70..1FA7C; COMMON
7357 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7358 0x1FA80, // 1FA80..1FA8A; COMMON
7359 0x1FA8B, // 1FA8B..1FA8D; UNKNOWN
7360 0x1FA8E, // 1FA8E..1FAC6; COMMON
7361 0x1FAC7, // 1FAC7 ; UNKNOWN
7362 0x1FAC8, // 1FAC8 ; COMMON
7363 0x1FAC9, // 1FAC9..1FACC; UNKNOWN
7364 0x1FACD, // 1FACD..1FADC; COMMON
7365 0x1FADD, // 1FADD..1FADE; UNKNOWN
7366 0x1FADF, // 1FADF..1FAEA; COMMON
7367 0x1FAEB, // 1FAEB..1FAEE; UNKNOWN
7368 0x1FAEF, // 1FAEF..1FAF8; COMMON
7369 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7370 0x1FB00, // 1FB00..1FB92; COMMON
7371 0x1FB93, // 1FB93 ; UNKNOWN
7372 0x1FB94, // 1FB94..1FBFA; COMMON
7373 0x1FBFB, // 1FBFB..1FFFF; UNKNOWN
7374 0x20000, // 20000..2A6DF; HAN
7375 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7376 0x2A700, // 2A700..2B81D; HAN
7377 0x2B81E, // 2B81E..2B81F; UNKNOWN
7378 0x2B820, // 2B820..2CEAD; HAN
7379 0x2CEAE, // 2CEAE..2CEAF; UNKNOWN
7380 0x2CEB0, // 2CEB0..2EBE0; HAN
7381 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7382 0x2EBF0, // 2EBF0..2EE5D; HAN
7383 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7384 0x2F800, // 2F800..2FA1D; HAN
7385 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7386 0x30000, // 30000..3134A; HAN
7387 0x3134B, // 3134B..3134F; UNKNOWN
7388 0x31350, // 31350..33479; HAN
7389 0x3347A, // 3347A..E0000; UNKNOWN
7390 0xE0001, // E0001 ; COMMON
7391 0xE0002, // E0002..E001F; UNKNOWN
7392 0xE0020, // E0020..E007F; COMMON
7393 0xE0080, // E0080..E00FF; UNKNOWN
7394 0xE0100, // E0100..E01EF; INHERITED
7395 0xE01F0, // E01F0..10FFFF; UNKNOWN
7396 };
7397
7398 private static final UnicodeScript[] scripts = {
7399 COMMON, // 0000..0040
7400 LATIN, // 0041..005A
7401 COMMON, // 005B..0060
7402 LATIN, // 0061..007A
7403 COMMON, // 007B..00A9
7404 LATIN, // 00AA
7405 COMMON, // 00AB..00B9
7406 LATIN, // 00BA
7407 COMMON, // 00BB..00BF
7408 LATIN, // 00C0..00D6
7409 COMMON, // 00D7
7410 LATIN, // 00D8..00F6
7411 COMMON, // 00F7
7412 LATIN, // 00F8..02B8
7413 COMMON, // 02B9..02DF
7414 LATIN, // 02E0..02E4
7415 COMMON, // 02E5..02E9
7416 BOPOMOFO, // 02EA..02EB
7417 COMMON, // 02EC..02FF
7418 INHERITED, // 0300..036F
7419 GREEK, // 0370..0373
7420 COMMON, // 0374
7421 GREEK, // 0375..0377
7422 UNKNOWN, // 0378..0379
7423 GREEK, // 037A..037D
7424 COMMON, // 037E
7425 GREEK, // 037F
7426 UNKNOWN, // 0380..0383
7427 GREEK, // 0384
7428 COMMON, // 0385
7429 GREEK, // 0386
7430 COMMON, // 0387
7431 GREEK, // 0388..038A
7432 UNKNOWN, // 038B
7433 GREEK, // 038C
7434 UNKNOWN, // 038D
7435 GREEK, // 038E..03A1
7436 UNKNOWN, // 03A2
7437 GREEK, // 03A3..03E1
7438 COPTIC, // 03E2..03EF
7439 GREEK, // 03F0..03FF
7440 CYRILLIC, // 0400..0484
7441 INHERITED, // 0485..0486
7442 CYRILLIC, // 0487..052F
7443 UNKNOWN, // 0530
7444 ARMENIAN, // 0531..0556
7445 UNKNOWN, // 0557..0558
7446 ARMENIAN, // 0559..058A
7447 UNKNOWN, // 058B..058C
7448 ARMENIAN, // 058D..058F
7449 UNKNOWN, // 0590
7450 HEBREW, // 0591..05C7
7451 UNKNOWN, // 05C8..05CF
7452 HEBREW, // 05D0..05EA
7453 UNKNOWN, // 05EB..05EE
7454 HEBREW, // 05EF..05F4
7455 UNKNOWN, // 05F5..05FF
7456 ARABIC, // 0600..0604
7457 COMMON, // 0605
7458 ARABIC, // 0606..060B
7459 COMMON, // 060C
7460 ARABIC, // 060D..061A
7461 COMMON, // 061B
7462 ARABIC, // 061C..061E
7463 COMMON, // 061F
7464 ARABIC, // 0620..063F
7465 COMMON, // 0640
7466 ARABIC, // 0641..064A
7467 INHERITED, // 064B..0655
7468 ARABIC, // 0656..066F
7469 INHERITED, // 0670
7470 ARABIC, // 0671..06DC
7471 COMMON, // 06DD
7472 ARABIC, // 06DE..06FF
7473 SYRIAC, // 0700..070D
7474 UNKNOWN, // 070E
7475 SYRIAC, // 070F..074A
7476 UNKNOWN, // 074B..074C
7477 SYRIAC, // 074D..074F
7478 ARABIC, // 0750..077F
7479 THAANA, // 0780..07B1
7480 UNKNOWN, // 07B2..07BF
7481 NKO, // 07C0..07FA
7482 UNKNOWN, // 07FB..07FC
7483 NKO, // 07FD..07FF
7484 SAMARITAN, // 0800..082D
7485 UNKNOWN, // 082E..082F
7486 SAMARITAN, // 0830..083E
7487 UNKNOWN, // 083F
7488 MANDAIC, // 0840..085B
7489 UNKNOWN, // 085C..085D
7490 MANDAIC, // 085E
7491 UNKNOWN, // 085F
7492 SYRIAC, // 0860..086A
7493 UNKNOWN, // 086B..086F
7494 ARABIC, // 0870..0891
7495 UNKNOWN, // 0892..0896
7496 ARABIC, // 0897..08E1
7497 COMMON, // 08E2
7498 ARABIC, // 08E3..08FF
7499 DEVANAGARI, // 0900..0950
7500 INHERITED, // 0951..0954
7501 DEVANAGARI, // 0955..0963
7502 COMMON, // 0964..0965
7503 DEVANAGARI, // 0966..097F
7504 BENGALI, // 0980..0983
7505 UNKNOWN, // 0984
7506 BENGALI, // 0985..098C
7507 UNKNOWN, // 098D..098E
7508 BENGALI, // 098F..0990
7509 UNKNOWN, // 0991..0992
7510 BENGALI, // 0993..09A8
7511 UNKNOWN, // 09A9
7512 BENGALI, // 09AA..09B0
7513 UNKNOWN, // 09B1
7514 BENGALI, // 09B2
7515 UNKNOWN, // 09B3..09B5
7516 BENGALI, // 09B6..09B9
7517 UNKNOWN, // 09BA..09BB
7518 BENGALI, // 09BC..09C4
7519 UNKNOWN, // 09C5..09C6
7520 BENGALI, // 09C7..09C8
7521 UNKNOWN, // 09C9..09CA
7522 BENGALI, // 09CB..09CE
7523 UNKNOWN, // 09CF..09D6
7524 BENGALI, // 09D7
7525 UNKNOWN, // 09D8..09DB
7526 BENGALI, // 09DC..09DD
7527 UNKNOWN, // 09DE
7528 BENGALI, // 09DF..09E3
7529 UNKNOWN, // 09E4..09E5
7530 BENGALI, // 09E6..09FE
7531 UNKNOWN, // 09FF..0A00
7532 GURMUKHI, // 0A01..0A03
7533 UNKNOWN, // 0A04
7534 GURMUKHI, // 0A05..0A0A
7535 UNKNOWN, // 0A0B..0A0E
7536 GURMUKHI, // 0A0F..0A10
7537 UNKNOWN, // 0A11..0A12
7538 GURMUKHI, // 0A13..0A28
7539 UNKNOWN, // 0A29
7540 GURMUKHI, // 0A2A..0A30
7541 UNKNOWN, // 0A31
7542 GURMUKHI, // 0A32..0A33
7543 UNKNOWN, // 0A34
7544 GURMUKHI, // 0A35..0A36
7545 UNKNOWN, // 0A37
7546 GURMUKHI, // 0A38..0A39
7547 UNKNOWN, // 0A3A..0A3B
7548 GURMUKHI, // 0A3C
7549 UNKNOWN, // 0A3D
7550 GURMUKHI, // 0A3E..0A42
7551 UNKNOWN, // 0A43..0A46
7552 GURMUKHI, // 0A47..0A48
7553 UNKNOWN, // 0A49..0A4A
7554 GURMUKHI, // 0A4B..0A4D
7555 UNKNOWN, // 0A4E..0A50
7556 GURMUKHI, // 0A51
7557 UNKNOWN, // 0A52..0A58
7558 GURMUKHI, // 0A59..0A5C
7559 UNKNOWN, // 0A5D
7560 GURMUKHI, // 0A5E
7561 UNKNOWN, // 0A5F..0A65
7562 GURMUKHI, // 0A66..0A76
7563 UNKNOWN, // 0A77..0A80
7564 GUJARATI, // 0A81..0A83
7565 UNKNOWN, // 0A84
7566 GUJARATI, // 0A85..0A8D
7567 UNKNOWN, // 0A8E
7568 GUJARATI, // 0A8F..0A91
7569 UNKNOWN, // 0A92
7570 GUJARATI, // 0A93..0AA8
7571 UNKNOWN, // 0AA9
7572 GUJARATI, // 0AAA..0AB0
7573 UNKNOWN, // 0AB1
7574 GUJARATI, // 0AB2..0AB3
7575 UNKNOWN, // 0AB4
7576 GUJARATI, // 0AB5..0AB9
7577 UNKNOWN, // 0ABA..0ABB
7578 GUJARATI, // 0ABC..0AC5
7579 UNKNOWN, // 0AC6
7580 GUJARATI, // 0AC7..0AC9
7581 UNKNOWN, // 0ACA
7582 GUJARATI, // 0ACB..0ACD
7583 UNKNOWN, // 0ACE..0ACF
7584 GUJARATI, // 0AD0
7585 UNKNOWN, // 0AD1..0ADF
7586 GUJARATI, // 0AE0..0AE3
7587 UNKNOWN, // 0AE4..0AE5
7588 GUJARATI, // 0AE6..0AF1
7589 UNKNOWN, // 0AF2..0AF8
7590 GUJARATI, // 0AF9..0AFF
7591 UNKNOWN, // 0B00
7592 ORIYA, // 0B01..0B03
7593 UNKNOWN, // 0B04
7594 ORIYA, // 0B05..0B0C
7595 UNKNOWN, // 0B0D..0B0E
7596 ORIYA, // 0B0F..0B10
7597 UNKNOWN, // 0B11..0B12
7598 ORIYA, // 0B13..0B28
7599 UNKNOWN, // 0B29
7600 ORIYA, // 0B2A..0B30
7601 UNKNOWN, // 0B31
7602 ORIYA, // 0B32..0B33
7603 UNKNOWN, // 0B34
7604 ORIYA, // 0B35..0B39
7605 UNKNOWN, // 0B3A..0B3B
7606 ORIYA, // 0B3C..0B44
7607 UNKNOWN, // 0B45..0B46
7608 ORIYA, // 0B47..0B48
7609 UNKNOWN, // 0B49..0B4A
7610 ORIYA, // 0B4B..0B4D
7611 UNKNOWN, // 0B4E..0B54
7612 ORIYA, // 0B55..0B57
7613 UNKNOWN, // 0B58..0B5B
7614 ORIYA, // 0B5C..0B5D
7615 UNKNOWN, // 0B5E
7616 ORIYA, // 0B5F..0B63
7617 UNKNOWN, // 0B64..0B65
7618 ORIYA, // 0B66..0B77
7619 UNKNOWN, // 0B78..0B81
7620 TAMIL, // 0B82..0B83
7621 UNKNOWN, // 0B84
7622 TAMIL, // 0B85..0B8A
7623 UNKNOWN, // 0B8B..0B8D
7624 TAMIL, // 0B8E..0B90
7625 UNKNOWN, // 0B91
7626 TAMIL, // 0B92..0B95
7627 UNKNOWN, // 0B96..0B98
7628 TAMIL, // 0B99..0B9A
7629 UNKNOWN, // 0B9B
7630 TAMIL, // 0B9C
7631 UNKNOWN, // 0B9D
7632 TAMIL, // 0B9E..0B9F
7633 UNKNOWN, // 0BA0..0BA2
7634 TAMIL, // 0BA3..0BA4
7635 UNKNOWN, // 0BA5..0BA7
7636 TAMIL, // 0BA8..0BAA
7637 UNKNOWN, // 0BAB..0BAD
7638 TAMIL, // 0BAE..0BB9
7639 UNKNOWN, // 0BBA..0BBD
7640 TAMIL, // 0BBE..0BC2
7641 UNKNOWN, // 0BC3..0BC5
7642 TAMIL, // 0BC6..0BC8
7643 UNKNOWN, // 0BC9
7644 TAMIL, // 0BCA..0BCD
7645 UNKNOWN, // 0BCE..0BCF
7646 TAMIL, // 0BD0
7647 UNKNOWN, // 0BD1..0BD6
7648 TAMIL, // 0BD7
7649 UNKNOWN, // 0BD8..0BE5
7650 TAMIL, // 0BE6..0BFA
7651 UNKNOWN, // 0BFB..0BFF
7652 TELUGU, // 0C00..0C0C
7653 UNKNOWN, // 0C0D
7654 TELUGU, // 0C0E..0C10
7655 UNKNOWN, // 0C11
7656 TELUGU, // 0C12..0C28
7657 UNKNOWN, // 0C29
7658 TELUGU, // 0C2A..0C39
7659 UNKNOWN, // 0C3A..0C3B
7660 TELUGU, // 0C3C..0C44
7661 UNKNOWN, // 0C45
7662 TELUGU, // 0C46..0C48
7663 UNKNOWN, // 0C49
7664 TELUGU, // 0C4A..0C4D
7665 UNKNOWN, // 0C4E..0C54
7666 TELUGU, // 0C55..0C56
7667 UNKNOWN, // 0C57
7668 TELUGU, // 0C58..0C5A
7669 UNKNOWN, // 0C5B
7670 TELUGU, // 0C5C..0C5D
7671 UNKNOWN, // 0C5E..0C5F
7672 TELUGU, // 0C60..0C63
7673 UNKNOWN, // 0C64..0C65
7674 TELUGU, // 0C66..0C6F
7675 UNKNOWN, // 0C70..0C76
7676 TELUGU, // 0C77..0C7F
7677 KANNADA, // 0C80..0C8C
7678 UNKNOWN, // 0C8D
7679 KANNADA, // 0C8E..0C90
7680 UNKNOWN, // 0C91
7681 KANNADA, // 0C92..0CA8
7682 UNKNOWN, // 0CA9
7683 KANNADA, // 0CAA..0CB3
7684 UNKNOWN, // 0CB4
7685 KANNADA, // 0CB5..0CB9
7686 UNKNOWN, // 0CBA..0CBB
7687 KANNADA, // 0CBC..0CC4
7688 UNKNOWN, // 0CC5
7689 KANNADA, // 0CC6..0CC8
7690 UNKNOWN, // 0CC9
7691 KANNADA, // 0CCA..0CCD
7692 UNKNOWN, // 0CCE..0CD4
7693 KANNADA, // 0CD5..0CD6
7694 UNKNOWN, // 0CD7..0CDB
7695 KANNADA, // 0CDC..0CDE
7696 UNKNOWN, // 0CDF
7697 KANNADA, // 0CE0..0CE3
7698 UNKNOWN, // 0CE4..0CE5
7699 KANNADA, // 0CE6..0CEF
7700 UNKNOWN, // 0CF0
7701 KANNADA, // 0CF1..0CF3
7702 UNKNOWN, // 0CF4..0CFF
7703 MALAYALAM, // 0D00..0D0C
7704 UNKNOWN, // 0D0D
7705 MALAYALAM, // 0D0E..0D10
7706 UNKNOWN, // 0D11
7707 MALAYALAM, // 0D12..0D44
7708 UNKNOWN, // 0D45
7709 MALAYALAM, // 0D46..0D48
7710 UNKNOWN, // 0D49
7711 MALAYALAM, // 0D4A..0D4F
7712 UNKNOWN, // 0D50..0D53
7713 MALAYALAM, // 0D54..0D63
7714 UNKNOWN, // 0D64..0D65
7715 MALAYALAM, // 0D66..0D7F
7716 UNKNOWN, // 0D80
7717 SINHALA, // 0D81..0D83
7718 UNKNOWN, // 0D84
7719 SINHALA, // 0D85..0D96
7720 UNKNOWN, // 0D97..0D99
7721 SINHALA, // 0D9A..0DB1
7722 UNKNOWN, // 0DB2
7723 SINHALA, // 0DB3..0DBB
7724 UNKNOWN, // 0DBC
7725 SINHALA, // 0DBD
7726 UNKNOWN, // 0DBE..0DBF
7727 SINHALA, // 0DC0..0DC6
7728 UNKNOWN, // 0DC7..0DC9
7729 SINHALA, // 0DCA
7730 UNKNOWN, // 0DCB..0DCE
7731 SINHALA, // 0DCF..0DD4
7732 UNKNOWN, // 0DD5
7733 SINHALA, // 0DD6
7734 UNKNOWN, // 0DD7
7735 SINHALA, // 0DD8..0DDF
7736 UNKNOWN, // 0DE0..0DE5
7737 SINHALA, // 0DE6..0DEF
7738 UNKNOWN, // 0DF0..0DF1
7739 SINHALA, // 0DF2..0DF4
7740 UNKNOWN, // 0DF5..0E00
7741 THAI, // 0E01..0E3A
7742 UNKNOWN, // 0E3B..0E3E
7743 COMMON, // 0E3F
7744 THAI, // 0E40..0E5B
7745 UNKNOWN, // 0E5C..0E80
7746 LAO, // 0E81..0E82
7747 UNKNOWN, // 0E83
7748 LAO, // 0E84
7749 UNKNOWN, // 0E85
7750 LAO, // 0E86..0E8A
7751 UNKNOWN, // 0E8B
7752 LAO, // 0E8C..0EA3
7753 UNKNOWN, // 0EA4
7754 LAO, // 0EA5
7755 UNKNOWN, // 0EA6
7756 LAO, // 0EA7..0EBD
7757 UNKNOWN, // 0EBE..0EBF
7758 LAO, // 0EC0..0EC4
7759 UNKNOWN, // 0EC5
7760 LAO, // 0EC6
7761 UNKNOWN, // 0EC7
7762 LAO, // 0EC8..0ECE
7763 UNKNOWN, // 0ECF
7764 LAO, // 0ED0..0ED9
7765 UNKNOWN, // 0EDA..0EDB
7766 LAO, // 0EDC..0EDF
7767 UNKNOWN, // 0EE0..0EFF
7768 TIBETAN, // 0F00..0F47
7769 UNKNOWN, // 0F48
7770 TIBETAN, // 0F49..0F6C
7771 UNKNOWN, // 0F6D..0F70
7772 TIBETAN, // 0F71..0F97
7773 UNKNOWN, // 0F98
7774 TIBETAN, // 0F99..0FBC
7775 UNKNOWN, // 0FBD
7776 TIBETAN, // 0FBE..0FCC
7777 UNKNOWN, // 0FCD
7778 TIBETAN, // 0FCE..0FD4
7779 COMMON, // 0FD5..0FD8
7780 TIBETAN, // 0FD9..0FDA
7781 UNKNOWN, // 0FDB..0FFF
7782 MYANMAR, // 1000..109F
7783 GEORGIAN, // 10A0..10C5
7784 UNKNOWN, // 10C6
7785 GEORGIAN, // 10C7
7786 UNKNOWN, // 10C8..10CC
7787 GEORGIAN, // 10CD
7788 UNKNOWN, // 10CE..10CF
7789 GEORGIAN, // 10D0..10FA
7790 COMMON, // 10FB
7791 GEORGIAN, // 10FC..10FF
7792 HANGUL, // 1100..11FF
7793 ETHIOPIC, // 1200..1248
7794 UNKNOWN, // 1249
7795 ETHIOPIC, // 124A..124D
7796 UNKNOWN, // 124E..124F
7797 ETHIOPIC, // 1250..1256
7798 UNKNOWN, // 1257
7799 ETHIOPIC, // 1258
7800 UNKNOWN, // 1259
7801 ETHIOPIC, // 125A..125D
7802 UNKNOWN, // 125E..125F
7803 ETHIOPIC, // 1260..1288
7804 UNKNOWN, // 1289
7805 ETHIOPIC, // 128A..128D
7806 UNKNOWN, // 128E..128F
7807 ETHIOPIC, // 1290..12B0
7808 UNKNOWN, // 12B1
7809 ETHIOPIC, // 12B2..12B5
7810 UNKNOWN, // 12B6..12B7
7811 ETHIOPIC, // 12B8..12BE
7812 UNKNOWN, // 12BF
7813 ETHIOPIC, // 12C0
7814 UNKNOWN, // 12C1
7815 ETHIOPIC, // 12C2..12C5
7816 UNKNOWN, // 12C6..12C7
7817 ETHIOPIC, // 12C8..12D6
7818 UNKNOWN, // 12D7
7819 ETHIOPIC, // 12D8..1310
7820 UNKNOWN, // 1311
7821 ETHIOPIC, // 1312..1315
7822 UNKNOWN, // 1316..1317
7823 ETHIOPIC, // 1318..135A
7824 UNKNOWN, // 135B..135C
7825 ETHIOPIC, // 135D..137C
7826 UNKNOWN, // 137D..137F
7827 ETHIOPIC, // 1380..1399
7828 UNKNOWN, // 139A..139F
7829 CHEROKEE, // 13A0..13F5
7830 UNKNOWN, // 13F6..13F7
7831 CHEROKEE, // 13F8..13FD
7832 UNKNOWN, // 13FE..13FF
7833 CANADIAN_ABORIGINAL, // 1400..167F
7834 OGHAM, // 1680..169C
7835 UNKNOWN, // 169D..169F
7836 RUNIC, // 16A0..16EA
7837 COMMON, // 16EB..16ED
7838 RUNIC, // 16EE..16F8
7839 UNKNOWN, // 16F9..16FF
7840 TAGALOG, // 1700..1715
7841 UNKNOWN, // 1716..171E
7842 TAGALOG, // 171F
7843 HANUNOO, // 1720..1734
7844 COMMON, // 1735..1736
7845 UNKNOWN, // 1737..173F
7846 BUHID, // 1740..1753
7847 UNKNOWN, // 1754..175F
7848 TAGBANWA, // 1760..176C
7849 UNKNOWN, // 176D
7850 TAGBANWA, // 176E..1770
7851 UNKNOWN, // 1771
7852 TAGBANWA, // 1772..1773
7853 UNKNOWN, // 1774..177F
7854 KHMER, // 1780..17DD
7855 UNKNOWN, // 17DE..17DF
7856 KHMER, // 17E0..17E9
7857 UNKNOWN, // 17EA..17EF
7858 KHMER, // 17F0..17F9
7859 UNKNOWN, // 17FA..17FF
7860 MONGOLIAN, // 1800..1801
7861 COMMON, // 1802..1803
7862 MONGOLIAN, // 1804
7863 COMMON, // 1805
7864 MONGOLIAN, // 1806..1819
7865 UNKNOWN, // 181A..181F
7866 MONGOLIAN, // 1820..1878
7867 UNKNOWN, // 1879..187F
7868 MONGOLIAN, // 1880..18AA
7869 UNKNOWN, // 18AB..18AF
7870 CANADIAN_ABORIGINAL, // 18B0..18F5
7871 UNKNOWN, // 18F6..18FF
7872 LIMBU, // 1900..191E
7873 UNKNOWN, // 191F
7874 LIMBU, // 1920..192B
7875 UNKNOWN, // 192C..192F
7876 LIMBU, // 1930..193B
7877 UNKNOWN, // 193C..193F
7878 LIMBU, // 1940
7879 UNKNOWN, // 1941..1943
7880 LIMBU, // 1944..194F
7881 TAI_LE, // 1950..196D
7882 UNKNOWN, // 196E..196F
7883 TAI_LE, // 1970..1974
7884 UNKNOWN, // 1975..197F
7885 NEW_TAI_LUE, // 1980..19AB
7886 UNKNOWN, // 19AC..19AF
7887 NEW_TAI_LUE, // 19B0..19C9
7888 UNKNOWN, // 19CA..19CF
7889 NEW_TAI_LUE, // 19D0..19DA
7890 UNKNOWN, // 19DB..19DD
7891 NEW_TAI_LUE, // 19DE..19DF
7892 KHMER, // 19E0..19FF
7893 BUGINESE, // 1A00..1A1B
7894 UNKNOWN, // 1A1C..1A1D
7895 BUGINESE, // 1A1E..1A1F
7896 TAI_THAM, // 1A20..1A5E
7897 UNKNOWN, // 1A5F
7898 TAI_THAM, // 1A60..1A7C
7899 UNKNOWN, // 1A7D..1A7E
7900 TAI_THAM, // 1A7F..1A89
7901 UNKNOWN, // 1A8A..1A8F
7902 TAI_THAM, // 1A90..1A99
7903 UNKNOWN, // 1A9A..1A9F
7904 TAI_THAM, // 1AA0..1AAD
7905 UNKNOWN, // 1AAE..1AAF
7906 INHERITED, // 1AB0..1ADD
7907 UNKNOWN, // 1ADE..1ADF
7908 INHERITED, // 1AE0..1AEB
7909 UNKNOWN, // 1AEC..1AFF
7910 BALINESE, // 1B00..1B4C
7911 UNKNOWN, // 1B4D
7912 BALINESE, // 1B4E..1B7F
7913 SUNDANESE, // 1B80..1BBF
7914 BATAK, // 1BC0..1BF3
7915 UNKNOWN, // 1BF4..1BFB
7916 BATAK, // 1BFC..1BFF
7917 LEPCHA, // 1C00..1C37
7918 UNKNOWN, // 1C38..1C3A
7919 LEPCHA, // 1C3B..1C49
7920 UNKNOWN, // 1C4A..1C4C
7921 LEPCHA, // 1C4D..1C4F
7922 OL_CHIKI, // 1C50..1C7F
7923 CYRILLIC, // 1C80..1C8A
7924 UNKNOWN, // 1C8B..1C8F
7925 GEORGIAN, // 1C90..1CBA
7926 UNKNOWN, // 1CBB..1CBC
7927 GEORGIAN, // 1CBD..1CBF
7928 SUNDANESE, // 1CC0..1CC7
7929 UNKNOWN, // 1CC8..1CCF
7930 INHERITED, // 1CD0..1CD2
7931 COMMON, // 1CD3
7932 INHERITED, // 1CD4..1CE0
7933 COMMON, // 1CE1
7934 INHERITED, // 1CE2..1CE8
7935 COMMON, // 1CE9..1CEC
7936 INHERITED, // 1CED
7937 COMMON, // 1CEE..1CF3
7938 INHERITED, // 1CF4
7939 COMMON, // 1CF5..1CF7
7940 INHERITED, // 1CF8..1CF9
7941 COMMON, // 1CFA
7942 UNKNOWN, // 1CFB..1CFF
7943 LATIN, // 1D00..1D25
7944 GREEK, // 1D26..1D2A
7945 CYRILLIC, // 1D2B
