1 /*
2 * Copyright (c) 2002, 2025, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import jdk.internal.misc.CDS;
29 import jdk.internal.vm.annotation.IntrinsicCandidate;
30 import jdk.internal.vm.annotation.Stable;
31
32 import java.lang.constant.Constable;
33 import java.lang.constant.DynamicConstantDesc;
34 import java.util.Arrays;
35 import java.util.HashMap;
36 import java.util.Locale;
37 import java.util.Map;
38 import java.util.Objects;
39 import java.util.Optional;
40
41 import static java.lang.constant.ConstantDescs.BSM_EXPLICIT_CAST;
42 import static java.lang.constant.ConstantDescs.CD_char;
43 import static java.lang.constant.ConstantDescs.DEFAULT_NAME;
44
45 /**
46 * The {@code Character} class is the {@linkplain
47 * java.lang##wrapperClass wrapper class} for values of the primitive
48 * type {@code char}. An object of type {@code Character} contains a
49 * single field whose type is {@code char}.
50 *
51 * <p>In addition, this class provides a large number of static methods for
52 * determining a character's category (lowercase letter, digit, etc.)
53 * and for converting characters from uppercase to lowercase and vice
54 * versa.
55 *
56 * <h2><a id="conformance">Unicode Conformance</a></h2>
57 * <p>
58 * The fields and methods of class {@code Character} are defined in terms
59 * of character information from the Unicode Standard, specifically the
60 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
61 * This file specifies properties including name and category for every
62 * assigned Unicode code point or character range. The file is available
63 * from the Unicode Consortium at
64 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
65 * <p>
66 * Character information is based on the Unicode Standard, version 16.0.
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 24</th>
79 * <td>Unicode 16.0</td></tr>
80 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
81 * <td>Unicode 15.1</td></tr>
82 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
83 * <td>Unicode 15.0</td></tr>
84 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
85 * <td>Unicode 14.0</td></tr>
86 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
87 * <td>Unicode 13.0</td></tr>
88 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
89 * <td>Unicode 12.1</td></tr>
90 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
91 * <td>Unicode 11.0</td></tr>
92 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
93 * <td>Unicode 10.0</td></tr>
94 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
95 * <td>Unicode 8.0</td></tr>
96 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
97 * <td>Unicode 6.2</td></tr>
98 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
99 * <td>Unicode 6.0</td></tr>
100 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
101 * <td>Unicode 4.0</td></tr>
102 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
103 * <td>Unicode 3.0</td></tr>
104 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
105 * <td>Unicode 2.0</td></tr>
106 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
107 * <td>Unicode 1.1.5</td></tr>
108 * </tbody>
109 * </table>
110 * Variations from these base Unicode versions, such as recognized appendixes,
111 * are documented elsewhere.
112 * <h2><a id="unicode">Unicode Character Representations</a></h2>
113 *
114 * <p>The {@code char} data type (and therefore the value that a
115 * {@code Character} object encapsulates) are based on the
116 * original Unicode specification, which defined characters as
117 * fixed-width 16-bit entities. The Unicode Standard has since been
118 * changed to allow for characters whose representation requires more
119 * than 16 bits. The range of legal <em>code point</em>s is now
120 * U+0000 to U+10FFFF, known as
121 * <em><a href="https://www.unicode.org/glossary/#unicode_scalar_value">
122 * Unicode scalar value</a></em>.
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/tr44 Unicode Character Database
175 * @author Lee Boynton
176 * @author Guy Steele
177 * @author Akira Tanaka
178 * @author Martin Buchholz
179 * @author Ulf Zibis
180 * @since 1.0
181 */
182 @jdk.internal.ValueBased
183 public final
184 class Character implements java.io.Serializable, Comparable<Character>, Constable {
185 /**
186 * The minimum radix available for conversion to and from strings.
187 * The constant value of this field is the smallest value permitted
188 * for the radix argument in radix-conversion methods such as the
189 * {@code digit} method, the {@code forDigit} method, and the
190 * {@code toString} method of class {@code Integer}.
191 *
192 * @see Character#digit(char, int)
193 * @see Character#forDigit(int, int)
194 * @see Integer#toString(int, int)
195 * @see Integer#valueOf(String)
196 */
197 public static final int MIN_RADIX = 2;
198
199 /**
200 * The maximum radix available for conversion to and from strings.
201 * The constant value of this field is the largest value permitted
202 * for the radix argument in radix-conversion methods such as the
203 * {@code digit} method, the {@code forDigit} method, and the
204 * {@code toString} method of class {@code Integer}.
205 *
206 * @see Character#digit(char, int)
207 * @see Character#forDigit(int, int)
208 * @see Integer#toString(int, int)
209 * @see Integer#valueOf(String)
210 */
211 public static final int MAX_RADIX = 36;
212
213 /**
214 * The constant value of this field is the smallest value of type
215 * {@code char}, {@code '\u005Cu0000'}.
216 *
217 * @since 1.0.2
218 */
219 public static final char MIN_VALUE = '\u0000';
220
221 /**
222 * The constant value of this field is the largest value of type
223 * {@code char}, {@code '\u005CuFFFF'}.
224 *
225 * @since 1.0.2
226 */
227 public static final char MAX_VALUE = '\uFFFF';
228
229 /**
230 * The {@code Class} instance representing the primitive type
231 * {@code char}.
232 *
233 * @since 1.1
234 */
235 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
236
237 /*
238 * Normative general types
239 */
240
241 /*
242 * General character types
243 */
244
245 /**
246 * General category "Cn" in the Unicode specification.
247 * @since 1.1
248 */
249 public static final byte UNASSIGNED = 0;
250
251 /**
252 * General category "Lu" in the Unicode specification.
253 * @since 1.1
254 */
255 public static final byte UPPERCASE_LETTER = 1;
256
257 /**
258 * General category "Ll" in the Unicode specification.
259 * @since 1.1
260 */
261 public static final byte LOWERCASE_LETTER = 2;
262
263 /**
264 * General category "Lt" in the Unicode specification.
265 * @since 1.1
266 */
267 public static final byte TITLECASE_LETTER = 3;
268
269 /**
270 * General category "Lm" in the Unicode specification.
271 * @since 1.1
272 */
273 public static final byte MODIFIER_LETTER = 4;
274
275 /**
276 * General category "Lo" in the Unicode specification.
277 * @since 1.1
278 */
279 public static final byte OTHER_LETTER = 5;
280
281 /**
282 * General category "Mn" in the Unicode specification.
283 * @since 1.1
284 */
285 public static final byte NON_SPACING_MARK = 6;
286
287 /**
288 * General category "Me" in the Unicode specification.
289 * @since 1.1
290 */
291 public static final byte ENCLOSING_MARK = 7;
292
293 /**
294 * General category "Mc" in the Unicode specification.
295 * @since 1.1
296 */
297 public static final byte COMBINING_SPACING_MARK = 8;
298
299 /**
300 * General category "Nd" in the Unicode specification.
301 * @since 1.1
302 */
303 public static final byte DECIMAL_DIGIT_NUMBER = 9;
304
305 /**
306 * General category "Nl" in the Unicode specification.
307 * @since 1.1
308 */
309 public static final byte LETTER_NUMBER = 10;
310
311 /**
312 * General category "No" in the Unicode specification.
313 * @since 1.1
314 */
315 public static final byte OTHER_NUMBER = 11;
316
317 /**
318 * General category "Zs" in the Unicode specification.
319 * @since 1.1
320 */
321 public static final byte SPACE_SEPARATOR = 12;
322
323 /**
324 * General category "Zl" in the Unicode specification.
325 * @since 1.1
326 */
327 public static final byte LINE_SEPARATOR = 13;
328
329 /**
330 * General category "Zp" in the Unicode specification.
331 * @since 1.1
332 */
333 public static final byte PARAGRAPH_SEPARATOR = 14;
334
335 /**
336 * General category "Cc" in the Unicode specification.
337 * @since 1.1
338 */
339 public static final byte CONTROL = 15;
340
341 /**
342 * General category "Cf" in the Unicode specification.
343 * @since 1.1
344 */
345 public static final byte FORMAT = 16;
346
347 /**
348 * General category "Co" in the Unicode specification.
349 * @since 1.1
350 */
351 public static final byte PRIVATE_USE = 18;
352
353 /**
354 * General category "Cs" in the Unicode specification.
355 * @since 1.1
356 */
357 public static final byte SURROGATE = 19;
358
359 /**
360 * General category "Pd" in the Unicode specification.
361 * @since 1.1
362 */
363 public static final byte DASH_PUNCTUATION = 20;
364
365 /**
366 * General category "Ps" in the Unicode specification.
367 * @since 1.1
368 */
369 public static final byte START_PUNCTUATION = 21;
370
371 /**
372 * General category "Pe" in the Unicode specification.
373 * @since 1.1
374 */
375 public static final byte END_PUNCTUATION = 22;
376
377 /**
378 * General category "Pc" in the Unicode specification.
379 * @since 1.1
380 */
381 public static final byte CONNECTOR_PUNCTUATION = 23;
382
383 /**
384 * General category "Po" in the Unicode specification.
385 * @since 1.1
386 */
387 public static final byte OTHER_PUNCTUATION = 24;
388
389 /**
390 * General category "Sm" in the Unicode specification.
391 * @since 1.1
392 */
393 public static final byte MATH_SYMBOL = 25;
394
395 /**
396 * General category "Sc" in the Unicode specification.
397 * @since 1.1
398 */
399 public static final byte CURRENCY_SYMBOL = 26;
400
401 /**
402 * General category "Sk" in the Unicode specification.
403 * @since 1.1
404 */
405 public static final byte MODIFIER_SYMBOL = 27;
406
407 /**
408 * General category "So" in the Unicode specification.
409 * @since 1.1
410 */
411 public static final byte OTHER_SYMBOL = 28;
412
413 /**
414 * General category "Pi" in the Unicode specification.
415 * @since 1.4
416 */
417 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
418
419 /**
420 * General category "Pf" in the Unicode specification.
421 * @since 1.4
422 */
423 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
424
425 /**
426 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
427 */
428 static final int ERROR = 0xFFFFFFFF;
429
430
431 /**
432 * Undefined bidirectional character type. Undefined {@code char}
433 * values have undefined directionality in the Unicode specification.
434 * @since 1.4
435 */
436 public static final byte DIRECTIONALITY_UNDEFINED = -1;
437
438 /**
439 * Strong bidirectional character type "L" in the Unicode specification.
440 * @since 1.4
441 */
442 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
443
444 /**
445 * Strong bidirectional character type "R" in the Unicode specification.
446 * @since 1.4
447 */
448 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
449
450 /**
451 * Strong bidirectional character type "AL" in the Unicode specification.
452 * @since 1.4
453 */
454 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
455
456 /**
457 * Weak bidirectional character type "EN" in the Unicode specification.
458 * @since 1.4
459 */
460 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
461
462 /**
463 * Weak bidirectional character type "ES" in the Unicode specification.
464 * @since 1.4
465 */
466 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
467
468 /**
469 * Weak bidirectional character type "ET" in the Unicode specification.
470 * @since 1.4
471 */
472 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
473
474 /**
475 * Weak bidirectional character type "AN" in the Unicode specification.
476 * @since 1.4
477 */
478 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
479
480 /**
481 * Weak bidirectional character type "CS" in the Unicode specification.
482 * @since 1.4
483 */
484 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
485
486 /**
487 * Weak bidirectional character type "NSM" in the Unicode specification.
488 * @since 1.4
489 */
490 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
491
492 /**
493 * Weak bidirectional character type "BN" in the Unicode specification.
494 * @since 1.4
495 */
496 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
497
498 /**
499 * Neutral bidirectional character type "B" in the Unicode specification.
500 * @since 1.4
501 */
502 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
503
504 /**
505 * Neutral bidirectional character type "S" in the Unicode specification.
506 * @since 1.4
507 */
508 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
509
510 /**
511 * Neutral bidirectional character type "WS" in the Unicode specification.
512 * @since 1.4
513 */
514 public static final byte DIRECTIONALITY_WHITESPACE = 12;
515
516 /**
517 * Neutral bidirectional character type "ON" in the Unicode specification.
518 * @since 1.4
519 */
520 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
521
522 /**
523 * Strong bidirectional character type "LRE" in the Unicode specification.
524 * @since 1.4
525 */
526 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
527
528 /**
529 * Strong bidirectional character type "LRO" in the Unicode specification.
530 * @since 1.4
531 */
532 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
533
534 /**
535 * Strong bidirectional character type "RLE" in the Unicode specification.
536 * @since 1.4
537 */
538 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
539
540 /**
541 * Strong bidirectional character type "RLO" in the Unicode specification.
542 * @since 1.4
543 */
544 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
545
546 /**
547 * Weak bidirectional character type "PDF" in the Unicode specification.
548 * @since 1.4
549 */
550 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
551
552 /**
553 * Weak bidirectional character type "LRI" in the Unicode specification.
554 * @since 9
555 */
556 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
557
558 /**
559 * Weak bidirectional character type "RLI" in the Unicode specification.
560 * @since 9
561 */
562 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
563
564 /**
565 * Weak bidirectional character type "FSI" in the Unicode specification.
566 * @since 9
567 */
568 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
569
570 /**
571 * Weak bidirectional character type "PDI" in the Unicode specification.
572 * @since 9
573 */
574 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
575
576 /**
577 * The minimum value of a
578 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
579 * Unicode high-surrogate code unit</a>
580 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
581 * A high-surrogate is also known as a <i>leading-surrogate</i>.
582 *
583 * @since 1.5
584 */
585 public static final char MIN_HIGH_SURROGATE = '\uD800';
586
587 /**
588 * The maximum value of a
589 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
590 * Unicode high-surrogate code unit</a>
591 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
592 * A high-surrogate is also known as a <i>leading-surrogate</i>.
593 *
594 * @since 1.5
595 */
596 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
597
598 /**
599 * The minimum value of a
600 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
601 * Unicode low-surrogate code unit</a>
602 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
603 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
604 *
605 * @since 1.5
606 */
607 public static final char MIN_LOW_SURROGATE = '\uDC00';
608
609 /**
610 * The maximum value of a
611 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
612 * Unicode low-surrogate code unit</a>
613 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
614 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
615 *
616 * @since 1.5
617 */
618 public static final char MAX_LOW_SURROGATE = '\uDFFF';
619
620 /**
621 * The minimum value of a Unicode surrogate code unit in the
622 * UTF-16 encoding, constant {@code '\u005CuD800'}.
623 *
624 * @since 1.5
625 */
626 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
627
628 /**
629 * The maximum value of a Unicode surrogate code unit in the
630 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
631 *
632 * @since 1.5
633 */
634 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
635
636 /**
637 * The minimum value of a
638 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
639 * Unicode supplementary code point</a>, constant {@code U+10000}.
640 *
641 * @since 1.5
642 */
643 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
644
645 /**
646 * The minimum value of a
647 * <a href="http://www.unicode.org/glossary/#code_point">
648 * Unicode code point</a>, constant {@code U+0000}.
649 *
650 * @since 1.5
651 */
652 public static final int MIN_CODE_POINT = 0x000000;
653
654 /**
655 * The maximum value of a
656 * <a href="http://www.unicode.org/glossary/#code_point">
657 * Unicode code point</a>, constant {@code U+10FFFF}.
658 *
659 * @since 1.5
660 */
661 public static final int MAX_CODE_POINT = 0X10FFFF;
662
663 /**
664 * Returns an {@link Optional} containing the nominal descriptor for this
665 * instance.
666 *
667 * @return an {@link Optional} describing the {@linkplain Character} instance
668 * @since 15
669 */
670 @Override
671 public Optional<DynamicConstantDesc<Character>> describeConstable() {
672 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
673 }
674
675 /**
676 * Instances of this class represent particular subsets of the Unicode
677 * character set. The only family of subsets defined in the
678 * {@code Character} class is {@link Character.UnicodeBlock}.
679 * Other portions of the Java API may define other subsets for their
680 * own purposes.
681 *
682 * @since 1.2
683 */
684 public static class Subset {
685
686 private String name;
687
688 /**
689 * Constructs a new {@code Subset} instance.
690 *
691 * @param name The name of this subset
692 * @throws NullPointerException if name is {@code null}
693 */
694 protected Subset(String name) {
695 if (name == null) {
696 throw new NullPointerException("name");
697 }
698 this.name = name;
699 }
700
701 /**
702 * Compares two {@code Subset} objects for equality.
703 * This method returns {@code true} if and only if
704 * {@code this} and the argument refer to the same
705 * object; since this method is {@code final}, this
706 * guarantee holds for all subclasses.
707 */
708 public final boolean equals(Object obj) {
709 return (this == obj);
710 }
711
712 /**
713 * Returns the standard hash code as defined by the
714 * {@link Object#hashCode} method. This method
715 * is {@code final} in order to ensure that the
716 * {@code equals} and {@code hashCode} methods will
717 * be consistent in all subclasses.
718 */
719 public final int hashCode() {
720 return super.hashCode();
721 }
722
723 /**
724 * Returns the name of this subset.
725 */
726 public final String toString() {
727 return name;
728 }
729 }
730
731 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
732 // for the latest specification of Unicode Blocks.
733
734 /**
735 * A family of character subsets representing the character blocks in the
736 * Unicode specification. Character blocks generally define characters
737 * used for a specific script or purpose. A character is contained by
738 * at most one Unicode block.
739 *
740 * @since 1.2
741 */
742 public static final class UnicodeBlock extends Subset {
743 /**
744 * NUM_ENTITIES should match the total number of UnicodeBlocks.
745 * It should be adjusted whenever the Unicode Character Database
746 * is upgraded.
747 */
748 private static final int NUM_ENTITIES = 782;
749 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
750
751 /**
752 * Creates a UnicodeBlock with the given identifier name.
753 * This name must be the same as the block identifier.
754 */
755 private UnicodeBlock(String idName) {
756 super(idName);
757 map.put(idName, this);
758 }
759
760 /**
761 * Creates a UnicodeBlock with the given identifier name and
762 * alias name.
763 */
764 private UnicodeBlock(String idName, String alias) {
765 this(idName);
766 map.put(alias, this);
767 }
768
769 /**
770 * Creates a UnicodeBlock with the given identifier name and
771 * alias names.
772 */
773 private UnicodeBlock(String idName, String... aliases) {
774 this(idName);
775 for (String alias : aliases)
776 map.put(alias, this);
777 }
778
779 /**
780 * Constant for the "Basic Latin" Unicode character block.
781 * @since 1.2
782 */
783 public static final UnicodeBlock BASIC_LATIN =
784 new UnicodeBlock("BASIC_LATIN",
785 "BASIC LATIN",
786 "BASICLATIN");
787
788 /**
789 * Constant for the "Latin-1 Supplement" Unicode character block.
790 * @since 1.2
791 */
792 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
793 new UnicodeBlock("LATIN_1_SUPPLEMENT",
794 "LATIN-1 SUPPLEMENT",
795 "LATIN-1SUPPLEMENT");
796
797 /**
798 * Constant for the "Latin Extended-A" Unicode character block.
799 * @since 1.2
800 */
801 public static final UnicodeBlock LATIN_EXTENDED_A =
802 new UnicodeBlock("LATIN_EXTENDED_A",
803 "LATIN EXTENDED-A",
804 "LATINEXTENDED-A");
805
806 /**
807 * Constant for the "Latin Extended-B" Unicode character block.
808 * @since 1.2
809 */
810 public static final UnicodeBlock LATIN_EXTENDED_B =
811 new UnicodeBlock("LATIN_EXTENDED_B",
812 "LATIN EXTENDED-B",
813 "LATINEXTENDED-B");
814
815 /**
816 * Constant for the "IPA Extensions" Unicode character block.
817 * @since 1.2
818 */
819 public static final UnicodeBlock IPA_EXTENSIONS =
820 new UnicodeBlock("IPA_EXTENSIONS",
821 "IPA EXTENSIONS",
822 "IPAEXTENSIONS");
823
824 /**
825 * Constant for the "Spacing Modifier Letters" Unicode character block.
826 * @since 1.2
827 */
828 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
829 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
830 "SPACING MODIFIER LETTERS",
831 "SPACINGMODIFIERLETTERS");
832
833 /**
834 * Constant for the "Combining Diacritical Marks" Unicode character block.
835 * @since 1.2
836 */
837 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
838 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
839 "COMBINING DIACRITICAL MARKS",
840 "COMBININGDIACRITICALMARKS");
841
842 /**
843 * Constant for the "Greek and Coptic" Unicode character block.
844 * <p>
845 * This block was previously known as the "Greek" block.
846 *
847 * @since 1.2
848 */
849 public static final UnicodeBlock GREEK =
850 new UnicodeBlock("GREEK",
851 "GREEK AND COPTIC",
852 "GREEKANDCOPTIC");
853
854 /**
855 * Constant for the "Cyrillic" Unicode character block.
856 * @since 1.2
857 */
858 public static final UnicodeBlock CYRILLIC =
859 new UnicodeBlock("CYRILLIC");
860
861 /**
862 * Constant for the "Armenian" Unicode character block.
863 * @since 1.2
864 */
865 public static final UnicodeBlock ARMENIAN =
866 new UnicodeBlock("ARMENIAN");
867
868 /**
869 * Constant for the "Hebrew" Unicode character block.
870 * @since 1.2
871 */
872 public static final UnicodeBlock HEBREW =
873 new UnicodeBlock("HEBREW");
874
875 /**
876 * Constant for the "Arabic" Unicode character block.
877 * @since 1.2
878 */
879 public static final UnicodeBlock ARABIC =
880 new UnicodeBlock("ARABIC");
881
882 /**
883 * Constant for the "Devanagari" Unicode character block.
884 * @since 1.2
885 */
886 public static final UnicodeBlock DEVANAGARI =
887 new UnicodeBlock("DEVANAGARI");
888
889 /**
890 * Constant for the "Bengali" Unicode character block.
891 * @since 1.2
892 */
893 public static final UnicodeBlock BENGALI =
894 new UnicodeBlock("BENGALI");
895
896 /**
897 * Constant for the "Gurmukhi" Unicode character block.
898 * @since 1.2
899 */
900 public static final UnicodeBlock GURMUKHI =
901 new UnicodeBlock("GURMUKHI");
902
903 /**
904 * Constant for the "Gujarati" Unicode character block.
905 * @since 1.2
906 */
907 public static final UnicodeBlock GUJARATI =
908 new UnicodeBlock("GUJARATI");
909
910 /**
911 * Constant for the "Oriya" Unicode character block.
912 * @since 1.2
913 */
914 public static final UnicodeBlock ORIYA =
915 new UnicodeBlock("ORIYA");
916
917 /**
918 * Constant for the "Tamil" Unicode character block.
919 * @since 1.2
920 */
921 public static final UnicodeBlock TAMIL =
922 new UnicodeBlock("TAMIL");
923
924 /**
925 * Constant for the "Telugu" Unicode character block.
926 * @since 1.2
927 */
928 public static final UnicodeBlock TELUGU =
929 new UnicodeBlock("TELUGU");
930
931 /**
932 * Constant for the "Kannada" Unicode character block.
933 * @since 1.2
934 */
935 public static final UnicodeBlock KANNADA =
936 new UnicodeBlock("KANNADA");
937
938 /**
939 * Constant for the "Malayalam" Unicode character block.
940 * @since 1.2
941 */
942 public static final UnicodeBlock MALAYALAM =
943 new UnicodeBlock("MALAYALAM");
944
945 /**
946 * Constant for the "Thai" Unicode character block.
947 * @since 1.2
948 */
949 public static final UnicodeBlock THAI =
950 new UnicodeBlock("THAI");
951
952 /**
953 * Constant for the "Lao" Unicode character block.
954 * @since 1.2
955 */
956 public static final UnicodeBlock LAO =
957 new UnicodeBlock("LAO");
958
959 /**
960 * Constant for the "Tibetan" Unicode character block.
961 * @since 1.2
962 */
963 public static final UnicodeBlock TIBETAN =
964 new UnicodeBlock("TIBETAN");
965
966 /**
967 * Constant for the "Georgian" Unicode character block.
968 * @since 1.2
969 */
970 public static final UnicodeBlock GEORGIAN =
971 new UnicodeBlock("GEORGIAN");
972
973 /**
974 * Constant for the "Hangul Jamo" Unicode character block.
975 * @since 1.2
976 */
977 public static final UnicodeBlock HANGUL_JAMO =
978 new UnicodeBlock("HANGUL_JAMO",
979 "HANGUL JAMO",
980 "HANGULJAMO");
981
982 /**
983 * Constant for the "Latin Extended Additional" Unicode character block.
984 * @since 1.2
985 */
986 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
987 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
988 "LATIN EXTENDED ADDITIONAL",
989 "LATINEXTENDEDADDITIONAL");
990
991 /**
992 * Constant for the "Greek Extended" Unicode character block.
993 * @since 1.2
994 */
995 public static final UnicodeBlock GREEK_EXTENDED =
996 new UnicodeBlock("GREEK_EXTENDED",
997 "GREEK EXTENDED",
998 "GREEKEXTENDED");
999
1000 /**
1001 * Constant for the "General Punctuation" Unicode character block.
1002 * @since 1.2
1003 */
1004 public static final UnicodeBlock GENERAL_PUNCTUATION =
1005 new UnicodeBlock("GENERAL_PUNCTUATION",
1006 "GENERAL PUNCTUATION",
1007 "GENERALPUNCTUATION");
1008
1009 /**
1010 * Constant for the "Superscripts and Subscripts" Unicode character
1011 * block.
1012 * @since 1.2
1013 */
1014 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1015 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1016 "SUPERSCRIPTS AND SUBSCRIPTS",
1017 "SUPERSCRIPTSANDSUBSCRIPTS");
1018
1019 /**
1020 * Constant for the "Currency Symbols" Unicode character block.
1021 * @since 1.2
1022 */
1023 public static final UnicodeBlock CURRENCY_SYMBOLS =
1024 new UnicodeBlock("CURRENCY_SYMBOLS",
1025 "CURRENCY SYMBOLS",
1026 "CURRENCYSYMBOLS");
1027
1028 /**
1029 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1030 * character block.
1031 * <p>
1032 * This block was previously known as "Combining Marks for Symbols".
1033 * @since 1.2
1034 */
1035 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1036 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1037 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1038 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1039 "COMBINING MARKS FOR SYMBOLS",
1040 "COMBININGMARKSFORSYMBOLS");
1041
1042 /**
1043 * Constant for the "Letterlike Symbols" Unicode character block.
1044 * @since 1.2
1045 */
1046 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1047 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1048 "LETTERLIKE SYMBOLS",
1049 "LETTERLIKESYMBOLS");
1050
1051 /**
1052 * Constant for the "Number Forms" Unicode character block.
1053 * @since 1.2
1054 */
1055 public static final UnicodeBlock NUMBER_FORMS =
1056 new UnicodeBlock("NUMBER_FORMS",
1057 "NUMBER FORMS",
1058 "NUMBERFORMS");
1059
1060 /**
1061 * Constant for the "Arrows" Unicode character block.
1062 * @since 1.2
1063 */
1064 public static final UnicodeBlock ARROWS =
1065 new UnicodeBlock("ARROWS");
1066
1067 /**
1068 * Constant for the "Mathematical Operators" Unicode character block.
1069 * @since 1.2
1070 */
1071 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1072 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1073 "MATHEMATICAL OPERATORS",
1074 "MATHEMATICALOPERATORS");
1075
1076 /**
1077 * Constant for the "Miscellaneous Technical" Unicode character block.
1078 * @since 1.2
1079 */
1080 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1081 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1082 "MISCELLANEOUS TECHNICAL",
1083 "MISCELLANEOUSTECHNICAL");
1084
1085 /**
1086 * Constant for the "Control Pictures" Unicode character block.
1087 * @since 1.2
1088 */
1089 public static final UnicodeBlock CONTROL_PICTURES =
1090 new UnicodeBlock("CONTROL_PICTURES",
1091 "CONTROL PICTURES",
1092 "CONTROLPICTURES");
1093
1094 /**
1095 * Constant for the "Optical Character Recognition" Unicode character block.
1096 * @since 1.2
1097 */
1098 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1099 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1100 "OPTICAL CHARACTER RECOGNITION",
1101 "OPTICALCHARACTERRECOGNITION");
1102
1103 /**
1104 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1105 * @since 1.2
1106 */
1107 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1108 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1109 "ENCLOSED ALPHANUMERICS",
1110 "ENCLOSEDALPHANUMERICS");
1111
1112 /**
1113 * Constant for the "Box Drawing" Unicode character block.
1114 * @since 1.2
1115 */
1116 public static final UnicodeBlock BOX_DRAWING =
1117 new UnicodeBlock("BOX_DRAWING",
1118 "BOX DRAWING",
1119 "BOXDRAWING");
1120
1121 /**
1122 * Constant for the "Block Elements" Unicode character block.
1123 * @since 1.2
1124 */
1125 public static final UnicodeBlock BLOCK_ELEMENTS =
1126 new UnicodeBlock("BLOCK_ELEMENTS",
1127 "BLOCK ELEMENTS",
1128 "BLOCKELEMENTS");
1129
1130 /**
1131 * Constant for the "Geometric Shapes" Unicode character block.
1132 * @since 1.2
1133 */
1134 public static final UnicodeBlock GEOMETRIC_SHAPES =
1135 new UnicodeBlock("GEOMETRIC_SHAPES",
1136 "GEOMETRIC SHAPES",
1137 "GEOMETRICSHAPES");
1138
1139 /**
1140 * Constant for the "Miscellaneous Symbols" Unicode character block.
1141 * @since 1.2
1142 */
1143 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1144 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1145 "MISCELLANEOUS SYMBOLS",
1146 "MISCELLANEOUSSYMBOLS");
1147
1148 /**
1149 * Constant for the "Dingbats" Unicode character block.
1150 * @since 1.2
1151 */
1152 public static final UnicodeBlock DINGBATS =
1153 new UnicodeBlock("DINGBATS");
1154
1155 /**
1156 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1157 * @since 1.2
1158 */
1159 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1160 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1161 "CJK SYMBOLS AND PUNCTUATION",
1162 "CJKSYMBOLSANDPUNCTUATION");
1163
1164 /**
1165 * Constant for the "Hiragana" Unicode character block.
1166 * @since 1.2
1167 */
1168 public static final UnicodeBlock HIRAGANA =
1169 new UnicodeBlock("HIRAGANA");
1170
1171 /**
1172 * Constant for the "Katakana" Unicode character block.
1173 * @since 1.2
1174 */
1175 public static final UnicodeBlock KATAKANA =
1176 new UnicodeBlock("KATAKANA");
1177
1178 /**
1179 * Constant for the "Bopomofo" Unicode character block.
1180 * @since 1.2
1181 */
1182 public static final UnicodeBlock BOPOMOFO =
1183 new UnicodeBlock("BOPOMOFO");
1184
1185 /**
1186 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1187 * @since 1.2
1188 */
1189 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1190 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1191 "HANGUL COMPATIBILITY JAMO",
1192 "HANGULCOMPATIBILITYJAMO");
1193
1194 /**
1195 * Constant for the "Kanbun" Unicode character block.
1196 * @since 1.2
1197 */
1198 public static final UnicodeBlock KANBUN =
1199 new UnicodeBlock("KANBUN");
1200
1201 /**
1202 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1203 * @since 1.2
1204 */
1205 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1206 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1207 "ENCLOSED CJK LETTERS AND MONTHS",
1208 "ENCLOSEDCJKLETTERSANDMONTHS");
1209
1210 /**
1211 * Constant for the "CJK Compatibility" Unicode character block.
1212 * @since 1.2
1213 */
1214 public static final UnicodeBlock CJK_COMPATIBILITY =
1215 new UnicodeBlock("CJK_COMPATIBILITY",
1216 "CJK COMPATIBILITY",
1217 "CJKCOMPATIBILITY");
1218
1219 /**
1220 * Constant for the "CJK Unified Ideographs" Unicode character block.
1221 * @since 1.2
1222 */
1223 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1224 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1225 "CJK UNIFIED IDEOGRAPHS",
1226 "CJKUNIFIEDIDEOGRAPHS");
1227
1228 /**
1229 * Constant for the "Hangul Syllables" Unicode character block.
1230 * @since 1.2
1231 */
1232 public static final UnicodeBlock HANGUL_SYLLABLES =
1233 new UnicodeBlock("HANGUL_SYLLABLES",
1234 "HANGUL SYLLABLES",
1235 "HANGULSYLLABLES");
1236
1237 /**
1238 * Constant for the "Private Use Area" Unicode character block.
1239 * @since 1.2
1240 */
1241 public static final UnicodeBlock PRIVATE_USE_AREA =
1242 new UnicodeBlock("PRIVATE_USE_AREA",
1243 "PRIVATE USE AREA",
1244 "PRIVATEUSEAREA");
1245
1246 /**
1247 * Constant for the "CJK Compatibility Ideographs" Unicode character
1248 * block.
1249 * @since 1.2
1250 */
1251 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1252 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1253 "CJK COMPATIBILITY IDEOGRAPHS",
1254 "CJKCOMPATIBILITYIDEOGRAPHS");
1255
1256 /**
1257 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1258 * @since 1.2
1259 */
1260 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1261 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1262 "ALPHABETIC PRESENTATION FORMS",
1263 "ALPHABETICPRESENTATIONFORMS");
1264
1265 /**
1266 * Constant for the "Arabic Presentation Forms-A" Unicode character
1267 * block.
1268 * @since 1.2
1269 */
1270 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1271 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1272 "ARABIC PRESENTATION FORMS-A",
1273 "ARABICPRESENTATIONFORMS-A");
1274
1275 /**
1276 * Constant for the "Combining Half Marks" Unicode character block.
1277 * @since 1.2
1278 */
1279 public static final UnicodeBlock COMBINING_HALF_MARKS =
1280 new UnicodeBlock("COMBINING_HALF_MARKS",
1281 "COMBINING HALF MARKS",
1282 "COMBININGHALFMARKS");
1283
1284 /**
1285 * Constant for the "CJK Compatibility Forms" Unicode character block.
1286 * @since 1.2
1287 */
1288 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1289 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1290 "CJK COMPATIBILITY FORMS",
1291 "CJKCOMPATIBILITYFORMS");
1292
1293 /**
1294 * Constant for the "Small Form Variants" Unicode character block.
1295 * @since 1.2
1296 */
1297 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1298 new UnicodeBlock("SMALL_FORM_VARIANTS",
1299 "SMALL FORM VARIANTS",
1300 "SMALLFORMVARIANTS");
1301
1302 /**
1303 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1304 * @since 1.2
1305 */
1306 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1307 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1308 "ARABIC PRESENTATION FORMS-B",
1309 "ARABICPRESENTATIONFORMS-B");
1310
1311 /**
1312 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1313 * block.
1314 * @since 1.2
1315 */
1316 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1317 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1318 "HALFWIDTH AND FULLWIDTH FORMS",
1319 "HALFWIDTHANDFULLWIDTHFORMS");
1320
1321 /**
1322 * Constant for the "Specials" Unicode character block.
1323 * @since 1.2
1324 */
1325 public static final UnicodeBlock SPECIALS =
1326 new UnicodeBlock("SPECIALS");
1327
1328 /**
1329 * @deprecated
1330 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1331 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1332 * These constants match the block definitions of the Unicode Standard.
1333 * The {@link #of(char)} and {@link #of(int)} methods return the
1334 * standard constants.
1335 */
1336 @Deprecated(since="1.5")
1337 public static final UnicodeBlock SURROGATES_AREA =
1338 new UnicodeBlock("SURROGATES_AREA");
1339
1340 /**
1341 * Constant for the "Syriac" Unicode character block.
1342 * @since 1.4
1343 */
1344 public static final UnicodeBlock SYRIAC =
1345 new UnicodeBlock("SYRIAC");
1346
1347 /**
1348 * Constant for the "Thaana" Unicode character block.
1349 * @since 1.4
1350 */
1351 public static final UnicodeBlock THAANA =
1352 new UnicodeBlock("THAANA");
1353
1354 /**
1355 * Constant for the "Sinhala" Unicode character block.
1356 * @since 1.4
1357 */
1358 public static final UnicodeBlock SINHALA =
1359 new UnicodeBlock("SINHALA");
1360
1361 /**
1362 * Constant for the "Myanmar" Unicode character block.
1363 * @since 1.4
1364 */
1365 public static final UnicodeBlock MYANMAR =
1366 new UnicodeBlock("MYANMAR");
1367
1368 /**
1369 * Constant for the "Ethiopic" Unicode character block.
1370 * @since 1.4
1371 */
1372 public static final UnicodeBlock ETHIOPIC =
1373 new UnicodeBlock("ETHIOPIC");
1374
1375 /**
1376 * Constant for the "Cherokee" Unicode character block.
1377 * @since 1.4
1378 */
1379 public static final UnicodeBlock CHEROKEE =
1380 new UnicodeBlock("CHEROKEE");
1381
1382 /**
1383 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1384 * @since 1.4
1385 */
1386 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1387 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1388 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1389 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1390
1391 /**
1392 * Constant for the "Ogham" Unicode character block.
1393 * @since 1.4
1394 */
1395 public static final UnicodeBlock OGHAM =
1396 new UnicodeBlock("OGHAM");
1397
1398 /**
1399 * Constant for the "Runic" Unicode character block.
1400 * @since 1.4
1401 */
1402 public static final UnicodeBlock RUNIC =
1403 new UnicodeBlock("RUNIC");
1404
1405 /**
1406 * Constant for the "Khmer" Unicode character block.
1407 * @since 1.4
1408 */
1409 public static final UnicodeBlock KHMER =
1410 new UnicodeBlock("KHMER");
1411
1412 /**
1413 * Constant for the "Mongolian" Unicode character block.
1414 * @since 1.4
1415 */
1416 public static final UnicodeBlock MONGOLIAN =
1417 new UnicodeBlock("MONGOLIAN");
1418
1419 /**
1420 * Constant for the "Braille Patterns" Unicode character block.
1421 * @since 1.4
1422 */
1423 public static final UnicodeBlock BRAILLE_PATTERNS =
1424 new UnicodeBlock("BRAILLE_PATTERNS",
1425 "BRAILLE PATTERNS",
1426 "BRAILLEPATTERNS");
1427
1428 /**
1429 * Constant for the "CJK Radicals Supplement" Unicode character block.
1430 * @since 1.4
1431 */
1432 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1433 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1434 "CJK RADICALS SUPPLEMENT",
1435 "CJKRADICALSSUPPLEMENT");
1436
1437 /**
1438 * Constant for the "Kangxi Radicals" Unicode character block.
1439 * @since 1.4
1440 */
1441 public static final UnicodeBlock KANGXI_RADICALS =
1442 new UnicodeBlock("KANGXI_RADICALS",
1443 "KANGXI RADICALS",
1444 "KANGXIRADICALS");
1445
1446 /**
1447 * Constant for the "Ideographic Description Characters" Unicode character block.
1448 * @since 1.4
1449 */
1450 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1451 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1452 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1453 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1454
1455 /**
1456 * Constant for the "Bopomofo Extended" Unicode character block.
1457 * @since 1.4
1458 */
1459 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1460 new UnicodeBlock("BOPOMOFO_EXTENDED",
1461 "BOPOMOFO EXTENDED",
1462 "BOPOMOFOEXTENDED");
1463
1464 /**
1465 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1466 * @since 1.4
1467 */
1468 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1469 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1470 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1471 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1472
1473 /**
1474 * Constant for the "Yi Syllables" Unicode character block.
1475 * @since 1.4
1476 */
1477 public static final UnicodeBlock YI_SYLLABLES =
1478 new UnicodeBlock("YI_SYLLABLES",
1479 "YI SYLLABLES",
1480 "YISYLLABLES");
1481
1482 /**
1483 * Constant for the "Yi Radicals" Unicode character block.
1484 * @since 1.4
1485 */
1486 public static final UnicodeBlock YI_RADICALS =
1487 new UnicodeBlock("YI_RADICALS",
1488 "YI RADICALS",
1489 "YIRADICALS");
1490
1491 /**
1492 * Constant for the "Cyrillic Supplement" Unicode character block.
1493 * This block was previously known as the "Cyrillic Supplementary" block.
1494 * @since 1.5
1495 */
1496 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1497 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1498 "CYRILLIC SUPPLEMENTARY",
1499 "CYRILLICSUPPLEMENTARY",
1500 "CYRILLIC SUPPLEMENT",
1501 "CYRILLICSUPPLEMENT");
1502
1503 /**
1504 * Constant for the "Tagalog" Unicode character block.
1505 * @since 1.5
1506 */
1507 public static final UnicodeBlock TAGALOG =
1508 new UnicodeBlock("TAGALOG");
1509
1510 /**
1511 * Constant for the "Hanunoo" Unicode character block.
1512 * @since 1.5
1513 */
1514 public static final UnicodeBlock HANUNOO =
1515 new UnicodeBlock("HANUNOO");
1516
1517 /**
1518 * Constant for the "Buhid" Unicode character block.
1519 * @since 1.5
1520 */
1521 public static final UnicodeBlock BUHID =
1522 new UnicodeBlock("BUHID");
1523
1524 /**
1525 * Constant for the "Tagbanwa" Unicode character block.
1526 * @since 1.5
1527 */
1528 public static final UnicodeBlock TAGBANWA =
1529 new UnicodeBlock("TAGBANWA");
1530
1531 /**
1532 * Constant for the "Limbu" Unicode character block.
1533 * @since 1.5
1534 */
1535 public static final UnicodeBlock LIMBU =
1536 new UnicodeBlock("LIMBU");
1537
1538 /**
1539 * Constant for the "Tai Le" Unicode character block.
1540 * @since 1.5
1541 */
1542 public static final UnicodeBlock TAI_LE =
1543 new UnicodeBlock("TAI_LE",
1544 "TAI LE",
1545 "TAILE");
1546
1547 /**
1548 * Constant for the "Khmer Symbols" Unicode character block.
1549 * @since 1.5
1550 */
1551 public static final UnicodeBlock KHMER_SYMBOLS =
1552 new UnicodeBlock("KHMER_SYMBOLS",
1553 "KHMER SYMBOLS",
1554 "KHMERSYMBOLS");
1555
1556 /**
1557 * Constant for the "Phonetic Extensions" Unicode character block.
1558 * @since 1.5
1559 */
1560 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1561 new UnicodeBlock("PHONETIC_EXTENSIONS",
1562 "PHONETIC EXTENSIONS",
1563 "PHONETICEXTENSIONS");
1564
1565 /**
1566 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1567 * @since 1.5
1568 */
1569 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1570 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1571 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1572 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1573
1574 /**
1575 * Constant for the "Supplemental Arrows-A" Unicode character block.
1576 * @since 1.5
1577 */
1578 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1579 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1580 "SUPPLEMENTAL ARROWS-A",
1581 "SUPPLEMENTALARROWS-A");
1582
1583 /**
1584 * Constant for the "Supplemental Arrows-B" Unicode character block.
1585 * @since 1.5
1586 */
1587 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1588 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1589 "SUPPLEMENTAL ARROWS-B",
1590 "SUPPLEMENTALARROWS-B");
1591
1592 /**
1593 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1594 * character block.
1595 * @since 1.5
1596 */
1597 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1598 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1599 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1600 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1601
1602 /**
1603 * Constant for the "Supplemental Mathematical Operators" Unicode
1604 * character block.
1605 * @since 1.5
1606 */
1607 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1608 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1609 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1610 "SUPPLEMENTALMATHEMATICALOPERATORS");
1611
1612 /**
1613 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1614 * block.
1615 * @since 1.5
1616 */
1617 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1618 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1619 "MISCELLANEOUS SYMBOLS AND ARROWS",
1620 "MISCELLANEOUSSYMBOLSANDARROWS");
1621
1622 /**
1623 * Constant for the "Katakana Phonetic Extensions" Unicode character
1624 * block.
1625 * @since 1.5
1626 */
1627 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1628 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1629 "KATAKANA PHONETIC EXTENSIONS",
1630 "KATAKANAPHONETICEXTENSIONS");
1631
1632 /**
1633 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1634 * @since 1.5
1635 */
1636 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1637 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1638 "YIJING HEXAGRAM SYMBOLS",
1639 "YIJINGHEXAGRAMSYMBOLS");
1640
1641 /**
1642 * Constant for the "Variation Selectors" Unicode character block.
1643 * @since 1.5
1644 */
1645 public static final UnicodeBlock VARIATION_SELECTORS =
1646 new UnicodeBlock("VARIATION_SELECTORS",
1647 "VARIATION SELECTORS",
1648 "VARIATIONSELECTORS");
1649
1650 /**
1651 * Constant for the "Linear B Syllabary" Unicode character block.
1652 * @since 1.5
1653 */
1654 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1655 new UnicodeBlock("LINEAR_B_SYLLABARY",
1656 "LINEAR B SYLLABARY",
1657 "LINEARBSYLLABARY");
1658
1659 /**
1660 * Constant for the "Linear B Ideograms" Unicode character block.
1661 * @since 1.5
1662 */
1663 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1664 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1665 "LINEAR B IDEOGRAMS",
1666 "LINEARBIDEOGRAMS");
1667
1668 /**
1669 * Constant for the "Aegean Numbers" Unicode character block.
1670 * @since 1.5
1671 */
1672 public static final UnicodeBlock AEGEAN_NUMBERS =
1673 new UnicodeBlock("AEGEAN_NUMBERS",
1674 "AEGEAN NUMBERS",
1675 "AEGEANNUMBERS");
1676
1677 /**
1678 * Constant for the "Old Italic" Unicode character block.
1679 * @since 1.5
1680 */
1681 public static final UnicodeBlock OLD_ITALIC =
1682 new UnicodeBlock("OLD_ITALIC",
1683 "OLD ITALIC",
1684 "OLDITALIC");
1685
1686 /**
1687 * Constant for the "Gothic" Unicode character block.
1688 * @since 1.5
1689 */
1690 public static final UnicodeBlock GOTHIC =
1691 new UnicodeBlock("GOTHIC");
1692
1693 /**
1694 * Constant for the "Ugaritic" Unicode character block.
1695 * @since 1.5
1696 */
1697 public static final UnicodeBlock UGARITIC =
1698 new UnicodeBlock("UGARITIC");
1699
1700 /**
1701 * Constant for the "Deseret" Unicode character block.
1702 * @since 1.5
1703 */
1704 public static final UnicodeBlock DESERET =
1705 new UnicodeBlock("DESERET");
1706
1707 /**
1708 * Constant for the "Shavian" Unicode character block.
1709 * @since 1.5
1710 */
1711 public static final UnicodeBlock SHAVIAN =
1712 new UnicodeBlock("SHAVIAN");
1713
1714 /**
1715 * Constant for the "Osmanya" Unicode character block.
1716 * @since 1.5
1717 */
1718 public static final UnicodeBlock OSMANYA =
1719 new UnicodeBlock("OSMANYA");
1720
1721 /**
1722 * Constant for the "Cypriot Syllabary" Unicode character block.
1723 * @since 1.5
1724 */
1725 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1726 new UnicodeBlock("CYPRIOT_SYLLABARY",
1727 "CYPRIOT SYLLABARY",
1728 "CYPRIOTSYLLABARY");
1729
1730 /**
1731 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1732 * @since 1.5
1733 */
1734 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1735 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1736 "BYZANTINE MUSICAL SYMBOLS",
1737 "BYZANTINEMUSICALSYMBOLS");
1738
1739 /**
1740 * Constant for the "Musical Symbols" Unicode character block.
1741 * @since 1.5
1742 */
1743 public static final UnicodeBlock MUSICAL_SYMBOLS =
1744 new UnicodeBlock("MUSICAL_SYMBOLS",
1745 "MUSICAL SYMBOLS",
1746 "MUSICALSYMBOLS");
1747
1748 /**
1749 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1750 * @since 1.5
1751 */
1752 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1753 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1754 "TAI XUAN JING SYMBOLS",
1755 "TAIXUANJINGSYMBOLS");
1756
1757 /**
1758 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1759 * character block.
1760 * @since 1.5
1761 */
1762 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1763 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1764 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1765 "MATHEMATICALALPHANUMERICSYMBOLS");
1766
1767 /**
1768 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1769 * character block.
1770 * @since 1.5
1771 */
1772 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1773 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1774 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1775 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1776
1777 /**
1778 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1779 * @since 1.5
1780 */
1781 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1782 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1783 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1784 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1785
1786 /**
1787 * Constant for the "Tags" Unicode character block.
1788 * @since 1.5
1789 */
1790 public static final UnicodeBlock TAGS =
1791 new UnicodeBlock("TAGS");
1792
1793 /**
1794 * Constant for the "Variation Selectors Supplement" Unicode character
1795 * block.
1796 * @since 1.5
1797 */
1798 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1799 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1800 "VARIATION SELECTORS SUPPLEMENT",
1801 "VARIATIONSELECTORSSUPPLEMENT");
1802
1803 /**
1804 * Constant for the "Supplementary Private Use Area-A" Unicode character
1805 * block.
1806 * @since 1.5
1807 */
1808 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1809 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1810 "SUPPLEMENTARY PRIVATE USE AREA-A",
1811 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1812
1813 /**
1814 * Constant for the "Supplementary Private Use Area-B" Unicode character
1815 * block.
1816 * @since 1.5
1817 */
1818 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1819 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1820 "SUPPLEMENTARY PRIVATE USE AREA-B",
1821 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1822
1823 /**
1824 * Constant for the "High Surrogates" Unicode character block.
1825 * This block represents codepoint values in the high surrogate
1826 * range: U+D800 through U+DB7F
1827 *
1828 * @since 1.5
1829 */
1830 public static final UnicodeBlock HIGH_SURROGATES =
1831 new UnicodeBlock("HIGH_SURROGATES",
1832 "HIGH SURROGATES",
1833 "HIGHSURROGATES");
1834
1835 /**
1836 * Constant for the "High Private Use Surrogates" Unicode character
1837 * block.
1838 * This block represents codepoint values in the private use high
1839 * surrogate range: U+DB80 through U+DBFF
1840 *
1841 * @since 1.5
1842 */
1843 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1844 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1845 "HIGH PRIVATE USE SURROGATES",
1846 "HIGHPRIVATEUSESURROGATES");
1847
1848 /**
1849 * Constant for the "Low Surrogates" Unicode character block.
1850 * This block represents codepoint values in the low surrogate
1851 * range: U+DC00 through U+DFFF
1852 *
1853 * @since 1.5
1854 */
1855 public static final UnicodeBlock LOW_SURROGATES =
1856 new UnicodeBlock("LOW_SURROGATES",
1857 "LOW SURROGATES",
1858 "LOWSURROGATES");
1859
1860 /**
1861 * Constant for the "Arabic Supplement" Unicode character block.
1862 * @since 1.7
1863 */
1864 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1865 new UnicodeBlock("ARABIC_SUPPLEMENT",
1866 "ARABIC SUPPLEMENT",
1867 "ARABICSUPPLEMENT");
1868
1869 /**
1870 * Constant for the "NKo" Unicode character block.
1871 * @since 1.7
1872 */
1873 public static final UnicodeBlock NKO =
1874 new UnicodeBlock("NKO");
1875
1876 /**
1877 * Constant for the "Samaritan" Unicode character block.
1878 * @since 1.7
1879 */
1880 public static final UnicodeBlock SAMARITAN =
1881 new UnicodeBlock("SAMARITAN");
1882
1883 /**
1884 * Constant for the "Mandaic" Unicode character block.
1885 * @since 1.7
1886 */
1887 public static final UnicodeBlock MANDAIC =
1888 new UnicodeBlock("MANDAIC");
1889
1890 /**
1891 * Constant for the "Ethiopic Supplement" Unicode character block.
1892 * @since 1.7
1893 */
1894 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1895 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1896 "ETHIOPIC SUPPLEMENT",
1897 "ETHIOPICSUPPLEMENT");
1898
1899 /**
1900 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1901 * Unicode character block.
1902 * @since 1.7
1903 */
1904 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1905 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1906 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1907 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1908
1909 /**
1910 * Constant for the "New Tai Lue" Unicode character block.
1911 * @since 1.7
1912 */
1913 public static final UnicodeBlock NEW_TAI_LUE =
1914 new UnicodeBlock("NEW_TAI_LUE",
1915 "NEW TAI LUE",
1916 "NEWTAILUE");
1917
1918 /**
1919 * Constant for the "Buginese" Unicode character block.
1920 * @since 1.7
1921 */
1922 public static final UnicodeBlock BUGINESE =
1923 new UnicodeBlock("BUGINESE");
1924
1925 /**
1926 * Constant for the "Tai Tham" Unicode character block.
1927 * @since 1.7
1928 */
1929 public static final UnicodeBlock TAI_THAM =
1930 new UnicodeBlock("TAI_THAM",
1931 "TAI THAM",
1932 "TAITHAM");
1933
1934 /**
1935 * Constant for the "Balinese" Unicode character block.
1936 * @since 1.7
1937 */
1938 public static final UnicodeBlock BALINESE =
1939 new UnicodeBlock("BALINESE");
1940
1941 /**
1942 * Constant for the "Sundanese" Unicode character block.
1943 * @since 1.7
1944 */
1945 public static final UnicodeBlock SUNDANESE =
1946 new UnicodeBlock("SUNDANESE");
1947
1948 /**
1949 * Constant for the "Batak" Unicode character block.
1950 * @since 1.7
1951 */
1952 public static final UnicodeBlock BATAK =
1953 new UnicodeBlock("BATAK");
1954
1955 /**
1956 * Constant for the "Lepcha" Unicode character block.
1957 * @since 1.7
1958 */
1959 public static final UnicodeBlock LEPCHA =
1960 new UnicodeBlock("LEPCHA");
1961
1962 /**
1963 * Constant for the "Ol Chiki" Unicode character block.
1964 * @since 1.7
1965 */
1966 public static final UnicodeBlock OL_CHIKI =
1967 new UnicodeBlock("OL_CHIKI",
1968 "OL CHIKI",
1969 "OLCHIKI");
1970
1971 /**
1972 * Constant for the "Vedic Extensions" Unicode character block.
1973 * @since 1.7
1974 */
1975 public static final UnicodeBlock VEDIC_EXTENSIONS =
1976 new UnicodeBlock("VEDIC_EXTENSIONS",
1977 "VEDIC EXTENSIONS",
1978 "VEDICEXTENSIONS");
1979
1980 /**
1981 * Constant for the "Phonetic Extensions Supplement" Unicode character
1982 * block.
1983 * @since 1.7
1984 */
1985 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1986 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1987 "PHONETIC EXTENSIONS SUPPLEMENT",
1988 "PHONETICEXTENSIONSSUPPLEMENT");
1989
1990 /**
1991 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1992 * character block.
1993 * @since 1.7
1994 */
1995 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1996 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1997 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1998 "COMBININGDIACRITICALMARKSSUPPLEMENT");
1999
2000 /**
2001 * Constant for the "Glagolitic" Unicode character block.
2002 * @since 1.7
2003 */
2004 public static final UnicodeBlock GLAGOLITIC =
2005 new UnicodeBlock("GLAGOLITIC");
2006
2007 /**
2008 * Constant for the "Latin Extended-C" Unicode character block.
2009 * @since 1.7
2010 */
2011 public static final UnicodeBlock LATIN_EXTENDED_C =
2012 new UnicodeBlock("LATIN_EXTENDED_C",
2013 "LATIN EXTENDED-C",
2014 "LATINEXTENDED-C");
2015
2016 /**
2017 * Constant for the "Coptic" Unicode character block.
2018 * @since 1.7
2019 */
2020 public static final UnicodeBlock COPTIC =
2021 new UnicodeBlock("COPTIC");
2022
2023 /**
2024 * Constant for the "Georgian Supplement" Unicode character block.
2025 * @since 1.7
2026 */
2027 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2028 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2029 "GEORGIAN SUPPLEMENT",
2030 "GEORGIANSUPPLEMENT");
2031
2032 /**
2033 * Constant for the "Tifinagh" Unicode character block.
2034 * @since 1.7
2035 */
2036 public static final UnicodeBlock TIFINAGH =
2037 new UnicodeBlock("TIFINAGH");
2038
2039 /**
2040 * Constant for the "Ethiopic Extended" Unicode character block.
2041 * @since 1.7
2042 */
2043 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2044 new UnicodeBlock("ETHIOPIC_EXTENDED",
2045 "ETHIOPIC EXTENDED",
2046 "ETHIOPICEXTENDED");
2047
2048 /**
2049 * Constant for the "Cyrillic Extended-A" Unicode character block.
2050 * @since 1.7
2051 */
2052 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2053 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2054 "CYRILLIC EXTENDED-A",
2055 "CYRILLICEXTENDED-A");
2056
2057 /**
2058 * Constant for the "Supplemental Punctuation" Unicode character block.
2059 * @since 1.7
2060 */
2061 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2062 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2063 "SUPPLEMENTAL PUNCTUATION",
2064 "SUPPLEMENTALPUNCTUATION");
2065
2066 /**
2067 * Constant for the "CJK Strokes" Unicode character block.
2068 * @since 1.7
2069 */
2070 public static final UnicodeBlock CJK_STROKES =
2071 new UnicodeBlock("CJK_STROKES",
2072 "CJK STROKES",
2073 "CJKSTROKES");
2074
2075 /**
2076 * Constant for the "Lisu" Unicode character block.
2077 * @since 1.7
2078 */
2079 public static final UnicodeBlock LISU =
2080 new UnicodeBlock("LISU");
2081
2082 /**
2083 * Constant for the "Vai" Unicode character block.
2084 * @since 1.7
2085 */
2086 public static final UnicodeBlock VAI =
2087 new UnicodeBlock("VAI");
2088
2089 /**
2090 * Constant for the "Cyrillic Extended-B" Unicode character block.
