1 /*
2 * Copyright (c) 2002, 2023, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import jdk.internal.misc.CDS;
29 import jdk.internal.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 wraps a value of the primitive
47 * type {@code char} in an object. An object of class
48 * {@code Character} contains a single field whose type is
49 * {@code char}.
50 * <p>
51 * 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 @SuppressWarnings("unchecked")
236 public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char");
237
238 /*
239 * Normative general types
240 */
241
242 /*
243 * General character types
244 */
245
246 /**
247 * General category "Cn" in the Unicode specification.
248 * @since 1.1
249 */
250 public static final byte UNASSIGNED = 0;
251
252 /**
253 * General category "Lu" in the Unicode specification.
254 * @since 1.1
255 */
256 public static final byte UPPERCASE_LETTER = 1;
257
258 /**
259 * General category "Ll" in the Unicode specification.
260 * @since 1.1
261 */
262 public static final byte LOWERCASE_LETTER = 2;
263
264 /**
265 * General category "Lt" in the Unicode specification.
266 * @since 1.1
267 */
268 public static final byte TITLECASE_LETTER = 3;
269
270 /**
271 * General category "Lm" in the Unicode specification.
272 * @since 1.1
273 */
274 public static final byte MODIFIER_LETTER = 4;
275
276 /**
277 * General category "Lo" in the Unicode specification.
278 * @since 1.1
279 */
280 public static final byte OTHER_LETTER = 5;
281
282 /**
283 * General category "Mn" in the Unicode specification.
284 * @since 1.1
285 */
286 public static final byte NON_SPACING_MARK = 6;
287
288 /**
289 * General category "Me" in the Unicode specification.
290 * @since 1.1
291 */
292 public static final byte ENCLOSING_MARK = 7;
293
294 /**
295 * General category "Mc" in the Unicode specification.
296 * @since 1.1
297 */
298 public static final byte COMBINING_SPACING_MARK = 8;
299
300 /**
301 * General category "Nd" in the Unicode specification.
302 * @since 1.1
303 */
304 public static final byte DECIMAL_DIGIT_NUMBER = 9;
305
306 /**
307 * General category "Nl" in the Unicode specification.
308 * @since 1.1
309 */
310 public static final byte LETTER_NUMBER = 10;
311
312 /**
313 * General category "No" in the Unicode specification.
314 * @since 1.1
315 */
316 public static final byte OTHER_NUMBER = 11;
317
318 /**
319 * General category "Zs" in the Unicode specification.
320 * @since 1.1
321 */
322 public static final byte SPACE_SEPARATOR = 12;
323
324 /**
325 * General category "Zl" in the Unicode specification.
326 * @since 1.1
327 */
328 public static final byte LINE_SEPARATOR = 13;
329
330 /**
331 * General category "Zp" in the Unicode specification.
332 * @since 1.1
333 */
334 public static final byte PARAGRAPH_SEPARATOR = 14;
335
336 /**
337 * General category "Cc" in the Unicode specification.
338 * @since 1.1
339 */
340 public static final byte CONTROL = 15;
341
342 /**
343 * General category "Cf" in the Unicode specification.
344 * @since 1.1
345 */
346 public static final byte FORMAT = 16;
347
348 /**
349 * General category "Co" in the Unicode specification.
350 * @since 1.1
351 */
352 public static final byte PRIVATE_USE = 18;
353
354 /**
355 * General category "Cs" in the Unicode specification.
356 * @since 1.1
357 */
358 public static final byte SURROGATE = 19;
359
360 /**
361 * General category "Pd" in the Unicode specification.
362 * @since 1.1
363 */
364 public static final byte DASH_PUNCTUATION = 20;
365
366 /**
367 * General category "Ps" in the Unicode specification.
368 * @since 1.1
369 */
370 public static final byte START_PUNCTUATION = 21;
371
372 /**
373 * General category "Pe" in the Unicode specification.
374 * @since 1.1
375 */
376 public static final byte END_PUNCTUATION = 22;
377
378 /**
379 * General category "Pc" in the Unicode specification.
380 * @since 1.1
381 */
382 public static final byte CONNECTOR_PUNCTUATION = 23;
383
384 /**
385 * General category "Po" in the Unicode specification.
386 * @since 1.1
387 */
388 public static final byte OTHER_PUNCTUATION = 24;
389
390 /**
391 * General category "Sm" in the Unicode specification.
392 * @since 1.1
393 */
394 public static final byte MATH_SYMBOL = 25;
395
396 /**
397 * General category "Sc" in the Unicode specification.
398 * @since 1.1
399 */
400 public static final byte CURRENCY_SYMBOL = 26;
401
402 /**
403 * General category "Sk" in the Unicode specification.
404 * @since 1.1
405 */
406 public static final byte MODIFIER_SYMBOL = 27;
407
408 /**
409 * General category "So" in the Unicode specification.
410 * @since 1.1
411 */
412 public static final byte OTHER_SYMBOL = 28;
413
414 /**
415 * General category "Pi" in the Unicode specification.
416 * @since 1.4
417 */
418 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
419
420 /**
421 * General category "Pf" in the Unicode specification.
422 * @since 1.4
423 */
424 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
425
426 /**
427 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
428 */
429 static final int ERROR = 0xFFFFFFFF;
430
431
432 /**
433 * Undefined bidirectional character type. Undefined {@code char}
434 * values have undefined directionality in the Unicode specification.
435 * @since 1.4
436 */
437 public static final byte DIRECTIONALITY_UNDEFINED = -1;
438
439 /**
440 * Strong bidirectional character type "L" in the Unicode specification.
441 * @since 1.4
442 */
443 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
444
445 /**
446 * Strong bidirectional character type "R" in the Unicode specification.
447 * @since 1.4
448 */
449 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
450
451 /**
452 * Strong bidirectional character type "AL" in the Unicode specification.
453 * @since 1.4
454 */
455 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
456
457 /**
458 * Weak bidirectional character type "EN" in the Unicode specification.
459 * @since 1.4
460 */
461 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
462
463 /**
464 * Weak bidirectional character type "ES" in the Unicode specification.
465 * @since 1.4
466 */
467 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
468
469 /**
470 * Weak bidirectional character type "ET" in the Unicode specification.
471 * @since 1.4
472 */
473 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
474
475 /**
476 * Weak bidirectional character type "AN" in the Unicode specification.
477 * @since 1.4
478 */
479 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
480
481 /**
482 * Weak bidirectional character type "CS" in the Unicode specification.
483 * @since 1.4
484 */
485 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
486
487 /**
488 * Weak bidirectional character type "NSM" in the Unicode specification.
489 * @since 1.4
490 */
491 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
492
493 /**
494 * Weak bidirectional character type "BN" in the Unicode specification.
495 * @since 1.4
496 */
497 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
498
499 /**
500 * Neutral bidirectional character type "B" in the Unicode specification.
501 * @since 1.4
502 */
503 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
504
505 /**
506 * Neutral bidirectional character type "S" in the Unicode specification.
507 * @since 1.4
508 */
509 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
510
511 /**
512 * Neutral bidirectional character type "WS" in the Unicode specification.
513 * @since 1.4
514 */
515 public static final byte DIRECTIONALITY_WHITESPACE = 12;
516
517 /**
518 * Neutral bidirectional character type "ON" in the Unicode specification.
519 * @since 1.4
520 */
521 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
522
523 /**
524 * Strong bidirectional character type "LRE" in the Unicode specification.
525 * @since 1.4
526 */
527 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
528
529 /**
530 * Strong bidirectional character type "LRO" in the Unicode specification.
531 * @since 1.4
532 */
533 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
534
535 /**
536 * Strong bidirectional character type "RLE" in the Unicode specification.
537 * @since 1.4
538 */
539 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
540
541 /**
542 * Strong bidirectional character type "RLO" in the Unicode specification.
543 * @since 1.4
544 */
545 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
546
547 /**
548 * Weak bidirectional character type "PDF" in the Unicode specification.
549 * @since 1.4
550 */
551 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
552
553 /**
554 * Weak bidirectional character type "LRI" in the Unicode specification.
555 * @since 9
556 */
557 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
558
559 /**
560 * Weak bidirectional character type "RLI" in the Unicode specification.
561 * @since 9
562 */
563 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
564
565 /**
566 * Weak bidirectional character type "FSI" in the Unicode specification.
567 * @since 9
568 */
569 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
570
571 /**
572 * Weak bidirectional character type "PDI" in the Unicode specification.
573 * @since 9
574 */
575 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
576
577 /**
578 * The minimum value of a
579 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
580 * Unicode high-surrogate code unit</a>
581 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
582 * A high-surrogate is also known as a <i>leading-surrogate</i>.
583 *
584 * @since 1.5
585 */
586 public static final char MIN_HIGH_SURROGATE = '\uD800';
587
588 /**
589 * The maximum value of a
590 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
591 * Unicode high-surrogate code unit</a>
592 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
593 * A high-surrogate is also known as a <i>leading-surrogate</i>.
594 *
595 * @since 1.5
596 */
597 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
598
599 /**
600 * The minimum value of a
601 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
602 * Unicode low-surrogate code unit</a>
603 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
604 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
605 *
606 * @since 1.5
607 */
608 public static final char MIN_LOW_SURROGATE = '\uDC00';
609
610 /**
611 * The maximum value of a
612 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
613 * Unicode low-surrogate code unit</a>
614 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
615 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
616 *
617 * @since 1.5
618 */
619 public static final char MAX_LOW_SURROGATE = '\uDFFF';
620
621 /**
622 * The minimum value of a Unicode surrogate code unit in the
623 * UTF-16 encoding, constant {@code '\u005CuD800'}.
624 *
625 * @since 1.5
626 */
627 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
628
629 /**
630 * The maximum value of a Unicode surrogate code unit in the
631 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
632 *
633 * @since 1.5
634 */
635 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
636
637 /**
638 * The minimum value of a
639 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
640 * Unicode supplementary code point</a>, constant {@code U+10000}.
641 *
642 * @since 1.5
643 */
644 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
645
646 /**
647 * The minimum value of a
648 * <a href="http://www.unicode.org/glossary/#code_point">
649 * Unicode code point</a>, constant {@code U+0000}.
650 *
651 * @since 1.5
652 */
653 public static final int MIN_CODE_POINT = 0x000000;
654
655 /**
656 * The maximum value of a
657 * <a href="http://www.unicode.org/glossary/#code_point">
658 * Unicode code point</a>, constant {@code U+10FFFF}.
659 *
660 * @since 1.5
661 */
662 public static final int MAX_CODE_POINT = 0X10FFFF;
663
664 /**
665 * Returns an {@link Optional} containing the nominal descriptor for this
666 * instance.
667 *
668 * @return an {@link Optional} describing the {@linkplain Character} instance
669 * @since 15
670 */
671 @Override
672 public Optional<DynamicConstantDesc<Character>> describeConstable() {
673 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
674 }
675
676 /**
677 * Instances of this class represent particular subsets of the Unicode
678 * character set. The only family of subsets defined in the
679 * {@code Character} class is {@link Character.UnicodeBlock}.
680 * Other portions of the Java API may define other subsets for their
681 * own purposes.
682 *
683 * @since 1.2
684 */
685 public static class Subset {
686
687 private String name;
688
689 /**
690 * Constructs a new {@code Subset} instance.
691 *
692 * @param name The name of this subset
693 * @throws NullPointerException if name is {@code null}
694 */
695 protected Subset(String name) {
696 if (name == null) {
697 throw new NullPointerException("name");
698 }
699 this.name = name;
700 }
701
702 /**
703 * Compares two {@code Subset} objects for equality.
704 * This method returns {@code true} if and only if
705 * {@code this} and the argument refer to the same
706 * object; since this method is {@code final}, this
707 * guarantee holds for all subclasses.
708 */
709 public final boolean equals(Object obj) {
710 return (this == obj);
711 }
712
713 /**
714 * Returns the standard hash code as defined by the
715 * {@link Object#hashCode} method. This method
716 * is {@code final} in order to ensure that the
717 * {@code equals} and {@code hashCode} methods will
718 * be consistent in all subclasses.
719 */
720 public final int hashCode() {
721 return super.hashCode();
722 }
723
724 /**
725 * Returns the name of this subset.
726 */
727 public final String toString() {
728 return name;
729 }
730 }
731
732 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
733 // for the latest specification of Unicode Blocks.
734
735 /**
736 * A family of character subsets representing the character blocks in the
737 * Unicode specification. Character blocks generally define characters
738 * used for a specific script or purpose. A character is contained by
739 * at most one Unicode block.
740 *
741 * @since 1.2
742 */
743 public static final class UnicodeBlock extends Subset {
744 /**
745 * NUM_ENTITIES should match the total number of UnicodeBlocks.
746 * It should be adjusted whenever the Unicode Character Database
747 * is upgraded.
748 */
749 private static final int NUM_ENTITIES = 759;
750 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
751
752 /**
753 * Creates a UnicodeBlock with the given identifier name.
754 * This name must be the same as the block identifier.
755 */
756 private UnicodeBlock(String idName) {
757 super(idName);
758 map.put(idName, this);
759 }
760
761 /**
762 * Creates a UnicodeBlock with the given identifier name and
763 * alias name.
764 */
765 private UnicodeBlock(String idName, String alias) {
766 this(idName);
767 map.put(alias, this);
768 }
769
770 /**
771 * Creates a UnicodeBlock with the given identifier name and
772 * alias names.
773 */
774 private UnicodeBlock(String idName, String... aliases) {
775 this(idName);
776 for (String alias : aliases)
777 map.put(alias, this);
778 }
779
780 /**
781 * Constant for the "Basic Latin" Unicode character block.
782 * @since 1.2
783 */
784 public static final UnicodeBlock BASIC_LATIN =
785 new UnicodeBlock("BASIC_LATIN",
786 "BASIC LATIN",
787 "BASICLATIN");
788
789 /**
790 * Constant for the "Latin-1 Supplement" Unicode character block.
791 * @since 1.2
792 */
793 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
794 new UnicodeBlock("LATIN_1_SUPPLEMENT",
795 "LATIN-1 SUPPLEMENT",
796 "LATIN-1SUPPLEMENT");
797
798 /**
799 * Constant for the "Latin Extended-A" Unicode character block.
800 * @since 1.2
801 */
802 public static final UnicodeBlock LATIN_EXTENDED_A =
803 new UnicodeBlock("LATIN_EXTENDED_A",
804 "LATIN EXTENDED-A",
805 "LATINEXTENDED-A");
806
807 /**
808 * Constant for the "Latin Extended-B" Unicode character block.
809 * @since 1.2
810 */
811 public static final UnicodeBlock LATIN_EXTENDED_B =
812 new UnicodeBlock("LATIN_EXTENDED_B",
813 "LATIN EXTENDED-B",
814 "LATINEXTENDED-B");
815
816 /**
817 * Constant for the "IPA Extensions" Unicode character block.
818 * @since 1.2
819 */
820 public static final UnicodeBlock IPA_EXTENSIONS =
821 new UnicodeBlock("IPA_EXTENSIONS",
822 "IPA EXTENSIONS",
823 "IPAEXTENSIONS");
824
825 /**
826 * Constant for the "Spacing Modifier Letters" Unicode character block.
827 * @since 1.2
828 */
829 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
830 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
831 "SPACING MODIFIER LETTERS",
832 "SPACINGMODIFIERLETTERS");
833
834 /**
835 * Constant for the "Combining Diacritical Marks" Unicode character block.
836 * @since 1.2
837 */
838 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
839 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
840 "COMBINING DIACRITICAL MARKS",
841 "COMBININGDIACRITICALMARKS");
842
843 /**
844 * Constant for the "Greek and Coptic" Unicode character block.
845 * <p>
846 * This block was previously known as the "Greek" block.
847 *
848 * @since 1.2
849 */
850 public static final UnicodeBlock GREEK =
851 new UnicodeBlock("GREEK",
852 "GREEK AND COPTIC",
853 "GREEKANDCOPTIC");
854
855 /**
856 * Constant for the "Cyrillic" Unicode character block.
857 * @since 1.2
858 */
859 public static final UnicodeBlock CYRILLIC =
860 new UnicodeBlock("CYRILLIC");
861
862 /**
863 * Constant for the "Armenian" Unicode character block.
864 * @since 1.2
865 */
866 public static final UnicodeBlock ARMENIAN =
867 new UnicodeBlock("ARMENIAN");
868
869 /**
870 * Constant for the "Hebrew" Unicode character block.
871 * @since 1.2
872 */
873 public static final UnicodeBlock HEBREW =
874 new UnicodeBlock("HEBREW");
875
876 /**
877 * Constant for the "Arabic" Unicode character block.
878 * @since 1.2
879 */
880 public static final UnicodeBlock ARABIC =
881 new UnicodeBlock("ARABIC");
882
883 /**
884 * Constant for the "Devanagari" Unicode character block.
885 * @since 1.2
886 */
887 public static final UnicodeBlock DEVANAGARI =
888 new UnicodeBlock("DEVANAGARI");
889
890 /**
891 * Constant for the "Bengali" Unicode character block.
892 * @since 1.2
893 */
894 public static final UnicodeBlock BENGALI =
895 new UnicodeBlock("BENGALI");
896
897 /**
898 * Constant for the "Gurmukhi" Unicode character block.
899 * @since 1.2
900 */
901 public static final UnicodeBlock GURMUKHI =
902 new UnicodeBlock("GURMUKHI");
903
904 /**
905 * Constant for the "Gujarati" Unicode character block.
906 * @since 1.2
907 */
908 public static final UnicodeBlock GUJARATI =
909 new UnicodeBlock("GUJARATI");
910
911 /**
912 * Constant for the "Oriya" Unicode character block.
913 * @since 1.2
914 */
915 public static final UnicodeBlock ORIYA =
916 new UnicodeBlock("ORIYA");
917
918 /**
919 * Constant for the "Tamil" Unicode character block.
920 * @since 1.2
921 */
922 public static final UnicodeBlock TAMIL =
923 new UnicodeBlock("TAMIL");
924
925 /**
926 * Constant for the "Telugu" Unicode character block.
927 * @since 1.2
928 */
929 public static final UnicodeBlock TELUGU =
930 new UnicodeBlock("TELUGU");
931
932 /**
933 * Constant for the "Kannada" Unicode character block.
934 * @since 1.2
935 */
936 public static final UnicodeBlock KANNADA =
937 new UnicodeBlock("KANNADA");
938
939 /**
940 * Constant for the "Malayalam" Unicode character block.
941 * @since 1.2
942 */
943 public static final UnicodeBlock MALAYALAM =
944 new UnicodeBlock("MALAYALAM");
945
946 /**
947 * Constant for the "Thai" Unicode character block.
948 * @since 1.2
949 */
950 public static final UnicodeBlock THAI =
951 new UnicodeBlock("THAI");
952
953 /**
954 * Constant for the "Lao" Unicode character block.
955 * @since 1.2
956 */
957 public static final UnicodeBlock LAO =
958 new UnicodeBlock("LAO");
959
960 /**
961 * Constant for the "Tibetan" Unicode character block.
962 * @since 1.2
963 */
964 public static final UnicodeBlock TIBETAN =
965 new UnicodeBlock("TIBETAN");
966
967 /**
968 * Constant for the "Georgian" Unicode character block.
969 * @since 1.2
970 */
971 public static final UnicodeBlock GEORGIAN =
972 new UnicodeBlock("GEORGIAN");
973
974 /**
975 * Constant for the "Hangul Jamo" Unicode character block.
976 * @since 1.2
977 */
978 public static final UnicodeBlock HANGUL_JAMO =
979 new UnicodeBlock("HANGUL_JAMO",
980 "HANGUL JAMO",
981 "HANGULJAMO");
982
983 /**
984 * Constant for the "Latin Extended Additional" Unicode character block.
985 * @since 1.2
986 */
987 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
988 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
989 "LATIN EXTENDED ADDITIONAL",
990 "LATINEXTENDEDADDITIONAL");
991
992 /**
993 * Constant for the "Greek Extended" Unicode character block.
994 * @since 1.2
995 */
996 public static final UnicodeBlock GREEK_EXTENDED =
997 new UnicodeBlock("GREEK_EXTENDED",
998 "GREEK EXTENDED",
999 "GREEKEXTENDED");
1000
1001 /**
1002 * Constant for the "General Punctuation" Unicode character block.
1003 * @since 1.2
1004 */
1005 public static final UnicodeBlock GENERAL_PUNCTUATION =
1006 new UnicodeBlock("GENERAL_PUNCTUATION",
1007 "GENERAL PUNCTUATION",
1008 "GENERALPUNCTUATION");
1009
1010 /**
1011 * Constant for the "Superscripts and Subscripts" Unicode character
1012 * block.
1013 * @since 1.2
1014 */
1015 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1016 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1017 "SUPERSCRIPTS AND SUBSCRIPTS",
1018 "SUPERSCRIPTSANDSUBSCRIPTS");
1019
1020 /**
1021 * Constant for the "Currency Symbols" Unicode character block.
1022 * @since 1.2
1023 */
1024 public static final UnicodeBlock CURRENCY_SYMBOLS =
1025 new UnicodeBlock("CURRENCY_SYMBOLS",
1026 "CURRENCY SYMBOLS",
1027 "CURRENCYSYMBOLS");
1028
1029 /**
1030 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1031 * character block.
1032 * <p>
1033 * This block was previously known as "Combining Marks for Symbols".
1034 * @since 1.2
1035 */
1036 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1037 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1038 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1039 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1040 "COMBINING MARKS FOR SYMBOLS",
1041 "COMBININGMARKSFORSYMBOLS");
1042
1043 /**
1044 * Constant for the "Letterlike Symbols" Unicode character block.
1045 * @since 1.2
1046 */
1047 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1048 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1049 "LETTERLIKE SYMBOLS",
1050 "LETTERLIKESYMBOLS");
1051
1052 /**
1053 * Constant for the "Number Forms" Unicode character block.
1054 * @since 1.2
1055 */
1056 public static final UnicodeBlock NUMBER_FORMS =
1057 new UnicodeBlock("NUMBER_FORMS",
1058 "NUMBER FORMS",
1059 "NUMBERFORMS");
1060
1061 /**
1062 * Constant for the "Arrows" Unicode character block.
1063 * @since 1.2
1064 */
1065 public static final UnicodeBlock ARROWS =
1066 new UnicodeBlock("ARROWS");
1067
1068 /**
1069 * Constant for the "Mathematical Operators" Unicode character block.
1070 * @since 1.2
1071 */
1072 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1073 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1074 "MATHEMATICAL OPERATORS",
1075 "MATHEMATICALOPERATORS");
1076
1077 /**
1078 * Constant for the "Miscellaneous Technical" Unicode character block.
1079 * @since 1.2
1080 */
1081 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1082 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1083 "MISCELLANEOUS TECHNICAL",
1084 "MISCELLANEOUSTECHNICAL");
1085
1086 /**
1087 * Constant for the "Control Pictures" Unicode character block.
1088 * @since 1.2
1089 */
1090 public static final UnicodeBlock CONTROL_PICTURES =
1091 new UnicodeBlock("CONTROL_PICTURES",
1092 "CONTROL PICTURES",
1093 "CONTROLPICTURES");
1094
1095 /**
1096 * Constant for the "Optical Character Recognition" Unicode character block.
1097 * @since 1.2
1098 */
1099 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1100 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1101 "OPTICAL CHARACTER RECOGNITION",
1102 "OPTICALCHARACTERRECOGNITION");
1103
1104 /**
1105 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1106 * @since 1.2
1107 */
1108 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1109 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1110 "ENCLOSED ALPHANUMERICS",
1111 "ENCLOSEDALPHANUMERICS");
1112
1113 /**
1114 * Constant for the "Box Drawing" Unicode character block.
1115 * @since 1.2
1116 */
1117 public static final UnicodeBlock BOX_DRAWING =
1118 new UnicodeBlock("BOX_DRAWING",
1119 "BOX DRAWING",
1120 "BOXDRAWING");
1121
1122 /**
1123 * Constant for the "Block Elements" Unicode character block.
1124 * @since 1.2
1125 */
1126 public static final UnicodeBlock BLOCK_ELEMENTS =
1127 new UnicodeBlock("BLOCK_ELEMENTS",
1128 "BLOCK ELEMENTS",
1129 "BLOCKELEMENTS");
1130
1131 /**
1132 * Constant for the "Geometric Shapes" Unicode character block.
1133 * @since 1.2
1134 */
1135 public static final UnicodeBlock GEOMETRIC_SHAPES =
1136 new UnicodeBlock("GEOMETRIC_SHAPES",
1137 "GEOMETRIC SHAPES",
1138 "GEOMETRICSHAPES");
1139
1140 /**
1141 * Constant for the "Miscellaneous Symbols" Unicode character block.
1142 * @since 1.2
1143 */
1144 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1145 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1146 "MISCELLANEOUS SYMBOLS",
1147 "MISCELLANEOUSSYMBOLS");
1148
1149 /**
1150 * Constant for the "Dingbats" Unicode character block.
1151 * @since 1.2
1152 */
1153 public static final UnicodeBlock DINGBATS =
1154 new UnicodeBlock("DINGBATS");
1155
1156 /**
1157 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1158 * @since 1.2
1159 */
1160 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1161 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1162 "CJK SYMBOLS AND PUNCTUATION",
1163 "CJKSYMBOLSANDPUNCTUATION");
1164
1165 /**
1166 * Constant for the "Hiragana" Unicode character block.
1167 * @since 1.2
1168 */
1169 public static final UnicodeBlock HIRAGANA =
1170 new UnicodeBlock("HIRAGANA");
1171
1172 /**
1173 * Constant for the "Katakana" Unicode character block.
1174 * @since 1.2
1175 */
1176 public static final UnicodeBlock KATAKANA =
1177 new UnicodeBlock("KATAKANA");
1178
1179 /**
1180 * Constant for the "Bopomofo" Unicode character block.
1181 * @since 1.2
1182 */
1183 public static final UnicodeBlock BOPOMOFO =
1184 new UnicodeBlock("BOPOMOFO");
1185
1186 /**
1187 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1188 * @since 1.2
1189 */
1190 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1191 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1192 "HANGUL COMPATIBILITY JAMO",
1193 "HANGULCOMPATIBILITYJAMO");
1194
1195 /**
1196 * Constant for the "Kanbun" Unicode character block.
1197 * @since 1.2
1198 */
1199 public static final UnicodeBlock KANBUN =
1200 new UnicodeBlock("KANBUN");
1201
1202 /**
1203 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1204 * @since 1.2
1205 */
1206 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1207 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1208 "ENCLOSED CJK LETTERS AND MONTHS",
1209 "ENCLOSEDCJKLETTERSANDMONTHS");
1210
1211 /**
1212 * Constant for the "CJK Compatibility" Unicode character block.
1213 * @since 1.2
1214 */
1215 public static final UnicodeBlock CJK_COMPATIBILITY =
1216 new UnicodeBlock("CJK_COMPATIBILITY",
1217 "CJK COMPATIBILITY",
1218 "CJKCOMPATIBILITY");
1219
1220 /**
1221 * Constant for the "CJK Unified Ideographs" Unicode character block.
1222 * @since 1.2
1223 */
1224 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1225 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1226 "CJK UNIFIED IDEOGRAPHS",
1227 "CJKUNIFIEDIDEOGRAPHS");
1228
1229 /**
1230 * Constant for the "Hangul Syllables" Unicode character block.
1231 * @since 1.2
1232 */
1233 public static final UnicodeBlock HANGUL_SYLLABLES =
1234 new UnicodeBlock("HANGUL_SYLLABLES",
1235 "HANGUL SYLLABLES",
1236 "HANGULSYLLABLES");
1237
1238 /**
1239 * Constant for the "Private Use Area" Unicode character block.
1240 * @since 1.2
1241 */
1242 public static final UnicodeBlock PRIVATE_USE_AREA =
1243 new UnicodeBlock("PRIVATE_USE_AREA",
1244 "PRIVATE USE AREA",
1245 "PRIVATEUSEAREA");
1246
1247 /**
1248 * Constant for the "CJK Compatibility Ideographs" Unicode character
1249 * block.
1250 * @since 1.2
1251 */
1252 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1253 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1254 "CJK COMPATIBILITY IDEOGRAPHS",
1255 "CJKCOMPATIBILITYIDEOGRAPHS");
1256
1257 /**
1258 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1259 * @since 1.2
1260 */
1261 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1262 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1263 "ALPHABETIC PRESENTATION FORMS",
1264 "ALPHABETICPRESENTATIONFORMS");
1265
1266 /**
1267 * Constant for the "Arabic Presentation Forms-A" Unicode character
1268 * block.
1269 * @since 1.2
1270 */
1271 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1272 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1273 "ARABIC PRESENTATION FORMS-A",
1274 "ARABICPRESENTATIONFORMS-A");
1275
1276 /**
1277 * Constant for the "Combining Half Marks" Unicode character block.
1278 * @since 1.2
1279 */
1280 public static final UnicodeBlock COMBINING_HALF_MARKS =
1281 new UnicodeBlock("COMBINING_HALF_MARKS",
1282 "COMBINING HALF MARKS",
1283 "COMBININGHALFMARKS");
1284
1285 /**
1286 * Constant for the "CJK Compatibility Forms" Unicode character block.
1287 * @since 1.2
1288 */
1289 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1290 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1291 "CJK COMPATIBILITY FORMS",
1292 "CJKCOMPATIBILITYFORMS");
1293
1294 /**
1295 * Constant for the "Small Form Variants" Unicode character block.
1296 * @since 1.2
1297 */
1298 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1299 new UnicodeBlock("SMALL_FORM_VARIANTS",
1300 "SMALL FORM VARIANTS",
1301 "SMALLFORMVARIANTS");
1302
1303 /**
1304 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1305 * @since 1.2
1306 */
1307 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1308 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1309 "ARABIC PRESENTATION FORMS-B",
1310 "ARABICPRESENTATIONFORMS-B");
1311
1312 /**
1313 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1314 * block.
1315 * @since 1.2
1316 */
1317 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1318 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1319 "HALFWIDTH AND FULLWIDTH FORMS",
1320 "HALFWIDTHANDFULLWIDTHFORMS");
1321
1322 /**
1323 * Constant for the "Specials" Unicode character block.
1324 * @since 1.2
1325 */
1326 public static final UnicodeBlock SPECIALS =
1327 new UnicodeBlock("SPECIALS");
1328
1329 /**
1330 * @deprecated
1331 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1332 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1333 * These constants match the block definitions of the Unicode Standard.
1334 * The {@link #of(char)} and {@link #of(int)} methods return the
1335 * standard constants.
1336 */
1337 @Deprecated(since="1.5")
1338 public static final UnicodeBlock SURROGATES_AREA =
1339 new UnicodeBlock("SURROGATES_AREA");
1340
1341 /**
1342 * Constant for the "Syriac" Unicode character block.
1343 * @since 1.4
1344 */
1345 public static final UnicodeBlock SYRIAC =
1346 new UnicodeBlock("SYRIAC");
1347
1348 /**
1349 * Constant for the "Thaana" Unicode character block.
1350 * @since 1.4
1351 */
1352 public static final UnicodeBlock THAANA =
1353 new UnicodeBlock("THAANA");
1354
1355 /**
1356 * Constant for the "Sinhala" Unicode character block.
1357 * @since 1.4
1358 */
1359 public static final UnicodeBlock SINHALA =
1360 new UnicodeBlock("SINHALA");
1361
1362 /**
1363 * Constant for the "Myanmar" Unicode character block.
1364 * @since 1.4
1365 */
1366 public static final UnicodeBlock MYANMAR =
1367 new UnicodeBlock("MYANMAR");
1368
1369 /**
1370 * Constant for the "Ethiopic" Unicode character block.
1371 * @since 1.4
1372 */
1373 public static final UnicodeBlock ETHIOPIC =
1374 new UnicodeBlock("ETHIOPIC");
1375
1376 /**
1377 * Constant for the "Cherokee" Unicode character block.
1378 * @since 1.4
1379 */
1380 public static final UnicodeBlock CHEROKEE =
1381 new UnicodeBlock("CHEROKEE");
1382
1383 /**
1384 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1385 * @since 1.4
1386 */
1387 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1388 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1389 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1390 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1391
1392 /**
1393 * Constant for the "Ogham" Unicode character block.
1394 * @since 1.4
1395 */
1396 public static final UnicodeBlock OGHAM =
1397 new UnicodeBlock("OGHAM");
1398
1399 /**
1400 * Constant for the "Runic" Unicode character block.
1401 * @since 1.4
1402 */
1403 public static final UnicodeBlock RUNIC =
1404 new UnicodeBlock("RUNIC");
1405
1406 /**
1407 * Constant for the "Khmer" Unicode character block.
1408 * @since 1.4
1409 */
1410 public static final UnicodeBlock KHMER =
1411 new UnicodeBlock("KHMER");
1412
1413 /**
1414 * Constant for the "Mongolian" Unicode character block.
1415 * @since 1.4
1416 */
1417 public static final UnicodeBlock MONGOLIAN =
1418 new UnicodeBlock("MONGOLIAN");
1419
1420 /**
1421 * Constant for the "Braille Patterns" Unicode character block.
1422 * @since 1.4
1423 */
1424 public static final UnicodeBlock BRAILLE_PATTERNS =
1425 new UnicodeBlock("BRAILLE_PATTERNS",
1426 "BRAILLE PATTERNS",
1427 "BRAILLEPATTERNS");
1428
1429 /**
1430 * Constant for the "CJK Radicals Supplement" Unicode character block.
1431 * @since 1.4
1432 */
1433 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1434 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1435 "CJK RADICALS SUPPLEMENT",
1436 "CJKRADICALSSUPPLEMENT");
1437
1438 /**
1439 * Constant for the "Kangxi Radicals" Unicode character block.
1440 * @since 1.4
1441 */
1442 public static final UnicodeBlock KANGXI_RADICALS =
1443 new UnicodeBlock("KANGXI_RADICALS",
1444 "KANGXI RADICALS",
1445 "KANGXIRADICALS");
1446
1447 /**
1448 * Constant for the "Ideographic Description Characters" Unicode character block.
1449 * @since 1.4
1450 */
1451 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1452 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1453 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1454 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1455
1456 /**
1457 * Constant for the "Bopomofo Extended" Unicode character block.
1458 * @since 1.4
1459 */
1460 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1461 new UnicodeBlock("BOPOMOFO_EXTENDED",
1462 "BOPOMOFO EXTENDED",
1463 "BOPOMOFOEXTENDED");
1464
1465 /**
1466 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1467 * @since 1.4
1468 */
1469 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1470 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1471 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1472 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1473
1474 /**
1475 * Constant for the "Yi Syllables" Unicode character block.
1476 * @since 1.4
1477 */
1478 public static final UnicodeBlock YI_SYLLABLES =
1479 new UnicodeBlock("YI_SYLLABLES",
1480 "YI SYLLABLES",
1481 "YISYLLABLES");
1482
1483 /**
1484 * Constant for the "Yi Radicals" Unicode character block.
1485 * @since 1.4
1486 */
1487 public static final UnicodeBlock YI_RADICALS =
1488 new UnicodeBlock("YI_RADICALS",
1489 "YI RADICALS",
1490 "YIRADICALS");
1491
1492 /**
1493 * Constant for the "Cyrillic Supplement" Unicode character block.
1494 * This block was previously known as the "Cyrillic Supplementary" block.
1495 * @since 1.5
1496 */
1497 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1498 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1499 "CYRILLIC SUPPLEMENTARY",
1500 "CYRILLICSUPPLEMENTARY",
1501 "CYRILLIC SUPPLEMENT",
1502 "CYRILLICSUPPLEMENT");
1503
1504 /**
1505 * Constant for the "Tagalog" Unicode character block.
1506 * @since 1.5
1507 */
1508 public static final UnicodeBlock TAGALOG =
1509 new UnicodeBlock("TAGALOG");
1510
1511 /**
1512 * Constant for the "Hanunoo" Unicode character block.
1513 * @since 1.5
1514 */
1515 public static final UnicodeBlock HANUNOO =
1516 new UnicodeBlock("HANUNOO");
1517
1518 /**
1519 * Constant for the "Buhid" Unicode character block.
1520 * @since 1.5
1521 */
1522 public static final UnicodeBlock BUHID =
1523 new UnicodeBlock("BUHID");
1524
1525 /**
1526 * Constant for the "Tagbanwa" Unicode character block.
1527 * @since 1.5
1528 */
1529 public static final UnicodeBlock TAGBANWA =
1530 new UnicodeBlock("TAGBANWA");
1531
1532 /**
1533 * Constant for the "Limbu" Unicode character block.
1534 * @since 1.5
1535 */
1536 public static final UnicodeBlock LIMBU =
1537 new UnicodeBlock("LIMBU");
1538
1539 /**
1540 * Constant for the "Tai Le" Unicode character block.
1541 * @since 1.5
1542 */
1543 public static final UnicodeBlock TAI_LE =
1544 new UnicodeBlock("TAI_LE",
1545 "TAI LE",
1546 "TAILE");
1547
1548 /**
1549 * Constant for the "Khmer Symbols" Unicode character block.
1550 * @since 1.5
1551 */
1552 public static final UnicodeBlock KHMER_SYMBOLS =
1553 new UnicodeBlock("KHMER_SYMBOLS",
1554 "KHMER SYMBOLS",
1555 "KHMERSYMBOLS");
1556
1557 /**
1558 * Constant for the "Phonetic Extensions" Unicode character block.
1559 * @since 1.5
1560 */
1561 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1562 new UnicodeBlock("PHONETIC_EXTENSIONS",
1563 "PHONETIC EXTENSIONS",
1564 "PHONETICEXTENSIONS");
1565
1566 /**
1567 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1568 * @since 1.5
1569 */
1570 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1571 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1572 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1573 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1574
1575 /**
1576 * Constant for the "Supplemental Arrows-A" Unicode character block.
1577 * @since 1.5
1578 */
1579 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1580 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1581 "SUPPLEMENTAL ARROWS-A",
1582 "SUPPLEMENTALARROWS-A");
1583
1584 /**
1585 * Constant for the "Supplemental Arrows-B" Unicode character block.
1586 * @since 1.5
1587 */
1588 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1589 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1590 "SUPPLEMENTAL ARROWS-B",
1591 "SUPPLEMENTALARROWS-B");
1592
1593 /**
1594 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1595 * character block.
1596 * @since 1.5
1597 */
1598 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1599 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1600 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1601 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1602
1603 /**
1604 * Constant for the "Supplemental Mathematical Operators" Unicode
1605 * character block.
1606 * @since 1.5
1607 */
1608 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1609 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1610 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1611 "SUPPLEMENTALMATHEMATICALOPERATORS");
1612
1613 /**
1614 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1615 * block.
1616 * @since 1.5
1617 */
1618 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1619 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1620 "MISCELLANEOUS SYMBOLS AND ARROWS",
1621 "MISCELLANEOUSSYMBOLSANDARROWS");
1622
1623 /**
1624 * Constant for the "Katakana Phonetic Extensions" Unicode character
1625 * block.
1626 * @since 1.5
1627 */
1628 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1629 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1630 "KATAKANA PHONETIC EXTENSIONS",
1631 "KATAKANAPHONETICEXTENSIONS");
1632
1633 /**
1634 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1635 * @since 1.5
1636 */
1637 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1638 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1639 "YIJING HEXAGRAM SYMBOLS",
1640 "YIJINGHEXAGRAMSYMBOLS");
1641
1642 /**
1643 * Constant for the "Variation Selectors" Unicode character block.
1644 * @since 1.5
1645 */
1646 public static final UnicodeBlock VARIATION_SELECTORS =
1647 new UnicodeBlock("VARIATION_SELECTORS",
1648 "VARIATION SELECTORS",
1649 "VARIATIONSELECTORS");
1650
1651 /**
1652 * Constant for the "Linear B Syllabary" Unicode character block.
1653 * @since 1.5
1654 */
1655 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1656 new UnicodeBlock("LINEAR_B_SYLLABARY",
1657 "LINEAR B SYLLABARY",
1658 "LINEARBSYLLABARY");
1659
1660 /**
1661 * Constant for the "Linear B Ideograms" Unicode character block.
1662 * @since 1.5
1663 */
1664 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1665 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1666 "LINEAR B IDEOGRAMS",
1667 "LINEARBIDEOGRAMS");
1668
1669 /**
1670 * Constant for the "Aegean Numbers" Unicode character block.
1671 * @since 1.5
1672 */
1673 public static final UnicodeBlock AEGEAN_NUMBERS =
1674 new UnicodeBlock("AEGEAN_NUMBERS",
1675 "AEGEAN NUMBERS",
1676 "AEGEANNUMBERS");
1677
1678 /**
1679 * Constant for the "Old Italic" Unicode character block.
1680 * @since 1.5
1681 */
1682 public static final UnicodeBlock OLD_ITALIC =
1683 new UnicodeBlock("OLD_ITALIC",
1684 "OLD ITALIC",
1685 "OLDITALIC");
1686
1687 /**
1688 * Constant for the "Gothic" Unicode character block.
1689 * @since 1.5
1690 */
1691 public static final UnicodeBlock GOTHIC =
1692 new UnicodeBlock("GOTHIC");
1693
1694 /**
1695 * Constant for the "Ugaritic" Unicode character block.
1696 * @since 1.5
1697 */
1698 public static final UnicodeBlock UGARITIC =
1699 new UnicodeBlock("UGARITIC");
1700
1701 /**
1702 * Constant for the "Deseret" Unicode character block.
1703 * @since 1.5
1704 */
1705 public static final UnicodeBlock DESERET =
1706 new UnicodeBlock("DESERET");
1707
1708 /**
1709 * Constant for the "Shavian" Unicode character block.
1710 * @since 1.5
1711 */
1712 public static final UnicodeBlock SHAVIAN =
1713 new UnicodeBlock("SHAVIAN");
1714
1715 /**
1716 * Constant for the "Osmanya" Unicode character block.
1717 * @since 1.5
1718 */
1719 public static final UnicodeBlock OSMANYA =
1720 new UnicodeBlock("OSMANYA");
1721
1722 /**
1723 * Constant for the "Cypriot Syllabary" Unicode character block.
1724 * @since 1.5
1725 */
1726 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1727 new UnicodeBlock("CYPRIOT_SYLLABARY",
1728 "CYPRIOT SYLLABARY",
1729 "CYPRIOTSYLLABARY");
1730
1731 /**
1732 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1733 * @since 1.5
1734 */
1735 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1736 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1737 "BYZANTINE MUSICAL SYMBOLS",
1738 "BYZANTINEMUSICALSYMBOLS");
1739
1740 /**
1741 * Constant for the "Musical Symbols" Unicode character block.