7946 LATIN, // 1D2C..1D5C
7947 GREEK, // 1D5D..1D61
7948 LATIN, // 1D62..1D65
7949 GREEK, // 1D66..1D6A
7950 LATIN, // 1D6B..1D77
7951 CYRILLIC, // 1D78
7952 LATIN, // 1D79..1DBE
7953 GREEK, // 1DBF
7954 INHERITED, // 1DC0..1DFF
7955 LATIN, // 1E00..1EFF
7956 GREEK, // 1F00..1F15
7957 UNKNOWN, // 1F16..1F17
7958 GREEK, // 1F18..1F1D
7959 UNKNOWN, // 1F1E..1F1F
7960 GREEK, // 1F20..1F45
7961 UNKNOWN, // 1F46..1F47
7962 GREEK, // 1F48..1F4D
7963 UNKNOWN, // 1F4E..1F4F
7964 GREEK, // 1F50..1F57
7965 UNKNOWN, // 1F58
7966 GREEK, // 1F59
7967 UNKNOWN, // 1F5A
7968 GREEK, // 1F5B
7969 UNKNOWN, // 1F5C
7970 GREEK, // 1F5D
7971 UNKNOWN, // 1F5E
7972 GREEK, // 1F5F..1F7D
7973 UNKNOWN, // 1F7E..1F7F
7974 GREEK, // 1F80..1FB4
7975 UNKNOWN, // 1FB5
7976 GREEK, // 1FB6..1FC4
7977 UNKNOWN, // 1FC5
7978 GREEK, // 1FC6..1FD3
7979 UNKNOWN, // 1FD4..1FD5
7980 GREEK, // 1FD6..1FDB
7981 UNKNOWN, // 1FDC
7982 GREEK, // 1FDD..1FEF
7983 UNKNOWN, // 1FF0..1FF1
7984 GREEK, // 1FF2..1FF4
7985 UNKNOWN, // 1FF5
7986 GREEK, // 1FF6..1FFE
7987 UNKNOWN, // 1FFF
7988 COMMON, // 2000..200B
7989 INHERITED, // 200C..200D
7990 COMMON, // 200E..2064
7991 UNKNOWN, // 2065
7992 COMMON, // 2066..2070
7993 LATIN, // 2071
7994 UNKNOWN, // 2072..2073
7995 COMMON, // 2074..207E
7996 LATIN, // 207F
7997 COMMON, // 2080..208E
7998 UNKNOWN, // 208F
7999 LATIN, // 2090..209C
8000 UNKNOWN, // 209D..209F
8001 COMMON, // 20A0..20C1
8002 UNKNOWN, // 20C2..20CF
8003 INHERITED, // 20D0..20F0
8004 UNKNOWN, // 20F1..20FF
8005 COMMON, // 2100..2125
8006 GREEK, // 2126
8007 COMMON, // 2127..2129
8008 LATIN, // 212A..212B
8009 COMMON, // 212C..2131
8010 LATIN, // 2132
8011 COMMON, // 2133..214D
8012 LATIN, // 214E
8013 COMMON, // 214F..215F
8014 LATIN, // 2160..2188
8015 COMMON, // 2189..218B
8016 UNKNOWN, // 218C..218F
8017 COMMON, // 2190..2429
8018 UNKNOWN, // 242A..243F
8019 COMMON, // 2440..244A
8020 UNKNOWN, // 244B..245F
8021 COMMON, // 2460..27FF
8022 BRAILLE, // 2800..28FF
8023 COMMON, // 2900..2B73
8024 UNKNOWN, // 2B74..2B75
8025 COMMON, // 2B76..2BFF
8026 GLAGOLITIC, // 2C00..2C5F
8027 LATIN, // 2C60..2C7F
8028 COPTIC, // 2C80..2CF3
8029 UNKNOWN, // 2CF4..2CF8
8030 COPTIC, // 2CF9..2CFF
8031 GEORGIAN, // 2D00..2D25
8032 UNKNOWN, // 2D26
8033 GEORGIAN, // 2D27
8034 UNKNOWN, // 2D28..2D2C
8035 GEORGIAN, // 2D2D
8036 UNKNOWN, // 2D2E..2D2F
8037 TIFINAGH, // 2D30..2D67
8038 UNKNOWN, // 2D68..2D6E
8039 TIFINAGH, // 2D6F..2D70
8040 UNKNOWN, // 2D71..2D7E
8041 TIFINAGH, // 2D7F
8042 ETHIOPIC, // 2D80..2D96
8043 UNKNOWN, // 2D97..2D9F
8044 ETHIOPIC, // 2DA0..2DA6
8045 UNKNOWN, // 2DA7
8046 ETHIOPIC, // 2DA8..2DAE
8047 UNKNOWN, // 2DAF
8048 ETHIOPIC, // 2DB0..2DB6
8049 UNKNOWN, // 2DB7
8050 ETHIOPIC, // 2DB8..2DBE
8051 UNKNOWN, // 2DBF
8052 ETHIOPIC, // 2DC0..2DC6
8053 UNKNOWN, // 2DC7
8054 ETHIOPIC, // 2DC8..2DCE
8055 UNKNOWN, // 2DCF
8056 ETHIOPIC, // 2DD0..2DD6
8057 UNKNOWN, // 2DD7
8058 ETHIOPIC, // 2DD8..2DDE
8059 UNKNOWN, // 2DDF
8060 CYRILLIC, // 2DE0..2DFF
8061 COMMON, // 2E00..2E5D
8062 UNKNOWN, // 2E5E..2E7F
8063 HAN, // 2E80..2E99
8064 UNKNOWN, // 2E9A
8065 HAN, // 2E9B..2EF3
8066 UNKNOWN, // 2EF4..2EFF
8067 HAN, // 2F00..2FD5
8068 UNKNOWN, // 2FD6..2FEF
8069 COMMON, // 2FF0..3004
8070 HAN, // 3005
8071 COMMON, // 3006
8072 HAN, // 3007
8073 COMMON, // 3008..3020
8074 HAN, // 3021..3029
8075 INHERITED, // 302A..302D
8076 HANGUL, // 302E..302F
8077 COMMON, // 3030..3037
8078 HAN, // 3038..303B
8079 COMMON, // 303C..303F
8080 UNKNOWN, // 3040
8081 HIRAGANA, // 3041..3096
8082 UNKNOWN, // 3097..3098
8083 INHERITED, // 3099..309A
8084 COMMON, // 309B..309C
8085 HIRAGANA, // 309D..309F
8086 COMMON, // 30A0
8087 KATAKANA, // 30A1..30FA
8088 COMMON, // 30FB..30FC
8089 KATAKANA, // 30FD..30FF
8090 UNKNOWN, // 3100..3104
8091 BOPOMOFO, // 3105..312F
8092 UNKNOWN, // 3130
8093 HANGUL, // 3131..318E
8094 UNKNOWN, // 318F
8095 COMMON, // 3190..319F
8096 BOPOMOFO, // 31A0..31BF
8097 COMMON, // 31C0..31E5
8098 UNKNOWN, // 31E6..31EE
8099 COMMON, // 31EF
8100 KATAKANA, // 31F0..31FF
8101 HANGUL, // 3200..321E
8102 UNKNOWN, // 321F
8103 COMMON, // 3220..325F
8104 HANGUL, // 3260..327E
8105 COMMON, // 327F..32CF
8106 KATAKANA, // 32D0..32FE
8107 COMMON, // 32FF
8108 KATAKANA, // 3300..3357
8109 COMMON, // 3358..33FF
8110 HAN, // 3400..4DBF
8111 COMMON, // 4DC0..4DFF
8112 HAN, // 4E00..9FFF
8113 YI, // A000..A48C
8114 UNKNOWN, // A48D..A48F
8115 YI, // A490..A4C6
8116 UNKNOWN, // A4C7..A4CF
8117 LISU, // A4D0..A4FF
8118 VAI, // A500..A62B
8119 UNKNOWN, // A62C..A63F
8120 CYRILLIC, // A640..A69F
8121 BAMUM, // A6A0..A6F7
8122 UNKNOWN, // A6F8..A6FF
8123 COMMON, // A700..A721
8124 LATIN, // A722..A787
8125 COMMON, // A788..A78A
8126 LATIN, // A78B..A7DC
8127 UNKNOWN, // A7DD..A7F0
8128 LATIN, // A7F1..A7FF
8129 SYLOTI_NAGRI, // A800..A82C
8130 UNKNOWN, // A82D..A82F
8131 COMMON, // A830..A839
8132 UNKNOWN, // A83A..A83F
8133 PHAGS_PA, // A840..A877
8134 UNKNOWN, // A878..A87F
8135 SAURASHTRA, // A880..A8C5
8136 UNKNOWN, // A8C6..A8CD
8137 SAURASHTRA, // A8CE..A8D9
8138 UNKNOWN, // A8DA..A8DF
8139 DEVANAGARI, // A8E0..A8FF
8140 KAYAH_LI, // A900..A92D
8141 COMMON, // A92E
8142 KAYAH_LI, // A92F
8143 REJANG, // A930..A953
8144 UNKNOWN, // A954..A95E
8145 REJANG, // A95F
8146 HANGUL, // A960..A97C
8147 UNKNOWN, // A97D..A97F
8148 JAVANESE, // A980..A9CD
8149 UNKNOWN, // A9CE
8150 COMMON, // A9CF
8151 JAVANESE, // A9D0..A9D9
8152 UNKNOWN, // A9DA..A9DD
8153 JAVANESE, // A9DE..A9DF
8154 MYANMAR, // A9E0..A9FE
8155 UNKNOWN, // A9FF
8156 CHAM, // AA00..AA36
8157 UNKNOWN, // AA37..AA3F
8158 CHAM, // AA40..AA4D
8159 UNKNOWN, // AA4E..AA4F
8160 CHAM, // AA50..AA59
8161 UNKNOWN, // AA5A..AA5B
8162 CHAM, // AA5C..AA5F
8163 MYANMAR, // AA60..AA7F
8164 TAI_VIET, // AA80..AAC2
8165 UNKNOWN, // AAC3..AADA
8166 TAI_VIET, // AADB..AADF
8167 MEETEI_MAYEK, // AAE0..AAF6
8168 UNKNOWN, // AAF7..AB00
8169 ETHIOPIC, // AB01..AB06
8170 UNKNOWN, // AB07..AB08
8171 ETHIOPIC, // AB09..AB0E
8172 UNKNOWN, // AB0F..AB10
8173 ETHIOPIC, // AB11..AB16
8174 UNKNOWN, // AB17..AB1F
8175 ETHIOPIC, // AB20..AB26
8176 UNKNOWN, // AB27
8177 ETHIOPIC, // AB28..AB2E
8178 UNKNOWN, // AB2F
8179 LATIN, // AB30..AB5A
8180 COMMON, // AB5B
8181 LATIN, // AB5C..AB64
8182 GREEK, // AB65
8183 LATIN, // AB66..AB69
8184 COMMON, // AB6A..AB6B
8185 UNKNOWN, // AB6C..AB6F
8186 CHEROKEE, // AB70..ABBF
8187 MEETEI_MAYEK, // ABC0..ABED
8188 UNKNOWN, // ABEE..ABEF
8189 MEETEI_MAYEK, // ABF0..ABF9
8190 UNKNOWN, // ABFA..ABFF
8191 HANGUL, // AC00..D7A3
8192 UNKNOWN, // D7A4..D7AF
8193 HANGUL, // D7B0..D7C6
8194 UNKNOWN, // D7C7..D7CA
8195 HANGUL, // D7CB..D7FB
8196 UNKNOWN, // D7FC..F8FF
8197 HAN, // F900..FA6D
8198 UNKNOWN, // FA6E..FA6F
8199 HAN, // FA70..FAD9
8200 UNKNOWN, // FADA..FAFF
8201 LATIN, // FB00..FB06
8202 UNKNOWN, // FB07..FB12
8203 ARMENIAN, // FB13..FB17
8204 UNKNOWN, // FB18..FB1C
8205 HEBREW, // FB1D..FB36
8206 UNKNOWN, // FB37
8207 HEBREW, // FB38..FB3C
8208 UNKNOWN, // FB3D
8209 HEBREW, // FB3E
8210 UNKNOWN, // FB3F
8211 HEBREW, // FB40..FB41
8212 UNKNOWN, // FB42
8213 HEBREW, // FB43..FB44
8214 UNKNOWN, // FB45
8215 HEBREW, // FB46..FB4F
8216 ARABIC, // FB50..FD3D
8217 COMMON, // FD3E..FD3F
8218 ARABIC, // FD40..FDCF
8219 UNKNOWN, // FDD0..FDEF
8220 ARABIC, // FDF0..FDFF
8221 INHERITED, // FE00..FE0F
8222 COMMON, // FE10..FE19
8223 UNKNOWN, // FE1A..FE1F
8224 INHERITED, // FE20..FE2D
8225 CYRILLIC, // FE2E..FE2F
8226 COMMON, // FE30..FE52
8227 UNKNOWN, // FE53
8228 COMMON, // FE54..FE66
8229 UNKNOWN, // FE67
8230 COMMON, // FE68..FE6B
8231 UNKNOWN, // FE6C..FE6F
8232 ARABIC, // FE70..FE74
8233 UNKNOWN, // FE75
8234 ARABIC, // FE76..FEFC
8235 UNKNOWN, // FEFD..FEFE
8236 COMMON, // FEFF
8237 UNKNOWN, // FF00
8238 COMMON, // FF01..FF20
8239 LATIN, // FF21..FF3A
8240 COMMON, // FF3B..FF40
8241 LATIN, // FF41..FF5A
8242 COMMON, // FF5B..FF65
8243 KATAKANA, // FF66..FF6F
8244 COMMON, // FF70
8245 KATAKANA, // FF71..FF9D
8246 COMMON, // FF9E..FF9F
8247 HANGUL, // FFA0..FFBE
8248 UNKNOWN, // FFBF..FFC1
8249 HANGUL, // FFC2..FFC7
8250 UNKNOWN, // FFC8..FFC9
8251 HANGUL, // FFCA..FFCF
8252 UNKNOWN, // FFD0..FFD1
8253 HANGUL, // FFD2..FFD7
8254 UNKNOWN, // FFD8..FFD9
8255 HANGUL, // FFDA..FFDC
8256 UNKNOWN, // FFDD..FFDF
8257 COMMON, // FFE0..FFE6
8258 UNKNOWN, // FFE7
8259 COMMON, // FFE8..FFEE
8260 UNKNOWN, // FFEF..FFF8
8261 COMMON, // FFF9..FFFD
8262 UNKNOWN, // FFFE..FFFF
8263 LINEAR_B, // 10000..1000B
8264 UNKNOWN, // 1000C
8265 LINEAR_B, // 1000D..10026
8266 UNKNOWN, // 10027
8267 LINEAR_B, // 10028..1003A
8268 UNKNOWN, // 1003B
8269 LINEAR_B, // 1003C..1003D
8270 UNKNOWN, // 1003E
8271 LINEAR_B, // 1003F..1004D
8272 UNKNOWN, // 1004E..1004F
8273 LINEAR_B, // 10050..1005D
8274 UNKNOWN, // 1005E..1007F
8275 LINEAR_B, // 10080..100FA
8276 UNKNOWN, // 100FB..100FF
8277 COMMON, // 10100..10102
8278 UNKNOWN, // 10103..10106
8279 COMMON, // 10107..10133
8280 UNKNOWN, // 10134..10136
8281 COMMON, // 10137..1013F
8282 GREEK, // 10140..1018E
8283 UNKNOWN, // 1018F
8284 COMMON, // 10190..1019C
8285 UNKNOWN, // 1019D..1019F
8286 GREEK, // 101A0
8287 UNKNOWN, // 101A1..101CF
8288 COMMON, // 101D0..101FC
8289 INHERITED, // 101FD
8290 UNKNOWN, // 101FE..1027F
8291 LYCIAN, // 10280..1029C
8292 UNKNOWN, // 1029D..1029F
8293 CARIAN, // 102A0..102D0
8294 UNKNOWN, // 102D1..102DF
8295 INHERITED, // 102E0
8296 COMMON, // 102E1..102FB
8297 UNKNOWN, // 102FC..102FF
8298 OLD_ITALIC, // 10300..10323
8299 UNKNOWN, // 10324..1032C
8300 OLD_ITALIC, // 1032D..1032F
8301 GOTHIC, // 10330..1034A
8302 UNKNOWN, // 1034B..1034F
8303 OLD_PERMIC, // 10350..1037A
8304 UNKNOWN, // 1037B..1037F
8305 UGARITIC, // 10380..1039D
8306 UNKNOWN, // 1039E
8307 UGARITIC, // 1039F
8308 OLD_PERSIAN, // 103A0..103C3
8309 UNKNOWN, // 103C4..103C7
8310 OLD_PERSIAN, // 103C8..103D5
8311 UNKNOWN, // 103D6..103FF
8312 DESERET, // 10400..1044F
8313 SHAVIAN, // 10450..1047F
8314 OSMANYA, // 10480..1049D
8315 UNKNOWN, // 1049E..1049F
8316 OSMANYA, // 104A0..104A9
8317 UNKNOWN, // 104AA..104AF
8318 OSAGE, // 104B0..104D3
8319 UNKNOWN, // 104D4..104D7
8320 OSAGE, // 104D8..104FB
8321 UNKNOWN, // 104FC..104FF
8322 ELBASAN, // 10500..10527
8323 UNKNOWN, // 10528..1052F
8324 CAUCASIAN_ALBANIAN, // 10530..10563
8325 UNKNOWN, // 10564..1056E
8326 CAUCASIAN_ALBANIAN, // 1056F
8327 VITHKUQI, // 10570..1057A
8328 UNKNOWN, // 1057B
8329 VITHKUQI, // 1057C..1058A
8330 UNKNOWN, // 1058B
8331 VITHKUQI, // 1058C..10592
8332 UNKNOWN, // 10593
8333 VITHKUQI, // 10594..10595
8334 UNKNOWN, // 10596
8335 VITHKUQI, // 10597..105A1
8336 UNKNOWN, // 105A2
8337 VITHKUQI, // 105A3..105B1
8338 UNKNOWN, // 105B2
8339 VITHKUQI, // 105B3..105B9
8340 UNKNOWN, // 105BA
8341 VITHKUQI, // 105BB..105BC
8342 UNKNOWN, // 105BD..105BF
8343 TODHRI, // 105C0..105F3
8344 UNKNOWN, // 105F4..105FF
8345 LINEAR_A, // 10600..10736
8346 UNKNOWN, // 10737..1073F
8347 LINEAR_A, // 10740..10755
8348 UNKNOWN, // 10756..1075F
8349 LINEAR_A, // 10760..10767
8350 UNKNOWN, // 10768..1077F
8351 LATIN, // 10780..10785
8352 UNKNOWN, // 10786
8353 LATIN, // 10787..107B0
8354 UNKNOWN, // 107B1
8355 LATIN, // 107B2..107BA
8356 UNKNOWN, // 107BB..107FF
8357 CYPRIOT, // 10800..10805
8358 UNKNOWN, // 10806..10807
8359 CYPRIOT, // 10808
8360 UNKNOWN, // 10809
8361 CYPRIOT, // 1080A..10835
8362 UNKNOWN, // 10836
8363 CYPRIOT, // 10837..10838
8364 UNKNOWN, // 10839..1083B
8365 CYPRIOT, // 1083C
8366 UNKNOWN, // 1083D..1083E
8367 CYPRIOT, // 1083F
8368 IMPERIAL_ARAMAIC, // 10840..10855
8369 UNKNOWN, // 10856
8370 IMPERIAL_ARAMAIC, // 10857..1085F
8371 PALMYRENE, // 10860..1087F
8372 NABATAEAN, // 10880..1089E
8373 UNKNOWN, // 1089F..108A6
8374 NABATAEAN, // 108A7..108AF
8375 UNKNOWN, // 108B0..108DF
8376 HATRAN, // 108E0..108F2
8377 UNKNOWN, // 108F3
8378 HATRAN, // 108F4..108F5
8379 UNKNOWN, // 108F6..108FA
8380 HATRAN, // 108FB..108FF
8381 PHOENICIAN, // 10900..1091B
8382 UNKNOWN, // 1091C..1091E
8383 PHOENICIAN, // 1091F
8384 LYDIAN, // 10920..10939
8385 UNKNOWN, // 1093A..1093E
8386 LYDIAN, // 1093F
8387 SIDETIC, // 10940..10959
8388 UNKNOWN, // 1095A..1097F
8389 MEROITIC_HIEROGLYPHS, // 10980..1099F
8390 MEROITIC_CURSIVE, // 109A0..109B7
8391 UNKNOWN, // 109B8..109BB
8392 MEROITIC_CURSIVE, // 109BC..109CF
8393 UNKNOWN, // 109D0..109D1
8394 MEROITIC_CURSIVE, // 109D2..109FF
8395 KHAROSHTHI, // 10A00..10A03
8396 UNKNOWN, // 10A04
8397 KHAROSHTHI, // 10A05..10A06
8398 UNKNOWN, // 10A07..10A0B
8399 KHAROSHTHI, // 10A0C..10A13
8400 UNKNOWN, // 10A14
8401 KHAROSHTHI, // 10A15..10A17
8402 UNKNOWN, // 10A18
8403 KHAROSHTHI, // 10A19..10A35
8404 UNKNOWN, // 10A36..10A37
8405 KHAROSHTHI, // 10A38..10A3A
8406 UNKNOWN, // 10A3B..10A3E
8407 KHAROSHTHI, // 10A3F..10A48
8408 UNKNOWN, // 10A49..10A4F
8409 KHAROSHTHI, // 10A50..10A58
8410 UNKNOWN, // 10A59..10A5F
8411 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8412 OLD_NORTH_ARABIAN, // 10A80..10A9F
8413 UNKNOWN, // 10AA0..10ABF
8414 MANICHAEAN, // 10AC0..10AE6
8415 UNKNOWN, // 10AE7..10AEA
8416 MANICHAEAN, // 10AEB..10AF6
8417 UNKNOWN, // 10AF7..10AFF
8418 AVESTAN, // 10B00..10B35
8419 UNKNOWN, // 10B36..10B38
8420 AVESTAN, // 10B39..10B3F
8421 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8422 UNKNOWN, // 10B56..10B57
8423 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8424 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8425 UNKNOWN, // 10B73..10B77
8426 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8427 PSALTER_PAHLAVI, // 10B80..10B91
8428 UNKNOWN, // 10B92..10B98
8429 PSALTER_PAHLAVI, // 10B99..10B9C
8430 UNKNOWN, // 10B9D..10BA8
8431 PSALTER_PAHLAVI, // 10BA9..10BAF
8432 UNKNOWN, // 10BB0..10BFF
8433 OLD_TURKIC, // 10C00..10C48
8434 UNKNOWN, // 10C49..10C7F
8435 OLD_HUNGARIAN, // 10C80..10CB2
8436 UNKNOWN, // 10CB3..10CBF
8437 OLD_HUNGARIAN, // 10CC0..10CF2
8438 UNKNOWN, // 10CF3..10CF9
8439 OLD_HUNGARIAN, // 10CFA..10CFF
8440 HANIFI_ROHINGYA, // 10D00..10D27
8441 UNKNOWN, // 10D28..10D2F
8442 HANIFI_ROHINGYA, // 10D30..10D39
8443 UNKNOWN, // 10D3A..10D3F
8444 GARAY, // 10D40..10D65
8445 UNKNOWN, // 10D66..10D68
8446 GARAY, // 10D69..10D85
8447 UNKNOWN, // 10D86..10D8D
8448 GARAY, // 10D8E..10D8F
8449 UNKNOWN, // 10D90..10E5F
8450 ARABIC, // 10E60..10E7E
8451 UNKNOWN, // 10E7F
8452 YEZIDI, // 10E80..10EA9
8453 UNKNOWN, // 10EAA
8454 YEZIDI, // 10EAB..10EAD
8455 UNKNOWN, // 10EAE..10EAF
8456 YEZIDI, // 10EB0..10EB1
8457 UNKNOWN, // 10EB2..10EC1
8458 ARABIC, // 10EC2..10EC7
8459 UNKNOWN, // 10EC8..10ECF
8460 ARABIC, // 10ED0..10ED8
8461 UNKNOWN, // 10ED9..10EF9
8462 ARABIC, // 10EFA..10EFF
8463 OLD_SOGDIAN, // 10F00..10F27
8464 UNKNOWN, // 10F28..10F2F
8465 SOGDIAN, // 10F30..10F59
8466 UNKNOWN, // 10F5A..10F6F
8467 OLD_UYGHUR, // 10F70..10F89
8468 UNKNOWN, // 10F8A..10FAF
8469 CHORASMIAN, // 10FB0..10FCB
8470 UNKNOWN, // 10FCC..10FDF
8471 ELYMAIC, // 10FE0..10FF6
8472 UNKNOWN, // 10FF7..10FFF
8473 BRAHMI, // 11000..1104D
8474 UNKNOWN, // 1104E..11051
8475 BRAHMI, // 11052..11075
8476 UNKNOWN, // 11076..1107E
8477 BRAHMI, // 1107F
8478 KAITHI, // 11080..110C2
8479 UNKNOWN, // 110C3..110CC
8480 KAITHI, // 110CD
8481 UNKNOWN, // 110CE..110CF
8482 SORA_SOMPENG, // 110D0..110E8
8483 UNKNOWN, // 110E9..110EF
8484 SORA_SOMPENG, // 110F0..110F9
8485 UNKNOWN, // 110FA..110FF
8486 CHAKMA, // 11100..11134
8487 UNKNOWN, // 11135
8488 CHAKMA, // 11136..11147
8489 UNKNOWN, // 11148..1114F
8490 MAHAJANI, // 11150..11176
8491 UNKNOWN, // 11177..1117F
8492 SHARADA, // 11180..111DF
8493 UNKNOWN, // 111E0
8494 SINHALA, // 111E1..111F4
8495 UNKNOWN, // 111F5..111FF
8496 KHOJKI, // 11200..11211
8497 UNKNOWN, // 11212
8498 KHOJKI, // 11213..11241
8499 UNKNOWN, // 11242..1127F
8500 MULTANI, // 11280..11286
8501 UNKNOWN, // 11287
8502 MULTANI, // 11288
8503 UNKNOWN, // 11289
8504 MULTANI, // 1128A..1128D
8505 UNKNOWN, // 1128E
8506 MULTANI, // 1128F..1129D
8507 UNKNOWN, // 1129E
8508 MULTANI, // 1129F..112A9
8509 UNKNOWN, // 112AA..112AF
8510 KHUDAWADI, // 112B0..112EA
8511 UNKNOWN, // 112EB..112EF
8512 KHUDAWADI, // 112F0..112F9
8513 UNKNOWN, // 112FA..112FF
8514 GRANTHA, // 11300..11303
8515 UNKNOWN, // 11304
8516 GRANTHA, // 11305..1130C
8517 UNKNOWN, // 1130D..1130E
8518 GRANTHA, // 1130F..11310