2091 * @since 1.7
2092 */
2093 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2094 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2095 "CYRILLIC EXTENDED-B",
2096 "CYRILLICEXTENDED-B");
2097
2098 /**
2099 * Constant for the "Bamum" Unicode character block.
2100 * @since 1.7
2101 */
2102 public static final UnicodeBlock BAMUM =
2103 new UnicodeBlock("BAMUM");
2104
2105 /**
2106 * Constant for the "Modifier Tone Letters" Unicode character block.
2107 * @since 1.7
2108 */
2109 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2110 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2111 "MODIFIER TONE LETTERS",
2112 "MODIFIERTONELETTERS");
2113
2114 /**
2115 * Constant for the "Latin Extended-D" Unicode character block.
2116 * @since 1.7
2117 */
2118 public static final UnicodeBlock LATIN_EXTENDED_D =
2119 new UnicodeBlock("LATIN_EXTENDED_D",
2120 "LATIN EXTENDED-D",
2121 "LATINEXTENDED-D");
2122
2123 /**
2124 * Constant for the "Syloti Nagri" Unicode character block.
2125 * @since 1.7
2126 */
2127 public static final UnicodeBlock SYLOTI_NAGRI =
2128 new UnicodeBlock("SYLOTI_NAGRI",
2129 "SYLOTI NAGRI",
2130 "SYLOTINAGRI");
2131
2132 /**
2133 * Constant for the "Common Indic Number Forms" Unicode character block.
2134 * @since 1.7
2135 */
2136 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2137 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2138 "COMMON INDIC NUMBER FORMS",
2139 "COMMONINDICNUMBERFORMS");
2140
2141 /**
2142 * Constant for the "Phags-pa" Unicode character block.
2143 * @since 1.7
2144 */
2145 public static final UnicodeBlock PHAGS_PA =
2146 new UnicodeBlock("PHAGS_PA",
2147 "PHAGS-PA");
2148
2149 /**
2150 * Constant for the "Saurashtra" Unicode character block.
2151 * @since 1.7
2152 */
2153 public static final UnicodeBlock SAURASHTRA =
2154 new UnicodeBlock("SAURASHTRA");
2155
2156 /**
2157 * Constant for the "Devanagari Extended" Unicode character block.
2158 * @since 1.7
2159 */
2160 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2161 new UnicodeBlock("DEVANAGARI_EXTENDED",
2162 "DEVANAGARI EXTENDED",
2163 "DEVANAGARIEXTENDED");
2164
2165 /**
2166 * Constant for the "Kayah Li" Unicode character block.
2167 * @since 1.7
2168 */
2169 public static final UnicodeBlock KAYAH_LI =
2170 new UnicodeBlock("KAYAH_LI",
2171 "KAYAH LI",
2172 "KAYAHLI");
2173
2174 /**
2175 * Constant for the "Rejang" Unicode character block.
2176 * @since 1.7
2177 */
2178 public static final UnicodeBlock REJANG =
2179 new UnicodeBlock("REJANG");
2180
2181 /**
2182 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2183 * @since 1.7
2184 */
2185 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2186 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2187 "HANGUL JAMO EXTENDED-A",
2188 "HANGULJAMOEXTENDED-A");
2189
2190 /**
2191 * Constant for the "Javanese" Unicode character block.
2192 * @since 1.7
2193 */
2194 public static final UnicodeBlock JAVANESE =
2195 new UnicodeBlock("JAVANESE");
2196
2197 /**
2198 * Constant for the "Cham" Unicode character block.
2199 * @since 1.7
2200 */
2201 public static final UnicodeBlock CHAM =
2202 new UnicodeBlock("CHAM");
2203
2204 /**
2205 * Constant for the "Myanmar Extended-A" Unicode character block.
2206 * @since 1.7
2207 */
2208 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2209 new UnicodeBlock("MYANMAR_EXTENDED_A",
2210 "MYANMAR EXTENDED-A",
2211 "MYANMAREXTENDED-A");
2212
2213 /**
2214 * Constant for the "Tai Viet" Unicode character block.
2215 * @since 1.7
2216 */
2217 public static final UnicodeBlock TAI_VIET =
2218 new UnicodeBlock("TAI_VIET",
2219 "TAI VIET",
2220 "TAIVIET");
2221
2222 /**
2223 * Constant for the "Ethiopic Extended-A" Unicode character block.
2224 * @since 1.7
2225 */
2226 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2227 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2228 "ETHIOPIC EXTENDED-A",
2229 "ETHIOPICEXTENDED-A");
2230
2231 /**
2232 * Constant for the "Meetei Mayek" Unicode character block.
2233 * @since 1.7
2234 */
2235 public static final UnicodeBlock MEETEI_MAYEK =
2236 new UnicodeBlock("MEETEI_MAYEK",
2237 "MEETEI MAYEK",
2238 "MEETEIMAYEK");
2239
2240 /**
2241 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2242 * @since 1.7
2243 */
2244 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2245 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2246 "HANGUL JAMO EXTENDED-B",
2247 "HANGULJAMOEXTENDED-B");
2248
2249 /**
2250 * Constant for the "Vertical Forms" Unicode character block.
2251 * @since 1.7
2252 */
2253 public static final UnicodeBlock VERTICAL_FORMS =
2254 new UnicodeBlock("VERTICAL_FORMS",
2255 "VERTICAL FORMS",
2256 "VERTICALFORMS");
2257
2258 /**
2259 * Constant for the "Ancient Greek Numbers" Unicode character block.
2260 * @since 1.7
2261 */
2262 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2263 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2264 "ANCIENT GREEK NUMBERS",
2265 "ANCIENTGREEKNUMBERS");
2266
2267 /**
2268 * Constant for the "Ancient Symbols" Unicode character block.
2269 * @since 1.7
2270 */
2271 public static final UnicodeBlock ANCIENT_SYMBOLS =
2272 new UnicodeBlock("ANCIENT_SYMBOLS",
2273 "ANCIENT SYMBOLS",
2274 "ANCIENTSYMBOLS");
2275
2276 /**
2277 * Constant for the "Phaistos Disc" Unicode character block.
2278 * @since 1.7
2279 */
2280 public static final UnicodeBlock PHAISTOS_DISC =
2281 new UnicodeBlock("PHAISTOS_DISC",
2282 "PHAISTOS DISC",
2283 "PHAISTOSDISC");
2284
2285 /**
2286 * Constant for the "Lycian" Unicode character block.
2287 * @since 1.7
2288 */
2289 public static final UnicodeBlock LYCIAN =
2290 new UnicodeBlock("LYCIAN");
2291
2292 /**
2293 * Constant for the "Carian" Unicode character block.
2294 * @since 1.7
2295 */
2296 public static final UnicodeBlock CARIAN =
2297 new UnicodeBlock("CARIAN");
2298
2299 /**
2300 * Constant for the "Old Persian" Unicode character block.
2301 * @since 1.7
2302 */
2303 public static final UnicodeBlock OLD_PERSIAN =
2304 new UnicodeBlock("OLD_PERSIAN",
2305 "OLD PERSIAN",
2306 "OLDPERSIAN");
2307
2308 /**
2309 * Constant for the "Imperial Aramaic" Unicode character block.
2310 * @since 1.7
2311 */
2312 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2313 new UnicodeBlock("IMPERIAL_ARAMAIC",
2314 "IMPERIAL ARAMAIC",
2315 "IMPERIALARAMAIC");
2316
2317 /**
2318 * Constant for the "Phoenician" Unicode character block.
2319 * @since 1.7
2320 */
2321 public static final UnicodeBlock PHOENICIAN =
2322 new UnicodeBlock("PHOENICIAN");
2323
2324 /**
2325 * Constant for the "Lydian" Unicode character block.
2326 * @since 1.7
2327 */
2328 public static final UnicodeBlock LYDIAN =
2329 new UnicodeBlock("LYDIAN");
2330
2331 /**
2332 * Constant for the "Kharoshthi" Unicode character block.
2333 * @since 1.7
2334 */
2335 public static final UnicodeBlock KHAROSHTHI =
2336 new UnicodeBlock("KHAROSHTHI");
2337
2338 /**
2339 * Constant for the "Old South Arabian" Unicode character block.
2340 * @since 1.7
2341 */
2342 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2343 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2344 "OLD SOUTH ARABIAN",
2345 "OLDSOUTHARABIAN");
2346
2347 /**
2348 * Constant for the "Avestan" Unicode character block.
2349 * @since 1.7
2350 */
2351 public static final UnicodeBlock AVESTAN =
2352 new UnicodeBlock("AVESTAN");
2353
2354 /**
2355 * Constant for the "Inscriptional Parthian" Unicode character block.
2356 * @since 1.7
2357 */
2358 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2359 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2360 "INSCRIPTIONAL PARTHIAN",
2361 "INSCRIPTIONALPARTHIAN");
2362
2363 /**
2364 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2365 * @since 1.7
2366 */
2367 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2368 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2369 "INSCRIPTIONAL PAHLAVI",
2370 "INSCRIPTIONALPAHLAVI");
2371
2372 /**
2373 * Constant for the "Old Turkic" Unicode character block.
2374 * @since 1.7
2375 */
2376 public static final UnicodeBlock OLD_TURKIC =
2377 new UnicodeBlock("OLD_TURKIC",
2378 "OLD TURKIC",
2379 "OLDTURKIC");
2380
2381 /**
2382 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2383 * @since 1.7
2384 */
2385 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2386 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2387 "RUMI NUMERAL SYMBOLS",
2388 "RUMINUMERALSYMBOLS");
2389
2390 /**
2391 * Constant for the "Brahmi" Unicode character block.
2392 * @since 1.7
2393 */
2394 public static final UnicodeBlock BRAHMI =
2395 new UnicodeBlock("BRAHMI");
2396
2397 /**
2398 * Constant for the "Kaithi" Unicode character block.
2399 * @since 1.7
2400 */
2401 public static final UnicodeBlock KAITHI =
2402 new UnicodeBlock("KAITHI");
2403
2404 /**
2405 * Constant for the "Cuneiform" Unicode character block.
2406 * @since 1.7
2407 */
2408 public static final UnicodeBlock CUNEIFORM =
2409 new UnicodeBlock("CUNEIFORM");
2410
2411 /**
2412 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2413 * character block.
2414 * @since 1.7
2415 */
2416 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2417 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2418 "CUNEIFORM NUMBERS AND PUNCTUATION",
2419 "CUNEIFORMNUMBERSANDPUNCTUATION");
2420
2421 /**
2422 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2423 * @since 1.7
2424 */
2425 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2426 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2427 "EGYPTIAN HIEROGLYPHS",
2428 "EGYPTIANHIEROGLYPHS");
2429
2430 /**
2431 * Constant for the "Bamum Supplement" Unicode character block.
2432 * @since 1.7
2433 */
2434 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2435 new UnicodeBlock("BAMUM_SUPPLEMENT",
2436 "BAMUM SUPPLEMENT",
2437 "BAMUMSUPPLEMENT");
2438
2439 /**
2440 * Constant for the "Kana Supplement" Unicode character block.
2441 * @since 1.7
2442 */
2443 public static final UnicodeBlock KANA_SUPPLEMENT =
2444 new UnicodeBlock("KANA_SUPPLEMENT",
2445 "KANA SUPPLEMENT",
2446 "KANASUPPLEMENT");
2447
2448 /**
2449 * Constant for the "Ancient Greek Musical Notation" Unicode character
2450 * block.
2451 * @since 1.7
2452 */
2453 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2454 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2455 "ANCIENT GREEK MUSICAL NOTATION",
2456 "ANCIENTGREEKMUSICALNOTATION");
2457
2458 /**
2459 * Constant for the "Counting Rod Numerals" Unicode character block.
2460 * @since 1.7
2461 */
2462 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2463 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2464 "COUNTING ROD NUMERALS",
2465 "COUNTINGRODNUMERALS");
2466
2467 /**
2468 * Constant for the "Mahjong Tiles" Unicode character block.
2469 * @since 1.7
2470 */
2471 public static final UnicodeBlock MAHJONG_TILES =
2472 new UnicodeBlock("MAHJONG_TILES",
2473 "MAHJONG TILES",
2474 "MAHJONGTILES");
2475
2476 /**
2477 * Constant for the "Domino Tiles" Unicode character block.
2478 * @since 1.7
2479 */
2480 public static final UnicodeBlock DOMINO_TILES =
2481 new UnicodeBlock("DOMINO_TILES",
2482 "DOMINO TILES",
2483 "DOMINOTILES");
2484
2485 /**
2486 * Constant for the "Playing Cards" Unicode character block.
2487 * @since 1.7
2488 */
2489 public static final UnicodeBlock PLAYING_CARDS =
2490 new UnicodeBlock("PLAYING_CARDS",
2491 "PLAYING CARDS",
2492 "PLAYINGCARDS");
2493
2494 /**
2495 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2496 * block.
2497 * @since 1.7
2498 */
2499 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2500 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2501 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2502 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2503
2504 /**
2505 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2506 * block.
2507 * @since 1.7
2508 */
2509 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2510 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2511 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2512 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2513
2514 /**
2515 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2516 * character block.
2517 * @since 1.7
2518 */
2519 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2520 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2521 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2522 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2523
2524 /**
2525 * Constant for the "Emoticons" Unicode character block.
2526 * @since 1.7
2527 */
2528 public static final UnicodeBlock EMOTICONS =
2529 new UnicodeBlock("EMOTICONS");
2530
2531 /**
2532 * Constant for the "Transport And Map Symbols" Unicode character block.
2533 * @since 1.7
2534 */
2535 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2536 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2537 "TRANSPORT AND MAP SYMBOLS",
2538 "TRANSPORTANDMAPSYMBOLS");
2539
2540 /**
2541 * Constant for the "Alchemical Symbols" Unicode character block.
2542 * @since 1.7
2543 */
2544 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2545 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2546 "ALCHEMICAL SYMBOLS",
2547 "ALCHEMICALSYMBOLS");
2548
2549 /**
2550 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2551 * character block.
2552 * @since 1.7
2553 */
2554 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2555 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2556 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2557 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2558
2559 /**
2560 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2561 * character block.
2562 * @since 1.7
2563 */
2564 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2565 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2566 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2567 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2568
2569 /**
2570 * Constant for the "Arabic Extended-A" Unicode character block.
2571 * @since 1.8
2572 */
2573 public static final UnicodeBlock ARABIC_EXTENDED_A =
2574 new UnicodeBlock("ARABIC_EXTENDED_A",
2575 "ARABIC EXTENDED-A",
2576 "ARABICEXTENDED-A");
2577
2578 /**
2579 * Constant for the "Sundanese Supplement" Unicode character block.
2580 * @since 1.8
2581 */
2582 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2583 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2584 "SUNDANESE SUPPLEMENT",
2585 "SUNDANESESUPPLEMENT");
2586
2587 /**
2588 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2589 * @since 1.8
2590 */
2591 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2592 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2593 "MEETEI MAYEK EXTENSIONS",
2594 "MEETEIMAYEKEXTENSIONS");
2595
2596 /**
2597 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2598 * @since 1.8
2599 */
2600 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2601 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2602 "MEROITIC HIEROGLYPHS",
2603 "MEROITICHIEROGLYPHS");
2604
2605 /**
2606 * Constant for the "Meroitic Cursive" Unicode character block.
2607 * @since 1.8
2608 */
2609 public static final UnicodeBlock MEROITIC_CURSIVE =
2610 new UnicodeBlock("MEROITIC_CURSIVE",
2611 "MEROITIC CURSIVE",
2612 "MEROITICCURSIVE");
2613
2614 /**
2615 * Constant for the "Sora Sompeng" Unicode character block.
2616 * @since 1.8
2617 */
2618 public static final UnicodeBlock SORA_SOMPENG =
2619 new UnicodeBlock("SORA_SOMPENG",
2620 "SORA SOMPENG",
2621 "SORASOMPENG");
2622
2623 /**
2624 * Constant for the "Chakma" Unicode character block.
2625 * @since 1.8
2626 */
2627 public static final UnicodeBlock CHAKMA =
2628 new UnicodeBlock("CHAKMA");
2629
2630 /**
2631 * Constant for the "Sharada" Unicode character block.
2632 * @since 1.8
2633 */
2634 public static final UnicodeBlock SHARADA =
2635 new UnicodeBlock("SHARADA");
2636
2637 /**
2638 * Constant for the "Takri" Unicode character block.
2639 * @since 1.8
2640 */
2641 public static final UnicodeBlock TAKRI =
2642 new UnicodeBlock("TAKRI");
2643
2644 /**
2645 * Constant for the "Miao" Unicode character block.
2646 * @since 1.8
2647 */
2648 public static final UnicodeBlock MIAO =
2649 new UnicodeBlock("MIAO");
2650
2651 /**
2652 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2653 * character block.
2654 * @since 1.8
2655 */
2656 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2657 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2658 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2659 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2660
2661 /**
2662 * Constant for the "Combining Diacritical Marks Extended" Unicode
2663 * character block.
2664 * @since 9
2665 */
2666 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2667 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2668 "COMBINING DIACRITICAL MARKS EXTENDED",
2669 "COMBININGDIACRITICALMARKSEXTENDED");
2670
2671 /**
2672 * Constant for the "Myanmar Extended-B" Unicode character block.
2673 * @since 9
2674 */
2675 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2676 new UnicodeBlock("MYANMAR_EXTENDED_B",
2677 "MYANMAR EXTENDED-B",
2678 "MYANMAREXTENDED-B");
2679
2680 /**
2681 * Constant for the "Latin Extended-E" Unicode character block.
2682 * @since 9
2683 */
2684 public static final UnicodeBlock LATIN_EXTENDED_E =
2685 new UnicodeBlock("LATIN_EXTENDED_E",
2686 "LATIN EXTENDED-E",
2687 "LATINEXTENDED-E");
2688
2689 /**
2690 * Constant for the "Coptic Epact Numbers" Unicode character block.
2691 * @since 9
2692 */
2693 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2694 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2695 "COPTIC EPACT NUMBERS",
2696 "COPTICEPACTNUMBERS");
2697
2698 /**
2699 * Constant for the "Old Permic" Unicode character block.
2700 * @since 9
2701 */
2702 public static final UnicodeBlock OLD_PERMIC =
2703 new UnicodeBlock("OLD_PERMIC",
2704 "OLD PERMIC",
2705 "OLDPERMIC");
2706
2707 /**
2708 * Constant for the "Elbasan" Unicode character block.
2709 * @since 9
2710 */
2711 public static final UnicodeBlock ELBASAN =
2712 new UnicodeBlock("ELBASAN");
2713
2714 /**
2715 * Constant for the "Caucasian Albanian" Unicode character block.
2716 * @since 9
2717 */
2718 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2719 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2720 "CAUCASIAN ALBANIAN",
2721 "CAUCASIANALBANIAN");
2722
2723 /**
2724 * Constant for the "Linear A" Unicode character block.
2725 * @since 9
2726 */
2727 public static final UnicodeBlock LINEAR_A =
2728 new UnicodeBlock("LINEAR_A",
2729 "LINEAR A",
2730 "LINEARA");
2731
2732 /**
2733 * Constant for the "Palmyrene" Unicode character block.
2734 * @since 9
2735 */
2736 public static final UnicodeBlock PALMYRENE =
2737 new UnicodeBlock("PALMYRENE");
2738
2739 /**
2740 * Constant for the "Nabataean" Unicode character block.
2741 * @since 9
2742 */
2743 public static final UnicodeBlock NABATAEAN =
2744 new UnicodeBlock("NABATAEAN");
2745
2746 /**
2747 * Constant for the "Old North Arabian" Unicode character block.
2748 * @since 9
2749 */
2750 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2751 new UnicodeBlock("OLD_NORTH_ARABIAN",
2752 "OLD NORTH ARABIAN",
2753 "OLDNORTHARABIAN");
2754
2755 /**
2756 * Constant for the "Manichaean" Unicode character block.
2757 * @since 9
2758 */
2759 public static final UnicodeBlock MANICHAEAN =
2760 new UnicodeBlock("MANICHAEAN");
2761
2762 /**
2763 * Constant for the "Psalter Pahlavi" Unicode character block.
2764 * @since 9
2765 */
2766 public static final UnicodeBlock PSALTER_PAHLAVI =
2767 new UnicodeBlock("PSALTER_PAHLAVI",
2768 "PSALTER PAHLAVI",
2769 "PSALTERPAHLAVI");
2770
2771 /**
2772 * Constant for the "Mahajani" Unicode character block.
2773 * @since 9
2774 */
2775 public static final UnicodeBlock MAHAJANI =
2776 new UnicodeBlock("MAHAJANI");
2777
2778 /**
2779 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2780 * @since 9
2781 */
2782 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2783 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2784 "SINHALA ARCHAIC NUMBERS",
2785 "SINHALAARCHAICNUMBERS");
2786
2787 /**
2788 * Constant for the "Khojki" Unicode character block.
2789 * @since 9
2790 */
2791 public static final UnicodeBlock KHOJKI =
2792 new UnicodeBlock("KHOJKI");
2793
2794 /**
2795 * Constant for the "Khudawadi" Unicode character block.
2796 * @since 9
2797 */
2798 public static final UnicodeBlock KHUDAWADI =
2799 new UnicodeBlock("KHUDAWADI");
2800
2801 /**
2802 * Constant for the "Grantha" Unicode character block.
2803 * @since 9
2804 */
2805 public static final UnicodeBlock GRANTHA =
2806 new UnicodeBlock("GRANTHA");
2807
2808 /**
2809 * Constant for the "Tirhuta" Unicode character block.
2810 * @since 9
2811 */
2812 public static final UnicodeBlock TIRHUTA =
2813 new UnicodeBlock("TIRHUTA");
2814
2815 /**
2816 * Constant for the "Siddham" Unicode character block.
2817 * @since 9
2818 */
2819 public static final UnicodeBlock SIDDHAM =
2820 new UnicodeBlock("SIDDHAM");
2821
2822 /**
2823 * Constant for the "Modi" Unicode character block.
2824 * @since 9
2825 */
2826 public static final UnicodeBlock MODI =
2827 new UnicodeBlock("MODI");
2828
2829 /**
2830 * Constant for the "Warang Citi" Unicode character block.
2831 * @since 9
2832 */
2833 public static final UnicodeBlock WARANG_CITI =
2834 new UnicodeBlock("WARANG_CITI",
2835 "WARANG CITI",
2836 "WARANGCITI");
2837
2838 /**
2839 * Constant for the "Pau Cin Hau" Unicode character block.
2840 * @since 9
2841 */
2842 public static final UnicodeBlock PAU_CIN_HAU =
2843 new UnicodeBlock("PAU_CIN_HAU",
2844 "PAU CIN HAU",
2845 "PAUCINHAU");
2846
2847 /**
2848 * Constant for the "Mro" Unicode character block.
2849 * @since 9
2850 */
2851 public static final UnicodeBlock MRO =
2852 new UnicodeBlock("MRO");
2853
2854 /**
2855 * Constant for the "Bassa Vah" Unicode character block.
2856 * @since 9
2857 */
2858 public static final UnicodeBlock BASSA_VAH =
2859 new UnicodeBlock("BASSA_VAH",
2860 "BASSA VAH",
2861 "BASSAVAH");
2862
2863 /**
2864 * Constant for the "Pahawh Hmong" Unicode character block.
2865 * @since 9
2866 */
2867 public static final UnicodeBlock PAHAWH_HMONG =
2868 new UnicodeBlock("PAHAWH_HMONG",
2869 "PAHAWH HMONG",
2870 "PAHAWHHMONG");
2871
2872 /**
2873 * Constant for the "Duployan" Unicode character block.
2874 * @since 9
2875 */
2876 public static final UnicodeBlock DUPLOYAN =
2877 new UnicodeBlock("DUPLOYAN");
2878
2879 /**
2880 * Constant for the "Shorthand Format Controls" Unicode character block.
2881 * @since 9
2882 */
2883 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2884 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2885 "SHORTHAND FORMAT CONTROLS",
2886 "SHORTHANDFORMATCONTROLS");
2887
2888 /**
2889 * Constant for the "Mende Kikakui" Unicode character block.
2890 * @since 9
2891 */
2892 public static final UnicodeBlock MENDE_KIKAKUI =
2893 new UnicodeBlock("MENDE_KIKAKUI",
2894 "MENDE KIKAKUI",
2895 "MENDEKIKAKUI");
2896
2897 /**
2898 * Constant for the "Ornamental Dingbats" Unicode character block.
2899 * @since 9
2900 */
2901 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2902 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2903 "ORNAMENTAL DINGBATS",
2904 "ORNAMENTALDINGBATS");
2905
2906 /**
2907 * Constant for the "Geometric Shapes Extended" Unicode character block.
2908 * @since 9
2909 */
2910 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2911 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2912 "GEOMETRIC SHAPES EXTENDED",
2913 "GEOMETRICSHAPESEXTENDED");
2914
2915 /**
2916 * Constant for the "Supplemental Arrows-C" Unicode character block.
2917 * @since 9
2918 */
2919 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2920 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2921 "SUPPLEMENTAL ARROWS-C",
2922 "SUPPLEMENTALARROWS-C");
2923
2924 /**
2925 * Constant for the "Cherokee Supplement" Unicode character block.
2926 * @since 9
2927 */
2928 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2929 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2930 "CHEROKEE SUPPLEMENT",
2931 "CHEROKEESUPPLEMENT");
2932
2933 /**
2934 * Constant for the "Hatran" Unicode character block.
2935 * @since 9
2936 */
2937 public static final UnicodeBlock HATRAN =
2938 new UnicodeBlock("HATRAN");
2939
2940 /**
2941 * Constant for the "Old Hungarian" Unicode character block.
2942 * @since 9
2943 */
2944 public static final UnicodeBlock OLD_HUNGARIAN =
2945 new UnicodeBlock("OLD_HUNGARIAN",
2946 "OLD HUNGARIAN",
2947 "OLDHUNGARIAN");
2948
2949 /**
2950 * Constant for the "Multani" Unicode character block.
2951 * @since 9
2952 */
2953 public static final UnicodeBlock MULTANI =
2954 new UnicodeBlock("MULTANI");
2955
2956 /**
2957 * Constant for the "Ahom" Unicode character block.
2958 * @since 9
2959 */
2960 public static final UnicodeBlock AHOM =
2961 new UnicodeBlock("AHOM");
2962
2963 /**
2964 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2965 * @since 9
2966 */
2967 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2968 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2969 "EARLY DYNASTIC CUNEIFORM",
2970 "EARLYDYNASTICCUNEIFORM");
2971
2972 /**
2973 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2974 * @since 9
2975 */
2976 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2977 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2978 "ANATOLIAN HIEROGLYPHS",
2979 "ANATOLIANHIEROGLYPHS");
2980
2981 /**
2982 * Constant for the "Sutton SignWriting" Unicode character block.
2983 * @since 9
2984 */
2985 public static final UnicodeBlock SUTTON_SIGNWRITING =
2986 new UnicodeBlock("SUTTON_SIGNWRITING",
2987 "SUTTON SIGNWRITING",
2988 "SUTTONSIGNWRITING");
2989
2990 /**
2991 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2992 * character block.
2993 * @since 9
2994 */
2995 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2996 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2997 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2998 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2999
3000 /**
3001 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3002 * character block.
3003 * @since 9
3004 */
3005 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3006 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3007 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3008 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3009
3010 /**
3011 * Constant for the "Syriac Supplement" Unicode
3012 * character block.
3013 * @since 11
3014 */
3015 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3016 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3017 "SYRIAC SUPPLEMENT",
3018 "SYRIACSUPPLEMENT");
3019
3020 /**
3021 * Constant for the "Cyrillic Extended-C" Unicode
3022 * character block.
3023 * @since 11
3024 */
3025 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3026 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3027 "CYRILLIC EXTENDED-C",
3028 "CYRILLICEXTENDED-C");
3029
3030 /**
3031 * Constant for the "Osage" Unicode
3032 * character block.
3033 * @since 11
3034 */
3035 public static final UnicodeBlock OSAGE =
3036 new UnicodeBlock("OSAGE");
3037
3038 /**
3039 * Constant for the "Newa" Unicode
3040 * character block.
3041 * @since 11
3042 */
3043 public static final UnicodeBlock NEWA =
3044 new UnicodeBlock("NEWA");
3045
3046 /**
3047 * Constant for the "Mongolian Supplement" Unicode
3048 * character block.
3049 * @since 11
3050 */
3051 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3052 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3053 "MONGOLIAN SUPPLEMENT",
3054 "MONGOLIANSUPPLEMENT");
3055
3056 /**
3057 * Constant for the "Marchen" Unicode
3058 * character block.
3059 * @since 11
3060 */
3061 public static final UnicodeBlock MARCHEN =
3062 new UnicodeBlock("MARCHEN");
3063
3064 /**
3065 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3066 * character block.
3067 * @since 11
3068 */
3069 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3070 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3071 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3072 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3073
3074 /**
3075 * Constant for the "Tangut" Unicode
3076 * character block.
3077 * @since 11
3078 */
3079 public static final UnicodeBlock TANGUT =
3080 new UnicodeBlock("TANGUT");
3081
3082 /**
3083 * Constant for the "Tangut Components" Unicode
3084 * character block.
3085 * @since 11
3086 */
3087 public static final UnicodeBlock TANGUT_COMPONENTS =
3088 new UnicodeBlock("TANGUT_COMPONENTS",
3089 "TANGUT COMPONENTS",
3090 "TANGUTCOMPONENTS");
3091
3092 /**
3093 * Constant for the "Kana Extended-A" Unicode
3094 * character block.
3095 * @since 11
3096 */
3097 public static final UnicodeBlock KANA_EXTENDED_A =
3098 new UnicodeBlock("KANA_EXTENDED_A",
3099 "KANA EXTENDED-A",
3100 "KANAEXTENDED-A");
3101 /**
3102 * Constant for the "Glagolitic Supplement" Unicode
3103 * character block.
3104 * @since 11
3105 */
3106 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3107 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3108 "GLAGOLITIC SUPPLEMENT",
3109 "GLAGOLITICSUPPLEMENT");
3110 /**
3111 * Constant for the "Adlam" Unicode
3112 * character block.
3113 * @since 11
3114 */
3115 public static final UnicodeBlock ADLAM =
3116 new UnicodeBlock("ADLAM");
3117
3118 /**
3119 * Constant for the "Masaram Gondi" Unicode
3120 * character block.
3121 * @since 11
3122 */
3123 public static final UnicodeBlock MASARAM_GONDI =
3124 new UnicodeBlock("MASARAM_GONDI",
3125 "MASARAM GONDI",
3126 "MASARAMGONDI");
3127
3128 /**
3129 * Constant for the "Zanabazar Square" Unicode
3130 * character block.
3131 * @since 11
3132 */
3133 public static final UnicodeBlock ZANABAZAR_SQUARE =
3134 new UnicodeBlock("ZANABAZAR_SQUARE",
3135 "ZANABAZAR SQUARE",
3136 "ZANABAZARSQUARE");
3137
3138 /**
3139 * Constant for the "Nushu" Unicode
3140 * character block.
3141 * @since 11
3142 */
3143 public static final UnicodeBlock NUSHU =
3144 new UnicodeBlock("NUSHU");
3145
3146 /**
3147 * Constant for the "Soyombo" Unicode
3148 * character block.
3149 * @since 11
3150 */
3151 public static final UnicodeBlock SOYOMBO =
3152 new UnicodeBlock("SOYOMBO");
3153
3154 /**
3155 * Constant for the "Bhaiksuki" Unicode
3156 * character block.
3157 * @since 11
3158 */
3159 public static final UnicodeBlock BHAIKSUKI =
3160 new UnicodeBlock("BHAIKSUKI");
3161
3162 /**
3163 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3164 * character block.
3165 * @since 11
3166 */
3167 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3168 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3169 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3170 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3171 /**
3172 * Constant for the "Georgian Extended" Unicode
3173 * character block.
3174 * @since 12
3175 */
3176 public static final UnicodeBlock GEORGIAN_EXTENDED =
3177 new UnicodeBlock("GEORGIAN_EXTENDED",
3178 "GEORGIAN EXTENDED",
3179 "GEORGIANEXTENDED");
3180
3181 /**
3182 * Constant for the "Hanifi Rohingya" Unicode
3183 * character block.
3184 * @since 12
3185 */
3186 public static final UnicodeBlock HANIFI_ROHINGYA =
3187 new UnicodeBlock("HANIFI_ROHINGYA",
3188 "HANIFI ROHINGYA",
3189 "HANIFIROHINGYA");
3190
3191 /**
3192 * Constant for the "Old Sogdian" Unicode
3193 * character block.
3194 * @since 12
3195 */
3196 public static final UnicodeBlock OLD_SOGDIAN =
3197 new UnicodeBlock("OLD_SOGDIAN",
3198 "OLD SOGDIAN",
3199 "OLDSOGDIAN");
3200
3201 /**
3202 * Constant for the "Sogdian" Unicode
3203 * character block.
3204 * @since 12
3205 */
3206 public static final UnicodeBlock SOGDIAN =
3207 new UnicodeBlock("SOGDIAN");
3208
3209 /**
3210 * Constant for the "Dogra" Unicode
3211 * character block.
3212 * @since 12
3213 */
3214 public static final UnicodeBlock DOGRA =
3215 new UnicodeBlock("DOGRA");
3216
3217 /**
3218 * Constant for the "Gunjala Gondi" Unicode
3219 * character block.
3220 * @since 12
3221 */
3222 public static final UnicodeBlock GUNJALA_GONDI =
3223 new UnicodeBlock("GUNJALA_GONDI",
3224 "GUNJALA GONDI",
3225 "GUNJALAGONDI");
3226
3227 /**
3228 * Constant for the "Makasar" Unicode
3229 * character block.
3230 * @since 12
3231 */
3232 public static final UnicodeBlock MAKASAR =
3233 new UnicodeBlock("MAKASAR");
3234
3235 /**
3236 * Constant for the "Medefaidrin" Unicode
3237 * character block.
3238 * @since 12
3239 */
3240 public static final UnicodeBlock MEDEFAIDRIN =
3241 new UnicodeBlock("MEDEFAIDRIN");
3242
3243 /**
3244 * Constant for the "Mayan Numerals" Unicode
3245 * character block.
3246 * @since 12
3247 */
3248 public static final UnicodeBlock MAYAN_NUMERALS =
3249 new UnicodeBlock("MAYAN_NUMERALS",
3250 "MAYAN NUMERALS",
3251 "MAYANNUMERALS");
3252
3253 /**
3254 * Constant for the "Indic Siyaq Numbers" Unicode
3255 * character block.
3256 * @since 12
3257 */
3258 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3259 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3260 "INDIC SIYAQ NUMBERS",
3261 "INDICSIYAQNUMBERS");
3262
3263 /**
3264 * Constant for the "Chess Symbols" Unicode
3265 * character block.
3266 * @since 12
3267 */
3268 public static final UnicodeBlock CHESS_SYMBOLS =
3269 new UnicodeBlock("CHESS_SYMBOLS",
3270 "CHESS SYMBOLS",
3271 "CHESSSYMBOLS");
3272
3273 /**
3274 * Constant for the "Elymaic" Unicode
3275 * character block.
3276 * @since 13
3277 */
3278 public static final UnicodeBlock ELYMAIC =
3279 new UnicodeBlock("ELYMAIC");
3280
3281 /**
3282 * Constant for the "Nandinagari" Unicode
3283 * character block.
3284 * @since 13
3285 */
3286 public static final UnicodeBlock NANDINAGARI =
3287 new UnicodeBlock("NANDINAGARI");
3288
3289 /**
3290 * Constant for the "Tamil Supplement" Unicode
3291 * character block.
3292 * @since 13
3293 */
3294 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3295 new UnicodeBlock("TAMIL_SUPPLEMENT",
3296 "TAMIL SUPPLEMENT",
3297 "TAMILSUPPLEMENT");
3298
3299 /**
3300 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3301 * character block.
3302 * @since 13
3303 */
3304 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3305 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3306 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3307 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3308
3309 /**
3310 * Constant for the "Small Kana Extension" Unicode
3311 * character block.
3312 * @since 13
3313 */
3314 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3315 new UnicodeBlock("SMALL_KANA_EXTENSION",
3316 "SMALL KANA EXTENSION",
3317 "SMALLKANAEXTENSION");
3318
3319 /**
3320 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3321 * character block.
3322 * @since 13
3323 */
3324 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3325 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3326 "NYIAKENG PUACHUE HMONG",
3327 "NYIAKENGPUACHUEHMONG");
3328
3329 /**
3330 * Constant for the "Wancho" Unicode
3331 * character block.
3332 * @since 13
3333 */
3334 public static final UnicodeBlock WANCHO =
3335 new UnicodeBlock("WANCHO");
3336
3337 /**
3338 * Constant for the "Ottoman Siyaq Numbers" Unicode
3339 * character block.
3340 * @since 13
3341 */
3342 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3343 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3344 "OTTOMAN SIYAQ NUMBERS",
3345 "OTTOMANSIYAQNUMBERS");
3346
3347 /**
3348 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3349 * character block.
3350 * @since 13
3351 */
3352 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3353 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3354 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3355 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3356
3357 /**
3358 * Constant for the "Yezidi" Unicode
3359 * character block.
3360 * @since 15
3361 */
3362 public static final UnicodeBlock YEZIDI =
3363 new UnicodeBlock("YEZIDI");
3364
3365 /**
3366 * Constant for the "Chorasmian" Unicode
3367 * character block.
3368 * @since 15
3369 */
3370 public static final UnicodeBlock CHORASMIAN =
3371 new UnicodeBlock("CHORASMIAN");
3372
3373 /**
3374 * Constant for the "Dives Akuru" Unicode
3375 * character block.
3376 * @since 15
3377 */
3378 public static final UnicodeBlock DIVES_AKURU =
3379 new UnicodeBlock("DIVES_AKURU",
3380 "DIVES AKURU",
3381 "DIVESAKURU");
3382
3383 /**
3384 * Constant for the "Lisu Supplement" Unicode
3385 * character block.
3386 * @since 15
3387 */
3388 public static final UnicodeBlock LISU_SUPPLEMENT =
3389 new UnicodeBlock("LISU_SUPPLEMENT",
3390 "LISU SUPPLEMENT",
3391 "LISUSUPPLEMENT");
3392
3393 /**
3394 * Constant for the "Khitan Small Script" Unicode
3395 * character block.
3396 * @since 15
3397 */
3398 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3399 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3400 "KHITAN SMALL SCRIPT",
3401 "KHITANSMALLSCRIPT");
3402
3403 /**
3404 * Constant for the "Tangut Supplement" Unicode
3405 * character block.
3406 * @since 15
3407 */
3408 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3409 new UnicodeBlock("TANGUT_SUPPLEMENT",
3410 "TANGUT SUPPLEMENT",
3411 "TANGUTSUPPLEMENT");
3412
3413 /**
3414 * Constant for the "Symbols for Legacy Computing" Unicode
3415 * character block.
3416 * @since 15
3417 */
3418 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3419 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3420 "SYMBOLS FOR LEGACY COMPUTING",
3421 "SYMBOLSFORLEGACYCOMPUTING");
3422
3423 /**
3424 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3425 * character block.
3426 * @since 15
3427 */
3428 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3429 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3430 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3431 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3432
3433 /**
3434 * Constant for the "Arabic Extended-B" Unicode
3435 * character block.
3436 * @since 19
3437 */
3438 public static final UnicodeBlock ARABIC_EXTENDED_B =
3439 new UnicodeBlock("ARABIC_EXTENDED_B",
3440 "ARABIC EXTENDED-B",
3441 "ARABICEXTENDED-B");
3442
3443 /**
3444 * Constant for the "Vithkuqi" Unicode
3445 * character block.
3446 * @since 19
3447 */
3448 public static final UnicodeBlock VITHKUQI =
3449 new UnicodeBlock("VITHKUQI");
3450
3451 /**
3452 * Constant for the "Latin Extended-F" Unicode
3453 * character block.
3454 * @since 19
3455 */
3456 public static final UnicodeBlock LATIN_EXTENDED_F =
3457 new UnicodeBlock("LATIN_EXTENDED_F",
3458 "LATIN EXTENDED-F",
3459 "LATINEXTENDED-F");
3460
3461 /**
3462 * Constant for the "Old Uyghur" Unicode
3463 * character block.
3464 * @since 19
3465 */
3466 public static final UnicodeBlock OLD_UYGHUR =
3467 new UnicodeBlock("OLD_UYGHUR",
3468 "OLD UYGHUR",
3469 "OLDUYGHUR");
3470
3471 /**
3472 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3473 * character block.
3474 * @since 19
3475 */
3476 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3477 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3478 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3479 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3480
3481 /**
3482 * Constant for the "Cypro-Minoan" Unicode
3483 * character block.
3484 * @since 19
3485 */
3486 public static final UnicodeBlock CYPRO_MINOAN =
3487 new UnicodeBlock("CYPRO_MINOAN",
3488 "CYPRO-MINOAN",
3489 "CYPRO-MINOAN");
3490
3491 /**
3492 * Constant for the "Tangsa" Unicode
3493 * character block.
3494 * @since 19
3495 */
3496 public static final UnicodeBlock TANGSA =
3497 new UnicodeBlock("TANGSA");
3498
3499 /**
3500 * Constant for the "Kana Extended-B" Unicode
3501 * character block.
3502 * @since 19
3503 */
3504 public static final UnicodeBlock KANA_EXTENDED_B =
3505 new UnicodeBlock("KANA_EXTENDED_B",
3506 "KANA EXTENDED-B",
3507 "KANAEXTENDED-B");
3508
3509 /**
3510 * Constant for the "Znamenny Musical Notation" Unicode
3511 * character block.
3512 * @since 19
3513 */
3514 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3515 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3516 "ZNAMENNY MUSICAL NOTATION",
3517 "ZNAMENNYMUSICALNOTATION");
3518
3519 /**
3520 * Constant for the "Latin Extended-G" Unicode
3521 * character block.
3522 * @since 19
3523 */
3524 public static final UnicodeBlock LATIN_EXTENDED_G =
3525 new UnicodeBlock("LATIN_EXTENDED_G",
3526 "LATIN EXTENDED-G",
3527 "LATINEXTENDED-G");
3528
3529 /**
3530 * Constant for the "Toto" Unicode
3531 * character block.
3532 * @since 19
3533 */
3534 public static final UnicodeBlock TOTO =
3535 new UnicodeBlock("TOTO");
3536
3537 /**
3538 * Constant for the "Ethiopic Extended-B" Unicode
3539 * character block.
3540 * @since 19
3541 */
3542 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3543 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3544 "ETHIOPIC EXTENDED-B",
3545 "ETHIOPICEXTENDED-B");
3546
3547 /**
3548 * Constant for the "Arabic Extended-C" Unicode
3549 * character block.
3550 * @since 20
3551 */
3552 public static final UnicodeBlock ARABIC_EXTENDED_C =
3553 new UnicodeBlock("ARABIC_EXTENDED_C",
3554 "ARABIC EXTENDED-C",
3555 "ARABICEXTENDED-C");
3556
3557 /**
3558 * Constant for the "Devanagari Extended-A" Unicode
3559 * character block.
3560 * @since 20
3561 */
3562 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3563 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3564 "DEVANAGARI EXTENDED-A",
3565 "DEVANAGARIEXTENDED-A");
3566
3567 /**
3568 * Constant for the "Kawi" Unicode
3569 * character block.
3570 * @since 20
3571 */
3572 public static final UnicodeBlock KAWI =
3573 new UnicodeBlock("KAWI");
3574
3575 /**
3576 * Constant for the "Kaktovik Numerals" Unicode
3577 * character block.
3578 * @since 20
3579 */
3580 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3581 new UnicodeBlock("KAKTOVIK_NUMERALS",
3582 "KAKTOVIK NUMERALS",
3583 "KAKTOVIKNUMERALS");
3584
3585 /**
3586 * Constant for the "Cyrillic Extended-D" Unicode
3587 * character block.
3588 * @since 20
3589 */
3590 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3591 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3592 "CYRILLIC EXTENDED-D",
3593 "CYRILLICEXTENDED-D");
3594
3595 /**
3596 * Constant for the "Nag Mundari" Unicode
3597 * character block.
3598 * @since 20
3599 */
3600 public static final UnicodeBlock NAG_MUNDARI =
3601 new UnicodeBlock("NAG_MUNDARI",
3602 "NAG MUNDARI",
3603 "NAGMUNDARI");
3604
3605 /**
3606 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3607 * character block.
3608 * @since 20
3609 */
3610 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3611 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3612 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3613 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3614
3615 /**
3616 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3617 * character block.
3618 * @since 22
3619 */
3620 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3621 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3622 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3623 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3624
3625 /**
3626 * Constant for the "Todhri" Unicode
3627 * character block.
3628 * @since 24
3629 */
3630 public static final UnicodeBlock TODHRI =
3631 new UnicodeBlock("TODHRI");
3632
3633 /**
3634 * Constant for the "Garay" Unicode
3635 * character block.
3636 * @since 24
3637 */
3638 public static final UnicodeBlock GARAY =
3639 new UnicodeBlock("GARAY");
3640
3641 /**
3642 * Constant for the "Tulu-Tigalari" Unicode
3643 * character block.
3644 * @since 24
3645 */
3646 public static final UnicodeBlock TULU_TIGALARI =
3647 new UnicodeBlock("TULU_TIGALARI",
3648 "TULU-TIGALARI");
3649
3650 /**
3651 * Constant for the "Myanmar Extended-C" Unicode
3652 * character block.
3653 * @since 24
3654 */
3655 public static final UnicodeBlock MYANMAR_EXTENDED_C =
3656 new UnicodeBlock("MYANMAR_EXTENDED_C",
3657 "MYANMAR EXTENDED-C",
3658 "MYANMAREXTENDED-C");
3659
3660 /**
3661 * Constant for the "Sunuwar" Unicode
3662 * character block.
3663 * @since 24
3664 */
3665 public static final UnicodeBlock SUNUWAR =
3666 new UnicodeBlock("SUNUWAR");
3667
3668 /**
3669 * Constant for the "Egyptian Hieroglyphs Extended-A" Unicode
3670 * character block.
3671 * @since 24
3672 */
3673 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS_EXTENDED_A =
3674 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS_EXTENDED_A",
3675 "EGYPTIAN HIEROGLYPHS EXTENDED-A",
3676 "EGYPTIANHIEROGLYPHSEXTENDED-A");
3677
3678 /**
3679 * Constant for the "Gurung Khema" Unicode
3680 * character block.
3681 * @since 24
3682 */
3683 public static final UnicodeBlock GURUNG_KHEMA =
3684 new UnicodeBlock("GURUNG_KHEMA",
3685 "GURUNG KHEMA",
3686 "GURUNGKHEMA");
3687
3688 /**
3689 * Constant for the "Kirat Rai" Unicode
3690 * character block.
3691 * @since 24
3692 */
3693 public static final UnicodeBlock KIRAT_RAI =
3694 new UnicodeBlock("KIRAT_RAI",
3695 "KIRAT RAI",
3696 "KIRATRAI");
3697
3698 /**
3699 * Constant for the "Symbols for Legacy Computing Supplement" Unicode
3700 * character block.
3701 * @since 24
3702 */
3703 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT =
3704 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT",
3705 "SYMBOLS FOR LEGACY COMPUTING SUPPLEMENT",
3706 "SYMBOLSFORLEGACYCOMPUTINGSUPPLEMENT");
3707
3708 /**
3709 * Constant for the "Ol Onal" Unicode
3710 * character block.
