1 /*
2 * Copyright (c) 2002, 2024, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import jdk.internal.misc.CDS;
29 import jdk.internal.vm.annotation.IntrinsicCandidate;
30 import jdk.internal.vm.annotation.Stable;
31
32 import java.lang.constant.Constable;
33 import java.lang.constant.DynamicConstantDesc;
34 import java.util.Arrays;
35 import java.util.HashMap;
36 import java.util.Locale;
37 import java.util.Map;
38 import java.util.Objects;
39 import java.util.Optional;
40
41 import static java.lang.constant.ConstantDescs.BSM_EXPLICIT_CAST;
42 import static java.lang.constant.ConstantDescs.CD_char;
43 import static java.lang.constant.ConstantDescs.DEFAULT_NAME;
44
45 /**
46 * The {@code Character} class is the {@linkplain
47 * java.lang##wrapperClass wrapper class} for values of the primitive
48 * type {@code char}. An object of type {@code Character} contains a
49 * single field whose type is {@code char}.
50 *
51 * <p>In addition, this class provides a large number of static methods for
52 * determining a character's category (lowercase letter, digit, etc.)
53 * and for converting characters from uppercase to lowercase and vice
54 * versa.
55 *
56 * <h2><a id="conformance">Unicode Conformance</a></h2>
57 * <p>
58 * The fields and methods of class {@code Character} are defined in terms
59 * of character information from the Unicode Standard, specifically the
60 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
61 * This file specifies properties including name and category for every
62 * assigned Unicode code point or character range. The file is available
63 * from the Unicode Consortium at
64 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
65 * <p>
66 * Character information is based on the Unicode Standard, version 15.1.
67 * <p>
68 * The Java platform has supported different versions of the Unicode
69 * Standard over time. Upgrades to newer versions of the Unicode Standard
70 * occurred in the following Java releases, each indicating the new version:
71 * <table class="striped">
72 * <caption style="display:none">Shows Java releases and supported Unicode versions</caption>
73 * <thead>
74 * <tr><th scope="col">Java release</th>
75 * <th scope="col">Unicode version</th></tr>
76 * </thead>
77 * <tbody>
78 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
79 * <td>Unicode 15.1</td></tr>
80 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
81 * <td>Unicode 15.0</td></tr>
82 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
83 * <td>Unicode 14.0</td></tr>
84 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
85 * <td>Unicode 13.0</td></tr>
86 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
87 * <td>Unicode 12.1</td></tr>
88 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
89 * <td>Unicode 11.0</td></tr>
90 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
91 * <td>Unicode 10.0</td></tr>
92 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
93 * <td>Unicode 8.0</td></tr>
94 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
95 * <td>Unicode 6.2</td></tr>
96 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
97 * <td>Unicode 6.0</td></tr>
98 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
99 * <td>Unicode 4.0</td></tr>
100 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
101 * <td>Unicode 3.0</td></tr>
102 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
103 * <td>Unicode 2.0</td></tr>
104 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
105 * <td>Unicode 1.1.5</td></tr>
106 * </tbody>
107 * </table>
108 * Variations from these base Unicode versions, such as recognized appendixes,
109 * are documented elsewhere.
110 * <h2><a id="unicode">Unicode Character Representations</a></h2>
111 *
112 * <p>The {@code char} data type (and therefore the value that a
113 * {@code Character} object encapsulates) are based on the
114 * original Unicode specification, which defined characters as
115 * fixed-width 16-bit entities. The Unicode Standard has since been
116 * changed to allow for characters whose representation requires more
117 * than 16 bits. The range of legal <em>code point</em>s is now
118 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
119 * (Refer to the <a
120 * href="http://www.unicode.org/reports/tr27/#notation"><i>
121 * definition</i></a> of the U+<i>n</i> notation in the Unicode
122 * Standard.)
123 *
124 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
125 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
126 * <a id="supplementary">Characters</a> whose code points are greater
127 * than U+FFFF are called <em>supplementary character</em>s. The Java
128 * platform uses the UTF-16 representation in {@code char} arrays and
129 * in the {@code String} and {@code StringBuffer} classes. In
130 * this representation, supplementary characters are represented as a pair
131 * of {@code char} values, the first from the <em>high-surrogates</em>
132 * range, (\uD800-\uDBFF), the second from the
133 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
134 *
135 * <p>A {@code char} value, therefore, represents Basic
136 * Multilingual Plane (BMP) code points, including the surrogate
137 * code points, or code units of the UTF-16 encoding. An
138 * {@code int} value represents all Unicode code points,
139 * including supplementary code points. The lower (least significant)
140 * 21 bits of {@code int} are used to represent Unicode code
141 * points and the upper (most significant) 11 bits must be zero.
142 * Unless otherwise specified, the behavior with respect to
143 * supplementary characters and surrogate {@code char} values is
144 * as follows:
145 *
146 * <ul>
147 * <li>The methods that only accept a {@code char} value cannot support
148 * supplementary characters. They treat {@code char} values from the
149 * surrogate ranges as undefined characters. For example,
150 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
151 * this specific value if followed by any low-surrogate value in a string
152 * would represent a letter.
153 *
154 * <li>The methods that accept an {@code int} value support all
155 * Unicode characters, including supplementary characters. For
156 * example, {@code Character.isLetter(0x2F81A)} returns
157 * {@code true} because the code point value represents a letter
158 * (a CJK ideograph).
159 * </ul>
160 *
161 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
162 * used for character values in the range between U+0000 and U+10FFFF,
163 * and <em>Unicode code unit</em> is used for 16-bit
164 * {@code char} values that are code units of the <em>UTF-16</em>
165 * encoding. For more information on Unicode terminology, refer to the
166 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
167 *
168 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
169 * class; programmers should treat instances that are
170 * {@linkplain #equals(Object) equal} as interchangeable and should not
171 * use instances for synchronization, or unpredictable behavior may
172 * occur. For example, in a future release, synchronization may fail.
173 *
174 * @spec https://www.unicode.org/reports/tr27 Unicode 3.1.0
175 * @author Lee Boynton
176 * @author Guy Steele
177 * @author Akira Tanaka
178 * @author Martin Buchholz
179 * @author Ulf Zibis
180 * @since 1.0
181 */
182 @jdk.internal.ValueBased
183 public final
184 class Character implements java.io.Serializable, Comparable<Character>, Constable {
185 /**
186 * The minimum radix available for conversion to and from strings.
187 * The constant value of this field is the smallest value permitted
188 * for the radix argument in radix-conversion methods such as the
189 * {@code digit} method, the {@code forDigit} method, and the
190 * {@code toString} method of class {@code Integer}.
191 *
192 * @see Character#digit(char, int)
193 * @see Character#forDigit(int, int)
194 * @see Integer#toString(int, int)
195 * @see Integer#valueOf(String)
196 */
197 public static final int MIN_RADIX = 2;
198
199 /**
200 * The maximum radix available for conversion to and from strings.
201 * The constant value of this field is the largest value permitted
202 * for the radix argument in radix-conversion methods such as the
203 * {@code digit} method, the {@code forDigit} method, and the
204 * {@code toString} method of class {@code Integer}.
205 *
206 * @see Character#digit(char, int)
207 * @see Character#forDigit(int, int)
208 * @see Integer#toString(int, int)
209 * @see Integer#valueOf(String)
210 */
211 public static final int MAX_RADIX = 36;
212
213 /**
214 * The constant value of this field is the smallest value of type
215 * {@code char}, {@code '\u005Cu0000'}.
216 *
217 * @since 1.0.2
218 */
219 public static final char MIN_VALUE = '\u0000';
220
221 /**
222 * The constant value of this field is the largest value of type
223 * {@code char}, {@code '\u005CuFFFF'}.
224 *
225 * @since 1.0.2
226 */
227 public static final char MAX_VALUE = '\uFFFF';
228
229 /**
230 * The {@code Class} instance representing the primitive type
231 * {@code char}.
232 *
233 * @since 1.1
234 */
235 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
236
237 /*
238 * Normative general types
239 */
240
241 /*
242 * General character types
243 */
244
245 /**
246 * General category "Cn" in the Unicode specification.
247 * @since 1.1
248 */
249 public static final byte UNASSIGNED = 0;
250
251 /**
252 * General category "Lu" in the Unicode specification.
253 * @since 1.1
254 */
255 public static final byte UPPERCASE_LETTER = 1;
256
257 /**
258 * General category "Ll" in the Unicode specification.
259 * @since 1.1
260 */
261 public static final byte LOWERCASE_LETTER = 2;
262
263 /**
264 * General category "Lt" in the Unicode specification.
265 * @since 1.1
266 */
267 public static final byte TITLECASE_LETTER = 3;
268
269 /**
270 * General category "Lm" in the Unicode specification.
271 * @since 1.1
272 */
273 public static final byte MODIFIER_LETTER = 4;
274
275 /**
276 * General category "Lo" in the Unicode specification.
277 * @since 1.1
278 */
279 public static final byte OTHER_LETTER = 5;
280
281 /**
282 * General category "Mn" in the Unicode specification.
283 * @since 1.1
284 */
285 public static final byte NON_SPACING_MARK = 6;
286
287 /**
288 * General category "Me" in the Unicode specification.
289 * @since 1.1
290 */
291 public static final byte ENCLOSING_MARK = 7;
292
293 /**
294 * General category "Mc" in the Unicode specification.
295 * @since 1.1
296 */
297 public static final byte COMBINING_SPACING_MARK = 8;
298
299 /**
300 * General category "Nd" in the Unicode specification.
301 * @since 1.1
302 */
303 public static final byte DECIMAL_DIGIT_NUMBER = 9;
304
305 /**
306 * General category "Nl" in the Unicode specification.
307 * @since 1.1
308 */
309 public static final byte LETTER_NUMBER = 10;
310
311 /**
312 * General category "No" in the Unicode specification.
313 * @since 1.1
314 */
315 public static final byte OTHER_NUMBER = 11;
316
317 /**
318 * General category "Zs" in the Unicode specification.
319 * @since 1.1
320 */
321 public static final byte SPACE_SEPARATOR = 12;
322
323 /**
324 * General category "Zl" in the Unicode specification.
325 * @since 1.1
326 */
327 public static final byte LINE_SEPARATOR = 13;
328
329 /**
330 * General category "Zp" in the Unicode specification.
331 * @since 1.1
332 */
333 public static final byte PARAGRAPH_SEPARATOR = 14;
334
335 /**
336 * General category "Cc" in the Unicode specification.
337 * @since 1.1
338 */
339 public static final byte CONTROL = 15;
340
341 /**
342 * General category "Cf" in the Unicode specification.
343 * @since 1.1
344 */
345 public static final byte FORMAT = 16;
346
347 /**
348 * General category "Co" in the Unicode specification.
349 * @since 1.1
350 */
351 public static final byte PRIVATE_USE = 18;
352
353 /**
354 * General category "Cs" in the Unicode specification.
355 * @since 1.1
356 */
357 public static final byte SURROGATE = 19;
358
359 /**
360 * General category "Pd" in the Unicode specification.
361 * @since 1.1
362 */
363 public static final byte DASH_PUNCTUATION = 20;
364
365 /**
366 * General category "Ps" in the Unicode specification.
367 * @since 1.1
368 */
369 public static final byte START_PUNCTUATION = 21;
370
371 /**
372 * General category "Pe" in the Unicode specification.
373 * @since 1.1
374 */
375 public static final byte END_PUNCTUATION = 22;
376
377 /**
378 * General category "Pc" in the Unicode specification.
379 * @since 1.1
380 */
381 public static final byte CONNECTOR_PUNCTUATION = 23;
382
383 /**
384 * General category "Po" in the Unicode specification.
385 * @since 1.1
386 */
387 public static final byte OTHER_PUNCTUATION = 24;
388
389 /**
390 * General category "Sm" in the Unicode specification.
391 * @since 1.1
392 */
393 public static final byte MATH_SYMBOL = 25;
394
395 /**
396 * General category "Sc" in the Unicode specification.
397 * @since 1.1
398 */
399 public static final byte CURRENCY_SYMBOL = 26;
400
401 /**
402 * General category "Sk" in the Unicode specification.
403 * @since 1.1
404 */
405 public static final byte MODIFIER_SYMBOL = 27;
406
407 /**
408 * General category "So" in the Unicode specification.
409 * @since 1.1
410 */
411 public static final byte OTHER_SYMBOL = 28;
412
413 /**
414 * General category "Pi" in the Unicode specification.
415 * @since 1.4
416 */
417 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
418
419 /**
420 * General category "Pf" in the Unicode specification.
421 * @since 1.4
422 */
423 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
424
425 /**
426 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
427 */
428 static final int ERROR = 0xFFFFFFFF;
429
430
431 /**
432 * Undefined bidirectional character type. Undefined {@code char}
433 * values have undefined directionality in the Unicode specification.
434 * @since 1.4
435 */
436 public static final byte DIRECTIONALITY_UNDEFINED = -1;
437
438 /**
439 * Strong bidirectional character type "L" in the Unicode specification.
440 * @since 1.4
441 */
442 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
443
444 /**
445 * Strong bidirectional character type "R" in the Unicode specification.
446 * @since 1.4
447 */
448 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
449
450 /**
451 * Strong bidirectional character type "AL" in the Unicode specification.
452 * @since 1.4
453 */
454 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
455
456 /**
457 * Weak bidirectional character type "EN" in the Unicode specification.
458 * @since 1.4
459 */
460 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
461
462 /**
463 * Weak bidirectional character type "ES" in the Unicode specification.
464 * @since 1.4
465 */
466 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
467
468 /**
469 * Weak bidirectional character type "ET" in the Unicode specification.
470 * @since 1.4
471 */
472 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
473
474 /**
475 * Weak bidirectional character type "AN" in the Unicode specification.
476 * @since 1.4
477 */
478 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
479
480 /**
481 * Weak bidirectional character type "CS" in the Unicode specification.
482 * @since 1.4
483 */
484 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
485
486 /**
487 * Weak bidirectional character type "NSM" in the Unicode specification.
488 * @since 1.4
489 */
490 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
491
492 /**
493 * Weak bidirectional character type "BN" in the Unicode specification.
494 * @since 1.4
495 */
496 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
497
498 /**
499 * Neutral bidirectional character type "B" in the Unicode specification.
500 * @since 1.4
501 */
502 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
503
504 /**
505 * Neutral bidirectional character type "S" in the Unicode specification.
506 * @since 1.4
507 */
508 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
509
510 /**
511 * Neutral bidirectional character type "WS" in the Unicode specification.
512 * @since 1.4
513 */
514 public static final byte DIRECTIONALITY_WHITESPACE = 12;
515
516 /**
517 * Neutral bidirectional character type "ON" in the Unicode specification.
518 * @since 1.4
519 */
520 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
521
522 /**
523 * Strong bidirectional character type "LRE" in the Unicode specification.
524 * @since 1.4
525 */
526 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
527
528 /**
529 * Strong bidirectional character type "LRO" in the Unicode specification.
530 * @since 1.4
531 */
532 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
533
534 /**
535 * Strong bidirectional character type "RLE" in the Unicode specification.
536 * @since 1.4
537 */
538 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
539
540 /**
541 * Strong bidirectional character type "RLO" in the Unicode specification.
542 * @since 1.4
543 */
544 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
545
546 /**
547 * Weak bidirectional character type "PDF" in the Unicode specification.
548 * @since 1.4
549 */
550 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
551
552 /**
553 * Weak bidirectional character type "LRI" in the Unicode specification.
554 * @since 9
555 */
556 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
557
558 /**
559 * Weak bidirectional character type "RLI" in the Unicode specification.
560 * @since 9
561 */
562 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
563
564 /**
565 * Weak bidirectional character type "FSI" in the Unicode specification.
566 * @since 9
567 */
568 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
569
570 /**
571 * Weak bidirectional character type "PDI" in the Unicode specification.
572 * @since 9
573 */
574 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
575
576 /**
577 * The minimum value of a
578 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
579 * Unicode high-surrogate code unit</a>
580 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
581 * A high-surrogate is also known as a <i>leading-surrogate</i>.
582 *
583 * @since 1.5
584 */
585 public static final char MIN_HIGH_SURROGATE = '\uD800';
586
587 /**
588 * The maximum value of a
589 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
590 * Unicode high-surrogate code unit</a>
591 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
592 * A high-surrogate is also known as a <i>leading-surrogate</i>.
593 *
594 * @since 1.5
595 */
596 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
597
598 /**
599 * The minimum value of a
600 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
601 * Unicode low-surrogate code unit</a>
602 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
603 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
604 *
605 * @since 1.5
606 */
607 public static final char MIN_LOW_SURROGATE = '\uDC00';
608
609 /**
610 * The maximum value of a
611 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
612 * Unicode low-surrogate code unit</a>
613 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
614 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
615 *
616 * @since 1.5
617 */
618 public static final char MAX_LOW_SURROGATE = '\uDFFF';
619
620 /**
621 * The minimum value of a Unicode surrogate code unit in the
622 * UTF-16 encoding, constant {@code '\u005CuD800'}.
623 *
624 * @since 1.5
625 */
626 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
627
628 /**
629 * The maximum value of a Unicode surrogate code unit in the
630 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
631 *
632 * @since 1.5
633 */
634 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
635
636 /**
637 * The minimum value of a
638 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
639 * Unicode supplementary code point</a>, constant {@code U+10000}.
640 *
641 * @since 1.5
642 */
643 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
644
645 /**
646 * The minimum value of a
647 * <a href="http://www.unicode.org/glossary/#code_point">
648 * Unicode code point</a>, constant {@code U+0000}.
649 *
650 * @since 1.5
651 */
652 public static final int MIN_CODE_POINT = 0x000000;
653
654 /**
655 * The maximum value of a
656 * <a href="http://www.unicode.org/glossary/#code_point">
657 * Unicode code point</a>, constant {@code U+10FFFF}.
658 *
659 * @since 1.5
660 */
661 public static final int MAX_CODE_POINT = 0X10FFFF;
662
663 /**
664 * Returns an {@link Optional} containing the nominal descriptor for this
665 * instance.
666 *
667 * @return an {@link Optional} describing the {@linkplain Character} instance
668 * @since 15
669 */
670 @Override
671 public Optional<DynamicConstantDesc<Character>> describeConstable() {
672 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
673 }
674
675 /**
676 * Instances of this class represent particular subsets of the Unicode
677 * character set. The only family of subsets defined in the
678 * {@code Character} class is {@link Character.UnicodeBlock}.
679 * Other portions of the Java API may define other subsets for their
680 * own purposes.
681 *
682 * @since 1.2
683 */
684 public static class Subset {
685
686 private String name;
687
688 /**
689 * Constructs a new {@code Subset} instance.
690 *
691 * @param name The name of this subset
692 * @throws NullPointerException if name is {@code null}
693 */
694 protected Subset(String name) {
695 if (name == null) {
696 throw new NullPointerException("name");
697 }
698 this.name = name;
699 }
700
701 /**
702 * Compares two {@code Subset} objects for equality.
703 * This method returns {@code true} if and only if
704 * {@code this} and the argument refer to the same
705 * object; since this method is {@code final}, this
706 * guarantee holds for all subclasses.
707 */
708 public final boolean equals(Object obj) {
709 return (this == obj);
710 }
711
712 /**
713 * Returns the standard hash code as defined by the
714 * {@link Object#hashCode} method. This method
715 * is {@code final} in order to ensure that the
716 * {@code equals} and {@code hashCode} methods will
717 * be consistent in all subclasses.
718 */
719 public final int hashCode() {
720 return super.hashCode();
721 }
722
723 /**
724 * Returns the name of this subset.
725 */
726 public final String toString() {
727 return name;
728 }
729 }
730
731 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
732 // for the latest specification of Unicode Blocks.
733
734 /**
735 * A family of character subsets representing the character blocks in the
736 * Unicode specification. Character blocks generally define characters
737 * used for a specific script or purpose. A character is contained by
738 * at most one Unicode block.
739 *
740 * @since 1.2
741 */
742 public static final class UnicodeBlock extends Subset {
743 /**
744 * NUM_ENTITIES should match the total number of UnicodeBlocks.
745 * It should be adjusted whenever the Unicode Character Database
746 * is upgraded.
747 */
748 private static final int NUM_ENTITIES = 759;
749 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
750
751 /**
752 * Creates a UnicodeBlock with the given identifier name.
753 * This name must be the same as the block identifier.
754 */
755 private UnicodeBlock(String idName) {
756 super(idName);
757 map.put(idName, this);
758 }
759
760 /**
761 * Creates a UnicodeBlock with the given identifier name and
762 * alias name.
763 */
764 private UnicodeBlock(String idName, String alias) {
765 this(idName);
766 map.put(alias, this);
767 }
768
769 /**
770 * Creates a UnicodeBlock with the given identifier name and
771 * alias names.
772 */
773 private UnicodeBlock(String idName, String... aliases) {
774 this(idName);
775 for (String alias : aliases)
776 map.put(alias, this);
777 }
778
779 /**
780 * Constant for the "Basic Latin" Unicode character block.
781 * @since 1.2
782 */
783 public static final UnicodeBlock BASIC_LATIN =
784 new UnicodeBlock("BASIC_LATIN",
785 "BASIC LATIN",
786 "BASICLATIN");
787
788 /**
789 * Constant for the "Latin-1 Supplement" Unicode character block.
790 * @since 1.2
791 */
792 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
793 new UnicodeBlock("LATIN_1_SUPPLEMENT",
794 "LATIN-1 SUPPLEMENT",
795 "LATIN-1SUPPLEMENT");
796
797 /**
798 * Constant for the "Latin Extended-A" Unicode character block.
799 * @since 1.2
800 */
801 public static final UnicodeBlock LATIN_EXTENDED_A =
802 new UnicodeBlock("LATIN_EXTENDED_A",
803 "LATIN EXTENDED-A",
804 "LATINEXTENDED-A");
805
806 /**
807 * Constant for the "Latin Extended-B" Unicode character block.
808 * @since 1.2
809 */
810 public static final UnicodeBlock LATIN_EXTENDED_B =
811 new UnicodeBlock("LATIN_EXTENDED_B",
812 "LATIN EXTENDED-B",
813 "LATINEXTENDED-B");
814
815 /**
816 * Constant for the "IPA Extensions" Unicode character block.
817 * @since 1.2
818 */
819 public static final UnicodeBlock IPA_EXTENSIONS =
820 new UnicodeBlock("IPA_EXTENSIONS",
821 "IPA EXTENSIONS",
822 "IPAEXTENSIONS");
823
824 /**
825 * Constant for the "Spacing Modifier Letters" Unicode character block.
826 * @since 1.2
827 */
828 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
829 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
830 "SPACING MODIFIER LETTERS",
831 "SPACINGMODIFIERLETTERS");
832
833 /**
834 * Constant for the "Combining Diacritical Marks" Unicode character block.
835 * @since 1.2
836 */
837 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
838 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
839 "COMBINING DIACRITICAL MARKS",
840 "COMBININGDIACRITICALMARKS");
841
842 /**
843 * Constant for the "Greek and Coptic" Unicode character block.
844 * <p>
845 * This block was previously known as the "Greek" block.
846 *
847 * @since 1.2
848 */
849 public static final UnicodeBlock GREEK =
850 new UnicodeBlock("GREEK",
851 "GREEK AND COPTIC",
852 "GREEKANDCOPTIC");
853
854 /**
855 * Constant for the "Cyrillic" Unicode character block.
856 * @since 1.2
857 */
858 public static final UnicodeBlock CYRILLIC =
859 new UnicodeBlock("CYRILLIC");
860
861 /**
862 * Constant for the "Armenian" Unicode character block.
863 * @since 1.2
864 */
865 public static final UnicodeBlock ARMENIAN =
866 new UnicodeBlock("ARMENIAN");
867
868 /**
869 * Constant for the "Hebrew" Unicode character block.
870 * @since 1.2
871 */
872 public static final UnicodeBlock HEBREW =
873 new UnicodeBlock("HEBREW");
874
875 /**
876 * Constant for the "Arabic" Unicode character block.
877 * @since 1.2
878 */
879 public static final UnicodeBlock ARABIC =
880 new UnicodeBlock("ARABIC");
881
882 /**
883 * Constant for the "Devanagari" Unicode character block.
884 * @since 1.2
885 */
886 public static final UnicodeBlock DEVANAGARI =
887 new UnicodeBlock("DEVANAGARI");
888
889 /**
890 * Constant for the "Bengali" Unicode character block.
891 * @since 1.2
892 */
893 public static final UnicodeBlock BENGALI =
894 new UnicodeBlock("BENGALI");
895
896 /**
897 * Constant for the "Gurmukhi" Unicode character block.
898 * @since 1.2
899 */
900 public static final UnicodeBlock GURMUKHI =
901 new UnicodeBlock("GURMUKHI");
902
903 /**
904 * Constant for the "Gujarati" Unicode character block.
905 * @since 1.2
906 */
907 public static final UnicodeBlock GUJARATI =
908 new UnicodeBlock("GUJARATI");
909
910 /**
911 * Constant for the "Oriya" Unicode character block.
912 * @since 1.2
913 */
914 public static final UnicodeBlock ORIYA =
915 new UnicodeBlock("ORIYA");
916
917 /**
918 * Constant for the "Tamil" Unicode character block.
919 * @since 1.2
920 */
921 public static final UnicodeBlock TAMIL =
922 new UnicodeBlock("TAMIL");
923
924 /**
925 * Constant for the "Telugu" Unicode character block.
926 * @since 1.2
927 */
928 public static final UnicodeBlock TELUGU =
929 new UnicodeBlock("TELUGU");
930
931 /**
932 * Constant for the "Kannada" Unicode character block.
933 * @since 1.2
934 */
935 public static final UnicodeBlock KANNADA =
936 new UnicodeBlock("KANNADA");
937
938 /**
939 * Constant for the "Malayalam" Unicode character block.
940 * @since 1.2
941 */
942 public static final UnicodeBlock MALAYALAM =
943 new UnicodeBlock("MALAYALAM");
944
945 /**
946 * Constant for the "Thai" Unicode character block.
947 * @since 1.2
948 */
949 public static final UnicodeBlock THAI =
950 new UnicodeBlock("THAI");
951
952 /**
953 * Constant for the "Lao" Unicode character block.
954 * @since 1.2
955 */
956 public static final UnicodeBlock LAO =
957 new UnicodeBlock("LAO");
958
959 /**
960 * Constant for the "Tibetan" Unicode character block.
961 * @since 1.2
962 */
963 public static final UnicodeBlock TIBETAN =
964 new UnicodeBlock("TIBETAN");
965
966 /**
967 * Constant for the "Georgian" Unicode character block.
968 * @since 1.2
969 */
970 public static final UnicodeBlock GEORGIAN =
971 new UnicodeBlock("GEORGIAN");
972
973 /**
974 * Constant for the "Hangul Jamo" Unicode character block.
975 * @since 1.2
976 */
977 public static final UnicodeBlock HANGUL_JAMO =
978 new UnicodeBlock("HANGUL_JAMO",
979 "HANGUL JAMO",
980 "HANGULJAMO");
981
982 /**
983 * Constant for the "Latin Extended Additional" Unicode character block.
984 * @since 1.2
985 */
986 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
987 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
988 "LATIN EXTENDED ADDITIONAL",
989 "LATINEXTENDEDADDITIONAL");
990
991 /**
992 * Constant for the "Greek Extended" Unicode character block.
993 * @since 1.2
994 */
995 public static final UnicodeBlock GREEK_EXTENDED =
996 new UnicodeBlock("GREEK_EXTENDED",
997 "GREEK EXTENDED",
998 "GREEKEXTENDED");
999
1000 /**
1001 * Constant for the "General Punctuation" Unicode character block.
1002 * @since 1.2
1003 */
1004 public static final UnicodeBlock GENERAL_PUNCTUATION =
1005 new UnicodeBlock("GENERAL_PUNCTUATION",
1006 "GENERAL PUNCTUATION",
1007 "GENERALPUNCTUATION");
1008
1009 /**
1010 * Constant for the "Superscripts and Subscripts" Unicode character
1011 * block.
1012 * @since 1.2
1013 */
1014 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1015 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1016 "SUPERSCRIPTS AND SUBSCRIPTS",
1017 "SUPERSCRIPTSANDSUBSCRIPTS");
1018
1019 /**
1020 * Constant for the "Currency Symbols" Unicode character block.
1021 * @since 1.2
1022 */
1023 public static final UnicodeBlock CURRENCY_SYMBOLS =
1024 new UnicodeBlock("CURRENCY_SYMBOLS",
1025 "CURRENCY SYMBOLS",
1026 "CURRENCYSYMBOLS");
1027
1028 /**
1029 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1030 * character block.
1031 * <p>
1032 * This block was previously known as "Combining Marks for Symbols".
1033 * @since 1.2
1034 */
1035 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1036 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1037 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1038 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1039 "COMBINING MARKS FOR SYMBOLS",
1040 "COMBININGMARKSFORSYMBOLS");
1041
1042 /**
1043 * Constant for the "Letterlike Symbols" Unicode character block.
1044 * @since 1.2
1045 */
1046 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1047 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1048 "LETTERLIKE SYMBOLS",
1049 "LETTERLIKESYMBOLS");
1050
1051 /**
1052 * Constant for the "Number Forms" Unicode character block.
1053 * @since 1.2
1054 */
1055 public static final UnicodeBlock NUMBER_FORMS =
1056 new UnicodeBlock("NUMBER_FORMS",
1057 "NUMBER FORMS",
1058 "NUMBERFORMS");
1059
1060 /**
1061 * Constant for the "Arrows" Unicode character block.
1062 * @since 1.2
1063 */
1064 public static final UnicodeBlock ARROWS =
1065 new UnicodeBlock("ARROWS");
1066
1067 /**
1068 * Constant for the "Mathematical Operators" Unicode character block.
1069 * @since 1.2
1070 */
1071 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1072 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1073 "MATHEMATICAL OPERATORS",
1074 "MATHEMATICALOPERATORS");
1075
1076 /**
1077 * Constant for the "Miscellaneous Technical" Unicode character block.
1078 * @since 1.2
1079 */
1080 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1081 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1082 "MISCELLANEOUS TECHNICAL",
1083 "MISCELLANEOUSTECHNICAL");
1084
1085 /**
1086 * Constant for the "Control Pictures" Unicode character block.
1087 * @since 1.2
1088 */
1089 public static final UnicodeBlock CONTROL_PICTURES =
1090 new UnicodeBlock("CONTROL_PICTURES",
1091 "CONTROL PICTURES",
1092 "CONTROLPICTURES");
1093
1094 /**
1095 * Constant for the "Optical Character Recognition" Unicode character block.
1096 * @since 1.2
1097 */
1098 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1099 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1100 "OPTICAL CHARACTER RECOGNITION",
1101 "OPTICALCHARACTERRECOGNITION");
1102
1103 /**
1104 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1105 * @since 1.2
1106 */
1107 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1108 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1109 "ENCLOSED ALPHANUMERICS",
1110 "ENCLOSEDALPHANUMERICS");
1111
1112 /**
1113 * Constant for the "Box Drawing" Unicode character block.
1114 * @since 1.2
1115 */
1116 public static final UnicodeBlock BOX_DRAWING =
1117 new UnicodeBlock("BOX_DRAWING",
1118 "BOX DRAWING",
1119 "BOXDRAWING");
1120
1121 /**
1122 * Constant for the "Block Elements" Unicode character block.
1123 * @since 1.2
1124 */
1125 public static final UnicodeBlock BLOCK_ELEMENTS =
1126 new UnicodeBlock("BLOCK_ELEMENTS",
1127 "BLOCK ELEMENTS",
1128 "BLOCKELEMENTS");
1129
1130 /**
1131 * Constant for the "Geometric Shapes" Unicode character block.
1132 * @since 1.2
1133 */
1134 public static final UnicodeBlock GEOMETRIC_SHAPES =
1135 new UnicodeBlock("GEOMETRIC_SHAPES",
1136 "GEOMETRIC SHAPES",
1137 "GEOMETRICSHAPES");
1138
1139 /**
1140 * Constant for the "Miscellaneous Symbols" Unicode character block.
1141 * @since 1.2
1142 */
1143 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1144 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1145 "MISCELLANEOUS SYMBOLS",
1146 "MISCELLANEOUSSYMBOLS");
1147
1148 /**
1149 * Constant for the "Dingbats" Unicode character block.
1150 * @since 1.2
1151 */
1152 public static final UnicodeBlock DINGBATS =
1153 new UnicodeBlock("DINGBATS");
1154
1155 /**
1156 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1157 * @since 1.2
1158 */
1159 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1160 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1161 "CJK SYMBOLS AND PUNCTUATION",
1162 "CJKSYMBOLSANDPUNCTUATION");
1163
1164 /**
1165 * Constant for the "Hiragana" Unicode character block.
1166 * @since 1.2
1167 */
1168 public static final UnicodeBlock HIRAGANA =
1169 new UnicodeBlock("HIRAGANA");
1170
1171 /**
1172 * Constant for the "Katakana" Unicode character block.
1173 * @since 1.2
1174 */
1175 public static final UnicodeBlock KATAKANA =
1176 new UnicodeBlock("KATAKANA");
1177
1178 /**
1179 * Constant for the "Bopomofo" Unicode character block.
1180 * @since 1.2
1181 */
1182 public static final UnicodeBlock BOPOMOFO =
1183 new UnicodeBlock("BOPOMOFO");
1184
1185 /**
1186 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1187 * @since 1.2
1188 */
1189 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1190 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1191 "HANGUL COMPATIBILITY JAMO",
1192 "HANGULCOMPATIBILITYJAMO");
1193
1194 /**
1195 * Constant for the "Kanbun" Unicode character block.
1196 * @since 1.2
1197 */
1198 public static final UnicodeBlock KANBUN =
1199 new UnicodeBlock("KANBUN");
1200
1201 /**
1202 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1203 * @since 1.2
1204 */
1205 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1206 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1207 "ENCLOSED CJK LETTERS AND MONTHS",
1208 "ENCLOSEDCJKLETTERSANDMONTHS");
1209
1210 /**
1211 * Constant for the "CJK Compatibility" Unicode character block.
1212 * @since 1.2
1213 */
1214 public static final UnicodeBlock CJK_COMPATIBILITY =
1215 new UnicodeBlock("CJK_COMPATIBILITY",
1216 "CJK COMPATIBILITY",
1217 "CJKCOMPATIBILITY");
1218
1219 /**
1220 * Constant for the "CJK Unified Ideographs" Unicode character block.
1221 * @since 1.2
1222 */
1223 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1224 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1225 "CJK UNIFIED IDEOGRAPHS",
1226 "CJKUNIFIEDIDEOGRAPHS");
1227
1228 /**
1229 * Constant for the "Hangul Syllables" Unicode character block.
1230 * @since 1.2
1231 */
1232 public static final UnicodeBlock HANGUL_SYLLABLES =
1233 new UnicodeBlock("HANGUL_SYLLABLES",
1234 "HANGUL SYLLABLES",
1235 "HANGULSYLLABLES");
1236
1237 /**
1238 * Constant for the "Private Use Area" Unicode character block.
1239 * @since 1.2
1240 */
1241 public static final UnicodeBlock PRIVATE_USE_AREA =
1242 new UnicodeBlock("PRIVATE_USE_AREA",
1243 "PRIVATE USE AREA",
1244 "PRIVATEUSEAREA");
1245
1246 /**
1247 * Constant for the "CJK Compatibility Ideographs" Unicode character
1248 * block.
1249 * @since 1.2
1250 */
1251 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1252 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1253 "CJK COMPATIBILITY IDEOGRAPHS",
1254 "CJKCOMPATIBILITYIDEOGRAPHS");
1255
1256 /**
1257 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1258 * @since 1.2
1259 */
1260 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1261 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1262 "ALPHABETIC PRESENTATION FORMS",
1263 "ALPHABETICPRESENTATIONFORMS");
1264
1265 /**
1266 * Constant for the "Arabic Presentation Forms-A" Unicode character
1267 * block.
1268 * @since 1.2
1269 */
1270 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1271 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1272 "ARABIC PRESENTATION FORMS-A",
1273 "ARABICPRESENTATIONFORMS-A");
1274
1275 /**
1276 * Constant for the "Combining Half Marks" Unicode character block.
1277 * @since 1.2
1278 */
1279 public static final UnicodeBlock COMBINING_HALF_MARKS =
1280 new UnicodeBlock("COMBINING_HALF_MARKS",
1281 "COMBINING HALF MARKS",
1282 "COMBININGHALFMARKS");
1283
1284 /**
1285 * Constant for the "CJK Compatibility Forms" Unicode character block.
1286 * @since 1.2
1287 */
1288 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1289 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1290 "CJK COMPATIBILITY FORMS",
1291 "CJKCOMPATIBILITYFORMS");
1292
1293 /**
1294 * Constant for the "Small Form Variants" Unicode character block.
1295 * @since 1.2
1296 */
1297 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1298 new UnicodeBlock("SMALL_FORM_VARIANTS",
1299 "SMALL FORM VARIANTS",
1300 "SMALLFORMVARIANTS");
1301
1302 /**
1303 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1304 * @since 1.2
1305 */
1306 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1307 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1308 "ARABIC PRESENTATION FORMS-B",
1309 "ARABICPRESENTATIONFORMS-B");
1310
1311 /**
1312 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1313 * block.
1314 * @since 1.2
1315 */
1316 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1317 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1318 "HALFWIDTH AND FULLWIDTH FORMS",
1319 "HALFWIDTHANDFULLWIDTHFORMS");
1320
1321 /**
1322 * Constant for the "Specials" Unicode character block.
1323 * @since 1.2
1324 */
1325 public static final UnicodeBlock SPECIALS =
1326 new UnicodeBlock("SPECIALS");
1327
1328 /**
1329 * @deprecated
1330 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1331 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1332 * These constants match the block definitions of the Unicode Standard.
1333 * The {@link #of(char)} and {@link #of(int)} methods return the
1334 * standard constants.
1335 */
1336 @Deprecated(since="1.5")
1337 public static final UnicodeBlock SURROGATES_AREA =
1338 new UnicodeBlock("SURROGATES_AREA");
1339
1340 /**
1341 * Constant for the "Syriac" Unicode character block.
1342 * @since 1.4
1343 */
1344 public static final UnicodeBlock SYRIAC =
1345 new UnicodeBlock("SYRIAC");
1346
1347 /**
1348 * Constant for the "Thaana" Unicode character block.
1349 * @since 1.4
1350 */
1351 public static final UnicodeBlock THAANA =
1352 new UnicodeBlock("THAANA");
1353
1354 /**
1355 * Constant for the "Sinhala" Unicode character block.
1356 * @since 1.4
1357 */
1358 public static final UnicodeBlock SINHALA =
1359 new UnicodeBlock("SINHALA");
1360
1361 /**
1362 * Constant for the "Myanmar" Unicode character block.
1363 * @since 1.4
1364 */
1365 public static final UnicodeBlock MYANMAR =
1366 new UnicodeBlock("MYANMAR");
1367
1368 /**
1369 * Constant for the "Ethiopic" Unicode character block.
1370 * @since 1.4
1371 */
1372 public static final UnicodeBlock ETHIOPIC =
1373 new UnicodeBlock("ETHIOPIC");
1374
1375 /**
1376 * Constant for the "Cherokee" Unicode character block.
1377 * @since 1.4
1378 */
1379 public static final UnicodeBlock CHEROKEE =
1380 new UnicodeBlock("CHEROKEE");
1381
1382 /**
1383 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1384 * @since 1.4
1385 */
1386 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1387 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1388 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1389 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1390
1391 /**
1392 * Constant for the "Ogham" Unicode character block.
1393 * @since 1.4
1394 */
1395 public static final UnicodeBlock OGHAM =
1396 new UnicodeBlock("OGHAM");
1397
1398 /**
1399 * Constant for the "Runic" Unicode character block.
1400 * @since 1.4
1401 */
1402 public static final UnicodeBlock RUNIC =
1403 new UnicodeBlock("RUNIC");
1404
1405 /**
1406 * Constant for the "Khmer" Unicode character block.
1407 * @since 1.4
1408 */
1409 public static final UnicodeBlock KHMER =
1410 new UnicodeBlock("KHMER");
1411
1412 /**
1413 * Constant for the "Mongolian" Unicode character block.
1414 * @since 1.4
1415 */
1416 public static final UnicodeBlock MONGOLIAN =
1417 new UnicodeBlock("MONGOLIAN");
1418
1419 /**
1420 * Constant for the "Braille Patterns" Unicode character block.
1421 * @since 1.4
1422 */
1423 public static final UnicodeBlock BRAILLE_PATTERNS =
1424 new UnicodeBlock("BRAILLE_PATTERNS",
1425 "BRAILLE PATTERNS",
1426 "BRAILLEPATTERNS");
1427
1428 /**
1429 * Constant for the "CJK Radicals Supplement" Unicode character block.
1430 * @since 1.4
1431 */
1432 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1433 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1434 "CJK RADICALS SUPPLEMENT",
1435 "CJKRADICALSSUPPLEMENT");
1436
1437 /**
1438 * Constant for the "Kangxi Radicals" Unicode character block.
1439 * @since 1.4
1440 */
1441 public static final UnicodeBlock KANGXI_RADICALS =
1442 new UnicodeBlock("KANGXI_RADICALS",
1443 "KANGXI RADICALS",
1444 "KANGXIRADICALS");
1445
1446 /**
1447 * Constant for the "Ideographic Description Characters" Unicode character block.
1448 * @since 1.4
1449 */
1450 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1451 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1452 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1453 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1454
1455 /**
1456 * Constant for the "Bopomofo Extended" Unicode character block.
1457 * @since 1.4
1458 */
1459 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1460 new UnicodeBlock("BOPOMOFO_EXTENDED",
1461 "BOPOMOFO EXTENDED",
1462 "BOPOMOFOEXTENDED");
1463
1464 /**
1465 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1466 * @since 1.4
1467 */
1468 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1469 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1470 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1471 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1472
1473 /**
1474 * Constant for the "Yi Syllables" Unicode character block.
1475 * @since 1.4
1476 */
1477 public static final UnicodeBlock YI_SYLLABLES =
1478 new UnicodeBlock("YI_SYLLABLES",
1479 "YI SYLLABLES",
1480 "YISYLLABLES");
1481
1482 /**
1483 * Constant for the "Yi Radicals" Unicode character block.
1484 * @since 1.4
1485 */
1486 public static final UnicodeBlock YI_RADICALS =
1487 new UnicodeBlock("YI_RADICALS",
1488 "YI RADICALS",
1489 "YIRADICALS");
1490
1491 /**
1492 * Constant for the "Cyrillic Supplement" Unicode character block.
1493 * This block was previously known as the "Cyrillic Supplementary" block.
1494 * @since 1.5
1495 */
1496 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1497 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1498 "CYRILLIC SUPPLEMENTARY",
1499 "CYRILLICSUPPLEMENTARY",
1500 "CYRILLIC SUPPLEMENT",
1501 "CYRILLICSUPPLEMENT");
1502
1503 /**
1504 * Constant for the "Tagalog" Unicode character block.
1505 * @since 1.5
1506 */
1507 public static final UnicodeBlock TAGALOG =
1508 new UnicodeBlock("TAGALOG");
1509
1510 /**
1511 * Constant for the "Hanunoo" Unicode character block.
1512 * @since 1.5
1513 */
1514 public static final UnicodeBlock HANUNOO =
1515 new UnicodeBlock("HANUNOO");
1516
1517 /**
1518 * Constant for the "Buhid" Unicode character block.
1519 * @since 1.5
1520 */
1521 public static final UnicodeBlock BUHID =
1522 new UnicodeBlock("BUHID");
1523
1524 /**
1525 * Constant for the "Tagbanwa" Unicode character block.
1526 * @since 1.5
1527 */
1528 public static final UnicodeBlock TAGBANWA =
1529 new UnicodeBlock("TAGBANWA");
1530
1531 /**
1532 * Constant for the "Limbu" Unicode character block.
1533 * @since 1.5
1534 */
1535 public static final UnicodeBlock LIMBU =
1536 new UnicodeBlock("LIMBU");
1537
1538 /**
1539 * Constant for the "Tai Le" Unicode character block.
1540 * @since 1.5
1541 */
1542 public static final UnicodeBlock TAI_LE =
1543 new UnicodeBlock("TAI_LE",
1544 "TAI LE",
1545 "TAILE");
1546
1547 /**
1548 * Constant for the "Khmer Symbols" Unicode character block.
1549 * @since 1.5
1550 */
1551 public static final UnicodeBlock KHMER_SYMBOLS =
1552 new UnicodeBlock("KHMER_SYMBOLS",
1553 "KHMER SYMBOLS",
1554 "KHMERSYMBOLS");
1555
1556 /**
1557 * Constant for the "Phonetic Extensions" Unicode character block.
1558 * @since 1.5
1559 */
1560 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1561 new UnicodeBlock("PHONETIC_EXTENSIONS",
1562 "PHONETIC EXTENSIONS",
1563 "PHONETICEXTENSIONS");
1564
1565 /**
1566 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1567 * @since 1.5
1568 */
1569 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1570 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1571 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1572 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1573
1574 /**
1575 * Constant for the "Supplemental Arrows-A" Unicode character block.
1576 * @since 1.5
1577 */
1578 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1579 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1580 "SUPPLEMENTAL ARROWS-A",
1581 "SUPPLEMENTALARROWS-A");
1582
1583 /**
1584 * Constant for the "Supplemental Arrows-B" Unicode character block.
1585 * @since 1.5
1586 */
1587 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1588 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1589 "SUPPLEMENTAL ARROWS-B",
1590 "SUPPLEMENTALARROWS-B");
1591
1592 /**
1593 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1594 * character block.
1595 * @since 1.5
1596 */
1597 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1598 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1599 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1600 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1601
1602 /**
1603 * Constant for the "Supplemental Mathematical Operators" Unicode
1604 * character block.
1605 * @since 1.5
1606 */
1607 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1608 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1609 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1610 "SUPPLEMENTALMATHEMATICALOPERATORS");
1611
1612 /**
1613 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1614 * block.
1615 * @since 1.5
1616 */
1617 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1618 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1619 "MISCELLANEOUS SYMBOLS AND ARROWS",
1620 "MISCELLANEOUSSYMBOLSANDARROWS");
1621
1622 /**
1623 * Constant for the "Katakana Phonetic Extensions" Unicode character
1624 * block.
1625 * @since 1.5
1626 */
1627 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1628 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1629 "KATAKANA PHONETIC EXTENSIONS",
1630 "KATAKANAPHONETICEXTENSIONS");
1631
1632 /**
1633 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1634 * @since 1.5
1635 */
1636 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1637 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1638 "YIJING HEXAGRAM SYMBOLS",
1639 "YIJINGHEXAGRAMSYMBOLS");
1640
1641 /**
1642 * Constant for the "Variation Selectors" Unicode character block.
1643 * @since 1.5
1644 */
1645 public static final UnicodeBlock VARIATION_SELECTORS =
1646 new UnicodeBlock("VARIATION_SELECTORS",
1647 "VARIATION SELECTORS",
1648 "VARIATIONSELECTORS");
1649
1650 /**
1651 * Constant for the "Linear B Syllabary" Unicode character block.
1652 * @since 1.5
1653 */
1654 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1655 new UnicodeBlock("LINEAR_B_SYLLABARY",
1656 "LINEAR B SYLLABARY",
1657 "LINEARBSYLLABARY");
1658
1659 /**
1660 * Constant for the "Linear B Ideograms" Unicode character block.
1661 * @since 1.5
1662 */
1663 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1664 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1665 "LINEAR B IDEOGRAMS",
1666 "LINEARBIDEOGRAMS");
1667
1668 /**
1669 * Constant for the "Aegean Numbers" Unicode character block.
1670 * @since 1.5
1671 */
1672 public static final UnicodeBlock AEGEAN_NUMBERS =
1673 new UnicodeBlock("AEGEAN_NUMBERS",
1674 "AEGEAN NUMBERS",
1675 "AEGEANNUMBERS");
1676
1677 /**
1678 * Constant for the "Old Italic" Unicode character block.
1679 * @since 1.5
1680 */
1681 public static final UnicodeBlock OLD_ITALIC =
1682 new UnicodeBlock("OLD_ITALIC",
1683 "OLD ITALIC",
1684 "OLDITALIC");
1685
1686 /**
1687 * Constant for the "Gothic" Unicode character block.
1688 * @since 1.5
1689 */
1690 public static final UnicodeBlock GOTHIC =
1691 new UnicodeBlock("GOTHIC");
1692
1693 /**
1694 * Constant for the "Ugaritic" Unicode character block.
1695 * @since 1.5
1696 */
1697 public static final UnicodeBlock UGARITIC =
1698 new UnicodeBlock("UGARITIC");
1699
1700 /**
1701 * Constant for the "Deseret" Unicode character block.
1702 * @since 1.5
1703 */
1704 public static final UnicodeBlock DESERET =
1705 new UnicodeBlock("DESERET");
1706
1707 /**
1708 * Constant for the "Shavian" Unicode character block.
1709 * @since 1.5
1710 */
1711 public static final UnicodeBlock SHAVIAN =
1712 new UnicodeBlock("SHAVIAN");
1713
1714 /**
1715 * Constant for the "Osmanya" Unicode character block.
1716 * @since 1.5
1717 */
1718 public static final UnicodeBlock OSMANYA =
1719 new UnicodeBlock("OSMANYA");
1720
1721 /**
1722 * Constant for the "Cypriot Syllabary" Unicode character block.
1723 * @since 1.5
1724 */
1725 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1726 new UnicodeBlock("CYPRIOT_SYLLABARY",
1727 "CYPRIOT SYLLABARY",
1728 "CYPRIOTSYLLABARY");
1729
1730 /**
1731 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1732 * @since 1.5
1733 */
1734 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1735 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1736 "BYZANTINE MUSICAL SYMBOLS",
1737 "BYZANTINEMUSICALSYMBOLS");
1738
1739 /**
1740 * Constant for the "Musical Symbols" Unicode character block.
1741 * @since 1.5
1742 */
1743 public static final UnicodeBlock MUSICAL_SYMBOLS =
1744 new UnicodeBlock("MUSICAL_SYMBOLS",
1745 "MUSICAL SYMBOLS",
1746 "MUSICALSYMBOLS");
1747
1748 /**
1749 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1750 * @since 1.5
1751 */
1752 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1753 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1754 "TAI XUAN JING SYMBOLS",
1755 "TAIXUANJINGSYMBOLS");
1756
1757 /**
1758 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1759 * character block.
1760 * @since 1.5
1761 */
1762 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1763 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1764 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1765 "MATHEMATICALALPHANUMERICSYMBOLS");
1766
1767 /**
1768 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1769 * character block.
1770 * @since 1.5
1771 */
1772 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1773 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1774 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1775 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1776
1777 /**
1778 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1779 * @since 1.5
1780 */
1781 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1782 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1783 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1784 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1785
1786 /**
1787 * Constant for the "Tags" Unicode character block.
1788 * @since 1.5
1789 */
1790 public static final UnicodeBlock TAGS =
1791 new UnicodeBlock("TAGS");
1792
1793 /**
1794 * Constant for the "Variation Selectors Supplement" Unicode character
1795 * block.
1796 * @since 1.5
1797 */
1798 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1799 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1800 "VARIATION SELECTORS SUPPLEMENT",
1801 "VARIATIONSELECTORSSUPPLEMENT");
1802
1803 /**
1804 * Constant for the "Supplementary Private Use Area-A" Unicode character
1805 * block.
1806 * @since 1.5
1807 */
1808 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1809 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1810 "SUPPLEMENTARY PRIVATE USE AREA-A",
1811 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1812
1813 /**
1814 * Constant for the "Supplementary Private Use Area-B" Unicode character
1815 * block.
1816 * @since 1.5
1817 */
1818 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1819 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1820 "SUPPLEMENTARY PRIVATE USE AREA-B",
1821 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1822
1823 /**
1824 * Constant for the "High Surrogates" Unicode character block.
1825 * This block represents codepoint values in the high surrogate
1826 * range: U+D800 through U+DB7F
1827 *
1828 * @since 1.5
1829 */
1830 public static final UnicodeBlock HIGH_SURROGATES =
1831 new UnicodeBlock("HIGH_SURROGATES",
1832 "HIGH SURROGATES",
1833 "HIGHSURROGATES");
1834
1835 /**
1836 * Constant for the "High Private Use Surrogates" Unicode character
1837 * block.
1838 * This block represents codepoint values in the private use high
1839 * surrogate range: U+DB80 through U+DBFF
1840 *
1841 * @since 1.5
1842 */
1843 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1844 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1845 "HIGH PRIVATE USE SURROGATES",
1846 "HIGHPRIVATEUSESURROGATES");
1847
1848 /**
1849 * Constant for the "Low Surrogates" Unicode character block.
1850 * This block represents codepoint values in the low surrogate
1851 * range: U+DC00 through U+DFFF
1852 *
1853 * @since 1.5
1854 */
1855 public static final UnicodeBlock LOW_SURROGATES =
1856 new UnicodeBlock("LOW_SURROGATES",
1857 "LOW SURROGATES",
1858 "LOWSURROGATES");
1859
1860 /**
1861 * Constant for the "Arabic Supplement" Unicode character block.
1862 * @since 1.7
1863 */
1864 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1865 new UnicodeBlock("ARABIC_SUPPLEMENT",
1866 "ARABIC SUPPLEMENT",
1867 "ARABICSUPPLEMENT");
1868
1869 /**
1870 * Constant for the "NKo" Unicode character block.
1871 * @since 1.7
1872 */
1873 public static final UnicodeBlock NKO =
1874 new UnicodeBlock("NKO");
1875
1876 /**
1877 * Constant for the "Samaritan" Unicode character block.
1878 * @since 1.7
1879 */
1880 public static final UnicodeBlock SAMARITAN =
1881 new UnicodeBlock("SAMARITAN");
1882
1883 /**
1884 * Constant for the "Mandaic" Unicode character block.
1885 * @since 1.7
1886 */
1887 public static final UnicodeBlock MANDAIC =
1888 new UnicodeBlock("MANDAIC");
1889
1890 /**
1891 * Constant for the "Ethiopic Supplement" Unicode character block.
1892 * @since 1.7
1893 */
1894 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1895 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1896 "ETHIOPIC SUPPLEMENT",
1897 "ETHIOPICSUPPLEMENT");
1898
1899 /**
1900 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1901 * Unicode character block.
1902 * @since 1.7
1903 */
1904 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1905 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1906 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1907 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1908
1909 /**
1910 * Constant for the "New Tai Lue" Unicode character block.
1911 * @since 1.7
1912 */
1913 public static final UnicodeBlock NEW_TAI_LUE =
1914 new UnicodeBlock("NEW_TAI_LUE",
1915 "NEW TAI LUE",
1916 "NEWTAILUE");
1917
1918 /**
1919 * Constant for the "Buginese" Unicode character block.
1920 * @since 1.7
1921 */
1922 public static final UnicodeBlock BUGINESE =
1923 new UnicodeBlock("BUGINESE");
1924
1925 /**
1926 * Constant for the "Tai Tham" Unicode character block.
1927 * @since 1.7
1928 */
1929 public static final UnicodeBlock TAI_THAM =
1930 new UnicodeBlock("TAI_THAM",
1931 "TAI THAM",
1932 "TAITHAM");
1933
1934 /**
1935 * Constant for the "Balinese" Unicode character block.
1936 * @since 1.7
1937 */
1938 public static final UnicodeBlock BALINESE =
1939 new UnicodeBlock("BALINESE");
1940
1941 /**
1942 * Constant for the "Sundanese" Unicode character block.
1943 * @since 1.7
1944 */
1945 public static final UnicodeBlock SUNDANESE =
1946 new UnicodeBlock("SUNDANESE");
1947
1948 /**
1949 * Constant for the "Batak" Unicode character block.
1950 * @since 1.7
1951 */
1952 public static final UnicodeBlock BATAK =
1953 new UnicodeBlock("BATAK");
1954
1955 /**
1956 * Constant for the "Lepcha" Unicode character block.
1957 * @since 1.7
1958 */
1959 public static final UnicodeBlock LEPCHA =
1960 new UnicodeBlock("LEPCHA");
1961
1962 /**
1963 * Constant for the "Ol Chiki" Unicode character block.
1964 * @since 1.7
1965 */
1966 public static final UnicodeBlock OL_CHIKI =
1967 new UnicodeBlock("OL_CHIKI",
1968 "OL CHIKI",
1969 "OLCHIKI");
1970
1971 /**
1972 * Constant for the "Vedic Extensions" Unicode character block.