8519 UNKNOWN, // 11311..11312
8520 GRANTHA, // 11313..11328
8521 UNKNOWN, // 11329
8522 GRANTHA, // 1132A..11330
8523 UNKNOWN, // 11331
8524 GRANTHA, // 11332..11333
8525 UNKNOWN, // 11334
8526 GRANTHA, // 11335..11339
8527 UNKNOWN, // 1133A
8528 INHERITED, // 1133B
8529 GRANTHA, // 1133C..11344
8530 UNKNOWN, // 11345..11346
8531 GRANTHA, // 11347..11348
8532 UNKNOWN, // 11349..1134A
8533 GRANTHA, // 1134B..1134D
8534 UNKNOWN, // 1134E..1134F
8535 GRANTHA, // 11350
8536 UNKNOWN, // 11351..11356
8537 GRANTHA, // 11357
8538 UNKNOWN, // 11358..1135C
8539 GRANTHA, // 1135D..11363
8540 UNKNOWN, // 11364..11365
8541 GRANTHA, // 11366..1136C
8542 UNKNOWN, // 1136D..1136F
8543 GRANTHA, // 11370..11374
8544 UNKNOWN, // 11375..1137F
8545 TULU_TIGALARI, // 11380..11389
8546 UNKNOWN, // 1138A
8547 TULU_TIGALARI, // 1138B
8548 UNKNOWN, // 1138C..1138D
8549 TULU_TIGALARI, // 1138E
8550 UNKNOWN, // 1138F
8551 TULU_TIGALARI, // 11390..113B5
8552 UNKNOWN, // 113B6
8553 TULU_TIGALARI, // 113B7..113C0
8554 UNKNOWN, // 113C1
8555 TULU_TIGALARI, // 113C2
8556 UNKNOWN, // 113C3..113C4
8557 TULU_TIGALARI, // 113C5
8558 UNKNOWN, // 113C6
8559 TULU_TIGALARI, // 113C7..113CA
8560 UNKNOWN, // 113CB
8561 TULU_TIGALARI, // 113CC..113D5
8562 UNKNOWN, // 113D6
8563 TULU_TIGALARI, // 113D7..113D8
8564 UNKNOWN, // 113D9..113E0
8565 TULU_TIGALARI, // 113E1..113E2
8566 UNKNOWN, // 113E3..113FF
8567 NEWA, // 11400..1145B
8568 UNKNOWN, // 1145C
8569 NEWA, // 1145D..11461
8570 UNKNOWN, // 11462..1147F
8571 TIRHUTA, // 11480..114C7
8572 UNKNOWN, // 114C8..114CF
8573 TIRHUTA, // 114D0..114D9
8574 UNKNOWN, // 114DA..1157F
8575 SIDDHAM, // 11580..115B5
8576 UNKNOWN, // 115B6..115B7
8577 SIDDHAM, // 115B8..115DD
8578 UNKNOWN, // 115DE..115FF
8579 MODI, // 11600..11644
8580 UNKNOWN, // 11645..1164F
8581 MODI, // 11650..11659
8582 UNKNOWN, // 1165A..1165F
8583 MONGOLIAN, // 11660..1166C
8584 UNKNOWN, // 1166D..1167F
8585 TAKRI, // 11680..116B9
8586 UNKNOWN, // 116BA..116BF
8587 TAKRI, // 116C0..116C9
8588 UNKNOWN, // 116CA..116CF
8589 MYANMAR, // 116D0..116E3
8590 UNKNOWN, // 116E4..116FF
8591 AHOM, // 11700..1171A
8592 UNKNOWN, // 1171B..1171C
8593 AHOM, // 1171D..1172B
8594 UNKNOWN, // 1172C..1172F
8595 AHOM, // 11730..11746
8596 UNKNOWN, // 11747..117FF
8597 DOGRA, // 11800..1183B
8598 UNKNOWN, // 1183C..1189F
8599 WARANG_CITI, // 118A0..118F2
8600 UNKNOWN, // 118F3..118FE
8601 WARANG_CITI, // 118FF
8602 DIVES_AKURU, // 11900..11906
8603 UNKNOWN, // 11907..11908
8604 DIVES_AKURU, // 11909
8605 UNKNOWN, // 1190A..1190B
8606 DIVES_AKURU, // 1190C..11913
8607 UNKNOWN, // 11914
8608 DIVES_AKURU, // 11915..11916
8609 UNKNOWN, // 11917
8610 DIVES_AKURU, // 11918..11935
8611 UNKNOWN, // 11936
8612 DIVES_AKURU, // 11937..11938
8613 UNKNOWN, // 11939..1193A
8614 DIVES_AKURU, // 1193B..11946
8615 UNKNOWN, // 11947..1194F
8616 DIVES_AKURU, // 11950..11959
8617 UNKNOWN, // 1195A..1199F
8618 NANDINAGARI, // 119A0..119A7
8619 UNKNOWN, // 119A8..119A9
8620 NANDINAGARI, // 119AA..119D7
8621 UNKNOWN, // 119D8..119D9
8622 NANDINAGARI, // 119DA..119E4
8623 UNKNOWN, // 119E5..119FF
8624 ZANABAZAR_SQUARE, // 11A00..11A47
8625 UNKNOWN, // 11A48..11A4F
8626 SOYOMBO, // 11A50..11AA2
8627 UNKNOWN, // 11AA3..11AAF
8628 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8629 PAU_CIN_HAU, // 11AC0..11AF8
8630 UNKNOWN, // 11AF9..11AFF
8631 DEVANAGARI, // 11B00..11B09
8632 UNKNOWN, // 11B0A..11B5F
8633 SHARADA, // 11B60..11B67
8634 UNKNOWN, // 11B68..11BBF
8635 SUNUWAR, // 11BC0..11BE1
8636 UNKNOWN, // 11BE2..11BEF
8637 SUNUWAR, // 11BF0..11BF9
8638 UNKNOWN, // 11BFA..11BFF
8639 BHAIKSUKI, // 11C00..11C08
8640 UNKNOWN, // 11C09
8641 BHAIKSUKI, // 11C0A..11C36
8642 UNKNOWN, // 11C37
8643 BHAIKSUKI, // 11C38..11C45
8644 UNKNOWN, // 11C46..11C4F
8645 BHAIKSUKI, // 11C50..11C6C
8646 UNKNOWN, // 11C6D..11C6F
8647 MARCHEN, // 11C70..11C8F
8648 UNKNOWN, // 11C90..11C91
8649 MARCHEN, // 11C92..11CA7
8650 UNKNOWN, // 11CA8
8651 MARCHEN, // 11CA9..11CB6
8652 UNKNOWN, // 11CB7..11CFF
8653 MASARAM_GONDI, // 11D00..11D06
8654 UNKNOWN, // 11D07
8655 MASARAM_GONDI, // 11D08..11D09
8656 UNKNOWN, // 11D0A
8657 MASARAM_GONDI, // 11D0B..11D36
8658 UNKNOWN, // 11D37..11D39
8659 MASARAM_GONDI, // 11D3A
8660 UNKNOWN, // 11D3B
8661 MASARAM_GONDI, // 11D3C..11D3D
8662 UNKNOWN, // 11D3E
8663 MASARAM_GONDI, // 11D3F..11D47
8664 UNKNOWN, // 11D48..11D4F
8665 MASARAM_GONDI, // 11D50..11D59
8666 UNKNOWN, // 11D5A..11D5F
8667 GUNJALA_GONDI, // 11D60..11D65
8668 UNKNOWN, // 11D66
8669 GUNJALA_GONDI, // 11D67..11D68
8670 UNKNOWN, // 11D69
8671 GUNJALA_GONDI, // 11D6A..11D8E
8672 UNKNOWN, // 11D8F
8673 GUNJALA_GONDI, // 11D90..11D91
8674 UNKNOWN, // 11D92
8675 GUNJALA_GONDI, // 11D93..11D98
8676 UNKNOWN, // 11D99..11D9F
8677 GUNJALA_GONDI, // 11DA0..11DA9
8678 UNKNOWN, // 11DAA..11DAF
8679 TOLONG_SIKI, // 11DB0..11DDB
8680 UNKNOWN, // 11DDC..11DDF
8681 TOLONG_SIKI, // 11DE0..11DE9
8682 UNKNOWN, // 11DEA..11EDF
8683 MAKASAR, // 11EE0..11EF8
8684 UNKNOWN, // 11EF9..11EFF
8685 KAWI, // 11F00..11F10
8686 UNKNOWN, // 11F11
8687 KAWI, // 11F12..11F3A
8688 UNKNOWN, // 11F3B..11F3D
8689 KAWI, // 11F3E..11F5A
8690 UNKNOWN, // 11F5B..11FAF
8691 LISU, // 11FB0
8692 UNKNOWN, // 11FB1..11FBF
8693 TAMIL, // 11FC0..11FF1
8694 UNKNOWN, // 11FF2..11FFE
8695 TAMIL, // 11FFF
8696 CUNEIFORM, // 12000..12399
8697 UNKNOWN, // 1239A..123FF
8698 CUNEIFORM, // 12400..1246E
8699 UNKNOWN, // 1246F
8700 CUNEIFORM, // 12470..12474
8701 UNKNOWN, // 12475..1247F
8702 CUNEIFORM, // 12480..12543
8703 UNKNOWN, // 12544..12F8F
8704 CYPRO_MINOAN, // 12F90..12FF2
8705 UNKNOWN, // 12FF3..12FFF
8706 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8707 UNKNOWN, // 13456..1345F
8708 EGYPTIAN_HIEROGLYPHS, // 13460..143FA
8709 UNKNOWN, // 143FB..143FF
8710 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8711 UNKNOWN, // 14647..160FF
8712 GURUNG_KHEMA, // 16100..16139
8713 UNKNOWN, // 1613A..167FF
8714 BAMUM, // 16800..16A38
8715 UNKNOWN, // 16A39..16A3F
8716 MRO, // 16A40..16A5E
8717 UNKNOWN, // 16A5F
8718 MRO, // 16A60..16A69
8719 UNKNOWN, // 16A6A..16A6D
8720 MRO, // 16A6E..16A6F
8721 TANGSA, // 16A70..16ABE
8722 UNKNOWN, // 16ABF
8723 TANGSA, // 16AC0..16AC9
8724 UNKNOWN, // 16ACA..16ACF
8725 BASSA_VAH, // 16AD0..16AED
8726 UNKNOWN, // 16AEE..16AEF
8727 BASSA_VAH, // 16AF0..16AF5
8728 UNKNOWN, // 16AF6..16AFF
8729 PAHAWH_HMONG, // 16B00..16B45
8730 UNKNOWN, // 16B46..16B4F
8731 PAHAWH_HMONG, // 16B50..16B59
8732 UNKNOWN, // 16B5A
8733 PAHAWH_HMONG, // 16B5B..16B61
8734 UNKNOWN, // 16B62
8735 PAHAWH_HMONG, // 16B63..16B77
8736 UNKNOWN, // 16B78..16B7C
8737 PAHAWH_HMONG, // 16B7D..16B8F
8738 UNKNOWN, // 16B90..16D3F
8739 KIRAT_RAI, // 16D40..16D79
8740 UNKNOWN, // 16D7A..16E3F
8741 MEDEFAIDRIN, // 16E40..16E9A
8742 UNKNOWN, // 16E9B..16E9F
8743 BERIA_ERFE, // 16EA0..16EB8
8744 UNKNOWN, // 16EB9..16EBA
8745 BERIA_ERFE, // 16EBB..16ED3
8746 UNKNOWN, // 16ED4..16EFF
8747 MIAO, // 16F00..16F4A
8748 UNKNOWN, // 16F4B..16F4E
8749 MIAO, // 16F4F..16F87
8750 UNKNOWN, // 16F88..16F8E
8751 MIAO, // 16F8F..16F9F
8752 UNKNOWN, // 16FA0..16FDF
8753 TANGUT, // 16FE0
8754 NUSHU, // 16FE1
8755 HAN, // 16FE2..16FE3
8756 KHITAN_SMALL_SCRIPT, // 16FE4
8757 UNKNOWN, // 16FE5..16FEF
8758 HAN, // 16FF0..16FF6
8759 UNKNOWN, // 16FF7..16FFF
8760 TANGUT, // 17000..18AFF
8761 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8762 UNKNOWN, // 18CD6..18CFE
8763 KHITAN_SMALL_SCRIPT, // 18CFF
8764 TANGUT, // 18D00..18D1E
8765 UNKNOWN, // 18D1F..18D7F
8766 TANGUT, // 18D80..18DF2
8767 UNKNOWN, // 18DF3..1AFEF
8768 KATAKANA, // 1AFF0..1AFF3
8769 UNKNOWN, // 1AFF4
8770 KATAKANA, // 1AFF5..1AFFB
8771 UNKNOWN, // 1AFFC
8772 KATAKANA, // 1AFFD..1AFFE
8773 UNKNOWN, // 1AFFF
8774 KATAKANA, // 1B000
8775 HIRAGANA, // 1B001..1B11F
8776 KATAKANA, // 1B120..1B122
8777 UNKNOWN, // 1B123..1B131
8778 HIRAGANA, // 1B132
8779 UNKNOWN, // 1B133..1B14F
8780 HIRAGANA, // 1B150..1B152
8781 UNKNOWN, // 1B153..1B154
8782 KATAKANA, // 1B155
8783 UNKNOWN, // 1B156..1B163
8784 KATAKANA, // 1B164..1B167
8785 UNKNOWN, // 1B168..1B16F
8786 NUSHU, // 1B170..1B2FB
8787 UNKNOWN, // 1B2FC..1BBFF
8788 DUPLOYAN, // 1BC00..1BC6A
8789 UNKNOWN, // 1BC6B..1BC6F
8790 DUPLOYAN, // 1BC70..1BC7C
8791 UNKNOWN, // 1BC7D..1BC7F
8792 DUPLOYAN, // 1BC80..1BC88
8793 UNKNOWN, // 1BC89..1BC8F
8794 DUPLOYAN, // 1BC90..1BC99
8795 UNKNOWN, // 1BC9A..1BC9B
8796 DUPLOYAN, // 1BC9C..1BC9F
8797 COMMON, // 1BCA0..1BCA3
8798 UNKNOWN, // 1BCA4..1CBFF
8799 COMMON, // 1CC00..1CCFC
8800 UNKNOWN, // 1CCFD..1CCFF
8801 COMMON, // 1CD00..1CEB3
8802 UNKNOWN, // 1CEB4..1CEB9
8803 COMMON, // 1CEBA..1CED0
8804 UNKNOWN, // 1CED1..1CEDF
8805 COMMON, // 1CEE0..1CEF0
8806 UNKNOWN, // 1CEF1..1CEFF
8807 INHERITED, // 1CF00..1CF2D
8808 UNKNOWN, // 1CF2E..1CF2F
8809 INHERITED, // 1CF30..1CF46
8810 UNKNOWN, // 1CF47..1CF4F
8811 COMMON, // 1CF50..1CFC3
8812 UNKNOWN, // 1CFC4..1CFFF
8813 COMMON, // 1D000..1D0F5
8814 UNKNOWN, // 1D0F6..1D0FF
8815 COMMON, // 1D100..1D126
8816 UNKNOWN, // 1D127..1D128
8817 COMMON, // 1D129..1D166
8818 INHERITED, // 1D167..1D169
8819 COMMON, // 1D16A..1D17A
8820 INHERITED, // 1D17B..1D182
8821 COMMON, // 1D183..1D184
8822 INHERITED, // 1D185..1D18B
8823 COMMON, // 1D18C..1D1A9
8824 INHERITED, // 1D1AA..1D1AD
8825 COMMON, // 1D1AE..1D1EA
8826 UNKNOWN, // 1D1EB..1D1FF
8827 GREEK, // 1D200..1D245
8828 UNKNOWN, // 1D246..1D2BF
8829 COMMON, // 1D2C0..1D2D3
8830 UNKNOWN, // 1D2D4..1D2DF
8831 COMMON, // 1D2E0..1D2F3
8832 UNKNOWN, // 1D2F4..1D2FF
8833 COMMON, // 1D300..1D356
8834 UNKNOWN, // 1D357..1D35F
8835 COMMON, // 1D360..1D378
8836 UNKNOWN, // 1D379..1D3FF
8837 COMMON, // 1D400..1D454
8838 UNKNOWN, // 1D455
8839 COMMON, // 1D456..1D49C
8840 UNKNOWN, // 1D49D
8841 COMMON, // 1D49E..1D49F
8842 UNKNOWN, // 1D4A0..1D4A1
8843 COMMON, // 1D4A2
8844 UNKNOWN, // 1D4A3..1D4A4
8845 COMMON, // 1D4A5..1D4A6
8846 UNKNOWN, // 1D4A7..1D4A8
8847 COMMON, // 1D4A9..1D4AC
8848 UNKNOWN, // 1D4AD
8849 COMMON, // 1D4AE..1D4B9
8850 UNKNOWN, // 1D4BA
8851 COMMON, // 1D4BB
8852 UNKNOWN, // 1D4BC
8853 COMMON, // 1D4BD..1D4C3
8854 UNKNOWN, // 1D4C4
8855 COMMON, // 1D4C5..1D505
8856 UNKNOWN, // 1D506
8857 COMMON, // 1D507..1D50A
8858 UNKNOWN, // 1D50B..1D50C
8859 COMMON, // 1D50D..1D514
8860 UNKNOWN, // 1D515
8861 COMMON, // 1D516..1D51C
8862 UNKNOWN, // 1D51D
8863 COMMON, // 1D51E..1D539
8864 UNKNOWN, // 1D53A
8865 COMMON, // 1D53B..1D53E
8866 UNKNOWN, // 1D53F
8867 COMMON, // 1D540..1D544
8868 UNKNOWN, // 1D545
8869 COMMON, // 1D546
8870 UNKNOWN, // 1D547..1D549
8871 COMMON, // 1D54A..1D550
8872 UNKNOWN, // 1D551
8873 COMMON, // 1D552..1D6A5
8874 UNKNOWN, // 1D6A6..1D6A7
8875 COMMON, // 1D6A8..1D7CB
8876 UNKNOWN, // 1D7CC..1D7CD
8877 COMMON, // 1D7CE..1D7FF
8878 SIGNWRITING, // 1D800..1DA8B
8879 UNKNOWN, // 1DA8C..1DA9A
8880 SIGNWRITING, // 1DA9B..1DA9F
8881 UNKNOWN, // 1DAA0
8882 SIGNWRITING, // 1DAA1..1DAAF
8883 UNKNOWN, // 1DAB0..1DEFF
8884 LATIN, // 1DF00..1DF1E
8885 UNKNOWN, // 1DF1F..1DF24
8886 LATIN, // 1DF25..1DF2A
8887 UNKNOWN, // 1DF2B..1DFFF
8888 GLAGOLITIC, // 1E000..1E006
8889 UNKNOWN, // 1E007
8890 GLAGOLITIC, // 1E008..1E018
8891 UNKNOWN, // 1E019..1E01A
8892 GLAGOLITIC, // 1E01B..1E021
8893 UNKNOWN, // 1E022
8894 GLAGOLITIC, // 1E023..1E024
8895 UNKNOWN, // 1E025
8896 GLAGOLITIC, // 1E026..1E02A
8897 UNKNOWN, // 1E02B..1E02F
8898 CYRILLIC, // 1E030..1E06D
8899 UNKNOWN, // 1E06E..1E08E
8900 CYRILLIC, // 1E08F
8901 UNKNOWN, // 1E090..1E0FF
8902 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8903 UNKNOWN, // 1E12D..1E12F
8904 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8905 UNKNOWN, // 1E13E..1E13F
8906 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8907 UNKNOWN, // 1E14A..1E14D
8908 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8909 UNKNOWN, // 1E150..1E28F
8910 TOTO, // 1E290..1E2AE
8911 UNKNOWN, // 1E2AF..1E2BF
8912 WANCHO, // 1E2C0..1E2F9
8913 UNKNOWN, // 1E2FA..1E2FE
8914 WANCHO, // 1E2FF
8915 UNKNOWN, // 1E300..1E4CF
8916 NAG_MUNDARI, // 1E4D0..1E4F9
8917 UNKNOWN, // 1E4FA..1E5CF
8918 OL_ONAL, // 1E5D0..1E5FA
8919 UNKNOWN, // 1E5FB..1E5FE
8920 OL_ONAL, // 1E5FF
8921 UNKNOWN, // 1E600..1E6BF
8922 TAI_YO, // 1E6C0..1E6DE
8923 UNKNOWN, // 1E6DF
8924 TAI_YO, // 1E6E0..1E6F5
8925 UNKNOWN, // 1E6F6..1E6FD
8926 TAI_YO, // 1E6FE..1E6FF
8927 UNKNOWN, // 1E700..1E7DF
8928 ETHIOPIC, // 1E7E0..1E7E6
8929 UNKNOWN, // 1E7E7
8930 ETHIOPIC, // 1E7E8..1E7EB
8931 UNKNOWN, // 1E7EC
8932 ETHIOPIC, // 1E7ED..1E7EE
8933 UNKNOWN, // 1E7EF
8934 ETHIOPIC, // 1E7F0..1E7FE
8935 UNKNOWN, // 1E7FF
8936 MENDE_KIKAKUI, // 1E800..1E8C4
8937 UNKNOWN, // 1E8C5..1E8C6
8938 MENDE_KIKAKUI, // 1E8C7..1E8D6
8939 UNKNOWN, // 1E8D7..1E8FF
8940 ADLAM, // 1E900..1E94B
8941 UNKNOWN, // 1E94C..1E94F
8942 ADLAM, // 1E950..1E959
8943 UNKNOWN, // 1E95A..1E95D
8944 ADLAM, // 1E95E..1E95F
8945 UNKNOWN, // 1E960..1EC70
8946 COMMON, // 1EC71..1ECB4
8947 UNKNOWN, // 1ECB5..1ED00
8948 COMMON, // 1ED01..1ED3D
8949 UNKNOWN, // 1ED3E..1EDFF
8950 ARABIC, // 1EE00..1EE03
8951 UNKNOWN, // 1EE04
8952 ARABIC, // 1EE05..1EE1F
8953 UNKNOWN, // 1EE20
8954 ARABIC, // 1EE21..1EE22
8955 UNKNOWN, // 1EE23
8956 ARABIC, // 1EE24
8957 UNKNOWN, // 1EE25..1EE26
8958 ARABIC, // 1EE27
8959 UNKNOWN, // 1EE28
8960 ARABIC, // 1EE29..1EE32
8961 UNKNOWN, // 1EE33
8962 ARABIC, // 1EE34..1EE37
8963 UNKNOWN, // 1EE38
8964 ARABIC, // 1EE39
8965 UNKNOWN, // 1EE3A
8966 ARABIC, // 1EE3B
8967 UNKNOWN, // 1EE3C..1EE41
8968 ARABIC, // 1EE42
8969 UNKNOWN, // 1EE43..1EE46
8970 ARABIC, // 1EE47
8971 UNKNOWN, // 1EE48
8972 ARABIC, // 1EE49
8973 UNKNOWN, // 1EE4A
8974 ARABIC, // 1EE4B
8975 UNKNOWN, // 1EE4C
8976 ARABIC, // 1EE4D..1EE4F
8977 UNKNOWN, // 1EE50
8978 ARABIC, // 1EE51..1EE52
8979 UNKNOWN, // 1EE53
8980 ARABIC, // 1EE54
8981 UNKNOWN, // 1EE55..1EE56
8982 ARABIC, // 1EE57
8983 UNKNOWN, // 1EE58
8984 ARABIC, // 1EE59
8985 UNKNOWN, // 1EE5A
8986 ARABIC, // 1EE5B
8987 UNKNOWN, // 1EE5C
8988 ARABIC, // 1EE5D
8989 UNKNOWN, // 1EE5E
8990 ARABIC, // 1EE5F
8991 UNKNOWN, // 1EE60
8992 ARABIC, // 1EE61..1EE62
8993 UNKNOWN, // 1EE63
8994 ARABIC, // 1EE64
8995 UNKNOWN, // 1EE65..1EE66
8996 ARABIC, // 1EE67..1EE6A
8997 UNKNOWN, // 1EE6B
8998 ARABIC, // 1EE6C..1EE72
8999 UNKNOWN, // 1EE73
9000 ARABIC, // 1EE74..1EE77
9001 UNKNOWN, // 1EE78
9002 ARABIC, // 1EE79..1EE7C
9003 UNKNOWN, // 1EE7D
9004 ARABIC, // 1EE7E
9005 UNKNOWN, // 1EE7F
9006 ARABIC, // 1EE80..1EE89
9007 UNKNOWN, // 1EE8A
9008 ARABIC, // 1EE8B..1EE9B
9009 UNKNOWN, // 1EE9C..1EEA0
9010 ARABIC, // 1EEA1..1EEA3
9011 UNKNOWN, // 1EEA4
9012 ARABIC, // 1EEA5..1EEA9
9013 UNKNOWN, // 1EEAA
9014 ARABIC, // 1EEAB..1EEBB
9015 UNKNOWN, // 1EEBC..1EEEF
9016 ARABIC, // 1EEF0..1EEF1
9017 UNKNOWN, // 1EEF2..1EFFF
9018 COMMON, // 1F000..1F02B
9019 UNKNOWN, // 1F02C..1F02F
9020 COMMON, // 1F030..1F093
9021 UNKNOWN, // 1F094..1F09F
9022 COMMON, // 1F0A0..1F0AE
9023 UNKNOWN, // 1F0AF..1F0B0
9024 COMMON, // 1F0B1..1F0BF
9025 UNKNOWN, // 1F0C0
9026 COMMON, // 1F0C1..1F0CF
9027 UNKNOWN, // 1F0D0
9028 COMMON, // 1F0D1..1F0F5
9029 UNKNOWN, // 1F0F6..1F0FF
9030 COMMON, // 1F100..1F1AD
9031 UNKNOWN, // 1F1AE..1F1E5
9032 COMMON, // 1F1E6..1F1FF
9033 HIRAGANA, // 1F200
9034 COMMON, // 1F201..1F202
9035 UNKNOWN, // 1F203..1F20F
9036 COMMON, // 1F210..1F23B
9037 UNKNOWN, // 1F23C..1F23F
9038 COMMON, // 1F240..1F248
9039 UNKNOWN, // 1F249..1F24F
9040 COMMON, // 1F250..1F251
9041 UNKNOWN, // 1F252..1F25F
9042 COMMON, // 1F260..1F265
9043 UNKNOWN, // 1F266..1F2FF
9044 COMMON, // 1F300..1F6D8
9045 UNKNOWN, // 1F6D9..1F6DB
9046 COMMON, // 1F6DC..1F6EC
9047 UNKNOWN, // 1F6ED..1F6EF
9048 COMMON, // 1F6F0..1F6FC
9049 UNKNOWN, // 1F6FD..1F6FF
9050 COMMON, // 1F700..1F7D9
9051 UNKNOWN, // 1F7DA..1F7DF
9052 COMMON, // 1F7E0..1F7EB
9053 UNKNOWN, // 1F7EC..1F7EF
9054 COMMON, // 1F7F0
9055 UNKNOWN, // 1F7F1..1F7FF
9056 COMMON, // 1F800..1F80B
9057 UNKNOWN, // 1F80C..1F80F
9058 COMMON, // 1F810..1F847
9059 UNKNOWN, // 1F848..1F84F
9060 COMMON, // 1F850..1F859
9061 UNKNOWN, // 1F85A..1F85F
9062 COMMON, // 1F860..1F887
9063 UNKNOWN, // 1F888..1F88F
9064 COMMON, // 1F890..1F8AD
9065 UNKNOWN, // 1F8AE..1F8AF
9066 COMMON, // 1F8B0..1F8BB
9067 UNKNOWN, // 1F8BC..1F8BF
9068 COMMON, // 1F8C0..1F8C1