3711 * @since 24
3712 */
3713 public static final UnicodeBlock OL_ONAL =
3714 new UnicodeBlock("OL_ONAL",
3715 "OL ONAL",
3716 "OLONAL");
3717
3718 private static final int[] blockStarts = {
3719 0x0000, // 0000..007F; Basic Latin
3720 0x0080, // 0080..00FF; Latin-1 Supplement
3721 0x0100, // 0100..017F; Latin Extended-A
3722 0x0180, // 0180..024F; Latin Extended-B
3723 0x0250, // 0250..02AF; IPA Extensions
3724 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3725 0x0300, // 0300..036F; Combining Diacritical Marks
3726 0x0370, // 0370..03FF; Greek and Coptic
3727 0x0400, // 0400..04FF; Cyrillic
3728 0x0500, // 0500..052F; Cyrillic Supplement
3729 0x0530, // 0530..058F; Armenian
3730 0x0590, // 0590..05FF; Hebrew
3731 0x0600, // 0600..06FF; Arabic
3732 0x0700, // 0700..074F; Syriac
3733 0x0750, // 0750..077F; Arabic Supplement
3734 0x0780, // 0780..07BF; Thaana
3735 0x07C0, // 07C0..07FF; NKo
3736 0x0800, // 0800..083F; Samaritan
3737 0x0840, // 0840..085F; Mandaic
3738 0x0860, // 0860..086F; Syriac Supplement
3739 0x0870, // 0870..089F; Arabic Extended-B
3740 0x08A0, // 08A0..08FF; Arabic Extended-A
3741 0x0900, // 0900..097F; Devanagari
3742 0x0980, // 0980..09FF; Bengali
3743 0x0A00, // 0A00..0A7F; Gurmukhi
3744 0x0A80, // 0A80..0AFF; Gujarati
3745 0x0B00, // 0B00..0B7F; Oriya
3746 0x0B80, // 0B80..0BFF; Tamil
3747 0x0C00, // 0C00..0C7F; Telugu
3748 0x0C80, // 0C80..0CFF; Kannada
3749 0x0D00, // 0D00..0D7F; Malayalam
3750 0x0D80, // 0D80..0DFF; Sinhala
3751 0x0E00, // 0E00..0E7F; Thai
3752 0x0E80, // 0E80..0EFF; Lao
3753 0x0F00, // 0F00..0FFF; Tibetan
3754 0x1000, // 1000..109F; Myanmar
3755 0x10A0, // 10A0..10FF; Georgian
3756 0x1100, // 1100..11FF; Hangul Jamo
3757 0x1200, // 1200..137F; Ethiopic
3758 0x1380, // 1380..139F; Ethiopic Supplement
3759 0x13A0, // 13A0..13FF; Cherokee
3760 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3761 0x1680, // 1680..169F; Ogham
3762 0x16A0, // 16A0..16FF; Runic
3763 0x1700, // 1700..171F; Tagalog
3764 0x1720, // 1720..173F; Hanunoo
3765 0x1740, // 1740..175F; Buhid
3766 0x1760, // 1760..177F; Tagbanwa
3767 0x1780, // 1780..17FF; Khmer
3768 0x1800, // 1800..18AF; Mongolian
3769 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3770 0x1900, // 1900..194F; Limbu
3771 0x1950, // 1950..197F; Tai Le
3772 0x1980, // 1980..19DF; New Tai Lue
3773 0x19E0, // 19E0..19FF; Khmer Symbols
3774 0x1A00, // 1A00..1A1F; Buginese
3775 0x1A20, // 1A20..1AAF; Tai Tham
3776 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3777 0x1B00, // 1B00..1B7F; Balinese
3778 0x1B80, // 1B80..1BBF; Sundanese
3779 0x1BC0, // 1BC0..1BFF; Batak
3780 0x1C00, // 1C00..1C4F; Lepcha
3781 0x1C50, // 1C50..1C7F; Ol Chiki
3782 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3783 0x1C90, // 1C90..1CBF; Georgian Extended
3784 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3785 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3786 0x1D00, // 1D00..1D7F; Phonetic Extensions
3787 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3788 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3789 0x1E00, // 1E00..1EFF; Latin Extended Additional
3790 0x1F00, // 1F00..1FFF; Greek Extended
3791 0x2000, // 2000..206F; General Punctuation
3792 0x2070, // 2070..209F; Superscripts and Subscripts
3793 0x20A0, // 20A0..20CF; Currency Symbols
3794 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3795 0x2100, // 2100..214F; Letterlike Symbols
3796 0x2150, // 2150..218F; Number Forms
3797 0x2190, // 2190..21FF; Arrows
3798 0x2200, // 2200..22FF; Mathematical Operators
3799 0x2300, // 2300..23FF; Miscellaneous Technical
3800 0x2400, // 2400..243F; Control Pictures
3801 0x2440, // 2440..245F; Optical Character Recognition
3802 0x2460, // 2460..24FF; Enclosed Alphanumerics
3803 0x2500, // 2500..257F; Box Drawing
3804 0x2580, // 2580..259F; Block Elements
3805 0x25A0, // 25A0..25FF; Geometric Shapes
3806 0x2600, // 2600..26FF; Miscellaneous Symbols
3807 0x2700, // 2700..27BF; Dingbats
3808 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3809 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3810 0x2800, // 2800..28FF; Braille Patterns
3811 0x2900, // 2900..297F; Supplemental Arrows-B
3812 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3813 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3814 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3815 0x2C00, // 2C00..2C5F; Glagolitic
3816 0x2C60, // 2C60..2C7F; Latin Extended-C
3817 0x2C80, // 2C80..2CFF; Coptic
3818 0x2D00, // 2D00..2D2F; Georgian Supplement
3819 0x2D30, // 2D30..2D7F; Tifinagh
3820 0x2D80, // 2D80..2DDF; Ethiopic Extended
3821 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3822 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3823 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3824 0x2F00, // 2F00..2FDF; Kangxi Radicals
3825 0x2FE0, // unassigned
3826 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3827 0x3000, // 3000..303F; CJK Symbols and Punctuation
3828 0x3040, // 3040..309F; Hiragana
3829 0x30A0, // 30A0..30FF; Katakana
3830 0x3100, // 3100..312F; Bopomofo
3831 0x3130, // 3130..318F; Hangul Compatibility Jamo
3832 0x3190, // 3190..319F; Kanbun
3833 0x31A0, // 31A0..31BF; Bopomofo Extended
3834 0x31C0, // 31C0..31EF; CJK Strokes
3835 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3836 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3837 0x3300, // 3300..33FF; CJK Compatibility
3838 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3839 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3840 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3841 0xA000, // A000..A48F; Yi Syllables
3842 0xA490, // A490..A4CF; Yi Radicals
3843 0xA4D0, // A4D0..A4FF; Lisu
3844 0xA500, // A500..A63F; Vai
3845 0xA640, // A640..A69F; Cyrillic Extended-B
3846 0xA6A0, // A6A0..A6FF; Bamum
3847 0xA700, // A700..A71F; Modifier Tone Letters
3848 0xA720, // A720..A7FF; Latin Extended-D
3849 0xA800, // A800..A82F; Syloti Nagri
3850 0xA830, // A830..A83F; Common Indic Number Forms
3851 0xA840, // A840..A87F; Phags-pa
3852 0xA880, // A880..A8DF; Saurashtra
3853 0xA8E0, // A8E0..A8FF; Devanagari Extended
3854 0xA900, // A900..A92F; Kayah Li
3855 0xA930, // A930..A95F; Rejang
3856 0xA960, // A960..A97F; Hangul Jamo Extended-A
3857 0xA980, // A980..A9DF; Javanese
3858 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3859 0xAA00, // AA00..AA5F; Cham
3860 0xAA60, // AA60..AA7F; Myanmar Extended-A
3861 0xAA80, // AA80..AADF; Tai Viet
3862 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3863 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3864 0xAB30, // AB30..AB6F; Latin Extended-E
3865 0xAB70, // AB70..ABBF; Cherokee Supplement
3866 0xABC0, // ABC0..ABFF; Meetei Mayek
3867 0xAC00, // AC00..D7AF; Hangul Syllables
3868 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3869 0xD800, // D800..DB7F; High Surrogates
3870 0xDB80, // DB80..DBFF; High Private Use Surrogates
3871 0xDC00, // DC00..DFFF; Low Surrogates
3872 0xE000, // E000..F8FF; Private Use Area
3873 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3874 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3875 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3876 0xFE00, // FE00..FE0F; Variation Selectors
3877 0xFE10, // FE10..FE1F; Vertical Forms
3878 0xFE20, // FE20..FE2F; Combining Half Marks
3879 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3880 0xFE50, // FE50..FE6F; Small Form Variants
3881 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3882 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3883 0xFFF0, // FFF0..FFFF; Specials
3884 0x10000, // 10000..1007F; Linear B Syllabary
3885 0x10080, // 10080..100FF; Linear B Ideograms
3886 0x10100, // 10100..1013F; Aegean Numbers
3887 0x10140, // 10140..1018F; Ancient Greek Numbers
3888 0x10190, // 10190..101CF; Ancient Symbols
3889 0x101D0, // 101D0..101FF; Phaistos Disc
3890 0x10200, // unassigned
3891 0x10280, // 10280..1029F; Lycian
3892 0x102A0, // 102A0..102DF; Carian
3893 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3894 0x10300, // 10300..1032F; Old Italic
3895 0x10330, // 10330..1034F; Gothic
3896 0x10350, // 10350..1037F; Old Permic
3897 0x10380, // 10380..1039F; Ugaritic
3898 0x103A0, // 103A0..103DF; Old Persian
3899 0x103E0, // unassigned
3900 0x10400, // 10400..1044F; Deseret
3901 0x10450, // 10450..1047F; Shavian
3902 0x10480, // 10480..104AF; Osmanya
3903 0x104B0, // 104B0..104FF; Osage
3904 0x10500, // 10500..1052F; Elbasan
3905 0x10530, // 10530..1056F; Caucasian Albanian
3906 0x10570, // 10570..105BF; Vithkuqi
3907 0x105C0, // 105C0..105FF; Todhri
3908 0x10600, // 10600..1077F; Linear A
3909 0x10780, // 10780..107BF; Latin Extended-F
3910 0x107C0, // unassigned
3911 0x10800, // 10800..1083F; Cypriot Syllabary
3912 0x10840, // 10840..1085F; Imperial Aramaic
3913 0x10860, // 10860..1087F; Palmyrene
3914 0x10880, // 10880..108AF; Nabataean
3915 0x108B0, // unassigned
3916 0x108E0, // 108E0..108FF; Hatran
3917 0x10900, // 10900..1091F; Phoenician
3918 0x10920, // 10920..1093F; Lydian
3919 0x10940, // unassigned
3920 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3921 0x109A0, // 109A0..109FF; Meroitic Cursive
3922 0x10A00, // 10A00..10A5F; Kharoshthi
3923 0x10A60, // 10A60..10A7F; Old South Arabian
3924 0x10A80, // 10A80..10A9F; Old North Arabian
3925 0x10AA0, // unassigned
3926 0x10AC0, // 10AC0..10AFF; Manichaean
3927 0x10B00, // 10B00..10B3F; Avestan
3928 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3929 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3930 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3931 0x10BB0, // unassigned
3932 0x10C00, // 10C00..10C4F; Old Turkic
3933 0x10C50, // unassigned
3934 0x10C80, // 10C80..10CFF; Old Hungarian
3935 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3936 0x10D40, // 10D40..10D8F; Garay
3937 0x10D90, // unassigned
3938 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3939 0x10E80, // 10E80..10EBF; Yezidi
3940 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
3941 0x10F00, // 10F00..10F2F; Old Sogdian
3942 0x10F30, // 10F30..10F6F; Sogdian
3943 0x10F70, // 10F70..10FAF; Old Uyghur
3944 0x10FB0, // 10FB0..10FDF; Chorasmian
3945 0x10FE0, // 10FE0..10FFF; Elymaic
3946 0x11000, // 11000..1107F; Brahmi
3947 0x11080, // 11080..110CF; Kaithi
3948 0x110D0, // 110D0..110FF; Sora Sompeng
3949 0x11100, // 11100..1114F; Chakma
3950 0x11150, // 11150..1117F; Mahajani
3951 0x11180, // 11180..111DF; Sharada
3952 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3953 0x11200, // 11200..1124F; Khojki
3954 0x11250, // unassigned
3955 0x11280, // 11280..112AF; Multani
3956 0x112B0, // 112B0..112FF; Khudawadi
3957 0x11300, // 11300..1137F; Grantha
3958 0x11380, // 11380..113FF; Tulu-Tigalari
3959 0x11400, // 11400..1147F; Newa
3960 0x11480, // 11480..114DF; Tirhuta
3961 0x114E0, // unassigned
3962 0x11580, // 11580..115FF; Siddham
3963 0x11600, // 11600..1165F; Modi
3964 0x11660, // 11660..1167F; Mongolian Supplement
3965 0x11680, // 11680..116CF; Takri
3966 0x116D0, // 116D0..116FF; Myanmar Extended-C
3967 0x11700, // 11700..1174F; Ahom
3968 0x11750, // unassigned
3969 0x11800, // 11800..1184F; Dogra
3970 0x11850, // unassigned
3971 0x118A0, // 118A0..118FF; Warang Citi
3972 0x11900, // 11900..1195F; Dives Akuru
3973 0x11960, // unassigned
3974 0x119A0, // 119A0..119FF; Nandinagari
3975 0x11A00, // 11A00..11A4F; Zanabazar Square
3976 0x11A50, // 11A50..11AAF; Soyombo
3977 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
3978 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3979 0x11B00, // 11B00..11B5F; Devanagari Extended-A
3980 0x11B60, // unassigned
3981 0x11BC0, // 11BC0..11BFF; Sunuwar
3982 0x11C00, // 11C00..11C6F; Bhaiksuki
3983 0x11C70, // 11C70..11CBF; Marchen
3984 0x11CC0, // unassigned
3985 0x11D00, // 11D00..11D5F; Masaram Gondi
3986 0x11D60, // 11D60..11DAF; Gunjala Gondi
3987 0x11DB0, // unassigned
3988 0x11EE0, // 11EE0..11EFF; Makasar
3989 0x11F00, // 11F00..11F5F; Kawi
3990 0x11F60, // unassigned
3991 0x11FB0, // 11FB0..11FBF; Lisu Supplement
3992 0x11FC0, // 11FC0..11FFF; Tamil Supplement
3993 0x12000, // 12000..123FF; Cuneiform
3994 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3995 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3996 0x12550, // unassigned
3997 0x12F90, // 12F90..12FFF; Cypro-Minoan
3998 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3999 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
4000 0x13460, // 13460..143FF; Egyptian Hieroglyphs Extended-A
4001 0x14400, // 14400..1467F; Anatolian Hieroglyphs
4002 0x14680, // unassigned
4003 0x16100, // 16100..1613F; Gurung Khema
4004 0x16140, // unassigned
4005 0x16800, // 16800..16A3F; Bamum Supplement
4006 0x16A40, // 16A40..16A6F; Mro
4007 0x16A70, // 16A70..16ACF; Tangsa
4008 0x16AD0, // 16AD0..16AFF; Bassa Vah
4009 0x16B00, // 16B00..16B8F; Pahawh Hmong
4010 0x16B90, // unassigned
4011 0x16D40, // 16D40..16D7F; Kirat Rai
4012 0x16D80, // unassigned
4013 0x16E40, // 16E40..16E9F; Medefaidrin
4014 0x16EA0, // unassigned
4015 0x16F00, // 16F00..16F9F; Miao
4016 0x16FA0, // unassigned
4017 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
4018 0x17000, // 17000..187FF; Tangut
4019 0x18800, // 18800..18AFF; Tangut Components
4020 0x18B00, // 18B00..18CFF; Khitan Small Script
4021 0x18D00, // 18D00..18D7F; Tangut Supplement
4022 0x18D80, // unassigned
4023 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
4024 0x1B000, // 1B000..1B0FF; Kana Supplement
4025 0x1B100, // 1B100..1B12F; Kana Extended-A
4026 0x1B130, // 1B130..1B16F; Small Kana Extension
4027 0x1B170, // 1B170..1B2FF; Nushu
4028 0x1B300, // unassigned
4029 0x1BC00, // 1BC00..1BC9F; Duployan
4030 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
4031 0x1BCB0, // unassigned
4032 0x1CC00, // 1CC00..1CEBF; Symbols for Legacy Computing Supplement
4033 0x1CEC0, // unassigned
4034 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
4035 0x1CFD0, // unassigned
4036 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
4037 0x1D100, // 1D100..1D1FF; Musical Symbols
4038 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
4039 0x1D250, // unassigned
4040 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
4041 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
4042 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
4043 0x1D360, // 1D360..1D37F; Counting Rod Numerals
4044 0x1D380, // unassigned
4045 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
4046 0x1D800, // 1D800..1DAAF; Sutton SignWriting
4047 0x1DAB0, // unassigned
4048 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
4049 0x1E000, // 1E000..1E02F; Glagolitic Supplement
4050 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
4051 0x1E090, // unassigned
4052 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
4053 0x1E150, // unassigned
4054 0x1E290, // 1E290..1E2BF; Toto
4055 0x1E2C0, // 1E2C0..1E2FF; Wancho
4056 0x1E300, // unassigned
4057 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
4058 0x1E500, // unassigned
4059 0x1E5D0, // 1E5D0..1E5FF; Ol Onal
4060 0x1E600, // unassigned
4061 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
4062 0x1E800, // 1E800..1E8DF; Mende Kikakui
4063 0x1E8E0, // unassigned
4064 0x1E900, // 1E900..1E95F; Adlam
4065 0x1E960, // unassigned
4066 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
4067 0x1ECC0, // unassigned
4068 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
4069 0x1ED50, // unassigned
4070 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
4071 0x1EF00, // unassigned
4072 0x1F000, // 1F000..1F02F; Mahjong Tiles
4073 0x1F030, // 1F030..1F09F; Domino Tiles
4074 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
4075 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
4076 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
4077 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
4078 0x1F600, // 1F600..1F64F; Emoticons
4079 0x1F650, // 1F650..1F67F; Ornamental Dingbats
4080 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
4081 0x1F700, // 1F700..1F77F; Alchemical Symbols
4082 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
4083 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
4084 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
4085 0x1FA00, // 1FA00..1FA6F; Chess Symbols
4086 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
4087 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
4088 0x1FC00, // unassigned
4089 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
4090 0x2A6E0, // unassigned
4091 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
4092 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
4093 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
4094 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
4095 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
4096 0x2EE60, // unassigned
4097 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
4098 0x2FA20, // unassigned
4099 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
4100 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4101 0x323B0, // unassigned
4102 0xE0000, // E0000..E007F; Tags
4103 0xE0080, // unassigned
4104 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4105 0xE01F0, // unassigned
4106 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4107 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4108 };
4109
4110 private static final UnicodeBlock[] blocks = {
4111 BASIC_LATIN,
4112 LATIN_1_SUPPLEMENT,
4113 LATIN_EXTENDED_A,
4114 LATIN_EXTENDED_B,
4115 IPA_EXTENSIONS,
4116 SPACING_MODIFIER_LETTERS,
4117 COMBINING_DIACRITICAL_MARKS,
4118 GREEK,
4119 CYRILLIC,
4120 CYRILLIC_SUPPLEMENTARY,
4121 ARMENIAN,
4122 HEBREW,
4123 ARABIC,
4124 SYRIAC,
4125 ARABIC_SUPPLEMENT,
4126 THAANA,
4127 NKO,
4128 SAMARITAN,
4129 MANDAIC,
4130 SYRIAC_SUPPLEMENT,
4131 ARABIC_EXTENDED_B,
4132 ARABIC_EXTENDED_A,
4133 DEVANAGARI,
4134 BENGALI,
4135 GURMUKHI,
4136 GUJARATI,
4137 ORIYA,
4138 TAMIL,
4139 TELUGU,
4140 KANNADA,
4141 MALAYALAM,
4142 SINHALA,
4143 THAI,
4144 LAO,
4145 TIBETAN,
4146 MYANMAR,
4147 GEORGIAN,
4148 HANGUL_JAMO,
4149 ETHIOPIC,
4150 ETHIOPIC_SUPPLEMENT,
4151 CHEROKEE,
4152 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4153 OGHAM,
4154 RUNIC,
4155 TAGALOG,
4156 HANUNOO,
4157 BUHID,
4158 TAGBANWA,
4159 KHMER,
4160 MONGOLIAN,
4161 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4162 LIMBU,
4163 TAI_LE,
4164 NEW_TAI_LUE,
4165 KHMER_SYMBOLS,
4166 BUGINESE,
4167 TAI_THAM,
4168 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4169 BALINESE,
4170 SUNDANESE,
4171 BATAK,
4172 LEPCHA,
4173 OL_CHIKI,
4174 CYRILLIC_EXTENDED_C,
4175 GEORGIAN_EXTENDED,
4176 SUNDANESE_SUPPLEMENT,
4177 VEDIC_EXTENSIONS,
4178 PHONETIC_EXTENSIONS,
4179 PHONETIC_EXTENSIONS_SUPPLEMENT,
4180 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4181 LATIN_EXTENDED_ADDITIONAL,
4182 GREEK_EXTENDED,
4183 GENERAL_PUNCTUATION,
4184 SUPERSCRIPTS_AND_SUBSCRIPTS,
4185 CURRENCY_SYMBOLS,
4186 COMBINING_MARKS_FOR_SYMBOLS,
4187 LETTERLIKE_SYMBOLS,
4188 NUMBER_FORMS,
4189 ARROWS,
4190 MATHEMATICAL_OPERATORS,
4191 MISCELLANEOUS_TECHNICAL,
4192 CONTROL_PICTURES,
4193 OPTICAL_CHARACTER_RECOGNITION,
4194 ENCLOSED_ALPHANUMERICS,
4195 BOX_DRAWING,
4196 BLOCK_ELEMENTS,
4197 GEOMETRIC_SHAPES,
4198 MISCELLANEOUS_SYMBOLS,
4199 DINGBATS,
4200 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4201 SUPPLEMENTAL_ARROWS_A,
4202 BRAILLE_PATTERNS,
4203 SUPPLEMENTAL_ARROWS_B,
4204 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4205 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4206 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4207 GLAGOLITIC,
4208 LATIN_EXTENDED_C,
4209 COPTIC,
4210 GEORGIAN_SUPPLEMENT,
4211 TIFINAGH,
4212 ETHIOPIC_EXTENDED,
4213 CYRILLIC_EXTENDED_A,
4214 SUPPLEMENTAL_PUNCTUATION,
4215 CJK_RADICALS_SUPPLEMENT,
4216 KANGXI_RADICALS,
4217 null,
4218 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4219 CJK_SYMBOLS_AND_PUNCTUATION,
4220 HIRAGANA,
4221 KATAKANA,
4222 BOPOMOFO,
4223 HANGUL_COMPATIBILITY_JAMO,
4224 KANBUN,
4225 BOPOMOFO_EXTENDED,
4226 CJK_STROKES,
4227 KATAKANA_PHONETIC_EXTENSIONS,
4228 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4229 CJK_COMPATIBILITY,
4230 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4231 YIJING_HEXAGRAM_SYMBOLS,
4232 CJK_UNIFIED_IDEOGRAPHS,
4233 YI_SYLLABLES,
4234 YI_RADICALS,
4235 LISU,
4236 VAI,
4237 CYRILLIC_EXTENDED_B,
4238 BAMUM,
4239 MODIFIER_TONE_LETTERS,
4240 LATIN_EXTENDED_D,
4241 SYLOTI_NAGRI,
4242 COMMON_INDIC_NUMBER_FORMS,
4243 PHAGS_PA,
4244 SAURASHTRA,
4245 DEVANAGARI_EXTENDED,
4246 KAYAH_LI,
4247 REJANG,
4248 HANGUL_JAMO_EXTENDED_A,
4249 JAVANESE,
4250 MYANMAR_EXTENDED_B,
4251 CHAM,
4252 MYANMAR_EXTENDED_A,
4253 TAI_VIET,
4254 MEETEI_MAYEK_EXTENSIONS,
4255 ETHIOPIC_EXTENDED_A,
4256 LATIN_EXTENDED_E,
4257 CHEROKEE_SUPPLEMENT,
4258 MEETEI_MAYEK,
4259 HANGUL_SYLLABLES,
4260 HANGUL_JAMO_EXTENDED_B,
4261 HIGH_SURROGATES,
4262 HIGH_PRIVATE_USE_SURROGATES,
4263 LOW_SURROGATES,
4264 PRIVATE_USE_AREA,
4265 CJK_COMPATIBILITY_IDEOGRAPHS,
4266 ALPHABETIC_PRESENTATION_FORMS,
4267 ARABIC_PRESENTATION_FORMS_A,
4268 VARIATION_SELECTORS,
4269 VERTICAL_FORMS,
4270 COMBINING_HALF_MARKS,
4271 CJK_COMPATIBILITY_FORMS,
4272 SMALL_FORM_VARIANTS,
4273 ARABIC_PRESENTATION_FORMS_B,
4274 HALFWIDTH_AND_FULLWIDTH_FORMS,
4275 SPECIALS,
4276 LINEAR_B_SYLLABARY,
4277 LINEAR_B_IDEOGRAMS,
4278 AEGEAN_NUMBERS,
4279 ANCIENT_GREEK_NUMBERS,
4280 ANCIENT_SYMBOLS,
4281 PHAISTOS_DISC,
4282 null,
4283 LYCIAN,
4284 CARIAN,
4285 COPTIC_EPACT_NUMBERS,
4286 OLD_ITALIC,
4287 GOTHIC,
4288 OLD_PERMIC,
4289 UGARITIC,
4290 OLD_PERSIAN,
4291 null,
4292 DESERET,
4293 SHAVIAN,
4294 OSMANYA,
4295 OSAGE,
4296 ELBASAN,
4297 CAUCASIAN_ALBANIAN,
4298 VITHKUQI,
4299 TODHRI,
4300 LINEAR_A,
4301 LATIN_EXTENDED_F,
4302 null,
4303 CYPRIOT_SYLLABARY,
4304 IMPERIAL_ARAMAIC,
4305 PALMYRENE,
4306 NABATAEAN,
4307 null,
4308 HATRAN,
4309 PHOENICIAN,
4310 LYDIAN,
4311 null,
4312 MEROITIC_HIEROGLYPHS,
4313 MEROITIC_CURSIVE,
4314 KHAROSHTHI,
4315 OLD_SOUTH_ARABIAN,
4316 OLD_NORTH_ARABIAN,
4317 null,
4318 MANICHAEAN,
4319 AVESTAN,
4320 INSCRIPTIONAL_PARTHIAN,
4321 INSCRIPTIONAL_PAHLAVI,
4322 PSALTER_PAHLAVI,
4323 null,
4324 OLD_TURKIC,
4325 null,
4326 OLD_HUNGARIAN,
4327 HANIFI_ROHINGYA,
4328 GARAY,
4329 null,
4330 RUMI_NUMERAL_SYMBOLS,
4331 YEZIDI,
4332 ARABIC_EXTENDED_C,
4333 OLD_SOGDIAN,
4334 SOGDIAN,
4335 OLD_UYGHUR,
4336 CHORASMIAN,
4337 ELYMAIC,
4338 BRAHMI,
4339 KAITHI,
4340 SORA_SOMPENG,
4341 CHAKMA,
4342 MAHAJANI,
4343 SHARADA,
4344 SINHALA_ARCHAIC_NUMBERS,
4345 KHOJKI,
4346 null,
4347 MULTANI,
4348 KHUDAWADI,
4349 GRANTHA,
4350 TULU_TIGALARI,
4351 NEWA,
4352 TIRHUTA,
4353 null,
4354 SIDDHAM,
4355 MODI,
4356 MONGOLIAN_SUPPLEMENT,
4357 TAKRI,
4358 MYANMAR_EXTENDED_C,
4359 AHOM,
4360 null,
4361 DOGRA,
4362 null,
4363 WARANG_CITI,
4364 DIVES_AKURU,
4365 null,
4366 NANDINAGARI,
4367 ZANABAZAR_SQUARE,
4368 SOYOMBO,
4369 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4370 PAU_CIN_HAU,
4371 DEVANAGARI_EXTENDED_A,
4372 null,
4373 SUNUWAR,
4374 BHAIKSUKI,
4375 MARCHEN,
4376 null,
4377 MASARAM_GONDI,
4378 GUNJALA_GONDI,
4379 null,
4380 MAKASAR,
4381 KAWI,
4382 null,
4383 LISU_SUPPLEMENT,
4384 TAMIL_SUPPLEMENT,
4385 CUNEIFORM,
4386 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4387 EARLY_DYNASTIC_CUNEIFORM,
4388 null,
4389 CYPRO_MINOAN,
4390 EGYPTIAN_HIEROGLYPHS,
4391 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4392 EGYPTIAN_HIEROGLYPHS_EXTENDED_A,
4393 ANATOLIAN_HIEROGLYPHS,
4394 null,
4395 GURUNG_KHEMA,
4396 null,
4397 BAMUM_SUPPLEMENT,
4398 MRO,
4399 TANGSA,
4400 BASSA_VAH,
4401 PAHAWH_HMONG,
4402 null,
4403 KIRAT_RAI,
4404 null,
4405 MEDEFAIDRIN,
4406 null,
4407 MIAO,
4408 null,
4409 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4410 TANGUT,
4411 TANGUT_COMPONENTS,
4412 KHITAN_SMALL_SCRIPT,
4413 TANGUT_SUPPLEMENT,
4414 null,
4415 KANA_EXTENDED_B,
4416 KANA_SUPPLEMENT,
4417 KANA_EXTENDED_A,
4418 SMALL_KANA_EXTENSION,
4419 NUSHU,
4420 null,
4421 DUPLOYAN,
4422 SHORTHAND_FORMAT_CONTROLS,
4423 null,
4424 SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT,
4425 null,
4426 ZNAMENNY_MUSICAL_NOTATION,
4427 null,
4428 BYZANTINE_MUSICAL_SYMBOLS,
4429 MUSICAL_SYMBOLS,
4430 ANCIENT_GREEK_MUSICAL_NOTATION,
4431 null,
4432 KAKTOVIK_NUMERALS,
4433 MAYAN_NUMERALS,
4434 TAI_XUAN_JING_SYMBOLS,
4435 COUNTING_ROD_NUMERALS,
4436 null,
4437 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4438 SUTTON_SIGNWRITING,
4439 null,
4440 LATIN_EXTENDED_G,
4441 GLAGOLITIC_SUPPLEMENT,
4442 CYRILLIC_EXTENDED_D,
4443 null,
4444 NYIAKENG_PUACHUE_HMONG,
4445 null,
4446 TOTO,
4447 WANCHO,
4448 null,
4449 NAG_MUNDARI,
4450 null,
4451 OL_ONAL,
4452 null,
4453 ETHIOPIC_EXTENDED_B,
4454 MENDE_KIKAKUI,
4455 null,
4456 ADLAM,
4457 null,
4458 INDIC_SIYAQ_NUMBERS,
4459 null,
4460 OTTOMAN_SIYAQ_NUMBERS,
4461 null,
4462 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4463 null,
4464 MAHJONG_TILES,
4465 DOMINO_TILES,
4466 PLAYING_CARDS,
4467 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4468 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4469 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4470 EMOTICONS,
4471 ORNAMENTAL_DINGBATS,
4472 TRANSPORT_AND_MAP_SYMBOLS,
4473 ALCHEMICAL_SYMBOLS,
4474 GEOMETRIC_SHAPES_EXTENDED,
4475 SUPPLEMENTAL_ARROWS_C,
4476 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4477 CHESS_SYMBOLS,
4478 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4479 SYMBOLS_FOR_LEGACY_COMPUTING,
4480 null,
4481 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4482 null,
4483 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4484 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4485 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4486 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4487 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4488 null,
4489 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4490 null,
4491 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4492 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4493 null,
4494 TAGS,
4495 null,
4496 VARIATION_SELECTORS_SUPPLEMENT,
4497 null,
4498 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4499 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4500 };
4501
4502
4503 /**
4504 * Returns the object representing the Unicode block containing the
4505 * given character, or {@code null} if the character is not a
4506 * member of a defined block.
4507 *
4508 * <p><b>Note:</b> This method cannot handle
4509 * <a href="Character.html#supplementary"> supplementary
4510 * characters</a>. To support all Unicode characters, including
4511 * supplementary characters, use the {@link #of(int)} method.
4512 *
4513 * @param c The character in question
4514 * @return The {@code UnicodeBlock} instance representing the
4515 * Unicode block of which this character is a member, or
4516 * {@code null} if the character is not a member of any
4517 * Unicode block
4518 */
4519 public static UnicodeBlock of(char c) {
4520 return of((int)c);
4521 }
4522
4523 /**
4524 * Returns the object representing the Unicode block
4525 * containing the given character (Unicode code point), or
4526 * {@code null} if the character is not a member of a
4527 * defined block.
4528 *
4529 * @param codePoint the character (Unicode code point) in question.
4530 * @return The {@code UnicodeBlock} instance representing the
4531 * Unicode block of which this character is a member, or
4532 * {@code null} if the character is not a member of any
4533 * Unicode block
4534 * @throws IllegalArgumentException if the specified
4535 * {@code codePoint} is an invalid Unicode code point.
4536 * @see Character#isValidCodePoint(int)
4537 * @since 1.5
4538 */
4539 public static UnicodeBlock of(int codePoint) {
4540 if (!isValidCodePoint(codePoint)) {
4541 throw new IllegalArgumentException(
4542 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4543 }
4544
4545 int top, bottom, current;
4546 bottom = 0;
4547 top = blockStarts.length;
4548 current = top/2;
4549
4550 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4551 while (top - bottom > 1) {
4552 if (codePoint >= blockStarts[current]) {
4553 bottom = current;
4554 } else {
4555 top = current;
4556 }
4557 current = (top + bottom) / 2;
4558 }
4559 return blocks[current];
4560 }
4561
4562 /**
4563 * Returns the UnicodeBlock with the given name. Block
4564 * names are determined by The Unicode Standard. The file
4565 * {@code Blocks.txt} defines blocks for a particular
4566 * version of the standard. The {@link Character} class specifies
4567 * the version of the standard that it supports.
4568 * <p>
4569 * This method accepts block names in the following forms:
4570 * <ol>
4571 * <li> Canonical block names as defined by the Unicode Standard.
4572 * For example, the standard defines a "Basic Latin" block. Therefore, this
4573 * method accepts "Basic Latin" as a valid block name. The documentation of
4574 * each UnicodeBlock provides the canonical name.
4575 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4576 * is a valid block name for the "Basic Latin" block.
4577 * <li>The text representation of each constant UnicodeBlock identifier.
4578 * For example, this method will return the {@link #BASIC_LATIN} block if
4579 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4580 * hyphens in the canonical name with underscores.
4581 * </ol>
4582 * Finally, character case is ignored for all of the valid block name forms.
4583 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4584 * The en_US locale's case mapping rules are used to provide case-insensitive
4585 * string comparisons for block name validation.
4586 * <p>
4587 * If the Unicode Standard changes block names, both the previous and
4588 * current names will be accepted.
4589 *
4590 * @param blockName A {@code UnicodeBlock} name.
4591 * @return The {@code UnicodeBlock} instance identified
4592 * by {@code blockName}
4593 * @throws IllegalArgumentException if {@code blockName} is an
4594 * invalid name
4595 * @throws NullPointerException if {@code blockName} is null
4596 * @since 1.5
4597 */
4598 public static final UnicodeBlock forName(String blockName) {
4599 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4600 if (block == null) {
4601 throw new IllegalArgumentException("Not a valid block name: "
4602 + blockName);
4603 }
4604 return block;
4605 }
4606 }
4607
4608
4609 /**
4610 * A family of character subsets representing the character scripts
4611 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4612 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4613 * character is assigned to a single Unicode script, either a specific
4614 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4615 * one of the following three special values,
4616 * {@link Character.UnicodeScript#INHERITED Inherited},
4617 * {@link Character.UnicodeScript#COMMON Common} or
4618 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4619 *
4620 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4621 * @since 1.7
4622 */
4623 public static enum UnicodeScript {
4624
4625 /**
4626 * Unicode script "Common".
4627 */
4628 COMMON,
4629
4630 /**
4631 * Unicode script "Latin".
4632 */
4633 LATIN,
4634
4635 /**
4636 * Unicode script "Greek".
4637 */
4638 GREEK,
4639
4640 /**
4641 * Unicode script "Cyrillic".
4642 */
4643 CYRILLIC,
4644
4645 /**
4646 * Unicode script "Armenian".
4647 */
4648 ARMENIAN,
4649
4650 /**
4651 * Unicode script "Hebrew".
4652 */
4653 HEBREW,
4654
4655 /**
4656 * Unicode script "Arabic".
4657 */
4658 ARABIC,
4659
4660 /**
4661 * Unicode script "Syriac".
4662 */
4663 SYRIAC,
4664
4665 /**
4666 * Unicode script "Thaana".
4667 */
4668 THAANA,
4669
4670 /**
4671 * Unicode script "Devanagari".
4672 */
4673 DEVANAGARI,
4674
4675 /**
4676 * Unicode script "Bengali".
4677 */
4678 BENGALI,
4679
4680 /**
4681 * Unicode script "Gurmukhi".
4682 */
4683 GURMUKHI,
4684
4685 /**
4686 * Unicode script "Gujarati".
4687 */
4688 GUJARATI,
4689
4690 /**
4691 * Unicode script "Oriya".
4692 */
4693 ORIYA,
4694
4695 /**
4696 * Unicode script "Tamil".
4697 */
4698 TAMIL,
4699
4700 /**
4701 * Unicode script "Telugu".
4702 */
4703 TELUGU,
4704
4705 /**
4706 * Unicode script "Kannada".
4707 */
4708 KANNADA,
4709
4710 /**
4711 * Unicode script "Malayalam".
4712 */
4713 MALAYALAM,
4714
4715 /**
4716 * Unicode script "Sinhala".
4717 */
4718 SINHALA,
4719
4720 /**
4721 * Unicode script "Thai".
4722 */
4723 THAI,
4724
4725 /**
4726 * Unicode script "Lao".
4727 */
4728 LAO,
4729
4730 /**
4731 * Unicode script "Tibetan".
4732 */
4733 TIBETAN,
4734
4735 /**
4736 * Unicode script "Myanmar".
4737 */
4738 MYANMAR,
4739
4740 /**
4741 * Unicode script "Georgian".
4742 */
4743 GEORGIAN,
4744
4745 /**
4746 * Unicode script "Hangul".
4747 */
4748 HANGUL,
4749
4750 /**
4751 * Unicode script "Ethiopic".
4752 */
4753 ETHIOPIC,
4754
4755 /**
4756 * Unicode script "Cherokee".
4757 */
4758 CHEROKEE,
4759
4760 /**
4761 * Unicode script "Canadian_Aboriginal".
4762 */
4763 CANADIAN_ABORIGINAL,
4764
4765 /**
4766 * Unicode script "Ogham".
4767 */
4768 OGHAM,
4769
4770 /**
4771 * Unicode script "Runic".
4772 */
4773 RUNIC,
4774
4775 /**
4776 * Unicode script "Khmer".
4777 */
4778 KHMER,
4779
4780 /**
4781 * Unicode script "Mongolian".
4782 */
4783 MONGOLIAN,
4784
4785 /**
4786 * Unicode script "Hiragana".
4787 */
4788 HIRAGANA,
4789
4790 /**
4791 * Unicode script "Katakana".
4792 */
4793 KATAKANA,
4794
4795 /**
4796 * Unicode script "Bopomofo".
4797 */
4798 BOPOMOFO,
4799
4800 /**
4801 * Unicode script "Han".
4802 */
4803 HAN,
4804
4805 /**
4806 * Unicode script "Yi".
4807 */
4808 YI,
4809
4810 /**
4811 * Unicode script "Old_Italic".
4812 */
4813 OLD_ITALIC,
4814
4815 /**
4816 * Unicode script "Gothic".
4817 */
4818 GOTHIC,
4819
4820 /**
4821 * Unicode script "Deseret".
4822 */
4823 DESERET,
4824
4825 /**
4826 * Unicode script "Inherited".
4827 */
4828 INHERITED,
4829
4830 /**
4831 * Unicode script "Tagalog".
4832 */
4833 TAGALOG,
4834
4835 /**
4836 * Unicode script "Hanunoo".
4837 */
4838 HANUNOO,
4839
4840 /**
4841 * Unicode script "Buhid".
4842 */
4843 BUHID,
4844
4845 /**
4846 * Unicode script "Tagbanwa".
4847 */
4848 TAGBANWA,
4849
4850 /**
4851 * Unicode script "Limbu".
4852 */
4853 LIMBU,
4854
4855 /**
4856 * Unicode script "Tai_Le".
4857 */
4858 TAI_LE,
4859
4860 /**
4861 * Unicode script "Linear_B".
4862 */
4863 LINEAR_B,
4864
4865 /**
4866 * Unicode script "Ugaritic".
4867 */
4868 UGARITIC,
4869
4870 /**
4871 * Unicode script "Shavian".
4872 */
4873 SHAVIAN,
4874
4875 /**
4876 * Unicode script "Osmanya".
4877 */
4878 OSMANYA,
4879
4880 /**
4881 * Unicode script "Cypriot".
4882 */
4883 CYPRIOT,
4884
4885 /**
4886 * Unicode script "Braille".
4887 */
4888 BRAILLE,
4889
4890 /**
4891 * Unicode script "Buginese".
4892 */
4893 BUGINESE,
4894
4895 /**
4896 * Unicode script "Coptic".
4897 */
4898 COPTIC,
4899
4900 /**
4901 * Unicode script "New_Tai_Lue".
4902 */
4903 NEW_TAI_LUE,
4904
4905 /**
4906 * Unicode script "Glagolitic".
4907 */
4908 GLAGOLITIC,
4909
4910 /**
4911 * Unicode script "Tifinagh".
4912 */
4913 TIFINAGH,
4914
4915 /**
4916 * Unicode script "Syloti_Nagri".
4917 */
4918 SYLOTI_NAGRI,
4919
4920 /**
4921 * Unicode script "Old_Persian".
4922 */
4923 OLD_PERSIAN,
4924
4925 /**
4926 * Unicode script "Kharoshthi".
4927 */
4928 KHAROSHTHI,
4929
4930 /**
4931 * Unicode script "Balinese".
4932 */
4933 BALINESE,
4934
4935 /**
4936 * Unicode script "Cuneiform".
4937 */
4938 CUNEIFORM,
4939
4940 /**
4941 * Unicode script "Phoenician".
4942 */
4943 PHOENICIAN,
4944
4945 /**
4946 * Unicode script "Phags_Pa".
4947 */
4948 PHAGS_PA,
4949
4950 /**
4951 * Unicode script "Nko".
4952 */
4953 NKO,
4954
4955 /**
4956 * Unicode script "Sundanese".
4957 */
4958 SUNDANESE,
4959
4960 /**
4961 * Unicode script "Batak".
4962 */
4963 BATAK,
4964
4965 /**
4966 * Unicode script "Lepcha".
4967 */
4968 LEPCHA,
4969
4970 /**
4971 * Unicode script "Ol_Chiki".
4972 */
4973 OL_CHIKI,
4974
4975 /**
4976 * Unicode script "Vai".
4977 */
4978 VAI,
4979
4980 /**
4981 * Unicode script "Saurashtra".
4982 */
4983 SAURASHTRA,
4984
4985 /**
4986 * Unicode script "Kayah_Li".
4987 */
4988 KAYAH_LI,
4989
4990 /**
4991 * Unicode script "Rejang".
4992 */
4993 REJANG,
4994
4995 /**
4996 * Unicode script "Lycian".
4997 */
4998 LYCIAN,
4999
5000 /**
5001 * Unicode script "Carian".
5002 */
5003 CARIAN,
5004
5005 /**
5006 * Unicode script "Lydian".
5007 */
5008 LYDIAN,
5009
5010 /**
5011 * Unicode script "Cham".
5012 */
5013 CHAM,
5014
5015 /**
5016 * Unicode script "Tai_Tham".
5017 */
5018 TAI_THAM,
5019
5020 /**
5021 * Unicode script "Tai_Viet".
5022 */
5023 TAI_VIET,
5024
5025 /**
5026 * Unicode script "Avestan".
5027 */
5028 AVESTAN,
5029
5030 /**
5031 * Unicode script "Egyptian_Hieroglyphs".
5032 */
5033 EGYPTIAN_HIEROGLYPHS,
5034
5035 /**
5036 * Unicode script "Samaritan".
5037 */
5038 SAMARITAN,
5039
5040 /**
5041 * Unicode script "Mandaic".
5042 */
5043 MANDAIC,
5044
5045 /**
5046 * Unicode script "Lisu".
5047 */
5048 LISU,
5049
5050 /**
5051 * Unicode script "Bamum".
5052 */
5053 BAMUM,
5054
5055 /**
5056 * Unicode script "Javanese".
5057 */
5058 JAVANESE,
5059
5060 /**
5061 * Unicode script "Meetei_Mayek".
5062 */
5063 MEETEI_MAYEK,
5064
5065 /**
5066 * Unicode script "Imperial_Aramaic".
5067 */
5068 IMPERIAL_ARAMAIC,
5069
5070 /**
5071 * Unicode script "Old_South_Arabian".
5072 */
5073 OLD_SOUTH_ARABIAN,
5074
5075 /**
5076 * Unicode script "Inscriptional_Parthian".
5077 */
5078 INSCRIPTIONAL_PARTHIAN,
5079
5080 /**
5081 * Unicode script "Inscriptional_Pahlavi".
5082 */
5083 INSCRIPTIONAL_PAHLAVI,
5084
5085 /**
5086 * Unicode script "Old_Turkic".
5087 */
5088 OLD_TURKIC,
5089
5090 /**
5091 * Unicode script "Brahmi".
5092 */
5093 BRAHMI,
5094
5095 /**
5096 * Unicode script "Kaithi".
5097 */
5098 KAITHI,
5099
5100 /**
5101 * Unicode script "Meroitic Hieroglyphs".
5102 * @since 1.8
5103 */
5104 MEROITIC_HIEROGLYPHS,
5105
5106 /**
5107 * Unicode script "Meroitic Cursive".
5108 * @since 1.8
5109 */
5110 MEROITIC_CURSIVE,
5111
5112 /**
5113 * Unicode script "Sora Sompeng".
5114 * @since 1.8
5115 */
5116 SORA_SOMPENG,
5117
5118 /**
5119 * Unicode script "Chakma".
5120 * @since 1.8
5121 */
5122 CHAKMA,
5123
5124 /**
5125 * Unicode script "Sharada".
5126 * @since 1.8
5127 */
5128 SHARADA,
5129
5130 /**
5131 * Unicode script "Takri".
5132 * @since 1.8
5133 */
5134 TAKRI,
5135
5136 /**
5137 * Unicode script "Miao".
5138 * @since 1.8
5139 */
5140 MIAO,
5141
5142 /**
5143 * Unicode script "Caucasian Albanian".
5144 * @since 9
5145 */
5146 CAUCASIAN_ALBANIAN,
5147
5148 /**
5149 * Unicode script "Bassa Vah".
5150 * @since 9
5151 */
5152 BASSA_VAH,
5153
5154 /**
5155 * Unicode script "Duployan".
5156 * @since 9
5157 */
5158 DUPLOYAN,
5159
5160 /**
5161 * Unicode script "Elbasan".
5162 * @since 9
5163 */
5164 ELBASAN,
5165
5166 /**
5167 * Unicode script "Grantha".
5168 * @since 9
5169 */
5170 GRANTHA,
5171
5172 /**
5173 * Unicode script "Pahawh Hmong".
5174 * @since 9
5175 */
5176 PAHAWH_HMONG,
5177
5178 /**
5179 * Unicode script "Khojki".
5180 * @since 9
5181 */
5182 KHOJKI,
5183
5184 /**
5185 * Unicode script "Linear A".
5186 * @since 9
5187 */
5188 LINEAR_A,
5189
5190 /**
5191 * Unicode script "Mahajani".
5192 * @since 9
5193 */
5194 MAHAJANI,
5195
5196 /**
5197 * Unicode script "Manichaean".
5198 * @since 9
5199 */
5200 MANICHAEAN,
5201
5202 /**
5203 * Unicode script "Mende Kikakui".
5204 * @since 9
5205 */
5206 MENDE_KIKAKUI,
5207
5208 /**
5209 * Unicode script "Modi".
5210 * @since 9
5211 */
5212 MODI,
5213
5214 /**
5215 * Unicode script "Mro".
5216 * @since 9
5217 */
5218 MRO,
5219
5220 /**
5221 * Unicode script "Old North Arabian".
5222 * @since 9
5223 */
5224 OLD_NORTH_ARABIAN,
5225
5226 /**
5227 * Unicode script "Nabataean".
5228 * @since 9
5229 */
5230 NABATAEAN,
5231
5232 /**
5233 * Unicode script "Palmyrene".
5234 * @since 9
5235 */
5236 PALMYRENE,
5237
5238 /**
5239 * Unicode script "Pau Cin Hau".
5240 * @since 9
5241 */
5242 PAU_CIN_HAU,
5243
5244 /**
5245 * Unicode script "Old Permic".
5246 * @since 9
5247 */
5248 OLD_PERMIC,
5249
5250 /**
5251 * Unicode script "Psalter Pahlavi".
5252 * @since 9
5253 */
5254 PSALTER_PAHLAVI,
5255
5256 /**
5257 * Unicode script "Siddham".
5258 * @since 9
5259 */
5260 SIDDHAM,
5261
5262 /**
5263 * Unicode script "Khudawadi".
5264 * @since 9
5265 */
5266 KHUDAWADI,
5267
5268 /**
5269 * Unicode script "Tirhuta".
5270 * @since 9
5271 */
5272 TIRHUTA,
5273
5274 /**
5275 * Unicode script "Warang Citi".
5276 * @since 9
5277 */
5278 WARANG_CITI,
5279
5280 /**
5281 * Unicode script "Ahom".
5282 * @since 9
5283 */
5284 AHOM,
5285
5286 /**
5287 * Unicode script "Anatolian Hieroglyphs".
5288 * @since 9
5289 */
5290 ANATOLIAN_HIEROGLYPHS,
5291
5292 /**
5293 * Unicode script "Hatran".
5294 * @since 9
5295 */
5296 HATRAN,
5297
5298 /**
5299 * Unicode script "Multani".
5300 * @since 9
5301 */
5302 MULTANI,
5303
5304 /**
5305 * Unicode script "Old Hungarian".
5306 * @since 9
5307 */
5308 OLD_HUNGARIAN,
5309
5310 /**
5311 * Unicode script "SignWriting".
5312 * @since 9
5313 */
5314 SIGNWRITING,
5315
5316 /**
5317 * Unicode script "Adlam".
5318 * @since 11
5319 */
5320 ADLAM,
5321
5322 /**
5323 * Unicode script "Bhaiksuki".
5324 * @since 11
5325 */
5326 BHAIKSUKI,
5327
5328 /**
5329 * Unicode script "Marchen".
5330 * @since 11
5331 */
5332 MARCHEN,
5333
5334 /**
5335 * Unicode script "Newa".
5336 * @since 11
5337 */
5338 NEWA,
5339
5340 /**
5341 * Unicode script "Osage".
5342 * @since 11
5343 */
5344 OSAGE,
5345
5346 /**
5347 * Unicode script "Tangut".
5348 * @since 11
5349 */
5350 TANGUT,
5351
5352 /**
5353 * Unicode script "Masaram Gondi".
5354 * @since 11
5355 */
5356 MASARAM_GONDI,
5357
5358 /**
5359 * Unicode script "Nushu".
5360 * @since 11
5361 */
5362 NUSHU,
5363
5364 /**
5365 * Unicode script "Soyombo".
5366 * @since 11
5367 */
5368 SOYOMBO,
5369
5370 /**
5371 * Unicode script "Zanabazar Square".
5372 * @since 11
5373 */
5374 ZANABAZAR_SQUARE,
5375
5376 /**
5377 * Unicode script "Hanifi Rohingya".
5378 * @since 12
5379 */
5380 HANIFI_ROHINGYA,
5381
5382 /**
5383 * Unicode script "Old Sogdian".
5384 * @since 12
5385 */
5386 OLD_SOGDIAN,
5387
5388 /**
5389 * Unicode script "Sogdian".
5390 * @since 12
5391 */
5392 SOGDIAN,
5393
5394 /**
5395 * Unicode script "Dogra".
5396 * @since 12
5397 */
5398 DOGRA,
5399
5400 /**
5401 * Unicode script "Gunjala Gondi".
5402 * @since 12
5403 */
5404 GUNJALA_GONDI,
5405
5406 /**
5407 * Unicode script "Makasar".
5408 * @since 12
5409 */
5410 MAKASAR,
5411
5412 /**
5413 * Unicode script "Medefaidrin".
5414 * @since 12
5415 */
5416 MEDEFAIDRIN,
5417
5418 /**
5419 * Unicode script "Elymaic".
5420 * @since 13
5421 */
5422 ELYMAIC,
5423
5424 /**
5425 * Unicode script "Nandinagari".
5426 * @since 13
5427 */
5428 NANDINAGARI,
5429
5430 /**
5431 * Unicode script "Nyiakeng Puachue Hmong".
5432 * @since 13
5433 */
5434 NYIAKENG_PUACHUE_HMONG,
5435
5436 /**
5437 * Unicode script "Wancho".
5438 * @since 13
5439 */
5440 WANCHO,
5441
5442 /**
5443 * Unicode script "Yezidi".
5444 * @since 15
5445 */
5446 YEZIDI,
5447
5448 /**
5449 * Unicode script "Chorasmian".
5450 * @since 15
5451 */
5452 CHORASMIAN,
5453
5454 /**
5455 * Unicode script "Dives Akuru".
5456 * @since 15
5457 */
5458 DIVES_AKURU,
5459
5460 /**
5461 * Unicode script "Khitan Small Script".
5462 * @since 15
5463 */
5464 KHITAN_SMALL_SCRIPT,
5465
5466 /**
5467 * Unicode script "Vithkuqi".
5468 * @since 19
5469 */
5470 VITHKUQI,
5471
5472 /**
5473 * Unicode script "Old Uyghur".
5474 * @since 19
5475 */
5476 OLD_UYGHUR,
5477
5478 /**
5479 * Unicode script "Cypro Minoan".
5480 * @since 19
5481 */
5482 CYPRO_MINOAN,
5483
5484 /**
5485 * Unicode script "Tangsa".
5486 * @since 19
5487 */
5488 TANGSA,
5489
5490 /**
5491 * Unicode script "Toto".
5492 * @since 19
5493 */
5494 TOTO,
5495
5496 /**
5497 * Unicode script "Kawi".
5498 * @since 20
5499 */
5500 KAWI,
5501
5502 /**
5503 * Unicode script "Nag Mundari".
5504 * @since 20
5505 */
5506 NAG_MUNDARI,
5507
5508 /**
5509 * Unicode script "Todhri".
5510 * @since 24
5511 */
5512 TODHRI,
5513
5514 /**
5515 * Unicode script "Garay".
5516 * @since 24
5517 */
5518 GARAY,
5519
5520 /**
5521 * Unicode script "Tulu Tigalari".
5522 * @since 24
5523 */
5524 TULU_TIGALARI,
5525
5526 /**
5527 * Unicode script "Sunuwar".
5528 * @since 24
5529 */
5530 SUNUWAR,
5531
5532 /**
5533 * Unicode script "Gurung Khema".
5534 * @since 24
5535 */
5536 GURUNG_KHEMA,
5537
5538 /**
5539 * Unicode script "Kirat Rai".
5540 * @since 24
5541 */
5542 KIRAT_RAI,
5543
5544 /**
5545 * Unicode script "Ol Onal".
5546 * @since 24
5547 */
5548 OL_ONAL,
5549
5550 /**
5551 * Unicode script "Unknown".