1742 * @since 1.5
1743 */
1744 public static final UnicodeBlock MUSICAL_SYMBOLS =
1745 new UnicodeBlock("MUSICAL_SYMBOLS",
1746 "MUSICAL SYMBOLS",
1747 "MUSICALSYMBOLS");
1748
1749 /**
1750 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1751 * @since 1.5
1752 */
1753 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1754 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1755 "TAI XUAN JING SYMBOLS",
1756 "TAIXUANJINGSYMBOLS");
1757
1758 /**
1759 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1760 * character block.
1761 * @since 1.5
1762 */
1763 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1764 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1765 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1766 "MATHEMATICALALPHANUMERICSYMBOLS");
1767
1768 /**
1769 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1770 * character block.
1771 * @since 1.5
1772 */
1773 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1774 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1775 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1776 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1777
1778 /**
1779 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1780 * @since 1.5
1781 */
1782 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1783 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1784 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1785 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1786
1787 /**
1788 * Constant for the "Tags" Unicode character block.
1789 * @since 1.5
1790 */
1791 public static final UnicodeBlock TAGS =
1792 new UnicodeBlock("TAGS");
1793
1794 /**
1795 * Constant for the "Variation Selectors Supplement" Unicode character
1796 * block.
1797 * @since 1.5
1798 */
1799 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1800 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1801 "VARIATION SELECTORS SUPPLEMENT",
1802 "VARIATIONSELECTORSSUPPLEMENT");
1803
1804 /**
1805 * Constant for the "Supplementary Private Use Area-A" Unicode character
1806 * block.
1807 * @since 1.5
1808 */
1809 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1810 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1811 "SUPPLEMENTARY PRIVATE USE AREA-A",
1812 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1813
1814 /**
1815 * Constant for the "Supplementary Private Use Area-B" Unicode character
1816 * block.
1817 * @since 1.5
1818 */
1819 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1820 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1821 "SUPPLEMENTARY PRIVATE USE AREA-B",
1822 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1823
1824 /**
1825 * Constant for the "High Surrogates" Unicode character block.
1826 * This block represents codepoint values in the high surrogate
1827 * range: U+D800 through U+DB7F
1828 *
1829 * @since 1.5
1830 */
1831 public static final UnicodeBlock HIGH_SURROGATES =
1832 new UnicodeBlock("HIGH_SURROGATES",
1833 "HIGH SURROGATES",
1834 "HIGHSURROGATES");
1835
1836 /**
1837 * Constant for the "High Private Use Surrogates" Unicode character
1838 * block.
1839 * This block represents codepoint values in the private use high
1840 * surrogate range: U+DB80 through U+DBFF
1841 *
1842 * @since 1.5
1843 */
1844 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1845 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1846 "HIGH PRIVATE USE SURROGATES",
1847 "HIGHPRIVATEUSESURROGATES");
1848
1849 /**
1850 * Constant for the "Low Surrogates" Unicode character block.
1851 * This block represents codepoint values in the low surrogate
1852 * range: U+DC00 through U+DFFF
1853 *
1854 * @since 1.5
1855 */
1856 public static final UnicodeBlock LOW_SURROGATES =
1857 new UnicodeBlock("LOW_SURROGATES",
1858 "LOW SURROGATES",
1859 "LOWSURROGATES");
1860
1861 /**
1862 * Constant for the "Arabic Supplement" Unicode character block.
1863 * @since 1.7
1864 */
1865 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1866 new UnicodeBlock("ARABIC_SUPPLEMENT",
1867 "ARABIC SUPPLEMENT",
1868 "ARABICSUPPLEMENT");
1869
1870 /**
1871 * Constant for the "NKo" Unicode character block.
1872 * @since 1.7
1873 */
1874 public static final UnicodeBlock NKO =
1875 new UnicodeBlock("NKO");
1876
1877 /**
1878 * Constant for the "Samaritan" Unicode character block.
1879 * @since 1.7
1880 */
1881 public static final UnicodeBlock SAMARITAN =
1882 new UnicodeBlock("SAMARITAN");
1883
1884 /**
1885 * Constant for the "Mandaic" Unicode character block.
1886 * @since 1.7
1887 */
1888 public static final UnicodeBlock MANDAIC =
1889 new UnicodeBlock("MANDAIC");
1890
1891 /**
1892 * Constant for the "Ethiopic Supplement" Unicode character block.
1893 * @since 1.7
1894 */
1895 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1896 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1897 "ETHIOPIC SUPPLEMENT",
1898 "ETHIOPICSUPPLEMENT");
1899
1900 /**
1901 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1902 * Unicode character block.
1903 * @since 1.7
1904 */
1905 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1906 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1907 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1908 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1909
1910 /**
1911 * Constant for the "New Tai Lue" Unicode character block.
1912 * @since 1.7
1913 */
1914 public static final UnicodeBlock NEW_TAI_LUE =
1915 new UnicodeBlock("NEW_TAI_LUE",
1916 "NEW TAI LUE",
1917 "NEWTAILUE");
1918
1919 /**
1920 * Constant for the "Buginese" Unicode character block.
1921 * @since 1.7
1922 */
1923 public static final UnicodeBlock BUGINESE =
1924 new UnicodeBlock("BUGINESE");
1925
1926 /**
1927 * Constant for the "Tai Tham" Unicode character block.
1928 * @since 1.7
1929 */
1930 public static final UnicodeBlock TAI_THAM =
1931 new UnicodeBlock("TAI_THAM",
1932 "TAI THAM",
1933 "TAITHAM");
1934
1935 /**
1936 * Constant for the "Balinese" Unicode character block.
1937 * @since 1.7
1938 */
1939 public static final UnicodeBlock BALINESE =
1940 new UnicodeBlock("BALINESE");
1941
1942 /**
1943 * Constant for the "Sundanese" Unicode character block.
1944 * @since 1.7
1945 */
1946 public static final UnicodeBlock SUNDANESE =
1947 new UnicodeBlock("SUNDANESE");
1948
1949 /**
1950 * Constant for the "Batak" Unicode character block.
1951 * @since 1.7
1952 */
1953 public static final UnicodeBlock BATAK =
1954 new UnicodeBlock("BATAK");
1955
1956 /**
1957 * Constant for the "Lepcha" Unicode character block.
1958 * @since 1.7
1959 */
1960 public static final UnicodeBlock LEPCHA =
1961 new UnicodeBlock("LEPCHA");
1962
1963 /**
1964 * Constant for the "Ol Chiki" Unicode character block.
1965 * @since 1.7
1966 */
1967 public static final UnicodeBlock OL_CHIKI =
1968 new UnicodeBlock("OL_CHIKI",
1969 "OL CHIKI",
1970 "OLCHIKI");
1971
1972 /**
1973 * Constant for the "Vedic Extensions" Unicode character block.
1974 * @since 1.7
1975 */
1976 public static final UnicodeBlock VEDIC_EXTENSIONS =
1977 new UnicodeBlock("VEDIC_EXTENSIONS",
1978 "VEDIC EXTENSIONS",
1979 "VEDICEXTENSIONS");
1980
1981 /**
1982 * Constant for the "Phonetic Extensions Supplement" Unicode character
1983 * block.
1984 * @since 1.7
1985 */
1986 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1987 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1988 "PHONETIC EXTENSIONS SUPPLEMENT",
1989 "PHONETICEXTENSIONSSUPPLEMENT");
1990
1991 /**
1992 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1993 * character block.
1994 * @since 1.7
1995 */
1996 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1997 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1998 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1999 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2000
2001 /**
2002 * Constant for the "Glagolitic" Unicode character block.
2003 * @since 1.7
2004 */
2005 public static final UnicodeBlock GLAGOLITIC =
2006 new UnicodeBlock("GLAGOLITIC");
2007
2008 /**
2009 * Constant for the "Latin Extended-C" Unicode character block.
2010 * @since 1.7
2011 */
2012 public static final UnicodeBlock LATIN_EXTENDED_C =
2013 new UnicodeBlock("LATIN_EXTENDED_C",
2014 "LATIN EXTENDED-C",
2015 "LATINEXTENDED-C");
2016
2017 /**
2018 * Constant for the "Coptic" Unicode character block.
2019 * @since 1.7
2020 */
2021 public static final UnicodeBlock COPTIC =
2022 new UnicodeBlock("COPTIC");
2023
2024 /**
2025 * Constant for the "Georgian Supplement" Unicode character block.
2026 * @since 1.7
2027 */
2028 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2029 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2030 "GEORGIAN SUPPLEMENT",
2031 "GEORGIANSUPPLEMENT");
2032
2033 /**
2034 * Constant for the "Tifinagh" Unicode character block.
2035 * @since 1.7
2036 */
2037 public static final UnicodeBlock TIFINAGH =
2038 new UnicodeBlock("TIFINAGH");
2039
2040 /**
2041 * Constant for the "Ethiopic Extended" Unicode character block.
2042 * @since 1.7
2043 */
2044 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2045 new UnicodeBlock("ETHIOPIC_EXTENDED",
2046 "ETHIOPIC EXTENDED",
2047 "ETHIOPICEXTENDED");
2048
2049 /**
2050 * Constant for the "Cyrillic Extended-A" Unicode character block.
2051 * @since 1.7
2052 */
2053 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2054 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2055 "CYRILLIC EXTENDED-A",
2056 "CYRILLICEXTENDED-A");
2057
2058 /**
2059 * Constant for the "Supplemental Punctuation" Unicode character block.
2060 * @since 1.7
2061 */
2062 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2063 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2064 "SUPPLEMENTAL PUNCTUATION",
2065 "SUPPLEMENTALPUNCTUATION");
2066
2067 /**
2068 * Constant for the "CJK Strokes" Unicode character block.
2069 * @since 1.7
2070 */
2071 public static final UnicodeBlock CJK_STROKES =
2072 new UnicodeBlock("CJK_STROKES",
2073 "CJK STROKES",
2074 "CJKSTROKES");
2075
2076 /**
2077 * Constant for the "Lisu" Unicode character block.
2078 * @since 1.7
2079 */
2080 public static final UnicodeBlock LISU =
2081 new UnicodeBlock("LISU");
2082
2083 /**
2084 * Constant for the "Vai" Unicode character block.
2085 * @since 1.7
2086 */
2087 public static final UnicodeBlock VAI =
2088 new UnicodeBlock("VAI");
2089
2090 /**
2091 * Constant for the "Cyrillic Extended-B" Unicode character block.
2092 * @since 1.7
2093 */
2094 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2095 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2096 "CYRILLIC EXTENDED-B",
2097 "CYRILLICEXTENDED-B");
2098
2099 /**
2100 * Constant for the "Bamum" Unicode character block.
2101 * @since 1.7
2102 */
2103 public static final UnicodeBlock BAMUM =
2104 new UnicodeBlock("BAMUM");
2105
2106 /**
2107 * Constant for the "Modifier Tone Letters" Unicode character block.
2108 * @since 1.7
2109 */
2110 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2111 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2112 "MODIFIER TONE LETTERS",
2113 "MODIFIERTONELETTERS");
2114
2115 /**
2116 * Constant for the "Latin Extended-D" Unicode character block.
2117 * @since 1.7
2118 */
2119 public static final UnicodeBlock LATIN_EXTENDED_D =
2120 new UnicodeBlock("LATIN_EXTENDED_D",
2121 "LATIN EXTENDED-D",
2122 "LATINEXTENDED-D");
2123
2124 /**
2125 * Constant for the "Syloti Nagri" Unicode character block.
2126 * @since 1.7
2127 */
2128 public static final UnicodeBlock SYLOTI_NAGRI =
2129 new UnicodeBlock("SYLOTI_NAGRI",
2130 "SYLOTI NAGRI",
2131 "SYLOTINAGRI");
2132
2133 /**
2134 * Constant for the "Common Indic Number Forms" Unicode character block.
2135 * @since 1.7
2136 */
2137 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2138 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2139 "COMMON INDIC NUMBER FORMS",
2140 "COMMONINDICNUMBERFORMS");
2141
2142 /**
2143 * Constant for the "Phags-pa" Unicode character block.
2144 * @since 1.7
2145 */
2146 public static final UnicodeBlock PHAGS_PA =
2147 new UnicodeBlock("PHAGS_PA",
2148 "PHAGS-PA");
2149
2150 /**
2151 * Constant for the "Saurashtra" Unicode character block.
2152 * @since 1.7
2153 */
2154 public static final UnicodeBlock SAURASHTRA =
2155 new UnicodeBlock("SAURASHTRA");
2156
2157 /**
2158 * Constant for the "Devanagari Extended" Unicode character block.
2159 * @since 1.7
2160 */
2161 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2162 new UnicodeBlock("DEVANAGARI_EXTENDED",
2163 "DEVANAGARI EXTENDED",
2164 "DEVANAGARIEXTENDED");
2165
2166 /**
2167 * Constant for the "Kayah Li" Unicode character block.
2168 * @since 1.7
2169 */
2170 public static final UnicodeBlock KAYAH_LI =
2171 new UnicodeBlock("KAYAH_LI",
2172 "KAYAH LI",
2173 "KAYAHLI");
2174
2175 /**
2176 * Constant for the "Rejang" Unicode character block.
2177 * @since 1.7
2178 */
2179 public static final UnicodeBlock REJANG =
2180 new UnicodeBlock("REJANG");
2181
2182 /**
2183 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2184 * @since 1.7
2185 */
2186 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2187 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2188 "HANGUL JAMO EXTENDED-A",
2189 "HANGULJAMOEXTENDED-A");
2190
2191 /**
2192 * Constant for the "Javanese" Unicode character block.
2193 * @since 1.7
2194 */
2195 public static final UnicodeBlock JAVANESE =
2196 new UnicodeBlock("JAVANESE");
2197
2198 /**
2199 * Constant for the "Cham" Unicode character block.
2200 * @since 1.7
2201 */
2202 public static final UnicodeBlock CHAM =
2203 new UnicodeBlock("CHAM");
2204
2205 /**
2206 * Constant for the "Myanmar Extended-A" Unicode character block.
2207 * @since 1.7
2208 */
2209 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2210 new UnicodeBlock("MYANMAR_EXTENDED_A",
2211 "MYANMAR EXTENDED-A",
2212 "MYANMAREXTENDED-A");
2213
2214 /**
2215 * Constant for the "Tai Viet" Unicode character block.
2216 * @since 1.7
2217 */
2218 public static final UnicodeBlock TAI_VIET =
2219 new UnicodeBlock("TAI_VIET",
2220 "TAI VIET",
2221 "TAIVIET");
2222
2223 /**
2224 * Constant for the "Ethiopic Extended-A" Unicode character block.
2225 * @since 1.7
2226 */
2227 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2228 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2229 "ETHIOPIC EXTENDED-A",
2230 "ETHIOPICEXTENDED-A");
2231
2232 /**
2233 * Constant for the "Meetei Mayek" Unicode character block.
2234 * @since 1.7
2235 */
2236 public static final UnicodeBlock MEETEI_MAYEK =
2237 new UnicodeBlock("MEETEI_MAYEK",
2238 "MEETEI MAYEK",
2239 "MEETEIMAYEK");
2240
2241 /**
2242 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2243 * @since 1.7
2244 */
2245 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2246 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2247 "HANGUL JAMO EXTENDED-B",
2248 "HANGULJAMOEXTENDED-B");
2249
2250 /**
2251 * Constant for the "Vertical Forms" Unicode character block.
2252 * @since 1.7
2253 */
2254 public static final UnicodeBlock VERTICAL_FORMS =
2255 new UnicodeBlock("VERTICAL_FORMS",
2256 "VERTICAL FORMS",
2257 "VERTICALFORMS");
2258
2259 /**
2260 * Constant for the "Ancient Greek Numbers" Unicode character block.
2261 * @since 1.7
2262 */
2263 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2264 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2265 "ANCIENT GREEK NUMBERS",
2266 "ANCIENTGREEKNUMBERS");
2267
2268 /**
2269 * Constant for the "Ancient Symbols" Unicode character block.
2270 * @since 1.7
2271 */
2272 public static final UnicodeBlock ANCIENT_SYMBOLS =
2273 new UnicodeBlock("ANCIENT_SYMBOLS",
2274 "ANCIENT SYMBOLS",
2275 "ANCIENTSYMBOLS");
2276
2277 /**
2278 * Constant for the "Phaistos Disc" Unicode character block.
2279 * @since 1.7
2280 */
2281 public static final UnicodeBlock PHAISTOS_DISC =
2282 new UnicodeBlock("PHAISTOS_DISC",
2283 "PHAISTOS DISC",
2284 "PHAISTOSDISC");
2285
2286 /**
2287 * Constant for the "Lycian" Unicode character block.
2288 * @since 1.7
2289 */
2290 public static final UnicodeBlock LYCIAN =
2291 new UnicodeBlock("LYCIAN");
2292
2293 /**
2294 * Constant for the "Carian" Unicode character block.
2295 * @since 1.7
2296 */
2297 public static final UnicodeBlock CARIAN =
2298 new UnicodeBlock("CARIAN");
2299
2300 /**
2301 * Constant for the "Old Persian" Unicode character block.
2302 * @since 1.7
2303 */
2304 public static final UnicodeBlock OLD_PERSIAN =
2305 new UnicodeBlock("OLD_PERSIAN",
2306 "OLD PERSIAN",
2307 "OLDPERSIAN");
2308
2309 /**
2310 * Constant for the "Imperial Aramaic" Unicode character block.
2311 * @since 1.7
2312 */
2313 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2314 new UnicodeBlock("IMPERIAL_ARAMAIC",
2315 "IMPERIAL ARAMAIC",
2316 "IMPERIALARAMAIC");
2317
2318 /**
2319 * Constant for the "Phoenician" Unicode character block.
2320 * @since 1.7
2321 */
2322 public static final UnicodeBlock PHOENICIAN =
2323 new UnicodeBlock("PHOENICIAN");
2324
2325 /**
2326 * Constant for the "Lydian" Unicode character block.
2327 * @since 1.7
2328 */
2329 public static final UnicodeBlock LYDIAN =
2330 new UnicodeBlock("LYDIAN");
2331
2332 /**
2333 * Constant for the "Kharoshthi" Unicode character block.
2334 * @since 1.7
2335 */
2336 public static final UnicodeBlock KHAROSHTHI =
2337 new UnicodeBlock("KHAROSHTHI");
2338
2339 /**
2340 * Constant for the "Old South Arabian" Unicode character block.
2341 * @since 1.7
2342 */
2343 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2344 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2345 "OLD SOUTH ARABIAN",
2346 "OLDSOUTHARABIAN");
2347
2348 /**
2349 * Constant for the "Avestan" Unicode character block.
2350 * @since 1.7
2351 */
2352 public static final UnicodeBlock AVESTAN =
2353 new UnicodeBlock("AVESTAN");
2354
2355 /**
2356 * Constant for the "Inscriptional Parthian" Unicode character block.
2357 * @since 1.7
2358 */
2359 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2360 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2361 "INSCRIPTIONAL PARTHIAN",
2362 "INSCRIPTIONALPARTHIAN");
2363
2364 /**
2365 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2366 * @since 1.7
2367 */
2368 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2369 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2370 "INSCRIPTIONAL PAHLAVI",
2371 "INSCRIPTIONALPAHLAVI");
2372
2373 /**
2374 * Constant for the "Old Turkic" Unicode character block.
2375 * @since 1.7
2376 */
2377 public static final UnicodeBlock OLD_TURKIC =
2378 new UnicodeBlock("OLD_TURKIC",
2379 "OLD TURKIC",
2380 "OLDTURKIC");
2381
2382 /**
2383 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2384 * @since 1.7
2385 */
2386 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2387 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2388 "RUMI NUMERAL SYMBOLS",
2389 "RUMINUMERALSYMBOLS");
2390
2391 /**
2392 * Constant for the "Brahmi" Unicode character block.
2393 * @since 1.7
2394 */
2395 public static final UnicodeBlock BRAHMI =
2396 new UnicodeBlock("BRAHMI");
2397
2398 /**
2399 * Constant for the "Kaithi" Unicode character block.
2400 * @since 1.7
2401 */
2402 public static final UnicodeBlock KAITHI =
2403 new UnicodeBlock("KAITHI");
2404
2405 /**
2406 * Constant for the "Cuneiform" Unicode character block.
2407 * @since 1.7
2408 */
2409 public static final UnicodeBlock CUNEIFORM =
2410 new UnicodeBlock("CUNEIFORM");
2411
2412 /**
2413 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2414 * character block.
2415 * @since 1.7
2416 */
2417 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2418 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2419 "CUNEIFORM NUMBERS AND PUNCTUATION",
2420 "CUNEIFORMNUMBERSANDPUNCTUATION");
2421
2422 /**
2423 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2424 * @since 1.7
2425 */
2426 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2427 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2428 "EGYPTIAN HIEROGLYPHS",
2429 "EGYPTIANHIEROGLYPHS");
2430
2431 /**
2432 * Constant for the "Bamum Supplement" Unicode character block.
2433 * @since 1.7
2434 */
2435 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2436 new UnicodeBlock("BAMUM_SUPPLEMENT",
2437 "BAMUM SUPPLEMENT",
2438 "BAMUMSUPPLEMENT");
2439
2440 /**
2441 * Constant for the "Kana Supplement" Unicode character block.
2442 * @since 1.7
2443 */
2444 public static final UnicodeBlock KANA_SUPPLEMENT =
2445 new UnicodeBlock("KANA_SUPPLEMENT",
2446 "KANA SUPPLEMENT",
2447 "KANASUPPLEMENT");
2448
2449 /**
2450 * Constant for the "Ancient Greek Musical Notation" Unicode character
2451 * block.
2452 * @since 1.7
2453 */
2454 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2455 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2456 "ANCIENT GREEK MUSICAL NOTATION",
2457 "ANCIENTGREEKMUSICALNOTATION");
2458
2459 /**
2460 * Constant for the "Counting Rod Numerals" Unicode character block.
2461 * @since 1.7
2462 */
2463 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2464 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2465 "COUNTING ROD NUMERALS",
2466 "COUNTINGRODNUMERALS");
2467
2468 /**
2469 * Constant for the "Mahjong Tiles" Unicode character block.
2470 * @since 1.7
2471 */
2472 public static final UnicodeBlock MAHJONG_TILES =
2473 new UnicodeBlock("MAHJONG_TILES",
2474 "MAHJONG TILES",
2475 "MAHJONGTILES");
2476
2477 /**
2478 * Constant for the "Domino Tiles" Unicode character block.
2479 * @since 1.7
2480 */
2481 public static final UnicodeBlock DOMINO_TILES =
2482 new UnicodeBlock("DOMINO_TILES",
2483 "DOMINO TILES",
2484 "DOMINOTILES");
2485
2486 /**
2487 * Constant for the "Playing Cards" Unicode character block.
2488 * @since 1.7
2489 */
2490 public static final UnicodeBlock PLAYING_CARDS =
2491 new UnicodeBlock("PLAYING_CARDS",
2492 "PLAYING CARDS",
2493 "PLAYINGCARDS");
2494
2495 /**
2496 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2497 * block.
2498 * @since 1.7
2499 */
2500 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2501 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2502 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2503 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2504
2505 /**
2506 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2507 * block.
2508 * @since 1.7
2509 */
2510 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2511 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2512 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2513 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2514
2515 /**
2516 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2517 * character block.
2518 * @since 1.7
2519 */
2520 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2521 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2522 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2523 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2524
2525 /**
2526 * Constant for the "Emoticons" Unicode character block.
2527 * @since 1.7
2528 */
2529 public static final UnicodeBlock EMOTICONS =
2530 new UnicodeBlock("EMOTICONS");
2531
2532 /**
2533 * Constant for the "Transport And Map Symbols" Unicode character block.
2534 * @since 1.7
2535 */
2536 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2537 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2538 "TRANSPORT AND MAP SYMBOLS",
2539 "TRANSPORTANDMAPSYMBOLS");
2540
2541 /**
2542 * Constant for the "Alchemical Symbols" Unicode character block.
2543 * @since 1.7
2544 */
2545 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2546 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2547 "ALCHEMICAL SYMBOLS",
2548 "ALCHEMICALSYMBOLS");
2549
2550 /**
2551 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2552 * character block.
2553 * @since 1.7
2554 */
2555 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2556 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2557 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2558 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2559
2560 /**
2561 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2562 * character block.
2563 * @since 1.7
2564 */
2565 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2566 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2567 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2568 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2569
2570 /**
2571 * Constant for the "Arabic Extended-A" Unicode character block.
2572 * @since 1.8
2573 */
2574 public static final UnicodeBlock ARABIC_EXTENDED_A =
2575 new UnicodeBlock("ARABIC_EXTENDED_A",
2576 "ARABIC EXTENDED-A",
2577 "ARABICEXTENDED-A");
2578
2579 /**
2580 * Constant for the "Sundanese Supplement" Unicode character block.
2581 * @since 1.8
2582 */
2583 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2584 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2585 "SUNDANESE SUPPLEMENT",
2586 "SUNDANESESUPPLEMENT");
2587
2588 /**
2589 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2590 * @since 1.8
2591 */
2592 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2593 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2594 "MEETEI MAYEK EXTENSIONS",
2595 "MEETEIMAYEKEXTENSIONS");
2596
2597 /**
2598 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2599 * @since 1.8
2600 */
2601 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2602 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2603 "MEROITIC HIEROGLYPHS",
2604 "MEROITICHIEROGLYPHS");
2605
2606 /**
2607 * Constant for the "Meroitic Cursive" Unicode character block.
2608 * @since 1.8
2609 */
2610 public static final UnicodeBlock MEROITIC_CURSIVE =
2611 new UnicodeBlock("MEROITIC_CURSIVE",
2612 "MEROITIC CURSIVE",
2613 "MEROITICCURSIVE");
2614
2615 /**
2616 * Constant for the "Sora Sompeng" Unicode character block.
2617 * @since 1.8
2618 */
2619 public static final UnicodeBlock SORA_SOMPENG =
2620 new UnicodeBlock("SORA_SOMPENG",
2621 "SORA SOMPENG",
2622 "SORASOMPENG");
2623
2624 /**
2625 * Constant for the "Chakma" Unicode character block.
2626 * @since 1.8
2627 */
2628 public static final UnicodeBlock CHAKMA =
2629 new UnicodeBlock("CHAKMA");
2630
2631 /**
2632 * Constant for the "Sharada" Unicode character block.
2633 * @since 1.8
2634 */
2635 public static final UnicodeBlock SHARADA =
2636 new UnicodeBlock("SHARADA");
2637
2638 /**
2639 * Constant for the "Takri" Unicode character block.
2640 * @since 1.8
2641 */
2642 public static final UnicodeBlock TAKRI =
2643 new UnicodeBlock("TAKRI");
2644
2645 /**
2646 * Constant for the "Miao" Unicode character block.
2647 * @since 1.8
2648 */
2649 public static final UnicodeBlock MIAO =
2650 new UnicodeBlock("MIAO");
2651
2652 /**
2653 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2654 * character block.
2655 * @since 1.8
2656 */
2657 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2658 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2659 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2660 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2661
2662 /**
2663 * Constant for the "Combining Diacritical Marks Extended" Unicode
2664 * character block.
2665 * @since 9
2666 */
2667 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2668 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2669 "COMBINING DIACRITICAL MARKS EXTENDED",
2670 "COMBININGDIACRITICALMARKSEXTENDED");
2671
2672 /**
2673 * Constant for the "Myanmar Extended-B" Unicode character block.
2674 * @since 9
2675 */
2676 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2677 new UnicodeBlock("MYANMAR_EXTENDED_B",
2678 "MYANMAR EXTENDED-B",
2679 "MYANMAREXTENDED-B");
2680
2681 /**
2682 * Constant for the "Latin Extended-E" Unicode character block.
2683 * @since 9
2684 */
2685 public static final UnicodeBlock LATIN_EXTENDED_E =
2686 new UnicodeBlock("LATIN_EXTENDED_E",
2687 "LATIN EXTENDED-E",
2688 "LATINEXTENDED-E");
2689
2690 /**
2691 * Constant for the "Coptic Epact Numbers" Unicode character block.
2692 * @since 9
2693 */
2694 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2695 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2696 "COPTIC EPACT NUMBERS",
2697 "COPTICEPACTNUMBERS");
2698
2699 /**
2700 * Constant for the "Old Permic" Unicode character block.
2701 * @since 9
2702 */
2703 public static final UnicodeBlock OLD_PERMIC =
2704 new UnicodeBlock("OLD_PERMIC",
2705 "OLD PERMIC",
2706 "OLDPERMIC");
2707
2708 /**
2709 * Constant for the "Elbasan" Unicode character block.
2710 * @since 9
2711 */
2712 public static final UnicodeBlock ELBASAN =
2713 new UnicodeBlock("ELBASAN");
2714
2715 /**
2716 * Constant for the "Caucasian Albanian" Unicode character block.
2717 * @since 9
2718 */
2719 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2720 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2721 "CAUCASIAN ALBANIAN",
2722 "CAUCASIANALBANIAN");
2723
2724 /**
2725 * Constant for the "Linear A" Unicode character block.
2726 * @since 9
2727 */
2728 public static final UnicodeBlock LINEAR_A =
2729 new UnicodeBlock("LINEAR_A",
2730 "LINEAR A",
2731 "LINEARA");
2732
2733 /**
2734 * Constant for the "Palmyrene" Unicode character block.
2735 * @since 9
2736 */
2737 public static final UnicodeBlock PALMYRENE =
2738 new UnicodeBlock("PALMYRENE");
2739
2740 /**
2741 * Constant for the "Nabataean" Unicode character block.
2742 * @since 9
2743 */
2744 public static final UnicodeBlock NABATAEAN =
2745 new UnicodeBlock("NABATAEAN");
2746
2747 /**
2748 * Constant for the "Old North Arabian" Unicode character block.
2749 * @since 9
2750 */
2751 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2752 new UnicodeBlock("OLD_NORTH_ARABIAN",
2753 "OLD NORTH ARABIAN",
2754 "OLDNORTHARABIAN");
2755
2756 /**
2757 * Constant for the "Manichaean" Unicode character block.
2758 * @since 9
2759 */
2760 public static final UnicodeBlock MANICHAEAN =
2761 new UnicodeBlock("MANICHAEAN");
2762
2763 /**
2764 * Constant for the "Psalter Pahlavi" Unicode character block.
2765 * @since 9
2766 */
2767 public static final UnicodeBlock PSALTER_PAHLAVI =
2768 new UnicodeBlock("PSALTER_PAHLAVI",
2769 "PSALTER PAHLAVI",
2770 "PSALTERPAHLAVI");
2771
2772 /**
2773 * Constant for the "Mahajani" Unicode character block.
2774 * @since 9
2775 */
2776 public static final UnicodeBlock MAHAJANI =
2777 new UnicodeBlock("MAHAJANI");
2778
2779 /**
2780 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2781 * @since 9
2782 */
2783 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2784 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2785 "SINHALA ARCHAIC NUMBERS",
2786 "SINHALAARCHAICNUMBERS");
2787
2788 /**
2789 * Constant for the "Khojki" Unicode character block.
2790 * @since 9
2791 */
2792 public static final UnicodeBlock KHOJKI =
2793 new UnicodeBlock("KHOJKI");
2794
2795 /**
2796 * Constant for the "Khudawadi" Unicode character block.
2797 * @since 9
2798 */
2799 public static final UnicodeBlock KHUDAWADI =
2800 new UnicodeBlock("KHUDAWADI");
2801
2802 /**
2803 * Constant for the "Grantha" Unicode character block.
2804 * @since 9
2805 */
2806 public static final UnicodeBlock GRANTHA =
2807 new UnicodeBlock("GRANTHA");
2808
2809 /**
2810 * Constant for the "Tirhuta" Unicode character block.
2811 * @since 9
2812 */
2813 public static final UnicodeBlock TIRHUTA =
2814 new UnicodeBlock("TIRHUTA");
2815
2816 /**
2817 * Constant for the "Siddham" Unicode character block.
2818 * @since 9
2819 */
2820 public static final UnicodeBlock SIDDHAM =
2821 new UnicodeBlock("SIDDHAM");
2822
2823 /**
2824 * Constant for the "Modi" Unicode character block.
2825 * @since 9
2826 */
2827 public static final UnicodeBlock MODI =
2828 new UnicodeBlock("MODI");
2829
2830 /**
2831 * Constant for the "Warang Citi" Unicode character block.
2832 * @since 9
2833 */
2834 public static final UnicodeBlock WARANG_CITI =
2835 new UnicodeBlock("WARANG_CITI",
2836 "WARANG CITI",
2837 "WARANGCITI");
2838
2839 /**
2840 * Constant for the "Pau Cin Hau" Unicode character block.
2841 * @since 9
2842 */
2843 public static final UnicodeBlock PAU_CIN_HAU =
2844 new UnicodeBlock("PAU_CIN_HAU",
2845 "PAU CIN HAU",
2846 "PAUCINHAU");
2847
2848 /**
2849 * Constant for the "Mro" Unicode character block.
2850 * @since 9
2851 */
2852 public static final UnicodeBlock MRO =
2853 new UnicodeBlock("MRO");
2854
2855 /**
2856 * Constant for the "Bassa Vah" Unicode character block.
2857 * @since 9
2858 */
2859 public static final UnicodeBlock BASSA_VAH =
2860 new UnicodeBlock("BASSA_VAH",
2861 "BASSA VAH",
2862 "BASSAVAH");
2863
2864 /**
2865 * Constant for the "Pahawh Hmong" Unicode character block.
2866 * @since 9
2867 */
2868 public static final UnicodeBlock PAHAWH_HMONG =
2869 new UnicodeBlock("PAHAWH_HMONG",
2870 "PAHAWH HMONG",
2871 "PAHAWHHMONG");
2872
2873 /**
2874 * Constant for the "Duployan" Unicode character block.
2875 * @since 9
2876 */
2877 public static final UnicodeBlock DUPLOYAN =
2878 new UnicodeBlock("DUPLOYAN");
2879
2880 /**
2881 * Constant for the "Shorthand Format Controls" Unicode character block.
2882 * @since 9
2883 */
2884 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2885 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2886 "SHORTHAND FORMAT CONTROLS",
2887 "SHORTHANDFORMATCONTROLS");
2888
2889 /**
2890 * Constant for the "Mende Kikakui" Unicode character block.
2891 * @since 9
2892 */
2893 public static final UnicodeBlock MENDE_KIKAKUI =
2894 new UnicodeBlock("MENDE_KIKAKUI",
2895 "MENDE KIKAKUI",
2896 "MENDEKIKAKUI");
2897
2898 /**
2899 * Constant for the "Ornamental Dingbats" Unicode character block.
2900 * @since 9
2901 */
2902 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2903 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2904 "ORNAMENTAL DINGBATS",
2905 "ORNAMENTALDINGBATS");
2906
2907 /**
2908 * Constant for the "Geometric Shapes Extended" Unicode character block.
2909 * @since 9
2910 */
2911 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2912 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2913 "GEOMETRIC SHAPES EXTENDED",
2914 "GEOMETRICSHAPESEXTENDED");
2915
2916 /**
2917 * Constant for the "Supplemental Arrows-C" Unicode character block.
2918 * @since 9
2919 */
2920 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2921 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2922 "SUPPLEMENTAL ARROWS-C",
2923 "SUPPLEMENTALARROWS-C");
2924
2925 /**
2926 * Constant for the "Cherokee Supplement" Unicode character block.
2927 * @since 9
2928 */
2929 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2930 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2931 "CHEROKEE SUPPLEMENT",
2932 "CHEROKEESUPPLEMENT");
2933
2934 /**
2935 * Constant for the "Hatran" Unicode character block.
2936 * @since 9
2937 */
2938 public static final UnicodeBlock HATRAN =
2939 new UnicodeBlock("HATRAN");
2940
2941 /**
2942 * Constant for the "Old Hungarian" Unicode character block.
2943 * @since 9
2944 */
2945 public static final UnicodeBlock OLD_HUNGARIAN =
2946 new UnicodeBlock("OLD_HUNGARIAN",
2947 "OLD HUNGARIAN",
2948 "OLDHUNGARIAN");
2949
2950 /**
2951 * Constant for the "Multani" Unicode character block.
2952 * @since 9
2953 */
2954 public static final UnicodeBlock MULTANI =
2955 new UnicodeBlock("MULTANI");
2956
2957 /**
2958 * Constant for the "Ahom" Unicode character block.
2959 * @since 9
2960 */
2961 public static final UnicodeBlock AHOM =
2962 new UnicodeBlock("AHOM");
2963
2964 /**
2965 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2966 * @since 9
2967 */
2968 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2969 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2970 "EARLY DYNASTIC CUNEIFORM",
2971 "EARLYDYNASTICCUNEIFORM");
2972
2973 /**
2974 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2975 * @since 9
2976 */
2977 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2978 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2979 "ANATOLIAN HIEROGLYPHS",
2980 "ANATOLIANHIEROGLYPHS");
2981
2982 /**
2983 * Constant for the "Sutton SignWriting" Unicode character block.
2984 * @since 9
2985 */
2986 public static final UnicodeBlock SUTTON_SIGNWRITING =
2987 new UnicodeBlock("SUTTON_SIGNWRITING",
2988 "SUTTON SIGNWRITING",
2989 "SUTTONSIGNWRITING");
2990
2991 /**
2992 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2993 * character block.
2994 * @since 9
2995 */
2996 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2997 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2998 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2999 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3000
3001 /**
3002 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3003 * character block.
3004 * @since 9
3005 */
3006 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3007 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3008 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3009 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3010
3011 /**
3012 * Constant for the "Syriac Supplement" Unicode
3013 * character block.
3014 * @since 11
3015 */
3016 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3017 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3018 "SYRIAC SUPPLEMENT",
3019 "SYRIACSUPPLEMENT");
3020
3021 /**
3022 * Constant for the "Cyrillic Extended-C" Unicode
3023 * character block.
3024 * @since 11
3025 */
3026 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3027 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3028 "CYRILLIC EXTENDED-C",
3029 "CYRILLICEXTENDED-C");
3030
3031 /**
3032 * Constant for the "Osage" Unicode
3033 * character block.
3034 * @since 11
3035 */
3036 public static final UnicodeBlock OSAGE =
3037 new UnicodeBlock("OSAGE");
3038
3039 /**
3040 * Constant for the "Newa" Unicode
3041 * character block.
3042 * @since 11
3043 */
3044 public static final UnicodeBlock NEWA =
3045 new UnicodeBlock("NEWA");
3046
3047 /**
3048 * Constant for the "Mongolian Supplement" Unicode
3049 * character block.
3050 * @since 11
3051 */
3052 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3053 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3054 "MONGOLIAN SUPPLEMENT",
3055 "MONGOLIANSUPPLEMENT");
3056
3057 /**
3058 * Constant for the "Marchen" Unicode
3059 * character block.
3060 * @since 11
3061 */
3062 public static final UnicodeBlock MARCHEN =
3063 new UnicodeBlock("MARCHEN");
3064
3065 /**
3066 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3067 * character block.
3068 * @since 11
3069 */
3070 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3071 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3072 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3073 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3074
3075 /**
3076 * Constant for the "Tangut" Unicode
3077 * character block.
3078 * @since 11
3079 */
3080 public static final UnicodeBlock TANGUT =
3081 new UnicodeBlock("TANGUT");
3082
3083 /**
3084 * Constant for the "Tangut Components" Unicode
3085 * character block.
3086 * @since 11
3087 */
3088 public static final UnicodeBlock TANGUT_COMPONENTS =
3089 new UnicodeBlock("TANGUT_COMPONENTS",
3090 "TANGUT COMPONENTS",
3091 "TANGUTCOMPONENTS");
3092
3093 /**
3094 * Constant for the "Kana Extended-A" Unicode
3095 * character block.
3096 * @since 11
3097 */
3098 public static final UnicodeBlock KANA_EXTENDED_A =
3099 new UnicodeBlock("KANA_EXTENDED_A",
3100 "KANA EXTENDED-A",
3101 "KANAEXTENDED-A");
3102 /**
3103 * Constant for the "Glagolitic Supplement" Unicode
3104 * character block.
3105 * @since 11
3106 */
3107 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3108 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3109 "GLAGOLITIC SUPPLEMENT",
3110 "GLAGOLITICSUPPLEMENT");
3111 /**
3112 * Constant for the "Adlam" Unicode
3113 * character block.
3114 * @since 11
3115 */
3116 public static final UnicodeBlock ADLAM =
3117 new UnicodeBlock("ADLAM");
3118
3119 /**
3120 * Constant for the "Masaram Gondi" Unicode
3121 * character block.
3122 * @since 11
3123 */
3124 public static final UnicodeBlock MASARAM_GONDI =
3125 new UnicodeBlock("MASARAM_GONDI",
3126 "MASARAM GONDI",
3127 "MASARAMGONDI");
3128
3129 /**
3130 * Constant for the "Zanabazar Square" Unicode
3131 * character block.
3132 * @since 11
3133 */
3134 public static final UnicodeBlock ZANABAZAR_SQUARE =
3135 new UnicodeBlock("ZANABAZAR_SQUARE",
3136 "ZANABAZAR SQUARE",
3137 "ZANABAZARSQUARE");
3138
3139 /**
3140 * Constant for the "Nushu" Unicode
3141 * character block.
3142 * @since 11
3143 */
3144 public static final UnicodeBlock NUSHU =
3145 new UnicodeBlock("NUSHU");
3146
3147 /**
3148 * Constant for the "Soyombo" Unicode
3149 * character block.
3150 * @since 11
3151 */
3152 public static final UnicodeBlock SOYOMBO =
3153 new UnicodeBlock("SOYOMBO");
3154
3155 /**
3156 * Constant for the "Bhaiksuki" Unicode
3157 * character block.
3158 * @since 11
3159 */
3160 public static final UnicodeBlock BHAIKSUKI =
3161 new UnicodeBlock("BHAIKSUKI");
3162
3163 /**
3164 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3165 * character block.
3166 * @since 11
3167 */
3168 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3169 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3170 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3171 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3172 /**
3173 * Constant for the "Georgian Extended" Unicode
3174 * character block.
3175 * @since 12
3176 */
3177 public static final UnicodeBlock GEORGIAN_EXTENDED =
3178 new UnicodeBlock("GEORGIAN_EXTENDED",
3179 "GEORGIAN EXTENDED",
3180 "GEORGIANEXTENDED");
3181
3182 /**
3183 * Constant for the "Hanifi Rohingya" Unicode
3184 * character block.