9069 UNKNOWN, // 1F8C2..1F8CF
9070 COMMON, // 1F8D0..1F8D8
9071 UNKNOWN, // 1F8D9..1F8FF
9072 COMMON, // 1F900..1FA57
9073 UNKNOWN, // 1FA58..1FA5F
9074 COMMON, // 1FA60..1FA6D
9075 UNKNOWN, // 1FA6E..1FA6F
9076 COMMON, // 1FA70..1FA7C
9077 UNKNOWN, // 1FA7D..1FA7F
9078 COMMON, // 1FA80..1FA8A
9079 UNKNOWN, // 1FA8B..1FA8D
9080 COMMON, // 1FA8E..1FAC6
9081 UNKNOWN, // 1FAC7
9082 COMMON, // 1FAC8
9083 UNKNOWN, // 1FAC9..1FACC
9084 COMMON, // 1FACD..1FADC
9085 UNKNOWN, // 1FADD..1FADE
9086 COMMON, // 1FADF..1FAEA
9087 UNKNOWN, // 1FAEB..1FAEE
9088 COMMON, // 1FAEF..1FAF8
9089 UNKNOWN, // 1FAF9..1FAFF
9090 COMMON, // 1FB00..1FB92
9091 UNKNOWN, // 1FB93
9092 COMMON, // 1FB94..1FBFA
9093 UNKNOWN, // 1FBFB..1FFFF
9094 HAN, // 20000..2A6DF
9095 UNKNOWN, // 2A6E0..2A6FF
9096 HAN, // 2A700..2B81D
9097 UNKNOWN, // 2B81E..2B81F
9098 HAN, // 2B820..2CEAD
9099 UNKNOWN, // 2CEAE..2CEAF
9100 HAN, // 2CEB0..2EBE0
9101 UNKNOWN, // 2EBE1..2EBEF
9102 HAN, // 2EBF0..2EE5D
9103 UNKNOWN, // 2EE5E..2F7FF
9104 HAN, // 2F800..2FA1D
9105 UNKNOWN, // 2FA1E..2FFFF
9106 HAN, // 30000..3134A
9107 UNKNOWN, // 3134B..3134F
9108 HAN, // 31350..33479
9109 UNKNOWN, // 3347A..E0000
9110 COMMON, // E0001
9111 UNKNOWN, // E0002..E001F
9112 COMMON, // E0020..E007F
9113 UNKNOWN, // E0080..E00FF
9114 INHERITED, // E0100..E01EF
9115 UNKNOWN, // E01F0..10FFFF
9116 };
9117
9118 private static final HashMap<String, Character.UnicodeScript> aliases;
9119 static {
9120 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
9121 aliases.put("ADLM", ADLAM);
9122 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
9123 aliases.put("AHOM", AHOM);
9124 aliases.put("ARAB", ARABIC);
9125 aliases.put("ARMI", IMPERIAL_ARAMAIC);
9126 aliases.put("ARMN", ARMENIAN);
9127 aliases.put("AVST", AVESTAN);
9128 aliases.put("BALI", BALINESE);
9129 aliases.put("BAMU", BAMUM);
9130 aliases.put("BASS", BASSA_VAH);
9131 aliases.put("BATK", BATAK);
9132 aliases.put("BENG", BENGALI);
9133 aliases.put("BERF", BERIA_ERFE);
9134 aliases.put("BHKS", BHAIKSUKI);
9135 aliases.put("BOPO", BOPOMOFO);
9136 aliases.put("BRAH", BRAHMI);
9137 aliases.put("BRAI", BRAILLE);
9138 aliases.put("BUGI", BUGINESE);
9139 aliases.put("BUHD", BUHID);
9140 aliases.put("CAKM", CHAKMA);
9141 aliases.put("CANS", CANADIAN_ABORIGINAL);
9142 aliases.put("CARI", CARIAN);
9143 aliases.put("CHAM", CHAM);
9144 aliases.put("CHER", CHEROKEE);
9145 aliases.put("CHRS", CHORASMIAN);
9146 aliases.put("COPT", COPTIC);
9147 aliases.put("CPMN", CYPRO_MINOAN);
9148 aliases.put("CPRT", CYPRIOT);
9149 aliases.put("CYRL", CYRILLIC);
9150 aliases.put("DEVA", DEVANAGARI);
9151 aliases.put("DIAK", DIVES_AKURU);
9152 aliases.put("DOGR", DOGRA);
9153 aliases.put("DSRT", DESERET);
9154 aliases.put("DUPL", DUPLOYAN);
9155 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
9156 aliases.put("ELBA", ELBASAN);
9157 aliases.put("ELYM", ELYMAIC);
9158 aliases.put("ETHI", ETHIOPIC);
9159 aliases.put("GARA", GARAY);
9160 aliases.put("GEOR", GEORGIAN);
9161 aliases.put("GLAG", GLAGOLITIC);
9162 aliases.put("GONG", GUNJALA_GONDI);
9163 aliases.put("GONM", MASARAM_GONDI);
9164 aliases.put("GOTH", GOTHIC);
9165 aliases.put("GRAN", GRANTHA);
9166 aliases.put("GREK", GREEK);
9167 aliases.put("GUJR", GUJARATI);
9168 aliases.put("GUKH", GURUNG_KHEMA);
9169 aliases.put("GURU", GURMUKHI);
9170 aliases.put("HANG", HANGUL);
9171 aliases.put("HANI", HAN);
9172 aliases.put("HANO", HANUNOO);
9173 aliases.put("HATR", HATRAN);
9174 aliases.put("HEBR", HEBREW);
9175 aliases.put("HIRA", HIRAGANA);
9176 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
9177 aliases.put("HMNG", PAHAWH_HMONG);
9178 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
9179 aliases.put("HUNG", OLD_HUNGARIAN);
9180 aliases.put("ITAL", OLD_ITALIC);
9181 aliases.put("JAVA", JAVANESE);
9182 aliases.put("KALI", KAYAH_LI);
9183 aliases.put("KANA", KATAKANA);
9184 aliases.put("KAWI", KAWI);
9185 aliases.put("KHAR", KHAROSHTHI);
9186 aliases.put("KHMR", KHMER);
9187 aliases.put("KHOJ", KHOJKI);
9188 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
9189 aliases.put("KNDA", KANNADA);
9190 aliases.put("KRAI", KIRAT_RAI);
9191 aliases.put("KTHI", KAITHI);
9192 aliases.put("LANA", TAI_THAM);
9193 aliases.put("LAOO", LAO);
9194 aliases.put("LATN", LATIN);
9195 aliases.put("LEPC", LEPCHA);
9196 aliases.put("LIMB", LIMBU);
9197 aliases.put("LINA", LINEAR_A);
9198 aliases.put("LINB", LINEAR_B);
9199 aliases.put("LISU", LISU);
9200 aliases.put("LYCI", LYCIAN);
9201 aliases.put("LYDI", LYDIAN);
9202 aliases.put("MAHJ", MAHAJANI);
9203 aliases.put("MAKA", MAKASAR);
9204 aliases.put("MAND", MANDAIC);
9205 aliases.put("MANI", MANICHAEAN);
9206 aliases.put("MARC", MARCHEN);
9207 aliases.put("MEDF", MEDEFAIDRIN);
9208 aliases.put("MEND", MENDE_KIKAKUI);
9209 aliases.put("MERC", MEROITIC_CURSIVE);
9210 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
9211 aliases.put("MLYM", MALAYALAM);
9212 aliases.put("MODI", MODI);
9213 aliases.put("MONG", MONGOLIAN);
9214 aliases.put("MROO", MRO);
9215 aliases.put("MTEI", MEETEI_MAYEK);
9216 aliases.put("MULT", MULTANI);
9217 aliases.put("MYMR", MYANMAR);
9218 aliases.put("NAGM", NAG_MUNDARI);
9219 aliases.put("NAND", NANDINAGARI);
9220 aliases.put("NARB", OLD_NORTH_ARABIAN);
9221 aliases.put("NBAT", NABATAEAN);
9222 aliases.put("NEWA", NEWA);
9223 aliases.put("NKOO", NKO);
9224 aliases.put("NSHU", NUSHU);
9225 aliases.put("OGAM", OGHAM);
9226 aliases.put("OLCK", OL_CHIKI);
9227 aliases.put("ONAO", OL_ONAL);
9228 aliases.put("ORKH", OLD_TURKIC);
9229 aliases.put("ORYA", ORIYA);
9230 aliases.put("OSGE", OSAGE);
9231 aliases.put("OSMA", OSMANYA);
9232 aliases.put("OUGR", OLD_UYGHUR);
9233 aliases.put("PALM", PALMYRENE);
9234 aliases.put("PAUC", PAU_CIN_HAU);
9235 aliases.put("PERM", OLD_PERMIC);
9236 aliases.put("PHAG", PHAGS_PA);
9237 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
9238 aliases.put("PHLP", PSALTER_PAHLAVI);
9239 aliases.put("PHNX", PHOENICIAN);
9240 aliases.put("PLRD", MIAO);
9241 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
9242 aliases.put("RJNG", REJANG);
9243 aliases.put("ROHG", HANIFI_ROHINGYA);
9244 aliases.put("RUNR", RUNIC);
9245 aliases.put("SAMR", SAMARITAN);
9246 aliases.put("SARB", OLD_SOUTH_ARABIAN);
9247 aliases.put("SAUR", SAURASHTRA);
9248 aliases.put("SGNW", SIGNWRITING);
9249 aliases.put("SHAW", SHAVIAN);
9250 aliases.put("SHRD", SHARADA);
9251 aliases.put("SIDD", SIDDHAM);
9252 aliases.put("SIDT", SIDETIC);
9253 aliases.put("SIND", KHUDAWADI);
9254 aliases.put("SINH", SINHALA);
9255 aliases.put("SOGD", SOGDIAN);
9256 aliases.put("SOGO", OLD_SOGDIAN);
9257 aliases.put("SORA", SORA_SOMPENG);
9258 aliases.put("SOYO", SOYOMBO);
9259 aliases.put("SUND", SUNDANESE);
9260 aliases.put("SUNU", SUNUWAR);
9261 aliases.put("SYLO", SYLOTI_NAGRI);
9262 aliases.put("SYRC", SYRIAC);
9263 aliases.put("TAGB", TAGBANWA);
9264 aliases.put("TAKR", TAKRI);
9265 aliases.put("TALE", TAI_LE);
9266 aliases.put("TALU", NEW_TAI_LUE);
9267 aliases.put("TAML", TAMIL);
9268 aliases.put("TANG", TANGUT);
9269 aliases.put("TAVT", TAI_VIET);
9270 aliases.put("TAYO", TAI_YO);
9271 aliases.put("TELU", TELUGU);
9272 aliases.put("TFNG", TIFINAGH);
9273 aliases.put("TGLG", TAGALOG);
9274 aliases.put("THAA", THAANA);
9275 aliases.put("THAI", THAI);
9276 aliases.put("TIBT", TIBETAN);
9277 aliases.put("TIRH", TIRHUTA);
9278 aliases.put("TNSA", TANGSA);
9279 aliases.put("TODR", TODHRI);
9280 aliases.put("TOLS", TOLONG_SIKI);
9281 aliases.put("TOTO", TOTO);
9282 aliases.put("TUTG", TULU_TIGALARI);
9283 aliases.put("UGAR", UGARITIC);
9284 aliases.put("VAII", VAI);
9285 aliases.put("VITH", VITHKUQI);
9286 aliases.put("WARA", WARANG_CITI);
9287 aliases.put("WCHO", WANCHO);
9288 aliases.put("XPEO", OLD_PERSIAN);
9289 aliases.put("XSUX", CUNEIFORM);
9290 aliases.put("YEZI", YEZIDI);
9291 aliases.put("YIII", YI);
9292 aliases.put("ZANB", ZANABAZAR_SQUARE);
9293 aliases.put("ZINH", INHERITED);
9294 aliases.put("ZYYY", COMMON);
9295 aliases.put("ZZZZ", UNKNOWN);
9296 }
9297
9298 /**
9299 * Returns the enum constant representing the Unicode script of which
9300 * the given character (Unicode code point) is assigned to.
9301 *
9302 * @param codePoint the character (Unicode code point) in question.
9303 * @return The {@code UnicodeScript} constant representing the
9304 * Unicode script of which this character is assigned to.
9305 *
9306 * @throws IllegalArgumentException if the specified
9307 * {@code codePoint} is an invalid Unicode code point.
9308 * @see Character#isValidCodePoint(int)
9309 *
9310 */
9311 public static UnicodeScript of(int codePoint) {
9312 if (!isValidCodePoint(codePoint))
9313 throw new IllegalArgumentException(
9314 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9315 int type = getType(codePoint);
9316 // leave SURROGATE and PRIVATE_USE for table lookup
9317 if (type == UNASSIGNED)
9318 return UNKNOWN;
9319 int index = Arrays.binarySearch(scriptStarts, codePoint);
9320 if (index < 0)
9321 index = -index - 2;
9322 return scripts[index];
9323 }
9324
9325 /**
9326 * Returns the UnicodeScript constant with the given Unicode script
9327 * name or the script name alias. Script names and their aliases are
9328 * determined by The Unicode Standard. The files {@code Scripts.txt}
9329 * and {@code PropertyValueAliases.txt} define script names
9330 * and the script name aliases for a particular version of the
9331 * standard. The {@link Character} class specifies the version of
9332 * the standard that it supports.
9333 * <p>
9334 * Character case is ignored for all of the valid script names.
9335 * The en_US locale's case mapping rules are used to provide
9336 * case-insensitive string comparisons for script name validation.
9337 *
9338 * @param scriptName A {@code UnicodeScript} name.
9339 * @return The {@code UnicodeScript} constant identified
9340 * by {@code scriptName}
9341 * @throws IllegalArgumentException if {@code scriptName} is an
9342 * invalid name
9343 * @throws NullPointerException if {@code scriptName} is null
9344 */
9345 public static final UnicodeScript forName(String scriptName) {
9346 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
9347 //.replace(' ', '_'));
9348 UnicodeScript sc = aliases.get(scriptName);
9349 if (sc != null)
9350 return sc;
9351 return valueOf(scriptName);
9352 }
9353 }
9354
9355 /**
9356 * The value of the {@code Character}.
9357 *
9358 * @serial
9359 */
9360 private final char value;
9361
9362 /** use serialVersionUID from JDK 1.0.2 for interoperability */
9363 @java.io.Serial
9364 private static final long serialVersionUID = 3786198910865385080L;
9365
9366 /**
9367 * Constructs a newly allocated {@code Character} object that
9368 * represents the specified {@code char} value.
9369 *
9370 * @param value the value to be represented by the
9371 * {@code Character} object.
9372 *
9373 * @deprecated
9374 * It is rarely appropriate to use this constructor. The static factory
9375 * {@link #valueOf(char)} is generally a better choice, as it is
9376 * likely to yield significantly better space and time performance.
9377 */
9378 @Deprecated(since="9")
9379 public Character(char value) {
9380 this.value = value;
9381 }
9382
9383 @AOTSafeClassInitializer
9384 private static final class CharacterCache {
9385 private CharacterCache(){}
9386
9387 @Stable
9388 static final Character[] cache;
9389 static Character[] archivedCache;
9390
9391 static {
9392 int size = 127 + 1;
9393
9394 // Load and use the archived cache if it exists
9395 CDS.initializeFromArchive(CharacterCache.class);
9396 if (archivedCache == null) {
9397 Character[] c = new Character[size];
9398 for (int i = 0; i < size; i++) {
9399 c[i] = new Character((char) i);
9400 }
9401 archivedCache = c;
9402 }
9403 cache = archivedCache;
9404 assert cache.length == size;
9405 }
9406 }
9407
9408 /**
9409 * Returns a {@code Character} instance representing the specified
9410 * {@code char} value.
9411 * If a new {@code Character} instance is not required, this method
9412 * should generally be used in preference to the constructor
9413 * {@link #Character(char)}, as this method is likely to yield
9414 * significantly better space and time performance by caching
9415 * frequently requested values.
9416 *
9417 * This method will always cache values in the range {@code
9418 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9419 * cache other values outside of this range.
9420 *
9421 * @param c a char value.
9422 * @return a {@code Character} instance representing {@code c}.
9423 * @since 1.5
9424 */
9425 @IntrinsicCandidate
9426 public static Character valueOf(char c) {
9427 if (c <= 127) { // must cache
9428 return CharacterCache.cache[(int)c];
9429 }
9430 return new Character(c);
9431 }
9432
9433 /**
9434 * Returns the value of this {@code Character} object.
9435 * @return the primitive {@code char} value represented by
9436 * this object.
9437 */
9438 @IntrinsicCandidate
9439 public char charValue() {
9440 return value;
9441 }
9442
9443 /**
9444 * Returns a hash code for this {@code Character}; equal to the result
9445 * of invoking {@code charValue()}.
9446 *
9447 * @return a hash code value for this {@code Character}
9448 */
9449 @Override
9450 public int hashCode() {
9451 return Character.hashCode(value);
9452 }
9453
9454 /**
9455 * Returns a hash code for a {@code char} value; compatible with
9456 * {@code Character.hashCode()}.
9457 *
9458 * @since 1.8
9459 *
9460 * @param value The {@code char} for which to return a hash code.
9461 * @return a hash code value for a {@code char} value.
9462 */
9463 public static int hashCode(char value) {
9464 return (int)value;
9465 }
9466
9467 /**
9468 * Compares this object against the specified object.
9469 * The result is {@code true} if and only if the argument is not
9470 * {@code null} and is a {@code Character} object that
9471 * represents the same {@code char} value as this object.
9472 *
9473 * @param obj the object to compare with.
9474 * @return {@code true} if the objects are the same;
9475 * {@code false} otherwise.
9476 */
9477 public boolean equals(Object obj) {
9478 if (obj instanceof Character c) {
9479 return value == c.charValue();
9480 }
9481 return false;
9482 }
9483
9484 /**
9485 * Returns a {@code String} object representing this
9486 * {@code Character}'s value. The result is a string of
9487 * length 1 whose sole component is the primitive
9488 * {@code char} value represented by this
9489 * {@code Character} object.
9490 *
9491 * @return a string representation of this object.
9492 */
9493 @Override
9494 public String toString() {
9495 return String.valueOf(value);
9496 }
9497
9498 /**
9499 * Returns a {@code String} object representing the
9500 * specified {@code char}. The result is a string of length
9501 * 1 consisting solely of the specified {@code char}.
9502 *
9503 * @apiNote This method cannot handle <a
9504 * href="#supplementary"> supplementary characters</a>. To support
9505 * all Unicode characters, including supplementary characters, use
9506 * the {@link #toString(int)} method.
9507 *
9508 * @param c the {@code char} to be converted
9509 * @return the string representation of the specified {@code char}
9510 * @since 1.4
9511 */
9512 public static String toString(char c) {
9513 return String.valueOf(c);
9514 }
9515
9516 /**
9517 * Returns a {@code String} object representing the
9518 * specified character (Unicode code point). The result is a string of
9519 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9520 *
9521 * @param codePoint the {@code codePoint} to be converted
9522 * @return the string representation of the specified {@code codePoint}
9523 * @throws IllegalArgumentException if the specified
9524 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9525 * valid Unicode code point}.
9526 * @since 11
9527 */
9528 public static String toString(int codePoint) {
9529 return String.valueOfCodePoint(codePoint);
9530 }
9531
9532 /**
9533 * Determines whether the specified code point is a valid
9534 * <a href="http://www.unicode.org/glossary/#code_point">
9535 * Unicode code point value</a>.