1973 * @since 1.7
1974 */
1975 public static final UnicodeBlock VEDIC_EXTENSIONS =
1976 new UnicodeBlock("VEDIC_EXTENSIONS",
1977 "VEDIC EXTENSIONS",
1978 "VEDICEXTENSIONS");
1979
1980 /**
1981 * Constant for the "Phonetic Extensions Supplement" Unicode character
1982 * block.
1983 * @since 1.7
1984 */
1985 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1986 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1987 "PHONETIC EXTENSIONS SUPPLEMENT",
1988 "PHONETICEXTENSIONSSUPPLEMENT");
1989
1990 /**
1991 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1992 * character block.
1993 * @since 1.7
1994 */
1995 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1996 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1997 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1998 "COMBININGDIACRITICALMARKSSUPPLEMENT");
1999
2000 /**
2001 * Constant for the "Glagolitic" Unicode character block.
2002 * @since 1.7
2003 */
2004 public static final UnicodeBlock GLAGOLITIC =
2005 new UnicodeBlock("GLAGOLITIC");
2006
2007 /**
2008 * Constant for the "Latin Extended-C" Unicode character block.
2009 * @since 1.7
2010 */
2011 public static final UnicodeBlock LATIN_EXTENDED_C =
2012 new UnicodeBlock("LATIN_EXTENDED_C",
2013 "LATIN EXTENDED-C",
2014 "LATINEXTENDED-C");
2015
2016 /**
2017 * Constant for the "Coptic" Unicode character block.
2018 * @since 1.7
2019 */
2020 public static final UnicodeBlock COPTIC =
2021 new UnicodeBlock("COPTIC");
2022
2023 /**
2024 * Constant for the "Georgian Supplement" Unicode character block.
2025 * @since 1.7
2026 */
2027 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2028 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2029 "GEORGIAN SUPPLEMENT",
2030 "GEORGIANSUPPLEMENT");
2031
2032 /**
2033 * Constant for the "Tifinagh" Unicode character block.
2034 * @since 1.7
2035 */
2036 public static final UnicodeBlock TIFINAGH =
2037 new UnicodeBlock("TIFINAGH");
2038
2039 /**
2040 * Constant for the "Ethiopic Extended" Unicode character block.
2041 * @since 1.7
2042 */
2043 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2044 new UnicodeBlock("ETHIOPIC_EXTENDED",
2045 "ETHIOPIC EXTENDED",
2046 "ETHIOPICEXTENDED");
2047
2048 /**
2049 * Constant for the "Cyrillic Extended-A" Unicode character block.
2050 * @since 1.7
2051 */
2052 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2053 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2054 "CYRILLIC EXTENDED-A",
2055 "CYRILLICEXTENDED-A");
2056
2057 /**
2058 * Constant for the "Supplemental Punctuation" Unicode character block.
2059 * @since 1.7
2060 */
2061 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2062 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2063 "SUPPLEMENTAL PUNCTUATION",
2064 "SUPPLEMENTALPUNCTUATION");
2065
2066 /**
2067 * Constant for the "CJK Strokes" Unicode character block.
2068 * @since 1.7
2069 */
2070 public static final UnicodeBlock CJK_STROKES =
2071 new UnicodeBlock("CJK_STROKES",
2072 "CJK STROKES",
2073 "CJKSTROKES");
2074
2075 /**
2076 * Constant for the "Lisu" Unicode character block.
2077 * @since 1.7
2078 */
2079 public static final UnicodeBlock LISU =
2080 new UnicodeBlock("LISU");
2081
2082 /**
2083 * Constant for the "Vai" Unicode character block.
2084 * @since 1.7
2085 */
2086 public static final UnicodeBlock VAI =
2087 new UnicodeBlock("VAI");
2088
2089 /**
2090 * Constant for the "Cyrillic Extended-B" Unicode character block.
2091 * @since 1.7
2092 */
2093 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2094 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2095 "CYRILLIC EXTENDED-B",
2096 "CYRILLICEXTENDED-B");
2097
2098 /**
2099 * Constant for the "Bamum" Unicode character block.
2100 * @since 1.7
2101 */
2102 public static final UnicodeBlock BAMUM =
2103 new UnicodeBlock("BAMUM");
2104
2105 /**
2106 * Constant for the "Modifier Tone Letters" Unicode character block.
2107 * @since 1.7
2108 */
2109 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2110 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2111 "MODIFIER TONE LETTERS",
2112 "MODIFIERTONELETTERS");
2113
2114 /**
2115 * Constant for the "Latin Extended-D" Unicode character block.
2116 * @since 1.7
2117 */
2118 public static final UnicodeBlock LATIN_EXTENDED_D =
2119 new UnicodeBlock("LATIN_EXTENDED_D",
2120 "LATIN EXTENDED-D",
2121 "LATINEXTENDED-D");
2122
2123 /**
2124 * Constant for the "Syloti Nagri" Unicode character block.
2125 * @since 1.7
2126 */
2127 public static final UnicodeBlock SYLOTI_NAGRI =
2128 new UnicodeBlock("SYLOTI_NAGRI",
2129 "SYLOTI NAGRI",
2130 "SYLOTINAGRI");
2131
2132 /**
2133 * Constant for the "Common Indic Number Forms" Unicode character block.
2134 * @since 1.7
2135 */
2136 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2137 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2138 "COMMON INDIC NUMBER FORMS",
2139 "COMMONINDICNUMBERFORMS");
2140
2141 /**
2142 * Constant for the "Phags-pa" Unicode character block.
2143 * @since 1.7
2144 */
2145 public static final UnicodeBlock PHAGS_PA =
2146 new UnicodeBlock("PHAGS_PA",
2147 "PHAGS-PA");
2148
2149 /**
2150 * Constant for the "Saurashtra" Unicode character block.
2151 * @since 1.7
2152 */
2153 public static final UnicodeBlock SAURASHTRA =
2154 new UnicodeBlock("SAURASHTRA");
2155
2156 /**
2157 * Constant for the "Devanagari Extended" Unicode character block.
2158 * @since 1.7
2159 */
2160 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2161 new UnicodeBlock("DEVANAGARI_EXTENDED",
2162 "DEVANAGARI EXTENDED",
2163 "DEVANAGARIEXTENDED");
2164
2165 /**
2166 * Constant for the "Kayah Li" Unicode character block.
2167 * @since 1.7
2168 */
2169 public static final UnicodeBlock KAYAH_LI =
2170 new UnicodeBlock("KAYAH_LI",
2171 "KAYAH LI",
2172 "KAYAHLI");
2173
2174 /**
2175 * Constant for the "Rejang" Unicode character block.
2176 * @since 1.7
2177 */
2178 public static final UnicodeBlock REJANG =
2179 new UnicodeBlock("REJANG");
2180
2181 /**
2182 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2183 * @since 1.7
2184 */
2185 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2186 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2187 "HANGUL JAMO EXTENDED-A",
2188 "HANGULJAMOEXTENDED-A");
2189
2190 /**
2191 * Constant for the "Javanese" Unicode character block.
2192 * @since 1.7
2193 */
2194 public static final UnicodeBlock JAVANESE =
2195 new UnicodeBlock("JAVANESE");
2196
2197 /**
2198 * Constant for the "Cham" Unicode character block.
2199 * @since 1.7
2200 */
2201 public static final UnicodeBlock CHAM =
2202 new UnicodeBlock("CHAM");
2203
2204 /**
2205 * Constant for the "Myanmar Extended-A" Unicode character block.
2206 * @since 1.7
2207 */
2208 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2209 new UnicodeBlock("MYANMAR_EXTENDED_A",
2210 "MYANMAR EXTENDED-A",
2211 "MYANMAREXTENDED-A");
2212
2213 /**
2214 * Constant for the "Tai Viet" Unicode character block.
2215 * @since 1.7
2216 */
2217 public static final UnicodeBlock TAI_VIET =
2218 new UnicodeBlock("TAI_VIET",
2219 "TAI VIET",
2220 "TAIVIET");
2221
2222 /**
2223 * Constant for the "Ethiopic Extended-A" Unicode character block.
2224 * @since 1.7
2225 */
2226 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2227 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2228 "ETHIOPIC EXTENDED-A",
2229 "ETHIOPICEXTENDED-A");
2230
2231 /**
2232 * Constant for the "Meetei Mayek" Unicode character block.
2233 * @since 1.7
2234 */
2235 public static final UnicodeBlock MEETEI_MAYEK =
2236 new UnicodeBlock("MEETEI_MAYEK",
2237 "MEETEI MAYEK",
2238 "MEETEIMAYEK");
2239
2240 /**
2241 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2242 * @since 1.7
2243 */
2244 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2245 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2246 "HANGUL JAMO EXTENDED-B",
2247 "HANGULJAMOEXTENDED-B");
2248
2249 /**
2250 * Constant for the "Vertical Forms" Unicode character block.
2251 * @since 1.7
2252 */
2253 public static final UnicodeBlock VERTICAL_FORMS =
2254 new UnicodeBlock("VERTICAL_FORMS",
2255 "VERTICAL FORMS",
2256 "VERTICALFORMS");
2257
2258 /**
2259 * Constant for the "Ancient Greek Numbers" Unicode character block.
2260 * @since 1.7
2261 */
2262 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2263 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2264 "ANCIENT GREEK NUMBERS",
2265 "ANCIENTGREEKNUMBERS");
2266
2267 /**
2268 * Constant for the "Ancient Symbols" Unicode character block.
2269 * @since 1.7
2270 */
2271 public static final UnicodeBlock ANCIENT_SYMBOLS =
2272 new UnicodeBlock("ANCIENT_SYMBOLS",
2273 "ANCIENT SYMBOLS",
2274 "ANCIENTSYMBOLS");
2275
2276 /**
2277 * Constant for the "Phaistos Disc" Unicode character block.
2278 * @since 1.7
2279 */
2280 public static final UnicodeBlock PHAISTOS_DISC =
2281 new UnicodeBlock("PHAISTOS_DISC",
2282 "PHAISTOS DISC",
2283 "PHAISTOSDISC");
2284
2285 /**
2286 * Constant for the "Lycian" Unicode character block.
2287 * @since 1.7
2288 */
2289 public static final UnicodeBlock LYCIAN =
2290 new UnicodeBlock("LYCIAN");
2291
2292 /**
2293 * Constant for the "Carian" Unicode character block.
2294 * @since 1.7
2295 */
2296 public static final UnicodeBlock CARIAN =
2297 new UnicodeBlock("CARIAN");
2298
2299 /**
2300 * Constant for the "Old Persian" Unicode character block.
2301 * @since 1.7
2302 */
2303 public static final UnicodeBlock OLD_PERSIAN =
2304 new UnicodeBlock("OLD_PERSIAN",
2305 "OLD PERSIAN",
2306 "OLDPERSIAN");
2307
2308 /**
2309 * Constant for the "Imperial Aramaic" Unicode character block.
2310 * @since 1.7
2311 */
2312 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2313 new UnicodeBlock("IMPERIAL_ARAMAIC",
2314 "IMPERIAL ARAMAIC",
2315 "IMPERIALARAMAIC");
2316
2317 /**
2318 * Constant for the "Phoenician" Unicode character block.
2319 * @since 1.7
2320 */
2321 public static final UnicodeBlock PHOENICIAN =
2322 new UnicodeBlock("PHOENICIAN");
2323
2324 /**
2325 * Constant for the "Lydian" Unicode character block.
2326 * @since 1.7
2327 */
2328 public static final UnicodeBlock LYDIAN =
2329 new UnicodeBlock("LYDIAN");
2330
2331 /**
2332 * Constant for the "Kharoshthi" Unicode character block.
2333 * @since 1.7
2334 */
2335 public static final UnicodeBlock KHAROSHTHI =
2336 new UnicodeBlock("KHAROSHTHI");
2337
2338 /**
2339 * Constant for the "Old South Arabian" Unicode character block.
2340 * @since 1.7
2341 */
2342 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2343 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2344 "OLD SOUTH ARABIAN",
2345 "OLDSOUTHARABIAN");
2346
2347 /**
2348 * Constant for the "Avestan" Unicode character block.
2349 * @since 1.7
2350 */
2351 public static final UnicodeBlock AVESTAN =
2352 new UnicodeBlock("AVESTAN");
2353
2354 /**
2355 * Constant for the "Inscriptional Parthian" Unicode character block.
2356 * @since 1.7
2357 */
2358 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2359 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2360 "INSCRIPTIONAL PARTHIAN",
2361 "INSCRIPTIONALPARTHIAN");
2362
2363 /**
2364 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2365 * @since 1.7
2366 */
2367 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2368 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2369 "INSCRIPTIONAL PAHLAVI",
2370 "INSCRIPTIONALPAHLAVI");
2371
2372 /**
2373 * Constant for the "Old Turkic" Unicode character block.
2374 * @since 1.7
2375 */
2376 public static final UnicodeBlock OLD_TURKIC =
2377 new UnicodeBlock("OLD_TURKIC",
2378 "OLD TURKIC",
2379 "OLDTURKIC");
2380
2381 /**
2382 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2383 * @since 1.7
2384 */
2385 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2386 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2387 "RUMI NUMERAL SYMBOLS",
2388 "RUMINUMERALSYMBOLS");
2389
2390 /**
2391 * Constant for the "Brahmi" Unicode character block.
2392 * @since 1.7
2393 */
2394 public static final UnicodeBlock BRAHMI =
2395 new UnicodeBlock("BRAHMI");
2396
2397 /**
2398 * Constant for the "Kaithi" Unicode character block.
2399 * @since 1.7
2400 */
2401 public static final UnicodeBlock KAITHI =
2402 new UnicodeBlock("KAITHI");
2403
2404 /**
2405 * Constant for the "Cuneiform" Unicode character block.
2406 * @since 1.7
2407 */
2408 public static final UnicodeBlock CUNEIFORM =
2409 new UnicodeBlock("CUNEIFORM");
2410
2411 /**
2412 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2413 * character block.
2414 * @since 1.7
2415 */
2416 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2417 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2418 "CUNEIFORM NUMBERS AND PUNCTUATION",
2419 "CUNEIFORMNUMBERSANDPUNCTUATION");
2420
2421 /**
2422 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2423 * @since 1.7
2424 */
2425 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2426 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2427 "EGYPTIAN HIEROGLYPHS",
2428 "EGYPTIANHIEROGLYPHS");
2429
2430 /**
2431 * Constant for the "Bamum Supplement" Unicode character block.
2432 * @since 1.7
2433 */
2434 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2435 new UnicodeBlock("BAMUM_SUPPLEMENT",
2436 "BAMUM SUPPLEMENT",
2437 "BAMUMSUPPLEMENT");
2438
2439 /**
2440 * Constant for the "Kana Supplement" Unicode character block.
2441 * @since 1.7
2442 */
2443 public static final UnicodeBlock KANA_SUPPLEMENT =
2444 new UnicodeBlock("KANA_SUPPLEMENT",
2445 "KANA SUPPLEMENT",
2446 "KANASUPPLEMENT");
2447
2448 /**
2449 * Constant for the "Ancient Greek Musical Notation" Unicode character
2450 * block.
2451 * @since 1.7
2452 */
2453 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2454 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2455 "ANCIENT GREEK MUSICAL NOTATION",
2456 "ANCIENTGREEKMUSICALNOTATION");
2457
2458 /**
2459 * Constant for the "Counting Rod Numerals" Unicode character block.
2460 * @since 1.7
2461 */
2462 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2463 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2464 "COUNTING ROD NUMERALS",
2465 "COUNTINGRODNUMERALS");
2466
2467 /**
2468 * Constant for the "Mahjong Tiles" Unicode character block.
2469 * @since 1.7
2470 */
2471 public static final UnicodeBlock MAHJONG_TILES =
2472 new UnicodeBlock("MAHJONG_TILES",
2473 "MAHJONG TILES",
2474 "MAHJONGTILES");
2475
2476 /**
2477 * Constant for the "Domino Tiles" Unicode character block.
2478 * @since 1.7
2479 */
2480 public static final UnicodeBlock DOMINO_TILES =
2481 new UnicodeBlock("DOMINO_TILES",
2482 "DOMINO TILES",
2483 "DOMINOTILES");
2484
2485 /**
2486 * Constant for the "Playing Cards" Unicode character block.
2487 * @since 1.7
2488 */
2489 public static final UnicodeBlock PLAYING_CARDS =
2490 new UnicodeBlock("PLAYING_CARDS",
2491 "PLAYING CARDS",
2492 "PLAYINGCARDS");
2493
2494 /**
2495 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2496 * block.
2497 * @since 1.7
2498 */
2499 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2500 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2501 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2502 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2503
2504 /**
2505 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2506 * block.
2507 * @since 1.7
2508 */
2509 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2510 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2511 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2512 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2513
2514 /**
2515 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2516 * character block.
2517 * @since 1.7
2518 */
2519 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2520 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2521 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2522 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2523
2524 /**
2525 * Constant for the "Emoticons" Unicode character block.
2526 * @since 1.7
2527 */
2528 public static final UnicodeBlock EMOTICONS =
2529 new UnicodeBlock("EMOTICONS");
2530
2531 /**
2532 * Constant for the "Transport And Map Symbols" Unicode character block.
2533 * @since 1.7
2534 */
2535 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2536 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2537 "TRANSPORT AND MAP SYMBOLS",
2538 "TRANSPORTANDMAPSYMBOLS");
2539
2540 /**
2541 * Constant for the "Alchemical Symbols" Unicode character block.
2542 * @since 1.7
2543 */
2544 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2545 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2546 "ALCHEMICAL SYMBOLS",
2547 "ALCHEMICALSYMBOLS");
2548
2549 /**
2550 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2551 * character block.
2552 * @since 1.7
2553 */
2554 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2555 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2556 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2557 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2558
2559 /**
2560 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2561 * character block.
2562 * @since 1.7
2563 */
2564 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2565 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2566 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2567 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2568
2569 /**
2570 * Constant for the "Arabic Extended-A" Unicode character block.
2571 * @since 1.8
2572 */
2573 public static final UnicodeBlock ARABIC_EXTENDED_A =
2574 new UnicodeBlock("ARABIC_EXTENDED_A",
2575 "ARABIC EXTENDED-A",
2576 "ARABICEXTENDED-A");
2577
2578 /**
2579 * Constant for the "Sundanese Supplement" Unicode character block.
2580 * @since 1.8
2581 */
2582 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2583 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2584 "SUNDANESE SUPPLEMENT",
2585 "SUNDANESESUPPLEMENT");
2586
2587 /**
2588 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2589 * @since 1.8
2590 */
2591 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2592 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2593 "MEETEI MAYEK EXTENSIONS",
2594 "MEETEIMAYEKEXTENSIONS");
2595
2596 /**
2597 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2598 * @since 1.8
2599 */
2600 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2601 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2602 "MEROITIC HIEROGLYPHS",
2603 "MEROITICHIEROGLYPHS");
2604
2605 /**
2606 * Constant for the "Meroitic Cursive" Unicode character block.
2607 * @since 1.8
2608 */
2609 public static final UnicodeBlock MEROITIC_CURSIVE =
2610 new UnicodeBlock("MEROITIC_CURSIVE",
2611 "MEROITIC CURSIVE",
2612 "MEROITICCURSIVE");
2613
2614 /**
2615 * Constant for the "Sora Sompeng" Unicode character block.
2616 * @since 1.8
2617 */
2618 public static final UnicodeBlock SORA_SOMPENG =
2619 new UnicodeBlock("SORA_SOMPENG",
2620 "SORA SOMPENG",
2621 "SORASOMPENG");
2622
2623 /**
2624 * Constant for the "Chakma" Unicode character block.
2625 * @since 1.8
2626 */
2627 public static final UnicodeBlock CHAKMA =
2628 new UnicodeBlock("CHAKMA");
2629
2630 /**
2631 * Constant for the "Sharada" Unicode character block.
2632 * @since 1.8
2633 */
2634 public static final UnicodeBlock SHARADA =
2635 new UnicodeBlock("SHARADA");
2636
2637 /**
2638 * Constant for the "Takri" Unicode character block.
2639 * @since 1.8
2640 */
2641 public static final UnicodeBlock TAKRI =
2642 new UnicodeBlock("TAKRI");
2643
2644 /**
2645 * Constant for the "Miao" Unicode character block.
2646 * @since 1.8
2647 */
2648 public static final UnicodeBlock MIAO =
2649 new UnicodeBlock("MIAO");
2650
2651 /**
2652 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2653 * character block.
2654 * @since 1.8
2655 */
2656 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2657 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2658 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2659 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2660
2661 /**
2662 * Constant for the "Combining Diacritical Marks Extended" Unicode
2663 * character block.
2664 * @since 9
2665 */
2666 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2667 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2668 "COMBINING DIACRITICAL MARKS EXTENDED",
2669 "COMBININGDIACRITICALMARKSEXTENDED");
2670
2671 /**
2672 * Constant for the "Myanmar Extended-B" Unicode character block.
2673 * @since 9
2674 */
2675 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2676 new UnicodeBlock("MYANMAR_EXTENDED_B",
2677 "MYANMAR EXTENDED-B",
2678 "MYANMAREXTENDED-B");
2679
2680 /**
2681 * Constant for the "Latin Extended-E" Unicode character block.
2682 * @since 9
2683 */
2684 public static final UnicodeBlock LATIN_EXTENDED_E =
2685 new UnicodeBlock("LATIN_EXTENDED_E",
2686 "LATIN EXTENDED-E",
2687 "LATINEXTENDED-E");
2688
2689 /**
2690 * Constant for the "Coptic Epact Numbers" Unicode character block.
2691 * @since 9
2692 */
2693 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2694 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2695 "COPTIC EPACT NUMBERS",
2696 "COPTICEPACTNUMBERS");
2697
2698 /**
2699 * Constant for the "Old Permic" Unicode character block.
2700 * @since 9
2701 */
2702 public static final UnicodeBlock OLD_PERMIC =
2703 new UnicodeBlock("OLD_PERMIC",
2704 "OLD PERMIC",
2705 "OLDPERMIC");
2706
2707 /**
2708 * Constant for the "Elbasan" Unicode character block.
2709 * @since 9
2710 */
2711 public static final UnicodeBlock ELBASAN =
2712 new UnicodeBlock("ELBASAN");
2713
2714 /**
2715 * Constant for the "Caucasian Albanian" Unicode character block.
2716 * @since 9
2717 */
2718 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2719 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2720 "CAUCASIAN ALBANIAN",
2721 "CAUCASIANALBANIAN");
2722
2723 /**
2724 * Constant for the "Linear A" Unicode character block.
2725 * @since 9
2726 */
2727 public static final UnicodeBlock LINEAR_A =
2728 new UnicodeBlock("LINEAR_A",
2729 "LINEAR A",
2730 "LINEARA");
2731
2732 /**
2733 * Constant for the "Palmyrene" Unicode character block.
2734 * @since 9
2735 */
2736 public static final UnicodeBlock PALMYRENE =
2737 new UnicodeBlock("PALMYRENE");
2738
2739 /**
2740 * Constant for the "Nabataean" Unicode character block.
2741 * @since 9
2742 */
2743 public static final UnicodeBlock NABATAEAN =
2744 new UnicodeBlock("NABATAEAN");
2745
2746 /**
2747 * Constant for the "Old North Arabian" Unicode character block.
2748 * @since 9
2749 */
2750 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2751 new UnicodeBlock("OLD_NORTH_ARABIAN",
2752 "OLD NORTH ARABIAN",
2753 "OLDNORTHARABIAN");
2754
2755 /**
2756 * Constant for the "Manichaean" Unicode character block.
2757 * @since 9
2758 */
2759 public static final UnicodeBlock MANICHAEAN =
2760 new UnicodeBlock("MANICHAEAN");
2761
2762 /**
2763 * Constant for the "Psalter Pahlavi" Unicode character block.
2764 * @since 9
2765 */
2766 public static final UnicodeBlock PSALTER_PAHLAVI =
2767 new UnicodeBlock("PSALTER_PAHLAVI",
2768 "PSALTER PAHLAVI",
2769 "PSALTERPAHLAVI");
2770
2771 /**
2772 * Constant for the "Mahajani" Unicode character block.
2773 * @since 9
2774 */
2775 public static final UnicodeBlock MAHAJANI =
2776 new UnicodeBlock("MAHAJANI");
2777
2778 /**
2779 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2780 * @since 9
2781 */
2782 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2783 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2784 "SINHALA ARCHAIC NUMBERS",
2785 "SINHALAARCHAICNUMBERS");
2786
2787 /**
2788 * Constant for the "Khojki" Unicode character block.
2789 * @since 9
2790 */
2791 public static final UnicodeBlock KHOJKI =
2792 new UnicodeBlock("KHOJKI");
2793
2794 /**
2795 * Constant for the "Khudawadi" Unicode character block.
2796 * @since 9
2797 */
2798 public static final UnicodeBlock KHUDAWADI =
2799 new UnicodeBlock("KHUDAWADI");
2800
2801 /**
2802 * Constant for the "Grantha" Unicode character block.
2803 * @since 9
2804 */
2805 public static final UnicodeBlock GRANTHA =
2806 new UnicodeBlock("GRANTHA");
2807
2808 /**
2809 * Constant for the "Tirhuta" Unicode character block.
2810 * @since 9
2811 */
2812 public static final UnicodeBlock TIRHUTA =
2813 new UnicodeBlock("TIRHUTA");
2814
2815 /**
2816 * Constant for the "Siddham" Unicode character block.
2817 * @since 9
2818 */
2819 public static final UnicodeBlock SIDDHAM =
2820 new UnicodeBlock("SIDDHAM");
2821
2822 /**
2823 * Constant for the "Modi" Unicode character block.
2824 * @since 9
2825 */
2826 public static final UnicodeBlock MODI =
2827 new UnicodeBlock("MODI");
2828
2829 /**
2830 * Constant for the "Warang Citi" Unicode character block.
2831 * @since 9
2832 */
2833 public static final UnicodeBlock WARANG_CITI =
2834 new UnicodeBlock("WARANG_CITI",
2835 "WARANG CITI",
2836 "WARANGCITI");
2837
2838 /**
2839 * Constant for the "Pau Cin Hau" Unicode character block.
2840 * @since 9
2841 */
2842 public static final UnicodeBlock PAU_CIN_HAU =
2843 new UnicodeBlock("PAU_CIN_HAU",
2844 "PAU CIN HAU",
2845 "PAUCINHAU");
2846
2847 /**
2848 * Constant for the "Mro" Unicode character block.
2849 * @since 9
2850 */
2851 public static final UnicodeBlock MRO =
2852 new UnicodeBlock("MRO");
2853
2854 /**
2855 * Constant for the "Bassa Vah" Unicode character block.
2856 * @since 9
2857 */
2858 public static final UnicodeBlock BASSA_VAH =
2859 new UnicodeBlock("BASSA_VAH",
2860 "BASSA VAH",
2861 "BASSAVAH");
2862
2863 /**
2864 * Constant for the "Pahawh Hmong" Unicode character block.
2865 * @since 9
2866 */
2867 public static final UnicodeBlock PAHAWH_HMONG =
2868 new UnicodeBlock("PAHAWH_HMONG",
2869 "PAHAWH HMONG",
2870 "PAHAWHHMONG");
2871
2872 /**
2873 * Constant for the "Duployan" Unicode character block.
2874 * @since 9
2875 */
2876 public static final UnicodeBlock DUPLOYAN =
2877 new UnicodeBlock("DUPLOYAN");
2878
2879 /**
2880 * Constant for the "Shorthand Format Controls" Unicode character block.
2881 * @since 9
2882 */
2883 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2884 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2885 "SHORTHAND FORMAT CONTROLS",
2886 "SHORTHANDFORMATCONTROLS");
2887
2888 /**
2889 * Constant for the "Mende Kikakui" Unicode character block.
2890 * @since 9
2891 */
2892 public static final UnicodeBlock MENDE_KIKAKUI =
2893 new UnicodeBlock("MENDE_KIKAKUI",
2894 "MENDE KIKAKUI",
2895 "MENDEKIKAKUI");
2896
2897 /**
2898 * Constant for the "Ornamental Dingbats" Unicode character block.
2899 * @since 9
2900 */
2901 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2902 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2903 "ORNAMENTAL DINGBATS",
2904 "ORNAMENTALDINGBATS");
2905
2906 /**
2907 * Constant for the "Geometric Shapes Extended" Unicode character block.
2908 * @since 9
2909 */
2910 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2911 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2912 "GEOMETRIC SHAPES EXTENDED",
2913 "GEOMETRICSHAPESEXTENDED");
2914
2915 /**
2916 * Constant for the "Supplemental Arrows-C" Unicode character block.
2917 * @since 9
2918 */
2919 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2920 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2921 "SUPPLEMENTAL ARROWS-C",
2922 "SUPPLEMENTALARROWS-C");
2923
2924 /**
2925 * Constant for the "Cherokee Supplement" Unicode character block.
2926 * @since 9
2927 */
2928 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2929 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2930 "CHEROKEE SUPPLEMENT",
2931 "CHEROKEESUPPLEMENT");
2932
2933 /**
2934 * Constant for the "Hatran" Unicode character block.
2935 * @since 9
2936 */
2937 public static final UnicodeBlock HATRAN =
2938 new UnicodeBlock("HATRAN");
2939
2940 /**
2941 * Constant for the "Old Hungarian" Unicode character block.
2942 * @since 9
2943 */
2944 public static final UnicodeBlock OLD_HUNGARIAN =
2945 new UnicodeBlock("OLD_HUNGARIAN",
2946 "OLD HUNGARIAN",
2947 "OLDHUNGARIAN");
2948
2949 /**
2950 * Constant for the "Multani" Unicode character block.
2951 * @since 9
2952 */
2953 public static final UnicodeBlock MULTANI =
2954 new UnicodeBlock("MULTANI");
2955
2956 /**
2957 * Constant for the "Ahom" Unicode character block.
2958 * @since 9
2959 */
2960 public static final UnicodeBlock AHOM =
2961 new UnicodeBlock("AHOM");
2962
2963 /**
2964 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2965 * @since 9
2966 */
2967 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2968 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2969 "EARLY DYNASTIC CUNEIFORM",
2970 "EARLYDYNASTICCUNEIFORM");
2971
2972 /**
2973 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2974 * @since 9
2975 */
2976 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2977 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2978 "ANATOLIAN HIEROGLYPHS",
2979 "ANATOLIANHIEROGLYPHS");
2980
2981 /**
2982 * Constant for the "Sutton SignWriting" Unicode character block.
2983 * @since 9
2984 */
2985 public static final UnicodeBlock SUTTON_SIGNWRITING =
2986 new UnicodeBlock("SUTTON_SIGNWRITING",
2987 "SUTTON SIGNWRITING",
2988 "SUTTONSIGNWRITING");
2989
2990 /**
2991 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2992 * character block.
2993 * @since 9
2994 */
2995 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2996 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2997 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2998 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2999
3000 /**
3001 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3002 * character block.
3003 * @since 9
3004 */
3005 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3006 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3007 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3008 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3009
3010 /**
3011 * Constant for the "Syriac Supplement" Unicode
3012 * character block.
3013 * @since 11
3014 */
3015 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3016 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3017 "SYRIAC SUPPLEMENT",
3018 "SYRIACSUPPLEMENT");
3019
3020 /**
3021 * Constant for the "Cyrillic Extended-C" Unicode
3022 * character block.
3023 * @since 11
3024 */
3025 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3026 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3027 "CYRILLIC EXTENDED-C",
3028 "CYRILLICEXTENDED-C");
3029
3030 /**
3031 * Constant for the "Osage" Unicode
3032 * character block.
3033 * @since 11
3034 */
3035 public static final UnicodeBlock OSAGE =
3036 new UnicodeBlock("OSAGE");
3037
3038 /**
3039 * Constant for the "Newa" Unicode
3040 * character block.
3041 * @since 11
3042 */
3043 public static final UnicodeBlock NEWA =
3044 new UnicodeBlock("NEWA");
3045
3046 /**
3047 * Constant for the "Mongolian Supplement" Unicode
3048 * character block.
3049 * @since 11
3050 */
3051 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3052 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3053 "MONGOLIAN SUPPLEMENT",
3054 "MONGOLIANSUPPLEMENT");
3055
3056 /**
3057 * Constant for the "Marchen" Unicode
3058 * character block.
3059 * @since 11
3060 */
3061 public static final UnicodeBlock MARCHEN =
3062 new UnicodeBlock("MARCHEN");
3063
3064 /**
3065 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3066 * character block.
3067 * @since 11
3068 */
3069 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3070 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3071 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3072 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3073
3074 /**
3075 * Constant for the "Tangut" Unicode
3076 * character block.
3077 * @since 11
3078 */
3079 public static final UnicodeBlock TANGUT =
3080 new UnicodeBlock("TANGUT");
3081
3082 /**
3083 * Constant for the "Tangut Components" Unicode
3084 * character block.
3085 * @since 11
3086 */
3087 public static final UnicodeBlock TANGUT_COMPONENTS =
3088 new UnicodeBlock("TANGUT_COMPONENTS",
3089 "TANGUT COMPONENTS",
3090 "TANGUTCOMPONENTS");
3091
3092 /**
3093 * Constant for the "Kana Extended-A" Unicode
3094 * character block.
3095 * @since 11
3096 */
3097 public static final UnicodeBlock KANA_EXTENDED_A =
3098 new UnicodeBlock("KANA_EXTENDED_A",
3099 "KANA EXTENDED-A",
3100 "KANAEXTENDED-A");
3101 /**
3102 * Constant for the "Glagolitic Supplement" Unicode
3103 * character block.
3104 * @since 11
3105 */
3106 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3107 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3108 "GLAGOLITIC SUPPLEMENT",
3109 "GLAGOLITICSUPPLEMENT");
3110 /**
3111 * Constant for the "Adlam" Unicode
3112 * character block.
3113 * @since 11
3114 */
3115 public static final UnicodeBlock ADLAM =
3116 new UnicodeBlock("ADLAM");
3117
3118 /**
3119 * Constant for the "Masaram Gondi" Unicode
3120 * character block.
3121 * @since 11
3122 */
3123 public static final UnicodeBlock MASARAM_GONDI =
3124 new UnicodeBlock("MASARAM_GONDI",
3125 "MASARAM GONDI",
3126 "MASARAMGONDI");
3127
3128 /**
3129 * Constant for the "Zanabazar Square" Unicode
3130 * character block.
3131 * @since 11
3132 */
3133 public static final UnicodeBlock ZANABAZAR_SQUARE =
3134 new UnicodeBlock("ZANABAZAR_SQUARE",
3135 "ZANABAZAR SQUARE",
3136 "ZANABAZARSQUARE");
3137
3138 /**
3139 * Constant for the "Nushu" Unicode
3140 * character block.
3141 * @since 11
3142 */
3143 public static final UnicodeBlock NUSHU =
3144 new UnicodeBlock("NUSHU");
3145
3146 /**
3147 * Constant for the "Soyombo" Unicode
3148 * character block.
3149 * @since 11
3150 */
3151 public static final UnicodeBlock SOYOMBO =
3152 new UnicodeBlock("SOYOMBO");
3153
3154 /**
3155 * Constant for the "Bhaiksuki" Unicode
3156 * character block.
3157 * @since 11
3158 */
3159 public static final UnicodeBlock BHAIKSUKI =
3160 new UnicodeBlock("BHAIKSUKI");
3161
3162 /**
3163 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3164 * character block.
3165 * @since 11
3166 */
3167 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3168 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3169 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3170 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3171 /**
3172 * Constant for the "Georgian Extended" Unicode
3173 * character block.
3174 * @since 12
3175 */
3176 public static final UnicodeBlock GEORGIAN_EXTENDED =
3177 new UnicodeBlock("GEORGIAN_EXTENDED",
3178 "GEORGIAN EXTENDED",
3179 "GEORGIANEXTENDED");
3180
3181 /**
3182 * Constant for the "Hanifi Rohingya" Unicode
3183 * character block.
3184 * @since 12
3185 */
3186 public static final UnicodeBlock HANIFI_ROHINGYA =
3187 new UnicodeBlock("HANIFI_ROHINGYA",
3188 "HANIFI ROHINGYA",
3189 "HANIFIROHINGYA");
3190
3191 /**
3192 * Constant for the "Old Sogdian" Unicode
3193 * character block.
3194 * @since 12
3195 */
3196 public static final UnicodeBlock OLD_SOGDIAN =
3197 new UnicodeBlock("OLD_SOGDIAN",
3198 "OLD SOGDIAN",
3199 "OLDSOGDIAN");
3200
3201 /**
3202 * Constant for the "Sogdian" Unicode
3203 * character block.
3204 * @since 12
3205 */
3206 public static final UnicodeBlock SOGDIAN =
3207 new UnicodeBlock("SOGDIAN");
3208
3209 /**
3210 * Constant for the "Dogra" Unicode
3211 * character block.
3212 * @since 12
3213 */
3214 public static final UnicodeBlock DOGRA =
3215 new UnicodeBlock("DOGRA");
3216
3217 /**
3218 * Constant for the "Gunjala Gondi" Unicode
3219 * character block.
3220 * @since 12
3221 */
3222 public static final UnicodeBlock GUNJALA_GONDI =
3223 new UnicodeBlock("GUNJALA_GONDI",
3224 "GUNJALA GONDI",
3225 "GUNJALAGONDI");
3226
3227 /**
3228 * Constant for the "Makasar" Unicode
3229 * character block.
3230 * @since 12
3231 */
3232 public static final UnicodeBlock MAKASAR =
3233 new UnicodeBlock("MAKASAR");
3234
3235 /**
3236 * Constant for the "Medefaidrin" Unicode
3237 * character block.
3238 * @since 12
3239 */
3240 public static final UnicodeBlock MEDEFAIDRIN =
3241 new UnicodeBlock("MEDEFAIDRIN");
3242
3243 /**
3244 * Constant for the "Mayan Numerals" Unicode
3245 * character block.
3246 * @since 12
3247 */
3248 public static final UnicodeBlock MAYAN_NUMERALS =
3249 new UnicodeBlock("MAYAN_NUMERALS",
3250 "MAYAN NUMERALS",
3251 "MAYANNUMERALS");
3252
3253 /**
3254 * Constant for the "Indic Siyaq Numbers" Unicode
3255 * character block.
3256 * @since 12
3257 */
3258 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3259 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3260 "INDIC SIYAQ NUMBERS",
3261 "INDICSIYAQNUMBERS");
3262
3263 /**
3264 * Constant for the "Chess Symbols" Unicode
3265 * character block.
3266 * @since 12
3267 */
3268 public static final UnicodeBlock CHESS_SYMBOLS =
3269 new UnicodeBlock("CHESS_SYMBOLS",
3270 "CHESS SYMBOLS",
3271 "CHESSSYMBOLS");
3272
3273 /**
3274 * Constant for the "Elymaic" Unicode
3275 * character block.
3276 * @since 13
3277 */
3278 public static final UnicodeBlock ELYMAIC =
3279 new UnicodeBlock("ELYMAIC");
3280
3281 /**
3282 * Constant for the "Nandinagari" Unicode
3283 * character block.
3284 * @since 13
3285 */
3286 public static final UnicodeBlock NANDINAGARI =
3287 new UnicodeBlock("NANDINAGARI");
3288
3289 /**
3290 * Constant for the "Tamil Supplement" Unicode
3291 * character block.
3292 * @since 13
3293 */
3294 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3295 new UnicodeBlock("TAMIL_SUPPLEMENT",
3296 "TAMIL SUPPLEMENT",
3297 "TAMILSUPPLEMENT");
3298
3299 /**
3300 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3301 * character block.
3302 * @since 13
3303 */
3304 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3305 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3306 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3307 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3308
3309 /**
3310 * Constant for the "Small Kana Extension" Unicode
3311 * character block.
3312 * @since 13
3313 */
3314 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3315 new UnicodeBlock("SMALL_KANA_EXTENSION",
3316 "SMALL KANA EXTENSION",
3317 "SMALLKANAEXTENSION");
3318
3319 /**
3320 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3321 * character block.
3322 * @since 13
3323 */
3324 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3325 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3326 "NYIAKENG PUACHUE HMONG",
3327 "NYIAKENGPUACHUEHMONG");
3328
3329 /**
3330 * Constant for the "Wancho" Unicode
3331 * character block.
3332 * @since 13
3333 */
3334 public static final UnicodeBlock WANCHO =
3335 new UnicodeBlock("WANCHO");
3336
3337 /**
3338 * Constant for the "Ottoman Siyaq Numbers" Unicode
3339 * character block.
3340 * @since 13
3341 */
3342 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3343 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3344 "OTTOMAN SIYAQ NUMBERS",
3345 "OTTOMANSIYAQNUMBERS");
3346
3347 /**
3348 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3349 * character block.
3350 * @since 13
3351 */
3352 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3353 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3354 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3355 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3356
3357 /**
3358 * Constant for the "Yezidi" Unicode
3359 * character block.
3360 * @since 15
3361 */
3362 public static final UnicodeBlock YEZIDI =
3363 new UnicodeBlock("YEZIDI");
3364
3365 /**
3366 * Constant for the "Chorasmian" Unicode
3367 * character block.
3368 * @since 15
3369 */
3370 public static final UnicodeBlock CHORASMIAN =
3371 new UnicodeBlock("CHORASMIAN");
3372
3373 /**
3374 * Constant for the "Dives Akuru" Unicode
3375 * character block.
3376 * @since 15
3377 */
3378 public static final UnicodeBlock DIVES_AKURU =
3379 new UnicodeBlock("DIVES_AKURU",
3380 "DIVES AKURU",
3381 "DIVESAKURU");
3382
3383 /**
3384 * Constant for the "Lisu Supplement" Unicode
3385 * character block.
3386 * @since 15
3387 */
3388 public static final UnicodeBlock LISU_SUPPLEMENT =
3389 new UnicodeBlock("LISU_SUPPLEMENT",
3390 "LISU SUPPLEMENT",
3391 "LISUSUPPLEMENT");
3392
3393 /**
3394 * Constant for the "Khitan Small Script" Unicode
3395 * character block.
3396 * @since 15
3397 */
3398 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3399 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3400 "KHITAN SMALL SCRIPT",
3401 "KHITANSMALLSCRIPT");
3402
3403 /**
3404 * Constant for the "Tangut Supplement" Unicode
3405 * character block.
3406 * @since 15
3407 */
3408 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3409 new UnicodeBlock("TANGUT_SUPPLEMENT",
3410 "TANGUT SUPPLEMENT",
3411 "TANGUTSUPPLEMENT");
3412
3413 /**
3414 * Constant for the "Symbols for Legacy Computing" Unicode
3415 * character block.
3416 * @since 15
3417 */
3418 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3419 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3420 "SYMBOLS FOR LEGACY COMPUTING",
3421 "SYMBOLSFORLEGACYCOMPUTING");
3422
3423 /**
3424 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3425 * character block.
3426 * @since 15
3427 */
3428 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3429 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3430 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3431 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3432
3433 /**
3434 * Constant for the "Arabic Extended-B" Unicode
3435 * character block.
3436 * @since 19
3437 */
3438 public static final UnicodeBlock ARABIC_EXTENDED_B =
3439 new UnicodeBlock("ARABIC_EXTENDED_B",
3440 "ARABIC EXTENDED-B",
3441 "ARABICEXTENDED-B");
3442
3443 /**
3444 * Constant for the "Vithkuqi" Unicode
3445 * character block.
3446 * @since 19
3447 */
3448 public static final UnicodeBlock VITHKUQI =
3449 new UnicodeBlock("VITHKUQI");
3450
3451 /**
3452 * Constant for the "Latin Extended-F" Unicode
3453 * character block.
3454 * @since 19
3455 */
3456 public static final UnicodeBlock LATIN_EXTENDED_F =
3457 new UnicodeBlock("LATIN_EXTENDED_F",
3458 "LATIN EXTENDED-F",
3459 "LATINEXTENDED-F");
3460
3461 /**
3462 * Constant for the "Old Uyghur" Unicode
3463 * character block.
3464 * @since 19
3465 */
3466 public static final UnicodeBlock OLD_UYGHUR =
3467 new UnicodeBlock("OLD_UYGHUR",
3468 "OLD UYGHUR",
3469 "OLDUYGHUR");
3470
3471 /**
3472 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3473 * character block.
3474 * @since 19
3475 */
3476 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3477 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3478 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3479 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3480
3481 /**
3482 * Constant for the "Cypro-Minoan" Unicode
3483 * character block.
3484 * @since 19
3485 */
3486 public static final UnicodeBlock CYPRO_MINOAN =
3487 new UnicodeBlock("CYPRO_MINOAN",
3488 "CYPRO-MINOAN",
3489 "CYPRO-MINOAN");
3490
3491 /**
3492 * Constant for the "Tangsa" Unicode
3493 * character block.
3494 * @since 19
3495 */
3496 public static final UnicodeBlock TANGSA =
3497 new UnicodeBlock("TANGSA");
3498
3499 /**
3500 * Constant for the "Kana Extended-B" Unicode
3501 * character block.
3502 * @since 19
3503 */
3504 public static final UnicodeBlock KANA_EXTENDED_B =
3505 new UnicodeBlock("KANA_EXTENDED_B",
3506 "KANA EXTENDED-B",
3507 "KANAEXTENDED-B");
3508
3509 /**
3510 * Constant for the "Znamenny Musical Notation" Unicode
3511 * character block.
3512 * @since 19
3513 */
3514 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3515 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3516 "ZNAMENNY MUSICAL NOTATION",
3517 "ZNAMENNYMUSICALNOTATION");
3518
3519 /**
3520 * Constant for the "Latin Extended-G" Unicode
3521 * character block.
3522 * @since 19
3523 */
3524 public static final UnicodeBlock LATIN_EXTENDED_G =
3525 new UnicodeBlock("LATIN_EXTENDED_G",
3526 "LATIN EXTENDED-G",
3527 "LATINEXTENDED-G");
3528
3529 /**
3530 * Constant for the "Toto" Unicode
3531 * character block.
3532 * @since 19
3533 */
3534 public static final UnicodeBlock TOTO =
3535 new UnicodeBlock("TOTO");
3536
3537 /**
3538 * Constant for the "Ethiopic Extended-B" Unicode
3539 * character block.
3540 * @since 19
3541 */
3542 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3543 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3544 "ETHIOPIC EXTENDED-B",
3545 "ETHIOPICEXTENDED-B");
3546
3547 /**
3548 * Constant for the "Arabic Extended-C" Unicode
3549 * character block.
3550 * @since 20
3551 */
3552 public static final UnicodeBlock ARABIC_EXTENDED_C =
3553 new UnicodeBlock("ARABIC_EXTENDED_C",
3554 "ARABIC EXTENDED-C",
3555 "ARABICEXTENDED-C");
3556
3557 /**
3558 * Constant for the "Devanagari Extended-A" Unicode
3559 * character block.
3560 * @since 20
3561 */
3562 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3563 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3564 "DEVANAGARI EXTENDED-A",
3565 "DEVANAGARIEXTENDED-A");
3566
3567 /**
3568 * Constant for the "Kawi" Unicode
3569 * character block.
3570 * @since 20
3571 */
3572 public static final UnicodeBlock KAWI =
3573 new UnicodeBlock("KAWI");
3574
3575 /**
3576 * Constant for the "Kaktovik Numerals" Unicode
3577 * character block.
3578 * @since 20
3579 */
3580 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3581 new UnicodeBlock("KAKTOVIK_NUMERALS",
3582 "KAKTOVIK NUMERALS",
3583 "KAKTOVIKNUMERALS");
3584
3585 /**
3586 * Constant for the "Cyrillic Extended-D" Unicode
3587 * character block.
3588 * @since 20
3589 */
3590 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3591 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3592 "CYRILLIC EXTENDED-D",
3593 "CYRILLICEXTENDED-D");
3594
3595 /**
3596 * Constant for the "Nag Mundari" Unicode
3597 * character block.
3598 * @since 20
3599 */
3600 public static final UnicodeBlock NAG_MUNDARI =
3601 new UnicodeBlock("NAG_MUNDARI",
3602 "NAG MUNDARI",
3603 "NAGMUNDARI");
3604
3605 /**
3606 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3607 * character block.
3608 * @since 20
3609 */
3610 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3611 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3612 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3613 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3614
3615 /**
3616 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3617 * character block.