3185 * @since 12
3186 */
3187 public static final UnicodeBlock HANIFI_ROHINGYA =
3188 new UnicodeBlock("HANIFI_ROHINGYA",
3189 "HANIFI ROHINGYA",
3190 "HANIFIROHINGYA");
3191
3192 /**
3193 * Constant for the "Old Sogdian" Unicode
3194 * character block.
3195 * @since 12
3196 */
3197 public static final UnicodeBlock OLD_SOGDIAN =
3198 new UnicodeBlock("OLD_SOGDIAN",
3199 "OLD SOGDIAN",
3200 "OLDSOGDIAN");
3201
3202 /**
3203 * Constant for the "Sogdian" Unicode
3204 * character block.
3205 * @since 12
3206 */
3207 public static final UnicodeBlock SOGDIAN =
3208 new UnicodeBlock("SOGDIAN");
3209
3210 /**
3211 * Constant for the "Dogra" Unicode
3212 * character block.
3213 * @since 12
3214 */
3215 public static final UnicodeBlock DOGRA =
3216 new UnicodeBlock("DOGRA");
3217
3218 /**
3219 * Constant for the "Gunjala Gondi" Unicode
3220 * character block.
3221 * @since 12
3222 */
3223 public static final UnicodeBlock GUNJALA_GONDI =
3224 new UnicodeBlock("GUNJALA_GONDI",
3225 "GUNJALA GONDI",
3226 "GUNJALAGONDI");
3227
3228 /**
3229 * Constant for the "Makasar" Unicode
3230 * character block.
3231 * @since 12
3232 */
3233 public static final UnicodeBlock MAKASAR =
3234 new UnicodeBlock("MAKASAR");
3235
3236 /**
3237 * Constant for the "Medefaidrin" Unicode
3238 * character block.
3239 * @since 12
3240 */
3241 public static final UnicodeBlock MEDEFAIDRIN =
3242 new UnicodeBlock("MEDEFAIDRIN");
3243
3244 /**
3245 * Constant for the "Mayan Numerals" Unicode
3246 * character block.
3247 * @since 12
3248 */
3249 public static final UnicodeBlock MAYAN_NUMERALS =
3250 new UnicodeBlock("MAYAN_NUMERALS",
3251 "MAYAN NUMERALS",
3252 "MAYANNUMERALS");
3253
3254 /**
3255 * Constant for the "Indic Siyaq Numbers" Unicode
3256 * character block.
3257 * @since 12
3258 */
3259 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3260 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3261 "INDIC SIYAQ NUMBERS",
3262 "INDICSIYAQNUMBERS");
3263
3264 /**
3265 * Constant for the "Chess Symbols" Unicode
3266 * character block.
3267 * @since 12
3268 */
3269 public static final UnicodeBlock CHESS_SYMBOLS =
3270 new UnicodeBlock("CHESS_SYMBOLS",
3271 "CHESS SYMBOLS",
3272 "CHESSSYMBOLS");
3273
3274 /**
3275 * Constant for the "Elymaic" Unicode
3276 * character block.
3277 * @since 13
3278 */
3279 public static final UnicodeBlock ELYMAIC =
3280 new UnicodeBlock("ELYMAIC");
3281
3282 /**
3283 * Constant for the "Nandinagari" Unicode
3284 * character block.
3285 * @since 13
3286 */
3287 public static final UnicodeBlock NANDINAGARI =
3288 new UnicodeBlock("NANDINAGARI");
3289
3290 /**
3291 * Constant for the "Tamil Supplement" Unicode
3292 * character block.
3293 * @since 13
3294 */
3295 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3296 new UnicodeBlock("TAMIL_SUPPLEMENT",
3297 "TAMIL SUPPLEMENT",
3298 "TAMILSUPPLEMENT");
3299
3300 /**
3301 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3302 * character block.
3303 * @since 13
3304 */
3305 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3306 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3307 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3308 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3309
3310 /**
3311 * Constant for the "Small Kana Extension" Unicode
3312 * character block.
3313 * @since 13
3314 */
3315 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3316 new UnicodeBlock("SMALL_KANA_EXTENSION",
3317 "SMALL KANA EXTENSION",
3318 "SMALLKANAEXTENSION");
3319
3320 /**
3321 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3322 * character block.
3323 * @since 13
3324 */
3325 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3326 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3327 "NYIAKENG PUACHUE HMONG",
3328 "NYIAKENGPUACHUEHMONG");
3329
3330 /**
3331 * Constant for the "Wancho" Unicode
3332 * character block.
3333 * @since 13
3334 */
3335 public static final UnicodeBlock WANCHO =
3336 new UnicodeBlock("WANCHO");
3337
3338 /**
3339 * Constant for the "Ottoman Siyaq Numbers" Unicode
3340 * character block.
3341 * @since 13
3342 */
3343 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3344 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3345 "OTTOMAN SIYAQ NUMBERS",
3346 "OTTOMANSIYAQNUMBERS");
3347
3348 /**
3349 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3350 * character block.
3351 * @since 13
3352 */
3353 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3354 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3355 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3356 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3357
3358 /**
3359 * Constant for the "Yezidi" Unicode
3360 * character block.
3361 * @since 15
3362 */
3363 public static final UnicodeBlock YEZIDI =
3364 new UnicodeBlock("YEZIDI");
3365
3366 /**
3367 * Constant for the "Chorasmian" Unicode
3368 * character block.
3369 * @since 15
3370 */
3371 public static final UnicodeBlock CHORASMIAN =
3372 new UnicodeBlock("CHORASMIAN");
3373
3374 /**
3375 * Constant for the "Dives Akuru" Unicode
3376 * character block.
3377 * @since 15
3378 */
3379 public static final UnicodeBlock DIVES_AKURU =
3380 new UnicodeBlock("DIVES_AKURU",
3381 "DIVES AKURU",
3382 "DIVESAKURU");
3383
3384 /**
3385 * Constant for the "Lisu Supplement" Unicode
3386 * character block.
3387 * @since 15
3388 */
3389 public static final UnicodeBlock LISU_SUPPLEMENT =
3390 new UnicodeBlock("LISU_SUPPLEMENT",
3391 "LISU SUPPLEMENT",
3392 "LISUSUPPLEMENT");
3393
3394 /**
3395 * Constant for the "Khitan Small Script" Unicode
3396 * character block.
3397 * @since 15
3398 */
3399 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3400 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3401 "KHITAN SMALL SCRIPT",
3402 "KHITANSMALLSCRIPT");
3403
3404 /**
3405 * Constant for the "Tangut Supplement" Unicode
3406 * character block.
3407 * @since 15
3408 */
3409 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3410 new UnicodeBlock("TANGUT_SUPPLEMENT",
3411 "TANGUT SUPPLEMENT",
3412 "TANGUTSUPPLEMENT");
3413
3414 /**
3415 * Constant for the "Symbols for Legacy Computing" Unicode
3416 * character block.
3417 * @since 15
3418 */
3419 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3420 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3421 "SYMBOLS FOR LEGACY COMPUTING",
3422 "SYMBOLSFORLEGACYCOMPUTING");
3423
3424 /**
3425 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3426 * character block.
3427 * @since 15
3428 */
3429 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3430 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3431 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3432 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3433
3434 /**
3435 * Constant for the "Arabic Extended-B" Unicode
3436 * character block.
3437 * @since 19
3438 */
3439 public static final UnicodeBlock ARABIC_EXTENDED_B =
3440 new UnicodeBlock("ARABIC_EXTENDED_B",
3441 "ARABIC EXTENDED-B",
3442 "ARABICEXTENDED-B");
3443
3444 /**
3445 * Constant for the "Vithkuqi" Unicode
3446 * character block.
3447 * @since 19
3448 */
3449 public static final UnicodeBlock VITHKUQI =
3450 new UnicodeBlock("VITHKUQI");
3451
3452 /**
3453 * Constant for the "Latin Extended-F" Unicode
3454 * character block.
3455 * @since 19
3456 */
3457 public static final UnicodeBlock LATIN_EXTENDED_F =
3458 new UnicodeBlock("LATIN_EXTENDED_F",
3459 "LATIN EXTENDED-F",
3460 "LATINEXTENDED-F");
3461
3462 /**
3463 * Constant for the "Old Uyghur" Unicode
3464 * character block.
3465 * @since 19
3466 */
3467 public static final UnicodeBlock OLD_UYGHUR =
3468 new UnicodeBlock("OLD_UYGHUR",
3469 "OLD UYGHUR",
3470 "OLDUYGHUR");
3471
3472 /**
3473 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3474 * character block.
3475 * @since 19
3476 */
3477 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3478 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3479 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3480 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3481
3482 /**
3483 * Constant for the "Cypro-Minoan" Unicode
3484 * character block.
3485 * @since 19
3486 */
3487 public static final UnicodeBlock CYPRO_MINOAN =
3488 new UnicodeBlock("CYPRO_MINOAN",
3489 "CYPRO-MINOAN",
3490 "CYPRO-MINOAN");
3491
3492 /**
3493 * Constant for the "Tangsa" Unicode
3494 * character block.
3495 * @since 19
3496 */
3497 public static final UnicodeBlock TANGSA =
3498 new UnicodeBlock("TANGSA");
3499
3500 /**
3501 * Constant for the "Kana Extended-B" Unicode
3502 * character block.
3503 * @since 19
3504 */
3505 public static final UnicodeBlock KANA_EXTENDED_B =
3506 new UnicodeBlock("KANA_EXTENDED_B",
3507 "KANA EXTENDED-B",
3508 "KANAEXTENDED-B");
3509
3510 /**
3511 * Constant for the "Znamenny Musical Notation" Unicode
3512 * character block.
3513 * @since 19
3514 */
3515 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3516 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3517 "ZNAMENNY MUSICAL NOTATION",
3518 "ZNAMENNYMUSICALNOTATION");
3519
3520 /**
3521 * Constant for the "Latin Extended-G" Unicode
3522 * character block.
3523 * @since 19
3524 */
3525 public static final UnicodeBlock LATIN_EXTENDED_G =
3526 new UnicodeBlock("LATIN_EXTENDED_G",
3527 "LATIN EXTENDED-G",
3528 "LATINEXTENDED-G");
3529
3530 /**
3531 * Constant for the "Toto" Unicode
3532 * character block.
3533 * @since 19
3534 */
3535 public static final UnicodeBlock TOTO =
3536 new UnicodeBlock("TOTO");
3537
3538 /**
3539 * Constant for the "Ethiopic Extended-B" Unicode
3540 * character block.
3541 * @since 19
3542 */
3543 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3544 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3545 "ETHIOPIC EXTENDED-B",
3546 "ETHIOPICEXTENDED-B");
3547
3548 /**
3549 * Constant for the "Arabic Extended-C" Unicode
3550 * character block.
3551 * @since 20
3552 */
3553 public static final UnicodeBlock ARABIC_EXTENDED_C =
3554 new UnicodeBlock("ARABIC_EXTENDED_C",
3555 "ARABIC EXTENDED-C",
3556 "ARABICEXTENDED-C");
3557
3558 /**
3559 * Constant for the "Devanagari Extended-A" Unicode
3560 * character block.
3561 * @since 20
3562 */
3563 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3564 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3565 "DEVANAGARI EXTENDED-A",
3566 "DEVANAGARIEXTENDED-A");
3567
3568 /**
3569 * Constant for the "Kawi" Unicode
3570 * character block.
3571 * @since 20
3572 */
3573 public static final UnicodeBlock KAWI =
3574 new UnicodeBlock("KAWI");
3575
3576 /**
3577 * Constant for the "Kaktovik Numerals" Unicode
3578 * character block.
3579 * @since 20
3580 */
3581 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3582 new UnicodeBlock("KAKTOVIK_NUMERALS",
3583 "KAKTOVIK NUMERALS",
3584 "KAKTOVIKNUMERALS");
3585
3586 /**
3587 * Constant for the "Cyrillic Extended-D" Unicode
3588 * character block.
3589 * @since 20
3590 */
3591 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3592 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3593 "CYRILLIC EXTENDED-D",
3594 "CYRILLICEXTENDED-D");
3595
3596 /**
3597 * Constant for the "Nag Mundari" Unicode
3598 * character block.
3599 * @since 20
3600 */
3601 public static final UnicodeBlock NAG_MUNDARI =
3602 new UnicodeBlock("NAG_MUNDARI",
3603 "NAG MUNDARI",
3604 "NAGMUNDARI");
3605
3606 /**
3607 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3608 * character block.
3609 * @since 20
3610 */
3611 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3612 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3613 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3614 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3615
3616 /**
3617 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3618 * character block.
3619 * @since 22
3620 */
3621 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3622 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3623 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3624 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3625
3626 private static final int[] blockStarts = {
3627 0x0000, // 0000..007F; Basic Latin
3628 0x0080, // 0080..00FF; Latin-1 Supplement
3629 0x0100, // 0100..017F; Latin Extended-A
3630 0x0180, // 0180..024F; Latin Extended-B
3631 0x0250, // 0250..02AF; IPA Extensions
3632 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3633 0x0300, // 0300..036F; Combining Diacritical Marks
3634 0x0370, // 0370..03FF; Greek and Coptic
3635 0x0400, // 0400..04FF; Cyrillic
3636 0x0500, // 0500..052F; Cyrillic Supplement
3637 0x0530, // 0530..058F; Armenian
3638 0x0590, // 0590..05FF; Hebrew
3639 0x0600, // 0600..06FF; Arabic
3640 0x0700, // 0700..074F; Syriac
3641 0x0750, // 0750..077F; Arabic Supplement
3642 0x0780, // 0780..07BF; Thaana
3643 0x07C0, // 07C0..07FF; NKo
3644 0x0800, // 0800..083F; Samaritan
3645 0x0840, // 0840..085F; Mandaic
3646 0x0860, // 0860..086F; Syriac Supplement
3647 0x0870, // 0870..089F; Arabic Extended-B
3648 0x08A0, // 08A0..08FF; Arabic Extended-A
3649 0x0900, // 0900..097F; Devanagari
3650 0x0980, // 0980..09FF; Bengali
3651 0x0A00, // 0A00..0A7F; Gurmukhi
3652 0x0A80, // 0A80..0AFF; Gujarati
3653 0x0B00, // 0B00..0B7F; Oriya
3654 0x0B80, // 0B80..0BFF; Tamil
3655 0x0C00, // 0C00..0C7F; Telugu
3656 0x0C80, // 0C80..0CFF; Kannada
3657 0x0D00, // 0D00..0D7F; Malayalam
3658 0x0D80, // 0D80..0DFF; Sinhala
3659 0x0E00, // 0E00..0E7F; Thai
3660 0x0E80, // 0E80..0EFF; Lao
3661 0x0F00, // 0F00..0FFF; Tibetan
3662 0x1000, // 1000..109F; Myanmar
3663 0x10A0, // 10A0..10FF; Georgian
3664 0x1100, // 1100..11FF; Hangul Jamo
3665 0x1200, // 1200..137F; Ethiopic
3666 0x1380, // 1380..139F; Ethiopic Supplement
3667 0x13A0, // 13A0..13FF; Cherokee
3668 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3669 0x1680, // 1680..169F; Ogham
3670 0x16A0, // 16A0..16FF; Runic
3671 0x1700, // 1700..171F; Tagalog
3672 0x1720, // 1720..173F; Hanunoo
3673 0x1740, // 1740..175F; Buhid
3674 0x1760, // 1760..177F; Tagbanwa
3675 0x1780, // 1780..17FF; Khmer
3676 0x1800, // 1800..18AF; Mongolian
3677 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3678 0x1900, // 1900..194F; Limbu
3679 0x1950, // 1950..197F; Tai Le
3680 0x1980, // 1980..19DF; New Tai Lue
3681 0x19E0, // 19E0..19FF; Khmer Symbols
3682 0x1A00, // 1A00..1A1F; Buginese
3683 0x1A20, // 1A20..1AAF; Tai Tham
3684 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3685 0x1B00, // 1B00..1B7F; Balinese
3686 0x1B80, // 1B80..1BBF; Sundanese
3687 0x1BC0, // 1BC0..1BFF; Batak
3688 0x1C00, // 1C00..1C4F; Lepcha
3689 0x1C50, // 1C50..1C7F; Ol Chiki
3690 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3691 0x1C90, // 1C90..1CBF; Georgian Extended
3692 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3693 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3694 0x1D00, // 1D00..1D7F; Phonetic Extensions
3695 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3696 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3697 0x1E00, // 1E00..1EFF; Latin Extended Additional
3698 0x1F00, // 1F00..1FFF; Greek Extended
3699 0x2000, // 2000..206F; General Punctuation
3700 0x2070, // 2070..209F; Superscripts and Subscripts
3701 0x20A0, // 20A0..20CF; Currency Symbols
3702 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3703 0x2100, // 2100..214F; Letterlike Symbols
3704 0x2150, // 2150..218F; Number Forms
3705 0x2190, // 2190..21FF; Arrows
3706 0x2200, // 2200..22FF; Mathematical Operators
3707 0x2300, // 2300..23FF; Miscellaneous Technical
3708 0x2400, // 2400..243F; Control Pictures
3709 0x2440, // 2440..245F; Optical Character Recognition
3710 0x2460, // 2460..24FF; Enclosed Alphanumerics
3711 0x2500, // 2500..257F; Box Drawing
3712 0x2580, // 2580..259F; Block Elements
3713 0x25A0, // 25A0..25FF; Geometric Shapes
3714 0x2600, // 2600..26FF; Miscellaneous Symbols
3715 0x2700, // 2700..27BF; Dingbats
3716 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3717 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3718 0x2800, // 2800..28FF; Braille Patterns
3719 0x2900, // 2900..297F; Supplemental Arrows-B
3720 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3721 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3722 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3723 0x2C00, // 2C00..2C5F; Glagolitic
3724 0x2C60, // 2C60..2C7F; Latin Extended-C
3725 0x2C80, // 2C80..2CFF; Coptic
3726 0x2D00, // 2D00..2D2F; Georgian Supplement
3727 0x2D30, // 2D30..2D7F; Tifinagh
3728 0x2D80, // 2D80..2DDF; Ethiopic Extended
3729 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3730 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3731 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3732 0x2F00, // 2F00..2FDF; Kangxi Radicals
3733 0x2FE0, // unassigned
3734 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3735 0x3000, // 3000..303F; CJK Symbols and Punctuation
3736 0x3040, // 3040..309F; Hiragana
3737 0x30A0, // 30A0..30FF; Katakana
3738 0x3100, // 3100..312F; Bopomofo
3739 0x3130, // 3130..318F; Hangul Compatibility Jamo
3740 0x3190, // 3190..319F; Kanbun
3741 0x31A0, // 31A0..31BF; Bopomofo Extended
3742 0x31C0, // 31C0..31EF; CJK Strokes
3743 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3744 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3745 0x3300, // 3300..33FF; CJK Compatibility
3746 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3747 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3748 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3749 0xA000, // A000..A48F; Yi Syllables
3750 0xA490, // A490..A4CF; Yi Radicals
3751 0xA4D0, // A4D0..A4FF; Lisu
3752 0xA500, // A500..A63F; Vai
3753 0xA640, // A640..A69F; Cyrillic Extended-B
3754 0xA6A0, // A6A0..A6FF; Bamum
3755 0xA700, // A700..A71F; Modifier Tone Letters
3756 0xA720, // A720..A7FF; Latin Extended-D
3757 0xA800, // A800..A82F; Syloti Nagri
3758 0xA830, // A830..A83F; Common Indic Number Forms
3759 0xA840, // A840..A87F; Phags-pa
3760 0xA880, // A880..A8DF; Saurashtra
3761 0xA8E0, // A8E0..A8FF; Devanagari Extended
3762 0xA900, // A900..A92F; Kayah Li
3763 0xA930, // A930..A95F; Rejang
3764 0xA960, // A960..A97F; Hangul Jamo Extended-A
3765 0xA980, // A980..A9DF; Javanese
3766 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3767 0xAA00, // AA00..AA5F; Cham
3768 0xAA60, // AA60..AA7F; Myanmar Extended-A
3769 0xAA80, // AA80..AADF; Tai Viet
3770 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3771 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3772 0xAB30, // AB30..AB6F; Latin Extended-E
3773 0xAB70, // AB70..ABBF; Cherokee Supplement
3774 0xABC0, // ABC0..ABFF; Meetei Mayek
3775 0xAC00, // AC00..D7AF; Hangul Syllables
3776 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3777 0xD800, // D800..DB7F; High Surrogates
3778 0xDB80, // DB80..DBFF; High Private Use Surrogates
3779 0xDC00, // DC00..DFFF; Low Surrogates
3780 0xE000, // E000..F8FF; Private Use Area
3781 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3782 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3783 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3784 0xFE00, // FE00..FE0F; Variation Selectors
3785 0xFE10, // FE10..FE1F; Vertical Forms
3786 0xFE20, // FE20..FE2F; Combining Half Marks
3787 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3788 0xFE50, // FE50..FE6F; Small Form Variants
3789 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3790 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3791 0xFFF0, // FFF0..FFFF; Specials
3792 0x10000, // 10000..1007F; Linear B Syllabary
3793 0x10080, // 10080..100FF; Linear B Ideograms
3794 0x10100, // 10100..1013F; Aegean Numbers
3795 0x10140, // 10140..1018F; Ancient Greek Numbers
3796 0x10190, // 10190..101CF; Ancient Symbols
3797 0x101D0, // 101D0..101FF; Phaistos Disc
3798 0x10200, // unassigned
3799 0x10280, // 10280..1029F; Lycian
3800 0x102A0, // 102A0..102DF; Carian
3801 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3802 0x10300, // 10300..1032F; Old Italic
3803 0x10330, // 10330..1034F; Gothic
3804 0x10350, // 10350..1037F; Old Permic
3805 0x10380, // 10380..1039F; Ugaritic
3806 0x103A0, // 103A0..103DF; Old Persian
3807 0x103E0, // unassigned
3808 0x10400, // 10400..1044F; Deseret
3809 0x10450, // 10450..1047F; Shavian
3810 0x10480, // 10480..104AF; Osmanya
3811 0x104B0, // 104B0..104FF; Osage
3812 0x10500, // 10500..1052F; Elbasan
3813 0x10530, // 10530..1056F; Caucasian Albanian
3814 0x10570, // 10570..105BF; Vithkuqi
3815 0x105C0, // unassigned
3816 0x10600, // 10600..1077F; Linear A
3817 0x10780, // 10780..107BF; Latin Extended-F
3818 0x107C0, // unassigned
3819 0x10800, // 10800..1083F; Cypriot Syllabary
3820 0x10840, // 10840..1085F; Imperial Aramaic
3821 0x10860, // 10860..1087F; Palmyrene
3822 0x10880, // 10880..108AF; Nabataean
3823 0x108B0, // unassigned
3824 0x108E0, // 108E0..108FF; Hatran
3825 0x10900, // 10900..1091F; Phoenician
3826 0x10920, // 10920..1093F; Lydian
3827 0x10940, // unassigned
3828 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3829 0x109A0, // 109A0..109FF; Meroitic Cursive
3830 0x10A00, // 10A00..10A5F; Kharoshthi
3831 0x10A60, // 10A60..10A7F; Old South Arabian
3832 0x10A80, // 10A80..10A9F; Old North Arabian
3833 0x10AA0, // unassigned
3834 0x10AC0, // 10AC0..10AFF; Manichaean
3835 0x10B00, // 10B00..10B3F; Avestan
3836 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3837 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3838 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3839 0x10BB0, // unassigned
3840 0x10C00, // 10C00..10C4F; Old Turkic
3841 0x10C50, // unassigned
3842 0x10C80, // 10C80..10CFF; Old Hungarian
3843 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3844 0x10D40, // unassigned
3845 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3846 0x10E80, // 10E80..10EBF; Yezidi
3847 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
3848 0x10F00, // 10F00..10F2F; Old Sogdian
3849 0x10F30, // 10F30..10F6F; Sogdian
3850 0x10F70, // 10F70..10FAF; Old Uyghur
3851 0x10FB0, // 10FB0..10FDF; Chorasmian
3852 0x10FE0, // 10FE0..10FFF; Elymaic
3853 0x11000, // 11000..1107F; Brahmi
3854 0x11080, // 11080..110CF; Kaithi
3855 0x110D0, // 110D0..110FF; Sora Sompeng
3856 0x11100, // 11100..1114F; Chakma
3857 0x11150, // 11150..1117F; Mahajani
3858 0x11180, // 11180..111DF; Sharada
3859 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3860 0x11200, // 11200..1124F; Khojki
3861 0x11250, // unassigned
3862 0x11280, // 11280..112AF; Multani
3863 0x112B0, // 112B0..112FF; Khudawadi
3864 0x11300, // 11300..1137F; Grantha
3865 0x11380, // unassigned
3866 0x11400, // 11400..1147F; Newa
3867 0x11480, // 11480..114DF; Tirhuta
3868 0x114E0, // unassigned
3869 0x11580, // 11580..115FF; Siddham
3870 0x11600, // 11600..1165F; Modi
3871 0x11660, // 11660..1167F; Mongolian Supplement
3872 0x11680, // 11680..116CF; Takri
3873 0x116D0, // unassigned
3874 0x11700, // 11700..1174F; Ahom
3875 0x11750, // unassigned
3876 0x11800, // 11800..1184F; Dogra
3877 0x11850, // unassigned
3878 0x118A0, // 118A0..118FF; Warang Citi
3879 0x11900, // 11900..1195F; Dives Akuru
3880 0x11960, // unassigned
3881 0x119A0, // 119A0..119FF; Nandinagari
3882 0x11A00, // 11A00..11A4F; Zanabazar Square
3883 0x11A50, // 11A50..11AAF; Soyombo
3884 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
3885 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3886 0x11B00, // 11B00..11B5F; Devanagari Extended-A
3887 0x11B60, // unassigned
3888 0x11C00, // 11C00..11C6F; Bhaiksuki
3889 0x11C70, // 11C70..11CBF; Marchen
3890 0x11CC0, // unassigned
3891 0x11D00, // 11D00..11D5F; Masaram Gondi
3892 0x11D60, // 11D60..11DAF; Gunjala Gondi
3893 0x11DB0, // unassigned
3894 0x11EE0, // 11EE0..11EFF; Makasar
3895 0x11F00, // 11F00..11F5F; Kawi
3896 0x11F60, // unassigned
3897 0x11FB0, // 11FB0..11FBF; Lisu Supplement
3898 0x11FC0, // 11FC0..11FFF; Tamil Supplement
3899 0x12000, // 12000..123FF; Cuneiform
3900 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3901 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3902 0x12550, // unassigned
3903 0x12F90, // 12F90..12FFF; Cypro-Minoan
3904 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3905 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
3906 0x13460, // unassigned
3907 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3908 0x14680, // unassigned
3909 0x16800, // 16800..16A3F; Bamum Supplement
3910 0x16A40, // 16A40..16A6F; Mro
3911 0x16A70, // 16A70..16ACF; Tangsa
3912 0x16AD0, // 16AD0..16AFF; Bassa Vah
3913 0x16B00, // 16B00..16B8F; Pahawh Hmong
3914 0x16B90, // unassigned
3915 0x16E40, // 16E40..16E9F; Medefaidrin
3916 0x16EA0, // unassigned
3917 0x16F00, // 16F00..16F9F; Miao
3918 0x16FA0, // unassigned
3919 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
3920 0x17000, // 17000..187FF; Tangut
3921 0x18800, // 18800..18AFF; Tangut Components
3922 0x18B00, // 18B00..18CFF; Khitan Small Script
3923 0x18D00, // 18D00..18D7F; Tangut Supplement
3924 0x18D80, // unassigned
3925 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
3926 0x1B000, // 1B000..1B0FF; Kana Supplement
3927 0x1B100, // 1B100..1B12F; Kana Extended-A
3928 0x1B130, // 1B130..1B16F; Small Kana Extension
3929 0x1B170, // 1B170..1B2FF; Nushu
3930 0x1B300, // unassigned
3931 0x1BC00, // 1BC00..1BC9F; Duployan
3932 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3933 0x1BCB0, // unassigned
3934 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
3935 0x1CFD0, // unassigned
3936 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3937 0x1D100, // 1D100..1D1FF; Musical Symbols
3938 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3939 0x1D250, // unassigned
3940 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
3941 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
3942 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3943 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3944 0x1D380, // unassigned
3945 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3946 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3947 0x1DAB0, // unassigned
3948 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
3949 0x1E000, // 1E000..1E02F; Glagolitic Supplement
3950 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
3951 0x1E090, // unassigned
3952 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
3953 0x1E150, // unassigned
3954 0x1E290, // 1E290..1E2BF; Toto
3955 0x1E2C0, // 1E2C0..1E2FF; Wancho
3956 0x1E300, // unassigned
3957 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
3958 0x1E500, // unassigned
3959 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
3960 0x1E800, // 1E800..1E8DF; Mende Kikakui
3961 0x1E8E0, // unassigned
3962 0x1E900, // 1E900..1E95F; Adlam
3963 0x1E960, // unassigned
3964 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
3965 0x1ECC0, // unassigned
3966 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
3967 0x1ED50, // unassigned
3968 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3969 0x1EF00, // unassigned
3970 0x1F000, // 1F000..1F02F; Mahjong Tiles
3971 0x1F030, // 1F030..1F09F; Domino Tiles
3972 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3973 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3974 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3975 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3976 0x1F600, // 1F600..1F64F; Emoticons
3977 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3978 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3979 0x1F700, // 1F700..1F77F; Alchemical Symbols
3980 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3981 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3982 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3983 0x1FA00, // 1FA00..1FA6F; Chess Symbols
3984 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
3985 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
3986 0x1FC00, // unassigned
3987 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3988 0x2A6E0, // unassigned
3989 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3990 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3991 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
3992 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
3993 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
3994 0x2EE60, // unassigned
3995 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
3996 0x2FA20, // unassigned
3997 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
3998 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
3999 0x323B0, // unassigned
4000 0xE0000, // E0000..E007F; Tags
4001 0xE0080, // unassigned
4002 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4003 0xE01F0, // unassigned
4004 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4005 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4006 };
4007
4008 private static final UnicodeBlock[] blocks = {
4009 BASIC_LATIN,
4010 LATIN_1_SUPPLEMENT,
4011 LATIN_EXTENDED_A,
4012 LATIN_EXTENDED_B,
4013 IPA_EXTENSIONS,
4014 SPACING_MODIFIER_LETTERS,
4015 COMBINING_DIACRITICAL_MARKS,
4016 GREEK,
4017 CYRILLIC,
4018 CYRILLIC_SUPPLEMENTARY,
4019 ARMENIAN,
4020 HEBREW,
4021 ARABIC,
4022 SYRIAC,
4023 ARABIC_SUPPLEMENT,
4024 THAANA,
4025 NKO,
4026 SAMARITAN,
4027 MANDAIC,
4028 SYRIAC_SUPPLEMENT,
4029 ARABIC_EXTENDED_B,
4030 ARABIC_EXTENDED_A,
4031 DEVANAGARI,
4032 BENGALI,
4033 GURMUKHI,
4034 GUJARATI,
4035 ORIYA,
4036 TAMIL,
4037 TELUGU,
4038 KANNADA,
4039 MALAYALAM,
4040 SINHALA,
4041 THAI,
4042 LAO,
4043 TIBETAN,
4044 MYANMAR,
4045 GEORGIAN,
4046 HANGUL_JAMO,
4047 ETHIOPIC,
4048 ETHIOPIC_SUPPLEMENT,
4049 CHEROKEE,
4050 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4051 OGHAM,
4052 RUNIC,
4053 TAGALOG,
4054 HANUNOO,
4055 BUHID,
4056 TAGBANWA,
4057 KHMER,
4058 MONGOLIAN,
4059 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4060 LIMBU,
4061 TAI_LE,
4062 NEW_TAI_LUE,
4063 KHMER_SYMBOLS,
4064 BUGINESE,
4065 TAI_THAM,
4066 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4067 BALINESE,
4068 SUNDANESE,
4069 BATAK,
4070 LEPCHA,
4071 OL_CHIKI,
4072 CYRILLIC_EXTENDED_C,
4073 GEORGIAN_EXTENDED,
4074 SUNDANESE_SUPPLEMENT,
4075 VEDIC_EXTENSIONS,
4076 PHONETIC_EXTENSIONS,
4077 PHONETIC_EXTENSIONS_SUPPLEMENT,
4078 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4079 LATIN_EXTENDED_ADDITIONAL,
4080 GREEK_EXTENDED,
4081 GENERAL_PUNCTUATION,
4082 SUPERSCRIPTS_AND_SUBSCRIPTS,
4083 CURRENCY_SYMBOLS,
4084 COMBINING_MARKS_FOR_SYMBOLS,
4085 LETTERLIKE_SYMBOLS,
4086 NUMBER_FORMS,
4087 ARROWS,
4088 MATHEMATICAL_OPERATORS,
4089 MISCELLANEOUS_TECHNICAL,
4090 CONTROL_PICTURES,
4091 OPTICAL_CHARACTER_RECOGNITION,
4092 ENCLOSED_ALPHANUMERICS,
4093 BOX_DRAWING,
4094 BLOCK_ELEMENTS,
4095 GEOMETRIC_SHAPES,
4096 MISCELLANEOUS_SYMBOLS,
4097 DINGBATS,
4098 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4099 SUPPLEMENTAL_ARROWS_A,
4100 BRAILLE_PATTERNS,
4101 SUPPLEMENTAL_ARROWS_B,
4102 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4103 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4104 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4105 GLAGOLITIC,
4106 LATIN_EXTENDED_C,
4107 COPTIC,
4108 GEORGIAN_SUPPLEMENT,
4109 TIFINAGH,
4110 ETHIOPIC_EXTENDED,
4111 CYRILLIC_EXTENDED_A,
4112 SUPPLEMENTAL_PUNCTUATION,
4113 CJK_RADICALS_SUPPLEMENT,
4114 KANGXI_RADICALS,
4115 null,
4116 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4117 CJK_SYMBOLS_AND_PUNCTUATION,
4118 HIRAGANA,
4119 KATAKANA,
4120 BOPOMOFO,
4121 HANGUL_COMPATIBILITY_JAMO,
4122 KANBUN,
4123 BOPOMOFO_EXTENDED,
4124 CJK_STROKES,
4125 KATAKANA_PHONETIC_EXTENSIONS,
4126 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4127 CJK_COMPATIBILITY,
4128 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4129 YIJING_HEXAGRAM_SYMBOLS,
4130 CJK_UNIFIED_IDEOGRAPHS,
4131 YI_SYLLABLES,
4132 YI_RADICALS,
4133 LISU,
4134 VAI,
4135 CYRILLIC_EXTENDED_B,
4136 BAMUM,
4137 MODIFIER_TONE_LETTERS,
4138 LATIN_EXTENDED_D,
4139 SYLOTI_NAGRI,
4140 COMMON_INDIC_NUMBER_FORMS,
4141 PHAGS_PA,
4142 SAURASHTRA,
4143 DEVANAGARI_EXTENDED,
4144 KAYAH_LI,
4145 REJANG,
4146 HANGUL_JAMO_EXTENDED_A,
4147 JAVANESE,
4148 MYANMAR_EXTENDED_B,
4149 CHAM,
4150 MYANMAR_EXTENDED_A,
4151 TAI_VIET,
4152 MEETEI_MAYEK_EXTENSIONS,
4153 ETHIOPIC_EXTENDED_A,
4154 LATIN_EXTENDED_E,
4155 CHEROKEE_SUPPLEMENT,
4156 MEETEI_MAYEK,
4157 HANGUL_SYLLABLES,
4158 HANGUL_JAMO_EXTENDED_B,
4159 HIGH_SURROGATES,
4160 HIGH_PRIVATE_USE_SURROGATES,
4161 LOW_SURROGATES,
4162 PRIVATE_USE_AREA,
4163 CJK_COMPATIBILITY_IDEOGRAPHS,
4164 ALPHABETIC_PRESENTATION_FORMS,
4165 ARABIC_PRESENTATION_FORMS_A,
4166 VARIATION_SELECTORS,
4167 VERTICAL_FORMS,
4168 COMBINING_HALF_MARKS,
4169 CJK_COMPATIBILITY_FORMS,
4170 SMALL_FORM_VARIANTS,
4171 ARABIC_PRESENTATION_FORMS_B,
4172 HALFWIDTH_AND_FULLWIDTH_FORMS,
4173 SPECIALS,
4174 LINEAR_B_SYLLABARY,
4175 LINEAR_B_IDEOGRAMS,
4176 AEGEAN_NUMBERS,
4177 ANCIENT_GREEK_NUMBERS,
4178 ANCIENT_SYMBOLS,
4179 PHAISTOS_DISC,
4180 null,
4181 LYCIAN,
4182 CARIAN,
4183 COPTIC_EPACT_NUMBERS,
4184 OLD_ITALIC,
4185 GOTHIC,
4186 OLD_PERMIC,
4187 UGARITIC,
4188 OLD_PERSIAN,
4189 null,
4190 DESERET,
4191 SHAVIAN,
4192 OSMANYA,
4193 OSAGE,
4194 ELBASAN,
4195 CAUCASIAN_ALBANIAN,
4196 VITHKUQI,
4197 null,
4198 LINEAR_A,
4199 LATIN_EXTENDED_F,
4200 null,
4201 CYPRIOT_SYLLABARY,
4202 IMPERIAL_ARAMAIC,
4203 PALMYRENE,
4204 NABATAEAN,
4205 null,
4206 HATRAN,
4207 PHOENICIAN,
4208 LYDIAN,
4209 null,
4210 MEROITIC_HIEROGLYPHS,
4211 MEROITIC_CURSIVE,
4212 KHAROSHTHI,
4213 OLD_SOUTH_ARABIAN,
4214 OLD_NORTH_ARABIAN,
4215 null,
4216 MANICHAEAN,
4217 AVESTAN,
4218 INSCRIPTIONAL_PARTHIAN,
4219 INSCRIPTIONAL_PAHLAVI,
4220 PSALTER_PAHLAVI,
4221 null,
4222 OLD_TURKIC,
4223 null,
4224 OLD_HUNGARIAN,
4225 HANIFI_ROHINGYA,
4226 null,
4227 RUMI_NUMERAL_SYMBOLS,
4228 YEZIDI,
4229 ARABIC_EXTENDED_C,
4230 OLD_SOGDIAN,
4231 SOGDIAN,
4232 OLD_UYGHUR,
4233 CHORASMIAN,
4234 ELYMAIC,
4235 BRAHMI,
4236 KAITHI,
4237 SORA_SOMPENG,
4238 CHAKMA,
4239 MAHAJANI,
4240 SHARADA,
4241 SINHALA_ARCHAIC_NUMBERS,
4242 KHOJKI,
4243 null,
4244 MULTANI,
4245 KHUDAWADI,
4246 GRANTHA,
4247 null,
4248 NEWA,
4249 TIRHUTA,
4250 null,
4251 SIDDHAM,
4252 MODI,
4253 MONGOLIAN_SUPPLEMENT,
4254 TAKRI,
4255 null,
4256 AHOM,
4257 null,
4258 DOGRA,
4259 null,
4260 WARANG_CITI,
4261 DIVES_AKURU,
4262 null,
4263 NANDINAGARI,
4264 ZANABAZAR_SQUARE,
4265 SOYOMBO,
4266 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4267 PAU_CIN_HAU,
4268 DEVANAGARI_EXTENDED_A,
4269 null,
4270 BHAIKSUKI,
4271 MARCHEN,
4272 null,
4273 MASARAM_GONDI,
4274 GUNJALA_GONDI,
4275 null,
4276 MAKASAR,
4277 KAWI,
4278 null,
4279 LISU_SUPPLEMENT,
4280 TAMIL_SUPPLEMENT,
4281 CUNEIFORM,
4282 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4283 EARLY_DYNASTIC_CUNEIFORM,
4284 null,
4285 CYPRO_MINOAN,
4286 EGYPTIAN_HIEROGLYPHS,
4287 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4288 null,
4289 ANATOLIAN_HIEROGLYPHS,
4290 null,
4291 BAMUM_SUPPLEMENT,
4292 MRO,
4293 TANGSA,
4294 BASSA_VAH,
4295 PAHAWH_HMONG,
4296 null,
4297 MEDEFAIDRIN,
4298 null,
4299 MIAO,
4300 null,
4301 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4302 TANGUT,
4303 TANGUT_COMPONENTS,
4304 KHITAN_SMALL_SCRIPT,
4305 TANGUT_SUPPLEMENT,
4306 null,
4307 KANA_EXTENDED_B,
4308 KANA_SUPPLEMENT,
4309 KANA_EXTENDED_A,
4310 SMALL_KANA_EXTENSION,
4311 NUSHU,
4312 null,
4313 DUPLOYAN,
4314 SHORTHAND_FORMAT_CONTROLS,
4315 null,
4316 ZNAMENNY_MUSICAL_NOTATION,
4317 null,
4318 BYZANTINE_MUSICAL_SYMBOLS,
4319 MUSICAL_SYMBOLS,
4320 ANCIENT_GREEK_MUSICAL_NOTATION,
4321 null,
4322 KAKTOVIK_NUMERALS,
4323 MAYAN_NUMERALS,
4324 TAI_XUAN_JING_SYMBOLS,
4325 COUNTING_ROD_NUMERALS,
4326 null,
4327 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4328 SUTTON_SIGNWRITING,
4329 null,
4330 LATIN_EXTENDED_G,
4331 GLAGOLITIC_SUPPLEMENT,
4332 CYRILLIC_EXTENDED_D,
4333 null,
4334 NYIAKENG_PUACHUE_HMONG,
4335 null,
4336 TOTO,
4337 WANCHO,
4338 null,
4339 NAG_MUNDARI,
4340 null,
4341 ETHIOPIC_EXTENDED_B,
4342 MENDE_KIKAKUI,
4343 null,
4344 ADLAM,
4345 null,
4346 INDIC_SIYAQ_NUMBERS,
4347 null,
4348 OTTOMAN_SIYAQ_NUMBERS,
4349 null,
4350 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4351 null,
4352 MAHJONG_TILES,
4353 DOMINO_TILES,
4354 PLAYING_CARDS,
4355 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4356 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4357 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4358 EMOTICONS,
4359 ORNAMENTAL_DINGBATS,
4360 TRANSPORT_AND_MAP_SYMBOLS,
4361 ALCHEMICAL_SYMBOLS,
4362 GEOMETRIC_SHAPES_EXTENDED,
4363 SUPPLEMENTAL_ARROWS_C,
4364 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4365 CHESS_SYMBOLS,
4366 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4367 SYMBOLS_FOR_LEGACY_COMPUTING,
4368 null,
4369 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4370 null,
4371 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4372 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4373 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4374 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4375 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4376 null,
4377 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4378 null,
4379 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4380 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4381 null,
4382 TAGS,
4383 null,
4384 VARIATION_SELECTORS_SUPPLEMENT,
4385 null,
4386 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4387 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4388 };
4389
4390
4391 /**
4392 * Returns the object representing the Unicode block containing the
4393 * given character, or {@code null} if the character is not a
4394 * member of a defined block.