5552 */
5553 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5554
5555 private static final int[] scriptStarts = {
5556 0x0000, // 0000..0040; COMMON
5557 0x0041, // 0041..005A; LATIN
5558 0x005B, // 005B..0060; COMMON
5559 0x0061, // 0061..007A; LATIN
5560 0x007B, // 007B..00A9; COMMON
5561 0x00AA, // 00AA ; LATIN
5562 0x00AB, // 00AB..00B9; COMMON
5563 0x00BA, // 00BA ; LATIN
5564 0x00BB, // 00BB..00BF; COMMON
5565 0x00C0, // 00C0..00D6; LATIN
5566 0x00D7, // 00D7 ; COMMON
5567 0x00D8, // 00D8..00F6; LATIN
5568 0x00F7, // 00F7 ; COMMON
5569 0x00F8, // 00F8..02B8; LATIN
5570 0x02B9, // 02B9..02DF; COMMON
5571 0x02E0, // 02E0..02E4; LATIN
5572 0x02E5, // 02E5..02E9; COMMON
5573 0x02EA, // 02EA..02EB; BOPOMOFO
5574 0x02EC, // 02EC..02FF; COMMON
5575 0x0300, // 0300..036F; INHERITED
5576 0x0370, // 0370..0373; GREEK
5577 0x0374, // 0374 ; COMMON
5578 0x0375, // 0375..0377; GREEK
5579 0x0378, // 0378..0379; UNKNOWN
5580 0x037A, // 037A..037D; GREEK
5581 0x037E, // 037E ; COMMON
5582 0x037F, // 037F ; GREEK
5583 0x0380, // 0380..0383; UNKNOWN
5584 0x0384, // 0384 ; GREEK
5585 0x0385, // 0385 ; COMMON
5586 0x0386, // 0386 ; GREEK
5587 0x0387, // 0387 ; COMMON
5588 0x0388, // 0388..038A; GREEK
5589 0x038B, // 038B ; UNKNOWN
5590 0x038C, // 038C ; GREEK
5591 0x038D, // 038D ; UNKNOWN
5592 0x038E, // 038E..03A1; GREEK
5593 0x03A2, // 03A2 ; UNKNOWN
5594 0x03A3, // 03A3..03E1; GREEK
5595 0x03E2, // 03E2..03EF; COPTIC
5596 0x03F0, // 03F0..03FF; GREEK
5597 0x0400, // 0400..0484; CYRILLIC
5598 0x0485, // 0485..0486; INHERITED
5599 0x0487, // 0487..052F; CYRILLIC
5600 0x0530, // 0530 ; UNKNOWN
5601 0x0531, // 0531..0556; ARMENIAN
5602 0x0557, // 0557..0558; UNKNOWN
5603 0x0559, // 0559..058A; ARMENIAN
5604 0x058B, // 058B..058C; UNKNOWN
5605 0x058D, // 058D..058F; ARMENIAN
5606 0x0590, // 0590 ; UNKNOWN
5607 0x0591, // 0591..05C7; HEBREW
5608 0x05C8, // 05C8..05CF; UNKNOWN
5609 0x05D0, // 05D0..05EA; HEBREW
5610 0x05EB, // 05EB..05EE; UNKNOWN
5611 0x05EF, // 05EF..05F4; HEBREW
5612 0x05F5, // 05F5..05FF; UNKNOWN
5613 0x0600, // 0600..0604; ARABIC
5614 0x0605, // 0605 ; COMMON
5615 0x0606, // 0606..060B; ARABIC
5616 0x060C, // 060C ; COMMON
5617 0x060D, // 060D..061A; ARABIC
5618 0x061B, // 061B ; COMMON
5619 0x061C, // 061C..061E; ARABIC
5620 0x061F, // 061F ; COMMON
5621 0x0620, // 0620..063F; ARABIC
5622 0x0640, // 0640 ; COMMON
5623 0x0641, // 0641..064A; ARABIC
5624 0x064B, // 064B..0655; INHERITED
5625 0x0656, // 0656..066F; ARABIC
5626 0x0670, // 0670 ; INHERITED
5627 0x0671, // 0671..06DC; ARABIC
5628 0x06DD, // 06DD ; COMMON
5629 0x06DE, // 06DE..06FF; ARABIC
5630 0x0700, // 0700..070D; SYRIAC
5631 0x070E, // 070E ; UNKNOWN
5632 0x070F, // 070F..074A; SYRIAC
5633 0x074B, // 074B..074C; UNKNOWN
5634 0x074D, // 074D..074F; SYRIAC
5635 0x0750, // 0750..077F; ARABIC
5636 0x0780, // 0780..07B1; THAANA
5637 0x07B2, // 07B2..07BF; UNKNOWN
5638 0x07C0, // 07C0..07FA; NKO
5639 0x07FB, // 07FB..07FC; UNKNOWN
5640 0x07FD, // 07FD..07FF; NKO
5641 0x0800, // 0800..082D; SAMARITAN
5642 0x082E, // 082E..082F; UNKNOWN
5643 0x0830, // 0830..083E; SAMARITAN
5644 0x083F, // 083F ; UNKNOWN
5645 0x0840, // 0840..085B; MANDAIC
5646 0x085C, // 085C..085D; UNKNOWN
5647 0x085E, // 085E ; MANDAIC
5648 0x085F, // 085F ; UNKNOWN
5649 0x0860, // 0860..086A; SYRIAC
5650 0x086B, // 086B..086F; UNKNOWN
5651 0x0870, // 0870..088E; ARABIC
5652 0x088F, // 088F ; UNKNOWN
5653 0x0890, // 0890..0891; ARABIC
5654 0x0892, // 0892..0896; UNKNOWN
5655 0x0897, // 0897..08E1; ARABIC
5656 0x08E2, // 08E2 ; COMMON
5657 0x08E3, // 08E3..08FF; ARABIC
5658 0x0900, // 0900..0950; DEVANAGARI
5659 0x0951, // 0951..0954; INHERITED
5660 0x0955, // 0955..0963; DEVANAGARI
5661 0x0964, // 0964..0965; COMMON
5662 0x0966, // 0966..097F; DEVANAGARI
5663 0x0980, // 0980..0983; BENGALI
5664 0x0984, // 0984 ; UNKNOWN
5665 0x0985, // 0985..098C; BENGALI
5666 0x098D, // 098D..098E; UNKNOWN
5667 0x098F, // 098F..0990; BENGALI
5668 0x0991, // 0991..0992; UNKNOWN
5669 0x0993, // 0993..09A8; BENGALI
5670 0x09A9, // 09A9 ; UNKNOWN
5671 0x09AA, // 09AA..09B0; BENGALI
5672 0x09B1, // 09B1 ; UNKNOWN
5673 0x09B2, // 09B2 ; BENGALI
5674 0x09B3, // 09B3..09B5; UNKNOWN
5675 0x09B6, // 09B6..09B9; BENGALI
5676 0x09BA, // 09BA..09BB; UNKNOWN
5677 0x09BC, // 09BC..09C4; BENGALI
5678 0x09C5, // 09C5..09C6; UNKNOWN
5679 0x09C7, // 09C7..09C8; BENGALI
5680 0x09C9, // 09C9..09CA; UNKNOWN
5681 0x09CB, // 09CB..09CE; BENGALI
5682 0x09CF, // 09CF..09D6; UNKNOWN
5683 0x09D7, // 09D7 ; BENGALI
5684 0x09D8, // 09D8..09DB; UNKNOWN
5685 0x09DC, // 09DC..09DD; BENGALI
5686 0x09DE, // 09DE ; UNKNOWN
5687 0x09DF, // 09DF..09E3; BENGALI
5688 0x09E4, // 09E4..09E5; UNKNOWN
5689 0x09E6, // 09E6..09FE; BENGALI
5690 0x09FF, // 09FF..0A00; UNKNOWN
5691 0x0A01, // 0A01..0A03; GURMUKHI
5692 0x0A04, // 0A04 ; UNKNOWN
5693 0x0A05, // 0A05..0A0A; GURMUKHI
5694 0x0A0B, // 0A0B..0A0E; UNKNOWN
5695 0x0A0F, // 0A0F..0A10; GURMUKHI
5696 0x0A11, // 0A11..0A12; UNKNOWN
5697 0x0A13, // 0A13..0A28; GURMUKHI
5698 0x0A29, // 0A29 ; UNKNOWN
5699 0x0A2A, // 0A2A..0A30; GURMUKHI
5700 0x0A31, // 0A31 ; UNKNOWN
5701 0x0A32, // 0A32..0A33; GURMUKHI
5702 0x0A34, // 0A34 ; UNKNOWN
5703 0x0A35, // 0A35..0A36; GURMUKHI
5704 0x0A37, // 0A37 ; UNKNOWN
5705 0x0A38, // 0A38..0A39; GURMUKHI
5706 0x0A3A, // 0A3A..0A3B; UNKNOWN
5707 0x0A3C, // 0A3C ; GURMUKHI
5708 0x0A3D, // 0A3D ; UNKNOWN
5709 0x0A3E, // 0A3E..0A42; GURMUKHI
5710 0x0A43, // 0A43..0A46; UNKNOWN
5711 0x0A47, // 0A47..0A48; GURMUKHI
5712 0x0A49, // 0A49..0A4A; UNKNOWN
5713 0x0A4B, // 0A4B..0A4D; GURMUKHI
5714 0x0A4E, // 0A4E..0A50; UNKNOWN
5715 0x0A51, // 0A51 ; GURMUKHI
5716 0x0A52, // 0A52..0A58; UNKNOWN
5717 0x0A59, // 0A59..0A5C; GURMUKHI
5718 0x0A5D, // 0A5D ; UNKNOWN
5719 0x0A5E, // 0A5E ; GURMUKHI
5720 0x0A5F, // 0A5F..0A65; UNKNOWN
5721 0x0A66, // 0A66..0A76; GURMUKHI
5722 0x0A77, // 0A77..0A80; UNKNOWN
5723 0x0A81, // 0A81..0A83; GUJARATI
5724 0x0A84, // 0A84 ; UNKNOWN
5725 0x0A85, // 0A85..0A8D; GUJARATI
5726 0x0A8E, // 0A8E ; UNKNOWN
5727 0x0A8F, // 0A8F..0A91; GUJARATI
5728 0x0A92, // 0A92 ; UNKNOWN
5729 0x0A93, // 0A93..0AA8; GUJARATI
5730 0x0AA9, // 0AA9 ; UNKNOWN
5731 0x0AAA, // 0AAA..0AB0; GUJARATI
5732 0x0AB1, // 0AB1 ; UNKNOWN
5733 0x0AB2, // 0AB2..0AB3; GUJARATI
5734 0x0AB4, // 0AB4 ; UNKNOWN
5735 0x0AB5, // 0AB5..0AB9; GUJARATI
5736 0x0ABA, // 0ABA..0ABB; UNKNOWN
5737 0x0ABC, // 0ABC..0AC5; GUJARATI
5738 0x0AC6, // 0AC6 ; UNKNOWN
5739 0x0AC7, // 0AC7..0AC9; GUJARATI
5740 0x0ACA, // 0ACA ; UNKNOWN
5741 0x0ACB, // 0ACB..0ACD; GUJARATI
5742 0x0ACE, // 0ACE..0ACF; UNKNOWN
5743 0x0AD0, // 0AD0 ; GUJARATI
5744 0x0AD1, // 0AD1..0ADF; UNKNOWN
5745 0x0AE0, // 0AE0..0AE3; GUJARATI
5746 0x0AE4, // 0AE4..0AE5; UNKNOWN
5747 0x0AE6, // 0AE6..0AF1; GUJARATI
5748 0x0AF2, // 0AF2..0AF8; UNKNOWN
5749 0x0AF9, // 0AF9..0AFF; GUJARATI
5750 0x0B00, // 0B00 ; UNKNOWN
5751 0x0B01, // 0B01..0B03; ORIYA
5752 0x0B04, // 0B04 ; UNKNOWN
5753 0x0B05, // 0B05..0B0C; ORIYA
5754 0x0B0D, // 0B0D..0B0E; UNKNOWN
5755 0x0B0F, // 0B0F..0B10; ORIYA
5756 0x0B11, // 0B11..0B12; UNKNOWN
5757 0x0B13, // 0B13..0B28; ORIYA
5758 0x0B29, // 0B29 ; UNKNOWN
5759 0x0B2A, // 0B2A..0B30; ORIYA
5760 0x0B31, // 0B31 ; UNKNOWN
5761 0x0B32, // 0B32..0B33; ORIYA
5762 0x0B34, // 0B34 ; UNKNOWN
5763 0x0B35, // 0B35..0B39; ORIYA
5764 0x0B3A, // 0B3A..0B3B; UNKNOWN
5765 0x0B3C, // 0B3C..0B44; ORIYA
5766 0x0B45, // 0B45..0B46; UNKNOWN
5767 0x0B47, // 0B47..0B48; ORIYA
5768 0x0B49, // 0B49..0B4A; UNKNOWN
5769 0x0B4B, // 0B4B..0B4D; ORIYA
5770 0x0B4E, // 0B4E..0B54; UNKNOWN
5771 0x0B55, // 0B55..0B57; ORIYA
5772 0x0B58, // 0B58..0B5B; UNKNOWN
5773 0x0B5C, // 0B5C..0B5D; ORIYA
5774 0x0B5E, // 0B5E ; UNKNOWN
5775 0x0B5F, // 0B5F..0B63; ORIYA
5776 0x0B64, // 0B64..0B65; UNKNOWN
5777 0x0B66, // 0B66..0B77; ORIYA
5778 0x0B78, // 0B78..0B81; UNKNOWN
5779 0x0B82, // 0B82..0B83; TAMIL
5780 0x0B84, // 0B84 ; UNKNOWN
5781 0x0B85, // 0B85..0B8A; TAMIL
5782 0x0B8B, // 0B8B..0B8D; UNKNOWN
5783 0x0B8E, // 0B8E..0B90; TAMIL
5784 0x0B91, // 0B91 ; UNKNOWN
5785 0x0B92, // 0B92..0B95; TAMIL
5786 0x0B96, // 0B96..0B98; UNKNOWN
5787 0x0B99, // 0B99..0B9A; TAMIL
5788 0x0B9B, // 0B9B ; UNKNOWN
5789 0x0B9C, // 0B9C ; TAMIL
5790 0x0B9D, // 0B9D ; UNKNOWN
5791 0x0B9E, // 0B9E..0B9F; TAMIL
5792 0x0BA0, // 0BA0..0BA2; UNKNOWN
5793 0x0BA3, // 0BA3..0BA4; TAMIL
5794 0x0BA5, // 0BA5..0BA7; UNKNOWN
5795 0x0BA8, // 0BA8..0BAA; TAMIL
5796 0x0BAB, // 0BAB..0BAD; UNKNOWN
5797 0x0BAE, // 0BAE..0BB9; TAMIL
5798 0x0BBA, // 0BBA..0BBD; UNKNOWN
5799 0x0BBE, // 0BBE..0BC2; TAMIL
5800 0x0BC3, // 0BC3..0BC5; UNKNOWN
5801 0x0BC6, // 0BC6..0BC8; TAMIL
5802 0x0BC9, // 0BC9 ; UNKNOWN
5803 0x0BCA, // 0BCA..0BCD; TAMIL
5804 0x0BCE, // 0BCE..0BCF; UNKNOWN
5805 0x0BD0, // 0BD0 ; TAMIL
5806 0x0BD1, // 0BD1..0BD6; UNKNOWN
5807 0x0BD7, // 0BD7 ; TAMIL
5808 0x0BD8, // 0BD8..0BE5; UNKNOWN
5809 0x0BE6, // 0BE6..0BFA; TAMIL
5810 0x0BFB, // 0BFB..0BFF; UNKNOWN
5811 0x0C00, // 0C00..0C0C; TELUGU
5812 0x0C0D, // 0C0D ; UNKNOWN
5813 0x0C0E, // 0C0E..0C10; TELUGU
5814 0x0C11, // 0C11 ; UNKNOWN
5815 0x0C12, // 0C12..0C28; TELUGU
5816 0x0C29, // 0C29 ; UNKNOWN
5817 0x0C2A, // 0C2A..0C39; TELUGU
5818 0x0C3A, // 0C3A..0C3B; UNKNOWN
5819 0x0C3C, // 0C3C..0C44; TELUGU
5820 0x0C45, // 0C45 ; UNKNOWN
5821 0x0C46, // 0C46..0C48; TELUGU
5822 0x0C49, // 0C49 ; UNKNOWN
5823 0x0C4A, // 0C4A..0C4D; TELUGU
5824 0x0C4E, // 0C4E..0C54; UNKNOWN
5825 0x0C55, // 0C55..0C56; TELUGU
5826 0x0C57, // 0C57 ; UNKNOWN
5827 0x0C58, // 0C58..0C5A; TELUGU
5828 0x0C5B, // 0C5B..0C5C; UNKNOWN
5829 0x0C5D, // 0C5D ; TELUGU
5830 0x0C5E, // 0C5E..0C5F; UNKNOWN
5831 0x0C60, // 0C60..0C63; TELUGU
5832 0x0C64, // 0C64..0C65; UNKNOWN
5833 0x0C66, // 0C66..0C6F; TELUGU
5834 0x0C70, // 0C70..0C76; UNKNOWN
5835 0x0C77, // 0C77..0C7F; TELUGU
5836 0x0C80, // 0C80..0C8C; KANNADA
5837 0x0C8D, // 0C8D ; UNKNOWN
5838 0x0C8E, // 0C8E..0C90; KANNADA
5839 0x0C91, // 0C91 ; UNKNOWN
5840 0x0C92, // 0C92..0CA8; KANNADA
5841 0x0CA9, // 0CA9 ; UNKNOWN
5842 0x0CAA, // 0CAA..0CB3; KANNADA
5843 0x0CB4, // 0CB4 ; UNKNOWN
5844 0x0CB5, // 0CB5..0CB9; KANNADA
5845 0x0CBA, // 0CBA..0CBB; UNKNOWN
5846 0x0CBC, // 0CBC..0CC4; KANNADA
5847 0x0CC5, // 0CC5 ; UNKNOWN
5848 0x0CC6, // 0CC6..0CC8; KANNADA
5849 0x0CC9, // 0CC9 ; UNKNOWN
5850 0x0CCA, // 0CCA..0CCD; KANNADA
5851 0x0CCE, // 0CCE..0CD4; UNKNOWN
5852 0x0CD5, // 0CD5..0CD6; KANNADA
5853 0x0CD7, // 0CD7..0CDC; UNKNOWN
5854 0x0CDD, // 0CDD..0CDE; KANNADA
5855 0x0CDF, // 0CDF ; UNKNOWN
5856 0x0CE0, // 0CE0..0CE3; KANNADA
5857 0x0CE4, // 0CE4..0CE5; UNKNOWN
5858 0x0CE6, // 0CE6..0CEF; KANNADA
5859 0x0CF0, // 0CF0 ; UNKNOWN
5860 0x0CF1, // 0CF1..0CF3; KANNADA
5861 0x0CF4, // 0CF4..0CFF; UNKNOWN
5862 0x0D00, // 0D00..0D0C; MALAYALAM
5863 0x0D0D, // 0D0D ; UNKNOWN
5864 0x0D0E, // 0D0E..0D10; MALAYALAM
5865 0x0D11, // 0D11 ; UNKNOWN
5866 0x0D12, // 0D12..0D44; MALAYALAM
5867 0x0D45, // 0D45 ; UNKNOWN
5868 0x0D46, // 0D46..0D48; MALAYALAM
5869 0x0D49, // 0D49 ; UNKNOWN
5870 0x0D4A, // 0D4A..0D4F; MALAYALAM
5871 0x0D50, // 0D50..0D53; UNKNOWN
5872 0x0D54, // 0D54..0D63; MALAYALAM
5873 0x0D64, // 0D64..0D65; UNKNOWN
5874 0x0D66, // 0D66..0D7F; MALAYALAM
5875 0x0D80, // 0D80 ; UNKNOWN
5876 0x0D81, // 0D81..0D83; SINHALA
5877 0x0D84, // 0D84 ; UNKNOWN
5878 0x0D85, // 0D85..0D96; SINHALA
5879 0x0D97, // 0D97..0D99; UNKNOWN
5880 0x0D9A, // 0D9A..0DB1; SINHALA
5881 0x0DB2, // 0DB2 ; UNKNOWN
5882 0x0DB3, // 0DB3..0DBB; SINHALA
5883 0x0DBC, // 0DBC ; UNKNOWN
5884 0x0DBD, // 0DBD ; SINHALA
5885 0x0DBE, // 0DBE..0DBF; UNKNOWN
5886 0x0DC0, // 0DC0..0DC6; SINHALA
5887 0x0DC7, // 0DC7..0DC9; UNKNOWN
5888 0x0DCA, // 0DCA ; SINHALA
5889 0x0DCB, // 0DCB..0DCE; UNKNOWN
5890 0x0DCF, // 0DCF..0DD4; SINHALA
5891 0x0DD5, // 0DD5 ; UNKNOWN
5892 0x0DD6, // 0DD6 ; SINHALA
5893 0x0DD7, // 0DD7 ; UNKNOWN
5894 0x0DD8, // 0DD8..0DDF; SINHALA
5895 0x0DE0, // 0DE0..0DE5; UNKNOWN
5896 0x0DE6, // 0DE6..0DEF; SINHALA
5897 0x0DF0, // 0DF0..0DF1; UNKNOWN
5898 0x0DF2, // 0DF2..0DF4; SINHALA
5899 0x0DF5, // 0DF5..0E00; UNKNOWN
5900 0x0E01, // 0E01..0E3A; THAI
5901 0x0E3B, // 0E3B..0E3E; UNKNOWN
5902 0x0E3F, // 0E3F ; COMMON
5903 0x0E40, // 0E40..0E5B; THAI
5904 0x0E5C, // 0E5C..0E80; UNKNOWN
5905 0x0E81, // 0E81..0E82; LAO
5906 0x0E83, // 0E83 ; UNKNOWN
5907 0x0E84, // 0E84 ; LAO
5908 0x0E85, // 0E85 ; UNKNOWN
5909 0x0E86, // 0E86..0E8A; LAO
5910 0x0E8B, // 0E8B ; UNKNOWN
5911 0x0E8C, // 0E8C..0EA3; LAO
5912 0x0EA4, // 0EA4 ; UNKNOWN
5913 0x0EA5, // 0EA5 ; LAO
5914 0x0EA6, // 0EA6 ; UNKNOWN
5915 0x0EA7, // 0EA7..0EBD; LAO
5916 0x0EBE, // 0EBE..0EBF; UNKNOWN
5917 0x0EC0, // 0EC0..0EC4; LAO
5918 0x0EC5, // 0EC5 ; UNKNOWN
5919 0x0EC6, // 0EC6 ; LAO
5920 0x0EC7, // 0EC7 ; UNKNOWN
5921 0x0EC8, // 0EC8..0ECE; LAO
5922 0x0ECF, // 0ECF ; UNKNOWN
5923 0x0ED0, // 0ED0..0ED9; LAO
5924 0x0EDA, // 0EDA..0EDB; UNKNOWN
5925 0x0EDC, // 0EDC..0EDF; LAO
5926 0x0EE0, // 0EE0..0EFF; UNKNOWN
5927 0x0F00, // 0F00..0F47; TIBETAN
5928 0x0F48, // 0F48 ; UNKNOWN
5929 0x0F49, // 0F49..0F6C; TIBETAN
5930 0x0F6D, // 0F6D..0F70; UNKNOWN
5931 0x0F71, // 0F71..0F97; TIBETAN
5932 0x0F98, // 0F98 ; UNKNOWN
5933 0x0F99, // 0F99..0FBC; TIBETAN
5934 0x0FBD, // 0FBD ; UNKNOWN
5935 0x0FBE, // 0FBE..0FCC; TIBETAN
5936 0x0FCD, // 0FCD ; UNKNOWN
5937 0x0FCE, // 0FCE..0FD4; TIBETAN
5938 0x0FD5, // 0FD5..0FD8; COMMON
5939 0x0FD9, // 0FD9..0FDA; TIBETAN
5940 0x0FDB, // 0FDB..0FFF; UNKNOWN
5941 0x1000, // 1000..109F; MYANMAR
5942 0x10A0, // 10A0..10C5; GEORGIAN
5943 0x10C6, // 10C6 ; UNKNOWN
5944 0x10C7, // 10C7 ; GEORGIAN
5945 0x10C8, // 10C8..10CC; UNKNOWN
5946 0x10CD, // 10CD ; GEORGIAN
5947 0x10CE, // 10CE..10CF; UNKNOWN
5948 0x10D0, // 10D0..10FA; GEORGIAN
5949 0x10FB, // 10FB ; COMMON
5950 0x10FC, // 10FC..10FF; GEORGIAN
5951 0x1100, // 1100..11FF; HANGUL
5952 0x1200, // 1200..1248; ETHIOPIC
5953 0x1249, // 1249 ; UNKNOWN
5954 0x124A, // 124A..124D; ETHIOPIC
5955 0x124E, // 124E..124F; UNKNOWN
5956 0x1250, // 1250..1256; ETHIOPIC
5957 0x1257, // 1257 ; UNKNOWN
5958 0x1258, // 1258 ; ETHIOPIC
5959 0x1259, // 1259 ; UNKNOWN
5960 0x125A, // 125A..125D; ETHIOPIC
5961 0x125E, // 125E..125F; UNKNOWN
5962 0x1260, // 1260..1288; ETHIOPIC
5963 0x1289, // 1289 ; UNKNOWN
5964 0x128A, // 128A..128D; ETHIOPIC
5965 0x128E, // 128E..128F; UNKNOWN
5966 0x1290, // 1290..12B0; ETHIOPIC
5967 0x12B1, // 12B1 ; UNKNOWN
5968 0x12B2, // 12B2..12B5; ETHIOPIC
5969 0x12B6, // 12B6..12B7; UNKNOWN
5970 0x12B8, // 12B8..12BE; ETHIOPIC
5971 0x12BF, // 12BF ; UNKNOWN
5972 0x12C0, // 12C0 ; ETHIOPIC
5973 0x12C1, // 12C1 ; UNKNOWN
5974 0x12C2, // 12C2..12C5; ETHIOPIC
5975 0x12C6, // 12C6..12C7; UNKNOWN
5976 0x12C8, // 12C8..12D6; ETHIOPIC
5977 0x12D7, // 12D7 ; UNKNOWN
5978 0x12D8, // 12D8..1310; ETHIOPIC
5979 0x1311, // 1311 ; UNKNOWN
5980 0x1312, // 1312..1315; ETHIOPIC
5981 0x1316, // 1316..1317; UNKNOWN
5982 0x1318, // 1318..135A; ETHIOPIC
5983 0x135B, // 135B..135C; UNKNOWN
5984 0x135D, // 135D..137C; ETHIOPIC
5985 0x137D, // 137D..137F; UNKNOWN
5986 0x1380, // 1380..1399; ETHIOPIC
5987 0x139A, // 139A..139F; UNKNOWN
5988 0x13A0, // 13A0..13F5; CHEROKEE
5989 0x13F6, // 13F6..13F7; UNKNOWN
5990 0x13F8, // 13F8..13FD; CHEROKEE
5991 0x13FE, // 13FE..13FF; UNKNOWN
5992 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5993 0x1680, // 1680..169C; OGHAM
5994 0x169D, // 169D..169F; UNKNOWN
5995 0x16A0, // 16A0..16EA; RUNIC
5996 0x16EB, // 16EB..16ED; COMMON
5997 0x16EE, // 16EE..16F8; RUNIC
5998 0x16F9, // 16F9..16FF; UNKNOWN
5999 0x1700, // 1700..1715; TAGALOG
6000 0x1716, // 1716..171E; UNKNOWN
6001 0x171F, // 171F ; TAGALOG
6002 0x1720, // 1720..1734; HANUNOO
6003 0x1735, // 1735..1736; COMMON
6004 0x1737, // 1737..173F; UNKNOWN
6005 0x1740, // 1740..1753; BUHID
6006 0x1754, // 1754..175F; UNKNOWN
6007 0x1760, // 1760..176C; TAGBANWA
6008 0x176D, // 176D ; UNKNOWN
6009 0x176E, // 176E..1770; TAGBANWA
6010 0x1771, // 1771 ; UNKNOWN
6011 0x1772, // 1772..1773; TAGBANWA
6012 0x1774, // 1774..177F; UNKNOWN
6013 0x1780, // 1780..17DD; KHMER
6014 0x17DE, // 17DE..17DF; UNKNOWN
6015 0x17E0, // 17E0..17E9; KHMER
6016 0x17EA, // 17EA..17EF; UNKNOWN
6017 0x17F0, // 17F0..17F9; KHMER
6018 0x17FA, // 17FA..17FF; UNKNOWN
6019 0x1800, // 1800..1801; MONGOLIAN
6020 0x1802, // 1802..1803; COMMON
6021 0x1804, // 1804 ; MONGOLIAN
6022 0x1805, // 1805 ; COMMON
6023 0x1806, // 1806..1819; MONGOLIAN
6024 0x181A, // 181A..181F; UNKNOWN
6025 0x1820, // 1820..1878; MONGOLIAN
6026 0x1879, // 1879..187F; UNKNOWN
6027 0x1880, // 1880..18AA; MONGOLIAN
6028 0x18AB, // 18AB..18AF; UNKNOWN
6029 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
6030 0x18F6, // 18F6..18FF; UNKNOWN
6031 0x1900, // 1900..191E; LIMBU
6032 0x191F, // 191F ; UNKNOWN
6033 0x1920, // 1920..192B; LIMBU
6034 0x192C, // 192C..192F; UNKNOWN
6035 0x1930, // 1930..193B; LIMBU
6036 0x193C, // 193C..193F; UNKNOWN
6037 0x1940, // 1940 ; LIMBU
6038 0x1941, // 1941..1943; UNKNOWN
6039 0x1944, // 1944..194F; LIMBU
6040 0x1950, // 1950..196D; TAI_LE
6041 0x196E, // 196E..196F; UNKNOWN
6042 0x1970, // 1970..1974; TAI_LE
6043 0x1975, // 1975..197F; UNKNOWN
6044 0x1980, // 1980..19AB; NEW_TAI_LUE
6045 0x19AC, // 19AC..19AF; UNKNOWN
6046 0x19B0, // 19B0..19C9; NEW_TAI_LUE
6047 0x19CA, // 19CA..19CF; UNKNOWN
6048 0x19D0, // 19D0..19DA; NEW_TAI_LUE
6049 0x19DB, // 19DB..19DD; UNKNOWN
6050 0x19DE, // 19DE..19DF; NEW_TAI_LUE
6051 0x19E0, // 19E0..19FF; KHMER
6052 0x1A00, // 1A00..1A1B; BUGINESE
6053 0x1A1C, // 1A1C..1A1D; UNKNOWN
6054 0x1A1E, // 1A1E..1A1F; BUGINESE
6055 0x1A20, // 1A20..1A5E; TAI_THAM
6056 0x1A5F, // 1A5F ; UNKNOWN
6057 0x1A60, // 1A60..1A7C; TAI_THAM
6058 0x1A7D, // 1A7D..1A7E; UNKNOWN
6059 0x1A7F, // 1A7F..1A89; TAI_THAM
6060 0x1A8A, // 1A8A..1A8F; UNKNOWN
6061 0x1A90, // 1A90..1A99; TAI_THAM
6062 0x1A9A, // 1A9A..1A9F; UNKNOWN
6063 0x1AA0, // 1AA0..1AAD; TAI_THAM
6064 0x1AAE, // 1AAE..1AAF; UNKNOWN
6065 0x1AB0, // 1AB0..1ACE; INHERITED
6066 0x1ACF, // 1ACF..1AFF; UNKNOWN
6067 0x1B00, // 1B00..1B4C; BALINESE
6068 0x1B4D, // 1B4D ; UNKNOWN
6069 0x1B4E, // 1B4E..1B7F; BALINESE
6070 0x1B80, // 1B80..1BBF; SUNDANESE
6071 0x1BC0, // 1BC0..1BF3; BATAK
6072 0x1BF4, // 1BF4..1BFB; UNKNOWN
6073 0x1BFC, // 1BFC..1BFF; BATAK
6074 0x1C00, // 1C00..1C37; LEPCHA
6075 0x1C38, // 1C38..1C3A; UNKNOWN
6076 0x1C3B, // 1C3B..1C49; LEPCHA
6077 0x1C4A, // 1C4A..1C4C; UNKNOWN
6078 0x1C4D, // 1C4D..1C4F; LEPCHA
6079 0x1C50, // 1C50..1C7F; OL_CHIKI
6080 0x1C80, // 1C80..1C8A; CYRILLIC
6081 0x1C8B, // 1C8B..1C8F; UNKNOWN
6082 0x1C90, // 1C90..1CBA; GEORGIAN
6083 0x1CBB, // 1CBB..1CBC; UNKNOWN
6084 0x1CBD, // 1CBD..1CBF; GEORGIAN
6085 0x1CC0, // 1CC0..1CC7; SUNDANESE
6086 0x1CC8, // 1CC8..1CCF; UNKNOWN
6087 0x1CD0, // 1CD0..1CD2; INHERITED
6088 0x1CD3, // 1CD3 ; COMMON
6089 0x1CD4, // 1CD4..1CE0; INHERITED
6090 0x1CE1, // 1CE1 ; COMMON
6091 0x1CE2, // 1CE2..1CE8; INHERITED
6092 0x1CE9, // 1CE9..1CEC; COMMON
6093 0x1CED, // 1CED ; INHERITED
6094 0x1CEE, // 1CEE..1CF3; COMMON
6095 0x1CF4, // 1CF4 ; INHERITED
6096 0x1CF5, // 1CF5..1CF7; COMMON
6097 0x1CF8, // 1CF8..1CF9; INHERITED
6098 0x1CFA, // 1CFA ; COMMON
6099 0x1CFB, // 1CFB..1CFF; UNKNOWN
6100 0x1D00, // 1D00..1D25; LATIN
6101 0x1D26, // 1D26..1D2A; GREEK
6102 0x1D2B, // 1D2B ; CYRILLIC
6103 0x1D2C, // 1D2C..1D5C; LATIN
6104 0x1D5D, // 1D5D..1D61; GREEK
6105 0x1D62, // 1D62..1D65; LATIN
6106 0x1D66, // 1D66..1D6A; GREEK
6107 0x1D6B, // 1D6B..1D77; LATIN
6108 0x1D78, // 1D78 ; CYRILLIC
6109 0x1D79, // 1D79..1DBE; LATIN
6110 0x1DBF, // 1DBF ; GREEK
6111 0x1DC0, // 1DC0..1DFF; INHERITED
6112 0x1E00, // 1E00..1EFF; LATIN
6113 0x1F00, // 1F00..1F15; GREEK
6114 0x1F16, // 1F16..1F17; UNKNOWN
6115 0x1F18, // 1F18..1F1D; GREEK
6116 0x1F1E, // 1F1E..1F1F; UNKNOWN
6117 0x1F20, // 1F20..1F45; GREEK
6118 0x1F46, // 1F46..1F47; UNKNOWN
6119 0x1F48, // 1F48..1F4D; GREEK
6120 0x1F4E, // 1F4E..1F4F; UNKNOWN
6121 0x1F50, // 1F50..1F57; GREEK
6122 0x1F58, // 1F58 ; UNKNOWN
6123 0x1F59, // 1F59 ; GREEK
6124 0x1F5A, // 1F5A ; UNKNOWN
6125 0x1F5B, // 1F5B ; GREEK
6126 0x1F5C, // 1F5C ; UNKNOWN
6127 0x1F5D, // 1F5D ; GREEK
6128 0x1F5E, // 1F5E ; UNKNOWN
6129 0x1F5F, // 1F5F..1F7D; GREEK
6130 0x1F7E, // 1F7E..1F7F; UNKNOWN
6131 0x1F80, // 1F80..1FB4; GREEK
6132 0x1FB5, // 1FB5 ; UNKNOWN
6133 0x1FB6, // 1FB6..1FC4; GREEK
6134 0x1FC5, // 1FC5 ; UNKNOWN
6135 0x1FC6, // 1FC6..1FD3; GREEK
6136 0x1FD4, // 1FD4..1FD5; UNKNOWN
6137 0x1FD6, // 1FD6..1FDB; GREEK
6138 0x1FDC, // 1FDC ; UNKNOWN
6139 0x1FDD, // 1FDD..1FEF; GREEK
6140 0x1FF0, // 1FF0..1FF1; UNKNOWN
6141 0x1FF2, // 1FF2..1FF4; GREEK
6142 0x1FF5, // 1FF5 ; UNKNOWN
6143 0x1FF6, // 1FF6..1FFE; GREEK
6144 0x1FFF, // 1FFF ; UNKNOWN
6145 0x2000, // 2000..200B; COMMON
6146 0x200C, // 200C..200D; INHERITED
6147 0x200E, // 200E..2064; COMMON
6148 0x2065, // 2065 ; UNKNOWN
6149 0x2066, // 2066..2070; COMMON
6150 0x2071, // 2071 ; LATIN
6151 0x2072, // 2072..2073; UNKNOWN
6152 0x2074, // 2074..207E; COMMON
6153 0x207F, // 207F ; LATIN
6154 0x2080, // 2080..208E; COMMON
6155 0x208F, // 208F ; UNKNOWN
6156 0x2090, // 2090..209C; LATIN
6157 0x209D, // 209D..209F; UNKNOWN
6158 0x20A0, // 20A0..20C0; COMMON
6159 0x20C1, // 20C1..20CF; UNKNOWN
6160 0x20D0, // 20D0..20F0; INHERITED
6161 0x20F1, // 20F1..20FF; UNKNOWN
6162 0x2100, // 2100..2125; COMMON
6163 0x2126, // 2126 ; GREEK
6164 0x2127, // 2127..2129; COMMON
6165 0x212A, // 212A..212B; LATIN
6166 0x212C, // 212C..2131; COMMON
6167 0x2132, // 2132 ; LATIN
6168 0x2133, // 2133..214D; COMMON
6169 0x214E, // 214E ; LATIN
6170 0x214F, // 214F..215F; COMMON
6171 0x2160, // 2160..2188; LATIN
6172 0x2189, // 2189..218B; COMMON
6173 0x218C, // 218C..218F; UNKNOWN
6174 0x2190, // 2190..2429; COMMON
6175 0x242A, // 242A..243F; UNKNOWN
6176 0x2440, // 2440..244A; COMMON
6177 0x244B, // 244B..245F; UNKNOWN
6178 0x2460, // 2460..27FF; COMMON
6179 0x2800, // 2800..28FF; BRAILLE
6180 0x2900, // 2900..2B73; COMMON
6181 0x2B74, // 2B74..2B75; UNKNOWN
6182 0x2B76, // 2B76..2B95; COMMON
6183 0x2B96, // 2B96 ; UNKNOWN
6184 0x2B97, // 2B97..2BFF; COMMON
6185 0x2C00, // 2C00..2C5F; GLAGOLITIC
6186 0x2C60, // 2C60..2C7F; LATIN
6187 0x2C80, // 2C80..2CF3; COPTIC
6188 0x2CF4, // 2CF4..2CF8; UNKNOWN
6189 0x2CF9, // 2CF9..2CFF; COPTIC
6190 0x2D00, // 2D00..2D25; GEORGIAN
6191 0x2D26, // 2D26 ; UNKNOWN
6192 0x2D27, // 2D27 ; GEORGIAN
6193 0x2D28, // 2D28..2D2C; UNKNOWN
6194 0x2D2D, // 2D2D ; GEORGIAN
6195 0x2D2E, // 2D2E..2D2F; UNKNOWN
6196 0x2D30, // 2D30..2D67; TIFINAGH
6197 0x2D68, // 2D68..2D6E; UNKNOWN
6198 0x2D6F, // 2D6F..2D70; TIFINAGH
6199 0x2D71, // 2D71..2D7E; UNKNOWN
6200 0x2D7F, // 2D7F ; TIFINAGH
6201 0x2D80, // 2D80..2D96; ETHIOPIC
6202 0x2D97, // 2D97..2D9F; UNKNOWN
6203 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6204 0x2DA7, // 2DA7 ; UNKNOWN
6205 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6206 0x2DAF, // 2DAF ; UNKNOWN
6207 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6208 0x2DB7, // 2DB7 ; UNKNOWN
6209 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6210 0x2DBF, // 2DBF ; UNKNOWN
6211 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6212 0x2DC7, // 2DC7 ; UNKNOWN
6213 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6214 0x2DCF, // 2DCF ; UNKNOWN
6215 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6216 0x2DD7, // 2DD7 ; UNKNOWN
6217 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6218 0x2DDF, // 2DDF ; UNKNOWN
6219 0x2DE0, // 2DE0..2DFF; CYRILLIC
6220 0x2E00, // 2E00..2E5D; COMMON
6221 0x2E5E, // 2E5E..2E7F; UNKNOWN
6222 0x2E80, // 2E80..2E99; HAN
6223 0x2E9A, // 2E9A ; UNKNOWN
6224 0x2E9B, // 2E9B..2EF3; HAN
6225 0x2EF4, // 2EF4..2EFF; UNKNOWN
6226 0x2F00, // 2F00..2FD5; HAN
6227 0x2FD6, // 2FD6..2FEF; UNKNOWN
6228 0x2FF0, // 2FF0..3004; COMMON
6229 0x3005, // 3005 ; HAN
6230 0x3006, // 3006 ; COMMON
6231 0x3007, // 3007 ; HAN
6232 0x3008, // 3008..3020; COMMON
6233 0x3021, // 3021..3029; HAN
6234 0x302A, // 302A..302D; INHERITED
6235 0x302E, // 302E..302F; HANGUL
6236 0x3030, // 3030..3037; COMMON
6237 0x3038, // 3038..303B; HAN
6238 0x303C, // 303C..303F; COMMON
6239 0x3040, // 3040 ; UNKNOWN
6240 0x3041, // 3041..3096; HIRAGANA
6241 0x3097, // 3097..3098; UNKNOWN
6242 0x3099, // 3099..309A; INHERITED
6243 0x309B, // 309B..309C; COMMON
6244 0x309D, // 309D..309F; HIRAGANA
6245 0x30A0, // 30A0 ; COMMON
6246 0x30A1, // 30A1..30FA; KATAKANA
6247 0x30FB, // 30FB..30FC; COMMON
6248 0x30FD, // 30FD..30FF; KATAKANA
6249 0x3100, // 3100..3104; UNKNOWN
6250 0x3105, // 3105..312F; BOPOMOFO
6251 0x3130, // 3130 ; UNKNOWN
6252 0x3131, // 3131..318E; HANGUL
6253 0x318F, // 318F ; UNKNOWN
6254 0x3190, // 3190..319F; COMMON
6255 0x31A0, // 31A0..31BF; BOPOMOFO
6256 0x31C0, // 31C0..31E5; COMMON
6257 0x31E6, // 31E6..31EE; UNKNOWN
6258 0x31EF, // 31EF ; COMMON
6259 0x31F0, // 31F0..31FF; KATAKANA
6260 0x3200, // 3200..321E; HANGUL
6261 0x321F, // 321F ; UNKNOWN
6262 0x3220, // 3220..325F; COMMON
6263 0x3260, // 3260..327E; HANGUL
6264 0x327F, // 327F..32CF; COMMON
6265 0x32D0, // 32D0..32FE; KATAKANA
6266 0x32FF, // 32FF ; COMMON
6267 0x3300, // 3300..3357; KATAKANA
6268 0x3358, // 3358..33FF; COMMON
6269 0x3400, // 3400..4DBF; HAN
6270 0x4DC0, // 4DC0..4DFF; COMMON
6271 0x4E00, // 4E00..9FFF; HAN
6272 0xA000, // A000..A48C; YI
6273 0xA48D, // A48D..A48F; UNKNOWN
6274 0xA490, // A490..A4C6; YI
6275 0xA4C7, // A4C7..A4CF; UNKNOWN
6276 0xA4D0, // A4D0..A4FF; LISU
6277 0xA500, // A500..A62B; VAI
6278 0xA62C, // A62C..A63F; UNKNOWN
6279 0xA640, // A640..A69F; CYRILLIC
6280 0xA6A0, // A6A0..A6F7; BAMUM
6281 0xA6F8, // A6F8..A6FF; UNKNOWN
6282 0xA700, // A700..A721; COMMON
6283 0xA722, // A722..A787; LATIN
6284 0xA788, // A788..A78A; COMMON
6285 0xA78B, // A78B..A7CD; LATIN
6286 0xA7CE, // A7CE..A7CF; UNKNOWN
6287 0xA7D0, // A7D0..A7D1; LATIN
6288 0xA7D2, // A7D2 ; UNKNOWN
6289 0xA7D3, // A7D3 ; LATIN
6290 0xA7D4, // A7D4 ; UNKNOWN
6291 0xA7D5, // A7D5..A7DC; LATIN
6292 0xA7DD, // A7DD..A7F1; UNKNOWN
6293 0xA7F2, // A7F2..A7FF; LATIN
6294 0xA800, // A800..A82C; SYLOTI_NAGRI
6295 0xA82D, // A82D..A82F; UNKNOWN
6296 0xA830, // A830..A839; COMMON
6297 0xA83A, // A83A..A83F; UNKNOWN
6298 0xA840, // A840..A877; PHAGS_PA
6299 0xA878, // A878..A87F; UNKNOWN
6300 0xA880, // A880..A8C5; SAURASHTRA
6301 0xA8C6, // A8C6..A8CD; UNKNOWN
6302 0xA8CE, // A8CE..A8D9; SAURASHTRA
6303 0xA8DA, // A8DA..A8DF; UNKNOWN
6304 0xA8E0, // A8E0..A8FF; DEVANAGARI
6305 0xA900, // A900..A92D; KAYAH_LI
6306 0xA92E, // A92E ; COMMON
6307 0xA92F, // A92F ; KAYAH_LI
6308 0xA930, // A930..A953; REJANG
6309 0xA954, // A954..A95E; UNKNOWN
6310 0xA95F, // A95F ; REJANG
6311 0xA960, // A960..A97C; HANGUL
6312 0xA97D, // A97D..A97F; UNKNOWN
6313 0xA980, // A980..A9CD; JAVANESE
6314 0xA9CE, // A9CE ; UNKNOWN
6315 0xA9CF, // A9CF ; COMMON
6316 0xA9D0, // A9D0..A9D9; JAVANESE
6317 0xA9DA, // A9DA..A9DD; UNKNOWN
6318 0xA9DE, // A9DE..A9DF; JAVANESE
6319 0xA9E0, // A9E0..A9FE; MYANMAR
6320 0xA9FF, // A9FF ; UNKNOWN
6321 0xAA00, // AA00..AA36; CHAM
6322 0xAA37, // AA37..AA3F; UNKNOWN
6323 0xAA40, // AA40..AA4D; CHAM
6324 0xAA4E, // AA4E..AA4F; UNKNOWN
6325 0xAA50, // AA50..AA59; CHAM
6326 0xAA5A, // AA5A..AA5B; UNKNOWN
6327 0xAA5C, // AA5C..AA5F; CHAM
6328 0xAA60, // AA60..AA7F; MYANMAR
6329 0xAA80, // AA80..AAC2; TAI_VIET
6330 0xAAC3, // AAC3..AADA; UNKNOWN
6331 0xAADB, // AADB..AADF; TAI_VIET
6332 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6333 0xAAF7, // AAF7..AB00; UNKNOWN
6334 0xAB01, // AB01..AB06; ETHIOPIC
6335 0xAB07, // AB07..AB08; UNKNOWN
6336 0xAB09, // AB09..AB0E; ETHIOPIC
6337 0xAB0F, // AB0F..AB10; UNKNOWN
6338 0xAB11, // AB11..AB16; ETHIOPIC
6339 0xAB17, // AB17..AB1F; UNKNOWN
6340 0xAB20, // AB20..AB26; ETHIOPIC
6341 0xAB27, // AB27 ; UNKNOWN
6342 0xAB28, // AB28..AB2E; ETHIOPIC
6343 0xAB2F, // AB2F ; UNKNOWN
6344 0xAB30, // AB30..AB5A; LATIN
6345 0xAB5B, // AB5B ; COMMON
6346 0xAB5C, // AB5C..AB64; LATIN
6347 0xAB65, // AB65 ; GREEK
6348 0xAB66, // AB66..AB69; LATIN
6349 0xAB6A, // AB6A..AB6B; COMMON
6350 0xAB6C, // AB6C..AB6F; UNKNOWN
6351 0xAB70, // AB70..ABBF; CHEROKEE
6352 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6353 0xABEE, // ABEE..ABEF; UNKNOWN
6354 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6355 0xABFA, // ABFA..ABFF; UNKNOWN
6356 0xAC00, // AC00..D7A3; HANGUL
6357 0xD7A4, // D7A4..D7AF; UNKNOWN
6358 0xD7B0, // D7B0..D7C6; HANGUL
6359 0xD7C7, // D7C7..D7CA; UNKNOWN
6360 0xD7CB, // D7CB..D7FB; HANGUL
6361 0xD7FC, // D7FC..F8FF; UNKNOWN
6362 0xF900, // F900..FA6D; HAN
6363 0xFA6E, // FA6E..FA6F; UNKNOWN
6364 0xFA70, // FA70..FAD9; HAN
6365 0xFADA, // FADA..FAFF; UNKNOWN
6366 0xFB00, // FB00..FB06; LATIN
6367 0xFB07, // FB07..FB12; UNKNOWN
6368 0xFB13, // FB13..FB17; ARMENIAN
6369 0xFB18, // FB18..FB1C; UNKNOWN
6370 0xFB1D, // FB1D..FB36; HEBREW
6371 0xFB37, // FB37 ; UNKNOWN
6372 0xFB38, // FB38..FB3C; HEBREW
6373 0xFB3D, // FB3D ; UNKNOWN
6374 0xFB3E, // FB3E ; HEBREW
6375 0xFB3F, // FB3F ; UNKNOWN
6376 0xFB40, // FB40..FB41; HEBREW
6377 0xFB42, // FB42 ; UNKNOWN
6378 0xFB43, // FB43..FB44; HEBREW
6379 0xFB45, // FB45 ; UNKNOWN
6380 0xFB46, // FB46..FB4F; HEBREW
6381 0xFB50, // FB50..FBC2; ARABIC
6382 0xFBC3, // FBC3..FBD2; UNKNOWN
6383 0xFBD3, // FBD3..FD3D; ARABIC
6384 0xFD3E, // FD3E..FD3F; COMMON
6385 0xFD40, // FD40..FD8F; ARABIC
6386 0xFD90, // FD90..FD91; UNKNOWN
6387 0xFD92, // FD92..FDC7; ARABIC
6388 0xFDC8, // FDC8..FDCE; UNKNOWN
6389 0xFDCF, // FDCF ; ARABIC
6390 0xFDD0, // FDD0..FDEF; UNKNOWN
6391 0xFDF0, // FDF0..FDFF; ARABIC
6392 0xFE00, // FE00..FE0F; INHERITED
6393 0xFE10, // FE10..FE19; COMMON
6394 0xFE1A, // FE1A..FE1F; UNKNOWN
6395 0xFE20, // FE20..FE2D; INHERITED
6396 0xFE2E, // FE2E..FE2F; CYRILLIC
6397 0xFE30, // FE30..FE52; COMMON
6398 0xFE53, // FE53 ; UNKNOWN
6399 0xFE54, // FE54..FE66; COMMON
6400 0xFE67, // FE67 ; UNKNOWN
6401 0xFE68, // FE68..FE6B; COMMON
6402 0xFE6C, // FE6C..FE6F; UNKNOWN
6403 0xFE70, // FE70..FE74; ARABIC
6404 0xFE75, // FE75 ; UNKNOWN
6405 0xFE76, // FE76..FEFC; ARABIC
6406 0xFEFD, // FEFD..FEFE; UNKNOWN
6407 0xFEFF, // FEFF ; COMMON
6408 0xFF00, // FF00 ; UNKNOWN
6409 0xFF01, // FF01..FF20; COMMON
6410 0xFF21, // FF21..FF3A; LATIN
6411 0xFF3B, // FF3B..FF40; COMMON
6412 0xFF41, // FF41..FF5A; LATIN
6413 0xFF5B, // FF5B..FF65; COMMON
6414 0xFF66, // FF66..FF6F; KATAKANA
6415 0xFF70, // FF70 ; COMMON
6416 0xFF71, // FF71..FF9D; KATAKANA
6417 0xFF9E, // FF9E..FF9F; COMMON
6418 0xFFA0, // FFA0..FFBE; HANGUL
6419 0xFFBF, // FFBF..FFC1; UNKNOWN
6420 0xFFC2, // FFC2..FFC7; HANGUL
6421 0xFFC8, // FFC8..FFC9; UNKNOWN
6422 0xFFCA, // FFCA..FFCF; HANGUL
6423 0xFFD0, // FFD0..FFD1; UNKNOWN
6424 0xFFD2, // FFD2..FFD7; HANGUL
6425 0xFFD8, // FFD8..FFD9; UNKNOWN
6426 0xFFDA, // FFDA..FFDC; HANGUL
6427 0xFFDD, // FFDD..FFDF; UNKNOWN
6428 0xFFE0, // FFE0..FFE6; COMMON
6429 0xFFE7, // FFE7 ; UNKNOWN
6430 0xFFE8, // FFE8..FFEE; COMMON
6431 0xFFEF, // FFEF..FFF8; UNKNOWN
6432 0xFFF9, // FFF9..FFFD; COMMON
6433 0xFFFE, // FFFE..FFFF; UNKNOWN
6434 0x10000, // 10000..1000B; LINEAR_B
6435 0x1000C, // 1000C ; UNKNOWN
6436 0x1000D, // 1000D..10026; LINEAR_B
6437 0x10027, // 10027 ; UNKNOWN
6438 0x10028, // 10028..1003A; LINEAR_B
6439 0x1003B, // 1003B ; UNKNOWN
6440 0x1003C, // 1003C..1003D; LINEAR_B
6441 0x1003E, // 1003E ; UNKNOWN
6442 0x1003F, // 1003F..1004D; LINEAR_B
6443 0x1004E, // 1004E..1004F; UNKNOWN
6444 0x10050, // 10050..1005D; LINEAR_B
6445 0x1005E, // 1005E..1007F; UNKNOWN
6446 0x10080, // 10080..100FA; LINEAR_B
6447 0x100FB, // 100FB..100FF; UNKNOWN
6448 0x10100, // 10100..10102; COMMON
6449 0x10103, // 10103..10106; UNKNOWN
6450 0x10107, // 10107..10133; COMMON
6451 0x10134, // 10134..10136; UNKNOWN
6452 0x10137, // 10137..1013F; COMMON
6453 0x10140, // 10140..1018E; GREEK
6454 0x1018F, // 1018F ; UNKNOWN
6455 0x10190, // 10190..1019C; COMMON
6456 0x1019D, // 1019D..1019F; UNKNOWN
6457 0x101A0, // 101A0 ; GREEK
6458 0x101A1, // 101A1..101CF; UNKNOWN
6459 0x101D0, // 101D0..101FC; COMMON
6460 0x101FD, // 101FD ; INHERITED
6461 0x101FE, // 101FE..1027F; UNKNOWN
6462 0x10280, // 10280..1029C; LYCIAN
6463 0x1029D, // 1029D..1029F; UNKNOWN
6464 0x102A0, // 102A0..102D0; CARIAN
6465 0x102D1, // 102D1..102DF; UNKNOWN
6466 0x102E0, // 102E0 ; INHERITED
6467 0x102E1, // 102E1..102FB; COMMON
6468 0x102FC, // 102FC..102FF; UNKNOWN
6469 0x10300, // 10300..10323; OLD_ITALIC
6470 0x10324, // 10324..1032C; UNKNOWN
6471 0x1032D, // 1032D..1032F; OLD_ITALIC
6472 0x10330, // 10330..1034A; GOTHIC
6473 0x1034B, // 1034B..1034F; UNKNOWN
6474 0x10350, // 10350..1037A; OLD_PERMIC
6475 0x1037B, // 1037B..1037F; UNKNOWN
6476 0x10380, // 10380..1039D; UGARITIC
6477 0x1039E, // 1039E ; UNKNOWN
6478 0x1039F, // 1039F ; UGARITIC
6479 0x103A0, // 103A0..103C3; OLD_PERSIAN
6480 0x103C4, // 103C4..103C7; UNKNOWN
6481 0x103C8, // 103C8..103D5; OLD_PERSIAN
6482 0x103D6, // 103D6..103FF; UNKNOWN
6483 0x10400, // 10400..1044F; DESERET
6484 0x10450, // 10450..1047F; SHAVIAN
6485 0x10480, // 10480..1049D; OSMANYA
6486 0x1049E, // 1049E..1049F; UNKNOWN
6487 0x104A0, // 104A0..104A9; OSMANYA
6488 0x104AA, // 104AA..104AF; UNKNOWN
6489 0x104B0, // 104B0..104D3; OSAGE
6490 0x104D4, // 104D4..104D7; UNKNOWN
6491 0x104D8, // 104D8..104FB; OSAGE
6492 0x104FC, // 104FC..104FF; UNKNOWN
6493 0x10500, // 10500..10527; ELBASAN
6494 0x10528, // 10528..1052F; UNKNOWN
6495 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6496 0x10564, // 10564..1056E; UNKNOWN
6497 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6498 0x10570, // 10570..1057A; VITHKUQI
6499 0x1057B, // 1057B ; UNKNOWN
6500 0x1057C, // 1057C..1058A; VITHKUQI
6501 0x1058B, // 1058B ; UNKNOWN
6502 0x1058C, // 1058C..10592; VITHKUQI
6503 0x10593, // 10593 ; UNKNOWN
6504 0x10594, // 10594..10595; VITHKUQI
6505 0x10596, // 10596 ; UNKNOWN
6506 0x10597, // 10597..105A1; VITHKUQI
6507 0x105A2, // 105A2 ; UNKNOWN
6508 0x105A3, // 105A3..105B1; VITHKUQI
6509 0x105B2, // 105B2 ; UNKNOWN
6510 0x105B3, // 105B3..105B9; VITHKUQI
6511 0x105BA, // 105BA ; UNKNOWN
6512 0x105BB, // 105BB..105BC; VITHKUQI
6513 0x105BD, // 105BD..105BF; UNKNOWN
6514 0x105C0, // 105C0..105F3; TODHRI
6515 0x105F4, // 105F4..105FF; UNKNOWN
6516 0x10600, // 10600..10736; LINEAR_A
6517 0x10737, // 10737..1073F; UNKNOWN
6518 0x10740, // 10740..10755; LINEAR_A
6519 0x10756, // 10756..1075F; UNKNOWN
6520 0x10760, // 10760..10767; LINEAR_A
6521 0x10768, // 10768..1077F; UNKNOWN
6522 0x10780, // 10780..10785; LATIN
6523 0x10786, // 10786 ; UNKNOWN
6524 0x10787, // 10787..107B0; LATIN
6525 0x107B1, // 107B1 ; UNKNOWN
6526 0x107B2, // 107B2..107BA; LATIN
6527 0x107BB, // 107BB..107FF; UNKNOWN
6528 0x10800, // 10800..10805; CYPRIOT
6529 0x10806, // 10806..10807; UNKNOWN
6530 0x10808, // 10808 ; CYPRIOT
6531 0x10809, // 10809 ; UNKNOWN
6532 0x1080A, // 1080A..10835; CYPRIOT
6533 0x10836, // 10836 ; UNKNOWN
6534 0x10837, // 10837..10838; CYPRIOT
6535 0x10839, // 10839..1083B; UNKNOWN
6536 0x1083C, // 1083C ; CYPRIOT
6537 0x1083D, // 1083D..1083E; UNKNOWN
6538 0x1083F, // 1083F ; CYPRIOT
6539 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6540 0x10856, // 10856 ; UNKNOWN
6541 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6542 0x10860, // 10860..1087F; PALMYRENE
6543 0x10880, // 10880..1089E; NABATAEAN
6544 0x1089F, // 1089F..108A6; UNKNOWN
6545 0x108A7, // 108A7..108AF; NABATAEAN
6546 0x108B0, // 108B0..108DF; UNKNOWN
6547 0x108E0, // 108E0..108F2; HATRAN
6548 0x108F3, // 108F3 ; UNKNOWN
6549 0x108F4, // 108F4..108F5; HATRAN
6550 0x108F6, // 108F6..108FA; UNKNOWN
6551 0x108FB, // 108FB..108FF; HATRAN
6552 0x10900, // 10900..1091B; PHOENICIAN
6553 0x1091C, // 1091C..1091E; UNKNOWN
6554 0x1091F, // 1091F ; PHOENICIAN
6555 0x10920, // 10920..10939; LYDIAN
6556 0x1093A, // 1093A..1093E; UNKNOWN
6557 0x1093F, // 1093F ; LYDIAN
6558 0x10940, // 10940..1097F; UNKNOWN
6559 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6560 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6561 0x109B8, // 109B8..109BB; UNKNOWN
6562 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6563 0x109D0, // 109D0..109D1; UNKNOWN
6564 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6565 0x10A00, // 10A00..10A03; KHAROSHTHI
6566 0x10A04, // 10A04 ; UNKNOWN
6567 0x10A05, // 10A05..10A06; KHAROSHTHI
6568 0x10A07, // 10A07..10A0B; UNKNOWN
6569 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6570 0x10A14, // 10A14 ; UNKNOWN
6571 0x10A15, // 10A15..10A17; KHAROSHTHI
6572 0x10A18, // 10A18 ; UNKNOWN
6573 0x10A19, // 10A19..10A35; KHAROSHTHI
6574 0x10A36, // 10A36..10A37; UNKNOWN
6575 0x10A38, // 10A38..10A3A; KHAROSHTHI
6576 0x10A3B, // 10A3B..10A3E; UNKNOWN
6577 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6578 0x10A49, // 10A49..10A4F; UNKNOWN
6579 0x10A50, // 10A50..10A58; KHAROSHTHI
6580 0x10A59, // 10A59..10A5F; UNKNOWN
6581 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6582 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6583 0x10AA0, // 10AA0..10ABF; UNKNOWN
6584 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6585 0x10AE7, // 10AE7..10AEA; UNKNOWN
6586 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6587 0x10AF7, // 10AF7..10AFF; UNKNOWN
6588 0x10B00, // 10B00..10B35; AVESTAN
6589 0x10B36, // 10B36..10B38; UNKNOWN
6590 0x10B39, // 10B39..10B3F; AVESTAN
6591 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6592 0x10B56, // 10B56..10B57; UNKNOWN
6593 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6594 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6595 0x10B73, // 10B73..10B77; UNKNOWN
6596 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6597 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6598 0x10B92, // 10B92..10B98; UNKNOWN
6599 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6600 0x10B9D, // 10B9D..10BA8; UNKNOWN
6601 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6602 0x10BB0, // 10BB0..10BFF; UNKNOWN
6603 0x10C00, // 10C00..10C48; OLD_TURKIC
6604 0x10C49, // 10C49..10C7F; UNKNOWN
6605 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6606 0x10CB3, // 10CB3..10CBF; UNKNOWN
6607 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6608 0x10CF3, // 10CF3..10CF9; UNKNOWN
6609 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6610 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6611 0x10D28, // 10D28..10D2F; UNKNOWN
6612 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6613 0x10D3A, // 10D3A..10D3F; UNKNOWN
6614 0x10D40, // 10D40..10D65; GARAY
6615 0x10D66, // 10D66..10D68; UNKNOWN
6616 0x10D69, // 10D69..10D85; GARAY
6617 0x10D86, // 10D86..10D8D; UNKNOWN
6618 0x10D8E, // 10D8E..10D8F; GARAY
6619 0x10D90, // 10D90..10E5F; UNKNOWN
6620 0x10E60, // 10E60..10E7E; ARABIC
6621 0x10E7F, // 10E7F ; UNKNOWN
6622 0x10E80, // 10E80..10EA9; YEZIDI
6623 0x10EAA, // 10EAA ; UNKNOWN
6624 0x10EAB, // 10EAB..10EAD; YEZIDI
6625 0x10EAE, // 10EAE..10EAF; UNKNOWN
6626 0x10EB0, // 10EB0..10EB1; YEZIDI
6627 0x10EB2, // 10EB2..10EC1; UNKNOWN
6628 0x10EC2, // 10EC2..10EC4; ARABIC
6629 0x10EC5, // 10EC5..10EFB; UNKNOWN
6630 0x10EFC, // 10EFC..10EFF; ARABIC
6631 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6632 0x10F28, // 10F28..10F2F; UNKNOWN
6633 0x10F30, // 10F30..10F59; SOGDIAN
6634 0x10F5A, // 10F5A..10F6F; UNKNOWN
6635 0x10F70, // 10F70..10F89; OLD_UYGHUR
6636 0x10F8A, // 10F8A..10FAF; UNKNOWN
6637 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6638 0x10FCC, // 10FCC..10FDF; UNKNOWN
6639 0x10FE0, // 10FE0..10FF6; ELYMAIC
6640 0x10FF7, // 10FF7..10FFF; UNKNOWN
6641 0x11000, // 11000..1104D; BRAHMI
6642 0x1104E, // 1104E..11051; UNKNOWN
6643 0x11052, // 11052..11075; BRAHMI
6644 0x11076, // 11076..1107E; UNKNOWN
6645 0x1107F, // 1107F ; BRAHMI
6646 0x11080, // 11080..110C2; KAITHI
6647 0x110C3, // 110C3..110CC; UNKNOWN
6648 0x110CD, // 110CD ; KAITHI
6649 0x110CE, // 110CE..110CF; UNKNOWN
6650 0x110D0, // 110D0..110E8; SORA_SOMPENG
6651 0x110E9, // 110E9..110EF; UNKNOWN
6652 0x110F0, // 110F0..110F9; SORA_SOMPENG