3618 * @since 22
3619 */
3620 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3621 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3622 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3623 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3624
3625 private static final int[] blockStarts = {
3626 0x0000, // 0000..007F; Basic Latin
3627 0x0080, // 0080..00FF; Latin-1 Supplement
3628 0x0100, // 0100..017F; Latin Extended-A
3629 0x0180, // 0180..024F; Latin Extended-B
3630 0x0250, // 0250..02AF; IPA Extensions
3631 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3632 0x0300, // 0300..036F; Combining Diacritical Marks
3633 0x0370, // 0370..03FF; Greek and Coptic
3634 0x0400, // 0400..04FF; Cyrillic
3635 0x0500, // 0500..052F; Cyrillic Supplement
3636 0x0530, // 0530..058F; Armenian
3637 0x0590, // 0590..05FF; Hebrew
3638 0x0600, // 0600..06FF; Arabic
3639 0x0700, // 0700..074F; Syriac
3640 0x0750, // 0750..077F; Arabic Supplement
3641 0x0780, // 0780..07BF; Thaana
3642 0x07C0, // 07C0..07FF; NKo
3643 0x0800, // 0800..083F; Samaritan
3644 0x0840, // 0840..085F; Mandaic
3645 0x0860, // 0860..086F; Syriac Supplement
3646 0x0870, // 0870..089F; Arabic Extended-B
3647 0x08A0, // 08A0..08FF; Arabic Extended-A
3648 0x0900, // 0900..097F; Devanagari
3649 0x0980, // 0980..09FF; Bengali
3650 0x0A00, // 0A00..0A7F; Gurmukhi
3651 0x0A80, // 0A80..0AFF; Gujarati
3652 0x0B00, // 0B00..0B7F; Oriya
3653 0x0B80, // 0B80..0BFF; Tamil
3654 0x0C00, // 0C00..0C7F; Telugu
3655 0x0C80, // 0C80..0CFF; Kannada
3656 0x0D00, // 0D00..0D7F; Malayalam
3657 0x0D80, // 0D80..0DFF; Sinhala
3658 0x0E00, // 0E00..0E7F; Thai
3659 0x0E80, // 0E80..0EFF; Lao
3660 0x0F00, // 0F00..0FFF; Tibetan
3661 0x1000, // 1000..109F; Myanmar
3662 0x10A0, // 10A0..10FF; Georgian
3663 0x1100, // 1100..11FF; Hangul Jamo
3664 0x1200, // 1200..137F; Ethiopic
3665 0x1380, // 1380..139F; Ethiopic Supplement
3666 0x13A0, // 13A0..13FF; Cherokee
3667 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3668 0x1680, // 1680..169F; Ogham
3669 0x16A0, // 16A0..16FF; Runic
3670 0x1700, // 1700..171F; Tagalog
3671 0x1720, // 1720..173F; Hanunoo
3672 0x1740, // 1740..175F; Buhid
3673 0x1760, // 1760..177F; Tagbanwa
3674 0x1780, // 1780..17FF; Khmer
3675 0x1800, // 1800..18AF; Mongolian
3676 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3677 0x1900, // 1900..194F; Limbu
3678 0x1950, // 1950..197F; Tai Le
3679 0x1980, // 1980..19DF; New Tai Lue
3680 0x19E0, // 19E0..19FF; Khmer Symbols
3681 0x1A00, // 1A00..1A1F; Buginese
3682 0x1A20, // 1A20..1AAF; Tai Tham
3683 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3684 0x1B00, // 1B00..1B7F; Balinese
3685 0x1B80, // 1B80..1BBF; Sundanese
3686 0x1BC0, // 1BC0..1BFF; Batak
3687 0x1C00, // 1C00..1C4F; Lepcha
3688 0x1C50, // 1C50..1C7F; Ol Chiki
3689 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3690 0x1C90, // 1C90..1CBF; Georgian Extended
3691 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3692 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3693 0x1D00, // 1D00..1D7F; Phonetic Extensions
3694 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3695 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3696 0x1E00, // 1E00..1EFF; Latin Extended Additional
3697 0x1F00, // 1F00..1FFF; Greek Extended
3698 0x2000, // 2000..206F; General Punctuation
3699 0x2070, // 2070..209F; Superscripts and Subscripts
3700 0x20A0, // 20A0..20CF; Currency Symbols
3701 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3702 0x2100, // 2100..214F; Letterlike Symbols
3703 0x2150, // 2150..218F; Number Forms
3704 0x2190, // 2190..21FF; Arrows
3705 0x2200, // 2200..22FF; Mathematical Operators
3706 0x2300, // 2300..23FF; Miscellaneous Technical
3707 0x2400, // 2400..243F; Control Pictures
3708 0x2440, // 2440..245F; Optical Character Recognition
3709 0x2460, // 2460..24FF; Enclosed Alphanumerics
3710 0x2500, // 2500..257F; Box Drawing
3711 0x2580, // 2580..259F; Block Elements
3712 0x25A0, // 25A0..25FF; Geometric Shapes
3713 0x2600, // 2600..26FF; Miscellaneous Symbols
3714 0x2700, // 2700..27BF; Dingbats
3715 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3716 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3717 0x2800, // 2800..28FF; Braille Patterns
3718 0x2900, // 2900..297F; Supplemental Arrows-B
3719 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3720 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3721 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3722 0x2C00, // 2C00..2C5F; Glagolitic
3723 0x2C60, // 2C60..2C7F; Latin Extended-C
3724 0x2C80, // 2C80..2CFF; Coptic
3725 0x2D00, // 2D00..2D2F; Georgian Supplement
3726 0x2D30, // 2D30..2D7F; Tifinagh
3727 0x2D80, // 2D80..2DDF; Ethiopic Extended
3728 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3729 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3730 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3731 0x2F00, // 2F00..2FDF; Kangxi Radicals
3732 0x2FE0, // unassigned
3733 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3734 0x3000, // 3000..303F; CJK Symbols and Punctuation
3735 0x3040, // 3040..309F; Hiragana
3736 0x30A0, // 30A0..30FF; Katakana
3737 0x3100, // 3100..312F; Bopomofo
3738 0x3130, // 3130..318F; Hangul Compatibility Jamo
3739 0x3190, // 3190..319F; Kanbun
3740 0x31A0, // 31A0..31BF; Bopomofo Extended
3741 0x31C0, // 31C0..31EF; CJK Strokes
3742 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3743 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3744 0x3300, // 3300..33FF; CJK Compatibility
3745 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3746 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3747 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3748 0xA000, // A000..A48F; Yi Syllables
3749 0xA490, // A490..A4CF; Yi Radicals
3750 0xA4D0, // A4D0..A4FF; Lisu
3751 0xA500, // A500..A63F; Vai
3752 0xA640, // A640..A69F; Cyrillic Extended-B
3753 0xA6A0, // A6A0..A6FF; Bamum
3754 0xA700, // A700..A71F; Modifier Tone Letters
3755 0xA720, // A720..A7FF; Latin Extended-D
3756 0xA800, // A800..A82F; Syloti Nagri
3757 0xA830, // A830..A83F; Common Indic Number Forms
3758 0xA840, // A840..A87F; Phags-pa
3759 0xA880, // A880..A8DF; Saurashtra
3760 0xA8E0, // A8E0..A8FF; Devanagari Extended
3761 0xA900, // A900..A92F; Kayah Li
3762 0xA930, // A930..A95F; Rejang
3763 0xA960, // A960..A97F; Hangul Jamo Extended-A
3764 0xA980, // A980..A9DF; Javanese
3765 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3766 0xAA00, // AA00..AA5F; Cham
3767 0xAA60, // AA60..AA7F; Myanmar Extended-A
3768 0xAA80, // AA80..AADF; Tai Viet
3769 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3770 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3771 0xAB30, // AB30..AB6F; Latin Extended-E
3772 0xAB70, // AB70..ABBF; Cherokee Supplement
3773 0xABC0, // ABC0..ABFF; Meetei Mayek
3774 0xAC00, // AC00..D7AF; Hangul Syllables
3775 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3776 0xD800, // D800..DB7F; High Surrogates
3777 0xDB80, // DB80..DBFF; High Private Use Surrogates
3778 0xDC00, // DC00..DFFF; Low Surrogates
3779 0xE000, // E000..F8FF; Private Use Area
3780 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3781 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3782 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3783 0xFE00, // FE00..FE0F; Variation Selectors
3784 0xFE10, // FE10..FE1F; Vertical Forms
3785 0xFE20, // FE20..FE2F; Combining Half Marks
3786 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3787 0xFE50, // FE50..FE6F; Small Form Variants
3788 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3789 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3790 0xFFF0, // FFF0..FFFF; Specials
3791 0x10000, // 10000..1007F; Linear B Syllabary
3792 0x10080, // 10080..100FF; Linear B Ideograms
3793 0x10100, // 10100..1013F; Aegean Numbers
3794 0x10140, // 10140..1018F; Ancient Greek Numbers
3795 0x10190, // 10190..101CF; Ancient Symbols
3796 0x101D0, // 101D0..101FF; Phaistos Disc
3797 0x10200, // unassigned
3798 0x10280, // 10280..1029F; Lycian
3799 0x102A0, // 102A0..102DF; Carian
3800 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3801 0x10300, // 10300..1032F; Old Italic
3802 0x10330, // 10330..1034F; Gothic
3803 0x10350, // 10350..1037F; Old Permic
3804 0x10380, // 10380..1039F; Ugaritic
3805 0x103A0, // 103A0..103DF; Old Persian
3806 0x103E0, // unassigned
3807 0x10400, // 10400..1044F; Deseret
3808 0x10450, // 10450..1047F; Shavian
3809 0x10480, // 10480..104AF; Osmanya
3810 0x104B0, // 104B0..104FF; Osage
3811 0x10500, // 10500..1052F; Elbasan
3812 0x10530, // 10530..1056F; Caucasian Albanian
3813 0x10570, // 10570..105BF; Vithkuqi
3814 0x105C0, // unassigned
3815 0x10600, // 10600..1077F; Linear A
3816 0x10780, // 10780..107BF; Latin Extended-F
3817 0x107C0, // unassigned
3818 0x10800, // 10800..1083F; Cypriot Syllabary
3819 0x10840, // 10840..1085F; Imperial Aramaic
3820 0x10860, // 10860..1087F; Palmyrene
3821 0x10880, // 10880..108AF; Nabataean
3822 0x108B0, // unassigned
3823 0x108E0, // 108E0..108FF; Hatran
3824 0x10900, // 10900..1091F; Phoenician
3825 0x10920, // 10920..1093F; Lydian
3826 0x10940, // unassigned
3827 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3828 0x109A0, // 109A0..109FF; Meroitic Cursive
3829 0x10A00, // 10A00..10A5F; Kharoshthi
3830 0x10A60, // 10A60..10A7F; Old South Arabian
3831 0x10A80, // 10A80..10A9F; Old North Arabian
3832 0x10AA0, // unassigned
3833 0x10AC0, // 10AC0..10AFF; Manichaean
3834 0x10B00, // 10B00..10B3F; Avestan
3835 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3836 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3837 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3838 0x10BB0, // unassigned
3839 0x10C00, // 10C00..10C4F; Old Turkic
3840 0x10C50, // unassigned
3841 0x10C80, // 10C80..10CFF; Old Hungarian
3842 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3843 0x10D40, // unassigned
3844 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3845 0x10E80, // 10E80..10EBF; Yezidi
3846 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
3847 0x10F00, // 10F00..10F2F; Old Sogdian
3848 0x10F30, // 10F30..10F6F; Sogdian
3849 0x10F70, // 10F70..10FAF; Old Uyghur
3850 0x10FB0, // 10FB0..10FDF; Chorasmian
3851 0x10FE0, // 10FE0..10FFF; Elymaic
3852 0x11000, // 11000..1107F; Brahmi
3853 0x11080, // 11080..110CF; Kaithi
3854 0x110D0, // 110D0..110FF; Sora Sompeng
3855 0x11100, // 11100..1114F; Chakma
3856 0x11150, // 11150..1117F; Mahajani
3857 0x11180, // 11180..111DF; Sharada
3858 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3859 0x11200, // 11200..1124F; Khojki
3860 0x11250, // unassigned
3861 0x11280, // 11280..112AF; Multani
3862 0x112B0, // 112B0..112FF; Khudawadi
3863 0x11300, // 11300..1137F; Grantha
3864 0x11380, // unassigned
3865 0x11400, // 11400..1147F; Newa
3866 0x11480, // 11480..114DF; Tirhuta
3867 0x114E0, // unassigned
3868 0x11580, // 11580..115FF; Siddham
3869 0x11600, // 11600..1165F; Modi
3870 0x11660, // 11660..1167F; Mongolian Supplement
3871 0x11680, // 11680..116CF; Takri
3872 0x116D0, // unassigned
3873 0x11700, // 11700..1174F; Ahom
3874 0x11750, // unassigned
3875 0x11800, // 11800..1184F; Dogra
3876 0x11850, // unassigned
3877 0x118A0, // 118A0..118FF; Warang Citi
3878 0x11900, // 11900..1195F; Dives Akuru
3879 0x11960, // unassigned
3880 0x119A0, // 119A0..119FF; Nandinagari
3881 0x11A00, // 11A00..11A4F; Zanabazar Square
3882 0x11A50, // 11A50..11AAF; Soyombo
3883 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
3884 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3885 0x11B00, // 11B00..11B5F; Devanagari Extended-A
3886 0x11B60, // unassigned
3887 0x11C00, // 11C00..11C6F; Bhaiksuki
3888 0x11C70, // 11C70..11CBF; Marchen
3889 0x11CC0, // unassigned
3890 0x11D00, // 11D00..11D5F; Masaram Gondi
3891 0x11D60, // 11D60..11DAF; Gunjala Gondi
3892 0x11DB0, // unassigned
3893 0x11EE0, // 11EE0..11EFF; Makasar
3894 0x11F00, // 11F00..11F5F; Kawi
3895 0x11F60, // unassigned
3896 0x11FB0, // 11FB0..11FBF; Lisu Supplement
3897 0x11FC0, // 11FC0..11FFF; Tamil Supplement
3898 0x12000, // 12000..123FF; Cuneiform
3899 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3900 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3901 0x12550, // unassigned
3902 0x12F90, // 12F90..12FFF; Cypro-Minoan
3903 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3904 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
3905 0x13460, // unassigned
3906 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3907 0x14680, // unassigned
3908 0x16800, // 16800..16A3F; Bamum Supplement
3909 0x16A40, // 16A40..16A6F; Mro
3910 0x16A70, // 16A70..16ACF; Tangsa
3911 0x16AD0, // 16AD0..16AFF; Bassa Vah
3912 0x16B00, // 16B00..16B8F; Pahawh Hmong
3913 0x16B90, // unassigned
3914 0x16E40, // 16E40..16E9F; Medefaidrin
3915 0x16EA0, // unassigned
3916 0x16F00, // 16F00..16F9F; Miao
3917 0x16FA0, // unassigned
3918 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
3919 0x17000, // 17000..187FF; Tangut
3920 0x18800, // 18800..18AFF; Tangut Components
3921 0x18B00, // 18B00..18CFF; Khitan Small Script
3922 0x18D00, // 18D00..18D7F; Tangut Supplement
3923 0x18D80, // unassigned
3924 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
3925 0x1B000, // 1B000..1B0FF; Kana Supplement
3926 0x1B100, // 1B100..1B12F; Kana Extended-A
3927 0x1B130, // 1B130..1B16F; Small Kana Extension
3928 0x1B170, // 1B170..1B2FF; Nushu
3929 0x1B300, // unassigned
3930 0x1BC00, // 1BC00..1BC9F; Duployan
3931 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3932 0x1BCB0, // unassigned
3933 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
3934 0x1CFD0, // unassigned
3935 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3936 0x1D100, // 1D100..1D1FF; Musical Symbols
3937 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3938 0x1D250, // unassigned
3939 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
3940 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
3941 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3942 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3943 0x1D380, // unassigned
3944 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3945 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3946 0x1DAB0, // unassigned
3947 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
3948 0x1E000, // 1E000..1E02F; Glagolitic Supplement
3949 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
3950 0x1E090, // unassigned
3951 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
3952 0x1E150, // unassigned
3953 0x1E290, // 1E290..1E2BF; Toto
3954 0x1E2C0, // 1E2C0..1E2FF; Wancho
3955 0x1E300, // unassigned
3956 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
3957 0x1E500, // unassigned
3958 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
3959 0x1E800, // 1E800..1E8DF; Mende Kikakui
3960 0x1E8E0, // unassigned
3961 0x1E900, // 1E900..1E95F; Adlam
3962 0x1E960, // unassigned
3963 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
3964 0x1ECC0, // unassigned
3965 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
3966 0x1ED50, // unassigned
3967 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3968 0x1EF00, // unassigned
3969 0x1F000, // 1F000..1F02F; Mahjong Tiles
3970 0x1F030, // 1F030..1F09F; Domino Tiles
3971 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3972 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3973 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3974 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3975 0x1F600, // 1F600..1F64F; Emoticons
3976 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3977 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3978 0x1F700, // 1F700..1F77F; Alchemical Symbols
3979 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3980 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3981 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3982 0x1FA00, // 1FA00..1FA6F; Chess Symbols
3983 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
3984 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
3985 0x1FC00, // unassigned
3986 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3987 0x2A6E0, // unassigned
3988 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3989 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3990 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
3991 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
3992 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
3993 0x2EE60, // unassigned
3994 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
3995 0x2FA20, // unassigned
3996 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
3997 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
3998 0x323B0, // unassigned
3999 0xE0000, // E0000..E007F; Tags
4000 0xE0080, // unassigned
4001 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4002 0xE01F0, // unassigned
4003 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4004 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4005 };
4006
4007 private static final UnicodeBlock[] blocks = {
4008 BASIC_LATIN,
4009 LATIN_1_SUPPLEMENT,
4010 LATIN_EXTENDED_A,
4011 LATIN_EXTENDED_B,
4012 IPA_EXTENSIONS,
4013 SPACING_MODIFIER_LETTERS,
4014 COMBINING_DIACRITICAL_MARKS,
4015 GREEK,
4016 CYRILLIC,
4017 CYRILLIC_SUPPLEMENTARY,
4018 ARMENIAN,
4019 HEBREW,
4020 ARABIC,
4021 SYRIAC,
4022 ARABIC_SUPPLEMENT,
4023 THAANA,
4024 NKO,
4025 SAMARITAN,
4026 MANDAIC,
4027 SYRIAC_SUPPLEMENT,
4028 ARABIC_EXTENDED_B,
4029 ARABIC_EXTENDED_A,
4030 DEVANAGARI,
4031 BENGALI,
4032 GURMUKHI,
4033 GUJARATI,
4034 ORIYA,
4035 TAMIL,
4036 TELUGU,
4037 KANNADA,
4038 MALAYALAM,
4039 SINHALA,
4040 THAI,
4041 LAO,
4042 TIBETAN,
4043 MYANMAR,
4044 GEORGIAN,
4045 HANGUL_JAMO,
4046 ETHIOPIC,
4047 ETHIOPIC_SUPPLEMENT,
4048 CHEROKEE,
4049 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4050 OGHAM,
4051 RUNIC,
4052 TAGALOG,
4053 HANUNOO,
4054 BUHID,
4055 TAGBANWA,
4056 KHMER,
4057 MONGOLIAN,
4058 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4059 LIMBU,
4060 TAI_LE,
4061 NEW_TAI_LUE,
4062 KHMER_SYMBOLS,
4063 BUGINESE,
4064 TAI_THAM,
4065 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4066 BALINESE,
4067 SUNDANESE,
4068 BATAK,
4069 LEPCHA,
4070 OL_CHIKI,
4071 CYRILLIC_EXTENDED_C,
4072 GEORGIAN_EXTENDED,
4073 SUNDANESE_SUPPLEMENT,
4074 VEDIC_EXTENSIONS,
4075 PHONETIC_EXTENSIONS,
4076 PHONETIC_EXTENSIONS_SUPPLEMENT,
4077 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4078 LATIN_EXTENDED_ADDITIONAL,
4079 GREEK_EXTENDED,
4080 GENERAL_PUNCTUATION,
4081 SUPERSCRIPTS_AND_SUBSCRIPTS,
4082 CURRENCY_SYMBOLS,
4083 COMBINING_MARKS_FOR_SYMBOLS,
4084 LETTERLIKE_SYMBOLS,
4085 NUMBER_FORMS,
4086 ARROWS,
4087 MATHEMATICAL_OPERATORS,
4088 MISCELLANEOUS_TECHNICAL,
4089 CONTROL_PICTURES,
4090 OPTICAL_CHARACTER_RECOGNITION,
4091 ENCLOSED_ALPHANUMERICS,
4092 BOX_DRAWING,
4093 BLOCK_ELEMENTS,
4094 GEOMETRIC_SHAPES,
4095 MISCELLANEOUS_SYMBOLS,
4096 DINGBATS,
4097 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4098 SUPPLEMENTAL_ARROWS_A,
4099 BRAILLE_PATTERNS,
4100 SUPPLEMENTAL_ARROWS_B,
4101 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4102 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4103 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4104 GLAGOLITIC,
4105 LATIN_EXTENDED_C,
4106 COPTIC,
4107 GEORGIAN_SUPPLEMENT,
4108 TIFINAGH,
4109 ETHIOPIC_EXTENDED,
4110 CYRILLIC_EXTENDED_A,
4111 SUPPLEMENTAL_PUNCTUATION,
4112 CJK_RADICALS_SUPPLEMENT,
4113 KANGXI_RADICALS,
4114 null,
4115 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4116 CJK_SYMBOLS_AND_PUNCTUATION,
4117 HIRAGANA,
4118 KATAKANA,
4119 BOPOMOFO,
4120 HANGUL_COMPATIBILITY_JAMO,
4121 KANBUN,
4122 BOPOMOFO_EXTENDED,
4123 CJK_STROKES,
4124 KATAKANA_PHONETIC_EXTENSIONS,
4125 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4126 CJK_COMPATIBILITY,
4127 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4128 YIJING_HEXAGRAM_SYMBOLS,
4129 CJK_UNIFIED_IDEOGRAPHS,
4130 YI_SYLLABLES,
4131 YI_RADICALS,
4132 LISU,
4133 VAI,
4134 CYRILLIC_EXTENDED_B,
4135 BAMUM,
4136 MODIFIER_TONE_LETTERS,
4137 LATIN_EXTENDED_D,
4138 SYLOTI_NAGRI,
4139 COMMON_INDIC_NUMBER_FORMS,
4140 PHAGS_PA,
4141 SAURASHTRA,
4142 DEVANAGARI_EXTENDED,
4143 KAYAH_LI,
4144 REJANG,
4145 HANGUL_JAMO_EXTENDED_A,
4146 JAVANESE,
4147 MYANMAR_EXTENDED_B,
4148 CHAM,
4149 MYANMAR_EXTENDED_A,
4150 TAI_VIET,
4151 MEETEI_MAYEK_EXTENSIONS,
4152 ETHIOPIC_EXTENDED_A,
4153 LATIN_EXTENDED_E,
4154 CHEROKEE_SUPPLEMENT,
4155 MEETEI_MAYEK,
4156 HANGUL_SYLLABLES,
4157 HANGUL_JAMO_EXTENDED_B,
4158 HIGH_SURROGATES,
4159 HIGH_PRIVATE_USE_SURROGATES,
4160 LOW_SURROGATES,
4161 PRIVATE_USE_AREA,
4162 CJK_COMPATIBILITY_IDEOGRAPHS,
4163 ALPHABETIC_PRESENTATION_FORMS,
4164 ARABIC_PRESENTATION_FORMS_A,
4165 VARIATION_SELECTORS,
4166 VERTICAL_FORMS,
4167 COMBINING_HALF_MARKS,
4168 CJK_COMPATIBILITY_FORMS,
4169 SMALL_FORM_VARIANTS,
4170 ARABIC_PRESENTATION_FORMS_B,
4171 HALFWIDTH_AND_FULLWIDTH_FORMS,
4172 SPECIALS,
4173 LINEAR_B_SYLLABARY,
4174 LINEAR_B_IDEOGRAMS,
4175 AEGEAN_NUMBERS,
4176 ANCIENT_GREEK_NUMBERS,
4177 ANCIENT_SYMBOLS,
4178 PHAISTOS_DISC,
4179 null,
4180 LYCIAN,
4181 CARIAN,
4182 COPTIC_EPACT_NUMBERS,
4183 OLD_ITALIC,
4184 GOTHIC,
4185 OLD_PERMIC,
4186 UGARITIC,
4187 OLD_PERSIAN,
4188 null,
4189 DESERET,
4190 SHAVIAN,
4191 OSMANYA,
4192 OSAGE,
4193 ELBASAN,
4194 CAUCASIAN_ALBANIAN,
4195 VITHKUQI,
4196 null,
4197 LINEAR_A,
4198 LATIN_EXTENDED_F,
4199 null,
4200 CYPRIOT_SYLLABARY,
4201 IMPERIAL_ARAMAIC,
4202 PALMYRENE,
4203 NABATAEAN,
4204 null,
4205 HATRAN,
4206 PHOENICIAN,
4207 LYDIAN,
4208 null,
4209 MEROITIC_HIEROGLYPHS,
4210 MEROITIC_CURSIVE,
4211 KHAROSHTHI,
4212 OLD_SOUTH_ARABIAN,
4213 OLD_NORTH_ARABIAN,
4214 null,
4215 MANICHAEAN,
4216 AVESTAN,
4217 INSCRIPTIONAL_PARTHIAN,
4218 INSCRIPTIONAL_PAHLAVI,
4219 PSALTER_PAHLAVI,
4220 null,
4221 OLD_TURKIC,
4222 null,
4223 OLD_HUNGARIAN,
4224 HANIFI_ROHINGYA,
4225 null,
4226 RUMI_NUMERAL_SYMBOLS,
4227 YEZIDI,
4228 ARABIC_EXTENDED_C,
4229 OLD_SOGDIAN,
4230 SOGDIAN,
4231 OLD_UYGHUR,
4232 CHORASMIAN,
4233 ELYMAIC,
4234 BRAHMI,
4235 KAITHI,
4236 SORA_SOMPENG,
4237 CHAKMA,
4238 MAHAJANI,
4239 SHARADA,
4240 SINHALA_ARCHAIC_NUMBERS,
4241 KHOJKI,
4242 null,
4243 MULTANI,
4244 KHUDAWADI,
4245 GRANTHA,
4246 null,
4247 NEWA,
4248 TIRHUTA,
4249 null,
4250 SIDDHAM,
4251 MODI,
4252 MONGOLIAN_SUPPLEMENT,
4253 TAKRI,
4254 null,
4255 AHOM,
4256 null,
4257 DOGRA,
4258 null,
4259 WARANG_CITI,
4260 DIVES_AKURU,
4261 null,
4262 NANDINAGARI,
4263 ZANABAZAR_SQUARE,
4264 SOYOMBO,
4265 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4266 PAU_CIN_HAU,
4267 DEVANAGARI_EXTENDED_A,
4268 null,
4269 BHAIKSUKI,
4270 MARCHEN,
4271 null,
4272 MASARAM_GONDI,
4273 GUNJALA_GONDI,
4274 null,
4275 MAKASAR,
4276 KAWI,
4277 null,
4278 LISU_SUPPLEMENT,
4279 TAMIL_SUPPLEMENT,
4280 CUNEIFORM,
4281 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4282 EARLY_DYNASTIC_CUNEIFORM,
4283 null,
4284 CYPRO_MINOAN,
4285 EGYPTIAN_HIEROGLYPHS,
4286 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4287 null,
4288 ANATOLIAN_HIEROGLYPHS,
4289 null,
4290 BAMUM_SUPPLEMENT,
4291 MRO,
4292 TANGSA,
4293 BASSA_VAH,
4294 PAHAWH_HMONG,
4295 null,
4296 MEDEFAIDRIN,
4297 null,
4298 MIAO,
4299 null,
4300 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4301 TANGUT,
4302 TANGUT_COMPONENTS,
4303 KHITAN_SMALL_SCRIPT,
4304 TANGUT_SUPPLEMENT,
4305 null,
4306 KANA_EXTENDED_B,
4307 KANA_SUPPLEMENT,
4308 KANA_EXTENDED_A,
4309 SMALL_KANA_EXTENSION,
4310 NUSHU,
4311 null,
4312 DUPLOYAN,
4313 SHORTHAND_FORMAT_CONTROLS,
4314 null,
4315 ZNAMENNY_MUSICAL_NOTATION,
4316 null,
4317 BYZANTINE_MUSICAL_SYMBOLS,
4318 MUSICAL_SYMBOLS,
4319 ANCIENT_GREEK_MUSICAL_NOTATION,
4320 null,
4321 KAKTOVIK_NUMERALS,
4322 MAYAN_NUMERALS,
4323 TAI_XUAN_JING_SYMBOLS,
4324 COUNTING_ROD_NUMERALS,
4325 null,
4326 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4327 SUTTON_SIGNWRITING,
4328 null,
4329 LATIN_EXTENDED_G,
4330 GLAGOLITIC_SUPPLEMENT,
4331 CYRILLIC_EXTENDED_D,
4332 null,
4333 NYIAKENG_PUACHUE_HMONG,
4334 null,
4335 TOTO,
4336 WANCHO,
4337 null,
4338 NAG_MUNDARI,
4339 null,
4340 ETHIOPIC_EXTENDED_B,
4341 MENDE_KIKAKUI,
4342 null,
4343 ADLAM,
4344 null,
4345 INDIC_SIYAQ_NUMBERS,
4346 null,
4347 OTTOMAN_SIYAQ_NUMBERS,
4348 null,
4349 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4350 null,
4351 MAHJONG_TILES,
4352 DOMINO_TILES,
4353 PLAYING_CARDS,
4354 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4355 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4356 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4357 EMOTICONS,
4358 ORNAMENTAL_DINGBATS,
4359 TRANSPORT_AND_MAP_SYMBOLS,
4360 ALCHEMICAL_SYMBOLS,
4361 GEOMETRIC_SHAPES_EXTENDED,
4362 SUPPLEMENTAL_ARROWS_C,
4363 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4364 CHESS_SYMBOLS,
4365 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4366 SYMBOLS_FOR_LEGACY_COMPUTING,
4367 null,
4368 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4369 null,
4370 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4371 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4372 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4373 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4374 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4375 null,
4376 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4377 null,
4378 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4379 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4380 null,
4381 TAGS,
4382 null,
4383 VARIATION_SELECTORS_SUPPLEMENT,
4384 null,
4385 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4386 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4387 };
4388
4389
4390 /**
4391 * Returns the object representing the Unicode block containing the
4392 * given character, or {@code null} if the character is not a
4393 * member of a defined block.
4394 *
4395 * <p><b>Note:</b> This method cannot handle
4396 * <a href="Character.html#supplementary"> supplementary
4397 * characters</a>. To support all Unicode characters, including
4398 * supplementary characters, use the {@link #of(int)} method.
4399 *
4400 * @param c The character in question
4401 * @return The {@code UnicodeBlock} instance representing the
4402 * Unicode block of which this character is a member, or
4403 * {@code null} if the character is not a member of any
4404 * Unicode block
4405 */
4406 public static UnicodeBlock of(char c) {
4407 return of((int)c);
4408 }
4409
4410 /**
4411 * Returns the object representing the Unicode block
4412 * containing the given character (Unicode code point), or
4413 * {@code null} if the character is not a member of a
4414 * defined block.
4415 *
4416 * @param codePoint the character (Unicode code point) in question.
4417 * @return The {@code UnicodeBlock} instance representing the
4418 * Unicode block of which this character is a member, or
4419 * {@code null} if the character is not a member of any
4420 * Unicode block
4421 * @throws IllegalArgumentException if the specified
4422 * {@code codePoint} is an invalid Unicode code point.
4423 * @see Character#isValidCodePoint(int)
4424 * @since 1.5
4425 */
4426 public static UnicodeBlock of(int codePoint) {
4427 if (!isValidCodePoint(codePoint)) {
4428 throw new IllegalArgumentException(
4429 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4430 }
4431
4432 int top, bottom, current;
4433 bottom = 0;
4434 top = blockStarts.length;
4435 current = top/2;
4436
4437 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4438 while (top - bottom > 1) {
4439 if (codePoint >= blockStarts[current]) {
4440 bottom = current;
4441 } else {
4442 top = current;
4443 }
4444 current = (top + bottom) / 2;
4445 }
4446 return blocks[current];
4447 }
4448
4449 /**
4450 * Returns the UnicodeBlock with the given name. Block
4451 * names are determined by The Unicode Standard. The file
4452 * {@code Blocks.txt} defines blocks for a particular
4453 * version of the standard. The {@link Character} class specifies
4454 * the version of the standard that it supports.
4455 * <p>
4456 * This method accepts block names in the following forms:
4457 * <ol>
4458 * <li> Canonical block names as defined by the Unicode Standard.
4459 * For example, the standard defines a "Basic Latin" block. Therefore, this
4460 * method accepts "Basic Latin" as a valid block name. The documentation of
4461 * each UnicodeBlock provides the canonical name.
4462 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4463 * is a valid block name for the "Basic Latin" block.
4464 * <li>The text representation of each constant UnicodeBlock identifier.
4465 * For example, this method will return the {@link #BASIC_LATIN} block if
4466 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4467 * hyphens in the canonical name with underscores.
4468 * </ol>
4469 * Finally, character case is ignored for all of the valid block name forms.
4470 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4471 * The en_US locale's case mapping rules are used to provide case-insensitive
4472 * string comparisons for block name validation.
4473 * <p>
4474 * If the Unicode Standard changes block names, both the previous and
4475 * current names will be accepted.
4476 *
4477 * @param blockName A {@code UnicodeBlock} name.
4478 * @return The {@code UnicodeBlock} instance identified
4479 * by {@code blockName}
4480 * @throws IllegalArgumentException if {@code blockName} is an
4481 * invalid name
4482 * @throws NullPointerException if {@code blockName} is null
4483 * @since 1.5
4484 */
4485 public static final UnicodeBlock forName(String blockName) {
4486 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4487 if (block == null) {
4488 throw new IllegalArgumentException("Not a valid block name: "
4489 + blockName);
4490 }
4491 return block;
4492 }
4493 }
4494
4495
4496 /**
4497 * A family of character subsets representing the character scripts
4498 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4499 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4500 * character is assigned to a single Unicode script, either a specific
4501 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4502 * one of the following three special values,
4503 * {@link Character.UnicodeScript#INHERITED Inherited},
4504 * {@link Character.UnicodeScript#COMMON Common} or
4505 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4506 *
4507 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4508 * @since 1.7
4509 */
4510 public static enum UnicodeScript {
4511 /**
4512 * Unicode script "Common".
4513 */
4514 COMMON,
4515
4516 /**
4517 * Unicode script "Latin".
4518 */
4519 LATIN,
4520
4521 /**
4522 * Unicode script "Greek".
4523 */
4524 GREEK,
4525
4526 /**
4527 * Unicode script "Cyrillic".
4528 */
4529 CYRILLIC,
4530
4531 /**
4532 * Unicode script "Armenian".
4533 */
4534 ARMENIAN,
4535
4536 /**
4537 * Unicode script "Hebrew".
4538 */
4539 HEBREW,
4540
4541 /**
4542 * Unicode script "Arabic".
4543 */
4544 ARABIC,
4545
4546 /**
4547 * Unicode script "Syriac".
4548 */
4549 SYRIAC,
4550
4551 /**
4552 * Unicode script "Thaana".
4553 */
4554 THAANA,
4555
4556 /**
4557 * Unicode script "Devanagari".
4558 */
4559 DEVANAGARI,
4560
4561 /**
4562 * Unicode script "Bengali".
4563 */
4564 BENGALI,
4565
4566 /**
4567 * Unicode script "Gurmukhi".
4568 */
4569 GURMUKHI,
4570
4571 /**
4572 * Unicode script "Gujarati".
4573 */
4574 GUJARATI,
4575
4576 /**
4577 * Unicode script "Oriya".
4578 */
4579 ORIYA,
4580
4581 /**
4582 * Unicode script "Tamil".
4583 */
4584 TAMIL,
4585
4586 /**
4587 * Unicode script "Telugu".
4588 */
4589 TELUGU,
4590
4591 /**
4592 * Unicode script "Kannada".
4593 */
4594 KANNADA,
4595
4596 /**
4597 * Unicode script "Malayalam".
4598 */
4599 MALAYALAM,
4600
4601 /**
4602 * Unicode script "Sinhala".
4603 */
4604 SINHALA,
4605
4606 /**
4607 * Unicode script "Thai".
4608 */
4609 THAI,
4610
4611 /**
4612 * Unicode script "Lao".
4613 */
4614 LAO,
4615
4616 /**
4617 * Unicode script "Tibetan".
4618 */
4619 TIBETAN,
4620
4621 /**
4622 * Unicode script "Myanmar".
4623 */
4624 MYANMAR,
4625
4626 /**
4627 * Unicode script "Georgian".
4628 */
4629 GEORGIAN,
4630
4631 /**
4632 * Unicode script "Hangul".
4633 */
4634 HANGUL,
4635
4636 /**
4637 * Unicode script "Ethiopic".
4638 */
4639 ETHIOPIC,
4640
4641 /**
4642 * Unicode script "Cherokee".
4643 */
4644 CHEROKEE,
4645
4646 /**
4647 * Unicode script "Canadian_Aboriginal".
4648 */
4649 CANADIAN_ABORIGINAL,
4650
4651 /**
4652 * Unicode script "Ogham".
4653 */
4654 OGHAM,
4655
4656 /**
4657 * Unicode script "Runic".
4658 */
4659 RUNIC,
4660
4661 /**
4662 * Unicode script "Khmer".
4663 */
4664 KHMER,
4665
4666 /**
4667 * Unicode script "Mongolian".
4668 */
4669 MONGOLIAN,
4670
4671 /**
4672 * Unicode script "Hiragana".
4673 */
4674 HIRAGANA,
4675
4676 /**
4677 * Unicode script "Katakana".
4678 */
4679 KATAKANA,
4680
4681 /**
4682 * Unicode script "Bopomofo".
4683 */
4684 BOPOMOFO,
4685
4686 /**
4687 * Unicode script "Han".
4688 */
4689 HAN,
4690
4691 /**
4692 * Unicode script "Yi".
4693 */
4694 YI,
4695
4696 /**
4697 * Unicode script "Old_Italic".
4698 */
4699 OLD_ITALIC,
4700
4701 /**
4702 * Unicode script "Gothic".
4703 */
4704 GOTHIC,
4705
4706 /**
4707 * Unicode script "Deseret".
4708 */
4709 DESERET,
4710
4711 /**
4712 * Unicode script "Inherited".
4713 */
4714 INHERITED,
4715
4716 /**
4717 * Unicode script "Tagalog".
4718 */
4719 TAGALOG,
4720
4721 /**
4722 * Unicode script "Hanunoo".
4723 */
4724 HANUNOO,
4725
4726 /**
4727 * Unicode script "Buhid".
4728 */
4729 BUHID,
4730
4731 /**
4732 * Unicode script "Tagbanwa".
4733 */
4734 TAGBANWA,
4735
4736 /**
4737 * Unicode script "Limbu".
4738 */
4739 LIMBU,
4740
4741 /**
4742 * Unicode script "Tai_Le".
4743 */
4744 TAI_LE,
4745
4746 /**
4747 * Unicode script "Linear_B".
4748 */
4749 LINEAR_B,
4750
4751 /**
4752 * Unicode script "Ugaritic".
4753 */
4754 UGARITIC,
4755
4756 /**
4757 * Unicode script "Shavian".
4758 */
4759 SHAVIAN,
4760
4761 /**
4762 * Unicode script "Osmanya".
4763 */
4764 OSMANYA,
4765
4766 /**
4767 * Unicode script "Cypriot".
4768 */
4769 CYPRIOT,
4770
4771 /**
4772 * Unicode script "Braille".
4773 */
4774 BRAILLE,
4775
4776 /**
4777 * Unicode script "Buginese".
4778 */
4779 BUGINESE,
4780
4781 /**
4782 * Unicode script "Coptic".
4783 */
4784 COPTIC,
4785
4786 /**
4787 * Unicode script "New_Tai_Lue".
4788 */
4789 NEW_TAI_LUE,
4790
4791 /**
4792 * Unicode script "Glagolitic".
4793 */
4794 GLAGOLITIC,
4795
4796 /**
4797 * Unicode script "Tifinagh".
4798 */
4799 TIFINAGH,
4800
4801 /**
4802 * Unicode script "Syloti_Nagri".
4803 */
4804 SYLOTI_NAGRI,
4805
4806 /**
4807 * Unicode script "Old_Persian".
4808 */
4809 OLD_PERSIAN,
4810
4811 /**
4812 * Unicode script "Kharoshthi".
4813 */
4814 KHAROSHTHI,
4815
4816 /**
4817 * Unicode script "Balinese".
4818 */
4819 BALINESE,
4820
4821 /**
4822 * Unicode script "Cuneiform".
4823 */
4824 CUNEIFORM,
4825
4826 /**
4827 * Unicode script "Phoenician".
4828 */
4829 PHOENICIAN,
4830
4831 /**
4832 * Unicode script "Phags_Pa".
4833 */
4834 PHAGS_PA,
4835
4836 /**
4837 * Unicode script "Nko".
4838 */
4839 NKO,
4840
4841 /**
4842 * Unicode script "Sundanese".
4843 */
4844 SUNDANESE,
4845
4846 /**
4847 * Unicode script "Batak".
4848 */
4849 BATAK,
4850
4851 /**
4852 * Unicode script "Lepcha".
4853 */
4854 LEPCHA,
4855
4856 /**
4857 * Unicode script "Ol_Chiki".
4858 */
4859 OL_CHIKI,
4860
4861 /**
4862 * Unicode script "Vai".
4863 */
4864 VAI,
4865
4866 /**
4867 * Unicode script "Saurashtra".
4868 */
4869 SAURASHTRA,
4870
4871 /**
4872 * Unicode script "Kayah_Li".
4873 */
4874 KAYAH_LI,
4875
4876 /**
4877 * Unicode script "Rejang".
4878 */
4879 REJANG,
4880
4881 /**
4882 * Unicode script "Lycian".
4883 */
4884 LYCIAN,
4885
4886 /**
4887 * Unicode script "Carian".
4888 */
4889 CARIAN,
4890
4891 /**
4892 * Unicode script "Lydian".
4893 */
4894 LYDIAN,
4895
4896 /**
4897 * Unicode script "Cham".
4898 */
4899 CHAM,
4900
4901 /**
4902 * Unicode script "Tai_Tham".
4903 */
4904 TAI_THAM,
4905
4906 /**
4907 * Unicode script "Tai_Viet".
4908 */
4909 TAI_VIET,
4910
4911 /**
4912 * Unicode script "Avestan".
4913 */
4914 AVESTAN,
4915
4916 /**
4917 * Unicode script "Egyptian_Hieroglyphs".
4918 */
4919 EGYPTIAN_HIEROGLYPHS,
4920
4921 /**
4922 * Unicode script "Samaritan".
4923 */
4924 SAMARITAN,
4925
4926 /**
4927 * Unicode script "Mandaic".
4928 */
4929 MANDAIC,
4930
4931 /**
4932 * Unicode script "Lisu".
4933 */
4934 LISU,
4935
4936 /**
4937 * Unicode script "Bamum".
4938 */
4939 BAMUM,
4940
4941 /**
4942 * Unicode script "Javanese".
4943 */
4944 JAVANESE,
4945
4946 /**
4947 * Unicode script "Meetei_Mayek".
4948 */
4949 MEETEI_MAYEK,
4950
4951 /**
4952 * Unicode script "Imperial_Aramaic".
4953 */
4954 IMPERIAL_ARAMAIC,
4955
4956 /**
4957 * Unicode script "Old_South_Arabian".
4958 */
4959 OLD_SOUTH_ARABIAN,
4960
4961 /**
4962 * Unicode script "Inscriptional_Parthian".
4963 */
4964 INSCRIPTIONAL_PARTHIAN,
4965
4966 /**
4967 * Unicode script "Inscriptional_Pahlavi".
4968 */
4969 INSCRIPTIONAL_PAHLAVI,
4970
4971 /**
4972 * Unicode script "Old_Turkic".
4973 */
4974 OLD_TURKIC,
4975
4976 /**
4977 * Unicode script "Brahmi".
4978 */
4979 BRAHMI,
4980
4981 /**
4982 * Unicode script "Kaithi".
4983 */
4984 KAITHI,
4985
4986 /**
4987 * Unicode script "Meroitic Hieroglyphs".
4988 * @since 1.8
4989 */
4990 MEROITIC_HIEROGLYPHS,
4991
4992 /**
4993 * Unicode script "Meroitic Cursive".
4994 * @since 1.8
4995 */
4996 MEROITIC_CURSIVE,
4997
4998 /**
4999 * Unicode script "Sora Sompeng".
5000 * @since 1.8
5001 */
5002 SORA_SOMPENG,
5003
5004 /**
5005 * Unicode script "Chakma".
5006 * @since 1.8
5007 */
5008 CHAKMA,
5009
5010 /**
5011 * Unicode script "Sharada".
5012 * @since 1.8
5013 */
5014 SHARADA,
5015
5016 /**
5017 * Unicode script "Takri".
5018 * @since 1.8
5019 */
5020 TAKRI,
5021
5022 /**
5023 * Unicode script "Miao".
5024 * @since 1.8
5025 */
5026 MIAO,
5027
5028 /**
5029 * Unicode script "Caucasian Albanian".
5030 * @since 9
5031 */
5032 CAUCASIAN_ALBANIAN,
5033
5034 /**
5035 * Unicode script "Bassa Vah".
5036 * @since 9
5037 */
5038 BASSA_VAH,
5039
5040 /**
5041 * Unicode script "Duployan".
5042 * @since 9
5043 */
5044 DUPLOYAN,
5045
5046 /**
5047 * Unicode script "Elbasan".
5048 * @since 9
5049 */
5050 ELBASAN,
5051
5052 /**
5053 * Unicode script "Grantha".
5054 * @since 9
5055 */
5056 GRANTHA,
5057
5058 /**
5059 * Unicode script "Pahawh Hmong".
5060 * @since 9
5061 */
5062 PAHAWH_HMONG,
5063
5064 /**
5065 * Unicode script "Khojki".
5066 * @since 9
5067 */
5068 KHOJKI,
5069
5070 /**
5071 * Unicode script "Linear A".
5072 * @since 9
5073 */
5074 LINEAR_A,
5075
5076 /**
5077 * Unicode script "Mahajani".
5078 * @since 9
5079 */
5080 MAHAJANI,
5081
5082 /**
5083 * Unicode script "Manichaean".
5084 * @since 9
5085 */
5086 MANICHAEAN,
5087
5088 /**
5089 * Unicode script "Mende Kikakui".
5090 * @since 9
5091 */
5092 MENDE_KIKAKUI,
5093
5094 /**
5095 * Unicode script "Modi".
5096 * @since 9
5097 */
5098 MODI,
5099
5100 /**
5101 * Unicode script "Mro".
5102 * @since 9
5103 */
5104 MRO,
5105
5106 /**
5107 * Unicode script "Old North Arabian".
5108 * @since 9
5109 */
5110 OLD_NORTH_ARABIAN,
5111
5112 /**
5113 * Unicode script "Nabataean".
5114 * @since 9
5115 */
5116 NABATAEAN,
5117
5118 /**
5119 * Unicode script "Palmyrene".
5120 * @since 9
5121 */
5122 PALMYRENE,
5123
5124 /**
5125 * Unicode script "Pau Cin Hau".
5126 * @since 9
5127 */
5128 PAU_CIN_HAU,
5129
5130 /**
5131 * Unicode script "Old Permic".
5132 * @since 9
5133 */
5134 OLD_PERMIC,
5135
5136 /**
5137 * Unicode script "Psalter Pahlavi".
5138 * @since 9
5139 */
5140 PSALTER_PAHLAVI,
5141
5142 /**
5143 * Unicode script "Siddham".
5144 * @since 9
5145 */
5146 SIDDHAM,
5147
5148 /**
5149 * Unicode script "Khudawadi".
5150 * @since 9
5151 */
5152 KHUDAWADI,
5153
5154 /**
5155 * Unicode script "Tirhuta".
5156 * @since 9
5157 */
5158 TIRHUTA,
5159
5160 /**
5161 * Unicode script "Warang Citi".
5162 * @since 9
5163 */
5164 WARANG_CITI,
5165
5166 /**
5167 * Unicode script "Ahom".
5168 * @since 9
5169 */
5170 AHOM,
5171
5172 /**
5173 * Unicode script "Anatolian Hieroglyphs".
5174 * @since 9
5175 */
5176 ANATOLIAN_HIEROGLYPHS,
5177
5178 /**
5179 * Unicode script "Hatran".
5180 * @since 9
5181 */
5182 HATRAN,
5183
5184 /**
5185 * Unicode script "Multani".
5186 * @since 9
5187 */
5188 MULTANI,
5189
5190 /**
5191 * Unicode script "Old Hungarian".
5192 * @since 9
5193 */
5194 OLD_HUNGARIAN,
5195
5196 /**
5197 * Unicode script "SignWriting".
5198 * @since 9
5199 */
5200 SIGNWRITING,
5201
5202 /**
5203 * Unicode script "Adlam".
5204 * @since 11
5205 */
5206 ADLAM,
5207
5208 /**
5209 * Unicode script "Bhaiksuki".
5210 * @since 11
5211 */
5212 BHAIKSUKI,
5213
5214 /**
5215 * Unicode script "Marchen".
5216 * @since 11
5217 */
5218 MARCHEN,
5219
5220 /**
5221 * Unicode script "Newa".
5222 * @since 11
5223 */
5224 NEWA,
5225
5226 /**
5227 * Unicode script "Osage".
5228 * @since 11
5229 */
5230 OSAGE,
5231
5232 /**
5233 * Unicode script "Tangut".
5234 * @since 11
5235 */
5236 TANGUT,
5237
5238 /**
5239 * Unicode script "Masaram Gondi".
5240 * @since 11
5241 */
5242 MASARAM_GONDI,
5243
5244 /**
5245 * Unicode script "Nushu".
5246 * @since 11
5247 */
5248 NUSHU,
5249
5250 /**
5251 * Unicode script "Soyombo".
5252 * @since 11
5253 */
5254 SOYOMBO,
5255
5256 /**
5257 * Unicode script "Zanabazar Square".
5258 * @since 11
5259 */
5260 ZANABAZAR_SQUARE,
5261
5262 /**
5263 * Unicode script "Hanifi Rohingya".
5264 * @since 12
5265 */
5266 HANIFI_ROHINGYA,
5267
5268 /**
5269 * Unicode script "Old Sogdian".
5270 * @since 12
5271 */
5272 OLD_SOGDIAN,
5273
5274 /**
5275 * Unicode script "Sogdian".
5276 * @since 12
5277 */
5278 SOGDIAN,
5279
5280 /**
5281 * Unicode script "Dogra".
5282 * @since 12
5283 */
5284 DOGRA,
5285
5286 /**
5287 * Unicode script "Gunjala Gondi".
5288 * @since 12
5289 */
5290 GUNJALA_GONDI,
5291
5292 /**
5293 * Unicode script "Makasar".
5294 * @since 12
5295 */
5296 MAKASAR,
5297
5298 /**
5299 * Unicode script "Medefaidrin".
5300 * @since 12
5301 */
5302 MEDEFAIDRIN,
5303
5304 /**
5305 * Unicode script "Elymaic".
5306 * @since 13
5307 */
5308 ELYMAIC,
5309
5310 /**
5311 * Unicode script "Nandinagari".
5312 * @since 13
5313 */
5314 NANDINAGARI,
5315
5316 /**
5317 * Unicode script "Nyiakeng Puachue Hmong".
5318 * @since 13
5319 */
5320 NYIAKENG_PUACHUE_HMONG,
5321
5322 /**
5323 * Unicode script "Wancho".
5324 * @since 13
5325 */
5326 WANCHO,
5327
5328 /**
5329 * Unicode script "Yezidi".
5330 * @since 15
5331 */
5332 YEZIDI,
5333
5334 /**
5335 * Unicode script "Chorasmian".
5336 * @since 15
5337 */
5338 CHORASMIAN,
5339
5340 /**
5341 * Unicode script "Dives Akuru".
5342 * @since 15
5343 */
5344 DIVES_AKURU,
5345
5346 /**
5347 * Unicode script "Khitan Small Script".
5348 * @since 15
5349 */
5350 KHITAN_SMALL_SCRIPT,
5351
5352 /**
5353 * Unicode script "Vithkuqi".
5354 * @since 19
5355 */
5356 VITHKUQI,
5357
5358 /**
5359 * Unicode script "Old Uyghur".
5360 * @since 19
5361 */
5362 OLD_UYGHUR,
5363
5364 /**
5365 * Unicode script "Cypro Minoan".
5366 * @since 19
5367 */
5368 CYPRO_MINOAN,
5369
5370 /**
5371 * Unicode script "Tangsa".
5372 * @since 19
5373 */
5374 TANGSA,
5375
5376 /**
5377 * Unicode script "Toto".
5378 * @since 19
5379 */
5380 TOTO,
5381
5382 /**
5383 * Unicode script "Kawi".
5384 * @since 20
5385 */
5386 KAWI,
5387
5388 /**
5389 * Unicode script "Nag Mundari".
5390 * @since 20
5391 */
5392 NAG_MUNDARI,
5393
5394 /**
5395 * Unicode script "Unknown".