4395 *
4396 * <p><b>Note:</b> This method cannot handle
4397 * <a href="Character.html#supplementary"> supplementary
4398 * characters</a>. To support all Unicode characters, including
4399 * supplementary characters, use the {@link #of(int)} method.
4400 *
4401 * @param c The character in question
4402 * @return The {@code UnicodeBlock} instance representing the
4403 * Unicode block of which this character is a member, or
4404 * {@code null} if the character is not a member of any
4405 * Unicode block
4406 */
4407 public static UnicodeBlock of(char c) {
4408 return of((int)c);
4409 }
4410
4411 /**
4412 * Returns the object representing the Unicode block
4413 * containing the given character (Unicode code point), or
4414 * {@code null} if the character is not a member of a
4415 * defined block.
4416 *
4417 * @param codePoint the character (Unicode code point) in question.
4418 * @return The {@code UnicodeBlock} instance representing the
4419 * Unicode block of which this character is a member, or
4420 * {@code null} if the character is not a member of any
4421 * Unicode block
4422 * @throws IllegalArgumentException if the specified
4423 * {@code codePoint} is an invalid Unicode code point.
4424 * @see Character#isValidCodePoint(int)
4425 * @since 1.5
4426 */
4427 public static UnicodeBlock of(int codePoint) {
4428 if (!isValidCodePoint(codePoint)) {
4429 throw new IllegalArgumentException(
4430 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4431 }
4432
4433 int top, bottom, current;
4434 bottom = 0;
4435 top = blockStarts.length;
4436 current = top/2;
4437
4438 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4439 while (top - bottom > 1) {
4440 if (codePoint >= blockStarts[current]) {
4441 bottom = current;
4442 } else {
4443 top = current;
4444 }
4445 current = (top + bottom) / 2;
4446 }
4447 return blocks[current];
4448 }
4449
4450 /**
4451 * Returns the UnicodeBlock with the given name. Block
4452 * names are determined by The Unicode Standard. The file
4453 * {@code Blocks.txt} defines blocks for a particular
4454 * version of the standard. The {@link Character} class specifies
4455 * the version of the standard that it supports.
4456 * <p>
4457 * This method accepts block names in the following forms:
4458 * <ol>
4459 * <li> Canonical block names as defined by the Unicode Standard.
4460 * For example, the standard defines a "Basic Latin" block. Therefore, this
4461 * method accepts "Basic Latin" as a valid block name. The documentation of
4462 * each UnicodeBlock provides the canonical name.
4463 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4464 * is a valid block name for the "Basic Latin" block.
4465 * <li>The text representation of each constant UnicodeBlock identifier.
4466 * For example, this method will return the {@link #BASIC_LATIN} block if
4467 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4468 * hyphens in the canonical name with underscores.
4469 * </ol>
4470 * Finally, character case is ignored for all of the valid block name forms.
4471 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4472 * The en_US locale's case mapping rules are used to provide case-insensitive
4473 * string comparisons for block name validation.
4474 * <p>
4475 * If the Unicode Standard changes block names, both the previous and
4476 * current names will be accepted.
4477 *
4478 * @param blockName A {@code UnicodeBlock} name.
4479 * @return The {@code UnicodeBlock} instance identified
4480 * by {@code blockName}
4481 * @throws IllegalArgumentException if {@code blockName} is an
4482 * invalid name
4483 * @throws NullPointerException if {@code blockName} is null
4484 * @since 1.5
4485 */
4486 public static final UnicodeBlock forName(String blockName) {
4487 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4488 if (block == null) {
4489 throw new IllegalArgumentException("Not a valid block name: "
4490 + blockName);
4491 }
4492 return block;
4493 }
4494 }
4495
4496
4497 /**
4498 * A family of character subsets representing the character scripts
4499 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4500 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4501 * character is assigned to a single Unicode script, either a specific
4502 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4503 * one of the following three special values,
4504 * {@link Character.UnicodeScript#INHERITED Inherited},
4505 * {@link Character.UnicodeScript#COMMON Common} or
4506 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4507 *
4508 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4509 * @since 1.7
4510 */
4511 public static enum UnicodeScript {
4512 /**
4513 * Unicode script "Common".
4514 */
4515 COMMON,
4516
4517 /**
4518 * Unicode script "Latin".
4519 */
4520 LATIN,
4521
4522 /**
4523 * Unicode script "Greek".
4524 */
4525 GREEK,
4526
4527 /**
4528 * Unicode script "Cyrillic".
4529 */
4530 CYRILLIC,
4531
4532 /**
4533 * Unicode script "Armenian".
4534 */
4535 ARMENIAN,
4536
4537 /**
4538 * Unicode script "Hebrew".
4539 */
4540 HEBREW,
4541
4542 /**
4543 * Unicode script "Arabic".
4544 */
4545 ARABIC,
4546
4547 /**
4548 * Unicode script "Syriac".
4549 */
4550 SYRIAC,
4551
4552 /**
4553 * Unicode script "Thaana".
4554 */
4555 THAANA,
4556
4557 /**
4558 * Unicode script "Devanagari".
4559 */
4560 DEVANAGARI,
4561
4562 /**
4563 * Unicode script "Bengali".
4564 */
4565 BENGALI,
4566
4567 /**
4568 * Unicode script "Gurmukhi".
4569 */
4570 GURMUKHI,
4571
4572 /**
4573 * Unicode script "Gujarati".
4574 */
4575 GUJARATI,
4576
4577 /**
4578 * Unicode script "Oriya".
4579 */
4580 ORIYA,
4581
4582 /**
4583 * Unicode script "Tamil".
4584 */
4585 TAMIL,
4586
4587 /**
4588 * Unicode script "Telugu".
4589 */
4590 TELUGU,
4591
4592 /**
4593 * Unicode script "Kannada".
4594 */
4595 KANNADA,
4596
4597 /**
4598 * Unicode script "Malayalam".
4599 */
4600 MALAYALAM,
4601
4602 /**
4603 * Unicode script "Sinhala".
4604 */
4605 SINHALA,
4606
4607 /**
4608 * Unicode script "Thai".
4609 */
4610 THAI,
4611
4612 /**
4613 * Unicode script "Lao".
4614 */
4615 LAO,
4616
4617 /**
4618 * Unicode script "Tibetan".
4619 */
4620 TIBETAN,
4621
4622 /**
4623 * Unicode script "Myanmar".
4624 */
4625 MYANMAR,
4626
4627 /**
4628 * Unicode script "Georgian".
4629 */
4630 GEORGIAN,
4631
4632 /**
4633 * Unicode script "Hangul".
4634 */
4635 HANGUL,
4636
4637 /**
4638 * Unicode script "Ethiopic".
4639 */
4640 ETHIOPIC,
4641
4642 /**
4643 * Unicode script "Cherokee".
4644 */
4645 CHEROKEE,
4646
4647 /**
4648 * Unicode script "Canadian_Aboriginal".
4649 */
4650 CANADIAN_ABORIGINAL,
4651
4652 /**
4653 * Unicode script "Ogham".
4654 */
4655 OGHAM,
4656
4657 /**
4658 * Unicode script "Runic".
4659 */
4660 RUNIC,
4661
4662 /**
4663 * Unicode script "Khmer".
4664 */
4665 KHMER,
4666
4667 /**
4668 * Unicode script "Mongolian".
4669 */
4670 MONGOLIAN,
4671
4672 /**
4673 * Unicode script "Hiragana".
4674 */
4675 HIRAGANA,
4676
4677 /**
4678 * Unicode script "Katakana".
4679 */
4680 KATAKANA,
4681
4682 /**
4683 * Unicode script "Bopomofo".
4684 */
4685 BOPOMOFO,
4686
4687 /**
4688 * Unicode script "Han".
4689 */
4690 HAN,
4691
4692 /**
4693 * Unicode script "Yi".
4694 */
4695 YI,
4696
4697 /**
4698 * Unicode script "Old_Italic".
4699 */
4700 OLD_ITALIC,
4701
4702 /**
4703 * Unicode script "Gothic".
4704 */
4705 GOTHIC,
4706
4707 /**
4708 * Unicode script "Deseret".
4709 */
4710 DESERET,
4711
4712 /**
4713 * Unicode script "Inherited".
4714 */
4715 INHERITED,
4716
4717 /**
4718 * Unicode script "Tagalog".
4719 */
4720 TAGALOG,
4721
4722 /**
4723 * Unicode script "Hanunoo".
4724 */
4725 HANUNOO,
4726
4727 /**
4728 * Unicode script "Buhid".
4729 */
4730 BUHID,
4731
4732 /**
4733 * Unicode script "Tagbanwa".
4734 */
4735 TAGBANWA,
4736
4737 /**
4738 * Unicode script "Limbu".
4739 */
4740 LIMBU,
4741
4742 /**
4743 * Unicode script "Tai_Le".
4744 */
4745 TAI_LE,
4746
4747 /**
4748 * Unicode script "Linear_B".
4749 */
4750 LINEAR_B,
4751
4752 /**
4753 * Unicode script "Ugaritic".
4754 */
4755 UGARITIC,
4756
4757 /**
4758 * Unicode script "Shavian".
4759 */
4760 SHAVIAN,
4761
4762 /**
4763 * Unicode script "Osmanya".
4764 */
4765 OSMANYA,
4766
4767 /**
4768 * Unicode script "Cypriot".
4769 */
4770 CYPRIOT,
4771
4772 /**
4773 * Unicode script "Braille".
4774 */
4775 BRAILLE,
4776
4777 /**
4778 * Unicode script "Buginese".
4779 */
4780 BUGINESE,
4781
4782 /**
4783 * Unicode script "Coptic".
4784 */
4785 COPTIC,
4786
4787 /**
4788 * Unicode script "New_Tai_Lue".
4789 */
4790 NEW_TAI_LUE,
4791
4792 /**
4793 * Unicode script "Glagolitic".
4794 */
4795 GLAGOLITIC,
4796
4797 /**
4798 * Unicode script "Tifinagh".
4799 */
4800 TIFINAGH,
4801
4802 /**
4803 * Unicode script "Syloti_Nagri".
4804 */
4805 SYLOTI_NAGRI,
4806
4807 /**
4808 * Unicode script "Old_Persian".
4809 */
4810 OLD_PERSIAN,
4811
4812 /**
4813 * Unicode script "Kharoshthi".
4814 */
4815 KHAROSHTHI,
4816
4817 /**
4818 * Unicode script "Balinese".
4819 */
4820 BALINESE,
4821
4822 /**
4823 * Unicode script "Cuneiform".
4824 */
4825 CUNEIFORM,
4826
4827 /**
4828 * Unicode script "Phoenician".
4829 */
4830 PHOENICIAN,
4831
4832 /**
4833 * Unicode script "Phags_Pa".
4834 */
4835 PHAGS_PA,
4836
4837 /**
4838 * Unicode script "Nko".
4839 */
4840 NKO,
4841
4842 /**
4843 * Unicode script "Sundanese".
4844 */
4845 SUNDANESE,
4846
4847 /**
4848 * Unicode script "Batak".
4849 */
4850 BATAK,
4851
4852 /**
4853 * Unicode script "Lepcha".
4854 */
4855 LEPCHA,
4856
4857 /**
4858 * Unicode script "Ol_Chiki".
4859 */
4860 OL_CHIKI,
4861
4862 /**
4863 * Unicode script "Vai".
4864 */
4865 VAI,
4866
4867 /**
4868 * Unicode script "Saurashtra".
4869 */
4870 SAURASHTRA,
4871
4872 /**
4873 * Unicode script "Kayah_Li".
4874 */
4875 KAYAH_LI,
4876
4877 /**
4878 * Unicode script "Rejang".
4879 */
4880 REJANG,
4881
4882 /**
4883 * Unicode script "Lycian".
4884 */
4885 LYCIAN,
4886
4887 /**
4888 * Unicode script "Carian".
4889 */
4890 CARIAN,
4891
4892 /**
4893 * Unicode script "Lydian".
4894 */
4895 LYDIAN,
4896
4897 /**
4898 * Unicode script "Cham".
4899 */
4900 CHAM,
4901
4902 /**
4903 * Unicode script "Tai_Tham".
4904 */
4905 TAI_THAM,
4906
4907 /**
4908 * Unicode script "Tai_Viet".
4909 */
4910 TAI_VIET,
4911
4912 /**
4913 * Unicode script "Avestan".
4914 */
4915 AVESTAN,
4916
4917 /**
4918 * Unicode script "Egyptian_Hieroglyphs".
4919 */
4920 EGYPTIAN_HIEROGLYPHS,
4921
4922 /**
4923 * Unicode script "Samaritan".
4924 */
4925 SAMARITAN,
4926
4927 /**
4928 * Unicode script "Mandaic".
4929 */
4930 MANDAIC,
4931
4932 /**
4933 * Unicode script "Lisu".
4934 */
4935 LISU,
4936
4937 /**
4938 * Unicode script "Bamum".
4939 */
4940 BAMUM,
4941
4942 /**
4943 * Unicode script "Javanese".
4944 */
4945 JAVANESE,
4946
4947 /**
4948 * Unicode script "Meetei_Mayek".
4949 */
4950 MEETEI_MAYEK,
4951
4952 /**
4953 * Unicode script "Imperial_Aramaic".
4954 */
4955 IMPERIAL_ARAMAIC,
4956
4957 /**
4958 * Unicode script "Old_South_Arabian".
4959 */
4960 OLD_SOUTH_ARABIAN,
4961
4962 /**
4963 * Unicode script "Inscriptional_Parthian".
4964 */
4965 INSCRIPTIONAL_PARTHIAN,
4966
4967 /**
4968 * Unicode script "Inscriptional_Pahlavi".
4969 */
4970 INSCRIPTIONAL_PAHLAVI,
4971
4972 /**
4973 * Unicode script "Old_Turkic".
4974 */
4975 OLD_TURKIC,
4976
4977 /**
4978 * Unicode script "Brahmi".
4979 */
4980 BRAHMI,
4981
4982 /**
4983 * Unicode script "Kaithi".
4984 */
4985 KAITHI,
4986
4987 /**
4988 * Unicode script "Meroitic Hieroglyphs".
4989 * @since 1.8
4990 */
4991 MEROITIC_HIEROGLYPHS,
4992
4993 /**
4994 * Unicode script "Meroitic Cursive".
4995 * @since 1.8
4996 */
4997 MEROITIC_CURSIVE,
4998
4999 /**
5000 * Unicode script "Sora Sompeng".
5001 * @since 1.8
5002 */
5003 SORA_SOMPENG,
5004
5005 /**
5006 * Unicode script "Chakma".
5007 * @since 1.8
5008 */
5009 CHAKMA,
5010
5011 /**
5012 * Unicode script "Sharada".
5013 * @since 1.8
5014 */
5015 SHARADA,
5016
5017 /**
5018 * Unicode script "Takri".
5019 * @since 1.8
5020 */
5021 TAKRI,
5022
5023 /**
5024 * Unicode script "Miao".
5025 * @since 1.8
5026 */
5027 MIAO,
5028
5029 /**
5030 * Unicode script "Caucasian Albanian".
5031 * @since 9
5032 */
5033 CAUCASIAN_ALBANIAN,
5034
5035 /**
5036 * Unicode script "Bassa Vah".
5037 * @since 9
5038 */
5039 BASSA_VAH,
5040
5041 /**
5042 * Unicode script "Duployan".
5043 * @since 9
5044 */
5045 DUPLOYAN,
5046
5047 /**
5048 * Unicode script "Elbasan".
5049 * @since 9
5050 */
5051 ELBASAN,
5052
5053 /**
5054 * Unicode script "Grantha".
5055 * @since 9
5056 */
5057 GRANTHA,
5058
5059 /**
5060 * Unicode script "Pahawh Hmong".
5061 * @since 9
5062 */
5063 PAHAWH_HMONG,
5064
5065 /**
5066 * Unicode script "Khojki".
5067 * @since 9
5068 */
5069 KHOJKI,
5070
5071 /**
5072 * Unicode script "Linear A".
5073 * @since 9
5074 */
5075 LINEAR_A,
5076
5077 /**
5078 * Unicode script "Mahajani".
5079 * @since 9
5080 */
5081 MAHAJANI,
5082
5083 /**
5084 * Unicode script "Manichaean".
5085 * @since 9
5086 */
5087 MANICHAEAN,
5088
5089 /**
5090 * Unicode script "Mende Kikakui".
5091 * @since 9
5092 */
5093 MENDE_KIKAKUI,
5094
5095 /**
5096 * Unicode script "Modi".
5097 * @since 9
5098 */
5099 MODI,
5100
5101 /**
5102 * Unicode script "Mro".
5103 * @since 9
5104 */
5105 MRO,
5106
5107 /**
5108 * Unicode script "Old North Arabian".
5109 * @since 9
5110 */
5111 OLD_NORTH_ARABIAN,
5112
5113 /**
5114 * Unicode script "Nabataean".
5115 * @since 9
5116 */
5117 NABATAEAN,
5118
5119 /**
5120 * Unicode script "Palmyrene".
5121 * @since 9
5122 */
5123 PALMYRENE,
5124
5125 /**
5126 * Unicode script "Pau Cin Hau".
5127 * @since 9
5128 */
5129 PAU_CIN_HAU,
5130
5131 /**
5132 * Unicode script "Old Permic".
5133 * @since 9
5134 */
5135 OLD_PERMIC,
5136
5137 /**
5138 * Unicode script "Psalter Pahlavi".
5139 * @since 9
5140 */
5141 PSALTER_PAHLAVI,
5142
5143 /**
5144 * Unicode script "Siddham".
5145 * @since 9
5146 */
5147 SIDDHAM,
5148
5149 /**
5150 * Unicode script "Khudawadi".
5151 * @since 9
5152 */
5153 KHUDAWADI,
5154
5155 /**
5156 * Unicode script "Tirhuta".
5157 * @since 9
5158 */
5159 TIRHUTA,
5160
5161 /**
5162 * Unicode script "Warang Citi".
5163 * @since 9
5164 */
5165 WARANG_CITI,
5166
5167 /**
5168 * Unicode script "Ahom".
5169 * @since 9
5170 */
5171 AHOM,
5172
5173 /**
5174 * Unicode script "Anatolian Hieroglyphs".
5175 * @since 9
5176 */
5177 ANATOLIAN_HIEROGLYPHS,
5178
5179 /**
5180 * Unicode script "Hatran".
5181 * @since 9
5182 */
5183 HATRAN,
5184
5185 /**
5186 * Unicode script "Multani".
5187 * @since 9
5188 */
5189 MULTANI,
5190
5191 /**
5192 * Unicode script "Old Hungarian".
5193 * @since 9
5194 */
5195 OLD_HUNGARIAN,
5196
5197 /**
5198 * Unicode script "SignWriting".
5199 * @since 9
5200 */
5201 SIGNWRITING,
5202
5203 /**
5204 * Unicode script "Adlam".
5205 * @since 11
5206 */
5207 ADLAM,
5208
5209 /**
5210 * Unicode script "Bhaiksuki".
5211 * @since 11
5212 */
5213 BHAIKSUKI,
5214
5215 /**
5216 * Unicode script "Marchen".
5217 * @since 11
5218 */
5219 MARCHEN,
5220
5221 /**
5222 * Unicode script "Newa".
5223 * @since 11
5224 */
5225 NEWA,
5226
5227 /**
5228 * Unicode script "Osage".
5229 * @since 11
5230 */
5231 OSAGE,
5232
5233 /**
5234 * Unicode script "Tangut".
5235 * @since 11
5236 */
5237 TANGUT,
5238
5239 /**
5240 * Unicode script "Masaram Gondi".
5241 * @since 11
5242 */
5243 MASARAM_GONDI,
5244
5245 /**
5246 * Unicode script "Nushu".
5247 * @since 11
5248 */
5249 NUSHU,
5250
5251 /**
5252 * Unicode script "Soyombo".
5253 * @since 11
5254 */
5255 SOYOMBO,
5256
5257 /**
5258 * Unicode script "Zanabazar Square".
5259 * @since 11
5260 */
5261 ZANABAZAR_SQUARE,
5262
5263 /**
5264 * Unicode script "Hanifi Rohingya".
5265 * @since 12
5266 */
5267 HANIFI_ROHINGYA,
5268
5269 /**
5270 * Unicode script "Old Sogdian".
5271 * @since 12
5272 */
5273 OLD_SOGDIAN,
5274
5275 /**
5276 * Unicode script "Sogdian".
5277 * @since 12
5278 */
5279 SOGDIAN,
5280
5281 /**
5282 * Unicode script "Dogra".
5283 * @since 12
5284 */
5285 DOGRA,
5286
5287 /**
5288 * Unicode script "Gunjala Gondi".
5289 * @since 12
5290 */
5291 GUNJALA_GONDI,
5292
5293 /**
5294 * Unicode script "Makasar".
5295 * @since 12
5296 */
5297 MAKASAR,
5298
5299 /**
5300 * Unicode script "Medefaidrin".
5301 * @since 12
5302 */
5303 MEDEFAIDRIN,
5304
5305 /**
5306 * Unicode script "Elymaic".
5307 * @since 13
5308 */
5309 ELYMAIC,
5310
5311 /**
5312 * Unicode script "Nandinagari".
5313 * @since 13
5314 */
5315 NANDINAGARI,
5316
5317 /**
5318 * Unicode script "Nyiakeng Puachue Hmong".
5319 * @since 13
5320 */
5321 NYIAKENG_PUACHUE_HMONG,
5322
5323 /**
5324 * Unicode script "Wancho".
5325 * @since 13
5326 */
5327 WANCHO,
5328
5329 /**
5330 * Unicode script "Yezidi".
5331 * @since 15
5332 */
5333 YEZIDI,
5334
5335 /**
5336 * Unicode script "Chorasmian".
5337 * @since 15
5338 */
5339 CHORASMIAN,
5340
5341 /**
5342 * Unicode script "Dives Akuru".
5343 * @since 15
5344 */
5345 DIVES_AKURU,
5346
5347 /**
5348 * Unicode script "Khitan Small Script".
5349 * @since 15
5350 */
5351 KHITAN_SMALL_SCRIPT,
5352
5353 /**
5354 * Unicode script "Vithkuqi".
5355 * @since 19
5356 */
5357 VITHKUQI,
5358
5359 /**
5360 * Unicode script "Old Uyghur".
5361 * @since 19
5362 */
5363 OLD_UYGHUR,
5364
5365 /**
5366 * Unicode script "Cypro Minoan".
5367 * @since 19
5368 */
5369 CYPRO_MINOAN,
5370
5371 /**
5372 * Unicode script "Tangsa".
5373 * @since 19
5374 */
5375 TANGSA,
5376
5377 /**
5378 * Unicode script "Toto".
5379 * @since 19
5380 */
5381 TOTO,
5382
5383 /**
5384 * Unicode script "Kawi".
5385 * @since 20
5386 */
5387 KAWI,
5388
5389 /**
5390 * Unicode script "Nag Mundari".
5391 * @since 20
5392 */
5393 NAG_MUNDARI,
5394
5395 /**
5396 * Unicode script "Unknown".
5397 */
5398 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5399
5400 private static final int[] scriptStarts = {
5401 0x0000, // 0000..0040; COMMON
5402 0x0041, // 0041..005A; LATIN
5403 0x005B, // 005B..0060; COMMON
5404 0x0061, // 0061..007A; LATIN
5405 0x007B, // 007B..00A9; COMMON
5406 0x00AA, // 00AA ; LATIN
5407 0x00AB, // 00AB..00B9; COMMON
5408 0x00BA, // 00BA ; LATIN
5409 0x00BB, // 00BB..00BF; COMMON
5410 0x00C0, // 00C0..00D6; LATIN
5411 0x00D7, // 00D7 ; COMMON
5412 0x00D8, // 00D8..00F6; LATIN
5413 0x00F7, // 00F7 ; COMMON
5414 0x00F8, // 00F8..02B8; LATIN
5415 0x02B9, // 02B9..02DF; COMMON
5416 0x02E0, // 02E0..02E4; LATIN
5417 0x02E5, // 02E5..02E9; COMMON
5418 0x02EA, // 02EA..02EB; BOPOMOFO
5419 0x02EC, // 02EC..02FF; COMMON
5420 0x0300, // 0300..036F; INHERITED
5421 0x0370, // 0370..0373; GREEK
5422 0x0374, // 0374 ; COMMON
5423 0x0375, // 0375..0377; GREEK
5424 0x0378, // 0378..0379; UNKNOWN
5425 0x037A, // 037A..037D; GREEK
5426 0x037E, // 037E ; COMMON
5427 0x037F, // 037F ; GREEK
5428 0x0380, // 0380..0383; UNKNOWN
5429 0x0384, // 0384 ; GREEK
5430 0x0385, // 0385 ; COMMON
5431 0x0386, // 0386 ; GREEK
5432 0x0387, // 0387 ; COMMON
5433 0x0388, // 0388..038A; GREEK
5434 0x038B, // 038B ; UNKNOWN
5435 0x038C, // 038C ; GREEK
5436 0x038D, // 038D ; UNKNOWN
5437 0x038E, // 038E..03A1; GREEK
5438 0x03A2, // 03A2 ; UNKNOWN
5439 0x03A3, // 03A3..03E1; GREEK
5440 0x03E2, // 03E2..03EF; COPTIC
5441 0x03F0, // 03F0..03FF; GREEK
5442 0x0400, // 0400..0484; CYRILLIC
5443 0x0485, // 0485..0486; INHERITED
5444 0x0487, // 0487..052F; CYRILLIC
5445 0x0530, // 0530 ; UNKNOWN
5446 0x0531, // 0531..0556; ARMENIAN
5447 0x0557, // 0557..0558; UNKNOWN
5448 0x0559, // 0559..058A; ARMENIAN
5449 0x058B, // 058B..058C; UNKNOWN
5450 0x058D, // 058D..058F; ARMENIAN
5451 0x0590, // 0590 ; UNKNOWN
5452 0x0591, // 0591..05C7; HEBREW
5453 0x05C8, // 05C8..05CF; UNKNOWN
5454 0x05D0, // 05D0..05EA; HEBREW
5455 0x05EB, // 05EB..05EE; UNKNOWN
5456 0x05EF, // 05EF..05F4; HEBREW
5457 0x05F5, // 05F5..05FF; UNKNOWN
5458 0x0600, // 0600..0604; ARABIC
5459 0x0605, // 0605 ; COMMON
5460 0x0606, // 0606..060B; ARABIC
5461 0x060C, // 060C ; COMMON
5462 0x060D, // 060D..061A; ARABIC
5463 0x061B, // 061B ; COMMON
5464 0x061C, // 061C..061E; ARABIC
5465 0x061F, // 061F ; COMMON
5466 0x0620, // 0620..063F; ARABIC
5467 0x0640, // 0640 ; COMMON
5468 0x0641, // 0641..064A; ARABIC
5469 0x064B, // 064B..0655; INHERITED
5470 0x0656, // 0656..066F; ARABIC
5471 0x0670, // 0670 ; INHERITED
5472 0x0671, // 0671..06DC; ARABIC
5473 0x06DD, // 06DD ; COMMON
5474 0x06DE, // 06DE..06FF; ARABIC
5475 0x0700, // 0700..070D; SYRIAC
5476 0x070E, // 070E ; UNKNOWN
5477 0x070F, // 070F..074A; SYRIAC
5478 0x074B, // 074B..074C; UNKNOWN
5479 0x074D, // 074D..074F; SYRIAC
5480 0x0750, // 0750..077F; ARABIC
5481 0x0780, // 0780..07B1; THAANA
5482 0x07B2, // 07B2..07BF; UNKNOWN
5483 0x07C0, // 07C0..07FA; NKO
5484 0x07FB, // 07FB..07FC; UNKNOWN
5485 0x07FD, // 07FD..07FF; NKO
5486 0x0800, // 0800..082D; SAMARITAN
5487 0x082E, // 082E..082F; UNKNOWN
5488 0x0830, // 0830..083E; SAMARITAN
5489 0x083F, // 083F ; UNKNOWN
5490 0x0840, // 0840..085B; MANDAIC
5491 0x085C, // 085C..085D; UNKNOWN
5492 0x085E, // 085E ; MANDAIC
5493 0x085F, // 085F ; UNKNOWN
5494 0x0860, // 0860..086A; SYRIAC
5495 0x086B, // 086B..086F; UNKNOWN
5496 0x0870, // 0870..088E; ARABIC
5497 0x088F, // 088F ; UNKNOWN
5498 0x0890, // 0890..0891; ARABIC
5499 0x0892, // 0892..0897; UNKNOWN
5500 0x0898, // 0898..08E1; ARABIC
5501 0x08E2, // 08E2 ; COMMON
5502 0x08E3, // 08E3..08FF; ARABIC
5503 0x0900, // 0900..0950; DEVANAGARI
5504 0x0951, // 0951..0954; INHERITED
5505 0x0955, // 0955..0963; DEVANAGARI
5506 0x0964, // 0964..0965; COMMON
5507 0x0966, // 0966..097F; DEVANAGARI
5508 0x0980, // 0980..0983; BENGALI
5509 0x0984, // 0984 ; UNKNOWN
5510 0x0985, // 0985..098C; BENGALI
5511 0x098D, // 098D..098E; UNKNOWN
5512 0x098F, // 098F..0990; BENGALI
5513 0x0991, // 0991..0992; UNKNOWN
5514 0x0993, // 0993..09A8; BENGALI
5515 0x09A9, // 09A9 ; UNKNOWN
5516 0x09AA, // 09AA..09B0; BENGALI
5517 0x09B1, // 09B1 ; UNKNOWN
5518 0x09B2, // 09B2 ; BENGALI
5519 0x09B3, // 09B3..09B5; UNKNOWN
5520 0x09B6, // 09B6..09B9; BENGALI
5521 0x09BA, // 09BA..09BB; UNKNOWN
5522 0x09BC, // 09BC..09C4; BENGALI
5523 0x09C5, // 09C5..09C6; UNKNOWN
5524 0x09C7, // 09C7..09C8; BENGALI
5525 0x09C9, // 09C9..09CA; UNKNOWN
5526 0x09CB, // 09CB..09CE; BENGALI
5527 0x09CF, // 09CF..09D6; UNKNOWN
5528 0x09D7, // 09D7 ; BENGALI
5529 0x09D8, // 09D8..09DB; UNKNOWN
5530 0x09DC, // 09DC..09DD; BENGALI
5531 0x09DE, // 09DE ; UNKNOWN
5532 0x09DF, // 09DF..09E3; BENGALI
5533 0x09E4, // 09E4..09E5; UNKNOWN
5534 0x09E6, // 09E6..09FE; BENGALI
5535 0x09FF, // 09FF..0A00; UNKNOWN
5536 0x0A01, // 0A01..0A03; GURMUKHI
5537 0x0A04, // 0A04 ; UNKNOWN
5538 0x0A05, // 0A05..0A0A; GURMUKHI
5539 0x0A0B, // 0A0B..0A0E; UNKNOWN
5540 0x0A0F, // 0A0F..0A10; GURMUKHI
5541 0x0A11, // 0A11..0A12; UNKNOWN
5542 0x0A13, // 0A13..0A28; GURMUKHI
5543 0x0A29, // 0A29 ; UNKNOWN
5544 0x0A2A, // 0A2A..0A30; GURMUKHI
5545 0x0A31, // 0A31 ; UNKNOWN
5546 0x0A32, // 0A32..0A33; GURMUKHI
5547 0x0A34, // 0A34 ; UNKNOWN
5548 0x0A35, // 0A35..0A36; GURMUKHI
5549 0x0A37, // 0A37 ; UNKNOWN
5550 0x0A38, // 0A38..0A39; GURMUKHI
5551 0x0A3A, // 0A3A..0A3B; UNKNOWN
5552 0x0A3C, // 0A3C ; GURMUKHI
5553 0x0A3D, // 0A3D ; UNKNOWN
5554 0x0A3E, // 0A3E..0A42; GURMUKHI
5555 0x0A43, // 0A43..0A46; UNKNOWN
5556 0x0A47, // 0A47..0A48; GURMUKHI
5557 0x0A49, // 0A49..0A4A; UNKNOWN
5558 0x0A4B, // 0A4B..0A4D; GURMUKHI
5559 0x0A4E, // 0A4E..0A50; UNKNOWN
5560 0x0A51, // 0A51 ; GURMUKHI
5561 0x0A52, // 0A52..0A58; UNKNOWN
5562 0x0A59, // 0A59..0A5C; GURMUKHI
5563 0x0A5D, // 0A5D ; UNKNOWN
5564 0x0A5E, // 0A5E ; GURMUKHI
5565 0x0A5F, // 0A5F..0A65; UNKNOWN
5566 0x0A66, // 0A66..0A76; GURMUKHI
5567 0x0A77, // 0A77..0A80; UNKNOWN
5568 0x0A81, // 0A81..0A83; GUJARATI
5569 0x0A84, // 0A84 ; UNKNOWN
5570 0x0A85, // 0A85..0A8D; GUJARATI
5571 0x0A8E, // 0A8E ; UNKNOWN
5572 0x0A8F, // 0A8F..0A91; GUJARATI
5573 0x0A92, // 0A92 ; UNKNOWN
5574 0x0A93, // 0A93..0AA8; GUJARATI
5575 0x0AA9, // 0AA9 ; UNKNOWN
5576 0x0AAA, // 0AAA..0AB0; GUJARATI
5577 0x0AB1, // 0AB1 ; UNKNOWN
5578 0x0AB2, // 0AB2..0AB3; GUJARATI
5579 0x0AB4, // 0AB4 ; UNKNOWN
5580 0x0AB5, // 0AB5..0AB9; GUJARATI
5581 0x0ABA, // 0ABA..0ABB; UNKNOWN
5582 0x0ABC, // 0ABC..0AC5; GUJARATI
5583 0x0AC6, // 0AC6 ; UNKNOWN
5584 0x0AC7, // 0AC7..0AC9; GUJARATI
5585 0x0ACA, // 0ACA ; UNKNOWN
5586 0x0ACB, // 0ACB..0ACD; GUJARATI
5587 0x0ACE, // 0ACE..0ACF; UNKNOWN
5588 0x0AD0, // 0AD0 ; GUJARATI
5589 0x0AD1, // 0AD1..0ADF; UNKNOWN
5590 0x0AE0, // 0AE0..0AE3; GUJARATI
5591 0x0AE4, // 0AE4..0AE5; UNKNOWN
5592 0x0AE6, // 0AE6..0AF1; GUJARATI
5593 0x0AF2, // 0AF2..0AF8; UNKNOWN
5594 0x0AF9, // 0AF9..0AFF; GUJARATI
5595 0x0B00, // 0B00 ; UNKNOWN
5596 0x0B01, // 0B01..0B03; ORIYA
5597 0x0B04, // 0B04 ; UNKNOWN
5598 0x0B05, // 0B05..0B0C; ORIYA
5599 0x0B0D, // 0B0D..0B0E; UNKNOWN
5600 0x0B0F, // 0B0F..0B10; ORIYA
5601 0x0B11, // 0B11..0B12; UNKNOWN
5602 0x0B13, // 0B13..0B28; ORIYA
5603 0x0B29, // 0B29 ; UNKNOWN
5604 0x0B2A, // 0B2A..0B30; ORIYA
5605 0x0B31, // 0B31 ; UNKNOWN
5606 0x0B32, // 0B32..0B33; ORIYA
5607 0x0B34, // 0B34 ; UNKNOWN
5608 0x0B35, // 0B35..0B39; ORIYA
5609 0x0B3A, // 0B3A..0B3B; UNKNOWN
5610 0x0B3C, // 0B3C..0B44; ORIYA
5611 0x0B45, // 0B45..0B46; UNKNOWN
5612 0x0B47, // 0B47..0B48; ORIYA
5613 0x0B49, // 0B49..0B4A; UNKNOWN
5614 0x0B4B, // 0B4B..0B4D; ORIYA
5615 0x0B4E, // 0B4E..0B54; UNKNOWN
5616 0x0B55, // 0B55..0B57; ORIYA
5617 0x0B58, // 0B58..0B5B; UNKNOWN
5618 0x0B5C, // 0B5C..0B5D; ORIYA
5619 0x0B5E, // 0B5E ; UNKNOWN
5620 0x0B5F, // 0B5F..0B63; ORIYA
5621 0x0B64, // 0B64..0B65; UNKNOWN
5622 0x0B66, // 0B66..0B77; ORIYA
5623 0x0B78, // 0B78..0B81; UNKNOWN
5624 0x0B82, // 0B82..0B83; TAMIL
5625 0x0B84, // 0B84 ; UNKNOWN
5626 0x0B85, // 0B85..0B8A; TAMIL
5627 0x0B8B, // 0B8B..0B8D; UNKNOWN
5628 0x0B8E, // 0B8E..0B90; TAMIL
5629 0x0B91, // 0B91 ; UNKNOWN
5630 0x0B92, // 0B92..0B95; TAMIL
5631 0x0B96, // 0B96..0B98; UNKNOWN
5632 0x0B99, // 0B99..0B9A; TAMIL
5633 0x0B9B, // 0B9B ; UNKNOWN
5634 0x0B9C, // 0B9C ; TAMIL
5635 0x0B9D, // 0B9D ; UNKNOWN
5636 0x0B9E, // 0B9E..0B9F; TAMIL
5637 0x0BA0, // 0BA0..0BA2; UNKNOWN
5638 0x0BA3, // 0BA3..0BA4; TAMIL
5639 0x0BA5, // 0BA5..0BA7; UNKNOWN
5640 0x0BA8, // 0BA8..0BAA; TAMIL
5641 0x0BAB, // 0BAB..0BAD; UNKNOWN
5642 0x0BAE, // 0BAE..0BB9; TAMIL
5643 0x0BBA, // 0BBA..0BBD; UNKNOWN
5644 0x0BBE, // 0BBE..0BC2; TAMIL
5645 0x0BC3, // 0BC3..0BC5; UNKNOWN
5646 0x0BC6, // 0BC6..0BC8; TAMIL
5647 0x0BC9, // 0BC9 ; UNKNOWN
5648 0x0BCA, // 0BCA..0BCD; TAMIL
5649 0x0BCE, // 0BCE..0BCF; UNKNOWN
5650 0x0BD0, // 0BD0 ; TAMIL
5651 0x0BD1, // 0BD1..0BD6; UNKNOWN
5652 0x0BD7, // 0BD7 ; TAMIL
5653 0x0BD8, // 0BD8..0BE5; UNKNOWN
5654 0x0BE6, // 0BE6..0BFA; TAMIL
5655 0x0BFB, // 0BFB..0BFF; UNKNOWN
5656 0x0C00, // 0C00..0C0C; TELUGU
5657 0x0C0D, // 0C0D ; UNKNOWN
5658 0x0C0E, // 0C0E..0C10; TELUGU
5659 0x0C11, // 0C11 ; UNKNOWN
5660 0x0C12, // 0C12..0C28; TELUGU
5661 0x0C29, // 0C29 ; UNKNOWN
5662 0x0C2A, // 0C2A..0C39; TELUGU
5663 0x0C3A, // 0C3A..0C3B; UNKNOWN
5664 0x0C3C, // 0C3C..0C44; TELUGU
5665 0x0C45, // 0C45 ; UNKNOWN
5666 0x0C46, // 0C46..0C48; TELUGU
5667 0x0C49, // 0C49 ; UNKNOWN
5668 0x0C4A, // 0C4A..0C4D; TELUGU
5669 0x0C4E, // 0C4E..0C54; UNKNOWN
5670 0x0C55, // 0C55..0C56; TELUGU
5671 0x0C57, // 0C57 ; UNKNOWN
5672 0x0C58, // 0C58..0C5A; TELUGU
5673 0x0C5B, // 0C5B..0C5C; UNKNOWN
5674 0x0C5D, // 0C5D ; TELUGU
5675 0x0C5E, // 0C5E..0C5F; UNKNOWN
5676 0x0C60, // 0C60..0C63; TELUGU
5677 0x0C64, // 0C64..0C65; UNKNOWN
5678 0x0C66, // 0C66..0C6F; TELUGU
5679 0x0C70, // 0C70..0C76; UNKNOWN
