1 /*
2 * Copyright (c) 2002, 2026, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import jdk.internal.misc.CDS;
29 import jdk.internal.vm.annotation.AOTSafeClassInitializer;
30 import jdk.internal.vm.annotation.IntrinsicCandidate;
31 import jdk.internal.vm.annotation.Stable;
32
33 import java.lang.constant.Constable;
34 import java.lang.constant.DynamicConstantDesc;
35 import java.util.Arrays;
36 import java.util.HashMap;
37 import java.util.Locale;
38 import java.util.Map;
39 import java.util.Objects;
40 import java.util.Optional;
41
42 import static java.lang.constant.ConstantDescs.BSM_EXPLICIT_CAST;
43 import static java.lang.constant.ConstantDescs.CD_char;
44 import static java.lang.constant.ConstantDescs.DEFAULT_NAME;
45
46 /**
47 * The {@code Character} class is the {@linkplain
48 * java.lang##wrapperClass wrapper class} for values of the primitive
49 * type {@code char}. An object of type {@code Character} contains a
50 * single field whose type is {@code char}.
51 *
52 * <p>In addition, this class provides a large number of static methods for
53 * determining a character's category (lowercase letter, digit, etc.)
54 * and for converting characters from uppercase to lowercase and vice
55 * versa.
56 *
57 * <h2><a id="conformance">Unicode Conformance</a></h2>
58 * <p>
59 * The fields and methods of class {@code Character} are defined in terms
60 * of character information from the Unicode Standard, specifically the
61 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
62 * This file specifies properties including name and category for every
63 * assigned Unicode code point or character range. The file is available
64 * from the Unicode Consortium at
65 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
66 * <p>
67 * Character information is based on the Unicode Standard, version 17.0.
68 * <p>
69 * The Java platform has supported different versions of the Unicode
70 * Standard over time. The following tables list the version of Unicode used
71 * in each Java release. Unless otherwise specified, all update releases in a
72 * given Java release family use the same Unicode version.
73 * <table class="striped">
74 * <!-- The expanded table should include the current Java release, followed
75 * by commonly used releases, with other releases listed in the details
76 * section -->
77 * <caption style="display:none">Shows Java releases and supported Unicode versions</caption>
78 * <thead>
79 * <tr><th scope="col">Java release</th>
80 * <th scope="col">Unicode version</th></tr>
81 * </thead>
82 * <tbody>
83 * <tr><th scope="row" style="text-align:left">Java SE 26</th>
84 * <td>Unicode 17.0</td></tr>
85 * <tr><th scope="row" style="text-align:left">Java SE 25</th>
86 * <td>Unicode 16.0</td></tr>
87 * <tr><th scope="row" style="text-align:left">Java SE 21</th>
88 * <td>Unicode 15.0</td></tr>
89 * <tr><th scope="row" style="text-align:left">Java SE 17</th>
90 * <td>Unicode 13.0</td></tr>
91 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
92 * <td>Unicode 10.0</td></tr>
93 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
94 * <td>Unicode 6.2</td></tr>
95 * </tbody>
96 * </table>
97 * <details>
98 * <summary>Show other Java releases</summary>
99 * <p>Java releases prior to Java SE 8 are listed only if they upgraded the
100 * Unicode version</p>
101 * <table class="striped">
102 * <caption style="display:none">Shows other Java releases and supported Unicode
103 * versions</caption>
104 * <thead>
105 * <tr><th scope="col">Java release</th>
106 * <th scope="col">Unicode version</th></tr>
107 * </thead>
108 * <tbody>
109 * <tr><th scope="row" style="text-align:left">Java SE 24</th>
110 * <td>Unicode 16.0</td></tr>
111 * <tr><th scope="row" style="text-align:left">Java SE 23</th>
112 * <td>Unicode 15.1</td></tr>
113 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
114 * <td>Unicode 15.1</td></tr>
115 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
116 * <td>Unicode 15.0</td></tr>
117 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
118 * <td>Unicode 14.0</td></tr>
119 * <tr><th scope="row" style="text-align:left">Java SE 18</th>
120 * <td>Unicode 13.0</td></tr>
121 * <tr><th scope="row" style="text-align:left">Java SE 16</th>
122 * <td>Unicode 13.0</td></tr>
123 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
124 * <td>Unicode 13.0</td></tr>
125 * <tr><th scope="row" style="text-align:left">Java SE 14</th>
126 * <td>Unicode 12.1</td></tr>
127 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
128 * <td>Unicode 12.1</td></tr>
129 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
130 * <td>Unicode 11.0</td></tr>
131 * <tr><th scope="row" style="text-align:left">Java SE 10</th>
132 * <td>Unicode 8.0</td></tr>
133 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
134 * <td>Unicode 8.0</td></tr>
135 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
136 * <td>Unicode 6.0</td></tr>
137 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
138 * <td>Unicode 4.0</td></tr>
139 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
140 * <td>Unicode 3.0</td></tr>
141 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
142 * <td>Unicode 2.0</td></tr>
143 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
144 * <td>Unicode 1.1.5</td></tr>
145 * </tbody>
146 * </table>
147 * </details>
148 * <p>
149 * Variations from these base Unicode versions, such as recognized appendixes,
150 * are documented elsewhere.
151 * <h2><a id="unicode">Unicode Character Representations</a></h2>
152 *
153 * <p>The {@code char} data type (and therefore the value that a
154 * {@code Character} object encapsulates) are based on the
155 * original Unicode specification, which defined characters as
156 * fixed-width 16-bit entities. The Unicode Standard has since been
157 * changed to allow for characters whose representation requires more
158 * than 16 bits. The range of legal <em>code point</em>s is now
159 * U+0000 to U+10FFFF, known as
160 * <em><a href="https://www.unicode.org/glossary/#unicode_scalar_value">
161 * Unicode scalar value</a></em>.
162 *
163 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
164 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
165 * <a id="supplementary">Characters</a> whose code points are greater
166 * than U+FFFF are called <em>supplementary character</em>s. The Java
167 * platform uses the UTF-16 representation in {@code char} arrays and
168 * in the {@code String} and {@code StringBuffer} classes. In
169 * this representation, supplementary characters are represented as a pair
170 * of {@code char} values, the first from the <em>high-surrogates</em>
171 * range, (\uD800-\uDBFF), the second from the
172 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
173 *
174 * <p>A {@code char} value, therefore, represents Basic
175 * Multilingual Plane (BMP) code points, including the surrogate
176 * code points, or code units of the UTF-16 encoding. An
177 * {@code int} value represents all Unicode code points,
178 * including supplementary code points. The lower (least significant)
179 * 21 bits of {@code int} are used to represent Unicode code
180 * points and the upper (most significant) 11 bits must be zero.
181 * Unless otherwise specified, the behavior with respect to
182 * supplementary characters and surrogate {@code char} values is
183 * as follows:
184 *
185 * <ul>
186 * <li>The methods that only accept a {@code char} value cannot support
187 * supplementary characters. They treat {@code char} values from the
188 * surrogate ranges as undefined characters. For example,
189 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
190 * this specific value if followed by any low-surrogate value in a string
191 * would represent a letter.
192 *
193 * <li>The methods that accept an {@code int} value support all
194 * Unicode characters, including supplementary characters. For
195 * example, {@code Character.isLetter(0x2F81A)} returns
196 * {@code true} because the code point value represents a letter
197 * (a CJK ideograph).
198 * </ul>
199 *
200 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
201 * used for character values in the range between U+0000 and U+10FFFF,
202 * and <em>Unicode code unit</em> is used for 16-bit
203 * {@code char} values that are code units of the <em>UTF-16</em>
204 * encoding. For more information on Unicode terminology, refer to the
205 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
206 *
207 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
208 * class; programmers should treat instances that are
209 * {@linkplain #equals(Object) equal} as interchangeable and should not
210 * use instances for synchronization, or unpredictable behavior may
211 * occur. For example, in a future release, synchronization may fail.
212 *
213 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
214 * @author Lee Boynton
215 * @author Guy Steele
216 * @author Akira Tanaka
217 * @author Martin Buchholz
218 * @author Ulf Zibis
219 * @since 1.0
220 */
221 @jdk.internal.ValueBased
222 public final
223 class Character implements java.io.Serializable, Comparable<Character>, Constable {
224 /**
225 * The minimum radix available for conversion to and from strings.
226 * The constant value of this field is the smallest value permitted
227 * for the radix argument in radix-conversion methods such as the
228 * {@code digit} method, the {@code forDigit} method, and the
229 * {@code toString} method of class {@code Integer}.
230 *
231 * @see Character#digit(char, int)
232 * @see Character#forDigit(int, int)
233 * @see Integer#toString(int, int)
234 * @see Integer#valueOf(String)
235 */
236 public static final int MIN_RADIX = 2;
237
238 /**
239 * The maximum radix available for conversion to and from strings.
240 * The constant value of this field is the largest value permitted
241 * for the radix argument in radix-conversion methods such as the
242 * {@code digit} method, the {@code forDigit} method, and the
243 * {@code toString} method of class {@code Integer}.
244 *
245 * @see Character#digit(char, int)
246 * @see Character#forDigit(int, int)
247 * @see Integer#toString(int, int)
248 * @see Integer#valueOf(String)
249 */
250 public static final int MAX_RADIX = 36;
251
252 /**
253 * The constant value of this field is the smallest value of type
254 * {@code char}, {@code '\u005Cu0000'}.
255 *
256 * @since 1.0.2
257 */
258 public static final char MIN_VALUE = '\u0000';
259
260 /**
261 * The constant value of this field is the largest value of type
262 * {@code char}, {@code '\u005CuFFFF'}.
263 *
264 * @since 1.0.2
265 */
266 public static final char MAX_VALUE = '\uFFFF';
267
268 /**
269 * The {@code Class} instance representing the primitive type
270 * {@code char}.
271 *
272 * @since 1.1
273 */
274 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
275
276 /*
277 * Normative general types
278 */
279
280 /*
281 * General character types
282 */
283
284 /**
285 * General category "Cn" in the Unicode specification.
286 * @since 1.1
287 */
288 public static final byte UNASSIGNED = 0;
289
290 /**
291 * General category "Lu" in the Unicode specification.
292 * @since 1.1
293 */
294 public static final byte UPPERCASE_LETTER = 1;
295
296 /**
297 * General category "Ll" in the Unicode specification.
298 * @since 1.1
299 */
300 public static final byte LOWERCASE_LETTER = 2;
301
302 /**
303 * General category "Lt" in the Unicode specification.
304 * @since 1.1
305 */
306 public static final byte TITLECASE_LETTER = 3;
307
308 /**
309 * General category "Lm" in the Unicode specification.
310 * @since 1.1
311 */
312 public static final byte MODIFIER_LETTER = 4;
313
314 /**
315 * General category "Lo" in the Unicode specification.
316 * @since 1.1
317 */
318 public static final byte OTHER_LETTER = 5;
319
320 /**
321 * General category "Mn" in the Unicode specification.
322 * @since 1.1
323 */
324 public static final byte NON_SPACING_MARK = 6;
325
326 /**
327 * General category "Me" in the Unicode specification.
328 * @since 1.1
329 */
330 public static final byte ENCLOSING_MARK = 7;
331
332 /**
333 * General category "Mc" in the Unicode specification.
334 * @since 1.1
335 */
336 public static final byte COMBINING_SPACING_MARK = 8;
337
338 /**
339 * General category "Nd" in the Unicode specification.
340 * @since 1.1
341 */
342 public static final byte DECIMAL_DIGIT_NUMBER = 9;
343
344 /**
345 * General category "Nl" in the Unicode specification.
346 * @since 1.1
347 */
348 public static final byte LETTER_NUMBER = 10;
349
350 /**
351 * General category "No" in the Unicode specification.
352 * @since 1.1
353 */
354 public static final byte OTHER_NUMBER = 11;
355
356 /**
357 * General category "Zs" in the Unicode specification.
358 * @since 1.1
359 */
360 public static final byte SPACE_SEPARATOR = 12;
361
362 /**
363 * General category "Zl" in the Unicode specification.
364 * @since 1.1
365 */
366 public static final byte LINE_SEPARATOR = 13;
367
368 /**
369 * General category "Zp" in the Unicode specification.
370 * @since 1.1
371 */
372 public static final byte PARAGRAPH_SEPARATOR = 14;
373
374 /**
375 * General category "Cc" in the Unicode specification.
376 * @since 1.1
377 */
378 public static final byte CONTROL = 15;
379
380 /**
381 * General category "Cf" in the Unicode specification.
382 * @since 1.1
383 */
384 public static final byte FORMAT = 16;
385
386 /**
387 * General category "Co" in the Unicode specification.
388 * @since 1.1
389 */
390 public static final byte PRIVATE_USE = 18;
391
392 /**
393 * General category "Cs" in the Unicode specification.
394 * @since 1.1
395 */
396 public static final byte SURROGATE = 19;
397
398 /**
399 * General category "Pd" in the Unicode specification.
400 * @since 1.1
401 */
402 public static final byte DASH_PUNCTUATION = 20;
403
404 /**
405 * General category "Ps" in the Unicode specification.
406 * @since 1.1
407 */
408 public static final byte START_PUNCTUATION = 21;
409
410 /**
411 * General category "Pe" in the Unicode specification.
412 * @since 1.1
413 */
414 public static final byte END_PUNCTUATION = 22;
415
416 /**
417 * General category "Pc" in the Unicode specification.
418 * @since 1.1
419 */
420 public static final byte CONNECTOR_PUNCTUATION = 23;
421
422 /**
423 * General category "Po" in the Unicode specification.
424 * @since 1.1
425 */
426 public static final byte OTHER_PUNCTUATION = 24;
427
428 /**
429 * General category "Sm" in the Unicode specification.
430 * @since 1.1
431 */
432 public static final byte MATH_SYMBOL = 25;
433
434 /**
435 * General category "Sc" in the Unicode specification.
436 * @since 1.1
437 */
438 public static final byte CURRENCY_SYMBOL = 26;
439
440 /**
441 * General category "Sk" in the Unicode specification.
442 * @since 1.1
443 */
444 public static final byte MODIFIER_SYMBOL = 27;
445
446 /**
447 * General category "So" in the Unicode specification.
448 * @since 1.1
449 */
450 public static final byte OTHER_SYMBOL = 28;
451
452 /**
453 * General category "Pi" in the Unicode specification.
454 * @since 1.4
455 */
456 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
457
458 /**
459 * General category "Pf" in the Unicode specification.
460 * @since 1.4
461 */
462 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
463
464 /**
465 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
466 */
467 static final int ERROR = 0xFFFFFFFF;
468
469
470 /**
471 * Undefined bidirectional character type. Undefined {@code char}
472 * values have undefined directionality in the Unicode specification.
473 * @since 1.4
474 */
475 public static final byte DIRECTIONALITY_UNDEFINED = -1;
476
477 /**
478 * Strong bidirectional character type "L" in the Unicode specification.
479 * @since 1.4
480 */
481 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
482
483 /**
484 * Strong bidirectional character type "R" in the Unicode specification.
485 * @since 1.4
486 */
487 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
488
489 /**
490 * Strong bidirectional character type "AL" in the Unicode specification.
491 * @since 1.4
492 */
493 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
494
495 /**
496 * Weak bidirectional character type "EN" in the Unicode specification.
497 * @since 1.4
498 */
499 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
500
501 /**
502 * Weak bidirectional character type "ES" in the Unicode specification.
503 * @since 1.4
504 */
505 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
506
507 /**
508 * Weak bidirectional character type "ET" in the Unicode specification.
509 * @since 1.4
510 */
511 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
512
513 /**
514 * Weak bidirectional character type "AN" in the Unicode specification.
515 * @since 1.4
516 */
517 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
518
519 /**
520 * Weak bidirectional character type "CS" in the Unicode specification.
521 * @since 1.4
522 */
523 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
524
525 /**
526 * Weak bidirectional character type "NSM" in the Unicode specification.
527 * @since 1.4
528 */
529 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
530
531 /**
532 * Weak bidirectional character type "BN" in the Unicode specification.
533 * @since 1.4
534 */
535 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
536
537 /**
538 * Neutral bidirectional character type "B" in the Unicode specification.
539 * @since 1.4
540 */
541 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
542
543 /**
544 * Neutral bidirectional character type "S" in the Unicode specification.
545 * @since 1.4
546 */
547 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
548
549 /**
550 * Neutral bidirectional character type "WS" in the Unicode specification.
551 * @since 1.4
552 */
553 public static final byte DIRECTIONALITY_WHITESPACE = 12;
554
555 /**
556 * Neutral bidirectional character type "ON" in the Unicode specification.
557 * @since 1.4
558 */
559 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
560
561 /**
562 * Strong bidirectional character type "LRE" in the Unicode specification.
563 * @since 1.4
564 */
565 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
566
567 /**
568 * Strong bidirectional character type "LRO" in the Unicode specification.
569 * @since 1.4
570 */
571 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
572
573 /**
574 * Strong bidirectional character type "RLE" in the Unicode specification.
575 * @since 1.4
576 */
577 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
578
579 /**
580 * Strong bidirectional character type "RLO" in the Unicode specification.
581 * @since 1.4
582 */
583 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
584
585 /**
586 * Weak bidirectional character type "PDF" in the Unicode specification.
587 * @since 1.4
588 */
589 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
590
591 /**
592 * Weak bidirectional character type "LRI" in the Unicode specification.
593 * @since 9
594 */
595 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
596
597 /**
598 * Weak bidirectional character type "RLI" in the Unicode specification.
599 * @since 9
600 */
601 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
602
603 /**
604 * Weak bidirectional character type "FSI" in the Unicode specification.
605 * @since 9
606 */
607 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
608
609 /**
610 * Weak bidirectional character type "PDI" in the Unicode specification.
611 * @since 9
612 */
613 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
614
615 /**
616 * The minimum value of a
617 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
618 * Unicode high-surrogate code unit</a>
619 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
620 * A high-surrogate is also known as a <i>leading-surrogate</i>.
621 *
622 * @since 1.5
623 */
624 public static final char MIN_HIGH_SURROGATE = '\uD800';
625
626 /**
627 * The maximum value of a
628 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
629 * Unicode high-surrogate code unit</a>
630 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
631 * A high-surrogate is also known as a <i>leading-surrogate</i>.
632 *
633 * @since 1.5
634 */
635 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
636
637 /**
638 * The minimum value of a
639 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
640 * Unicode low-surrogate code unit</a>
641 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
642 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
643 *
644 * @since 1.5
645 */
646 public static final char MIN_LOW_SURROGATE = '\uDC00';
647
648 /**
649 * The maximum value of a
650 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
651 * Unicode low-surrogate code unit</a>
652 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
653 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
654 *
655 * @since 1.5
656 */
657 public static final char MAX_LOW_SURROGATE = '\uDFFF';
658
659 /**
660 * The minimum value of a Unicode surrogate code unit in the
661 * UTF-16 encoding, constant {@code '\u005CuD800'}.