5396 */
5397 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5398
5399 private static final int[] scriptStarts = {
5400 0x0000, // 0000..0040; COMMON
5401 0x0041, // 0041..005A; LATIN
5402 0x005B, // 005B..0060; COMMON
5403 0x0061, // 0061..007A; LATIN
5404 0x007B, // 007B..00A9; COMMON
5405 0x00AA, // 00AA ; LATIN
5406 0x00AB, // 00AB..00B9; COMMON
5407 0x00BA, // 00BA ; LATIN
5408 0x00BB, // 00BB..00BF; COMMON
5409 0x00C0, // 00C0..00D6; LATIN
5410 0x00D7, // 00D7 ; COMMON
5411 0x00D8, // 00D8..00F6; LATIN
5412 0x00F7, // 00F7 ; COMMON
5413 0x00F8, // 00F8..02B8; LATIN
5414 0x02B9, // 02B9..02DF; COMMON
5415 0x02E0, // 02E0..02E4; LATIN
5416 0x02E5, // 02E5..02E9; COMMON
5417 0x02EA, // 02EA..02EB; BOPOMOFO
5418 0x02EC, // 02EC..02FF; COMMON
5419 0x0300, // 0300..036F; INHERITED
5420 0x0370, // 0370..0373; GREEK
5421 0x0374, // 0374 ; COMMON
5422 0x0375, // 0375..0377; GREEK
5423 0x0378, // 0378..0379; UNKNOWN
5424 0x037A, // 037A..037D; GREEK
5425 0x037E, // 037E ; COMMON
5426 0x037F, // 037F ; GREEK
5427 0x0380, // 0380..0383; UNKNOWN
5428 0x0384, // 0384 ; GREEK
5429 0x0385, // 0385 ; COMMON
5430 0x0386, // 0386 ; GREEK
5431 0x0387, // 0387 ; COMMON
5432 0x0388, // 0388..038A; GREEK
5433 0x038B, // 038B ; UNKNOWN
5434 0x038C, // 038C ; GREEK
5435 0x038D, // 038D ; UNKNOWN
5436 0x038E, // 038E..03A1; GREEK
5437 0x03A2, // 03A2 ; UNKNOWN
5438 0x03A3, // 03A3..03E1; GREEK
5439 0x03E2, // 03E2..03EF; COPTIC
5440 0x03F0, // 03F0..03FF; GREEK
5441 0x0400, // 0400..0484; CYRILLIC
5442 0x0485, // 0485..0486; INHERITED
5443 0x0487, // 0487..052F; CYRILLIC
5444 0x0530, // 0530 ; UNKNOWN
5445 0x0531, // 0531..0556; ARMENIAN
5446 0x0557, // 0557..0558; UNKNOWN
5447 0x0559, // 0559..058A; ARMENIAN
5448 0x058B, // 058B..058C; UNKNOWN
5449 0x058D, // 058D..058F; ARMENIAN
5450 0x0590, // 0590 ; UNKNOWN
5451 0x0591, // 0591..05C7; HEBREW
5452 0x05C8, // 05C8..05CF; UNKNOWN
5453 0x05D0, // 05D0..05EA; HEBREW
5454 0x05EB, // 05EB..05EE; UNKNOWN
5455 0x05EF, // 05EF..05F4; HEBREW
5456 0x05F5, // 05F5..05FF; UNKNOWN
5457 0x0600, // 0600..0604; ARABIC
5458 0x0605, // 0605 ; COMMON
5459 0x0606, // 0606..060B; ARABIC
5460 0x060C, // 060C ; COMMON
5461 0x060D, // 060D..061A; ARABIC
5462 0x061B, // 061B ; COMMON
5463 0x061C, // 061C..061E; ARABIC
5464 0x061F, // 061F ; COMMON
5465 0x0620, // 0620..063F; ARABIC
5466 0x0640, // 0640 ; COMMON
5467 0x0641, // 0641..064A; ARABIC
5468 0x064B, // 064B..0655; INHERITED
5469 0x0656, // 0656..066F; ARABIC
5470 0x0670, // 0670 ; INHERITED
5471 0x0671, // 0671..06DC; ARABIC
5472 0x06DD, // 06DD ; COMMON
5473 0x06DE, // 06DE..06FF; ARABIC
5474 0x0700, // 0700..070D; SYRIAC
5475 0x070E, // 070E ; UNKNOWN
5476 0x070F, // 070F..074A; SYRIAC
5477 0x074B, // 074B..074C; UNKNOWN
5478 0x074D, // 074D..074F; SYRIAC
5479 0x0750, // 0750..077F; ARABIC
5480 0x0780, // 0780..07B1; THAANA
5481 0x07B2, // 07B2..07BF; UNKNOWN
5482 0x07C0, // 07C0..07FA; NKO
5483 0x07FB, // 07FB..07FC; UNKNOWN
5484 0x07FD, // 07FD..07FF; NKO
5485 0x0800, // 0800..082D; SAMARITAN
5486 0x082E, // 082E..082F; UNKNOWN
5487 0x0830, // 0830..083E; SAMARITAN
5488 0x083F, // 083F ; UNKNOWN
5489 0x0840, // 0840..085B; MANDAIC
5490 0x085C, // 085C..085D; UNKNOWN
5491 0x085E, // 085E ; MANDAIC
5492 0x085F, // 085F ; UNKNOWN
5493 0x0860, // 0860..086A; SYRIAC
5494 0x086B, // 086B..086F; UNKNOWN
5495 0x0870, // 0870..088E; ARABIC
5496 0x088F, // 088F ; UNKNOWN
5497 0x0890, // 0890..0891; ARABIC
5498 0x0892, // 0892..0897; UNKNOWN
5499 0x0898, // 0898..08E1; ARABIC
5500 0x08E2, // 08E2 ; COMMON
5501 0x08E3, // 08E3..08FF; ARABIC
5502 0x0900, // 0900..0950; DEVANAGARI
5503 0x0951, // 0951..0954; INHERITED
5504 0x0955, // 0955..0963; DEVANAGARI
5505 0x0964, // 0964..0965; COMMON
5506 0x0966, // 0966..097F; DEVANAGARI
5507 0x0980, // 0980..0983; BENGALI
5508 0x0984, // 0984 ; UNKNOWN
5509 0x0985, // 0985..098C; BENGALI
5510 0x098D, // 098D..098E; UNKNOWN
5511 0x098F, // 098F..0990; BENGALI
5512 0x0991, // 0991..0992; UNKNOWN
5513 0x0993, // 0993..09A8; BENGALI
5514 0x09A9, // 09A9 ; UNKNOWN
5515 0x09AA, // 09AA..09B0; BENGALI
5516 0x09B1, // 09B1 ; UNKNOWN
5517 0x09B2, // 09B2 ; BENGALI
5518 0x09B3, // 09B3..09B5; UNKNOWN
5519 0x09B6, // 09B6..09B9; BENGALI
5520 0x09BA, // 09BA..09BB; UNKNOWN
5521 0x09BC, // 09BC..09C4; BENGALI
5522 0x09C5, // 09C5..09C6; UNKNOWN
5523 0x09C7, // 09C7..09C8; BENGALI
5524 0x09C9, // 09C9..09CA; UNKNOWN
5525 0x09CB, // 09CB..09CE; BENGALI
5526 0x09CF, // 09CF..09D6; UNKNOWN
5527 0x09D7, // 09D7 ; BENGALI
5528 0x09D8, // 09D8..09DB; UNKNOWN
5529 0x09DC, // 09DC..09DD; BENGALI
5530 0x09DE, // 09DE ; UNKNOWN
5531 0x09DF, // 09DF..09E3; BENGALI
5532 0x09E4, // 09E4..09E5; UNKNOWN
5533 0x09E6, // 09E6..09FE; BENGALI
5534 0x09FF, // 09FF..0A00; UNKNOWN
5535 0x0A01, // 0A01..0A03; GURMUKHI
5536 0x0A04, // 0A04 ; UNKNOWN
5537 0x0A05, // 0A05..0A0A; GURMUKHI
5538 0x0A0B, // 0A0B..0A0E; UNKNOWN
5539 0x0A0F, // 0A0F..0A10; GURMUKHI
5540 0x0A11, // 0A11..0A12; UNKNOWN
5541 0x0A13, // 0A13..0A28; GURMUKHI
5542 0x0A29, // 0A29 ; UNKNOWN
5543 0x0A2A, // 0A2A..0A30; GURMUKHI
5544 0x0A31, // 0A31 ; UNKNOWN
5545 0x0A32, // 0A32..0A33; GURMUKHI
5546 0x0A34, // 0A34 ; UNKNOWN
5547 0x0A35, // 0A35..0A36; GURMUKHI
5548 0x0A37, // 0A37 ; UNKNOWN
5549 0x0A38, // 0A38..0A39; GURMUKHI
5550 0x0A3A, // 0A3A..0A3B; UNKNOWN
5551 0x0A3C, // 0A3C ; GURMUKHI
5552 0x0A3D, // 0A3D ; UNKNOWN
5553 0x0A3E, // 0A3E..0A42; GURMUKHI
5554 0x0A43, // 0A43..0A46; UNKNOWN
5555 0x0A47, // 0A47..0A48; GURMUKHI
5556 0x0A49, // 0A49..0A4A; UNKNOWN
5557 0x0A4B, // 0A4B..0A4D; GURMUKHI
5558 0x0A4E, // 0A4E..0A50; UNKNOWN
5559 0x0A51, // 0A51 ; GURMUKHI
5560 0x0A52, // 0A52..0A58; UNKNOWN
5561 0x0A59, // 0A59..0A5C; GURMUKHI
5562 0x0A5D, // 0A5D ; UNKNOWN
5563 0x0A5E, // 0A5E ; GURMUKHI
5564 0x0A5F, // 0A5F..0A65; UNKNOWN
5565 0x0A66, // 0A66..0A76; GURMUKHI
5566 0x0A77, // 0A77..0A80; UNKNOWN
5567 0x0A81, // 0A81..0A83; GUJARATI
5568 0x0A84, // 0A84 ; UNKNOWN
5569 0x0A85, // 0A85..0A8D; GUJARATI
5570 0x0A8E, // 0A8E ; UNKNOWN
5571 0x0A8F, // 0A8F..0A91; GUJARATI
5572 0x0A92, // 0A92 ; UNKNOWN
5573 0x0A93, // 0A93..0AA8; GUJARATI
5574 0x0AA9, // 0AA9 ; UNKNOWN
5575 0x0AAA, // 0AAA..0AB0; GUJARATI
5576 0x0AB1, // 0AB1 ; UNKNOWN
5577 0x0AB2, // 0AB2..0AB3; GUJARATI
5578 0x0AB4, // 0AB4 ; UNKNOWN
5579 0x0AB5, // 0AB5..0AB9; GUJARATI
5580 0x0ABA, // 0ABA..0ABB; UNKNOWN
5581 0x0ABC, // 0ABC..0AC5; GUJARATI
5582 0x0AC6, // 0AC6 ; UNKNOWN
5583 0x0AC7, // 0AC7..0AC9; GUJARATI
5584 0x0ACA, // 0ACA ; UNKNOWN
5585 0x0ACB, // 0ACB..0ACD; GUJARATI
5586 0x0ACE, // 0ACE..0ACF; UNKNOWN
5587 0x0AD0, // 0AD0 ; GUJARATI
5588 0x0AD1, // 0AD1..0ADF; UNKNOWN
5589 0x0AE0, // 0AE0..0AE3; GUJARATI
5590 0x0AE4, // 0AE4..0AE5; UNKNOWN
5591 0x0AE6, // 0AE6..0AF1; GUJARATI
5592 0x0AF2, // 0AF2..0AF8; UNKNOWN
5593 0x0AF9, // 0AF9..0AFF; GUJARATI
5594 0x0B00, // 0B00 ; UNKNOWN
5595 0x0B01, // 0B01..0B03; ORIYA
5596 0x0B04, // 0B04 ; UNKNOWN
5597 0x0B05, // 0B05..0B0C; ORIYA
5598 0x0B0D, // 0B0D..0B0E; UNKNOWN
5599 0x0B0F, // 0B0F..0B10; ORIYA
5600 0x0B11, // 0B11..0B12; UNKNOWN
5601 0x0B13, // 0B13..0B28; ORIYA
5602 0x0B29, // 0B29 ; UNKNOWN
5603 0x0B2A, // 0B2A..0B30; ORIYA
5604 0x0B31, // 0B31 ; UNKNOWN
5605 0x0B32, // 0B32..0B33; ORIYA
5606 0x0B34, // 0B34 ; UNKNOWN
5607 0x0B35, // 0B35..0B39; ORIYA
5608 0x0B3A, // 0B3A..0B3B; UNKNOWN
5609 0x0B3C, // 0B3C..0B44; ORIYA
5610 0x0B45, // 0B45..0B46; UNKNOWN
5611 0x0B47, // 0B47..0B48; ORIYA
5612 0x0B49, // 0B49..0B4A; UNKNOWN
5613 0x0B4B, // 0B4B..0B4D; ORIYA
5614 0x0B4E, // 0B4E..0B54; UNKNOWN
5615 0x0B55, // 0B55..0B57; ORIYA
5616 0x0B58, // 0B58..0B5B; UNKNOWN
5617 0x0B5C, // 0B5C..0B5D; ORIYA
5618 0x0B5E, // 0B5E ; UNKNOWN
5619 0x0B5F, // 0B5F..0B63; ORIYA
5620 0x0B64, // 0B64..0B65; UNKNOWN
5621 0x0B66, // 0B66..0B77; ORIYA
5622 0x0B78, // 0B78..0B81; UNKNOWN
5623 0x0B82, // 0B82..0B83; TAMIL
5624 0x0B84, // 0B84 ; UNKNOWN
5625 0x0B85, // 0B85..0B8A; TAMIL
5626 0x0B8B, // 0B8B..0B8D; UNKNOWN
5627 0x0B8E, // 0B8E..0B90; TAMIL
5628 0x0B91, // 0B91 ; UNKNOWN
5629 0x0B92, // 0B92..0B95; TAMIL
5630 0x0B96, // 0B96..0B98; UNKNOWN
5631 0x0B99, // 0B99..0B9A; TAMIL
5632 0x0B9B, // 0B9B ; UNKNOWN
5633 0x0B9C, // 0B9C ; TAMIL
5634 0x0B9D, // 0B9D ; UNKNOWN
5635 0x0B9E, // 0B9E..0B9F; TAMIL
5636 0x0BA0, // 0BA0..0BA2; UNKNOWN
5637 0x0BA3, // 0BA3..0BA4; TAMIL
5638 0x0BA5, // 0BA5..0BA7; UNKNOWN
5639 0x0BA8, // 0BA8..0BAA; TAMIL
5640 0x0BAB, // 0BAB..0BAD; UNKNOWN
5641 0x0BAE, // 0BAE..0BB9; TAMIL
5642 0x0BBA, // 0BBA..0BBD; UNKNOWN
5643 0x0BBE, // 0BBE..0BC2; TAMIL
5644 0x0BC3, // 0BC3..0BC5; UNKNOWN
5645 0x0BC6, // 0BC6..0BC8; TAMIL
5646 0x0BC9, // 0BC9 ; UNKNOWN
5647 0x0BCA, // 0BCA..0BCD; TAMIL
5648 0x0BCE, // 0BCE..0BCF; UNKNOWN
5649 0x0BD0, // 0BD0 ; TAMIL
5650 0x0BD1, // 0BD1..0BD6; UNKNOWN
5651 0x0BD7, // 0BD7 ; TAMIL
5652 0x0BD8, // 0BD8..0BE5; UNKNOWN
5653 0x0BE6, // 0BE6..0BFA; TAMIL
5654 0x0BFB, // 0BFB..0BFF; UNKNOWN
5655 0x0C00, // 0C00..0C0C; TELUGU
5656 0x0C0D, // 0C0D ; UNKNOWN
5657 0x0C0E, // 0C0E..0C10; TELUGU
5658 0x0C11, // 0C11 ; UNKNOWN
5659 0x0C12, // 0C12..0C28; TELUGU
5660 0x0C29, // 0C29 ; UNKNOWN
5661 0x0C2A, // 0C2A..0C39; TELUGU
5662 0x0C3A, // 0C3A..0C3B; UNKNOWN
5663 0x0C3C, // 0C3C..0C44; TELUGU
5664 0x0C45, // 0C45 ; UNKNOWN
5665 0x0C46, // 0C46..0C48; TELUGU
5666 0x0C49, // 0C49 ; UNKNOWN
5667 0x0C4A, // 0C4A..0C4D; TELUGU
5668 0x0C4E, // 0C4E..0C54; UNKNOWN
5669 0x0C55, // 0C55..0C56; TELUGU
5670 0x0C57, // 0C57 ; UNKNOWN
5671 0x0C58, // 0C58..0C5A; TELUGU
5672 0x0C5B, // 0C5B..0C5C; UNKNOWN
5673 0x0C5D, // 0C5D ; TELUGU
5674 0x0C5E, // 0C5E..0C5F; UNKNOWN
5675 0x0C60, // 0C60..0C63; TELUGU
5676 0x0C64, // 0C64..0C65; UNKNOWN
5677 0x0C66, // 0C66..0C6F; TELUGU
5678 0x0C70, // 0C70..0C76; UNKNOWN
5679 0x0C77, // 0C77..0C7F; TELUGU
5680 0x0C80, // 0C80..0C8C; KANNADA
5681 0x0C8D, // 0C8D ; UNKNOWN
5682 0x0C8E, // 0C8E..0C90; KANNADA
5683 0x0C91, // 0C91 ; UNKNOWN
5684 0x0C92, // 0C92..0CA8; KANNADA
5685 0x0CA9, // 0CA9 ; UNKNOWN
5686 0x0CAA, // 0CAA..0CB3; KANNADA
5687 0x0CB4, // 0CB4 ; UNKNOWN
5688 0x0CB5, // 0CB5..0CB9; KANNADA
5689 0x0CBA, // 0CBA..0CBB; UNKNOWN
5690 0x0CBC, // 0CBC..0CC4; KANNADA
5691 0x0CC5, // 0CC5 ; UNKNOWN
5692 0x0CC6, // 0CC6..0CC8; KANNADA
5693 0x0CC9, // 0CC9 ; UNKNOWN
5694 0x0CCA, // 0CCA..0CCD; KANNADA
5695 0x0CCE, // 0CCE..0CD4; UNKNOWN
5696 0x0CD5, // 0CD5..0CD6; KANNADA
5697 0x0CD7, // 0CD7..0CDC; UNKNOWN
5698 0x0CDD, // 0CDD..0CDE; KANNADA
5699 0x0CDF, // 0CDF ; UNKNOWN
5700 0x0CE0, // 0CE0..0CE3; KANNADA
5701 0x0CE4, // 0CE4..0CE5; UNKNOWN
5702 0x0CE6, // 0CE6..0CEF; KANNADA
5703 0x0CF0, // 0CF0 ; UNKNOWN
5704 0x0CF1, // 0CF1..0CF3; KANNADA
5705 0x0CF4, // 0CF4..0CFF; UNKNOWN
5706 0x0D00, // 0D00..0D0C; MALAYALAM
5707 0x0D0D, // 0D0D ; UNKNOWN
5708 0x0D0E, // 0D0E..0D10; MALAYALAM
5709 0x0D11, // 0D11 ; UNKNOWN
5710 0x0D12, // 0D12..0D44; MALAYALAM
5711 0x0D45, // 0D45 ; UNKNOWN
5712 0x0D46, // 0D46..0D48; MALAYALAM
5713 0x0D49, // 0D49 ; UNKNOWN
5714 0x0D4A, // 0D4A..0D4F; MALAYALAM
5715 0x0D50, // 0D50..0D53; UNKNOWN
5716 0x0D54, // 0D54..0D63; MALAYALAM
5717 0x0D64, // 0D64..0D65; UNKNOWN
5718 0x0D66, // 0D66..0D7F; MALAYALAM
5719 0x0D80, // 0D80 ; UNKNOWN
5720 0x0D81, // 0D81..0D83; SINHALA
5721 0x0D84, // 0D84 ; UNKNOWN
5722 0x0D85, // 0D85..0D96; SINHALA
5723 0x0D97, // 0D97..0D99; UNKNOWN
5724 0x0D9A, // 0D9A..0DB1; SINHALA
5725 0x0DB2, // 0DB2 ; UNKNOWN
5726 0x0DB3, // 0DB3..0DBB; SINHALA
5727 0x0DBC, // 0DBC ; UNKNOWN
5728 0x0DBD, // 0DBD ; SINHALA
5729 0x0DBE, // 0DBE..0DBF; UNKNOWN
5730 0x0DC0, // 0DC0..0DC6; SINHALA
5731 0x0DC7, // 0DC7..0DC9; UNKNOWN
5732 0x0DCA, // 0DCA ; SINHALA
5733 0x0DCB, // 0DCB..0DCE; UNKNOWN
5734 0x0DCF, // 0DCF..0DD4; SINHALA
5735 0x0DD5, // 0DD5 ; UNKNOWN
5736 0x0DD6, // 0DD6 ; SINHALA
5737 0x0DD7, // 0DD7 ; UNKNOWN
5738 0x0DD8, // 0DD8..0DDF; SINHALA
5739 0x0DE0, // 0DE0..0DE5; UNKNOWN
5740 0x0DE6, // 0DE6..0DEF; SINHALA
5741 0x0DF0, // 0DF0..0DF1; UNKNOWN
5742 0x0DF2, // 0DF2..0DF4; SINHALA
5743 0x0DF5, // 0DF5..0E00; UNKNOWN
5744 0x0E01, // 0E01..0E3A; THAI
5745 0x0E3B, // 0E3B..0E3E; UNKNOWN
5746 0x0E3F, // 0E3F ; COMMON
5747 0x0E40, // 0E40..0E5B; THAI
5748 0x0E5C, // 0E5C..0E80; UNKNOWN
5749 0x0E81, // 0E81..0E82; LAO
5750 0x0E83, // 0E83 ; UNKNOWN
5751 0x0E84, // 0E84 ; LAO
5752 0x0E85, // 0E85 ; UNKNOWN
5753 0x0E86, // 0E86..0E8A; LAO
5754 0x0E8B, // 0E8B ; UNKNOWN
5755 0x0E8C, // 0E8C..0EA3; LAO
5756 0x0EA4, // 0EA4 ; UNKNOWN
5757 0x0EA5, // 0EA5 ; LAO
5758 0x0EA6, // 0EA6 ; UNKNOWN
5759 0x0EA7, // 0EA7..0EBD; LAO
5760 0x0EBE, // 0EBE..0EBF; UNKNOWN
5761 0x0EC0, // 0EC0..0EC4; LAO
5762 0x0EC5, // 0EC5 ; UNKNOWN
5763 0x0EC6, // 0EC6 ; LAO
5764 0x0EC7, // 0EC7 ; UNKNOWN
5765 0x0EC8, // 0EC8..0ECE; LAO
5766 0x0ECF, // 0ECF ; UNKNOWN
5767 0x0ED0, // 0ED0..0ED9; LAO
5768 0x0EDA, // 0EDA..0EDB; UNKNOWN
5769 0x0EDC, // 0EDC..0EDF; LAO
5770 0x0EE0, // 0EE0..0EFF; UNKNOWN
5771 0x0F00, // 0F00..0F47; TIBETAN
5772 0x0F48, // 0F48 ; UNKNOWN
5773 0x0F49, // 0F49..0F6C; TIBETAN
5774 0x0F6D, // 0F6D..0F70; UNKNOWN
5775 0x0F71, // 0F71..0F97; TIBETAN
5776 0x0F98, // 0F98 ; UNKNOWN
5777 0x0F99, // 0F99..0FBC; TIBETAN
5778 0x0FBD, // 0FBD ; UNKNOWN
5779 0x0FBE, // 0FBE..0FCC; TIBETAN
5780 0x0FCD, // 0FCD ; UNKNOWN
5781 0x0FCE, // 0FCE..0FD4; TIBETAN
5782 0x0FD5, // 0FD5..0FD8; COMMON
5783 0x0FD9, // 0FD9..0FDA; TIBETAN
5784 0x0FDB, // 0FDB..0FFF; UNKNOWN
5785 0x1000, // 1000..109F; MYANMAR
5786 0x10A0, // 10A0..10C5; GEORGIAN
5787 0x10C6, // 10C6 ; UNKNOWN
5788 0x10C7, // 10C7 ; GEORGIAN
5789 0x10C8, // 10C8..10CC; UNKNOWN
5790 0x10CD, // 10CD ; GEORGIAN
5791 0x10CE, // 10CE..10CF; UNKNOWN
5792 0x10D0, // 10D0..10FA; GEORGIAN
5793 0x10FB, // 10FB ; COMMON
5794 0x10FC, // 10FC..10FF; GEORGIAN
5795 0x1100, // 1100..11FF; HANGUL
5796 0x1200, // 1200..1248; ETHIOPIC
5797 0x1249, // 1249 ; UNKNOWN
5798 0x124A, // 124A..124D; ETHIOPIC
5799 0x124E, // 124E..124F; UNKNOWN
5800 0x1250, // 1250..1256; ETHIOPIC
5801 0x1257, // 1257 ; UNKNOWN
5802 0x1258, // 1258 ; ETHIOPIC
5803 0x1259, // 1259 ; UNKNOWN
5804 0x125A, // 125A..125D; ETHIOPIC
5805 0x125E, // 125E..125F; UNKNOWN
5806 0x1260, // 1260..1288; ETHIOPIC
5807 0x1289, // 1289 ; UNKNOWN
5808 0x128A, // 128A..128D; ETHIOPIC
5809 0x128E, // 128E..128F; UNKNOWN
5810 0x1290, // 1290..12B0; ETHIOPIC
5811 0x12B1, // 12B1 ; UNKNOWN
5812 0x12B2, // 12B2..12B5; ETHIOPIC
5813 0x12B6, // 12B6..12B7; UNKNOWN
5814 0x12B8, // 12B8..12BE; ETHIOPIC
5815 0x12BF, // 12BF ; UNKNOWN
5816 0x12C0, // 12C0 ; ETHIOPIC
5817 0x12C1, // 12C1 ; UNKNOWN
5818 0x12C2, // 12C2..12C5; ETHIOPIC
5819 0x12C6, // 12C6..12C7; UNKNOWN
5820 0x12C8, // 12C8..12D6; ETHIOPIC
5821 0x12D7, // 12D7 ; UNKNOWN
5822 0x12D8, // 12D8..1310; ETHIOPIC
5823 0x1311, // 1311 ; UNKNOWN
5824 0x1312, // 1312..1315; ETHIOPIC
5825 0x1316, // 1316..1317; UNKNOWN
5826 0x1318, // 1318..135A; ETHIOPIC
5827 0x135B, // 135B..135C; UNKNOWN
5828 0x135D, // 135D..137C; ETHIOPIC
5829 0x137D, // 137D..137F; UNKNOWN
5830 0x1380, // 1380..1399; ETHIOPIC
5831 0x139A, // 139A..139F; UNKNOWN
5832 0x13A0, // 13A0..13F5; CHEROKEE
5833 0x13F6, // 13F6..13F7; UNKNOWN
5834 0x13F8, // 13F8..13FD; CHEROKEE
5835 0x13FE, // 13FE..13FF; UNKNOWN
5836 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5837 0x1680, // 1680..169C; OGHAM
5838 0x169D, // 169D..169F; UNKNOWN
5839 0x16A0, // 16A0..16EA; RUNIC
5840 0x16EB, // 16EB..16ED; COMMON
5841 0x16EE, // 16EE..16F8; RUNIC
5842 0x16F9, // 16F9..16FF; UNKNOWN
5843 0x1700, // 1700..1715; TAGALOG
5844 0x1716, // 1716..171E; UNKNOWN
5845 0x171F, // 171F ; TAGALOG
5846 0x1720, // 1720..1734; HANUNOO
5847 0x1735, // 1735..1736; COMMON
5848 0x1737, // 1737..173F; UNKNOWN
5849 0x1740, // 1740..1753; BUHID
5850 0x1754, // 1754..175F; UNKNOWN
5851 0x1760, // 1760..176C; TAGBANWA
5852 0x176D, // 176D ; UNKNOWN
5853 0x176E, // 176E..1770; TAGBANWA
5854 0x1771, // 1771 ; UNKNOWN
5855 0x1772, // 1772..1773; TAGBANWA
5856 0x1774, // 1774..177F; UNKNOWN
5857 0x1780, // 1780..17DD; KHMER
5858 0x17DE, // 17DE..17DF; UNKNOWN
5859 0x17E0, // 17E0..17E9; KHMER
5860 0x17EA, // 17EA..17EF; UNKNOWN
5861 0x17F0, // 17F0..17F9; KHMER
5862 0x17FA, // 17FA..17FF; UNKNOWN
5863 0x1800, // 1800..1801; MONGOLIAN
5864 0x1802, // 1802..1803; COMMON
5865 0x1804, // 1804 ; MONGOLIAN
5866 0x1805, // 1805 ; COMMON
5867 0x1806, // 1806..1819; MONGOLIAN
5868 0x181A, // 181A..181F; UNKNOWN
5869 0x1820, // 1820..1878; MONGOLIAN
5870 0x1879, // 1879..187F; UNKNOWN
5871 0x1880, // 1880..18AA; MONGOLIAN
5872 0x18AB, // 18AB..18AF; UNKNOWN
5873 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
5874 0x18F6, // 18F6..18FF; UNKNOWN
5875 0x1900, // 1900..191E; LIMBU
5876 0x191F, // 191F ; UNKNOWN
5877 0x1920, // 1920..192B; LIMBU
5878 0x192C, // 192C..192F; UNKNOWN
5879 0x1930, // 1930..193B; LIMBU
5880 0x193C, // 193C..193F; UNKNOWN
5881 0x1940, // 1940 ; LIMBU
5882 0x1941, // 1941..1943; UNKNOWN
5883 0x1944, // 1944..194F; LIMBU
5884 0x1950, // 1950..196D; TAI_LE
5885 0x196E, // 196E..196F; UNKNOWN
5886 0x1970, // 1970..1974; TAI_LE
5887 0x1975, // 1975..197F; UNKNOWN
5888 0x1980, // 1980..19AB; NEW_TAI_LUE
5889 0x19AC, // 19AC..19AF; UNKNOWN
5890 0x19B0, // 19B0..19C9; NEW_TAI_LUE
5891 0x19CA, // 19CA..19CF; UNKNOWN
5892 0x19D0, // 19D0..19DA; NEW_TAI_LUE
5893 0x19DB, // 19DB..19DD; UNKNOWN
5894 0x19DE, // 19DE..19DF; NEW_TAI_LUE
5895 0x19E0, // 19E0..19FF; KHMER
5896 0x1A00, // 1A00..1A1B; BUGINESE
5897 0x1A1C, // 1A1C..1A1D; UNKNOWN
5898 0x1A1E, // 1A1E..1A1F; BUGINESE
5899 0x1A20, // 1A20..1A5E; TAI_THAM
5900 0x1A5F, // 1A5F ; UNKNOWN
5901 0x1A60, // 1A60..1A7C; TAI_THAM
5902 0x1A7D, // 1A7D..1A7E; UNKNOWN
5903 0x1A7F, // 1A7F..1A89; TAI_THAM
5904 0x1A8A, // 1A8A..1A8F; UNKNOWN
5905 0x1A90, // 1A90..1A99; TAI_THAM
5906 0x1A9A, // 1A9A..1A9F; UNKNOWN
5907 0x1AA0, // 1AA0..1AAD; TAI_THAM
5908 0x1AAE, // 1AAE..1AAF; UNKNOWN
5909 0x1AB0, // 1AB0..1ACE; INHERITED
5910 0x1ACF, // 1ACF..1AFF; UNKNOWN
5911 0x1B00, // 1B00..1B4C; BALINESE
5912 0x1B4D, // 1B4D..1B4F; UNKNOWN
5913 0x1B50, // 1B50..1B7E; BALINESE
5914 0x1B7F, // 1B7F ; UNKNOWN
5915 0x1B80, // 1B80..1BBF; SUNDANESE
5916 0x1BC0, // 1BC0..1BF3; BATAK
5917 0x1BF4, // 1BF4..1BFB; UNKNOWN
5918 0x1BFC, // 1BFC..1BFF; BATAK
5919 0x1C00, // 1C00..1C37; LEPCHA
5920 0x1C38, // 1C38..1C3A; UNKNOWN
5921 0x1C3B, // 1C3B..1C49; LEPCHA
5922 0x1C4A, // 1C4A..1C4C; UNKNOWN
5923 0x1C4D, // 1C4D..1C4F; LEPCHA
5924 0x1C50, // 1C50..1C7F; OL_CHIKI
5925 0x1C80, // 1C80..1C88; CYRILLIC
5926 0x1C89, // 1C89..1C8F; UNKNOWN
5927 0x1C90, // 1C90..1CBA; GEORGIAN
5928 0x1CBB, // 1CBB..1CBC; UNKNOWN
5929 0x1CBD, // 1CBD..1CBF; GEORGIAN
5930 0x1CC0, // 1CC0..1CC7; SUNDANESE
5931 0x1CC8, // 1CC8..1CCF; UNKNOWN
5932 0x1CD0, // 1CD0..1CD2; INHERITED
5933 0x1CD3, // 1CD3 ; COMMON
5934 0x1CD4, // 1CD4..1CE0; INHERITED
5935 0x1CE1, // 1CE1 ; COMMON
5936 0x1CE2, // 1CE2..1CE8; INHERITED
5937 0x1CE9, // 1CE9..1CEC; COMMON
5938 0x1CED, // 1CED ; INHERITED
5939 0x1CEE, // 1CEE..1CF3; COMMON
5940 0x1CF4, // 1CF4 ; INHERITED
5941 0x1CF5, // 1CF5..1CF7; COMMON
5942 0x1CF8, // 1CF8..1CF9; INHERITED
5943 0x1CFA, // 1CFA ; COMMON
5944 0x1CFB, // 1CFB..1CFF; UNKNOWN
5945 0x1D00, // 1D00..1D25; LATIN
5946 0x1D26, // 1D26..1D2A; GREEK
5947 0x1D2B, // 1D2B ; CYRILLIC
5948 0x1D2C, // 1D2C..1D5C; LATIN
5949 0x1D5D, // 1D5D..1D61; GREEK
5950 0x1D62, // 1D62..1D65; LATIN
5951 0x1D66, // 1D66..1D6A; GREEK
5952 0x1D6B, // 1D6B..1D77; LATIN
5953 0x1D78, // 1D78 ; CYRILLIC
5954 0x1D79, // 1D79..1DBE; LATIN
5955 0x1DBF, // 1DBF ; GREEK
5956 0x1DC0, // 1DC0..1DFF; INHERITED
5957 0x1E00, // 1E00..1EFF; LATIN
5958 0x1F00, // 1F00..1F15; GREEK
5959 0x1F16, // 1F16..1F17; UNKNOWN
5960 0x1F18, // 1F18..1F1D; GREEK
5961 0x1F1E, // 1F1E..1F1F; UNKNOWN
5962 0x1F20, // 1F20..1F45; GREEK
5963 0x1F46, // 1F46..1F47; UNKNOWN
5964 0x1F48, // 1F48..1F4D; GREEK
5965 0x1F4E, // 1F4E..1F4F; UNKNOWN
5966 0x1F50, // 1F50..1F57; GREEK
5967 0x1F58, // 1F58 ; UNKNOWN
5968 0x1F59, // 1F59 ; GREEK
5969 0x1F5A, // 1F5A ; UNKNOWN
5970 0x1F5B, // 1F5B ; GREEK
5971 0x1F5C, // 1F5C ; UNKNOWN
5972 0x1F5D, // 1F5D ; GREEK
5973 0x1F5E, // 1F5E ; UNKNOWN
5974 0x1F5F, // 1F5F..1F7D; GREEK
5975 0x1F7E, // 1F7E..1F7F; UNKNOWN
5976 0x1F80, // 1F80..1FB4; GREEK
5977 0x1FB5, // 1FB5 ; UNKNOWN
5978 0x1FB6, // 1FB6..1FC4; GREEK
5979 0x1FC5, // 1FC5 ; UNKNOWN
5980 0x1FC6, // 1FC6..1FD3; GREEK
5981 0x1FD4, // 1FD4..1FD5; UNKNOWN
5982 0x1FD6, // 1FD6..1FDB; GREEK
5983 0x1FDC, // 1FDC ; UNKNOWN
5984 0x1FDD, // 1FDD..1FEF; GREEK
5985 0x1FF0, // 1FF0..1FF1; UNKNOWN
5986 0x1FF2, // 1FF2..1FF4; GREEK
5987 0x1FF5, // 1FF5 ; UNKNOWN
5988 0x1FF6, // 1FF6..1FFE; GREEK
5989 0x1FFF, // 1FFF ; UNKNOWN
5990 0x2000, // 2000..200B; COMMON
5991 0x200C, // 200C..200D; INHERITED
5992 0x200E, // 200E..2064; COMMON
5993 0x2065, // 2065 ; UNKNOWN
5994 0x2066, // 2066..2070; COMMON
5995 0x2071, // 2071 ; LATIN
5996 0x2072, // 2072..2073; UNKNOWN
5997 0x2074, // 2074..207E; COMMON
5998 0x207F, // 207F ; LATIN
5999 0x2080, // 2080..208E; COMMON
6000 0x208F, // 208F ; UNKNOWN
6001 0x2090, // 2090..209C; LATIN
6002 0x209D, // 209D..209F; UNKNOWN
6003 0x20A0, // 20A0..20C0; COMMON
6004 0x20C1, // 20C1..20CF; UNKNOWN
6005 0x20D0, // 20D0..20F0; INHERITED
6006 0x20F1, // 20F1..20FF; UNKNOWN
6007 0x2100, // 2100..2125; COMMON
6008 0x2126, // 2126 ; GREEK
6009 0x2127, // 2127..2129; COMMON
6010 0x212A, // 212A..212B; LATIN
6011 0x212C, // 212C..2131; COMMON
6012 0x2132, // 2132 ; LATIN
6013 0x2133, // 2133..214D; COMMON
6014 0x214E, // 214E ; LATIN
6015 0x214F, // 214F..215F; COMMON
6016 0x2160, // 2160..2188; LATIN
6017 0x2189, // 2189..218B; COMMON
6018 0x218C, // 218C..218F; UNKNOWN
6019 0x2190, // 2190..2426; COMMON
6020 0x2427, // 2427..243F; UNKNOWN
6021 0x2440, // 2440..244A; COMMON
6022 0x244B, // 244B..245F; UNKNOWN
6023 0x2460, // 2460..27FF; COMMON
6024 0x2800, // 2800..28FF; BRAILLE
6025 0x2900, // 2900..2B73; COMMON
6026 0x2B74, // 2B74..2B75; UNKNOWN
6027 0x2B76, // 2B76..2B95; COMMON
6028 0x2B96, // 2B96 ; UNKNOWN
6029 0x2B97, // 2B97..2BFF; COMMON
6030 0x2C00, // 2C00..2C5F; GLAGOLITIC
6031 0x2C60, // 2C60..2C7F; LATIN
6032 0x2C80, // 2C80..2CF3; COPTIC
6033 0x2CF4, // 2CF4..2CF8; UNKNOWN
6034 0x2CF9, // 2CF9..2CFF; COPTIC
6035 0x2D00, // 2D00..2D25; GEORGIAN
6036 0x2D26, // 2D26 ; UNKNOWN
6037 0x2D27, // 2D27 ; GEORGIAN
6038 0x2D28, // 2D28..2D2C; UNKNOWN
6039 0x2D2D, // 2D2D ; GEORGIAN
6040 0x2D2E, // 2D2E..2D2F; UNKNOWN
6041 0x2D30, // 2D30..2D67; TIFINAGH
6042 0x2D68, // 2D68..2D6E; UNKNOWN
6043 0x2D6F, // 2D6F..2D70; TIFINAGH
6044 0x2D71, // 2D71..2D7E; UNKNOWN
6045 0x2D7F, // 2D7F ; TIFINAGH
6046 0x2D80, // 2D80..2D96; ETHIOPIC
6047 0x2D97, // 2D97..2D9F; UNKNOWN
6048 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6049 0x2DA7, // 2DA7 ; UNKNOWN
6050 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6051 0x2DAF, // 2DAF ; UNKNOWN
6052 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6053 0x2DB7, // 2DB7 ; UNKNOWN
6054 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6055 0x2DBF, // 2DBF ; UNKNOWN
6056 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6057 0x2DC7, // 2DC7 ; UNKNOWN
6058 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6059 0x2DCF, // 2DCF ; UNKNOWN
6060 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6061 0x2DD7, // 2DD7 ; UNKNOWN
6062 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6063 0x2DDF, // 2DDF ; UNKNOWN
6064 0x2DE0, // 2DE0..2DFF; CYRILLIC
6065 0x2E00, // 2E00..2E5D; COMMON
6066 0x2E5E, // 2E5E..2E7F; UNKNOWN
6067 0x2E80, // 2E80..2E99; HAN
6068 0x2E9A, // 2E9A ; UNKNOWN
6069 0x2E9B, // 2E9B..2EF3; HAN
6070 0x2EF4, // 2EF4..2EFF; UNKNOWN
6071 0x2F00, // 2F00..2FD5; HAN
6072 0x2FD6, // 2FD6..2FEF; UNKNOWN
6073 0x2FF0, // 2FF0..3004; COMMON
6074 0x3005, // 3005 ; HAN
6075 0x3006, // 3006 ; COMMON
6076 0x3007, // 3007 ; HAN
6077 0x3008, // 3008..3020; COMMON
6078 0x3021, // 3021..3029; HAN
6079 0x302A, // 302A..302D; INHERITED
6080 0x302E, // 302E..302F; HANGUL
6081 0x3030, // 3030..3037; COMMON
6082 0x3038, // 3038..303B; HAN
6083 0x303C, // 303C..303F; COMMON
6084 0x3040, // 3040 ; UNKNOWN
6085 0x3041, // 3041..3096; HIRAGANA
6086 0x3097, // 3097..3098; UNKNOWN
6087 0x3099, // 3099..309A; INHERITED
6088 0x309B, // 309B..309C; COMMON
6089 0x309D, // 309D..309F; HIRAGANA
6090 0x30A0, // 30A0 ; COMMON
6091 0x30A1, // 30A1..30FA; KATAKANA
6092 0x30FB, // 30FB..30FC; COMMON
6093 0x30FD, // 30FD..30FF; KATAKANA
6094 0x3100, // 3100..3104; UNKNOWN
6095 0x3105, // 3105..312F; BOPOMOFO
6096 0x3130, // 3130 ; UNKNOWN
6097 0x3131, // 3131..318E; HANGUL
6098 0x318F, // 318F ; UNKNOWN
6099 0x3190, // 3190..319F; COMMON
6100 0x31A0, // 31A0..31BF; BOPOMOFO
6101 0x31C0, // 31C0..31E3; COMMON
6102 0x31E4, // 31E4..31EE; UNKNOWN
6103 0x31EF, // 31EF ; COMMON
6104 0x31F0, // 31F0..31FF; KATAKANA
6105 0x3200, // 3200..321E; HANGUL
6106 0x321F, // 321F ; UNKNOWN
6107 0x3220, // 3220..325F; COMMON
6108 0x3260, // 3260..327E; HANGUL
6109 0x327F, // 327F..32CF; COMMON
6110 0x32D0, // 32D0..32FE; KATAKANA
6111 0x32FF, // 32FF ; COMMON
6112 0x3300, // 3300..3357; KATAKANA
6113 0x3358, // 3358..33FF; COMMON
6114 0x3400, // 3400..4DBF; HAN
6115 0x4DC0, // 4DC0..4DFF; COMMON
6116 0x4E00, // 4E00..9FFF; HAN
6117 0xA000, // A000..A48C; YI
6118 0xA48D, // A48D..A48F; UNKNOWN
6119 0xA490, // A490..A4C6; YI
6120 0xA4C7, // A4C7..A4CF; UNKNOWN
6121 0xA4D0, // A4D0..A4FF; LISU
6122 0xA500, // A500..A62B; VAI
6123 0xA62C, // A62C..A63F; UNKNOWN
6124 0xA640, // A640..A69F; CYRILLIC
6125 0xA6A0, // A6A0..A6F7; BAMUM
6126 0xA6F8, // A6F8..A6FF; UNKNOWN
6127 0xA700, // A700..A721; COMMON
6128 0xA722, // A722..A787; LATIN
6129 0xA788, // A788..A78A; COMMON
6130 0xA78B, // A78B..A7CA; LATIN
6131 0xA7CB, // A7CB..A7CF; UNKNOWN
6132 0xA7D0, // A7D0..A7D1; LATIN
6133 0xA7D2, // A7D2 ; UNKNOWN
6134 0xA7D3, // A7D3 ; LATIN
6135 0xA7D4, // A7D4 ; UNKNOWN
6136 0xA7D5, // A7D5..A7D9; LATIN
6137 0xA7DA, // A7DA..A7F1; UNKNOWN
6138 0xA7F2, // A7F2..A7FF; LATIN
6139 0xA800, // A800..A82C; SYLOTI_NAGRI
6140 0xA82D, // A82D..A82F; UNKNOWN
6141 0xA830, // A830..A839; COMMON
6142 0xA83A, // A83A..A83F; UNKNOWN
6143 0xA840, // A840..A877; PHAGS_PA
6144 0xA878, // A878..A87F; UNKNOWN
6145 0xA880, // A880..A8C5; SAURASHTRA
6146 0xA8C6, // A8C6..A8CD; UNKNOWN
6147 0xA8CE, // A8CE..A8D9; SAURASHTRA
6148 0xA8DA, // A8DA..A8DF; UNKNOWN
6149 0xA8E0, // A8E0..A8FF; DEVANAGARI
6150 0xA900, // A900..A92D; KAYAH_LI
6151 0xA92E, // A92E ; COMMON
6152 0xA92F, // A92F ; KAYAH_LI
6153 0xA930, // A930..A953; REJANG
6154 0xA954, // A954..A95E; UNKNOWN
6155 0xA95F, // A95F ; REJANG
6156 0xA960, // A960..A97C; HANGUL
6157 0xA97D, // A97D..A97F; UNKNOWN
6158 0xA980, // A980..A9CD; JAVANESE
6159 0xA9CE, // A9CE ; UNKNOWN
6160 0xA9CF, // A9CF ; COMMON
6161 0xA9D0, // A9D0..A9D9; JAVANESE
6162 0xA9DA, // A9DA..A9DD; UNKNOWN
6163 0xA9DE, // A9DE..A9DF; JAVANESE
6164 0xA9E0, // A9E0..A9FE; MYANMAR
6165 0xA9FF, // A9FF ; UNKNOWN
6166 0xAA00, // AA00..AA36; CHAM
6167 0xAA37, // AA37..AA3F; UNKNOWN
6168 0xAA40, // AA40..AA4D; CHAM
6169 0xAA4E, // AA4E..AA4F; UNKNOWN
6170 0xAA50, // AA50..AA59; CHAM
6171 0xAA5A, // AA5A..AA5B; UNKNOWN
6172 0xAA5C, // AA5C..AA5F; CHAM
6173 0xAA60, // AA60..AA7F; MYANMAR
6174 0xAA80, // AA80..AAC2; TAI_VIET
6175 0xAAC3, // AAC3..AADA; UNKNOWN
6176 0xAADB, // AADB..AADF; TAI_VIET
6177 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6178 0xAAF7, // AAF7..AB00; UNKNOWN
6179 0xAB01, // AB01..AB06; ETHIOPIC
6180 0xAB07, // AB07..AB08; UNKNOWN
6181 0xAB09, // AB09..AB0E; ETHIOPIC
6182 0xAB0F, // AB0F..AB10; UNKNOWN
6183 0xAB11, // AB11..AB16; ETHIOPIC
6184 0xAB17, // AB17..AB1F; UNKNOWN
6185 0xAB20, // AB20..AB26; ETHIOPIC
6186 0xAB27, // AB27 ; UNKNOWN
6187 0xAB28, // AB28..AB2E; ETHIOPIC
6188 0xAB2F, // AB2F ; UNKNOWN
6189 0xAB30, // AB30..AB5A; LATIN
6190 0xAB5B, // AB5B ; COMMON
6191 0xAB5C, // AB5C..AB64; LATIN
6192 0xAB65, // AB65 ; GREEK
6193 0xAB66, // AB66..AB69; LATIN
6194 0xAB6A, // AB6A..AB6B; COMMON
6195 0xAB6C, // AB6C..AB6F; UNKNOWN
6196 0xAB70, // AB70..ABBF; CHEROKEE
6197 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6198 0xABEE, // ABEE..ABEF; UNKNOWN
6199 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6200 0xABFA, // ABFA..ABFF; UNKNOWN
6201 0xAC00, // AC00..D7A3; HANGUL
6202 0xD7A4, // D7A4..D7AF; UNKNOWN
6203 0xD7B0, // D7B0..D7C6; HANGUL
6204 0xD7C7, // D7C7..D7CA; UNKNOWN
6205 0xD7CB, // D7CB..D7FB; HANGUL
6206 0xD7FC, // D7FC..F8FF; UNKNOWN
6207 0xF900, // F900..FA6D; HAN
6208 0xFA6E, // FA6E..FA6F; UNKNOWN
6209 0xFA70, // FA70..FAD9; HAN
6210 0xFADA, // FADA..FAFF; UNKNOWN
6211 0xFB00, // FB00..FB06; LATIN
6212 0xFB07, // FB07..FB12; UNKNOWN
6213 0xFB13, // FB13..FB17; ARMENIAN
6214 0xFB18, // FB18..FB1C; UNKNOWN
6215 0xFB1D, // FB1D..FB36; HEBREW
6216 0xFB37, // FB37 ; UNKNOWN
6217 0xFB38, // FB38..FB3C; HEBREW
6218 0xFB3D, // FB3D ; UNKNOWN
6219 0xFB3E, // FB3E ; HEBREW
6220 0xFB3F, // FB3F ; UNKNOWN
6221 0xFB40, // FB40..FB41; HEBREW
6222 0xFB42, // FB42 ; UNKNOWN
6223 0xFB43, // FB43..FB44; HEBREW
6224 0xFB45, // FB45 ; UNKNOWN
6225 0xFB46, // FB46..FB4F; HEBREW
6226 0xFB50, // FB50..FBC2; ARABIC
6227 0xFBC3, // FBC3..FBD2; UNKNOWN
6228 0xFBD3, // FBD3..FD3D; ARABIC
6229 0xFD3E, // FD3E..FD3F; COMMON
6230 0xFD40, // FD40..FD8F; ARABIC
6231 0xFD90, // FD90..FD91; UNKNOWN
6232 0xFD92, // FD92..FDC7; ARABIC
6233 0xFDC8, // FDC8..FDCE; UNKNOWN
6234 0xFDCF, // FDCF ; ARABIC
6235 0xFDD0, // FDD0..FDEF; UNKNOWN
6236 0xFDF0, // FDF0..FDFF; ARABIC
6237 0xFE00, // FE00..FE0F; INHERITED
6238 0xFE10, // FE10..FE19; COMMON
6239 0xFE1A, // FE1A..FE1F; UNKNOWN
6240 0xFE20, // FE20..FE2D; INHERITED
6241 0xFE2E, // FE2E..FE2F; CYRILLIC
6242 0xFE30, // FE30..FE52; COMMON
6243 0xFE53, // FE53 ; UNKNOWN
6244 0xFE54, // FE54..FE66; COMMON
6245 0xFE67, // FE67 ; UNKNOWN
6246 0xFE68, // FE68..FE6B; COMMON
6247 0xFE6C, // FE6C..FE6F; UNKNOWN
6248 0xFE70, // FE70..FE74; ARABIC
6249 0xFE75, // FE75 ; UNKNOWN
6250 0xFE76, // FE76..FEFC; ARABIC
6251 0xFEFD, // FEFD..FEFE; UNKNOWN
6252 0xFEFF, // FEFF ; COMMON
6253 0xFF00, // FF00 ; UNKNOWN
6254 0xFF01, // FF01..FF20; COMMON
6255 0xFF21, // FF21..FF3A; LATIN
6256 0xFF3B, // FF3B..FF40; COMMON
6257 0xFF41, // FF41..FF5A; LATIN
6258 0xFF5B, // FF5B..FF65; COMMON
6259 0xFF66, // FF66..FF6F; KATAKANA
6260 0xFF70, // FF70 ; COMMON
6261 0xFF71, // FF71..FF9D; KATAKANA
6262 0xFF9E, // FF9E..FF9F; COMMON
6263 0xFFA0, // FFA0..FFBE; HANGUL
6264 0xFFBF, // FFBF..FFC1; UNKNOWN
6265 0xFFC2, // FFC2..FFC7; HANGUL
6266 0xFFC8, // FFC8..FFC9; UNKNOWN
6267 0xFFCA, // FFCA..FFCF; HANGUL
6268 0xFFD0, // FFD0..FFD1; UNKNOWN
6269 0xFFD2, // FFD2..FFD7; HANGUL
6270 0xFFD8, // FFD8..FFD9; UNKNOWN
6271 0xFFDA, // FFDA..FFDC; HANGUL
6272 0xFFDD, // FFDD..FFDF; UNKNOWN
6273 0xFFE0, // FFE0..FFE6; COMMON
6274 0xFFE7, // FFE7 ; UNKNOWN
6275 0xFFE8, // FFE8..FFEE; COMMON
6276 0xFFEF, // FFEF..FFF8; UNKNOWN
6277 0xFFF9, // FFF9..FFFD; COMMON
6278 0xFFFE, // FFFE..FFFF; UNKNOWN
6279 0x10000, // 10000..1000B; LINEAR_B
6280 0x1000C, // 1000C ; UNKNOWN
6281 0x1000D, // 1000D..10026; LINEAR_B
6282 0x10027, // 10027 ; UNKNOWN
6283 0x10028, // 10028..1003A; LINEAR_B
6284 0x1003B, // 1003B ; UNKNOWN
6285 0x1003C, // 1003C..1003D; LINEAR_B
6286 0x1003E, // 1003E ; UNKNOWN
6287 0x1003F, // 1003F..1004D; LINEAR_B
6288 0x1004E, // 1004E..1004F; UNKNOWN
6289 0x10050, // 10050..1005D; LINEAR_B
6290 0x1005E, // 1005E..1007F; UNKNOWN
6291 0x10080, // 10080..100FA; LINEAR_B
6292 0x100FB, // 100FB..100FF; UNKNOWN
6293 0x10100, // 10100..10102; COMMON
6294 0x10103, // 10103..10106; UNKNOWN
6295 0x10107, // 10107..10133; COMMON
6296 0x10134, // 10134..10136; UNKNOWN
6297 0x10137, // 10137..1013F; COMMON
6298 0x10140, // 10140..1018E; GREEK
6299 0x1018F, // 1018F ; UNKNOWN
6300 0x10190, // 10190..1019C; COMMON
6301 0x1019D, // 1019D..1019F; UNKNOWN
6302 0x101A0, // 101A0 ; GREEK
6303 0x101A1, // 101A1..101CF; UNKNOWN
6304 0x101D0, // 101D0..101FC; COMMON
6305 0x101FD, // 101FD ; INHERITED
6306 0x101FE, // 101FE..1027F; UNKNOWN
6307 0x10280, // 10280..1029C; LYCIAN
6308 0x1029D, // 1029D..1029F; UNKNOWN
6309 0x102A0, // 102A0..102D0; CARIAN
6310 0x102D1, // 102D1..102DF; UNKNOWN
6311 0x102E0, // 102E0 ; INHERITED
6312 0x102E1, // 102E1..102FB; COMMON
6313 0x102FC, // 102FC..102FF; UNKNOWN
6314 0x10300, // 10300..10323; OLD_ITALIC
6315 0x10324, // 10324..1032C; UNKNOWN
6316 0x1032D, // 1032D..1032F; OLD_ITALIC
6317 0x10330, // 10330..1034A; GOTHIC
6318 0x1034B, // 1034B..1034F; UNKNOWN
6319 0x10350, // 10350..1037A; OLD_PERMIC
6320 0x1037B, // 1037B..1037F; UNKNOWN
6321 0x10380, // 10380..1039D; UGARITIC
6322 0x1039E, // 1039E ; UNKNOWN
6323 0x1039F, // 1039F ; UGARITIC
6324 0x103A0, // 103A0..103C3; OLD_PERSIAN
6325 0x103C4, // 103C4..103C7; UNKNOWN
6326 0x103C8, // 103C8..103D5; OLD_PERSIAN
6327 0x103D6, // 103D6..103FF; UNKNOWN
6328 0x10400, // 10400..1044F; DESERET
6329 0x10450, // 10450..1047F; SHAVIAN
6330 0x10480, // 10480..1049D; OSMANYA
6331 0x1049E, // 1049E..1049F; UNKNOWN
6332 0x104A0, // 104A0..104A9; OSMANYA
6333 0x104AA, // 104AA..104AF; UNKNOWN
6334 0x104B0, // 104B0..104D3; OSAGE
6335 0x104D4, // 104D4..104D7; UNKNOWN
6336 0x104D8, // 104D8..104FB; OSAGE
6337 0x104FC, // 104FC..104FF; UNKNOWN
6338 0x10500, // 10500..10527; ELBASAN
6339 0x10528, // 10528..1052F; UNKNOWN
6340 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6341 0x10564, // 10564..1056E; UNKNOWN
6342 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6343 0x10570, // 10570..1057A; VITHKUQI
6344 0x1057B, // 1057B ; UNKNOWN
6345 0x1057C, // 1057C..1058A; VITHKUQI
6346 0x1058B, // 1058B ; UNKNOWN
6347 0x1058C, // 1058C..10592; VITHKUQI
6348 0x10593, // 10593 ; UNKNOWN
6349 0x10594, // 10594..10595; VITHKUQI
6350 0x10596, // 10596 ; UNKNOWN
6351 0x10597, // 10597..105A1; VITHKUQI
6352 0x105A2, // 105A2 ; UNKNOWN
6353 0x105A3, // 105A3..105B1; VITHKUQI
6354 0x105B2, // 105B2 ; UNKNOWN
6355 0x105B3, // 105B3..105B9; VITHKUQI
6356 0x105BA, // 105BA ; UNKNOWN
6357 0x105BB, // 105BB..105BC; VITHKUQI
6358 0x105BD, // 105BD..105FF; UNKNOWN
6359 0x10600, // 10600..10736; LINEAR_A
6360 0x10737, // 10737..1073F; UNKNOWN
6361 0x10740, // 10740..10755; LINEAR_A
6362 0x10756, // 10756..1075F; UNKNOWN
6363 0x10760, // 10760..10767; LINEAR_A
6364 0x10768, // 10768..1077F; UNKNOWN
6365 0x10780, // 10780..10785; LATIN
6366 0x10786, // 10786 ; UNKNOWN
6367 0x10787, // 10787..107B0; LATIN
6368 0x107B1, // 107B1 ; UNKNOWN
6369 0x107B2, // 107B2..107BA; LATIN
6370 0x107BB, // 107BB..107FF; UNKNOWN
6371 0x10800, // 10800..10805; CYPRIOT
6372 0x10806, // 10806..10807; UNKNOWN
6373 0x10808, // 10808 ; CYPRIOT
6374 0x10809, // 10809 ; UNKNOWN
6375 0x1080A, // 1080A..10835; CYPRIOT
6376 0x10836, // 10836 ; UNKNOWN
6377 0x10837, // 10837..10838; CYPRIOT
6378 0x10839, // 10839..1083B; UNKNOWN
6379 0x1083C, // 1083C ; CYPRIOT
6380 0x1083D, // 1083D..1083E; UNKNOWN
6381 0x1083F, // 1083F ; CYPRIOT
6382 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6383 0x10856, // 10856 ; UNKNOWN
6384 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6385 0x10860, // 10860..1087F; PALMYRENE
6386 0x10880, // 10880..1089E; NABATAEAN
6387 0x1089F, // 1089F..108A6; UNKNOWN
6388 0x108A7, // 108A7..108AF; NABATAEAN
6389 0x108B0, // 108B0..108DF; UNKNOWN
6390 0x108E0, // 108E0..108F2; HATRAN
6391 0x108F3, // 108F3 ; UNKNOWN
6392 0x108F4, // 108F4..108F5; HATRAN
6393 0x108F6, // 108F6..108FA; UNKNOWN
6394 0x108FB, // 108FB..108FF; HATRAN
6395 0x10900, // 10900..1091B; PHOENICIAN
6396 0x1091C, // 1091C..1091E; UNKNOWN
6397 0x1091F, // 1091F ; PHOENICIAN
6398 0x10920, // 10920..10939; LYDIAN
6399 0x1093A, // 1093A..1093E; UNKNOWN
6400 0x1093F, // 1093F ; LYDIAN
6401 0x10940, // 10940..1097F; UNKNOWN
6402 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6403 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6404 0x109B8, // 109B8..109BB; UNKNOWN
6405 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6406 0x109D0, // 109D0..109D1; UNKNOWN
6407 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6408 0x10A00, // 10A00..10A03; KHAROSHTHI
6409 0x10A04, // 10A04 ; UNKNOWN
6410 0x10A05, // 10A05..10A06; KHAROSHTHI
6411 0x10A07, // 10A07..10A0B; UNKNOWN
6412 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6413 0x10A14, // 10A14 ; UNKNOWN
6414 0x10A15, // 10A15..10A17; KHAROSHTHI
6415 0x10A18, // 10A18 ; UNKNOWN
6416 0x10A19, // 10A19..10A35; KHAROSHTHI
6417 0x10A36, // 10A36..10A37; UNKNOWN
6418 0x10A38, // 10A38..10A3A; KHAROSHTHI
6419 0x10A3B, // 10A3B..10A3E; UNKNOWN
6420 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6421 0x10A49, // 10A49..10A4F; UNKNOWN
6422 0x10A50, // 10A50..10A58; KHAROSHTHI
6423 0x10A59, // 10A59..10A5F; UNKNOWN
6424 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6425 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6426 0x10AA0, // 10AA0..10ABF; UNKNOWN
6427 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6428 0x10AE7, // 10AE7..10AEA; UNKNOWN
6429 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6430 0x10AF7, // 10AF7..10AFF; UNKNOWN
6431 0x10B00, // 10B00..10B35; AVESTAN
6432 0x10B36, // 10B36..10B38; UNKNOWN
6433 0x10B39, // 10B39..10B3F; AVESTAN
6434 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6435 0x10B56, // 10B56..10B57; UNKNOWN
6436 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6437 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6438 0x10B73, // 10B73..10B77; UNKNOWN
6439 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6440 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6441 0x10B92, // 10B92..10B98; UNKNOWN
6442 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6443 0x10B9D, // 10B9D..10BA8; UNKNOWN
6444 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6445 0x10BB0, // 10BB0..10BFF; UNKNOWN
6446 0x10C00, // 10C00..10C48; OLD_TURKIC
6447 0x10C49, // 10C49..10C7F; UNKNOWN
6448 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6449 0x10CB3, // 10CB3..10CBF; UNKNOWN
6450 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6451 0x10CF3, // 10CF3..10CF9; UNKNOWN
6452 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6453 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6454 0x10D28, // 10D28..10D2F; UNKNOWN
6455 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6456 0x10D3A, // 10D3A..10E5F; UNKNOWN
6457 0x10E60, // 10E60..10E7E; ARABIC
6458 0x10E7F, // 10E7F ; UNKNOWN
6459 0x10E80, // 10E80..10EA9; YEZIDI
6460 0x10EAA, // 10EAA ; UNKNOWN
6461 0x10EAB, // 10EAB..10EAD; YEZIDI
6462 0x10EAE, // 10EAE..10EAF; UNKNOWN
6463 0x10EB0, // 10EB0..10EB1; YEZIDI
6464 0x10EB2, // 10EB2..10EFC; UNKNOWN