5680 0x0C77, // 0C77..0C7F; TELUGU
5681 0x0C80, // 0C80..0C8C; KANNADA
5682 0x0C8D, // 0C8D ; UNKNOWN
5683 0x0C8E, // 0C8E..0C90; KANNADA
5684 0x0C91, // 0C91 ; UNKNOWN
5685 0x0C92, // 0C92..0CA8; KANNADA
5686 0x0CA9, // 0CA9 ; UNKNOWN
5687 0x0CAA, // 0CAA..0CB3; KANNADA
5688 0x0CB4, // 0CB4 ; UNKNOWN
5689 0x0CB5, // 0CB5..0CB9; KANNADA
5690 0x0CBA, // 0CBA..0CBB; UNKNOWN
5691 0x0CBC, // 0CBC..0CC4; KANNADA
5692 0x0CC5, // 0CC5 ; UNKNOWN
5693 0x0CC6, // 0CC6..0CC8; KANNADA
5694 0x0CC9, // 0CC9 ; UNKNOWN
5695 0x0CCA, // 0CCA..0CCD; KANNADA
5696 0x0CCE, // 0CCE..0CD4; UNKNOWN
5697 0x0CD5, // 0CD5..0CD6; KANNADA
5698 0x0CD7, // 0CD7..0CDC; UNKNOWN
5699 0x0CDD, // 0CDD..0CDE; KANNADA
5700 0x0CDF, // 0CDF ; UNKNOWN
5701 0x0CE0, // 0CE0..0CE3; KANNADA
5702 0x0CE4, // 0CE4..0CE5; UNKNOWN
5703 0x0CE6, // 0CE6..0CEF; KANNADA
5704 0x0CF0, // 0CF0 ; UNKNOWN
5705 0x0CF1, // 0CF1..0CF3; KANNADA
5706 0x0CF4, // 0CF4..0CFF; UNKNOWN
5707 0x0D00, // 0D00..0D0C; MALAYALAM
5708 0x0D0D, // 0D0D ; UNKNOWN
5709 0x0D0E, // 0D0E..0D10; MALAYALAM
5710 0x0D11, // 0D11 ; UNKNOWN
5711 0x0D12, // 0D12..0D44; MALAYALAM
5712 0x0D45, // 0D45 ; UNKNOWN
5713 0x0D46, // 0D46..0D48; MALAYALAM
5714 0x0D49, // 0D49 ; UNKNOWN
5715 0x0D4A, // 0D4A..0D4F; MALAYALAM
5716 0x0D50, // 0D50..0D53; UNKNOWN
5717 0x0D54, // 0D54..0D63; MALAYALAM
5718 0x0D64, // 0D64..0D65; UNKNOWN
5719 0x0D66, // 0D66..0D7F; MALAYALAM
5720 0x0D80, // 0D80 ; UNKNOWN
5721 0x0D81, // 0D81..0D83; SINHALA
5722 0x0D84, // 0D84 ; UNKNOWN
5723 0x0D85, // 0D85..0D96; SINHALA
5724 0x0D97, // 0D97..0D99; UNKNOWN
5725 0x0D9A, // 0D9A..0DB1; SINHALA
5726 0x0DB2, // 0DB2 ; UNKNOWN
5727 0x0DB3, // 0DB3..0DBB; SINHALA
5728 0x0DBC, // 0DBC ; UNKNOWN
5729 0x0DBD, // 0DBD ; SINHALA
5730 0x0DBE, // 0DBE..0DBF; UNKNOWN
5731 0x0DC0, // 0DC0..0DC6; SINHALA
5732 0x0DC7, // 0DC7..0DC9; UNKNOWN
5733 0x0DCA, // 0DCA ; SINHALA
5734 0x0DCB, // 0DCB..0DCE; UNKNOWN
5735 0x0DCF, // 0DCF..0DD4; SINHALA
5736 0x0DD5, // 0DD5 ; UNKNOWN
5737 0x0DD6, // 0DD6 ; SINHALA
5738 0x0DD7, // 0DD7 ; UNKNOWN
5739 0x0DD8, // 0DD8..0DDF; SINHALA
5740 0x0DE0, // 0DE0..0DE5; UNKNOWN
5741 0x0DE6, // 0DE6..0DEF; SINHALA
5742 0x0DF0, // 0DF0..0DF1; UNKNOWN
5743 0x0DF2, // 0DF2..0DF4; SINHALA
5744 0x0DF5, // 0DF5..0E00; UNKNOWN
5745 0x0E01, // 0E01..0E3A; THAI
5746 0x0E3B, // 0E3B..0E3E; UNKNOWN
5747 0x0E3F, // 0E3F ; COMMON
5748 0x0E40, // 0E40..0E5B; THAI
5749 0x0E5C, // 0E5C..0E80; UNKNOWN
5750 0x0E81, // 0E81..0E82; LAO
5751 0x0E83, // 0E83 ; UNKNOWN
5752 0x0E84, // 0E84 ; LAO
5753 0x0E85, // 0E85 ; UNKNOWN
5754 0x0E86, // 0E86..0E8A; LAO
5755 0x0E8B, // 0E8B ; UNKNOWN
5756 0x0E8C, // 0E8C..0EA3; LAO
5757 0x0EA4, // 0EA4 ; UNKNOWN
5758 0x0EA5, // 0EA5 ; LAO
5759 0x0EA6, // 0EA6 ; UNKNOWN
5760 0x0EA7, // 0EA7..0EBD; LAO
5761 0x0EBE, // 0EBE..0EBF; UNKNOWN
5762 0x0EC0, // 0EC0..0EC4; LAO
5763 0x0EC5, // 0EC5 ; UNKNOWN
5764 0x0EC6, // 0EC6 ; LAO
5765 0x0EC7, // 0EC7 ; UNKNOWN
5766 0x0EC8, // 0EC8..0ECE; LAO
5767 0x0ECF, // 0ECF ; UNKNOWN
5768 0x0ED0, // 0ED0..0ED9; LAO
5769 0x0EDA, // 0EDA..0EDB; UNKNOWN
5770 0x0EDC, // 0EDC..0EDF; LAO
5771 0x0EE0, // 0EE0..0EFF; UNKNOWN
5772 0x0F00, // 0F00..0F47; TIBETAN
5773 0x0F48, // 0F48 ; UNKNOWN
5774 0x0F49, // 0F49..0F6C; TIBETAN
5775 0x0F6D, // 0F6D..0F70; UNKNOWN
5776 0x0F71, // 0F71..0F97; TIBETAN
5777 0x0F98, // 0F98 ; UNKNOWN
5778 0x0F99, // 0F99..0FBC; TIBETAN
5779 0x0FBD, // 0FBD ; UNKNOWN
5780 0x0FBE, // 0FBE..0FCC; TIBETAN
5781 0x0FCD, // 0FCD ; UNKNOWN
5782 0x0FCE, // 0FCE..0FD4; TIBETAN
5783 0x0FD5, // 0FD5..0FD8; COMMON
5784 0x0FD9, // 0FD9..0FDA; TIBETAN
5785 0x0FDB, // 0FDB..0FFF; UNKNOWN
5786 0x1000, // 1000..109F; MYANMAR
5787 0x10A0, // 10A0..10C5; GEORGIAN
5788 0x10C6, // 10C6 ; UNKNOWN
5789 0x10C7, // 10C7 ; GEORGIAN
5790 0x10C8, // 10C8..10CC; UNKNOWN
5791 0x10CD, // 10CD ; GEORGIAN
5792 0x10CE, // 10CE..10CF; UNKNOWN
5793 0x10D0, // 10D0..10FA; GEORGIAN
5794 0x10FB, // 10FB ; COMMON
5795 0x10FC, // 10FC..10FF; GEORGIAN
5796 0x1100, // 1100..11FF; HANGUL
5797 0x1200, // 1200..1248; ETHIOPIC
5798 0x1249, // 1249 ; UNKNOWN
5799 0x124A, // 124A..124D; ETHIOPIC
5800 0x124E, // 124E..124F; UNKNOWN
5801 0x1250, // 1250..1256; ETHIOPIC
5802 0x1257, // 1257 ; UNKNOWN
5803 0x1258, // 1258 ; ETHIOPIC
5804 0x1259, // 1259 ; UNKNOWN
5805 0x125A, // 125A..125D; ETHIOPIC
5806 0x125E, // 125E..125F; UNKNOWN
5807 0x1260, // 1260..1288; ETHIOPIC
5808 0x1289, // 1289 ; UNKNOWN
5809 0x128A, // 128A..128D; ETHIOPIC
5810 0x128E, // 128E..128F; UNKNOWN
5811 0x1290, // 1290..12B0; ETHIOPIC
5812 0x12B1, // 12B1 ; UNKNOWN
5813 0x12B2, // 12B2..12B5; ETHIOPIC
5814 0x12B6, // 12B6..12B7; UNKNOWN
5815 0x12B8, // 12B8..12BE; ETHIOPIC
5816 0x12BF, // 12BF ; UNKNOWN
5817 0x12C0, // 12C0 ; ETHIOPIC
5818 0x12C1, // 12C1 ; UNKNOWN
5819 0x12C2, // 12C2..12C5; ETHIOPIC
5820 0x12C6, // 12C6..12C7; UNKNOWN
5821 0x12C8, // 12C8..12D6; ETHIOPIC
5822 0x12D7, // 12D7 ; UNKNOWN
5823 0x12D8, // 12D8..1310; ETHIOPIC
5824 0x1311, // 1311 ; UNKNOWN
5825 0x1312, // 1312..1315; ETHIOPIC
5826 0x1316, // 1316..1317; UNKNOWN
5827 0x1318, // 1318..135A; ETHIOPIC
5828 0x135B, // 135B..135C; UNKNOWN
5829 0x135D, // 135D..137C; ETHIOPIC
5830 0x137D, // 137D..137F; UNKNOWN
5831 0x1380, // 1380..1399; ETHIOPIC
5832 0x139A, // 139A..139F; UNKNOWN
5833 0x13A0, // 13A0..13F5; CHEROKEE
5834 0x13F6, // 13F6..13F7; UNKNOWN
5835 0x13F8, // 13F8..13FD; CHEROKEE
5836 0x13FE, // 13FE..13FF; UNKNOWN
5837 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5838 0x1680, // 1680..169C; OGHAM
5839 0x169D, // 169D..169F; UNKNOWN
5840 0x16A0, // 16A0..16EA; RUNIC
5841 0x16EB, // 16EB..16ED; COMMON
5842 0x16EE, // 16EE..16F8; RUNIC
5843 0x16F9, // 16F9..16FF; UNKNOWN
5844 0x1700, // 1700..1715; TAGALOG
5845 0x1716, // 1716..171E; UNKNOWN
5846 0x171F, // 171F ; TAGALOG
5847 0x1720, // 1720..1734; HANUNOO
5848 0x1735, // 1735..1736; COMMON
5849 0x1737, // 1737..173F; UNKNOWN
5850 0x1740, // 1740..1753; BUHID
5851 0x1754, // 1754..175F; UNKNOWN
5852 0x1760, // 1760..176C; TAGBANWA
5853 0x176D, // 176D ; UNKNOWN
5854 0x176E, // 176E..1770; TAGBANWA
5855 0x1771, // 1771 ; UNKNOWN
5856 0x1772, // 1772..1773; TAGBANWA
5857 0x1774, // 1774..177F; UNKNOWN
5858 0x1780, // 1780..17DD; KHMER
5859 0x17DE, // 17DE..17DF; UNKNOWN
5860 0x17E0, // 17E0..17E9; KHMER
5861 0x17EA, // 17EA..17EF; UNKNOWN
5862 0x17F0, // 17F0..17F9; KHMER
5863 0x17FA, // 17FA..17FF; UNKNOWN
5864 0x1800, // 1800..1801; MONGOLIAN
5865 0x1802, // 1802..1803; COMMON
5866 0x1804, // 1804 ; MONGOLIAN
5867 0x1805, // 1805 ; COMMON
5868 0x1806, // 1806..1819; MONGOLIAN
5869 0x181A, // 181A..181F; UNKNOWN
5870 0x1820, // 1820..1878; MONGOLIAN
5871 0x1879, // 1879..187F; UNKNOWN
5872 0x1880, // 1880..18AA; MONGOLIAN
5873 0x18AB, // 18AB..18AF; UNKNOWN
5874 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
5875 0x18F6, // 18F6..18FF; UNKNOWN
5876 0x1900, // 1900..191E; LIMBU
5877 0x191F, // 191F ; UNKNOWN
5878 0x1920, // 1920..192B; LIMBU
5879 0x192C, // 192C..192F; UNKNOWN
5880 0x1930, // 1930..193B; LIMBU
5881 0x193C, // 193C..193F; UNKNOWN
5882 0x1940, // 1940 ; LIMBU
5883 0x1941, // 1941..1943; UNKNOWN
5884 0x1944, // 1944..194F; LIMBU
5885 0x1950, // 1950..196D; TAI_LE
5886 0x196E, // 196E..196F; UNKNOWN
5887 0x1970, // 1970..1974; TAI_LE
5888 0x1975, // 1975..197F; UNKNOWN
5889 0x1980, // 1980..19AB; NEW_TAI_LUE
5890 0x19AC, // 19AC..19AF; UNKNOWN
5891 0x19B0, // 19B0..19C9; NEW_TAI_LUE
5892 0x19CA, // 19CA..19CF; UNKNOWN
5893 0x19D0, // 19D0..19DA; NEW_TAI_LUE
5894 0x19DB, // 19DB..19DD; UNKNOWN
5895 0x19DE, // 19DE..19DF; NEW_TAI_LUE
5896 0x19E0, // 19E0..19FF; KHMER
5897 0x1A00, // 1A00..1A1B; BUGINESE
5898 0x1A1C, // 1A1C..1A1D; UNKNOWN
5899 0x1A1E, // 1A1E..1A1F; BUGINESE
5900 0x1A20, // 1A20..1A5E; TAI_THAM
5901 0x1A5F, // 1A5F ; UNKNOWN
5902 0x1A60, // 1A60..1A7C; TAI_THAM
5903 0x1A7D, // 1A7D..1A7E; UNKNOWN
5904 0x1A7F, // 1A7F..1A89; TAI_THAM
5905 0x1A8A, // 1A8A..1A8F; UNKNOWN
5906 0x1A90, // 1A90..1A99; TAI_THAM
5907 0x1A9A, // 1A9A..1A9F; UNKNOWN
5908 0x1AA0, // 1AA0..1AAD; TAI_THAM
5909 0x1AAE, // 1AAE..1AAF; UNKNOWN
5910 0x1AB0, // 1AB0..1ACE; INHERITED
5911 0x1ACF, // 1ACF..1AFF; UNKNOWN
5912 0x1B00, // 1B00..1B4C; BALINESE
5913 0x1B4D, // 1B4D..1B4F; UNKNOWN
5914 0x1B50, // 1B50..1B7E; BALINESE
5915 0x1B7F, // 1B7F ; UNKNOWN
5916 0x1B80, // 1B80..1BBF; SUNDANESE
5917 0x1BC0, // 1BC0..1BF3; BATAK
5918 0x1BF4, // 1BF4..1BFB; UNKNOWN
5919 0x1BFC, // 1BFC..1BFF; BATAK
5920 0x1C00, // 1C00..1C37; LEPCHA
5921 0x1C38, // 1C38..1C3A; UNKNOWN
5922 0x1C3B, // 1C3B..1C49; LEPCHA
5923 0x1C4A, // 1C4A..1C4C; UNKNOWN
5924 0x1C4D, // 1C4D..1C4F; LEPCHA
5925 0x1C50, // 1C50..1C7F; OL_CHIKI
5926 0x1C80, // 1C80..1C88; CYRILLIC
5927 0x1C89, // 1C89..1C8F; UNKNOWN
5928 0x1C90, // 1C90..1CBA; GEORGIAN
5929 0x1CBB, // 1CBB..1CBC; UNKNOWN
5930 0x1CBD, // 1CBD..1CBF; GEORGIAN
5931 0x1CC0, // 1CC0..1CC7; SUNDANESE
5932 0x1CC8, // 1CC8..1CCF; UNKNOWN
5933 0x1CD0, // 1CD0..1CD2; INHERITED
5934 0x1CD3, // 1CD3 ; COMMON
5935 0x1CD4, // 1CD4..1CE0; INHERITED
5936 0x1CE1, // 1CE1 ; COMMON
5937 0x1CE2, // 1CE2..1CE8; INHERITED
5938 0x1CE9, // 1CE9..1CEC; COMMON
5939 0x1CED, // 1CED ; INHERITED
5940 0x1CEE, // 1CEE..1CF3; COMMON
5941 0x1CF4, // 1CF4 ; INHERITED
5942 0x1CF5, // 1CF5..1CF7; COMMON
5943 0x1CF8, // 1CF8..1CF9; INHERITED
5944 0x1CFA, // 1CFA ; COMMON
5945 0x1CFB, // 1CFB..1CFF; UNKNOWN
5946 0x1D00, // 1D00..1D25; LATIN
5947 0x1D26, // 1D26..1D2A; GREEK
5948 0x1D2B, // 1D2B ; CYRILLIC
5949 0x1D2C, // 1D2C..1D5C; LATIN
5950 0x1D5D, // 1D5D..1D61; GREEK
5951 0x1D62, // 1D62..1D65; LATIN
5952 0x1D66, // 1D66..1D6A; GREEK
5953 0x1D6B, // 1D6B..1D77; LATIN
5954 0x1D78, // 1D78 ; CYRILLIC
5955 0x1D79, // 1D79..1DBE; LATIN
5956 0x1DBF, // 1DBF ; GREEK
5957 0x1DC0, // 1DC0..1DFF; INHERITED
5958 0x1E00, // 1E00..1EFF; LATIN
5959 0x1F00, // 1F00..1F15; GREEK
5960 0x1F16, // 1F16..1F17; UNKNOWN
5961 0x1F18, // 1F18..1F1D; GREEK
5962 0x1F1E, // 1F1E..1F1F; UNKNOWN
5963 0x1F20, // 1F20..1F45; GREEK
5964 0x1F46, // 1F46..1F47; UNKNOWN
5965 0x1F48, // 1F48..1F4D; GREEK
5966 0x1F4E, // 1F4E..1F4F; UNKNOWN
5967 0x1F50, // 1F50..1F57; GREEK
5968 0x1F58, // 1F58 ; UNKNOWN
5969 0x1F59, // 1F59 ; GREEK
5970 0x1F5A, // 1F5A ; UNKNOWN
5971 0x1F5B, // 1F5B ; GREEK
5972 0x1F5C, // 1F5C ; UNKNOWN
5973 0x1F5D, // 1F5D ; GREEK
5974 0x1F5E, // 1F5E ; UNKNOWN
5975 0x1F5F, // 1F5F..1F7D; GREEK
5976 0x1F7E, // 1F7E..1F7F; UNKNOWN
5977 0x1F80, // 1F80..1FB4; GREEK
5978 0x1FB5, // 1FB5 ; UNKNOWN
5979 0x1FB6, // 1FB6..1FC4; GREEK
5980 0x1FC5, // 1FC5 ; UNKNOWN
5981 0x1FC6, // 1FC6..1FD3; GREEK
5982 0x1FD4, // 1FD4..1FD5; UNKNOWN
5983 0x1FD6, // 1FD6..1FDB; GREEK
5984 0x1FDC, // 1FDC ; UNKNOWN
5985 0x1FDD, // 1FDD..1FEF; GREEK
5986 0x1FF0, // 1FF0..1FF1; UNKNOWN
5987 0x1FF2, // 1FF2..1FF4; GREEK
5988 0x1FF5, // 1FF5 ; UNKNOWN
5989 0x1FF6, // 1FF6..1FFE; GREEK
5990 0x1FFF, // 1FFF ; UNKNOWN
5991 0x2000, // 2000..200B; COMMON
5992 0x200C, // 200C..200D; INHERITED
5993 0x200E, // 200E..2064; COMMON
5994 0x2065, // 2065 ; UNKNOWN
5995 0x2066, // 2066..2070; COMMON
5996 0x2071, // 2071 ; LATIN
5997 0x2072, // 2072..2073; UNKNOWN
5998 0x2074, // 2074..207E; COMMON
5999 0x207F, // 207F ; LATIN
6000 0x2080, // 2080..208E; COMMON
6001 0x208F, // 208F ; UNKNOWN
6002 0x2090, // 2090..209C; LATIN
6003 0x209D, // 209D..209F; UNKNOWN
6004 0x20A0, // 20A0..20C0; COMMON
6005 0x20C1, // 20C1..20CF; UNKNOWN
6006 0x20D0, // 20D0..20F0; INHERITED
6007 0x20F1, // 20F1..20FF; UNKNOWN
6008 0x2100, // 2100..2125; COMMON
6009 0x2126, // 2126 ; GREEK
6010 0x2127, // 2127..2129; COMMON
6011 0x212A, // 212A..212B; LATIN
6012 0x212C, // 212C..2131; COMMON
6013 0x2132, // 2132 ; LATIN
6014 0x2133, // 2133..214D; COMMON
6015 0x214E, // 214E ; LATIN
6016 0x214F, // 214F..215F; COMMON
6017 0x2160, // 2160..2188; LATIN
6018 0x2189, // 2189..218B; COMMON
6019 0x218C, // 218C..218F; UNKNOWN
6020 0x2190, // 2190..2426; COMMON
6021 0x2427, // 2427..243F; UNKNOWN
6022 0x2440, // 2440..244A; COMMON
6023 0x244B, // 244B..245F; UNKNOWN
6024 0x2460, // 2460..27FF; COMMON
6025 0x2800, // 2800..28FF; BRAILLE
6026 0x2900, // 2900..2B73; COMMON
6027 0x2B74, // 2B74..2B75; UNKNOWN
6028 0x2B76, // 2B76..2B95; COMMON
6029 0x2B96, // 2B96 ; UNKNOWN
6030 0x2B97, // 2B97..2BFF; COMMON
6031 0x2C00, // 2C00..2C5F; GLAGOLITIC
6032 0x2C60, // 2C60..2C7F; LATIN
6033 0x2C80, // 2C80..2CF3; COPTIC
6034 0x2CF4, // 2CF4..2CF8; UNKNOWN
6035 0x2CF9, // 2CF9..2CFF; COPTIC
6036 0x2D00, // 2D00..2D25; GEORGIAN
6037 0x2D26, // 2D26 ; UNKNOWN
6038 0x2D27, // 2D27 ; GEORGIAN
6039 0x2D28, // 2D28..2D2C; UNKNOWN
6040 0x2D2D, // 2D2D ; GEORGIAN
6041 0x2D2E, // 2D2E..2D2F; UNKNOWN
6042 0x2D30, // 2D30..2D67; TIFINAGH
6043 0x2D68, // 2D68..2D6E; UNKNOWN
6044 0x2D6F, // 2D6F..2D70; TIFINAGH
6045 0x2D71, // 2D71..2D7E; UNKNOWN
6046 0x2D7F, // 2D7F ; TIFINAGH
6047 0x2D80, // 2D80..2D96; ETHIOPIC
6048 0x2D97, // 2D97..2D9F; UNKNOWN
6049 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6050 0x2DA7, // 2DA7 ; UNKNOWN
6051 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6052 0x2DAF, // 2DAF ; UNKNOWN
6053 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6054 0x2DB7, // 2DB7 ; UNKNOWN
6055 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6056 0x2DBF, // 2DBF ; UNKNOWN
6057 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6058 0x2DC7, // 2DC7 ; UNKNOWN
6059 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6060 0x2DCF, // 2DCF ; UNKNOWN
6061 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6062 0x2DD7, // 2DD7 ; UNKNOWN
6063 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6064 0x2DDF, // 2DDF ; UNKNOWN
6065 0x2DE0, // 2DE0..2DFF; CYRILLIC
6066 0x2E00, // 2E00..2E5D; COMMON
6067 0x2E5E, // 2E5E..2E7F; UNKNOWN
6068 0x2E80, // 2E80..2E99; HAN
6069 0x2E9A, // 2E9A ; UNKNOWN
6070 0x2E9B, // 2E9B..2EF3; HAN
6071 0x2EF4, // 2EF4..2EFF; UNKNOWN
6072 0x2F00, // 2F00..2FD5; HAN
6073 0x2FD6, // 2FD6..2FEF; UNKNOWN
6074 0x2FF0, // 2FF0..3004; COMMON
6075 0x3005, // 3005 ; HAN
6076 0x3006, // 3006 ; COMMON
6077 0x3007, // 3007 ; HAN
6078 0x3008, // 3008..3020; COMMON
6079 0x3021, // 3021..3029; HAN
6080 0x302A, // 302A..302D; INHERITED
6081 0x302E, // 302E..302F; HANGUL
6082 0x3030, // 3030..3037; COMMON
6083 0x3038, // 3038..303B; HAN
6084 0x303C, // 303C..303F; COMMON
6085 0x3040, // 3040 ; UNKNOWN
6086 0x3041, // 3041..3096; HIRAGANA
6087 0x3097, // 3097..3098; UNKNOWN
6088 0x3099, // 3099..309A; INHERITED
6089 0x309B, // 309B..309C; COMMON
6090 0x309D, // 309D..309F; HIRAGANA
6091 0x30A0, // 30A0 ; COMMON
6092 0x30A1, // 30A1..30FA; KATAKANA
6093 0x30FB, // 30FB..30FC; COMMON
6094 0x30FD, // 30FD..30FF; KATAKANA
6095 0x3100, // 3100..3104; UNKNOWN
6096 0x3105, // 3105..312F; BOPOMOFO
6097 0x3130, // 3130 ; UNKNOWN
6098 0x3131, // 3131..318E; HANGUL
6099 0x318F, // 318F ; UNKNOWN
6100 0x3190, // 3190..319F; COMMON
6101 0x31A0, // 31A0..31BF; BOPOMOFO
6102 0x31C0, // 31C0..31E3; COMMON
6103 0x31E4, // 31E4..31EE; UNKNOWN
6104 0x31EF, // 31EF ; COMMON
6105 0x31F0, // 31F0..31FF; KATAKANA
6106 0x3200, // 3200..321E; HANGUL
6107 0x321F, // 321F ; UNKNOWN
6108 0x3220, // 3220..325F; COMMON
6109 0x3260, // 3260..327E; HANGUL
6110 0x327F, // 327F..32CF; COMMON
6111 0x32D0, // 32D0..32FE; KATAKANA
6112 0x32FF, // 32FF ; COMMON
6113 0x3300, // 3300..3357; KATAKANA
6114 0x3358, // 3358..33FF; COMMON
6115 0x3400, // 3400..4DBF; HAN
6116 0x4DC0, // 4DC0..4DFF; COMMON
6117 0x4E00, // 4E00..9FFF; HAN
6118 0xA000, // A000..A48C; YI
6119 0xA48D, // A48D..A48F; UNKNOWN
6120 0xA490, // A490..A4C6; YI
6121 0xA4C7, // A4C7..A4CF; UNKNOWN
6122 0xA4D0, // A4D0..A4FF; LISU
6123 0xA500, // A500..A62B; VAI
6124 0xA62C, // A62C..A63F; UNKNOWN
6125 0xA640, // A640..A69F; CYRILLIC
6126 0xA6A0, // A6A0..A6F7; BAMUM
6127 0xA6F8, // A6F8..A6FF; UNKNOWN
6128 0xA700, // A700..A721; COMMON
6129 0xA722, // A722..A787; LATIN
6130 0xA788, // A788..A78A; COMMON
6131 0xA78B, // A78B..A7CA; LATIN
6132 0xA7CB, // A7CB..A7CF; UNKNOWN
6133 0xA7D0, // A7D0..A7D1; LATIN
6134 0xA7D2, // A7D2 ; UNKNOWN
6135 0xA7D3, // A7D3 ; LATIN
6136 0xA7D4, // A7D4 ; UNKNOWN
6137 0xA7D5, // A7D5..A7D9; LATIN
6138 0xA7DA, // A7DA..A7F1; UNKNOWN
6139 0xA7F2, // A7F2..A7FF; LATIN
6140 0xA800, // A800..A82C; SYLOTI_NAGRI
6141 0xA82D, // A82D..A82F; UNKNOWN
6142 0xA830, // A830..A839; COMMON
6143 0xA83A, // A83A..A83F; UNKNOWN
6144 0xA840, // A840..A877; PHAGS_PA
6145 0xA878, // A878..A87F; UNKNOWN
6146 0xA880, // A880..A8C5; SAURASHTRA
6147 0xA8C6, // A8C6..A8CD; UNKNOWN
6148 0xA8CE, // A8CE..A8D9; SAURASHTRA
6149 0xA8DA, // A8DA..A8DF; UNKNOWN
6150 0xA8E0, // A8E0..A8FF; DEVANAGARI
6151 0xA900, // A900..A92D; KAYAH_LI
6152 0xA92E, // A92E ; COMMON
6153 0xA92F, // A92F ; KAYAH_LI
6154 0xA930, // A930..A953; REJANG
6155 0xA954, // A954..A95E; UNKNOWN
6156 0xA95F, // A95F ; REJANG
6157 0xA960, // A960..A97C; HANGUL
6158 0xA97D, // A97D..A97F; UNKNOWN
6159 0xA980, // A980..A9CD; JAVANESE
6160 0xA9CE, // A9CE ; UNKNOWN
6161 0xA9CF, // A9CF ; COMMON
6162 0xA9D0, // A9D0..A9D9; JAVANESE
6163 0xA9DA, // A9DA..A9DD; UNKNOWN
6164 0xA9DE, // A9DE..A9DF; JAVANESE
6165 0xA9E0, // A9E0..A9FE; MYANMAR
6166 0xA9FF, // A9FF ; UNKNOWN
6167 0xAA00, // AA00..AA36; CHAM
6168 0xAA37, // AA37..AA3F; UNKNOWN
6169 0xAA40, // AA40..AA4D; CHAM
6170 0xAA4E, // AA4E..AA4F; UNKNOWN
6171 0xAA50, // AA50..AA59; CHAM
6172 0xAA5A, // AA5A..AA5B; UNKNOWN
6173 0xAA5C, // AA5C..AA5F; CHAM
6174 0xAA60, // AA60..AA7F; MYANMAR
6175 0xAA80, // AA80..AAC2; TAI_VIET
6176 0xAAC3, // AAC3..AADA; UNKNOWN
6177 0xAADB, // AADB..AADF; TAI_VIET
6178 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6179 0xAAF7, // AAF7..AB00; UNKNOWN
6180 0xAB01, // AB01..AB06; ETHIOPIC
6181 0xAB07, // AB07..AB08; UNKNOWN
6182 0xAB09, // AB09..AB0E; ETHIOPIC
6183 0xAB0F, // AB0F..AB10; UNKNOWN
6184 0xAB11, // AB11..AB16; ETHIOPIC
6185 0xAB17, // AB17..AB1F; UNKNOWN
6186 0xAB20, // AB20..AB26; ETHIOPIC
6187 0xAB27, // AB27 ; UNKNOWN
6188 0xAB28, // AB28..AB2E; ETHIOPIC
6189 0xAB2F, // AB2F ; UNKNOWN
6190 0xAB30, // AB30..AB5A; LATIN
6191 0xAB5B, // AB5B ; COMMON
6192 0xAB5C, // AB5C..AB64; LATIN
6193 0xAB65, // AB65 ; GREEK
6194 0xAB66, // AB66..AB69; LATIN
6195 0xAB6A, // AB6A..AB6B; COMMON
6196 0xAB6C, // AB6C..AB6F; UNKNOWN
6197 0xAB70, // AB70..ABBF; CHEROKEE
6198 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6199 0xABEE, // ABEE..ABEF; UNKNOWN
6200 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6201 0xABFA, // ABFA..ABFF; UNKNOWN
6202 0xAC00, // AC00..D7A3; HANGUL
6203 0xD7A4, // D7A4..D7AF; UNKNOWN
6204 0xD7B0, // D7B0..D7C6; HANGUL
6205 0xD7C7, // D7C7..D7CA; UNKNOWN
6206 0xD7CB, // D7CB..D7FB; HANGUL
6207 0xD7FC, // D7FC..F8FF; UNKNOWN
6208 0xF900, // F900..FA6D; HAN
6209 0xFA6E, // FA6E..FA6F; UNKNOWN
6210 0xFA70, // FA70..FAD9; HAN
6211 0xFADA, // FADA..FAFF; UNKNOWN
6212 0xFB00, // FB00..FB06; LATIN
6213 0xFB07, // FB07..FB12; UNKNOWN
6214 0xFB13, // FB13..FB17; ARMENIAN
6215 0xFB18, // FB18..FB1C; UNKNOWN
6216 0xFB1D, // FB1D..FB36; HEBREW
6217 0xFB37, // FB37 ; UNKNOWN
6218 0xFB38, // FB38..FB3C; HEBREW
6219 0xFB3D, // FB3D ; UNKNOWN
6220 0xFB3E, // FB3E ; HEBREW
6221 0xFB3F, // FB3F ; UNKNOWN
6222 0xFB40, // FB40..FB41; HEBREW
6223 0xFB42, // FB42 ; UNKNOWN
6224 0xFB43, // FB43..FB44; HEBREW
6225 0xFB45, // FB45 ; UNKNOWN
6226 0xFB46, // FB46..FB4F; HEBREW
6227 0xFB50, // FB50..FBC2; ARABIC
6228 0xFBC3, // FBC3..FBD2; UNKNOWN
6229 0xFBD3, // FBD3..FD3D; ARABIC
6230 0xFD3E, // FD3E..FD3F; COMMON
6231 0xFD40, // FD40..FD8F; ARABIC
6232 0xFD90, // FD90..FD91; UNKNOWN
6233 0xFD92, // FD92..FDC7; ARABIC
6234 0xFDC8, // FDC8..FDCE; UNKNOWN
6235 0xFDCF, // FDCF ; ARABIC
6236 0xFDD0, // FDD0..FDEF; UNKNOWN
6237 0xFDF0, // FDF0..FDFF; ARABIC
6238 0xFE00, // FE00..FE0F; INHERITED
6239 0xFE10, // FE10..FE19; COMMON
6240 0xFE1A, // FE1A..FE1F; UNKNOWN
6241 0xFE20, // FE20..FE2D; INHERITED
6242 0xFE2E, // FE2E..FE2F; CYRILLIC
6243 0xFE30, // FE30..FE52; COMMON
6244 0xFE53, // FE53 ; UNKNOWN
6245 0xFE54, // FE54..FE66; COMMON
6246 0xFE67, // FE67 ; UNKNOWN
6247 0xFE68, // FE68..FE6B; COMMON
6248 0xFE6C, // FE6C..FE6F; UNKNOWN
6249 0xFE70, // FE70..FE74; ARABIC
6250 0xFE75, // FE75 ; UNKNOWN
6251 0xFE76, // FE76..FEFC; ARABIC
6252 0xFEFD, // FEFD..FEFE; UNKNOWN
6253 0xFEFF, // FEFF ; COMMON
6254 0xFF00, // FF00 ; UNKNOWN
6255 0xFF01, // FF01..FF20; COMMON
6256 0xFF21, // FF21..FF3A; LATIN
6257 0xFF3B, // FF3B..FF40; COMMON
6258 0xFF41, // FF41..FF5A; LATIN
6259 0xFF5B, // FF5B..FF65; COMMON
6260 0xFF66, // FF66..FF6F; KATAKANA
6261 0xFF70, // FF70 ; COMMON
6262 0xFF71, // FF71..FF9D; KATAKANA
6263 0xFF9E, // FF9E..FF9F; COMMON
6264 0xFFA0, // FFA0..FFBE; HANGUL
6265 0xFFBF, // FFBF..FFC1; UNKNOWN
6266 0xFFC2, // FFC2..FFC7; HANGUL
6267 0xFFC8, // FFC8..FFC9; UNKNOWN
6268 0xFFCA, // FFCA..FFCF; HANGUL
6269 0xFFD0, // FFD0..FFD1; UNKNOWN
6270 0xFFD2, // FFD2..FFD7; HANGUL
6271 0xFFD8, // FFD8..FFD9; UNKNOWN
6272 0xFFDA, // FFDA..FFDC; HANGUL
6273 0xFFDD, // FFDD..FFDF; UNKNOWN
6274 0xFFE0, // FFE0..FFE6; COMMON
6275 0xFFE7, // FFE7 ; UNKNOWN
6276 0xFFE8, // FFE8..FFEE; COMMON
6277 0xFFEF, // FFEF..FFF8; UNKNOWN
6278 0xFFF9, // FFF9..FFFD; COMMON
6279 0xFFFE, // FFFE..FFFF; UNKNOWN
6280 0x10000, // 10000..1000B; LINEAR_B
6281 0x1000C, // 1000C ; UNKNOWN
6282 0x1000D, // 1000D..10026; LINEAR_B
6283 0x10027, // 10027 ; UNKNOWN
6284 0x10028, // 10028..1003A; LINEAR_B
6285 0x1003B, // 1003B ; UNKNOWN
6286 0x1003C, // 1003C..1003D; LINEAR_B
6287 0x1003E, // 1003E ; UNKNOWN
6288 0x1003F, // 1003F..1004D; LINEAR_B
6289 0x1004E, // 1004E..1004F; UNKNOWN
6290 0x10050, // 10050..1005D; LINEAR_B
6291 0x1005E, // 1005E..1007F; UNKNOWN
6292 0x10080, // 10080..100FA; LINEAR_B
6293 0x100FB, // 100FB..100FF; UNKNOWN
6294 0x10100, // 10100..10102; COMMON
6295 0x10103, // 10103..10106; UNKNOWN
6296 0x10107, // 10107..10133; COMMON
6297 0x10134, // 10134..10136; UNKNOWN
6298 0x10137, // 10137..1013F; COMMON
6299 0x10140, // 10140..1018E; GREEK
6300 0x1018F, // 1018F ; UNKNOWN
6301 0x10190, // 10190..1019C; COMMON
6302 0x1019D, // 1019D..1019F; UNKNOWN
6303 0x101A0, // 101A0 ; GREEK
6304 0x101A1, // 101A1..101CF; UNKNOWN
6305 0x101D0, // 101D0..101FC; COMMON
6306 0x101FD, // 101FD ; INHERITED
6307 0x101FE, // 101FE..1027F; UNKNOWN
6308 0x10280, // 10280..1029C; LYCIAN
6309 0x1029D, // 1029D..1029F; UNKNOWN
6310 0x102A0, // 102A0..102D0; CARIAN
6311 0x102D1, // 102D1..102DF; UNKNOWN
6312 0x102E0, // 102E0 ; INHERITED
6313 0x102E1, // 102E1..102FB; COMMON
6314 0x102FC, // 102FC..102FF; UNKNOWN
6315 0x10300, // 10300..10323; OLD_ITALIC
6316 0x10324, // 10324..1032C; UNKNOWN
6317 0x1032D, // 1032D..1032F; OLD_ITALIC
6318 0x10330, // 10330..1034A; GOTHIC
6319 0x1034B, // 1034B..1034F; UNKNOWN
6320 0x10350, // 10350..1037A; OLD_PERMIC
6321 0x1037B, // 1037B..1037F; UNKNOWN
6322 0x10380, // 10380..1039D; UGARITIC
6323 0x1039E, // 1039E ; UNKNOWN
6324 0x1039F, // 1039F ; UGARITIC
6325 0x103A0, // 103A0..103C3; OLD_PERSIAN
6326 0x103C4, // 103C4..103C7; UNKNOWN
6327 0x103C8, // 103C8..103D5; OLD_PERSIAN
6328 0x103D6, // 103D6..103FF; UNKNOWN
6329 0x10400, // 10400..1044F; DESERET
6330 0x10450, // 10450..1047F; SHAVIAN
6331 0x10480, // 10480..1049D; OSMANYA
6332 0x1049E, // 1049E..1049F; UNKNOWN
6333 0x104A0, // 104A0..104A9; OSMANYA
6334 0x104AA, // 104AA..104AF; UNKNOWN
6335 0x104B0, // 104B0..104D3; OSAGE
6336 0x104D4, // 104D4..104D7; UNKNOWN
6337 0x104D8, // 104D8..104FB; OSAGE
6338 0x104FC, // 104FC..104FF; UNKNOWN
6339 0x10500, // 10500..10527; ELBASAN
6340 0x10528, // 10528..1052F; UNKNOWN
6341 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6342 0x10564, // 10564..1056E; UNKNOWN
6343 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6344 0x10570, // 10570..1057A; VITHKUQI
6345 0x1057B, // 1057B ; UNKNOWN
6346 0x1057C, // 1057C..1058A; VITHKUQI
6347 0x1058B, // 1058B ; UNKNOWN
6348 0x1058C, // 1058C..10592; VITHKUQI
6349 0x10593, // 10593 ; UNKNOWN
6350 0x10594, // 10594..10595; VITHKUQI
6351 0x10596, // 10596 ; UNKNOWN
6352 0x10597, // 10597..105A1; VITHKUQI
6353 0x105A2, // 105A2 ; UNKNOWN
6354 0x105A3, // 105A3..105B1; VITHKUQI
6355 0x105B2, // 105B2 ; UNKNOWN
6356 0x105B3, // 105B3..105B9; VITHKUQI
6357 0x105BA, // 105BA ; UNKNOWN
6358 0x105BB, // 105BB..105BC; VITHKUQI
6359 0x105BD, // 105BD..105FF; UNKNOWN
6360 0x10600, // 10600..10736; LINEAR_A
6361 0x10737, // 10737..1073F; UNKNOWN
6362 0x10740, // 10740..10755; LINEAR_A
6363 0x10756, // 10756..1075F; UNKNOWN
6364 0x10760, // 10760..10767; LINEAR_A
6365 0x10768, // 10768..1077F; UNKNOWN
6366 0x10780, // 10780..10785; LATIN
6367 0x10786, // 10786 ; UNKNOWN
6368 0x10787, // 10787..107B0; LATIN
6369 0x107B1, // 107B1 ; UNKNOWN
6370 0x107B2, // 107B2..107BA; LATIN
6371 0x107BB, // 107BB..107FF; UNKNOWN
6372 0x10800, // 10800..10805; CYPRIOT
6373 0x10806, // 10806..10807; UNKNOWN
6374 0x10808, // 10808 ; CYPRIOT
6375 0x10809, // 10809 ; UNKNOWN
6376 0x1080A, // 1080A..10835; CYPRIOT
6377 0x10836, // 10836 ; UNKNOWN
6378 0x10837, // 10837..10838; CYPRIOT
6379 0x10839, // 10839..1083B; UNKNOWN
6380 0x1083C, // 1083C ; CYPRIOT
6381 0x1083D, // 1083D..1083E; UNKNOWN
6382 0x1083F, // 1083F ; CYPRIOT
6383 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6384 0x10856, // 10856 ; UNKNOWN
6385 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6386 0x10860, // 10860..1087F; PALMYRENE
6387 0x10880, // 10880..1089E; NABATAEAN
6388 0x1089F, // 1089F..108A6; UNKNOWN
6389 0x108A7, // 108A7..108AF; NABATAEAN
6390 0x108B0, // 108B0..108DF; UNKNOWN
6391 0x108E0, // 108E0..108F2; HATRAN
6392 0x108F3, // 108F3 ; UNKNOWN
6393 0x108F4, // 108F4..108F5; HATRAN
6394 0x108F6, // 108F6..108FA; UNKNOWN
6395 0x108FB, // 108FB..108FF; HATRAN
6396 0x10900, // 10900..1091B; PHOENICIAN
6397 0x1091C, // 1091C..1091E; UNKNOWN
6398 0x1091F, // 1091F ; PHOENICIAN
6399 0x10920, // 10920..10939; LYDIAN
6400 0x1093A, // 1093A..1093E; UNKNOWN
6401 0x1093F, // 1093F ; LYDIAN
6402 0x10940, // 10940..1097F; UNKNOWN
6403 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6404 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6405 0x109B8, // 109B8..109BB; UNKNOWN
6406 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6407 0x109D0, // 109D0..109D1; UNKNOWN
6408 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6409 0x10A00, // 10A00..10A03; KHAROSHTHI
6410 0x10A04, // 10A04 ; UNKNOWN
6411 0x10A05, // 10A05..10A06; KHAROSHTHI
6412 0x10A07, // 10A07..10A0B; UNKNOWN
6413 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6414 0x10A14, // 10A14 ; UNKNOWN
6415 0x10A15, // 10A15..10A17; KHAROSHTHI
6416 0x10A18, // 10A18 ; UNKNOWN
6417 0x10A19, // 10A19..10A35; KHAROSHTHI
6418 0x10A36, // 10A36..10A37; UNKNOWN
6419 0x10A38, // 10A38..10A3A; KHAROSHTHI
6420 0x10A3B, // 10A3B..10A3E; UNKNOWN
6421 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6422 0x10A49, // 10A49..10A4F; UNKNOWN
6423 0x10A50, // 10A50..10A58; KHAROSHTHI
6424 0x10A59, // 10A59..10A5F; UNKNOWN
6425 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6426 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6427 0x10AA0, // 10AA0..10ABF; UNKNOWN
6428 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6429 0x10AE7, // 10AE7..10AEA; UNKNOWN
6430 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6431 0x10AF7, // 10AF7..10AFF; UNKNOWN
6432 0x10B00, // 10B00..10B35; AVESTAN
6433 0x10B36, // 10B36..10B38; UNKNOWN
6434 0x10B39, // 10B39..10B3F; AVESTAN
6435 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6436 0x10B56, // 10B56..10B57; UNKNOWN