9536 *
9537 * @param codePoint the Unicode code point to be tested
9538 * @return {@code true} if the specified code point value is between
9539 * {@link #MIN_CODE_POINT} and
9540 * {@link #MAX_CODE_POINT} inclusive;
9541 * {@code false} otherwise.
9542 * @since 1.5
9543 */
9544 public static boolean isValidCodePoint(int codePoint) {
9545 // Optimized form of:
9546 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9547 int plane = codePoint >>> 16;
9548 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9549 }
9550
9551 /**
9552 * Determines whether the specified character (Unicode code point)
9553 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9554 * Such code points can be represented using a single {@code char}.
9555 *
9556 * @param codePoint the character (Unicode code point) to be tested
9557 * @return {@code true} if the specified code point is between
9558 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9559 * {@code false} otherwise.
9560 * @since 1.7
9561 */
9562 public static boolean isBmpCodePoint(int codePoint) {
9563 return codePoint >>> 16 == 0;
9564 // Optimized form of:
9565 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9566 // We consistently use logical shift (>>>) to facilitate
9567 // additional runtime optimizations.
9568 }
9569
9570 /**
9571 * Determines whether the specified character (Unicode code point)
9572 * is in the <a href="#supplementary">supplementary character</a> range.
9573 *
9574 * @param codePoint the character (Unicode code point) to be tested
9575 * @return {@code true} if the specified code point is between
9576 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9577 * {@link #MAX_CODE_POINT} inclusive;
9578 * {@code false} otherwise.
9579 * @since 1.5
9580 */
9581 public static boolean isSupplementaryCodePoint(int codePoint) {
9582 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9583 && codePoint < MAX_CODE_POINT + 1;
9584 }
9585
9586 /**
9587 * Determines if the given {@code char} value is a
9588 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9589 * Unicode high-surrogate code unit</a>
9590 * (also known as <i>leading-surrogate code unit</i>).
9591 *
9592 * <p>Such values do not represent characters by themselves,
9593 * but are used in the representation of
9594 * <a href="#supplementary">supplementary characters</a>
9595 * in the UTF-16 encoding.
9596 *
9597 * @param ch the {@code char} value to be tested.
9598 * @return {@code true} if the {@code char} value is between
9599 * {@link #MIN_HIGH_SURROGATE} and
9600 * {@link #MAX_HIGH_SURROGATE} inclusive;
9601 * {@code false} otherwise.
9602 * @see Character#isLowSurrogate(char)
9603 * @see Character.UnicodeBlock#of(int)
9604 * @since 1.5
9605 */
9606 public static boolean isHighSurrogate(char ch) {
9607 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9608 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9609 }
9610
9611 /**
9612 * Determines if the given {@code char} value is a
9613 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9614 * Unicode low-surrogate code unit</a>
9615 * (also known as <i>trailing-surrogate code unit</i>).
9616 *
9617 * <p>Such values do not represent characters by themselves,
9618 * but are used in the representation of
9619 * <a href="#supplementary">supplementary characters</a>
9620 * in the UTF-16 encoding.
9621 *
9622 * @param ch the {@code char} value to be tested.
9623 * @return {@code true} if the {@code char} value is between
9624 * {@link #MIN_LOW_SURROGATE} and
9625 * {@link #MAX_LOW_SURROGATE} inclusive;
9626 * {@code false} otherwise.
9627 * @see Character#isHighSurrogate(char)
9628 * @since 1.5
9629 */
9630 public static boolean isLowSurrogate(char ch) {
9631 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9632 }
9633
9634 /**
9635 * Determines if the given {@code char} value is a Unicode
9636 * <i>surrogate code unit</i>.
9637 *
9638 * <p>Such values do not represent characters by themselves,
9639 * but are used in the representation of
9640 * <a href="#supplementary">supplementary characters</a>
9641 * in the UTF-16 encoding.
9642 *
9643 * <p>A char value is a surrogate code unit if and only if it is either
9644 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9645 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9646 *
9647 * @param ch the {@code char} value to be tested.
9648 * @return {@code true} if the {@code char} value is between
9649 * {@link #MIN_SURROGATE} and
9650 * {@link #MAX_SURROGATE} inclusive;
9651 * {@code false} otherwise.
9652 * @since 1.7
9653 */
9654 public static boolean isSurrogate(char ch) {
9655 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9656 }
9657
9658 /**
9659 * Determines whether the specified pair of {@code char}
9660 * values is a valid
9661 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9662 * Unicode surrogate pair</a>.
9663 *
9664 * <p>This method is equivalent to the expression:
9665 * <blockquote><pre>{@code
9666 * isHighSurrogate(high) && isLowSurrogate(low)
9667 * }</pre></blockquote>
9668 *
9669 * @param high the high-surrogate code value to be tested
9670 * @param low the low-surrogate code value to be tested
9671 * @return {@code true} if the specified high and
9672 * low-surrogate code values represent a valid surrogate pair;
9673 * {@code false} otherwise.
9674 * @since 1.5
9675 */
9676 public static boolean isSurrogatePair(char high, char low) {
9677 return isHighSurrogate(high) && isLowSurrogate(low);
9678 }
9679
9680 /**
9681 * Determines the number of {@code char} values needed to
9682 * represent the specified character (Unicode code point). If the
9683 * specified character is equal to or greater than 0x10000, then
9684 * the method returns 2. Otherwise, the method returns 1.
9685 *
9686 * <p>This method doesn't validate the specified character to be a
9687 * valid Unicode code point. The caller must validate the
9688 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9689 * if necessary.
9690 *
9691 * @param codePoint the character (Unicode code point) to be tested.
9692 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9693 * @see Character#isSupplementaryCodePoint(int)
9694 * @since 1.5
9695 */
9696 public static int charCount(int codePoint) {
9697 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9698 }
9699
9700 /**
9701 * Converts the specified surrogate pair to its supplementary code
9702 * point value. This method does not validate the specified
9703 * surrogate pair. The caller must validate it using {@link
9704 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9705 *
9706 * @param high the high-surrogate code unit
9707 * @param low the low-surrogate code unit
9708 * @return the supplementary code point composed from the
9709 * specified surrogate pair.
9710 * @since 1.5
9711 */
9712 public static int toCodePoint(char high, char low) {
9713 // Optimized form of:
9714 // return ((high - MIN_HIGH_SURROGATE) << 10)
9715 // + (low - MIN_LOW_SURROGATE)
9716 // + MIN_SUPPLEMENTARY_CODE_POINT;
9717 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9718 - (MIN_HIGH_SURROGATE << 10)
9719 - MIN_LOW_SURROGATE);
9720 }
9721
9722 /**
9723 * Returns the code point at the given index of the
9724 * {@code CharSequence}. If the {@code char} value at
9725 * the given index in the {@code CharSequence} is in the
9726 * high-surrogate range, the following index is less than the
9727 * length of the {@code CharSequence}, and the
9728 * {@code char} value at the following index is in the
9729 * low-surrogate range, then the supplementary code point
9730 * corresponding to this surrogate pair is returned. Otherwise,
9731 * the {@code char} value at the given index is returned.
9732 *
9733 * @param seq a sequence of {@code char} values (Unicode code
9734 * units)
9735 * @param index the index to the {@code char} values (Unicode
9736 * code units) in {@code seq} to be converted
9737 * @return the Unicode code point at the given index
9738 * @throws NullPointerException if {@code seq} is null.
9739 * @throws IndexOutOfBoundsException if the value
9740 * {@code index} is negative or not less than
9741 * {@link CharSequence#length() seq.length()}.
9742 * @since 1.5
9743 */
9744 public static int codePointAt(CharSequence seq, int index) {
9745 char c1 = seq.charAt(index);
9746 if (isHighSurrogate(c1) && ++index < seq.length()) {
9747 char c2 = seq.charAt(index);
9748 if (isLowSurrogate(c2)) {
9749 return toCodePoint(c1, c2);
9750 }
9751 }
9752 return c1;
9753 }
9754
9755 /**
9756 * Returns the code point at the given index of the
9757 * {@code char} array. If the {@code char} value at
9758 * the given index in the {@code char} array is in the
9759 * high-surrogate range, the following index is less than the
9760 * length of the {@code char} array, and the
9761 * {@code char} value at the following index is in the
9762 * low-surrogate range, then the supplementary code point
9763 * corresponding to this surrogate pair is returned. Otherwise,
9764 * the {@code char} value at the given index is returned.
9765 *
9766 * @param a the {@code char} array
9767 * @param index the index to the {@code char} values (Unicode
9768 * code units) in the {@code char} array to be converted
9769 * @return the Unicode code point at the given index
9770 * @throws NullPointerException if {@code a} is null.
9771 * @throws IndexOutOfBoundsException if the value
9772 * {@code index} is negative or not less than
9773 * the length of the {@code char} array.
9774 * @since 1.5
9775 */
9776 public static int codePointAt(char[] a, int index) {
9777 return codePointAtImpl(a, index, a.length);
9778 }
9779
9780 /**
9781 * Returns the code point at the given index of the
9782 * {@code char} array, where only array elements with
9783 * {@code index} less than {@code limit} can be used. If
9784 * the {@code char} value at the given index in the
9785 * {@code char} array is in the high-surrogate range, the
9786 * following index is less than the {@code limit}, and the
9787 * {@code char} value at the following index is in the
9788 * low-surrogate range, then the supplementary code point
9789 * corresponding to this surrogate pair is returned. Otherwise,
9790 * the {@code char} value at the given index is returned.
9791 *
9792 * @param a the {@code char} array
9793 * @param index the index to the {@code char} values (Unicode
9794 * code units) in the {@code char} array to be converted
9795 * @param limit the index after the last array element that
9796 * can be used in the {@code char} array
9797 * @return the Unicode code point at the given index
9798 * @throws NullPointerException if {@code a} is null.
9799 * @throws IndexOutOfBoundsException if the {@code index}
9800 * argument is negative or not less than the {@code limit}
9801 * argument, or if the {@code limit} argument is negative or
9802 * greater than the length of the {@code char} array.
9803 * @since 1.5
9804 */
9805 public static int codePointAt(char[] a, int index, int limit) {
9806 if (index >= limit || index < 0 || limit > a.length) {
9807 throw new IndexOutOfBoundsException();
9808 }
9809 return codePointAtImpl(a, index, limit);
9810 }
9811
9812 // throws ArrayIndexOutOfBoundsException if index out of bounds
9813 static int codePointAtImpl(char[] a, int index, int limit) {
9814 char c1 = a[index];
9815 if (isHighSurrogate(c1) && ++index < limit) {
9816 char c2 = a[index];
9817 if (isLowSurrogate(c2)) {
9818 return toCodePoint(c1, c2);
9819 }
9820 }
9821 return c1;
9822 }
9823
9824 /**
9825 * Returns the code point preceding the given index of the
9826 * {@code CharSequence}. If the {@code char} value at
9827 * {@code (index - 1)} in the {@code CharSequence} is in
9828 * the low-surrogate range, {@code (index - 2)} is not
9829 * negative, and the {@code char} value at {@code (index - 2)}
9830 * in the {@code CharSequence} is in the
9831 * high-surrogate range, then the supplementary code point
9832 * corresponding to this surrogate pair is returned. Otherwise,
9833 * the {@code char} value at {@code (index - 1)} is
9834 * returned.
9835 *
9836 * @param seq the {@code CharSequence} instance
9837 * @param index the index following the code point that should be returned
9838 * @return the Unicode code point value before the given index.
9839 * @throws NullPointerException if {@code seq} is null.
9840 * @throws IndexOutOfBoundsException if the {@code index}
9841 * argument is less than 1 or greater than {@link
9842 * CharSequence#length() seq.length()}.
9843 * @since 1.5
9844 */
9845 public static int codePointBefore(CharSequence seq, int index) {
9846 char c2 = seq.charAt(--index);
9847 if (isLowSurrogate(c2) && index > 0) {
9848 char c1 = seq.charAt(--index);
9849 if (isHighSurrogate(c1)) {
9850 return toCodePoint(c1, c2);
9851 }
9852 }
9853 return c2;
9854 }
9855
9856 /**
9857 * Returns the code point preceding the given index of the
9858 * {@code char} array. If the {@code char} value at
9859 * {@code (index - 1)} in the {@code char} array is in
9860 * the low-surrogate range, {@code (index - 2)} is not
9861 * negative, and the {@code char} value at {@code (index - 2)}
9862 * in the {@code char} array is in the
9863 * high-surrogate range, then the supplementary code point
9864 * corresponding to this surrogate pair is returned. Otherwise,
9865 * the {@code char} value at {@code (index - 1)} is
9866 * returned.
9867 *
9868 * @param a the {@code char} array
9869 * @param index the index following the code point that should be returned
9870 * @return the Unicode code point value before the given index.
9871 * @throws NullPointerException if {@code a} is null.
9872 * @throws IndexOutOfBoundsException if the {@code index}
9873 * argument is less than 1 or greater than the length of the
9874 * {@code char} array
9875 * @since 1.5
9876 */
9877 public static int codePointBefore(char[] a, int index) {
9878 return codePointBeforeImpl(a, index, 0);
9879 }
9880
9881 /**
9882 * Returns the code point preceding the given index of the
9883 * {@code char} array, where only array elements with
9884 * {@code index} greater than or equal to {@code start}
9885 * can be used. If the {@code char} value at {@code (index - 1)}
9886 * in the {@code char} array is in the
9887 * low-surrogate range, {@code (index - 2)} is not less than
9888 * {@code start}, and the {@code char} value at
9889 * {@code (index - 2)} in the {@code char} array is in
9890 * the high-surrogate range, then the supplementary code point
9891 * corresponding to this surrogate pair is returned. Otherwise,
9892 * the {@code char} value at {@code (index - 1)} is
9893 * returned.
9894 *
9895 * @param a the {@code char} array
9896 * @param index the index following the code point that should be returned
9897 * @param start the index of the first array element in the
9898 * {@code char} array
9899 * @return the Unicode code point value before the given index.
9900 * @throws NullPointerException if {@code a} is null.
9901 * @throws IndexOutOfBoundsException if the {@code index}
9902 * argument is not greater than the {@code start} argument or
9903 * is greater than the length of the {@code char} array, or
9904 * if the {@code start} argument is negative or not less than
9905 * the length of the {@code char} array.
9906 * @since 1.5
9907 */
9908 public static int codePointBefore(char[] a, int index, int start) {
9909 if (index <= start || start < 0 || index > a.length) {
9910 throw new IndexOutOfBoundsException();
9911 }
9912 return codePointBeforeImpl(a, index, start);
9913 }
9914
9915 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9916 static int codePointBeforeImpl(char[] a, int index, int start) {
9917 char c2 = a[--index];
9918 if (isLowSurrogate(c2) && index > start) {
9919 char c1 = a[--index];
9920 if (isHighSurrogate(c1)) {
9921 return toCodePoint(c1, c2);
9922 }
9923 }
9924 return c2;
9925 }
9926
9927 /**
9928 * Returns the leading surrogate (a
9929 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9930 * high surrogate code unit</a>) of the
9931 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9932 * surrogate pair</a>
9933 * representing the specified supplementary character (Unicode
9934 * code point) in the UTF-16 encoding. If the specified character
9935 * is not a
9936 * <a href="Character.html#supplementary">supplementary character</a>,
9937 * an unspecified {@code char} is returned.
9938 *
9939 * <p>If
9940 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9941 * is {@code true}, then
9942 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9943 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9944 * are also always {@code true}.
9945 *
9946 * @param codePoint a supplementary character (Unicode code point)
9947 * @return the leading surrogate code unit used to represent the
9948 * character in the UTF-16 encoding
9949 * @since 1.7
9950 */
9951 public static char highSurrogate(int codePoint) {
9952 return (char) ((codePoint >>> 10)
9953 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9954 }
9955
9956 /**
9957 * Returns the trailing surrogate (a
9958 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9959 * low surrogate code unit</a>) of the
9960 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9961 * surrogate pair</a>
9962 * representing the specified supplementary character (Unicode
9963 * code point) in the UTF-16 encoding. If the specified character
9964 * is not a
9965 * <a href="Character.html#supplementary">supplementary character</a>,
9966 * an unspecified {@code char} is returned.
9967 *
9968 * <p>If
9969 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9970 * is {@code true}, then
9971 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9972 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9973 * are also always {@code true}.
9974 *
9975 * @param codePoint a supplementary character (Unicode code point)
9976 * @return the trailing surrogate code unit used to represent the
9977 * character in the UTF-16 encoding
9978 * @since 1.7
9979 */
9980 public static char lowSurrogate(int codePoint) {
9981 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
9982 }
9983
9984 /**
9985 * Converts the specified character (Unicode code point) to its
9986 * UTF-16 representation. If the specified code point is a BMP
9987 * (Basic Multilingual Plane or Plane 0) value, the same value is
9988 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
9989 * specified code point is a supplementary character, its
9990 * surrogate values are stored in {@code dst[dstIndex]}
9991 * (high-surrogate) and {@code dst[dstIndex+1]}
9992 * (low-surrogate), and 2 is returned.
9993 *
9994 * @param codePoint the character (Unicode code point) to be converted.
9995 * @param dst an array of {@code char} in which the
9996 * {@code codePoint}'s UTF-16 value is stored.
9997 * @param dstIndex the start index into the {@code dst}
9998 * array where the converted value is stored.
9999 * @return 1 if the code point is a BMP code point, 2 if the
10000 * code point is a supplementary code point.
10001 * @throws IllegalArgumentException if the specified
10002 * {@code codePoint} is not a valid Unicode code point.
10003 * @throws NullPointerException if the specified {@code dst} is null.
10004 * @throws IndexOutOfBoundsException if {@code dstIndex}
10005 * is negative or not less than {@code dst.length}, or if
10006 * {@code dst} at {@code dstIndex} doesn't have enough
10007 * array element(s) to store the resulting {@code char}
10008 * value(s). (If {@code dstIndex} is equal to
10009 * {@code dst.length-1} and the specified
10010 * {@code codePoint} is a supplementary character, the
10011 * high-surrogate value is not stored in
10012 * {@code dst[dstIndex]}.)
10013 * @since 1.5
10014 */
10015 public static int toChars(int codePoint, char[] dst, int dstIndex) {
10016 if (isBmpCodePoint(codePoint)) {
10017 dst[dstIndex] = (char) codePoint;
10018 return 1;
10019 } else if (isValidCodePoint(codePoint)) {
10020 toSurrogates(codePoint, dst, dstIndex);
10021 return 2;
10022 } else {
10023 throw new IllegalArgumentException(
10024 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10025 }
10026 }
10027
10028 /**
10029 * Converts the specified character (Unicode code point) to its
10030 * UTF-16 representation stored in a {@code char} array. If
10031 * the specified code point is a BMP (Basic Multilingual Plane or
10032 * Plane 0) value, the resulting {@code char} array has
10033 * the same value as {@code codePoint}. If the specified code
10034 * point is a supplementary code point, the resulting
10035 * {@code char} array has the corresponding surrogate pair.
10036 *
10037 * @param codePoint a Unicode code point
10038 * @return a {@code char} array having
10039 * {@code codePoint}'s UTF-16 representation.
10040 * @throws IllegalArgumentException if the specified
10041 * {@code codePoint} is not a valid Unicode code point.
10042 * @since 1.5
10043 */
10044 public static char[] toChars(int codePoint) {
10045 if (isBmpCodePoint(codePoint)) {
10046 return new char[] { (char) codePoint };
10047 } else if (isValidCodePoint(codePoint)) {
10048 char[] result = new char[2];
10049 toSurrogates(codePoint, result, 0);
10050 return result;
10051 } else {
10052 throw new IllegalArgumentException(
10053 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10054 }
10055 }
10056
10057 static void toSurrogates(int codePoint, char[] dst, int index) {
10058 // We write elements "backwards" to guarantee all-or-nothing
10059 dst[index+1] = lowSurrogate(codePoint);
10060 dst[index] = highSurrogate(codePoint);
10061 }
10062
10063 /**
10064 * Returns the number of Unicode code points in the text range of
10065 * the specified char sequence. The text range begins at the
10066 * specified {@code beginIndex} and extends to the
10067 * {@code char} at index {@code endIndex - 1}. Thus the
10068 * length (in {@code char}s) of the text range is
10069 * {@code endIndex-beginIndex}. Unpaired surrogates within
10070 * the text range count as one code point each.
10071 *
10072 * @param seq the char sequence
10073 * @param beginIndex the index to the first {@code char} of
10074 * the text range.
10075 * @param endIndex the index after the last {@code char} of
10076 * the text range.
10077 * @return the number of Unicode code points in the specified text
10078 * range
10079 * @throws NullPointerException if {@code seq} is null.
10080 * @throws IndexOutOfBoundsException if the
10081 * {@code beginIndex} is negative, or {@code endIndex}
10082 * is larger than the length of the given sequence, or
10083 * {@code beginIndex} is larger than {@code endIndex}.
10084 * @since 1.5
10085 */
10086 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
10087 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
10088 int n = endIndex - beginIndex;
10089 for (int i = beginIndex; i < endIndex; ) {
10090 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
10091 isLowSurrogate(seq.charAt(i))) {
10092 n--;
10093 i++;
10094 }
10095 }
10096 return n;
10097 }
10098
10099 /**
10100 * Returns the number of Unicode code points in a subarray of the
10101 * {@code char} array argument. The {@code offset}
10102 * argument is the index of the first {@code char} of the
10103 * subarray and the {@code count} argument specifies the
10104 * length of the subarray in {@code char}s. Unpaired
10105 * surrogates within the subarray count as one code point each.
10106 *
10107 * @param a the {@code char} array
10108 * @param offset the index of the first {@code char} in the
10109 * given {@code char} array
10110 * @param count the length of the subarray in {@code char}s
10111 * @return the number of Unicode code points in the specified subarray
10112 * @throws NullPointerException if {@code a} is null.
10113 * @throws IndexOutOfBoundsException if {@code offset} or
10114 * {@code count} is negative, or if {@code offset +
10115 * count} is larger than the length of the given array.
10116 * @since 1.5
10117 */
10118 public static int codePointCount(char[] a, int offset, int count) {
10119 Objects.checkFromIndexSize(offset, count, a.length);
10120 return codePointCountImpl(a, offset, count);
10121 }
10122
10123 static int codePointCountImpl(char[] a, int offset, int count) {
10124 int endIndex = offset + count;
10125 int n = count;
10126 for (int i = offset; i < endIndex; ) {
10127 if (isHighSurrogate(a[i++]) && i < endIndex &&
10128 isLowSurrogate(a[i])) {
10129 n--;
10130 i++;
10131 }
10132 }
10133 return n;
10134 }
10135
10136 /**
10137 * Returns the index within the given char sequence that is offset
10138 * from the given {@code index} by {@code codePointOffset}
10139 * code points. Unpaired surrogates within the text range given by
10140 * {@code index} and {@code codePointOffset} count as
10141 * one code point each.
10142 *
10143 * @param seq the char sequence
10144 * @param index the index to be offset
10145 * @param codePointOffset the offset in code points
10146 * @return the index within the char sequence
10147 * @throws NullPointerException if {@code seq} is null.
10148 * @throws IndexOutOfBoundsException if {@code index}
10149 * is negative or larger than the length of the char sequence,
10150 * or if {@code codePointOffset} is positive and the
10151 * subsequence starting with {@code index} has fewer than
10152 * {@code codePointOffset} code points, or if
10153 * {@code codePointOffset} is negative and the subsequence
10154 * before {@code index} has fewer than the absolute value
10155 * of {@code codePointOffset} code points.
10156 * @since 1.5
10157 */
10158 public static int offsetByCodePoints(CharSequence seq, int index,
10159 int codePointOffset) {
10160 int length = seq.length();
10161 if (index < 0 || index > length) {
10162 throw new IndexOutOfBoundsException();
10163 }
10164
10165 int x = index;
10166 if (codePointOffset >= 0) {
10167 int i;
10168 for (i = 0; x < length && i < codePointOffset; i++) {
10169 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
10170 isLowSurrogate(seq.charAt(x))) {
10171 x++;
10172 }
10173 }
10174 if (i < codePointOffset) {
10175 throw new IndexOutOfBoundsException();
10176 }
10177 } else {
10178 int i;
10179 for (i = codePointOffset; x > 0 && i < 0; i++) {
10180 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
10181 isHighSurrogate(seq.charAt(x-1))) {
10182 x--;
10183 }
10184 }
10185 if (i < 0) {
10186 throw new IndexOutOfBoundsException();
10187 }
10188 }
10189 return x;
10190 }
10191
10192 /**
10193 * Returns the index within the given {@code char} subarray
10194 * that is offset from the given {@code index} by
10195 * {@code codePointOffset} code points. The
10196 * {@code start} and {@code count} arguments specify a
10197 * subarray of the {@code char} array. Unpaired surrogates
10198 * within the text range given by {@code index} and
10199 * {@code codePointOffset} count as one code point each.
10200 *
10201 * @param a the {@code char} array
10202 * @param start the index of the first {@code char} of the
10203 * subarray
10204 * @param count the length of the subarray in {@code char}s
10205 * @param index the index to be offset
10206 * @param codePointOffset the offset in code points
10207 * @return the index within the subarray
10208 * @throws NullPointerException if {@code a} is null.