662 *
663 * @since 1.5
664 */
665 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
666
667 /**
668 * The maximum value of a Unicode surrogate code unit in the
669 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
670 *
671 * @since 1.5
672 */
673 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
674
675 /**
676 * The minimum value of a
677 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
678 * Unicode supplementary code point</a>, constant {@code U+10000}.
679 *
680 * @since 1.5
681 */
682 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
683
684 /**
685 * The minimum value of a
686 * <a href="http://www.unicode.org/glossary/#code_point">
687 * Unicode code point</a>, constant {@code U+0000}.
688 *
689 * @since 1.5
690 */
691 public static final int MIN_CODE_POINT = 0x000000;
692
693 /**
694 * The maximum value of a
695 * <a href="http://www.unicode.org/glossary/#code_point">
696 * Unicode code point</a>, constant {@code U+10FFFF}.
697 *
698 * @since 1.5
699 */
700 public static final int MAX_CODE_POINT = 0X10FFFF;
701
702 /**
703 * Returns an {@link Optional} containing the nominal descriptor for this
704 * instance.
705 *
706 * @return an {@link Optional} describing the {@linkplain Character} instance
707 * @since 15
708 */
709 @Override
710 public Optional<DynamicConstantDesc<Character>> describeConstable() {
711 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
712 }
713
714 /**
715 * Instances of this class represent particular subsets of the Unicode
716 * character set. The only family of subsets defined in the
717 * {@code Character} class is {@link Character.UnicodeBlock}.
718 * Other portions of the Java API may define other subsets for their
719 * own purposes.
720 *
721 * @since 1.2
722 */
723 public static class Subset {
724
725 private String name;
726
727 /**
728 * Constructs a new {@code Subset} instance.
729 *
730 * @param name The name of this subset
731 * @throws NullPointerException if name is {@code null}
732 */
733 protected Subset(String name) {
734 if (name == null) {
735 throw new NullPointerException("name");
736 }
737 this.name = name;
738 }
739
740 /**
741 * Compares two {@code Subset} objects for equality.
742 * This method returns {@code true} if and only if
743 * {@code this} and the argument refer to the same
744 * object; since this method is {@code final}, this
745 * guarantee holds for all subclasses.
746 */
747 public final boolean equals(Object obj) {
748 return (this == obj);
749 }
750
751 /**
752 * Returns the standard hash code as defined by the
753 * {@link Object#hashCode} method. This method
754 * is {@code final} in order to ensure that the
755 * {@code equals} and {@code hashCode} methods will
756 * be consistent in all subclasses.
757 */
758 public final int hashCode() {
759 return super.hashCode();
760 }
761
762 /**
763 * Returns the name of this subset.
764 */
765 public final String toString() {
766 return name;
767 }
768 }
769
770 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
771 // for the latest specification of Unicode Blocks.
772
773 /**
774 * A family of character subsets representing the character blocks in the
775 * Unicode specification. Character blocks generally define characters
776 * used for a specific script or purpose. A character is contained by
777 * at most one Unicode block.
778 *
779 * @since 1.2
780 */
781 public static final class UnicodeBlock extends Subset {
782 /**
783 * NUM_ENTITIES should match the total number of UnicodeBlock identifier
784 * names plus their aliases.
785 * It should be adjusted whenever the Unicode Character Database
786 * is upgraded.
787 */
788 private static final int NUM_ENTITIES = 804;
789 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
790
791 /**
792 * Creates a UnicodeBlock with the given identifier name.
793 * This name must be the same as the block identifier.
794 */
795 private UnicodeBlock(String idName) {
796 super(idName);
797 map.put(idName, this);
798 }
799
800 /**
801 * Creates a UnicodeBlock with the given identifier name and
802 * alias name.
803 */
804 private UnicodeBlock(String idName, String alias) {
805 this(idName);
806 map.put(alias, this);
807 }
808
809 /**
810 * Creates a UnicodeBlock with the given identifier name and
811 * alias names.
812 */
813 private UnicodeBlock(String idName, String... aliases) {
814 this(idName);
815 for (String alias : aliases)
816 map.put(alias, this);
817 }
818
819 /**
820 * Constant for the "Basic Latin" Unicode character block.
821 * @since 1.2
822 */
823 public static final UnicodeBlock BASIC_LATIN =
824 new UnicodeBlock("BASIC_LATIN",
825 "BASIC LATIN",
826 "BASICLATIN");
827
828 /**
829 * Constant for the "Latin-1 Supplement" Unicode character block.
830 * @since 1.2
831 */
832 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
833 new UnicodeBlock("LATIN_1_SUPPLEMENT",
834 "LATIN-1 SUPPLEMENT",
835 "LATIN-1SUPPLEMENT");
836
837 /**
838 * Constant for the "Latin Extended-A" Unicode character block.
839 * @since 1.2
840 */
841 public static final UnicodeBlock LATIN_EXTENDED_A =
842 new UnicodeBlock("LATIN_EXTENDED_A",
843 "LATIN EXTENDED-A",
844 "LATINEXTENDED-A");
845
846 /**
847 * Constant for the "Latin Extended-B" Unicode character block.
848 * @since 1.2
849 */
850 public static final UnicodeBlock LATIN_EXTENDED_B =
851 new UnicodeBlock("LATIN_EXTENDED_B",
852 "LATIN EXTENDED-B",
853 "LATINEXTENDED-B");
854
855 /**
856 * Constant for the "IPA Extensions" Unicode character block.
857 * @since 1.2
858 */
859 public static final UnicodeBlock IPA_EXTENSIONS =
860 new UnicodeBlock("IPA_EXTENSIONS",
861 "IPA EXTENSIONS",
862 "IPAEXTENSIONS");
863
864 /**
865 * Constant for the "Spacing Modifier Letters" Unicode character block.
866 * @since 1.2
867 */
868 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
869 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
870 "SPACING MODIFIER LETTERS",
871 "SPACINGMODIFIERLETTERS");
872
873 /**
874 * Constant for the "Combining Diacritical Marks" Unicode character block.
875 * @since 1.2
876 */
877 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
878 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
879 "COMBINING DIACRITICAL MARKS",
880 "COMBININGDIACRITICALMARKS");
881
882 /**
883 * Constant for the "Greek and Coptic" Unicode character block.
884 * <p>
885 * This block was previously known as the "Greek" block.
886 *
887 * @since 1.2
888 */
889 public static final UnicodeBlock GREEK =
890 new UnicodeBlock("GREEK",
891 "GREEK AND COPTIC",
892 "GREEKANDCOPTIC");
893
894 /**
895 * Constant for the "Cyrillic" Unicode character block.
896 * @since 1.2
897 */
898 public static final UnicodeBlock CYRILLIC =
899 new UnicodeBlock("CYRILLIC");
900
901 /**
902 * Constant for the "Armenian" Unicode character block.
903 * @since 1.2
904 */
905 public static final UnicodeBlock ARMENIAN =
906 new UnicodeBlock("ARMENIAN");
907
908 /**
909 * Constant for the "Hebrew" Unicode character block.
910 * @since 1.2
911 */
912 public static final UnicodeBlock HEBREW =
913 new UnicodeBlock("HEBREW");
914
915 /**
916 * Constant for the "Arabic" Unicode character block.
917 * @since 1.2
918 */
919 public static final UnicodeBlock ARABIC =
920 new UnicodeBlock("ARABIC");
921
922 /**
923 * Constant for the "Devanagari" Unicode character block.
924 * @since 1.2
925 */
926 public static final UnicodeBlock DEVANAGARI =
927 new UnicodeBlock("DEVANAGARI");
928
929 /**
930 * Constant for the "Bengali" Unicode character block.
931 * @since 1.2
932 */
933 public static final UnicodeBlock BENGALI =
934 new UnicodeBlock("BENGALI");
935
936 /**
937 * Constant for the "Gurmukhi" Unicode character block.
938 * @since 1.2
939 */
940 public static final UnicodeBlock GURMUKHI =
941 new UnicodeBlock("GURMUKHI");
942
943 /**
944 * Constant for the "Gujarati" Unicode character block.
945 * @since 1.2
946 */
947 public static final UnicodeBlock GUJARATI =
948 new UnicodeBlock("GUJARATI");
949
950 /**
951 * Constant for the "Oriya" Unicode character block.
952 * @since 1.2
953 */
954 public static final UnicodeBlock ORIYA =
955 new UnicodeBlock("ORIYA");
956
957 /**
958 * Constant for the "Tamil" Unicode character block.
959 * @since 1.2
960 */
961 public static final UnicodeBlock TAMIL =
962 new UnicodeBlock("TAMIL");
963
964 /**
965 * Constant for the "Telugu" Unicode character block.
966 * @since 1.2
967 */
968 public static final UnicodeBlock TELUGU =
969 new UnicodeBlock("TELUGU");
970
971 /**
972 * Constant for the "Kannada" Unicode character block.
973 * @since 1.2
974 */
975 public static final UnicodeBlock KANNADA =
976 new UnicodeBlock("KANNADA");
977
978 /**
979 * Constant for the "Malayalam" Unicode character block.
980 * @since 1.2
981 */
982 public static final UnicodeBlock MALAYALAM =
983 new UnicodeBlock("MALAYALAM");
984
985 /**
986 * Constant for the "Thai" Unicode character block.
987 * @since 1.2
988 */
989 public static final UnicodeBlock THAI =
990 new UnicodeBlock("THAI");
991
992 /**
993 * Constant for the "Lao" Unicode character block.
994 * @since 1.2
995 */
996 public static final UnicodeBlock LAO =
997 new UnicodeBlock("LAO");
998
999 /**
1000 * Constant for the "Tibetan" Unicode character block.
1001 * @since 1.2
1002 */
1003 public static final UnicodeBlock TIBETAN =
1004 new UnicodeBlock("TIBETAN");
1005
1006 /**
1007 * Constant for the "Georgian" Unicode character block.
1008 * @since 1.2
1009 */
1010 public static final UnicodeBlock GEORGIAN =
1011 new UnicodeBlock("GEORGIAN");
1012
1013 /**
1014 * Constant for the "Hangul Jamo" Unicode character block.
1015 * @since 1.2
1016 */
1017 public static final UnicodeBlock HANGUL_JAMO =
1018 new UnicodeBlock("HANGUL_JAMO",
1019 "HANGUL JAMO",
1020 "HANGULJAMO");
1021
1022 /**
1023 * Constant for the "Latin Extended Additional" Unicode character block.
1024 * @since 1.2
1025 */
1026 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
1027 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
1028 "LATIN EXTENDED ADDITIONAL",
1029 "LATINEXTENDEDADDITIONAL");
1030
1031 /**
1032 * Constant for the "Greek Extended" Unicode character block.
1033 * @since 1.2
1034 */
1035 public static final UnicodeBlock GREEK_EXTENDED =
1036 new UnicodeBlock("GREEK_EXTENDED",
1037 "GREEK EXTENDED",
1038 "GREEKEXTENDED");
1039
1040 /**
1041 * Constant for the "General Punctuation" Unicode character block.
1042 * @since 1.2
1043 */
1044 public static final UnicodeBlock GENERAL_PUNCTUATION =
1045 new UnicodeBlock("GENERAL_PUNCTUATION",
1046 "GENERAL PUNCTUATION",
1047 "GENERALPUNCTUATION");
1048
1049 /**
1050 * Constant for the "Superscripts and Subscripts" Unicode character
1051 * block.
1052 * @since 1.2
1053 */
1054 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1055 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1056 "SUPERSCRIPTS AND SUBSCRIPTS",
1057 "SUPERSCRIPTSANDSUBSCRIPTS");
1058
1059 /**
1060 * Constant for the "Currency Symbols" Unicode character block.
1061 * @since 1.2
1062 */
1063 public static final UnicodeBlock CURRENCY_SYMBOLS =
1064 new UnicodeBlock("CURRENCY_SYMBOLS",
1065 "CURRENCY SYMBOLS",
1066 "CURRENCYSYMBOLS");
1067
1068 /**
1069 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1070 * character block.
1071 * <p>
1072 * This block was previously known as "Combining Marks for Symbols".
1073 * @since 1.2
1074 */
1075 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1076 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1077 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1078 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1079 "COMBINING MARKS FOR SYMBOLS",
1080 "COMBININGMARKSFORSYMBOLS");
1081
1082 /**
1083 * Constant for the "Letterlike Symbols" Unicode character block.
1084 * @since 1.2
1085 */
1086 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1087 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1088 "LETTERLIKE SYMBOLS",
1089 "LETTERLIKESYMBOLS");
1090
1091 /**
1092 * Constant for the "Number Forms" Unicode character block.
1093 * @since 1.2
1094 */
1095 public static final UnicodeBlock NUMBER_FORMS =
1096 new UnicodeBlock("NUMBER_FORMS",
1097 "NUMBER FORMS",
1098 "NUMBERFORMS");
1099
1100 /**
1101 * Constant for the "Arrows" Unicode character block.
1102 * @since 1.2
1103 */
1104 public static final UnicodeBlock ARROWS =
1105 new UnicodeBlock("ARROWS");
1106
1107 /**
1108 * Constant for the "Mathematical Operators" Unicode character block.
1109 * @since 1.2
1110 */
1111 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1112 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1113 "MATHEMATICAL OPERATORS",
1114 "MATHEMATICALOPERATORS");
1115
1116 /**
1117 * Constant for the "Miscellaneous Technical" Unicode character block.
1118 * @since 1.2
1119 */
1120 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1121 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1122 "MISCELLANEOUS TECHNICAL",
1123 "MISCELLANEOUSTECHNICAL");
1124
1125 /**
1126 * Constant for the "Control Pictures" Unicode character block.
1127 * @since 1.2
1128 */
1129 public static final UnicodeBlock CONTROL_PICTURES =
1130 new UnicodeBlock("CONTROL_PICTURES",
1131 "CONTROL PICTURES",
1132 "CONTROLPICTURES");
1133
1134 /**
1135 * Constant for the "Optical Character Recognition" Unicode character block.
1136 * @since 1.2
1137 */
1138 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1139 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1140 "OPTICAL CHARACTER RECOGNITION",
1141 "OPTICALCHARACTERRECOGNITION");
1142
1143 /**
1144 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1145 * @since 1.2
1146 */
1147 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1148 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1149 "ENCLOSED ALPHANUMERICS",
1150 "ENCLOSEDALPHANUMERICS");
1151
1152 /**
1153 * Constant for the "Box Drawing" Unicode character block.
1154 * @since 1.2
1155 */
1156 public static final UnicodeBlock BOX_DRAWING =
1157 new UnicodeBlock("BOX_DRAWING",
1158 "BOX DRAWING",
1159 "BOXDRAWING");
1160
1161 /**
1162 * Constant for the "Block Elements" Unicode character block.
1163 * @since 1.2
1164 */
1165 public static final UnicodeBlock BLOCK_ELEMENTS =
1166 new UnicodeBlock("BLOCK_ELEMENTS",
1167 "BLOCK ELEMENTS",
1168 "BLOCKELEMENTS");
1169
1170 /**
1171 * Constant for the "Geometric Shapes" Unicode character block.
1172 * @since 1.2
1173 */
1174 public static final UnicodeBlock GEOMETRIC_SHAPES =
1175 new UnicodeBlock("GEOMETRIC_SHAPES",
1176 "GEOMETRIC SHAPES",
1177 "GEOMETRICSHAPES");
1178
1179 /**
1180 * Constant for the "Miscellaneous Symbols" Unicode character block.
1181 * @since 1.2
1182 */
1183 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1184 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1185 "MISCELLANEOUS SYMBOLS",
1186 "MISCELLANEOUSSYMBOLS");
1187
1188 /**
1189 * Constant for the "Dingbats" Unicode character block.
1190 * @since 1.2
1191 */
1192 public static final UnicodeBlock DINGBATS =
1193 new UnicodeBlock("DINGBATS");
1194
1195 /**
1196 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1197 * @since 1.2
1198 */
1199 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1200 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1201 "CJK SYMBOLS AND PUNCTUATION",
1202 "CJKSYMBOLSANDPUNCTUATION");
1203
1204 /**
1205 * Constant for the "Hiragana" Unicode character block.
1206 * @since 1.2
1207 */
1208 public static final UnicodeBlock HIRAGANA =
1209 new UnicodeBlock("HIRAGANA");
1210
1211 /**
1212 * Constant for the "Katakana" Unicode character block.
1213 * @since 1.2
1214 */
1215 public static final UnicodeBlock KATAKANA =
1216 new UnicodeBlock("KATAKANA");
1217
1218 /**
1219 * Constant for the "Bopomofo" Unicode character block.
1220 * @since 1.2
1221 */
1222 public static final UnicodeBlock BOPOMOFO =
1223 new UnicodeBlock("BOPOMOFO");
1224
1225 /**
1226 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1227 * @since 1.2
1228 */
1229 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1230 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1231 "HANGUL COMPATIBILITY JAMO",
1232 "HANGULCOMPATIBILITYJAMO");
1233
1234 /**
1235 * Constant for the "Kanbun" Unicode character block.
1236 * @since 1.2
1237 */
1238 public static final UnicodeBlock KANBUN =
1239 new UnicodeBlock("KANBUN");
1240
1241 /**
1242 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1243 * @since 1.2
1244 */
1245 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1246 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1247 "ENCLOSED CJK LETTERS AND MONTHS",
1248 "ENCLOSEDCJKLETTERSANDMONTHS");
1249
1250 /**
1251 * Constant for the "CJK Compatibility" Unicode character block.
1252 * @since 1.2
1253 */
1254 public static final UnicodeBlock CJK_COMPATIBILITY =
1255 new UnicodeBlock("CJK_COMPATIBILITY",
1256 "CJK COMPATIBILITY",
1257 "CJKCOMPATIBILITY");
1258
1259 /**
1260 * Constant for the "CJK Unified Ideographs" Unicode character block.
1261 * @since 1.2
1262 */
1263 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1264 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1265 "CJK UNIFIED IDEOGRAPHS",
1266 "CJKUNIFIEDIDEOGRAPHS");
1267
1268 /**
1269 * Constant for the "Hangul Syllables" Unicode character block.
1270 * @since 1.2
1271 */
1272 public static final UnicodeBlock HANGUL_SYLLABLES =
1273 new UnicodeBlock("HANGUL_SYLLABLES",
1274 "HANGUL SYLLABLES",
1275 "HANGULSYLLABLES");
1276
1277 /**
1278 * Constant for the "Private Use Area" Unicode character block.