6437 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6438 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6439 0x10B73, // 10B73..10B77; UNKNOWN
6440 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6441 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6442 0x10B92, // 10B92..10B98; UNKNOWN
6443 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6444 0x10B9D, // 10B9D..10BA8; UNKNOWN
6445 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6446 0x10BB0, // 10BB0..10BFF; UNKNOWN
6447 0x10C00, // 10C00..10C48; OLD_TURKIC
6448 0x10C49, // 10C49..10C7F; UNKNOWN
6449 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6450 0x10CB3, // 10CB3..10CBF; UNKNOWN
6451 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6452 0x10CF3, // 10CF3..10CF9; UNKNOWN
6453 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6454 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6455 0x10D28, // 10D28..10D2F; UNKNOWN
6456 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6457 0x10D3A, // 10D3A..10E5F; UNKNOWN
6458 0x10E60, // 10E60..10E7E; ARABIC
6459 0x10E7F, // 10E7F ; UNKNOWN
6460 0x10E80, // 10E80..10EA9; YEZIDI
6461 0x10EAA, // 10EAA ; UNKNOWN
6462 0x10EAB, // 10EAB..10EAD; YEZIDI
6463 0x10EAE, // 10EAE..10EAF; UNKNOWN
6464 0x10EB0, // 10EB0..10EB1; YEZIDI
6465 0x10EB2, // 10EB2..10EFC; UNKNOWN
6466 0x10EFD, // 10EFD..10EFF; ARABIC
6467 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6468 0x10F28, // 10F28..10F2F; UNKNOWN
6469 0x10F30, // 10F30..10F59; SOGDIAN
6470 0x10F5A, // 10F5A..10F6F; UNKNOWN
6471 0x10F70, // 10F70..10F89; OLD_UYGHUR
6472 0x10F8A, // 10F8A..10FAF; UNKNOWN
6473 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6474 0x10FCC, // 10FCC..10FDF; UNKNOWN
6475 0x10FE0, // 10FE0..10FF6; ELYMAIC
6476 0x10FF7, // 10FF7..10FFF; UNKNOWN
6477 0x11000, // 11000..1104D; BRAHMI
6478 0x1104E, // 1104E..11051; UNKNOWN
6479 0x11052, // 11052..11075; BRAHMI
6480 0x11076, // 11076..1107E; UNKNOWN
6481 0x1107F, // 1107F ; BRAHMI
6482 0x11080, // 11080..110C2; KAITHI
6483 0x110C3, // 110C3..110CC; UNKNOWN
6484 0x110CD, // 110CD ; KAITHI
6485 0x110CE, // 110CE..110CF; UNKNOWN
6486 0x110D0, // 110D0..110E8; SORA_SOMPENG
6487 0x110E9, // 110E9..110EF; UNKNOWN
6488 0x110F0, // 110F0..110F9; SORA_SOMPENG
6489 0x110FA, // 110FA..110FF; UNKNOWN
6490 0x11100, // 11100..11134; CHAKMA
6491 0x11135, // 11135 ; UNKNOWN
6492 0x11136, // 11136..11147; CHAKMA
6493 0x11148, // 11148..1114F; UNKNOWN
6494 0x11150, // 11150..11176; MAHAJANI
6495 0x11177, // 11177..1117F; UNKNOWN
6496 0x11180, // 11180..111DF; SHARADA
6497 0x111E0, // 111E0 ; UNKNOWN
6498 0x111E1, // 111E1..111F4; SINHALA
6499 0x111F5, // 111F5..111FF; UNKNOWN
6500 0x11200, // 11200..11211; KHOJKI
6501 0x11212, // 11212 ; UNKNOWN
6502 0x11213, // 11213..11241; KHOJKI
6503 0x11242, // 11242..1127F; UNKNOWN
6504 0x11280, // 11280..11286; MULTANI
6505 0x11287, // 11287 ; UNKNOWN
6506 0x11288, // 11288 ; MULTANI
6507 0x11289, // 11289 ; UNKNOWN
6508 0x1128A, // 1128A..1128D; MULTANI
6509 0x1128E, // 1128E ; UNKNOWN
6510 0x1128F, // 1128F..1129D; MULTANI
6511 0x1129E, // 1129E ; UNKNOWN
6512 0x1129F, // 1129F..112A9; MULTANI
6513 0x112AA, // 112AA..112AF; UNKNOWN
6514 0x112B0, // 112B0..112EA; KHUDAWADI
6515 0x112EB, // 112EB..112EF; UNKNOWN
6516 0x112F0, // 112F0..112F9; KHUDAWADI
6517 0x112FA, // 112FA..112FF; UNKNOWN
6518 0x11300, // 11300..11303; GRANTHA
6519 0x11304, // 11304 ; UNKNOWN
6520 0x11305, // 11305..1130C; GRANTHA
6521 0x1130D, // 1130D..1130E; UNKNOWN
6522 0x1130F, // 1130F..11310; GRANTHA
6523 0x11311, // 11311..11312; UNKNOWN
6524 0x11313, // 11313..11328; GRANTHA
6525 0x11329, // 11329 ; UNKNOWN
6526 0x1132A, // 1132A..11330; GRANTHA
6527 0x11331, // 11331 ; UNKNOWN
6528 0x11332, // 11332..11333; GRANTHA
6529 0x11334, // 11334 ; UNKNOWN
6530 0x11335, // 11335..11339; GRANTHA
6531 0x1133A, // 1133A ; UNKNOWN
6532 0x1133B, // 1133B ; INHERITED
6533 0x1133C, // 1133C..11344; GRANTHA
6534 0x11345, // 11345..11346; UNKNOWN
6535 0x11347, // 11347..11348; GRANTHA
6536 0x11349, // 11349..1134A; UNKNOWN
6537 0x1134B, // 1134B..1134D; GRANTHA
6538 0x1134E, // 1134E..1134F; UNKNOWN
6539 0x11350, // 11350 ; GRANTHA
6540 0x11351, // 11351..11356; UNKNOWN
6541 0x11357, // 11357 ; GRANTHA
6542 0x11358, // 11358..1135C; UNKNOWN
6543 0x1135D, // 1135D..11363; GRANTHA
6544 0x11364, // 11364..11365; UNKNOWN
6545 0x11366, // 11366..1136C; GRANTHA
6546 0x1136D, // 1136D..1136F; UNKNOWN
6547 0x11370, // 11370..11374; GRANTHA
6548 0x11375, // 11375..113FF; UNKNOWN
6549 0x11400, // 11400..1145B; NEWA
6550 0x1145C, // 1145C ; UNKNOWN
6551 0x1145D, // 1145D..11461; NEWA
6552 0x11462, // 11462..1147F; UNKNOWN
6553 0x11480, // 11480..114C7; TIRHUTA
6554 0x114C8, // 114C8..114CF; UNKNOWN
6555 0x114D0, // 114D0..114D9; TIRHUTA
6556 0x114DA, // 114DA..1157F; UNKNOWN
6557 0x11580, // 11580..115B5; SIDDHAM
6558 0x115B6, // 115B6..115B7; UNKNOWN
6559 0x115B8, // 115B8..115DD; SIDDHAM
6560 0x115DE, // 115DE..115FF; UNKNOWN
6561 0x11600, // 11600..11644; MODI
6562 0x11645, // 11645..1164F; UNKNOWN
6563 0x11650, // 11650..11659; MODI
6564 0x1165A, // 1165A..1165F; UNKNOWN
6565 0x11660, // 11660..1166C; MONGOLIAN
6566 0x1166D, // 1166D..1167F; UNKNOWN
6567 0x11680, // 11680..116B9; TAKRI
6568 0x116BA, // 116BA..116BF; UNKNOWN
6569 0x116C0, // 116C0..116C9; TAKRI
6570 0x116CA, // 116CA..116FF; UNKNOWN
6571 0x11700, // 11700..1171A; AHOM
6572 0x1171B, // 1171B..1171C; UNKNOWN
6573 0x1171D, // 1171D..1172B; AHOM
6574 0x1172C, // 1172C..1172F; UNKNOWN
6575 0x11730, // 11730..11746; AHOM
6576 0x11747, // 11747..117FF; UNKNOWN
6577 0x11800, // 11800..1183B; DOGRA
6578 0x1183C, // 1183C..1189F; UNKNOWN
6579 0x118A0, // 118A0..118F2; WARANG_CITI
6580 0x118F3, // 118F3..118FE; UNKNOWN
6581 0x118FF, // 118FF ; WARANG_CITI
6582 0x11900, // 11900..11906; DIVES_AKURU
6583 0x11907, // 11907..11908; UNKNOWN
6584 0x11909, // 11909 ; DIVES_AKURU
6585 0x1190A, // 1190A..1190B; UNKNOWN
6586 0x1190C, // 1190C..11913; DIVES_AKURU
6587 0x11914, // 11914 ; UNKNOWN
6588 0x11915, // 11915..11916; DIVES_AKURU
6589 0x11917, // 11917 ; UNKNOWN
6590 0x11918, // 11918..11935; DIVES_AKURU
6591 0x11936, // 11936 ; UNKNOWN
6592 0x11937, // 11937..11938; DIVES_AKURU
6593 0x11939, // 11939..1193A; UNKNOWN
6594 0x1193B, // 1193B..11946; DIVES_AKURU
6595 0x11947, // 11947..1194F; UNKNOWN
6596 0x11950, // 11950..11959; DIVES_AKURU
6597 0x1195A, // 1195A..1199F; UNKNOWN
6598 0x119A0, // 119A0..119A7; NANDINAGARI
6599 0x119A8, // 119A8..119A9; UNKNOWN
6600 0x119AA, // 119AA..119D7; NANDINAGARI
6601 0x119D8, // 119D8..119D9; UNKNOWN
6602 0x119DA, // 119DA..119E4; NANDINAGARI
6603 0x119E5, // 119E5..119FF; UNKNOWN
6604 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6605 0x11A48, // 11A48..11A4F; UNKNOWN
6606 0x11A50, // 11A50..11AA2; SOYOMBO
6607 0x11AA3, // 11AA3..11AAF; UNKNOWN
6608 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6609 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6610 0x11AF9, // 11AF9..11AFF; UNKNOWN
6611 0x11B00, // 11B00..11B09; DEVANAGARI
6612 0x11B0A, // 11B0A..11BFF; UNKNOWN
6613 0x11C00, // 11C00..11C08; BHAIKSUKI
6614 0x11C09, // 11C09 ; UNKNOWN
6615 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6616 0x11C37, // 11C37 ; UNKNOWN
6617 0x11C38, // 11C38..11C45; BHAIKSUKI
6618 0x11C46, // 11C46..11C4F; UNKNOWN
6619 0x11C50, // 11C50..11C6C; BHAIKSUKI
6620 0x11C6D, // 11C6D..11C6F; UNKNOWN
6621 0x11C70, // 11C70..11C8F; MARCHEN
6622 0x11C90, // 11C90..11C91; UNKNOWN
6623 0x11C92, // 11C92..11CA7; MARCHEN
6624 0x11CA8, // 11CA8 ; UNKNOWN
6625 0x11CA9, // 11CA9..11CB6; MARCHEN
6626 0x11CB7, // 11CB7..11CFF; UNKNOWN
6627 0x11D00, // 11D00..11D06; MASARAM_GONDI
6628 0x11D07, // 11D07 ; UNKNOWN
6629 0x11D08, // 11D08..11D09; MASARAM_GONDI
6630 0x11D0A, // 11D0A ; UNKNOWN
6631 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6632 0x11D37, // 11D37..11D39; UNKNOWN
6633 0x11D3A, // 11D3A ; MASARAM_GONDI
6634 0x11D3B, // 11D3B ; UNKNOWN
6635 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6636 0x11D3E, // 11D3E ; UNKNOWN
6637 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6638 0x11D48, // 11D48..11D4F; UNKNOWN
6639 0x11D50, // 11D50..11D59; MASARAM_GONDI
6640 0x11D5A, // 11D5A..11D5F; UNKNOWN
6641 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6642 0x11D66, // 11D66 ; UNKNOWN
6643 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6644 0x11D69, // 11D69 ; UNKNOWN
6645 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6646 0x11D8F, // 11D8F ; UNKNOWN
6647 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6648 0x11D92, // 11D92 ; UNKNOWN
6649 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6650 0x11D99, // 11D99..11D9F; UNKNOWN
6651 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6652 0x11DAA, // 11DAA..11EDF; UNKNOWN
6653 0x11EE0, // 11EE0..11EF8; MAKASAR
6654 0x11EF9, // 11EF9..11EFF; UNKNOWN
6655 0x11F00, // 11F00..11F10; KAWI
6656 0x11F11, // 11F11 ; UNKNOWN
6657 0x11F12, // 11F12..11F3A; KAWI
6658 0x11F3B, // 11F3B..11F3D; UNKNOWN
6659 0x11F3E, // 11F3E..11F59; KAWI
6660 0x11F5A, // 11F5A..11FAF; UNKNOWN
6661 0x11FB0, // 11FB0 ; LISU
6662 0x11FB1, // 11FB1..11FBF; UNKNOWN
6663 0x11FC0, // 11FC0..11FF1; TAMIL
6664 0x11FF2, // 11FF2..11FFE; UNKNOWN
6665 0x11FFF, // 11FFF ; TAMIL
6666 0x12000, // 12000..12399; CUNEIFORM
6667 0x1239A, // 1239A..123FF; UNKNOWN
6668 0x12400, // 12400..1246E; CUNEIFORM
6669 0x1246F, // 1246F ; UNKNOWN
6670 0x12470, // 12470..12474; CUNEIFORM
6671 0x12475, // 12475..1247F; UNKNOWN
6672 0x12480, // 12480..12543; CUNEIFORM
6673 0x12544, // 12544..12F8F; UNKNOWN
6674 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6675 0x12FF3, // 12FF3..12FFF; UNKNOWN
6676 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6677 0x13456, // 13456..143FF; UNKNOWN
6678 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6679 0x14647, // 14647..167FF; UNKNOWN
6680 0x16800, // 16800..16A38; BAMUM
6681 0x16A39, // 16A39..16A3F; UNKNOWN
6682 0x16A40, // 16A40..16A5E; MRO
6683 0x16A5F, // 16A5F ; UNKNOWN
6684 0x16A60, // 16A60..16A69; MRO
6685 0x16A6A, // 16A6A..16A6D; UNKNOWN
6686 0x16A6E, // 16A6E..16A6F; MRO
6687 0x16A70, // 16A70..16ABE; TANGSA
6688 0x16ABF, // 16ABF ; UNKNOWN
6689 0x16AC0, // 16AC0..16AC9; TANGSA
6690 0x16ACA, // 16ACA..16ACF; UNKNOWN
6691 0x16AD0, // 16AD0..16AED; BASSA_VAH
6692 0x16AEE, // 16AEE..16AEF; UNKNOWN
6693 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6694 0x16AF6, // 16AF6..16AFF; UNKNOWN
6695 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6696 0x16B46, // 16B46..16B4F; UNKNOWN
6697 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6698 0x16B5A, // 16B5A ; UNKNOWN
6699 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6700 0x16B62, // 16B62 ; UNKNOWN
6701 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6702 0x16B78, // 16B78..16B7C; UNKNOWN
6703 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6704 0x16B90, // 16B90..16E3F; UNKNOWN
6705 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6706 0x16E9B, // 16E9B..16EFF; UNKNOWN
6707 0x16F00, // 16F00..16F4A; MIAO
6708 0x16F4B, // 16F4B..16F4E; UNKNOWN
6709 0x16F4F, // 16F4F..16F87; MIAO
6710 0x16F88, // 16F88..16F8E; UNKNOWN
6711 0x16F8F, // 16F8F..16F9F; MIAO
6712 0x16FA0, // 16FA0..16FDF; UNKNOWN
6713 0x16FE0, // 16FE0 ; TANGUT
6714 0x16FE1, // 16FE1 ; NUSHU
6715 0x16FE2, // 16FE2..16FE3; HAN
6716 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
6717 0x16FE5, // 16FE5..16FEF; UNKNOWN
6718 0x16FF0, // 16FF0..16FF1; HAN
6719 0x16FF2, // 16FF2..16FFF; UNKNOWN
6720 0x17000, // 17000..187F7; TANGUT
6721 0x187F8, // 187F8..187FF; UNKNOWN
6722 0x18800, // 18800..18AFF; TANGUT
6723 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
6724 0x18CD6, // 18CD6..18CFF; UNKNOWN
6725 0x18D00, // 18D00..18D08; TANGUT
6726 0x18D09, // 18D09..1AFEF; UNKNOWN
6727 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
6728 0x1AFF4, // 1AFF4 ; UNKNOWN
6729 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
6730 0x1AFFC, // 1AFFC ; UNKNOWN
6731 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
6732 0x1AFFF, // 1AFFF ; UNKNOWN
6733 0x1B000, // 1B000 ; KATAKANA
6734 0x1B001, // 1B001..1B11F; HIRAGANA
6735 0x1B120, // 1B120..1B122; KATAKANA
6736 0x1B123, // 1B123..1B131; UNKNOWN
6737 0x1B132, // 1B132 ; HIRAGANA
6738 0x1B133, // 1B133..1B14F; UNKNOWN
6739 0x1B150, // 1B150..1B152; HIRAGANA
6740 0x1B153, // 1B153..1B154; UNKNOWN
6741 0x1B155, // 1B155 ; KATAKANA
6742 0x1B156, // 1B156..1B163; UNKNOWN
6743 0x1B164, // 1B164..1B167; KATAKANA
6744 0x1B168, // 1B168..1B16F; UNKNOWN
6745 0x1B170, // 1B170..1B2FB; NUSHU
6746 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6747 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6748 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6749 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6750 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6751 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6752 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6753 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6754 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6755 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6756 0x1BCA0, // 1BCA0..1BCA3; COMMON
6757 0x1BCA4, // 1BCA4..1CEFF; UNKNOWN
6758 0x1CF00, // 1CF00..1CF2D; INHERITED
6759 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
6760 0x1CF30, // 1CF30..1CF46; INHERITED
6761 0x1CF47, // 1CF47..1CF4F; UNKNOWN
6762 0x1CF50, // 1CF50..1CFC3; COMMON
6763 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
6764 0x1D000, // 1D000..1D0F5; COMMON
6765 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6766 0x1D100, // 1D100..1D126; COMMON
6767 0x1D127, // 1D127..1D128; UNKNOWN
6768 0x1D129, // 1D129..1D166; COMMON
6769 0x1D167, // 1D167..1D169; INHERITED
6770 0x1D16A, // 1D16A..1D17A; COMMON
6771 0x1D17B, // 1D17B..1D182; INHERITED
6772 0x1D183, // 1D183..1D184; COMMON
6773 0x1D185, // 1D185..1D18B; INHERITED
6774 0x1D18C, // 1D18C..1D1A9; COMMON
6775 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6776 0x1D1AE, // 1D1AE..1D1EA; COMMON
6777 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
6778 0x1D200, // 1D200..1D245; GREEK
6779 0x1D246, // 1D246..1D2BF; UNKNOWN
6780 0x1D2C0, // 1D2C0..1D2D3; COMMON
6781 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
6782 0x1D2E0, // 1D2E0..1D2F3; COMMON
6783 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6784 0x1D300, // 1D300..1D356; COMMON
6785 0x1D357, // 1D357..1D35F; UNKNOWN
6786 0x1D360, // 1D360..1D378; COMMON
6787 0x1D379, // 1D379..1D3FF; UNKNOWN
6788 0x1D400, // 1D400..1D454; COMMON
6789 0x1D455, // 1D455 ; UNKNOWN
6790 0x1D456, // 1D456..1D49C; COMMON
6791 0x1D49D, // 1D49D ; UNKNOWN
6792 0x1D49E, // 1D49E..1D49F; COMMON
6793 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
6794 0x1D4A2, // 1D4A2 ; COMMON
6795 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
6796 0x1D4A5, // 1D4A5..1D4A6; COMMON
6797 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
6798 0x1D4A9, // 1D4A9..1D4AC; COMMON
6799 0x1D4AD, // 1D4AD ; UNKNOWN
6800 0x1D4AE, // 1D4AE..1D4B9; COMMON
6801 0x1D4BA, // 1D4BA ; UNKNOWN
6802 0x1D4BB, // 1D4BB ; COMMON
6803 0x1D4BC, // 1D4BC ; UNKNOWN
6804 0x1D4BD, // 1D4BD..1D4C3; COMMON
6805 0x1D4C4, // 1D4C4 ; UNKNOWN
6806 0x1D4C5, // 1D4C5..1D505; COMMON
6807 0x1D506, // 1D506 ; UNKNOWN
6808 0x1D507, // 1D507..1D50A; COMMON
6809 0x1D50B, // 1D50B..1D50C; UNKNOWN
6810 0x1D50D, // 1D50D..1D514; COMMON
6811 0x1D515, // 1D515 ; UNKNOWN
6812 0x1D516, // 1D516..1D51C; COMMON
6813 0x1D51D, // 1D51D ; UNKNOWN
6814 0x1D51E, // 1D51E..1D539; COMMON
6815 0x1D53A, // 1D53A ; UNKNOWN
6816 0x1D53B, // 1D53B..1D53E; COMMON
6817 0x1D53F, // 1D53F ; UNKNOWN
6818 0x1D540, // 1D540..1D544; COMMON
6819 0x1D545, // 1D545 ; UNKNOWN
6820 0x1D546, // 1D546 ; COMMON
6821 0x1D547, // 1D547..1D549; UNKNOWN
6822 0x1D54A, // 1D54A..1D550; COMMON
6823 0x1D551, // 1D551 ; UNKNOWN
6824 0x1D552, // 1D552..1D6A5; COMMON
6825 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
6826 0x1D6A8, // 1D6A8..1D7CB; COMMON
6827 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
6828 0x1D7CE, // 1D7CE..1D7FF; COMMON
6829 0x1D800, // 1D800..1DA8B; SIGNWRITING
6830 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
6831 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
6832 0x1DAA0, // 1DAA0 ; UNKNOWN
6833 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
6834 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
6835 0x1DF00, // 1DF00..1DF1E; LATIN
6836 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
6837 0x1DF25, // 1DF25..1DF2A; LATIN
6838 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
6839 0x1E000, // 1E000..1E006; GLAGOLITIC
6840 0x1E007, // 1E007 ; UNKNOWN
6841 0x1E008, // 1E008..1E018; GLAGOLITIC
6842 0x1E019, // 1E019..1E01A; UNKNOWN
6843 0x1E01B, // 1E01B..1E021; GLAGOLITIC
6844 0x1E022, // 1E022 ; UNKNOWN
6845 0x1E023, // 1E023..1E024; GLAGOLITIC
6846 0x1E025, // 1E025 ; UNKNOWN
6847 0x1E026, // 1E026..1E02A; GLAGOLITIC
6848 0x1E02B, // 1E02B..1E02F; UNKNOWN
6849 0x1E030, // 1E030..1E06D; CYRILLIC
6850 0x1E06E, // 1E06E..1E08E; UNKNOWN
6851 0x1E08F, // 1E08F ; CYRILLIC
6852 0x1E090, // 1E090..1E0FF; UNKNOWN
6853 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
6854 0x1E12D, // 1E12D..1E12F; UNKNOWN
6855 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
6856 0x1E13E, // 1E13E..1E13F; UNKNOWN
6857 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
6858 0x1E14A, // 1E14A..1E14D; UNKNOWN
6859 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
6860 0x1E150, // 1E150..1E28F; UNKNOWN
6861 0x1E290, // 1E290..1E2AE; TOTO
6862 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
6863 0x1E2C0, // 1E2C0..1E2F9; WANCHO
6864 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
6865 0x1E2FF, // 1E2FF ; WANCHO
6866 0x1E300, // 1E300..1E4CF; UNKNOWN
6867 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
6868 0x1E4FA, // 1E4FA..1E7DF; UNKNOWN
6869 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
6870 0x1E7E7, // 1E7E7 ; UNKNOWN
6871 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
6872 0x1E7EC, // 1E7EC ; UNKNOWN
6873 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
6874 0x1E7EF, // 1E7EF ; UNKNOWN
6875 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
6876 0x1E7FF, // 1E7FF ; UNKNOWN
6877 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
6878 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
6879 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
6880 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
6881 0x1E900, // 1E900..1E94B; ADLAM
6882 0x1E94C, // 1E94C..1E94F; UNKNOWN
6883 0x1E950, // 1E950..1E959; ADLAM
6884 0x1E95A, // 1E95A..1E95D; UNKNOWN
6885 0x1E95E, // 1E95E..1E95F; ADLAM
6886 0x1E960, // 1E960..1EC70; UNKNOWN
6887 0x1EC71, // 1EC71..1ECB4; COMMON
6888 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
6889 0x1ED01, // 1ED01..1ED3D; COMMON
6890 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
6891 0x1EE00, // 1EE00..1EE03; ARABIC
6892 0x1EE04, // 1EE04 ; UNKNOWN
6893 0x1EE05, // 1EE05..1EE1F; ARABIC
6894 0x1EE20, // 1EE20 ; UNKNOWN
6895 0x1EE21, // 1EE21..1EE22; ARABIC
6896 0x1EE23, // 1EE23 ; UNKNOWN
6897 0x1EE24, // 1EE24 ; ARABIC
6898 0x1EE25, // 1EE25..1EE26; UNKNOWN
6899 0x1EE27, // 1EE27 ; ARABIC
6900 0x1EE28, // 1EE28 ; UNKNOWN
6901 0x1EE29, // 1EE29..1EE32; ARABIC
6902 0x1EE33, // 1EE33 ; UNKNOWN
6903 0x1EE34, // 1EE34..1EE37; ARABIC
6904 0x1EE38, // 1EE38 ; UNKNOWN
6905 0x1EE39, // 1EE39 ; ARABIC
6906 0x1EE3A, // 1EE3A ; UNKNOWN
6907 0x1EE3B, // 1EE3B ; ARABIC
6908 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
6909 0x1EE42, // 1EE42 ; ARABIC
6910 0x1EE43, // 1EE43..1EE46; UNKNOWN
6911 0x1EE47, // 1EE47 ; ARABIC
6912 0x1EE48, // 1EE48 ; UNKNOWN
6913 0x1EE49, // 1EE49 ; ARABIC
6914 0x1EE4A, // 1EE4A ; UNKNOWN
6915 0x1EE4B, // 1EE4B ; ARABIC
6916 0x1EE4C, // 1EE4C ; UNKNOWN
6917 0x1EE4D, // 1EE4D..1EE4F; ARABIC
6918 0x1EE50, // 1EE50 ; UNKNOWN
6919 0x1EE51, // 1EE51..1EE52; ARABIC
6920 0x1EE53, // 1EE53 ; UNKNOWN
6921 0x1EE54, // 1EE54 ; ARABIC
6922 0x1EE55, // 1EE55..1EE56; UNKNOWN
6923 0x1EE57, // 1EE57 ; ARABIC
6924 0x1EE58, // 1EE58 ; UNKNOWN
6925 0x1EE59, // 1EE59 ; ARABIC
6926 0x1EE5A, // 1EE5A ; UNKNOWN
6927 0x1EE5B, // 1EE5B ; ARABIC
6928 0x1EE5C, // 1EE5C ; UNKNOWN
6929 0x1EE5D, // 1EE5D ; ARABIC
6930 0x1EE5E, // 1EE5E ; UNKNOWN
6931 0x1EE5F, // 1EE5F ; ARABIC
6932 0x1EE60, // 1EE60 ; UNKNOWN
6933 0x1EE61, // 1EE61..1EE62; ARABIC
6934 0x1EE63, // 1EE63 ; UNKNOWN
6935 0x1EE64, // 1EE64 ; ARABIC
6936 0x1EE65, // 1EE65..1EE66; UNKNOWN
6937 0x1EE67, // 1EE67..1EE6A; ARABIC
6938 0x1EE6B, // 1EE6B ; UNKNOWN
6939 0x1EE6C, // 1EE6C..1EE72; ARABIC
6940 0x1EE73, // 1EE73 ; UNKNOWN
6941 0x1EE74, // 1EE74..1EE77; ARABIC
6942 0x1EE78, // 1EE78 ; UNKNOWN
6943 0x1EE79, // 1EE79..1EE7C; ARABIC
6944 0x1EE7D, // 1EE7D ; UNKNOWN
6945 0x1EE7E, // 1EE7E ; ARABIC
6946 0x1EE7F, // 1EE7F ; UNKNOWN
6947 0x1EE80, // 1EE80..1EE89; ARABIC
6948 0x1EE8A, // 1EE8A ; UNKNOWN
6949 0x1EE8B, // 1EE8B..1EE9B; ARABIC
6950 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
6951 0x1EEA1, // 1EEA1..1EEA3; ARABIC
6952 0x1EEA4, // 1EEA4 ; UNKNOWN
6953 0x1EEA5, // 1EEA5..1EEA9; ARABIC
6954 0x1EEAA, // 1EEAA ; UNKNOWN
6955 0x1EEAB, // 1EEAB..1EEBB; ARABIC
6956 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
6957 0x1EEF0, // 1EEF0..1EEF1; ARABIC
6958 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
6959 0x1F000, // 1F000..1F02B; COMMON
6960 0x1F02C, // 1F02C..1F02F; UNKNOWN
6961 0x1F030, // 1F030..1F093; COMMON
6962 0x1F094, // 1F094..1F09F; UNKNOWN
6963 0x1F0A0, // 1F0A0..1F0AE; COMMON
6964 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
6965 0x1F0B1, // 1F0B1..1F0BF; COMMON
6966 0x1F0C0, // 1F0C0 ; UNKNOWN
6967 0x1F0C1, // 1F0C1..1F0CF; COMMON
6968 0x1F0D0, // 1F0D0 ; UNKNOWN
6969 0x1F0D1, // 1F0D1..1F0F5; COMMON
6970 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
6971 0x1F100, // 1F100..1F1AD; COMMON
6972 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
6973 0x1F1E6, // 1F1E6..1F1FF; COMMON
6974 0x1F200, // 1F200 ; HIRAGANA
6975 0x1F201, // 1F201..1F202; COMMON
6976 0x1F203, // 1F203..1F20F; UNKNOWN
6977 0x1F210, // 1F210..1F23B; COMMON
6978 0x1F23C, // 1F23C..1F23F; UNKNOWN
6979 0x1F240, // 1F240..1F248; COMMON
6980 0x1F249, // 1F249..1F24F; UNKNOWN
6981 0x1F250, // 1F250..1F251; COMMON
6982 0x1F252, // 1F252..1F25F; UNKNOWN
6983 0x1F260, // 1F260..1F265; COMMON
6984 0x1F266, // 1F266..1F2FF; UNKNOWN
6985 0x1F300, // 1F300..1F6D7; COMMON
6986 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN
6987 0x1F6DC, // 1F6DC..1F6EC; COMMON
6988 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
6989 0x1F6F0, // 1F6F0..1F6FC; COMMON
6990 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
6991 0x1F700, // 1F700..1F776; COMMON
6992 0x1F777, // 1F777..1F77A; UNKNOWN
6993 0x1F77B, // 1F77B..1F7D9; COMMON
6994 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
6995 0x1F7E0, // 1F7E0..1F7EB; COMMON
6996 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
6997 0x1F7F0, // 1F7F0 ; COMMON
6998 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
6999 0x1F800, // 1F800..1F80B; COMMON
7000 0x1F80C, // 1F80C..1F80F; UNKNOWN
7001 0x1F810, // 1F810..1F847; COMMON
7002 0x1F848, // 1F848..1F84F; UNKNOWN
7003 0x1F850, // 1F850..1F859; COMMON
7004 0x1F85A, // 1F85A..1F85F; UNKNOWN
7005 0x1F860, // 1F860..1F887; COMMON
7006 0x1F888, // 1F888..1F88F; UNKNOWN
7007 0x1F890, // 1F890..1F8AD; COMMON
7008 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7009 0x1F8B0, // 1F8B0..1F8B1; COMMON
7010 0x1F8B2, // 1F8B2..1F8FF; UNKNOWN
7011 0x1F900, // 1F900..1FA53; COMMON
7012 0x1FA54, // 1FA54..1FA5F; UNKNOWN
7013 0x1FA60, // 1FA60..1FA6D; COMMON
7014 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7015 0x1FA70, // 1FA70..1FA7C; COMMON
7016 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7017 0x1FA80, // 1FA80..1FA88; COMMON
7018 0x1FA89, // 1FA89..1FA8F; UNKNOWN
7019 0x1FA90, // 1FA90..1FABD; COMMON
7020 0x1FABE, // 1FABE ; UNKNOWN
7021 0x1FABF, // 1FABF..1FAC5; COMMON
7022 0x1FAC6, // 1FAC6..1FACD; UNKNOWN
7023 0x1FACE, // 1FACE..1FADB; COMMON
7024 0x1FADC, // 1FADC..1FADF; UNKNOWN
7025 0x1FAE0, // 1FAE0..1FAE8; COMMON
7026 0x1FAE9, // 1FAE9..1FAEF; UNKNOWN
7027 0x1FAF0, // 1FAF0..1FAF8; COMMON
7028 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7029 0x1FB00, // 1FB00..1FB92; COMMON
7030 0x1FB93, // 1FB93 ; UNKNOWN
7031 0x1FB94, // 1FB94..1FBCA; COMMON
7032 0x1FBCB, // 1FBCB..1FBEF; UNKNOWN
7033 0x1FBF0, // 1FBF0..1FBF9; COMMON
7034 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN
7035 0x20000, // 20000..2A6DF; HAN
7036 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7037 0x2A700, // 2A700..2B739; HAN
7038 0x2B73A, // 2B73A..2B73F; UNKNOWN
7039 0x2B740, // 2B740..2B81D; HAN
7040 0x2B81E, // 2B81E..2B81F; UNKNOWN
7041 0x2B820, // 2B820..2CEA1; HAN
7042 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
7043 0x2CEB0, // 2CEB0..2EBE0; HAN
7044 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7045 0x2EBF0, // 2EBF0..2EE5D; HAN
7046 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7047 0x2F800, // 2F800..2FA1D; HAN
7048 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7049 0x30000, // 30000..3134A; HAN
7050 0x3134B, // 3134B..3134F; UNKNOWN
7051 0x31350, // 31350..323AF; HAN
7052 0x323B0, // 323B0..E0000; UNKNOWN
7053 0xE0001, // E0001 ; COMMON
7054 0xE0002, // E0002..E001F; UNKNOWN
7055 0xE0020, // E0020..E007F; COMMON
7056 0xE0080, // E0080..E00FF; UNKNOWN
7057 0xE0100, // E0100..E01EF; INHERITED
7058 0xE01F0, // E01F0..10FFFF; UNKNOWN
7059 };
7060
7061 private static final UnicodeScript[] scripts = {
7062 COMMON, // 0000..0040
7063 LATIN, // 0041..005A
7064 COMMON, // 005B..0060
7065 LATIN, // 0061..007A
7066 COMMON, // 007B..00A9
7067 LATIN, // 00AA
7068 COMMON, // 00AB..00B9
7069 LATIN, // 00BA
7070 COMMON, // 00BB..00BF
7071 LATIN, // 00C0..00D6
7072 COMMON, // 00D7
7073 LATIN, // 00D8..00F6
7074 COMMON, // 00F7
7075 LATIN, // 00F8..02B8
7076 COMMON, // 02B9..02DF
7077 LATIN, // 02E0..02E4
7078 COMMON, // 02E5..02E9
7079 BOPOMOFO, // 02EA..02EB
7080 COMMON, // 02EC..02FF
7081 INHERITED, // 0300..036F
7082 GREEK, // 0370..0373
7083 COMMON, // 0374
7084 GREEK, // 0375..0377
7085 UNKNOWN, // 0378..0379
7086 GREEK, // 037A..037D
7087 COMMON, // 037E
7088 GREEK, // 037F
7089 UNKNOWN, // 0380..0383
7090 GREEK, // 0384
7091 COMMON, // 0385
7092 GREEK, // 0386
7093 COMMON, // 0387
7094 GREEK, // 0388..038A
7095 UNKNOWN, // 038B
7096 GREEK, // 038C
7097 UNKNOWN, // 038D
7098 GREEK, // 038E..03A1
7099 UNKNOWN, // 03A2
7100 GREEK, // 03A3..03E1
7101 COPTIC, // 03E2..03EF
7102 GREEK, // 03F0..03FF
7103 CYRILLIC, // 0400..0484
7104 INHERITED, // 0485..0486
7105 CYRILLIC, // 0487..052F
7106 UNKNOWN, // 0530
7107 ARMENIAN, // 0531..0556
7108 UNKNOWN, // 0557..0558
7109 ARMENIAN, // 0559..058A
7110 UNKNOWN, // 058B..058C
7111 ARMENIAN, // 058D..058F
7112 UNKNOWN, // 0590
7113 HEBREW, // 0591..05C7
7114 UNKNOWN, // 05C8..05CF
7115 HEBREW, // 05D0..05EA
7116 UNKNOWN, // 05EB..05EE
7117 HEBREW, // 05EF..05F4
7118 UNKNOWN, // 05F5..05FF
7119 ARABIC, // 0600..0604
7120 COMMON, // 0605
7121 ARABIC, // 0606..060B
7122 COMMON, // 060C
7123 ARABIC, // 060D..061A
7124 COMMON, // 061B
7125 ARABIC, // 061C..061E