10209 * @throws IndexOutOfBoundsException
10210 * if {@code start} or {@code count} is negative,
10211 * or if {@code start + count} is larger than the length of
10212 * the given array,
10213 * or if {@code index} is less than {@code start} or
10214 * larger then {@code start + count},
10215 * or if {@code codePointOffset} is positive and the text range
10216 * starting with {@code index} and ending with {@code start + count - 1}
10217 * has fewer than {@code codePointOffset} code
10218 * points,
10219 * or if {@code codePointOffset} is negative and the text range
10220 * starting with {@code start} and ending with {@code index - 1}
10221 * has fewer than the absolute value of
10222 * {@code codePointOffset} code points.
10223 * @since 1.5
10224 */
10225 public static int offsetByCodePoints(char[] a, int start, int count,
10226 int index, int codePointOffset) {
10227 if (count > a.length-start || start < 0 || count < 0
10228 || index < start || index > start+count) {
10229 throw new IndexOutOfBoundsException();
10230 }
10231 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
10232 }
10233
10234 static int offsetByCodePointsImpl(char[]a, int start, int count,
10235 int index, int codePointOffset) {
10236 int x = index;
10237 if (codePointOffset >= 0) {
10238 int limit = start + count;
10239 int i;
10240 for (i = 0; x < limit && i < codePointOffset; i++) {
10241 if (isHighSurrogate(a[x++]) && x < limit &&
10242 isLowSurrogate(a[x])) {
10243 x++;
10244 }
10245 }
10246 if (i < codePointOffset) {
10247 throw new IndexOutOfBoundsException();
10248 }
10249 } else {
10250 int i;
10251 for (i = codePointOffset; x > start && i < 0; i++) {
10252 if (isLowSurrogate(a[--x]) && x > start &&
10253 isHighSurrogate(a[x-1])) {
10254 x--;
10255 }
10256 }
10257 if (i < 0) {
10258 throw new IndexOutOfBoundsException();
10259 }
10260 }
10261 return x;
10262 }
10263
10264 /**
10265 * Determines if the specified character is a lowercase character.
10266 * <p>
10267 * A character is lowercase if its general category type, provided
10268 * by {@code Character.getType(ch)}, is
10269 * {@code LOWERCASE_LETTER}, or it has contributory property
10270 * Other_Lowercase as defined by the Unicode Standard.
10271 * <p>
10272 * The following are examples of lowercase characters:
10273 * <blockquote><pre>
10274 * 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
10275 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10276 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10277 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10278 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10279 * </pre></blockquote>
10280 * <p> Many other Unicode characters are lowercase too.
10281 *
10282 * <p><b>Note:</b> This method cannot handle <a
10283 * href="#supplementary"> supplementary characters</a>. To support
10284 * all Unicode characters, including supplementary characters, use
10285 * the {@link #isLowerCase(int)} method.
10286 *
10287 * @param ch the character to be tested.
10288 * @return {@code true} if the character is lowercase;
10289 * {@code false} otherwise.
10290 * @see Character#isLowerCase(char)
10291 * @see Character#isTitleCase(char)
10292 * @see Character#toLowerCase(char)
10293 * @see Character#getType(char)
10294 */
10295 public static boolean isLowerCase(char ch) {
10296 return isLowerCase((int)ch);
10297 }
10298
10299 /**
10300 * Determines if the specified character (Unicode code point) is a
10301 * lowercase character.
10302 * <p>
10303 * A character is lowercase if its general category type, provided
10304 * by {@link Character#getType getType(codePoint)}, is
10305 * {@code LOWERCASE_LETTER}, or it has contributory property
10306 * Other_Lowercase as defined by the Unicode Standard.
10307 * <p>
10308 * The following are examples of lowercase characters:
10309 * <blockquote><pre>
10310 * 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
10311 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10312 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10313 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10314 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10315 * </pre></blockquote>
10316 * <p> Many other Unicode characters are lowercase too.
10317 *
10318 * @param codePoint the character (Unicode code point) to be tested.
10319 * @return {@code true} if the character is lowercase;
10320 * {@code false} otherwise.
10321 * @see Character#isLowerCase(int)
10322 * @see Character#isTitleCase(int)
10323 * @see Character#toLowerCase(int)
10324 * @see Character#getType(int)
10325 * @since 1.5
10326 */
10327 public static boolean isLowerCase(int codePoint) {
10328 return CharacterData.of(codePoint).isLowerCase(codePoint);
10329 }
10330
10331 /**
10332 * Determines if the specified character is an uppercase character.
10333 * <p>
10334 * A character is uppercase if its general category type, provided by
10335 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
10336 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10337 * <p>
10338 * The following are examples of uppercase characters:
10339 * <blockquote><pre>
10340 * 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
10341 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10342 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10343 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10344 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10345 * </pre></blockquote>
10346 * <p> Many other Unicode characters are uppercase too.
10347 *
10348 * <p><b>Note:</b> This method cannot handle <a
10349 * href="#supplementary"> supplementary characters</a>. To support
10350 * all Unicode characters, including supplementary characters, use
10351 * the {@link #isUpperCase(int)} method.
10352 *
10353 * @param ch the character to be tested.
10354 * @return {@code true} if the character is uppercase;
10355 * {@code false} otherwise.
10356 * @see Character#isLowerCase(char)
10357 * @see Character#isTitleCase(char)
10358 * @see Character#toUpperCase(char)
10359 * @see Character#getType(char)
10360 * @since 1.0
10361 */
10362 public static boolean isUpperCase(char ch) {
10363 return isUpperCase((int)ch);
10364 }
10365
10366 /**
10367 * Determines if the specified character (Unicode code point) is an uppercase character.
10368 * <p>
10369 * A character is uppercase if its general category type, provided by
10370 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
10371 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10372 * <p>
10373 * The following are examples of uppercase characters:
10374 * <blockquote><pre>
10375 * 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
10376 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10377 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10378 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10379 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10380 * </pre></blockquote>
10381 * <p> Many other Unicode characters are uppercase too.
10382 *
10383 * @param codePoint the character (Unicode code point) to be tested.
10384 * @return {@code true} if the character is uppercase;
10385 * {@code false} otherwise.
10386 * @see Character#isLowerCase(int)
10387 * @see Character#isTitleCase(int)
10388 * @see Character#toUpperCase(int)
10389 * @see Character#getType(int)
10390 * @since 1.5
10391 */
10392 public static boolean isUpperCase(int codePoint) {
10393 return CharacterData.of(codePoint).isUpperCase(codePoint);
10394 }
10395
10396 /**
10397 * Determines if the specified character is a titlecase character.
10398 * <p>
10399 * A character is a titlecase character if its general
10400 * category type, provided by {@code Character.getType(ch)},
10401 * is {@code TITLECASE_LETTER}.
10402 * <p>
10403 * Some characters look like pairs of Latin letters. For example, there
10404 * is an uppercase letter that looks like "LJ" and has a corresponding
10405 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10406 * is the appropriate form to use when rendering a word in lowercase
10407 * with initial capitals, as for a book title.
10408 * <p>
10409 * These are some of the Unicode characters for which this method returns
10410 * {@code true}:
10411 * <ul>
10412 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10413 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10414 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10415 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10416 * </ul>
10417 * <p> Many other Unicode characters are titlecase too.
10418 *
10419 * <p><b>Note:</b> This method cannot handle <a
10420 * href="#supplementary"> supplementary characters</a>. To support
10421 * all Unicode characters, including supplementary characters, use
10422 * the {@link #isTitleCase(int)} method.
10423 *
10424 * @param ch the character to be tested.
10425 * @return {@code true} if the character is titlecase;
10426 * {@code false} otherwise.
10427 * @see Character#isLowerCase(char)
10428 * @see Character#isUpperCase(char)
10429 * @see Character#toTitleCase(char)
10430 * @see Character#getType(char)
10431 * @since 1.0.2
10432 */
10433 public static boolean isTitleCase(char ch) {
10434 return isTitleCase((int)ch);
10435 }
10436
10437 /**
10438 * Determines if the specified character (Unicode code point) is a titlecase character.
10439 * <p>
10440 * A character is a titlecase character if its general
10441 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10442 * is {@code TITLECASE_LETTER}.
10443 * <p>
10444 * Some characters look like pairs of Latin letters. For example, there
10445 * is an uppercase letter that looks like "LJ" and has a corresponding
10446 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10447 * is the appropriate form to use when rendering a word in lowercase
10448 * with initial capitals, as for a book title.
10449 * <p>
10450 * These are some of the Unicode characters for which this method returns
10451 * {@code true}:
10452 * <ul>
10453 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10454 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10455 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10456 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10457 * </ul>
10458 * <p> Many other Unicode characters are titlecase too.
10459 *
10460 * @param codePoint the character (Unicode code point) to be tested.
10461 * @return {@code true} if the character is titlecase;
10462 * {@code false} otherwise.
10463 * @see Character#isLowerCase(int)
10464 * @see Character#isUpperCase(int)
10465 * @see Character#toTitleCase(int)
10466 * @see Character#getType(int)
10467 * @since 1.5
10468 */
10469 public static boolean isTitleCase(int codePoint) {
10470 return getType(codePoint) == Character.TITLECASE_LETTER;
10471 }
10472
10473 /**
10474 * Determines if the specified character is a digit.
10475 * <p>
10476 * A character is a digit if its general category type, provided
10477 * by {@code Character.getType(ch)}, is
10478 * {@code DECIMAL_DIGIT_NUMBER}.
10479 * <p>
10480 * Some Unicode character ranges that contain digits:
10481 * <ul>
10482 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10483 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10484 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10485 * Arabic-Indic digits
10486 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10487 * Extended Arabic-Indic digits
10488 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10489 * Devanagari digits
10490 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10491 * Fullwidth digits
10492 * </ul>
10493 *
10494 * Many other character ranges contain digits as well.
10495 *
10496 * <p><b>Note:</b> This method cannot handle <a
10497 * href="#supplementary"> supplementary characters</a>. To support
10498 * all Unicode characters, including supplementary characters, use
10499 * the {@link #isDigit(int)} method.
10500 *
10501 * @param ch the character to be tested.
10502 * @return {@code true} if the character is a digit;
10503 * {@code false} otherwise.
10504 * @see Character#digit(char, int)
10505 * @see Character#forDigit(int, int)
10506 * @see Character#getType(char)
10507 */
10508 public static boolean isDigit(char ch) {
10509 return isDigit((int)ch);
10510 }
10511
10512 /**
10513 * Determines if the specified character (Unicode code point) is a digit.
10514 * <p>
10515 * A character is a digit if its general category type, provided
10516 * by {@link Character#getType(int) getType(codePoint)}, is
10517 * {@code DECIMAL_DIGIT_NUMBER}.
10518 * <p>
10519 * Some Unicode character ranges that contain digits:
10520 * <ul>
10521 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10522 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10523 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10524 * Arabic-Indic digits
10525 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10526 * Extended Arabic-Indic digits
10527 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10528 * Devanagari digits
10529 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10530 * Fullwidth digits
10531 * </ul>
10532 *
10533 * Many other character ranges contain digits as well.
10534 *
10535 * @param codePoint the character (Unicode code point) to be tested.
10536 * @return {@code true} if the character is a digit;
10537 * {@code false} otherwise.
10538 * @see Character#forDigit(int, int)
10539 * @see Character#getType(int)
10540 * @since 1.5
10541 */
10542 public static boolean isDigit(int codePoint) {
10543 return CharacterData.of(codePoint).isDigit(codePoint);
10544 }
10545
10546 /**
10547 * Determines if a character is defined in Unicode.
10548 * <p>
10549 * A character is defined if at least one of the following is true:
10550 * <ul>
10551 * <li>It has an entry in the UnicodeData file.
10552 * <li>It has a value in a range defined by the UnicodeData file.
10553 * </ul>
10554 *
10555 * <p><b>Note:</b> This method cannot handle <a
10556 * href="#supplementary"> supplementary characters</a>. To support
10557 * all Unicode characters, including supplementary characters, use
10558 * the {@link #isDefined(int)} method.
10559 *
10560 * @param ch the character to be tested
10561 * @return {@code true} if the character has a defined meaning
10562 * in Unicode; {@code false} otherwise.
10563 * @see Character#isDigit(char)
10564 * @see Character#isLetter(char)
10565 * @see Character#isLetterOrDigit(char)
10566 * @see Character#isLowerCase(char)
10567 * @see Character#isTitleCase(char)
10568 * @see Character#isUpperCase(char)
10569 * @since 1.0.2
10570 */
10571 public static boolean isDefined(char ch) {
10572 return isDefined((int)ch);
10573 }
10574
10575 /**
10576 * Determines if a character (Unicode code point) is defined in Unicode.
10577 * <p>
10578 * A character is defined if at least one of the following is true:
10579 * <ul>
10580 * <li>It has an entry in the UnicodeData file.
10581 * <li>It has a value in a range defined by the UnicodeData file.
10582 * </ul>
10583 *
10584 * @param codePoint the character (Unicode code point) to be tested.
10585 * @return {@code true} if the character has a defined meaning
10586 * in Unicode; {@code false} otherwise.
10587 * @see Character#isDigit(int)
10588 * @see Character#isLetter(int)
10589 * @see Character#isLetterOrDigit(int)
10590 * @see Character#isLowerCase(int)
10591 * @see Character#isTitleCase(int)
10592 * @see Character#isUpperCase(int)
10593 * @since 1.5
10594 */
10595 public static boolean isDefined(int codePoint) {
10596 return getType(codePoint) != Character.UNASSIGNED;
10597 }
10598
10599 /**
10600 * Determines if the specified character is a letter.
10601 * <p>
10602 * A character is considered to be a letter if its general
10603 * category type, provided by {@code Character.getType(ch)},
10604 * is any of the following:
10605 * <ul>
10606 * <li> {@code UPPERCASE_LETTER}
10607 * <li> {@code LOWERCASE_LETTER}
10608 * <li> {@code TITLECASE_LETTER}
10609 * <li> {@code MODIFIER_LETTER}
10610 * <li> {@code OTHER_LETTER}
10611 * </ul>
10612 *
10613 * Not all letters have case. Many characters are
10614 * letters but are neither uppercase nor lowercase nor titlecase.
10615 *
10616 * <p><b>Note:</b> This method cannot handle <a
10617 * href="#supplementary"> supplementary characters</a>. To support
10618 * all Unicode characters, including supplementary characters, use
10619 * the {@link #isLetter(int)} method.
10620 *
10621 * @param ch the character to be tested.
10622 * @return {@code true} if the character is a letter;
10623 * {@code false} otherwise.
10624 * @see Character#isDigit(char)
10625 * @see Character#isJavaIdentifierStart(char)
10626 * @see Character#isJavaLetter(char)
10627 * @see Character#isJavaLetterOrDigit(char)
10628 * @see Character#isLetterOrDigit(char)
10629 * @see Character#isLowerCase(char)
10630 * @see Character#isTitleCase(char)
10631 * @see Character#isUnicodeIdentifierStart(char)
10632 * @see Character#isUpperCase(char)
10633 */
10634 public static boolean isLetter(char ch) {
10635 return isLetter((int)ch);
10636 }
10637
10638 /**
10639 * Determines if the specified character (Unicode code point) is a letter.
10640 * <p>
10641 * A character is considered to be a letter if its general
10642 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10643 * is any of the following:
10644 * <ul>
10645 * <li> {@code UPPERCASE_LETTER}
10646 * <li> {@code LOWERCASE_LETTER}
10647 * <li> {@code TITLECASE_LETTER}
10648 * <li> {@code MODIFIER_LETTER}
10649 * <li> {@code OTHER_LETTER}
10650 * </ul>
10651 *
10652 * Not all letters have case. Many characters are
10653 * letters but are neither uppercase nor lowercase nor titlecase.
10654 *
10655 * @param codePoint the character (Unicode code point) to be tested.
10656 * @return {@code true} if the character is a letter;
10657 * {@code false} otherwise.
10658 * @see Character#isDigit(int)
10659 * @see Character#isJavaIdentifierStart(int)
10660 * @see Character#isLetterOrDigit(int)
10661 * @see Character#isLowerCase(int)
10662 * @see Character#isTitleCase(int)
10663 * @see Character#isUnicodeIdentifierStart(int)
10664 * @see Character#isUpperCase(int)
10665 * @since 1.5
10666 */
10667 public static boolean isLetter(int codePoint) {
10668 return ((((1 << Character.UPPERCASE_LETTER) |
10669 (1 << Character.LOWERCASE_LETTER) |
10670 (1 << Character.TITLECASE_LETTER) |
10671 (1 << Character.MODIFIER_LETTER) |
10672 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10673 != 0;
10674 }
10675
10676 /**
10677 * Determines if the specified character is a letter or digit.
10678 * <p>
10679 * A character is considered to be a letter or digit if either
10680 * {@code Character.isLetter(char ch)} or
10681 * {@code Character.isDigit(char ch)} returns
10682 * {@code true} for the character.
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 #isLetterOrDigit(int)} method.
10688 *
10689 * @param ch the character to be tested.
10690 * @return {@code true} if the character is a letter or digit;
10691 * {@code false} otherwise.
10692 * @see Character#isDigit(char)
10693 * @see Character#isJavaIdentifierPart(char)
10694 * @see Character#isJavaLetter(char)
10695 * @see Character#isJavaLetterOrDigit(char)
10696 * @see Character#isLetter(char)
10697 * @see Character#isUnicodeIdentifierPart(char)
10698 * @since 1.0.2
10699 */
10700 public static boolean isLetterOrDigit(char ch) {
10701 return isLetterOrDigit((int)ch);
10702 }
10703
10704 /**
10705 * Determines if the specified character (Unicode code point) is a letter or digit.
10706 * <p>
10707 * A character is considered to be a letter or digit if either
10708 * {@link #isLetter(int) isLetter(codePoint)} or
10709 * {@link #isDigit(int) isDigit(codePoint)} returns
10710 * {@code true} for the character.
10711 *
10712 * @param codePoint the character (Unicode code point) to be tested.
10713 * @return {@code true} if the character is a letter or digit;
10714 * {@code false} otherwise.
10715 * @see Character#isDigit(int)
10716 * @see Character#isJavaIdentifierPart(int)
10717 * @see Character#isLetter(int)
10718 * @see Character#isUnicodeIdentifierPart(int)
10719 * @since 1.5
10720 */
10721 public static boolean isLetterOrDigit(int codePoint) {
10722 return ((((1 << Character.UPPERCASE_LETTER) |
10723 (1 << Character.LOWERCASE_LETTER) |
10724 (1 << Character.TITLECASE_LETTER) |
10725 (1 << Character.MODIFIER_LETTER) |
10726 (1 << Character.OTHER_LETTER) |
10727 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10728 != 0;
10729 }
10730
10731 /**
10732 * Determines if the specified character is permissible as the first
10733 * character in a Java identifier.
10734 * <p>
10735 * A character may start a Java identifier if and only if
10736 * one of the following conditions is true:
10737 * <ul>
10738 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10739 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10740 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10741 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10742 * </ul>
10743 *
10744 * @param ch the character to be tested.
10745 * @return {@code true} if the character may start a Java
10746 * identifier; {@code false} otherwise.
10747 * @see Character#isJavaLetterOrDigit(char)
10748 * @see Character#isJavaIdentifierStart(char)
10749 * @see Character#isJavaIdentifierPart(char)
10750 * @see Character#isLetter(char)
10751 * @see Character#isLetterOrDigit(char)
10752 * @see Character#isUnicodeIdentifierStart(char)
10753 * @since 1.0.2
10754 * @deprecated Replaced by isJavaIdentifierStart(char).
10755 */
10756 @Deprecated(since="1.1")
10757 public static boolean isJavaLetter(char ch) {
10758 return isJavaIdentifierStart(ch);
10759 }
10760
10761 /**
10762 * Determines if the specified character may be part of a Java
10763 * identifier as other than the first character.
10764 * <p>
10765 * A character may be part of a Java identifier if and only if one
10766 * of the following conditions is true:
10767 * <ul>
10768 * <li> it is a letter
10769 * <li> it is a currency symbol (such as {@code '$'})
10770 * <li> it is a connecting punctuation character (such as {@code '_'})
10771 * <li> it is a digit
10772 * <li> it is a numeric letter (such as a Roman numeral character)
10773 * <li> it is a combining mark
10774 * <li> it is a non-spacing mark
10775 * <li> {@code isIdentifierIgnorable} returns
10776 * {@code true} for the character.
10777 * </ul>
10778 *
10779 * @param ch the character to be tested.
10780 * @return {@code true} if the character may be part of a
10781 * Java identifier; {@code false} otherwise.
10782 * @see Character#isJavaLetter(char)
10783 * @see Character#isJavaIdentifierStart(char)
10784 * @see Character#isJavaIdentifierPart(char)
10785 * @see Character#isLetter(char)
10786 * @see Character#isLetterOrDigit(char)
10787 * @see Character#isUnicodeIdentifierPart(char)
10788 * @see Character#isIdentifierIgnorable(char)
10789 * @since 1.0.2
10790 * @deprecated Replaced by isJavaIdentifierPart(char).
10791 */
10792 @Deprecated(since="1.1")
10793 public static boolean isJavaLetterOrDigit(char ch) {
10794 return isJavaIdentifierPart(ch);
10795 }
10796
10797 /**
10798 * Determines if the specified character (Unicode code point) is alphabetic.
10799 * <p>
10800 * A character is considered to be alphabetic if its general category type,
10801 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10802 * the following:
10803 * <ul>
10804 * <li> {@code UPPERCASE_LETTER}
10805 * <li> {@code LOWERCASE_LETTER}
10806 * <li> {@code TITLECASE_LETTER}
10807 * <li> {@code MODIFIER_LETTER}
10808 * <li> {@code OTHER_LETTER}
10809 * <li> {@code LETTER_NUMBER}
10810 * </ul>
10811 * or it has contributory property Other_Alphabetic as defined by the
10812 * Unicode Standard.
10813 *
10814 * @param codePoint the character (Unicode code point) to be tested.
10815 * @return {@code true} if the character is a Unicode alphabet
10816 * character, {@code false} otherwise.
10817 * @since 1.7
10818 */
10819 public static boolean isAlphabetic(int codePoint) {
10820 return (((((1 << Character.UPPERCASE_LETTER) |
10821 (1 << Character.LOWERCASE_LETTER) |
10822 (1 << Character.TITLECASE_LETTER) |
10823 (1 << Character.MODIFIER_LETTER) |
10824 (1 << Character.OTHER_LETTER) |
10825 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10826 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10827 }
10828
10829 /**
10830 * Determines if the specified character (Unicode code point) is a CJKV
10831 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10832 * the Unicode Standard.
10833 *
10834 * @param codePoint the character (Unicode code point) to be tested.
10835 * @return {@code true} if the character is a Unicode ideograph
10836 * character, {@code false} otherwise.
10837 * @since 1.7
10838 */
10839 public static boolean isIdeographic(int codePoint) {
10840 return CharacterData.of(codePoint).isIdeographic(codePoint);
10841 }
10842
10843 /**
10844 * Determines if the specified character is
10845 * permissible as the first character in a Java identifier.
10846 * <p>
10847 * A character may start a Java identifier if and only if
10848 * one of the following conditions is true:
10849 * <ul>
10850 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10851 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10852 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10853 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10854 * </ul>
10855 *
10856 * <p><b>Note:</b> This method cannot handle <a
10857 * href="#supplementary"> supplementary characters</a>. To support
10858 * all Unicode characters, including supplementary characters, use
10859 * the {@link #isJavaIdentifierStart(int)} method.
10860 *
10861 * @param ch the character to be tested.
10862 * @return {@code true} if the character may start a Java identifier;
10863 * {@code false} otherwise.
10864 * @see Character#isJavaIdentifierPart(char)
10865 * @see Character#isLetter(char)
10866 * @see Character#isUnicodeIdentifierStart(char)
10867 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10868 * @since 1.1
10869 */
10870 @SuppressWarnings("doclint:reference") // cross-module links
10871 public static boolean isJavaIdentifierStart(char ch) {
10872 return isJavaIdentifierStart((int)ch);
10873 }
10874
10875 /**
10876 * Determines if the character (Unicode code point) is
10877 * permissible as the first character in a Java identifier.
10878 * <p>
10879 * A character may start a Java identifier if and only if
10880 * one of the following conditions is true:
10881 * <ul>
10882 * <li> {@link #isLetter(int) isLetter(codePoint)}
10883 * returns {@code true}
10884 * <li> {@link #getType(int) getType(codePoint)}
10885 * returns {@code LETTER_NUMBER}
10886 * <li> the referenced character is a currency symbol (such as {@code '$'})
10887 * <li> the referenced character is a connecting punctuation character
10888 * (such as {@code '_'}).
10889 * </ul>
10890 *
10891 * @param codePoint the character (Unicode code point) to be tested.
10892 * @return {@code true} if the character may start a Java identifier;
10893 * {@code false} otherwise.
10894 * @see Character#isJavaIdentifierPart(int)
10895 * @see Character#isLetter(int)
10896 * @see Character#isUnicodeIdentifierStart(int)
10897 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10898 * @since 1.5
10899 */
10900 @SuppressWarnings("doclint:reference") // cross-module links
10901 public static boolean isJavaIdentifierStart(int codePoint) {
10902 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10903 }
10904
10905 /**
10906 * Determines if the specified character may be part of a Java
10907 * identifier as other than the first character.
10908 * <p>
10909 * A character may be part of a Java identifier if any of the following
10910 * conditions are true:
10911 * <ul>
10912 * <li> it is a letter
10913 * <li> it is a currency symbol (such as {@code '$'})
10914 * <li> it is a connecting punctuation character (such as {@code '_'})
10915 * <li> it is a digit
10916 * <li> it is a numeric letter (such as a Roman numeral character)
10917 * <li> it is a combining mark
10918 * <li> it is a non-spacing mark
10919 * <li> {@code isIdentifierIgnorable} returns
10920 * {@code true} for the character
10921 * </ul>
10922 *
10923 * <p><b>Note:</b> This method cannot handle <a
10924 * href="#supplementary"> supplementary characters</a>. To support
10925 * all Unicode characters, including supplementary characters, use
10926 * the {@link #isJavaIdentifierPart(int)} method.