6653 0x110FA, // 110FA..110FF; UNKNOWN
6654 0x11100, // 11100..11134; CHAKMA
6655 0x11135, // 11135 ; UNKNOWN
6656 0x11136, // 11136..11147; CHAKMA
6657 0x11148, // 11148..1114F; UNKNOWN
6658 0x11150, // 11150..11176; MAHAJANI
6659 0x11177, // 11177..1117F; UNKNOWN
6660 0x11180, // 11180..111DF; SHARADA
6661 0x111E0, // 111E0 ; UNKNOWN
6662 0x111E1, // 111E1..111F4; SINHALA
6663 0x111F5, // 111F5..111FF; UNKNOWN
6664 0x11200, // 11200..11211; KHOJKI
6665 0x11212, // 11212 ; UNKNOWN
6666 0x11213, // 11213..11241; KHOJKI
6667 0x11242, // 11242..1127F; UNKNOWN
6668 0x11280, // 11280..11286; MULTANI
6669 0x11287, // 11287 ; UNKNOWN
6670 0x11288, // 11288 ; MULTANI
6671 0x11289, // 11289 ; UNKNOWN
6672 0x1128A, // 1128A..1128D; MULTANI
6673 0x1128E, // 1128E ; UNKNOWN
6674 0x1128F, // 1128F..1129D; MULTANI
6675 0x1129E, // 1129E ; UNKNOWN
6676 0x1129F, // 1129F..112A9; MULTANI
6677 0x112AA, // 112AA..112AF; UNKNOWN
6678 0x112B0, // 112B0..112EA; KHUDAWADI
6679 0x112EB, // 112EB..112EF; UNKNOWN
6680 0x112F0, // 112F0..112F9; KHUDAWADI
6681 0x112FA, // 112FA..112FF; UNKNOWN
6682 0x11300, // 11300..11303; GRANTHA
6683 0x11304, // 11304 ; UNKNOWN
6684 0x11305, // 11305..1130C; GRANTHA
6685 0x1130D, // 1130D..1130E; UNKNOWN
6686 0x1130F, // 1130F..11310; GRANTHA
6687 0x11311, // 11311..11312; UNKNOWN
6688 0x11313, // 11313..11328; GRANTHA
6689 0x11329, // 11329 ; UNKNOWN
6690 0x1132A, // 1132A..11330; GRANTHA
6691 0x11331, // 11331 ; UNKNOWN
6692 0x11332, // 11332..11333; GRANTHA
6693 0x11334, // 11334 ; UNKNOWN
6694 0x11335, // 11335..11339; GRANTHA
6695 0x1133A, // 1133A ; UNKNOWN
6696 0x1133B, // 1133B ; INHERITED
6697 0x1133C, // 1133C..11344; GRANTHA
6698 0x11345, // 11345..11346; UNKNOWN
6699 0x11347, // 11347..11348; GRANTHA
6700 0x11349, // 11349..1134A; UNKNOWN
6701 0x1134B, // 1134B..1134D; GRANTHA
6702 0x1134E, // 1134E..1134F; UNKNOWN
6703 0x11350, // 11350 ; GRANTHA
6704 0x11351, // 11351..11356; UNKNOWN
6705 0x11357, // 11357 ; GRANTHA
6706 0x11358, // 11358..1135C; UNKNOWN
6707 0x1135D, // 1135D..11363; GRANTHA
6708 0x11364, // 11364..11365; UNKNOWN
6709 0x11366, // 11366..1136C; GRANTHA
6710 0x1136D, // 1136D..1136F; UNKNOWN
6711 0x11370, // 11370..11374; GRANTHA
6712 0x11375, // 11375..1137F; UNKNOWN
6713 0x11380, // 11380..11389; TULU_TIGALARI
6714 0x1138A, // 1138A ; UNKNOWN
6715 0x1138B, // 1138B ; TULU_TIGALARI
6716 0x1138C, // 1138C..1138D; UNKNOWN
6717 0x1138E, // 1138E ; TULU_TIGALARI
6718 0x1138F, // 1138F ; UNKNOWN
6719 0x11390, // 11390..113B5; TULU_TIGALARI
6720 0x113B6, // 113B6 ; UNKNOWN
6721 0x113B7, // 113B7..113C0; TULU_TIGALARI
6722 0x113C1, // 113C1 ; UNKNOWN
6723 0x113C2, // 113C2 ; TULU_TIGALARI
6724 0x113C3, // 113C3..113C4; UNKNOWN
6725 0x113C5, // 113C5 ; TULU_TIGALARI
6726 0x113C6, // 113C6 ; UNKNOWN
6727 0x113C7, // 113C7..113CA; TULU_TIGALARI
6728 0x113CB, // 113CB ; UNKNOWN
6729 0x113CC, // 113CC..113D5; TULU_TIGALARI
6730 0x113D6, // 113D6 ; UNKNOWN
6731 0x113D7, // 113D7..113D8; TULU_TIGALARI
6732 0x113D9, // 113D9..113E0; UNKNOWN
6733 0x113E1, // 113E1..113E2; TULU_TIGALARI
6734 0x113E3, // 113E3..113FF; UNKNOWN
6735 0x11400, // 11400..1145B; NEWA
6736 0x1145C, // 1145C ; UNKNOWN
6737 0x1145D, // 1145D..11461; NEWA
6738 0x11462, // 11462..1147F; UNKNOWN
6739 0x11480, // 11480..114C7; TIRHUTA
6740 0x114C8, // 114C8..114CF; UNKNOWN
6741 0x114D0, // 114D0..114D9; TIRHUTA
6742 0x114DA, // 114DA..1157F; UNKNOWN
6743 0x11580, // 11580..115B5; SIDDHAM
6744 0x115B6, // 115B6..115B7; UNKNOWN
6745 0x115B8, // 115B8..115DD; SIDDHAM
6746 0x115DE, // 115DE..115FF; UNKNOWN
6747 0x11600, // 11600..11644; MODI
6748 0x11645, // 11645..1164F; UNKNOWN
6749 0x11650, // 11650..11659; MODI
6750 0x1165A, // 1165A..1165F; UNKNOWN
6751 0x11660, // 11660..1166C; MONGOLIAN
6752 0x1166D, // 1166D..1167F; UNKNOWN
6753 0x11680, // 11680..116B9; TAKRI
6754 0x116BA, // 116BA..116BF; UNKNOWN
6755 0x116C0, // 116C0..116C9; TAKRI
6756 0x116CA, // 116CA..116CF; UNKNOWN
6757 0x116D0, // 116D0..116E3; MYANMAR
6758 0x116E4, // 116E4..116FF; UNKNOWN
6759 0x11700, // 11700..1171A; AHOM
6760 0x1171B, // 1171B..1171C; UNKNOWN
6761 0x1171D, // 1171D..1172B; AHOM
6762 0x1172C, // 1172C..1172F; UNKNOWN
6763 0x11730, // 11730..11746; AHOM
6764 0x11747, // 11747..117FF; UNKNOWN
6765 0x11800, // 11800..1183B; DOGRA
6766 0x1183C, // 1183C..1189F; UNKNOWN
6767 0x118A0, // 118A0..118F2; WARANG_CITI
6768 0x118F3, // 118F3..118FE; UNKNOWN
6769 0x118FF, // 118FF ; WARANG_CITI
6770 0x11900, // 11900..11906; DIVES_AKURU
6771 0x11907, // 11907..11908; UNKNOWN
6772 0x11909, // 11909 ; DIVES_AKURU
6773 0x1190A, // 1190A..1190B; UNKNOWN
6774 0x1190C, // 1190C..11913; DIVES_AKURU
6775 0x11914, // 11914 ; UNKNOWN
6776 0x11915, // 11915..11916; DIVES_AKURU
6777 0x11917, // 11917 ; UNKNOWN
6778 0x11918, // 11918..11935; DIVES_AKURU
6779 0x11936, // 11936 ; UNKNOWN
6780 0x11937, // 11937..11938; DIVES_AKURU
6781 0x11939, // 11939..1193A; UNKNOWN
6782 0x1193B, // 1193B..11946; DIVES_AKURU
6783 0x11947, // 11947..1194F; UNKNOWN
6784 0x11950, // 11950..11959; DIVES_AKURU
6785 0x1195A, // 1195A..1199F; UNKNOWN
6786 0x119A0, // 119A0..119A7; NANDINAGARI
6787 0x119A8, // 119A8..119A9; UNKNOWN
6788 0x119AA, // 119AA..119D7; NANDINAGARI
6789 0x119D8, // 119D8..119D9; UNKNOWN
6790 0x119DA, // 119DA..119E4; NANDINAGARI
6791 0x119E5, // 119E5..119FF; UNKNOWN
6792 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6793 0x11A48, // 11A48..11A4F; UNKNOWN
6794 0x11A50, // 11A50..11AA2; SOYOMBO
6795 0x11AA3, // 11AA3..11AAF; UNKNOWN
6796 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6797 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6798 0x11AF9, // 11AF9..11AFF; UNKNOWN
6799 0x11B00, // 11B00..11B09; DEVANAGARI
6800 0x11B0A, // 11B0A..11BBF; UNKNOWN
6801 0x11BC0, // 11BC0..11BE1; SUNUWAR
6802 0x11BE2, // 11BE2..11BEF; UNKNOWN
6803 0x11BF0, // 11BF0..11BF9; SUNUWAR
6804 0x11BFA, // 11BFA..11BFF; UNKNOWN
6805 0x11C00, // 11C00..11C08; BHAIKSUKI
6806 0x11C09, // 11C09 ; UNKNOWN
6807 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6808 0x11C37, // 11C37 ; UNKNOWN
6809 0x11C38, // 11C38..11C45; BHAIKSUKI
6810 0x11C46, // 11C46..11C4F; UNKNOWN
6811 0x11C50, // 11C50..11C6C; BHAIKSUKI
6812 0x11C6D, // 11C6D..11C6F; UNKNOWN
6813 0x11C70, // 11C70..11C8F; MARCHEN
6814 0x11C90, // 11C90..11C91; UNKNOWN
6815 0x11C92, // 11C92..11CA7; MARCHEN
6816 0x11CA8, // 11CA8 ; UNKNOWN
6817 0x11CA9, // 11CA9..11CB6; MARCHEN
6818 0x11CB7, // 11CB7..11CFF; UNKNOWN
6819 0x11D00, // 11D00..11D06; MASARAM_GONDI
6820 0x11D07, // 11D07 ; UNKNOWN
6821 0x11D08, // 11D08..11D09; MASARAM_GONDI
6822 0x11D0A, // 11D0A ; UNKNOWN
6823 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6824 0x11D37, // 11D37..11D39; UNKNOWN
6825 0x11D3A, // 11D3A ; MASARAM_GONDI
6826 0x11D3B, // 11D3B ; UNKNOWN
6827 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6828 0x11D3E, // 11D3E ; UNKNOWN
6829 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6830 0x11D48, // 11D48..11D4F; UNKNOWN
6831 0x11D50, // 11D50..11D59; MASARAM_GONDI
6832 0x11D5A, // 11D5A..11D5F; UNKNOWN
6833 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6834 0x11D66, // 11D66 ; UNKNOWN
6835 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6836 0x11D69, // 11D69 ; UNKNOWN
6837 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6838 0x11D8F, // 11D8F ; UNKNOWN
6839 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6840 0x11D92, // 11D92 ; UNKNOWN
6841 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6842 0x11D99, // 11D99..11D9F; UNKNOWN
6843 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6844 0x11DAA, // 11DAA..11EDF; UNKNOWN
6845 0x11EE0, // 11EE0..11EF8; MAKASAR
6846 0x11EF9, // 11EF9..11EFF; UNKNOWN
6847 0x11F00, // 11F00..11F10; KAWI
6848 0x11F11, // 11F11 ; UNKNOWN
6849 0x11F12, // 11F12..11F3A; KAWI
6850 0x11F3B, // 11F3B..11F3D; UNKNOWN
6851 0x11F3E, // 11F3E..11F5A; KAWI
6852 0x11F5B, // 11F5B..11FAF; UNKNOWN
6853 0x11FB0, // 11FB0 ; LISU
6854 0x11FB1, // 11FB1..11FBF; UNKNOWN
6855 0x11FC0, // 11FC0..11FF1; TAMIL
6856 0x11FF2, // 11FF2..11FFE; UNKNOWN
6857 0x11FFF, // 11FFF ; TAMIL
6858 0x12000, // 12000..12399; CUNEIFORM
6859 0x1239A, // 1239A..123FF; UNKNOWN
6860 0x12400, // 12400..1246E; CUNEIFORM
6861 0x1246F, // 1246F ; UNKNOWN
6862 0x12470, // 12470..12474; CUNEIFORM
6863 0x12475, // 12475..1247F; UNKNOWN
6864 0x12480, // 12480..12543; CUNEIFORM
6865 0x12544, // 12544..12F8F; UNKNOWN
6866 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6867 0x12FF3, // 12FF3..12FFF; UNKNOWN
6868 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6869 0x13456, // 13456..1345F; UNKNOWN
6870 0x13460, // 13460..143FA; EGYPTIAN_HIEROGLYPHS
6871 0x143FB, // 143FB..143FF; UNKNOWN
6872 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6873 0x14647, // 14647..160FF; UNKNOWN
6874 0x16100, // 16100..16139; GURUNG_KHEMA
6875 0x1613A, // 1613A..167FF; UNKNOWN
6876 0x16800, // 16800..16A38; BAMUM
6877 0x16A39, // 16A39..16A3F; UNKNOWN
6878 0x16A40, // 16A40..16A5E; MRO
6879 0x16A5F, // 16A5F ; UNKNOWN
6880 0x16A60, // 16A60..16A69; MRO
6881 0x16A6A, // 16A6A..16A6D; UNKNOWN
6882 0x16A6E, // 16A6E..16A6F; MRO
6883 0x16A70, // 16A70..16ABE; TANGSA
6884 0x16ABF, // 16ABF ; UNKNOWN
6885 0x16AC0, // 16AC0..16AC9; TANGSA
6886 0x16ACA, // 16ACA..16ACF; UNKNOWN
6887 0x16AD0, // 16AD0..16AED; BASSA_VAH
6888 0x16AEE, // 16AEE..16AEF; UNKNOWN
6889 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6890 0x16AF6, // 16AF6..16AFF; UNKNOWN
6891 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6892 0x16B46, // 16B46..16B4F; UNKNOWN
6893 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6894 0x16B5A, // 16B5A ; UNKNOWN
6895 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6896 0x16B62, // 16B62 ; UNKNOWN
6897 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6898 0x16B78, // 16B78..16B7C; UNKNOWN
6899 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6900 0x16B90, // 16B90..16D3F; UNKNOWN
6901 0x16D40, // 16D40..16D79; KIRAT_RAI
6902 0x16D7A, // 16D7A..16E3F; UNKNOWN
6903 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6904 0x16E9B, // 16E9B..16EFF; UNKNOWN
6905 0x16F00, // 16F00..16F4A; MIAO
6906 0x16F4B, // 16F4B..16F4E; UNKNOWN
6907 0x16F4F, // 16F4F..16F87; MIAO
6908 0x16F88, // 16F88..16F8E; UNKNOWN
6909 0x16F8F, // 16F8F..16F9F; MIAO
6910 0x16FA0, // 16FA0..16FDF; UNKNOWN
6911 0x16FE0, // 16FE0 ; TANGUT
6912 0x16FE1, // 16FE1 ; NUSHU
6913 0x16FE2, // 16FE2..16FE3; HAN
6914 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
6915 0x16FE5, // 16FE5..16FEF; UNKNOWN
6916 0x16FF0, // 16FF0..16FF1; HAN
6917 0x16FF2, // 16FF2..16FFF; UNKNOWN
6918 0x17000, // 17000..187F7; TANGUT
6919 0x187F8, // 187F8..187FF; UNKNOWN
6920 0x18800, // 18800..18AFF; TANGUT
6921 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
6922 0x18CD6, // 18CD6..18CFE; UNKNOWN
6923 0x18CFF, // 18CFF ; KHITAN_SMALL_SCRIPT
6924 0x18D00, // 18D00..18D08; TANGUT
6925 0x18D09, // 18D09..1AFEF; UNKNOWN
6926 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
6927 0x1AFF4, // 1AFF4 ; UNKNOWN
6928 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
6929 0x1AFFC, // 1AFFC ; UNKNOWN
6930 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
6931 0x1AFFF, // 1AFFF ; UNKNOWN
6932 0x1B000, // 1B000 ; KATAKANA
6933 0x1B001, // 1B001..1B11F; HIRAGANA
6934 0x1B120, // 1B120..1B122; KATAKANA
6935 0x1B123, // 1B123..1B131; UNKNOWN
6936 0x1B132, // 1B132 ; HIRAGANA
6937 0x1B133, // 1B133..1B14F; UNKNOWN
6938 0x1B150, // 1B150..1B152; HIRAGANA
6939 0x1B153, // 1B153..1B154; UNKNOWN
6940 0x1B155, // 1B155 ; KATAKANA
6941 0x1B156, // 1B156..1B163; UNKNOWN
6942 0x1B164, // 1B164..1B167; KATAKANA
6943 0x1B168, // 1B168..1B16F; UNKNOWN
6944 0x1B170, // 1B170..1B2FB; NUSHU
6945 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6946 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6947 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6948 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6949 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6950 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6951 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6952 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6953 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6954 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6955 0x1BCA0, // 1BCA0..1BCA3; COMMON
6956 0x1BCA4, // 1BCA4..1CBFF; UNKNOWN
6957 0x1CC00, // 1CC00..1CCF9; COMMON
6958 0x1CCFA, // 1CCFA..1CCFF; UNKNOWN
6959 0x1CD00, // 1CD00..1CEB3; COMMON
6960 0x1CEB4, // 1CEB4..1CEFF; UNKNOWN
6961 0x1CF00, // 1CF00..1CF2D; INHERITED
6962 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
6963 0x1CF30, // 1CF30..1CF46; INHERITED
6964 0x1CF47, // 1CF47..1CF4F; UNKNOWN
6965 0x1CF50, // 1CF50..1CFC3; COMMON
6966 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
6967 0x1D000, // 1D000..1D0F5; COMMON
6968 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6969 0x1D100, // 1D100..1D126; COMMON
6970 0x1D127, // 1D127..1D128; UNKNOWN
6971 0x1D129, // 1D129..1D166; COMMON
6972 0x1D167, // 1D167..1D169; INHERITED
6973 0x1D16A, // 1D16A..1D17A; COMMON
6974 0x1D17B, // 1D17B..1D182; INHERITED
6975 0x1D183, // 1D183..1D184; COMMON
6976 0x1D185, // 1D185..1D18B; INHERITED
6977 0x1D18C, // 1D18C..1D1A9; COMMON
6978 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6979 0x1D1AE, // 1D1AE..1D1EA; COMMON
6980 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
6981 0x1D200, // 1D200..1D245; GREEK
6982 0x1D246, // 1D246..1D2BF; UNKNOWN
6983 0x1D2C0, // 1D2C0..1D2D3; COMMON
6984 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
6985 0x1D2E0, // 1D2E0..1D2F3; COMMON
6986 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6987 0x1D300, // 1D300..1D356; COMMON
6988 0x1D357, // 1D357..1D35F; UNKNOWN
6989 0x1D360, // 1D360..1D378; COMMON
6990 0x1D379, // 1D379..1D3FF; UNKNOWN
6991 0x1D400, // 1D400..1D454; COMMON
6992 0x1D455, // 1D455 ; UNKNOWN
6993 0x1D456, // 1D456..1D49C; COMMON
6994 0x1D49D, // 1D49D ; UNKNOWN
6995 0x1D49E, // 1D49E..1D49F; COMMON
6996 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
6997 0x1D4A2, // 1D4A2 ; COMMON
6998 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
6999 0x1D4A5, // 1D4A5..1D4A6; COMMON
7000 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
7001 0x1D4A9, // 1D4A9..1D4AC; COMMON
7002 0x1D4AD, // 1D4AD ; UNKNOWN
7003 0x1D4AE, // 1D4AE..1D4B9; COMMON
7004 0x1D4BA, // 1D4BA ; UNKNOWN
7005 0x1D4BB, // 1D4BB ; COMMON
7006 0x1D4BC, // 1D4BC ; UNKNOWN
7007 0x1D4BD, // 1D4BD..1D4C3; COMMON
7008 0x1D4C4, // 1D4C4 ; UNKNOWN
7009 0x1D4C5, // 1D4C5..1D505; COMMON
7010 0x1D506, // 1D506 ; UNKNOWN
7011 0x1D507, // 1D507..1D50A; COMMON
7012 0x1D50B, // 1D50B..1D50C; UNKNOWN
7013 0x1D50D, // 1D50D..1D514; COMMON
7014 0x1D515, // 1D515 ; UNKNOWN
7015 0x1D516, // 1D516..1D51C; COMMON
7016 0x1D51D, // 1D51D ; UNKNOWN
7017 0x1D51E, // 1D51E..1D539; COMMON
7018 0x1D53A, // 1D53A ; UNKNOWN
7019 0x1D53B, // 1D53B..1D53E; COMMON
7020 0x1D53F, // 1D53F ; UNKNOWN
7021 0x1D540, // 1D540..1D544; COMMON
7022 0x1D545, // 1D545 ; UNKNOWN
7023 0x1D546, // 1D546 ; COMMON
7024 0x1D547, // 1D547..1D549; UNKNOWN
7025 0x1D54A, // 1D54A..1D550; COMMON
7026 0x1D551, // 1D551 ; UNKNOWN
7027 0x1D552, // 1D552..1D6A5; COMMON
7028 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
7029 0x1D6A8, // 1D6A8..1D7CB; COMMON
7030 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
7031 0x1D7CE, // 1D7CE..1D7FF; COMMON
7032 0x1D800, // 1D800..1DA8B; SIGNWRITING
7033 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
7034 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
7035 0x1DAA0, // 1DAA0 ; UNKNOWN
7036 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
7037 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
7038 0x1DF00, // 1DF00..1DF1E; LATIN
7039 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
7040 0x1DF25, // 1DF25..1DF2A; LATIN
7041 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
7042 0x1E000, // 1E000..1E006; GLAGOLITIC
7043 0x1E007, // 1E007 ; UNKNOWN
7044 0x1E008, // 1E008..1E018; GLAGOLITIC
7045 0x1E019, // 1E019..1E01A; UNKNOWN
7046 0x1E01B, // 1E01B..1E021; GLAGOLITIC
7047 0x1E022, // 1E022 ; UNKNOWN
7048 0x1E023, // 1E023..1E024; GLAGOLITIC
7049 0x1E025, // 1E025 ; UNKNOWN
7050 0x1E026, // 1E026..1E02A; GLAGOLITIC
7051 0x1E02B, // 1E02B..1E02F; UNKNOWN
7052 0x1E030, // 1E030..1E06D; CYRILLIC
7053 0x1E06E, // 1E06E..1E08E; UNKNOWN
7054 0x1E08F, // 1E08F ; CYRILLIC
7055 0x1E090, // 1E090..1E0FF; UNKNOWN
7056 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
7057 0x1E12D, // 1E12D..1E12F; UNKNOWN
7058 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
7059 0x1E13E, // 1E13E..1E13F; UNKNOWN
7060 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
7061 0x1E14A, // 1E14A..1E14D; UNKNOWN
7062 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
7063 0x1E150, // 1E150..1E28F; UNKNOWN
7064 0x1E290, // 1E290..1E2AE; TOTO
7065 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
7066 0x1E2C0, // 1E2C0..1E2F9; WANCHO
7067 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
7068 0x1E2FF, // 1E2FF ; WANCHO
7069 0x1E300, // 1E300..1E4CF; UNKNOWN
7070 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
7071 0x1E4FA, // 1E4FA..1E5CF; UNKNOWN
7072 0x1E5D0, // 1E5D0..1E5FA; OL_ONAL
7073 0x1E5FB, // 1E5FB..1E5FE; UNKNOWN
7074 0x1E5FF, // 1E5FF ; OL_ONAL
7075 0x1E600, // 1E600..1E7DF; UNKNOWN
7076 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
7077 0x1E7E7, // 1E7E7 ; UNKNOWN
7078 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
7079 0x1E7EC, // 1E7EC ; UNKNOWN
7080 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
7081 0x1E7EF, // 1E7EF ; UNKNOWN
7082 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
7083 0x1E7FF, // 1E7FF ; UNKNOWN
7084 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
7085 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
7086 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
7087 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
7088 0x1E900, // 1E900..1E94B; ADLAM
7089 0x1E94C, // 1E94C..1E94F; UNKNOWN
7090 0x1E950, // 1E950..1E959; ADLAM
7091 0x1E95A, // 1E95A..1E95D; UNKNOWN
7092 0x1E95E, // 1E95E..1E95F; ADLAM
7093 0x1E960, // 1E960..1EC70; UNKNOWN
7094 0x1EC71, // 1EC71..1ECB4; COMMON
7095 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
7096 0x1ED01, // 1ED01..1ED3D; COMMON
7097 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
7098 0x1EE00, // 1EE00..1EE03; ARABIC
7099 0x1EE04, // 1EE04 ; UNKNOWN
7100 0x1EE05, // 1EE05..1EE1F; ARABIC
7101 0x1EE20, // 1EE20 ; UNKNOWN
7102 0x1EE21, // 1EE21..1EE22; ARABIC
7103 0x1EE23, // 1EE23 ; UNKNOWN
7104 0x1EE24, // 1EE24 ; ARABIC
7105 0x1EE25, // 1EE25..1EE26; UNKNOWN
7106 0x1EE27, // 1EE27 ; ARABIC
7107 0x1EE28, // 1EE28 ; UNKNOWN
7108 0x1EE29, // 1EE29..1EE32; ARABIC
7109 0x1EE33, // 1EE33 ; UNKNOWN
7110 0x1EE34, // 1EE34..1EE37; ARABIC
7111 0x1EE38, // 1EE38 ; UNKNOWN
7112 0x1EE39, // 1EE39 ; ARABIC
7113 0x1EE3A, // 1EE3A ; UNKNOWN
7114 0x1EE3B, // 1EE3B ; ARABIC
7115 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
7116 0x1EE42, // 1EE42 ; ARABIC
7117 0x1EE43, // 1EE43..1EE46; UNKNOWN
7118 0x1EE47, // 1EE47 ; ARABIC
7119 0x1EE48, // 1EE48 ; UNKNOWN
7120 0x1EE49, // 1EE49 ; ARABIC
7121 0x1EE4A, // 1EE4A ; UNKNOWN
7122 0x1EE4B, // 1EE4B ; ARABIC
7123 0x1EE4C, // 1EE4C ; UNKNOWN
7124 0x1EE4D, // 1EE4D..1EE4F; ARABIC
7125 0x1EE50, // 1EE50 ; UNKNOWN
7126 0x1EE51, // 1EE51..1EE52; ARABIC
7127 0x1EE53, // 1EE53 ; UNKNOWN
7128 0x1EE54, // 1EE54 ; ARABIC
7129 0x1EE55, // 1EE55..1EE56; UNKNOWN
7130 0x1EE57, // 1EE57 ; ARABIC
7131 0x1EE58, // 1EE58 ; UNKNOWN
7132 0x1EE59, // 1EE59 ; ARABIC
7133 0x1EE5A, // 1EE5A ; UNKNOWN
7134 0x1EE5B, // 1EE5B ; ARABIC
7135 0x1EE5C, // 1EE5C ; UNKNOWN
7136 0x1EE5D, // 1EE5D ; ARABIC
7137 0x1EE5E, // 1EE5E ; UNKNOWN
7138 0x1EE5F, // 1EE5F ; ARABIC
7139 0x1EE60, // 1EE60 ; UNKNOWN
7140 0x1EE61, // 1EE61..1EE62; ARABIC
7141 0x1EE63, // 1EE63 ; UNKNOWN
7142 0x1EE64, // 1EE64 ; ARABIC
7143 0x1EE65, // 1EE65..1EE66; UNKNOWN
7144 0x1EE67, // 1EE67..1EE6A; ARABIC
7145 0x1EE6B, // 1EE6B ; UNKNOWN
7146 0x1EE6C, // 1EE6C..1EE72; ARABIC
7147 0x1EE73, // 1EE73 ; UNKNOWN
7148 0x1EE74, // 1EE74..1EE77; ARABIC
7149 0x1EE78, // 1EE78 ; UNKNOWN
7150 0x1EE79, // 1EE79..1EE7C; ARABIC
7151 0x1EE7D, // 1EE7D ; UNKNOWN
7152 0x1EE7E, // 1EE7E ; ARABIC
7153 0x1EE7F, // 1EE7F ; UNKNOWN
7154 0x1EE80, // 1EE80..1EE89; ARABIC
7155 0x1EE8A, // 1EE8A ; UNKNOWN
7156 0x1EE8B, // 1EE8B..1EE9B; ARABIC
7157 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
7158 0x1EEA1, // 1EEA1..1EEA3; ARABIC
7159 0x1EEA4, // 1EEA4 ; UNKNOWN
7160 0x1EEA5, // 1EEA5..1EEA9; ARABIC
7161 0x1EEAA, // 1EEAA ; UNKNOWN
7162 0x1EEAB, // 1EEAB..1EEBB; ARABIC
7163 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
7164 0x1EEF0, // 1EEF0..1EEF1; ARABIC
7165 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
7166 0x1F000, // 1F000..1F02B; COMMON
7167 0x1F02C, // 1F02C..1F02F; UNKNOWN
7168 0x1F030, // 1F030..1F093; COMMON
7169 0x1F094, // 1F094..1F09F; UNKNOWN
7170 0x1F0A0, // 1F0A0..1F0AE; COMMON
7171 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
7172 0x1F0B1, // 1F0B1..1F0BF; COMMON
7173 0x1F0C0, // 1F0C0 ; UNKNOWN
7174 0x1F0C1, // 1F0C1..1F0CF; COMMON
7175 0x1F0D0, // 1F0D0 ; UNKNOWN
7176 0x1F0D1, // 1F0D1..1F0F5; COMMON
7177 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
7178 0x1F100, // 1F100..1F1AD; COMMON
7179 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
7180 0x1F1E6, // 1F1E6..1F1FF; COMMON
7181 0x1F200, // 1F200 ; HIRAGANA
7182 0x1F201, // 1F201..1F202; COMMON
7183 0x1F203, // 1F203..1F20F; UNKNOWN
7184 0x1F210, // 1F210..1F23B; COMMON
7185 0x1F23C, // 1F23C..1F23F; UNKNOWN
7186 0x1F240, // 1F240..1F248; COMMON
7187 0x1F249, // 1F249..1F24F; UNKNOWN
7188 0x1F250, // 1F250..1F251; COMMON
7189 0x1F252, // 1F252..1F25F; UNKNOWN
7190 0x1F260, // 1F260..1F265; COMMON
7191 0x1F266, // 1F266..1F2FF; UNKNOWN
7192 0x1F300, // 1F300..1F6D7; COMMON
7193 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN
7194 0x1F6DC, // 1F6DC..1F6EC; COMMON
7195 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
7196 0x1F6F0, // 1F6F0..1F6FC; COMMON
7197 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
7198 0x1F700, // 1F700..1F776; COMMON
7199 0x1F777, // 1F777..1F77A; UNKNOWN
7200 0x1F77B, // 1F77B..1F7D9; COMMON
7201 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
7202 0x1F7E0, // 1F7E0..1F7EB; COMMON
7203 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
7204 0x1F7F0, // 1F7F0 ; COMMON
7205 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7206 0x1F800, // 1F800..1F80B; COMMON
7207 0x1F80C, // 1F80C..1F80F; UNKNOWN
7208 0x1F810, // 1F810..1F847; COMMON
7209 0x1F848, // 1F848..1F84F; UNKNOWN
7210 0x1F850, // 1F850..1F859; COMMON
7211 0x1F85A, // 1F85A..1F85F; UNKNOWN
7212 0x1F860, // 1F860..1F887; COMMON
7213 0x1F888, // 1F888..1F88F; UNKNOWN
7214 0x1F890, // 1F890..1F8AD; COMMON
7215 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7216 0x1F8B0, // 1F8B0..1F8BB; COMMON
7217 0x1F8BC, // 1F8BC..1F8BF; UNKNOWN
7218 0x1F8C0, // 1F8C0..1F8C1; COMMON
7219 0x1F8C2, // 1F8C2..1F8FF; UNKNOWN
7220 0x1F900, // 1F900..1FA53; COMMON
7221 0x1FA54, // 1FA54..1FA5F; UNKNOWN
7222 0x1FA60, // 1FA60..1FA6D; COMMON
7223 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7224 0x1FA70, // 1FA70..1FA7C; COMMON
7225 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7226 0x1FA80, // 1FA80..1FA89; COMMON
7227 0x1FA8A, // 1FA8A..1FA8E; UNKNOWN
7228 0x1FA8F, // 1FA8F..1FAC6; COMMON
7229 0x1FAC7, // 1FAC7..1FACD; UNKNOWN
7230 0x1FACE, // 1FACE..1FADC; COMMON
7231 0x1FADD, // 1FADD..1FADE; UNKNOWN
7232 0x1FADF, // 1FADF..1FAE9; COMMON
7233 0x1FAEA, // 1FAEA..1FAEF; UNKNOWN
7234 0x1FAF0, // 1FAF0..1FAF8; COMMON
7235 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7236 0x1FB00, // 1FB00..1FB92; COMMON
7237 0x1FB93, // 1FB93 ; UNKNOWN
7238 0x1FB94, // 1FB94..1FBF9; COMMON
7239 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN
7240 0x20000, // 20000..2A6DF; HAN
7241 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7242 0x2A700, // 2A700..2B739; HAN
7243 0x2B73A, // 2B73A..2B73F; UNKNOWN
7244 0x2B740, // 2B740..2B81D; HAN
7245 0x2B81E, // 2B81E..2B81F; UNKNOWN
7246 0x2B820, // 2B820..2CEA1; HAN
7247 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
7248 0x2CEB0, // 2CEB0..2EBE0; HAN
7249 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7250 0x2EBF0, // 2EBF0..2EE5D; HAN
7251 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7252 0x2F800, // 2F800..2FA1D; HAN
7253 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7254 0x30000, // 30000..3134A; HAN
7255 0x3134B, // 3134B..3134F; UNKNOWN
7256 0x31350, // 31350..323AF; HAN
7257 0x323B0, // 323B0..E0000; UNKNOWN
7258 0xE0001, // E0001 ; COMMON
7259 0xE0002, // E0002..E001F; UNKNOWN
7260 0xE0020, // E0020..E007F; COMMON
7261 0xE0080, // E0080..E00FF; UNKNOWN
7262 0xE0100, // E0100..E01EF; INHERITED
7263 0xE01F0, // E01F0..10FFFF; UNKNOWN
7264 };
7265
7266 private static final UnicodeScript[] scripts = {
7267 COMMON, // 0000..0040
7268 LATIN, // 0041..005A
7269 COMMON, // 005B..0060
7270 LATIN, // 0061..007A
7271 COMMON, // 007B..00A9
7272 LATIN, // 00AA
7273 COMMON, // 00AB..00B9
7274 LATIN, // 00BA
7275 COMMON, // 00BB..00BF
7276 LATIN, // 00C0..00D6
7277 COMMON, // 00D7
7278 LATIN, // 00D8..00F6
7279 COMMON, // 00F7
7280 LATIN, // 00F8..02B8
7281 COMMON, // 02B9..02DF
7282 LATIN, // 02E0..02E4
7283 COMMON, // 02E5..02E9
7284 BOPOMOFO, // 02EA..02EB
7285 COMMON, // 02EC..02FF
7286 INHERITED, // 0300..036F
7287 GREEK, // 0370..0373
7288 COMMON, // 0374
7289 GREEK, // 0375..0377
7290 UNKNOWN, // 0378..0379
7291 GREEK, // 037A..037D
7292 COMMON, // 037E
7293 GREEK, // 037F
7294 UNKNOWN, // 0380..0383
7295 GREEK, // 0384
7296 COMMON, // 0385
7297 GREEK, // 0386
7298 COMMON, // 0387
7299 GREEK, // 0388..038A
7300 UNKNOWN, // 038B
7301 GREEK, // 038C
7302 UNKNOWN, // 038D
7303 GREEK, // 038E..03A1
7304 UNKNOWN, // 03A2
7305 GREEK, // 03A3..03E1
7306 COPTIC, // 03E2..03EF
7307 GREEK, // 03F0..03FF
7308 CYRILLIC, // 0400..0484
7309 INHERITED, // 0485..0486
7310 CYRILLIC, // 0487..052F
7311 UNKNOWN, // 0530
7312 ARMENIAN, // 0531..0556
7313 UNKNOWN, // 0557..0558
7314 ARMENIAN, // 0559..058A
7315 UNKNOWN, // 058B..058C
7316 ARMENIAN, // 058D..058F
7317 UNKNOWN, // 0590
7318 HEBREW, // 0591..05C7
7319 UNKNOWN, // 05C8..05CF
7320 HEBREW, // 05D0..05EA
7321 UNKNOWN, // 05EB..05EE
7322 HEBREW, // 05EF..05F4
7323 UNKNOWN, // 05F5..05FF
7324 ARABIC, // 0600..0604
7325 COMMON, // 0605
7326 ARABIC, // 0606..060B
7327 COMMON, // 060C
7328 ARABIC, // 060D..061A
7329 COMMON, // 061B
7330 ARABIC, // 061C..061E
7331 COMMON, // 061F
7332 ARABIC, // 0620..063F
7333 COMMON, // 0640
7334 ARABIC, // 0641..064A
7335 INHERITED, // 064B..0655
7336 ARABIC, // 0656..066F
7337 INHERITED, // 0670
7338 ARABIC, // 0671..06DC
7339 COMMON, // 06DD
7340 ARABIC, // 06DE..06FF
7341 SYRIAC, // 0700..070D
7342 UNKNOWN, // 070E
7343 SYRIAC, // 070F..074A
7344 UNKNOWN, // 074B..074C
7345 SYRIAC, // 074D..074F
7346 ARABIC, // 0750..077F
7347 THAANA, // 0780..07B1
7348 UNKNOWN, // 07B2..07BF
7349 NKO, // 07C0..07FA
7350 UNKNOWN, // 07FB..07FC
7351 NKO, // 07FD..07FF
7352 SAMARITAN, // 0800..082D
7353 UNKNOWN, // 082E..082F
7354 SAMARITAN, // 0830..083E
7355 UNKNOWN, // 083F
7356 MANDAIC, // 0840..085B
7357 UNKNOWN, // 085C..085D
7358 MANDAIC, // 085E
7359 UNKNOWN, // 085F
7360 SYRIAC, // 0860..086A
7361 UNKNOWN, // 086B..086F
7362 ARABIC, // 0870..088E
7363 UNKNOWN, // 088F
7364 ARABIC, // 0890..0891
7365 UNKNOWN, // 0892..0896
7366 ARABIC, // 0897..08E1
7367 COMMON, // 08E2
7368 ARABIC, // 08E3..08FF
7369 DEVANAGARI, // 0900..0950
7370 INHERITED, // 0951..0954
7371 DEVANAGARI, // 0955..0963
7372 COMMON, // 0964..0965
7373 DEVANAGARI, // 0966..097F
7374 BENGALI, // 0980..0983
7375 UNKNOWN, // 0984
7376 BENGALI, // 0985..098C
7377 UNKNOWN, // 098D..098E
7378 BENGALI, // 098F..0990
7379 UNKNOWN, // 0991..0992
7380 BENGALI, // 0993..09A8
7381 UNKNOWN, // 09A9
7382 BENGALI, // 09AA..09B0
7383 UNKNOWN, // 09B1
7384 BENGALI, // 09B2
7385 UNKNOWN, // 09B3..09B5
7386 BENGALI, // 09B6..09B9
7387 UNKNOWN, // 09BA..09BB
7388 BENGALI, // 09BC..09C4
7389 UNKNOWN, // 09C5..09C6
7390 BENGALI, // 09C7..09C8
7391 UNKNOWN, // 09C9..09CA
7392 BENGALI, // 09CB..09CE
7393 UNKNOWN, // 09CF..09D6
7394 BENGALI, // 09D7
7395 UNKNOWN, // 09D8..09DB
7396 BENGALI, // 09DC..09DD
7397 UNKNOWN, // 09DE
7398 BENGALI, // 09DF..09E3
7399 UNKNOWN, // 09E4..09E5
7400 BENGALI, // 09E6..09FE
7401 UNKNOWN, // 09FF..0A00
7402 GURMUKHI, // 0A01..0A03
7403 UNKNOWN, // 0A04
7404 GURMUKHI, // 0A05..0A0A
7405 UNKNOWN, // 0A0B..0A0E
7406 GURMUKHI, // 0A0F..0A10
7407 UNKNOWN, // 0A11..0A12
7408 GURMUKHI, // 0A13..0A28
7409 UNKNOWN, // 0A29
7410 GURMUKHI, // 0A2A..0A30
7411 UNKNOWN, // 0A31
7412 GURMUKHI, // 0A32..0A33
7413 UNKNOWN, // 0A34
7414 GURMUKHI, // 0A35..0A36
7415 UNKNOWN, // 0A37
7416 GURMUKHI, // 0A38..0A39
7417 UNKNOWN, // 0A3A..0A3B
7418 GURMUKHI, // 0A3C
7419 UNKNOWN, // 0A3D
7420 GURMUKHI, // 0A3E..0A42
7421 UNKNOWN, // 0A43..0A46
7422 GURMUKHI, // 0A47..0A48
7423 UNKNOWN, // 0A49..0A4A
7424 GURMUKHI, // 0A4B..0A4D
7425 UNKNOWN, // 0A4E..0A50
7426 GURMUKHI, // 0A51
7427 UNKNOWN, // 0A52..0A58
7428 GURMUKHI, // 0A59..0A5C
7429 UNKNOWN, // 0A5D
7430 GURMUKHI, // 0A5E
7431 UNKNOWN, // 0A5F..0A65
7432 GURMUKHI, // 0A66..0A76
7433 UNKNOWN, // 0A77..0A80
7434 GUJARATI, // 0A81..0A83
7435 UNKNOWN, // 0A84
7436 GUJARATI, // 0A85..0A8D
7437 UNKNOWN, // 0A8E
7438 GUJARATI, // 0A8F..0A91
7439 UNKNOWN, // 0A92
7440 GUJARATI, // 0A93..0AA8
7441 UNKNOWN, // 0AA9
7442 GUJARATI, // 0AAA..0AB0
7443 UNKNOWN, // 0AB1
7444 GUJARATI, // 0AB2..0AB3
7445 UNKNOWN, // 0AB4
7446 GUJARATI, // 0AB5..0AB9
7447 UNKNOWN, // 0ABA..0ABB
7448 GUJARATI, // 0ABC..0AC5
7449 UNKNOWN, // 0AC6
7450 GUJARATI, // 0AC7..0AC9
7451 UNKNOWN, // 0ACA
7452 GUJARATI, // 0ACB..0ACD
7453 UNKNOWN, // 0ACE..0ACF
7454 GUJARATI, // 0AD0
7455 UNKNOWN, // 0AD1..0ADF
7456 GUJARATI, // 0AE0..0AE3
7457 UNKNOWN, // 0AE4..0AE5
7458 GUJARATI, // 0AE6..0AF1
7459 UNKNOWN, // 0AF2..0AF8
7460 GUJARATI, // 0AF9..0AFF
7461 UNKNOWN, // 0B00
7462 ORIYA, // 0B01..0B03
7463 UNKNOWN, // 0B04
7464 ORIYA, // 0B05..0B0C
7465 UNKNOWN, // 0B0D..0B0E
7466 ORIYA, // 0B0F..0B10
7467 UNKNOWN, // 0B11..0B12
7468 ORIYA, // 0B13..0B28
7469 UNKNOWN, // 0B29
7470 ORIYA, // 0B2A..0B30
7471 UNKNOWN, // 0B31
7472 ORIYA, // 0B32..0B33
7473 UNKNOWN, // 0B34
7474 ORIYA, // 0B35..0B39
7475 UNKNOWN, // 0B3A..0B3B
7476 ORIYA, // 0B3C..0B44
7477 UNKNOWN, // 0B45..0B46
7478 ORIYA, // 0B47..0B48
7479 UNKNOWN, // 0B49..0B4A
7480 ORIYA, // 0B4B..0B4D
7481 UNKNOWN, // 0B4E..0B54
7482 ORIYA, // 0B55..0B57
7483 UNKNOWN, // 0B58..0B5B
7484 ORIYA, // 0B5C..0B5D
7485 UNKNOWN, // 0B5E
7486 ORIYA, // 0B5F..0B63
7487 UNKNOWN, // 0B64..0B65
7488 ORIYA, // 0B66..0B77
7489 UNKNOWN, // 0B78..0B81
7490 TAMIL, // 0B82..0B83
7491 UNKNOWN, // 0B84
7492 TAMIL, // 0B85..0B8A
7493 UNKNOWN, // 0B8B..0B8D
7494 TAMIL, // 0B8E..0B90
7495 UNKNOWN, // 0B91
7496 TAMIL, // 0B92..0B95
7497 UNKNOWN, // 0B96..0B98
7498 TAMIL, // 0B99..0B9A
7499 UNKNOWN, // 0B9B
7500 TAMIL, // 0B9C
7501 UNKNOWN, // 0B9D
7502 TAMIL, // 0B9E..0B9F
7503 UNKNOWN, // 0BA0..0BA2
7504 TAMIL, // 0BA3..0BA4
7505 UNKNOWN, // 0BA5..0BA7
7506 TAMIL, // 0BA8..0BAA
7507 UNKNOWN, // 0BAB..0BAD
7508 TAMIL, // 0BAE..0BB9
7509 UNKNOWN, // 0BBA..0BBD
7510 TAMIL, // 0BBE..0BC2
7511 UNKNOWN, // 0BC3..0BC5
7512 TAMIL, // 0BC6..0BC8
7513 UNKNOWN, // 0BC9
7514 TAMIL, // 0BCA..0BCD
7515 UNKNOWN, // 0BCE..0BCF
7516 TAMIL, // 0BD0
7517 UNKNOWN, // 0BD1..0BD6
7518 TAMIL, // 0BD7
7519 UNKNOWN, // 0BD8..0BE5
7520 TAMIL, // 0BE6..0BFA
7521 UNKNOWN, // 0BFB..0BFF
7522 TELUGU, // 0C00..0C0C
7523 UNKNOWN, // 0C0D
7524 TELUGU, // 0C0E..0C10
7525 UNKNOWN, // 0C11
7526 TELUGU, // 0C12..0C28
7527 UNKNOWN, // 0C29
7528 TELUGU, // 0C2A..0C39
7529 UNKNOWN, // 0C3A..0C3B
7530 TELUGU, // 0C3C..0C44
7531 UNKNOWN, // 0C45
7532 TELUGU, // 0C46..0C48
7533 UNKNOWN, // 0C49
7534 TELUGU, // 0C4A..0C4D
7535 UNKNOWN, // 0C4E..0C54
7536 TELUGU, // 0C55..0C56
7537 UNKNOWN, // 0C57
7538 TELUGU, // 0C58..0C5A
7539 UNKNOWN, // 0C5B..0C5C
7540 TELUGU, // 0C5D
7541 UNKNOWN, // 0C5E..0C5F
7542 TELUGU, // 0C60..0C63
7543 UNKNOWN, // 0C64..0C65
7544 TELUGU, // 0C66..0C6F
7545 UNKNOWN, // 0C70..0C76
7546 TELUGU, // 0C77..0C7F
7547 KANNADA, // 0C80..0C8C
7548 UNKNOWN, // 0C8D
7549 KANNADA, // 0C8E..0C90
7550 UNKNOWN, // 0C91
7551 KANNADA, // 0C92..0CA8
7552 UNKNOWN, // 0CA9
7553 KANNADA, // 0CAA..0CB3
7554 UNKNOWN, // 0CB4
7555 KANNADA, // 0CB5..0CB9
7556 UNKNOWN, // 0CBA..0CBB
7557 KANNADA, // 0CBC..0CC4
7558 UNKNOWN, // 0CC5
7559 KANNADA, // 0CC6..0CC8
7560 UNKNOWN, // 0CC9
7561 KANNADA, // 0CCA..0CCD
7562 UNKNOWN, // 0CCE..0CD4
7563 KANNADA, // 0CD5..0CD6
7564 UNKNOWN, // 0CD7..0CDC
7565 KANNADA, // 0CDD..0CDE
7566 UNKNOWN, // 0CDF
7567 KANNADA, // 0CE0..0CE3
7568 UNKNOWN, // 0CE4..0CE5
7569 KANNADA, // 0CE6..0CEF
7570 UNKNOWN, // 0CF0
7571 KANNADA, // 0CF1..0CF3
7572 UNKNOWN, // 0CF4..0CFF
7573 MALAYALAM, // 0D00..0D0C
7574 UNKNOWN, // 0D0D
7575 MALAYALAM, // 0D0E..0D10
7576 UNKNOWN, // 0D11
7577 MALAYALAM, // 0D12..0D44
7578 UNKNOWN, // 0D45
7579 MALAYALAM, // 0D46..0D48
7580 UNKNOWN, // 0D49
7581 MALAYALAM, // 0D4A..0D4F
7582 UNKNOWN, // 0D50..0D53
7583 MALAYALAM, // 0D54..0D63
7584 UNKNOWN, // 0D64..0D65
7585 MALAYALAM, // 0D66..0D7F
7586 UNKNOWN, // 0D80
7587 SINHALA, // 0D81..0D83
7588 UNKNOWN, // 0D84
7589 SINHALA, // 0D85..0D96
7590 UNKNOWN, // 0D97..0D99
7591 SINHALA, // 0D9A..0DB1
7592 UNKNOWN, // 0DB2
7593 SINHALA, // 0DB3..0DBB
7594 UNKNOWN, // 0DBC
7595 SINHALA, // 0DBD
7596 UNKNOWN, // 0DBE..0DBF
7597 SINHALA, // 0DC0..0DC6
7598 UNKNOWN, // 0DC7..0DC9
7599 SINHALA, // 0DCA
7600 UNKNOWN, // 0DCB..0DCE
7601 SINHALA, // 0DCF..0DD4
7602 UNKNOWN, // 0DD5
7603 SINHALA, // 0DD6
7604 UNKNOWN, // 0DD7
7605 SINHALA, // 0DD8..0DDF
7606 UNKNOWN, // 0DE0..0DE5
7607 SINHALA, // 0DE6..0DEF
7608 UNKNOWN, // 0DF0..0DF1
7609 SINHALA, // 0DF2..0DF4
7610 UNKNOWN, // 0DF5..0E00
7611 THAI, // 0E01..0E3A
7612 UNKNOWN, // 0E3B..0E3E
7613 COMMON, // 0E3F
7614 THAI, // 0E40..0E5B
7615 UNKNOWN, // 0E5C..0E80
7616 LAO, // 0E81..0E82
7617 UNKNOWN, // 0E83
7618 LAO, // 0E84
7619 UNKNOWN, // 0E85
7620 LAO, // 0E86..0E8A
7621 UNKNOWN, // 0E8B
7622 LAO, // 0E8C..0EA3
7623 UNKNOWN, // 0EA4
7624 LAO, // 0EA5
7625 UNKNOWN, // 0EA6
7626 LAO, // 0EA7..0EBD
7627 UNKNOWN, // 0EBE..0EBF
7628 LAO, // 0EC0..0EC4
7629 UNKNOWN, // 0EC5
7630 LAO, // 0EC6
7631 UNKNOWN, // 0EC7
7632 LAO, // 0EC8..0ECE
7633 UNKNOWN, // 0ECF
7634 LAO, // 0ED0..0ED9
7635 UNKNOWN, // 0EDA..0EDB
7636 LAO, // 0EDC..0EDF
7637 UNKNOWN, // 0EE0..0EFF
7638 TIBETAN, // 0F00..0F47
7639 UNKNOWN, // 0F48
7640 TIBETAN, // 0F49..0F6C
7641 UNKNOWN, // 0F6D..0F70
7642 TIBETAN, // 0F71..0F97
7643 UNKNOWN, // 0F98
7644 TIBETAN, // 0F99..0FBC
7645 UNKNOWN, // 0FBD
7646 TIBETAN, // 0FBE..0FCC
7647 UNKNOWN, // 0FCD
7648 TIBETAN, // 0FCE..0FD4
7649 COMMON, // 0FD5..0FD8
7650 TIBETAN, // 0FD9..0FDA
7651 UNKNOWN, // 0FDB..0FFF
7652 MYANMAR, // 1000..109F
7653 GEORGIAN, // 10A0..10C5
7654 UNKNOWN, // 10C6
7655 GEORGIAN, // 10C7
7656 UNKNOWN, // 10C8..10CC
7657 GEORGIAN, // 10CD
7658 UNKNOWN, // 10CE..10CF
7659 GEORGIAN, // 10D0..10FA
7660 COMMON, // 10FB
7661 GEORGIAN, // 10FC..10FF
7662 HANGUL, // 1100..11FF
7663 ETHIOPIC, // 1200..1248
7664 UNKNOWN, // 1249
7665 ETHIOPIC, // 124A..124D
7666 UNKNOWN, // 124E..124F
7667 ETHIOPIC, // 1250..1256
7668 UNKNOWN, // 1257
7669 ETHIOPIC, // 1258
7670 UNKNOWN, // 1259
7671 ETHIOPIC, // 125A..125D
7672 UNKNOWN, // 125E..125F
7673 ETHIOPIC, // 1260..1288
7674 UNKNOWN, // 1289
7675 ETHIOPIC, // 128A..128D
7676 UNKNOWN, // 128E..128F
7677 ETHIOPIC, // 1290..12B0
7678 UNKNOWN, // 12B1
7679 ETHIOPIC, // 12B2..12B5
7680 UNKNOWN, // 12B6..12B7
7681 ETHIOPIC, // 12B8..12BE
7682 UNKNOWN, // 12BF
7683 ETHIOPIC, // 12C0
7684 UNKNOWN, // 12C1
7685 ETHIOPIC, // 12C2..12C5
7686 UNKNOWN, // 12C6..12C7
7687 ETHIOPIC, // 12C8..12D6
7688 UNKNOWN, // 12D7
7689 ETHIOPIC, // 12D8..1310
7690 UNKNOWN, // 1311
7691 ETHIOPIC, // 1312..1315
7692 UNKNOWN, // 1316..1317
7693 ETHIOPIC, // 1318..135A
7694 UNKNOWN, // 135B..135C
7695 ETHIOPIC, // 135D..137C
7696 UNKNOWN, // 137D..137F
7697 ETHIOPIC, // 1380..1399
7698 UNKNOWN, // 139A..139F
7699 CHEROKEE, // 13A0..13F5
7700 UNKNOWN, // 13F6..13F7
7701 CHEROKEE, // 13F8..13FD
7702 UNKNOWN, // 13FE..13FF
7703 CANADIAN_ABORIGINAL, // 1400..167F
7704 OGHAM, // 1680..169C
7705 UNKNOWN, // 169D..169F
7706 RUNIC, // 16A0..16EA
7707 COMMON, // 16EB..16ED
7708 RUNIC, // 16EE..16F8
7709 UNKNOWN, // 16F9..16FF
7710 TAGALOG, // 1700..1715
7711 UNKNOWN, // 1716..171E
7712 TAGALOG, // 171F
7713 HANUNOO, // 1720..1734
7714 COMMON, // 1735..1736
7715 UNKNOWN, // 1737..173F
7716 BUHID, // 1740..1753
7717 UNKNOWN, // 1754..175F
7718 TAGBANWA, // 1760..176C
7719 UNKNOWN, // 176D
7720 TAGBANWA, // 176E..1770
7721 UNKNOWN, // 1771
7722 TAGBANWA, // 1772..1773
7723 UNKNOWN, // 1774..177F
7724 KHMER, // 1780..17DD
7725 UNKNOWN, // 17DE..17DF
7726 KHMER, // 17E0..17E9
7727 UNKNOWN, // 17EA..17EF
7728 KHMER, // 17F0..17F9
7729 UNKNOWN, // 17FA..17FF
7730 MONGOLIAN, // 1800..1801
7731 COMMON, // 1802..1803
7732 MONGOLIAN, // 1804
7733 COMMON, // 1805
7734 MONGOLIAN, // 1806..1819
7735 UNKNOWN, // 181A..181F
7736 MONGOLIAN, // 1820..1878
7737 UNKNOWN, // 1879..187F
7738 MONGOLIAN, // 1880..18AA
7739 UNKNOWN, // 18AB..18AF
7740 CANADIAN_ABORIGINAL, // 18B0..18F5
7741 UNKNOWN, // 18F6..18FF
7742 LIMBU, // 1900..191E
7743 UNKNOWN, // 191F
7744 LIMBU, // 1920..192B
7745 UNKNOWN, // 192C..192F
7746 LIMBU, // 1930..193B
7747 UNKNOWN, // 193C..193F
7748 LIMBU, // 1940
7749 UNKNOWN, // 1941..1943
7750 LIMBU, // 1944..194F
7751 TAI_LE, // 1950..196D
7752 UNKNOWN, // 196E..196F
7753 TAI_LE, // 1970..1974
7754 UNKNOWN, // 1975..197F
7755 NEW_TAI_LUE, // 1980..19AB
7756 UNKNOWN, // 19AC..19AF
7757 NEW_TAI_LUE, // 19B0..19C9
7758 UNKNOWN, // 19CA..19CF
7759 NEW_TAI_LUE, // 19D0..19DA
7760 UNKNOWN, // 19DB..19DD
7761 NEW_TAI_LUE, // 19DE..19DF
7762 KHMER, // 19E0..19FF
7763 BUGINESE, // 1A00..1A1B
7764 UNKNOWN, // 1A1C..1A1D
7765 BUGINESE, // 1A1E..1A1F
7766 TAI_THAM, // 1A20..1A5E
7767 UNKNOWN, // 1A5F
7768 TAI_THAM, // 1A60..1A7C
7769 UNKNOWN, // 1A7D..1A7E
7770 TAI_THAM, // 1A7F..1A89
7771 UNKNOWN, // 1A8A..1A8F
7772 TAI_THAM, // 1A90..1A99
7773 UNKNOWN, // 1A9A..1A9F
7774 TAI_THAM, // 1AA0..1AAD
7775 UNKNOWN, // 1AAE..1AAF
7776 INHERITED, // 1AB0..1ACE
7777 UNKNOWN, // 1ACF..1AFF
7778 BALINESE, // 1B00..1B4C
7779 UNKNOWN, // 1B4D
7780 BALINESE, // 1B4E..1B7F
7781 SUNDANESE, // 1B80..1BBF
7782 BATAK, // 1BC0..1BF3
7783 UNKNOWN, // 1BF4..1BFB
7784 BATAK, // 1BFC..1BFF
7785 LEPCHA, // 1C00..1C37
7786 UNKNOWN, // 1C38..1C3A
7787 LEPCHA, // 1C3B..1C49
7788 UNKNOWN, // 1C4A..1C4C
7789 LEPCHA, // 1C4D..1C4F
7790 OL_CHIKI, // 1C50..1C7F
7791 CYRILLIC, // 1C80..1C8A
7792 UNKNOWN, // 1C8B..1C8F
7793 GEORGIAN, // 1C90..1CBA
7794 UNKNOWN, // 1CBB..1CBC
7795 GEORGIAN, // 1CBD..1CBF
7796 SUNDANESE, // 1CC0..1CC7
7797 UNKNOWN, // 1CC8..1CCF
7798 INHERITED, // 1CD0..1CD2
7799 COMMON, // 1CD3
7800 INHERITED, // 1CD4..1CE0
7801 COMMON, // 1CE1
7802 INHERITED, // 1CE2..1CE8
7803 COMMON, // 1CE9..1CEC
7804 INHERITED, // 1CED
7805 COMMON, // 1CEE..1CF3
7806 INHERITED, // 1CF4
7807 COMMON, // 1CF5..1CF7
7808 INHERITED, // 1CF8..1CF9
7809 COMMON, // 1CFA
7810 UNKNOWN, // 1CFB..1CFF
7811 LATIN, // 1D00..1D25
7812 GREEK, // 1D26..1D2A
7813 CYRILLIC, // 1D2B
7814 LATIN, // 1D2C..1D5C
7815 GREEK, // 1D5D..1D61
7816 LATIN, // 1D62..1D65
7817 GREEK, // 1D66..1D6A
7818 LATIN, // 1D6B..1D77
7819 CYRILLIC, // 1D78
7820 LATIN, // 1D79..1DBE
7821 GREEK, // 1DBF