1279 * @since 1.2
1280 */
1281 public static final UnicodeBlock PRIVATE_USE_AREA =
1282 new UnicodeBlock("PRIVATE_USE_AREA",
1283 "PRIVATE USE AREA",
1284 "PRIVATEUSEAREA");
1285
1286 /**
1287 * Constant for the "CJK Compatibility Ideographs" Unicode character
1288 * block.
1289 * @since 1.2
1290 */
1291 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1292 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1293 "CJK COMPATIBILITY IDEOGRAPHS",
1294 "CJKCOMPATIBILITYIDEOGRAPHS");
1295
1296 /**
1297 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1298 * @since 1.2
1299 */
1300 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1301 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1302 "ALPHABETIC PRESENTATION FORMS",
1303 "ALPHABETICPRESENTATIONFORMS");
1304
1305 /**
1306 * Constant for the "Arabic Presentation Forms-A" Unicode character
1307 * block.
1308 * @since 1.2
1309 */
1310 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1311 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1312 "ARABIC PRESENTATION FORMS-A",
1313 "ARABICPRESENTATIONFORMS-A");
1314
1315 /**
1316 * Constant for the "Combining Half Marks" Unicode character block.
1317 * @since 1.2
1318 */
1319 public static final UnicodeBlock COMBINING_HALF_MARKS =
1320 new UnicodeBlock("COMBINING_HALF_MARKS",
1321 "COMBINING HALF MARKS",
1322 "COMBININGHALFMARKS");
1323
1324 /**
1325 * Constant for the "CJK Compatibility Forms" Unicode character block.
1326 * @since 1.2
1327 */
1328 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1329 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1330 "CJK COMPATIBILITY FORMS",
1331 "CJKCOMPATIBILITYFORMS");
1332
1333 /**
1334 * Constant for the "Small Form Variants" Unicode character block.
1335 * @since 1.2
1336 */
1337 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1338 new UnicodeBlock("SMALL_FORM_VARIANTS",
1339 "SMALL FORM VARIANTS",
1340 "SMALLFORMVARIANTS");
1341
1342 /**
1343 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1344 * @since 1.2
1345 */
1346 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1347 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1348 "ARABIC PRESENTATION FORMS-B",
1349 "ARABICPRESENTATIONFORMS-B");
1350
1351 /**
1352 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1353 * block.
1354 * @since 1.2
1355 */
1356 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1357 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1358 "HALFWIDTH AND FULLWIDTH FORMS",
1359 "HALFWIDTHANDFULLWIDTHFORMS");
1360
1361 /**
1362 * Constant for the "Specials" Unicode character block.
1363 * @since 1.2
1364 */
1365 public static final UnicodeBlock SPECIALS =
1366 new UnicodeBlock("SPECIALS");
1367
1368 /**
1369 * @deprecated
1370 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1371 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1372 * These constants match the block definitions of the Unicode Standard.
1373 * The {@link #of(char)} and {@link #of(int)} methods return the
1374 * standard constants.
1375 */
1376 @Deprecated(since="1.5")
1377 public static final UnicodeBlock SURROGATES_AREA =
1378 new UnicodeBlock("SURROGATES_AREA");
1379
1380 /**
1381 * Constant for the "Syriac" Unicode character block.
1382 * @since 1.4
1383 */
1384 public static final UnicodeBlock SYRIAC =
1385 new UnicodeBlock("SYRIAC");
1386
1387 /**
1388 * Constant for the "Thaana" Unicode character block.
1389 * @since 1.4
1390 */
1391 public static final UnicodeBlock THAANA =
1392 new UnicodeBlock("THAANA");
1393
1394 /**
1395 * Constant for the "Sinhala" Unicode character block.
1396 * @since 1.4
1397 */
1398 public static final UnicodeBlock SINHALA =
1399 new UnicodeBlock("SINHALA");
1400
1401 /**
1402 * Constant for the "Myanmar" Unicode character block.
1403 * @since 1.4
1404 */
1405 public static final UnicodeBlock MYANMAR =
1406 new UnicodeBlock("MYANMAR");
1407
1408 /**
1409 * Constant for the "Ethiopic" Unicode character block.
1410 * @since 1.4
1411 */
1412 public static final UnicodeBlock ETHIOPIC =
1413 new UnicodeBlock("ETHIOPIC");
1414
1415 /**
1416 * Constant for the "Cherokee" Unicode character block.
1417 * @since 1.4
1418 */
1419 public static final UnicodeBlock CHEROKEE =
1420 new UnicodeBlock("CHEROKEE");
1421
1422 /**
1423 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1424 * @since 1.4
1425 */
1426 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1427 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1428 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1429 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1430
1431 /**
1432 * Constant for the "Ogham" Unicode character block.
1433 * @since 1.4
1434 */
1435 public static final UnicodeBlock OGHAM =
1436 new UnicodeBlock("OGHAM");
1437
1438 /**
1439 * Constant for the "Runic" Unicode character block.
1440 * @since 1.4
1441 */
1442 public static final UnicodeBlock RUNIC =
1443 new UnicodeBlock("RUNIC");
1444
1445 /**
1446 * Constant for the "Khmer" Unicode character block.
1447 * @since 1.4
1448 */
1449 public static final UnicodeBlock KHMER =
1450 new UnicodeBlock("KHMER");
1451
1452 /**
1453 * Constant for the "Mongolian" Unicode character block.
1454 * @since 1.4
1455 */
1456 public static final UnicodeBlock MONGOLIAN =
1457 new UnicodeBlock("MONGOLIAN");
1458
1459 /**
1460 * Constant for the "Braille Patterns" Unicode character block.
1461 * @since 1.4
1462 */
1463 public static final UnicodeBlock BRAILLE_PATTERNS =
1464 new UnicodeBlock("BRAILLE_PATTERNS",
1465 "BRAILLE PATTERNS",
1466 "BRAILLEPATTERNS");
1467
1468 /**
1469 * Constant for the "CJK Radicals Supplement" Unicode character block.
1470 * @since 1.4
1471 */
1472 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1473 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1474 "CJK RADICALS SUPPLEMENT",
1475 "CJKRADICALSSUPPLEMENT");
1476
1477 /**
1478 * Constant for the "Kangxi Radicals" Unicode character block.
1479 * @since 1.4
1480 */
1481 public static final UnicodeBlock KANGXI_RADICALS =
1482 new UnicodeBlock("KANGXI_RADICALS",
1483 "KANGXI RADICALS",
1484 "KANGXIRADICALS");
1485
1486 /**
1487 * Constant for the "Ideographic Description Characters" Unicode character block.
1488 * @since 1.4
1489 */
1490 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1491 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1492 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1493 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1494
1495 /**
1496 * Constant for the "Bopomofo Extended" Unicode character block.
1497 * @since 1.4
1498 */
1499 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1500 new UnicodeBlock("BOPOMOFO_EXTENDED",
1501 "BOPOMOFO EXTENDED",
1502 "BOPOMOFOEXTENDED");
1503
1504 /**
1505 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1506 * @since 1.4
1507 */
1508 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1509 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1510 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1511 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1512
1513 /**
1514 * Constant for the "Yi Syllables" Unicode character block.
1515 * @since 1.4
1516 */
1517 public static final UnicodeBlock YI_SYLLABLES =
1518 new UnicodeBlock("YI_SYLLABLES",
1519 "YI SYLLABLES",
1520 "YISYLLABLES");
1521
1522 /**
1523 * Constant for the "Yi Radicals" Unicode character block.
1524 * @since 1.4
1525 */
1526 public static final UnicodeBlock YI_RADICALS =
1527 new UnicodeBlock("YI_RADICALS",
1528 "YI RADICALS",
1529 "YIRADICALS");
1530
1531 /**
1532 * Constant for the "Cyrillic Supplement" Unicode character block.
1533 * This block was previously known as the "Cyrillic Supplementary" block.
1534 * @since 1.5
1535 */
1536 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1537 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1538 "CYRILLIC SUPPLEMENTARY",
1539 "CYRILLICSUPPLEMENTARY",
1540 "CYRILLIC SUPPLEMENT",
1541 "CYRILLICSUPPLEMENT");
1542
1543 /**
1544 * Constant for the "Tagalog" Unicode character block.
1545 * @since 1.5
1546 */
1547 public static final UnicodeBlock TAGALOG =
1548 new UnicodeBlock("TAGALOG");
1549
1550 /**
1551 * Constant for the "Hanunoo" Unicode character block.
1552 * @since 1.5
1553 */
1554 public static final UnicodeBlock HANUNOO =
1555 new UnicodeBlock("HANUNOO");
1556
1557 /**
1558 * Constant for the "Buhid" Unicode character block.
1559 * @since 1.5
1560 */
1561 public static final UnicodeBlock BUHID =
1562 new UnicodeBlock("BUHID");
1563
1564 /**
1565 * Constant for the "Tagbanwa" Unicode character block.
1566 * @since 1.5
1567 */
1568 public static final UnicodeBlock TAGBANWA =
1569 new UnicodeBlock("TAGBANWA");
1570
1571 /**
1572 * Constant for the "Limbu" Unicode character block.
1573 * @since 1.5
1574 */
1575 public static final UnicodeBlock LIMBU =
1576 new UnicodeBlock("LIMBU");
1577
1578 /**
1579 * Constant for the "Tai Le" Unicode character block.
1580 * @since 1.5
1581 */
1582 public static final UnicodeBlock TAI_LE =
1583 new UnicodeBlock("TAI_LE",
1584 "TAI LE",
1585 "TAILE");
1586
1587 /**
1588 * Constant for the "Khmer Symbols" Unicode character block.
1589 * @since 1.5
1590 */
1591 public static final UnicodeBlock KHMER_SYMBOLS =
1592 new UnicodeBlock("KHMER_SYMBOLS",
1593 "KHMER SYMBOLS",
1594 "KHMERSYMBOLS");
1595
1596 /**
1597 * Constant for the "Phonetic Extensions" Unicode character block.
1598 * @since 1.5
1599 */
1600 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1601 new UnicodeBlock("PHONETIC_EXTENSIONS",
1602 "PHONETIC EXTENSIONS",
1603 "PHONETICEXTENSIONS");
1604
1605 /**
1606 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1607 * @since 1.5
1608 */
1609 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1610 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1611 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1612 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1613
1614 /**
1615 * Constant for the "Supplemental Arrows-A" Unicode character block.
1616 * @since 1.5
1617 */
1618 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1619 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1620 "SUPPLEMENTAL ARROWS-A",
1621 "SUPPLEMENTALARROWS-A");
1622
1623 /**
1624 * Constant for the "Supplemental Arrows-B" Unicode character block.
1625 * @since 1.5
1626 */
1627 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1628 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1629 "SUPPLEMENTAL ARROWS-B",
1630 "SUPPLEMENTALARROWS-B");
1631
1632 /**
1633 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1634 * character block.
1635 * @since 1.5
1636 */
1637 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1638 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1639 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1640 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1641
1642 /**
1643 * Constant for the "Supplemental Mathematical Operators" Unicode
1644 * character block.
1645 * @since 1.5
1646 */
1647 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1648 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1649 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1650 "SUPPLEMENTALMATHEMATICALOPERATORS");
1651
1652 /**
1653 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1654 * block.
1655 * @since 1.5
1656 */
1657 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1658 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1659 "MISCELLANEOUS SYMBOLS AND ARROWS",
1660 "MISCELLANEOUSSYMBOLSANDARROWS");
1661
1662 /**
1663 * Constant for the "Katakana Phonetic Extensions" Unicode character
1664 * block.
1665 * @since 1.5
1666 */
1667 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1668 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1669 "KATAKANA PHONETIC EXTENSIONS",
1670 "KATAKANAPHONETICEXTENSIONS");
1671
1672 /**
1673 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1674 * @since 1.5
1675 */
1676 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1677 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1678 "YIJING HEXAGRAM SYMBOLS",
1679 "YIJINGHEXAGRAMSYMBOLS");
1680
1681 /**
1682 * Constant for the "Variation Selectors" Unicode character block.
1683 * @since 1.5
1684 */
1685 public static final UnicodeBlock VARIATION_SELECTORS =
1686 new UnicodeBlock("VARIATION_SELECTORS",
1687 "VARIATION SELECTORS",
1688 "VARIATIONSELECTORS");
1689
1690 /**
1691 * Constant for the "Linear B Syllabary" Unicode character block.
1692 * @since 1.5
1693 */
1694 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1695 new UnicodeBlock("LINEAR_B_SYLLABARY",
1696 "LINEAR B SYLLABARY",
1697 "LINEARBSYLLABARY");
1698
1699 /**
1700 * Constant for the "Linear B Ideograms" Unicode character block.
1701 * @since 1.5
1702 */
1703 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1704 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1705 "LINEAR B IDEOGRAMS",
1706 "LINEARBIDEOGRAMS");
1707
1708 /**
1709 * Constant for the "Aegean Numbers" Unicode character block.
1710 * @since 1.5
1711 */
1712 public static final UnicodeBlock AEGEAN_NUMBERS =
1713 new UnicodeBlock("AEGEAN_NUMBERS",
1714 "AEGEAN NUMBERS",
1715 "AEGEANNUMBERS");
1716
1717 /**
1718 * Constant for the "Old Italic" Unicode character block.
1719 * @since 1.5
1720 */
1721 public static final UnicodeBlock OLD_ITALIC =
1722 new UnicodeBlock("OLD_ITALIC",
1723 "OLD ITALIC",
1724 "OLDITALIC");
1725
1726 /**
1727 * Constant for the "Gothic" Unicode character block.
1728 * @since 1.5
1729 */
1730 public static final UnicodeBlock GOTHIC =
1731 new UnicodeBlock("GOTHIC");
1732
1733 /**
1734 * Constant for the "Ugaritic" Unicode character block.
1735 * @since 1.5
1736 */
1737 public static final UnicodeBlock UGARITIC =
1738 new UnicodeBlock("UGARITIC");
1739
1740 /**
1741 * Constant for the "Deseret" Unicode character block.
1742 * @since 1.5
1743 */
1744 public static final UnicodeBlock DESERET =
1745 new UnicodeBlock("DESERET");
1746
1747 /**
1748 * Constant for the "Shavian" Unicode character block.
1749 * @since 1.5
1750 */
1751 public static final UnicodeBlock SHAVIAN =
1752 new UnicodeBlock("SHAVIAN");
1753
1754 /**
1755 * Constant for the "Osmanya" Unicode character block.
1756 * @since 1.5
1757 */
1758 public static final UnicodeBlock OSMANYA =
1759 new UnicodeBlock("OSMANYA");
1760
1761 /**
1762 * Constant for the "Cypriot Syllabary" Unicode character block.
1763 * @since 1.5
1764 */
1765 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1766 new UnicodeBlock("CYPRIOT_SYLLABARY",
1767 "CYPRIOT SYLLABARY",
1768 "CYPRIOTSYLLABARY");
1769
1770 /**
1771 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1772 * @since 1.5
1773 */
1774 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1775 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1776 "BYZANTINE MUSICAL SYMBOLS",
1777 "BYZANTINEMUSICALSYMBOLS");
1778
1779 /**
1780 * Constant for the "Musical Symbols" Unicode character block.
1781 * @since 1.5
1782 */
1783 public static final UnicodeBlock MUSICAL_SYMBOLS =
1784 new UnicodeBlock("MUSICAL_SYMBOLS",
1785 "MUSICAL SYMBOLS",
1786 "MUSICALSYMBOLS");
1787
1788 /**
1789 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1790 * @since 1.5
1791 */
1792 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1793 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1794 "TAI XUAN JING SYMBOLS",
1795 "TAIXUANJINGSYMBOLS");
1796
1797 /**
1798 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1799 * character block.
1800 * @since 1.5
1801 */
1802 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1803 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1804 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1805 "MATHEMATICALALPHANUMERICSYMBOLS");
1806
1807 /**
1808 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1809 * character block.
1810 * @since 1.5
1811 */
1812 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1813 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1814 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1815 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1816
1817 /**
1818 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1819 * @since 1.5
1820 */
1821 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1822 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1823 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1824 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1825
1826 /**
1827 * Constant for the "Tags" Unicode character block.
1828 * @since 1.5
1829 */
1830 public static final UnicodeBlock TAGS =
1831 new UnicodeBlock("TAGS");
1832
1833 /**
1834 * Constant for the "Variation Selectors Supplement" Unicode character
1835 * block.
1836 * @since 1.5
1837 */
1838 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1839 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1840 "VARIATION SELECTORS SUPPLEMENT",
1841 "VARIATIONSELECTORSSUPPLEMENT");
1842
1843 /**
1844 * Constant for the "Supplementary Private Use Area-A" Unicode character
1845 * block.
1846 * @since 1.5
1847 */
1848 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1849 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1850 "SUPPLEMENTARY PRIVATE USE AREA-A",
1851 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1852
1853 /**
1854 * Constant for the "Supplementary Private Use Area-B" Unicode character
1855 * block.
1856 * @since 1.5
1857 */
1858 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1859 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1860 "SUPPLEMENTARY PRIVATE USE AREA-B",
1861 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1862
1863 /**
1864 * Constant for the "High Surrogates" Unicode character block.
1865 * This block represents codepoint values in the high surrogate
1866 * range: U+D800 through U+DB7F
1867 *
1868 * @since 1.5
1869 */
1870 public static final UnicodeBlock HIGH_SURROGATES =
1871 new UnicodeBlock("HIGH_SURROGATES",
1872 "HIGH SURROGATES",
1873 "HIGHSURROGATES");
1874
1875 /**
1876 * Constant for the "High Private Use Surrogates" Unicode character
1877 * block.
1878 * This block represents codepoint values in the private use high
1879 * surrogate range: U+DB80 through U+DBFF
1880 *
1881 * @since 1.5
1882 */
1883 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1884 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1885 "HIGH PRIVATE USE SURROGATES",
1886 "HIGHPRIVATEUSESURROGATES");
1887
1888 /**
1889 * Constant for the "Low Surrogates" Unicode character block.
1890 * This block represents codepoint values in the low surrogate
1891 * range: U+DC00 through U+DFFF
1892 *
1893 * @since 1.5
1894 */
1895 public static final UnicodeBlock LOW_SURROGATES =
1896 new UnicodeBlock("LOW_SURROGATES",
1897 "LOW SURROGATES",
1898 "LOWSURROGATES");
1899
1900 /**
1901 * Constant for the "Arabic Supplement" Unicode character block.
1902 * @since 1.7
1903 */
1904 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1905 new UnicodeBlock("ARABIC_SUPPLEMENT",
1906 "ARABIC SUPPLEMENT",
1907 "ARABICSUPPLEMENT");
1908
1909 /**
1910 * Constant for the "NKo" Unicode character block.