7126 COMMON, // 061F
7127 ARABIC, // 0620..063F
7128 COMMON, // 0640
7129 ARABIC, // 0641..064A
7130 INHERITED, // 064B..0655
7131 ARABIC, // 0656..066F
7132 INHERITED, // 0670
7133 ARABIC, // 0671..06DC
7134 COMMON, // 06DD
7135 ARABIC, // 06DE..06FF
7136 SYRIAC, // 0700..070D
7137 UNKNOWN, // 070E
7138 SYRIAC, // 070F..074A
7139 UNKNOWN, // 074B..074C
7140 SYRIAC, // 074D..074F
7141 ARABIC, // 0750..077F
7142 THAANA, // 0780..07B1
7143 UNKNOWN, // 07B2..07BF
7144 NKO, // 07C0..07FA
7145 UNKNOWN, // 07FB..07FC
7146 NKO, // 07FD..07FF
7147 SAMARITAN, // 0800..082D
7148 UNKNOWN, // 082E..082F
7149 SAMARITAN, // 0830..083E
7150 UNKNOWN, // 083F
7151 MANDAIC, // 0840..085B
7152 UNKNOWN, // 085C..085D
7153 MANDAIC, // 085E
7154 UNKNOWN, // 085F
7155 SYRIAC, // 0860..086A
7156 UNKNOWN, // 086B..086F
7157 ARABIC, // 0870..088E
7158 UNKNOWN, // 088F
7159 ARABIC, // 0890..0891
7160 UNKNOWN, // 0892..0897
7161 ARABIC, // 0898..08E1
7162 COMMON, // 08E2
7163 ARABIC, // 08E3..08FF
7164 DEVANAGARI, // 0900..0950
7165 INHERITED, // 0951..0954
7166 DEVANAGARI, // 0955..0963
7167 COMMON, // 0964..0965
7168 DEVANAGARI, // 0966..097F
7169 BENGALI, // 0980..0983
7170 UNKNOWN, // 0984
7171 BENGALI, // 0985..098C
7172 UNKNOWN, // 098D..098E
7173 BENGALI, // 098F..0990
7174 UNKNOWN, // 0991..0992
7175 BENGALI, // 0993..09A8
7176 UNKNOWN, // 09A9
7177 BENGALI, // 09AA..09B0
7178 UNKNOWN, // 09B1
7179 BENGALI, // 09B2
7180 UNKNOWN, // 09B3..09B5
7181 BENGALI, // 09B6..09B9
7182 UNKNOWN, // 09BA..09BB
7183 BENGALI, // 09BC..09C4
7184 UNKNOWN, // 09C5..09C6
7185 BENGALI, // 09C7..09C8
7186 UNKNOWN, // 09C9..09CA
7187 BENGALI, // 09CB..09CE
7188 UNKNOWN, // 09CF..09D6
7189 BENGALI, // 09D7
7190 UNKNOWN, // 09D8..09DB
7191 BENGALI, // 09DC..09DD
7192 UNKNOWN, // 09DE
7193 BENGALI, // 09DF..09E3
7194 UNKNOWN, // 09E4..09E5
7195 BENGALI, // 09E6..09FE
7196 UNKNOWN, // 09FF..0A00
7197 GURMUKHI, // 0A01..0A03
7198 UNKNOWN, // 0A04
7199 GURMUKHI, // 0A05..0A0A
7200 UNKNOWN, // 0A0B..0A0E
7201 GURMUKHI, // 0A0F..0A10
7202 UNKNOWN, // 0A11..0A12
7203 GURMUKHI, // 0A13..0A28
7204 UNKNOWN, // 0A29
7205 GURMUKHI, // 0A2A..0A30
7206 UNKNOWN, // 0A31
7207 GURMUKHI, // 0A32..0A33
7208 UNKNOWN, // 0A34
7209 GURMUKHI, // 0A35..0A36
7210 UNKNOWN, // 0A37
7211 GURMUKHI, // 0A38..0A39
7212 UNKNOWN, // 0A3A..0A3B
7213 GURMUKHI, // 0A3C
7214 UNKNOWN, // 0A3D
7215 GURMUKHI, // 0A3E..0A42
7216 UNKNOWN, // 0A43..0A46
7217 GURMUKHI, // 0A47..0A48
7218 UNKNOWN, // 0A49..0A4A
7219 GURMUKHI, // 0A4B..0A4D
7220 UNKNOWN, // 0A4E..0A50
7221 GURMUKHI, // 0A51
7222 UNKNOWN, // 0A52..0A58
7223 GURMUKHI, // 0A59..0A5C
7224 UNKNOWN, // 0A5D
7225 GURMUKHI, // 0A5E
7226 UNKNOWN, // 0A5F..0A65
7227 GURMUKHI, // 0A66..0A76
7228 UNKNOWN, // 0A77..0A80
7229 GUJARATI, // 0A81..0A83
7230 UNKNOWN, // 0A84
7231 GUJARATI, // 0A85..0A8D
7232 UNKNOWN, // 0A8E
7233 GUJARATI, // 0A8F..0A91
7234 UNKNOWN, // 0A92
7235 GUJARATI, // 0A93..0AA8
7236 UNKNOWN, // 0AA9
7237 GUJARATI, // 0AAA..0AB0
7238 UNKNOWN, // 0AB1
7239 GUJARATI, // 0AB2..0AB3
7240 UNKNOWN, // 0AB4
7241 GUJARATI, // 0AB5..0AB9
7242 UNKNOWN, // 0ABA..0ABB
7243 GUJARATI, // 0ABC..0AC5
7244 UNKNOWN, // 0AC6
7245 GUJARATI, // 0AC7..0AC9
7246 UNKNOWN, // 0ACA
7247 GUJARATI, // 0ACB..0ACD
7248 UNKNOWN, // 0ACE..0ACF
7249 GUJARATI, // 0AD0
7250 UNKNOWN, // 0AD1..0ADF
7251 GUJARATI, // 0AE0..0AE3
7252 UNKNOWN, // 0AE4..0AE5
7253 GUJARATI, // 0AE6..0AF1
7254 UNKNOWN, // 0AF2..0AF8
7255 GUJARATI, // 0AF9..0AFF
7256 UNKNOWN, // 0B00
7257 ORIYA, // 0B01..0B03
7258 UNKNOWN, // 0B04
7259 ORIYA, // 0B05..0B0C
7260 UNKNOWN, // 0B0D..0B0E
7261 ORIYA, // 0B0F..0B10
7262 UNKNOWN, // 0B11..0B12
7263 ORIYA, // 0B13..0B28
7264 UNKNOWN, // 0B29
7265 ORIYA, // 0B2A..0B30
7266 UNKNOWN, // 0B31
7267 ORIYA, // 0B32..0B33
7268 UNKNOWN, // 0B34
7269 ORIYA, // 0B35..0B39
7270 UNKNOWN, // 0B3A..0B3B
7271 ORIYA, // 0B3C..0B44
7272 UNKNOWN, // 0B45..0B46
7273 ORIYA, // 0B47..0B48
7274 UNKNOWN, // 0B49..0B4A
7275 ORIYA, // 0B4B..0B4D
7276 UNKNOWN, // 0B4E..0B54
7277 ORIYA, // 0B55..0B57
7278 UNKNOWN, // 0B58..0B5B
7279 ORIYA, // 0B5C..0B5D
7280 UNKNOWN, // 0B5E
7281 ORIYA, // 0B5F..0B63
7282 UNKNOWN, // 0B64..0B65
7283 ORIYA, // 0B66..0B77
7284 UNKNOWN, // 0B78..0B81
7285 TAMIL, // 0B82..0B83
7286 UNKNOWN, // 0B84
7287 TAMIL, // 0B85..0B8A
7288 UNKNOWN, // 0B8B..0B8D
7289 TAMIL, // 0B8E..0B90
7290 UNKNOWN, // 0B91
7291 TAMIL, // 0B92..0B95
7292 UNKNOWN, // 0B96..0B98
7293 TAMIL, // 0B99..0B9A
7294 UNKNOWN, // 0B9B
7295 TAMIL, // 0B9C
7296 UNKNOWN, // 0B9D
7297 TAMIL, // 0B9E..0B9F
7298 UNKNOWN, // 0BA0..0BA2
7299 TAMIL, // 0BA3..0BA4
7300 UNKNOWN, // 0BA5..0BA7
7301 TAMIL, // 0BA8..0BAA
7302 UNKNOWN, // 0BAB..0BAD
7303 TAMIL, // 0BAE..0BB9
7304 UNKNOWN, // 0BBA..0BBD
7305 TAMIL, // 0BBE..0BC2
7306 UNKNOWN, // 0BC3..0BC5
7307 TAMIL, // 0BC6..0BC8
7308 UNKNOWN, // 0BC9
7309 TAMIL, // 0BCA..0BCD
7310 UNKNOWN, // 0BCE..0BCF
7311 TAMIL, // 0BD0
7312 UNKNOWN, // 0BD1..0BD6
7313 TAMIL, // 0BD7
7314 UNKNOWN, // 0BD8..0BE5
7315 TAMIL, // 0BE6..0BFA
7316 UNKNOWN, // 0BFB..0BFF
7317 TELUGU, // 0C00..0C0C
7318 UNKNOWN, // 0C0D
7319 TELUGU, // 0C0E..0C10
7320 UNKNOWN, // 0C11
7321 TELUGU, // 0C12..0C28
7322 UNKNOWN, // 0C29
7323 TELUGU, // 0C2A..0C39
7324 UNKNOWN, // 0C3A..0C3B
7325 TELUGU, // 0C3C..0C44
7326 UNKNOWN, // 0C45
7327 TELUGU, // 0C46..0C48
7328 UNKNOWN, // 0C49
7329 TELUGU, // 0C4A..0C4D
7330 UNKNOWN, // 0C4E..0C54
7331 TELUGU, // 0C55..0C56
7332 UNKNOWN, // 0C57
7333 TELUGU, // 0C58..0C5A
7334 UNKNOWN, // 0C5B..0C5C
7335 TELUGU, // 0C5D
7336 UNKNOWN, // 0C5E..0C5F
7337 TELUGU, // 0C60..0C63
7338 UNKNOWN, // 0C64..0C65
7339 TELUGU, // 0C66..0C6F
7340 UNKNOWN, // 0C70..0C76
7341 TELUGU, // 0C77..0C7F
7342 KANNADA, // 0C80..0C8C
7343 UNKNOWN, // 0C8D
7344 KANNADA, // 0C8E..0C90
7345 UNKNOWN, // 0C91
7346 KANNADA, // 0C92..0CA8
7347 UNKNOWN, // 0CA9
7348 KANNADA, // 0CAA..0CB3
7349 UNKNOWN, // 0CB4
7350 KANNADA, // 0CB5..0CB9
7351 UNKNOWN, // 0CBA..0CBB
7352 KANNADA, // 0CBC..0CC4
7353 UNKNOWN, // 0CC5
7354 KANNADA, // 0CC6..0CC8
7355 UNKNOWN, // 0CC9
7356 KANNADA, // 0CCA..0CCD
7357 UNKNOWN, // 0CCE..0CD4
7358 KANNADA, // 0CD5..0CD6
7359 UNKNOWN, // 0CD7..0CDC
7360 KANNADA, // 0CDD..0CDE
7361 UNKNOWN, // 0CDF
7362 KANNADA, // 0CE0..0CE3
7363 UNKNOWN, // 0CE4..0CE5
7364 KANNADA, // 0CE6..0CEF
7365 UNKNOWN, // 0CF0
7366 KANNADA, // 0CF1..0CF3
7367 UNKNOWN, // 0CF4..0CFF
7368 MALAYALAM, // 0D00..0D0C
7369 UNKNOWN, // 0D0D
7370 MALAYALAM, // 0D0E..0D10
7371 UNKNOWN, // 0D11
7372 MALAYALAM, // 0D12..0D44
7373 UNKNOWN, // 0D45
7374 MALAYALAM, // 0D46..0D48
7375 UNKNOWN, // 0D49
7376 MALAYALAM, // 0D4A..0D4F
7377 UNKNOWN, // 0D50..0D53
7378 MALAYALAM, // 0D54..0D63
7379 UNKNOWN, // 0D64..0D65
7380 MALAYALAM, // 0D66..0D7F
7381 UNKNOWN, // 0D80
7382 SINHALA, // 0D81..0D83
7383 UNKNOWN, // 0D84
7384 SINHALA, // 0D85..0D96
7385 UNKNOWN, // 0D97..0D99
7386 SINHALA, // 0D9A..0DB1
7387 UNKNOWN, // 0DB2
7388 SINHALA, // 0DB3..0DBB
7389 UNKNOWN, // 0DBC
7390 SINHALA, // 0DBD
7391 UNKNOWN, // 0DBE..0DBF
7392 SINHALA, // 0DC0..0DC6
7393 UNKNOWN, // 0DC7..0DC9
7394 SINHALA, // 0DCA
7395 UNKNOWN, // 0DCB..0DCE
7396 SINHALA, // 0DCF..0DD4
7397 UNKNOWN, // 0DD5
7398 SINHALA, // 0DD6
7399 UNKNOWN, // 0DD7
7400 SINHALA, // 0DD8..0DDF
7401 UNKNOWN, // 0DE0..0DE5
7402 SINHALA, // 0DE6..0DEF
7403 UNKNOWN, // 0DF0..0DF1
7404 SINHALA, // 0DF2..0DF4
7405 UNKNOWN, // 0DF5..0E00
7406 THAI, // 0E01..0E3A
7407 UNKNOWN, // 0E3B..0E3E
7408 COMMON, // 0E3F
7409 THAI, // 0E40..0E5B
7410 UNKNOWN, // 0E5C..0E80
7411 LAO, // 0E81..0E82
7412 UNKNOWN, // 0E83
7413 LAO, // 0E84
7414 UNKNOWN, // 0E85
7415 LAO, // 0E86..0E8A
7416 UNKNOWN, // 0E8B
7417 LAO, // 0E8C..0EA3
7418 UNKNOWN, // 0EA4
7419 LAO, // 0EA5
7420 UNKNOWN, // 0EA6
7421 LAO, // 0EA7..0EBD
7422 UNKNOWN, // 0EBE..0EBF
7423 LAO, // 0EC0..0EC4
7424 UNKNOWN, // 0EC5
7425 LAO, // 0EC6
7426 UNKNOWN, // 0EC7
7427 LAO, // 0EC8..0ECE
7428 UNKNOWN, // 0ECF
7429 LAO, // 0ED0..0ED9
7430 UNKNOWN, // 0EDA..0EDB
7431 LAO, // 0EDC..0EDF
7432 UNKNOWN, // 0EE0..0EFF
7433 TIBETAN, // 0F00..0F47
7434 UNKNOWN, // 0F48
7435 TIBETAN, // 0F49..0F6C
7436 UNKNOWN, // 0F6D..0F70
7437 TIBETAN, // 0F71..0F97
7438 UNKNOWN, // 0F98
7439 TIBETAN, // 0F99..0FBC
7440 UNKNOWN, // 0FBD
7441 TIBETAN, // 0FBE..0FCC
7442 UNKNOWN, // 0FCD
7443 TIBETAN, // 0FCE..0FD4
7444 COMMON, // 0FD5..0FD8
7445 TIBETAN, // 0FD9..0FDA
7446 UNKNOWN, // 0FDB..0FFF
7447 MYANMAR, // 1000..109F
7448 GEORGIAN, // 10A0..10C5
7449 UNKNOWN, // 10C6
7450 GEORGIAN, // 10C7
7451 UNKNOWN, // 10C8..10CC
7452 GEORGIAN, // 10CD
7453 UNKNOWN, // 10CE..10CF
7454 GEORGIAN, // 10D0..10FA
7455 COMMON, // 10FB
7456 GEORGIAN, // 10FC..10FF
7457 HANGUL, // 1100..11FF
7458 ETHIOPIC, // 1200..1248
7459 UNKNOWN, // 1249
7460 ETHIOPIC, // 124A..124D
7461 UNKNOWN, // 124E..124F
7462 ETHIOPIC, // 1250..1256
7463 UNKNOWN, // 1257
7464 ETHIOPIC, // 1258
7465 UNKNOWN, // 1259
7466 ETHIOPIC, // 125A..125D
7467 UNKNOWN, // 125E..125F
7468 ETHIOPIC, // 1260..1288
7469 UNKNOWN, // 1289
7470 ETHIOPIC, // 128A..128D
7471 UNKNOWN, // 128E..128F
7472 ETHIOPIC, // 1290..12B0
7473 UNKNOWN, // 12B1
7474 ETHIOPIC, // 12B2..12B5
7475 UNKNOWN, // 12B6..12B7
7476 ETHIOPIC, // 12B8..12BE
7477 UNKNOWN, // 12BF
7478 ETHIOPIC, // 12C0
7479 UNKNOWN, // 12C1
7480 ETHIOPIC, // 12C2..12C5
7481 UNKNOWN, // 12C6..12C7
7482 ETHIOPIC, // 12C8..12D6
7483 UNKNOWN, // 12D7
7484 ETHIOPIC, // 12D8..1310
7485 UNKNOWN, // 1311
7486 ETHIOPIC, // 1312..1315
7487 UNKNOWN, // 1316..1317
7488 ETHIOPIC, // 1318..135A
7489 UNKNOWN, // 135B..135C
7490 ETHIOPIC, // 135D..137C
7491 UNKNOWN, // 137D..137F
7492 ETHIOPIC, // 1380..1399
7493 UNKNOWN, // 139A..139F
7494 CHEROKEE, // 13A0..13F5
7495 UNKNOWN, // 13F6..13F7
7496 CHEROKEE, // 13F8..13FD
7497 UNKNOWN, // 13FE..13FF
7498 CANADIAN_ABORIGINAL, // 1400..167F
7499 OGHAM, // 1680..169C
7500 UNKNOWN, // 169D..169F
7501 RUNIC, // 16A0..16EA
7502 COMMON, // 16EB..16ED
7503 RUNIC, // 16EE..16F8
7504 UNKNOWN, // 16F9..16FF
7505 TAGALOG, // 1700..1715
7506 UNKNOWN, // 1716..171E
7507 TAGALOG, // 171F
7508 HANUNOO, // 1720..1734
7509 COMMON, // 1735..1736
7510 UNKNOWN, // 1737..173F
7511 BUHID, // 1740..1753
7512 UNKNOWN, // 1754..175F
7513 TAGBANWA, // 1760..176C
7514 UNKNOWN, // 176D
7515 TAGBANWA, // 176E..1770
7516 UNKNOWN, // 1771
7517 TAGBANWA, // 1772..1773
7518 UNKNOWN, // 1774..177F
7519 KHMER, // 1780..17DD
7520 UNKNOWN, // 17DE..17DF
7521 KHMER, // 17E0..17E9
7522 UNKNOWN, // 17EA..17EF
7523 KHMER, // 17F0..17F9
7524 UNKNOWN, // 17FA..17FF
7525 MONGOLIAN, // 1800..1801
7526 COMMON, // 1802..1803
7527 MONGOLIAN, // 1804
7528 COMMON, // 1805
7529 MONGOLIAN, // 1806..1819
7530 UNKNOWN, // 181A..181F
7531 MONGOLIAN, // 1820..1878
7532 UNKNOWN, // 1879..187F
7533 MONGOLIAN, // 1880..18AA
7534 UNKNOWN, // 18AB..18AF
7535 CANADIAN_ABORIGINAL, // 18B0..18F5
7536 UNKNOWN, // 18F6..18FF
7537 LIMBU, // 1900..191E
7538 UNKNOWN, // 191F
7539 LIMBU, // 1920..192B
7540 UNKNOWN, // 192C..192F
7541 LIMBU, // 1930..193B
7542 UNKNOWN, // 193C..193F
7543 LIMBU, // 1940
7544 UNKNOWN, // 1941..1943
7545 LIMBU, // 1944..194F
7546 TAI_LE, // 1950..196D
7547 UNKNOWN, // 196E..196F
7548 TAI_LE, // 1970..1974
7549 UNKNOWN, // 1975..197F
7550 NEW_TAI_LUE, // 1980..19AB
7551 UNKNOWN, // 19AC..19AF
7552 NEW_TAI_LUE, // 19B0..19C9
7553 UNKNOWN, // 19CA..19CF
7554 NEW_TAI_LUE, // 19D0..19DA
7555 UNKNOWN, // 19DB..19DD
7556 NEW_TAI_LUE, // 19DE..19DF
7557 KHMER, // 19E0..19FF
7558 BUGINESE, // 1A00..1A1B
7559 UNKNOWN, // 1A1C..1A1D
7560 BUGINESE, // 1A1E..1A1F
7561 TAI_THAM, // 1A20..1A5E
7562 UNKNOWN, // 1A5F
7563 TAI_THAM, // 1A60..1A7C
7564 UNKNOWN, // 1A7D..1A7E
7565 TAI_THAM, // 1A7F..1A89
7566 UNKNOWN, // 1A8A..1A8F
7567 TAI_THAM, // 1A90..1A99
7568 UNKNOWN, // 1A9A..1A9F
7569 TAI_THAM, // 1AA0..1AAD
7570 UNKNOWN, // 1AAE..1AAF
7571 INHERITED, // 1AB0..1ACE
7572 UNKNOWN, // 1ACF..1AFF
7573 BALINESE, // 1B00..1B4C
7574 UNKNOWN, // 1B4D..1B4F
7575 BALINESE, // 1B50..1B7E
7576 UNKNOWN, // 1B7F
7577 SUNDANESE, // 1B80..1BBF
7578 BATAK, // 1BC0..1BF3
7579 UNKNOWN, // 1BF4..1BFB
7580 BATAK, // 1BFC..1BFF
7581 LEPCHA, // 1C00..1C37
7582 UNKNOWN, // 1C38..1C3A
7583 LEPCHA, // 1C3B..1C49
7584 UNKNOWN, // 1C4A..1C4C
7585 LEPCHA, // 1C4D..1C4F
7586 OL_CHIKI, // 1C50..1C7F
7587 CYRILLIC, // 1C80..1C88
7588 UNKNOWN, // 1C89..1C8F
7589 GEORGIAN, // 1C90..1CBA
7590 UNKNOWN, // 1CBB..1CBC
7591 GEORGIAN, // 1CBD..1CBF
7592 SUNDANESE, // 1CC0..1CC7
7593 UNKNOWN, // 1CC8..1CCF
7594 INHERITED, // 1CD0..1CD2
7595 COMMON, // 1CD3
7596 INHERITED, // 1CD4..1CE0
7597 COMMON, // 1CE1
7598 INHERITED, // 1CE2..1CE8
7599 COMMON, // 1CE9..1CEC
7600 INHERITED, // 1CED
7601 COMMON, // 1CEE..1CF3
7602 INHERITED, // 1CF4
7603 COMMON, // 1CF5..1CF7
7604 INHERITED, // 1CF8..1CF9
7605 COMMON, // 1CFA
7606 UNKNOWN, // 1CFB..1CFF
7607 LATIN, // 1D00..1D25
7608 GREEK, // 1D26..1D2A
7609 CYRILLIC, // 1D2B
7610 LATIN, // 1D2C..1D5C
7611 GREEK, // 1D5D..1D61
7612 LATIN, // 1D62..1D65
7613 GREEK, // 1D66..1D6A
7614 LATIN, // 1D6B..1D77
7615 CYRILLIC, // 1D78
7616 LATIN, // 1D79..1DBE
7617 GREEK, // 1DBF
7618 INHERITED, // 1DC0..1DFF
7619 LATIN, // 1E00..1EFF
7620 GREEK, // 1F00..1F15
7621 UNKNOWN, // 1F16..1F17
7622 GREEK, // 1F18..1F1D
7623 UNKNOWN, // 1F1E..1F1F
7624 GREEK, // 1F20..1F45
7625 UNKNOWN, // 1F46..1F47
7626 GREEK, // 1F48..1F4D
7627 UNKNOWN, // 1F4E..1F4F
7628 GREEK, // 1F50..1F57
7629 UNKNOWN, // 1F58
7630 GREEK, // 1F59
7631 UNKNOWN, // 1F5A
7632 GREEK, // 1F5B
7633 UNKNOWN, // 1F5C
7634 GREEK, // 1F5D
7635 UNKNOWN, // 1F5E
7636 GREEK, // 1F5F..1F7D
7637 UNKNOWN, // 1F7E..1F7F
7638 GREEK, // 1F80..1FB4
7639 UNKNOWN, // 1FB5
7640 GREEK, // 1FB6..1FC4
7641 UNKNOWN, // 1FC5
7642 GREEK, // 1FC6..1FD3
7643 UNKNOWN, // 1FD4..1FD5
7644 GREEK, // 1FD6..1FDB
7645 UNKNOWN, // 1FDC
7646 GREEK, // 1FDD..1FEF
7647 UNKNOWN, // 1FF0..1FF1
7648 GREEK, // 1FF2..1FF4
7649 UNKNOWN, // 1FF5
7650 GREEK, // 1FF6..1FFE
7651 UNKNOWN, // 1FFF
7652 COMMON, // 2000..200B
7653 INHERITED, // 200C..200D
7654 COMMON, // 200E..2064
7655 UNKNOWN, // 2065
7656 COMMON, // 2066..2070
7657 LATIN, // 2071
7658 UNKNOWN, // 2072..2073
7659 COMMON, // 2074..207E
7660 LATIN, // 207F
7661 COMMON, // 2080..208E
7662 UNKNOWN, // 208F
7663 LATIN, // 2090..209C
7664 UNKNOWN, // 209D..209F
7665 COMMON, // 20A0..20C0
7666 UNKNOWN, // 20C1..20CF
7667 INHERITED, // 20D0..20F0
7668 UNKNOWN, // 20F1..20FF
7669 COMMON, // 2100..2125
7670 GREEK, // 2126
7671 COMMON, // 2127..2129
7672 LATIN, // 212A..212B
7673 COMMON, // 212C..2131
7674 LATIN, // 2132
7675 COMMON, // 2133..214D
7676 LATIN, // 214E
7677 COMMON, // 214F..215F
7678 LATIN, // 2160..2188
7679 COMMON, // 2189..218B
7680 UNKNOWN, // 218C..218F
7681 COMMON, // 2190..2426
7682 UNKNOWN, // 2427..243F
7683 COMMON, // 2440..244A
7684 UNKNOWN, // 244B..245F
7685 COMMON, // 2460..27FF
7686 BRAILLE, // 2800..28FF
7687 COMMON, // 2900..2B73
7688 UNKNOWN, // 2B74..2B75
7689 COMMON, // 2B76..2B95
7690 UNKNOWN, // 2B96
7691 COMMON, // 2B97..2BFF
7692 GLAGOLITIC, // 2C00..2C5F
7693 LATIN, // 2C60..2C7F
7694 COPTIC, // 2C80..2CF3
7695 UNKNOWN, // 2CF4..2CF8
7696 COPTIC, // 2CF9..2CFF
7697 GEORGIAN, // 2D00..2D25
7698 UNKNOWN, // 2D26
7699 GEORGIAN, // 2D27
7700 UNKNOWN, // 2D28..2D2C
7701 GEORGIAN, // 2D2D
7702 UNKNOWN, // 2D2E..2D2F
7703 TIFINAGH, // 2D30..2D67
7704 UNKNOWN, // 2D68..2D6E
7705 TIFINAGH, // 2D6F..2D70
7706 UNKNOWN, // 2D71..2D7E
7707 TIFINAGH, // 2D7F
7708 ETHIOPIC, // 2D80..2D96
7709 UNKNOWN, // 2D97..2D9F
7710 ETHIOPIC, // 2DA0..2DA6
7711 UNKNOWN, // 2DA7
7712 ETHIOPIC, // 2DA8..2DAE
7713 UNKNOWN, // 2DAF
7714 ETHIOPIC, // 2DB0..2DB6
7715 UNKNOWN, // 2DB7
7716 ETHIOPIC, // 2DB8..2DBE
7717 UNKNOWN, // 2DBF
7718 ETHIOPIC, // 2DC0..2DC6
7719 UNKNOWN, // 2DC7
7720 ETHIOPIC, // 2DC8..2DCE
7721 UNKNOWN, // 2DCF
7722 ETHIOPIC, // 2DD0..2DD6
7723 UNKNOWN, // 2DD7
7724 ETHIOPIC, // 2DD8..2DDE
7725 UNKNOWN, // 2DDF
7726 CYRILLIC, // 2DE0..2DFF
7727 COMMON, // 2E00..2E5D
7728 UNKNOWN, // 2E5E..2E7F
7729 HAN, // 2E80..2E99
7730 UNKNOWN, // 2E9A
7731 HAN, // 2E9B..2EF3
7732 UNKNOWN, // 2EF4..2EFF
7733 HAN, // 2F00..2FD5
7734 UNKNOWN, // 2FD6..2FEF
7735 COMMON, // 2FF0..3004
7736 HAN, // 3005
7737 COMMON, // 3006
7738 HAN, // 3007
7739 COMMON, // 3008..3020
7740 HAN, // 3021..3029
7741 INHERITED, // 302A..302D
7742 HANGUL, // 302E..302F
7743 COMMON, // 3030..3037
7744 HAN, // 3038..303B
7745 COMMON, // 303C..303F
7746 UNKNOWN, // 3040
7747 HIRAGANA, // 3041..3096
7748 UNKNOWN, // 3097..3098
7749 INHERITED, // 3099..309A
7750 COMMON, // 309B..309C
7751 HIRAGANA, // 309D..309F
7752 COMMON, // 30A0
7753 KATAKANA, // 30A1..30FA
7754 COMMON, // 30FB..30FC
7755 KATAKANA, // 30FD..30FF
7756 UNKNOWN, // 3100..3104
7757 BOPOMOFO, // 3105..312F
7758 UNKNOWN, // 3130
7759 HANGUL, // 3131..318E
7760 UNKNOWN, // 318F
7761 COMMON, // 3190..319F
7762 BOPOMOFO, // 31A0..31BF
7763 COMMON, // 31C0..31E3
7764 UNKNOWN, // 31E4..31EE
7765 COMMON, // 31EF
7766 KATAKANA, // 31F0..31FF
7767 HANGUL, // 3200..321E
7768 UNKNOWN, // 321F
7769 COMMON, // 3220..325F
7770 HANGUL, // 3260..327E
7771 COMMON, // 327F..32CF
7772 KATAKANA, // 32D0..32FE
7773 COMMON, // 32FF
7774 KATAKANA, // 3300..3357
7775 COMMON, // 3358..33FF
7776 HAN, // 3400..4DBF
7777 COMMON, // 4DC0..4DFF
7778 HAN, // 4E00..9FFF
7779 YI, // A000..A48C
7780 UNKNOWN, // A48D..A48F
7781 YI, // A490..A4C6
7782 UNKNOWN, // A4C7..A4CF
7783 LISU, // A4D0..A4FF
7784 VAI, // A500..A62B
7785 UNKNOWN, // A62C..A63F
7786 CYRILLIC, // A640..A69F
7787 BAMUM, // A6A0..A6F7
7788 UNKNOWN, // A6F8..A6FF
7789 COMMON, // A700..A721
7790 LATIN, // A722..A787
7791 COMMON, // A788..A78A
7792 LATIN, // A78B..A7CA
7793 UNKNOWN, // A7CB..A7CF
7794 LATIN, // A7D0..A7D1
7795 UNKNOWN, // A7D2
7796 LATIN, // A7D3
7797 UNKNOWN, // A7D4
7798 LATIN, // A7D5..A7D9
7799 UNKNOWN, // A7DA..A7F1
7800 LATIN, // A7F2..A7FF
7801 SYLOTI_NAGRI, // A800..A82C
7802 UNKNOWN, // A82D..A82F
7803 COMMON, // A830..A839
7804 UNKNOWN, // A83A..A83F
7805 PHAGS_PA, // A840..A877
7806 UNKNOWN, // A878..A87F
7807 SAURASHTRA, // A880..A8C5
7808 UNKNOWN, // A8C6..A8CD
7809 SAURASHTRA, // A8CE..A8D9
7810 UNKNOWN, // A8DA..A8DF
7811 DEVANAGARI, // A8E0..A8FF
7812 KAYAH_LI, // A900..A92D
7813 COMMON, // A92E
7814 KAYAH_LI, // A92F
7815 REJANG, // A930..A953
7816 UNKNOWN, // A954..A95E
7817 REJANG, // A95F
7818 HANGUL, // A960..A97C
7819 UNKNOWN, // A97D..A97F
7820 JAVANESE, // A980..A9CD
7821 UNKNOWN, // A9CE
7822 COMMON, // A9CF
7823 JAVANESE, // A9D0..A9D9
7824 UNKNOWN, // A9DA..A9DD
7825 JAVANESE, // A9DE..A9DF
7826 MYANMAR, // A9E0..A9FE
7827 UNKNOWN, // A9FF
7828 CHAM, // AA00..AA36
7829 UNKNOWN, // AA37..AA3F
7830 CHAM, // AA40..AA4D
7831 UNKNOWN, // AA4E..AA4F
7832 CHAM, // AA50..AA59
7833 UNKNOWN, // AA5A..AA5B
7834 CHAM, // AA5C..AA5F
7835 MYANMAR, // AA60..AA7F
7836 TAI_VIET, // AA80..AAC2
7837 UNKNOWN, // AAC3..AADA
7838 TAI_VIET, // AADB..AADF
7839 MEETEI_MAYEK, // AAE0..AAF6
7840 UNKNOWN, // AAF7..AB00
7841 ETHIOPIC, // AB01..AB06
7842 UNKNOWN, // AB07..AB08
7843 ETHIOPIC, // AB09..AB0E
7844 UNKNOWN, // AB0F..AB10
7845 ETHIOPIC, // AB11..AB16
7846 UNKNOWN, // AB17..AB1F
7847 ETHIOPIC, // AB20..AB26
7848 UNKNOWN, // AB27
7849 ETHIOPIC, // AB28..AB2E
7850 UNKNOWN, // AB2F
7851 LATIN, // AB30..AB5A
7852 COMMON, // AB5B
7853 LATIN, // AB5C..AB64
7854 GREEK, // AB65
7855 LATIN, // AB66..AB69
7856 COMMON, // AB6A..AB6B
7857 UNKNOWN, // AB6C..AB6F
7858 CHEROKEE, // AB70..ABBF
7859 MEETEI_MAYEK, // ABC0..ABED
7860 UNKNOWN, // ABEE..ABEF
7861 MEETEI_MAYEK, // ABF0..ABF9
7862 UNKNOWN, // ABFA..ABFF
7863 HANGUL, // AC00..D7A3
7864 UNKNOWN, // D7A4..D7AF
7865 HANGUL, // D7B0..D7C6
7866 UNKNOWN, // D7C7..D7CA
7867 HANGUL, // D7CB..D7FB
7868 UNKNOWN, // D7FC..F8FF
7869 HAN, // F900..FA6D
7870 UNKNOWN, // FA6E..FA6F
7871 HAN, // FA70..FAD9
7872 UNKNOWN, // FADA..FAFF
7873 LATIN, // FB00..FB06
7874 UNKNOWN, // FB07..FB12
7875 ARMENIAN, // FB13..FB17
7876 UNKNOWN, // FB18..FB1C
7877 HEBREW, // FB1D..FB36
7878 UNKNOWN, // FB37
7879 HEBREW, // FB38..FB3C
7880 UNKNOWN, // FB3D
7881 HEBREW, // FB3E
7882 UNKNOWN, // FB3F
7883 HEBREW, // FB40..FB41
7884 UNKNOWN, // FB42
7885 HEBREW, // FB43..FB44
7886 UNKNOWN, // FB45
7887 HEBREW, // FB46..FB4F
7888 ARABIC, // FB50..FBC2
7889 UNKNOWN, // FBC3..FBD2
7890 ARABIC, // FBD3..FD3D
7891 COMMON, // FD3E..FD3F
7892 ARABIC, // FD40..FD8F
7893 UNKNOWN, // FD90..FD91
7894 ARABIC, // FD92..FDC7
7895 UNKNOWN, // FDC8..FDCE
7896 ARABIC, // FDCF
7897 UNKNOWN, // FDD0..FDEF
7898 ARABIC, // FDF0..FDFF
7899 INHERITED, // FE00..FE0F
7900 COMMON, // FE10..FE19
7901 UNKNOWN, // FE1A..FE1F
7902 INHERITED, // FE20..FE2D
7903 CYRILLIC, // FE2E..FE2F
7904 COMMON, // FE30..FE52
7905 UNKNOWN, // FE53
7906 COMMON, // FE54..FE66
7907 UNKNOWN, // FE67
7908 COMMON, // FE68..FE6B
7909 UNKNOWN, // FE6C..FE6F
7910 ARABIC, // FE70..FE74
7911 UNKNOWN, // FE75
7912 ARABIC, // FE76..FEFC
7913 UNKNOWN, // FEFD..FEFE
7914 COMMON, // FEFF
7915 UNKNOWN, // FF00
7916 COMMON, // FF01..FF20
7917 LATIN, // FF21..FF3A
7918 COMMON, // FF3B..FF40
7919 LATIN, // FF41..FF5A
7920 COMMON, // FF5B..FF65
7921 KATAKANA, // FF66..FF6F
7922 COMMON, // FF70
7923 KATAKANA, // FF71..FF9D
7924 COMMON, // FF9E..FF9F
7925 HANGUL, // FFA0..FFBE
7926 UNKNOWN, // FFBF..FFC1
7927 HANGUL, // FFC2..FFC7
7928 UNKNOWN, // FFC8..FFC9
7929 HANGUL, // FFCA..FFCF
7930 UNKNOWN, // FFD0..FFD1
7931 HANGUL, // FFD2..FFD7
7932 UNKNOWN, // FFD8..FFD9
7933 HANGUL, // FFDA..FFDC
7934 UNKNOWN, // FFDD..FFDF
7935 COMMON, // FFE0..FFE6
7936 UNKNOWN, // FFE7
7937 COMMON, // FFE8..FFEE
7938 UNKNOWN, // FFEF..FFF8
7939 COMMON, // FFF9..FFFD
7940 UNKNOWN, // FFFE..FFFF
7941 LINEAR_B, // 10000..1000B
7942 UNKNOWN, // 1000C
7943 LINEAR_B, // 1000D..10026
7944 UNKNOWN, // 10027
7945 LINEAR_B, // 10028..1003A
7946 UNKNOWN, // 1003B
7947 LINEAR_B, // 1003C..1003D
7948 UNKNOWN, // 1003E
7949 LINEAR_B, // 1003F..1004D
7950 UNKNOWN, // 1004E..1004F
7951 LINEAR_B, // 10050..1005D
7952 UNKNOWN, // 1005E..1007F
7953 LINEAR_B, // 10080..100FA
7954 UNKNOWN, // 100FB..100FF
7955 COMMON, // 10100..10102
7956 UNKNOWN, // 10103..10106
7957 COMMON, // 10107..10133
7958 UNKNOWN, // 10134..10136
7959 COMMON, // 10137..1013F
7960 GREEK, // 10140..1018E
7961 UNKNOWN, // 1018F
7962 COMMON, // 10190..1019C
7963 UNKNOWN, // 1019D..1019F
7964 GREEK, // 101A0
7965 UNKNOWN, // 101A1..101CF
7966 COMMON, // 101D0..101FC
7967 INHERITED, // 101FD
7968 UNKNOWN, // 101FE..1027F
7969 LYCIAN, // 10280..1029C
7970 UNKNOWN, // 1029D..1029F
7971 CARIAN, // 102A0..102D0
7972 UNKNOWN, // 102D1..102DF
7973 INHERITED, // 102E0
7974 COMMON, // 102E1..102FB
7975 UNKNOWN, // 102FC..102FF
7976 OLD_ITALIC, // 10300..10323
7977 UNKNOWN, // 10324..1032C
7978 OLD_ITALIC, // 1032D..1032F
7979 GOTHIC, // 10330..1034A
7980 UNKNOWN, // 1034B..1034F
7981 OLD_PERMIC, // 10350..1037A
7982 UNKNOWN, // 1037B..1037F
7983 UGARITIC, // 10380..1039D
7984 UNKNOWN, // 1039E
7985 UGARITIC, // 1039F
7986 OLD_PERSIAN, // 103A0..103C3
7987 UNKNOWN, // 103C4..103C7
7988 OLD_PERSIAN, // 103C8..103D5
7989 UNKNOWN, // 103D6..103FF
7990 DESERET, // 10400..1044F
7991 SHAVIAN, // 10450..1047F
7992 OSMANYA, // 10480..1049D
7993 UNKNOWN, // 1049E..1049F
7994 OSMANYA, // 104A0..104A9
7995 UNKNOWN, // 104AA..104AF
7996 OSAGE, // 104B0..104D3
7997 UNKNOWN, // 104D4..104D7
7998 OSAGE, // 104D8..104FB
7999 UNKNOWN, // 104FC..104FF
8000 ELBASAN, // 10500..10527
8001 UNKNOWN, // 10528..1052F
8002 CAUCASIAN_ALBANIAN, // 10530..10563
8003 UNKNOWN, // 10564..1056E
8004 CAUCASIAN_ALBANIAN, // 1056F
8005 VITHKUQI, // 10570..1057A
8006 UNKNOWN, // 1057B
8007 VITHKUQI, // 1057C..1058A
8008 UNKNOWN, // 1058B
8009 VITHKUQI, // 1058C..10592
8010 UNKNOWN, // 10593
8011 VITHKUQI, // 10594..10595
8012 UNKNOWN, // 10596
8013 VITHKUQI, // 10597..105A1
8014 UNKNOWN, // 105A2
8015 VITHKUQI, // 105A3..105B1
8016 UNKNOWN, // 105B2
8017 VITHKUQI, // 105B3..105B9
8018 UNKNOWN, // 105BA
8019 VITHKUQI, // 105BB..105BC
8020 UNKNOWN, // 105BD..105FF
8021 LINEAR_A, // 10600..10736
8022 UNKNOWN, // 10737..1073F
8023 LINEAR_A, // 10740..10755
8024 UNKNOWN, // 10756..1075F
8025 LINEAR_A, // 10760..10767
8026 UNKNOWN, // 10768..1077F
8027 LATIN, // 10780..10785
8028 UNKNOWN, // 10786
8029 LATIN, // 10787..107B0
8030 UNKNOWN, // 107B1
8031 LATIN, // 107B2..107BA
8032 UNKNOWN, // 107BB..107FF
8033 CYPRIOT, // 10800..10805
8034 UNKNOWN, // 10806..10807
8035 CYPRIOT, // 10808
8036 UNKNOWN, // 10809
8037 CYPRIOT, // 1080A..10835
8038 UNKNOWN, // 10836
8039 CYPRIOT, // 10837..10838
8040 UNKNOWN, // 10839..1083B
8041 CYPRIOT, // 1083C
8042 UNKNOWN, // 1083D..1083E
8043 CYPRIOT, // 1083F
8044 IMPERIAL_ARAMAIC, // 10840..10855
8045 UNKNOWN, // 10856
8046 IMPERIAL_ARAMAIC, // 10857..1085F
8047 PALMYRENE, // 10860..1087F
8048 NABATAEAN, // 10880..1089E
8049 UNKNOWN, // 1089F..108A6
8050 NABATAEAN, // 108A7..108AF
8051 UNKNOWN, // 108B0..108DF
8052 HATRAN, // 108E0..108F2
8053 UNKNOWN, // 108F3
8054 HATRAN, // 108F4..108F5
8055 UNKNOWN, // 108F6..108FA
8056 HATRAN, // 108FB..108FF
8057 PHOENICIAN, // 10900..1091B
8058 UNKNOWN, // 1091C..1091E
8059 PHOENICIAN, // 1091F
8060 LYDIAN, // 10920..10939
8061 UNKNOWN, // 1093A..1093E
8062 LYDIAN, // 1093F
8063 UNKNOWN, // 10940..1097F
8064 MEROITIC_HIEROGLYPHS, // 10980..1099F
8065 MEROITIC_CURSIVE, // 109A0..109B7
8066 UNKNOWN, // 109B8..109BB
8067 MEROITIC_CURSIVE, // 109BC..109CF
8068 UNKNOWN, // 109D0..109D1
8069 MEROITIC_CURSIVE, // 109D2..109FF
8070 KHAROSHTHI, // 10A00..10A03
8071 UNKNOWN, // 10A04
8072 KHAROSHTHI, // 10A05..10A06
8073 UNKNOWN, // 10A07..10A0B
8074 KHAROSHTHI, // 10A0C..10A13
8075 UNKNOWN, // 10A14
8076 KHAROSHTHI, // 10A15..10A17
8077 UNKNOWN, // 10A18
8078 KHAROSHTHI, // 10A19..10A35
8079 UNKNOWN, // 10A36..10A37
8080 KHAROSHTHI, // 10A38..10A3A
8081 UNKNOWN, // 10A3B..10A3E
8082 KHAROSHTHI, // 10A3F..10A48
8083 UNKNOWN, // 10A49..10A4F
8084 KHAROSHTHI, // 10A50..10A58
8085 UNKNOWN, // 10A59..10A5F
8086 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8087 OLD_NORTH_ARABIAN, // 10A80..10A9F
8088 UNKNOWN, // 10AA0..10ABF
8089 MANICHAEAN, // 10AC0..10AE6
8090 UNKNOWN, // 10AE7..10AEA
8091 MANICHAEAN, // 10AEB..10AF6
8092 UNKNOWN, // 10AF7..10AFF
8093 AVESTAN, // 10B00..10B35
8094 UNKNOWN, // 10B36..10B38
8095 AVESTAN, // 10B39..10B3F
8096 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8097 UNKNOWN, // 10B56..10B57
8098 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8099 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8100 UNKNOWN, // 10B73..10B77
8101 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8102 PSALTER_PAHLAVI, // 10B80..10B91
8103 UNKNOWN, // 10B92..10B98
8104 PSALTER_PAHLAVI, // 10B99..10B9C
8105 UNKNOWN, // 10B9D..10BA8
8106 PSALTER_PAHLAVI, // 10BA9..10BAF
8107 UNKNOWN, // 10BB0..10BFF
8108 OLD_TURKIC, // 10C00..10C48
8109 UNKNOWN, // 10C49..10C7F
8110 OLD_HUNGARIAN, // 10C80..10CB2
8111 UNKNOWN, // 10CB3..10CBF
8112 OLD_HUNGARIAN, // 10CC0..10CF2
8113 UNKNOWN, // 10CF3..10CF9
8114 OLD_HUNGARIAN, // 10CFA..10CFF
8115 HANIFI_ROHINGYA, // 10D00..10D27
8116 UNKNOWN, // 10D28..10D2F
8117 HANIFI_ROHINGYA, // 10D30..10D39
8118 UNKNOWN, // 10D3A..10E5F
8119 ARABIC, // 10E60..10E7E
8120 UNKNOWN, // 10E7F
8121 YEZIDI, // 10E80..10EA9
8122 UNKNOWN, // 10EAA
8123 YEZIDI, // 10EAB..10EAD
8124 UNKNOWN, // 10EAE..10EAF
8125 YEZIDI, // 10EB0..10EB1
8126 UNKNOWN, // 10EB2..10EFC
8127 ARABIC, // 10EFD..10EFF
8128 OLD_SOGDIAN, // 10F00..10F27
8129 UNKNOWN, // 10F28..10F2F