7822 INHERITED, // 1DC0..1DFF
7823 LATIN, // 1E00..1EFF
7824 GREEK, // 1F00..1F15
7825 UNKNOWN, // 1F16..1F17
7826 GREEK, // 1F18..1F1D
7827 UNKNOWN, // 1F1E..1F1F
7828 GREEK, // 1F20..1F45
7829 UNKNOWN, // 1F46..1F47
7830 GREEK, // 1F48..1F4D
7831 UNKNOWN, // 1F4E..1F4F
7832 GREEK, // 1F50..1F57
7833 UNKNOWN, // 1F58
7834 GREEK, // 1F59
7835 UNKNOWN, // 1F5A
7836 GREEK, // 1F5B
7837 UNKNOWN, // 1F5C
7838 GREEK, // 1F5D
7839 UNKNOWN, // 1F5E
7840 GREEK, // 1F5F..1F7D
7841 UNKNOWN, // 1F7E..1F7F
7842 GREEK, // 1F80..1FB4
7843 UNKNOWN, // 1FB5
7844 GREEK, // 1FB6..1FC4
7845 UNKNOWN, // 1FC5
7846 GREEK, // 1FC6..1FD3
7847 UNKNOWN, // 1FD4..1FD5
7848 GREEK, // 1FD6..1FDB
7849 UNKNOWN, // 1FDC
7850 GREEK, // 1FDD..1FEF
7851 UNKNOWN, // 1FF0..1FF1
7852 GREEK, // 1FF2..1FF4
7853 UNKNOWN, // 1FF5
7854 GREEK, // 1FF6..1FFE
7855 UNKNOWN, // 1FFF
7856 COMMON, // 2000..200B
7857 INHERITED, // 200C..200D
7858 COMMON, // 200E..2064
7859 UNKNOWN, // 2065
7860 COMMON, // 2066..2070
7861 LATIN, // 2071
7862 UNKNOWN, // 2072..2073
7863 COMMON, // 2074..207E
7864 LATIN, // 207F
7865 COMMON, // 2080..208E
7866 UNKNOWN, // 208F
7867 LATIN, // 2090..209C
7868 UNKNOWN, // 209D..209F
7869 COMMON, // 20A0..20C0
7870 UNKNOWN, // 20C1..20CF
7871 INHERITED, // 20D0..20F0
7872 UNKNOWN, // 20F1..20FF
7873 COMMON, // 2100..2125
7874 GREEK, // 2126
7875 COMMON, // 2127..2129
7876 LATIN, // 212A..212B
7877 COMMON, // 212C..2131
7878 LATIN, // 2132
7879 COMMON, // 2133..214D
7880 LATIN, // 214E
7881 COMMON, // 214F..215F
7882 LATIN, // 2160..2188
7883 COMMON, // 2189..218B
7884 UNKNOWN, // 218C..218F
7885 COMMON, // 2190..2429
7886 UNKNOWN, // 242A..243F
7887 COMMON, // 2440..244A
7888 UNKNOWN, // 244B..245F
7889 COMMON, // 2460..27FF
7890 BRAILLE, // 2800..28FF
7891 COMMON, // 2900..2B73
7892 UNKNOWN, // 2B74..2B75
7893 COMMON, // 2B76..2B95
7894 UNKNOWN, // 2B96
7895 COMMON, // 2B97..2BFF
7896 GLAGOLITIC, // 2C00..2C5F
7897 LATIN, // 2C60..2C7F
7898 COPTIC, // 2C80..2CF3
7899 UNKNOWN, // 2CF4..2CF8
7900 COPTIC, // 2CF9..2CFF
7901 GEORGIAN, // 2D00..2D25
7902 UNKNOWN, // 2D26
7903 GEORGIAN, // 2D27
7904 UNKNOWN, // 2D28..2D2C
7905 GEORGIAN, // 2D2D
7906 UNKNOWN, // 2D2E..2D2F
7907 TIFINAGH, // 2D30..2D67
7908 UNKNOWN, // 2D68..2D6E
7909 TIFINAGH, // 2D6F..2D70
7910 UNKNOWN, // 2D71..2D7E
7911 TIFINAGH, // 2D7F
7912 ETHIOPIC, // 2D80..2D96
7913 UNKNOWN, // 2D97..2D9F
7914 ETHIOPIC, // 2DA0..2DA6
7915 UNKNOWN, // 2DA7
7916 ETHIOPIC, // 2DA8..2DAE
7917 UNKNOWN, // 2DAF
7918 ETHIOPIC, // 2DB0..2DB6
7919 UNKNOWN, // 2DB7
7920 ETHIOPIC, // 2DB8..2DBE
7921 UNKNOWN, // 2DBF
7922 ETHIOPIC, // 2DC0..2DC6
7923 UNKNOWN, // 2DC7
7924 ETHIOPIC, // 2DC8..2DCE
7925 UNKNOWN, // 2DCF
7926 ETHIOPIC, // 2DD0..2DD6
7927 UNKNOWN, // 2DD7
7928 ETHIOPIC, // 2DD8..2DDE
7929 UNKNOWN, // 2DDF
7930 CYRILLIC, // 2DE0..2DFF
7931 COMMON, // 2E00..2E5D
7932 UNKNOWN, // 2E5E..2E7F
7933 HAN, // 2E80..2E99
7934 UNKNOWN, // 2E9A
7935 HAN, // 2E9B..2EF3
7936 UNKNOWN, // 2EF4..2EFF
7937 HAN, // 2F00..2FD5
7938 UNKNOWN, // 2FD6..2FEF
7939 COMMON, // 2FF0..3004
7940 HAN, // 3005
7941 COMMON, // 3006
7942 HAN, // 3007
7943 COMMON, // 3008..3020
7944 HAN, // 3021..3029
7945 INHERITED, // 302A..302D
7946 HANGUL, // 302E..302F
7947 COMMON, // 3030..3037
7948 HAN, // 3038..303B
7949 COMMON, // 303C..303F
7950 UNKNOWN, // 3040
7951 HIRAGANA, // 3041..3096
7952 UNKNOWN, // 3097..3098
7953 INHERITED, // 3099..309A
7954 COMMON, // 309B..309C
7955 HIRAGANA, // 309D..309F
7956 COMMON, // 30A0
7957 KATAKANA, // 30A1..30FA
7958 COMMON, // 30FB..30FC
7959 KATAKANA, // 30FD..30FF
7960 UNKNOWN, // 3100..3104
7961 BOPOMOFO, // 3105..312F
7962 UNKNOWN, // 3130
7963 HANGUL, // 3131..318E
7964 UNKNOWN, // 318F
7965 COMMON, // 3190..319F
7966 BOPOMOFO, // 31A0..31BF
7967 COMMON, // 31C0..31E5
7968 UNKNOWN, // 31E6..31EE
7969 COMMON, // 31EF
7970 KATAKANA, // 31F0..31FF
7971 HANGUL, // 3200..321E
7972 UNKNOWN, // 321F
7973 COMMON, // 3220..325F
7974 HANGUL, // 3260..327E
7975 COMMON, // 327F..32CF
7976 KATAKANA, // 32D0..32FE
7977 COMMON, // 32FF
7978 KATAKANA, // 3300..3357
7979 COMMON, // 3358..33FF
7980 HAN, // 3400..4DBF
7981 COMMON, // 4DC0..4DFF
7982 HAN, // 4E00..9FFF
7983 YI, // A000..A48C
7984 UNKNOWN, // A48D..A48F
7985 YI, // A490..A4C6
7986 UNKNOWN, // A4C7..A4CF
7987 LISU, // A4D0..A4FF
7988 VAI, // A500..A62B
7989 UNKNOWN, // A62C..A63F
7990 CYRILLIC, // A640..A69F
7991 BAMUM, // A6A0..A6F7
7992 UNKNOWN, // A6F8..A6FF
7993 COMMON, // A700..A721
7994 LATIN, // A722..A787
7995 COMMON, // A788..A78A
7996 LATIN, // A78B..A7CD
7997 UNKNOWN, // A7CE..A7CF
7998 LATIN, // A7D0..A7D1
7999 UNKNOWN, // A7D2
8000 LATIN, // A7D3
8001 UNKNOWN, // A7D4
8002 LATIN, // A7D5..A7DC
8003 UNKNOWN, // A7DD..A7F1
8004 LATIN, // A7F2..A7FF
8005 SYLOTI_NAGRI, // A800..A82C
8006 UNKNOWN, // A82D..A82F
8007 COMMON, // A830..A839
8008 UNKNOWN, // A83A..A83F
8009 PHAGS_PA, // A840..A877
8010 UNKNOWN, // A878..A87F
8011 SAURASHTRA, // A880..A8C5
8012 UNKNOWN, // A8C6..A8CD
8013 SAURASHTRA, // A8CE..A8D9
8014 UNKNOWN, // A8DA..A8DF
8015 DEVANAGARI, // A8E0..A8FF
8016 KAYAH_LI, // A900..A92D
8017 COMMON, // A92E
8018 KAYAH_LI, // A92F
8019 REJANG, // A930..A953
8020 UNKNOWN, // A954..A95E
8021 REJANG, // A95F
8022 HANGUL, // A960..A97C
8023 UNKNOWN, // A97D..A97F
8024 JAVANESE, // A980..A9CD
8025 UNKNOWN, // A9CE
8026 COMMON, // A9CF
8027 JAVANESE, // A9D0..A9D9
8028 UNKNOWN, // A9DA..A9DD
8029 JAVANESE, // A9DE..A9DF
8030 MYANMAR, // A9E0..A9FE
8031 UNKNOWN, // A9FF
8032 CHAM, // AA00..AA36
8033 UNKNOWN, // AA37..AA3F
8034 CHAM, // AA40..AA4D
8035 UNKNOWN, // AA4E..AA4F
8036 CHAM, // AA50..AA59
8037 UNKNOWN, // AA5A..AA5B
8038 CHAM, // AA5C..AA5F
8039 MYANMAR, // AA60..AA7F
8040 TAI_VIET, // AA80..AAC2
8041 UNKNOWN, // AAC3..AADA
8042 TAI_VIET, // AADB..AADF
8043 MEETEI_MAYEK, // AAE0..AAF6
8044 UNKNOWN, // AAF7..AB00
8045 ETHIOPIC, // AB01..AB06
8046 UNKNOWN, // AB07..AB08
8047 ETHIOPIC, // AB09..AB0E
8048 UNKNOWN, // AB0F..AB10
8049 ETHIOPIC, // AB11..AB16
8050 UNKNOWN, // AB17..AB1F
8051 ETHIOPIC, // AB20..AB26
8052 UNKNOWN, // AB27
8053 ETHIOPIC, // AB28..AB2E
8054 UNKNOWN, // AB2F
8055 LATIN, // AB30..AB5A
8056 COMMON, // AB5B
8057 LATIN, // AB5C..AB64
8058 GREEK, // AB65
8059 LATIN, // AB66..AB69
8060 COMMON, // AB6A..AB6B
8061 UNKNOWN, // AB6C..AB6F
8062 CHEROKEE, // AB70..ABBF
8063 MEETEI_MAYEK, // ABC0..ABED
8064 UNKNOWN, // ABEE..ABEF
8065 MEETEI_MAYEK, // ABF0..ABF9
8066 UNKNOWN, // ABFA..ABFF
8067 HANGUL, // AC00..D7A3
8068 UNKNOWN, // D7A4..D7AF
8069 HANGUL, // D7B0..D7C6
8070 UNKNOWN, // D7C7..D7CA
8071 HANGUL, // D7CB..D7FB
8072 UNKNOWN, // D7FC..F8FF
8073 HAN, // F900..FA6D
8074 UNKNOWN, // FA6E..FA6F
8075 HAN, // FA70..FAD9
8076 UNKNOWN, // FADA..FAFF
8077 LATIN, // FB00..FB06
8078 UNKNOWN, // FB07..FB12
8079 ARMENIAN, // FB13..FB17
8080 UNKNOWN, // FB18..FB1C
8081 HEBREW, // FB1D..FB36
8082 UNKNOWN, // FB37
8083 HEBREW, // FB38..FB3C
8084 UNKNOWN, // FB3D
8085 HEBREW, // FB3E
8086 UNKNOWN, // FB3F
8087 HEBREW, // FB40..FB41
8088 UNKNOWN, // FB42
8089 HEBREW, // FB43..FB44
8090 UNKNOWN, // FB45
8091 HEBREW, // FB46..FB4F
8092 ARABIC, // FB50..FBC2
8093 UNKNOWN, // FBC3..FBD2
8094 ARABIC, // FBD3..FD3D
8095 COMMON, // FD3E..FD3F
8096 ARABIC, // FD40..FD8F
8097 UNKNOWN, // FD90..FD91
8098 ARABIC, // FD92..FDC7
8099 UNKNOWN, // FDC8..FDCE
8100 ARABIC, // FDCF
8101 UNKNOWN, // FDD0..FDEF
8102 ARABIC, // FDF0..FDFF
8103 INHERITED, // FE00..FE0F
8104 COMMON, // FE10..FE19
8105 UNKNOWN, // FE1A..FE1F
8106 INHERITED, // FE20..FE2D
8107 CYRILLIC, // FE2E..FE2F
8108 COMMON, // FE30..FE52
8109 UNKNOWN, // FE53
8110 COMMON, // FE54..FE66
8111 UNKNOWN, // FE67
8112 COMMON, // FE68..FE6B
8113 UNKNOWN, // FE6C..FE6F
8114 ARABIC, // FE70..FE74
8115 UNKNOWN, // FE75
8116 ARABIC, // FE76..FEFC
8117 UNKNOWN, // FEFD..FEFE
8118 COMMON, // FEFF
8119 UNKNOWN, // FF00
8120 COMMON, // FF01..FF20
8121 LATIN, // FF21..FF3A
8122 COMMON, // FF3B..FF40
8123 LATIN, // FF41..FF5A
8124 COMMON, // FF5B..FF65
8125 KATAKANA, // FF66..FF6F
8126 COMMON, // FF70
8127 KATAKANA, // FF71..FF9D
8128 COMMON, // FF9E..FF9F
8129 HANGUL, // FFA0..FFBE
8130 UNKNOWN, // FFBF..FFC1
8131 HANGUL, // FFC2..FFC7
8132 UNKNOWN, // FFC8..FFC9
8133 HANGUL, // FFCA..FFCF
8134 UNKNOWN, // FFD0..FFD1
8135 HANGUL, // FFD2..FFD7
8136 UNKNOWN, // FFD8..FFD9
8137 HANGUL, // FFDA..FFDC
8138 UNKNOWN, // FFDD..FFDF
8139 COMMON, // FFE0..FFE6
8140 UNKNOWN, // FFE7
8141 COMMON, // FFE8..FFEE
8142 UNKNOWN, // FFEF..FFF8
8143 COMMON, // FFF9..FFFD
8144 UNKNOWN, // FFFE..FFFF
8145 LINEAR_B, // 10000..1000B
8146 UNKNOWN, // 1000C
8147 LINEAR_B, // 1000D..10026
8148 UNKNOWN, // 10027
8149 LINEAR_B, // 10028..1003A
8150 UNKNOWN, // 1003B
8151 LINEAR_B, // 1003C..1003D
8152 UNKNOWN, // 1003E
8153 LINEAR_B, // 1003F..1004D
8154 UNKNOWN, // 1004E..1004F
8155 LINEAR_B, // 10050..1005D
8156 UNKNOWN, // 1005E..1007F
8157 LINEAR_B, // 10080..100FA
8158 UNKNOWN, // 100FB..100FF
8159 COMMON, // 10100..10102
8160 UNKNOWN, // 10103..10106
8161 COMMON, // 10107..10133
8162 UNKNOWN, // 10134..10136
8163 COMMON, // 10137..1013F
8164 GREEK, // 10140..1018E
8165 UNKNOWN, // 1018F
8166 COMMON, // 10190..1019C
8167 UNKNOWN, // 1019D..1019F
8168 GREEK, // 101A0
8169 UNKNOWN, // 101A1..101CF
8170 COMMON, // 101D0..101FC
8171 INHERITED, // 101FD
8172 UNKNOWN, // 101FE..1027F
8173 LYCIAN, // 10280..1029C
8174 UNKNOWN, // 1029D..1029F
8175 CARIAN, // 102A0..102D0
8176 UNKNOWN, // 102D1..102DF
8177 INHERITED, // 102E0
8178 COMMON, // 102E1..102FB
8179 UNKNOWN, // 102FC..102FF
8180 OLD_ITALIC, // 10300..10323
8181 UNKNOWN, // 10324..1032C
8182 OLD_ITALIC, // 1032D..1032F
8183 GOTHIC, // 10330..1034A
8184 UNKNOWN, // 1034B..1034F
8185 OLD_PERMIC, // 10350..1037A
8186 UNKNOWN, // 1037B..1037F
8187 UGARITIC, // 10380..1039D
8188 UNKNOWN, // 1039E
8189 UGARITIC, // 1039F
8190 OLD_PERSIAN, // 103A0..103C3
8191 UNKNOWN, // 103C4..103C7
8192 OLD_PERSIAN, // 103C8..103D5
8193 UNKNOWN, // 103D6..103FF
8194 DESERET, // 10400..1044F
8195 SHAVIAN, // 10450..1047F
8196 OSMANYA, // 10480..1049D
8197 UNKNOWN, // 1049E..1049F
8198 OSMANYA, // 104A0..104A9
8199 UNKNOWN, // 104AA..104AF
8200 OSAGE, // 104B0..104D3
8201 UNKNOWN, // 104D4..104D7
8202 OSAGE, // 104D8..104FB
8203 UNKNOWN, // 104FC..104FF
8204 ELBASAN, // 10500..10527
8205 UNKNOWN, // 10528..1052F
8206 CAUCASIAN_ALBANIAN, // 10530..10563
8207 UNKNOWN, // 10564..1056E
8208 CAUCASIAN_ALBANIAN, // 1056F
8209 VITHKUQI, // 10570..1057A
8210 UNKNOWN, // 1057B
8211 VITHKUQI, // 1057C..1058A
8212 UNKNOWN, // 1058B
8213 VITHKUQI, // 1058C..10592
8214 UNKNOWN, // 10593
8215 VITHKUQI, // 10594..10595
8216 UNKNOWN, // 10596
8217 VITHKUQI, // 10597..105A1
8218 UNKNOWN, // 105A2
8219 VITHKUQI, // 105A3..105B1
8220 UNKNOWN, // 105B2
8221 VITHKUQI, // 105B3..105B9
8222 UNKNOWN, // 105BA
8223 VITHKUQI, // 105BB..105BC
8224 UNKNOWN, // 105BD..105BF
8225 TODHRI, // 105C0..105F3
8226 UNKNOWN, // 105F4..105FF
8227 LINEAR_A, // 10600..10736
8228 UNKNOWN, // 10737..1073F
8229 LINEAR_A, // 10740..10755
8230 UNKNOWN, // 10756..1075F
8231 LINEAR_A, // 10760..10767
8232 UNKNOWN, // 10768..1077F
8233 LATIN, // 10780..10785
8234 UNKNOWN, // 10786
8235 LATIN, // 10787..107B0
8236 UNKNOWN, // 107B1
8237 LATIN, // 107B2..107BA
8238 UNKNOWN, // 107BB..107FF
8239 CYPRIOT, // 10800..10805
8240 UNKNOWN, // 10806..10807
8241 CYPRIOT, // 10808
8242 UNKNOWN, // 10809
8243 CYPRIOT, // 1080A..10835
8244 UNKNOWN, // 10836
8245 CYPRIOT, // 10837..10838
8246 UNKNOWN, // 10839..1083B
8247 CYPRIOT, // 1083C
8248 UNKNOWN, // 1083D..1083E
8249 CYPRIOT, // 1083F
8250 IMPERIAL_ARAMAIC, // 10840..10855
8251 UNKNOWN, // 10856
8252 IMPERIAL_ARAMAIC, // 10857..1085F
8253 PALMYRENE, // 10860..1087F
8254 NABATAEAN, // 10880..1089E
8255 UNKNOWN, // 1089F..108A6
8256 NABATAEAN, // 108A7..108AF
8257 UNKNOWN, // 108B0..108DF
8258 HATRAN, // 108E0..108F2
8259 UNKNOWN, // 108F3
8260 HATRAN, // 108F4..108F5
8261 UNKNOWN, // 108F6..108FA
8262 HATRAN, // 108FB..108FF
8263 PHOENICIAN, // 10900..1091B
8264 UNKNOWN, // 1091C..1091E
8265 PHOENICIAN, // 1091F
8266 LYDIAN, // 10920..10939
8267 UNKNOWN, // 1093A..1093E
8268 LYDIAN, // 1093F
8269 UNKNOWN, // 10940..1097F
8270 MEROITIC_HIEROGLYPHS, // 10980..1099F
8271 MEROITIC_CURSIVE, // 109A0..109B7
8272 UNKNOWN, // 109B8..109BB
8273 MEROITIC_CURSIVE, // 109BC..109CF
8274 UNKNOWN, // 109D0..109D1
8275 MEROITIC_CURSIVE, // 109D2..109FF
8276 KHAROSHTHI, // 10A00..10A03
8277 UNKNOWN, // 10A04
8278 KHAROSHTHI, // 10A05..10A06
8279 UNKNOWN, // 10A07..10A0B
8280 KHAROSHTHI, // 10A0C..10A13
8281 UNKNOWN, // 10A14
8282 KHAROSHTHI, // 10A15..10A17
8283 UNKNOWN, // 10A18
8284 KHAROSHTHI, // 10A19..10A35
8285 UNKNOWN, // 10A36..10A37
8286 KHAROSHTHI, // 10A38..10A3A
8287 UNKNOWN, // 10A3B..10A3E
8288 KHAROSHTHI, // 10A3F..10A48
8289 UNKNOWN, // 10A49..10A4F
8290 KHAROSHTHI, // 10A50..10A58
8291 UNKNOWN, // 10A59..10A5F
8292 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8293 OLD_NORTH_ARABIAN, // 10A80..10A9F
8294 UNKNOWN, // 10AA0..10ABF
8295 MANICHAEAN, // 10AC0..10AE6
8296 UNKNOWN, // 10AE7..10AEA
8297 MANICHAEAN, // 10AEB..10AF6
8298 UNKNOWN, // 10AF7..10AFF
8299 AVESTAN, // 10B00..10B35
8300 UNKNOWN, // 10B36..10B38
8301 AVESTAN, // 10B39..10B3F
8302 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8303 UNKNOWN, // 10B56..10B57
8304 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8305 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8306 UNKNOWN, // 10B73..10B77
8307 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8308 PSALTER_PAHLAVI, // 10B80..10B91
8309 UNKNOWN, // 10B92..10B98
8310 PSALTER_PAHLAVI, // 10B99..10B9C
8311 UNKNOWN, // 10B9D..10BA8
8312 PSALTER_PAHLAVI, // 10BA9..10BAF
8313 UNKNOWN, // 10BB0..10BFF
8314 OLD_TURKIC, // 10C00..10C48
8315 UNKNOWN, // 10C49..10C7F
8316 OLD_HUNGARIAN, // 10C80..10CB2
8317 UNKNOWN, // 10CB3..10CBF
8318 OLD_HUNGARIAN, // 10CC0..10CF2
8319 UNKNOWN, // 10CF3..10CF9
8320 OLD_HUNGARIAN, // 10CFA..10CFF
8321 HANIFI_ROHINGYA, // 10D00..10D27
8322 UNKNOWN, // 10D28..10D2F
8323 HANIFI_ROHINGYA, // 10D30..10D39
8324 UNKNOWN, // 10D3A..10D3F
8325 GARAY, // 10D40..10D65
8326 UNKNOWN, // 10D66..10D68
8327 GARAY, // 10D69..10D85
8328 UNKNOWN, // 10D86..10D8D
8329 GARAY, // 10D8E..10D8F
8330 UNKNOWN, // 10D90..10E5F
8331 ARABIC, // 10E60..10E7E
8332 UNKNOWN, // 10E7F
8333 YEZIDI, // 10E80..10EA9
8334 UNKNOWN, // 10EAA
8335 YEZIDI, // 10EAB..10EAD
8336 UNKNOWN, // 10EAE..10EAF
8337 YEZIDI, // 10EB0..10EB1
8338 UNKNOWN, // 10EB2..10EC1
8339 ARABIC, // 10EC2..10EC4
8340 UNKNOWN, // 10EC5..10EFB
8341 ARABIC, // 10EFC..10EFF
8342 OLD_SOGDIAN, // 10F00..10F27
8343 UNKNOWN, // 10F28..10F2F
8344 SOGDIAN, // 10F30..10F59
8345 UNKNOWN, // 10F5A..10F6F
8346 OLD_UYGHUR, // 10F70..10F89
8347 UNKNOWN, // 10F8A..10FAF
8348 CHORASMIAN, // 10FB0..10FCB
8349 UNKNOWN, // 10FCC..10FDF
8350 ELYMAIC, // 10FE0..10FF6
8351 UNKNOWN, // 10FF7..10FFF
8352 BRAHMI, // 11000..1104D
8353 UNKNOWN, // 1104E..11051
8354 BRAHMI, // 11052..11075
8355 UNKNOWN, // 11076..1107E
8356 BRAHMI, // 1107F
8357 KAITHI, // 11080..110C2
8358 UNKNOWN, // 110C3..110CC
8359 KAITHI, // 110CD
8360 UNKNOWN, // 110CE..110CF
8361 SORA_SOMPENG, // 110D0..110E8
8362 UNKNOWN, // 110E9..110EF
8363 SORA_SOMPENG, // 110F0..110F9
8364 UNKNOWN, // 110FA..110FF
8365 CHAKMA, // 11100..11134
8366 UNKNOWN, // 11135
8367 CHAKMA, // 11136..11147
8368 UNKNOWN, // 11148..1114F
8369 MAHAJANI, // 11150..11176
8370 UNKNOWN, // 11177..1117F
8371 SHARADA, // 11180..111DF
8372 UNKNOWN, // 111E0
8373 SINHALA, // 111E1..111F4
8374 UNKNOWN, // 111F5..111FF
8375 KHOJKI, // 11200..11211
8376 UNKNOWN, // 11212
8377 KHOJKI, // 11213..11241
8378 UNKNOWN, // 11242..1127F
8379 MULTANI, // 11280..11286
8380 UNKNOWN, // 11287
8381 MULTANI, // 11288
8382 UNKNOWN, // 11289
8383 MULTANI, // 1128A..1128D
8384 UNKNOWN, // 1128E
8385 MULTANI, // 1128F..1129D
8386 UNKNOWN, // 1129E
8387 MULTANI, // 1129F..112A9
8388 UNKNOWN, // 112AA..112AF
8389 KHUDAWADI, // 112B0..112EA
8390 UNKNOWN, // 112EB..112EF
8391 KHUDAWADI, // 112F0..112F9
8392 UNKNOWN, // 112FA..112FF
8393 GRANTHA, // 11300..11303
8394 UNKNOWN, // 11304
8395 GRANTHA, // 11305..1130C
8396 UNKNOWN, // 1130D..1130E
8397 GRANTHA, // 1130F..11310
8398 UNKNOWN, // 11311..11312
8399 GRANTHA, // 11313..11328
8400 UNKNOWN, // 11329
8401 GRANTHA, // 1132A..11330
8402 UNKNOWN, // 11331
8403 GRANTHA, // 11332..11333
8404 UNKNOWN, // 11334
8405 GRANTHA, // 11335..11339
8406 UNKNOWN, // 1133A
8407 INHERITED, // 1133B
8408 GRANTHA, // 1133C..11344
8409 UNKNOWN, // 11345..11346
8410 GRANTHA, // 11347..11348
8411 UNKNOWN, // 11349..1134A
8412 GRANTHA, // 1134B..1134D
8413 UNKNOWN, // 1134E..1134F
8414 GRANTHA, // 11350
8415 UNKNOWN, // 11351..11356
8416 GRANTHA, // 11357
8417 UNKNOWN, // 11358..1135C
8418 GRANTHA, // 1135D..11363
8419 UNKNOWN, // 11364..11365
8420 GRANTHA, // 11366..1136C
8421 UNKNOWN, // 1136D..1136F
8422 GRANTHA, // 11370..11374
8423 UNKNOWN, // 11375..1137F
8424 TULU_TIGALARI, // 11380..11389
8425 UNKNOWN, // 1138A
8426 TULU_TIGALARI, // 1138B
8427 UNKNOWN, // 1138C..1138D
8428 TULU_TIGALARI, // 1138E
8429 UNKNOWN, // 1138F
8430 TULU_TIGALARI, // 11390..113B5
8431 UNKNOWN, // 113B6
8432 TULU_TIGALARI, // 113B7..113C0
8433 UNKNOWN, // 113C1
8434 TULU_TIGALARI, // 113C2
8435 UNKNOWN, // 113C3..113C4
8436 TULU_TIGALARI, // 113C5
8437 UNKNOWN, // 113C6
8438 TULU_TIGALARI, // 113C7..113CA
8439 UNKNOWN, // 113CB
8440 TULU_TIGALARI, // 113CC..113D5
8441 UNKNOWN, // 113D6
8442 TULU_TIGALARI, // 113D7..113D8
8443 UNKNOWN, // 113D9..113E0
8444 TULU_TIGALARI, // 113E1..113E2
8445 UNKNOWN, // 113E3..113FF
8446 NEWA, // 11400..1145B
8447 UNKNOWN, // 1145C
8448 NEWA, // 1145D..11461
8449 UNKNOWN, // 11462..1147F
8450 TIRHUTA, // 11480..114C7
8451 UNKNOWN, // 114C8..114CF
8452 TIRHUTA, // 114D0..114D9
8453 UNKNOWN, // 114DA..1157F
8454 SIDDHAM, // 11580..115B5
8455 UNKNOWN, // 115B6..115B7
8456 SIDDHAM, // 115B8..115DD
8457 UNKNOWN, // 115DE..115FF
8458 MODI, // 11600..11644
8459 UNKNOWN, // 11645..1164F
8460 MODI, // 11650..11659
8461 UNKNOWN, // 1165A..1165F
8462 MONGOLIAN, // 11660..1166C
8463 UNKNOWN, // 1166D..1167F
8464 TAKRI, // 11680..116B9
8465 UNKNOWN, // 116BA..116BF
8466 TAKRI, // 116C0..116C9
8467 UNKNOWN, // 116CA..116CF
8468 MYANMAR, // 116D0..116E3
8469 UNKNOWN, // 116E4..116FF
8470 AHOM, // 11700..1171A
8471 UNKNOWN, // 1171B..1171C
8472 AHOM, // 1171D..1172B
8473 UNKNOWN, // 1172C..1172F
8474 AHOM, // 11730..11746
8475 UNKNOWN, // 11747..117FF
8476 DOGRA, // 11800..1183B
8477 UNKNOWN, // 1183C..1189F
8478 WARANG_CITI, // 118A0..118F2
8479 UNKNOWN, // 118F3..118FE
8480 WARANG_CITI, // 118FF
8481 DIVES_AKURU, // 11900..11906
8482 UNKNOWN, // 11907..11908
8483 DIVES_AKURU, // 11909
8484 UNKNOWN, // 1190A..1190B
8485 DIVES_AKURU, // 1190C..11913
8486 UNKNOWN, // 11914
8487 DIVES_AKURU, // 11915..11916
8488 UNKNOWN, // 11917
8489 DIVES_AKURU, // 11918..11935
8490 UNKNOWN, // 11936
8491 DIVES_AKURU, // 11937..11938
8492 UNKNOWN, // 11939..1193A
8493 DIVES_AKURU, // 1193B..11946
8494 UNKNOWN, // 11947..1194F
8495 DIVES_AKURU, // 11950..11959
8496 UNKNOWN, // 1195A..1199F
8497 NANDINAGARI, // 119A0..119A7
8498 UNKNOWN, // 119A8..119A9
8499 NANDINAGARI, // 119AA..119D7
8500 UNKNOWN, // 119D8..119D9
8501 NANDINAGARI, // 119DA..119E4
8502 UNKNOWN, // 119E5..119FF
8503 ZANABAZAR_SQUARE, // 11A00..11A47
8504 UNKNOWN, // 11A48..11A4F
8505 SOYOMBO, // 11A50..11AA2
8506 UNKNOWN, // 11AA3..11AAF
8507 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8508 PAU_CIN_HAU, // 11AC0..11AF8
8509 UNKNOWN, // 11AF9..11AFF
8510 DEVANAGARI, // 11B00..11B09
8511 UNKNOWN, // 11B0A..11BBF
8512 SUNUWAR, // 11BC0..11BE1
8513 UNKNOWN, // 11BE2..11BEF
8514 SUNUWAR, // 11BF0..11BF9
8515 UNKNOWN, // 11BFA..11BFF
8516 BHAIKSUKI, // 11C00..11C08
8517 UNKNOWN, // 11C09
8518 BHAIKSUKI, // 11C0A..11C36
8519 UNKNOWN, // 11C37
8520 BHAIKSUKI, // 11C38..11C45
8521 UNKNOWN, // 11C46..11C4F
8522 BHAIKSUKI, // 11C50..11C6C
8523 UNKNOWN, // 11C6D..11C6F
8524 MARCHEN, // 11C70..11C8F
8525 UNKNOWN, // 11C90..11C91
8526 MARCHEN, // 11C92..11CA7
8527 UNKNOWN, // 11CA8
8528 MARCHEN, // 11CA9..11CB6
8529 UNKNOWN, // 11CB7..11CFF
8530 MASARAM_GONDI, // 11D00..11D06
8531 UNKNOWN, // 11D07
8532 MASARAM_GONDI, // 11D08..11D09
8533 UNKNOWN, // 11D0A
8534 MASARAM_GONDI, // 11D0B..11D36
8535 UNKNOWN, // 11D37..11D39
8536 MASARAM_GONDI, // 11D3A
8537 UNKNOWN, // 11D3B
8538 MASARAM_GONDI, // 11D3C..11D3D
8539 UNKNOWN, // 11D3E
8540 MASARAM_GONDI, // 11D3F..11D47
8541 UNKNOWN, // 11D48..11D4F
8542 MASARAM_GONDI, // 11D50..11D59
8543 UNKNOWN, // 11D5A..11D5F
8544 GUNJALA_GONDI, // 11D60..11D65
8545 UNKNOWN, // 11D66
8546 GUNJALA_GONDI, // 11D67..11D68
8547 UNKNOWN, // 11D69
8548 GUNJALA_GONDI, // 11D6A..11D8E
8549 UNKNOWN, // 11D8F
8550 GUNJALA_GONDI, // 11D90..11D91
8551 UNKNOWN, // 11D92
8552 GUNJALA_GONDI, // 11D93..11D98
8553 UNKNOWN, // 11D99..11D9F
8554 GUNJALA_GONDI, // 11DA0..11DA9
8555 UNKNOWN, // 11DAA..11EDF
8556 MAKASAR, // 11EE0..11EF8
8557 UNKNOWN, // 11EF9..11EFF
8558 KAWI, // 11F00..11F10
8559 UNKNOWN, // 11F11
8560 KAWI, // 11F12..11F3A
8561 UNKNOWN, // 11F3B..11F3D
8562 KAWI, // 11F3E..11F5A
8563 UNKNOWN, // 11F5B..11FAF
8564 LISU, // 11FB0
8565 UNKNOWN, // 11FB1..11FBF
8566 TAMIL, // 11FC0..11FF1
8567 UNKNOWN, // 11FF2..11FFE
8568 TAMIL, // 11FFF
8569 CUNEIFORM, // 12000..12399
8570 UNKNOWN, // 1239A..123FF
8571 CUNEIFORM, // 12400..1246E
8572 UNKNOWN, // 1246F
8573 CUNEIFORM, // 12470..12474
8574 UNKNOWN, // 12475..1247F
8575 CUNEIFORM, // 12480..12543
8576 UNKNOWN, // 12544..12F8F
8577 CYPRO_MINOAN, // 12F90..12FF2
8578 UNKNOWN, // 12FF3..12FFF
8579 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8580 UNKNOWN, // 13456..1345F
8581 EGYPTIAN_HIEROGLYPHS, // 13460..143FA
8582 UNKNOWN, // 143FB..143FF
8583 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8584 UNKNOWN, // 14647..160FF
8585 GURUNG_KHEMA, // 16100..16139
8586 UNKNOWN, // 1613A..167FF
8587 BAMUM, // 16800..16A38
8588 UNKNOWN, // 16A39..16A3F
8589 MRO, // 16A40..16A5E
8590 UNKNOWN, // 16A5F
8591 MRO, // 16A60..16A69
8592 UNKNOWN, // 16A6A..16A6D
8593 MRO, // 16A6E..16A6F
8594 TANGSA, // 16A70..16ABE
8595 UNKNOWN, // 16ABF
8596 TANGSA, // 16AC0..16AC9
8597 UNKNOWN, // 16ACA..16ACF
8598 BASSA_VAH, // 16AD0..16AED
8599 UNKNOWN, // 16AEE..16AEF
8600 BASSA_VAH, // 16AF0..16AF5
8601 UNKNOWN, // 16AF6..16AFF
8602 PAHAWH_HMONG, // 16B00..16B45
8603 UNKNOWN, // 16B46..16B4F
8604 PAHAWH_HMONG, // 16B50..16B59
8605 UNKNOWN, // 16B5A
8606 PAHAWH_HMONG, // 16B5B..16B61
8607 UNKNOWN, // 16B62
8608 PAHAWH_HMONG, // 16B63..16B77
8609 UNKNOWN, // 16B78..16B7C
8610 PAHAWH_HMONG, // 16B7D..16B8F
8611 UNKNOWN, // 16B90..16D3F
8612 KIRAT_RAI, // 16D40..16D79
8613 UNKNOWN, // 16D7A..16E3F
8614 MEDEFAIDRIN, // 16E40..16E9A
8615 UNKNOWN, // 16E9B..16EFF
8616 MIAO, // 16F00..16F4A
8617 UNKNOWN, // 16F4B..16F4E
8618 MIAO, // 16F4F..16F87
8619 UNKNOWN, // 16F88..16F8E
8620 MIAO, // 16F8F..16F9F
8621 UNKNOWN, // 16FA0..16FDF
8622 TANGUT, // 16FE0
8623 NUSHU, // 16FE1
8624 HAN, // 16FE2..16FE3
8625 KHITAN_SMALL_SCRIPT, // 16FE4
8626 UNKNOWN, // 16FE5..16FEF
8627 HAN, // 16FF0..16FF1
8628 UNKNOWN, // 16FF2..16FFF
8629 TANGUT, // 17000..187F7
8630 UNKNOWN, // 187F8..187FF
8631 TANGUT, // 18800..18AFF
8632 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8633 UNKNOWN, // 18CD6..18CFE
8634 KHITAN_SMALL_SCRIPT, // 18CFF
8635 TANGUT, // 18D00..18D08
8636 UNKNOWN, // 18D09..1AFEF
8637 KATAKANA, // 1AFF0..1AFF3
8638 UNKNOWN, // 1AFF4
8639 KATAKANA, // 1AFF5..1AFFB
8640 UNKNOWN, // 1AFFC
8641 KATAKANA, // 1AFFD..1AFFE
8642 UNKNOWN, // 1AFFF
8643 KATAKANA, // 1B000
8644 HIRAGANA, // 1B001..1B11F
8645 KATAKANA, // 1B120..1B122
8646 UNKNOWN, // 1B123..1B131
8647 HIRAGANA, // 1B132
8648 UNKNOWN, // 1B133..1B14F
8649 HIRAGANA, // 1B150..1B152
8650 UNKNOWN, // 1B153..1B154
8651 KATAKANA, // 1B155
8652 UNKNOWN, // 1B156..1B163
8653 KATAKANA, // 1B164..1B167
8654 UNKNOWN, // 1B168..1B16F
8655 NUSHU, // 1B170..1B2FB
8656 UNKNOWN, // 1B2FC..1BBFF
8657 DUPLOYAN, // 1BC00..1BC6A
8658 UNKNOWN, // 1BC6B..1BC6F
8659 DUPLOYAN, // 1BC70..1BC7C
8660 UNKNOWN, // 1BC7D..1BC7F
8661 DUPLOYAN, // 1BC80..1BC88
8662 UNKNOWN, // 1BC89..1BC8F
8663 DUPLOYAN, // 1BC90..1BC99
8664 UNKNOWN, // 1BC9A..1BC9B
8665 DUPLOYAN, // 1BC9C..1BC9F
8666 COMMON, // 1BCA0..1BCA3
8667 UNKNOWN, // 1BCA4..1CBFF
8668 COMMON, // 1CC00..1CCF9
8669 UNKNOWN, // 1CCFA..1CCFF
8670 COMMON, // 1CD00..1CEB3
8671 UNKNOWN, // 1CEB4..1CEFF
8672 INHERITED, // 1CF00..1CF2D
8673 UNKNOWN, // 1CF2E..1CF2F
8674 INHERITED, // 1CF30..1CF46
8675 UNKNOWN, // 1CF47..1CF4F
8676 COMMON, // 1CF50..1CFC3
8677 UNKNOWN, // 1CFC4..1CFFF
8678 COMMON, // 1D000..1D0F5
8679 UNKNOWN, // 1D0F6..1D0FF
8680 COMMON, // 1D100..1D126
8681 UNKNOWN, // 1D127..1D128
8682 COMMON, // 1D129..1D166
8683 INHERITED, // 1D167..1D169
8684 COMMON, // 1D16A..1D17A
8685 INHERITED, // 1D17B..1D182
8686 COMMON, // 1D183..1D184
8687 INHERITED, // 1D185..1D18B
8688 COMMON, // 1D18C..1D1A9
8689 INHERITED, // 1D1AA..1D1AD
8690 COMMON, // 1D1AE..1D1EA
8691 UNKNOWN, // 1D1EB..1D1FF
8692 GREEK, // 1D200..1D245
8693 UNKNOWN, // 1D246..1D2BF
8694 COMMON, // 1D2C0..1D2D3
8695 UNKNOWN, // 1D2D4..1D2DF
8696 COMMON, // 1D2E0..1D2F3
8697 UNKNOWN, // 1D2F4..1D2FF
8698 COMMON, // 1D300..1D356
8699 UNKNOWN, // 1D357..1D35F
8700 COMMON, // 1D360..1D378
8701 UNKNOWN, // 1D379..1D3FF
8702 COMMON, // 1D400..1D454
8703 UNKNOWN, // 1D455
8704 COMMON, // 1D456..1D49C
8705 UNKNOWN, // 1D49D
8706 COMMON, // 1D49E..1D49F
8707 UNKNOWN, // 1D4A0..1D4A1
8708 COMMON, // 1D4A2
8709 UNKNOWN, // 1D4A3..1D4A4
8710 COMMON, // 1D4A5..1D4A6
8711 UNKNOWN, // 1D4A7..1D4A8
8712 COMMON, // 1D4A9..1D4AC
8713 UNKNOWN, // 1D4AD
8714 COMMON, // 1D4AE..1D4B9
8715 UNKNOWN, // 1D4BA
8716 COMMON, // 1D4BB
8717 UNKNOWN, // 1D4BC
8718 COMMON, // 1D4BD..1D4C3
8719 UNKNOWN, // 1D4C4
8720 COMMON, // 1D4C5..1D505
8721 UNKNOWN, // 1D506
8722 COMMON, // 1D507..1D50A
8723 UNKNOWN, // 1D50B..1D50C
8724 COMMON, // 1D50D..1D514
8725 UNKNOWN, // 1D515
8726 COMMON, // 1D516..1D51C
8727 UNKNOWN, // 1D51D
8728 COMMON, // 1D51E..1D539
8729 UNKNOWN, // 1D53A
8730 COMMON, // 1D53B..1D53E
8731 UNKNOWN, // 1D53F
8732 COMMON, // 1D540..1D544
8733 UNKNOWN, // 1D545
8734 COMMON, // 1D546
8735 UNKNOWN, // 1D547..1D549
8736 COMMON, // 1D54A..1D550
8737 UNKNOWN, // 1D551
8738 COMMON, // 1D552..1D6A5
8739 UNKNOWN, // 1D6A6..1D6A7
8740 COMMON, // 1D6A8..1D7CB
8741 UNKNOWN, // 1D7CC..1D7CD
8742 COMMON, // 1D7CE..1D7FF
8743 SIGNWRITING, // 1D800..1DA8B
8744 UNKNOWN, // 1DA8C..1DA9A
8745 SIGNWRITING, // 1DA9B..1DA9F
8746 UNKNOWN, // 1DAA0
8747 SIGNWRITING, // 1DAA1..1DAAF
8748 UNKNOWN, // 1DAB0..1DEFF
8749 LATIN, // 1DF00..1DF1E
8750 UNKNOWN, // 1DF1F..1DF24
8751 LATIN, // 1DF25..1DF2A
8752 UNKNOWN, // 1DF2B..1DFFF
8753 GLAGOLITIC, // 1E000..1E006
8754 UNKNOWN, // 1E007
8755 GLAGOLITIC, // 1E008..1E018
8756 UNKNOWN, // 1E019..1E01A
8757 GLAGOLITIC, // 1E01B..1E021
8758 UNKNOWN, // 1E022
8759 GLAGOLITIC, // 1E023..1E024
8760 UNKNOWN, // 1E025
8761 GLAGOLITIC, // 1E026..1E02A
8762 UNKNOWN, // 1E02B..1E02F
8763 CYRILLIC, // 1E030..1E06D
8764 UNKNOWN, // 1E06E..1E08E
8765 CYRILLIC, // 1E08F
8766 UNKNOWN, // 1E090..1E0FF
8767 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8768 UNKNOWN, // 1E12D..1E12F
8769 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8770 UNKNOWN, // 1E13E..1E13F
8771 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8772 UNKNOWN, // 1E14A..1E14D
8773 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8774 UNKNOWN, // 1E150..1E28F
8775 TOTO, // 1E290..1E2AE
8776 UNKNOWN, // 1E2AF..1E2BF
8777 WANCHO, // 1E2C0..1E2F9
8778 UNKNOWN, // 1E2FA..1E2FE
8779 WANCHO, // 1E2FF
8780 UNKNOWN, // 1E300..1E4CF
8781 NAG_MUNDARI, // 1E4D0..1E4F9
8782 UNKNOWN, // 1E4FA..1E5CF
8783 OL_ONAL, // 1E5D0..1E5FA
8784 UNKNOWN, // 1E5FB..1E5FE
8785 OL_ONAL, // 1E5FF
8786 UNKNOWN, // 1E600..1E7DF
8787 ETHIOPIC, // 1E7E0..1E7E6
8788 UNKNOWN, // 1E7E7
8789 ETHIOPIC, // 1E7E8..1E7EB
8790 UNKNOWN, // 1E7EC
8791 ETHIOPIC, // 1E7ED..1E7EE
8792 UNKNOWN, // 1E7EF
8793 ETHIOPIC, // 1E7F0..1E7FE
8794 UNKNOWN, // 1E7FF
8795 MENDE_KIKAKUI, // 1E800..1E8C4
8796 UNKNOWN, // 1E8C5..1E8C6
8797 MENDE_KIKAKUI, // 1E8C7..1E8D6
8798 UNKNOWN, // 1E8D7..1E8FF
8799 ADLAM, // 1E900..1E94B
8800 UNKNOWN, // 1E94C..1E94F
8801 ADLAM, // 1E950..1E959
8802 UNKNOWN, // 1E95A..1E95D
8803 ADLAM, // 1E95E..1E95F
8804 UNKNOWN, // 1E960..1EC70
8805 COMMON, // 1EC71..1ECB4
8806 UNKNOWN, // 1ECB5..1ED00
8807 COMMON, // 1ED01..1ED3D
8808 UNKNOWN, // 1ED3E..1EDFF
8809 ARABIC, // 1EE00..1EE03
8810 UNKNOWN, // 1EE04
8811 ARABIC, // 1EE05..1EE1F
8812 UNKNOWN, // 1EE20
8813 ARABIC, // 1EE21..1EE22
8814 UNKNOWN, // 1EE23
8815 ARABIC, // 1EE24
8816 UNKNOWN, // 1EE25..1EE26
8817 ARABIC, // 1EE27
8818 UNKNOWN, // 1EE28
8819 ARABIC, // 1EE29..1EE32
8820 UNKNOWN, // 1EE33
8821 ARABIC, // 1EE34..1EE37
8822 UNKNOWN, // 1EE38
8823 ARABIC, // 1EE39
8824 UNKNOWN, // 1EE3A
8825 ARABIC, // 1EE3B
8826 UNKNOWN, // 1EE3C..1EE41
8827 ARABIC, // 1EE42
8828 UNKNOWN, // 1EE43..1EE46
8829 ARABIC, // 1EE47
8830 UNKNOWN, // 1EE48
8831 ARABIC, // 1EE49
8832 UNKNOWN, // 1EE4A
8833 ARABIC, // 1EE4B
8834 UNKNOWN, // 1EE4C
8835 ARABIC, // 1EE4D..1EE4F
8836 UNKNOWN, // 1EE50
8837 ARABIC, // 1EE51..1EE52
8838 UNKNOWN, // 1EE53
8839 ARABIC, // 1EE54
8840 UNKNOWN, // 1EE55..1EE56
8841 ARABIC, // 1EE57
8842 UNKNOWN, // 1EE58
8843 ARABIC, // 1EE59
8844 UNKNOWN, // 1EE5A
8845 ARABIC, // 1EE5B
8846 UNKNOWN, // 1EE5C
8847 ARABIC, // 1EE5D
8848 UNKNOWN, // 1EE5E
8849 ARABIC, // 1EE5F
8850 UNKNOWN, // 1EE60
8851 ARABIC, // 1EE61..1EE62
8852 UNKNOWN, // 1EE63
8853 ARABIC, // 1EE64
8854 UNKNOWN, // 1EE65..1EE66
8855 ARABIC, // 1EE67..1EE6A
8856 UNKNOWN, // 1EE6B
8857 ARABIC, // 1EE6C..1EE72
8858 UNKNOWN, // 1EE73
8859 ARABIC, // 1EE74..1EE77
8860 UNKNOWN, // 1EE78
8861 ARABIC, // 1EE79..1EE7C
8862 UNKNOWN, // 1EE7D
8863 ARABIC, // 1EE7E
8864 UNKNOWN, // 1EE7F
8865 ARABIC, // 1EE80..1EE89
8866 UNKNOWN, // 1EE8A
8867 ARABIC, // 1EE8B..1EE9B
8868 UNKNOWN, // 1EE9C..1EEA0
8869 ARABIC, // 1EEA1..1EEA3
8870 UNKNOWN, // 1EEA4
8871 ARABIC, // 1EEA5..1EEA9
8872 UNKNOWN, // 1EEAA
8873 ARABIC, // 1EEAB..1EEBB
8874 UNKNOWN, // 1EEBC..1EEEF
8875 ARABIC, // 1EEF0..1EEF1
8876 UNKNOWN, // 1EEF2..1EFFF
8877 COMMON, // 1F000..1F02B
8878 UNKNOWN, // 1F02C..1F02F
8879 COMMON, // 1F030..1F093
8880 UNKNOWN, // 1F094..1F09F
8881 COMMON, // 1F0A0..1F0AE
8882 UNKNOWN, // 1F0AF..1F0B0
8883 COMMON, // 1F0B1..1F0BF
8884 UNKNOWN, // 1F0C0
8885 COMMON, // 1F0C1..1F0CF
8886 UNKNOWN, // 1F0D0
8887 COMMON, // 1F0D1..1F0F5
8888 UNKNOWN, // 1F0F6..1F0FF
8889 COMMON, // 1F100..1F1AD
8890 UNKNOWN, // 1F1AE..1F1E5
8891 COMMON, // 1F1E6..1F1FF
8892 HIRAGANA, // 1F200
8893 COMMON, // 1F201..1F202
8894 UNKNOWN, // 1F203..1F20F
8895 COMMON, // 1F210..1F23B
8896 UNKNOWN, // 1F23C..1F23F
8897 COMMON, // 1F240..1F248
8898 UNKNOWN, // 1F249..1F24F
8899 COMMON, // 1F250..1F251
8900 UNKNOWN, // 1F252..1F25F
8901 COMMON, // 1F260..1F265
8902 UNKNOWN, // 1F266..1F2FF
8903 COMMON, // 1F300..1F6D7
8904 UNKNOWN, // 1F6D8..1F6DB
8905 COMMON, // 1F6DC..1F6EC
8906 UNKNOWN, // 1F6ED..1F6EF
8907 COMMON, // 1F6F0..1F6FC
8908 UNKNOWN, // 1F6FD..1F6FF
8909 COMMON, // 1F700..1F776
8910 UNKNOWN, // 1F777..1F77A
8911 COMMON, // 1F77B..1F7D9
8912 UNKNOWN, // 1F7DA..1F7DF
8913 COMMON, // 1F7E0..1F7EB
8914 UNKNOWN, // 1F7EC..1F7EF
8915 COMMON, // 1F7F0
8916 UNKNOWN, // 1F7F1..1F7FF
8917 COMMON, // 1F800..1F80B
8918 UNKNOWN, // 1F80C..1F80F
8919 COMMON, // 1F810..1F847
8920 UNKNOWN, // 1F848..1F84F
8921 COMMON, // 1F850..1F859
8922 UNKNOWN, // 1F85A..1F85F
8923 COMMON, // 1F860..1F887
8924 UNKNOWN, // 1F888..1F88F
8925 COMMON, // 1F890..1F8AD
8926 UNKNOWN, // 1F8AE..1F8AF
8927 COMMON, // 1F8B0..1F8BB
8928 UNKNOWN, // 1F8BC..1F8BF
8929 COMMON, // 1F8C0..1F8C1
8930 UNKNOWN, // 1F8C2..1F8FF
8931 COMMON, // 1F900..1FA53
8932 UNKNOWN, // 1FA54..1FA5F
8933 COMMON, // 1FA60..1FA6D
8934 UNKNOWN, // 1FA6E..1FA6F
8935 COMMON, // 1FA70..1FA7C
8936 UNKNOWN, // 1FA7D..1FA7F
8937 COMMON, // 1FA80..1FA89
8938 UNKNOWN, // 1FA8A..1FA8E
8939 COMMON, // 1FA8F..1FAC6
8940 UNKNOWN, // 1FAC7..1FACD
8941 COMMON, // 1FACE..1FADC
8942 UNKNOWN, // 1FADD..1FADE
8943 COMMON, // 1FADF..1FAE9
8944 UNKNOWN, // 1FAEA..1FAEF
8945 COMMON, // 1FAF0..1FAF8
8946 UNKNOWN, // 1FAF9..1FAFF
8947 COMMON, // 1FB00..1FB92
8948 UNKNOWN, // 1FB93
8949 COMMON, // 1FB94..1FBF9
8950 UNKNOWN, // 1FBFA..1FFFF
8951 HAN, // 20000..2A6DF
8952 UNKNOWN, // 2A6E0..2A6FF
8953 HAN, // 2A700..2B739
8954 UNKNOWN, // 2B73A..2B73F
8955 HAN, // 2B740..2B81D
8956 UNKNOWN, // 2B81E..2B81F
8957 HAN, // 2B820..2CEA1
8958 UNKNOWN, // 2CEA2..2CEAF
8959 HAN, // 2CEB0..2EBE0
8960 UNKNOWN, // 2EBE1..2EBEF
8961 HAN, // 2EBF0..2EE5D
8962 UNKNOWN, // 2EE5E..2F7FF
8963 HAN, // 2F800..2FA1D
8964 UNKNOWN, // 2FA1E..2FFFF
8965 HAN, // 30000..3134A
8966 UNKNOWN, // 3134B..3134F
8967 HAN, // 31350..323AF
8968 UNKNOWN, // 323B0..E0000
8969 COMMON, // E0001
8970 UNKNOWN, // E0002..E001F
8971 COMMON, // E0020..E007F
8972 UNKNOWN, // E0080..E00FF
8973 INHERITED, // E0100..E01EF
8974 UNKNOWN, // E01F0..10FFFF
8975 };
8976
8977 private static final HashMap<String, Character.UnicodeScript> aliases;
8978 static {
8979 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
8980 aliases.put("ADLM", ADLAM);
8981 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
8982 aliases.put("AHOM", AHOM);
8983 aliases.put("ARAB", ARABIC);
8984 aliases.put("ARMI", IMPERIAL_ARAMAIC);
8985 aliases.put("ARMN", ARMENIAN);
8986 aliases.put("AVST", AVESTAN);
8987 aliases.put("BALI", BALINESE);
8988 aliases.put("BAMU", BAMUM);
8989 aliases.put("BASS", BASSA_VAH);
8990 aliases.put("BATK", BATAK);
8991 aliases.put("BENG", BENGALI);
8992 aliases.put("BHKS", BHAIKSUKI);
8993 aliases.put("BOPO", BOPOMOFO);
8994 aliases.put("BRAH", BRAHMI);
8995 aliases.put("BRAI", BRAILLE);
8996 aliases.put("BUGI", BUGINESE);
8997 aliases.put("BUHD", BUHID);
8998 aliases.put("CAKM", CHAKMA);
8999 aliases.put("CANS", CANADIAN_ABORIGINAL);
9000 aliases.put("CARI", CARIAN);
9001 aliases.put("CHAM", CHAM);
9002 aliases.put("CHER", CHEROKEE);
9003 aliases.put("CHRS", CHORASMIAN);
9004 aliases.put("COPT", COPTIC);
9005 aliases.put("CPMN", CYPRO_MINOAN);
9006 aliases.put("CPRT", CYPRIOT);
9007 aliases.put("CYRL", CYRILLIC);
9008 aliases.put("DEVA", DEVANAGARI);
9009 aliases.put("DIAK", DIVES_AKURU);
9010 aliases.put("DOGR", DOGRA);
9011 aliases.put("DSRT", DESERET);
9012 aliases.put("DUPL", DUPLOYAN);
9013 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
9014 aliases.put("ELBA", ELBASAN);
9015 aliases.put("ELYM", ELYMAIC);
9016 aliases.put("ETHI", ETHIOPIC);
9017 aliases.put("GARA", GARAY);
9018 aliases.put("GEOR", GEORGIAN);
9019 aliases.put("GLAG", GLAGOLITIC);
9020 aliases.put("GONG", GUNJALA_GONDI);
9021 aliases.put("GONM", MASARAM_GONDI);
9022 aliases.put("GOTH", GOTHIC);
9023 aliases.put("GRAN", GRANTHA);
9024 aliases.put("GREK", GREEK);
9025 aliases.put("GUJR", GUJARATI);
9026 aliases.put("GUKH", GURUNG_KHEMA);
9027 aliases.put("GURU", GURMUKHI);
9028 aliases.put("HANG", HANGUL);
9029 aliases.put("HANI", HAN);
9030 aliases.put("HANO", HANUNOO);
9031 aliases.put("HATR", HATRAN);
9032 aliases.put("HEBR", HEBREW);
9033 aliases.put("HIRA", HIRAGANA);
9034 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
9035 aliases.put("HMNG", PAHAWH_HMONG);
9036 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
9037 aliases.put("HUNG", OLD_HUNGARIAN);
9038 aliases.put("ITAL", OLD_ITALIC);
9039 aliases.put("JAVA", JAVANESE);
9040 aliases.put("KALI", KAYAH_LI);
9041 aliases.put("KANA", KATAKANA);
9042 aliases.put("KAWI", KAWI);
9043 aliases.put("KHAR", KHAROSHTHI);
9044 aliases.put("KHMR", KHMER);
9045 aliases.put("KHOJ", KHOJKI);
9046 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
9047 aliases.put("KNDA", KANNADA);
9048 aliases.put("KRAI", KIRAT_RAI);
9049 aliases.put("KTHI", KAITHI);
9050 aliases.put("LANA", TAI_THAM);
9051 aliases.put("LAOO", LAO);
9052 aliases.put("LATN", LATIN);
9053 aliases.put("LEPC", LEPCHA);
9054 aliases.put("LIMB", LIMBU);
9055 aliases.put("LINA", LINEAR_A);
9056 aliases.put("LINB", LINEAR_B);
9057 aliases.put("LISU", LISU);
9058 aliases.put("LYCI", LYCIAN);
9059 aliases.put("LYDI", LYDIAN);
9060 aliases.put("MAHJ", MAHAJANI);
9061 aliases.put("MAKA", MAKASAR);
9062 aliases.put("MAND", MANDAIC);
9063 aliases.put("MANI", MANICHAEAN);
9064 aliases.put("MARC", MARCHEN);
9065 aliases.put("MEDF", MEDEFAIDRIN);
9066 aliases.put("MEND", MENDE_KIKAKUI);
9067 aliases.put("MERC", MEROITIC_CURSIVE);
9068 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
9069 aliases.put("MLYM", MALAYALAM);
9070 aliases.put("MODI", MODI);
9071 aliases.put("MONG", MONGOLIAN);
9072 aliases.put("MROO", MRO);
9073 aliases.put("MTEI", MEETEI_MAYEK);
9074 aliases.put("MULT", MULTANI);
9075 aliases.put("MYMR", MYANMAR);
9076 aliases.put("NAGM", NAG_MUNDARI);
9077 aliases.put("NAND", NANDINAGARI);
9078 aliases.put("NARB", OLD_NORTH_ARABIAN);
9079 aliases.put("NBAT", NABATAEAN);
9080 aliases.put("NEWA", NEWA);
9081 aliases.put("NKOO", NKO);
9082 aliases.put("NSHU", NUSHU);
9083 aliases.put("OGAM", OGHAM);
9084 aliases.put("OLCK", OL_CHIKI);
9085 aliases.put("ONAO", OL_ONAL);
9086 aliases.put("ORKH", OLD_TURKIC);
9087 aliases.put("ORYA", ORIYA);
9088 aliases.put("OSGE", OSAGE);
9089 aliases.put("OSMA", OSMANYA);
9090 aliases.put("OUGR", OLD_UYGHUR);
9091 aliases.put("PALM", PALMYRENE);
9092 aliases.put("PAUC", PAU_CIN_HAU);
9093 aliases.put("PERM", OLD_PERMIC);
9094 aliases.put("PHAG", PHAGS_PA);
9095 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
9096 aliases.put("PHLP", PSALTER_PAHLAVI);
9097 aliases.put("PHNX", PHOENICIAN);
9098 aliases.put("PLRD", MIAO);
9099 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
9100 aliases.put("RJNG", REJANG);
9101 aliases.put("ROHG", HANIFI_ROHINGYA);
9102 aliases.put("RUNR", RUNIC);
9103 aliases.put("SAMR", SAMARITAN);
9104 aliases.put("SARB", OLD_SOUTH_ARABIAN);
9105 aliases.put("SAUR", SAURASHTRA);
9106 aliases.put("SGNW", SIGNWRITING);
9107 aliases.put("SHAW", SHAVIAN);
9108 aliases.put("SHRD", SHARADA);
9109 aliases.put("SIDD", SIDDHAM);
9110 aliases.put("SIND", KHUDAWADI);
9111 aliases.put("SINH", SINHALA);
9112 aliases.put("SOGD", SOGDIAN);
9113 aliases.put("SOGO", OLD_SOGDIAN);
9114 aliases.put("SORA", SORA_SOMPENG);
9115 aliases.put("SOYO", SOYOMBO);
9116 aliases.put("SUND", SUNDANESE);
9117 aliases.put("SUNU", SUNUWAR);
9118 aliases.put("SYLO", SYLOTI_NAGRI);
9119 aliases.put("SYRC", SYRIAC);
9120 aliases.put("TAGB", TAGBANWA);
9121 aliases.put("TAKR", TAKRI);
9122 aliases.put("TALE", TAI_LE);
9123 aliases.put("TALU", NEW_TAI_LUE);
9124 aliases.put("TAML", TAMIL);
9125 aliases.put("TANG", TANGUT);
9126 aliases.put("TAVT", TAI_VIET);
9127 aliases.put("TELU", TELUGU);
9128 aliases.put("TFNG", TIFINAGH);
9129 aliases.put("TGLG", TAGALOG);
9130 aliases.put("THAA", THAANA);
9131 aliases.put("THAI", THAI);
9132 aliases.put("TIBT", TIBETAN);
9133 aliases.put("TIRH", TIRHUTA);
9134 aliases.put("TNSA", TANGSA);
9135 aliases.put("TODR", TODHRI);
9136 aliases.put("TOTO", TOTO);
9137 aliases.put("TUTG", TULU_TIGALARI);
9138 aliases.put("UGAR", UGARITIC);
9139 aliases.put("VAII", VAI);
9140 aliases.put("VITH", VITHKUQI);
9141 aliases.put("WARA", WARANG_CITI);
9142 aliases.put("WCHO", WANCHO);
9143 aliases.put("XPEO", OLD_PERSIAN);
9144 aliases.put("XSUX", CUNEIFORM);
9145 aliases.put("YEZI", YEZIDI);
9146 aliases.put("YIII", YI);
9147 aliases.put("ZANB", ZANABAZAR_SQUARE);
9148 aliases.put("ZINH", INHERITED);
9149 aliases.put("ZYYY", COMMON);
9150 aliases.put("ZZZZ", UNKNOWN);
9151 }
9152
9153 /**
9154 * Returns the enum constant representing the Unicode script of which
9155 * the given character (Unicode code point) is assigned to.