1911 * @since 1.7
1912 */
1913 public static final UnicodeBlock NKO =
1914 new UnicodeBlock("NKO");
1915
1916 /**
1917 * Constant for the "Samaritan" Unicode character block.
1918 * @since 1.7
1919 */
1920 public static final UnicodeBlock SAMARITAN =
1921 new UnicodeBlock("SAMARITAN");
1922
1923 /**
1924 * Constant for the "Mandaic" Unicode character block.
1925 * @since 1.7
1926 */
1927 public static final UnicodeBlock MANDAIC =
1928 new UnicodeBlock("MANDAIC");
1929
1930 /**
1931 * Constant for the "Ethiopic Supplement" Unicode character block.
1932 * @since 1.7
1933 */
1934 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1935 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1936 "ETHIOPIC SUPPLEMENT",
1937 "ETHIOPICSUPPLEMENT");
1938
1939 /**
1940 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1941 * Unicode character block.
1942 * @since 1.7
1943 */
1944 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1945 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1946 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1947 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1948
1949 /**
1950 * Constant for the "New Tai Lue" Unicode character block.
1951 * @since 1.7
1952 */
1953 public static final UnicodeBlock NEW_TAI_LUE =
1954 new UnicodeBlock("NEW_TAI_LUE",
1955 "NEW TAI LUE",
1956 "NEWTAILUE");
1957
1958 /**
1959 * Constant for the "Buginese" Unicode character block.
1960 * @since 1.7
1961 */
1962 public static final UnicodeBlock BUGINESE =
1963 new UnicodeBlock("BUGINESE");
1964
1965 /**
1966 * Constant for the "Tai Tham" Unicode character block.
1967 * @since 1.7
1968 */
1969 public static final UnicodeBlock TAI_THAM =
1970 new UnicodeBlock("TAI_THAM",
1971 "TAI THAM",
1972 "TAITHAM");
1973
1974 /**
1975 * Constant for the "Balinese" Unicode character block.
1976 * @since 1.7
1977 */
1978 public static final UnicodeBlock BALINESE =
1979 new UnicodeBlock("BALINESE");
1980
1981 /**
1982 * Constant for the "Sundanese" Unicode character block.
1983 * @since 1.7
1984 */
1985 public static final UnicodeBlock SUNDANESE =
1986 new UnicodeBlock("SUNDANESE");
1987
1988 /**
1989 * Constant for the "Batak" Unicode character block.
1990 * @since 1.7
1991 */
1992 public static final UnicodeBlock BATAK =
1993 new UnicodeBlock("BATAK");
1994
1995 /**
1996 * Constant for the "Lepcha" Unicode character block.
1997 * @since 1.7
1998 */
1999 public static final UnicodeBlock LEPCHA =
2000 new UnicodeBlock("LEPCHA");
2001
2002 /**
2003 * Constant for the "Ol Chiki" Unicode character block.
2004 * @since 1.7
2005 */
2006 public static final UnicodeBlock OL_CHIKI =
2007 new UnicodeBlock("OL_CHIKI",
2008 "OL CHIKI",
2009 "OLCHIKI");
2010
2011 /**
2012 * Constant for the "Vedic Extensions" Unicode character block.
2013 * @since 1.7
2014 */
2015 public static final UnicodeBlock VEDIC_EXTENSIONS =
2016 new UnicodeBlock("VEDIC_EXTENSIONS",
2017 "VEDIC EXTENSIONS",
2018 "VEDICEXTENSIONS");
2019
2020 /**
2021 * Constant for the "Phonetic Extensions Supplement" Unicode character
2022 * block.
2023 * @since 1.7
2024 */
2025 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
2026 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
2027 "PHONETIC EXTENSIONS SUPPLEMENT",
2028 "PHONETICEXTENSIONSSUPPLEMENT");
2029
2030 /**
2031 * Constant for the "Combining Diacritical Marks Supplement" Unicode
2032 * character block.
2033 * @since 1.7
2034 */
2035 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
2036 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
2037 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
2038 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2039
2040 /**
2041 * Constant for the "Glagolitic" Unicode character block.
2042 * @since 1.7
2043 */
2044 public static final UnicodeBlock GLAGOLITIC =
2045 new UnicodeBlock("GLAGOLITIC");
2046
2047 /**
2048 * Constant for the "Latin Extended-C" Unicode character block.
2049 * @since 1.7
2050 */
2051 public static final UnicodeBlock LATIN_EXTENDED_C =
2052 new UnicodeBlock("LATIN_EXTENDED_C",
2053 "LATIN EXTENDED-C",
2054 "LATINEXTENDED-C");
2055
2056 /**
2057 * Constant for the "Coptic" Unicode character block.
2058 * @since 1.7
2059 */
2060 public static final UnicodeBlock COPTIC =
2061 new UnicodeBlock("COPTIC");
2062
2063 /**
2064 * Constant for the "Georgian Supplement" Unicode character block.
2065 * @since 1.7
2066 */
2067 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2068 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2069 "GEORGIAN SUPPLEMENT",
2070 "GEORGIANSUPPLEMENT");
2071
2072 /**
2073 * Constant for the "Tifinagh" Unicode character block.
2074 * @since 1.7
2075 */
2076 public static final UnicodeBlock TIFINAGH =
2077 new UnicodeBlock("TIFINAGH");
2078
2079 /**
2080 * Constant for the "Ethiopic Extended" Unicode character block.
2081 * @since 1.7
2082 */
2083 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2084 new UnicodeBlock("ETHIOPIC_EXTENDED",
2085 "ETHIOPIC EXTENDED",
2086 "ETHIOPICEXTENDED");
2087
2088 /**
2089 * Constant for the "Cyrillic Extended-A" Unicode character block.
2090 * @since 1.7
2091 */
2092 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2093 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2094 "CYRILLIC EXTENDED-A",
2095 "CYRILLICEXTENDED-A");
2096
2097 /**
2098 * Constant for the "Supplemental Punctuation" Unicode character block.
2099 * @since 1.7
2100 */
2101 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2102 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2103 "SUPPLEMENTAL PUNCTUATION",
2104 "SUPPLEMENTALPUNCTUATION");
2105
2106 /**
2107 * Constant for the "CJK Strokes" Unicode character block.
2108 * @since 1.7
2109 */
2110 public static final UnicodeBlock CJK_STROKES =
2111 new UnicodeBlock("CJK_STROKES",
2112 "CJK STROKES",
2113 "CJKSTROKES");
2114
2115 /**
2116 * Constant for the "Lisu" Unicode character block.
2117 * @since 1.7
2118 */
2119 public static final UnicodeBlock LISU =
2120 new UnicodeBlock("LISU");
2121
2122 /**
2123 * Constant for the "Vai" Unicode character block.
2124 * @since 1.7
2125 */
2126 public static final UnicodeBlock VAI =
2127 new UnicodeBlock("VAI");
2128
2129 /**
2130 * Constant for the "Cyrillic Extended-B" Unicode character block.
2131 * @since 1.7
2132 */
2133 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2134 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2135 "CYRILLIC EXTENDED-B",
2136 "CYRILLICEXTENDED-B");
2137
2138 /**
2139 * Constant for the "Bamum" Unicode character block.
2140 * @since 1.7
2141 */
2142 public static final UnicodeBlock BAMUM =
2143 new UnicodeBlock("BAMUM");
2144
2145 /**
2146 * Constant for the "Modifier Tone Letters" Unicode character block.
2147 * @since 1.7
2148 */
2149 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2150 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2151 "MODIFIER TONE LETTERS",
2152 "MODIFIERTONELETTERS");
2153
2154 /**
2155 * Constant for the "Latin Extended-D" Unicode character block.
2156 * @since 1.7
2157 */
2158 public static final UnicodeBlock LATIN_EXTENDED_D =
2159 new UnicodeBlock("LATIN_EXTENDED_D",
2160 "LATIN EXTENDED-D",
2161 "LATINEXTENDED-D");
2162
2163 /**
2164 * Constant for the "Syloti Nagri" Unicode character block.
2165 * @since 1.7
2166 */
2167 public static final UnicodeBlock SYLOTI_NAGRI =
2168 new UnicodeBlock("SYLOTI_NAGRI",
2169 "SYLOTI NAGRI",
2170 "SYLOTINAGRI");
2171
2172 /**
2173 * Constant for the "Common Indic Number Forms" Unicode character block.
2174 * @since 1.7
2175 */
2176 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2177 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2178 "COMMON INDIC NUMBER FORMS",
2179 "COMMONINDICNUMBERFORMS");
2180
2181 /**
2182 * Constant for the "Phags-pa" Unicode character block.
2183 * @since 1.7
2184 */
2185 public static final UnicodeBlock PHAGS_PA =
2186 new UnicodeBlock("PHAGS_PA",
2187 "PHAGS-PA");
2188
2189 /**
2190 * Constant for the "Saurashtra" Unicode character block.
2191 * @since 1.7
2192 */
2193 public static final UnicodeBlock SAURASHTRA =
2194 new UnicodeBlock("SAURASHTRA");
2195
2196 /**
2197 * Constant for the "Devanagari Extended" Unicode character block.
2198 * @since 1.7
2199 */
2200 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2201 new UnicodeBlock("DEVANAGARI_EXTENDED",
2202 "DEVANAGARI EXTENDED",
2203 "DEVANAGARIEXTENDED");
2204
2205 /**
2206 * Constant for the "Kayah Li" Unicode character block.
2207 * @since 1.7
2208 */
2209 public static final UnicodeBlock KAYAH_LI =
2210 new UnicodeBlock("KAYAH_LI",
2211 "KAYAH LI",
2212 "KAYAHLI");
2213
2214 /**
2215 * Constant for the "Rejang" Unicode character block.
2216 * @since 1.7
2217 */
2218 public static final UnicodeBlock REJANG =
2219 new UnicodeBlock("REJANG");
2220
2221 /**
2222 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2223 * @since 1.7
2224 */
2225 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2226 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2227 "HANGUL JAMO EXTENDED-A",
2228 "HANGULJAMOEXTENDED-A");
2229
2230 /**
2231 * Constant for the "Javanese" Unicode character block.
2232 * @since 1.7
2233 */
2234 public static final UnicodeBlock JAVANESE =
2235 new UnicodeBlock("JAVANESE");
2236
2237 /**
2238 * Constant for the "Cham" Unicode character block.
2239 * @since 1.7
2240 */
2241 public static final UnicodeBlock CHAM =
2242 new UnicodeBlock("CHAM");
2243
2244 /**
2245 * Constant for the "Myanmar Extended-A" Unicode character block.
2246 * @since 1.7
2247 */
2248 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2249 new UnicodeBlock("MYANMAR_EXTENDED_A",
2250 "MYANMAR EXTENDED-A",
2251 "MYANMAREXTENDED-A");
2252
2253 /**
2254 * Constant for the "Tai Viet" Unicode character block.
2255 * @since 1.7
2256 */
2257 public static final UnicodeBlock TAI_VIET =
2258 new UnicodeBlock("TAI_VIET",
2259 "TAI VIET",
2260 "TAIVIET");
2261
2262 /**
2263 * Constant for the "Ethiopic Extended-A" Unicode character block.
2264 * @since 1.7
2265 */
2266 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2267 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2268 "ETHIOPIC EXTENDED-A",
2269 "ETHIOPICEXTENDED-A");
2270
2271 /**
2272 * Constant for the "Meetei Mayek" Unicode character block.
2273 * @since 1.7
2274 */
2275 public static final UnicodeBlock MEETEI_MAYEK =
2276 new UnicodeBlock("MEETEI_MAYEK",
2277 "MEETEI MAYEK",
2278 "MEETEIMAYEK");
2279
2280 /**
2281 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2282 * @since 1.7
2283 */
2284 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2285 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2286 "HANGUL JAMO EXTENDED-B",
2287 "HANGULJAMOEXTENDED-B");
2288
2289 /**
2290 * Constant for the "Vertical Forms" Unicode character block.
2291 * @since 1.7
2292 */
2293 public static final UnicodeBlock VERTICAL_FORMS =
2294 new UnicodeBlock("VERTICAL_FORMS",
2295 "VERTICAL FORMS",
2296 "VERTICALFORMS");
2297
2298 /**
2299 * Constant for the "Ancient Greek Numbers" Unicode character block.
2300 * @since 1.7
2301 */
2302 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2303 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2304 "ANCIENT GREEK NUMBERS",
2305 "ANCIENTGREEKNUMBERS");
2306
2307 /**
2308 * Constant for the "Ancient Symbols" Unicode character block.
2309 * @since 1.7
2310 */
2311 public static final UnicodeBlock ANCIENT_SYMBOLS =
2312 new UnicodeBlock("ANCIENT_SYMBOLS",
2313 "ANCIENT SYMBOLS",
2314 "ANCIENTSYMBOLS");
2315
2316 /**
2317 * Constant for the "Phaistos Disc" Unicode character block.
2318 * @since 1.7
2319 */
2320 public static final UnicodeBlock PHAISTOS_DISC =
2321 new UnicodeBlock("PHAISTOS_DISC",
2322 "PHAISTOS DISC",
2323 "PHAISTOSDISC");
2324
2325 /**
2326 * Constant for the "Lycian" Unicode character block.
2327 * @since 1.7
2328 */
2329 public static final UnicodeBlock LYCIAN =
2330 new UnicodeBlock("LYCIAN");
2331
2332 /**
2333 * Constant for the "Carian" Unicode character block.
2334 * @since 1.7
2335 */
2336 public static final UnicodeBlock CARIAN =
2337 new UnicodeBlock("CARIAN");
2338
2339 /**
2340 * Constant for the "Old Persian" Unicode character block.
2341 * @since 1.7
2342 */
2343 public static final UnicodeBlock OLD_PERSIAN =
2344 new UnicodeBlock("OLD_PERSIAN",
2345 "OLD PERSIAN",
2346 "OLDPERSIAN");
2347
2348 /**
2349 * Constant for the "Imperial Aramaic" Unicode character block.
2350 * @since 1.7
2351 */
2352 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2353 new UnicodeBlock("IMPERIAL_ARAMAIC",
2354 "IMPERIAL ARAMAIC",
2355 "IMPERIALARAMAIC");
2356
2357 /**
2358 * Constant for the "Phoenician" Unicode character block.
2359 * @since 1.7
2360 */
2361 public static final UnicodeBlock PHOENICIAN =
2362 new UnicodeBlock("PHOENICIAN");
2363
2364 /**
2365 * Constant for the "Lydian" Unicode character block.
2366 * @since 1.7
2367 */
2368 public static final UnicodeBlock LYDIAN =
2369 new UnicodeBlock("LYDIAN");
2370
2371 /**
2372 * Constant for the "Kharoshthi" Unicode character block.
2373 * @since 1.7
2374 */
2375 public static final UnicodeBlock KHAROSHTHI =
2376 new UnicodeBlock("KHAROSHTHI");
2377
2378 /**
2379 * Constant for the "Old South Arabian" Unicode character block.
2380 * @since 1.7
2381 */
2382 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2383 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2384 "OLD SOUTH ARABIAN",
2385 "OLDSOUTHARABIAN");
2386
2387 /**
2388 * Constant for the "Avestan" Unicode character block.
2389 * @since 1.7
2390 */
2391 public static final UnicodeBlock AVESTAN =
2392 new UnicodeBlock("AVESTAN");
2393
2394 /**
2395 * Constant for the "Inscriptional Parthian" Unicode character block.
2396 * @since 1.7
2397 */
2398 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2399 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2400 "INSCRIPTIONAL PARTHIAN",
2401 "INSCRIPTIONALPARTHIAN");
2402
2403 /**
2404 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2405 * @since 1.7
2406 */
2407 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2408 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2409 "INSCRIPTIONAL PAHLAVI",
2410 "INSCRIPTIONALPAHLAVI");
2411
2412 /**
2413 * Constant for the "Old Turkic" Unicode character block.
2414 * @since 1.7
2415 */
2416 public static final UnicodeBlock OLD_TURKIC =
2417 new UnicodeBlock("OLD_TURKIC",
2418 "OLD TURKIC",
2419 "OLDTURKIC");
2420
2421 /**
2422 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2423 * @since 1.7
2424 */
2425 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2426 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2427 "RUMI NUMERAL SYMBOLS",
2428 "RUMINUMERALSYMBOLS");
2429
2430 /**
2431 * Constant for the "Brahmi" Unicode character block.
2432 * @since 1.7
2433 */
2434 public static final UnicodeBlock BRAHMI =
2435 new UnicodeBlock("BRAHMI");
2436
2437 /**
2438 * Constant for the "Kaithi" Unicode character block.
2439 * @since 1.7
2440 */
2441 public static final UnicodeBlock KAITHI =
2442 new UnicodeBlock("KAITHI");
2443
2444 /**
2445 * Constant for the "Cuneiform" Unicode character block.
2446 * @since 1.7
2447 */
2448 public static final UnicodeBlock CUNEIFORM =
2449 new UnicodeBlock("CUNEIFORM");
2450
2451 /**
2452 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2453 * character block.
2454 * @since 1.7
2455 */
2456 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2457 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2458 "CUNEIFORM NUMBERS AND PUNCTUATION",
2459 "CUNEIFORMNUMBERSANDPUNCTUATION");
2460
2461 /**
2462 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2463 * @since 1.7
2464 */
2465 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2466 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2467 "EGYPTIAN HIEROGLYPHS",
2468 "EGYPTIANHIEROGLYPHS");
2469
2470 /**
2471 * Constant for the "Bamum Supplement" Unicode character block.
2472 * @since 1.7
2473 */
2474 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2475 new UnicodeBlock("BAMUM_SUPPLEMENT",
2476 "BAMUM SUPPLEMENT",
2477 "BAMUMSUPPLEMENT");
2478
2479 /**
2480 * Constant for the "Kana Supplement" Unicode character block.
2481 * @since 1.7
2482 */
2483 public static final UnicodeBlock KANA_SUPPLEMENT =
2484 new UnicodeBlock("KANA_SUPPLEMENT",
2485 "KANA SUPPLEMENT",
2486 "KANASUPPLEMENT");
2487
2488 /**
2489 * Constant for the "Ancient Greek Musical Notation" Unicode character
2490 * block.
2491 * @since 1.7
2492 */
2493 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2494 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2495 "ANCIENT GREEK MUSICAL NOTATION",
2496 "ANCIENTGREEKMUSICALNOTATION");
2497
2498 /**
2499 * Constant for the "Counting Rod Numerals" Unicode character block.
2500 * @since 1.7
2501 */
2502 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2503 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2504 "COUNTING ROD NUMERALS",
2505 "COUNTINGRODNUMERALS");
2506
2507 /**
2508 * Constant for the "Mahjong Tiles" Unicode character block.