10927 *
10928 * @param ch the character to be tested.
10929 * @return {@code true} if the character may be part of a
10930 * Java identifier; {@code false} otherwise.
10931 * @see Character#isIdentifierIgnorable(char)
10932 * @see Character#isJavaIdentifierStart(char)
10933 * @see Character#isLetterOrDigit(char)
10934 * @see Character#isUnicodeIdentifierPart(char)
10935 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10936 * @since 1.1
10937 */
10938 @SuppressWarnings("doclint:reference") // cross-module links
10939 public static boolean isJavaIdentifierPart(char ch) {
10940 return isJavaIdentifierPart((int)ch);
10941 }
10942
10943 /**
10944 * Determines if the character (Unicode code point) may be part of a Java
10945 * identifier as other than the first character.
10946 * <p>
10947 * A character may be part of a Java identifier if any of the following
10948 * conditions are true:
10949 * <ul>
10950 * <li> it is a letter
10951 * <li> it is a currency symbol (such as {@code '$'})
10952 * <li> it is a connecting punctuation character (such as {@code '_'})
10953 * <li> it is a digit
10954 * <li> it is a numeric letter (such as a Roman numeral character)
10955 * <li> it is a combining mark
10956 * <li> it is a non-spacing mark
10957 * <li> {@link #isIdentifierIgnorable(int)
10958 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10959 * the code point
10960 * </ul>
10961 *
10962 * @param codePoint the character (Unicode code point) to be tested.
10963 * @return {@code true} if the character may be part of a
10964 * Java identifier; {@code false} otherwise.
10965 * @see Character#isIdentifierIgnorable(int)
10966 * @see Character#isJavaIdentifierStart(int)
10967 * @see Character#isLetterOrDigit(int)
10968 * @see Character#isUnicodeIdentifierPart(int)
10969 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10970 * @since 1.5
10971 */
10972 @SuppressWarnings("doclint:reference") // cross-module links
10973 public static boolean isJavaIdentifierPart(int codePoint) {
10974 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10975 }
10976
10977 /**
10978 * Determines if the specified character is permissible as the
10979 * first character in a Unicode identifier.
10980 * <p>
10981 * A character may start a Unicode identifier if and only if
10982 * one of the following conditions is true:
10983 * <ul>
10984 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10985 * <li> {@link #getType(char) getType(ch)} returns
10986 * {@code LETTER_NUMBER}.
10987 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10988 * {@code Other_ID_Start}</a> character.
10989 * </ul>
10990 * <p>
10991 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10992 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10993 * with the following profile of UAX31:
10994 * <pre>
10995 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10996 * </pre>
10997 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10998 * compatibility.
10999 *
11000 * <p><b>Note:</b> This method cannot handle <a
11001 * href="#supplementary"> supplementary characters</a>. To support
11002 * all Unicode characters, including supplementary characters, use
11003 * the {@link #isUnicodeIdentifierStart(int)} method.
11004 *
11005 * @param ch the character to be tested.
11006 * @return {@code true} if the character may start a Unicode
11007 * identifier; {@code false} otherwise.
11008 *
11009 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11010 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11011 * @see Character#isJavaIdentifierStart(char)
11012 * @see Character#isLetter(char)
11013 * @see Character#isUnicodeIdentifierPart(char)
11014 * @since 1.1
11015 */
11016 public static boolean isUnicodeIdentifierStart(char ch) {
11017 return isUnicodeIdentifierStart((int)ch);
11018 }
11019
11020 /**
11021 * Determines if the specified character (Unicode code point) is permissible as the
11022 * first character in a Unicode identifier.
11023 * <p>
11024 * A character may start a Unicode identifier if and only if
11025 * one of the following conditions is true:
11026 * <ul>
11027 * <li> {@link #isLetter(int) isLetter(codePoint)}
11028 * returns {@code true}
11029 * <li> {@link #getType(int) getType(codePoint)}
11030 * returns {@code LETTER_NUMBER}.
11031 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11032 * {@code Other_ID_Start}</a> character.
11033 * </ul>
11034 * <p>
11035 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11036 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11037 * with the following profile of UAX31:
11038 * <pre>
11039 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
11040 * </pre>
11041 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
11042 * compatibility.
11043 *
11044 * @param codePoint the character (Unicode code point) to be tested.
11045 * @return {@code true} if the character may start a Unicode
11046 * identifier; {@code false} otherwise.
11047 *
11048 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11049 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11050 * @see Character#isJavaIdentifierStart(int)
11051 * @see Character#isLetter(int)
11052 * @see Character#isUnicodeIdentifierPart(int)
11053 * @since 1.5
11054 */
11055 public static boolean isUnicodeIdentifierStart(int codePoint) {
11056 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
11057 }
11058
11059 /**
11060 * Determines if the specified character may be part of a Unicode
11061 * identifier as other than the first character.
11062 * <p>
11063 * A character may be part of a Unicode identifier if and only if
11064 * one of the following statements is true:
11065 * <ul>
11066 * <li> it is a letter
11067 * <li> it is a connecting punctuation character (such as {@code '_'})
11068 * <li> it is a digit
11069 * <li> it is a numeric letter (such as a Roman numeral character)
11070 * <li> it is a combining mark
11071 * <li> it is a non-spacing mark
11072 * <li> {@code isIdentifierIgnorable} returns
11073 * {@code true} for this character.
11074 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11075 * {@code Other_ID_Start}</a> character.
11076 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
11077 * {@code Other_ID_Continue}</a> character.
11078 * </ul>
11079 * <p>
11080 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11081 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11082 * with the following profile of UAX31:
11083 * <pre>
11084 * Continue := Start + ID_Continue + ignorable
11085 * Medial := empty
11086 * ignorable := isIdentifierIgnorable(char) returns true for the character
11087 * </pre>
11088 * {@code ignorable} is added to {@code Continue} for backward
11089 * compatibility.
11090 *
11091 * <p><b>Note:</b> This method cannot handle <a
11092 * href="#supplementary"> supplementary characters</a>. To support
11093 * all Unicode characters, including supplementary characters, use
11094 * the {@link #isUnicodeIdentifierPart(int)} method.
11095 *
11096 * @param ch the character to be tested.
11097 * @return {@code true} if the character may be part of a
11098 * Unicode identifier; {@code false} otherwise.
11099 *
11100 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11101 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11102 * @see Character#isIdentifierIgnorable(char)
11103 * @see Character#isJavaIdentifierPart(char)
11104 * @see Character#isLetterOrDigit(char)
11105 * @see Character#isUnicodeIdentifierStart(char)
11106 * @since 1.1
11107 */
11108 public static boolean isUnicodeIdentifierPart(char ch) {
11109 return isUnicodeIdentifierPart((int)ch);
11110 }
11111
11112 /**
11113 * Determines if the specified character (Unicode code point) may be part of a Unicode
11114 * identifier as other than the first character.
11115 * <p>
11116 * A character may be part of a Unicode identifier if and only if
11117 * one of the following statements is true:
11118 * <ul>
11119 * <li> it is a letter
11120 * <li> it is a connecting punctuation character (such as {@code '_'})
11121 * <li> it is a digit
11122 * <li> it is a numeric letter (such as a Roman numeral character)
11123 * <li> it is a combining mark
11124 * <li> it is a non-spacing mark
11125 * <li> {@code isIdentifierIgnorable} returns
11126 * {@code true} for this character.
11127 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11128 * {@code Other_ID_Start}</a> character.
11129 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
11130 * {@code Other_ID_Continue}</a> character.
11131 * </ul>
11132 * <p>
11133 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11134 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11135 * with the following profile of UAX31:
11136 * <pre>
11137 * Continue := Start + ID_Continue + ignorable
11138 * Medial := empty
11139 * ignorable := isIdentifierIgnorable(int) returns true for the character
11140 * </pre>
11141 * {@code ignorable} is added to {@code Continue} for backward
11142 * compatibility.
11143 *
11144 * @param codePoint the character (Unicode code point) to be tested.
11145 * @return {@code true} if the character may be part of a
11146 * Unicode identifier; {@code false} otherwise.
11147 *
11148 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11149 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11150 * @see Character#isIdentifierIgnorable(int)
11151 * @see Character#isJavaIdentifierPart(int)
11152 * @see Character#isLetterOrDigit(int)
11153 * @see Character#isUnicodeIdentifierStart(int)
11154 * @since 1.5
11155 */
11156 public static boolean isUnicodeIdentifierPart(int codePoint) {
11157 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
11158 }
11159
11160 /**
11161 * Determines if the specified character should be regarded as
11162 * an ignorable character in a Java identifier or a Unicode identifier.
11163 * <p>
11164 * The following Unicode characters are ignorable in a Java identifier
11165 * or a Unicode identifier:
11166 * <ul>
11167 * <li>ISO control characters that are not whitespace
11168 * <ul>
11169 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11170 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11171 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11172 * </ul>
11173 *
11174 * <li>all characters that have the {@code FORMAT} general
11175 * category value
11176 * </ul>
11177 *
11178 * <p><b>Note:</b> This method cannot handle <a
11179 * href="#supplementary"> supplementary characters</a>. To support
11180 * all Unicode characters, including supplementary characters, use
11181 * the {@link #isIdentifierIgnorable(int)} method.
11182 *
11183 * @param ch the character to be tested.
11184 * @return {@code true} if the character is an ignorable control
11185 * character that may be part of a Java or Unicode identifier;
11186 * {@code false} otherwise.
11187 * @see Character#isJavaIdentifierPart(char)
11188 * @see Character#isUnicodeIdentifierPart(char)
11189 * @since 1.1
11190 */
11191 public static boolean isIdentifierIgnorable(char ch) {
11192 return isIdentifierIgnorable((int)ch);
11193 }
11194
11195 /**
11196 * Determines if the specified character (Unicode code point) should be regarded as
11197 * an ignorable character in a Java identifier or a Unicode identifier.
11198 * <p>
11199 * The following Unicode characters are ignorable in a Java identifier
11200 * or a Unicode identifier:
11201 * <ul>
11202 * <li>ISO control characters that are not whitespace
11203 * <ul>
11204 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11205 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11206 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11207 * </ul>
11208 *
11209 * <li>all characters that have the {@code FORMAT} general
11210 * category value
11211 * </ul>
11212 *
11213 * @param codePoint the character (Unicode code point) to be tested.
11214 * @return {@code true} if the character is an ignorable control
11215 * character that may be part of a Java or Unicode identifier;
11216 * {@code false} otherwise.
11217 * @see Character#isJavaIdentifierPart(int)
11218 * @see Character#isUnicodeIdentifierPart(int)
11219 * @since 1.5
11220 */
11221 public static boolean isIdentifierIgnorable(int codePoint) {
11222 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
11223 }
11224
11225 /**
11226 * Determines if the specified character (Unicode code point) is an Emoji.
11227 * <p>
11228 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
11229 * property, defined in
11230 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11231 * Unicode Emoji (Technical Standard #51)</a>.
11232 *
11233 * @param codePoint the character (Unicode code point) to be tested.
11234 * @return {@code true} if the character is an Emoji;
11235 * {@code false} otherwise.
11236 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11237 * @since 21
11238 */
11239 public static boolean isEmoji(int codePoint) {
11240 return CharacterData.of(codePoint).isEmoji(codePoint);
11241 }
11242
11243 /**
11244 * Determines if the specified character (Unicode code point) has the
11245 * Emoji Presentation property by default.
11246 * <p>
11247 * A character is considered to have the Emoji Presentation property if and
11248 * only if it has the {@code Emoji_Presentation} property, defined in
11249 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11250 * Unicode Emoji (Technical Standard #51)</a>.
11251 *
11252 * @param codePoint the character (Unicode code point) to be tested.
11253 * @return {@code true} if the character has the Emoji Presentation
11254 * property; {@code false} otherwise.
11255 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11256 * @since 21
11257 */
11258 public static boolean isEmojiPresentation(int codePoint) {
11259 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
11260 }
11261
11262 /**
11263 * Determines if the specified character (Unicode code point) is an
11264 * Emoji Modifier.
11265 * <p>
11266 * A character is considered to be an Emoji Modifier if and only if it has
11267 * the {@code Emoji_Modifier} property, defined in
11268 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11269 * Unicode Emoji (Technical Standard #51)</a>.
11270 *
11271 * @param codePoint the character (Unicode code point) to be tested.
11272 * @return {@code true} if the character is an Emoji Modifier;
11273 * {@code false} otherwise.
11274 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11275 * @since 21
11276 */
11277 public static boolean isEmojiModifier(int codePoint) {
11278 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
11279 }
11280
11281 /**
11282 * Determines if the specified character (Unicode code point) is an
11283 * Emoji Modifier Base.
11284 * <p>
11285 * A character is considered to be an Emoji Modifier Base if and only if it has
11286 * the {@code Emoji_Modifier_Base} property, defined in
11287 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11288 * Unicode Emoji (Technical Standard #51)</a>.
11289 *
11290 * @param codePoint the character (Unicode code point) to be tested.
11291 * @return {@code true} if the character is an Emoji Modifier Base;
11292 * {@code false} otherwise.
11293 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11294 * @since 21
11295 */
11296 public static boolean isEmojiModifierBase(int codePoint) {
11297 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
11298 }
11299
11300 /**
11301 * Determines if the specified character (Unicode code point) is an
11302 * Emoji Component.
11303 * <p>
11304 * A character is considered to be an Emoji Component if and only if it has
11305 * the {@code Emoji_Component} property, defined in
11306 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11307 * Unicode Emoji (Technical Standard #51)</a>.
11308 *
11309 * @param codePoint the character (Unicode code point) to be tested.
11310 * @return {@code true} if the character is an Emoji Component;
11311 * {@code false} otherwise.
11312 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11313 * @since 21
11314 */
11315 public static boolean isEmojiComponent(int codePoint) {
11316 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
11317 }
11318
11319 /**
11320 * Determines if the specified character (Unicode code point) is
11321 * an Extended Pictographic.
11322 * <p>
11323 * A character is considered to be an Extended Pictographic if and only if it has
11324 * the {@code Extended_Pictographic} property, defined in
11325 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11326 * Unicode Emoji (Technical Standard #51)</a>.
11327 *
11328 * @param codePoint the character (Unicode code point) to be tested.
11329 * @return {@code true} if the character is an Extended Pictographic;
11330 * {@code false} otherwise.
11331 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11332 * @since 21
11333 */
11334 public static boolean isExtendedPictographic(int codePoint) {
11335 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
11336 }
11337
11338 /**
11339 * Converts the character argument to lowercase using case
11340 * mapping information from the UnicodeData file.
11341 * <p>
11342 * Note that
11343 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
11344 * does not always return {@code true} for some ranges of
11345 * characters, particularly those that are symbols or ideographs.
11346 *
11347 * <p>In general, {@link String#toLowerCase()} should be used to map
11348 * characters to lowercase. {@code String} case mapping methods
11349 * have several benefits over {@code Character} case mapping methods.
11350 * {@code String} case mapping methods can perform locale-sensitive
11351 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11352 * the {@code Character} case mapping methods cannot.
11353 *
11354 * <p><b>Note:</b> This method cannot handle <a
11355 * href="#supplementary"> supplementary characters</a>. To support
11356 * all Unicode characters, including supplementary characters, use
11357 * the {@link #toLowerCase(int)} method.
11358 *
11359 * @param ch the character to be converted.
11360 * @return the lowercase equivalent of the character, if any;
11361 * otherwise, the character itself.
11362 * @see Character#isLowerCase(char)
11363 * @see String#toLowerCase()
11364 */
11365 public static char toLowerCase(char ch) {
11366 return (char)toLowerCase((int)ch);
11367 }
11368
11369 /**
11370 * Converts the character (Unicode code point) argument to
11371 * lowercase using case mapping information from the UnicodeData
11372 * file.
11373 *
11374 * <p> Note that
11375 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
11376 * does not always return {@code true} for some ranges of
11377 * characters, particularly those that are symbols or ideographs.
11378 *
11379 * <p>In general, {@link String#toLowerCase()} should be used to map
11380 * characters to lowercase. {@code String} case mapping methods
11381 * have several benefits over {@code Character} case mapping methods.
11382 * {@code String} case mapping methods can perform locale-sensitive
11383 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11384 * the {@code Character} case mapping methods cannot.
11385 *
11386 * @param codePoint the character (Unicode code point) to be converted.
11387 * @return the lowercase equivalent of the character (Unicode code
11388 * point), if any; otherwise, the character itself.
11389 * @see Character#isLowerCase(int)
11390 * @see String#toLowerCase()
11391 *
11392 * @since 1.5
11393 */
11394 public static int toLowerCase(int codePoint) {
11395 return CharacterData.of(codePoint).toLowerCase(codePoint);
11396 }
11397
11398 /**
11399 * Converts the character argument to uppercase using case mapping
11400 * information from the UnicodeData file.
11401 * <p>
11402 * Note that
11403 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
11404 * does not always return {@code true} for some ranges of
11405 * characters, particularly those that are symbols or ideographs.
11406 *
11407 * <p>In general, {@link String#toUpperCase()} should be used to map
11408 * characters to uppercase. {@code String} case mapping methods
11409 * have several benefits over {@code Character} case mapping methods.
11410 * {@code String} case mapping methods can perform locale-sensitive
11411 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11412 * the {@code Character} case mapping methods cannot.
11413 *
11414 * <p><b>Note:</b> This method cannot handle <a
11415 * href="#supplementary"> supplementary characters</a>. To support
11416 * all Unicode characters, including supplementary characters, use
11417 * the {@link #toUpperCase(int)} method.
11418 *
11419 * @param ch the character to be converted.
11420 * @return the uppercase equivalent of the character, if any;
11421 * otherwise, the character itself.
11422 * @see Character#isUpperCase(char)
11423 * @see String#toUpperCase()
11424 */
11425 public static char toUpperCase(char ch) {
11426 return (char)toUpperCase((int)ch);
11427 }
11428
11429 /**
11430 * Converts the character (Unicode code point) argument to
11431 * uppercase using case mapping information from the UnicodeData
11432 * file.
11433 *
11434 * <p>Note that
11435 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11436 * does not always return {@code true} for some ranges of
11437 * characters, particularly those that are symbols or ideographs.
11438 *
11439 * <p>In general, {@link String#toUpperCase()} should be used to map
11440 * characters to uppercase. {@code String} case mapping methods
11441 * have several benefits over {@code Character} case mapping methods.
11442 * {@code String} case mapping methods can perform locale-sensitive
11443 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11444 * the {@code Character} case mapping methods cannot.
11445 *
11446 * @param codePoint the character (Unicode code point) to be converted.
11447 * @return the uppercase equivalent of the character, if any;
11448 * otherwise, the character itself.
11449 * @see Character#isUpperCase(int)
11450 * @see String#toUpperCase()
11451 *
11452 * @since 1.5
11453 */
11454 public static int toUpperCase(int codePoint) {
11455 return CharacterData.of(codePoint).toUpperCase(codePoint);
11456 }
11457
11458 /**
11459 * Converts the character argument to titlecase using case mapping
11460 * information from the UnicodeData file. If a character has no
11461 * explicit titlecase mapping and is not itself a titlecase char
11462 * according to UnicodeData, then the uppercase mapping is
11463 * returned as an equivalent titlecase mapping. If the
11464 * {@code char} argument is already a titlecase
11465 * {@code char}, the same {@code char} value will be
11466 * returned.
11467 * <p>
11468 * Note that
11469 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11470 * does not always return {@code true} for some ranges of
11471 * characters.
11472 *
11473 * <p><b>Note:</b> This method cannot handle <a
11474 * href="#supplementary"> supplementary characters</a>. To support
11475 * all Unicode characters, including supplementary characters, use
11476 * the {@link #toTitleCase(int)} method.
11477 *
11478 * @param ch the character to be converted.
11479 * @return the titlecase equivalent of the character, if any;
11480 * otherwise, the character itself.
11481 * @see Character#isTitleCase(char)
11482 * @see Character#toLowerCase(char)
11483 * @see Character#toUpperCase(char)
11484 * @since 1.0.2
11485 */
11486 public static char toTitleCase(char ch) {
11487 return (char)toTitleCase((int)ch);
11488 }
11489
11490 /**
11491 * Converts the character (Unicode code point) argument to titlecase using case mapping
11492 * information from the UnicodeData file. If a character has no
11493 * explicit titlecase mapping and is not itself a titlecase char
11494 * according to UnicodeData, then the uppercase mapping is
11495 * returned as an equivalent titlecase mapping. If the
11496 * character argument is already a titlecase
11497 * character, the same character value will be
11498 * returned.
11499 *
11500 * <p>Note that
11501 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11502 * does not always return {@code true} for some ranges of
11503 * characters.
11504 *
11505 * @param codePoint the character (Unicode code point) to be converted.
11506 * @return the titlecase equivalent of the character, if any;
11507 * otherwise, the character itself.
11508 * @see Character#isTitleCase(int)
11509 * @see Character#toLowerCase(int)
11510 * @see Character#toUpperCase(int)
11511 * @since 1.5
11512 */
11513 public static int toTitleCase(int codePoint) {
11514 return CharacterData.of(codePoint).toTitleCase(codePoint);
11515 }
11516
11517 /**
11518 * Returns the numeric value of the character {@code ch} in the
11519 * specified radix.
11520 * <p>
11521 * If the radix is not in the range {@code MIN_RADIX} ≤
11522 * {@code radix} ≤ {@code MAX_RADIX} or if the
11523 * value of {@code ch} is not a valid digit in the specified
11524 * radix, {@code -1} is returned. A character is a valid digit
11525 * if at least one of the following is true:
11526 * <ul>
11527 * <li>The method {@code isDigit} is {@code true} of the character
11528 * and the Unicode decimal digit value of the character (or its
11529 * single-character decomposition) is less than the specified radix.
11530 * In this case the decimal digit value is returned.
11531 * <li>The character is one of the uppercase Latin letters
11532 * {@code 'A'} through {@code 'Z'} and its code is less than
11533 * {@code radix + 'A' - 10}.
11534 * In this case, {@code ch - 'A' + 10}
11535 * is returned.
11536 * <li>The character is one of the lowercase Latin letters
11537 * {@code 'a'} through {@code 'z'} and its code is less than
11538 * {@code radix + 'a' - 10}.
11539 * In this case, {@code ch - 'a' + 10}
11540 * is returned.
11541 * <li>The character is one of the fullwidth uppercase Latin letters A
11542 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11543 * and its code is less than
11544 * {@code radix + '\u005CuFF21' - 10}.
11545 * In this case, {@code ch - '\u005CuFF21' + 10}
11546 * is returned.
11547 * <li>The character is one of the fullwidth lowercase Latin letters a
11548 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11549 * and its code is less than
11550 * {@code radix + '\u005CuFF41' - 10}.
11551 * In this case, {@code ch - '\u005CuFF41' + 10}
11552 * is returned.
11553 * </ul>
11554 *
11555 * <p><b>Note:</b> This method cannot handle <a
11556 * href="#supplementary"> supplementary characters</a>. To support
11557 * all Unicode characters, including supplementary characters, use
11558 * the {@link #digit(int, int)} method.
11559 *
11560 * @param ch the character to be converted.
11561 * @param radix the radix.
11562 * @return the numeric value represented by the character in the
11563 * specified radix.
11564 * @see Character#forDigit(int, int)
11565 * @see Character#isDigit(char)
11566 */
11567 public static int digit(char ch, int radix) {
11568 return digit((int)ch, radix);
11569 }
11570
11571 /**
11572 * Returns the numeric value of the specified character (Unicode
11573 * code point) in the specified radix.
11574 *
11575 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11576 * {@code radix} ≤ {@code MAX_RADIX} or if the
11577 * character is not a valid digit in the specified
11578 * radix, {@code -1} is returned. A character is a valid digit
11579 * if at least one of the following is true:
11580 * <ul>
11581 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11582 * and the Unicode decimal digit value of the character (or its
11583 * single-character decomposition) is less than the specified radix.
11584 * In this case the decimal digit value is returned.
11585 * <li>The character is one of the uppercase Latin letters
11586 * {@code 'A'} through {@code 'Z'} and its code is less than
11587 * {@code radix + 'A' - 10}.
11588 * In this case, {@code codePoint - 'A' + 10}
11589 * is returned.
11590 * <li>The character is one of the lowercase Latin letters
11591 * {@code 'a'} through {@code 'z'} and its code is less than
11592 * {@code radix + 'a' - 10}.
11593 * In this case, {@code codePoint - 'a' + 10}
11594 * is returned.
11595 * <li>The character is one of the fullwidth uppercase Latin letters A
11596 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11597 * and its code is less than
11598 * {@code radix + '\u005CuFF21' - 10}.
11599 * In this case,
11600 * {@code codePoint - '\u005CuFF21' + 10}
11601 * is returned.
11602 * <li>The character is one of the fullwidth lowercase Latin letters a
11603 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11604 * and its code is less than
11605 * {@code radix + '\u005CuFF41'- 10}.
11606 * In this case,
11607 * {@code codePoint - '\u005CuFF41' + 10}
11608 * is returned.
11609 * </ul>
11610 *
11611 * @param codePoint the character (Unicode code point) to be converted.
11612 * @param radix the radix.
11613 * @return the numeric value represented by the character in the
11614 * specified radix.