8130 SOGDIAN, // 10F30..10F59
8131 UNKNOWN, // 10F5A..10F6F
8132 OLD_UYGHUR, // 10F70..10F89
8133 UNKNOWN, // 10F8A..10FAF
8134 CHORASMIAN, // 10FB0..10FCB
8135 UNKNOWN, // 10FCC..10FDF
8136 ELYMAIC, // 10FE0..10FF6
8137 UNKNOWN, // 10FF7..10FFF
8138 BRAHMI, // 11000..1104D
8139 UNKNOWN, // 1104E..11051
8140 BRAHMI, // 11052..11075
8141 UNKNOWN, // 11076..1107E
8142 BRAHMI, // 1107F
8143 KAITHI, // 11080..110C2
8144 UNKNOWN, // 110C3..110CC
8145 KAITHI, // 110CD
8146 UNKNOWN, // 110CE..110CF
8147 SORA_SOMPENG, // 110D0..110E8
8148 UNKNOWN, // 110E9..110EF
8149 SORA_SOMPENG, // 110F0..110F9
8150 UNKNOWN, // 110FA..110FF
8151 CHAKMA, // 11100..11134
8152 UNKNOWN, // 11135
8153 CHAKMA, // 11136..11147
8154 UNKNOWN, // 11148..1114F
8155 MAHAJANI, // 11150..11176
8156 UNKNOWN, // 11177..1117F
8157 SHARADA, // 11180..111DF
8158 UNKNOWN, // 111E0
8159 SINHALA, // 111E1..111F4
8160 UNKNOWN, // 111F5..111FF
8161 KHOJKI, // 11200..11211
8162 UNKNOWN, // 11212
8163 KHOJKI, // 11213..11241
8164 UNKNOWN, // 11242..1127F
8165 MULTANI, // 11280..11286
8166 UNKNOWN, // 11287
8167 MULTANI, // 11288
8168 UNKNOWN, // 11289
8169 MULTANI, // 1128A..1128D
8170 UNKNOWN, // 1128E
8171 MULTANI, // 1128F..1129D
8172 UNKNOWN, // 1129E
8173 MULTANI, // 1129F..112A9
8174 UNKNOWN, // 112AA..112AF
8175 KHUDAWADI, // 112B0..112EA
8176 UNKNOWN, // 112EB..112EF
8177 KHUDAWADI, // 112F0..112F9
8178 UNKNOWN, // 112FA..112FF
8179 GRANTHA, // 11300..11303
8180 UNKNOWN, // 11304
8181 GRANTHA, // 11305..1130C
8182 UNKNOWN, // 1130D..1130E
8183 GRANTHA, // 1130F..11310
8184 UNKNOWN, // 11311..11312
8185 GRANTHA, // 11313..11328
8186 UNKNOWN, // 11329
8187 GRANTHA, // 1132A..11330
8188 UNKNOWN, // 11331
8189 GRANTHA, // 11332..11333
8190 UNKNOWN, // 11334
8191 GRANTHA, // 11335..11339
8192 UNKNOWN, // 1133A
8193 INHERITED, // 1133B
8194 GRANTHA, // 1133C..11344
8195 UNKNOWN, // 11345..11346
8196 GRANTHA, // 11347..11348
8197 UNKNOWN, // 11349..1134A
8198 GRANTHA, // 1134B..1134D
8199 UNKNOWN, // 1134E..1134F
8200 GRANTHA, // 11350
8201 UNKNOWN, // 11351..11356
8202 GRANTHA, // 11357
8203 UNKNOWN, // 11358..1135C
8204 GRANTHA, // 1135D..11363
8205 UNKNOWN, // 11364..11365
8206 GRANTHA, // 11366..1136C
8207 UNKNOWN, // 1136D..1136F
8208 GRANTHA, // 11370..11374
8209 UNKNOWN, // 11375..113FF
8210 NEWA, // 11400..1145B
8211 UNKNOWN, // 1145C
8212 NEWA, // 1145D..11461
8213 UNKNOWN, // 11462..1147F
8214 TIRHUTA, // 11480..114C7
8215 UNKNOWN, // 114C8..114CF
8216 TIRHUTA, // 114D0..114D9
8217 UNKNOWN, // 114DA..1157F
8218 SIDDHAM, // 11580..115B5
8219 UNKNOWN, // 115B6..115B7
8220 SIDDHAM, // 115B8..115DD
8221 UNKNOWN, // 115DE..115FF
8222 MODI, // 11600..11644
8223 UNKNOWN, // 11645..1164F
8224 MODI, // 11650..11659
8225 UNKNOWN, // 1165A..1165F
8226 MONGOLIAN, // 11660..1166C
8227 UNKNOWN, // 1166D..1167F
8228 TAKRI, // 11680..116B9
8229 UNKNOWN, // 116BA..116BF
8230 TAKRI, // 116C0..116C9
8231 UNKNOWN, // 116CA..116FF
8232 AHOM, // 11700..1171A
8233 UNKNOWN, // 1171B..1171C
8234 AHOM, // 1171D..1172B
8235 UNKNOWN, // 1172C..1172F
8236 AHOM, // 11730..11746
8237 UNKNOWN, // 11747..117FF
8238 DOGRA, // 11800..1183B
8239 UNKNOWN, // 1183C..1189F
8240 WARANG_CITI, // 118A0..118F2
8241 UNKNOWN, // 118F3..118FE
8242 WARANG_CITI, // 118FF
8243 DIVES_AKURU, // 11900..11906
8244 UNKNOWN, // 11907..11908
8245 DIVES_AKURU, // 11909
8246 UNKNOWN, // 1190A..1190B
8247 DIVES_AKURU, // 1190C..11913
8248 UNKNOWN, // 11914
8249 DIVES_AKURU, // 11915..11916
8250 UNKNOWN, // 11917
8251 DIVES_AKURU, // 11918..11935
8252 UNKNOWN, // 11936
8253 DIVES_AKURU, // 11937..11938
8254 UNKNOWN, // 11939..1193A
8255 DIVES_AKURU, // 1193B..11946
8256 UNKNOWN, // 11947..1194F
8257 DIVES_AKURU, // 11950..11959
8258 UNKNOWN, // 1195A..1199F
8259 NANDINAGARI, // 119A0..119A7
8260 UNKNOWN, // 119A8..119A9
8261 NANDINAGARI, // 119AA..119D7
8262 UNKNOWN, // 119D8..119D9
8263 NANDINAGARI, // 119DA..119E4
8264 UNKNOWN, // 119E5..119FF
8265 ZANABAZAR_SQUARE, // 11A00..11A47
8266 UNKNOWN, // 11A48..11A4F
8267 SOYOMBO, // 11A50..11AA2
8268 UNKNOWN, // 11AA3..11AAF
8269 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8270 PAU_CIN_HAU, // 11AC0..11AF8
8271 UNKNOWN, // 11AF9..11AFF
8272 DEVANAGARI, // 11B00..11B09
8273 UNKNOWN, // 11B0A..11BFF
8274 BHAIKSUKI, // 11C00..11C08
8275 UNKNOWN, // 11C09
8276 BHAIKSUKI, // 11C0A..11C36
8277 UNKNOWN, // 11C37
8278 BHAIKSUKI, // 11C38..11C45
8279 UNKNOWN, // 11C46..11C4F
8280 BHAIKSUKI, // 11C50..11C6C
8281 UNKNOWN, // 11C6D..11C6F
8282 MARCHEN, // 11C70..11C8F
8283 UNKNOWN, // 11C90..11C91
8284 MARCHEN, // 11C92..11CA7
8285 UNKNOWN, // 11CA8
8286 MARCHEN, // 11CA9..11CB6
8287 UNKNOWN, // 11CB7..11CFF
8288 MASARAM_GONDI, // 11D00..11D06
8289 UNKNOWN, // 11D07
8290 MASARAM_GONDI, // 11D08..11D09
8291 UNKNOWN, // 11D0A
8292 MASARAM_GONDI, // 11D0B..11D36
8293 UNKNOWN, // 11D37..11D39
8294 MASARAM_GONDI, // 11D3A
8295 UNKNOWN, // 11D3B
8296 MASARAM_GONDI, // 11D3C..11D3D
8297 UNKNOWN, // 11D3E
8298 MASARAM_GONDI, // 11D3F..11D47
8299 UNKNOWN, // 11D48..11D4F
8300 MASARAM_GONDI, // 11D50..11D59
8301 UNKNOWN, // 11D5A..11D5F
8302 GUNJALA_GONDI, // 11D60..11D65
8303 UNKNOWN, // 11D66
8304 GUNJALA_GONDI, // 11D67..11D68
8305 UNKNOWN, // 11D69
8306 GUNJALA_GONDI, // 11D6A..11D8E
8307 UNKNOWN, // 11D8F
8308 GUNJALA_GONDI, // 11D90..11D91
8309 UNKNOWN, // 11D92
8310 GUNJALA_GONDI, // 11D93..11D98
8311 UNKNOWN, // 11D99..11D9F
8312 GUNJALA_GONDI, // 11DA0..11DA9
8313 UNKNOWN, // 11DAA..11EDF
8314 MAKASAR, // 11EE0..11EF8
8315 UNKNOWN, // 11EF9..11EFF
8316 KAWI, // 11F00..11F10
8317 UNKNOWN, // 11F11
8318 KAWI, // 11F12..11F3A
8319 UNKNOWN, // 11F3B..11F3D
8320 KAWI, // 11F3E..11F59
8321 UNKNOWN, // 11F5A..11FAF
8322 LISU, // 11FB0
8323 UNKNOWN, // 11FB1..11FBF
8324 TAMIL, // 11FC0..11FF1
8325 UNKNOWN, // 11FF2..11FFE
8326 TAMIL, // 11FFF
8327 CUNEIFORM, // 12000..12399
8328 UNKNOWN, // 1239A..123FF
8329 CUNEIFORM, // 12400..1246E
8330 UNKNOWN, // 1246F
8331 CUNEIFORM, // 12470..12474
8332 UNKNOWN, // 12475..1247F
8333 CUNEIFORM, // 12480..12543
8334 UNKNOWN, // 12544..12F8F
8335 CYPRO_MINOAN, // 12F90..12FF2
8336 UNKNOWN, // 12FF3..12FFF
8337 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8338 UNKNOWN, // 13456..143FF
8339 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8340 UNKNOWN, // 14647..167FF
8341 BAMUM, // 16800..16A38
8342 UNKNOWN, // 16A39..16A3F
8343 MRO, // 16A40..16A5E
8344 UNKNOWN, // 16A5F
8345 MRO, // 16A60..16A69
8346 UNKNOWN, // 16A6A..16A6D
8347 MRO, // 16A6E..16A6F
8348 TANGSA, // 16A70..16ABE
8349 UNKNOWN, // 16ABF
8350 TANGSA, // 16AC0..16AC9
8351 UNKNOWN, // 16ACA..16ACF
8352 BASSA_VAH, // 16AD0..16AED
8353 UNKNOWN, // 16AEE..16AEF
8354 BASSA_VAH, // 16AF0..16AF5
8355 UNKNOWN, // 16AF6..16AFF
8356 PAHAWH_HMONG, // 16B00..16B45
8357 UNKNOWN, // 16B46..16B4F
8358 PAHAWH_HMONG, // 16B50..16B59
8359 UNKNOWN, // 16B5A
8360 PAHAWH_HMONG, // 16B5B..16B61
8361 UNKNOWN, // 16B62
8362 PAHAWH_HMONG, // 16B63..16B77
8363 UNKNOWN, // 16B78..16B7C
8364 PAHAWH_HMONG, // 16B7D..16B8F
8365 UNKNOWN, // 16B90..16E3F
8366 MEDEFAIDRIN, // 16E40..16E9A
8367 UNKNOWN, // 16E9B..16EFF
8368 MIAO, // 16F00..16F4A
8369 UNKNOWN, // 16F4B..16F4E
8370 MIAO, // 16F4F..16F87
8371 UNKNOWN, // 16F88..16F8E
8372 MIAO, // 16F8F..16F9F
8373 UNKNOWN, // 16FA0..16FDF
8374 TANGUT, // 16FE0
8375 NUSHU, // 16FE1
8376 HAN, // 16FE2..16FE3
8377 KHITAN_SMALL_SCRIPT, // 16FE4
8378 UNKNOWN, // 16FE5..16FEF
8379 HAN, // 16FF0..16FF1
8380 UNKNOWN, // 16FF2..16FFF
8381 TANGUT, // 17000..187F7
8382 UNKNOWN, // 187F8..187FF
8383 TANGUT, // 18800..18AFF
8384 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8385 UNKNOWN, // 18CD6..18CFF
8386 TANGUT, // 18D00..18D08
8387 UNKNOWN, // 18D09..1AFEF
8388 KATAKANA, // 1AFF0..1AFF3
8389 UNKNOWN, // 1AFF4
8390 KATAKANA, // 1AFF5..1AFFB
8391 UNKNOWN, // 1AFFC
8392 KATAKANA, // 1AFFD..1AFFE
8393 UNKNOWN, // 1AFFF
8394 KATAKANA, // 1B000
8395 HIRAGANA, // 1B001..1B11F
8396 KATAKANA, // 1B120..1B122
8397 UNKNOWN, // 1B123..1B131
8398 HIRAGANA, // 1B132
8399 UNKNOWN, // 1B133..1B14F
8400 HIRAGANA, // 1B150..1B152
8401 UNKNOWN, // 1B153..1B154
8402 KATAKANA, // 1B155
8403 UNKNOWN, // 1B156..1B163
8404 KATAKANA, // 1B164..1B167
8405 UNKNOWN, // 1B168..1B16F
8406 NUSHU, // 1B170..1B2FB
8407 UNKNOWN, // 1B2FC..1BBFF
8408 DUPLOYAN, // 1BC00..1BC6A
8409 UNKNOWN, // 1BC6B..1BC6F
8410 DUPLOYAN, // 1BC70..1BC7C
8411 UNKNOWN, // 1BC7D..1BC7F
8412 DUPLOYAN, // 1BC80..1BC88
8413 UNKNOWN, // 1BC89..1BC8F
8414 DUPLOYAN, // 1BC90..1BC99
8415 UNKNOWN, // 1BC9A..1BC9B
8416 DUPLOYAN, // 1BC9C..1BC9F
8417 COMMON, // 1BCA0..1BCA3
8418 UNKNOWN, // 1BCA4..1CEFF
8419 INHERITED, // 1CF00..1CF2D
8420 UNKNOWN, // 1CF2E..1CF2F
8421 INHERITED, // 1CF30..1CF46
8422 UNKNOWN, // 1CF47..1CF4F
8423 COMMON, // 1CF50..1CFC3
8424 UNKNOWN, // 1CFC4..1CFFF
8425 COMMON, // 1D000..1D0F5
8426 UNKNOWN, // 1D0F6..1D0FF
8427 COMMON, // 1D100..1D126
8428 UNKNOWN, // 1D127..1D128
8429 COMMON, // 1D129..1D166
8430 INHERITED, // 1D167..1D169
8431 COMMON, // 1D16A..1D17A
8432 INHERITED, // 1D17B..1D182
8433 COMMON, // 1D183..1D184
8434 INHERITED, // 1D185..1D18B
8435 COMMON, // 1D18C..1D1A9
8436 INHERITED, // 1D1AA..1D1AD
8437 COMMON, // 1D1AE..1D1EA
8438 UNKNOWN, // 1D1EB..1D1FF
8439 GREEK, // 1D200..1D245
8440 UNKNOWN, // 1D246..1D2BF
8441 COMMON, // 1D2C0..1D2D3
8442 UNKNOWN, // 1D2D4..1D2DF
8443 COMMON, // 1D2E0..1D2F3
8444 UNKNOWN, // 1D2F4..1D2FF
8445 COMMON, // 1D300..1D356
8446 UNKNOWN, // 1D357..1D35F
8447 COMMON, // 1D360..1D378
8448 UNKNOWN, // 1D379..1D3FF
8449 COMMON, // 1D400..1D454
8450 UNKNOWN, // 1D455
8451 COMMON, // 1D456..1D49C
8452 UNKNOWN, // 1D49D
8453 COMMON, // 1D49E..1D49F
8454 UNKNOWN, // 1D4A0..1D4A1
8455 COMMON, // 1D4A2
8456 UNKNOWN, // 1D4A3..1D4A4
8457 COMMON, // 1D4A5..1D4A6
8458 UNKNOWN, // 1D4A7..1D4A8
8459 COMMON, // 1D4A9..1D4AC
8460 UNKNOWN, // 1D4AD
8461 COMMON, // 1D4AE..1D4B9
8462 UNKNOWN, // 1D4BA
8463 COMMON, // 1D4BB
8464 UNKNOWN, // 1D4BC
8465 COMMON, // 1D4BD..1D4C3
8466 UNKNOWN, // 1D4C4
8467 COMMON, // 1D4C5..1D505
8468 UNKNOWN, // 1D506
8469 COMMON, // 1D507..1D50A
8470 UNKNOWN, // 1D50B..1D50C
8471 COMMON, // 1D50D..1D514
8472 UNKNOWN, // 1D515
8473 COMMON, // 1D516..1D51C
8474 UNKNOWN, // 1D51D
8475 COMMON, // 1D51E..1D539
8476 UNKNOWN, // 1D53A
8477 COMMON, // 1D53B..1D53E
8478 UNKNOWN, // 1D53F
8479 COMMON, // 1D540..1D544
8480 UNKNOWN, // 1D545
8481 COMMON, // 1D546
8482 UNKNOWN, // 1D547..1D549
8483 COMMON, // 1D54A..1D550
8484 UNKNOWN, // 1D551
8485 COMMON, // 1D552..1D6A5
8486 UNKNOWN, // 1D6A6..1D6A7
8487 COMMON, // 1D6A8..1D7CB
8488 UNKNOWN, // 1D7CC..1D7CD
8489 COMMON, // 1D7CE..1D7FF
8490 SIGNWRITING, // 1D800..1DA8B
8491 UNKNOWN, // 1DA8C..1DA9A
8492 SIGNWRITING, // 1DA9B..1DA9F
8493 UNKNOWN, // 1DAA0
8494 SIGNWRITING, // 1DAA1..1DAAF
8495 UNKNOWN, // 1DAB0..1DEFF
8496 LATIN, // 1DF00..1DF1E
8497 UNKNOWN, // 1DF1F..1DF24
8498 LATIN, // 1DF25..1DF2A
8499 UNKNOWN, // 1DF2B..1DFFF
8500 GLAGOLITIC, // 1E000..1E006
8501 UNKNOWN, // 1E007
8502 GLAGOLITIC, // 1E008..1E018
8503 UNKNOWN, // 1E019..1E01A
8504 GLAGOLITIC, // 1E01B..1E021
8505 UNKNOWN, // 1E022
8506 GLAGOLITIC, // 1E023..1E024
8507 UNKNOWN, // 1E025
8508 GLAGOLITIC, // 1E026..1E02A
8509 UNKNOWN, // 1E02B..1E02F
8510 CYRILLIC, // 1E030..1E06D
8511 UNKNOWN, // 1E06E..1E08E
8512 CYRILLIC, // 1E08F
8513 UNKNOWN, // 1E090..1E0FF
8514 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8515 UNKNOWN, // 1E12D..1E12F
8516 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8517 UNKNOWN, // 1E13E..1E13F
8518 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8519 UNKNOWN, // 1E14A..1E14D
8520 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8521 UNKNOWN, // 1E150..1E28F
8522 TOTO, // 1E290..1E2AE
8523 UNKNOWN, // 1E2AF..1E2BF
8524 WANCHO, // 1E2C0..1E2F9
8525 UNKNOWN, // 1E2FA..1E2FE
8526 WANCHO, // 1E2FF
8527 UNKNOWN, // 1E300..1E4CF
8528 NAG_MUNDARI, // 1E4D0..1E4F9
8529 UNKNOWN, // 1E4FA..1E7DF
8530 ETHIOPIC, // 1E7E0..1E7E6
8531 UNKNOWN, // 1E7E7
8532 ETHIOPIC, // 1E7E8..1E7EB
8533 UNKNOWN, // 1E7EC
8534 ETHIOPIC, // 1E7ED..1E7EE
8535 UNKNOWN, // 1E7EF
8536 ETHIOPIC, // 1E7F0..1E7FE
8537 UNKNOWN, // 1E7FF
8538 MENDE_KIKAKUI, // 1E800..1E8C4
8539 UNKNOWN, // 1E8C5..1E8C6
8540 MENDE_KIKAKUI, // 1E8C7..1E8D6
8541 UNKNOWN, // 1E8D7..1E8FF
8542 ADLAM, // 1E900..1E94B
8543 UNKNOWN, // 1E94C..1E94F
8544 ADLAM, // 1E950..1E959
8545 UNKNOWN, // 1E95A..1E95D
8546 ADLAM, // 1E95E..1E95F
8547 UNKNOWN, // 1E960..1EC70
8548 COMMON, // 1EC71..1ECB4
8549 UNKNOWN, // 1ECB5..1ED00
8550 COMMON, // 1ED01..1ED3D
8551 UNKNOWN, // 1ED3E..1EDFF
8552 ARABIC, // 1EE00..1EE03
8553 UNKNOWN, // 1EE04
8554 ARABIC, // 1EE05..1EE1F
8555 UNKNOWN, // 1EE20
8556 ARABIC, // 1EE21..1EE22
8557 UNKNOWN, // 1EE23
8558 ARABIC, // 1EE24
8559 UNKNOWN, // 1EE25..1EE26
8560 ARABIC, // 1EE27
8561 UNKNOWN, // 1EE28
8562 ARABIC, // 1EE29..1EE32
8563 UNKNOWN, // 1EE33
8564 ARABIC, // 1EE34..1EE37
8565 UNKNOWN, // 1EE38
8566 ARABIC, // 1EE39
8567 UNKNOWN, // 1EE3A
8568 ARABIC, // 1EE3B
8569 UNKNOWN, // 1EE3C..1EE41
8570 ARABIC, // 1EE42
8571 UNKNOWN, // 1EE43..1EE46
8572 ARABIC, // 1EE47
8573 UNKNOWN, // 1EE48
8574 ARABIC, // 1EE49
8575 UNKNOWN, // 1EE4A
8576 ARABIC, // 1EE4B
8577 UNKNOWN, // 1EE4C
8578 ARABIC, // 1EE4D..1EE4F
8579 UNKNOWN, // 1EE50
8580 ARABIC, // 1EE51..1EE52
8581 UNKNOWN, // 1EE53
8582 ARABIC, // 1EE54
8583 UNKNOWN, // 1EE55..1EE56
8584 ARABIC, // 1EE57
8585 UNKNOWN, // 1EE58
8586 ARABIC, // 1EE59
8587 UNKNOWN, // 1EE5A
8588 ARABIC, // 1EE5B
8589 UNKNOWN, // 1EE5C
8590 ARABIC, // 1EE5D
8591 UNKNOWN, // 1EE5E
8592 ARABIC, // 1EE5F
8593 UNKNOWN, // 1EE60
8594 ARABIC, // 1EE61..1EE62
8595 UNKNOWN, // 1EE63
8596 ARABIC, // 1EE64
8597 UNKNOWN, // 1EE65..1EE66
8598 ARABIC, // 1EE67..1EE6A
8599 UNKNOWN, // 1EE6B
8600 ARABIC, // 1EE6C..1EE72
8601 UNKNOWN, // 1EE73
8602 ARABIC, // 1EE74..1EE77
8603 UNKNOWN, // 1EE78
8604 ARABIC, // 1EE79..1EE7C
8605 UNKNOWN, // 1EE7D
8606 ARABIC, // 1EE7E
8607 UNKNOWN, // 1EE7F
8608 ARABIC, // 1EE80..1EE89
8609 UNKNOWN, // 1EE8A
8610 ARABIC, // 1EE8B..1EE9B
8611 UNKNOWN, // 1EE9C..1EEA0
8612 ARABIC, // 1EEA1..1EEA3
8613 UNKNOWN, // 1EEA4
8614 ARABIC, // 1EEA5..1EEA9
8615 UNKNOWN, // 1EEAA
8616 ARABIC, // 1EEAB..1EEBB
8617 UNKNOWN, // 1EEBC..1EEEF
8618 ARABIC, // 1EEF0..1EEF1
8619 UNKNOWN, // 1EEF2..1EFFF
8620 COMMON, // 1F000..1F02B
8621 UNKNOWN, // 1F02C..1F02F
8622 COMMON, // 1F030..1F093
8623 UNKNOWN, // 1F094..1F09F
8624 COMMON, // 1F0A0..1F0AE
8625 UNKNOWN, // 1F0AF..1F0B0
8626 COMMON, // 1F0B1..1F0BF
8627 UNKNOWN, // 1F0C0
8628 COMMON, // 1F0C1..1F0CF
8629 UNKNOWN, // 1F0D0
8630 COMMON, // 1F0D1..1F0F5
8631 UNKNOWN, // 1F0F6..1F0FF
8632 COMMON, // 1F100..1F1AD
8633 UNKNOWN, // 1F1AE..1F1E5
8634 COMMON, // 1F1E6..1F1FF
8635 HIRAGANA, // 1F200
8636 COMMON, // 1F201..1F202
8637 UNKNOWN, // 1F203..1F20F
8638 COMMON, // 1F210..1F23B
8639 UNKNOWN, // 1F23C..1F23F
8640 COMMON, // 1F240..1F248
8641 UNKNOWN, // 1F249..1F24F
8642 COMMON, // 1F250..1F251
8643 UNKNOWN, // 1F252..1F25F
8644 COMMON, // 1F260..1F265
8645 UNKNOWN, // 1F266..1F2FF
8646 COMMON, // 1F300..1F6D7
8647 UNKNOWN, // 1F6D8..1F6DB
8648 COMMON, // 1F6DC..1F6EC
8649 UNKNOWN, // 1F6ED..1F6EF
8650 COMMON, // 1F6F0..1F6FC
8651 UNKNOWN, // 1F6FD..1F6FF
8652 COMMON, // 1F700..1F776
8653 UNKNOWN, // 1F777..1F77A
8654 COMMON, // 1F77B..1F7D9
8655 UNKNOWN, // 1F7DA..1F7DF
8656 COMMON, // 1F7E0..1F7EB
8657 UNKNOWN, // 1F7EC..1F7EF
8658 COMMON, // 1F7F0
8659 UNKNOWN, // 1F7F1..1F7FF
8660 COMMON, // 1F800..1F80B
8661 UNKNOWN, // 1F80C..1F80F
8662 COMMON, // 1F810..1F847
8663 UNKNOWN, // 1F848..1F84F
8664 COMMON, // 1F850..1F859
8665 UNKNOWN, // 1F85A..1F85F
8666 COMMON, // 1F860..1F887
8667 UNKNOWN, // 1F888..1F88F
8668 COMMON, // 1F890..1F8AD
8669 UNKNOWN, // 1F8AE..1F8AF
8670 COMMON, // 1F8B0..1F8B1
8671 UNKNOWN, // 1F8B2..1F8FF
8672 COMMON, // 1F900..1FA53
8673 UNKNOWN, // 1FA54..1FA5F
8674 COMMON, // 1FA60..1FA6D
8675 UNKNOWN, // 1FA6E..1FA6F
8676 COMMON, // 1FA70..1FA7C
8677 UNKNOWN, // 1FA7D..1FA7F
8678 COMMON, // 1FA80..1FA88
8679 UNKNOWN, // 1FA89..1FA8F
8680 COMMON, // 1FA90..1FABD
8681 UNKNOWN, // 1FABE
8682 COMMON, // 1FABF..1FAC5
8683 UNKNOWN, // 1FAC6..1FACD
8684 COMMON, // 1FACE..1FADB
8685 UNKNOWN, // 1FADC..1FADF
8686 COMMON, // 1FAE0..1FAE8
8687 UNKNOWN, // 1FAE9..1FAEF
8688 COMMON, // 1FAF0..1FAF8
8689 UNKNOWN, // 1FAF9..1FAFF
8690 COMMON, // 1FB00..1FB92
8691 UNKNOWN, // 1FB93
8692 COMMON, // 1FB94..1FBCA
8693 UNKNOWN, // 1FBCB..1FBEF
8694 COMMON, // 1FBF0..1FBF9
8695 UNKNOWN, // 1FBFA..1FFFF
8696 HAN, // 20000..2A6DF
8697 UNKNOWN, // 2A6E0..2A6FF
8698 HAN, // 2A700..2B739
8699 UNKNOWN, // 2B73A..2B73F
8700 HAN, // 2B740..2B81D
8701 UNKNOWN, // 2B81E..2B81F
8702 HAN, // 2B820..2CEA1
8703 UNKNOWN, // 2CEA2..2CEAF
8704 HAN, // 2CEB0..2EBE0
8705 UNKNOWN, // 2EBE1..2EBEF
8706 HAN, // 2EBF0..2EE5D
8707 UNKNOWN, // 2EE5E..2F7FF
8708 HAN, // 2F800..2FA1D
8709 UNKNOWN, // 2FA1E..2FFFF
8710 HAN, // 30000..3134A
8711 UNKNOWN, // 3134B..3134F
8712 HAN, // 31350..323AF
8713 UNKNOWN, // 323B0..E0000
8714 COMMON, // E0001
8715 UNKNOWN, // E0002..E001F
8716 COMMON, // E0020..E007F
8717 UNKNOWN, // E0080..E00FF
8718 INHERITED, // E0100..E01EF
8719 UNKNOWN, // E01F0..10FFFF
8720 };
8721
8722 private static final HashMap<String, Character.UnicodeScript> aliases;
8723 static {
8724 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
8725 aliases.put("ADLM", ADLAM);
8726 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
8727 aliases.put("AHOM", AHOM);
8728 aliases.put("ARAB", ARABIC);
8729 aliases.put("ARMI", IMPERIAL_ARAMAIC);
8730 aliases.put("ARMN", ARMENIAN);
8731 aliases.put("AVST", AVESTAN);
8732 aliases.put("BALI", BALINESE);
8733 aliases.put("BAMU", BAMUM);
8734 aliases.put("BASS", BASSA_VAH);
8735 aliases.put("BATK", BATAK);
8736 aliases.put("BENG", BENGALI);
8737 aliases.put("BHKS", BHAIKSUKI);
8738 aliases.put("BOPO", BOPOMOFO);
8739 aliases.put("BRAH", BRAHMI);
8740 aliases.put("BRAI", BRAILLE);
8741 aliases.put("BUGI", BUGINESE);
8742 aliases.put("BUHD", BUHID);
8743 aliases.put("CAKM", CHAKMA);
8744 aliases.put("CANS", CANADIAN_ABORIGINAL);
8745 aliases.put("CARI", CARIAN);
8746 aliases.put("CHAM", CHAM);
8747 aliases.put("CHER", CHEROKEE);
8748 aliases.put("CHRS", CHORASMIAN);
8749 aliases.put("COPT", COPTIC);
8750 aliases.put("CPMN", CYPRO_MINOAN);
8751 aliases.put("CPRT", CYPRIOT);
8752 aliases.put("CYRL", CYRILLIC);
8753 aliases.put("DEVA", DEVANAGARI);
8754 aliases.put("DIAK", DIVES_AKURU);
8755 aliases.put("DOGR", DOGRA);
8756 aliases.put("DSRT", DESERET);
8757 aliases.put("DUPL", DUPLOYAN);
8758 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
8759 aliases.put("ELBA", ELBASAN);
8760 aliases.put("ELYM", ELYMAIC);
8761 aliases.put("ETHI", ETHIOPIC);
8762 aliases.put("GEOR", GEORGIAN);
8763 aliases.put("GLAG", GLAGOLITIC);
8764 aliases.put("GONG", GUNJALA_GONDI);
8765 aliases.put("GONM", MASARAM_GONDI);
8766 aliases.put("GOTH", GOTHIC);
8767 aliases.put("GRAN", GRANTHA);
8768 aliases.put("GREK", GREEK);
8769 aliases.put("GUJR", GUJARATI);
8770 aliases.put("GURU", GURMUKHI);
8771 aliases.put("HANG", HANGUL);
8772 aliases.put("HANI", HAN);
8773 aliases.put("HANO", HANUNOO);
8774 aliases.put("HATR", HATRAN);
8775 aliases.put("HEBR", HEBREW);
8776 aliases.put("HIRA", HIRAGANA);
8777 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
8778 aliases.put("HMNG", PAHAWH_HMONG);
8779 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
8780 aliases.put("HUNG", OLD_HUNGARIAN);
8781 aliases.put("ITAL", OLD_ITALIC);
8782 aliases.put("JAVA", JAVANESE);
8783 aliases.put("KALI", KAYAH_LI);
8784 aliases.put("KANA", KATAKANA);
8785 aliases.put("KAWI", KAWI);
8786 aliases.put("KHAR", KHAROSHTHI);
8787 aliases.put("KHMR", KHMER);
8788 aliases.put("KHOJ", KHOJKI);
8789 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
8790 aliases.put("KNDA", KANNADA);
8791 aliases.put("KTHI", KAITHI);
8792 aliases.put("LANA", TAI_THAM);
8793 aliases.put("LAOO", LAO);
8794 aliases.put("LATN", LATIN);
8795 aliases.put("LEPC", LEPCHA);
8796 aliases.put("LIMB", LIMBU);
8797 aliases.put("LINA", LINEAR_A);
8798 aliases.put("LINB", LINEAR_B);
8799 aliases.put("LISU", LISU);
8800 aliases.put("LYCI", LYCIAN);
8801 aliases.put("LYDI", LYDIAN);
8802 aliases.put("MAHJ", MAHAJANI);
8803 aliases.put("MAKA", MAKASAR);
8804 aliases.put("MAND", MANDAIC);
8805 aliases.put("MANI", MANICHAEAN);
8806 aliases.put("MARC", MARCHEN);
8807 aliases.put("MEDF", MEDEFAIDRIN);
8808 aliases.put("MEND", MENDE_KIKAKUI);
8809 aliases.put("MERC", MEROITIC_CURSIVE);
8810 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
8811 aliases.put("MLYM", MALAYALAM);
8812 aliases.put("MODI", MODI);
8813 aliases.put("MONG", MONGOLIAN);
8814 aliases.put("MROO", MRO);
8815 aliases.put("MTEI", MEETEI_MAYEK);
8816 aliases.put("MULT", MULTANI);
8817 aliases.put("MYMR", MYANMAR);
8818 aliases.put("NAGM", NAG_MUNDARI);
8819 aliases.put("NAND", NANDINAGARI);
8820 aliases.put("NARB", OLD_NORTH_ARABIAN);
8821 aliases.put("NBAT", NABATAEAN);
8822 aliases.put("NEWA", NEWA);
8823 aliases.put("NKOO", NKO);
8824 aliases.put("NSHU", NUSHU);
8825 aliases.put("OGAM", OGHAM);
8826 aliases.put("OLCK", OL_CHIKI);
8827 aliases.put("ORKH", OLD_TURKIC);
8828 aliases.put("ORYA", ORIYA);
8829 aliases.put("OSGE", OSAGE);
8830 aliases.put("OSMA", OSMANYA);
8831 aliases.put("OUGR", OLD_UYGHUR);
8832 aliases.put("PALM", PALMYRENE);
8833 aliases.put("PAUC", PAU_CIN_HAU);
8834 aliases.put("PERM", OLD_PERMIC);
8835 aliases.put("PHAG", PHAGS_PA);
8836 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
8837 aliases.put("PHLP", PSALTER_PAHLAVI);
8838 aliases.put("PHNX", PHOENICIAN);
8839 aliases.put("PLRD", MIAO);
8840 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
8841 aliases.put("RJNG", REJANG);
8842 aliases.put("ROHG", HANIFI_ROHINGYA);
8843 aliases.put("RUNR", RUNIC);
8844 aliases.put("SAMR", SAMARITAN);
8845 aliases.put("SARB", OLD_SOUTH_ARABIAN);
8846 aliases.put("SAUR", SAURASHTRA);
8847 aliases.put("SGNW", SIGNWRITING);
8848 aliases.put("SHAW", SHAVIAN);
8849 aliases.put("SHRD", SHARADA);
8850 aliases.put("SIDD", SIDDHAM);
8851 aliases.put("SIND", KHUDAWADI);
8852 aliases.put("SINH", SINHALA);
8853 aliases.put("SOGD", SOGDIAN);
8854 aliases.put("SOGO", OLD_SOGDIAN);
8855 aliases.put("SORA", SORA_SOMPENG);
8856 aliases.put("SOYO", SOYOMBO);
8857 aliases.put("SUND", SUNDANESE);
8858 aliases.put("SYLO", SYLOTI_NAGRI);
8859 aliases.put("SYRC", SYRIAC);
8860 aliases.put("TAGB", TAGBANWA);
8861 aliases.put("TAKR", TAKRI);
8862 aliases.put("TALE", TAI_LE);
8863 aliases.put("TALU", NEW_TAI_LUE);
8864 aliases.put("TAML", TAMIL);
8865 aliases.put("TANG", TANGUT);
8866 aliases.put("TAVT", TAI_VIET);
8867 aliases.put("TELU", TELUGU);
8868 aliases.put("TFNG", TIFINAGH);
8869 aliases.put("TGLG", TAGALOG);
8870 aliases.put("THAA", THAANA);
8871 aliases.put("THAI", THAI);
8872 aliases.put("TIBT", TIBETAN);
8873 aliases.put("TIRH", TIRHUTA);
8874 aliases.put("TNSA", TANGSA);
8875 aliases.put("TOTO", TOTO);
8876 aliases.put("UGAR", UGARITIC);
8877 aliases.put("VAII", VAI);
8878 aliases.put("VITH", VITHKUQI);
8879 aliases.put("WARA", WARANG_CITI);
8880 aliases.put("WCHO", WANCHO);
8881 aliases.put("XPEO", OLD_PERSIAN);
8882 aliases.put("XSUX", CUNEIFORM);
8883 aliases.put("YEZI", YEZIDI);
8884 aliases.put("YIII", YI);
8885 aliases.put("ZANB", ZANABAZAR_SQUARE);
8886 aliases.put("ZINH", INHERITED);
8887 aliases.put("ZYYY", COMMON);
8888 aliases.put("ZZZZ", UNKNOWN);
8889 }
8890
8891 /**
8892 * Returns the enum constant representing the Unicode script of which
8893 * the given character (Unicode code point) is assigned to.
8894 *
8895 * @param codePoint the character (Unicode code point) in question.
8896 * @return The {@code UnicodeScript} constant representing the
8897 * Unicode script of which this character is assigned to.
8898 *
8899 * @throws IllegalArgumentException if the specified
8900 * {@code codePoint} is an invalid Unicode code point.
8901 * @see Character#isValidCodePoint(int)
8902 *
8903 */
8904 public static UnicodeScript of(int codePoint) {
8905 if (!isValidCodePoint(codePoint))
8906 throw new IllegalArgumentException(
8907 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8908 int type = getType(codePoint);
8909 // leave SURROGATE and PRIVATE_USE for table lookup
8910 if (type == UNASSIGNED)
8911 return UNKNOWN;
8912 int index = Arrays.binarySearch(scriptStarts, codePoint);
8913 if (index < 0)
8914 index = -index - 2;
8915 return scripts[index];
8916 }
8917
8918 /**
8919 * Returns the UnicodeScript constant with the given Unicode script
8920 * name or the script name alias. Script names and their aliases are
8921 * determined by The Unicode Standard. The files {@code Scripts.txt}
8922 * and {@code PropertyValueAliases.txt} define script names
8923 * and the script name aliases for a particular version of the
8924 * standard. The {@link Character} class specifies the version of
8925 * the standard that it supports.
8926 * <p>
8927 * Character case is ignored for all of the valid script names.
8928 * The en_US locale's case mapping rules are used to provide
8929 * case-insensitive string comparisons for script name validation.
8930 *
8931 * @param scriptName A {@code UnicodeScript} name.
8932 * @return The {@code UnicodeScript} constant identified
8933 * by {@code scriptName}
8934 * @throws IllegalArgumentException if {@code scriptName} is an
8935 * invalid name
8936 * @throws NullPointerException if {@code scriptName} is null
8937 */
8938 public static final UnicodeScript forName(String scriptName) {
8939 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
8940 //.replace(' ', '_'));
8941 UnicodeScript sc = aliases.get(scriptName);
8942 if (sc != null)
8943 return sc;
8944 return valueOf(scriptName);
8945 }
8946 }
8947
8948 /**
8949 * The value of the {@code Character}.
8950 *
8951 * @serial
8952 */
8953 private final char value;
8954
8955 /** use serialVersionUID from JDK 1.0.2 for interoperability */
8956 @java.io.Serial
8957 private static final long serialVersionUID = 3786198910865385080L;
8958
8959 /**
8960 * Constructs a newly allocated {@code Character} object that
8961 * represents the specified {@code char} value.
8962 *
8963 * @param value the value to be represented by the
8964 * {@code Character} object.
8965 *
8966 * @deprecated
8967 * It is rarely appropriate to use this constructor. The static factory
8968 * {@link #valueOf(char)} is generally a better choice, as it is
8969 * likely to yield significantly better space and time performance.
8970 */
8971 @Deprecated(since="9", forRemoval = true)
8972 public Character(char value) {
8973 this.value = value;
8974 }
8975
8976 private static final class CharacterCache {
8977 private CharacterCache(){}
8978
8979 @Stable
8980 static final Character[] cache;
8981 static Character[] archivedCache;
8982
8983 static {
8984 int size = 127 + 1;
8985
8986 // Load and use the archived cache if it exists
8987 CDS.initializeFromArchive(CharacterCache.class);
8988 if (archivedCache == null || archivedCache.length != size) {
8989 Character[] c = new Character[size];
8990 for (int i = 0; i < size; i++) {
8991 c[i] = new Character((char) i);
8992 }
8993 archivedCache = c;
8994 }
8995 cache = archivedCache;
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) {
9070 return value == ((Character)obj).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 }