2509 * @since 1.7
2510 */
2511 public static final UnicodeBlock MAHJONG_TILES =
2512 new UnicodeBlock("MAHJONG_TILES",
2513 "MAHJONG TILES",
2514 "MAHJONGTILES");
2515
2516 /**
2517 * Constant for the "Domino Tiles" Unicode character block.
2518 * @since 1.7
2519 */
2520 public static final UnicodeBlock DOMINO_TILES =
2521 new UnicodeBlock("DOMINO_TILES",
2522 "DOMINO TILES",
2523 "DOMINOTILES");
2524
2525 /**
2526 * Constant for the "Playing Cards" Unicode character block.
2527 * @since 1.7
2528 */
2529 public static final UnicodeBlock PLAYING_CARDS =
2530 new UnicodeBlock("PLAYING_CARDS",
2531 "PLAYING CARDS",
2532 "PLAYINGCARDS");
2533
2534 /**
2535 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2536 * block.
2537 * @since 1.7
2538 */
2539 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2540 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2541 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2542 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2543
2544 /**
2545 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2546 * block.
2547 * @since 1.7
2548 */
2549 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2550 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2551 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2552 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2553
2554 /**
2555 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2556 * character block.
2557 * @since 1.7
2558 */
2559 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2560 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2561 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2562 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2563
2564 /**
2565 * Constant for the "Emoticons" Unicode character block.
2566 * @since 1.7
2567 */
2568 public static final UnicodeBlock EMOTICONS =
2569 new UnicodeBlock("EMOTICONS");
2570
2571 /**
2572 * Constant for the "Transport And Map Symbols" Unicode character block.
2573 * @since 1.7
2574 */
2575 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2576 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2577 "TRANSPORT AND MAP SYMBOLS",
2578 "TRANSPORTANDMAPSYMBOLS");
2579
2580 /**
2581 * Constant for the "Alchemical Symbols" Unicode character block.
2582 * @since 1.7
2583 */
2584 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2585 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2586 "ALCHEMICAL SYMBOLS",
2587 "ALCHEMICALSYMBOLS");
2588
2589 /**
2590 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2591 * character block.
2592 * @since 1.7
2593 */
2594 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2595 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2596 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2597 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2598
2599 /**
2600 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2601 * character block.
2602 * @since 1.7
2603 */
2604 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2605 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2606 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2607 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2608
2609 /**
2610 * Constant for the "Arabic Extended-A" Unicode character block.
2611 * @since 1.8
2612 */
2613 public static final UnicodeBlock ARABIC_EXTENDED_A =
2614 new UnicodeBlock("ARABIC_EXTENDED_A",
2615 "ARABIC EXTENDED-A",
2616 "ARABICEXTENDED-A");
2617
2618 /**
2619 * Constant for the "Sundanese Supplement" Unicode character block.
2620 * @since 1.8
2621 */
2622 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2623 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2624 "SUNDANESE SUPPLEMENT",
2625 "SUNDANESESUPPLEMENT");
2626
2627 /**
2628 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2629 * @since 1.8
2630 */
2631 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2632 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2633 "MEETEI MAYEK EXTENSIONS",
2634 "MEETEIMAYEKEXTENSIONS");
2635
2636 /**
2637 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2638 * @since 1.8
2639 */
2640 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2641 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2642 "MEROITIC HIEROGLYPHS",
2643 "MEROITICHIEROGLYPHS");
2644
2645 /**
2646 * Constant for the "Meroitic Cursive" Unicode character block.
2647 * @since 1.8
2648 */
2649 public static final UnicodeBlock MEROITIC_CURSIVE =
2650 new UnicodeBlock("MEROITIC_CURSIVE",
2651 "MEROITIC CURSIVE",
2652 "MEROITICCURSIVE");
2653
2654 /**
2655 * Constant for the "Sora Sompeng" Unicode character block.
2656 * @since 1.8
2657 */
2658 public static final UnicodeBlock SORA_SOMPENG =
2659 new UnicodeBlock("SORA_SOMPENG",
2660 "SORA SOMPENG",
2661 "SORASOMPENG");
2662
2663 /**
2664 * Constant for the "Chakma" Unicode character block.
2665 * @since 1.8
2666 */
2667 public static final UnicodeBlock CHAKMA =
2668 new UnicodeBlock("CHAKMA");
2669
2670 /**
2671 * Constant for the "Sharada" Unicode character block.
2672 * @since 1.8
2673 */
2674 public static final UnicodeBlock SHARADA =
2675 new UnicodeBlock("SHARADA");
2676
2677 /**
2678 * Constant for the "Takri" Unicode character block.
2679 * @since 1.8
2680 */
2681 public static final UnicodeBlock TAKRI =
2682 new UnicodeBlock("TAKRI");
2683
2684 /**
2685 * Constant for the "Miao" Unicode character block.
2686 * @since 1.8
2687 */
2688 public static final UnicodeBlock MIAO =
2689 new UnicodeBlock("MIAO");
2690
2691 /**
2692 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2693 * character block.
2694 * @since 1.8
2695 */
2696 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2697 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2698 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2699 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2700
2701 /**
2702 * Constant for the "Combining Diacritical Marks Extended" Unicode
2703 * character block.
2704 * @since 9
2705 */
2706 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2707 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2708 "COMBINING DIACRITICAL MARKS EXTENDED",
2709 "COMBININGDIACRITICALMARKSEXTENDED");
2710
2711 /**
2712 * Constant for the "Myanmar Extended-B" Unicode character block.
2713 * @since 9
2714 */
2715 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2716 new UnicodeBlock("MYANMAR_EXTENDED_B",
2717 "MYANMAR EXTENDED-B",
2718 "MYANMAREXTENDED-B");
2719
2720 /**
2721 * Constant for the "Latin Extended-E" Unicode character block.
2722 * @since 9
2723 */
2724 public static final UnicodeBlock LATIN_EXTENDED_E =
2725 new UnicodeBlock("LATIN_EXTENDED_E",
2726 "LATIN EXTENDED-E",
2727 "LATINEXTENDED-E");
2728
2729 /**
2730 * Constant for the "Coptic Epact Numbers" Unicode character block.
2731 * @since 9
2732 */
2733 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2734 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2735 "COPTIC EPACT NUMBERS",
2736 "COPTICEPACTNUMBERS");
2737
2738 /**
2739 * Constant for the "Old Permic" Unicode character block.
2740 * @since 9
2741 */
2742 public static final UnicodeBlock OLD_PERMIC =
2743 new UnicodeBlock("OLD_PERMIC",
2744 "OLD PERMIC",
2745 "OLDPERMIC");
2746
2747 /**
2748 * Constant for the "Elbasan" Unicode character block.
2749 * @since 9
2750 */
2751 public static final UnicodeBlock ELBASAN =
2752 new UnicodeBlock("ELBASAN");
2753
2754 /**
2755 * Constant for the "Caucasian Albanian" Unicode character block.
2756 * @since 9
2757 */
2758 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2759 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2760 "CAUCASIAN ALBANIAN",
2761 "CAUCASIANALBANIAN");
2762
2763 /**
2764 * Constant for the "Linear A" Unicode character block.
2765 * @since 9
2766 */
2767 public static final UnicodeBlock LINEAR_A =
2768 new UnicodeBlock("LINEAR_A",
2769 "LINEAR A",
2770 "LINEARA");
2771
2772 /**
2773 * Constant for the "Palmyrene" Unicode character block.
2774 * @since 9
2775 */
2776 public static final UnicodeBlock PALMYRENE =
2777 new UnicodeBlock("PALMYRENE");
2778
2779 /**
2780 * Constant for the "Nabataean" Unicode character block.
2781 * @since 9
2782 */
2783 public static final UnicodeBlock NABATAEAN =
2784 new UnicodeBlock("NABATAEAN");
2785
2786 /**
2787 * Constant for the "Old North Arabian" Unicode character block.
2788 * @since 9
2789 */
2790 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2791 new UnicodeBlock("OLD_NORTH_ARABIAN",
2792 "OLD NORTH ARABIAN",
2793 "OLDNORTHARABIAN");
2794
2795 /**
2796 * Constant for the "Manichaean" Unicode character block.
2797 * @since 9
2798 */
2799 public static final UnicodeBlock MANICHAEAN =
2800 new UnicodeBlock("MANICHAEAN");
2801
2802 /**
2803 * Constant for the "Psalter Pahlavi" Unicode character block.
2804 * @since 9
2805 */
2806 public static final UnicodeBlock PSALTER_PAHLAVI =
2807 new UnicodeBlock("PSALTER_PAHLAVI",
2808 "PSALTER PAHLAVI",
2809 "PSALTERPAHLAVI");
2810
2811 /**
2812 * Constant for the "Mahajani" Unicode character block.
2813 * @since 9
2814 */
2815 public static final UnicodeBlock MAHAJANI =
2816 new UnicodeBlock("MAHAJANI");
2817
2818 /**
2819 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2820 * @since 9
2821 */
2822 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2823 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2824 "SINHALA ARCHAIC NUMBERS",
2825 "SINHALAARCHAICNUMBERS");
2826
2827 /**
2828 * Constant for the "Khojki" Unicode character block.
2829 * @since 9
2830 */
2831 public static final UnicodeBlock KHOJKI =
2832 new UnicodeBlock("KHOJKI");
2833
2834 /**
2835 * Constant for the "Khudawadi" Unicode character block.
2836 * @since 9
2837 */
2838 public static final UnicodeBlock KHUDAWADI =
2839 new UnicodeBlock("KHUDAWADI");
2840
2841 /**
2842 * Constant for the "Grantha" Unicode character block.
2843 * @since 9
2844 */
2845 public static final UnicodeBlock GRANTHA =
2846 new UnicodeBlock("GRANTHA");
2847
2848 /**
2849 * Constant for the "Tirhuta" Unicode character block.
2850 * @since 9
2851 */
2852 public static final UnicodeBlock TIRHUTA =
2853 new UnicodeBlock("TIRHUTA");
2854
2855 /**
2856 * Constant for the "Siddham" Unicode character block.
2857 * @since 9
2858 */
2859 public static final UnicodeBlock SIDDHAM =
2860 new UnicodeBlock("SIDDHAM");
2861
2862 /**
2863 * Constant for the "Modi" Unicode character block.
2864 * @since 9
2865 */
2866 public static final UnicodeBlock MODI =
2867 new UnicodeBlock("MODI");
2868
2869 /**
2870 * Constant for the "Warang Citi" Unicode character block.
2871 * @since 9
2872 */
2873 public static final UnicodeBlock WARANG_CITI =
2874 new UnicodeBlock("WARANG_CITI",
2875 "WARANG CITI",
2876 "WARANGCITI");
2877
2878 /**
2879 * Constant for the "Pau Cin Hau" Unicode character block.
2880 * @since 9
2881 */
2882 public static final UnicodeBlock PAU_CIN_HAU =
2883 new UnicodeBlock("PAU_CIN_HAU",
2884 "PAU CIN HAU",
2885 "PAUCINHAU");
2886
2887 /**
2888 * Constant for the "Mro" Unicode character block.
2889 * @since 9
2890 */
2891 public static final UnicodeBlock MRO =
2892 new UnicodeBlock("MRO");
2893
2894 /**
2895 * Constant for the "Bassa Vah" Unicode character block.
2896 * @since 9
2897 */
2898 public static final UnicodeBlock BASSA_VAH =
2899 new UnicodeBlock("BASSA_VAH",
2900 "BASSA VAH",
2901 "BASSAVAH");
2902
2903 /**
2904 * Constant for the "Pahawh Hmong" Unicode character block.
2905 * @since 9
2906 */
2907 public static final UnicodeBlock PAHAWH_HMONG =
2908 new UnicodeBlock("PAHAWH_HMONG",
2909 "PAHAWH HMONG",
2910 "PAHAWHHMONG");
2911
2912 /**
2913 * Constant for the "Duployan" Unicode character block.
2914 * @since 9
2915 */
2916 public static final UnicodeBlock DUPLOYAN =
2917 new UnicodeBlock("DUPLOYAN");
2918
2919 /**
2920 * Constant for the "Shorthand Format Controls" Unicode character block.
2921 * @since 9
2922 */
2923 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2924 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2925 "SHORTHAND FORMAT CONTROLS",
2926 "SHORTHANDFORMATCONTROLS");
2927
2928 /**
2929 * Constant for the "Mende Kikakui" Unicode character block.
2930 * @since 9
2931 */
2932 public static final UnicodeBlock MENDE_KIKAKUI =
2933 new UnicodeBlock("MENDE_KIKAKUI",
2934 "MENDE KIKAKUI",
2935 "MENDEKIKAKUI");
2936
2937 /**
2938 * Constant for the "Ornamental Dingbats" Unicode character block.
2939 * @since 9
2940 */
2941 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2942 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2943 "ORNAMENTAL DINGBATS",
2944 "ORNAMENTALDINGBATS");
2945
2946 /**
2947 * Constant for the "Geometric Shapes Extended" Unicode character block.
2948 * @since 9
2949 */
2950 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2951 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2952 "GEOMETRIC SHAPES EXTENDED",
2953 "GEOMETRICSHAPESEXTENDED");
2954
2955 /**
2956 * Constant for the "Supplemental Arrows-C" Unicode character block.
2957 * @since 9
2958 */
2959 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2960 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2961 "SUPPLEMENTAL ARROWS-C",
2962 "SUPPLEMENTALARROWS-C");
2963
2964 /**
2965 * Constant for the "Cherokee Supplement" Unicode character block.
2966 * @since 9
2967 */
2968 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2969 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2970 "CHEROKEE SUPPLEMENT",
2971 "CHEROKEESUPPLEMENT");
2972
2973 /**
2974 * Constant for the "Hatran" Unicode character block.
2975 * @since 9
2976 */
2977 public static final UnicodeBlock HATRAN =
2978 new UnicodeBlock("HATRAN");
2979
2980 /**
2981 * Constant for the "Old Hungarian" Unicode character block.
2982 * @since 9
2983 */
2984 public static final UnicodeBlock OLD_HUNGARIAN =
2985 new UnicodeBlock("OLD_HUNGARIAN",
2986 "OLD HUNGARIAN",
2987 "OLDHUNGARIAN");
2988
2989 /**
2990 * Constant for the "Multani" Unicode character block.
2991 * @since 9
2992 */
2993 public static final UnicodeBlock MULTANI =
2994 new UnicodeBlock("MULTANI");
2995
2996 /**
2997 * Constant for the "Ahom" Unicode character block.
2998 * @since 9
2999 */
3000 public static final UnicodeBlock AHOM =
3001 new UnicodeBlock("AHOM");
3002
3003 /**
3004 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
3005 * @since 9
3006 */
3007 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
3008 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
3009 "EARLY DYNASTIC CUNEIFORM",
3010 "EARLYDYNASTICCUNEIFORM");
3011
3012 /**
3013 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
3014 * @since 9
3015 */
3016 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
3017 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
3018 "ANATOLIAN HIEROGLYPHS",
3019 "ANATOLIANHIEROGLYPHS");
3020
3021 /**
3022 * Constant for the "Sutton SignWriting" Unicode character block.
3023 * @since 9
3024 */
3025 public static final UnicodeBlock SUTTON_SIGNWRITING =
3026 new UnicodeBlock("SUTTON_SIGNWRITING",
3027 "SUTTON SIGNWRITING",
3028 "SUTTONSIGNWRITING");
3029
3030 /**
3031 * Constant for the "Supplemental Symbols and Pictographs" Unicode
3032 * character block.
3033 * @since 9
3034 */
3035 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
3036 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
3037 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
3038 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3039
3040 /**
3041 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3042 * character block.
3043 * @since 9
3044 */
3045 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3046 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3047 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3048 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3049
3050 /**
3051 * Constant for the "Syriac Supplement" Unicode
3052 * character block.
3053 * @since 11
3054 */
3055 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3056 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3057 "SYRIAC SUPPLEMENT",
3058 "SYRIACSUPPLEMENT");
3059
3060 /**
3061 * Constant for the "Cyrillic Extended-C" Unicode
3062 * character block.
3063 * @since 11
3064 */
3065 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3066 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3067 "CYRILLIC EXTENDED-C",
3068 "CYRILLICEXTENDED-C");
3069
3070 /**
3071 * Constant for the "Osage" Unicode
3072 * character block.
3073 * @since 11
3074 */
3075 public static final UnicodeBlock OSAGE =
3076 new UnicodeBlock("OSAGE");
3077
3078 /**
3079 * Constant for the "Newa" Unicode
3080 * character block.
3081 * @since 11
3082 */
3083 public static final UnicodeBlock NEWA =
3084 new UnicodeBlock("NEWA");
3085
3086 /**
3087 * Constant for the "Mongolian Supplement" Unicode
3088 * character block.
3089 * @since 11
3090 */
3091 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3092 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3093 "MONGOLIAN SUPPLEMENT",
3094 "MONGOLIANSUPPLEMENT");
3095
3096 /**
3097 * Constant for the "Marchen" Unicode
3098 * character block.
3099 * @since 11
3100 */
3101 public static final UnicodeBlock MARCHEN =
3102 new UnicodeBlock("MARCHEN");
3103
3104 /**
3105 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3106 * character block.
3107 * @since 11
3108 */
3109 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3110 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3111 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3112 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3113
3114 /**
3115 * Constant for the "Tangut" Unicode
3116 * character block.
3117 * @since 11
3118 */
3119 public static final UnicodeBlock TANGUT =
3120 new UnicodeBlock("TANGUT");
3121
3122 /**
3123 * Constant for the "Tangut Components" Unicode
3124 * character block.
3125 * @since 11
3126 */
3127 public static final UnicodeBlock TANGUT_COMPONENTS =
3128 new UnicodeBlock("TANGUT_COMPONENTS",
3129 "TANGUT COMPONENTS",
3130 "TANGUTCOMPONENTS");
3131
3132 /**
3133 * Constant for the "Kana Extended-A" Unicode
3134 * character block.
3135 * @since 11
3136 */
3137 public static final UnicodeBlock KANA_EXTENDED_A =
3138 new UnicodeBlock("KANA_EXTENDED_A",
3139 "KANA EXTENDED-A",
3140 "KANAEXTENDED-A");
3141 /**
3142 * Constant for the "Glagolitic Supplement" Unicode
3143 * character block.
3144 * @since 11
3145 */
3146 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3147 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3148 "GLAGOLITIC SUPPLEMENT",
3149 "GLAGOLITICSUPPLEMENT");
3150 /**
3151 * Constant for the "Adlam" Unicode
3152 * character block.
3153 * @since 11
3154 */
3155 public static final UnicodeBlock ADLAM =
3156 new UnicodeBlock("ADLAM");
3157
3158 /**
3159 * Constant for the "Masaram Gondi" Unicode
3160 * character block.