6465 0x10EFD, // 10EFD..10EFF; ARABIC
6466 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6467 0x10F28, // 10F28..10F2F; UNKNOWN
6468 0x10F30, // 10F30..10F59; SOGDIAN
6469 0x10F5A, // 10F5A..10F6F; UNKNOWN
6470 0x10F70, // 10F70..10F89; OLD_UYGHUR
6471 0x10F8A, // 10F8A..10FAF; UNKNOWN
6472 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6473 0x10FCC, // 10FCC..10FDF; UNKNOWN
6474 0x10FE0, // 10FE0..10FF6; ELYMAIC
6475 0x10FF7, // 10FF7..10FFF; UNKNOWN
6476 0x11000, // 11000..1104D; BRAHMI
6477 0x1104E, // 1104E..11051; UNKNOWN
6478 0x11052, // 11052..11075; BRAHMI
6479 0x11076, // 11076..1107E; UNKNOWN
6480 0x1107F, // 1107F ; BRAHMI
6481 0x11080, // 11080..110C2; KAITHI
6482 0x110C3, // 110C3..110CC; UNKNOWN
6483 0x110CD, // 110CD ; KAITHI
6484 0x110CE, // 110CE..110CF; UNKNOWN
6485 0x110D0, // 110D0..110E8; SORA_SOMPENG
6486 0x110E9, // 110E9..110EF; UNKNOWN
6487 0x110F0, // 110F0..110F9; SORA_SOMPENG
6488 0x110FA, // 110FA..110FF; UNKNOWN
6489 0x11100, // 11100..11134; CHAKMA
6490 0x11135, // 11135 ; UNKNOWN
6491 0x11136, // 11136..11147; CHAKMA
6492 0x11148, // 11148..1114F; UNKNOWN
6493 0x11150, // 11150..11176; MAHAJANI
6494 0x11177, // 11177..1117F; UNKNOWN
6495 0x11180, // 11180..111DF; SHARADA
6496 0x111E0, // 111E0 ; UNKNOWN
6497 0x111E1, // 111E1..111F4; SINHALA
6498 0x111F5, // 111F5..111FF; UNKNOWN
6499 0x11200, // 11200..11211; KHOJKI
6500 0x11212, // 11212 ; UNKNOWN
6501 0x11213, // 11213..11241; KHOJKI
6502 0x11242, // 11242..1127F; UNKNOWN
6503 0x11280, // 11280..11286; MULTANI
6504 0x11287, // 11287 ; UNKNOWN
6505 0x11288, // 11288 ; MULTANI
6506 0x11289, // 11289 ; UNKNOWN
6507 0x1128A, // 1128A..1128D; MULTANI
6508 0x1128E, // 1128E ; UNKNOWN
6509 0x1128F, // 1128F..1129D; MULTANI
6510 0x1129E, // 1129E ; UNKNOWN
6511 0x1129F, // 1129F..112A9; MULTANI
6512 0x112AA, // 112AA..112AF; UNKNOWN
6513 0x112B0, // 112B0..112EA; KHUDAWADI
6514 0x112EB, // 112EB..112EF; UNKNOWN
6515 0x112F0, // 112F0..112F9; KHUDAWADI
6516 0x112FA, // 112FA..112FF; UNKNOWN
6517 0x11300, // 11300..11303; GRANTHA
6518 0x11304, // 11304 ; UNKNOWN
6519 0x11305, // 11305..1130C; GRANTHA
6520 0x1130D, // 1130D..1130E; UNKNOWN
6521 0x1130F, // 1130F..11310; GRANTHA
6522 0x11311, // 11311..11312; UNKNOWN
6523 0x11313, // 11313..11328; GRANTHA
6524 0x11329, // 11329 ; UNKNOWN
6525 0x1132A, // 1132A..11330; GRANTHA
6526 0x11331, // 11331 ; UNKNOWN
6527 0x11332, // 11332..11333; GRANTHA
6528 0x11334, // 11334 ; UNKNOWN
6529 0x11335, // 11335..11339; GRANTHA
6530 0x1133A, // 1133A ; UNKNOWN
6531 0x1133B, // 1133B ; INHERITED
6532 0x1133C, // 1133C..11344; GRANTHA
6533 0x11345, // 11345..11346; UNKNOWN
6534 0x11347, // 11347..11348; GRANTHA
6535 0x11349, // 11349..1134A; UNKNOWN
6536 0x1134B, // 1134B..1134D; GRANTHA
6537 0x1134E, // 1134E..1134F; UNKNOWN
6538 0x11350, // 11350 ; GRANTHA
6539 0x11351, // 11351..11356; UNKNOWN
6540 0x11357, // 11357 ; GRANTHA
6541 0x11358, // 11358..1135C; UNKNOWN
6542 0x1135D, // 1135D..11363; GRANTHA
6543 0x11364, // 11364..11365; UNKNOWN
6544 0x11366, // 11366..1136C; GRANTHA
6545 0x1136D, // 1136D..1136F; UNKNOWN
6546 0x11370, // 11370..11374; GRANTHA
6547 0x11375, // 11375..113FF; UNKNOWN
6548 0x11400, // 11400..1145B; NEWA
6549 0x1145C, // 1145C ; UNKNOWN
6550 0x1145D, // 1145D..11461; NEWA
6551 0x11462, // 11462..1147F; UNKNOWN
6552 0x11480, // 11480..114C7; TIRHUTA
6553 0x114C8, // 114C8..114CF; UNKNOWN
6554 0x114D0, // 114D0..114D9; TIRHUTA
6555 0x114DA, // 114DA..1157F; UNKNOWN
6556 0x11580, // 11580..115B5; SIDDHAM
6557 0x115B6, // 115B6..115B7; UNKNOWN
6558 0x115B8, // 115B8..115DD; SIDDHAM
6559 0x115DE, // 115DE..115FF; UNKNOWN
6560 0x11600, // 11600..11644; MODI
6561 0x11645, // 11645..1164F; UNKNOWN
6562 0x11650, // 11650..11659; MODI
6563 0x1165A, // 1165A..1165F; UNKNOWN
6564 0x11660, // 11660..1166C; MONGOLIAN
6565 0x1166D, // 1166D..1167F; UNKNOWN
6566 0x11680, // 11680..116B9; TAKRI
6567 0x116BA, // 116BA..116BF; UNKNOWN
6568 0x116C0, // 116C0..116C9; TAKRI
6569 0x116CA, // 116CA..116FF; UNKNOWN
6570 0x11700, // 11700..1171A; AHOM
6571 0x1171B, // 1171B..1171C; UNKNOWN
6572 0x1171D, // 1171D..1172B; AHOM
6573 0x1172C, // 1172C..1172F; UNKNOWN
6574 0x11730, // 11730..11746; AHOM
6575 0x11747, // 11747..117FF; UNKNOWN
6576 0x11800, // 11800..1183B; DOGRA
6577 0x1183C, // 1183C..1189F; UNKNOWN
6578 0x118A0, // 118A0..118F2; WARANG_CITI
6579 0x118F3, // 118F3..118FE; UNKNOWN
6580 0x118FF, // 118FF ; WARANG_CITI
6581 0x11900, // 11900..11906; DIVES_AKURU
6582 0x11907, // 11907..11908; UNKNOWN
6583 0x11909, // 11909 ; DIVES_AKURU
6584 0x1190A, // 1190A..1190B; UNKNOWN
6585 0x1190C, // 1190C..11913; DIVES_AKURU
6586 0x11914, // 11914 ; UNKNOWN
6587 0x11915, // 11915..11916; DIVES_AKURU
6588 0x11917, // 11917 ; UNKNOWN
6589 0x11918, // 11918..11935; DIVES_AKURU
6590 0x11936, // 11936 ; UNKNOWN
6591 0x11937, // 11937..11938; DIVES_AKURU
6592 0x11939, // 11939..1193A; UNKNOWN
6593 0x1193B, // 1193B..11946; DIVES_AKURU
6594 0x11947, // 11947..1194F; UNKNOWN
6595 0x11950, // 11950..11959; DIVES_AKURU
6596 0x1195A, // 1195A..1199F; UNKNOWN
6597 0x119A0, // 119A0..119A7; NANDINAGARI
6598 0x119A8, // 119A8..119A9; UNKNOWN
6599 0x119AA, // 119AA..119D7; NANDINAGARI
6600 0x119D8, // 119D8..119D9; UNKNOWN
6601 0x119DA, // 119DA..119E4; NANDINAGARI
6602 0x119E5, // 119E5..119FF; UNKNOWN
6603 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6604 0x11A48, // 11A48..11A4F; UNKNOWN
6605 0x11A50, // 11A50..11AA2; SOYOMBO
6606 0x11AA3, // 11AA3..11AAF; UNKNOWN
6607 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6608 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6609 0x11AF9, // 11AF9..11AFF; UNKNOWN
6610 0x11B00, // 11B00..11B09; DEVANAGARI
6611 0x11B0A, // 11B0A..11BFF; UNKNOWN
6612 0x11C00, // 11C00..11C08; BHAIKSUKI
6613 0x11C09, // 11C09 ; UNKNOWN
6614 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6615 0x11C37, // 11C37 ; UNKNOWN
6616 0x11C38, // 11C38..11C45; BHAIKSUKI
6617 0x11C46, // 11C46..11C4F; UNKNOWN
6618 0x11C50, // 11C50..11C6C; BHAIKSUKI
6619 0x11C6D, // 11C6D..11C6F; UNKNOWN
6620 0x11C70, // 11C70..11C8F; MARCHEN
6621 0x11C90, // 11C90..11C91; UNKNOWN
6622 0x11C92, // 11C92..11CA7; MARCHEN
6623 0x11CA8, // 11CA8 ; UNKNOWN
6624 0x11CA9, // 11CA9..11CB6; MARCHEN
6625 0x11CB7, // 11CB7..11CFF; UNKNOWN
6626 0x11D00, // 11D00..11D06; MASARAM_GONDI
6627 0x11D07, // 11D07 ; UNKNOWN
6628 0x11D08, // 11D08..11D09; MASARAM_GONDI
6629 0x11D0A, // 11D0A ; UNKNOWN
6630 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6631 0x11D37, // 11D37..11D39; UNKNOWN
6632 0x11D3A, // 11D3A ; MASARAM_GONDI
6633 0x11D3B, // 11D3B ; UNKNOWN
6634 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6635 0x11D3E, // 11D3E ; UNKNOWN
6636 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6637 0x11D48, // 11D48..11D4F; UNKNOWN
6638 0x11D50, // 11D50..11D59; MASARAM_GONDI
6639 0x11D5A, // 11D5A..11D5F; UNKNOWN
6640 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6641 0x11D66, // 11D66 ; UNKNOWN
6642 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6643 0x11D69, // 11D69 ; UNKNOWN
6644 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6645 0x11D8F, // 11D8F ; UNKNOWN
6646 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6647 0x11D92, // 11D92 ; UNKNOWN
6648 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6649 0x11D99, // 11D99..11D9F; UNKNOWN
6650 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6651 0x11DAA, // 11DAA..11EDF; UNKNOWN
6652 0x11EE0, // 11EE0..11EF8; MAKASAR
6653 0x11EF9, // 11EF9..11EFF; UNKNOWN
6654 0x11F00, // 11F00..11F10; KAWI
6655 0x11F11, // 11F11 ; UNKNOWN
6656 0x11F12, // 11F12..11F3A; KAWI
6657 0x11F3B, // 11F3B..11F3D; UNKNOWN
6658 0x11F3E, // 11F3E..11F59; KAWI
6659 0x11F5A, // 11F5A..11FAF; UNKNOWN
6660 0x11FB0, // 11FB0 ; LISU
6661 0x11FB1, // 11FB1..11FBF; UNKNOWN
6662 0x11FC0, // 11FC0..11FF1; TAMIL
6663 0x11FF2, // 11FF2..11FFE; UNKNOWN
6664 0x11FFF, // 11FFF ; TAMIL
6665 0x12000, // 12000..12399; CUNEIFORM
6666 0x1239A, // 1239A..123FF; UNKNOWN
6667 0x12400, // 12400..1246E; CUNEIFORM
6668 0x1246F, // 1246F ; UNKNOWN
6669 0x12470, // 12470..12474; CUNEIFORM
6670 0x12475, // 12475..1247F; UNKNOWN
6671 0x12480, // 12480..12543; CUNEIFORM
6672 0x12544, // 12544..12F8F; UNKNOWN
6673 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6674 0x12FF3, // 12FF3..12FFF; UNKNOWN
6675 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6676 0x13456, // 13456..143FF; UNKNOWN
6677 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6678 0x14647, // 14647..167FF; UNKNOWN
6679 0x16800, // 16800..16A38; BAMUM
6680 0x16A39, // 16A39..16A3F; UNKNOWN
6681 0x16A40, // 16A40..16A5E; MRO
6682 0x16A5F, // 16A5F ; UNKNOWN
6683 0x16A60, // 16A60..16A69; MRO
6684 0x16A6A, // 16A6A..16A6D; UNKNOWN
6685 0x16A6E, // 16A6E..16A6F; MRO
6686 0x16A70, // 16A70..16ABE; TANGSA
6687 0x16ABF, // 16ABF ; UNKNOWN
6688 0x16AC0, // 16AC0..16AC9; TANGSA
6689 0x16ACA, // 16ACA..16ACF; UNKNOWN
6690 0x16AD0, // 16AD0..16AED; BASSA_VAH
6691 0x16AEE, // 16AEE..16AEF; UNKNOWN
6692 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6693 0x16AF6, // 16AF6..16AFF; UNKNOWN
6694 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6695 0x16B46, // 16B46..16B4F; UNKNOWN
6696 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6697 0x16B5A, // 16B5A ; UNKNOWN
6698 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6699 0x16B62, // 16B62 ; UNKNOWN
6700 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6701 0x16B78, // 16B78..16B7C; UNKNOWN
6702 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6703 0x16B90, // 16B90..16E3F; UNKNOWN
6704 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6705 0x16E9B, // 16E9B..16EFF; UNKNOWN
6706 0x16F00, // 16F00..16F4A; MIAO
6707 0x16F4B, // 16F4B..16F4E; UNKNOWN
6708 0x16F4F, // 16F4F..16F87; MIAO
6709 0x16F88, // 16F88..16F8E; UNKNOWN
6710 0x16F8F, // 16F8F..16F9F; MIAO
6711 0x16FA0, // 16FA0..16FDF; UNKNOWN
6712 0x16FE0, // 16FE0 ; TANGUT
6713 0x16FE1, // 16FE1 ; NUSHU
6714 0x16FE2, // 16FE2..16FE3; HAN
6715 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
6716 0x16FE5, // 16FE5..16FEF; UNKNOWN
6717 0x16FF0, // 16FF0..16FF1; HAN
6718 0x16FF2, // 16FF2..16FFF; UNKNOWN
6719 0x17000, // 17000..187F7; TANGUT
6720 0x187F8, // 187F8..187FF; UNKNOWN
6721 0x18800, // 18800..18AFF; TANGUT
6722 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
6723 0x18CD6, // 18CD6..18CFF; UNKNOWN
6724 0x18D00, // 18D00..18D08; TANGUT
6725 0x18D09, // 18D09..1AFEF; UNKNOWN
6726 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
6727 0x1AFF4, // 1AFF4 ; UNKNOWN
6728 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
6729 0x1AFFC, // 1AFFC ; UNKNOWN
6730 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
6731 0x1AFFF, // 1AFFF ; UNKNOWN
6732 0x1B000, // 1B000 ; KATAKANA
6733 0x1B001, // 1B001..1B11F; HIRAGANA
6734 0x1B120, // 1B120..1B122; KATAKANA
6735 0x1B123, // 1B123..1B131; UNKNOWN
6736 0x1B132, // 1B132 ; HIRAGANA
6737 0x1B133, // 1B133..1B14F; UNKNOWN
6738 0x1B150, // 1B150..1B152; HIRAGANA
6739 0x1B153, // 1B153..1B154; UNKNOWN
6740 0x1B155, // 1B155 ; KATAKANA
6741 0x1B156, // 1B156..1B163; UNKNOWN
6742 0x1B164, // 1B164..1B167; KATAKANA
6743 0x1B168, // 1B168..1B16F; UNKNOWN
6744 0x1B170, // 1B170..1B2FB; NUSHU
6745 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6746 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6747 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6748 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6749 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6750 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6751 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6752 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6753 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6754 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6755 0x1BCA0, // 1BCA0..1BCA3; COMMON
6756 0x1BCA4, // 1BCA4..1CEFF; UNKNOWN
6757 0x1CF00, // 1CF00..1CF2D; INHERITED
6758 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
6759 0x1CF30, // 1CF30..1CF46; INHERITED
6760 0x1CF47, // 1CF47..1CF4F; UNKNOWN
6761 0x1CF50, // 1CF50..1CFC3; COMMON
6762 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
6763 0x1D000, // 1D000..1D0F5; COMMON
6764 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6765 0x1D100, // 1D100..1D126; COMMON
6766 0x1D127, // 1D127..1D128; UNKNOWN
6767 0x1D129, // 1D129..1D166; COMMON
6768 0x1D167, // 1D167..1D169; INHERITED
6769 0x1D16A, // 1D16A..1D17A; COMMON
6770 0x1D17B, // 1D17B..1D182; INHERITED
6771 0x1D183, // 1D183..1D184; COMMON
6772 0x1D185, // 1D185..1D18B; INHERITED
6773 0x1D18C, // 1D18C..1D1A9; COMMON
6774 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6775 0x1D1AE, // 1D1AE..1D1EA; COMMON
6776 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
6777 0x1D200, // 1D200..1D245; GREEK
6778 0x1D246, // 1D246..1D2BF; UNKNOWN
6779 0x1D2C0, // 1D2C0..1D2D3; COMMON
6780 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
6781 0x1D2E0, // 1D2E0..1D2F3; COMMON
6782 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6783 0x1D300, // 1D300..1D356; COMMON
6784 0x1D357, // 1D357..1D35F; UNKNOWN
6785 0x1D360, // 1D360..1D378; COMMON
6786 0x1D379, // 1D379..1D3FF; UNKNOWN
6787 0x1D400, // 1D400..1D454; COMMON
6788 0x1D455, // 1D455 ; UNKNOWN
6789 0x1D456, // 1D456..1D49C; COMMON
6790 0x1D49D, // 1D49D ; UNKNOWN
6791 0x1D49E, // 1D49E..1D49F; COMMON
6792 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
6793 0x1D4A2, // 1D4A2 ; COMMON
6794 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
6795 0x1D4A5, // 1D4A5..1D4A6; COMMON
6796 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
6797 0x1D4A9, // 1D4A9..1D4AC; COMMON
6798 0x1D4AD, // 1D4AD ; UNKNOWN
6799 0x1D4AE, // 1D4AE..1D4B9; COMMON
6800 0x1D4BA, // 1D4BA ; UNKNOWN
6801 0x1D4BB, // 1D4BB ; COMMON
6802 0x1D4BC, // 1D4BC ; UNKNOWN
6803 0x1D4BD, // 1D4BD..1D4C3; COMMON
6804 0x1D4C4, // 1D4C4 ; UNKNOWN
6805 0x1D4C5, // 1D4C5..1D505; COMMON
6806 0x1D506, // 1D506 ; UNKNOWN
6807 0x1D507, // 1D507..1D50A; COMMON
6808 0x1D50B, // 1D50B..1D50C; UNKNOWN
6809 0x1D50D, // 1D50D..1D514; COMMON
6810 0x1D515, // 1D515 ; UNKNOWN
6811 0x1D516, // 1D516..1D51C; COMMON
6812 0x1D51D, // 1D51D ; UNKNOWN
6813 0x1D51E, // 1D51E..1D539; COMMON
6814 0x1D53A, // 1D53A ; UNKNOWN
6815 0x1D53B, // 1D53B..1D53E; COMMON
6816 0x1D53F, // 1D53F ; UNKNOWN
6817 0x1D540, // 1D540..1D544; COMMON
6818 0x1D545, // 1D545 ; UNKNOWN
6819 0x1D546, // 1D546 ; COMMON
6820 0x1D547, // 1D547..1D549; UNKNOWN
6821 0x1D54A, // 1D54A..1D550; COMMON
6822 0x1D551, // 1D551 ; UNKNOWN
6823 0x1D552, // 1D552..1D6A5; COMMON
6824 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
6825 0x1D6A8, // 1D6A8..1D7CB; COMMON
6826 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
6827 0x1D7CE, // 1D7CE..1D7FF; COMMON
6828 0x1D800, // 1D800..1DA8B; SIGNWRITING
6829 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
6830 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
6831 0x1DAA0, // 1DAA0 ; UNKNOWN
6832 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
6833 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
6834 0x1DF00, // 1DF00..1DF1E; LATIN
6835 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
6836 0x1DF25, // 1DF25..1DF2A; LATIN
6837 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
6838 0x1E000, // 1E000..1E006; GLAGOLITIC
6839 0x1E007, // 1E007 ; UNKNOWN
6840 0x1E008, // 1E008..1E018; GLAGOLITIC
6841 0x1E019, // 1E019..1E01A; UNKNOWN
6842 0x1E01B, // 1E01B..1E021; GLAGOLITIC
6843 0x1E022, // 1E022 ; UNKNOWN
6844 0x1E023, // 1E023..1E024; GLAGOLITIC
6845 0x1E025, // 1E025 ; UNKNOWN
6846 0x1E026, // 1E026..1E02A; GLAGOLITIC
6847 0x1E02B, // 1E02B..1E02F; UNKNOWN
6848 0x1E030, // 1E030..1E06D; CYRILLIC
6849 0x1E06E, // 1E06E..1E08E; UNKNOWN
6850 0x1E08F, // 1E08F ; CYRILLIC
6851 0x1E090, // 1E090..1E0FF; UNKNOWN
6852 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
6853 0x1E12D, // 1E12D..1E12F; UNKNOWN
6854 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
6855 0x1E13E, // 1E13E..1E13F; UNKNOWN
6856 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
6857 0x1E14A, // 1E14A..1E14D; UNKNOWN
6858 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
6859 0x1E150, // 1E150..1E28F; UNKNOWN
6860 0x1E290, // 1E290..1E2AE; TOTO
6861 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
6862 0x1E2C0, // 1E2C0..1E2F9; WANCHO
6863 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
6864 0x1E2FF, // 1E2FF ; WANCHO
6865 0x1E300, // 1E300..1E4CF; UNKNOWN
6866 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
6867 0x1E4FA, // 1E4FA..1E7DF; UNKNOWN
6868 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
6869 0x1E7E7, // 1E7E7 ; UNKNOWN
6870 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
6871 0x1E7EC, // 1E7EC ; UNKNOWN
6872 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
6873 0x1E7EF, // 1E7EF ; UNKNOWN
6874 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
6875 0x1E7FF, // 1E7FF ; UNKNOWN
6876 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
6877 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
6878 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
6879 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
6880 0x1E900, // 1E900..1E94B; ADLAM
6881 0x1E94C, // 1E94C..1E94F; UNKNOWN
6882 0x1E950, // 1E950..1E959; ADLAM
6883 0x1E95A, // 1E95A..1E95D; UNKNOWN
6884 0x1E95E, // 1E95E..1E95F; ADLAM
6885 0x1E960, // 1E960..1EC70; UNKNOWN
6886 0x1EC71, // 1EC71..1ECB4; COMMON
6887 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
6888 0x1ED01, // 1ED01..1ED3D; COMMON
6889 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
6890 0x1EE00, // 1EE00..1EE03; ARABIC
6891 0x1EE04, // 1EE04 ; UNKNOWN
6892 0x1EE05, // 1EE05..1EE1F; ARABIC
6893 0x1EE20, // 1EE20 ; UNKNOWN
6894 0x1EE21, // 1EE21..1EE22; ARABIC
6895 0x1EE23, // 1EE23 ; UNKNOWN
6896 0x1EE24, // 1EE24 ; ARABIC
6897 0x1EE25, // 1EE25..1EE26; UNKNOWN
6898 0x1EE27, // 1EE27 ; ARABIC
6899 0x1EE28, // 1EE28 ; UNKNOWN
6900 0x1EE29, // 1EE29..1EE32; ARABIC
6901 0x1EE33, // 1EE33 ; UNKNOWN
6902 0x1EE34, // 1EE34..1EE37; ARABIC
6903 0x1EE38, // 1EE38 ; UNKNOWN
6904 0x1EE39, // 1EE39 ; ARABIC
6905 0x1EE3A, // 1EE3A ; UNKNOWN
6906 0x1EE3B, // 1EE3B ; ARABIC
6907 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
6908 0x1EE42, // 1EE42 ; ARABIC
6909 0x1EE43, // 1EE43..1EE46; UNKNOWN
6910 0x1EE47, // 1EE47 ; ARABIC
6911 0x1EE48, // 1EE48 ; UNKNOWN
6912 0x1EE49, // 1EE49 ; ARABIC
6913 0x1EE4A, // 1EE4A ; UNKNOWN
6914 0x1EE4B, // 1EE4B ; ARABIC
6915 0x1EE4C, // 1EE4C ; UNKNOWN
6916 0x1EE4D, // 1EE4D..1EE4F; ARABIC
6917 0x1EE50, // 1EE50 ; UNKNOWN
6918 0x1EE51, // 1EE51..1EE52; ARABIC
6919 0x1EE53, // 1EE53 ; UNKNOWN
6920 0x1EE54, // 1EE54 ; ARABIC
6921 0x1EE55, // 1EE55..1EE56; UNKNOWN
6922 0x1EE57, // 1EE57 ; ARABIC
6923 0x1EE58, // 1EE58 ; UNKNOWN
6924 0x1EE59, // 1EE59 ; ARABIC
6925 0x1EE5A, // 1EE5A ; UNKNOWN
6926 0x1EE5B, // 1EE5B ; ARABIC
6927 0x1EE5C, // 1EE5C ; UNKNOWN
6928 0x1EE5D, // 1EE5D ; ARABIC
6929 0x1EE5E, // 1EE5E ; UNKNOWN
6930 0x1EE5F, // 1EE5F ; ARABIC
6931 0x1EE60, // 1EE60 ; UNKNOWN
6932 0x1EE61, // 1EE61..1EE62; ARABIC
6933 0x1EE63, // 1EE63 ; UNKNOWN
6934 0x1EE64, // 1EE64 ; ARABIC
6935 0x1EE65, // 1EE65..1EE66; UNKNOWN
6936 0x1EE67, // 1EE67..1EE6A; ARABIC
6937 0x1EE6B, // 1EE6B ; UNKNOWN
6938 0x1EE6C, // 1EE6C..1EE72; ARABIC
6939 0x1EE73, // 1EE73 ; UNKNOWN
6940 0x1EE74, // 1EE74..1EE77; ARABIC
6941 0x1EE78, // 1EE78 ; UNKNOWN
6942 0x1EE79, // 1EE79..1EE7C; ARABIC
6943 0x1EE7D, // 1EE7D ; UNKNOWN
6944 0x1EE7E, // 1EE7E ; ARABIC
6945 0x1EE7F, // 1EE7F ; UNKNOWN
6946 0x1EE80, // 1EE80..1EE89; ARABIC
6947 0x1EE8A, // 1EE8A ; UNKNOWN
6948 0x1EE8B, // 1EE8B..1EE9B; ARABIC
6949 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
6950 0x1EEA1, // 1EEA1..1EEA3; ARABIC
6951 0x1EEA4, // 1EEA4 ; UNKNOWN
6952 0x1EEA5, // 1EEA5..1EEA9; ARABIC
6953 0x1EEAA, // 1EEAA ; UNKNOWN
6954 0x1EEAB, // 1EEAB..1EEBB; ARABIC
6955 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
6956 0x1EEF0, // 1EEF0..1EEF1; ARABIC
6957 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
6958 0x1F000, // 1F000..1F02B; COMMON
6959 0x1F02C, // 1F02C..1F02F; UNKNOWN
6960 0x1F030, // 1F030..1F093; COMMON
6961 0x1F094, // 1F094..1F09F; UNKNOWN
6962 0x1F0A0, // 1F0A0..1F0AE; COMMON
6963 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
6964 0x1F0B1, // 1F0B1..1F0BF; COMMON
6965 0x1F0C0, // 1F0C0 ; UNKNOWN
6966 0x1F0C1, // 1F0C1..1F0CF; COMMON
6967 0x1F0D0, // 1F0D0 ; UNKNOWN
6968 0x1F0D1, // 1F0D1..1F0F5; COMMON
6969 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
6970 0x1F100, // 1F100..1F1AD; COMMON
6971 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
6972 0x1F1E6, // 1F1E6..1F1FF; COMMON
6973 0x1F200, // 1F200 ; HIRAGANA
6974 0x1F201, // 1F201..1F202; COMMON
6975 0x1F203, // 1F203..1F20F; UNKNOWN
6976 0x1F210, // 1F210..1F23B; COMMON
6977 0x1F23C, // 1F23C..1F23F; UNKNOWN
6978 0x1F240, // 1F240..1F248; COMMON
6979 0x1F249, // 1F249..1F24F; UNKNOWN
6980 0x1F250, // 1F250..1F251; COMMON
6981 0x1F252, // 1F252..1F25F; UNKNOWN
6982 0x1F260, // 1F260..1F265; COMMON
6983 0x1F266, // 1F266..1F2FF; UNKNOWN
6984 0x1F300, // 1F300..1F6D7; COMMON
6985 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN
6986 0x1F6DC, // 1F6DC..1F6EC; COMMON
6987 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
6988 0x1F6F0, // 1F6F0..1F6FC; COMMON
6989 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
6990 0x1F700, // 1F700..1F776; COMMON
6991 0x1F777, // 1F777..1F77A; UNKNOWN
6992 0x1F77B, // 1F77B..1F7D9; COMMON
6993 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
6994 0x1F7E0, // 1F7E0..1F7EB; COMMON
6995 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
6996 0x1F7F0, // 1F7F0 ; COMMON
6997 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
6998 0x1F800, // 1F800..1F80B; COMMON
6999 0x1F80C, // 1F80C..1F80F; UNKNOWN
7000 0x1F810, // 1F810..1F847; COMMON
7001 0x1F848, // 1F848..1F84F; UNKNOWN
7002 0x1F850, // 1F850..1F859; COMMON
7003 0x1F85A, // 1F85A..1F85F; UNKNOWN
7004 0x1F860, // 1F860..1F887; COMMON
7005 0x1F888, // 1F888..1F88F; UNKNOWN
7006 0x1F890, // 1F890..1F8AD; COMMON
7007 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7008 0x1F8B0, // 1F8B0..1F8B1; COMMON
7009 0x1F8B2, // 1F8B2..1F8FF; UNKNOWN
7010 0x1F900, // 1F900..1FA53; COMMON
7011 0x1FA54, // 1FA54..1FA5F; UNKNOWN
7012 0x1FA60, // 1FA60..1FA6D; COMMON
7013 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7014 0x1FA70, // 1FA70..1FA7C; COMMON
7015 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7016 0x1FA80, // 1FA80..1FA88; COMMON
7017 0x1FA89, // 1FA89..1FA8F; UNKNOWN
7018 0x1FA90, // 1FA90..1FABD; COMMON
7019 0x1FABE, // 1FABE ; UNKNOWN
7020 0x1FABF, // 1FABF..1FAC5; COMMON
7021 0x1FAC6, // 1FAC6..1FACD; UNKNOWN
7022 0x1FACE, // 1FACE..1FADB; COMMON
7023 0x1FADC, // 1FADC..1FADF; UNKNOWN
7024 0x1FAE0, // 1FAE0..1FAE8; COMMON
7025 0x1FAE9, // 1FAE9..1FAEF; UNKNOWN
7026 0x1FAF0, // 1FAF0..1FAF8; COMMON
7027 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7028 0x1FB00, // 1FB00..1FB92; COMMON
7029 0x1FB93, // 1FB93 ; UNKNOWN
7030 0x1FB94, // 1FB94..1FBCA; COMMON
7031 0x1FBCB, // 1FBCB..1FBEF; UNKNOWN
7032 0x1FBF0, // 1FBF0..1FBF9; COMMON
7033 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN
7034 0x20000, // 20000..2A6DF; HAN
7035 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7036 0x2A700, // 2A700..2B739; HAN
7037 0x2B73A, // 2B73A..2B73F; UNKNOWN
7038 0x2B740, // 2B740..2B81D; HAN
7039 0x2B81E, // 2B81E..2B81F; UNKNOWN
7040 0x2B820, // 2B820..2CEA1; HAN
7041 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
7042 0x2CEB0, // 2CEB0..2EBE0; HAN
7043 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7044 0x2EBF0, // 2EBF0..2EE5D; HAN
7045 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7046 0x2F800, // 2F800..2FA1D; HAN
7047 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7048 0x30000, // 30000..3134A; HAN
7049 0x3134B, // 3134B..3134F; UNKNOWN
7050 0x31350, // 31350..323AF; HAN
7051 0x323B0, // 323B0..E0000; UNKNOWN
7052 0xE0001, // E0001 ; COMMON
7053 0xE0002, // E0002..E001F; UNKNOWN
7054 0xE0020, // E0020..E007F; COMMON
7055 0xE0080, // E0080..E00FF; UNKNOWN
7056 0xE0100, // E0100..E01EF; INHERITED
7057 0xE01F0, // E01F0..10FFFF; UNKNOWN
7058 };
7059
7060 private static final UnicodeScript[] scripts = {
7061 COMMON, // 0000..0040
7062 LATIN, // 0041..005A
7063 COMMON, // 005B..0060
7064 LATIN, // 0061..007A
7065 COMMON, // 007B..00A9
7066 LATIN, // 00AA
7067 COMMON, // 00AB..00B9
7068 LATIN, // 00BA
7069 COMMON, // 00BB..00BF
7070 LATIN, // 00C0..00D6
7071 COMMON, // 00D7
7072 LATIN, // 00D8..00F6
7073 COMMON, // 00F7
7074 LATIN, // 00F8..02B8
7075 COMMON, // 02B9..02DF
7076 LATIN, // 02E0..02E4
7077 COMMON, // 02E5..02E9
7078 BOPOMOFO, // 02EA..02EB
7079 COMMON, // 02EC..02FF
7080 INHERITED, // 0300..036F
7081 GREEK, // 0370..0373
7082 COMMON, // 0374
7083 GREEK, // 0375..0377
7084 UNKNOWN, // 0378..0379
7085 GREEK, // 037A..037D
7086 COMMON, // 037E
7087 GREEK, // 037F
7088 UNKNOWN, // 0380..0383
7089 GREEK, // 0384
7090 COMMON, // 0385
7091 GREEK, // 0386
7092 COMMON, // 0387
7093 GREEK, // 0388..038A
7094 UNKNOWN, // 038B
7095 GREEK, // 038C
7096 UNKNOWN, // 038D
7097 GREEK, // 038E..03A1
7098 UNKNOWN, // 03A2
7099 GREEK, // 03A3..03E1
7100 COPTIC, // 03E2..03EF
7101 GREEK, // 03F0..03FF
7102 CYRILLIC, // 0400..0484
7103 INHERITED, // 0485..0486
7104 CYRILLIC, // 0487..052F
7105 UNKNOWN, // 0530
7106 ARMENIAN, // 0531..0556
7107 UNKNOWN, // 0557..0558
7108 ARMENIAN, // 0559..058A
7109 UNKNOWN, // 058B..058C
7110 ARMENIAN, // 058D..058F
7111 UNKNOWN, // 0590
7112 HEBREW, // 0591..05C7
7113 UNKNOWN, // 05C8..05CF
7114 HEBREW, // 05D0..05EA
7115 UNKNOWN, // 05EB..05EE
7116 HEBREW, // 05EF..05F4
7117 UNKNOWN, // 05F5..05FF
7118 ARABIC, // 0600..0604
7119 COMMON, // 0605
7120 ARABIC, // 0606..060B
7121 COMMON, // 060C
7122 ARABIC, // 060D..061A
7123 COMMON, // 061B
7124 ARABIC, // 061C..061E
7125 COMMON, // 061F
7126 ARABIC, // 0620..063F
7127 COMMON, // 0640
7128 ARABIC, // 0641..064A
7129 INHERITED, // 064B..0655
7130 ARABIC, // 0656..066F
7131 INHERITED, // 0670
7132 ARABIC, // 0671..06DC
7133 COMMON, // 06DD
7134 ARABIC, // 06DE..06FF
7135 SYRIAC, // 0700..070D
7136 UNKNOWN, // 070E
7137 SYRIAC, // 070F..074A
7138 UNKNOWN, // 074B..074C
7139 SYRIAC, // 074D..074F
7140 ARABIC, // 0750..077F
7141 THAANA, // 0780..07B1
7142 UNKNOWN, // 07B2..07BF
7143 NKO, // 07C0..07FA
7144 UNKNOWN, // 07FB..07FC
7145 NKO, // 07FD..07FF
7146 SAMARITAN, // 0800..082D
7147 UNKNOWN, // 082E..082F
7148 SAMARITAN, // 0830..083E
7149 UNKNOWN, // 083F
7150 MANDAIC, // 0840..085B
7151 UNKNOWN, // 085C..085D
7152 MANDAIC, // 085E
7153 UNKNOWN, // 085F
7154 SYRIAC, // 0860..086A
7155 UNKNOWN, // 086B..086F
7156 ARABIC, // 0870..088E
7157 UNKNOWN, // 088F
7158 ARABIC, // 0890..0891
7159 UNKNOWN, // 0892..0897
7160 ARABIC, // 0898..08E1
7161 COMMON, // 08E2
7162 ARABIC, // 08E3..08FF
7163 DEVANAGARI, // 0900..0950
7164 INHERITED, // 0951..0954
7165 DEVANAGARI, // 0955..0963
7166 COMMON, // 0964..0965
7167 DEVANAGARI, // 0966..097F
7168 BENGALI, // 0980..0983
7169 UNKNOWN, // 0984
7170 BENGALI, // 0985..098C
7171 UNKNOWN, // 098D..098E
7172 BENGALI, // 098F..0990
7173 UNKNOWN, // 0991..0992
7174 BENGALI, // 0993..09A8
7175 UNKNOWN, // 09A9
7176 BENGALI, // 09AA..09B0
7177 UNKNOWN, // 09B1
7178 BENGALI, // 09B2
7179 UNKNOWN, // 09B3..09B5
7180 BENGALI, // 09B6..09B9
7181 UNKNOWN, // 09BA..09BB
7182 BENGALI, // 09BC..09C4
7183 UNKNOWN, // 09C5..09C6
7184 BENGALI, // 09C7..09C8
7185 UNKNOWN, // 09C9..09CA
7186 BENGALI, // 09CB..09CE
7187 UNKNOWN, // 09CF..09D6
7188 BENGALI, // 09D7
7189 UNKNOWN, // 09D8..09DB
7190 BENGALI, // 09DC..09DD
7191 UNKNOWN, // 09DE
7192 BENGALI, // 09DF..09E3
7193 UNKNOWN, // 09E4..09E5
7194 BENGALI, // 09E6..09FE
7195 UNKNOWN, // 09FF..0A00
7196 GURMUKHI, // 0A01..0A03
7197 UNKNOWN, // 0A04
7198 GURMUKHI, // 0A05..0A0A
7199 UNKNOWN, // 0A0B..0A0E
7200 GURMUKHI, // 0A0F..0A10
7201 UNKNOWN, // 0A11..0A12
7202 GURMUKHI, // 0A13..0A28
7203 UNKNOWN, // 0A29
7204 GURMUKHI, // 0A2A..0A30
7205 UNKNOWN, // 0A31
7206 GURMUKHI, // 0A32..0A33
7207 UNKNOWN, // 0A34
7208 GURMUKHI, // 0A35..0A36
7209 UNKNOWN, // 0A37
7210 GURMUKHI, // 0A38..0A39
7211 UNKNOWN, // 0A3A..0A3B
7212 GURMUKHI, // 0A3C
7213 UNKNOWN, // 0A3D
7214 GURMUKHI, // 0A3E..0A42
7215 UNKNOWN, // 0A43..0A46
7216 GURMUKHI, // 0A47..0A48
7217 UNKNOWN, // 0A49..0A4A
7218 GURMUKHI, // 0A4B..0A4D
7219 UNKNOWN, // 0A4E..0A50
7220 GURMUKHI, // 0A51
7221 UNKNOWN, // 0A52..0A58
7222 GURMUKHI, // 0A59..0A5C
7223 UNKNOWN, // 0A5D
7224 GURMUKHI, // 0A5E
7225 UNKNOWN, // 0A5F..0A65
7226 GURMUKHI, // 0A66..0A76
7227 UNKNOWN, // 0A77..0A80
7228 GUJARATI, // 0A81..0A83
7229 UNKNOWN, // 0A84
7230 GUJARATI, // 0A85..0A8D
7231 UNKNOWN, // 0A8E
7232 GUJARATI, // 0A8F..0A91
7233 UNKNOWN, // 0A92
7234 GUJARATI, // 0A93..0AA8
7235 UNKNOWN, // 0AA9
7236 GUJARATI, // 0AAA..0AB0
7237 UNKNOWN, // 0AB1
7238 GUJARATI, // 0AB2..0AB3
7239 UNKNOWN, // 0AB4
7240 GUJARATI, // 0AB5..0AB9
7241 UNKNOWN, // 0ABA..0ABB
7242 GUJARATI, // 0ABC..0AC5
7243 UNKNOWN, // 0AC6
7244 GUJARATI, // 0AC7..0AC9
7245 UNKNOWN, // 0ACA
7246 GUJARATI, // 0ACB..0ACD
7247 UNKNOWN, // 0ACE..0ACF
7248 GUJARATI, // 0AD0
7249 UNKNOWN, // 0AD1..0ADF
7250 GUJARATI, // 0AE0..0AE3
7251 UNKNOWN, // 0AE4..0AE5
7252 GUJARATI, // 0AE6..0AF1
7253 UNKNOWN, // 0AF2..0AF8
7254 GUJARATI, // 0AF9..0AFF
7255 UNKNOWN, // 0B00
7256 ORIYA, // 0B01..0B03
7257 UNKNOWN, // 0B04
7258 ORIYA, // 0B05..0B0C
7259 UNKNOWN, // 0B0D..0B0E
7260 ORIYA, // 0B0F..0B10
7261 UNKNOWN, // 0B11..0B12
7262 ORIYA, // 0B13..0B28
7263 UNKNOWN, // 0B29
7264 ORIYA, // 0B2A..0B30
7265 UNKNOWN, // 0B31
7266 ORIYA, // 0B32..0B33
7267 UNKNOWN, // 0B34
7268 ORIYA, // 0B35..0B39
7269 UNKNOWN, // 0B3A..0B3B
7270 ORIYA, // 0B3C..0B44
7271 UNKNOWN, // 0B45..0B46
7272 ORIYA, // 0B47..0B48
7273 UNKNOWN, // 0B49..0B4A
7274 ORIYA, // 0B4B..0B4D
7275 UNKNOWN, // 0B4E..0B54
7276 ORIYA, // 0B55..0B57
7277 UNKNOWN, // 0B58..0B5B
7278 ORIYA, // 0B5C..0B5D
7279 UNKNOWN, // 0B5E
7280 ORIYA, // 0B5F..0B63
7281 UNKNOWN, // 0B64..0B65
7282 ORIYA, // 0B66..0B77
7283 UNKNOWN, // 0B78..0B81
7284 TAMIL, // 0B82..0B83
7285 UNKNOWN, // 0B84
7286 TAMIL, // 0B85..0B8A
7287 UNKNOWN, // 0B8B..0B8D
7288 TAMIL, // 0B8E..0B90
7289 UNKNOWN, // 0B91
7290 TAMIL, // 0B92..0B95
7291 UNKNOWN, // 0B96..0B98
7292 TAMIL, // 0B99..0B9A
7293 UNKNOWN, // 0B9B
7294 TAMIL, // 0B9C
7295 UNKNOWN, // 0B9D
7296 TAMIL, // 0B9E..0B9F
7297 UNKNOWN, // 0BA0..0BA2
7298 TAMIL, // 0BA3..0BA4
7299 UNKNOWN, // 0BA5..0BA7
7300 TAMIL, // 0BA8..0BAA
7301 UNKNOWN, // 0BAB..0BAD
7302 TAMIL, // 0BAE..0BB9
7303 UNKNOWN, // 0BBA..0BBD
7304 TAMIL, // 0BBE..0BC2
7305 UNKNOWN, // 0BC3..0BC5
7306 TAMIL, // 0BC6..0BC8
7307 UNKNOWN, // 0BC9
7308 TAMIL, // 0BCA..0BCD
7309 UNKNOWN, // 0BCE..0BCF
7310 TAMIL, // 0BD0
7311 UNKNOWN, // 0BD1..0BD6
7312 TAMIL, // 0BD7
7313 UNKNOWN, // 0BD8..0BE5
7314 TAMIL, // 0BE6..0BFA
7315 UNKNOWN, // 0BFB..0BFF
7316 TELUGU, // 0C00..0C0C
7317 UNKNOWN, // 0C0D
7318 TELUGU, // 0C0E..0C10
7319 UNKNOWN, // 0C11
7320 TELUGU, // 0C12..0C28
7321 UNKNOWN, // 0C29
7322 TELUGU, // 0C2A..0C39
7323 UNKNOWN, // 0C3A..0C3B
7324 TELUGU, // 0C3C..0C44
7325 UNKNOWN, // 0C45
7326 TELUGU, // 0C46..0C48
7327 UNKNOWN, // 0C49
7328 TELUGU, // 0C4A..0C4D
7329 UNKNOWN, // 0C4E..0C54
7330 TELUGU, // 0C55..0C56
7331 UNKNOWN, // 0C57
7332 TELUGU, // 0C58..0C5A
7333 UNKNOWN, // 0C5B..0C5C
7334 TELUGU, // 0C5D
7335 UNKNOWN, // 0C5E..0C5F
7336 TELUGU, // 0C60..0C63
7337 UNKNOWN, // 0C64..0C65
7338 TELUGU, // 0C66..0C6F
7339 UNKNOWN, // 0C70..0C76
7340 TELUGU, // 0C77..0C7F
7341 KANNADA, // 0C80..0C8C
7342 UNKNOWN, // 0C8D
7343 KANNADA, // 0C8E..0C90
7344 UNKNOWN, // 0C91
7345 KANNADA, // 0C92..0CA8
7346 UNKNOWN, // 0CA9
7347 KANNADA, // 0CAA..0CB3
7348 UNKNOWN, // 0CB4
7349 KANNADA, // 0CB5..0CB9
7350 UNKNOWN, // 0CBA..0CBB
7351 KANNADA, // 0CBC..0CC4
7352 UNKNOWN, // 0CC5
7353 KANNADA, // 0CC6..0CC8
7354 UNKNOWN, // 0CC9
7355 KANNADA, // 0CCA..0CCD
7356 UNKNOWN, // 0CCE..0CD4
7357 KANNADA, // 0CD5..0CD6
7358 UNKNOWN, // 0CD7..0CDC
7359 KANNADA, // 0CDD..0CDE
7360 UNKNOWN, // 0CDF
7361 KANNADA, // 0CE0..0CE3
7362 UNKNOWN, // 0CE4..0CE5
7363 KANNADA, // 0CE6..0CEF
7364 UNKNOWN, // 0CF0
7365 KANNADA, // 0CF1..0CF3
7366 UNKNOWN, // 0CF4..0CFF
7367 MALAYALAM, // 0D00..0D0C
7368 UNKNOWN, // 0D0D
7369 MALAYALAM, // 0D0E..0D10
7370 UNKNOWN, // 0D11
7371 MALAYALAM, // 0D12..0D44
7372 UNKNOWN, // 0D45
7373 MALAYALAM, // 0D46..0D48
7374 UNKNOWN, // 0D49
7375 MALAYALAM, // 0D4A..0D4F
7376 UNKNOWN, // 0D50..0D53
7377 MALAYALAM, // 0D54..0D63
7378 UNKNOWN, // 0D64..0D65
7379 MALAYALAM, // 0D66..0D7F
7380 UNKNOWN, // 0D80
7381 SINHALA, // 0D81..0D83
7382 UNKNOWN, // 0D84
7383 SINHALA, // 0D85..0D96
7384 UNKNOWN, // 0D97..0D99
7385 SINHALA, // 0D9A..0DB1
7386 UNKNOWN, // 0DB2
7387 SINHALA, // 0DB3..0DBB
7388 UNKNOWN, // 0DBC
7389 SINHALA, // 0DBD
7390 UNKNOWN, // 0DBE..0DBF
7391 SINHALA, // 0DC0..0DC6
7392 UNKNOWN, // 0DC7..0DC9
7393 SINHALA, // 0DCA
7394 UNKNOWN, // 0DCB..0DCE
7395 SINHALA, // 0DCF..0DD4
7396 UNKNOWN, // 0DD5
7397 SINHALA, // 0DD6
7398 UNKNOWN, // 0DD7
7399 SINHALA, // 0DD8..0DDF
7400 UNKNOWN, // 0DE0..0DE5
7401 SINHALA, // 0DE6..0DEF
7402 UNKNOWN, // 0DF0..0DF1
7403 SINHALA, // 0DF2..0DF4
7404 UNKNOWN, // 0DF5..0E00
7405 THAI, // 0E01..0E3A
7406 UNKNOWN, // 0E3B..0E3E
7407 COMMON, // 0E3F
7408 THAI, // 0E40..0E5B
7409 UNKNOWN, // 0E5C..0E80
7410 LAO, // 0E81..0E82
7411 UNKNOWN, // 0E83
7412 LAO, // 0E84
7413 UNKNOWN, // 0E85
7414 LAO, // 0E86..0E8A
7415 UNKNOWN, // 0E8B
7416 LAO, // 0E8C..0EA3
7417 UNKNOWN, // 0EA4
7418 LAO, // 0EA5
7419 UNKNOWN, // 0EA6
7420 LAO, // 0EA7..0EBD
7421 UNKNOWN, // 0EBE..0EBF
7422 LAO, // 0EC0..0EC4
7423 UNKNOWN, // 0EC5
7424 LAO, // 0EC6
7425 UNKNOWN, // 0EC7
7426 LAO, // 0EC8..0ECE
7427 UNKNOWN, // 0ECF
7428 LAO, // 0ED0..0ED9
7429 UNKNOWN, // 0EDA..0EDB
7430 LAO, // 0EDC..0EDF
7431 UNKNOWN, // 0EE0..0EFF
7432 TIBETAN, // 0F00..0F47
7433 UNKNOWN, // 0F48
7434 TIBETAN, // 0F49..0F6C
7435 UNKNOWN, // 0F6D..0F70
7436 TIBETAN, // 0F71..0F97
7437 UNKNOWN, // 0F98
7438 TIBETAN, // 0F99..0FBC
7439 UNKNOWN, // 0FBD
7440 TIBETAN, // 0FBE..0FCC
7441 UNKNOWN, // 0FCD
7442 TIBETAN, // 0FCE..0FD4
7443 COMMON, // 0FD5..0FD8
7444 TIBETAN, // 0FD9..0FDA
7445 UNKNOWN, // 0FDB..0FFF
7446 MYANMAR, // 1000..109F
7447 GEORGIAN, // 10A0..10C5
7448 UNKNOWN, // 10C6
7449 GEORGIAN, // 10C7
7450 UNKNOWN, // 10C8..10CC
7451 GEORGIAN, // 10CD
7452 UNKNOWN, // 10CE..10CF
7453 GEORGIAN, // 10D0..10FA
7454 COMMON, // 10FB
7455 GEORGIAN, // 10FC..10FF
7456 HANGUL, // 1100..11FF
7457 ETHIOPIC, // 1200..1248
7458 UNKNOWN, // 1249
7459 ETHIOPIC, // 124A..124D
7460 UNKNOWN, // 124E..124F
7461 ETHIOPIC, // 1250..1256
7462 UNKNOWN, // 1257
7463 ETHIOPIC, // 1258
7464 UNKNOWN, // 1259
7465 ETHIOPIC, // 125A..125D
7466 UNKNOWN, // 125E..125F
7467 ETHIOPIC, // 1260..1288
7468 UNKNOWN, // 1289
7469 ETHIOPIC, // 128A..128D
7470 UNKNOWN, // 128E..128F
7471 ETHIOPIC, // 1290..12B0
7472 UNKNOWN, // 12B1
7473 ETHIOPIC, // 12B2..12B5
7474 UNKNOWN, // 12B6..12B7
7475 ETHIOPIC, // 12B8..12BE
7476 UNKNOWN, // 12BF
7477 ETHIOPIC, // 12C0
7478 UNKNOWN, // 12C1
7479 ETHIOPIC, // 12C2..12C5
7480 UNKNOWN, // 12C6..12C7
7481 ETHIOPIC, // 12C8..12D6
7482 UNKNOWN, // 12D7
7483 ETHIOPIC, // 12D8..1310
7484 UNKNOWN, // 1311
7485 ETHIOPIC, // 1312..1315
7486 UNKNOWN, // 1316..1317
7487 ETHIOPIC, // 1318..135A
7488 UNKNOWN, // 135B..135C
7489 ETHIOPIC, // 135D..137C
7490 UNKNOWN, // 137D..137F
7491 ETHIOPIC, // 1380..1399
7492 UNKNOWN, // 139A..139F
7493 CHEROKEE, // 13A0..13F5
7494 UNKNOWN, // 13F6..13F7
7495 CHEROKEE, // 13F8..13FD
7496 UNKNOWN, // 13FE..13FF
7497 CANADIAN_ABORIGINAL, // 1400..167F
7498 OGHAM, // 1680..169C
7499 UNKNOWN, // 169D..169F
7500 RUNIC, // 16A0..16EA
7501 COMMON, // 16EB..16ED
7502 RUNIC, // 16EE..16F8
7503 UNKNOWN, // 16F9..16FF
7504 TAGALOG, // 1700..1715
7505 UNKNOWN, // 1716..171E
7506 TAGALOG, // 171F
7507 HANUNOO, // 1720..1734
7508 COMMON, // 1735..1736
7509 UNKNOWN, // 1737..173F
7510 BUHID, // 1740..1753
7511 UNKNOWN, // 1754..175F
7512 TAGBANWA, // 1760..176C
7513 UNKNOWN, // 176D
7514 TAGBANWA, // 176E..1770
7515 UNKNOWN, // 1771
7516 TAGBANWA, // 1772..1773
7517 UNKNOWN, // 1774..177F
7518 KHMER, // 1780..17DD
7519 UNKNOWN, // 17DE..17DF
7520 KHMER, // 17E0..17E9
7521 UNKNOWN, // 17EA..17EF
7522 KHMER, // 17F0..17F9
7523 UNKNOWN, // 17FA..17FF
7524 MONGOLIAN, // 1800..1801
7525 COMMON, // 1802..1803
7526 MONGOLIAN, // 1804
7527 COMMON, // 1805
7528 MONGOLIAN, // 1806..1819
7529 UNKNOWN, // 181A..181F
7530 MONGOLIAN, // 1820..1878
7531 UNKNOWN, // 1879..187F
7532 MONGOLIAN, // 1880..18AA
7533 UNKNOWN, // 18AB..18AF
7534 CANADIAN_ABORIGINAL, // 18B0..18F5
7535 UNKNOWN, // 18F6..18FF
7536 LIMBU, // 1900..191E
7537 UNKNOWN, // 191F
7538 LIMBU, // 1920..192B
7539 UNKNOWN, // 192C..192F
7540 LIMBU, // 1930..193B
7541 UNKNOWN, // 193C..193F
7542 LIMBU, // 1940
7543 UNKNOWN, // 1941..1943
7544 LIMBU, // 1944..194F
7545 TAI_LE, // 1950..196D
7546 UNKNOWN, // 196E..196F
7547 TAI_LE, // 1970..1974
7548 UNKNOWN, // 1975..197F
7549 NEW_TAI_LUE, // 1980..19AB
7550 UNKNOWN, // 19AC..19AF
7551 NEW_TAI_LUE, // 19B0..19C9
7552 UNKNOWN, // 19CA..19CF
7553 NEW_TAI_LUE, // 19D0..19DA
7554 UNKNOWN, // 19DB..19DD
7555 NEW_TAI_LUE, // 19DE..19DF
7556 KHMER, // 19E0..19FF
7557 BUGINESE, // 1A00..1A1B
7558 UNKNOWN, // 1A1C..1A1D
7559 BUGINESE, // 1A1E..1A1F
7560 TAI_THAM, // 1A20..1A5E
7561 UNKNOWN, // 1A5F
7562 TAI_THAM, // 1A60..1A7C
7563 UNKNOWN, // 1A7D..1A7E
7564 TAI_THAM, // 1A7F..1A89
7565 UNKNOWN, // 1A8A..1A8F
7566 TAI_THAM, // 1A90..1A99
7567 UNKNOWN, // 1A9A..1A9F
7568 TAI_THAM, // 1AA0..1AAD
7569 UNKNOWN, // 1AAE..1AAF
7570 INHERITED, // 1AB0..1ACE
7571 UNKNOWN, // 1ACF..1AFF
7572 BALINESE, // 1B00..1B4C
7573 UNKNOWN, // 1B4D..1B4F
7574 BALINESE, // 1B50..1B7E
7575 UNKNOWN, // 1B7F
7576 SUNDANESE, // 1B80..1BBF
7577 BATAK, // 1BC0..1BF3
7578 UNKNOWN, // 1BF4..1BFB
7579 BATAK, // 1BFC..1BFF
7580 LEPCHA, // 1C00..1C37
7581 UNKNOWN, // 1C38..1C3A
7582 LEPCHA, // 1C3B..1C49
7583 UNKNOWN, // 1C4A..1C4C
7584 LEPCHA, // 1C4D..1C4F
7585 OL_CHIKI, // 1C50..1C7F
7586 CYRILLIC, // 1C80..1C88
7587 UNKNOWN, // 1C89..1C8F
7588 GEORGIAN, // 1C90..1CBA
7589 UNKNOWN, // 1CBB..1CBC
7590 GEORGIAN, // 1CBD..1CBF
7591 SUNDANESE, // 1CC0..1CC7
7592 UNKNOWN, // 1CC8..1CCF
7593 INHERITED, // 1CD0..1CD2
7594 COMMON, // 1CD3