11615 * @see Character#forDigit(int, int)
11616 * @see Character#isDigit(int)
11617 * @since 1.5
11618 */
11619 public static int digit(int codePoint, int radix) {
11620 return CharacterData.of(codePoint).digit(codePoint, radix);
11621 }
11622
11623 /**
11624 * Returns the {@code int} value that the specified Unicode
11625 * character represents. For example, the character
11626 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11627 * an int with a value of 50.
11628 * <p>
11629 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11630 * {@code '\u005Cu005A'}), lowercase
11631 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11632 * full width variant ({@code '\u005CuFF21'} through
11633 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11634 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11635 * through 35. This is independent of the Unicode specification,
11636 * which does not assign numeric values to these {@code char}
11637 * values.
11638 * <p>
11639 * If the character does not have a numeric value, then -1 is returned.
11640 * If the character has a numeric value that cannot be represented as a
11641 * nonnegative integer (for example, a fractional value), then -2
11642 * is returned.
11643 *
11644 * <p><b>Note:</b> This method cannot handle <a
11645 * href="#supplementary"> supplementary characters</a>. To support
11646 * all Unicode characters, including supplementary characters, use
11647 * the {@link #getNumericValue(int)} method.
11648 *
11649 * @param ch the character to be converted.
11650 * @return the numeric value of the character, as a nonnegative {@code int}
11651 * value; -2 if the character has a numeric value but the value
11652 * can not be represented as a nonnegative {@code int} value;
11653 * -1 if the character has no numeric value.
11654 * @see Character#forDigit(int, int)
11655 * @see Character#isDigit(char)
11656 * @since 1.1
11657 */
11658 public static int getNumericValue(char ch) {
11659 return getNumericValue((int)ch);
11660 }
11661
11662 /**
11663 * Returns the {@code int} value that the specified
11664 * character (Unicode code point) represents. For example, the character
11665 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11666 * an {@code int} with a value of 50.
11667 * <p>
11668 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11669 * {@code '\u005Cu005A'}), lowercase
11670 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11671 * full width variant ({@code '\u005CuFF21'} through
11672 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11673 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11674 * through 35. This is independent of the Unicode specification,
11675 * which does not assign numeric values to these {@code char}
11676 * values.
11677 * <p>
11678 * If the character does not have a numeric value, then -1 is returned.
11679 * If the character has a numeric value that cannot be represented as a
11680 * nonnegative integer (for example, a fractional value), then -2
11681 * is returned.
11682 *
11683 * @param codePoint the character (Unicode code point) to be converted.
11684 * @return the numeric value of the character, as a nonnegative {@code int}
11685 * value; -2 if the character has a numeric value but the value
11686 * can not be represented as a nonnegative {@code int} value;
11687 * -1 if the character has no numeric value.
11688 * @see Character#forDigit(int, int)
11689 * @see Character#isDigit(int)
11690 * @since 1.5
11691 */
11692 public static int getNumericValue(int codePoint) {
11693 return CharacterData.of(codePoint).getNumericValue(codePoint);
11694 }
11695
11696 /**
11697 * Determines if the specified character is ISO-LATIN-1 white space.
11698 * This method returns {@code true} for the following five
11699 * characters only:
11700 * <table class="striped">
11701 * <caption style="display:none">truechars</caption>
11702 * <thead>
11703 * <tr><th scope="col">Character
11704 * <th scope="col">Code
11705 * <th scope="col">Name
11706 * </thead>
11707 * <tbody>
11708 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11709 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11710 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11711 * <td>{@code NEW LINE}</td></tr>
11712 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11713 * <td>{@code FORM FEED}</td></tr>
11714 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11715 * <td>{@code CARRIAGE RETURN}</td></tr>
11716 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11717 * <td>{@code SPACE}</td></tr>
11718 * </tbody>
11719 * </table>
11720 *
11721 * @param ch the character to be tested.
11722 * @return {@code true} if the character is ISO-LATIN-1 white
11723 * space; {@code false} otherwise.
11724 * @see Character#isSpaceChar(char)
11725 * @see Character#isWhitespace(char)
11726 * @deprecated Replaced by isWhitespace(char).
11727 */
11728 @Deprecated(since="1.1")
11729 public static boolean isSpace(char ch) {
11730 return (ch <= 0x0020) &&
11731 (((((1L << 0x0009) |
11732 (1L << 0x000A) |
11733 (1L << 0x000C) |
11734 (1L << 0x000D) |
11735 (1L << 0x0020)) >> ch) & 1L) != 0);
11736 }
11737
11738
11739 /**
11740 * Determines if the specified character is a Unicode space character.
11741 * A character is considered to be a space character if and only if
11742 * it is specified to be a space character by the Unicode Standard. This
11743 * method returns true if the character's general category type is any of
11744 * the following:
11745 * <ul>
11746 * <li> {@code SPACE_SEPARATOR}
11747 * <li> {@code LINE_SEPARATOR}
11748 * <li> {@code PARAGRAPH_SEPARATOR}
11749 * </ul>
11750 *
11751 * <p><b>Note:</b> This method cannot handle <a
11752 * href="#supplementary"> supplementary characters</a>. To support
11753 * all Unicode characters, including supplementary characters, use
11754 * the {@link #isSpaceChar(int)} method.
11755 *
11756 * @param ch the character to be tested.
11757 * @return {@code true} if the character is a space character;
11758 * {@code false} otherwise.
11759 * @see Character#isWhitespace(char)
11760 * @since 1.1
11761 */
11762 public static boolean isSpaceChar(char ch) {
11763 return isSpaceChar((int)ch);
11764 }
11765
11766 /**
11767 * Determines if the specified character (Unicode code point) is a
11768 * Unicode space character. A character is considered to be a
11769 * space character if and only if it is specified to be a space
11770 * character by the Unicode Standard. This method returns true if
11771 * the character's general category type is any of the following:
11772 *
11773 * <ul>
11774 * <li> {@link #SPACE_SEPARATOR}
11775 * <li> {@link #LINE_SEPARATOR}
11776 * <li> {@link #PARAGRAPH_SEPARATOR}
11777 * </ul>
11778 *
11779 * @param codePoint the character (Unicode code point) to be tested.
11780 * @return {@code true} if the character is a space character;
11781 * {@code false} otherwise.
11782 * @see Character#isWhitespace(int)
11783 * @since 1.5
11784 */
11785 public static boolean isSpaceChar(int codePoint) {
11786 return ((((1 << Character.SPACE_SEPARATOR) |
11787 (1 << Character.LINE_SEPARATOR) |
11788 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11789 != 0;
11790 }
11791
11792 /**
11793 * Determines if the specified character is white space according to Java.
11794 * A character is a Java whitespace character if and only if it satisfies
11795 * one of the following criteria:
11796 * <ul>
11797 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11798 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11799 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11800 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11801 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11802 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11803 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11804 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11805 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11806 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11807 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11808 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11809 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11810 * </ul>
11811 *
11812 * <p><b>Note:</b> This method cannot handle <a
11813 * href="#supplementary"> supplementary characters</a>. To support
11814 * all Unicode characters, including supplementary characters, use
11815 * the {@link #isWhitespace(int)} method.
11816 *
11817 * @param ch the character to be tested.
11818 * @return {@code true} if the character is a Java whitespace
11819 * character; {@code false} otherwise.
11820 * @see Character#isSpaceChar(char)
11821 * @since 1.1
11822 */
11823 public static boolean isWhitespace(char ch) {
11824 return isWhitespace((int)ch);
11825 }
11826
11827 /**
11828 * Determines if the specified character (Unicode code point) is
11829 * white space according to Java. A character is a Java
11830 * whitespace character if and only if it satisfies one of the
11831 * following criteria:
11832 * <ul>
11833 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11834 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11835 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11836 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11837 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11838 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11839 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11840 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11841 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11842 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11843 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11844 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11845 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11846 * </ul>
11847 *
11848 * @param codePoint the character (Unicode code point) to be tested.
11849 * @return {@code true} if the character is a Java whitespace
11850 * character; {@code false} otherwise.
11851 * @see Character#isSpaceChar(int)
11852 * @since 1.5
11853 */
11854 public static boolean isWhitespace(int codePoint) {
11855 return CharacterData.of(codePoint).isWhitespace(codePoint);
11856 }
11857
11858 /**
11859 * Determines if the specified character is an ISO control
11860 * character. A character is considered to be an ISO control
11861 * character if its code is in the range {@code '\u005Cu0000'}
11862 * through {@code '\u005Cu001F'} or in the range
11863 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11864 *
11865 * <p><b>Note:</b> This method cannot handle <a
11866 * href="#supplementary"> supplementary characters</a>. To support
11867 * all Unicode characters, including supplementary characters, use
11868 * the {@link #isISOControl(int)} method.
11869 *
11870 * @param ch the character to be tested.
11871 * @return {@code true} if the character is an ISO control character;
11872 * {@code false} otherwise.
11873 *
11874 * @see Character#isSpaceChar(char)
11875 * @see Character#isWhitespace(char)
11876 * @since 1.1
11877 */
11878 public static boolean isISOControl(char ch) {
11879 return isISOControl((int)ch);
11880 }
11881
11882 /**
11883 * Determines if the referenced character (Unicode code point) is an ISO control
11884 * character. A character is considered to be an ISO control
11885 * character if its code is in the range {@code '\u005Cu0000'}
11886 * through {@code '\u005Cu001F'} or in the range
11887 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11888 *
11889 * @param codePoint the character (Unicode code point) to be tested.
11890 * @return {@code true} if the character is an ISO control character;
11891 * {@code false} otherwise.
11892 * @see Character#isSpaceChar(int)
11893 * @see Character#isWhitespace(int)
11894 * @since 1.5
11895 */
11896 public static boolean isISOControl(int codePoint) {
11897 // Optimized form of:
11898 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11899 // (codePoint >= 0x7F && codePoint <= 0x9F);
11900 return codePoint <= 0x9F &&
11901 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11902 }
11903
11904 /**
11905 * Returns a value indicating a character's general category.
11906 *
11907 * <p><b>Note:</b> This method cannot handle <a
11908 * href="#supplementary"> supplementary characters</a>. To support
11909 * all Unicode characters, including supplementary characters, use
11910 * the {@link #getType(int)} method.
11911 *
11912 * @param ch the character to be tested.
11913 * @return a value of type {@code int} representing the
11914 * character's general category.
11915 * @see Character#COMBINING_SPACING_MARK
11916 * @see Character#CONNECTOR_PUNCTUATION
11917 * @see Character#CONTROL
11918 * @see Character#CURRENCY_SYMBOL
11919 * @see Character#DASH_PUNCTUATION
11920 * @see Character#DECIMAL_DIGIT_NUMBER
11921 * @see Character#ENCLOSING_MARK
11922 * @see Character#END_PUNCTUATION
11923 * @see Character#FINAL_QUOTE_PUNCTUATION
11924 * @see Character#FORMAT
11925 * @see Character#INITIAL_QUOTE_PUNCTUATION
11926 * @see Character#LETTER_NUMBER
11927 * @see Character#LINE_SEPARATOR
11928 * @see Character#LOWERCASE_LETTER
11929 * @see Character#MATH_SYMBOL
11930 * @see Character#MODIFIER_LETTER
11931 * @see Character#MODIFIER_SYMBOL
11932 * @see Character#NON_SPACING_MARK
11933 * @see Character#OTHER_LETTER
11934 * @see Character#OTHER_NUMBER
11935 * @see Character#OTHER_PUNCTUATION
11936 * @see Character#OTHER_SYMBOL
11937 * @see Character#PARAGRAPH_SEPARATOR
11938 * @see Character#PRIVATE_USE
11939 * @see Character#SPACE_SEPARATOR
11940 * @see Character#START_PUNCTUATION
11941 * @see Character#SURROGATE
11942 * @see Character#TITLECASE_LETTER
11943 * @see Character#UNASSIGNED
11944 * @see Character#UPPERCASE_LETTER
11945 * @since 1.1
11946 */
11947 public static int getType(char ch) {
11948 return getType((int)ch);
11949 }
11950
11951 /**
11952 * Returns a value indicating a character's general category.
11953 *
11954 * @param codePoint the character (Unicode code point) to be tested.
11955 * @return a value of type {@code int} representing the
11956 * character's general category.
11957 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11958 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11959 * @see Character#CONTROL CONTROL
11960 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11961 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11962 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11963 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11964 * @see Character#END_PUNCTUATION END_PUNCTUATION
11965 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11966 * @see Character#FORMAT FORMAT
11967 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11968 * @see Character#LETTER_NUMBER LETTER_NUMBER
11969 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11970 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11971 * @see Character#MATH_SYMBOL MATH_SYMBOL
11972 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11973 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11974 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11975 * @see Character#OTHER_LETTER OTHER_LETTER
11976 * @see Character#OTHER_NUMBER OTHER_NUMBER
11977 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
11978 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
11979 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
11980 * @see Character#PRIVATE_USE PRIVATE_USE
11981 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
11982 * @see Character#START_PUNCTUATION START_PUNCTUATION
11983 * @see Character#SURROGATE SURROGATE
11984 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
11985 * @see Character#UNASSIGNED UNASSIGNED
11986 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
11987 * @since 1.5
11988 */
11989 public static int getType(int codePoint) {
11990 return CharacterData.of(codePoint).getType(codePoint);
11991 }
11992
11993 /**
11994 * Determines the character representation for a specific digit in
11995 * the specified radix. If the value of {@code radix} is not a
11996 * valid radix, or the value of {@code digit} is not a valid
11997 * digit in the specified radix, the null character
11998 * ({@code '\u005Cu0000'}) is returned.
11999 * <p>
12000 * The {@code radix} argument is valid if it is greater than or
12001 * equal to {@code MIN_RADIX} and less than or equal to
12002 * {@code MAX_RADIX}. The {@code digit} argument is valid if
12003 * {@code 0 <= digit < radix}.
12004 * <p>
12005 * If the digit is less than 10, then
12006 * {@code '0' + digit} is returned. Otherwise, the value
12007 * {@code 'a' + digit - 10} is returned.
12008 *
12009 * @param digit the number to convert to a character.
12010 * @param radix the radix.
12011 * @return the {@code char} representation of the specified digit
12012 * in the specified radix.
12013 * @see Character#MIN_RADIX
12014 * @see Character#MAX_RADIX
12015 * @see Character#digit(char, int)
12016 */
12017 public static char forDigit(int digit, int radix) {
12018 if ((digit >= radix) || (digit < 0)) {
12019 return '\0';
12020 }
12021 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
12022 return '\0';
12023 }
12024 if (digit < 10) {
12025 return (char)('0' + digit);
12026 }
12027 return (char)('a' - 10 + digit);
12028 }
12029
12030 /**
12031 * Returns the Unicode directionality property for the given
12032 * character. Character directionality is used to calculate the
12033 * visual ordering of text. The directionality value of undefined
12034 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
12035 *
12036 * <p><b>Note:</b> This method cannot handle <a
12037 * href="#supplementary"> supplementary characters</a>. To support
12038 * all Unicode characters, including supplementary characters, use
12039 * the {@link #getDirectionality(int)} method.
12040 *
12041 * @param ch {@code char} for which the directionality property
12042 * is requested.
12043 * @return the directionality property of the {@code char} value.
12044 *
12045 * @see Character#DIRECTIONALITY_UNDEFINED
12046 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
12047 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
12048 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
12049 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
12050 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
12051 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
12052 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
12053 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
12054 * @see Character#DIRECTIONALITY_NONSPACING_MARK
12055 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
12056 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
12057 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
12058 * @see Character#DIRECTIONALITY_WHITESPACE
12059 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
12060 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
12061 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
12062 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
12063 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
12064 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
12065 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
12066 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
12067 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
12068 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
12069 * @since 1.4
12070 */
12071 public static byte getDirectionality(char ch) {
12072 return getDirectionality((int)ch);
12073 }
12074
12075 /**
12076 * Returns the Unicode directionality property for the given
12077 * character (Unicode code point). Character directionality is
12078 * used to calculate the visual ordering of text. The
12079 * directionality value of undefined character is {@link
12080 * #DIRECTIONALITY_UNDEFINED}.
12081 *
12082 * @param codePoint the character (Unicode code point) for which
12083 * the directionality property is requested.
12084 * @return the directionality property of the character.
12085 *
12086 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
12087 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
12088 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
12089 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
12090 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
12091 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
12092 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
12093 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
12094 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
12095 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
12096 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
12097 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
12098 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
12099 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
12100 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
12101 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
12102 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
12103 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
12104 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
12105 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
12106 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
12107 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
12108 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
12109 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
12110 * @since 1.5
12111 */
12112 public static byte getDirectionality(int codePoint) {
12113 return CharacterData.of(codePoint).getDirectionality(codePoint);
12114 }
12115
12116 /**
12117 * Determines whether the character is mirrored according to the
12118 * Unicode specification. Mirrored characters should have their
12119 * glyphs horizontally mirrored when displayed in text that is
12120 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
12121 * PARENTHESIS is semantically defined to be an <i>opening
12122 * parenthesis</i>. This will appear as a "(" in text that is
12123 * left-to-right but as a ")" in text that is right-to-left.
12124 *
12125 * <p><b>Note:</b> This method cannot handle <a
12126 * href="#supplementary"> supplementary characters</a>. To support
12127 * all Unicode characters, including supplementary characters, use
12128 * the {@link #isMirrored(int)} method.
12129 *
12130 * @param ch {@code char} for which the mirrored property is requested
12131 * @return {@code true} if the char is mirrored, {@code false}
12132 * if the {@code char} is not mirrored or is not defined.
12133 * @since 1.4
12134 */
12135 public static boolean isMirrored(char ch) {
12136 return isMirrored((int)ch);
12137 }
12138
12139 /**
12140 * Determines whether the specified character (Unicode code point)
12141 * is mirrored according to the Unicode specification. Mirrored
12142 * characters should have their glyphs horizontally mirrored when
12143 * displayed in text that is right-to-left. For example,
12144 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
12145 * defined to be an <i>opening parenthesis</i>. This will appear
12146 * as a "(" in text that is left-to-right but as a ")" in text
12147 * that is right-to-left.
12148 *
12149 * @param codePoint the character (Unicode code point) to be tested.
12150 * @return {@code true} if the character is mirrored, {@code false}
12151 * if the character is not mirrored or is not defined.
12152 * @since 1.5
12153 */
12154 public static boolean isMirrored(int codePoint) {
12155 return CharacterData.of(codePoint).isMirrored(codePoint);
12156 }
12157
12158 /**
12159 * Compares two {@code Character} objects numerically.
12160 *
12161 * @param anotherCharacter the {@code Character} to be compared.
12162 * @return the value {@code 0} if the argument {@code Character}
12163 * is equal to this {@code Character}; a value less than
12164 * {@code 0} if this {@code Character} is numerically less
12165 * than the {@code Character} argument; and a value greater than
12166 * {@code 0} if this {@code Character} is numerically greater
12167 * than the {@code Character} argument (unsigned comparison).
12168 * Note that this is strictly a numerical comparison; it is not
12169 * locale-dependent.
12170 * @since 1.2
12171 */
12172 public int compareTo(Character anotherCharacter) {
12173 return compare(this.value, anotherCharacter.value);
12174 }
12175
12176 /**
12177 * Compares two {@code char} values numerically.
12178 * The value returned is identical to what would be returned by:
12179 * <pre>
12180 * Character.valueOf(x).compareTo(Character.valueOf(y))
12181 * </pre>
12182 *
12183 * @param x the first {@code char} to compare
12184 * @param y the second {@code char} to compare
12185 * @return the value {@code 0} if {@code x == y};
12186 * a value less than {@code 0} if {@code x < y}; and
12187 * a value greater than {@code 0} if {@code x > y}
12188 * @since 1.7
12189 */
12190 public static int compare(char x, char y) {
12191 return x - y;
12192 }
12193
12194 /**
12195 * Converts the character (Unicode code point) argument to uppercase using
12196 * information from the UnicodeData file.
12197 *
12198 * @param codePoint the character (Unicode code point) to be converted.
12199 * @return either the uppercase equivalent of the character, if
12200 * any, or an error flag ({@code Character.ERROR})
12201 * that indicates that a 1:M {@code char} mapping exists.
12202 * @see Character#isLowerCase(char)
12203 * @see Character#isUpperCase(char)
12204 * @see Character#toLowerCase(char)
12205 * @see Character#toTitleCase(char)
12206 * @since 1.4
12207 */
12208 static int toUpperCaseEx(int codePoint) {
12209 assert isValidCodePoint(codePoint);
12210 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
12211 }
12212
12213 /**
12214 * Converts the character (Unicode code point) argument to uppercase using case
12215 * mapping information from the SpecialCasing file in the Unicode
12216 * specification. If a character has no explicit uppercase
12217 * mapping, then the {@code char} itself is returned in the
12218 * {@code char[]}.
12219 *
12220 * @param codePoint the character (Unicode code point) to be converted.
12221 * @return a {@code char[]} with the uppercased character.
12222 * @since 1.4
12223 */
12224 static char[] toUpperCaseCharArray(int codePoint) {
12225 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
12226 assert isBmpCodePoint(codePoint);
12227 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
12228 }
12229
12230 /**
12231 * The number of bits used to represent a {@code char} value in unsigned
12232 * binary form, constant {@code 16}.
12233 *
12234 * @since 1.5
12235 */
12236 public static final int SIZE = 16;
12237
12238 /**
12239 * The number of bytes used to represent a {@code char} value in unsigned
12240 * binary form.
12241 *
12242 * @since 1.8
12243 */
12244 public static final int BYTES = SIZE / Byte.SIZE;
12245
12246 /**
12247 * Returns the value obtained by reversing the order of the bytes in the
12248 * specified {@code char} value.
12249 *
12250 * @param ch The {@code char} of which to reverse the byte order.
12251 * @return the value obtained by reversing (or, equivalently, swapping)
12252 * the bytes in the specified {@code char} value.
12253 * @since 1.5
12254 */
12255 @IntrinsicCandidate
12256 public static char reverseBytes(char ch) {
12257 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
12258 }
12259
12260 /**
12261 * Returns the name of the specified character
12262 * {@code codePoint}, or null if the code point is
12263 * {@link #UNASSIGNED unassigned}.
12264 * <p>
12265 * If the specified character is not assigned a name by
12266 * the <i>UnicodeData</i> file (part of the Unicode Character
12267 * Database maintained by the Unicode Consortium), the returned
12268 * name is the same as the result of the expression:
12269 *
12270 * <blockquote>{@code
12271 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12272 * + " "
12273 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12274 *
12275 * }</blockquote>
12276 *
12277 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
12278 * returned by this method follows the naming scheme in the
12279 * "Unicode Name Property" section of the Unicode Standard. For other
12280 * code points, such as Hangul/Ideographs, The name generation rule above
12281 * differs from the one defined in the Unicode Standard.
12282 *
12283 * @param codePoint the character (Unicode code point)
12284 *
12285 * @return the name of the specified character, or null if
12286 * the code point is unassigned.
12287 *
12288 * @throws IllegalArgumentException if the specified
12289 * {@code codePoint} is not a valid Unicode
12290 * code point.
12291 *
12292 * @since 1.7
12293 */
12294 public static String getName(int codePoint) {
12295 if (!isValidCodePoint(codePoint)) {
12296 throw new IllegalArgumentException(
12297 String.format("Not a valid Unicode code point: 0x%X", codePoint));
12298 }
12299 String name = CharacterName.getInstance().getName(codePoint);
12300 if (name != null)
12301 return name;
12302 if (getType(codePoint) == UNASSIGNED)
12303 return null;
12304 UnicodeBlock block = UnicodeBlock.of(codePoint);
12305 if (block != null)
12306 return block.toString().replace('_', ' ') + " "
12307 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12308 // should never come here
12309 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12310 }
12311
12312 /**
12313 * Returns the code point value of the Unicode character specified by
12314 * the given character name.
12315 * <p>
12316 * If a character is not assigned a name by the <i>UnicodeData</i>
12317 * file (part of the Unicode Character Database maintained by the Unicode
12318 * Consortium), its name is defined as the result of the expression:
12319 *
12320 * <blockquote>{@code
12321 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12322 * + " "
12323 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12324 *
12325 * }</blockquote>
12326 * <p>
12327 * The {@code name} matching is case insensitive, with any leading and
12328 * trailing whitespace character removed.
12329 *
12330 * For the code points in the <i>UnicodeData</i> file, this method
12331 * recognizes the name which conforms to the name defined in the
12332 * "Unicode Name Property" section in the Unicode Standard. For other
12333 * code points, this method recognizes the name generated with
12334 * {@link #getName(int)} method.
12335 *
12336 * @param name the character name
12337 *
12338 * @return the code point value of the character specified by its name.
12339 *
12340 * @throws IllegalArgumentException if the specified {@code name}
12341 * is not a valid character name.
12342 * @throws NullPointerException if {@code name} is {@code null}
12343 *
12344 * @since 9
12345 */
12346 public static int codePointOf(String name) {
12347 name = name.trim().toUpperCase(Locale.ROOT);
12348 int cp = CharacterName.getInstance().getCodePoint(name);
12349 if (cp != -1)
12350 return cp;
12351 try {
12352 int off = name.lastIndexOf(' ');
12353 if (off != -1) {
12354 cp = Integer.parseInt(name, off + 1, name.length(), 16);
12355 if (isValidCodePoint(cp) && name.equals(getName(cp)))
12356 return cp;
12357 }
12358 } catch (Exception x) {}
12359 throw new IllegalArgumentException("Unrecognized character name :" + name);
12360 }
12361 }
--- EOF ---