3161 * @since 11
3162 */
3163 public static final UnicodeBlock MASARAM_GONDI =
3164 new UnicodeBlock("MASARAM_GONDI",
3165 "MASARAM GONDI",
3166 "MASARAMGONDI");
3167
3168 /**
3169 * Constant for the "Zanabazar Square" Unicode
3170 * character block.
3171 * @since 11
3172 */
3173 public static final UnicodeBlock ZANABAZAR_SQUARE =
3174 new UnicodeBlock("ZANABAZAR_SQUARE",
3175 "ZANABAZAR SQUARE",
3176 "ZANABAZARSQUARE");
3177
3178 /**
3179 * Constant for the "Nushu" Unicode
3180 * character block.
3181 * @since 11
3182 */
3183 public static final UnicodeBlock NUSHU =
3184 new UnicodeBlock("NUSHU");
3185
3186 /**
3187 * Constant for the "Soyombo" Unicode
3188 * character block.
3189 * @since 11
3190 */
3191 public static final UnicodeBlock SOYOMBO =
3192 new UnicodeBlock("SOYOMBO");
3193
3194 /**
3195 * Constant for the "Bhaiksuki" Unicode
3196 * character block.
3197 * @since 11
3198 */
3199 public static final UnicodeBlock BHAIKSUKI =
3200 new UnicodeBlock("BHAIKSUKI");
3201
3202 /**
3203 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3204 * character block.
3205 * @since 11
3206 */
3207 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3208 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3209 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3210 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3211 /**
3212 * Constant for the "Georgian Extended" Unicode
3213 * character block.
3214 * @since 12
3215 */
3216 public static final UnicodeBlock GEORGIAN_EXTENDED =
3217 new UnicodeBlock("GEORGIAN_EXTENDED",
3218 "GEORGIAN EXTENDED",
3219 "GEORGIANEXTENDED");
3220
3221 /**
3222 * Constant for the "Hanifi Rohingya" Unicode
3223 * character block.
3224 * @since 12
3225 */
3226 public static final UnicodeBlock HANIFI_ROHINGYA =
3227 new UnicodeBlock("HANIFI_ROHINGYA",
3228 "HANIFI ROHINGYA",
3229 "HANIFIROHINGYA");
3230
3231 /**
3232 * Constant for the "Old Sogdian" Unicode
3233 * character block.
3234 * @since 12
3235 */
3236 public static final UnicodeBlock OLD_SOGDIAN =
3237 new UnicodeBlock("OLD_SOGDIAN",
3238 "OLD SOGDIAN",
3239 "OLDSOGDIAN");
3240
3241 /**
3242 * Constant for the "Sogdian" Unicode
3243 * character block.
3244 * @since 12
3245 */
3246 public static final UnicodeBlock SOGDIAN =
3247 new UnicodeBlock("SOGDIAN");
3248
3249 /**
3250 * Constant for the "Dogra" Unicode
3251 * character block.
3252 * @since 12
3253 */
3254 public static final UnicodeBlock DOGRA =
3255 new UnicodeBlock("DOGRA");
3256
3257 /**
3258 * Constant for the "Gunjala Gondi" Unicode
3259 * character block.
3260 * @since 12
3261 */
3262 public static final UnicodeBlock GUNJALA_GONDI =
3263 new UnicodeBlock("GUNJALA_GONDI",
3264 "GUNJALA GONDI",
3265 "GUNJALAGONDI");
3266
3267 /**
3268 * Constant for the "Makasar" Unicode
3269 * character block.
3270 * @since 12
3271 */
3272 public static final UnicodeBlock MAKASAR =
3273 new UnicodeBlock("MAKASAR");
3274
3275 /**
3276 * Constant for the "Medefaidrin" Unicode
3277 * character block.
3278 * @since 12
3279 */
3280 public static final UnicodeBlock MEDEFAIDRIN =
3281 new UnicodeBlock("MEDEFAIDRIN");
3282
3283 /**
3284 * Constant for the "Mayan Numerals" Unicode
3285 * character block.
3286 * @since 12
3287 */
3288 public static final UnicodeBlock MAYAN_NUMERALS =
3289 new UnicodeBlock("MAYAN_NUMERALS",
3290 "MAYAN NUMERALS",
3291 "MAYANNUMERALS");
3292
3293 /**
3294 * Constant for the "Indic Siyaq Numbers" Unicode
3295 * character block.
3296 * @since 12
3297 */
3298 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3299 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3300 "INDIC SIYAQ NUMBERS",
3301 "INDICSIYAQNUMBERS");
3302
3303 /**
3304 * Constant for the "Chess Symbols" Unicode
3305 * character block.
3306 * @since 12
3307 */
3308 public static final UnicodeBlock CHESS_SYMBOLS =
3309 new UnicodeBlock("CHESS_SYMBOLS",
3310 "CHESS SYMBOLS",
3311 "CHESSSYMBOLS");
3312
3313 /**
3314 * Constant for the "Elymaic" Unicode
3315 * character block.
3316 * @since 13
3317 */
3318 public static final UnicodeBlock ELYMAIC =
3319 new UnicodeBlock("ELYMAIC");
3320
3321 /**
3322 * Constant for the "Nandinagari" Unicode
3323 * character block.
3324 * @since 13
3325 */
3326 public static final UnicodeBlock NANDINAGARI =
3327 new UnicodeBlock("NANDINAGARI");
3328
3329 /**
3330 * Constant for the "Tamil Supplement" Unicode
3331 * character block.
3332 * @since 13
3333 */
3334 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3335 new UnicodeBlock("TAMIL_SUPPLEMENT",
3336 "TAMIL SUPPLEMENT",
3337 "TAMILSUPPLEMENT");
3338
3339 /**
3340 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3341 * character block.
3342 * @since 13
3343 */
3344 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3345 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3346 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3347 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3348
3349 /**
3350 * Constant for the "Small Kana Extension" Unicode
3351 * character block.
3352 * @since 13
3353 */
3354 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3355 new UnicodeBlock("SMALL_KANA_EXTENSION",
3356 "SMALL KANA EXTENSION",
3357 "SMALLKANAEXTENSION");
3358
3359 /**
3360 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3361 * character block.
3362 * @since 13
3363 */
3364 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3365 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3366 "NYIAKENG PUACHUE HMONG",
3367 "NYIAKENGPUACHUEHMONG");
3368
3369 /**
3370 * Constant for the "Wancho" Unicode
3371 * character block.
3372 * @since 13
3373 */
3374 public static final UnicodeBlock WANCHO =
3375 new UnicodeBlock("WANCHO");
3376
3377 /**
3378 * Constant for the "Ottoman Siyaq Numbers" Unicode
3379 * character block.
3380 * @since 13
3381 */
3382 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3383 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3384 "OTTOMAN SIYAQ NUMBERS",
3385 "OTTOMANSIYAQNUMBERS");
3386
3387 /**
3388 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3389 * character block.
3390 * @since 13
3391 */
3392 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3393 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3394 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3395 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3396
3397 /**
3398 * Constant for the "Yezidi" Unicode
3399 * character block.
3400 * @since 15
3401 */
3402 public static final UnicodeBlock YEZIDI =
3403 new UnicodeBlock("YEZIDI");
3404
3405 /**
3406 * Constant for the "Chorasmian" Unicode
3407 * character block.
3408 * @since 15
3409 */
3410 public static final UnicodeBlock CHORASMIAN =
3411 new UnicodeBlock("CHORASMIAN");
3412
3413 /**
3414 * Constant for the "Dives Akuru" Unicode
3415 * character block.
3416 * @since 15
3417 */
3418 public static final UnicodeBlock DIVES_AKURU =
3419 new UnicodeBlock("DIVES_AKURU",
3420 "DIVES AKURU",
3421 "DIVESAKURU");
3422
3423 /**
3424 * Constant for the "Lisu Supplement" Unicode
3425 * character block.
3426 * @since 15
3427 */
3428 public static final UnicodeBlock LISU_SUPPLEMENT =
3429 new UnicodeBlock("LISU_SUPPLEMENT",
3430 "LISU SUPPLEMENT",
3431 "LISUSUPPLEMENT");
3432
3433 /**
3434 * Constant for the "Khitan Small Script" Unicode
3435 * character block.
3436 * @since 15
3437 */
3438 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3439 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3440 "KHITAN SMALL SCRIPT",
3441 "KHITANSMALLSCRIPT");
3442
3443 /**
3444 * Constant for the "Tangut Supplement" Unicode
3445 * character block.
3446 * @since 15
3447 */
3448 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3449 new UnicodeBlock("TANGUT_SUPPLEMENT",
3450 "TANGUT SUPPLEMENT",
3451 "TANGUTSUPPLEMENT");
3452
3453 /**
3454 * Constant for the "Symbols for Legacy Computing" Unicode
3455 * character block.
3456 * @since 15
3457 */
3458 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3459 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3460 "SYMBOLS FOR LEGACY COMPUTING",
3461 "SYMBOLSFORLEGACYCOMPUTING");
3462
3463 /**
3464 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3465 * character block.
3466 * @since 15
3467 */
3468 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3469 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3470 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3471 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3472
3473 /**
3474 * Constant for the "Arabic Extended-B" Unicode
3475 * character block.
3476 * @since 19
3477 */
3478 public static final UnicodeBlock ARABIC_EXTENDED_B =
3479 new UnicodeBlock("ARABIC_EXTENDED_B",
3480 "ARABIC EXTENDED-B",
3481 "ARABICEXTENDED-B");
3482
3483 /**
3484 * Constant for the "Vithkuqi" Unicode
3485 * character block.
3486 * @since 19
3487 */
3488 public static final UnicodeBlock VITHKUQI =
3489 new UnicodeBlock("VITHKUQI");
3490
3491 /**
3492 * Constant for the "Latin Extended-F" Unicode
3493 * character block.
3494 * @since 19
3495 */
3496 public static final UnicodeBlock LATIN_EXTENDED_F =
3497 new UnicodeBlock("LATIN_EXTENDED_F",
3498 "LATIN EXTENDED-F",
3499 "LATINEXTENDED-F");
3500
3501 /**
3502 * Constant for the "Old Uyghur" Unicode
3503 * character block.
3504 * @since 19
3505 */
3506 public static final UnicodeBlock OLD_UYGHUR =
3507 new UnicodeBlock("OLD_UYGHUR",
3508 "OLD UYGHUR",
3509 "OLDUYGHUR");
3510
3511 /**
3512 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3513 * character block.
3514 * @since 19
3515 */
3516 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3517 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3518 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3519 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3520
3521 /**
3522 * Constant for the "Cypro-Minoan" Unicode
3523 * character block.
3524 * @since 19
3525 */
3526 public static final UnicodeBlock CYPRO_MINOAN =
3527 new UnicodeBlock("CYPRO_MINOAN",
3528 "CYPRO-MINOAN",
3529 "CYPRO-MINOAN");
3530
3531 /**
3532 * Constant for the "Tangsa" Unicode
3533 * character block.
3534 * @since 19
3535 */
3536 public static final UnicodeBlock TANGSA =
3537 new UnicodeBlock("TANGSA");
3538
3539 /**
3540 * Constant for the "Kana Extended-B" Unicode
3541 * character block.
3542 * @since 19
3543 */
3544 public static final UnicodeBlock KANA_EXTENDED_B =
3545 new UnicodeBlock("KANA_EXTENDED_B",
3546 "KANA EXTENDED-B",
3547 "KANAEXTENDED-B");
3548
3549 /**
3550 * Constant for the "Znamenny Musical Notation" Unicode
3551 * character block.
3552 * @since 19
3553 */
3554 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3555 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3556 "ZNAMENNY MUSICAL NOTATION",
3557 "ZNAMENNYMUSICALNOTATION");
3558
3559 /**
3560 * Constant for the "Latin Extended-G" Unicode
3561 * character block.
3562 * @since 19
3563 */
3564 public static final UnicodeBlock LATIN_EXTENDED_G =
3565 new UnicodeBlock("LATIN_EXTENDED_G",
3566 "LATIN EXTENDED-G",
3567 "LATINEXTENDED-G");
3568
3569 /**
3570 * Constant for the "Toto" Unicode
3571 * character block.
3572 * @since 19
3573 */
3574 public static final UnicodeBlock TOTO =
3575 new UnicodeBlock("TOTO");
3576
3577 /**
3578 * Constant for the "Ethiopic Extended-B" Unicode
3579 * character block.
3580 * @since 19
3581 */
3582 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3583 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3584 "ETHIOPIC EXTENDED-B",
3585 "ETHIOPICEXTENDED-B");
3586
3587 /**
3588 * Constant for the "Arabic Extended-C" Unicode
3589 * character block.
3590 * @since 20
3591 */
3592 public static final UnicodeBlock ARABIC_EXTENDED_C =
3593 new UnicodeBlock("ARABIC_EXTENDED_C",
3594 "ARABIC EXTENDED-C",
3595 "ARABICEXTENDED-C");
3596
3597 /**
3598 * Constant for the "Devanagari Extended-A" Unicode
3599 * character block.
3600 * @since 20
3601 */
3602 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3603 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3604 "DEVANAGARI EXTENDED-A",
3605 "DEVANAGARIEXTENDED-A");
3606
3607 /**
3608 * Constant for the "Kawi" Unicode
3609 * character block.
3610 * @since 20
3611 */
3612 public static final UnicodeBlock KAWI =
3613 new UnicodeBlock("KAWI");
3614
3615 /**
3616 * Constant for the "Kaktovik Numerals" Unicode
3617 * character block.
3618 * @since 20
3619 */
3620 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3621 new UnicodeBlock("KAKTOVIK_NUMERALS",
3622 "KAKTOVIK NUMERALS",
3623 "KAKTOVIKNUMERALS");
3624
3625 /**
3626 * Constant for the "Cyrillic Extended-D" Unicode
3627 * character block.
3628 * @since 20
3629 */
3630 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3631 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3632 "CYRILLIC EXTENDED-D",
3633 "CYRILLICEXTENDED-D");
3634
3635 /**
3636 * Constant for the "Nag Mundari" Unicode
3637 * character block.
3638 * @since 20
3639 */
3640 public static final UnicodeBlock NAG_MUNDARI =
3641 new UnicodeBlock("NAG_MUNDARI",
3642 "NAG MUNDARI",
3643 "NAGMUNDARI");
3644
3645 /**
3646 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3647 * character block.
3648 * @since 20
3649 */
3650 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3651 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3652 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3653 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3654
3655 /**
3656 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3657 * character block.
3658 * @since 22
3659 */
3660 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3661 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3662 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3663 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3664
3665 /**
3666 * Constant for the "Todhri" Unicode
3667 * character block.
3668 * @since 24
3669 */
3670 public static final UnicodeBlock TODHRI =
3671 new UnicodeBlock("TODHRI");
3672
3673 /**
3674 * Constant for the "Garay" Unicode
3675 * character block.
3676 * @since 24
3677 */
3678 public static final UnicodeBlock GARAY =
3679 new UnicodeBlock("GARAY");
3680
3681 /**
3682 * Constant for the "Tulu-Tigalari" Unicode
3683 * character block.
3684 * @since 24
3685 */
3686 public static final UnicodeBlock TULU_TIGALARI =
3687 new UnicodeBlock("TULU_TIGALARI",
3688 "TULU-TIGALARI");
3689
3690 /**
3691 * Constant for the "Myanmar Extended-C" Unicode
3692 * character block.
3693 * @since 24
3694 */
3695 public static final UnicodeBlock MYANMAR_EXTENDED_C =
3696 new UnicodeBlock("MYANMAR_EXTENDED_C",
3697 "MYANMAR EXTENDED-C",
3698 "MYANMAREXTENDED-C");
3699
3700 /**
3701 * Constant for the "Sunuwar" Unicode
3702 * character block.
3703 * @since 24
3704 */
3705 public static final UnicodeBlock SUNUWAR =
3706 new UnicodeBlock("SUNUWAR");
3707
3708 /**
3709 * Constant for the "Egyptian Hieroglyphs Extended-A" Unicode
3710 * character block.
3711 * @since 24
3712 */
3713 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS_EXTENDED_A =
3714 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS_EXTENDED_A",
3715 "EGYPTIAN HIEROGLYPHS EXTENDED-A",
3716 "EGYPTIANHIEROGLYPHSEXTENDED-A");
3717
3718 /**
3719 * Constant for the "Gurung Khema" Unicode
3720 * character block.
3721 * @since 24
3722 */
3723 public static final UnicodeBlock GURUNG_KHEMA =
3724 new UnicodeBlock("GURUNG_KHEMA",
3725 "GURUNG KHEMA",
3726 "GURUNGKHEMA");
3727
3728 /**
3729 * Constant for the "Kirat Rai" Unicode
3730 * character block.
3731 * @since 24
3732 */
3733 public static final UnicodeBlock KIRAT_RAI =
3734 new UnicodeBlock("KIRAT_RAI",
3735 "KIRAT RAI",
3736 "KIRATRAI");
3737
3738 /**
3739 * Constant for the "Symbols for Legacy Computing Supplement" Unicode
3740 * character block.
3741 * @since 24
3742 */
3743 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT =
3744 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT",
3745 "SYMBOLS FOR LEGACY COMPUTING SUPPLEMENT",
3746 "SYMBOLSFORLEGACYCOMPUTINGSUPPLEMENT");
3747
3748 /**
3749 * Constant for the "Ol Onal" Unicode
3750 * character block.
3751 * @since 24
3752 */
3753 public static final UnicodeBlock OL_ONAL =
3754 new UnicodeBlock("OL_ONAL",
3755 "OL ONAL",
3756 "OLONAL");
3757
3758 /**
3759 * Constant for the "Sidetic" Unicode
3760 * character block.
3761 * @since 26
3762 */
3763 public static final UnicodeBlock SIDETIC =
3764 new UnicodeBlock("SIDETIC");
3765
3766 /**
3767 * Constant for the "Sharada Supplement" Unicode
3768 * character block.
3769 * @since 26
3770 */
3771 public static final UnicodeBlock SHARADA_SUPPLEMENT =
3772 new UnicodeBlock("SHARADA_SUPPLEMENT",
3773 "SHARADA SUPPLEMENT",
3774 "SHARADASUPPLEMENT");
3775
3776 /**
3777 * Constant for the "Tolong Siki" Unicode
3778 * character block.
3779 * @since 26
3780 */
3781 public static final UnicodeBlock TOLONG_SIKI =
3782 new UnicodeBlock("TOLONG_SIKI",
3783 "TOLONG SIKI",
3784 "TOLONGSIKI");
3785
3786 /**
3787 * Constant for the "Beria Erfe" Unicode
3788 * character block.