7595 INHERITED, // 1CD4..1CE0
7596 COMMON, // 1CE1
7597 INHERITED, // 1CE2..1CE8
7598 COMMON, // 1CE9..1CEC
7599 INHERITED, // 1CED
7600 COMMON, // 1CEE..1CF3
7601 INHERITED, // 1CF4
7602 COMMON, // 1CF5..1CF7
7603 INHERITED, // 1CF8..1CF9
7604 COMMON, // 1CFA
7605 UNKNOWN, // 1CFB..1CFF
7606 LATIN, // 1D00..1D25
7607 GREEK, // 1D26..1D2A
7608 CYRILLIC, // 1D2B
7609 LATIN, // 1D2C..1D5C
7610 GREEK, // 1D5D..1D61
7611 LATIN, // 1D62..1D65
7612 GREEK, // 1D66..1D6A
7613 LATIN, // 1D6B..1D77
7614 CYRILLIC, // 1D78
7615 LATIN, // 1D79..1DBE
7616 GREEK, // 1DBF
7617 INHERITED, // 1DC0..1DFF
7618 LATIN, // 1E00..1EFF
7619 GREEK, // 1F00..1F15
7620 UNKNOWN, // 1F16..1F17
7621 GREEK, // 1F18..1F1D
7622 UNKNOWN, // 1F1E..1F1F
7623 GREEK, // 1F20..1F45
7624 UNKNOWN, // 1F46..1F47
7625 GREEK, // 1F48..1F4D
7626 UNKNOWN, // 1F4E..1F4F
7627 GREEK, // 1F50..1F57
7628 UNKNOWN, // 1F58
7629 GREEK, // 1F59
7630 UNKNOWN, // 1F5A
7631 GREEK, // 1F5B
7632 UNKNOWN, // 1F5C
7633 GREEK, // 1F5D
7634 UNKNOWN, // 1F5E
7635 GREEK, // 1F5F..1F7D
7636 UNKNOWN, // 1F7E..1F7F
7637 GREEK, // 1F80..1FB4
7638 UNKNOWN, // 1FB5
7639 GREEK, // 1FB6..1FC4
7640 UNKNOWN, // 1FC5
7641 GREEK, // 1FC6..1FD3
7642 UNKNOWN, // 1FD4..1FD5
7643 GREEK, // 1FD6..1FDB
7644 UNKNOWN, // 1FDC
7645 GREEK, // 1FDD..1FEF
7646 UNKNOWN, // 1FF0..1FF1
7647 GREEK, // 1FF2..1FF4
7648 UNKNOWN, // 1FF5
7649 GREEK, // 1FF6..1FFE
7650 UNKNOWN, // 1FFF
7651 COMMON, // 2000..200B
7652 INHERITED, // 200C..200D
7653 COMMON, // 200E..2064
7654 UNKNOWN, // 2065
7655 COMMON, // 2066..2070
7656 LATIN, // 2071
7657 UNKNOWN, // 2072..2073
7658 COMMON, // 2074..207E
7659 LATIN, // 207F
7660 COMMON, // 2080..208E
7661 UNKNOWN, // 208F
7662 LATIN, // 2090..209C
7663 UNKNOWN, // 209D..209F
7664 COMMON, // 20A0..20C0
7665 UNKNOWN, // 20C1..20CF
7666 INHERITED, // 20D0..20F0
7667 UNKNOWN, // 20F1..20FF
7668 COMMON, // 2100..2125
7669 GREEK, // 2126
7670 COMMON, // 2127..2129
7671 LATIN, // 212A..212B
7672 COMMON, // 212C..2131
7673 LATIN, // 2132
7674 COMMON, // 2133..214D
7675 LATIN, // 214E
7676 COMMON, // 214F..215F
7677 LATIN, // 2160..2188
7678 COMMON, // 2189..218B
7679 UNKNOWN, // 218C..218F
7680 COMMON, // 2190..2426
7681 UNKNOWN, // 2427..243F
7682 COMMON, // 2440..244A
7683 UNKNOWN, // 244B..245F
7684 COMMON, // 2460..27FF
7685 BRAILLE, // 2800..28FF
7686 COMMON, // 2900..2B73
7687 UNKNOWN, // 2B74..2B75
7688 COMMON, // 2B76..2B95
7689 UNKNOWN, // 2B96
7690 COMMON, // 2B97..2BFF
7691 GLAGOLITIC, // 2C00..2C5F
7692 LATIN, // 2C60..2C7F
7693 COPTIC, // 2C80..2CF3
7694 UNKNOWN, // 2CF4..2CF8
7695 COPTIC, // 2CF9..2CFF
7696 GEORGIAN, // 2D00..2D25
7697 UNKNOWN, // 2D26
7698 GEORGIAN, // 2D27
7699 UNKNOWN, // 2D28..2D2C
7700 GEORGIAN, // 2D2D
7701 UNKNOWN, // 2D2E..2D2F
7702 TIFINAGH, // 2D30..2D67
7703 UNKNOWN, // 2D68..2D6E
7704 TIFINAGH, // 2D6F..2D70
7705 UNKNOWN, // 2D71..2D7E
7706 TIFINAGH, // 2D7F
7707 ETHIOPIC, // 2D80..2D96
7708 UNKNOWN, // 2D97..2D9F
7709 ETHIOPIC, // 2DA0..2DA6
7710 UNKNOWN, // 2DA7
7711 ETHIOPIC, // 2DA8..2DAE
7712 UNKNOWN, // 2DAF
7713 ETHIOPIC, // 2DB0..2DB6
7714 UNKNOWN, // 2DB7
7715 ETHIOPIC, // 2DB8..2DBE
7716 UNKNOWN, // 2DBF
7717 ETHIOPIC, // 2DC0..2DC6
7718 UNKNOWN, // 2DC7
7719 ETHIOPIC, // 2DC8..2DCE
7720 UNKNOWN, // 2DCF
7721 ETHIOPIC, // 2DD0..2DD6
7722 UNKNOWN, // 2DD7
7723 ETHIOPIC, // 2DD8..2DDE
7724 UNKNOWN, // 2DDF
7725 CYRILLIC, // 2DE0..2DFF
7726 COMMON, // 2E00..2E5D
7727 UNKNOWN, // 2E5E..2E7F
7728 HAN, // 2E80..2E99
7729 UNKNOWN, // 2E9A
7730 HAN, // 2E9B..2EF3
7731 UNKNOWN, // 2EF4..2EFF
7732 HAN, // 2F00..2FD5
7733 UNKNOWN, // 2FD6..2FEF
7734 COMMON, // 2FF0..3004
7735 HAN, // 3005
7736 COMMON, // 3006
7737 HAN, // 3007
7738 COMMON, // 3008..3020
7739 HAN, // 3021..3029
7740 INHERITED, // 302A..302D
7741 HANGUL, // 302E..302F
7742 COMMON, // 3030..3037
7743 HAN, // 3038..303B
7744 COMMON, // 303C..303F
7745 UNKNOWN, // 3040
7746 HIRAGANA, // 3041..3096
7747 UNKNOWN, // 3097..3098
7748 INHERITED, // 3099..309A
7749 COMMON, // 309B..309C
7750 HIRAGANA, // 309D..309F
7751 COMMON, // 30A0
7752 KATAKANA, // 30A1..30FA
7753 COMMON, // 30FB..30FC
7754 KATAKANA, // 30FD..30FF
7755 UNKNOWN, // 3100..3104
7756 BOPOMOFO, // 3105..312F
7757 UNKNOWN, // 3130
7758 HANGUL, // 3131..318E
7759 UNKNOWN, // 318F
7760 COMMON, // 3190..319F
7761 BOPOMOFO, // 31A0..31BF
7762 COMMON, // 31C0..31E3
7763 UNKNOWN, // 31E4..31EE
7764 COMMON, // 31EF
7765 KATAKANA, // 31F0..31FF
7766 HANGUL, // 3200..321E
7767 UNKNOWN, // 321F
7768 COMMON, // 3220..325F
7769 HANGUL, // 3260..327E
7770 COMMON, // 327F..32CF
7771 KATAKANA, // 32D0..32FE
7772 COMMON, // 32FF
7773 KATAKANA, // 3300..3357
7774 COMMON, // 3358..33FF
7775 HAN, // 3400..4DBF
7776 COMMON, // 4DC0..4DFF
7777 HAN, // 4E00..9FFF
7778 YI, // A000..A48C
7779 UNKNOWN, // A48D..A48F
7780 YI, // A490..A4C6
7781 UNKNOWN, // A4C7..A4CF
7782 LISU, // A4D0..A4FF
7783 VAI, // A500..A62B
7784 UNKNOWN, // A62C..A63F
7785 CYRILLIC, // A640..A69F
7786 BAMUM, // A6A0..A6F7
7787 UNKNOWN, // A6F8..A6FF
7788 COMMON, // A700..A721
7789 LATIN, // A722..A787
7790 COMMON, // A788..A78A
7791 LATIN, // A78B..A7CA
7792 UNKNOWN, // A7CB..A7CF
7793 LATIN, // A7D0..A7D1
7794 UNKNOWN, // A7D2
7795 LATIN, // A7D3
7796 UNKNOWN, // A7D4
7797 LATIN, // A7D5..A7D9
7798 UNKNOWN, // A7DA..A7F1
7799 LATIN, // A7F2..A7FF
7800 SYLOTI_NAGRI, // A800..A82C
7801 UNKNOWN, // A82D..A82F
7802 COMMON, // A830..A839
7803 UNKNOWN, // A83A..A83F
7804 PHAGS_PA, // A840..A877
7805 UNKNOWN, // A878..A87F
7806 SAURASHTRA, // A880..A8C5
7807 UNKNOWN, // A8C6..A8CD
7808 SAURASHTRA, // A8CE..A8D9
7809 UNKNOWN, // A8DA..A8DF
7810 DEVANAGARI, // A8E0..A8FF
7811 KAYAH_LI, // A900..A92D
7812 COMMON, // A92E
7813 KAYAH_LI, // A92F
7814 REJANG, // A930..A953
7815 UNKNOWN, // A954..A95E
7816 REJANG, // A95F
7817 HANGUL, // A960..A97C
7818 UNKNOWN, // A97D..A97F
7819 JAVANESE, // A980..A9CD
7820 UNKNOWN, // A9CE
7821 COMMON, // A9CF
7822 JAVANESE, // A9D0..A9D9
7823 UNKNOWN, // A9DA..A9DD
7824 JAVANESE, // A9DE..A9DF
7825 MYANMAR, // A9E0..A9FE
7826 UNKNOWN, // A9FF
7827 CHAM, // AA00..AA36
7828 UNKNOWN, // AA37..AA3F
7829 CHAM, // AA40..AA4D
7830 UNKNOWN, // AA4E..AA4F
7831 CHAM, // AA50..AA59
7832 UNKNOWN, // AA5A..AA5B
7833 CHAM, // AA5C..AA5F
7834 MYANMAR, // AA60..AA7F
7835 TAI_VIET, // AA80..AAC2
7836 UNKNOWN, // AAC3..AADA
7837 TAI_VIET, // AADB..AADF
7838 MEETEI_MAYEK, // AAE0..AAF6
7839 UNKNOWN, // AAF7..AB00
7840 ETHIOPIC, // AB01..AB06
7841 UNKNOWN, // AB07..AB08
7842 ETHIOPIC, // AB09..AB0E
7843 UNKNOWN, // AB0F..AB10
7844 ETHIOPIC, // AB11..AB16
7845 UNKNOWN, // AB17..AB1F
7846 ETHIOPIC, // AB20..AB26
7847 UNKNOWN, // AB27
7848 ETHIOPIC, // AB28..AB2E
7849 UNKNOWN, // AB2F
7850 LATIN, // AB30..AB5A
7851 COMMON, // AB5B
7852 LATIN, // AB5C..AB64
7853 GREEK, // AB65
7854 LATIN, // AB66..AB69
7855 COMMON, // AB6A..AB6B
7856 UNKNOWN, // AB6C..AB6F
7857 CHEROKEE, // AB70..ABBF
7858 MEETEI_MAYEK, // ABC0..ABED
7859 UNKNOWN, // ABEE..ABEF
7860 MEETEI_MAYEK, // ABF0..ABF9
7861 UNKNOWN, // ABFA..ABFF
7862 HANGUL, // AC00..D7A3
7863 UNKNOWN, // D7A4..D7AF
7864 HANGUL, // D7B0..D7C6
7865 UNKNOWN, // D7C7..D7CA
7866 HANGUL, // D7CB..D7FB
7867 UNKNOWN, // D7FC..F8FF
7868 HAN, // F900..FA6D
7869 UNKNOWN, // FA6E..FA6F
7870 HAN, // FA70..FAD9
7871 UNKNOWN, // FADA..FAFF
7872 LATIN, // FB00..FB06
7873 UNKNOWN, // FB07..FB12
7874 ARMENIAN, // FB13..FB17
7875 UNKNOWN, // FB18..FB1C
7876 HEBREW, // FB1D..FB36
7877 UNKNOWN, // FB37
7878 HEBREW, // FB38..FB3C
7879 UNKNOWN, // FB3D
7880 HEBREW, // FB3E
7881 UNKNOWN, // FB3F
7882 HEBREW, // FB40..FB41
7883 UNKNOWN, // FB42
7884 HEBREW, // FB43..FB44
7885 UNKNOWN, // FB45
7886 HEBREW, // FB46..FB4F
7887 ARABIC, // FB50..FBC2
7888 UNKNOWN, // FBC3..FBD2
7889 ARABIC, // FBD3..FD3D
7890 COMMON, // FD3E..FD3F
7891 ARABIC, // FD40..FD8F
7892 UNKNOWN, // FD90..FD91
7893 ARABIC, // FD92..FDC7
7894 UNKNOWN, // FDC8..FDCE
7895 ARABIC, // FDCF
7896 UNKNOWN, // FDD0..FDEF
7897 ARABIC, // FDF0..FDFF
7898 INHERITED, // FE00..FE0F
7899 COMMON, // FE10..FE19
7900 UNKNOWN, // FE1A..FE1F
7901 INHERITED, // FE20..FE2D
7902 CYRILLIC, // FE2E..FE2F
7903 COMMON, // FE30..FE52
7904 UNKNOWN, // FE53
7905 COMMON, // FE54..FE66
7906 UNKNOWN, // FE67
7907 COMMON, // FE68..FE6B
7908 UNKNOWN, // FE6C..FE6F
7909 ARABIC, // FE70..FE74
7910 UNKNOWN, // FE75
7911 ARABIC, // FE76..FEFC
7912 UNKNOWN, // FEFD..FEFE
7913 COMMON, // FEFF
7914 UNKNOWN, // FF00
7915 COMMON, // FF01..FF20
7916 LATIN, // FF21..FF3A
7917 COMMON, // FF3B..FF40
7918 LATIN, // FF41..FF5A
7919 COMMON, // FF5B..FF65
7920 KATAKANA, // FF66..FF6F
7921 COMMON, // FF70
7922 KATAKANA, // FF71..FF9D
7923 COMMON, // FF9E..FF9F
7924 HANGUL, // FFA0..FFBE
7925 UNKNOWN, // FFBF..FFC1
7926 HANGUL, // FFC2..FFC7
7927 UNKNOWN, // FFC8..FFC9
7928 HANGUL, // FFCA..FFCF
7929 UNKNOWN, // FFD0..FFD1
7930 HANGUL, // FFD2..FFD7
7931 UNKNOWN, // FFD8..FFD9
7932 HANGUL, // FFDA..FFDC
7933 UNKNOWN, // FFDD..FFDF
7934 COMMON, // FFE0..FFE6
7935 UNKNOWN, // FFE7
7936 COMMON, // FFE8..FFEE
7937 UNKNOWN, // FFEF..FFF8
7938 COMMON, // FFF9..FFFD
7939 UNKNOWN, // FFFE..FFFF
7940 LINEAR_B, // 10000..1000B
7941 UNKNOWN, // 1000C
7942 LINEAR_B, // 1000D..10026
7943 UNKNOWN, // 10027
7944 LINEAR_B, // 10028..1003A
7945 UNKNOWN, // 1003B
7946 LINEAR_B, // 1003C..1003D
7947 UNKNOWN, // 1003E
7948 LINEAR_B, // 1003F..1004D
7949 UNKNOWN, // 1004E..1004F
7950 LINEAR_B, // 10050..1005D
7951 UNKNOWN, // 1005E..1007F
7952 LINEAR_B, // 10080..100FA
7953 UNKNOWN, // 100FB..100FF
7954 COMMON, // 10100..10102
7955 UNKNOWN, // 10103..10106
7956 COMMON, // 10107..10133
7957 UNKNOWN, // 10134..10136
7958 COMMON, // 10137..1013F
7959 GREEK, // 10140..1018E
7960 UNKNOWN, // 1018F
7961 COMMON, // 10190..1019C
7962 UNKNOWN, // 1019D..1019F
7963 GREEK, // 101A0
7964 UNKNOWN, // 101A1..101CF
7965 COMMON, // 101D0..101FC
7966 INHERITED, // 101FD
7967 UNKNOWN, // 101FE..1027F
7968 LYCIAN, // 10280..1029C
7969 UNKNOWN, // 1029D..1029F
7970 CARIAN, // 102A0..102D0
7971 UNKNOWN, // 102D1..102DF
7972 INHERITED, // 102E0
7973 COMMON, // 102E1..102FB
7974 UNKNOWN, // 102FC..102FF
7975 OLD_ITALIC, // 10300..10323
7976 UNKNOWN, // 10324..1032C
7977 OLD_ITALIC, // 1032D..1032F
7978 GOTHIC, // 10330..1034A
7979 UNKNOWN, // 1034B..1034F
7980 OLD_PERMIC, // 10350..1037A
7981 UNKNOWN, // 1037B..1037F
7982 UGARITIC, // 10380..1039D
7983 UNKNOWN, // 1039E
7984 UGARITIC, // 1039F
7985 OLD_PERSIAN, // 103A0..103C3
7986 UNKNOWN, // 103C4..103C7
7987 OLD_PERSIAN, // 103C8..103D5
7988 UNKNOWN, // 103D6..103FF
7989 DESERET, // 10400..1044F
7990 SHAVIAN, // 10450..1047F
7991 OSMANYA, // 10480..1049D
7992 UNKNOWN, // 1049E..1049F
7993 OSMANYA, // 104A0..104A9
7994 UNKNOWN, // 104AA..104AF
7995 OSAGE, // 104B0..104D3
7996 UNKNOWN, // 104D4..104D7
7997 OSAGE, // 104D8..104FB
7998 UNKNOWN, // 104FC..104FF
7999 ELBASAN, // 10500..10527
8000 UNKNOWN, // 10528..1052F
8001 CAUCASIAN_ALBANIAN, // 10530..10563
8002 UNKNOWN, // 10564..1056E
8003 CAUCASIAN_ALBANIAN, // 1056F
8004 VITHKUQI, // 10570..1057A
8005 UNKNOWN, // 1057B
8006 VITHKUQI, // 1057C..1058A
8007 UNKNOWN, // 1058B
8008 VITHKUQI, // 1058C..10592
8009 UNKNOWN, // 10593
8010 VITHKUQI, // 10594..10595
8011 UNKNOWN, // 10596
8012 VITHKUQI, // 10597..105A1
8013 UNKNOWN, // 105A2
8014 VITHKUQI, // 105A3..105B1
8015 UNKNOWN, // 105B2
8016 VITHKUQI, // 105B3..105B9
8017 UNKNOWN, // 105BA
8018 VITHKUQI, // 105BB..105BC
8019 UNKNOWN, // 105BD..105FF
8020 LINEAR_A, // 10600..10736
8021 UNKNOWN, // 10737..1073F
8022 LINEAR_A, // 10740..10755
8023 UNKNOWN, // 10756..1075F
8024 LINEAR_A, // 10760..10767
8025 UNKNOWN, // 10768..1077F
8026 LATIN, // 10780..10785
8027 UNKNOWN, // 10786
8028 LATIN, // 10787..107B0
8029 UNKNOWN, // 107B1
8030 LATIN, // 107B2..107BA
8031 UNKNOWN, // 107BB..107FF
8032 CYPRIOT, // 10800..10805
8033 UNKNOWN, // 10806..10807
8034 CYPRIOT, // 10808
8035 UNKNOWN, // 10809
8036 CYPRIOT, // 1080A..10835
8037 UNKNOWN, // 10836
8038 CYPRIOT, // 10837..10838
8039 UNKNOWN, // 10839..1083B
8040 CYPRIOT, // 1083C
8041 UNKNOWN, // 1083D..1083E
8042 CYPRIOT, // 1083F
8043 IMPERIAL_ARAMAIC, // 10840..10855
8044 UNKNOWN, // 10856
8045 IMPERIAL_ARAMAIC, // 10857..1085F
8046 PALMYRENE, // 10860..1087F
8047 NABATAEAN, // 10880..1089E
8048 UNKNOWN, // 1089F..108A6
8049 NABATAEAN, // 108A7..108AF
8050 UNKNOWN, // 108B0..108DF
8051 HATRAN, // 108E0..108F2
8052 UNKNOWN, // 108F3
8053 HATRAN, // 108F4..108F5
8054 UNKNOWN, // 108F6..108FA
8055 HATRAN, // 108FB..108FF
8056 PHOENICIAN, // 10900..1091B
8057 UNKNOWN, // 1091C..1091E
8058 PHOENICIAN, // 1091F
8059 LYDIAN, // 10920..10939
8060 UNKNOWN, // 1093A..1093E
8061 LYDIAN, // 1093F
8062 UNKNOWN, // 10940..1097F
8063 MEROITIC_HIEROGLYPHS, // 10980..1099F
8064 MEROITIC_CURSIVE, // 109A0..109B7
8065 UNKNOWN, // 109B8..109BB
8066 MEROITIC_CURSIVE, // 109BC..109CF
8067 UNKNOWN, // 109D0..109D1
8068 MEROITIC_CURSIVE, // 109D2..109FF
8069 KHAROSHTHI, // 10A00..10A03
8070 UNKNOWN, // 10A04
8071 KHAROSHTHI, // 10A05..10A06
8072 UNKNOWN, // 10A07..10A0B
8073 KHAROSHTHI, // 10A0C..10A13
8074 UNKNOWN, // 10A14
8075 KHAROSHTHI, // 10A15..10A17
8076 UNKNOWN, // 10A18
8077 KHAROSHTHI, // 10A19..10A35
8078 UNKNOWN, // 10A36..10A37
8079 KHAROSHTHI, // 10A38..10A3A
8080 UNKNOWN, // 10A3B..10A3E
8081 KHAROSHTHI, // 10A3F..10A48
8082 UNKNOWN, // 10A49..10A4F
8083 KHAROSHTHI, // 10A50..10A58
8084 UNKNOWN, // 10A59..10A5F
8085 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8086 OLD_NORTH_ARABIAN, // 10A80..10A9F
8087 UNKNOWN, // 10AA0..10ABF
8088 MANICHAEAN, // 10AC0..10AE6
8089 UNKNOWN, // 10AE7..10AEA
8090 MANICHAEAN, // 10AEB..10AF6
8091 UNKNOWN, // 10AF7..10AFF
8092 AVESTAN, // 10B00..10B35
8093 UNKNOWN, // 10B36..10B38
8094 AVESTAN, // 10B39..10B3F
8095 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8096 UNKNOWN, // 10B56..10B57
8097 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8098 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8099 UNKNOWN, // 10B73..10B77
8100 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8101 PSALTER_PAHLAVI, // 10B80..10B91
8102 UNKNOWN, // 10B92..10B98
8103 PSALTER_PAHLAVI, // 10B99..10B9C
8104 UNKNOWN, // 10B9D..10BA8
8105 PSALTER_PAHLAVI, // 10BA9..10BAF
8106 UNKNOWN, // 10BB0..10BFF
8107 OLD_TURKIC, // 10C00..10C48
8108 UNKNOWN, // 10C49..10C7F
8109 OLD_HUNGARIAN, // 10C80..10CB2
8110 UNKNOWN, // 10CB3..10CBF
8111 OLD_HUNGARIAN, // 10CC0..10CF2
8112 UNKNOWN, // 10CF3..10CF9
8113 OLD_HUNGARIAN, // 10CFA..10CFF
8114 HANIFI_ROHINGYA, // 10D00..10D27
8115 UNKNOWN, // 10D28..10D2F
8116 HANIFI_ROHINGYA, // 10D30..10D39
8117 UNKNOWN, // 10D3A..10E5F
8118 ARABIC, // 10E60..10E7E
8119 UNKNOWN, // 10E7F
8120 YEZIDI, // 10E80..10EA9
8121 UNKNOWN, // 10EAA
8122 YEZIDI, // 10EAB..10EAD
8123 UNKNOWN, // 10EAE..10EAF
8124 YEZIDI, // 10EB0..10EB1
8125 UNKNOWN, // 10EB2..10EFC
8126 ARABIC, // 10EFD..10EFF
8127 OLD_SOGDIAN, // 10F00..10F27
8128 UNKNOWN, // 10F28..10F2F
8129 SOGDIAN, // 10F30..10F59
8130 UNKNOWN, // 10F5A..10F6F
8131 OLD_UYGHUR, // 10F70..10F89
8132 UNKNOWN, // 10F8A..10FAF
8133 CHORASMIAN, // 10FB0..10FCB
8134 UNKNOWN, // 10FCC..10FDF
8135 ELYMAIC, // 10FE0..10FF6
8136 UNKNOWN, // 10FF7..10FFF
8137 BRAHMI, // 11000..1104D
8138 UNKNOWN, // 1104E..11051
8139 BRAHMI, // 11052..11075
8140 UNKNOWN, // 11076..1107E
8141 BRAHMI, // 1107F
8142 KAITHI, // 11080..110C2
8143 UNKNOWN, // 110C3..110CC
8144 KAITHI, // 110CD
8145 UNKNOWN, // 110CE..110CF
8146 SORA_SOMPENG, // 110D0..110E8
8147 UNKNOWN, // 110E9..110EF
8148 SORA_SOMPENG, // 110F0..110F9
8149 UNKNOWN, // 110FA..110FF
8150 CHAKMA, // 11100..11134
8151 UNKNOWN, // 11135
8152 CHAKMA, // 11136..11147
8153 UNKNOWN, // 11148..1114F
8154 MAHAJANI, // 11150..11176
8155 UNKNOWN, // 11177..1117F
8156 SHARADA, // 11180..111DF
8157 UNKNOWN, // 111E0
8158 SINHALA, // 111E1..111F4
8159 UNKNOWN, // 111F5..111FF
8160 KHOJKI, // 11200..11211
8161 UNKNOWN, // 11212
8162 KHOJKI, // 11213..11241
8163 UNKNOWN, // 11242..1127F
8164 MULTANI, // 11280..11286
8165 UNKNOWN, // 11287
8166 MULTANI, // 11288
8167 UNKNOWN, // 11289
8168 MULTANI, // 1128A..1128D
8169 UNKNOWN, // 1128E
8170 MULTANI, // 1128F..1129D
8171 UNKNOWN, // 1129E
8172 MULTANI, // 1129F..112A9
8173 UNKNOWN, // 112AA..112AF
8174 KHUDAWADI, // 112B0..112EA
8175 UNKNOWN, // 112EB..112EF
8176 KHUDAWADI, // 112F0..112F9
8177 UNKNOWN, // 112FA..112FF
8178 GRANTHA, // 11300..11303
8179 UNKNOWN, // 11304
8180 GRANTHA, // 11305..1130C
8181 UNKNOWN, // 1130D..1130E
8182 GRANTHA, // 1130F..11310
8183 UNKNOWN, // 11311..11312
8184 GRANTHA, // 11313..11328
8185 UNKNOWN, // 11329
8186 GRANTHA, // 1132A..11330
8187 UNKNOWN, // 11331
8188 GRANTHA, // 11332..11333
8189 UNKNOWN, // 11334
8190 GRANTHA, // 11335..11339
8191 UNKNOWN, // 1133A
8192 INHERITED, // 1133B
8193 GRANTHA, // 1133C..11344
8194 UNKNOWN, // 11345..11346
8195 GRANTHA, // 11347..11348
8196 UNKNOWN, // 11349..1134A
8197 GRANTHA, // 1134B..1134D
8198 UNKNOWN, // 1134E..1134F
8199 GRANTHA, // 11350
8200 UNKNOWN, // 11351..11356
8201 GRANTHA, // 11357
8202 UNKNOWN, // 11358..1135C
8203 GRANTHA, // 1135D..11363
8204 UNKNOWN, // 11364..11365
8205 GRANTHA, // 11366..1136C
8206 UNKNOWN, // 1136D..1136F
8207 GRANTHA, // 11370..11374
8208 UNKNOWN, // 11375..113FF
8209 NEWA, // 11400..1145B
8210 UNKNOWN, // 1145C
8211 NEWA, // 1145D..11461
8212 UNKNOWN, // 11462..1147F
8213 TIRHUTA, // 11480..114C7
8214 UNKNOWN, // 114C8..114CF
8215 TIRHUTA, // 114D0..114D9
8216 UNKNOWN, // 114DA..1157F
8217 SIDDHAM, // 11580..115B5
8218 UNKNOWN, // 115B6..115B7
8219 SIDDHAM, // 115B8..115DD
8220 UNKNOWN, // 115DE..115FF
8221 MODI, // 11600..11644
8222 UNKNOWN, // 11645..1164F
8223 MODI, // 11650..11659
8224 UNKNOWN, // 1165A..1165F
8225 MONGOLIAN, // 11660..1166C
8226 UNKNOWN, // 1166D..1167F
8227 TAKRI, // 11680..116B9
8228 UNKNOWN, // 116BA..116BF
8229 TAKRI, // 116C0..116C9
8230 UNKNOWN, // 116CA..116FF
8231 AHOM, // 11700..1171A
8232 UNKNOWN, // 1171B..1171C
8233 AHOM, // 1171D..1172B
8234 UNKNOWN, // 1172C..1172F
8235 AHOM, // 11730..11746
8236 UNKNOWN, // 11747..117FF
8237 DOGRA, // 11800..1183B
8238 UNKNOWN, // 1183C..1189F
8239 WARANG_CITI, // 118A0..118F2
8240 UNKNOWN, // 118F3..118FE
8241 WARANG_CITI, // 118FF
8242 DIVES_AKURU, // 11900..11906
8243 UNKNOWN, // 11907..11908
8244 DIVES_AKURU, // 11909
8245 UNKNOWN, // 1190A..1190B
8246 DIVES_AKURU, // 1190C..11913
8247 UNKNOWN, // 11914
8248 DIVES_AKURU, // 11915..11916
8249 UNKNOWN, // 11917
8250 DIVES_AKURU, // 11918..11935
8251 UNKNOWN, // 11936
8252 DIVES_AKURU, // 11937..11938
8253 UNKNOWN, // 11939..1193A
8254 DIVES_AKURU, // 1193B..11946
8255 UNKNOWN, // 11947..1194F
8256 DIVES_AKURU, // 11950..11959
8257 UNKNOWN, // 1195A..1199F
8258 NANDINAGARI, // 119A0..119A7
8259 UNKNOWN, // 119A8..119A9
8260 NANDINAGARI, // 119AA..119D7
8261 UNKNOWN, // 119D8..119D9
8262 NANDINAGARI, // 119DA..119E4
8263 UNKNOWN, // 119E5..119FF
8264 ZANABAZAR_SQUARE, // 11A00..11A47
8265 UNKNOWN, // 11A48..11A4F
8266 SOYOMBO, // 11A50..11AA2
8267 UNKNOWN, // 11AA3..11AAF
8268 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8269 PAU_CIN_HAU, // 11AC0..11AF8
8270 UNKNOWN, // 11AF9..11AFF
8271 DEVANAGARI, // 11B00..11B09
8272 UNKNOWN, // 11B0A..11BFF
8273 BHAIKSUKI, // 11C00..11C08
8274 UNKNOWN, // 11C09
8275 BHAIKSUKI, // 11C0A..11C36
8276 UNKNOWN, // 11C37
8277 BHAIKSUKI, // 11C38..11C45
8278 UNKNOWN, // 11C46..11C4F
8279 BHAIKSUKI, // 11C50..11C6C
8280 UNKNOWN, // 11C6D..11C6F
8281 MARCHEN, // 11C70..11C8F
8282 UNKNOWN, // 11C90..11C91
8283 MARCHEN, // 11C92..11CA7
8284 UNKNOWN, // 11CA8
8285 MARCHEN, // 11CA9..11CB6
8286 UNKNOWN, // 11CB7..11CFF
8287 MASARAM_GONDI, // 11D00..11D06
8288 UNKNOWN, // 11D07
8289 MASARAM_GONDI, // 11D08..11D09
8290 UNKNOWN, // 11D0A
8291 MASARAM_GONDI, // 11D0B..11D36
8292 UNKNOWN, // 11D37..11D39
8293 MASARAM_GONDI, // 11D3A
8294 UNKNOWN, // 11D3B
8295 MASARAM_GONDI, // 11D3C..11D3D
8296 UNKNOWN, // 11D3E
8297 MASARAM_GONDI, // 11D3F..11D47
8298 UNKNOWN, // 11D48..11D4F
8299 MASARAM_GONDI, // 11D50..11D59
8300 UNKNOWN, // 11D5A..11D5F
8301 GUNJALA_GONDI, // 11D60..11D65
8302 UNKNOWN, // 11D66
8303 GUNJALA_GONDI, // 11D67..11D68
8304 UNKNOWN, // 11D69
8305 GUNJALA_GONDI, // 11D6A..11D8E
8306 UNKNOWN, // 11D8F
8307 GUNJALA_GONDI, // 11D90..11D91
8308 UNKNOWN, // 11D92
8309 GUNJALA_GONDI, // 11D93..11D98
8310 UNKNOWN, // 11D99..11D9F
8311 GUNJALA_GONDI, // 11DA0..11DA9
8312 UNKNOWN, // 11DAA..11EDF
8313 MAKASAR, // 11EE0..11EF8
8314 UNKNOWN, // 11EF9..11EFF
8315 KAWI, // 11F00..11F10
8316 UNKNOWN, // 11F11
8317 KAWI, // 11F12..11F3A
8318 UNKNOWN, // 11F3B..11F3D
8319 KAWI, // 11F3E..11F59
8320 UNKNOWN, // 11F5A..11FAF
8321 LISU, // 11FB0
8322 UNKNOWN, // 11FB1..11FBF
8323 TAMIL, // 11FC0..11FF1
8324 UNKNOWN, // 11FF2..11FFE
8325 TAMIL, // 11FFF
8326 CUNEIFORM, // 12000..12399
8327 UNKNOWN, // 1239A..123FF
8328 CUNEIFORM, // 12400..1246E
8329 UNKNOWN, // 1246F
8330 CUNEIFORM, // 12470..12474
8331 UNKNOWN, // 12475..1247F
8332 CUNEIFORM, // 12480..12543
8333 UNKNOWN, // 12544..12F8F
8334 CYPRO_MINOAN, // 12F90..12FF2
8335 UNKNOWN, // 12FF3..12FFF
8336 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8337 UNKNOWN, // 13456..143FF
8338 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8339 UNKNOWN, // 14647..167FF
8340 BAMUM, // 16800..16A38
8341 UNKNOWN, // 16A39..16A3F
8342 MRO, // 16A40..16A5E
8343 UNKNOWN, // 16A5F
8344 MRO, // 16A60..16A69
8345 UNKNOWN, // 16A6A..16A6D
8346 MRO, // 16A6E..16A6F
8347 TANGSA, // 16A70..16ABE
8348 UNKNOWN, // 16ABF
8349 TANGSA, // 16AC0..16AC9
8350 UNKNOWN, // 16ACA..16ACF
8351 BASSA_VAH, // 16AD0..16AED
8352 UNKNOWN, // 16AEE..16AEF
8353 BASSA_VAH, // 16AF0..16AF5
8354 UNKNOWN, // 16AF6..16AFF
8355 PAHAWH_HMONG, // 16B00..16B45
8356 UNKNOWN, // 16B46..16B4F
8357 PAHAWH_HMONG, // 16B50..16B59
8358 UNKNOWN, // 16B5A
8359 PAHAWH_HMONG, // 16B5B..16B61
8360 UNKNOWN, // 16B62
8361 PAHAWH_HMONG, // 16B63..16B77
8362 UNKNOWN, // 16B78..16B7C
8363 PAHAWH_HMONG, // 16B7D..16B8F
8364 UNKNOWN, // 16B90..16E3F
8365 MEDEFAIDRIN, // 16E40..16E9A
8366 UNKNOWN, // 16E9B..16EFF
8367 MIAO, // 16F00..16F4A
8368 UNKNOWN, // 16F4B..16F4E
8369 MIAO, // 16F4F..16F87
8370 UNKNOWN, // 16F88..16F8E
8371 MIAO, // 16F8F..16F9F
8372 UNKNOWN, // 16FA0..16FDF
8373 TANGUT, // 16FE0
8374 NUSHU, // 16FE1
8375 HAN, // 16FE2..16FE3
8376 KHITAN_SMALL_SCRIPT, // 16FE4
8377 UNKNOWN, // 16FE5..16FEF
8378 HAN, // 16FF0..16FF1
8379 UNKNOWN, // 16FF2..16FFF
8380 TANGUT, // 17000..187F7
8381 UNKNOWN, // 187F8..187FF
8382 TANGUT, // 18800..18AFF
8383 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8384 UNKNOWN, // 18CD6..18CFF
8385 TANGUT, // 18D00..18D08
8386 UNKNOWN, // 18D09..1AFEF
8387 KATAKANA, // 1AFF0..1AFF3
8388 UNKNOWN, // 1AFF4
8389 KATAKANA, // 1AFF5..1AFFB
8390 UNKNOWN, // 1AFFC
8391 KATAKANA, // 1AFFD..1AFFE
8392 UNKNOWN, // 1AFFF
8393 KATAKANA, // 1B000
8394 HIRAGANA, // 1B001..1B11F
8395 KATAKANA, // 1B120..1B122
8396 UNKNOWN, // 1B123..1B131
8397 HIRAGANA, // 1B132
8398 UNKNOWN, // 1B133..1B14F
8399 HIRAGANA, // 1B150..1B152
8400 UNKNOWN, // 1B153..1B154
8401 KATAKANA, // 1B155
8402 UNKNOWN, // 1B156..1B163
8403 KATAKANA, // 1B164..1B167
8404 UNKNOWN, // 1B168..1B16F
8405 NUSHU, // 1B170..1B2FB
8406 UNKNOWN, // 1B2FC..1BBFF
8407 DUPLOYAN, // 1BC00..1BC6A
8408 UNKNOWN, // 1BC6B..1BC6F
8409 DUPLOYAN, // 1BC70..1BC7C
8410 UNKNOWN, // 1BC7D..1BC7F
8411 DUPLOYAN, // 1BC80..1BC88
8412 UNKNOWN, // 1BC89..1BC8F
8413 DUPLOYAN, // 1BC90..1BC99
8414 UNKNOWN, // 1BC9A..1BC9B
8415 DUPLOYAN, // 1BC9C..1BC9F
8416 COMMON, // 1BCA0..1BCA3
8417 UNKNOWN, // 1BCA4..1CEFF
8418 INHERITED, // 1CF00..1CF2D
8419 UNKNOWN, // 1CF2E..1CF2F
8420 INHERITED, // 1CF30..1CF46
8421 UNKNOWN, // 1CF47..1CF4F
8422 COMMON, // 1CF50..1CFC3
8423 UNKNOWN, // 1CFC4..1CFFF
8424 COMMON, // 1D000..1D0F5
8425 UNKNOWN, // 1D0F6..1D0FF
8426 COMMON, // 1D100..1D126
8427 UNKNOWN, // 1D127..1D128
8428 COMMON, // 1D129..1D166
8429 INHERITED, // 1D167..1D169
8430 COMMON, // 1D16A..1D17A
8431 INHERITED, // 1D17B..1D182
8432 COMMON, // 1D183..1D184
8433 INHERITED, // 1D185..1D18B
8434 COMMON, // 1D18C..1D1A9
8435 INHERITED, // 1D1AA..1D1AD
8436 COMMON, // 1D1AE..1D1EA
8437 UNKNOWN, // 1D1EB..1D1FF
8438 GREEK, // 1D200..1D245
8439 UNKNOWN, // 1D246..1D2BF
8440 COMMON, // 1D2C0..1D2D3
8441 UNKNOWN, // 1D2D4..1D2DF
8442 COMMON, // 1D2E0..1D2F3
8443 UNKNOWN, // 1D2F4..1D2FF
8444 COMMON, // 1D300..1D356
8445 UNKNOWN, // 1D357..1D35F
8446 COMMON, // 1D360..1D378
8447 UNKNOWN, // 1D379..1D3FF
8448 COMMON, // 1D400..1D454
8449 UNKNOWN, // 1D455
8450 COMMON, // 1D456..1D49C
8451 UNKNOWN, // 1D49D
8452 COMMON, // 1D49E..1D49F
8453 UNKNOWN, // 1D4A0..1D4A1
8454 COMMON, // 1D4A2
8455 UNKNOWN, // 1D4A3..1D4A4
8456 COMMON, // 1D4A5..1D4A6
8457 UNKNOWN, // 1D4A7..1D4A8
8458 COMMON, // 1D4A9..1D4AC
8459 UNKNOWN, // 1D4AD
8460 COMMON, // 1D4AE..1D4B9
8461 UNKNOWN, // 1D4BA
8462 COMMON, // 1D4BB
8463 UNKNOWN, // 1D4BC
8464 COMMON, // 1D4BD..1D4C3
8465 UNKNOWN, // 1D4C4
8466 COMMON, // 1D4C5..1D505
8467 UNKNOWN, // 1D506
8468 COMMON, // 1D507..1D50A
8469 UNKNOWN, // 1D50B..1D50C
8470 COMMON, // 1D50D..1D514
8471 UNKNOWN, // 1D515
8472 COMMON, // 1D516..1D51C
8473 UNKNOWN, // 1D51D
8474 COMMON, // 1D51E..1D539
8475 UNKNOWN, // 1D53A
8476 COMMON, // 1D53B..1D53E
8477 UNKNOWN, // 1D53F
8478 COMMON, // 1D540..1D544
8479 UNKNOWN, // 1D545
8480 COMMON, // 1D546
8481 UNKNOWN, // 1D547..1D549
8482 COMMON, // 1D54A..1D550
8483 UNKNOWN, // 1D551
8484 COMMON, // 1D552..1D6A5
8485 UNKNOWN, // 1D6A6..1D6A7
8486 COMMON, // 1D6A8..1D7CB
8487 UNKNOWN, // 1D7CC..1D7CD
8488 COMMON, // 1D7CE..1D7FF
8489 SIGNWRITING, // 1D800..1DA8B
8490 UNKNOWN, // 1DA8C..1DA9A
8491 SIGNWRITING, // 1DA9B..1DA9F
8492 UNKNOWN, // 1DAA0
8493 SIGNWRITING, // 1DAA1..1DAAF
8494 UNKNOWN, // 1DAB0..1DEFF
8495 LATIN, // 1DF00..1DF1E
8496 UNKNOWN, // 1DF1F..1DF24
8497 LATIN, // 1DF25..1DF2A
8498 UNKNOWN, // 1DF2B..1DFFF
8499 GLAGOLITIC, // 1E000..1E006
8500 UNKNOWN, // 1E007
8501 GLAGOLITIC, // 1E008..1E018
8502 UNKNOWN, // 1E019..1E01A
8503 GLAGOLITIC, // 1E01B..1E021
8504 UNKNOWN, // 1E022
8505 GLAGOLITIC, // 1E023..1E024
8506 UNKNOWN, // 1E025
8507 GLAGOLITIC, // 1E026..1E02A
8508 UNKNOWN, // 1E02B..1E02F
8509 CYRILLIC, // 1E030..1E06D
8510 UNKNOWN, // 1E06E..1E08E
8511 CYRILLIC, // 1E08F
8512 UNKNOWN, // 1E090..1E0FF
8513 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8514 UNKNOWN, // 1E12D..1E12F
8515 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8516 UNKNOWN, // 1E13E..1E13F
8517 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8518 UNKNOWN, // 1E14A..1E14D
8519 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8520 UNKNOWN, // 1E150..1E28F
8521 TOTO, // 1E290..1E2AE
8522 UNKNOWN, // 1E2AF..1E2BF
8523 WANCHO, // 1E2C0..1E2F9
8524 UNKNOWN, // 1E2FA..1E2FE
8525 WANCHO, // 1E2FF
8526 UNKNOWN, // 1E300..1E4CF
8527 NAG_MUNDARI, // 1E4D0..1E4F9
8528 UNKNOWN, // 1E4FA..1E7DF
8529 ETHIOPIC, // 1E7E0..1E7E6
8530 UNKNOWN, // 1E7E7
8531 ETHIOPIC, // 1E7E8..1E7EB
8532 UNKNOWN, // 1E7EC
8533 ETHIOPIC, // 1E7ED..1E7EE
8534 UNKNOWN, // 1E7EF
8535 ETHIOPIC, // 1E7F0..1E7FE
8536 UNKNOWN, // 1E7FF
8537 MENDE_KIKAKUI, // 1E800..1E8C4
8538 UNKNOWN, // 1E8C5..1E8C6
8539 MENDE_KIKAKUI, // 1E8C7..1E8D6
8540 UNKNOWN, // 1E8D7..1E8FF
8541 ADLAM, // 1E900..1E94B
8542 UNKNOWN, // 1E94C..1E94F
8543 ADLAM, // 1E950..1E959
8544 UNKNOWN, // 1E95A..1E95D
8545 ADLAM, // 1E95E..1E95F
8546 UNKNOWN, // 1E960..1EC70
8547 COMMON, // 1EC71..1ECB4
8548 UNKNOWN, // 1ECB5..1ED00
8549 COMMON, // 1ED01..1ED3D
8550 UNKNOWN, // 1ED3E..1EDFF
8551 ARABIC, // 1EE00..1EE03
8552 UNKNOWN, // 1EE04
8553 ARABIC, // 1EE05..1EE1F
8554 UNKNOWN, // 1EE20
8555 ARABIC, // 1EE21..1EE22
8556 UNKNOWN, // 1EE23
8557 ARABIC, // 1EE24
8558 UNKNOWN, // 1EE25..1EE26
8559 ARABIC, // 1EE27
8560 UNKNOWN, // 1EE28
8561 ARABIC, // 1EE29..1EE32
8562 UNKNOWN, // 1EE33
8563 ARABIC, // 1EE34..1EE37
8564 UNKNOWN, // 1EE38
8565 ARABIC, // 1EE39
8566 UNKNOWN, // 1EE3A
8567 ARABIC, // 1EE3B
8568 UNKNOWN, // 1EE3C..1EE41
8569 ARABIC, // 1EE42
8570 UNKNOWN, // 1EE43..1EE46
8571 ARABIC, // 1EE47
8572 UNKNOWN, // 1EE48
8573 ARABIC, // 1EE49
8574 UNKNOWN, // 1EE4A
8575 ARABIC, // 1EE4B
8576 UNKNOWN, // 1EE4C
8577 ARABIC, // 1EE4D..1EE4F
8578 UNKNOWN, // 1EE50
8579 ARABIC, // 1EE51..1EE52
8580 UNKNOWN, // 1EE53
8581 ARABIC, // 1EE54
8582 UNKNOWN, // 1EE55..1EE56
8583 ARABIC, // 1EE57
8584 UNKNOWN, // 1EE58
8585 ARABIC, // 1EE59
8586 UNKNOWN, // 1EE5A
8587 ARABIC, // 1EE5B
8588 UNKNOWN, // 1EE5C
8589 ARABIC, // 1EE5D
8590 UNKNOWN, // 1EE5E
8591 ARABIC, // 1EE5F
8592 UNKNOWN, // 1EE60
8593 ARABIC, // 1EE61..1EE62
8594 UNKNOWN, // 1EE63
8595 ARABIC, // 1EE64
8596 UNKNOWN, // 1EE65..1EE66
8597 ARABIC, // 1EE67..1EE6A
8598 UNKNOWN, // 1EE6B
8599 ARABIC, // 1EE6C..1EE72
8600 UNKNOWN, // 1EE73
8601 ARABIC, // 1EE74..1EE77
8602 UNKNOWN, // 1EE78
8603 ARABIC, // 1EE79..1EE7C
8604 UNKNOWN, // 1EE7D
8605 ARABIC, // 1EE7E
8606 UNKNOWN, // 1EE7F
8607 ARABIC, // 1EE80..1EE89
8608 UNKNOWN, // 1EE8A
8609 ARABIC, // 1EE8B..1EE9B
8610 UNKNOWN, // 1EE9C..1EEA0
8611 ARABIC, // 1EEA1..1EEA3
8612 UNKNOWN, // 1EEA4
8613 ARABIC, // 1EEA5..1EEA9
8614 UNKNOWN, // 1EEAA
8615 ARABIC, // 1EEAB..1EEBB
8616 UNKNOWN, // 1EEBC..1EEEF
8617 ARABIC, // 1EEF0..1EEF1
8618 UNKNOWN, // 1EEF2..1EFFF
8619 COMMON, // 1F000..1F02B
8620 UNKNOWN, // 1F02C..1F02F
8621 COMMON, // 1F030..1F093
8622 UNKNOWN, // 1F094..1F09F
8623 COMMON, // 1F0A0..1F0AE
8624 UNKNOWN, // 1F0AF..1F0B0
8625 COMMON, // 1F0B1..1F0BF
8626 UNKNOWN, // 1F0C0
8627 COMMON, // 1F0C1..1F0CF
8628 UNKNOWN, // 1F0D0
8629 COMMON, // 1F0D1..1F0F5
8630 UNKNOWN, // 1F0F6..1F0FF
8631 COMMON, // 1F100..1F1AD
8632 UNKNOWN, // 1F1AE..1F1E5
8633 COMMON, // 1F1E6..1F1FF
8634 HIRAGANA, // 1F200
8635 COMMON, // 1F201..1F202
8636 UNKNOWN, // 1F203..1F20F
8637 COMMON, // 1F210..1F23B
8638 UNKNOWN, // 1F23C..1F23F
8639 COMMON, // 1F240..1F248
8640 UNKNOWN, // 1F249..1F24F
8641 COMMON, // 1F250..1F251
8642 UNKNOWN, // 1F252..1F25F
8643 COMMON, // 1F260..1F265
8644 UNKNOWN, // 1F266..1F2FF
8645 COMMON, // 1F300..1F6D7
8646 UNKNOWN, // 1F6D8..1F6DB
8647 COMMON, // 1F6DC..1F6EC
8648 UNKNOWN, // 1F6ED..1F6EF
8649 COMMON, // 1F6F0..1F6FC
8650 UNKNOWN, // 1F6FD..1F6FF
8651 COMMON, // 1F700..1F776
8652 UNKNOWN, // 1F777..1F77A
8653 COMMON, // 1F77B..1F7D9
8654 UNKNOWN, // 1F7DA..1F7DF
8655 COMMON, // 1F7E0..1F7EB
8656 UNKNOWN, // 1F7EC..1F7EF
8657 COMMON, // 1F7F0
8658 UNKNOWN, // 1F7F1..1F7FF
8659 COMMON, // 1F800..1F80B
8660 UNKNOWN, // 1F80C..1F80F
8661 COMMON, // 1F810..1F847
8662 UNKNOWN, // 1F848..1F84F
8663 COMMON, // 1F850..1F859
8664 UNKNOWN, // 1F85A..1F85F
8665 COMMON, // 1F860..1F887
8666 UNKNOWN, // 1F888..1F88F
8667 COMMON, // 1F890..1F8AD
8668 UNKNOWN, // 1F8AE..1F8AF
8669 COMMON, // 1F8B0..1F8B1
8670 UNKNOWN, // 1F8B2..1F8FF
8671 COMMON, // 1F900..1FA53
8672 UNKNOWN, // 1FA54..1FA5F
8673 COMMON, // 1FA60..1FA6D
8674 UNKNOWN, // 1FA6E..1FA6F
8675 COMMON, // 1FA70..1FA7C
8676 UNKNOWN, // 1FA7D..1FA7F
8677 COMMON, // 1FA80..1FA88
8678 UNKNOWN, // 1FA89..1FA8F
8679 COMMON, // 1FA90..1FABD
8680 UNKNOWN, // 1FABE
8681 COMMON, // 1FABF..1FAC5
8682 UNKNOWN, // 1FAC6..1FACD
8683 COMMON, // 1FACE..1FADB
8684 UNKNOWN, // 1FADC..1FADF
8685 COMMON, // 1FAE0..1FAE8
8686 UNKNOWN, // 1FAE9..1FAEF
8687 COMMON, // 1FAF0..1FAF8
8688 UNKNOWN, // 1FAF9..1FAFF
8689 COMMON, // 1FB00..1FB92
8690 UNKNOWN, // 1FB93
8691 COMMON, // 1FB94..1FBCA
8692 UNKNOWN, // 1FBCB..1FBEF
8693 COMMON, // 1FBF0..1FBF9
8694 UNKNOWN, // 1FBFA..1FFFF
8695 HAN, // 20000..2A6DF
8696 UNKNOWN, // 2A6E0..2A6FF
8697 HAN, // 2A700..2B739
8698 UNKNOWN, // 2B73A..2B73F
8699 HAN, // 2B740..2B81D
8700 UNKNOWN, // 2B81E..2B81F
8701 HAN, // 2B820..2CEA1
8702 UNKNOWN, // 2CEA2..2CEAF
8703 HAN, // 2CEB0..2EBE0
8704 UNKNOWN, // 2EBE1..2EBEF
8705 HAN, // 2EBF0..2EE5D
8706 UNKNOWN, // 2EE5E..2F7FF
8707 HAN, // 2F800..2FA1D
8708 UNKNOWN, // 2FA1E..2FFFF
8709 HAN, // 30000..3134A
8710 UNKNOWN, // 3134B..3134F
8711 HAN, // 31350..323AF
8712 UNKNOWN, // 323B0..E0000
8713 COMMON, // E0001
8714 UNKNOWN, // E0002..E001F
8715 COMMON, // E0020..E007F
8716 UNKNOWN, // E0080..E00FF
8717 INHERITED, // E0100..E01EF
8718 UNKNOWN, // E01F0..10FFFF
8719 };
8720
8721 private static final HashMap<String, Character.UnicodeScript> aliases;
8722 static {
8723 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
8724 aliases.put("ADLM", ADLAM);
8725 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
8726 aliases.put("AHOM", AHOM);
8727 aliases.put("ARAB", ARABIC);
8728 aliases.put("ARMI", IMPERIAL_ARAMAIC);
8729 aliases.put("ARMN", ARMENIAN);
8730 aliases.put("AVST", AVESTAN);
8731 aliases.put("BALI", BALINESE);
8732 aliases.put("BAMU", BAMUM);
8733 aliases.put("BASS", BASSA_VAH);
8734 aliases.put("BATK", BATAK);
8735 aliases.put("BENG", BENGALI);
8736 aliases.put("BHKS", BHAIKSUKI);
8737 aliases.put("BOPO", BOPOMOFO);
8738 aliases.put("BRAH", BRAHMI);
8739 aliases.put("BRAI", BRAILLE);
8740 aliases.put("BUGI", BUGINESE);
8741 aliases.put("BUHD", BUHID);
8742 aliases.put("CAKM", CHAKMA);
8743 aliases.put("CANS", CANADIAN_ABORIGINAL);
8744 aliases.put("CARI", CARIAN);
8745 aliases.put("CHAM", CHAM);
8746 aliases.put("CHER", CHEROKEE);
8747 aliases.put("CHRS", CHORASMIAN);
8748 aliases.put("COPT", COPTIC);
8749 aliases.put("CPMN", CYPRO_MINOAN);
8750 aliases.put("CPRT", CYPRIOT);
8751 aliases.put("CYRL", CYRILLIC);
8752 aliases.put("DEVA", DEVANAGARI);
8753 aliases.put("DIAK", DIVES_AKURU);
8754 aliases.put("DOGR", DOGRA);
8755 aliases.put("DSRT", DESERET);
8756 aliases.put("DUPL", DUPLOYAN);
8757 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
8758 aliases.put("ELBA", ELBASAN);
8759 aliases.put("ELYM", ELYMAIC);
8760 aliases.put("ETHI", ETHIOPIC);
8761 aliases.put("GEOR", GEORGIAN);
8762 aliases.put("GLAG", GLAGOLITIC);
8763 aliases.put("GONG", GUNJALA_GONDI);
8764 aliases.put("GONM", MASARAM_GONDI);
8765 aliases.put("GOTH", GOTHIC);
8766 aliases.put("GRAN", GRANTHA);
8767 aliases.put("GREK", GREEK);
8768 aliases.put("GUJR", GUJARATI);
8769 aliases.put("GURU", GURMUKHI);
8770 aliases.put("HANG", HANGUL);
8771 aliases.put("HANI", HAN);
8772 aliases.put("HANO", HANUNOO);
8773 aliases.put("HATR", HATRAN);
8774 aliases.put("HEBR", HEBREW);
8775 aliases.put("HIRA", HIRAGANA);
8776 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
8777 aliases.put("HMNG", PAHAWH_HMONG);
8778 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
8779 aliases.put("HUNG", OLD_HUNGARIAN);
8780 aliases.put("ITAL", OLD_ITALIC);
8781 aliases.put("JAVA", JAVANESE);
8782 aliases.put("KALI", KAYAH_LI);
8783 aliases.put("KANA", KATAKANA);
8784 aliases.put("KAWI", KAWI);
8785 aliases.put("KHAR", KHAROSHTHI);
8786 aliases.put("KHMR", KHMER);
8787 aliases.put("KHOJ", KHOJKI);
8788 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
8789 aliases.put("KNDA", KANNADA);
8790 aliases.put("KTHI", KAITHI);
8791 aliases.put("LANA", TAI_THAM);
8792 aliases.put("LAOO", LAO);
8793 aliases.put("LATN", LATIN);
8794 aliases.put("LEPC", LEPCHA);
8795 aliases.put("LIMB", LIMBU);
8796 aliases.put("LINA", LINEAR_A);
8797 aliases.put("LINB", LINEAR_B);
8798 aliases.put("LISU", LISU);
8799 aliases.put("LYCI", LYCIAN);
8800 aliases.put("LYDI", LYDIAN);
8801 aliases.put("MAHJ", MAHAJANI);
8802 aliases.put("MAKA", MAKASAR);
8803 aliases.put("MAND", MANDAIC);
8804 aliases.put("MANI", MANICHAEAN);
8805 aliases.put("MARC", MARCHEN);
8806 aliases.put("MEDF", MEDEFAIDRIN);
8807 aliases.put("MEND", MENDE_KIKAKUI);
8808 aliases.put("MERC", MEROITIC_CURSIVE);
8809 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
8810 aliases.put("MLYM", MALAYALAM);
8811 aliases.put("MODI", MODI);
8812 aliases.put("MONG", MONGOLIAN);
8813 aliases.put("MROO", MRO);
8814 aliases.put("MTEI", MEETEI_MAYEK);
8815 aliases.put("MULT", MULTANI);
8816 aliases.put("MYMR", MYANMAR);
8817 aliases.put("NAGM", NAG_MUNDARI);
8818 aliases.put("NAND", NANDINAGARI);
8819 aliases.put("NARB", OLD_NORTH_ARABIAN);
8820 aliases.put("NBAT", NABATAEAN);
8821 aliases.put("NEWA", NEWA);
8822 aliases.put("NKOO", NKO);
8823 aliases.put("NSHU", NUSHU);
8824 aliases.put("OGAM", OGHAM);
8825 aliases.put("OLCK", OL_CHIKI);
8826 aliases.put("ORKH", OLD_TURKIC);
8827 aliases.put("ORYA", ORIYA);
8828 aliases.put("OSGE", OSAGE);
8829 aliases.put("OSMA", OSMANYA);
8830 aliases.put("OUGR", OLD_UYGHUR);
8831 aliases.put("PALM", PALMYRENE);
8832 aliases.put("PAUC", PAU_CIN_HAU);
8833 aliases.put("PERM", OLD_PERMIC);
8834 aliases.put("PHAG", PHAGS_PA);
8835 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
8836 aliases.put("PHLP", PSALTER_PAHLAVI);
8837 aliases.put("PHNX", PHOENICIAN);
8838 aliases.put("PLRD", MIAO);
8839 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
8840 aliases.put("RJNG", REJANG);
8841 aliases.put("ROHG", HANIFI_ROHINGYA);
8842 aliases.put("RUNR", RUNIC);
8843 aliases.put("SAMR", SAMARITAN);
8844 aliases.put("SARB", OLD_SOUTH_ARABIAN);
8845 aliases.put("SAUR", SAURASHTRA);
8846 aliases.put("SGNW", SIGNWRITING);
8847 aliases.put("SHAW", SHAVIAN);
8848 aliases.put("SHRD", SHARADA);
8849 aliases.put("SIDD", SIDDHAM);
8850 aliases.put("SIND", KHUDAWADI);
8851 aliases.put("SINH", SINHALA);
8852 aliases.put("SOGD", SOGDIAN);
8853 aliases.put("SOGO", OLD_SOGDIAN);
8854 aliases.put("SORA", SORA_SOMPENG);
8855 aliases.put("SOYO", SOYOMBO);
8856 aliases.put("SUND", SUNDANESE);
8857 aliases.put("SYLO", SYLOTI_NAGRI);
8858 aliases.put("SYRC", SYRIAC);
8859 aliases.put("TAGB", TAGBANWA);
8860 aliases.put("TAKR", TAKRI);
8861 aliases.put("TALE", TAI_LE);
8862 aliases.put("TALU", NEW_TAI_LUE);
8863 aliases.put("TAML", TAMIL);
8864 aliases.put("TANG", TANGUT);
8865 aliases.put("TAVT", TAI_VIET);
8866 aliases.put("TELU", TELUGU);
8867 aliases.put("TFNG", TIFINAGH);
8868 aliases.put("TGLG", TAGALOG);
8869 aliases.put("THAA", THAANA);
8870 aliases.put("THAI", THAI);
8871 aliases.put("TIBT", TIBETAN);
8872 aliases.put("TIRH", TIRHUTA);
8873 aliases.put("TNSA", TANGSA);
8874 aliases.put("TOTO", TOTO);
8875 aliases.put("UGAR", UGARITIC);
8876 aliases.put("VAII", VAI);
8877 aliases.put("VITH", VITHKUQI);
8878 aliases.put("WARA", WARANG_CITI);
8879 aliases.put("WCHO", WANCHO);
8880 aliases.put("XPEO", OLD_PERSIAN);
8881 aliases.put("XSUX", CUNEIFORM);
8882 aliases.put("YEZI", YEZIDI);
8883 aliases.put("YIII", YI);
8884 aliases.put("ZANB", ZANABAZAR_SQUARE);
8885 aliases.put("ZINH", INHERITED);
8886 aliases.put("ZYYY", COMMON);
8887 aliases.put("ZZZZ", UNKNOWN);
8888 }
8889
8890 /**
8891 * Returns the enum constant representing the Unicode script of which
8892 * the given character (Unicode code point) is assigned to.