9156 *
9157 * @param codePoint the character (Unicode code point) in question.
9158 * @return The {@code UnicodeScript} constant representing the
9159 * Unicode script of which this character is assigned to.
9160 *
9161 * @throws IllegalArgumentException if the specified
9162 * {@code codePoint} is an invalid Unicode code point.
9163 * @see Character#isValidCodePoint(int)
9164 *
9165 */
9166 public static UnicodeScript of(int codePoint) {
9167 if (!isValidCodePoint(codePoint))
9168 throw new IllegalArgumentException(
9169 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9170 int type = getType(codePoint);
9171 // leave SURROGATE and PRIVATE_USE for table lookup
9172 if (type == UNASSIGNED)
9173 return UNKNOWN;
9174 int index = Arrays.binarySearch(scriptStarts, codePoint);
9175 if (index < 0)
9176 index = -index - 2;
9177 return scripts[index];
9178 }
9179
9180 /**
9181 * Returns the UnicodeScript constant with the given Unicode script
9182 * name or the script name alias. Script names and their aliases are
9183 * determined by The Unicode Standard. The files {@code Scripts.txt}
9184 * and {@code PropertyValueAliases.txt} define script names
9185 * and the script name aliases for a particular version of the
9186 * standard. The {@link Character} class specifies the version of
9187 * the standard that it supports.
9188 * <p>
9189 * Character case is ignored for all of the valid script names.
9190 * The en_US locale's case mapping rules are used to provide
9191 * case-insensitive string comparisons for script name validation.
9192 *
9193 * @param scriptName A {@code UnicodeScript} name.
9194 * @return The {@code UnicodeScript} constant identified
9195 * by {@code scriptName}
9196 * @throws IllegalArgumentException if {@code scriptName} is an
9197 * invalid name
9198 * @throws NullPointerException if {@code scriptName} is null
9199 */
9200 public static final UnicodeScript forName(String scriptName) {
9201 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
9202 //.replace(' ', '_'));
9203 UnicodeScript sc = aliases.get(scriptName);
9204 if (sc != null)
9205 return sc;
9206 return valueOf(scriptName);
9207 }
9208 }
9209
9210 /**
9211 * The value of the {@code Character}.
9212 *
9213 * @serial
9214 */
9215 private final char value;
9216
9217 /** use serialVersionUID from JDK 1.0.2 for interoperability */
9218 @java.io.Serial
9219 private static final long serialVersionUID = 3786198910865385080L;
9220
9221 /**
9222 * Constructs a newly allocated {@code Character} object that
9223 * represents the specified {@code char} value.
9224 *
9225 * @param value the value to be represented by the
9226 * {@code Character} object.
9227 *
9228 * @deprecated
9229 * It is rarely appropriate to use this constructor. The static factory
9230 * {@link #valueOf(char)} is generally a better choice, as it is
9231 * likely to yield significantly better space and time performance.
9232 */
9233 @Deprecated(since="9")
9234 public Character(char value) {
9235 this.value = value;
9236 }
9237
9238 private static final class CharacterCache {
9239 private CharacterCache(){}
9240
9241 @Stable
9242 static final Character[] cache;
9243 static Character[] archivedCache;
9244
9245 static {
9246 int size = 127 + 1;
9247
9248 // Load and use the archived cache if it exists
9249 CDS.initializeFromArchive(CharacterCache.class);
9250 if (archivedCache == null) {
9251 Character[] c = new Character[size];
9252 for (int i = 0; i < size; i++) {
9253 c[i] = new Character((char) i);
9254 }
9255 archivedCache = c;
9256 }
9257 cache = archivedCache;
9258 assert cache.length == size;
9259 }
9260 }
9261
9262 /**
9263 * Returns a {@code Character} instance representing the specified
9264 * {@code char} value.
9265 * If a new {@code Character} instance is not required, this method
9266 * should generally be used in preference to the constructor
9267 * {@link #Character(char)}, as this method is likely to yield
9268 * significantly better space and time performance by caching
9269 * frequently requested values.
9270 *
9271 * This method will always cache values in the range {@code
9272 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9273 * cache other values outside of this range.
9274 *
9275 * @param c a char value.
9276 * @return a {@code Character} instance representing {@code c}.
9277 * @since 1.5
9278 */
9279 @IntrinsicCandidate
9280 public static Character valueOf(char c) {
9281 if (c <= 127) { // must cache
9282 return CharacterCache.cache[(int)c];
9283 }
9284 return new Character(c);
9285 }
9286
9287 /**
9288 * Returns the value of this {@code Character} object.
9289 * @return the primitive {@code char} value represented by
9290 * this object.
9291 */
9292 @IntrinsicCandidate
9293 public char charValue() {
9294 return value;
9295 }
9296
9297 /**
9298 * Returns a hash code for this {@code Character}; equal to the result
9299 * of invoking {@code charValue()}.
9300 *
9301 * @return a hash code value for this {@code Character}
9302 */
9303 @Override
9304 public int hashCode() {
9305 return Character.hashCode(value);
9306 }
9307
9308 /**
9309 * Returns a hash code for a {@code char} value; compatible with
9310 * {@code Character.hashCode()}.
9311 *
9312 * @since 1.8
9313 *
9314 * @param value The {@code char} for which to return a hash code.
9315 * @return a hash code value for a {@code char} value.
9316 */
9317 public static int hashCode(char value) {
9318 return (int)value;
9319 }
9320
9321 /**
9322 * Compares this object against the specified object.
9323 * The result is {@code true} if and only if the argument is not
9324 * {@code null} and is a {@code Character} object that
9325 * represents the same {@code char} value as this object.
9326 *
9327 * @param obj the object to compare with.
9328 * @return {@code true} if the objects are the same;
9329 * {@code false} otherwise.
9330 */
9331 public boolean equals(Object obj) {
9332 if (obj instanceof Character c) {
9333 return value == c.charValue();
9334 }
9335 return false;
9336 }
9337
9338 /**
9339 * Returns a {@code String} object representing this
9340 * {@code Character}'s value. The result is a string of
9341 * length 1 whose sole component is the primitive
9342 * {@code char} value represented by this
9343 * {@code Character} object.
9344 *
9345 * @return a string representation of this object.
9346 */
9347 @Override
9348 public String toString() {
9349 return String.valueOf(value);
9350 }
9351
9352 /**
9353 * Returns a {@code String} object representing the
9354 * specified {@code char}. The result is a string of length
9355 * 1 consisting solely of the specified {@code char}.
9356 *
9357 * @apiNote This method cannot handle <a
9358 * href="#supplementary"> supplementary characters</a>. To support
9359 * all Unicode characters, including supplementary characters, use
9360 * the {@link #toString(int)} method.
9361 *
9362 * @param c the {@code char} to be converted
9363 * @return the string representation of the specified {@code char}
9364 * @since 1.4
9365 */
9366 public static String toString(char c) {
9367 return String.valueOf(c);
9368 }
9369
9370 /**
9371 * Returns a {@code String} object representing the
9372 * specified character (Unicode code point). The result is a string of
9373 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9374 *
9375 * @param codePoint the {@code codePoint} to be converted
9376 * @return the string representation of the specified {@code codePoint}
9377 * @throws IllegalArgumentException if the specified
9378 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9379 * valid Unicode code point}.
9380 * @since 11
9381 */
9382 public static String toString(int codePoint) {
9383 return String.valueOfCodePoint(codePoint);
9384 }
9385
9386 /**
9387 * Determines whether the specified code point is a valid
9388 * <a href="http://www.unicode.org/glossary/#code_point">
9389 * Unicode code point value</a>.
9390 *
9391 * @param codePoint the Unicode code point to be tested
9392 * @return {@code true} if the specified code point value is between
9393 * {@link #MIN_CODE_POINT} and
9394 * {@link #MAX_CODE_POINT} inclusive;
9395 * {@code false} otherwise.
9396 * @since 1.5
9397 */
9398 public static boolean isValidCodePoint(int codePoint) {
9399 // Optimized form of:
9400 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9401 int plane = codePoint >>> 16;
9402 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9403 }
9404
9405 /**
9406 * Determines whether the specified character (Unicode code point)
9407 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9408 * Such code points can be represented using a single {@code char}.
9409 *
9410 * @param codePoint the character (Unicode code point) to be tested
9411 * @return {@code true} if the specified code point is between
9412 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9413 * {@code false} otherwise.
9414 * @since 1.7
9415 */
9416 public static boolean isBmpCodePoint(int codePoint) {
9417 return codePoint >>> 16 == 0;
9418 // Optimized form of:
9419 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9420 // We consistently use logical shift (>>>) to facilitate
9421 // additional runtime optimizations.
9422 }
9423
9424 /**
9425 * Determines whether the specified character (Unicode code point)
9426 * is in the <a href="#supplementary">supplementary character</a> range.
9427 *
9428 * @param codePoint the character (Unicode code point) to be tested
9429 * @return {@code true} if the specified code point is between
9430 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9431 * {@link #MAX_CODE_POINT} inclusive;
9432 * {@code false} otherwise.
9433 * @since 1.5
9434 */
9435 public static boolean isSupplementaryCodePoint(int codePoint) {
9436 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9437 && codePoint < MAX_CODE_POINT + 1;
9438 }
9439
9440 /**
9441 * Determines if the given {@code char} value is a
9442 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9443 * Unicode high-surrogate code unit</a>
9444 * (also known as <i>leading-surrogate code unit</i>).
9445 *
9446 * <p>Such values do not represent characters by themselves,
9447 * but are used in the representation of
9448 * <a href="#supplementary">supplementary characters</a>
9449 * in the UTF-16 encoding.
9450 *
9451 * @param ch the {@code char} value to be tested.
9452 * @return {@code true} if the {@code char} value is between
9453 * {@link #MIN_HIGH_SURROGATE} and
9454 * {@link #MAX_HIGH_SURROGATE} inclusive;
9455 * {@code false} otherwise.
9456 * @see Character#isLowSurrogate(char)
9457 * @see Character.UnicodeBlock#of(int)
9458 * @since 1.5
9459 */
9460 public static boolean isHighSurrogate(char ch) {
9461 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9462 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9463 }
9464
9465 /**
9466 * Determines if the given {@code char} value is a
9467 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9468 * Unicode low-surrogate code unit</a>
9469 * (also known as <i>trailing-surrogate code unit</i>).
9470 *
9471 * <p>Such values do not represent characters by themselves,
9472 * but are used in the representation of
9473 * <a href="#supplementary">supplementary characters</a>
9474 * in the UTF-16 encoding.
9475 *
9476 * @param ch the {@code char} value to be tested.
9477 * @return {@code true} if the {@code char} value is between
9478 * {@link #MIN_LOW_SURROGATE} and
9479 * {@link #MAX_LOW_SURROGATE} inclusive;
9480 * {@code false} otherwise.
9481 * @see Character#isHighSurrogate(char)
9482 * @since 1.5
9483 */
9484 public static boolean isLowSurrogate(char ch) {
9485 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9486 }
9487
9488 /**
9489 * Determines if the given {@code char} value is a Unicode
9490 * <i>surrogate code unit</i>.
9491 *
9492 * <p>Such values do not represent characters by themselves,
9493 * but are used in the representation of
9494 * <a href="#supplementary">supplementary characters</a>
9495 * in the UTF-16 encoding.
9496 *
9497 * <p>A char value is a surrogate code unit if and only if it is either
9498 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9499 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9500 *
9501 * @param ch the {@code char} value to be tested.
9502 * @return {@code true} if the {@code char} value is between
9503 * {@link #MIN_SURROGATE} and
9504 * {@link #MAX_SURROGATE} inclusive;
9505 * {@code false} otherwise.
9506 * @since 1.7
9507 */
9508 public static boolean isSurrogate(char ch) {
9509 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9510 }
9511
9512 /**
9513 * Determines whether the specified pair of {@code char}
9514 * values is a valid
9515 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9516 * Unicode surrogate pair</a>.
9517 *
9518 * <p>This method is equivalent to the expression:
9519 * <blockquote><pre>{@code
9520 * isHighSurrogate(high) && isLowSurrogate(low)
9521 * }</pre></blockquote>
9522 *
9523 * @param high the high-surrogate code value to be tested
9524 * @param low the low-surrogate code value to be tested
9525 * @return {@code true} if the specified high and
9526 * low-surrogate code values represent a valid surrogate pair;
9527 * {@code false} otherwise.
9528 * @since 1.5
9529 */
9530 public static boolean isSurrogatePair(char high, char low) {
9531 return isHighSurrogate(high) && isLowSurrogate(low);
9532 }
9533
9534 /**
9535 * Determines the number of {@code char} values needed to
9536 * represent the specified character (Unicode code point). If the
9537 * specified character is equal to or greater than 0x10000, then
9538 * the method returns 2. Otherwise, the method returns 1.
9539 *
9540 * <p>This method doesn't validate the specified character to be a
9541 * valid Unicode code point. The caller must validate the
9542 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9543 * if necessary.
9544 *
9545 * @param codePoint the character (Unicode code point) to be tested.
9546 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9547 * @see Character#isSupplementaryCodePoint(int)
9548 * @since 1.5
9549 */
9550 public static int charCount(int codePoint) {
9551 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9552 }
9553
9554 /**
9555 * Converts the specified surrogate pair to its supplementary code
9556 * point value. This method does not validate the specified
9557 * surrogate pair. The caller must validate it using {@link
9558 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9559 *
9560 * @param high the high-surrogate code unit
9561 * @param low the low-surrogate code unit
9562 * @return the supplementary code point composed from the
9563 * specified surrogate pair.
9564 * @since 1.5
9565 */
9566 public static int toCodePoint(char high, char low) {
9567 // Optimized form of:
9568 // return ((high - MIN_HIGH_SURROGATE) << 10)
9569 // + (low - MIN_LOW_SURROGATE)
9570 // + MIN_SUPPLEMENTARY_CODE_POINT;
9571 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9572 - (MIN_HIGH_SURROGATE << 10)
9573 - MIN_LOW_SURROGATE);
9574 }
9575
9576 /**
9577 * Returns the code point at the given index of the
9578 * {@code CharSequence}. If the {@code char} value at
9579 * the given index in the {@code CharSequence} is in the
9580 * high-surrogate range, the following index is less than the
9581 * length of the {@code CharSequence}, and the
9582 * {@code char} value at the following index is in the
9583 * low-surrogate range, then the supplementary code point
9584 * corresponding to this surrogate pair is returned. Otherwise,
9585 * the {@code char} value at the given index is returned.
9586 *
9587 * @param seq a sequence of {@code char} values (Unicode code
9588 * units)
9589 * @param index the index to the {@code char} values (Unicode
9590 * code units) in {@code seq} to be converted
9591 * @return the Unicode code point at the given index
9592 * @throws NullPointerException if {@code seq} is null.
9593 * @throws IndexOutOfBoundsException if the value
9594 * {@code index} is negative or not less than
9595 * {@link CharSequence#length() seq.length()}.
9596 * @since 1.5
9597 */
9598 public static int codePointAt(CharSequence seq, int index) {
9599 char c1 = seq.charAt(index);
9600 if (isHighSurrogate(c1) && ++index < seq.length()) {
9601 char c2 = seq.charAt(index);
9602 if (isLowSurrogate(c2)) {
9603 return toCodePoint(c1, c2);
9604 }
9605 }
9606 return c1;
9607 }
9608
9609 /**
9610 * Returns the code point at the given index of the
9611 * {@code char} array. If the {@code char} value at
9612 * the given index in the {@code char} array is in the
9613 * high-surrogate range, the following index is less than the
9614 * length of the {@code char} array, and the
9615 * {@code char} value at the following index is in the
9616 * low-surrogate range, then the supplementary code point
9617 * corresponding to this surrogate pair is returned. Otherwise,
9618 * the {@code char} value at the given index is returned.
9619 *
9620 * @param a the {@code char} array
9621 * @param index the index to the {@code char} values (Unicode
9622 * code units) in the {@code char} array to be converted
9623 * @return the Unicode code point at the given index
9624 * @throws NullPointerException if {@code a} is null.
9625 * @throws IndexOutOfBoundsException if the value
9626 * {@code index} is negative or not less than
9627 * the length of the {@code char} array.
9628 * @since 1.5
9629 */
9630 public static int codePointAt(char[] a, int index) {
9631 return codePointAtImpl(a, index, a.length);
9632 }
9633
9634 /**
9635 * Returns the code point at the given index of the
9636 * {@code char} array, where only array elements with
9637 * {@code index} less than {@code limit} can be used. If
9638 * the {@code char} value at the given index in the
9639 * {@code char} array is in the high-surrogate range, the
9640 * following index is less than the {@code limit}, and the
9641 * {@code char} value at the following index is in the
9642 * low-surrogate range, then the supplementary code point
9643 * corresponding to this surrogate pair is returned. Otherwise,
9644 * the {@code char} value at the given index is returned.
9645 *
9646 * @param a the {@code char} array
9647 * @param index the index to the {@code char} values (Unicode
9648 * code units) in the {@code char} array to be converted
9649 * @param limit the index after the last array element that
9650 * can be used in the {@code char} array
9651 * @return the Unicode code point at the given index
9652 * @throws NullPointerException if {@code a} is null.
9653 * @throws IndexOutOfBoundsException if the {@code index}
9654 * argument is negative or not less than the {@code limit}
9655 * argument, or if the {@code limit} argument is negative or
9656 * greater than the length of the {@code char} array.
9657 * @since 1.5
9658 */
9659 public static int codePointAt(char[] a, int index, int limit) {
9660 if (index >= limit || index < 0 || limit > a.length) {
9661 throw new IndexOutOfBoundsException();
9662 }
9663 return codePointAtImpl(a, index, limit);
9664 }
9665
9666 // throws ArrayIndexOutOfBoundsException if index out of bounds
9667 static int codePointAtImpl(char[] a, int index, int limit) {
9668 char c1 = a[index];
9669 if (isHighSurrogate(c1) && ++index < limit) {
9670 char c2 = a[index];
9671 if (isLowSurrogate(c2)) {
9672 return toCodePoint(c1, c2);
9673 }
9674 }
9675 return c1;
9676 }
9677
9678 /**
9679 * Returns the code point preceding the given index of the
9680 * {@code CharSequence}. If the {@code char} value at
9681 * {@code (index - 1)} in the {@code CharSequence} is in
9682 * the low-surrogate range, {@code (index - 2)} is not
9683 * negative, and the {@code char} value at {@code (index - 2)}
9684 * in the {@code CharSequence} is in the
9685 * high-surrogate range, then the supplementary code point
9686 * corresponding to this surrogate pair is returned. Otherwise,
9687 * the {@code char} value at {@code (index - 1)} is
9688 * returned.
9689 *
9690 * @param seq the {@code CharSequence} instance
9691 * @param index the index following the code point that should be returned
9692 * @return the Unicode code point value before the given index.
9693 * @throws NullPointerException if {@code seq} is null.
9694 * @throws IndexOutOfBoundsException if the {@code index}
9695 * argument is less than 1 or greater than {@link
9696 * CharSequence#length() seq.length()}.
9697 * @since 1.5
9698 */
9699 public static int codePointBefore(CharSequence seq, int index) {
9700 char c2 = seq.charAt(--index);
9701 if (isLowSurrogate(c2) && index > 0) {
9702 char c1 = seq.charAt(--index);
9703 if (isHighSurrogate(c1)) {
9704 return toCodePoint(c1, c2);
9705 }
9706 }
9707 return c2;
9708 }
9709
9710 /**
9711 * Returns the code point preceding the given index of the
9712 * {@code char} array. If the {@code char} value at
9713 * {@code (index - 1)} in the {@code char} array is in
9714 * the low-surrogate range, {@code (index - 2)} is not
9715 * negative, and the {@code char} value at {@code (index - 2)}
9716 * in the {@code char} array is in the
9717 * high-surrogate range, then the supplementary code point
9718 * corresponding to this surrogate pair is returned. Otherwise,
9719 * the {@code char} value at {@code (index - 1)} is
9720 * returned.
9721 *
9722 * @param a the {@code char} array
9723 * @param index the index following the code point that should be returned
9724 * @return the Unicode code point value before the given index.
9725 * @throws NullPointerException if {@code a} is null.
9726 * @throws IndexOutOfBoundsException if the {@code index}
9727 * argument is less than 1 or greater than the length of the
9728 * {@code char} array
9729 * @since 1.5
9730 */
9731 public static int codePointBefore(char[] a, int index) {
9732 return codePointBeforeImpl(a, index, 0);
9733 }
9734
9735 /**
9736 * Returns the code point preceding the given index of the
9737 * {@code char} array, where only array elements with
9738 * {@code index} greater than or equal to {@code start}
9739 * can be used. If the {@code char} value at {@code (index - 1)}
9740 * in the {@code char} array is in the
9741 * low-surrogate range, {@code (index - 2)} is not less than
9742 * {@code start}, and the {@code char} value at
9743 * {@code (index - 2)} in the {@code char} array is in
9744 * the high-surrogate range, then the supplementary code point
9745 * corresponding to this surrogate pair is returned. Otherwise,
9746 * the {@code char} value at {@code (index - 1)} is
9747 * returned.
9748 *
9749 * @param a the {@code char} array
9750 * @param index the index following the code point that should be returned
9751 * @param start the index of the first array element in the
9752 * {@code char} array
9753 * @return the Unicode code point value before the given index.
9754 * @throws NullPointerException if {@code a} is null.
9755 * @throws IndexOutOfBoundsException if the {@code index}
9756 * argument is not greater than the {@code start} argument or
9757 * is greater than the length of the {@code char} array, or
9758 * if the {@code start} argument is negative or not less than
9759 * the length of the {@code char} array.
9760 * @since 1.5
9761 */
9762 public static int codePointBefore(char[] a, int index, int start) {
9763 if (index <= start || start < 0 || index > a.length) {
9764 throw new IndexOutOfBoundsException();
9765 }
9766 return codePointBeforeImpl(a, index, start);
9767 }
9768
9769 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9770 static int codePointBeforeImpl(char[] a, int index, int start) {
9771 char c2 = a[--index];
9772 if (isLowSurrogate(c2) && index > start) {
9773 char c1 = a[--index];
9774 if (isHighSurrogate(c1)) {
9775 return toCodePoint(c1, c2);
9776 }
9777 }
9778 return c2;
9779 }
9780
9781 /**
9782 * Returns the leading surrogate (a
9783 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9784 * high surrogate code unit</a>) of the
9785 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9786 * surrogate pair</a>
9787 * representing the specified supplementary character (Unicode
9788 * code point) in the UTF-16 encoding. If the specified character
9789 * is not a
9790 * <a href="Character.html#supplementary">supplementary character</a>,
9791 * an unspecified {@code char} is returned.
9792 *
9793 * <p>If
9794 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9795 * is {@code true}, then
9796 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9797 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9798 * are also always {@code true}.
9799 *
9800 * @param codePoint a supplementary character (Unicode code point)
9801 * @return the leading surrogate code unit used to represent the
9802 * character in the UTF-16 encoding
9803 * @since 1.7
9804 */
9805 public static char highSurrogate(int codePoint) {
9806 return (char) ((codePoint >>> 10)
9807 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9808 }
9809
9810 /**
9811 * Returns the trailing surrogate (a
9812 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9813 * low surrogate code unit</a>) of the
9814 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9815 * surrogate pair</a>
9816 * representing the specified supplementary character (Unicode
9817 * code point) in the UTF-16 encoding. If the specified character
9818 * is not a
9819 * <a href="Character.html#supplementary">supplementary character</a>,
9820 * an unspecified {@code char} is returned.
9821 *
9822 * <p>If
9823 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9824 * is {@code true}, then
9825 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9826 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9827 * are also always {@code true}.
9828 *
9829 * @param codePoint a supplementary character (Unicode code point)
9830 * @return the trailing surrogate code unit used to represent the
9831 * character in the UTF-16 encoding
9832 * @since 1.7
9833 */
9834 public static char lowSurrogate(int codePoint) {
9835 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
9836 }
9837
9838 /**
9839 * Converts the specified character (Unicode code point) to its
9840 * UTF-16 representation. If the specified code point is a BMP
9841 * (Basic Multilingual Plane or Plane 0) value, the same value is
9842 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
9843 * specified code point is a supplementary character, its
9844 * surrogate values are stored in {@code dst[dstIndex]}
9845 * (high-surrogate) and {@code dst[dstIndex+1]}
9846 * (low-surrogate), and 2 is returned.
9847 *
9848 * @param codePoint the character (Unicode code point) to be converted.
9849 * @param dst an array of {@code char} in which the
9850 * {@code codePoint}'s UTF-16 value is stored.
9851 * @param dstIndex the start index into the {@code dst}
9852 * array where the converted value is stored.
9853 * @return 1 if the code point is a BMP code point, 2 if the
9854 * code point is a supplementary code point.
9855 * @throws IllegalArgumentException if the specified
9856 * {@code codePoint} is not a valid Unicode code point.
9857 * @throws NullPointerException if the specified {@code dst} is null.
9858 * @throws IndexOutOfBoundsException if {@code dstIndex}
9859 * is negative or not less than {@code dst.length}, or if
9860 * {@code dst} at {@code dstIndex} doesn't have enough
9861 * array element(s) to store the resulting {@code char}
9862 * value(s). (If {@code dstIndex} is equal to
9863 * {@code dst.length-1} and the specified
9864 * {@code codePoint} is a supplementary character, the
9865 * high-surrogate value is not stored in
9866 * {@code dst[dstIndex]}.)
9867 * @since 1.5
9868 */
9869 public static int toChars(int codePoint, char[] dst, int dstIndex) {
9870 if (isBmpCodePoint(codePoint)) {
9871 dst[dstIndex] = (char) codePoint;
9872 return 1;
9873 } else if (isValidCodePoint(codePoint)) {
9874 toSurrogates(codePoint, dst, dstIndex);
9875 return 2;
9876 } else {
9877 throw new IllegalArgumentException(
9878 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9879 }
9880 }
9881
9882 /**
9883 * Converts the specified character (Unicode code point) to its
9884 * UTF-16 representation stored in a {@code char} array. If
9885 * the specified code point is a BMP (Basic Multilingual Plane or
9886 * Plane 0) value, the resulting {@code char} array has
9887 * the same value as {@code codePoint}. If the specified code
9888 * point is a supplementary code point, the resulting
9889 * {@code char} array has the corresponding surrogate pair.
9890 *
9891 * @param codePoint a Unicode code point
9892 * @return a {@code char} array having
9893 * {@code codePoint}'s UTF-16 representation.
9894 * @throws IllegalArgumentException if the specified
9895 * {@code codePoint} is not a valid Unicode code point.
9896 * @since 1.5
9897 */
9898 public static char[] toChars(int codePoint) {
9899 if (isBmpCodePoint(codePoint)) {
9900 return new char[] { (char) codePoint };
9901 } else if (isValidCodePoint(codePoint)) {
9902 char[] result = new char[2];
9903 toSurrogates(codePoint, result, 0);
9904 return result;
9905 } else {
9906 throw new IllegalArgumentException(
9907 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9908 }
9909 }
9910
9911 static void toSurrogates(int codePoint, char[] dst, int index) {
9912 // We write elements "backwards" to guarantee all-or-nothing
9913 dst[index+1] = lowSurrogate(codePoint);
9914 dst[index] = highSurrogate(codePoint);
9915 }
9916
9917 /**
9918 * Returns the number of Unicode code points in the text range of
9919 * the specified char sequence. The text range begins at the
9920 * specified {@code beginIndex} and extends to the
9921 * {@code char} at index {@code endIndex - 1}. Thus the
9922 * length (in {@code char}s) of the text range is
9923 * {@code endIndex-beginIndex}. Unpaired surrogates within
9924 * the text range count as one code point each.
9925 *
9926 * @param seq the char sequence
9927 * @param beginIndex the index to the first {@code char} of
9928 * the text range.
9929 * @param endIndex the index after the last {@code char} of
9930 * the text range.
9931 * @return the number of Unicode code points in the specified text
9932 * range
9933 * @throws NullPointerException if {@code seq} is null.
9934 * @throws IndexOutOfBoundsException if the
9935 * {@code beginIndex} is negative, or {@code endIndex}
9936 * is larger than the length of the given sequence, or
9937 * {@code beginIndex} is larger than {@code endIndex}.
9938 * @since 1.5
9939 */
9940 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
9941 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
9942 int n = endIndex - beginIndex;
9943 for (int i = beginIndex; i < endIndex; ) {
9944 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
9945 isLowSurrogate(seq.charAt(i))) {
9946 n--;
9947 i++;
9948 }
9949 }
9950 return n;
9951 }
9952
9953 /**
9954 * Returns the number of Unicode code points in a subarray of the
9955 * {@code char} array argument. The {@code offset}
9956 * argument is the index of the first {@code char} of the
9957 * subarray and the {@code count} argument specifies the
9958 * length of the subarray in {@code char}s. Unpaired
9959 * surrogates within the subarray count as one code point each.
9960 *
9961 * @param a the {@code char} array
9962 * @param offset the index of the first {@code char} in the
9963 * given {@code char} array
9964 * @param count the length of the subarray in {@code char}s
9965 * @return the number of Unicode code points in the specified subarray
9966 * @throws NullPointerException if {@code a} is null.
9967 * @throws IndexOutOfBoundsException if {@code offset} or
9968 * {@code count} is negative, or if {@code offset +
9969 * count} is larger than the length of the given array.
9970 * @since 1.5
9971 */
9972 public static int codePointCount(char[] a, int offset, int count) {
9973 Objects.checkFromIndexSize(offset, count, a.length);
9974 return codePointCountImpl(a, offset, count);
9975 }
9976
9977 static int codePointCountImpl(char[] a, int offset, int count) {
9978 int endIndex = offset + count;
9979 int n = count;
9980 for (int i = offset; i < endIndex; ) {
9981 if (isHighSurrogate(a[i++]) && i < endIndex &&
9982 isLowSurrogate(a[i])) {
9983 n--;
9984 i++;
9985 }
9986 }
9987 return n;
9988 }
9989
9990 /**
9991 * Returns the index within the given char sequence that is offset
9992 * from the given {@code index} by {@code codePointOffset}
9993 * code points. Unpaired surrogates within the text range given by
9994 * {@code index} and {@code codePointOffset} count as
9995 * one code point each.
9996 *
9997 * @param seq the char sequence
9998 * @param index the index to be offset
9999 * @param codePointOffset the offset in code points
10000 * @return the index within the char sequence
10001 * @throws NullPointerException if {@code seq} is null.
10002 * @throws IndexOutOfBoundsException if {@code index}
10003 * is negative or larger than the length of the char sequence,
10004 * or if {@code codePointOffset} is positive and the
10005 * subsequence starting with {@code index} has fewer than
10006 * {@code codePointOffset} code points, or if
10007 * {@code codePointOffset} is negative and the subsequence
10008 * before {@code index} has fewer than the absolute value
10009 * of {@code codePointOffset} code points.
10010 * @since 1.5
10011 */
10012 public static int offsetByCodePoints(CharSequence seq, int index,
10013 int codePointOffset) {
10014 int length = seq.length();
10015 if (index < 0 || index > length) {
10016 throw new IndexOutOfBoundsException();
10017 }
10018
10019 int x = index;
10020 if (codePointOffset >= 0) {
10021 int i;
10022 for (i = 0; x < length && i < codePointOffset; i++) {
10023 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
10024 isLowSurrogate(seq.charAt(x))) {
10025 x++;
10026 }
10027 }
10028 if (i < codePointOffset) {
10029 throw new IndexOutOfBoundsException();
10030 }
10031 } else {
10032 int i;
10033 for (i = codePointOffset; x > 0 && i < 0; i++) {
10034 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
10035 isHighSurrogate(seq.charAt(x-1))) {
10036 x--;
10037 }
10038 }
10039 if (i < 0) {
10040 throw new IndexOutOfBoundsException();
10041 }
10042 }
10043 return x;
10044 }
10045
10046 /**
10047 * Returns the index within the given {@code char} subarray
10048 * that is offset from the given {@code index} by
10049 * {@code codePointOffset} code points. The
10050 * {@code start} and {@code count} arguments specify a
10051 * subarray of the {@code char} array. Unpaired surrogates
10052 * within the text range given by {@code index} and
10053 * {@code codePointOffset} count as one code point each.
10054 *
10055 * @param a the {@code char} array
10056 * @param start the index of the first {@code char} of the
10057 * subarray
10058 * @param count the length of the subarray in {@code char}s
10059 * @param index the index to be offset
10060 * @param codePointOffset the offset in code points
10061 * @return the index within the subarray
10062 * @throws NullPointerException if {@code a} is null.
10063 * @throws IndexOutOfBoundsException
10064 * if {@code start} or {@code count} is negative,
10065 * or if {@code start + count} is larger than the length of
10066 * the given array,
10067 * or if {@code index} is less than {@code start} or
10068 * larger then {@code start + count},
10069 * or if {@code codePointOffset} is positive and the text range
10070 * starting with {@code index} and ending with {@code start + count - 1}
10071 * has fewer than {@code codePointOffset} code
10072 * points,
10073 * or if {@code codePointOffset} is negative and the text range
10074 * starting with {@code start} and ending with {@code index - 1}
10075 * has fewer than the absolute value of
10076 * {@code codePointOffset} code points.
10077 * @since 1.5
10078 */
10079 public static int offsetByCodePoints(char[] a, int start, int count,
10080 int index, int codePointOffset) {
10081 if (count > a.length-start || start < 0 || count < 0
10082 || index < start || index > start+count) {
10083 throw new IndexOutOfBoundsException();
10084 }
10085 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
10086 }
10087
10088 static int offsetByCodePointsImpl(char[]a, int start, int count,
10089 int index, int codePointOffset) {
10090 int x = index;
10091 if (codePointOffset >= 0) {
10092 int limit = start + count;
10093 int i;
10094 for (i = 0; x < limit && i < codePointOffset; i++) {
10095 if (isHighSurrogate(a[x++]) && x < limit &&
10096 isLowSurrogate(a[x])) {
10097 x++;
10098 }
10099 }
10100 if (i < codePointOffset) {
10101 throw new IndexOutOfBoundsException();
10102 }
10103 } else {
10104 int i;
10105 for (i = codePointOffset; x > start && i < 0; i++) {
10106 if (isLowSurrogate(a[--x]) && x > start &&
10107 isHighSurrogate(a[x-1])) {
10108 x--;
10109 }
10110 }
10111 if (i < 0) {
10112 throw new IndexOutOfBoundsException();
10113 }
10114 }
10115 return x;
10116 }
10117
10118 /**
10119 * Determines if the specified character is a lowercase character.
10120 * <p>
10121 * A character is lowercase if its general category type, provided
10122 * by {@code Character.getType(ch)}, is
10123 * {@code LOWERCASE_LETTER}, or it has contributory property
10124 * Other_Lowercase as defined by the Unicode Standard.
10125 * <p>
10126 * The following are examples of lowercase characters:
10127 * <blockquote><pre>
10128 * 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
10129 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10130 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10131 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10132 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10133 * </pre></blockquote>
10134 * <p> Many other Unicode characters are lowercase too.
10135 *
10136 * <p><b>Note:</b> This method cannot handle <a
10137 * href="#supplementary"> supplementary characters</a>. To support
10138 * all Unicode characters, including supplementary characters, use
10139 * the {@link #isLowerCase(int)} method.
10140 *
10141 * @param ch the character to be tested.
10142 * @return {@code true} if the character is lowercase;
10143 * {@code false} otherwise.
10144 * @see Character#isLowerCase(char)
10145 * @see Character#isTitleCase(char)
10146 * @see Character#toLowerCase(char)
10147 * @see Character#getType(char)
10148 */
10149 public static boolean isLowerCase(char ch) {
10150 return isLowerCase((int)ch);
10151 }
10152
10153 /**
10154 * Determines if the specified character (Unicode code point) is a
10155 * lowercase character.
10156 * <p>
10157 * A character is lowercase if its general category type, provided
10158 * by {@link Character#getType getType(codePoint)}, is
10159 * {@code LOWERCASE_LETTER}, or it has contributory property
10160 * Other_Lowercase as defined by the Unicode Standard.
10161 * <p>
10162 * The following are examples of lowercase characters:
10163 * <blockquote><pre>
10164 * 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
10165 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10166 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10167 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10168 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10169 * </pre></blockquote>
10170 * <p> Many other Unicode characters are lowercase too.
10171 *
10172 * @param codePoint the character (Unicode code point) to be tested.
10173 * @return {@code true} if the character is lowercase;
10174 * {@code false} otherwise.
10175 * @see Character#isLowerCase(int)
10176 * @see Character#isTitleCase(int)
10177 * @see Character#toLowerCase(int)
10178 * @see Character#getType(int)
10179 * @since 1.5
10180 */
10181 public static boolean isLowerCase(int codePoint) {
10182 return CharacterData.of(codePoint).isLowerCase(codePoint);
10183 }
10184
10185 /**
10186 * Determines if the specified character is an uppercase character.
10187 * <p>
10188 * A character is uppercase if its general category type, provided by
10189 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
10190 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10191 * <p>
10192 * The following are examples of uppercase characters:
10193 * <blockquote><pre>
10194 * 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
10195 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10196 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10197 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10198 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10199 * </pre></blockquote>
10200 * <p> Many other Unicode characters are uppercase too.
10201 *
10202 * <p><b>Note:</b> This method cannot handle <a
10203 * href="#supplementary"> supplementary characters</a>. To support
10204 * all Unicode characters, including supplementary characters, use
10205 * the {@link #isUpperCase(int)} method.
10206 *
10207 * @param ch the character to be tested.
10208 * @return {@code true} if the character is uppercase;
10209 * {@code false} otherwise.
10210 * @see Character#isLowerCase(char)
10211 * @see Character#isTitleCase(char)
10212 * @see Character#toUpperCase(char)
10213 * @see Character#getType(char)
10214 * @since 1.0
10215 */
10216 public static boolean isUpperCase(char ch) {
10217 return isUpperCase((int)ch);
10218 }
10219
10220 /**
10221 * Determines if the specified character (Unicode code point) is an uppercase character.
10222 * <p>
10223 * A character is uppercase if its general category type, provided by
10224 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
10225 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10226 * <p>
10227 * The following are examples of uppercase characters:
10228 * <blockquote><pre>
10229 * 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
10230 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10231 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10232 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10233 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10234 * </pre></blockquote>
10235 * <p> Many other Unicode characters are uppercase too.
10236 *
10237 * @param codePoint the character (Unicode code point) to be tested.
10238 * @return {@code true} if the character is uppercase;
10239 * {@code false} otherwise.
10240 * @see Character#isLowerCase(int)
10241 * @see Character#isTitleCase(int)
10242 * @see Character#toUpperCase(int)
10243 * @see Character#getType(int)
10244 * @since 1.5
10245 */
10246 public static boolean isUpperCase(int codePoint) {
10247 return CharacterData.of(codePoint).isUpperCase(codePoint);
10248 }
10249
10250 /**
10251 * Determines if the specified character is a titlecase character.
10252 * <p>
10253 * A character is a titlecase character if its general
10254 * category type, provided by {@code Character.getType(ch)},
10255 * is {@code TITLECASE_LETTER}.
10256 * <p>
10257 * Some characters look like pairs of Latin letters. For example, there
10258 * is an uppercase letter that looks like "LJ" and has a corresponding
10259 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10260 * is the appropriate form to use when rendering a word in lowercase
10261 * with initial capitals, as for a book title.
10262 * <p>
10263 * These are some of the Unicode characters for which this method returns
10264 * {@code true}:
10265 * <ul>
10266 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10267 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10268 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10269 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10270 * </ul>
10271 * <p> Many other Unicode characters are titlecase too.
10272 *
10273 * <p><b>Note:</b> This method cannot handle <a
10274 * href="#supplementary"> supplementary characters</a>. To support
10275 * all Unicode characters, including supplementary characters, use
10276 * the {@link #isTitleCase(int)} method.
10277 *
10278 * @param ch the character to be tested.
10279 * @return {@code true} if the character is titlecase;
10280 * {@code false} otherwise.
10281 * @see Character#isLowerCase(char)
10282 * @see Character#isUpperCase(char)
10283 * @see Character#toTitleCase(char)
10284 * @see Character#getType(char)
10285 * @since 1.0.2
10286 */
10287 public static boolean isTitleCase(char ch) {
10288 return isTitleCase((int)ch);
10289 }
10290
10291 /**
10292 * Determines if the specified character (Unicode code point) is a titlecase character.
10293 * <p>
10294 * A character is a titlecase character if its general
10295 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10296 * is {@code TITLECASE_LETTER}.
10297 * <p>
10298 * Some characters look like pairs of Latin letters. For example, there
10299 * is an uppercase letter that looks like "LJ" and has a corresponding
10300 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10301 * is the appropriate form to use when rendering a word in lowercase
10302 * with initial capitals, as for a book title.
10303 * <p>
10304 * These are some of the Unicode characters for which this method returns
10305 * {@code true}:
10306 * <ul>
10307 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10308 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10309 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10310 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10311 * </ul>
10312 * <p> Many other Unicode characters are titlecase too.
10313 *
10314 * @param codePoint the character (Unicode code point) to be tested.
10315 * @return {@code true} if the character is titlecase;
10316 * {@code false} otherwise.
10317 * @see Character#isLowerCase(int)
10318 * @see Character#isUpperCase(int)
10319 * @see Character#toTitleCase(int)
10320 * @see Character#getType(int)
10321 * @since 1.5
10322 */
10323 public static boolean isTitleCase(int codePoint) {
10324 return getType(codePoint) == Character.TITLECASE_LETTER;
10325 }
10326
10327 /**
10328 * Determines if the specified character is a digit.
10329 * <p>
10330 * A character is a digit if its general category type, provided
10331 * by {@code Character.getType(ch)}, is
10332 * {@code DECIMAL_DIGIT_NUMBER}.
10333 * <p>
10334 * Some Unicode character ranges that contain digits:
10335 * <ul>
10336 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10337 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10338 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10339 * Arabic-Indic digits
10340 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10341 * Extended Arabic-Indic digits
10342 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10343 * Devanagari digits
10344 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10345 * Fullwidth digits
10346 * </ul>
10347 *
10348 * Many other character ranges contain digits as well.
10349 *
10350 * <p><b>Note:</b> This method cannot handle <a
10351 * href="#supplementary"> supplementary characters</a>. To support
10352 * all Unicode characters, including supplementary characters, use
10353 * the {@link #isDigit(int)} method.
10354 *
10355 * @param ch the character to be tested.
10356 * @return {@code true} if the character is a digit;
10357 * {@code false} otherwise.
10358 * @see Character#digit(char, int)
10359 * @see Character#forDigit(int, int)
10360 * @see Character#getType(char)
10361 */
10362 public static boolean isDigit(char ch) {
10363 return isDigit((int)ch);
10364 }
10365
10366 /**
10367 * Determines if the specified character (Unicode code point) is a digit.
10368 * <p>
10369 * A character is a digit if its general category type, provided
10370 * by {@link Character#getType(int) getType(codePoint)}, is
10371 * {@code DECIMAL_DIGIT_NUMBER}.
10372 * <p>
10373 * Some Unicode character ranges that contain digits:
10374 * <ul>
10375 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10376 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10377 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10378 * Arabic-Indic digits
10379 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10380 * Extended Arabic-Indic digits
10381 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10382 * Devanagari digits
10383 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10384 * Fullwidth digits
10385 * </ul>
10386 *
10387 * Many other character ranges contain digits as well.
10388 *
10389 * @param codePoint the character (Unicode code point) to be tested.
10390 * @return {@code true} if the character is a digit;
10391 * {@code false} otherwise.
10392 * @see Character#forDigit(int, int)
10393 * @see Character#getType(int)
10394 * @since 1.5
10395 */
10396 public static boolean isDigit(int codePoint) {
10397 return CharacterData.of(codePoint).isDigit(codePoint);
10398 }
10399
10400 /**
10401 * Determines if a character is defined in Unicode.
10402 * <p>
10403 * A character is defined if at least one of the following is true:
10404 * <ul>
10405 * <li>It has an entry in the UnicodeData file.
10406 * <li>It has a value in a range defined by the UnicodeData file.
10407 * </ul>
10408 *
10409 * <p><b>Note:</b> This method cannot handle <a
10410 * href="#supplementary"> supplementary characters</a>. To support
10411 * all Unicode characters, including supplementary characters, use
10412 * the {@link #isDefined(int)} method.
10413 *
10414 * @param ch the character to be tested
10415 * @return {@code true} if the character has a defined meaning
10416 * in Unicode; {@code false} otherwise.
10417 * @see Character#isDigit(char)
10418 * @see Character#isLetter(char)
10419 * @see Character#isLetterOrDigit(char)
10420 * @see Character#isLowerCase(char)
10421 * @see Character#isTitleCase(char)
10422 * @see Character#isUpperCase(char)
10423 * @since 1.0.2
10424 */
10425 public static boolean isDefined(char ch) {
10426 return isDefined((int)ch);
10427 }
10428
10429 /**
10430 * Determines if a character (Unicode code point) is defined in Unicode.
10431 * <p>
10432 * A character is defined if at least one of the following is true:
10433 * <ul>
10434 * <li>It has an entry in the UnicodeData file.
10435 * <li>It has a value in a range defined by the UnicodeData file.
10436 * </ul>
10437 *
10438 * @param codePoint the character (Unicode code point) to be tested.
10439 * @return {@code true} if the character has a defined meaning
10440 * in Unicode; {@code false} otherwise.
10441 * @see Character#isDigit(int)
10442 * @see Character#isLetter(int)
10443 * @see Character#isLetterOrDigit(int)
10444 * @see Character#isLowerCase(int)
10445 * @see Character#isTitleCase(int)
10446 * @see Character#isUpperCase(int)
10447 * @since 1.5
10448 */
10449 public static boolean isDefined(int codePoint) {
10450 return getType(codePoint) != Character.UNASSIGNED;
10451 }
10452
10453 /**
10454 * Determines if the specified character is a letter.
10455 * <p>
10456 * A character is considered to be a letter if its general
10457 * category type, provided by {@code Character.getType(ch)},
10458 * is any of the following:
10459 * <ul>
10460 * <li> {@code UPPERCASE_LETTER}
10461 * <li> {@code LOWERCASE_LETTER}
10462 * <li> {@code TITLECASE_LETTER}
10463 * <li> {@code MODIFIER_LETTER}
10464 * <li> {@code OTHER_LETTER}
10465 * </ul>
10466 *
10467 * Not all letters have case. Many characters are
10468 * letters but are neither uppercase nor lowercase nor titlecase.
10469 *
10470 * <p><b>Note:</b> This method cannot handle <a
10471 * href="#supplementary"> supplementary characters</a>. To support
10472 * all Unicode characters, including supplementary characters, use
10473 * the {@link #isLetter(int)} method.
10474 *
10475 * @param ch the character to be tested.
10476 * @return {@code true} if the character is a letter;
10477 * {@code false} otherwise.
10478 * @see Character#isDigit(char)
10479 * @see Character#isJavaIdentifierStart(char)
10480 * @see Character#isJavaLetter(char)
10481 * @see Character#isJavaLetterOrDigit(char)
10482 * @see Character#isLetterOrDigit(char)
10483 * @see Character#isLowerCase(char)
10484 * @see Character#isTitleCase(char)
10485 * @see Character#isUnicodeIdentifierStart(char)
10486 * @see Character#isUpperCase(char)
10487 */
10488 public static boolean isLetter(char ch) {
10489 return isLetter((int)ch);
10490 }
10491
10492 /**
10493 * Determines if the specified character (Unicode code point) is a letter.
10494 * <p>
10495 * A character is considered to be a letter if its general
10496 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10497 * is any of the following:
10498 * <ul>
10499 * <li> {@code UPPERCASE_LETTER}
10500 * <li> {@code LOWERCASE_LETTER}
10501 * <li> {@code TITLECASE_LETTER}
10502 * <li> {@code MODIFIER_LETTER}
10503 * <li> {@code OTHER_LETTER}
10504 * </ul>
10505 *
10506 * Not all letters have case. Many characters are
10507 * letters but are neither uppercase nor lowercase nor titlecase.
10508 *
10509 * @param codePoint the character (Unicode code point) to be tested.
10510 * @return {@code true} if the character is a letter;
10511 * {@code false} otherwise.
10512 * @see Character#isDigit(int)
10513 * @see Character#isJavaIdentifierStart(int)
10514 * @see Character#isLetterOrDigit(int)
10515 * @see Character#isLowerCase(int)
10516 * @see Character#isTitleCase(int)
10517 * @see Character#isUnicodeIdentifierStart(int)
10518 * @see Character#isUpperCase(int)
10519 * @since 1.5
10520 */
10521 public static boolean isLetter(int codePoint) {
10522 return ((((1 << Character.UPPERCASE_LETTER) |
10523 (1 << Character.LOWERCASE_LETTER) |
10524 (1 << Character.TITLECASE_LETTER) |
10525 (1 << Character.MODIFIER_LETTER) |
10526 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10527 != 0;
10528 }
10529
10530 /**
10531 * Determines if the specified character is a letter or digit.
10532 * <p>
10533 * A character is considered to be a letter or digit if either
10534 * {@code Character.isLetter(char ch)} or
10535 * {@code Character.isDigit(char ch)} returns
10536 * {@code true} for the character.
10537 *
10538 * <p><b>Note:</b> This method cannot handle <a
10539 * href="#supplementary"> supplementary characters</a>. To support
10540 * all Unicode characters, including supplementary characters, use
10541 * the {@link #isLetterOrDigit(int)} method.
10542 *
10543 * @param ch the character to be tested.
10544 * @return {@code true} if the character is a letter or digit;
10545 * {@code false} otherwise.
10546 * @see Character#isDigit(char)
10547 * @see Character#isJavaIdentifierPart(char)
10548 * @see Character#isJavaLetter(char)
10549 * @see Character#isJavaLetterOrDigit(char)
10550 * @see Character#isLetter(char)
10551 * @see Character#isUnicodeIdentifierPart(char)
10552 * @since 1.0.2
10553 */
10554 public static boolean isLetterOrDigit(char ch) {
10555 return isLetterOrDigit((int)ch);
10556 }
10557
10558 /**
10559 * Determines if the specified character (Unicode code point) is a letter or digit.
10560 * <p>
10561 * A character is considered to be a letter or digit if either
10562 * {@link #isLetter(int) isLetter(codePoint)} or
10563 * {@link #isDigit(int) isDigit(codePoint)} returns
10564 * {@code true} for the character.
10565 *
10566 * @param codePoint the character (Unicode code point) to be tested.
10567 * @return {@code true} if the character is a letter or digit;
10568 * {@code false} otherwise.
10569 * @see Character#isDigit(int)
10570 * @see Character#isJavaIdentifierPart(int)
10571 * @see Character#isLetter(int)
10572 * @see Character#isUnicodeIdentifierPart(int)
10573 * @since 1.5
10574 */
10575 public static boolean isLetterOrDigit(int codePoint) {
10576 return ((((1 << Character.UPPERCASE_LETTER) |
10577 (1 << Character.LOWERCASE_LETTER) |
10578 (1 << Character.TITLECASE_LETTER) |
10579 (1 << Character.MODIFIER_LETTER) |
10580 (1 << Character.OTHER_LETTER) |
10581 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10582 != 0;
10583 }
10584
10585 /**
10586 * Determines if the specified character is permissible as the first
10587 * character in a Java identifier.
10588 * <p>
10589 * A character may start a Java identifier if and only if
10590 * one of the following conditions is true:
10591 * <ul>
10592 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10593 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10594 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10595 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10596 * </ul>
10597 *
10598 * @param ch the character to be tested.