3789 * @since 26
3790 */
3791 public static final UnicodeBlock BERIA_ERFE =
3792 new UnicodeBlock("BERIA_ERFE",
3793 "BERIA ERFE",
3794 "BERIAERFE");
3795
3796 /**
3797 * Constant for the "Tangut Components Supplement" Unicode
3798 * character block.
3799 * @since 26
3800 */
3801 public static final UnicodeBlock TANGUT_COMPONENTS_SUPPLEMENT =
3802 new UnicodeBlock("TANGUT_COMPONENTS_SUPPLEMENT",
3803 "TANGUT COMPONENTS SUPPLEMENT",
3804 "TANGUTCOMPONENTSSUPPLEMENT");
3805
3806 /**
3807 * Constant for the "Miscellaneous Symbols Supplement" Unicode
3808 * character block.
3809 * @since 26
3810 */
3811 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_SUPPLEMENT =
3812 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_SUPPLEMENT",
3813 "MISCELLANEOUS SYMBOLS SUPPLEMENT",
3814 "MISCELLANEOUSSYMBOLSSUPPLEMENT");
3815
3816 /**
3817 * Constant for the "Tai Yo" Unicode
3818 * character block.
3819 * @since 26
3820 */
3821 public static final UnicodeBlock TAI_YO =
3822 new UnicodeBlock("TAI_YO",
3823 "TAI YO",
3824 "TAIYO");
3825
3826 /**
3827 * Constant for the "CJK Unified Ideographs Extension J" Unicode
3828 * character block.
3829 * @since 26
3830 */
3831 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J =
3832 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J",
3833 "CJK UNIFIED IDEOGRAPHS EXTENSION J",
3834 "CJKUNIFIEDIDEOGRAPHSEXTENSIONJ");
3835
3836
3837 private static final int[] blockStarts = {
3838 0x0000, // 0000..007F; Basic Latin
3839 0x0080, // 0080..00FF; Latin-1 Supplement
3840 0x0100, // 0100..017F; Latin Extended-A
3841 0x0180, // 0180..024F; Latin Extended-B
3842 0x0250, // 0250..02AF; IPA Extensions
3843 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3844 0x0300, // 0300..036F; Combining Diacritical Marks
3845 0x0370, // 0370..03FF; Greek and Coptic
3846 0x0400, // 0400..04FF; Cyrillic
3847 0x0500, // 0500..052F; Cyrillic Supplement
3848 0x0530, // 0530..058F; Armenian
3849 0x0590, // 0590..05FF; Hebrew
3850 0x0600, // 0600..06FF; Arabic
3851 0x0700, // 0700..074F; Syriac
3852 0x0750, // 0750..077F; Arabic Supplement
3853 0x0780, // 0780..07BF; Thaana
3854 0x07C0, // 07C0..07FF; NKo
3855 0x0800, // 0800..083F; Samaritan
3856 0x0840, // 0840..085F; Mandaic
3857 0x0860, // 0860..086F; Syriac Supplement
3858 0x0870, // 0870..089F; Arabic Extended-B
3859 0x08A0, // 08A0..08FF; Arabic Extended-A
3860 0x0900, // 0900..097F; Devanagari
3861 0x0980, // 0980..09FF; Bengali
3862 0x0A00, // 0A00..0A7F; Gurmukhi
3863 0x0A80, // 0A80..0AFF; Gujarati
3864 0x0B00, // 0B00..0B7F; Oriya
3865 0x0B80, // 0B80..0BFF; Tamil
3866 0x0C00, // 0C00..0C7F; Telugu
3867 0x0C80, // 0C80..0CFF; Kannada
3868 0x0D00, // 0D00..0D7F; Malayalam
3869 0x0D80, // 0D80..0DFF; Sinhala
3870 0x0E00, // 0E00..0E7F; Thai
3871 0x0E80, // 0E80..0EFF; Lao
3872 0x0F00, // 0F00..0FFF; Tibetan
3873 0x1000, // 1000..109F; Myanmar
3874 0x10A0, // 10A0..10FF; Georgian
3875 0x1100, // 1100..11FF; Hangul Jamo
3876 0x1200, // 1200..137F; Ethiopic
3877 0x1380, // 1380..139F; Ethiopic Supplement
3878 0x13A0, // 13A0..13FF; Cherokee
3879 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3880 0x1680, // 1680..169F; Ogham
3881 0x16A0, // 16A0..16FF; Runic
3882 0x1700, // 1700..171F; Tagalog
3883 0x1720, // 1720..173F; Hanunoo
3884 0x1740, // 1740..175F; Buhid
3885 0x1760, // 1760..177F; Tagbanwa
3886 0x1780, // 1780..17FF; Khmer
3887 0x1800, // 1800..18AF; Mongolian
3888 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3889 0x1900, // 1900..194F; Limbu
3890 0x1950, // 1950..197F; Tai Le
3891 0x1980, // 1980..19DF; New Tai Lue
3892 0x19E0, // 19E0..19FF; Khmer Symbols
3893 0x1A00, // 1A00..1A1F; Buginese
3894 0x1A20, // 1A20..1AAF; Tai Tham
3895 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3896 0x1B00, // 1B00..1B7F; Balinese
3897 0x1B80, // 1B80..1BBF; Sundanese
3898 0x1BC0, // 1BC0..1BFF; Batak
3899 0x1C00, // 1C00..1C4F; Lepcha
3900 0x1C50, // 1C50..1C7F; Ol Chiki
3901 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3902 0x1C90, // 1C90..1CBF; Georgian Extended
3903 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3904 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3905 0x1D00, // 1D00..1D7F; Phonetic Extensions
3906 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3907 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3908 0x1E00, // 1E00..1EFF; Latin Extended Additional
3909 0x1F00, // 1F00..1FFF; Greek Extended
3910 0x2000, // 2000..206F; General Punctuation
3911 0x2070, // 2070..209F; Superscripts and Subscripts
3912 0x20A0, // 20A0..20CF; Currency Symbols
3913 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3914 0x2100, // 2100..214F; Letterlike Symbols
3915 0x2150, // 2150..218F; Number Forms
3916 0x2190, // 2190..21FF; Arrows
3917 0x2200, // 2200..22FF; Mathematical Operators
3918 0x2300, // 2300..23FF; Miscellaneous Technical
3919 0x2400, // 2400..243F; Control Pictures
3920 0x2440, // 2440..245F; Optical Character Recognition
3921 0x2460, // 2460..24FF; Enclosed Alphanumerics
3922 0x2500, // 2500..257F; Box Drawing
3923 0x2580, // 2580..259F; Block Elements
3924 0x25A0, // 25A0..25FF; Geometric Shapes
3925 0x2600, // 2600..26FF; Miscellaneous Symbols
3926 0x2700, // 2700..27BF; Dingbats
3927 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3928 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3929 0x2800, // 2800..28FF; Braille Patterns
3930 0x2900, // 2900..297F; Supplemental Arrows-B
3931 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3932 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3933 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3934 0x2C00, // 2C00..2C5F; Glagolitic
3935 0x2C60, // 2C60..2C7F; Latin Extended-C
3936 0x2C80, // 2C80..2CFF; Coptic
3937 0x2D00, // 2D00..2D2F; Georgian Supplement
3938 0x2D30, // 2D30..2D7F; Tifinagh
3939 0x2D80, // 2D80..2DDF; Ethiopic Extended
3940 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3941 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3942 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3943 0x2F00, // 2F00..2FDF; Kangxi Radicals
3944 0x2FE0, // unassigned
3945 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3946 0x3000, // 3000..303F; CJK Symbols and Punctuation
3947 0x3040, // 3040..309F; Hiragana
3948 0x30A0, // 30A0..30FF; Katakana
3949 0x3100, // 3100..312F; Bopomofo
3950 0x3130, // 3130..318F; Hangul Compatibility Jamo
3951 0x3190, // 3190..319F; Kanbun
3952 0x31A0, // 31A0..31BF; Bopomofo Extended
3953 0x31C0, // 31C0..31EF; CJK Strokes
3954 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3955 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3956 0x3300, // 3300..33FF; CJK Compatibility
3957 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3958 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3959 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3960 0xA000, // A000..A48F; Yi Syllables
3961 0xA490, // A490..A4CF; Yi Radicals
3962 0xA4D0, // A4D0..A4FF; Lisu
3963 0xA500, // A500..A63F; Vai
3964 0xA640, // A640..A69F; Cyrillic Extended-B
3965 0xA6A0, // A6A0..A6FF; Bamum
3966 0xA700, // A700..A71F; Modifier Tone Letters
3967 0xA720, // A720..A7FF; Latin Extended-D
3968 0xA800, // A800..A82F; Syloti Nagri
3969 0xA830, // A830..A83F; Common Indic Number Forms
3970 0xA840, // A840..A87F; Phags-pa
3971 0xA880, // A880..A8DF; Saurashtra
3972 0xA8E0, // A8E0..A8FF; Devanagari Extended
3973 0xA900, // A900..A92F; Kayah Li
3974 0xA930, // A930..A95F; Rejang
3975 0xA960, // A960..A97F; Hangul Jamo Extended-A
3976 0xA980, // A980..A9DF; Javanese
3977 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3978 0xAA00, // AA00..AA5F; Cham
3979 0xAA60, // AA60..AA7F; Myanmar Extended-A
3980 0xAA80, // AA80..AADF; Tai Viet
3981 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3982 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3983 0xAB30, // AB30..AB6F; Latin Extended-E
3984 0xAB70, // AB70..ABBF; Cherokee Supplement
3985 0xABC0, // ABC0..ABFF; Meetei Mayek
3986 0xAC00, // AC00..D7AF; Hangul Syllables
3987 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3988 0xD800, // D800..DB7F; High Surrogates
3989 0xDB80, // DB80..DBFF; High Private Use Surrogates
3990 0xDC00, // DC00..DFFF; Low Surrogates
3991 0xE000, // E000..F8FF; Private Use Area
3992 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3993 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3994 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3995 0xFE00, // FE00..FE0F; Variation Selectors
3996 0xFE10, // FE10..FE1F; Vertical Forms
3997 0xFE20, // FE20..FE2F; Combining Half Marks
3998 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3999 0xFE50, // FE50..FE6F; Small Form Variants
4000 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
4001 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
4002 0xFFF0, // FFF0..FFFF; Specials
4003 0x10000, // 10000..1007F; Linear B Syllabary
4004 0x10080, // 10080..100FF; Linear B Ideograms
4005 0x10100, // 10100..1013F; Aegean Numbers
4006 0x10140, // 10140..1018F; Ancient Greek Numbers
4007 0x10190, // 10190..101CF; Ancient Symbols
4008 0x101D0, // 101D0..101FF; Phaistos Disc
4009 0x10200, // unassigned
4010 0x10280, // 10280..1029F; Lycian
4011 0x102A0, // 102A0..102DF; Carian
4012 0x102E0, // 102E0..102FF; Coptic Epact Numbers
4013 0x10300, // 10300..1032F; Old Italic
4014 0x10330, // 10330..1034F; Gothic
4015 0x10350, // 10350..1037F; Old Permic
4016 0x10380, // 10380..1039F; Ugaritic
4017 0x103A0, // 103A0..103DF; Old Persian
4018 0x103E0, // unassigned
4019 0x10400, // 10400..1044F; Deseret
4020 0x10450, // 10450..1047F; Shavian
4021 0x10480, // 10480..104AF; Osmanya
4022 0x104B0, // 104B0..104FF; Osage
4023 0x10500, // 10500..1052F; Elbasan
4024 0x10530, // 10530..1056F; Caucasian Albanian
4025 0x10570, // 10570..105BF; Vithkuqi
4026 0x105C0, // 105C0..105FF; Todhri
4027 0x10600, // 10600..1077F; Linear A
4028 0x10780, // 10780..107BF; Latin Extended-F
4029 0x107C0, // unassigned
4030 0x10800, // 10800..1083F; Cypriot Syllabary
4031 0x10840, // 10840..1085F; Imperial Aramaic
4032 0x10860, // 10860..1087F; Palmyrene
4033 0x10880, // 10880..108AF; Nabataean
4034 0x108B0, // unassigned
4035 0x108E0, // 108E0..108FF; Hatran
4036 0x10900, // 10900..1091F; Phoenician
4037 0x10920, // 10920..1093F; Lydian
4038 0x10940, // 10940..1095F; Sidetic
4039 0x10960, // unassigned
4040 0x10980, // 10980..1099F; Meroitic Hieroglyphs
4041 0x109A0, // 109A0..109FF; Meroitic Cursive
4042 0x10A00, // 10A00..10A5F; Kharoshthi
4043 0x10A60, // 10A60..10A7F; Old South Arabian
4044 0x10A80, // 10A80..10A9F; Old North Arabian
4045 0x10AA0, // unassigned
4046 0x10AC0, // 10AC0..10AFF; Manichaean
4047 0x10B00, // 10B00..10B3F; Avestan
4048 0x10B40, // 10B40..10B5F; Inscriptional Parthian
4049 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
4050 0x10B80, // 10B80..10BAF; Psalter Pahlavi
4051 0x10BB0, // unassigned
4052 0x10C00, // 10C00..10C4F; Old Turkic
4053 0x10C50, // unassigned
4054 0x10C80, // 10C80..10CFF; Old Hungarian
4055 0x10D00, // 10D00..10D3F; Hanifi Rohingya
4056 0x10D40, // 10D40..10D8F; Garay
4057 0x10D90, // unassigned
4058 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
4059 0x10E80, // 10E80..10EBF; Yezidi
4060 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
4061 0x10F00, // 10F00..10F2F; Old Sogdian
4062 0x10F30, // 10F30..10F6F; Sogdian
4063 0x10F70, // 10F70..10FAF; Old Uyghur
4064 0x10FB0, // 10FB0..10FDF; Chorasmian
4065 0x10FE0, // 10FE0..10FFF; Elymaic
4066 0x11000, // 11000..1107F; Brahmi
4067 0x11080, // 11080..110CF; Kaithi
4068 0x110D0, // 110D0..110FF; Sora Sompeng
4069 0x11100, // 11100..1114F; Chakma
4070 0x11150, // 11150..1117F; Mahajani
4071 0x11180, // 11180..111DF; Sharada
4072 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
4073 0x11200, // 11200..1124F; Khojki
4074 0x11250, // unassigned
4075 0x11280, // 11280..112AF; Multani
4076 0x112B0, // 112B0..112FF; Khudawadi
4077 0x11300, // 11300..1137F; Grantha
4078 0x11380, // 11380..113FF; Tulu-Tigalari
4079 0x11400, // 11400..1147F; Newa
4080 0x11480, // 11480..114DF; Tirhuta
4081 0x114E0, // unassigned
4082 0x11580, // 11580..115FF; Siddham
4083 0x11600, // 11600..1165F; Modi
4084 0x11660, // 11660..1167F; Mongolian Supplement
4085 0x11680, // 11680..116CF; Takri
4086 0x116D0, // 116D0..116FF; Myanmar Extended-C
4087 0x11700, // 11700..1174F; Ahom
4088 0x11750, // unassigned
4089 0x11800, // 11800..1184F; Dogra
4090 0x11850, // unassigned
4091 0x118A0, // 118A0..118FF; Warang Citi
4092 0x11900, // 11900..1195F; Dives Akuru
4093 0x11960, // unassigned
4094 0x119A0, // 119A0..119FF; Nandinagari
4095 0x11A00, // 11A00..11A4F; Zanabazar Square
4096 0x11A50, // 11A50..11AAF; Soyombo
4097 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
4098 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
4099 0x11B00, // 11B00..11B5F; Devanagari Extended-A
4100 0x11B60, // 11B60..11B7F; Sharada Supplement
4101 0x11B80, // unassigned
4102 0x11BC0, // 11BC0..11BFF; Sunuwar
4103 0x11C00, // 11C00..11C6F; Bhaiksuki
4104 0x11C70, // 11C70..11CBF; Marchen
4105 0x11CC0, // unassigned
4106 0x11D00, // 11D00..11D5F; Masaram Gondi
4107 0x11D60, // 11D60..11DAF; Gunjala Gondi
4108 0x11DB0, // 11DB0..11DEF; Tolong Siki
4109 0x11DF0, // unassigned
4110 0x11EE0, // 11EE0..11EFF; Makasar
4111 0x11F00, // 11F00..11F5F; Kawi
4112 0x11F60, // unassigned
4113 0x11FB0, // 11FB0..11FBF; Lisu Supplement
4114 0x11FC0, // 11FC0..11FFF; Tamil Supplement
4115 0x12000, // 12000..123FF; Cuneiform
4116 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
4117 0x12480, // 12480..1254F; Early Dynastic Cuneiform
4118 0x12550, // unassigned
4119 0x12F90, // 12F90..12FFF; Cypro-Minoan
4120 0x13000, // 13000..1342F; Egyptian Hieroglyphs
4121 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
4122 0x13460, // 13460..143FF; Egyptian Hieroglyphs Extended-A
4123 0x14400, // 14400..1467F; Anatolian Hieroglyphs
4124 0x14680, // unassigned
4125 0x16100, // 16100..1613F; Gurung Khema
4126 0x16140, // unassigned
4127 0x16800, // 16800..16A3F; Bamum Supplement
4128 0x16A40, // 16A40..16A6F; Mro
4129 0x16A70, // 16A70..16ACF; Tangsa
4130 0x16AD0, // 16AD0..16AFF; Bassa Vah
4131 0x16B00, // 16B00..16B8F; Pahawh Hmong
4132 0x16B90, // unassigned
4133 0x16D40, // 16D40..16D7F; Kirat Rai
4134 0x16D80, // unassigned
4135 0x16E40, // 16E40..16E9F; Medefaidrin
4136 0x16EA0, // 16EA0..16EDF; Beria Erfe
4137 0x16EE0, // unassigned
4138 0x16F00, // 16F00..16F9F; Miao
4139 0x16FA0, // unassigned
4140 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
4141 0x17000, // 17000..187FF; Tangut
4142 0x18800, // 18800..18AFF; Tangut Components
4143 0x18B00, // 18B00..18CFF; Khitan Small Script
4144 0x18D00, // 18D00..18D7F; Tangut Supplement
4145 0x18D80, // 18D80..18DFF; Tangut Components Supplement
4146 0x18E00, // unassigned
4147 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
4148 0x1B000, // 1B000..1B0FF; Kana Supplement
4149 0x1B100, // 1B100..1B12F; Kana Extended-A
4150 0x1B130, // 1B130..1B16F; Small Kana Extension
4151 0x1B170, // 1B170..1B2FF; Nushu
4152 0x1B300, // unassigned
4153 0x1BC00, // 1BC00..1BC9F; Duployan
4154 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
4155 0x1BCB0, // unassigned