8893 *
8894 * @param codePoint the character (Unicode code point) in question.
8895 * @return The {@code UnicodeScript} constant representing the
8896 * Unicode script of which this character is assigned to.
8897 *
8898 * @throws IllegalArgumentException if the specified
8899 * {@code codePoint} is an invalid Unicode code point.
8900 * @see Character#isValidCodePoint(int)
8901 *
8902 */
8903 public static UnicodeScript of(int codePoint) {
8904 if (!isValidCodePoint(codePoint))
8905 throw new IllegalArgumentException(
8906 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8907 int type = getType(codePoint);
8908 // leave SURROGATE and PRIVATE_USE for table lookup
8909 if (type == UNASSIGNED)
8910 return UNKNOWN;
8911 int index = Arrays.binarySearch(scriptStarts, codePoint);
8912 if (index < 0)
8913 index = -index - 2;
8914 return scripts[index];
8915 }
8916
8917 /**
8918 * Returns the UnicodeScript constant with the given Unicode script
8919 * name or the script name alias. Script names and their aliases are
8920 * determined by The Unicode Standard. The files {@code Scripts.txt}
8921 * and {@code PropertyValueAliases.txt} define script names
8922 * and the script name aliases for a particular version of the
8923 * standard. The {@link Character} class specifies the version of
8924 * the standard that it supports.
8925 * <p>
8926 * Character case is ignored for all of the valid script names.
8927 * The en_US locale's case mapping rules are used to provide
8928 * case-insensitive string comparisons for script name validation.
8929 *
8930 * @param scriptName A {@code UnicodeScript} name.
8931 * @return The {@code UnicodeScript} constant identified
8932 * by {@code scriptName}
8933 * @throws IllegalArgumentException if {@code scriptName} is an
8934 * invalid name
8935 * @throws NullPointerException if {@code scriptName} is null
8936 */
8937 public static final UnicodeScript forName(String scriptName) {
8938 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
8939 //.replace(' ', '_'));
8940 UnicodeScript sc = aliases.get(scriptName);
8941 if (sc != null)
8942 return sc;
8943 return valueOf(scriptName);
8944 }
8945 }
8946
8947 /**
8948 * The value of the {@code Character}.
8949 *
8950 * @serial
8951 */
8952 private final char value;
8953
8954 /** use serialVersionUID from JDK 1.0.2 for interoperability */
8955 @java.io.Serial
8956 private static final long serialVersionUID = 3786198910865385080L;
8957
8958 /**
8959 * Constructs a newly allocated {@code Character} object that
8960 * represents the specified {@code char} value.
8961 *
8962 * @param value the value to be represented by the
8963 * {@code Character} object.
8964 *
8965 * @deprecated
8966 * It is rarely appropriate to use this constructor. The static factory
8967 * {@link #valueOf(char)} is generally a better choice, as it is
8968 * likely to yield significantly better space and time performance.
8969 */
8970 @Deprecated(since="9", forRemoval = true)
8971 public Character(char value) {
8972 this.value = value;
8973 }
8974
8975 private static final class CharacterCache {
8976 private CharacterCache(){}
8977
8978 @Stable
8979 static final Character[] cache;
8980 static Character[] archivedCache;
8981
8982 static {
8983 int size = 127 + 1;
8984
8985 // Load and use the archived cache if it exists
8986 CDS.initializeFromArchive(CharacterCache.class);
8987 if (archivedCache == null) {
8988 Character[] c = new Character[size];
8989 for (int i = 0; i < size; i++) {
8990 c[i] = new Character((char) i);
8991 }
8992 archivedCache = c;
8993 }
8994 cache = archivedCache;
8995 assert cache.length == size;
8996 }
8997 }
8998
8999 /**
9000 * Returns a {@code Character} instance representing the specified
9001 * {@code char} value.
9002 * If a new {@code Character} instance is not required, this method
9003 * should generally be used in preference to the constructor
9004 * {@link #Character(char)}, as this method is likely to yield
9005 * significantly better space and time performance by caching
9006 * frequently requested values.
9007 *
9008 * This method will always cache values in the range {@code
9009 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9010 * cache other values outside of this range.
9011 *
9012 * @param c a char value.
9013 * @return a {@code Character} instance representing {@code c}.
9014 * @since 1.5
9015 */
9016 @IntrinsicCandidate
9017 public static Character valueOf(char c) {
9018 if (c <= 127) { // must cache
9019 return CharacterCache.cache[(int)c];
9020 }
9021 return new Character(c);
9022 }
9023
9024 /**
9025 * Returns the value of this {@code Character} object.
9026 * @return the primitive {@code char} value represented by
9027 * this object.
9028 */
9029 @IntrinsicCandidate
9030 public char charValue() {
9031 return value;
9032 }
9033
9034 /**
9035 * Returns a hash code for this {@code Character}; equal to the result
9036 * of invoking {@code charValue()}.
9037 *
9038 * @return a hash code value for this {@code Character}
9039 */
9040 @Override
9041 public int hashCode() {
9042 return Character.hashCode(value);
9043 }
9044
9045 /**
9046 * Returns a hash code for a {@code char} value; compatible with
9047 * {@code Character.hashCode()}.
9048 *
9049 * @since 1.8
9050 *
9051 * @param value The {@code char} for which to return a hash code.
9052 * @return a hash code value for a {@code char} value.
9053 */
9054 public static int hashCode(char value) {
9055 return (int)value;
9056 }
9057
9058 /**
9059 * Compares this object against the specified object.
9060 * The result is {@code true} if and only if the argument is not
9061 * {@code null} and is a {@code Character} object that
9062 * represents the same {@code char} value as this object.
9063 *
9064 * @param obj the object to compare with.
9065 * @return {@code true} if the objects are the same;
9066 * {@code false} otherwise.
9067 */
9068 public boolean equals(Object obj) {
9069 if (obj instanceof Character c) {
9070 return value == c.charValue();
9071 }
9072 return false;
9073 }
9074
9075 /**
9076 * Returns a {@code String} object representing this
9077 * {@code Character}'s value. The result is a string of
9078 * length 1 whose sole component is the primitive
9079 * {@code char} value represented by this
9080 * {@code Character} object.
9081 *
9082 * @return a string representation of this object.
9083 */
9084 @Override
9085 public String toString() {
9086 return String.valueOf(value);
9087 }
9088
9089 /**
9090 * Returns a {@code String} object representing the
9091 * specified {@code char}. The result is a string of length
9092 * 1 consisting solely of the specified {@code char}.
9093 *
9094 * @apiNote This method cannot handle <a
9095 * href="#supplementary"> supplementary characters</a>. To support
9096 * all Unicode characters, including supplementary characters, use
9097 * the {@link #toString(int)} method.
9098 *
9099 * @param c the {@code char} to be converted
9100 * @return the string representation of the specified {@code char}
9101 * @since 1.4
9102 */
9103 public static String toString(char c) {
9104 return String.valueOf(c);
9105 }
9106
9107 /**
9108 * Returns a {@code String} object representing the
9109 * specified character (Unicode code point). The result is a string of
9110 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9111 *
9112 * @param codePoint the {@code codePoint} to be converted
9113 * @return the string representation of the specified {@code codePoint}
9114 * @throws IllegalArgumentException if the specified
9115 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9116 * valid Unicode code point}.
9117 * @since 11
9118 */
9119 public static String toString(int codePoint) {
9120 return String.valueOfCodePoint(codePoint);
9121 }
9122
9123 /**
9124 * Determines whether the specified code point is a valid
9125 * <a href="http://www.unicode.org/glossary/#code_point">
9126 * Unicode code point value</a>.
9127 *
9128 * @param codePoint the Unicode code point to be tested
9129 * @return {@code true} if the specified code point value is between
9130 * {@link #MIN_CODE_POINT} and
9131 * {@link #MAX_CODE_POINT} inclusive;
9132 * {@code false} otherwise.
9133 * @since 1.5
9134 */
9135 public static boolean isValidCodePoint(int codePoint) {
9136 // Optimized form of:
9137 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9138 int plane = codePoint >>> 16;
9139 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9140 }
9141
9142 /**
9143 * Determines whether the specified character (Unicode code point)
9144 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9145 * Such code points can be represented using a single {@code char}.
9146 *
9147 * @param codePoint the character (Unicode code point) to be tested
9148 * @return {@code true} if the specified code point is between
9149 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9150 * {@code false} otherwise.
9151 * @since 1.7
9152 */
9153 public static boolean isBmpCodePoint(int codePoint) {
9154 return codePoint >>> 16 == 0;
9155 // Optimized form of:
9156 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9157 // We consistently use logical shift (>>>) to facilitate
9158 // additional runtime optimizations.
9159 }
9160
9161 /**
9162 * Determines whether the specified character (Unicode code point)
9163 * is in the <a href="#supplementary">supplementary character</a> range.
9164 *
9165 * @param codePoint the character (Unicode code point) to be tested
9166 * @return {@code true} if the specified code point is between
9167 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9168 * {@link #MAX_CODE_POINT} inclusive;
9169 * {@code false} otherwise.
9170 * @since 1.5
9171 */
9172 public static boolean isSupplementaryCodePoint(int codePoint) {
9173 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9174 && codePoint < MAX_CODE_POINT + 1;
9175 }
9176
9177 /**
9178 * Determines if the given {@code char} value is a
9179 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9180 * Unicode high-surrogate code unit</a>
9181 * (also known as <i>leading-surrogate code unit</i>).
9182 *
9183 * <p>Such values do not represent characters by themselves,
9184 * but are used in the representation of
9185 * <a href="#supplementary">supplementary characters</a>
9186 * in the UTF-16 encoding.
9187 *
9188 * @param ch the {@code char} value to be tested.
9189 * @return {@code true} if the {@code char} value is between
9190 * {@link #MIN_HIGH_SURROGATE} and
9191 * {@link #MAX_HIGH_SURROGATE} inclusive;
9192 * {@code false} otherwise.
9193 * @see Character#isLowSurrogate(char)
9194 * @see Character.UnicodeBlock#of(int)
9195 * @since 1.5
9196 */
9197 public static boolean isHighSurrogate(char ch) {
9198 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9199 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9200 }
9201
9202 /**
9203 * Determines if the given {@code char} value is a
9204 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9205 * Unicode low-surrogate code unit</a>
9206 * (also known as <i>trailing-surrogate code unit</i>).
9207 *
9208 * <p>Such values do not represent characters by themselves,
9209 * but are used in the representation of
9210 * <a href="#supplementary">supplementary characters</a>
9211 * in the UTF-16 encoding.
9212 *
9213 * @param ch the {@code char} value to be tested.
9214 * @return {@code true} if the {@code char} value is between
9215 * {@link #MIN_LOW_SURROGATE} and
9216 * {@link #MAX_LOW_SURROGATE} inclusive;
9217 * {@code false} otherwise.
9218 * @see Character#isHighSurrogate(char)
9219 * @since 1.5
9220 */
9221 public static boolean isLowSurrogate(char ch) {
9222 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9223 }
9224
9225 /**
9226 * Determines if the given {@code char} value is a Unicode
9227 * <i>surrogate code unit</i>.
9228 *
9229 * <p>Such values do not represent characters by themselves,
9230 * but are used in the representation of
9231 * <a href="#supplementary">supplementary characters</a>
9232 * in the UTF-16 encoding.
9233 *
9234 * <p>A char value is a surrogate code unit if and only if it is either
9235 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9236 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9237 *
9238 * @param ch the {@code char} value to be tested.
9239 * @return {@code true} if the {@code char} value is between
9240 * {@link #MIN_SURROGATE} and
9241 * {@link #MAX_SURROGATE} inclusive;
9242 * {@code false} otherwise.
9243 * @since 1.7
9244 */
9245 public static boolean isSurrogate(char ch) {
9246 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9247 }
9248
9249 /**
9250 * Determines whether the specified pair of {@code char}
9251 * values is a valid
9252 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9253 * Unicode surrogate pair</a>.
9254 *
9255 * <p>This method is equivalent to the expression:
9256 * <blockquote><pre>{@code
9257 * isHighSurrogate(high) && isLowSurrogate(low)
9258 * }</pre></blockquote>
9259 *
9260 * @param high the high-surrogate code value to be tested
9261 * @param low the low-surrogate code value to be tested
9262 * @return {@code true} if the specified high and
9263 * low-surrogate code values represent a valid surrogate pair;
9264 * {@code false} otherwise.
9265 * @since 1.5
9266 */
9267 public static boolean isSurrogatePair(char high, char low) {
9268 return isHighSurrogate(high) && isLowSurrogate(low);
9269 }
9270
9271 /**
9272 * Determines the number of {@code char} values needed to
9273 * represent the specified character (Unicode code point). If the
9274 * specified character is equal to or greater than 0x10000, then
9275 * the method returns 2. Otherwise, the method returns 1.
9276 *
9277 * <p>This method doesn't validate the specified character to be a
9278 * valid Unicode code point. The caller must validate the
9279 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9280 * if necessary.
9281 *
9282 * @param codePoint the character (Unicode code point) to be tested.
9283 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9284 * @see Character#isSupplementaryCodePoint(int)
9285 * @since 1.5
9286 */
9287 public static int charCount(int codePoint) {
9288 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9289 }
9290
9291 /**
9292 * Converts the specified surrogate pair to its supplementary code
9293 * point value. This method does not validate the specified
9294 * surrogate pair. The caller must validate it using {@link
9295 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9296 *
9297 * @param high the high-surrogate code unit
9298 * @param low the low-surrogate code unit
9299 * @return the supplementary code point composed from the
9300 * specified surrogate pair.
9301 * @since 1.5
9302 */
9303 public static int toCodePoint(char high, char low) {
9304 // Optimized form of:
9305 // return ((high - MIN_HIGH_SURROGATE) << 10)
9306 // + (low - MIN_LOW_SURROGATE)
9307 // + MIN_SUPPLEMENTARY_CODE_POINT;
9308 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9309 - (MIN_HIGH_SURROGATE << 10)
9310 - MIN_LOW_SURROGATE);
9311 }
9312
9313 /**
9314 * Returns the code point at the given index of the
9315 * {@code CharSequence}. If the {@code char} value at
9316 * the given index in the {@code CharSequence} is in the
9317 * high-surrogate range, the following index is less than the
9318 * length of the {@code CharSequence}, and the
9319 * {@code char} value at the following index is in the
9320 * low-surrogate range, then the supplementary code point
9321 * corresponding to this surrogate pair is returned. Otherwise,
9322 * the {@code char} value at the given index is returned.
9323 *
9324 * @param seq a sequence of {@code char} values (Unicode code
9325 * units)
9326 * @param index the index to the {@code char} values (Unicode
9327 * code units) in {@code seq} to be converted
9328 * @return the Unicode code point at the given index
9329 * @throws NullPointerException if {@code seq} is null.
9330 * @throws IndexOutOfBoundsException if the value
9331 * {@code index} is negative or not less than
9332 * {@link CharSequence#length() seq.length()}.
9333 * @since 1.5
9334 */
9335 public static int codePointAt(CharSequence seq, int index) {
9336 char c1 = seq.charAt(index);
9337 if (isHighSurrogate(c1) && ++index < seq.length()) {
9338 char c2 = seq.charAt(index);
9339 if (isLowSurrogate(c2)) {
9340 return toCodePoint(c1, c2);
9341 }
9342 }
9343 return c1;
9344 }
9345
9346 /**
9347 * Returns the code point at the given index of the
9348 * {@code char} array. If the {@code char} value at
9349 * the given index in the {@code char} array is in the
9350 * high-surrogate range, the following index is less than the
9351 * length of the {@code char} array, and the
9352 * {@code char} value at the following index is in the
9353 * low-surrogate range, then the supplementary code point
9354 * corresponding to this surrogate pair is returned. Otherwise,
9355 * the {@code char} value at the given index is returned.
9356 *
9357 * @param a the {@code char} array
9358 * @param index the index to the {@code char} values (Unicode
9359 * code units) in the {@code char} array to be converted
9360 * @return the Unicode code point at the given index
9361 * @throws NullPointerException if {@code a} is null.
9362 * @throws IndexOutOfBoundsException if the value
9363 * {@code index} is negative or not less than
9364 * the length of the {@code char} array.
9365 * @since 1.5
9366 */
9367 public static int codePointAt(char[] a, int index) {
9368 return codePointAtImpl(a, index, a.length);
9369 }
9370
9371 /**
9372 * Returns the code point at the given index of the
9373 * {@code char} array, where only array elements with
9374 * {@code index} less than {@code limit} can be used. If
9375 * the {@code char} value at the given index in the
9376 * {@code char} array is in the high-surrogate range, the
9377 * following index is less than the {@code limit}, and the
9378 * {@code char} value at the following index is in the
9379 * low-surrogate range, then the supplementary code point
9380 * corresponding to this surrogate pair is returned. Otherwise,
9381 * the {@code char} value at the given index is returned.
9382 *
9383 * @param a the {@code char} array
9384 * @param index the index to the {@code char} values (Unicode
9385 * code units) in the {@code char} array to be converted
9386 * @param limit the index after the last array element that
9387 * can be used in the {@code char} array
9388 * @return the Unicode code point at the given index
9389 * @throws NullPointerException if {@code a} is null.
9390 * @throws IndexOutOfBoundsException if the {@code index}
9391 * argument is negative or not less than the {@code limit}
9392 * argument, or if the {@code limit} argument is negative or
9393 * greater than the length of the {@code char} array.
9394 * @since 1.5
9395 */
9396 public static int codePointAt(char[] a, int index, int limit) {
9397 if (index >= limit || index < 0 || limit > a.length) {
9398 throw new IndexOutOfBoundsException();
9399 }
9400 return codePointAtImpl(a, index, limit);
9401 }
9402
9403 // throws ArrayIndexOutOfBoundsException if index out of bounds
9404 static int codePointAtImpl(char[] a, int index, int limit) {
9405 char c1 = a[index];
9406 if (isHighSurrogate(c1) && ++index < limit) {
9407 char c2 = a[index];
9408 if (isLowSurrogate(c2)) {
9409 return toCodePoint(c1, c2);
9410 }
9411 }
9412 return c1;
9413 }
9414
9415 /**
9416 * Returns the code point preceding the given index of the
9417 * {@code CharSequence}. If the {@code char} value at
9418 * {@code (index - 1)} in the {@code CharSequence} is in
9419 * the low-surrogate range, {@code (index - 2)} is not
9420 * negative, and the {@code char} value at {@code (index - 2)}
9421 * in the {@code CharSequence} is in the
9422 * high-surrogate range, then the supplementary code point
9423 * corresponding to this surrogate pair is returned. Otherwise,
9424 * the {@code char} value at {@code (index - 1)} is
9425 * returned.
9426 *
9427 * @param seq the {@code CharSequence} instance
9428 * @param index the index following the code point that should be returned
9429 * @return the Unicode code point value before the given index.
9430 * @throws NullPointerException if {@code seq} is null.
9431 * @throws IndexOutOfBoundsException if the {@code index}
9432 * argument is less than 1 or greater than {@link
9433 * CharSequence#length() seq.length()}.
9434 * @since 1.5
9435 */
9436 public static int codePointBefore(CharSequence seq, int index) {
9437 char c2 = seq.charAt(--index);
9438 if (isLowSurrogate(c2) && index > 0) {
9439 char c1 = seq.charAt(--index);
9440 if (isHighSurrogate(c1)) {
9441 return toCodePoint(c1, c2);
9442 }
9443 }
9444 return c2;
9445 }
9446
9447 /**
9448 * Returns the code point preceding the given index of the
9449 * {@code char} array. If the {@code char} value at
9450 * {@code (index - 1)} in the {@code char} array is in
9451 * the low-surrogate range, {@code (index - 2)} is not
9452 * negative, and the {@code char} value at {@code (index - 2)}
9453 * in the {@code char} array is in the
9454 * high-surrogate range, then the supplementary code point
9455 * corresponding to this surrogate pair is returned. Otherwise,
9456 * the {@code char} value at {@code (index - 1)} is
9457 * returned.
9458 *
9459 * @param a the {@code char} array
9460 * @param index the index following the code point that should be returned
9461 * @return the Unicode code point value before the given index.
9462 * @throws NullPointerException if {@code a} is null.
9463 * @throws IndexOutOfBoundsException if the {@code index}
9464 * argument is less than 1 or greater than the length of the
9465 * {@code char} array
9466 * @since 1.5
9467 */
9468 public static int codePointBefore(char[] a, int index) {
9469 return codePointBeforeImpl(a, index, 0);
9470 }
9471
9472 /**
9473 * Returns the code point preceding the given index of the
9474 * {@code char} array, where only array elements with
9475 * {@code index} greater than or equal to {@code start}
9476 * can be used. If the {@code char} value at {@code (index - 1)}
9477 * in the {@code char} array is in the
9478 * low-surrogate range, {@code (index - 2)} is not less than
9479 * {@code start}, and the {@code char} value at
9480 * {@code (index - 2)} in the {@code char} array is in
9481 * the high-surrogate range, then the supplementary code point
9482 * corresponding to this surrogate pair is returned. Otherwise,
9483 * the {@code char} value at {@code (index - 1)} is
9484 * returned.
9485 *
9486 * @param a the {@code char} array
9487 * @param index the index following the code point that should be returned
9488 * @param start the index of the first array element in the
9489 * {@code char} array
9490 * @return the Unicode code point value before the given index.
9491 * @throws NullPointerException if {@code a} is null.
9492 * @throws IndexOutOfBoundsException if the {@code index}
9493 * argument is not greater than the {@code start} argument or
9494 * is greater than the length of the {@code char} array, or
9495 * if the {@code start} argument is negative or not less than
9496 * the length of the {@code char} array.
9497 * @since 1.5
9498 */
9499 public static int codePointBefore(char[] a, int index, int start) {
9500 if (index <= start || start < 0 || index > a.length) {
9501 throw new IndexOutOfBoundsException();
9502 }
9503 return codePointBeforeImpl(a, index, start);
9504 }
9505
9506 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9507 static int codePointBeforeImpl(char[] a, int index, int start) {
9508 char c2 = a[--index];
9509 if (isLowSurrogate(c2) && index > start) {
9510 char c1 = a[--index];
9511 if (isHighSurrogate(c1)) {
9512 return toCodePoint(c1, c2);
9513 }
9514 }
9515 return c2;
9516 }
9517
9518 /**
9519 * Returns the leading surrogate (a
9520 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9521 * high surrogate code unit</a>) of the
9522 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9523 * surrogate pair</a>
9524 * representing the specified supplementary character (Unicode
9525 * code point) in the UTF-16 encoding. If the specified character
9526 * is not a
9527 * <a href="Character.html#supplementary">supplementary character</a>,
9528 * an unspecified {@code char} is returned.
9529 *
9530 * <p>If
9531 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9532 * is {@code true}, then
9533 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9534 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9535 * are also always {@code true}.
9536 *
9537 * @param codePoint a supplementary character (Unicode code point)
9538 * @return the leading surrogate code unit used to represent the
9539 * character in the UTF-16 encoding
9540 * @since 1.7
9541 */
9542 public static char highSurrogate(int codePoint) {
9543 return (char) ((codePoint >>> 10)
9544 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9545 }
9546
9547 /**
9548 * Returns the trailing surrogate (a
9549 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9550 * low surrogate code unit</a>) of the
9551 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9552 * surrogate pair</a>
9553 * representing the specified supplementary character (Unicode
9554 * code point) in the UTF-16 encoding. If the specified character
9555 * is not a
9556 * <a href="Character.html#supplementary">supplementary character</a>,
9557 * an unspecified {@code char} is returned.
9558 *
9559 * <p>If
9560 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9561 * is {@code true}, then
9562 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9563 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9564 * are also always {@code true}.
9565 *
9566 * @param codePoint a supplementary character (Unicode code point)
9567 * @return the trailing surrogate code unit used to represent the
9568 * character in the UTF-16 encoding
9569 * @since 1.7
9570 */
9571 public static char lowSurrogate(int codePoint) {
9572 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
9573 }
9574
9575 /**
9576 * Converts the specified character (Unicode code point) to its
9577 * UTF-16 representation. If the specified code point is a BMP
9578 * (Basic Multilingual Plane or Plane 0) value, the same value is
9579 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
9580 * specified code point is a supplementary character, its
9581 * surrogate values are stored in {@code dst[dstIndex]}
9582 * (high-surrogate) and {@code dst[dstIndex+1]}
9583 * (low-surrogate), and 2 is returned.
9584 *
9585 * @param codePoint the character (Unicode code point) to be converted.
9586 * @param dst an array of {@code char} in which the
9587 * {@code codePoint}'s UTF-16 value is stored.
9588 * @param dstIndex the start index into the {@code dst}
9589 * array where the converted value is stored.
9590 * @return 1 if the code point is a BMP code point, 2 if the
9591 * code point is a supplementary code point.
9592 * @throws IllegalArgumentException if the specified
9593 * {@code codePoint} is not a valid Unicode code point.
9594 * @throws NullPointerException if the specified {@code dst} is null.
9595 * @throws IndexOutOfBoundsException if {@code dstIndex}
9596 * is negative or not less than {@code dst.length}, or if
9597 * {@code dst} at {@code dstIndex} doesn't have enough
9598 * array element(s) to store the resulting {@code char}
9599 * value(s). (If {@code dstIndex} is equal to
9600 * {@code dst.length-1} and the specified
9601 * {@code codePoint} is a supplementary character, the
9602 * high-surrogate value is not stored in
9603 * {@code dst[dstIndex]}.)
9604 * @since 1.5
9605 */
9606 public static int toChars(int codePoint, char[] dst, int dstIndex) {
9607 if (isBmpCodePoint(codePoint)) {
9608 dst[dstIndex] = (char) codePoint;
9609 return 1;
9610 } else if (isValidCodePoint(codePoint)) {
9611 toSurrogates(codePoint, dst, dstIndex);
9612 return 2;
9613 } else {
9614 throw new IllegalArgumentException(
9615 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9616 }
9617 }
9618
9619 /**
9620 * Converts the specified character (Unicode code point) to its
9621 * UTF-16 representation stored in a {@code char} array. If
9622 * the specified code point is a BMP (Basic Multilingual Plane or
9623 * Plane 0) value, the resulting {@code char} array has
9624 * the same value as {@code codePoint}. If the specified code
9625 * point is a supplementary code point, the resulting
9626 * {@code char} array has the corresponding surrogate pair.
9627 *
9628 * @param codePoint a Unicode code point
9629 * @return a {@code char} array having
9630 * {@code codePoint}'s UTF-16 representation.
9631 * @throws IllegalArgumentException if the specified
9632 * {@code codePoint} is not a valid Unicode code point.
9633 * @since 1.5
9634 */
9635 public static char[] toChars(int codePoint) {
9636 if (isBmpCodePoint(codePoint)) {
9637 return new char[] { (char) codePoint };
9638 } else if (isValidCodePoint(codePoint)) {
9639 char[] result = new char[2];
9640 toSurrogates(codePoint, result, 0);
9641 return result;
9642 } else {
9643 throw new IllegalArgumentException(
9644 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9645 }
9646 }
9647
9648 static void toSurrogates(int codePoint, char[] dst, int index) {
9649 // We write elements "backwards" to guarantee all-or-nothing
9650 dst[index+1] = lowSurrogate(codePoint);
9651 dst[index] = highSurrogate(codePoint);
9652 }
9653
9654 /**
9655 * Returns the number of Unicode code points in the text range of
9656 * the specified char sequence. The text range begins at the
9657 * specified {@code beginIndex} and extends to the
9658 * {@code char} at index {@code endIndex - 1}. Thus the
9659 * length (in {@code char}s) of the text range is
9660 * {@code endIndex-beginIndex}. Unpaired surrogates within
9661 * the text range count as one code point each.
9662 *
9663 * @param seq the char sequence
9664 * @param beginIndex the index to the first {@code char} of
9665 * the text range.
9666 * @param endIndex the index after the last {@code char} of
9667 * the text range.
9668 * @return the number of Unicode code points in the specified text
9669 * range
9670 * @throws NullPointerException if {@code seq} is null.
9671 * @throws IndexOutOfBoundsException if the
9672 * {@code beginIndex} is negative, or {@code endIndex}
9673 * is larger than the length of the given sequence, or
9674 * {@code beginIndex} is larger than {@code endIndex}.
9675 * @since 1.5
9676 */
9677 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
9678 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
9679 int n = endIndex - beginIndex;
9680 for (int i = beginIndex; i < endIndex; ) {
9681 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
9682 isLowSurrogate(seq.charAt(i))) {
9683 n--;
9684 i++;
9685 }
9686 }
9687 return n;
9688 }
9689
9690 /**
9691 * Returns the number of Unicode code points in a subarray of the
9692 * {@code char} array argument. The {@code offset}
9693 * argument is the index of the first {@code char} of the
9694 * subarray and the {@code count} argument specifies the
9695 * length of the subarray in {@code char}s. Unpaired
9696 * surrogates within the subarray count as one code point each.
9697 *
9698 * @param a the {@code char} array
9699 * @param offset the index of the first {@code char} in the
9700 * given {@code char} array
9701 * @param count the length of the subarray in {@code char}s
9702 * @return the number of Unicode code points in the specified subarray
9703 * @throws NullPointerException if {@code a} is null.
9704 * @throws IndexOutOfBoundsException if {@code offset} or
9705 * {@code count} is negative, or if {@code offset +
9706 * count} is larger than the length of the given array.
9707 * @since 1.5
9708 */
9709 public static int codePointCount(char[] a, int offset, int count) {
9710 Objects.checkFromIndexSize(offset, count, a.length);
9711 return codePointCountImpl(a, offset, count);
9712 }
9713
9714 static int codePointCountImpl(char[] a, int offset, int count) {
9715 int endIndex = offset + count;
9716 int n = count;
9717 for (int i = offset; i < endIndex; ) {
9718 if (isHighSurrogate(a[i++]) && i < endIndex &&
9719 isLowSurrogate(a[i])) {
9720 n--;
9721 i++;
9722 }
9723 }
9724 return n;
9725 }
9726
9727 /**
9728 * Returns the index within the given char sequence that is offset
9729 * from the given {@code index} by {@code codePointOffset}
9730 * code points. Unpaired surrogates within the text range given by
9731 * {@code index} and {@code codePointOffset} count as
9732 * one code point each.
9733 *
9734 * @param seq the char sequence
9735 * @param index the index to be offset
9736 * @param codePointOffset the offset in code points
9737 * @return the index within the char sequence
9738 * @throws NullPointerException if {@code seq} is null.
9739 * @throws IndexOutOfBoundsException if {@code index}
9740 * is negative or larger than the length of the char sequence,
9741 * or if {@code codePointOffset} is positive and the
9742 * subsequence starting with {@code index} has fewer than
9743 * {@code codePointOffset} code points, or if
9744 * {@code codePointOffset} is negative and the subsequence
9745 * before {@code index} has fewer than the absolute value
9746 * of {@code codePointOffset} code points.
9747 * @since 1.5
9748 */
9749 public static int offsetByCodePoints(CharSequence seq, int index,
9750 int codePointOffset) {
9751 int length = seq.length();
9752 if (index < 0 || index > length) {
9753 throw new IndexOutOfBoundsException();
9754 }
9755
9756 int x = index;
9757 if (codePointOffset >= 0) {
9758 int i;
9759 for (i = 0; x < length && i < codePointOffset; i++) {
9760 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
9761 isLowSurrogate(seq.charAt(x))) {
9762 x++;
9763 }
9764 }
9765 if (i < codePointOffset) {
9766 throw new IndexOutOfBoundsException();
9767 }
9768 } else {
9769 int i;
9770 for (i = codePointOffset; x > 0 && i < 0; i++) {
9771 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
9772 isHighSurrogate(seq.charAt(x-1))) {
9773 x--;
9774 }
9775 }
9776 if (i < 0) {
9777 throw new IndexOutOfBoundsException();
9778 }
9779 }
9780 return x;
9781 }
9782
9783 /**
9784 * Returns the index within the given {@code char} subarray
9785 * that is offset from the given {@code index} by
9786 * {@code codePointOffset} code points. The
9787 * {@code start} and {@code count} arguments specify a
9788 * subarray of the {@code char} array. Unpaired surrogates
9789 * within the text range given by {@code index} and
9790 * {@code codePointOffset} count as one code point each.
9791 *
9792 * @param a the {@code char} array
9793 * @param start the index of the first {@code char} of the
9794 * subarray
9795 * @param count the length of the subarray in {@code char}s
9796 * @param index the index to be offset
9797 * @param codePointOffset the offset in code points
9798 * @return the index within the subarray
9799 * @throws NullPointerException if {@code a} is null.
9800 * @throws IndexOutOfBoundsException
9801 * if {@code start} or {@code count} is negative,
9802 * or if {@code start + count} is larger than the length of
9803 * the given array,
9804 * or if {@code index} is less than {@code start} or
9805 * larger then {@code start + count},
9806 * or if {@code codePointOffset} is positive and the text range
9807 * starting with {@code index} and ending with {@code start + count - 1}
9808 * has fewer than {@code codePointOffset} code
9809 * points,
9810 * or if {@code codePointOffset} is negative and the text range
9811 * starting with {@code start} and ending with {@code index - 1}
9812 * has fewer than the absolute value of
9813 * {@code codePointOffset} code points.
9814 * @since 1.5
9815 */
9816 public static int offsetByCodePoints(char[] a, int start, int count,
9817 int index, int codePointOffset) {
9818 if (count > a.length-start || start < 0 || count < 0
9819 || index < start || index > start+count) {
9820 throw new IndexOutOfBoundsException();
9821 }
9822 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
9823 }
9824
9825 static int offsetByCodePointsImpl(char[]a, int start, int count,
9826 int index, int codePointOffset) {
9827 int x = index;
9828 if (codePointOffset >= 0) {
9829 int limit = start + count;
9830 int i;
9831 for (i = 0; x < limit && i < codePointOffset; i++) {
9832 if (isHighSurrogate(a[x++]) && x < limit &&
9833 isLowSurrogate(a[x])) {
9834 x++;
9835 }
9836 }
9837 if (i < codePointOffset) {
9838 throw new IndexOutOfBoundsException();
9839 }
9840 } else {
9841 int i;
9842 for (i = codePointOffset; x > start && i < 0; i++) {
9843 if (isLowSurrogate(a[--x]) && x > start &&
9844 isHighSurrogate(a[x-1])) {
9845 x--;
9846 }
9847 }
9848 if (i < 0) {
9849 throw new IndexOutOfBoundsException();
9850 }
9851 }
9852 return x;
9853 }
9854
9855 /**
9856 * Determines if the specified character is a lowercase character.
9857 * <p>
9858 * A character is lowercase if its general category type, provided
9859 * by {@code Character.getType(ch)}, is
9860 * {@code LOWERCASE_LETTER}, or it has contributory property
9861 * Other_Lowercase as defined by the Unicode Standard.
9862 * <p>
9863 * The following are examples of lowercase characters:
9864 * <blockquote><pre>
9865 * 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
9866 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9867 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9868 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9869 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9870 * </pre></blockquote>
9871 * <p> Many other Unicode characters are lowercase too.
9872 *
9873 * <p><b>Note:</b> This method cannot handle <a
9874 * href="#supplementary"> supplementary characters</a>. To support
9875 * all Unicode characters, including supplementary characters, use
9876 * the {@link #isLowerCase(int)} method.
9877 *
9878 * @param ch the character to be tested.
9879 * @return {@code true} if the character is lowercase;
9880 * {@code false} otherwise.
9881 * @see Character#isLowerCase(char)
9882 * @see Character#isTitleCase(char)
9883 * @see Character#toLowerCase(char)
9884 * @see Character#getType(char)
9885 */
9886 public static boolean isLowerCase(char ch) {
9887 return isLowerCase((int)ch);
9888 }
9889
9890 /**
9891 * Determines if the specified character (Unicode code point) is a
9892 * lowercase character.
9893 * <p>
9894 * A character is lowercase if its general category type, provided
9895 * by {@link Character#getType getType(codePoint)}, is
9896 * {@code LOWERCASE_LETTER}, or it has contributory property
9897 * Other_Lowercase as defined by the Unicode Standard.
9898 * <p>
9899 * The following are examples of lowercase characters:
9900 * <blockquote><pre>
9901 * 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
9902 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9903 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9904 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9905 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9906 * </pre></blockquote>
9907 * <p> Many other Unicode characters are lowercase too.
9908 *
9909 * @param codePoint the character (Unicode code point) to be tested.
9910 * @return {@code true} if the character is lowercase;
9911 * {@code false} otherwise.
9912 * @see Character#isLowerCase(int)
9913 * @see Character#isTitleCase(int)
9914 * @see Character#toLowerCase(int)
9915 * @see Character#getType(int)
9916 * @since 1.5
9917 */
9918 public static boolean isLowerCase(int codePoint) {
9919 return CharacterData.of(codePoint).isLowerCase(codePoint);
9920 }
9921
9922 /**
9923 * Determines if the specified character is an uppercase character.
9924 * <p>
9925 * A character is uppercase if its general category type, provided by
9926 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
9927 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9928 * <p>
9929 * The following are examples of uppercase characters:
9930 * <blockquote><pre>
9931 * 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
9932 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9933 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9934 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9935 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9936 * </pre></blockquote>
9937 * <p> Many other Unicode characters are uppercase too.
9938 *
9939 * <p><b>Note:</b> This method cannot handle <a
9940 * href="#supplementary"> supplementary characters</a>. To support
9941 * all Unicode characters, including supplementary characters, use
9942 * the {@link #isUpperCase(int)} method.
9943 *
9944 * @param ch the character to be tested.
9945 * @return {@code true} if the character is uppercase;
9946 * {@code false} otherwise.
9947 * @see Character#isLowerCase(char)
9948 * @see Character#isTitleCase(char)
9949 * @see Character#toUpperCase(char)
9950 * @see Character#getType(char)
9951 * @since 1.0
9952 */
9953 public static boolean isUpperCase(char ch) {
9954 return isUpperCase((int)ch);
9955 }
9956
9957 /**
9958 * Determines if the specified character (Unicode code point) is an uppercase character.
9959 * <p>
9960 * A character is uppercase if its general category type, provided by
9961 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
9962 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9963 * <p>
9964 * The following are examples of uppercase characters:
9965 * <blockquote><pre>
9966 * 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
9967 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9968 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9969 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9970 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9971 * </pre></blockquote>
9972 * <p> Many other Unicode characters are uppercase too.
9973 *
9974 * @param codePoint the character (Unicode code point) to be tested.
9975 * @return {@code true} if the character is uppercase;
9976 * {@code false} otherwise.
9977 * @see Character#isLowerCase(int)
9978 * @see Character#isTitleCase(int)
9979 * @see Character#toUpperCase(int)
9980 * @see Character#getType(int)
9981 * @since 1.5
9982 */
9983 public static boolean isUpperCase(int codePoint) {
9984 return CharacterData.of(codePoint).isUpperCase(codePoint);
9985 }
9986
9987 /**
9988 * Determines if the specified character is a titlecase character.
9989 * <p>
9990 * A character is a titlecase character if its general
9991 * category type, provided by {@code Character.getType(ch)},
9992 * is {@code TITLECASE_LETTER}.
9993 * <p>
9994 * Some characters look like pairs of Latin letters. For example, there
9995 * is an uppercase letter that looks like "LJ" and has a corresponding
9996 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
9997 * is the appropriate form to use when rendering a word in lowercase
9998 * with initial capitals, as for a book title.
9999 * <p>
10000 * These are some of the Unicode characters for which this method returns
10001 * {@code true}:
10002 * <ul>
10003 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10004 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10005 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10006 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10007 * </ul>
10008 * <p> Many other Unicode characters are titlecase too.
10009 *
10010 * <p><b>Note:</b> This method cannot handle <a
10011 * href="#supplementary"> supplementary characters</a>. To support
10012 * all Unicode characters, including supplementary characters, use
10013 * the {@link #isTitleCase(int)} method.
10014 *
10015 * @param ch the character to be tested.
10016 * @return {@code true} if the character is titlecase;
10017 * {@code false} otherwise.
10018 * @see Character#isLowerCase(char)
10019 * @see Character#isUpperCase(char)
10020 * @see Character#toTitleCase(char)
10021 * @see Character#getType(char)
10022 * @since 1.0.2
10023 */
10024 public static boolean isTitleCase(char ch) {
10025 return isTitleCase((int)ch);
10026 }
10027
10028 /**
10029 * Determines if the specified character (Unicode code point) is a titlecase character.
10030 * <p>
10031 * A character is a titlecase character if its general
10032 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10033 * is {@code TITLECASE_LETTER}.
10034 * <p>
10035 * Some characters look like pairs of Latin letters. For example, there
10036 * is an uppercase letter that looks like "LJ" and has a corresponding
10037 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10038 * is the appropriate form to use when rendering a word in lowercase
10039 * with initial capitals, as for a book title.
10040 * <p>
10041 * These are some of the Unicode characters for which this method returns
10042 * {@code true}:
10043 * <ul>
10044 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10045 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10046 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10047 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10048 * </ul>
10049 * <p> Many other Unicode characters are titlecase too.
10050 *
10051 * @param codePoint the character (Unicode code point) to be tested.
10052 * @return {@code true} if the character is titlecase;
10053 * {@code false} otherwise.
10054 * @see Character#isLowerCase(int)
10055 * @see Character#isUpperCase(int)
10056 * @see Character#toTitleCase(int)
10057 * @see Character#getType(int)
10058 * @since 1.5
10059 */
10060 public static boolean isTitleCase(int codePoint) {
10061 return getType(codePoint) == Character.TITLECASE_LETTER;
10062 }
10063
10064 /**
10065 * Determines if the specified character is a digit.
10066 * <p>
10067 * A character is a digit if its general category type, provided
10068 * by {@code Character.getType(ch)}, is
10069 * {@code DECIMAL_DIGIT_NUMBER}.
10070 * <p>
10071 * Some Unicode character ranges that contain digits:
10072 * <ul>
10073 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10074 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10075 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10076 * Arabic-Indic digits
10077 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10078 * Extended Arabic-Indic digits
10079 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10080 * Devanagari digits
10081 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10082 * Fullwidth digits
10083 * </ul>
10084 *
10085 * Many other character ranges contain digits as well.
10086 *
10087 * <p><b>Note:</b> This method cannot handle <a
10088 * href="#supplementary"> supplementary characters</a>. To support
10089 * all Unicode characters, including supplementary characters, use
10090 * the {@link #isDigit(int)} method.
10091 *
10092 * @param ch the character to be tested.
10093 * @return {@code true} if the character is a digit;
10094 * {@code false} otherwise.
10095 * @see Character#digit(char, int)
10096 * @see Character#forDigit(int, int)
10097 * @see Character#getType(char)
10098 */
10099 public static boolean isDigit(char ch) {
10100 return isDigit((int)ch);
10101 }
10102
10103 /**
10104 * Determines if the specified character (Unicode code point) is a digit.
10105 * <p>
10106 * A character is a digit if its general category type, provided
10107 * by {@link Character#getType(int) getType(codePoint)}, is
10108 * {@code DECIMAL_DIGIT_NUMBER}.
10109 * <p>
10110 * Some Unicode character ranges that contain digits:
10111 * <ul>
10112 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10113 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10114 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10115 * Arabic-Indic digits
10116 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10117 * Extended Arabic-Indic digits
10118 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10119 * Devanagari digits
10120 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10121 * Fullwidth digits
10122 * </ul>
10123 *
10124 * Many other character ranges contain digits as well.
10125 *
10126 * @param codePoint the character (Unicode code point) to be tested.
10127 * @return {@code true} if the character is a digit;
10128 * {@code false} otherwise.
10129 * @see Character#forDigit(int, int)
10130 * @see Character#getType(int)
10131 * @since 1.5
10132 */
10133 public static boolean isDigit(int codePoint) {
10134 return CharacterData.of(codePoint).isDigit(codePoint);
10135 }
10136
10137 /**
10138 * Determines if a character is defined in Unicode.
10139 * <p>
10140 * A character is defined if at least one of the following is true:
10141 * <ul>
10142 * <li>It has an entry in the UnicodeData file.
10143 * <li>It has a value in a range defined by the UnicodeData file.
10144 * </ul>
10145 *
10146 * <p><b>Note:</b> This method cannot handle <a
10147 * href="#supplementary"> supplementary characters</a>. To support
10148 * all Unicode characters, including supplementary characters, use
10149 * the {@link #isDefined(int)} method.
10150 *
10151 * @param ch the character to be tested
10152 * @return {@code true} if the character has a defined meaning
10153 * in Unicode; {@code false} otherwise.
10154 * @see Character#isDigit(char)
10155 * @see Character#isLetter(char)
10156 * @see Character#isLetterOrDigit(char)
10157 * @see Character#isLowerCase(char)
10158 * @see Character#isTitleCase(char)
10159 * @see Character#isUpperCase(char)
10160 * @since 1.0.2
10161 */
10162 public static boolean isDefined(char ch) {
10163 return isDefined((int)ch);
10164 }
10165
10166 /**
10167 * Determines if a character (Unicode code point) is defined in Unicode.
10168 * <p>
10169 * A character is defined if at least one of the following is true:
10170 * <ul>
10171 * <li>It has an entry in the UnicodeData file.
10172 * <li>It has a value in a range defined by the UnicodeData file.
10173 * </ul>
10174 *
10175 * @param codePoint the character (Unicode code point) to be tested.
10176 * @return {@code true} if the character has a defined meaning
10177 * in Unicode; {@code false} otherwise.
10178 * @see Character#isDigit(int)
10179 * @see Character#isLetter(int)
10180 * @see Character#isLetterOrDigit(int)
10181 * @see Character#isLowerCase(int)
10182 * @see Character#isTitleCase(int)
10183 * @see Character#isUpperCase(int)
10184 * @since 1.5
10185 */
10186 public static boolean isDefined(int codePoint) {
10187 return getType(codePoint) != Character.UNASSIGNED;
10188 }
10189
10190 /**
10191 * Determines if the specified character is a letter.
10192 * <p>
10193 * A character is considered to be a letter if its general
10194 * category type, provided by {@code Character.getType(ch)},
10195 * is any of the following:
10196 * <ul>
10197 * <li> {@code UPPERCASE_LETTER}
10198 * <li> {@code LOWERCASE_LETTER}
10199 * <li> {@code TITLECASE_LETTER}
10200 * <li> {@code MODIFIER_LETTER}
10201 * <li> {@code OTHER_LETTER}
10202 * </ul>
10203 *
10204 * Not all letters have case. Many characters are
10205 * letters but are neither uppercase nor lowercase nor titlecase.
10206 *
10207 * <p><b>Note:</b> This method cannot handle <a
10208 * href="#supplementary"> supplementary characters</a>. To support
10209 * all Unicode characters, including supplementary characters, use
10210 * the {@link #isLetter(int)} method.
10211 *
10212 * @param ch the character to be tested.
10213 * @return {@code true} if the character is a letter;
10214 * {@code false} otherwise.
10215 * @see Character#isDigit(char)
10216 * @see Character#isJavaIdentifierStart(char)
10217 * @see Character#isJavaLetter(char)
10218 * @see Character#isJavaLetterOrDigit(char)
10219 * @see Character#isLetterOrDigit(char)
10220 * @see Character#isLowerCase(char)
10221 * @see Character#isTitleCase(char)
10222 * @see Character#isUnicodeIdentifierStart(char)
10223 * @see Character#isUpperCase(char)
10224 */
10225 public static boolean isLetter(char ch) {
10226 return isLetter((int)ch);
10227 }
10228
10229 /**
10230 * Determines if the specified character (Unicode code point) is a letter.
10231 * <p>
10232 * A character is considered to be a letter if its general
10233 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10234 * is any of the following:
10235 * <ul>
10236 * <li> {@code UPPERCASE_LETTER}
10237 * <li> {@code LOWERCASE_LETTER}
10238 * <li> {@code TITLECASE_LETTER}
10239 * <li> {@code MODIFIER_LETTER}
10240 * <li> {@code OTHER_LETTER}
10241 * </ul>
10242 *
10243 * Not all letters have case. Many characters are
10244 * letters but are neither uppercase nor lowercase nor titlecase.
10245 *
10246 * @param codePoint the character (Unicode code point) to be tested.
10247 * @return {@code true} if the character is a letter;
10248 * {@code false} otherwise.
10249 * @see Character#isDigit(int)
10250 * @see Character#isJavaIdentifierStart(int)
10251 * @see Character#isLetterOrDigit(int)
10252 * @see Character#isLowerCase(int)
10253 * @see Character#isTitleCase(int)
10254 * @see Character#isUnicodeIdentifierStart(int)
10255 * @see Character#isUpperCase(int)
10256 * @since 1.5
10257 */
10258 public static boolean isLetter(int codePoint) {
10259 return ((((1 << Character.UPPERCASE_LETTER) |
10260 (1 << Character.LOWERCASE_LETTER) |
10261 (1 << Character.TITLECASE_LETTER) |
10262 (1 << Character.MODIFIER_LETTER) |
10263 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10264 != 0;
10265 }
10266
10267 /**
10268 * Determines if the specified character is a letter or digit.
10269 * <p>
10270 * A character is considered to be a letter or digit if either
10271 * {@code Character.isLetter(char ch)} or
10272 * {@code Character.isDigit(char ch)} returns
10273 * {@code true} for the character.
10274 *
10275 * <p><b>Note:</b> This method cannot handle <a
10276 * href="#supplementary"> supplementary characters</a>. To support
10277 * all Unicode characters, including supplementary characters, use
10278 * the {@link #isLetterOrDigit(int)} method.
10279 *
10280 * @param ch the character to be tested.
10281 * @return {@code true} if the character is a letter or digit;
10282 * {@code false} otherwise.
10283 * @see Character#isDigit(char)
10284 * @see Character#isJavaIdentifierPart(char)
10285 * @see Character#isJavaLetter(char)
10286 * @see Character#isJavaLetterOrDigit(char)
10287 * @see Character#isLetter(char)
10288 * @see Character#isUnicodeIdentifierPart(char)
10289 * @since 1.0.2
10290 */
10291 public static boolean isLetterOrDigit(char ch) {
10292 return isLetterOrDigit((int)ch);
10293 }
10294
10295 /**
10296 * Determines if the specified character (Unicode code point) is a letter or digit.
10297 * <p>
10298 * A character is considered to be a letter or digit if either
10299 * {@link #isLetter(int) isLetter(codePoint)} or
10300 * {@link #isDigit(int) isDigit(codePoint)} returns
10301 * {@code true} for the character.
10302 *
10303 * @param codePoint the character (Unicode code point) to be tested.
10304 * @return {@code true} if the character is a letter or digit;
10305 * {@code false} otherwise.
10306 * @see Character#isDigit(int)
10307 * @see Character#isJavaIdentifierPart(int)
10308 * @see Character#isLetter(int)
10309 * @see Character#isUnicodeIdentifierPart(int)
10310 * @since 1.5
10311 */
10312 public static boolean isLetterOrDigit(int codePoint) {
10313 return ((((1 << Character.UPPERCASE_LETTER) |
10314 (1 << Character.LOWERCASE_LETTER) |
10315 (1 << Character.TITLECASE_LETTER) |
10316 (1 << Character.MODIFIER_LETTER) |
10317 (1 << Character.OTHER_LETTER) |
10318 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10319 != 0;
10320 }
10321
10322 /**
10323 * Determines if the specified character is permissible as the first
10324 * character in a Java identifier.
10325 * <p>
10326 * A character may start a Java identifier if and only if
10327 * one of the following conditions is true:
10328 * <ul>
10329 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10330 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10331 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10332 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10333 * </ul>
10334 *
10335 * @param ch the character to be tested.
10336 * @return {@code true} if the character may start a Java
10337 * identifier; {@code false} otherwise.
10338 * @see Character#isJavaLetterOrDigit(char)
10339 * @see Character#isJavaIdentifierStart(char)
10340 * @see Character#isJavaIdentifierPart(char)
10341 * @see Character#isLetter(char)
10342 * @see Character#isLetterOrDigit(char)
10343 * @see Character#isUnicodeIdentifierStart(char)
10344 * @since 1.0.2
10345 * @deprecated Replaced by isJavaIdentifierStart(char).
10346 */
10347 @Deprecated(since="1.1")
10348 public static boolean isJavaLetter(char ch) {
10349 return isJavaIdentifierStart(ch);
10350 }
10351
10352 /**
10353 * Determines if the specified character may be part of a Java
10354 * identifier as other than the first character.