10599 * @return {@code true} if the character may start a Java
10600 * identifier; {@code false} otherwise.
10601 * @see Character#isJavaLetterOrDigit(char)
10602 * @see Character#isJavaIdentifierStart(char)
10603 * @see Character#isJavaIdentifierPart(char)
10604 * @see Character#isLetter(char)
10605 * @see Character#isLetterOrDigit(char)
10606 * @see Character#isUnicodeIdentifierStart(char)
10607 * @since 1.0.2
10608 * @deprecated Replaced by isJavaIdentifierStart(char).
10609 */
10610 @Deprecated(since="1.1")
10611 public static boolean isJavaLetter(char ch) {
10612 return isJavaIdentifierStart(ch);
10613 }
10614
10615 /**
10616 * Determines if the specified character may be part of a Java
10617 * identifier as other than the first character.
10618 * <p>
10619 * A character may be part of a Java identifier if and only if one
10620 * of the following conditions is true:
10621 * <ul>
10622 * <li> it is a letter
10623 * <li> it is a currency symbol (such as {@code '$'})
10624 * <li> it is a connecting punctuation character (such as {@code '_'})
10625 * <li> it is a digit
10626 * <li> it is a numeric letter (such as a Roman numeral character)
10627 * <li> it is a combining mark
10628 * <li> it is a non-spacing mark
10629 * <li> {@code isIdentifierIgnorable} returns
10630 * {@code true} for the character.
10631 * </ul>
10632 *
10633 * @param ch the character to be tested.
10634 * @return {@code true} if the character may be part of a
10635 * Java identifier; {@code false} otherwise.
10636 * @see Character#isJavaLetter(char)
10637 * @see Character#isJavaIdentifierStart(char)
10638 * @see Character#isJavaIdentifierPart(char)
10639 * @see Character#isLetter(char)
10640 * @see Character#isLetterOrDigit(char)
10641 * @see Character#isUnicodeIdentifierPart(char)
10642 * @see Character#isIdentifierIgnorable(char)
10643 * @since 1.0.2
10644 * @deprecated Replaced by isJavaIdentifierPart(char).
10645 */
10646 @Deprecated(since="1.1")
10647 public static boolean isJavaLetterOrDigit(char ch) {
10648 return isJavaIdentifierPart(ch);
10649 }
10650
10651 /**
10652 * Determines if the specified character (Unicode code point) is alphabetic.
10653 * <p>
10654 * A character is considered to be alphabetic if its general category type,
10655 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10656 * the following:
10657 * <ul>
10658 * <li> {@code UPPERCASE_LETTER}
10659 * <li> {@code LOWERCASE_LETTER}
10660 * <li> {@code TITLECASE_LETTER}
10661 * <li> {@code MODIFIER_LETTER}
10662 * <li> {@code OTHER_LETTER}
10663 * <li> {@code LETTER_NUMBER}
10664 * </ul>
10665 * or it has contributory property Other_Alphabetic as defined by the
10666 * Unicode Standard.
10667 *
10668 * @param codePoint the character (Unicode code point) to be tested.
10669 * @return {@code true} if the character is a Unicode alphabet
10670 * character, {@code false} otherwise.
10671 * @since 1.7
10672 */
10673 public static boolean isAlphabetic(int codePoint) {
10674 return (((((1 << Character.UPPERCASE_LETTER) |
10675 (1 << Character.LOWERCASE_LETTER) |
10676 (1 << Character.TITLECASE_LETTER) |
10677 (1 << Character.MODIFIER_LETTER) |
10678 (1 << Character.OTHER_LETTER) |
10679 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10680 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10681 }
10682
10683 /**
10684 * Determines if the specified character (Unicode code point) is a CJKV
10685 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10686 * the Unicode Standard.
10687 *
10688 * @param codePoint the character (Unicode code point) to be tested.
10689 * @return {@code true} if the character is a Unicode ideograph
10690 * character, {@code false} otherwise.
10691 * @since 1.7
10692 */
10693 public static boolean isIdeographic(int codePoint) {
10694 return CharacterData.of(codePoint).isIdeographic(codePoint);
10695 }
10696
10697 /**
10698 * Determines if the specified character is
10699 * permissible as the first character in a Java identifier.
10700 * <p>
10701 * A character may start a Java identifier if and only if
10702 * one of the following conditions is true:
10703 * <ul>
10704 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10705 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10706 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10707 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10708 * </ul>
10709 *
10710 * <p><b>Note:</b> This method cannot handle <a
10711 * href="#supplementary"> supplementary characters</a>. To support
10712 * all Unicode characters, including supplementary characters, use
10713 * the {@link #isJavaIdentifierStart(int)} method.
10714 *
10715 * @param ch the character to be tested.
10716 * @return {@code true} if the character may start a Java identifier;
10717 * {@code false} otherwise.
10718 * @see Character#isJavaIdentifierPart(char)
10719 * @see Character#isLetter(char)
10720 * @see Character#isUnicodeIdentifierStart(char)
10721 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10722 * @since 1.1
10723 */
10724 @SuppressWarnings("doclint:reference") // cross-module links
10725 public static boolean isJavaIdentifierStart(char ch) {
10726 return isJavaIdentifierStart((int)ch);
10727 }
10728
10729 /**
10730 * Determines if the character (Unicode code point) is
10731 * permissible as the first character in a Java identifier.
10732 * <p>
10733 * A character may start a Java identifier if and only if
10734 * one of the following conditions is true:
10735 * <ul>
10736 * <li> {@link #isLetter(int) isLetter(codePoint)}
10737 * returns {@code true}
10738 * <li> {@link #getType(int) getType(codePoint)}
10739 * returns {@code LETTER_NUMBER}
10740 * <li> the referenced character is a currency symbol (such as {@code '$'})
10741 * <li> the referenced character is a connecting punctuation character
10742 * (such as {@code '_'}).
10743 * </ul>
10744 *
10745 * @param codePoint the character (Unicode code point) to be tested.
10746 * @return {@code true} if the character may start a Java identifier;
10747 * {@code false} otherwise.
10748 * @see Character#isJavaIdentifierPart(int)
10749 * @see Character#isLetter(int)
10750 * @see Character#isUnicodeIdentifierStart(int)
10751 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10752 * @since 1.5
10753 */
10754 @SuppressWarnings("doclint:reference") // cross-module links
10755 public static boolean isJavaIdentifierStart(int codePoint) {
10756 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10757 }
10758
10759 /**
10760 * Determines if the specified character may be part of a Java
10761 * identifier as other than the first character.
10762 * <p>
10763 * A character may be part of a Java identifier if any of the following
10764 * conditions are true:
10765 * <ul>
10766 * <li> it is a letter
10767 * <li> it is a currency symbol (such as {@code '$'})
10768 * <li> it is a connecting punctuation character (such as {@code '_'})
10769 * <li> it is a digit
10770 * <li> it is a numeric letter (such as a Roman numeral character)
10771 * <li> it is a combining mark
10772 * <li> it is a non-spacing mark
10773 * <li> {@code isIdentifierIgnorable} returns
10774 * {@code true} for the character
10775 * </ul>
10776 *
10777 * <p><b>Note:</b> This method cannot handle <a
10778 * href="#supplementary"> supplementary characters</a>. To support
10779 * all Unicode characters, including supplementary characters, use
10780 * the {@link #isJavaIdentifierPart(int)} method.
10781 *
10782 * @param ch the character to be tested.
10783 * @return {@code true} if the character may be part of a
10784 * Java identifier; {@code false} otherwise.
10785 * @see Character#isIdentifierIgnorable(char)
10786 * @see Character#isJavaIdentifierStart(char)
10787 * @see Character#isLetterOrDigit(char)
10788 * @see Character#isUnicodeIdentifierPart(char)
10789 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10790 * @since 1.1
10791 */
10792 @SuppressWarnings("doclint:reference") // cross-module links
10793 public static boolean isJavaIdentifierPart(char ch) {
10794 return isJavaIdentifierPart((int)ch);
10795 }
10796
10797 /**
10798 * Determines if the character (Unicode code point) may be part of a Java
10799 * identifier as other than the first character.
10800 * <p>
10801 * A character may be part of a Java identifier if any of the following
10802 * conditions are true:
10803 * <ul>
10804 * <li> it is a letter
10805 * <li> it is a currency symbol (such as {@code '$'})
10806 * <li> it is a connecting punctuation character (such as {@code '_'})
10807 * <li> it is a digit
10808 * <li> it is a numeric letter (such as a Roman numeral character)
10809 * <li> it is a combining mark
10810 * <li> it is a non-spacing mark
10811 * <li> {@link #isIdentifierIgnorable(int)
10812 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10813 * the code point
10814 * </ul>
10815 *
10816 * @param codePoint the character (Unicode code point) to be tested.
10817 * @return {@code true} if the character may be part of a
10818 * Java identifier; {@code false} otherwise.
10819 * @see Character#isIdentifierIgnorable(int)
10820 * @see Character#isJavaIdentifierStart(int)
10821 * @see Character#isLetterOrDigit(int)
10822 * @see Character#isUnicodeIdentifierPart(int)
10823 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10824 * @since 1.5
10825 */
10826 @SuppressWarnings("doclint:reference") // cross-module links
10827 public static boolean isJavaIdentifierPart(int codePoint) {
10828 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10829 }
10830
10831 /**
10832 * Determines if the specified character is permissible as the
10833 * first character in a Unicode identifier.
10834 * <p>
10835 * A character may start a Unicode identifier if and only if
10836 * one of the following conditions is true:
10837 * <ul>
10838 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10839 * <li> {@link #getType(char) getType(ch)} returns
10840 * {@code LETTER_NUMBER}.
10841 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10842 * {@code Other_ID_Start}</a> character.
10843 * </ul>
10844 * <p>
10845 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10846 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10847 * with the following profile of UAX31:
10848 * <pre>
10849 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10850 * </pre>
10851 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10852 * compatibility.
10853 *
10854 * <p><b>Note:</b> This method cannot handle <a
10855 * href="#supplementary"> supplementary characters</a>. To support
10856 * all Unicode characters, including supplementary characters, use
10857 * the {@link #isUnicodeIdentifierStart(int)} method.
10858 *
10859 * @param ch the character to be tested.
10860 * @return {@code true} if the character may start a Unicode
10861 * identifier; {@code false} otherwise.
10862 *
10863 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10864 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10865 * @see Character#isJavaIdentifierStart(char)
10866 * @see Character#isLetter(char)
10867 * @see Character#isUnicodeIdentifierPart(char)
10868 * @since 1.1
10869 */
10870 public static boolean isUnicodeIdentifierStart(char ch) {
10871 return isUnicodeIdentifierStart((int)ch);
10872 }
10873
10874 /**
10875 * Determines if the specified character (Unicode code point) is permissible as the
10876 * first character in a Unicode identifier.
10877 * <p>
10878 * A character may start a Unicode identifier if and only if
10879 * one of the following conditions is true:
10880 * <ul>
10881 * <li> {@link #isLetter(int) isLetter(codePoint)}
10882 * returns {@code true}
10883 * <li> {@link #getType(int) getType(codePoint)}
10884 * returns {@code LETTER_NUMBER}.
10885 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10886 * {@code Other_ID_Start}</a> character.
10887 * </ul>
10888 * <p>
10889 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10890 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10891 * with the following profile of UAX31:
10892 * <pre>
10893 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10894 * </pre>
10895 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10896 * compatibility.
10897 *
10898 * @param codePoint the character (Unicode code point) to be tested.
10899 * @return {@code true} if the character may start a Unicode
10900 * identifier; {@code false} otherwise.
10901 *
10902 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10903 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10904 * @see Character#isJavaIdentifierStart(int)
10905 * @see Character#isLetter(int)
10906 * @see Character#isUnicodeIdentifierPart(int)
10907 * @since 1.5
10908 */
10909 public static boolean isUnicodeIdentifierStart(int codePoint) {
10910 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
10911 }
10912
10913 /**
10914 * Determines if the specified character may be part of a Unicode
10915 * identifier as other than the first character.
10916 * <p>
10917 * A character may be part of a Unicode identifier if and only if
10918 * one of the following statements is true:
10919 * <ul>
10920 * <li> it is a letter
10921 * <li> it is a connecting punctuation character (such as {@code '_'})
10922 * <li> it is a digit
10923 * <li> it is a numeric letter (such as a Roman numeral character)
10924 * <li> it is a combining mark
10925 * <li> it is a non-spacing mark
10926 * <li> {@code isIdentifierIgnorable} returns
10927 * {@code true} for this character.
10928 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10929 * {@code Other_ID_Start}</a> character.
10930 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10931 * {@code Other_ID_Continue}</a> character.
10932 * </ul>
10933 * <p>
10934 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10935 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10936 * with the following profile of UAX31:
10937 * <pre>
10938 * Continue := Start + ID_Continue + ignorable
10939 * Medial := empty
10940 * ignorable := isIdentifierIgnorable(char) returns true for the character
10941 * </pre>
10942 * {@code ignorable} is added to {@code Continue} for backward
10943 * compatibility.
10944 *
10945 * <p><b>Note:</b> This method cannot handle <a
10946 * href="#supplementary"> supplementary characters</a>. To support
10947 * all Unicode characters, including supplementary characters, use
10948 * the {@link #isUnicodeIdentifierPart(int)} method.
10949 *
10950 * @param ch the character to be tested.
10951 * @return {@code true} if the character may be part of a
10952 * Unicode identifier; {@code false} otherwise.
10953 *
10954 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10955 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10956 * @see Character#isIdentifierIgnorable(char)
10957 * @see Character#isJavaIdentifierPart(char)
10958 * @see Character#isLetterOrDigit(char)
10959 * @see Character#isUnicodeIdentifierStart(char)
10960 * @since 1.1
10961 */
10962 public static boolean isUnicodeIdentifierPart(char ch) {
10963 return isUnicodeIdentifierPart((int)ch);
10964 }
10965
10966 /**
10967 * Determines if the specified character (Unicode code point) may be part of a Unicode
10968 * identifier as other than the first character.
10969 * <p>
10970 * A character may be part of a Unicode identifier if and only if
10971 * one of the following statements is true:
10972 * <ul>
10973 * <li> it is a letter
10974 * <li> it is a connecting punctuation character (such as {@code '_'})
10975 * <li> it is a digit
10976 * <li> it is a numeric letter (such as a Roman numeral character)
10977 * <li> it is a combining mark
10978 * <li> it is a non-spacing mark
10979 * <li> {@code isIdentifierIgnorable} returns
10980 * {@code true} for this character.
10981 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10982 * {@code Other_ID_Start}</a> character.
10983 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10984 * {@code Other_ID_Continue}</a> character.
10985 * </ul>
10986 * <p>
10987 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10988 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10989 * with the following profile of UAX31:
10990 * <pre>
10991 * Continue := Start + ID_Continue + ignorable
10992 * Medial := empty
10993 * ignorable := isIdentifierIgnorable(int) returns true for the character
10994 * </pre>
10995 * {@code ignorable} is added to {@code Continue} for backward
10996 * compatibility.
10997 *
10998 * @param codePoint the character (Unicode code point) to be tested.
10999 * @return {@code true} if the character may be part of a
11000 * Unicode identifier; {@code false} otherwise.
11001 *
11002 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11003 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11004 * @see Character#isIdentifierIgnorable(int)
11005 * @see Character#isJavaIdentifierPart(int)
11006 * @see Character#isLetterOrDigit(int)
11007 * @see Character#isUnicodeIdentifierStart(int)
11008 * @since 1.5
11009 */
11010 public static boolean isUnicodeIdentifierPart(int codePoint) {
11011 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
11012 }
11013
11014 /**
11015 * Determines if the specified character should be regarded as
11016 * an ignorable character in a Java identifier or a Unicode identifier.
11017 * <p>
11018 * The following Unicode characters are ignorable in a Java identifier
11019 * or a Unicode identifier:
11020 * <ul>
11021 * <li>ISO control characters that are not whitespace
11022 * <ul>
11023 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11024 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11025 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11026 * </ul>
11027 *
11028 * <li>all characters that have the {@code FORMAT} general
11029 * category value
11030 * </ul>
11031 *
11032 * <p><b>Note:</b> This method cannot handle <a
11033 * href="#supplementary"> supplementary characters</a>. To support
11034 * all Unicode characters, including supplementary characters, use
11035 * the {@link #isIdentifierIgnorable(int)} method.
11036 *
11037 * @param ch the character to be tested.
11038 * @return {@code true} if the character is an ignorable control
11039 * character that may be part of a Java or Unicode identifier;
11040 * {@code false} otherwise.
11041 * @see Character#isJavaIdentifierPart(char)
11042 * @see Character#isUnicodeIdentifierPart(char)
11043 * @since 1.1
11044 */
11045 public static boolean isIdentifierIgnorable(char ch) {
11046 return isIdentifierIgnorable((int)ch);
11047 }
11048
11049 /**
11050 * Determines if the specified character (Unicode code point) should be regarded as
11051 * an ignorable character in a Java identifier or a Unicode identifier.
11052 * <p>
11053 * The following Unicode characters are ignorable in a Java identifier
11054 * or a Unicode identifier:
11055 * <ul>
11056 * <li>ISO control characters that are not whitespace
11057 * <ul>
11058 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11059 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11060 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11061 * </ul>
11062 *
11063 * <li>all characters that have the {@code FORMAT} general
11064 * category value
11065 * </ul>
11066 *
11067 * @param codePoint the character (Unicode code point) to be tested.
11068 * @return {@code true} if the character is an ignorable control
11069 * character that may be part of a Java or Unicode identifier;
11070 * {@code false} otherwise.
11071 * @see Character#isJavaIdentifierPart(int)
11072 * @see Character#isUnicodeIdentifierPart(int)
11073 * @since 1.5
11074 */
11075 public static boolean isIdentifierIgnorable(int codePoint) {
11076 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
11077 }
11078
11079 /**
11080 * Determines if the specified character (Unicode code point) is an Emoji.
11081 * <p>
11082 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
11083 * property, defined in
11084 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11085 * Unicode Emoji (Technical Standard #51)</a>.
11086 *
11087 * @param codePoint the character (Unicode code point) to be tested.
11088 * @return {@code true} if the character is an Emoji;
11089 * {@code false} otherwise.
11090 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11091 * @since 21
11092 */
11093 public static boolean isEmoji(int codePoint) {
11094 return CharacterData.of(codePoint).isEmoji(codePoint);
11095 }
11096
11097 /**
11098 * Determines if the specified character (Unicode code point) has the
11099 * Emoji Presentation property by default.
11100 * <p>
11101 * A character is considered to have the Emoji Presentation property if and
11102 * only if it has the {@code Emoji_Presentation} property, defined in
11103 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11104 * Unicode Emoji (Technical Standard #51)</a>.
11105 *
11106 * @param codePoint the character (Unicode code point) to be tested.
11107 * @return {@code true} if the character has the Emoji Presentation
11108 * property; {@code false} otherwise.
11109 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11110 * @since 21
11111 */
11112 public static boolean isEmojiPresentation(int codePoint) {
11113 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
11114 }
11115
11116 /**
11117 * Determines if the specified character (Unicode code point) is an
11118 * Emoji Modifier.
11119 * <p>
11120 * A character is considered to be an Emoji Modifier if and only if it has
11121 * the {@code Emoji_Modifier} property, defined in
11122 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11123 * Unicode Emoji (Technical Standard #51)</a>.
11124 *
11125 * @param codePoint the character (Unicode code point) to be tested.
11126 * @return {@code true} if the character is an Emoji Modifier;
11127 * {@code false} otherwise.
11128 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11129 * @since 21
11130 */
11131 public static boolean isEmojiModifier(int codePoint) {
11132 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
11133 }
11134
11135 /**
11136 * Determines if the specified character (Unicode code point) is an
11137 * Emoji Modifier Base.
11138 * <p>
11139 * A character is considered to be an Emoji Modifier Base if and only if it has
11140 * the {@code Emoji_Modifier_Base} property, defined in
11141 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11142 * Unicode Emoji (Technical Standard #51)</a>.
11143 *
11144 * @param codePoint the character (Unicode code point) to be tested.
11145 * @return {@code true} if the character is an Emoji Modifier Base;
11146 * {@code false} otherwise.
11147 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11148 * @since 21
11149 */
11150 public static boolean isEmojiModifierBase(int codePoint) {
11151 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
11152 }
11153
11154 /**
11155 * Determines if the specified character (Unicode code point) is an
11156 * Emoji Component.
11157 * <p>
11158 * A character is considered to be an Emoji Component if and only if it has
11159 * the {@code Emoji_Component} property, defined in
11160 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11161 * Unicode Emoji (Technical Standard #51)</a>.
11162 *
11163 * @param codePoint the character (Unicode code point) to be tested.
11164 * @return {@code true} if the character is an Emoji Component;
11165 * {@code false} otherwise.
11166 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11167 * @since 21
11168 */
11169 public static boolean isEmojiComponent(int codePoint) {
11170 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
11171 }
11172
11173 /**
11174 * Determines if the specified character (Unicode code point) is
11175 * an Extended Pictographic.
11176 * <p>
11177 * A character is considered to be an Extended Pictographic if and only if it has
11178 * the {@code Extended_Pictographic} property, defined in
11179 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11180 * Unicode Emoji (Technical Standard #51)</a>.
11181 *
11182 * @param codePoint the character (Unicode code point) to be tested.
11183 * @return {@code true} if the character is an Extended Pictographic;
11184 * {@code false} otherwise.
11185 * @spec https://unicode.org/reports/tr51/ Unicode Emoji
11186 * @since 21
11187 */
11188 public static boolean isExtendedPictographic(int codePoint) {
11189 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
11190 }
11191
11192 /**
11193 * Converts the character argument to lowercase using case
11194 * mapping information from the UnicodeData file.
11195 * <p>
11196 * Note that
11197 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
11198 * does not always return {@code true} for some ranges of
11199 * characters, particularly those that are symbols or ideographs.
11200 *
11201 * <p>In general, {@link String#toLowerCase()} should be used to map
11202 * characters to lowercase. {@code String} case mapping methods
11203 * have several benefits over {@code Character} case mapping methods.
11204 * {@code String} case mapping methods can perform locale-sensitive
11205 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11206 * the {@code Character} case mapping methods cannot.
11207 *
11208 * <p><b>Note:</b> This method cannot handle <a
11209 * href="#supplementary"> supplementary characters</a>. To support
11210 * all Unicode characters, including supplementary characters, use
11211 * the {@link #toLowerCase(int)} method.
11212 *
11213 * @param ch the character to be converted.
11214 * @return the lowercase equivalent of the character, if any;
11215 * otherwise, the character itself.
11216 * @see Character#isLowerCase(char)
11217 * @see String#toLowerCase()
11218 */
11219 public static char toLowerCase(char ch) {
11220 return (char)toLowerCase((int)ch);
11221 }
11222
11223 /**
11224 * Converts the character (Unicode code point) argument to
11225 * lowercase using case mapping information from the UnicodeData
11226 * file.
11227 *
11228 * <p> Note that
11229 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
11230 * does not always return {@code true} for some ranges of
11231 * characters, particularly those that are symbols or ideographs.
11232 *
11233 * <p>In general, {@link String#toLowerCase()} should be used to map
11234 * characters to lowercase. {@code String} case mapping methods
11235 * have several benefits over {@code Character} case mapping methods.
11236 * {@code String} case mapping methods can perform locale-sensitive
11237 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11238 * the {@code Character} case mapping methods cannot.
11239 *
11240 * @param codePoint the character (Unicode code point) to be converted.
11241 * @return the lowercase equivalent of the character (Unicode code
11242 * point), if any; otherwise, the character itself.
11243 * @see Character#isLowerCase(int)
11244 * @see String#toLowerCase()
11245 *
11246 * @since 1.5
11247 */
11248 public static int toLowerCase(int codePoint) {
11249 return CharacterData.of(codePoint).toLowerCase(codePoint);
11250 }
11251
11252 /**
11253 * Converts the character argument to uppercase using case mapping
11254 * information from the UnicodeData file.
11255 * <p>
11256 * Note that
11257 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
11258 * does not always return {@code true} for some ranges of
11259 * characters, particularly those that are symbols or ideographs.
11260 *
11261 * <p>In general, {@link String#toUpperCase()} should be used to map
11262 * characters to uppercase. {@code String} case mapping methods
11263 * have several benefits over {@code Character} case mapping methods.
11264 * {@code String} case mapping methods can perform locale-sensitive
11265 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11266 * the {@code Character} case mapping methods cannot.
11267 *
11268 * <p><b>Note:</b> This method cannot handle <a
11269 * href="#supplementary"> supplementary characters</a>. To support
11270 * all Unicode characters, including supplementary characters, use
11271 * the {@link #toUpperCase(int)} method.
11272 *
11273 * @param ch the character to be converted.
11274 * @return the uppercase equivalent of the character, if any;
11275 * otherwise, the character itself.
11276 * @see Character#isUpperCase(char)
11277 * @see String#toUpperCase()
11278 */
11279 public static char toUpperCase(char ch) {
11280 return (char)toUpperCase((int)ch);
11281 }
11282
11283 /**
11284 * Converts the character (Unicode code point) argument to
11285 * uppercase using case mapping information from the UnicodeData
11286 * file.
11287 *
11288 * <p>Note that
11289 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11290 * does not always return {@code true} for some ranges of
11291 * characters, particularly those that are symbols or ideographs.
11292 *
11293 * <p>In general, {@link String#toUpperCase()} should be used to map
11294 * characters to uppercase. {@code String} case mapping methods
11295 * have several benefits over {@code Character} case mapping methods.
11296 * {@code String} case mapping methods can perform locale-sensitive
11297 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11298 * the {@code Character} case mapping methods cannot.
11299 *
11300 * @param codePoint the character (Unicode code point) to be converted.
11301 * @return the uppercase equivalent of the character, if any;
11302 * otherwise, the character itself.
11303 * @see Character#isUpperCase(int)
11304 * @see String#toUpperCase()
11305 *
11306 * @since 1.5
11307 */
11308 public static int toUpperCase(int codePoint) {
11309 return CharacterData.of(codePoint).toUpperCase(codePoint);
11310 }
11311
11312 /**
11313 * Converts the character argument to titlecase using case mapping
11314 * information from the UnicodeData file. If a character has no
11315 * explicit titlecase mapping and is not itself a titlecase char
11316 * according to UnicodeData, then the uppercase mapping is
11317 * returned as an equivalent titlecase mapping. If the
11318 * {@code char} argument is already a titlecase
11319 * {@code char}, the same {@code char} value will be
11320 * returned.
11321 * <p>
11322 * Note that
11323 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11324 * does not always return {@code true} for some ranges of
11325 * characters.
11326 *
11327 * <p><b>Note:</b> This method cannot handle <a
11328 * href="#supplementary"> supplementary characters</a>. To support
11329 * all Unicode characters, including supplementary characters, use
11330 * the {@link #toTitleCase(int)} method.
11331 *
11332 * @param ch the character to be converted.
11333 * @return the titlecase equivalent of the character, if any;
11334 * otherwise, the character itself.
11335 * @see Character#isTitleCase(char)
11336 * @see Character#toLowerCase(char)
11337 * @see Character#toUpperCase(char)
11338 * @since 1.0.2
11339 */
11340 public static char toTitleCase(char ch) {
11341 return (char)toTitleCase((int)ch);
11342 }
11343
11344 /**
11345 * Converts the character (Unicode code point) argument to titlecase using case mapping
11346 * information from the UnicodeData file. If a character has no
11347 * explicit titlecase mapping and is not itself a titlecase char
11348 * according to UnicodeData, then the uppercase mapping is
11349 * returned as an equivalent titlecase mapping. If the
11350 * character argument is already a titlecase
11351 * character, the same character value will be
11352 * returned.
11353 *
11354 * <p>Note that
11355 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11356 * does not always return {@code true} for some ranges of
11357 * characters.
11358 *
11359 * @param codePoint the character (Unicode code point) to be converted.
11360 * @return the titlecase equivalent of the character, if any;
11361 * otherwise, the character itself.
11362 * @see Character#isTitleCase(int)
11363 * @see Character#toLowerCase(int)
11364 * @see Character#toUpperCase(int)
11365 * @since 1.5
11366 */
11367 public static int toTitleCase(int codePoint) {
11368 return CharacterData.of(codePoint).toTitleCase(codePoint);
11369 }
11370
11371 /**
11372 * Returns the numeric value of the character {@code ch} in the
11373 * specified radix.
11374 * <p>
11375 * If the radix is not in the range {@code MIN_RADIX} ≤
11376 * {@code radix} ≤ {@code MAX_RADIX} or if the
11377 * value of {@code ch} is not a valid digit in the specified
11378 * radix, {@code -1} is returned. A character is a valid digit
11379 * if at least one of the following is true:
11380 * <ul>
11381 * <li>The method {@code isDigit} is {@code true} of the character
11382 * and the Unicode decimal digit value of the character (or its
11383 * single-character decomposition) is less than the specified radix.
11384 * In this case the decimal digit value is returned.
11385 * <li>The character is one of the uppercase Latin letters
11386 * {@code 'A'} through {@code 'Z'} and its code is less than
11387 * {@code radix + 'A' - 10}.
11388 * In this case, {@code ch - 'A' + 10}
11389 * is returned.
11390 * <li>The character is one of the lowercase Latin letters
11391 * {@code 'a'} through {@code 'z'} and its code is less than
11392 * {@code radix + 'a' - 10}.
11393 * In this case, {@code ch - 'a' + 10}
11394 * is returned.
11395 * <li>The character is one of the fullwidth uppercase Latin letters A
11396 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11397 * and its code is less than
11398 * {@code radix + '\u005CuFF21' - 10}.
11399 * In this case, {@code ch - '\u005CuFF21' + 10}
11400 * is returned.
11401 * <li>The character is one of the fullwidth lowercase Latin letters a
11402 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11403 * and its code is less than
11404 * {@code radix + '\u005CuFF41' - 10}.
11405 * In this case, {@code ch - '\u005CuFF41' + 10}
11406 * is returned.
11407 * </ul>
11408 *
11409 * <p><b>Note:</b> This method cannot handle <a
11410 * href="#supplementary"> supplementary characters</a>. To support
11411 * all Unicode characters, including supplementary characters, use
11412 * the {@link #digit(int, int)} method.
11413 *
11414 * @param ch the character to be converted.
11415 * @param radix the radix.
11416 * @return the numeric value represented by the character in the
11417 * specified radix.
11418 * @see Character#forDigit(int, int)
11419 * @see Character#isDigit(char)
11420 */
11421 public static int digit(char ch, int radix) {
11422 return digit((int)ch, radix);
11423 }
11424
11425 /**
11426 * Returns the numeric value of the specified character (Unicode
11427 * code point) in the specified radix.
11428 *
11429 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11430 * {@code radix} ≤ {@code MAX_RADIX} or if the
11431 * character is not a valid digit in the specified
11432 * radix, {@code -1} is returned. A character is a valid digit
11433 * if at least one of the following is true:
11434 * <ul>
11435 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11436 * and the Unicode decimal digit value of the character (or its
11437 * single-character decomposition) is less than the specified radix.
11438 * In this case the decimal digit value is returned.
11439 * <li>The character is one of the uppercase Latin letters
11440 * {@code 'A'} through {@code 'Z'} and its code is less than
11441 * {@code radix + 'A' - 10}.
11442 * In this case, {@code codePoint - 'A' + 10}
11443 * is returned.
11444 * <li>The character is one of the lowercase Latin letters
11445 * {@code 'a'} through {@code 'z'} and its code is less than
11446 * {@code radix + 'a' - 10}.
11447 * In this case, {@code codePoint - 'a' + 10}
11448 * is returned.
11449 * <li>The character is one of the fullwidth uppercase Latin letters A
11450 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11451 * and its code is less than
11452 * {@code radix + '\u005CuFF21' - 10}.
11453 * In this case,
11454 * {@code codePoint - '\u005CuFF21' + 10}
11455 * is returned.
11456 * <li>The character is one of the fullwidth lowercase Latin letters a
11457 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11458 * and its code is less than
11459 * {@code radix + '\u005CuFF41'- 10}.
11460 * In this case,
11461 * {@code codePoint - '\u005CuFF41' + 10}
11462 * is returned.
11463 * </ul>
11464 *
11465 * @param codePoint the character (Unicode code point) to be converted.
11466 * @param radix the radix.
11467 * @return the numeric value represented by the character in the
11468 * specified radix.
11469 * @see Character#forDigit(int, int)
11470 * @see Character#isDigit(int)
11471 * @since 1.5
11472 */
11473 public static int digit(int codePoint, int radix) {
11474 return CharacterData.of(codePoint).digit(codePoint, radix);
11475 }
11476
11477 /**
11478 * Returns the {@code int} value that the specified Unicode
11479 * character represents. For example, the character
11480 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11481 * an int with a value of 50.
11482 * <p>
11483 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11484 * {@code '\u005Cu005A'}), lowercase
11485 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11486 * full width variant ({@code '\u005CuFF21'} through
11487 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11488 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11489 * through 35. This is independent of the Unicode specification,
11490 * which does not assign numeric values to these {@code char}
11491 * values.
11492 * <p>
11493 * If the character does not have a numeric value, then -1 is returned.
11494 * If the character has a numeric value that cannot be represented as a
11495 * nonnegative integer (for example, a fractional value), then -2
11496 * is returned.
11497 *
11498 * <p><b>Note:</b> This method cannot handle <a
11499 * href="#supplementary"> supplementary characters</a>. To support
11500 * all Unicode characters, including supplementary characters, use
11501 * the {@link #getNumericValue(int)} method.
11502 *
11503 * @param ch the character to be converted.
11504 * @return the numeric value of the character, as a nonnegative {@code int}
11505 * value; -2 if the character has a numeric value but the value
11506 * can not be represented as a nonnegative {@code int} value;
11507 * -1 if the character has no numeric value.
11508 * @see Character#forDigit(int, int)
11509 * @see Character#isDigit(char)
11510 * @since 1.1
11511 */
11512 public static int getNumericValue(char ch) {
11513 return getNumericValue((int)ch);
11514 }
11515
11516 /**
11517 * Returns the {@code int} value that the specified
11518 * character (Unicode code point) represents. For example, the character
11519 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11520 * an {@code int} with a value of 50.
11521 * <p>
11522 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11523 * {@code '\u005Cu005A'}), lowercase
11524 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11525 * full width variant ({@code '\u005CuFF21'} through
11526 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11527 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11528 * through 35. This is independent of the Unicode specification,
11529 * which does not assign numeric values to these {@code char}
11530 * values.
11531 * <p>
11532 * If the character does not have a numeric value, then -1 is returned.
11533 * If the character has a numeric value that cannot be represented as a
11534 * nonnegative integer (for example, a fractional value), then -2
11535 * is returned.
11536 *
11537 * @param codePoint the character (Unicode code point) to be converted.
11538 * @return the numeric value of the character, as a nonnegative {@code int}
11539 * value; -2 if the character has a numeric value but the value
11540 * can not be represented as a nonnegative {@code int} value;
11541 * -1 if the character has no numeric value.
11542 * @see Character#forDigit(int, int)
11543 * @see Character#isDigit(int)
11544 * @since 1.5
11545 */
11546 public static int getNumericValue(int codePoint) {
11547 return CharacterData.of(codePoint).getNumericValue(codePoint);
11548 }
11549
11550 /**
11551 * Determines if the specified character is ISO-LATIN-1 white space.
11552 * This method returns {@code true} for the following five
11553 * characters only:
11554 * <table class="striped">
11555 * <caption style="display:none">truechars</caption>
11556 * <thead>
11557 * <tr><th scope="col">Character
11558 * <th scope="col">Code
11559 * <th scope="col">Name
11560 * </thead>
11561 * <tbody>
11562 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11563 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11564 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11565 * <td>{@code NEW LINE}</td></tr>
11566 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11567 * <td>{@code FORM FEED}</td></tr>
11568 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11569 * <td>{@code CARRIAGE RETURN}</td></tr>
11570 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11571 * <td>{@code SPACE}</td></tr>
11572 * </tbody>
11573 * </table>
11574 *
11575 * @param ch the character to be tested.
11576 * @return {@code true} if the character is ISO-LATIN-1 white
11577 * space; {@code false} otherwise.
11578 * @see Character#isSpaceChar(char)
11579 * @see Character#isWhitespace(char)
11580 * @deprecated Replaced by isWhitespace(char).
11581 */
11582 @Deprecated(since="1.1")
11583 public static boolean isSpace(char ch) {
11584 return (ch <= 0x0020) &&
11585 (((((1L << 0x0009) |
11586 (1L << 0x000A) |
11587 (1L << 0x000C) |
11588 (1L << 0x000D) |
11589 (1L << 0x0020)) >> ch) & 1L) != 0);
11590 }
11591
11592
11593 /**
11594 * Determines if the specified character is a Unicode space character.
11595 * A character is considered to be a space character if and only if
11596 * it is specified to be a space character by the Unicode Standard. This
11597 * method returns true if the character's general category type is any of
11598 * the following:
11599 * <ul>
11600 * <li> {@code SPACE_SEPARATOR}
11601 * <li> {@code LINE_SEPARATOR}
11602 * <li> {@code PARAGRAPH_SEPARATOR}
11603 * </ul>
11604 *
11605 * <p><b>Note:</b> This method cannot handle <a
11606 * href="#supplementary"> supplementary characters</a>. To support
11607 * all Unicode characters, including supplementary characters, use
11608 * the {@link #isSpaceChar(int)} method.
11609 *
11610 * @param ch the character to be tested.
11611 * @return {@code true} if the character is a space character;
11612 * {@code false} otherwise.
11613 * @see Character#isWhitespace(char)
11614 * @since 1.1
11615 */
11616 public static boolean isSpaceChar(char ch) {
11617 return isSpaceChar((int)ch);
11618 }
11619
11620 /**
11621 * Determines if the specified character (Unicode code point) is a
11622 * Unicode space character. A character is considered to be a
11623 * space character if and only if it is specified to be a space
11624 * character by the Unicode Standard. This method returns true if
11625 * the character's general category type is any of the following:
11626 *
11627 * <ul>
11628 * <li> {@link #SPACE_SEPARATOR}
11629 * <li> {@link #LINE_SEPARATOR}
11630 * <li> {@link #PARAGRAPH_SEPARATOR}
11631 * </ul>
11632 *
11633 * @param codePoint the character (Unicode code point) to be tested.
11634 * @return {@code true} if the character is a space character;
11635 * {@code false} otherwise.
11636 * @see Character#isWhitespace(int)
11637 * @since 1.5
11638 */
11639 public static boolean isSpaceChar(int codePoint) {
11640 return ((((1 << Character.SPACE_SEPARATOR) |
11641 (1 << Character.LINE_SEPARATOR) |
11642 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11643 != 0;
11644 }
11645
11646 /**
11647 * Determines if the specified character is white space according to Java.
11648 * A character is a Java whitespace character if and only if it satisfies
11649 * one of the following criteria:
11650 * <ul>
11651 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11652 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11653 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11654 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11655 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11656 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11657 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11658 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11659 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11660 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11661 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11662 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11663 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11664 * </ul>
11665 *
11666 * <p><b>Note:</b> This method cannot handle <a
11667 * href="#supplementary"> supplementary characters</a>. To support
11668 * all Unicode characters, including supplementary characters, use
11669 * the {@link #isWhitespace(int)} method.
11670 *
11671 * @param ch the character to be tested.
11672 * @return {@code true} if the character is a Java whitespace
11673 * character; {@code false} otherwise.
11674 * @see Character#isSpaceChar(char)
11675 * @since 1.1
11676 */
11677 public static boolean isWhitespace(char ch) {
11678 return isWhitespace((int)ch);
11679 }
11680
11681 /**
11682 * Determines if the specified character (Unicode code point) is
11683 * white space according to Java. A character is a Java
11684 * whitespace character if and only if it satisfies one of the
11685 * following criteria:
11686 * <ul>
11687 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11688 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11689 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11690 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11691 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11692 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11693 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11694 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11695 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11696 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11697 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11698 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11699 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11700 * </ul>
11701 *
11702 * @param codePoint the character (Unicode code point) to be tested.
11703 * @return {@code true} if the character is a Java whitespace
11704 * character; {@code false} otherwise.
11705 * @see Character#isSpaceChar(int)
11706 * @since 1.5
11707 */
11708 public static boolean isWhitespace(int codePoint) {
11709 return CharacterData.of(codePoint).isWhitespace(codePoint);
11710 }
11711
11712 /**
11713 * Determines if the specified character is an ISO control
11714 * character. A character is considered to be an ISO control
11715 * character if its code is in the range {@code '\u005Cu0000'}
11716 * through {@code '\u005Cu001F'} or in the range
11717 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11718 *
11719 * <p><b>Note:</b> This method cannot handle <a
11720 * href="#supplementary"> supplementary characters</a>. To support
11721 * all Unicode characters, including supplementary characters, use
11722 * the {@link #isISOControl(int)} method.
11723 *
11724 * @param ch the character to be tested.
11725 * @return {@code true} if the character is an ISO control character;
11726 * {@code false} otherwise.
11727 *
11728 * @see Character#isSpaceChar(char)
11729 * @see Character#isWhitespace(char)
11730 * @since 1.1
11731 */
11732 public static boolean isISOControl(char ch) {
11733 return isISOControl((int)ch);
11734 }
11735
11736 /**
11737 * Determines if the referenced character (Unicode code point) is an ISO control
11738 * character. A character is considered to be an ISO control
11739 * character if its code is in the range {@code '\u005Cu0000'}
11740 * through {@code '\u005Cu001F'} or in the range
11741 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11742 *
11743 * @param codePoint the character (Unicode code point) to be tested.
11744 * @return {@code true} if the character is an ISO control character;
11745 * {@code false} otherwise.
11746 * @see Character#isSpaceChar(int)
11747 * @see Character#isWhitespace(int)
11748 * @since 1.5
11749 */
11750 public static boolean isISOControl(int codePoint) {
11751 // Optimized form of:
11752 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11753 // (codePoint >= 0x7F && codePoint <= 0x9F);
11754 return codePoint <= 0x9F &&
11755 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11756 }
11757
11758 /**
11759 * Returns a value indicating a character's general category.
11760 *
11761 * <p><b>Note:</b> This method cannot handle <a
11762 * href="#supplementary"> supplementary characters</a>. To support
11763 * all Unicode characters, including supplementary characters, use
11764 * the {@link #getType(int)} method.
11765 *
11766 * @param ch the character to be tested.
11767 * @return a value of type {@code int} representing the
11768 * character's general category.
11769 * @see Character#COMBINING_SPACING_MARK
11770 * @see Character#CONNECTOR_PUNCTUATION
11771 * @see Character#CONTROL
11772 * @see Character#CURRENCY_SYMBOL
11773 * @see Character#DASH_PUNCTUATION
11774 * @see Character#DECIMAL_DIGIT_NUMBER
11775 * @see Character#ENCLOSING_MARK
11776 * @see Character#END_PUNCTUATION
11777 * @see Character#FINAL_QUOTE_PUNCTUATION
11778 * @see Character#FORMAT
11779 * @see Character#INITIAL_QUOTE_PUNCTUATION
11780 * @see Character#LETTER_NUMBER
11781 * @see Character#LINE_SEPARATOR
11782 * @see Character#LOWERCASE_LETTER
11783 * @see Character#MATH_SYMBOL
11784 * @see Character#MODIFIER_LETTER
11785 * @see Character#MODIFIER_SYMBOL
11786 * @see Character#NON_SPACING_MARK
11787 * @see Character#OTHER_LETTER
11788 * @see Character#OTHER_NUMBER
11789 * @see Character#OTHER_PUNCTUATION
11790 * @see Character#OTHER_SYMBOL
11791 * @see Character#PARAGRAPH_SEPARATOR
11792 * @see Character#PRIVATE_USE
11793 * @see Character#SPACE_SEPARATOR
11794 * @see Character#START_PUNCTUATION
11795 * @see Character#SURROGATE
11796 * @see Character#TITLECASE_LETTER
11797 * @see Character#UNASSIGNED
11798 * @see Character#UPPERCASE_LETTER
11799 * @since 1.1
11800 */
11801 public static int getType(char ch) {
11802 return getType((int)ch);
11803 }
11804
11805 /**
11806 * Returns a value indicating a character's general category.
11807 *
11808 * @param codePoint the character (Unicode code point) to be tested.
11809 * @return a value of type {@code int} representing the
11810 * character's general category.
11811 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11812 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11813 * @see Character#CONTROL CONTROL
11814 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11815 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11816 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11817 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11818 * @see Character#END_PUNCTUATION END_PUNCTUATION
11819 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11820 * @see Character#FORMAT FORMAT
11821 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11822 * @see Character#LETTER_NUMBER LETTER_NUMBER
11823 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11824 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11825 * @see Character#MATH_SYMBOL MATH_SYMBOL
11826 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11827 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11828 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11829 * @see Character#OTHER_LETTER OTHER_LETTER
11830 * @see Character#OTHER_NUMBER OTHER_NUMBER
11831 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
11832 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
11833 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
11834 * @see Character#PRIVATE_USE PRIVATE_USE
11835 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
11836 * @see Character#START_PUNCTUATION START_PUNCTUATION
11837 * @see Character#SURROGATE SURROGATE
11838 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
11839 * @see Character#UNASSIGNED UNASSIGNED
11840 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
11841 * @since 1.5
11842 */
11843 public static int getType(int codePoint) {
11844 return CharacterData.of(codePoint).getType(codePoint);
11845 }
11846
11847 /**
11848 * Determines the character representation for a specific digit in
11849 * the specified radix. If the value of {@code radix} is not a
11850 * valid radix, or the value of {@code digit} is not a valid
11851 * digit in the specified radix, the null character
11852 * ({@code '\u005Cu0000'}) is returned.
11853 * <p>
11854 * The {@code radix} argument is valid if it is greater than or
11855 * equal to {@code MIN_RADIX} and less than or equal to
11856 * {@code MAX_RADIX}. The {@code digit} argument is valid if
11857 * {@code 0 <= digit < radix}.
11858 * <p>
11859 * If the digit is less than 10, then
11860 * {@code '0' + digit} is returned. Otherwise, the value
11861 * {@code 'a' + digit - 10} is returned.
11862 *
11863 * @param digit the number to convert to a character.
11864 * @param radix the radix.
11865 * @return the {@code char} representation of the specified digit
11866 * in the specified radix.
11867 * @see Character#MIN_RADIX
11868 * @see Character#MAX_RADIX
11869 * @see Character#digit(char, int)
11870 */
11871 public static char forDigit(int digit, int radix) {
11872 if ((digit >= radix) || (digit < 0)) {
11873 return '\0';
11874 }
11875 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
11876 return '\0';
11877 }
11878 if (digit < 10) {
11879 return (char)('0' + digit);
11880 }
11881 return (char)('a' - 10 + digit);
11882 }
11883
11884 /**
11885 * Returns the Unicode directionality property for the given
11886 * character. Character directionality is used to calculate the
11887 * visual ordering of text. The directionality value of undefined
11888 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
11889 *
11890 * <p><b>Note:</b> This method cannot handle <a
11891 * href="#supplementary"> supplementary characters</a>. To support
11892 * all Unicode characters, including supplementary characters, use
11893 * the {@link #getDirectionality(int)} method.
11894 *
11895 * @param ch {@code char} for which the directionality property
11896 * is requested.
11897 * @return the directionality property of the {@code char} value.
11898 *
11899 * @see Character#DIRECTIONALITY_UNDEFINED
11900 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
11901 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
11902 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11903 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
11904 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11905 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11906 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
11907 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11908 * @see Character#DIRECTIONALITY_NONSPACING_MARK
11909 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
11910 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
11911 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
11912 * @see Character#DIRECTIONALITY_WHITESPACE
11913 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
11914 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11915 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11916 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11917 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11918 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11919 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11920 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11921 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
11922 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11923 * @since 1.4
11924 */
11925 public static byte getDirectionality(char ch) {
11926 return getDirectionality((int)ch);
11927 }
11928
11929 /**
11930 * Returns the Unicode directionality property for the given
11931 * character (Unicode code point). Character directionality is
11932 * used to calculate the visual ordering of text. The
11933 * directionality value of undefined character is {@link
11934 * #DIRECTIONALITY_UNDEFINED}.
11935 *
11936 * @param codePoint the character (Unicode code point) for which
11937 * the directionality property is requested.
11938 * @return the directionality property of the character.
11939 *
11940 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
11941 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
11942 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
11943 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11944 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
11945 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11946 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11947 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
11948 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11949 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
11950 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
11951 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
11952 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
11953 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
11954 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
11955 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11956 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11957 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11958 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11959 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11960 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11961 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11962 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
11963 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11964 * @since 1.5
11965 */
11966 public static byte getDirectionality(int codePoint) {
11967 return CharacterData.of(codePoint).getDirectionality(codePoint);
11968 }
11969
11970 /**
11971 * Determines whether the character is mirrored according to the
11972 * Unicode specification. Mirrored characters should have their
11973 * glyphs horizontally mirrored when displayed in text that is
11974 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
11975 * PARENTHESIS is semantically defined to be an <i>opening
11976 * parenthesis</i>. This will appear as a "(" in text that is
11977 * left-to-right but as a ")" in text that is right-to-left.
11978 *
11979 * <p><b>Note:</b> This method cannot handle <a
11980 * href="#supplementary"> supplementary characters</a>. To support
11981 * all Unicode characters, including supplementary characters, use
11982 * the {@link #isMirrored(int)} method.
11983 *
11984 * @param ch {@code char} for which the mirrored property is requested
11985 * @return {@code true} if the char is mirrored, {@code false}
11986 * if the {@code char} is not mirrored or is not defined.
11987 * @since 1.4
11988 */
11989 public static boolean isMirrored(char ch) {
11990 return isMirrored((int)ch);
11991 }
11992
11993 /**
11994 * Determines whether the specified character (Unicode code point)
11995 * is mirrored according to the Unicode specification. Mirrored
11996 * characters should have their glyphs horizontally mirrored when
11997 * displayed in text that is right-to-left. For example,
11998 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
11999 * defined to be an <i>opening parenthesis</i>. This will appear
12000 * as a "(" in text that is left-to-right but as a ")" in text
12001 * that is right-to-left.
12002 *
12003 * @param codePoint the character (Unicode code point) to be tested.
12004 * @return {@code true} if the character is mirrored, {@code false}
12005 * if the character is not mirrored or is not defined.
12006 * @since 1.5
12007 */
12008 public static boolean isMirrored(int codePoint) {
12009 return CharacterData.of(codePoint).isMirrored(codePoint);
12010 }
12011
12012 /**
12013 * Compares two {@code Character} objects numerically.
12014 *
12015 * @param anotherCharacter the {@code Character} to be compared.
12016 * @return the value {@code 0} if the argument {@code Character}
12017 * is equal to this {@code Character}; a value less than
12018 * {@code 0} if this {@code Character} is numerically less
12019 * than the {@code Character} argument; and a value greater than
12020 * {@code 0} if this {@code Character} is numerically greater
12021 * than the {@code Character} argument (unsigned comparison).
12022 * Note that this is strictly a numerical comparison; it is not
12023 * locale-dependent.
12024 * @since 1.2
12025 */
12026 public int compareTo(Character anotherCharacter) {
12027 return compare(this.value, anotherCharacter.value);
12028 }
12029
12030 /**
12031 * Compares two {@code char} values numerically.
12032 * The value returned is identical to what would be returned by:
12033 * <pre>
12034 * Character.valueOf(x).compareTo(Character.valueOf(y))
12035 * </pre>
12036 *
12037 * @param x the first {@code char} to compare
12038 * @param y the second {@code char} to compare
12039 * @return the value {@code 0} if {@code x == y};
12040 * a value less than {@code 0} if {@code x < y}; and
12041 * a value greater than {@code 0} if {@code x > y}
12042 * @since 1.7
12043 */
12044 public static int compare(char x, char y) {
12045 return x - y;
12046 }
12047
12048 /**
12049 * Converts the character (Unicode code point) argument to uppercase using
12050 * information from the UnicodeData file.
12051 *
12052 * @param codePoint the character (Unicode code point) to be converted.
12053 * @return either the uppercase equivalent of the character, if
12054 * any, or an error flag ({@code Character.ERROR})
12055 * that indicates that a 1:M {@code char} mapping exists.
12056 * @see Character#isLowerCase(char)
12057 * @see Character#isUpperCase(char)
12058 * @see Character#toLowerCase(char)
12059 * @see Character#toTitleCase(char)
12060 * @since 1.4
12061 */
12062 static int toUpperCaseEx(int codePoint) {
12063 assert isValidCodePoint(codePoint);
12064 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
12065 }
12066
12067 /**
12068 * Converts the character (Unicode code point) argument to uppercase using case
12069 * mapping information from the SpecialCasing file in the Unicode
12070 * specification. If a character has no explicit uppercase
12071 * mapping, then the {@code char} itself is returned in the
12072 * {@code char[]}.
12073 *
12074 * @param codePoint the character (Unicode code point) to be converted.
12075 * @return a {@code char[]} with the uppercased character.
12076 * @since 1.4
12077 */
12078 static char[] toUpperCaseCharArray(int codePoint) {
12079 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
12080 assert isBmpCodePoint(codePoint);
12081 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
12082 }
12083
12084 /**
12085 * The number of bits used to represent a {@code char} value in unsigned
12086 * binary form, constant {@code 16}.
12087 *
12088 * @since 1.5
12089 */
12090 public static final int SIZE = 16;
12091
12092 /**
12093 * The number of bytes used to represent a {@code char} value in unsigned
12094 * binary form.
12095 *
12096 * @since 1.8
12097 */
12098 public static final int BYTES = SIZE / Byte.SIZE;
12099
12100 /**
12101 * Returns the value obtained by reversing the order of the bytes in the
12102 * specified {@code char} value.
12103 *
12104 * @param ch The {@code char} of which to reverse the byte order.
12105 * @return the value obtained by reversing (or, equivalently, swapping)
12106 * the bytes in the specified {@code char} value.
12107 * @since 1.5
12108 */
12109 @IntrinsicCandidate
12110 public static char reverseBytes(char ch) {
12111 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
12112 }
12113
12114 /**
12115 * Returns the name of the specified character
12116 * {@code codePoint}, or null if the code point is
12117 * {@link #UNASSIGNED unassigned}.
12118 * <p>
12119 * If the specified character is not assigned a name by
12120 * the <i>UnicodeData</i> file (part of the Unicode Character
12121 * Database maintained by the Unicode Consortium), the returned
12122 * name is the same as the result of the expression:
12123 *
12124 * <blockquote>{@code
12125 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12126 * + " "
12127 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12128 *
12129 * }</blockquote>
12130 *
12131 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
12132 * returned by this method follows the naming scheme in the
12133 * "Unicode Name Property" section of the Unicode Standard. For other
12134 * code points, such as Hangul/Ideographs, The name generation rule above
12135 * differs from the one defined in the Unicode Standard.
12136 *
12137 * @param codePoint the character (Unicode code point)
12138 *
12139 * @return the name of the specified character, or null if
12140 * the code point is unassigned.
12141 *
12142 * @throws IllegalArgumentException if the specified
12143 * {@code codePoint} is not a valid Unicode
12144 * code point.
12145 *
12146 * @since 1.7
12147 */
12148 public static String getName(int codePoint) {
12149 if (!isValidCodePoint(codePoint)) {
12150 throw new IllegalArgumentException(
12151 String.format("Not a valid Unicode code point: 0x%X", codePoint));
12152 }
12153 String name = CharacterName.getInstance().getName(codePoint);
12154 if (name != null)
12155 return name;
12156 if (getType(codePoint) == UNASSIGNED)
12157 return null;
12158 UnicodeBlock block = UnicodeBlock.of(codePoint);
12159 if (block != null)
12160 return block.toString().replace('_', ' ') + " "
12161 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12162 // should never come here
12163 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12164 }
12165
12166 /**
12167 * Returns the code point value of the Unicode character specified by
12168 * the given character name.
12169 * <p>
12170 * If a character is not assigned a name by the <i>UnicodeData</i>
12171 * file (part of the Unicode Character Database maintained by the Unicode
12172 * Consortium), its name is defined as the result of the expression:
12173 *
12174 * <blockquote>{@code
12175 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12176 * + " "
12177 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12178 *
12179 * }</blockquote>
12180 * <p>
12181 * The {@code name} matching is case insensitive, with any leading and
12182 * trailing whitespace character removed.
12183 *
12184 * For the code points in the <i>UnicodeData</i> file, this method
12185 * recognizes the name which conforms to the name defined in the
12186 * "Unicode Name Property" section in the Unicode Standard. For other
12187 * code points, this method recognizes the name generated with
12188 * {@link #getName(int)} method.
12189 *
12190 * @param name the character name
12191 *
12192 * @return the code point value of the character specified by its name.
12193 *
12194 * @throws IllegalArgumentException if the specified {@code name}
12195 * is not a valid character name.
12196 * @throws NullPointerException if {@code name} is {@code null}
12197 *
12198 * @since 9
12199 */
12200 public static int codePointOf(String name) {
12201 name = name.trim().toUpperCase(Locale.ROOT);
12202 int cp = CharacterName.getInstance().getCodePoint(name);
12203 if (cp != -1)
12204 return cp;
12205 try {
12206 int off = name.lastIndexOf(' ');
12207 if (off != -1) {
12208 cp = Integer.parseInt(name, off + 1, name.length(), 16);
12209 if (isValidCodePoint(cp) && name.equals(getName(cp)))
12210 return cp;
12211 }
12212 } catch (Exception x) {}
12213 throw new IllegalArgumentException("Unrecognized character name :" + name);
12214 }
12215 }