10355 * <p>
10356 * A character may be part of a Java identifier if and only if one
10357 * of the following conditions is true:
10358 * <ul>
10359 * <li> it is a letter
10360 * <li> it is a currency symbol (such as {@code '$'})
10361 * <li> it is a connecting punctuation character (such as {@code '_'})
10362 * <li> it is a digit
10363 * <li> it is a numeric letter (such as a Roman numeral character)
10364 * <li> it is a combining mark
10365 * <li> it is a non-spacing mark
10366 * <li> {@code isIdentifierIgnorable} returns
10367 * {@code true} for the character.
10368 * </ul>
10369 *
10370 * @param ch the character to be tested.
10371 * @return {@code true} if the character may be part of a
10372 * Java identifier; {@code false} otherwise.
10373 * @see Character#isJavaLetter(char)
10374 * @see Character#isJavaIdentifierStart(char)
10375 * @see Character#isJavaIdentifierPart(char)
10376 * @see Character#isLetter(char)
10377 * @see Character#isLetterOrDigit(char)
10378 * @see Character#isUnicodeIdentifierPart(char)
10379 * @see Character#isIdentifierIgnorable(char)
10380 * @since 1.0.2
10381 * @deprecated Replaced by isJavaIdentifierPart(char).
10382 */
10383 @Deprecated(since="1.1")
10384 public static boolean isJavaLetterOrDigit(char ch) {
10385 return isJavaIdentifierPart(ch);
10386 }
10387
10388 /**
10389 * Determines if the specified character (Unicode code point) is alphabetic.
10390 * <p>
10391 * A character is considered to be alphabetic if its general category type,
10392 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10393 * the following:
10394 * <ul>
10395 * <li> {@code UPPERCASE_LETTER}
10396 * <li> {@code LOWERCASE_LETTER}
10397 * <li> {@code TITLECASE_LETTER}
10398 * <li> {@code MODIFIER_LETTER}
10399 * <li> {@code OTHER_LETTER}
10400 * <li> {@code LETTER_NUMBER}
10401 * </ul>
10402 * or it has contributory property Other_Alphabetic as defined by the
10403 * Unicode Standard.
10404 *
10405 * @param codePoint the character (Unicode code point) to be tested.
10406 * @return {@code true} if the character is a Unicode alphabet
10407 * character, {@code false} otherwise.
10408 * @since 1.7
10409 */
10410 public static boolean isAlphabetic(int codePoint) {
10411 return (((((1 << Character.UPPERCASE_LETTER) |
10412 (1 << Character.LOWERCASE_LETTER) |
10413 (1 << Character.TITLECASE_LETTER) |
10414 (1 << Character.MODIFIER_LETTER) |
10415 (1 << Character.OTHER_LETTER) |
10416 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10417 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10418 }
10419
10420 /**
10421 * Determines if the specified character (Unicode code point) is a CJKV
10422 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10423 * the Unicode Standard.
10424 *
10425 * @param codePoint the character (Unicode code point) to be tested.
10426 * @return {@code true} if the character is a Unicode ideograph
10427 * character, {@code false} otherwise.
10428 * @since 1.7
10429 */
10430 public static boolean isIdeographic(int codePoint) {
10431 return CharacterData.of(codePoint).isIdeographic(codePoint);
10432 }
10433
10434 /**
10435 * Determines if the specified character is
10436 * permissible as the first character in a Java identifier.
10437 * <p>
10438 * A character may start a Java identifier if and only if
10439 * one of the following conditions is true:
10440 * <ul>
10441 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10442 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10443 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10444 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10445 * </ul>
10446 *
10447 * <p><b>Note:</b> This method cannot handle <a
10448 * href="#supplementary"> supplementary characters</a>. To support
10449 * all Unicode characters, including supplementary characters, use
10450 * the {@link #isJavaIdentifierStart(int)} method.
10451 *
10452 * @param ch the character to be tested.
10453 * @return {@code true} if the character may start a Java identifier;
10454 * {@code false} otherwise.
10455 * @see Character#isJavaIdentifierPart(char)
10456 * @see Character#isLetter(char)
10457 * @see Character#isUnicodeIdentifierStart(char)
10458 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10459 * @since 1.1
10460 */
10461 @SuppressWarnings("doclint:reference") // cross-module links
10462 public static boolean isJavaIdentifierStart(char ch) {
10463 return isJavaIdentifierStart((int)ch);
10464 }
10465
10466 /**
10467 * Determines if the character (Unicode code point) is
10468 * permissible as the first character in a Java identifier.
10469 * <p>
10470 * A character may start a Java identifier if and only if
10471 * one of the following conditions is true:
10472 * <ul>
10473 * <li> {@link #isLetter(int) isLetter(codePoint)}
10474 * returns {@code true}
10475 * <li> {@link #getType(int) getType(codePoint)}
10476 * returns {@code LETTER_NUMBER}
10477 * <li> the referenced character is a currency symbol (such as {@code '$'})
10478 * <li> the referenced character is a connecting punctuation character
10479 * (such as {@code '_'}).
10480 * </ul>
10481 *
10482 * @param codePoint the character (Unicode code point) to be tested.
10483 * @return {@code true} if the character may start a Java identifier;
10484 * {@code false} otherwise.
10485 * @see Character#isJavaIdentifierPart(int)
10486 * @see Character#isLetter(int)
10487 * @see Character#isUnicodeIdentifierStart(int)
10488 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10489 * @since 1.5
10490 */
10491 @SuppressWarnings("doclint:reference") // cross-module links
10492 public static boolean isJavaIdentifierStart(int codePoint) {
10493 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10494 }
10495
10496 /**
10497 * Determines if the specified character may be part of a Java
10498 * identifier as other than the first character.
10499 * <p>
10500 * A character may be part of a Java identifier if any of the following
10501 * conditions are true:
10502 * <ul>
10503 * <li> it is a letter
10504 * <li> it is a currency symbol (such as {@code '$'})
10505 * <li> it is a connecting punctuation character (such as {@code '_'})
10506 * <li> it is a digit
10507 * <li> it is a numeric letter (such as a Roman numeral character)
10508 * <li> it is a combining mark
10509 * <li> it is a non-spacing mark
10510 * <li> {@code isIdentifierIgnorable} returns
10511 * {@code true} for the character
10512 * </ul>
10513 *
10514 * <p><b>Note:</b> This method cannot handle <a
10515 * href="#supplementary"> supplementary characters</a>. To support
10516 * all Unicode characters, including supplementary characters, use
10517 * the {@link #isJavaIdentifierPart(int)} method.
10518 *
10519 * @param ch the character to be tested.
10520 * @return {@code true} if the character may be part of a
10521 * Java identifier; {@code false} otherwise.
10522 * @see Character#isIdentifierIgnorable(char)
10523 * @see Character#isJavaIdentifierStart(char)
10524 * @see Character#isLetterOrDigit(char)
10525 * @see Character#isUnicodeIdentifierPart(char)
10526 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10527 * @since 1.1
10528 */
10529 @SuppressWarnings("doclint:reference") // cross-module links
10530 public static boolean isJavaIdentifierPart(char ch) {
10531 return isJavaIdentifierPart((int)ch);
10532 }
10533
10534 /**
10535 * Determines if the character (Unicode code point) may be part of a Java
10536 * identifier as other than the first character.
10537 * <p>
10538 * A character may be part of a Java identifier if any of the following
10539 * conditions are true:
10540 * <ul>
10541 * <li> it is a letter
10542 * <li> it is a currency symbol (such as {@code '$'})
10543 * <li> it is a connecting punctuation character (such as {@code '_'})
10544 * <li> it is a digit
10545 * <li> it is a numeric letter (such as a Roman numeral character)
10546 * <li> it is a combining mark
10547 * <li> it is a non-spacing mark
10548 * <li> {@link #isIdentifierIgnorable(int)
10549 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10550 * the code point
10551 * </ul>
10552 *
10553 * @param codePoint the character (Unicode code point) to be tested.
10554 * @return {@code true} if the character may be part of a
10555 * Java identifier; {@code false} otherwise.
10556 * @see Character#isIdentifierIgnorable(int)
10557 * @see Character#isJavaIdentifierStart(int)
10558 * @see Character#isLetterOrDigit(int)
10559 * @see Character#isUnicodeIdentifierPart(int)
10560 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10561 * @since 1.5
10562 */
10563 @SuppressWarnings("doclint:reference") // cross-module links
10564 public static boolean isJavaIdentifierPart(int codePoint) {
10565 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10566 }
10567
10568 /**
10569 * Determines if the specified character is permissible as the
10570 * first character in a Unicode identifier.
10571 * <p>
10572 * A character may start a Unicode identifier if and only if
10573 * one of the following conditions is true:
10574 * <ul>
10575 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10576 * <li> {@link #getType(char) getType(ch)} returns
10577 * {@code LETTER_NUMBER}.
10578 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10579 * {@code Other_ID_Start}</a> character.
10580 * </ul>
10581 * <p>
10582 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10583 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10584 * with the following profile of UAX31:
10585 * <pre>
10586 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10587 * </pre>
10588 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10589 * compatibility.
10590 *
10591 * <p><b>Note:</b> This method cannot handle <a
10592 * href="#supplementary"> supplementary characters</a>. To support
10593 * all Unicode characters, including supplementary characters, use
10594 * the {@link #isUnicodeIdentifierStart(int)} method.
10595 *
10596 * @param ch the character to be tested.
10597 * @return {@code true} if the character may start a Unicode
10598 * identifier; {@code false} otherwise.
10599 *
10600 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10601 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10602 * @see Character#isJavaIdentifierStart(char)
10603 * @see Character#isLetter(char)
10604 * @see Character#isUnicodeIdentifierPart(char)
10605 * @since 1.1
10606 */
10607 public static boolean isUnicodeIdentifierStart(char ch) {
10608 return isUnicodeIdentifierStart((int)ch);
10609 }
10610
10611 /**
10612 * Determines if the specified character (Unicode code point) is permissible as the
10613 * first character in a Unicode identifier.
10614 * <p>
10615 * A character may start a Unicode identifier if and only if
10616 * one of the following conditions is true:
10617 * <ul>
10618 * <li> {@link #isLetter(int) isLetter(codePoint)}
10619 * returns {@code true}
10620 * <li> {@link #getType(int) getType(codePoint)}
10621 * returns {@code LETTER_NUMBER}.
10622 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10623 * {@code Other_ID_Start}</a> character.
10624 * </ul>
10625 * <p>
10626 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10627 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10628 * with the following profile of UAX31:
10629 * <pre>
10630 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10631 * </pre>
10632 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10633 * compatibility.
10634 *
10635 * @param codePoint the character (Unicode code point) to be tested.
10636 * @return {@code true} if the character may start a Unicode
10637 * identifier; {@code false} otherwise.
10638 *
10639 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10640 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10641 * @see Character#isJavaIdentifierStart(int)
10642 * @see Character#isLetter(int)
10643 * @see Character#isUnicodeIdentifierPart(int)
10644 * @since 1.5
10645 */
10646 public static boolean isUnicodeIdentifierStart(int codePoint) {
10647 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
10648 }
10649
10650 /**
10651 * Determines if the specified character may be part of a Unicode
10652 * identifier as other than the first character.
10653 * <p>
10654 * A character may be part of a Unicode identifier if and only if
10655 * one of the following statements is true:
10656 * <ul>
10657 * <li> it is a letter
10658 * <li> it is a connecting punctuation character (such as {@code '_'})
10659 * <li> it is a digit
10660 * <li> it is a numeric letter (such as a Roman numeral character)
10661 * <li> it is a combining mark
10662 * <li> it is a non-spacing mark
10663 * <li> {@code isIdentifierIgnorable} returns
10664 * {@code true} for this character.
10665 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10666 * {@code Other_ID_Start}</a> character.
10667 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10668 * {@code Other_ID_Continue}</a> character.
10669 * </ul>
10670 * <p>
10671 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10672 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10673 * with the following profile of UAX31:
10674 * <pre>
10675 * Continue := Start + ID_Continue + ignorable
10676 * Medial := empty
10677 * ignorable := isIdentifierIgnorable(char) returns true for the character
10678 * </pre>
10679 * {@code ignorable} is added to {@code Continue} for backward
10680 * compatibility.
10681 *
10682 * <p><b>Note:</b> This method cannot handle <a
10683 * href="#supplementary"> supplementary characters</a>. To support
10684 * all Unicode characters, including supplementary characters, use
10685 * the {@link #isUnicodeIdentifierPart(int)} method.
10686 *
10687 * @param ch the character to be tested.
10688 * @return {@code true} if the character may be part of a
10689 * Unicode identifier; {@code false} otherwise.
10690 *
10691 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10692 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10693 * @see Character#isIdentifierIgnorable(char)
10694 * @see Character#isJavaIdentifierPart(char)
10695 * @see Character#isLetterOrDigit(char)
10696 * @see Character#isUnicodeIdentifierStart(char)
10697 * @since 1.1
10698 */
10699 public static boolean isUnicodeIdentifierPart(char ch) {
10700 return isUnicodeIdentifierPart((int)ch);
10701 }
10702
10703 /**
10704 * Determines if the specified character (Unicode code point) may be part of a Unicode
10705 * identifier as other than the first character.
10706 * <p>
10707 * A character may be part of a Unicode identifier if and only if
10708 * one of the following statements is true:
10709 * <ul>
10710 * <li> it is a letter
10711 * <li> it is a connecting punctuation character (such as {@code '_'})
10712 * <li> it is a digit
10713 * <li> it is a numeric letter (such as a Roman numeral character)
10714 * <li> it is a combining mark
10715 * <li> it is a non-spacing mark
10716 * <li> {@code isIdentifierIgnorable} returns
10717 * {@code true} for this character.
10718 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10719 * {@code Other_ID_Start}</a> character.
10720 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10721 * {@code Other_ID_Continue}</a> character.
10722 * </ul>
10723 * <p>
10724 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10725 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10726 * with the following profile of UAX31:
10727 * <pre>
10728 * Continue := Start + ID_Continue + ignorable
10729 * Medial := empty
10730 * ignorable := isIdentifierIgnorable(int) returns true for the character
10731 * </pre>
10732 * {@code ignorable} is added to {@code Continue} for backward
10733 * compatibility.
10734 *
10735 * @param codePoint the character (Unicode code point) to be tested.
10736 * @return {@code true} if the character may be part of a
10737 * Unicode identifier; {@code false} otherwise.
10738 *
10739 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10740 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10741 * @see Character#isIdentifierIgnorable(int)
10742 * @see Character#isJavaIdentifierPart(int)
10743 * @see Character#isLetterOrDigit(int)
10744 * @see Character#isUnicodeIdentifierStart(int)
10745 * @since 1.5
10746 */
10747 public static boolean isUnicodeIdentifierPart(int codePoint) {
10748 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
10749 }
10750
10751 /**
10752 * Determines if the specified character should be regarded as
10753 * an ignorable character in a Java identifier or a Unicode identifier.
10754 * <p>
10755 * The following Unicode characters are ignorable in a Java identifier
10756 * or a Unicode identifier:
10757 * <ul>
10758 * <li>ISO control characters that are not whitespace
10759 * <ul>
10760 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
10761 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
10762 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
10763 * </ul>
10764 *
10765 * <li>all characters that have the {@code FORMAT} general
10766 * category value
10767 * </ul>
10768 *
10769 * <p><b>Note:</b> This method cannot handle <a
10770 * href="#supplementary"> supplementary characters</a>. To support
10771 * all Unicode characters, including supplementary characters, use
10772 * the {@link #isIdentifierIgnorable(int)} method.
10773 *
10774 * @param ch the character to be tested.
10775 * @return {@code true} if the character is an ignorable control
10776 * character that may be part of a Java or Unicode identifier;
10777 * {@code false} otherwise.
10778 * @see Character#isJavaIdentifierPart(char)
10779 * @see Character#isUnicodeIdentifierPart(char)
10780 * @since 1.1
10781 */
10782 public static boolean isIdentifierIgnorable(char ch) {
10783 return isIdentifierIgnorable((int)ch);
10784 }
10785
10786 /**
10787 * Determines if the specified character (Unicode code point) should be regarded as
10788 * an ignorable character in a Java identifier or a Unicode identifier.
10789 * <p>
10790 * The following Unicode characters are ignorable in a Java identifier
10791 * or a Unicode identifier:
10792 * <ul>
10793 * <li>ISO control characters that are not whitespace
10794 * <ul>
10795 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
10796 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
10797 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
10798 * </ul>
10799 *
10800 * <li>all characters that have the {@code FORMAT} general
10801 * category value
10802 * </ul>
10803 *
10804 * @param codePoint the character (Unicode code point) to be tested.
10805 * @return {@code true} if the character is an ignorable control
10806 * character that may be part of a Java or Unicode identifier;
10807 * {@code false} otherwise.
10808 * @see Character#isJavaIdentifierPart(int)
10809 * @see Character#isUnicodeIdentifierPart(int)
10810 * @since 1.5
10811 */
10812 public static boolean isIdentifierIgnorable(int codePoint) {
10813 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
10814 }
10815
10816 /**
10817 * Determines if the specified character (Unicode code point) is an Emoji.
10818 * <p>
10819 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
10820 * property, defined in
10821 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10822 * Unicode Emoji (Technical Standard #51)</a>.
10823 *
10824 * @param codePoint the character (Unicode code point) to be tested.
10825 * @return {@code true} if the character is an Emoji;
10826 * {@code false} otherwise.
10827 * @since 21
10828 */
10829 public static boolean isEmoji(int codePoint) {
10830 return CharacterData.of(codePoint).isEmoji(codePoint);
10831 }
10832
10833 /**
10834 * Determines if the specified character (Unicode code point) has the
10835 * Emoji Presentation property by default.
10836 * <p>
10837 * A character is considered to have the Emoji Presentation property if and
10838 * only if it has the {@code Emoji_Presentation} property, defined in
10839 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10840 * Unicode Emoji (Technical Standard #51)</a>.
10841 *
10842 * @param codePoint the character (Unicode code point) to be tested.
10843 * @return {@code true} if the character has the Emoji Presentation
10844 * property; {@code false} otherwise.
10845 * @since 21
10846 */
10847 public static boolean isEmojiPresentation(int codePoint) {
10848 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
10849 }
10850
10851 /**
10852 * Determines if the specified character (Unicode code point) is an
10853 * Emoji Modifier.
10854 * <p>
10855 * A character is considered to be an Emoji Modifier if and only if it has
10856 * the {@code Emoji_Modifier} property, defined in
10857 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10858 * Unicode Emoji (Technical Standard #51)</a>.
10859 *
10860 * @param codePoint the character (Unicode code point) to be tested.
10861 * @return {@code true} if the character is an Emoji Modifier;
10862 * {@code false} otherwise.
10863 * @since 21
10864 */
10865 public static boolean isEmojiModifier(int codePoint) {
10866 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
10867 }
10868
10869 /**
10870 * Determines if the specified character (Unicode code point) is an
10871 * Emoji Modifier Base.
10872 * <p>
10873 * A character is considered to be an Emoji Modifier Base if and only if it has
10874 * the {@code Emoji_Modifier_Base} property, defined in
10875 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10876 * Unicode Emoji (Technical Standard #51)</a>.
10877 *
10878 * @param codePoint the character (Unicode code point) to be tested.
10879 * @return {@code true} if the character is an Emoji Modifier Base;
10880 * {@code false} otherwise.
10881 * @since 21
10882 */
10883 public static boolean isEmojiModifierBase(int codePoint) {
10884 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
10885 }
10886
10887 /**
10888 * Determines if the specified character (Unicode code point) is an
10889 * Emoji Component.
10890 * <p>
10891 * A character is considered to be an Emoji Component if and only if it has
10892 * the {@code Emoji_Component} property, defined in
10893 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10894 * Unicode Emoji (Technical Standard #51)</a>.
10895 *
10896 * @param codePoint the character (Unicode code point) to be tested.
10897 * @return {@code true} if the character is an Emoji Component;
10898 * {@code false} otherwise.
10899 * @since 21
10900 */
10901 public static boolean isEmojiComponent(int codePoint) {
10902 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
10903 }
10904
10905 /**
10906 * Determines if the specified character (Unicode code point) is
10907 * an Extended Pictographic.
10908 * <p>
10909 * A character is considered to be an Extended Pictographic if and only if it has
10910 * the {@code Extended_Pictographic} property, defined in
10911 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10912 * Unicode Emoji (Technical Standard #51)</a>.
10913 *
10914 * @param codePoint the character (Unicode code point) to be tested.
10915 * @return {@code true} if the character is an Extended Pictographic;
10916 * {@code false} otherwise.
10917 * @since 21
10918 */
10919 public static boolean isExtendedPictographic(int codePoint) {
10920 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
10921 }
10922
10923 /**
10924 * Converts the character argument to lowercase using case
10925 * mapping information from the UnicodeData file.
10926 * <p>
10927 * Note that
10928 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
10929 * does not always return {@code true} for some ranges of
10930 * characters, particularly those that are symbols or ideographs.
10931 *
10932 * <p>In general, {@link String#toLowerCase()} should be used to map
10933 * characters to lowercase. {@code String} case mapping methods
10934 * have several benefits over {@code Character} case mapping methods.
10935 * {@code String} case mapping methods can perform locale-sensitive
10936 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10937 * the {@code Character} case mapping methods cannot.
10938 *
10939 * <p><b>Note:</b> This method cannot handle <a
10940 * href="#supplementary"> supplementary characters</a>. To support
10941 * all Unicode characters, including supplementary characters, use
10942 * the {@link #toLowerCase(int)} method.
10943 *
10944 * @param ch the character to be converted.
10945 * @return the lowercase equivalent of the character, if any;
10946 * otherwise, the character itself.
10947 * @see Character#isLowerCase(char)
10948 * @see String#toLowerCase()
10949 */
10950 public static char toLowerCase(char ch) {
10951 return (char)toLowerCase((int)ch);
10952 }
10953
10954 /**
10955 * Converts the character (Unicode code point) argument to
10956 * lowercase using case mapping information from the UnicodeData
10957 * file.
10958 *
10959 * <p> Note that
10960 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
10961 * does not always return {@code true} for some ranges of
10962 * characters, particularly those that are symbols or ideographs.
10963 *
10964 * <p>In general, {@link String#toLowerCase()} should be used to map
10965 * characters to lowercase. {@code String} case mapping methods
10966 * have several benefits over {@code Character} case mapping methods.
10967 * {@code String} case mapping methods can perform locale-sensitive
10968 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10969 * the {@code Character} case mapping methods cannot.
10970 *
10971 * @param codePoint the character (Unicode code point) to be converted.
10972 * @return the lowercase equivalent of the character (Unicode code
10973 * point), if any; otherwise, the character itself.
10974 * @see Character#isLowerCase(int)
10975 * @see String#toLowerCase()
10976 *
10977 * @since 1.5
10978 */
10979 public static int toLowerCase(int codePoint) {
10980 return CharacterData.of(codePoint).toLowerCase(codePoint);
10981 }
10982
10983 /**
10984 * Converts the character argument to uppercase using case mapping
10985 * information from the UnicodeData file.
10986 * <p>
10987 * Note that
10988 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
10989 * does not always return {@code true} for some ranges of
10990 * characters, particularly those that are symbols or ideographs.
10991 *
10992 * <p>In general, {@link String#toUpperCase()} should be used to map
10993 * characters to uppercase. {@code String} case mapping methods
10994 * have several benefits over {@code Character} case mapping methods.
10995 * {@code String} case mapping methods can perform locale-sensitive
10996 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10997 * the {@code Character} case mapping methods cannot.
10998 *
10999 * <p><b>Note:</b> This method cannot handle <a
11000 * href="#supplementary"> supplementary characters</a>. To support
11001 * all Unicode characters, including supplementary characters, use
11002 * the {@link #toUpperCase(int)} method.
11003 *
11004 * @param ch the character to be converted.
11005 * @return the uppercase equivalent of the character, if any;
11006 * otherwise, the character itself.
11007 * @see Character#isUpperCase(char)
11008 * @see String#toUpperCase()
11009 */
11010 public static char toUpperCase(char ch) {
11011 return (char)toUpperCase((int)ch);
11012 }
11013
11014 /**
11015 * Converts the character (Unicode code point) argument to
11016 * uppercase using case mapping information from the UnicodeData
11017 * file.
11018 *
11019 * <p>Note that
11020 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11021 * does not always return {@code true} for some ranges of
11022 * characters, particularly those that are symbols or ideographs.
11023 *
11024 * <p>In general, {@link String#toUpperCase()} should be used to map
11025 * characters to uppercase. {@code String} case mapping methods
11026 * have several benefits over {@code Character} case mapping methods.
11027 * {@code String} case mapping methods can perform locale-sensitive
11028 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11029 * the {@code Character} case mapping methods cannot.
11030 *
11031 * @param codePoint the character (Unicode code point) to be converted.
11032 * @return the uppercase equivalent of the character, if any;
11033 * otherwise, the character itself.
11034 * @see Character#isUpperCase(int)
11035 * @see String#toUpperCase()
11036 *
11037 * @since 1.5
11038 */
11039 public static int toUpperCase(int codePoint) {
11040 return CharacterData.of(codePoint).toUpperCase(codePoint);
11041 }
11042
11043 /**
11044 * Converts the character argument to titlecase using case mapping
11045 * information from the UnicodeData file. If a character has no
11046 * explicit titlecase mapping and is not itself a titlecase char
11047 * according to UnicodeData, then the uppercase mapping is
11048 * returned as an equivalent titlecase mapping. If the
11049 * {@code char} argument is already a titlecase
11050 * {@code char}, the same {@code char} value will be
11051 * returned.
11052 * <p>
11053 * Note that
11054 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11055 * does not always return {@code true} for some ranges of
11056 * characters.
11057 *
11058 * <p><b>Note:</b> This method cannot handle <a
11059 * href="#supplementary"> supplementary characters</a>. To support
11060 * all Unicode characters, including supplementary characters, use
11061 * the {@link #toTitleCase(int)} method.
11062 *
11063 * @param ch the character to be converted.
11064 * @return the titlecase equivalent of the character, if any;
11065 * otherwise, the character itself.
11066 * @see Character#isTitleCase(char)
11067 * @see Character#toLowerCase(char)
11068 * @see Character#toUpperCase(char)
11069 * @since 1.0.2
11070 */
11071 public static char toTitleCase(char ch) {
11072 return (char)toTitleCase((int)ch);
11073 }
11074
11075 /**
11076 * Converts the character (Unicode code point) argument to titlecase using case mapping
11077 * information from the UnicodeData file. If a character has no
11078 * explicit titlecase mapping and is not itself a titlecase char
11079 * according to UnicodeData, then the uppercase mapping is
11080 * returned as an equivalent titlecase mapping. If the
11081 * character argument is already a titlecase
11082 * character, the same character value will be
11083 * returned.
11084 *
11085 * <p>Note that
11086 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11087 * does not always return {@code true} for some ranges of
11088 * characters.
11089 *
11090 * @param codePoint the character (Unicode code point) to be converted.
11091 * @return the titlecase equivalent of the character, if any;
11092 * otherwise, the character itself.
11093 * @see Character#isTitleCase(int)
11094 * @see Character#toLowerCase(int)
11095 * @see Character#toUpperCase(int)
11096 * @since 1.5
11097 */
11098 public static int toTitleCase(int codePoint) {
11099 return CharacterData.of(codePoint).toTitleCase(codePoint);
11100 }
11101
11102 /**
11103 * Returns the numeric value of the character {@code ch} in the
11104 * specified radix.
11105 * <p>
11106 * If the radix is not in the range {@code MIN_RADIX} ≤
11107 * {@code radix} ≤ {@code MAX_RADIX} or if the
11108 * value of {@code ch} is not a valid digit in the specified
11109 * radix, {@code -1} is returned. A character is a valid digit
11110 * if at least one of the following is true:
11111 * <ul>
11112 * <li>The method {@code isDigit} is {@code true} of the character
11113 * and the Unicode decimal digit value of the character (or its
11114 * single-character decomposition) is less than the specified radix.
11115 * In this case the decimal digit value is returned.
11116 * <li>The character is one of the uppercase Latin letters
11117 * {@code 'A'} through {@code 'Z'} and its code is less than
11118 * {@code radix + 'A' - 10}.
11119 * In this case, {@code ch - 'A' + 10}
11120 * is returned.
11121 * <li>The character is one of the lowercase Latin letters
11122 * {@code 'a'} through {@code 'z'} and its code is less than
11123 * {@code radix + 'a' - 10}.
11124 * In this case, {@code ch - 'a' + 10}
11125 * is returned.
11126 * <li>The character is one of the fullwidth uppercase Latin letters A
11127 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11128 * and its code is less than
11129 * {@code radix + '\u005CuFF21' - 10}.
11130 * In this case, {@code ch - '\u005CuFF21' + 10}
11131 * is returned.
11132 * <li>The character is one of the fullwidth lowercase Latin letters a
11133 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11134 * and its code is less than
11135 * {@code radix + '\u005CuFF41' - 10}.
11136 * In this case, {@code ch - '\u005CuFF41' + 10}
11137 * is returned.
11138 * </ul>
11139 *
11140 * <p><b>Note:</b> This method cannot handle <a
11141 * href="#supplementary"> supplementary characters</a>. To support
11142 * all Unicode characters, including supplementary characters, use
11143 * the {@link #digit(int, int)} method.
11144 *
11145 * @param ch the character to be converted.
11146 * @param radix the radix.
11147 * @return the numeric value represented by the character in the
11148 * specified radix.
11149 * @see Character#forDigit(int, int)
11150 * @see Character#isDigit(char)
11151 */
11152 public static int digit(char ch, int radix) {
11153 return digit((int)ch, radix);
11154 }
11155
11156 /**
11157 * Returns the numeric value of the specified character (Unicode
11158 * code point) in the specified radix.
11159 *
11160 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11161 * {@code radix} ≤ {@code MAX_RADIX} or if the
11162 * character is not a valid digit in the specified
11163 * radix, {@code -1} is returned. A character is a valid digit
11164 * if at least one of the following is true:
11165 * <ul>
11166 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11167 * and the Unicode decimal digit value of the character (or its
11168 * single-character decomposition) is less than the specified radix.
11169 * In this case the decimal digit value is returned.
11170 * <li>The character is one of the uppercase Latin letters
11171 * {@code 'A'} through {@code 'Z'} and its code is less than
11172 * {@code radix + 'A' - 10}.
11173 * In this case, {@code codePoint - 'A' + 10}
11174 * is returned.
11175 * <li>The character is one of the lowercase Latin letters
11176 * {@code 'a'} through {@code 'z'} and its code is less than
11177 * {@code radix + 'a' - 10}.
11178 * In this case, {@code codePoint - 'a' + 10}
11179 * is returned.
11180 * <li>The character is one of the fullwidth uppercase Latin letters A
11181 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11182 * and its code is less than
11183 * {@code radix + '\u005CuFF21' - 10}.
11184 * In this case,
11185 * {@code codePoint - '\u005CuFF21' + 10}
11186 * is returned.
11187 * <li>The character is one of the fullwidth lowercase Latin letters a
11188 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11189 * and its code is less than
11190 * {@code radix + '\u005CuFF41'- 10}.
11191 * In this case,
11192 * {@code codePoint - '\u005CuFF41' + 10}
11193 * is returned.
11194 * </ul>
11195 *
11196 * @param codePoint the character (Unicode code point) to be converted.
11197 * @param radix the radix.
11198 * @return the numeric value represented by the character in the
11199 * specified radix.
11200 * @see Character#forDigit(int, int)
11201 * @see Character#isDigit(int)
11202 * @since 1.5
11203 */
11204 public static int digit(int codePoint, int radix) {
11205 return CharacterData.of(codePoint).digit(codePoint, radix);
11206 }
11207
11208 /**
11209 * Returns the {@code int} value that the specified Unicode
11210 * character represents. For example, the character
11211 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11212 * an int with a value of 50.
11213 * <p>
11214 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11215 * {@code '\u005Cu005A'}), lowercase
11216 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11217 * full width variant ({@code '\u005CuFF21'} through
11218 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11219 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11220 * through 35. This is independent of the Unicode specification,
11221 * which does not assign numeric values to these {@code char}
11222 * values.
11223 * <p>
11224 * If the character does not have a numeric value, then -1 is returned.
11225 * If the character has a numeric value that cannot be represented as a
11226 * nonnegative integer (for example, a fractional value), then -2
11227 * is returned.
11228 *
11229 * <p><b>Note:</b> This method cannot handle <a
11230 * href="#supplementary"> supplementary characters</a>. To support
11231 * all Unicode characters, including supplementary characters, use
11232 * the {@link #getNumericValue(int)} method.
11233 *
11234 * @param ch the character to be converted.
11235 * @return the numeric value of the character, as a nonnegative {@code int}
11236 * value; -2 if the character has a numeric value but the value
11237 * can not be represented as a nonnegative {@code int} value;
11238 * -1 if the character has no numeric value.
11239 * @see Character#forDigit(int, int)
11240 * @see Character#isDigit(char)
11241 * @since 1.1
11242 */
11243 public static int getNumericValue(char ch) {
11244 return getNumericValue((int)ch);
11245 }
11246
11247 /**
11248 * Returns the {@code int} value that the specified
11249 * character (Unicode code point) represents. For example, the character
11250 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11251 * an {@code int} with a value of 50.
11252 * <p>
11253 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11254 * {@code '\u005Cu005A'}), lowercase
11255 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11256 * full width variant ({@code '\u005CuFF21'} through
11257 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11258 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11259 * through 35. This is independent of the Unicode specification,
11260 * which does not assign numeric values to these {@code char}
11261 * values.
11262 * <p>
11263 * If the character does not have a numeric value, then -1 is returned.
11264 * If the character has a numeric value that cannot be represented as a
11265 * nonnegative integer (for example, a fractional value), then -2
11266 * is returned.
11267 *
11268 * @param codePoint the character (Unicode code point) to be converted.
11269 * @return the numeric value of the character, as a nonnegative {@code int}
11270 * value; -2 if the character has a numeric value but the value
11271 * can not be represented as a nonnegative {@code int} value;
11272 * -1 if the character has no numeric value.
11273 * @see Character#forDigit(int, int)
11274 * @see Character#isDigit(int)
11275 * @since 1.5
11276 */
11277 public static int getNumericValue(int codePoint) {
11278 return CharacterData.of(codePoint).getNumericValue(codePoint);
11279 }
11280
11281 /**
11282 * Determines if the specified character is ISO-LATIN-1 white space.
11283 * This method returns {@code true} for the following five
11284 * characters only:
11285 * <table class="striped">
11286 * <caption style="display:none">truechars</caption>
11287 * <thead>
11288 * <tr><th scope="col">Character
11289 * <th scope="col">Code
11290 * <th scope="col">Name
11291 * </thead>
11292 * <tbody>
11293 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11294 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11295 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11296 * <td>{@code NEW LINE}</td></tr>
11297 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11298 * <td>{@code FORM FEED}</td></tr>
11299 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11300 * <td>{@code CARRIAGE RETURN}</td></tr>
11301 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11302 * <td>{@code SPACE}</td></tr>
11303 * </tbody>
11304 * </table>
11305 *
11306 * @param ch the character to be tested.
11307 * @return {@code true} if the character is ISO-LATIN-1 white
11308 * space; {@code false} otherwise.
11309 * @see Character#isSpaceChar(char)
11310 * @see Character#isWhitespace(char)
11311 * @deprecated Replaced by isWhitespace(char).
11312 */
11313 @Deprecated(since="1.1")
11314 public static boolean isSpace(char ch) {
11315 return (ch <= 0x0020) &&
11316 (((((1L << 0x0009) |
11317 (1L << 0x000A) |
11318 (1L << 0x000C) |
11319 (1L << 0x000D) |
11320 (1L << 0x0020)) >> ch) & 1L) != 0);
11321 }
11322
11323
11324 /**
11325 * Determines if the specified character is a Unicode space character.
11326 * A character is considered to be a space character if and only if
11327 * it is specified to be a space character by the Unicode Standard. This
11328 * method returns true if the character's general category type is any of
11329 * the following:
11330 * <ul>
11331 * <li> {@code SPACE_SEPARATOR}
11332 * <li> {@code LINE_SEPARATOR}
11333 * <li> {@code PARAGRAPH_SEPARATOR}
11334 * </ul>
11335 *
11336 * <p><b>Note:</b> This method cannot handle <a
11337 * href="#supplementary"> supplementary characters</a>. To support
11338 * all Unicode characters, including supplementary characters, use
11339 * the {@link #isSpaceChar(int)} method.
11340 *
11341 * @param ch the character to be tested.
11342 * @return {@code true} if the character is a space character;
11343 * {@code false} otherwise.
11344 * @see Character#isWhitespace(char)
11345 * @since 1.1
11346 */
11347 public static boolean isSpaceChar(char ch) {
11348 return isSpaceChar((int)ch);
11349 }
11350
11351 /**
11352 * Determines if the specified character (Unicode code point) is a
11353 * Unicode space character. A character is considered to be a
11354 * space character if and only if it is specified to be a space
11355 * character by the Unicode Standard. This method returns true if
11356 * the character's general category type is any of the following:
11357 *
11358 * <ul>
11359 * <li> {@link #SPACE_SEPARATOR}
11360 * <li> {@link #LINE_SEPARATOR}
11361 * <li> {@link #PARAGRAPH_SEPARATOR}
11362 * </ul>
11363 *
11364 * @param codePoint the character (Unicode code point) to be tested.
11365 * @return {@code true} if the character is a space character;
11366 * {@code false} otherwise.
11367 * @see Character#isWhitespace(int)
11368 * @since 1.5
11369 */
11370 public static boolean isSpaceChar(int codePoint) {
11371 return ((((1 << Character.SPACE_SEPARATOR) |
11372 (1 << Character.LINE_SEPARATOR) |
11373 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11374 != 0;
11375 }
11376
11377 /**
11378 * Determines if the specified character is white space according to Java.
11379 * A character is a Java whitespace character if and only if it satisfies
11380 * one of the following criteria:
11381 * <ul>
11382 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11383 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11384 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11385 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11386 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11387 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11388 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11389 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11390 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11391 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11392 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11393 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11394 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11395 * </ul>
11396 *
11397 * <p><b>Note:</b> This method cannot handle <a
11398 * href="#supplementary"> supplementary characters</a>. To support
11399 * all Unicode characters, including supplementary characters, use
11400 * the {@link #isWhitespace(int)} method.
11401 *
11402 * @param ch the character to be tested.
11403 * @return {@code true} if the character is a Java whitespace
11404 * character; {@code false} otherwise.
11405 * @see Character#isSpaceChar(char)
11406 * @since 1.1
11407 */
11408 public static boolean isWhitespace(char ch) {
11409 return isWhitespace((int)ch);
11410 }
11411
11412 /**
11413 * Determines if the specified character (Unicode code point) is
11414 * white space according to Java. A character is a Java
11415 * whitespace character if and only if it satisfies one of the
11416 * following criteria:
11417 * <ul>
11418 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11419 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11420 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11421 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11422 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11423 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11424 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11425 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11426 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11427 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11428 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11429 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11430 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11431 * </ul>
11432 *
11433 * @param codePoint the character (Unicode code point) to be tested.
11434 * @return {@code true} if the character is a Java whitespace
11435 * character; {@code false} otherwise.
11436 * @see Character#isSpaceChar(int)
11437 * @since 1.5
11438 */
11439 public static boolean isWhitespace(int codePoint) {
11440 return CharacterData.of(codePoint).isWhitespace(codePoint);
11441 }
11442
11443 /**
11444 * Determines if the specified character is an ISO control
11445 * character. A character is considered to be an ISO control
11446 * character if its code is in the range {@code '\u005Cu0000'}
11447 * through {@code '\u005Cu001F'} or in the range
11448 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11449 *
11450 * <p><b>Note:</b> This method cannot handle <a
11451 * href="#supplementary"> supplementary characters</a>. To support
11452 * all Unicode characters, including supplementary characters, use
11453 * the {@link #isISOControl(int)} method.
11454 *
11455 * @param ch the character to be tested.
11456 * @return {@code true} if the character is an ISO control character;
11457 * {@code false} otherwise.
11458 *
11459 * @see Character#isSpaceChar(char)
11460 * @see Character#isWhitespace(char)
11461 * @since 1.1
11462 */
11463 public static boolean isISOControl(char ch) {
11464 return isISOControl((int)ch);
11465 }
11466
11467 /**
11468 * Determines if the referenced character (Unicode code point) is an ISO control
11469 * character. A character is considered to be an ISO control
11470 * character if its code is in the range {@code '\u005Cu0000'}
11471 * through {@code '\u005Cu001F'} or in the range
11472 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11473 *
11474 * @param codePoint the character (Unicode code point) to be tested.
11475 * @return {@code true} if the character is an ISO control character;
11476 * {@code false} otherwise.
11477 * @see Character#isSpaceChar(int)
11478 * @see Character#isWhitespace(int)
11479 * @since 1.5
11480 */
11481 public static boolean isISOControl(int codePoint) {
11482 // Optimized form of:
11483 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11484 // (codePoint >= 0x7F && codePoint <= 0x9F);
11485 return codePoint <= 0x9F &&
11486 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11487 }
11488
11489 /**
11490 * Returns a value indicating a character's general category.
11491 *
11492 * <p><b>Note:</b> This method cannot handle <a
11493 * href="#supplementary"> supplementary characters</a>. To support
11494 * all Unicode characters, including supplementary characters, use
11495 * the {@link #getType(int)} method.
11496 *
11497 * @param ch the character to be tested.
11498 * @return a value of type {@code int} representing the
11499 * character's general category.
11500 * @see Character#COMBINING_SPACING_MARK
11501 * @see Character#CONNECTOR_PUNCTUATION
11502 * @see Character#CONTROL
11503 * @see Character#CURRENCY_SYMBOL
11504 * @see Character#DASH_PUNCTUATION
11505 * @see Character#DECIMAL_DIGIT_NUMBER
11506 * @see Character#ENCLOSING_MARK
11507 * @see Character#END_PUNCTUATION
11508 * @see Character#FINAL_QUOTE_PUNCTUATION
11509 * @see Character#FORMAT
11510 * @see Character#INITIAL_QUOTE_PUNCTUATION
11511 * @see Character#LETTER_NUMBER
11512 * @see Character#LINE_SEPARATOR
11513 * @see Character#LOWERCASE_LETTER
11514 * @see Character#MATH_SYMBOL
11515 * @see Character#MODIFIER_LETTER
11516 * @see Character#MODIFIER_SYMBOL
11517 * @see Character#NON_SPACING_MARK
11518 * @see Character#OTHER_LETTER
11519 * @see Character#OTHER_NUMBER
11520 * @see Character#OTHER_PUNCTUATION
11521 * @see Character#OTHER_SYMBOL
11522 * @see Character#PARAGRAPH_SEPARATOR
11523 * @see Character#PRIVATE_USE
11524 * @see Character#SPACE_SEPARATOR
11525 * @see Character#START_PUNCTUATION
11526 * @see Character#SURROGATE
11527 * @see Character#TITLECASE_LETTER
11528 * @see Character#UNASSIGNED
11529 * @see Character#UPPERCASE_LETTER
11530 * @since 1.1
11531 */
11532 public static int getType(char ch) {
11533 return getType((int)ch);
11534 }
11535
11536 /**
11537 * Returns a value indicating a character's general category.
11538 *
11539 * @param codePoint the character (Unicode code point) to be tested.
11540 * @return a value of type {@code int} representing the
11541 * character's general category.
11542 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11543 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11544 * @see Character#CONTROL CONTROL
11545 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11546 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11547 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11548 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11549 * @see Character#END_PUNCTUATION END_PUNCTUATION
11550 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11551 * @see Character#FORMAT FORMAT
11552 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11553 * @see Character#LETTER_NUMBER LETTER_NUMBER
11554 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11555 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11556 * @see Character#MATH_SYMBOL MATH_SYMBOL
11557 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11558 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11559 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11560 * @see Character#OTHER_LETTER OTHER_LETTER
11561 * @see Character#OTHER_NUMBER OTHER_NUMBER
11562 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
11563 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
11564 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
11565 * @see Character#PRIVATE_USE PRIVATE_USE
11566 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
11567 * @see Character#START_PUNCTUATION START_PUNCTUATION
11568 * @see Character#SURROGATE SURROGATE
11569 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
11570 * @see Character#UNASSIGNED UNASSIGNED
11571 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
11572 * @since 1.5
11573 */
11574 public static int getType(int codePoint) {
11575 return CharacterData.of(codePoint).getType(codePoint);
11576 }
11577
11578 /**
11579 * Determines the character representation for a specific digit in
11580 * the specified radix. If the value of {@code radix} is not a
11581 * valid radix, or the value of {@code digit} is not a valid
11582 * digit in the specified radix, the null character
11583 * ({@code '\u005Cu0000'}) is returned.
11584 * <p>
11585 * The {@code radix} argument is valid if it is greater than or
11586 * equal to {@code MIN_RADIX} and less than or equal to
11587 * {@code MAX_RADIX}. The {@code digit} argument is valid if
11588 * {@code 0 <= digit < radix}.
11589 * <p>
11590 * If the digit is less than 10, then
11591 * {@code '0' + digit} is returned. Otherwise, the value
11592 * {@code 'a' + digit - 10} is returned.
11593 *
11594 * @param digit the number to convert to a character.
11595 * @param radix the radix.
11596 * @return the {@code char} representation of the specified digit
11597 * in the specified radix.
11598 * @see Character#MIN_RADIX
11599 * @see Character#MAX_RADIX
11600 * @see Character#digit(char, int)
11601 */
11602 public static char forDigit(int digit, int radix) {
11603 if ((digit >= radix) || (digit < 0)) {
11604 return '\0';
11605 }
11606 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
11607 return '\0';
11608 }
11609 if (digit < 10) {
11610 return (char)('0' + digit);
11611 }
11612 return (char)('a' - 10 + digit);
11613 }
11614
11615 /**
11616 * Returns the Unicode directionality property for the given
11617 * character. Character directionality is used to calculate the
11618 * visual ordering of text. The directionality value of undefined
11619 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
11620 *
11621 * <p><b>Note:</b> This method cannot handle <a
11622 * href="#supplementary"> supplementary characters</a>. To support
11623 * all Unicode characters, including supplementary characters, use
11624 * the {@link #getDirectionality(int)} method.
11625 *
11626 * @param ch {@code char} for which the directionality property
11627 * is requested.
11628 * @return the directionality property of the {@code char} value.
11629 *
11630 * @see Character#DIRECTIONALITY_UNDEFINED
11631 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
11632 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
11633 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11634 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
11635 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11636 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11637 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
11638 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11639 * @see Character#DIRECTIONALITY_NONSPACING_MARK
11640 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
11641 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
11642 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
11643 * @see Character#DIRECTIONALITY_WHITESPACE
11644 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
11645 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11646 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11647 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11648 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11649 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11650 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11651 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11652 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
11653 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11654 * @since 1.4
11655 */
11656 public static byte getDirectionality(char ch) {
11657 return getDirectionality((int)ch);
11658 }
11659
11660 /**
11661 * Returns the Unicode directionality property for the given
11662 * character (Unicode code point). Character directionality is
11663 * used to calculate the visual ordering of text. The
11664 * directionality value of undefined character is {@link
11665 * #DIRECTIONALITY_UNDEFINED}.
11666 *
11667 * @param codePoint the character (Unicode code point) for which
11668 * the directionality property is requested.
11669 * @return the directionality property of the character.
11670 *
11671 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
11672 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
11673 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
11674 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11675 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
11676 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11677 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11678 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
11679 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11680 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
11681 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
11682 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
11683 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
11684 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
11685 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
11686 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11687 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11688 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11689 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11690 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11691 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11692 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11693 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
11694 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11695 * @since 1.5
11696 */
11697 public static byte getDirectionality(int codePoint) {
11698 return CharacterData.of(codePoint).getDirectionality(codePoint);
11699 }
11700
11701 /**
11702 * Determines whether the character is mirrored according to the
11703 * Unicode specification. Mirrored characters should have their
11704 * glyphs horizontally mirrored when displayed in text that is
11705 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
11706 * PARENTHESIS is semantically defined to be an <i>opening
11707 * parenthesis</i>. This will appear as a "(" in text that is
11708 * left-to-right but as a ")" in text that is right-to-left.
11709 *
11710 * <p><b>Note:</b> This method cannot handle <a
11711 * href="#supplementary"> supplementary characters</a>. To support
11712 * all Unicode characters, including supplementary characters, use
11713 * the {@link #isMirrored(int)} method.
11714 *
11715 * @param ch {@code char} for which the mirrored property is requested
11716 * @return {@code true} if the char is mirrored, {@code false}
11717 * if the {@code char} is not mirrored or is not defined.
11718 * @since 1.4
11719 */
11720 public static boolean isMirrored(char ch) {
11721 return isMirrored((int)ch);
11722 }
11723
11724 /**
11725 * Determines whether the specified character (Unicode code point)
11726 * is mirrored according to the Unicode specification. Mirrored
11727 * characters should have their glyphs horizontally mirrored when
11728 * displayed in text that is right-to-left. For example,
11729 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
11730 * defined to be an <i>opening parenthesis</i>. This will appear
11731 * as a "(" in text that is left-to-right but as a ")" in text
11732 * that is right-to-left.
11733 *
11734 * @param codePoint the character (Unicode code point) to be tested.
11735 * @return {@code true} if the character is mirrored, {@code false}
11736 * if the character is not mirrored or is not defined.
11737 * @since 1.5
11738 */
11739 public static boolean isMirrored(int codePoint) {
11740 return CharacterData.of(codePoint).isMirrored(codePoint);
11741 }
11742
11743 /**
11744 * Compares two {@code Character} objects numerically.
11745 *
11746 * @param anotherCharacter the {@code Character} to be compared.
11747 * @return the value {@code 0} if the argument {@code Character}
11748 * is equal to this {@code Character}; a value less than
11749 * {@code 0} if this {@code Character} is numerically less
11750 * than the {@code Character} argument; and a value greater than
11751 * {@code 0} if this {@code Character} is numerically greater
11752 * than the {@code Character} argument (unsigned comparison).
11753 * Note that this is strictly a numerical comparison; it is not
11754 * locale-dependent.
11755 * @since 1.2
11756 */
11757 public int compareTo(Character anotherCharacter) {
11758 return compare(this.value, anotherCharacter.value);
11759 }
11760
11761 /**
11762 * Compares two {@code char} values numerically.
11763 * The value returned is identical to what would be returned by:
11764 * <pre>
11765 * Character.valueOf(x).compareTo(Character.valueOf(y))
11766 * </pre>
11767 *
11768 * @param x the first {@code char} to compare
11769 * @param y the second {@code char} to compare
11770 * @return the value {@code 0} if {@code x == y};
11771 * a value less than {@code 0} if {@code x < y}; and
11772 * a value greater than {@code 0} if {@code x > y}
11773 * @since 1.7
11774 */
11775 public static int compare(char x, char y) {
11776 return x - y;
11777 }
11778
11779 /**
11780 * Converts the character (Unicode code point) argument to uppercase using
11781 * information from the UnicodeData file.
11782 *
11783 * @param codePoint the character (Unicode code point) to be converted.
11784 * @return either the uppercase equivalent of the character, if
11785 * any, or an error flag ({@code Character.ERROR})
11786 * that indicates that a 1:M {@code char} mapping exists.
11787 * @see Character#isLowerCase(char)
11788 * @see Character#isUpperCase(char)
11789 * @see Character#toLowerCase(char)
11790 * @see Character#toTitleCase(char)
11791 * @since 1.4
11792 */
11793 static int toUpperCaseEx(int codePoint) {
11794 assert isValidCodePoint(codePoint);
11795 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
11796 }
11797
11798 /**
11799 * Converts the character (Unicode code point) argument to uppercase using case
11800 * mapping information from the SpecialCasing file in the Unicode
11801 * specification. If a character has no explicit uppercase
11802 * mapping, then the {@code char} itself is returned in the
11803 * {@code char[]}.
11804 *
11805 * @param codePoint the character (Unicode code point) to be converted.
11806 * @return a {@code char[]} with the uppercased character.
11807 * @since 1.4
11808 */
11809 static char[] toUpperCaseCharArray(int codePoint) {
11810 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
11811 assert isBmpCodePoint(codePoint);
11812 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
11813 }
11814
11815 /**
11816 * The number of bits used to represent a {@code char} value in unsigned
11817 * binary form, constant {@code 16}.
11818 *
11819 * @since 1.5
11820 */
11821 public static final int SIZE = 16;
11822
11823 /**
11824 * The number of bytes used to represent a {@code char} value in unsigned
11825 * binary form.
11826 *
11827 * @since 1.8
11828 */
11829 public static final int BYTES = SIZE / Byte.SIZE;
11830
11831 /**
11832 * Returns the value obtained by reversing the order of the bytes in the
11833 * specified {@code char} value.
11834 *
11835 * @param ch The {@code char} of which to reverse the byte order.
11836 * @return the value obtained by reversing (or, equivalently, swapping)
11837 * the bytes in the specified {@code char} value.
11838 * @since 1.5
11839 */
11840 @IntrinsicCandidate
11841 public static char reverseBytes(char ch) {
11842 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
11843 }
11844
11845 /**
11846 * Returns the name of the specified character
11847 * {@code codePoint}, or null if the code point is
11848 * {@link #UNASSIGNED unassigned}.
11849 * <p>
11850 * If the specified character is not assigned a name by
11851 * the <i>UnicodeData</i> file (part of the Unicode Character
11852 * Database maintained by the Unicode Consortium), the returned
11853 * name is the same as the result of the expression:
11854 *
11855 * <blockquote>{@code
11856 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
11857 * + " "
11858 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11859 *
11860 * }</blockquote>
11861 *
11862 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
11863 * returned by this method follows the naming scheme in the
11864 * "Unicode Name Property" section of the Unicode Standard. For other
11865 * code points, such as Hangul/Ideographs, The name generation rule above
11866 * differs from the one defined in the Unicode Standard.
11867 *
11868 * @param codePoint the character (Unicode code point)
11869 *
11870 * @return the name of the specified character, or null if
11871 * the code point is unassigned.
11872 *
11873 * @throws IllegalArgumentException if the specified
11874 * {@code codePoint} is not a valid Unicode
11875 * code point.
11876 *
11877 * @since 1.7
11878 */
11879 public static String getName(int codePoint) {
11880 if (!isValidCodePoint(codePoint)) {
11881 throw new IllegalArgumentException(
11882 String.format("Not a valid Unicode code point: 0x%X", codePoint));
11883 }
11884 String name = CharacterName.getInstance().getName(codePoint);
11885 if (name != null)
11886 return name;
11887 if (getType(codePoint) == UNASSIGNED)
11888 return null;
11889 UnicodeBlock block = UnicodeBlock.of(codePoint);
11890 if (block != null)
11891 return block.toString().replace('_', ' ') + " "
11892 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11893 // should never come here
11894 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11895 }
11896
11897 /**
11898 * Returns the code point value of the Unicode character specified by
11899 * the given character name.
11900 * <p>
11901 * If a character is not assigned a name by the <i>UnicodeData</i>
11902 * file (part of the Unicode Character Database maintained by the Unicode
11903 * Consortium), its name is defined as the result of the expression:
11904 *
11905 * <blockquote>{@code
11906 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
11907 * + " "
11908 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11909 *
11910 * }</blockquote>
11911 * <p>
11912 * The {@code name} matching is case insensitive, with any leading and
11913 * trailing whitespace character removed.
11914 *
11915 * For the code points in the <i>UnicodeData</i> file, this method
11916 * recognizes the name which conforms to the name defined in the
11917 * "Unicode Name Property" section in the Unicode Standard. For other
11918 * code points, this method recognizes the name generated with
11919 * {@link #getName(int)} method.
11920 *
11921 * @param name the character name
11922 *
11923 * @return the code point value of the character specified by its name.
11924 *
11925 * @throws IllegalArgumentException if the specified {@code name}
11926 * is not a valid character name.
11927 * @throws NullPointerException if {@code name} is {@code null}
11928 *
11929 * @since 9
11930 */
11931 public static int codePointOf(String name) {
11932 name = name.trim().toUpperCase(Locale.ROOT);
11933 int cp = CharacterName.getInstance().getCodePoint(name);
11934 if (cp != -1)
11935 return cp;
11936 try {
11937 int off = name.lastIndexOf(' ');
11938 if (off != -1) {
11939 cp = Integer.parseInt(name, off + 1, name.length(), 16);
11940 if (isValidCodePoint(cp) && name.equals(getName(cp)))
11941 return cp;
11942 }
11943 } catch (Exception x) {}
11944 throw new IllegalArgumentException("Unrecognized character name :" + name);
11945 }
11946 }