4156 0x1CC00, // 1CC00..1CEBF; Symbols for Legacy Computing Supplement
4157 0x1CEC0, // 1CEC0..1CEFF; Miscellaneous Symbols Supplement
4158 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
4159 0x1CFD0, // unassigned
4160 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
4161 0x1D100, // 1D100..1D1FF; Musical Symbols
4162 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
4163 0x1D250, // unassigned
4164 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
4165 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
4166 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
4167 0x1D360, // 1D360..1D37F; Counting Rod Numerals
4168 0x1D380, // unassigned
4169 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
4170 0x1D800, // 1D800..1DAAF; Sutton SignWriting
4171 0x1DAB0, // unassigned
4172 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
4173 0x1E000, // 1E000..1E02F; Glagolitic Supplement
4174 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
4175 0x1E090, // unassigned
4176 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
4177 0x1E150, // unassigned
4178 0x1E290, // 1E290..1E2BF; Toto
4179 0x1E2C0, // 1E2C0..1E2FF; Wancho
4180 0x1E300, // unassigned
4181 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
4182 0x1E500, // unassigned
4183 0x1E5D0, // 1E5D0..1E5FF; Ol Onal
4184 0x1E600, // unassigned
4185 0x1E6C0, // 1E6C0..1E6FF; Tai Yo
4186 0x1E700, // unassigned
4187 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
4188 0x1E800, // 1E800..1E8DF; Mende Kikakui
4189 0x1E8E0, // unassigned
4190 0x1E900, // 1E900..1E95F; Adlam
4191 0x1E960, // unassigned
4192 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
4193 0x1ECC0, // unassigned
4194 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
4195 0x1ED50, // unassigned
4196 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
4197 0x1EF00, // unassigned
4198 0x1F000, // 1F000..1F02F; Mahjong Tiles
4199 0x1F030, // 1F030..1F09F; Domino Tiles
4200 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
4201 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
4202 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
4203 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
4204 0x1F600, // 1F600..1F64F; Emoticons
4205 0x1F650, // 1F650..1F67F; Ornamental Dingbats
4206 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
4207 0x1F700, // 1F700..1F77F; Alchemical Symbols
4208 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
4209 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
4210 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
4211 0x1FA00, // 1FA00..1FA6F; Chess Symbols
4212 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
4213 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
4214 0x1FC00, // unassigned
4215 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
4216 0x2A6E0, // unassigned
4217 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
4218 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
4219 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
4220 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
4221 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
4222 0x2EE60, // unassigned
4223 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
4224 0x2FA20, // unassigned
4225 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
4226 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4227 0x323B0, // 323B0..3347F; CJK Unified Ideographs Extension J
4228 0x33480, // unassigned
4229 0xE0000, // E0000..E007F; Tags
4230 0xE0080, // unassigned
4231 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4232 0xE01F0, // unassigned
4233 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4234 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4235 };
4236
4237 private static final UnicodeBlock[] blocks = {
4238 BASIC_LATIN,
4239 LATIN_1_SUPPLEMENT,
4240 LATIN_EXTENDED_A,
4241 LATIN_EXTENDED_B,
4242 IPA_EXTENSIONS,
4243 SPACING_MODIFIER_LETTERS,
4244 COMBINING_DIACRITICAL_MARKS,
4245 GREEK,
4246 CYRILLIC,
4247 CYRILLIC_SUPPLEMENTARY,
4248 ARMENIAN,
4249 HEBREW,
4250 ARABIC,
4251 SYRIAC,
4252 ARABIC_SUPPLEMENT,
4253 THAANA,
4254 NKO,
4255 SAMARITAN,
4256 MANDAIC,
4257 SYRIAC_SUPPLEMENT,
4258 ARABIC_EXTENDED_B,
4259 ARABIC_EXTENDED_A,
4260 DEVANAGARI,
4261 BENGALI,
4262 GURMUKHI,
4263 GUJARATI,
4264 ORIYA,
4265 TAMIL,
4266 TELUGU,
4267 KANNADA,
4268 MALAYALAM,
4269 SINHALA,
4270 THAI,
4271 LAO,
4272 TIBETAN,
4273 MYANMAR,
4274 GEORGIAN,
4275 HANGUL_JAMO,
4276 ETHIOPIC,
4277 ETHIOPIC_SUPPLEMENT,
4278 CHEROKEE,
4279 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4280 OGHAM,
4281 RUNIC,
4282 TAGALOG,
4283 HANUNOO,
4284 BUHID,
4285 TAGBANWA,
4286 KHMER,
4287 MONGOLIAN,
4288 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4289 LIMBU,
4290 TAI_LE,
4291 NEW_TAI_LUE,
4292 KHMER_SYMBOLS,
4293 BUGINESE,
4294 TAI_THAM,
4295 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4296 BALINESE,
4297 SUNDANESE,
4298 BATAK,
4299 LEPCHA,
4300 OL_CHIKI,
4301 CYRILLIC_EXTENDED_C,
4302 GEORGIAN_EXTENDED,
4303 SUNDANESE_SUPPLEMENT,
4304 VEDIC_EXTENSIONS,
4305 PHONETIC_EXTENSIONS,
4306 PHONETIC_EXTENSIONS_SUPPLEMENT,
4307 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4308 LATIN_EXTENDED_ADDITIONAL,
4309 GREEK_EXTENDED,
4310 GENERAL_PUNCTUATION,
4311 SUPERSCRIPTS_AND_SUBSCRIPTS,
4312 CURRENCY_SYMBOLS,
4313 COMBINING_MARKS_FOR_SYMBOLS,
4314 LETTERLIKE_SYMBOLS,
4315 NUMBER_FORMS,
4316 ARROWS,
4317 MATHEMATICAL_OPERATORS,
4318 MISCELLANEOUS_TECHNICAL,
4319 CONTROL_PICTURES,
4320 OPTICAL_CHARACTER_RECOGNITION,
4321 ENCLOSED_ALPHANUMERICS,
4322 BOX_DRAWING,
4323 BLOCK_ELEMENTS,
4324 GEOMETRIC_SHAPES,
4325 MISCELLANEOUS_SYMBOLS,
4326 DINGBATS,
4327 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4328 SUPPLEMENTAL_ARROWS_A,
4329 BRAILLE_PATTERNS,
4330 SUPPLEMENTAL_ARROWS_B,
4331 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4332 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4333 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4334 GLAGOLITIC,
4335 LATIN_EXTENDED_C,
4336 COPTIC,
4337 GEORGIAN_SUPPLEMENT,
4338 TIFINAGH,
4339 ETHIOPIC_EXTENDED,
4340 CYRILLIC_EXTENDED_A,
4341 SUPPLEMENTAL_PUNCTUATION,
4342 CJK_RADICALS_SUPPLEMENT,
4343 KANGXI_RADICALS,
4344 null,
4345 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4346 CJK_SYMBOLS_AND_PUNCTUATION,
4347 HIRAGANA,
4348 KATAKANA,
4349 BOPOMOFO,
4350 HANGUL_COMPATIBILITY_JAMO,
4351 KANBUN,
4352 BOPOMOFO_EXTENDED,
4353 CJK_STROKES,
4354 KATAKANA_PHONETIC_EXTENSIONS,
4355 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4356 CJK_COMPATIBILITY,
4357 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4358 YIJING_HEXAGRAM_SYMBOLS,
4359 CJK_UNIFIED_IDEOGRAPHS,
4360 YI_SYLLABLES,
4361 YI_RADICALS,
4362 LISU,
4363 VAI,
4364 CYRILLIC_EXTENDED_B,
4365 BAMUM,
4366 MODIFIER_TONE_LETTERS,
4367 LATIN_EXTENDED_D,
4368 SYLOTI_NAGRI,
4369 COMMON_INDIC_NUMBER_FORMS,
4370 PHAGS_PA,
4371 SAURASHTRA,
4372 DEVANAGARI_EXTENDED,
4373 KAYAH_LI,
4374 REJANG,
4375 HANGUL_JAMO_EXTENDED_A,
4376 JAVANESE,
4377 MYANMAR_EXTENDED_B,
4378 CHAM,
4379 MYANMAR_EXTENDED_A,
4380 TAI_VIET,
4381 MEETEI_MAYEK_EXTENSIONS,
4382 ETHIOPIC_EXTENDED_A,
4383 LATIN_EXTENDED_E,
4384 CHEROKEE_SUPPLEMENT,
4385 MEETEI_MAYEK,
4386 HANGUL_SYLLABLES,
4387 HANGUL_JAMO_EXTENDED_B,
4388 HIGH_SURROGATES,
4389 HIGH_PRIVATE_USE_SURROGATES,
4390 LOW_SURROGATES,
4391 PRIVATE_USE_AREA,
4392 CJK_COMPATIBILITY_IDEOGRAPHS,
4393 ALPHABETIC_PRESENTATION_FORMS,
4394 ARABIC_PRESENTATION_FORMS_A,
4395 VARIATION_SELECTORS,
4396 VERTICAL_FORMS,
4397 COMBINING_HALF_MARKS,
4398 CJK_COMPATIBILITY_FORMS,
4399 SMALL_FORM_VARIANTS,
4400 ARABIC_PRESENTATION_FORMS_B,
4401 HALFWIDTH_AND_FULLWIDTH_FORMS,
4402 SPECIALS,
4403 LINEAR_B_SYLLABARY,
4404 LINEAR_B_IDEOGRAMS,
4405 AEGEAN_NUMBERS,
4406 ANCIENT_GREEK_NUMBERS,
4407 ANCIENT_SYMBOLS,
4408 PHAISTOS_DISC,
4409 null,
4410 LYCIAN,
4411 CARIAN,
4412 COPTIC_EPACT_NUMBERS,
4413 OLD_ITALIC,
4414 GOTHIC,
4415 OLD_PERMIC,
4416 UGARITIC,
4417 OLD_PERSIAN,
4418 null,
4419 DESERET,
4420 SHAVIAN,
4421 OSMANYA,
4422 OSAGE,
4423 ELBASAN,
4424 CAUCASIAN_ALBANIAN,
4425 VITHKUQI,
4426 TODHRI,
4427 LINEAR_A,
4428 LATIN_EXTENDED_F,
4429 null,
4430 CYPRIOT_SYLLABARY,
4431 IMPERIAL_ARAMAIC,
4432 PALMYRENE,
4433 NABATAEAN,
4434 null,
4435 HATRAN,
4436 PHOENICIAN,
4437 LYDIAN,
4438 SIDETIC,
4439 null,
4440 MEROITIC_HIEROGLYPHS,
4441 MEROITIC_CURSIVE,
4442 KHAROSHTHI,
4443 OLD_SOUTH_ARABIAN,
4444 OLD_NORTH_ARABIAN,
4445 null,
4446 MANICHAEAN,
4447 AVESTAN,
4448 INSCRIPTIONAL_PARTHIAN,
4449 INSCRIPTIONAL_PAHLAVI,
4450 PSALTER_PAHLAVI,
4451 null,
4452 OLD_TURKIC,
4453 null,
4454 OLD_HUNGARIAN,
4455 HANIFI_ROHINGYA,
4456 GARAY,
4457 null,
4458 RUMI_NUMERAL_SYMBOLS,
4459 YEZIDI,
4460 ARABIC_EXTENDED_C,
4461 OLD_SOGDIAN,
4462 SOGDIAN,
4463 OLD_UYGHUR,
4464 CHORASMIAN,
4465 ELYMAIC,
4466 BRAHMI,
4467 KAITHI,
4468 SORA_SOMPENG,
4469 CHAKMA,
4470 MAHAJANI,
4471 SHARADA,
4472 SINHALA_ARCHAIC_NUMBERS,
4473 KHOJKI,
4474 null,
4475 MULTANI,
4476 KHUDAWADI,
4477 GRANTHA,
4478 TULU_TIGALARI,
4479 NEWA,
4480 TIRHUTA,
4481 null,
4482 SIDDHAM,
4483 MODI,
4484 MONGOLIAN_SUPPLEMENT,
4485 TAKRI,
4486 MYANMAR_EXTENDED_C,
4487 AHOM,
4488 null,
4489 DOGRA,
4490 null,
4491 WARANG_CITI,
4492 DIVES_AKURU,
4493 null,
4494 NANDINAGARI,
4495 ZANABAZAR_SQUARE,
4496 SOYOMBO,
4497 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4498 PAU_CIN_HAU,
4499 DEVANAGARI_EXTENDED_A,
4500 SHARADA_SUPPLEMENT,
4501 null,
4502 SUNUWAR,
4503 BHAIKSUKI,
4504 MARCHEN,
4505 null,
4506 MASARAM_GONDI,
4507 GUNJALA_GONDI,
4508 TOLONG_SIKI,
4509 null,
4510 MAKASAR,
4511 KAWI,
4512 null,
4513 LISU_SUPPLEMENT,
4514 TAMIL_SUPPLEMENT,
4515 CUNEIFORM,
4516 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4517 EARLY_DYNASTIC_CUNEIFORM,
4518 null,
4519 CYPRO_MINOAN,
4520 EGYPTIAN_HIEROGLYPHS,
4521 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4522 EGYPTIAN_HIEROGLYPHS_EXTENDED_A,
4523 ANATOLIAN_HIEROGLYPHS,
4524 null,
4525 GURUNG_KHEMA,
4526 null,
4527 BAMUM_SUPPLEMENT,
4528 MRO,
4529 TANGSA,
4530 BASSA_VAH,
4531 PAHAWH_HMONG,
4532 null,
4533 KIRAT_RAI,
4534 null,
4535 MEDEFAIDRIN,
4536 BERIA_ERFE,
4537 null,
4538 MIAO,
4539 null,
4540 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4541 TANGUT,
4542 TANGUT_COMPONENTS,
4543 KHITAN_SMALL_SCRIPT,
4544 TANGUT_SUPPLEMENT,
4545 TANGUT_COMPONENTS_SUPPLEMENT,
4546 null,
4547 KANA_EXTENDED_B,
4548 KANA_SUPPLEMENT,
4549 KANA_EXTENDED_A,
4550 SMALL_KANA_EXTENSION,
4551 NUSHU,
4552 null,
4553 DUPLOYAN,
4554 SHORTHAND_FORMAT_CONTROLS,
4555 null,
4556 SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT,
4557 MISCELLANEOUS_SYMBOLS_SUPPLEMENT,
4558 ZNAMENNY_MUSICAL_NOTATION,
4559 null,
4560 BYZANTINE_MUSICAL_SYMBOLS,
4561 MUSICAL_SYMBOLS,
4562 ANCIENT_GREEK_MUSICAL_NOTATION,
4563 null,
4564 KAKTOVIK_NUMERALS,
4565 MAYAN_NUMERALS,
4566 TAI_XUAN_JING_SYMBOLS,
4567 COUNTING_ROD_NUMERALS,
4568 null,
4569 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4570 SUTTON_SIGNWRITING,
4571 null,
4572 LATIN_EXTENDED_G,
4573 GLAGOLITIC_SUPPLEMENT,
4574 CYRILLIC_EXTENDED_D,
4575 null,
4576 NYIAKENG_PUACHUE_HMONG,
4577 null,
4578 TOTO,
4579 WANCHO,
4580 null,
4581 NAG_MUNDARI,
4582 null,
4583 OL_ONAL,
4584 null,
4585 TAI_YO,
4586 null,
4587 ETHIOPIC_EXTENDED_B,
4588 MENDE_KIKAKUI,
4589 null,
4590 ADLAM,
4591 null,
4592 INDIC_SIYAQ_NUMBERS,
4593 null,
4594 OTTOMAN_SIYAQ_NUMBERS,
4595 null,
4596 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4597 null,
4598 MAHJONG_TILES,
4599 DOMINO_TILES,
4600 PLAYING_CARDS,
4601 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4602 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4603 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4604 EMOTICONS,
4605 ORNAMENTAL_DINGBATS,
4606 TRANSPORT_AND_MAP_SYMBOLS,
4607 ALCHEMICAL_SYMBOLS,
4608 GEOMETRIC_SHAPES_EXTENDED,
4609 SUPPLEMENTAL_ARROWS_C,
4610 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4611 CHESS_SYMBOLS,
4612 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4613 SYMBOLS_FOR_LEGACY_COMPUTING,
4614 null,
4615 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4616 null,
4617 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4618 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4619 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4620 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4621 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4622 null,
4623 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4624 null,
4625 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4626 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4627 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_J,
4628 null,
4629 TAGS,
4630 null,
4631 VARIATION_SELECTORS_SUPPLEMENT,
4632 null,
4633 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4634 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4635 };
4636
4637
4638 /**
4639 * Returns the object representing the Unicode block containing the
4640 * given character, or {@code null} if the character is not a
4641 * member of a defined block.
4642 *
4643 * <p><b>Note:</b> This method cannot handle
4644 * <a href="Character.html#supplementary"> supplementary
4645 * characters</a>. To support all Unicode characters, including
4646 * supplementary characters, use the {@link #of(int)} method.
4647 *
4648 * @param c The character in question
4649 * @return The {@code UnicodeBlock} instance representing the
4650 * Unicode block of which this character is a member, or
4651 * {@code null} if the character is not a member of any
4652 * Unicode block
4653 */
4654 public static UnicodeBlock of(char c) {
4655 return of((int)c);
4656 }
4657
4658 /**
4659 * Returns the object representing the Unicode block
4660 * containing the given character (Unicode code point), or
4661 * {@code null} if the character is not a member of a
4662 * defined block.
4663 *
4664 * @param codePoint the character (Unicode code point) in question.
4665 * @return The {@code UnicodeBlock} instance representing the
4666 * Unicode block of which this character is a member, or
4667 * {@code null} if the character is not a member of any
4668 * Unicode block
4669 * @throws IllegalArgumentException if the specified
4670 * {@code codePoint} is an invalid Unicode code point.
4671 * @see Character#isValidCodePoint(int)
4672 * @since 1.5
4673 */
4674 public static UnicodeBlock of(int codePoint) {
4675 if (!isValidCodePoint(codePoint)) {
4676 throw new IllegalArgumentException(
4677 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4678 }
4679
4680 int top, bottom, current;
4681 bottom = 0;
4682 top = blockStarts.length;
4683 current = top/2;
4684
4685 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4686 while (top - bottom > 1) {
4687 if (codePoint >= blockStarts[current]) {
4688 bottom = current;
4689 } else {
4690 top = current;
4691 }
4692 current = (top + bottom) / 2;
4693 }
4694 return blocks[current];
4695 }
4696
4697 /**
4698 * Returns the UnicodeBlock with the given name. Block
4699 * names are determined by The Unicode Standard. The file
4700 * {@code Blocks.txt} defines blocks for a particular
4701 * version of the standard. The {@link Character} class specifies
4702 * the version of the standard that it supports.
4703 * <p>
4704 * This method accepts block names in the following forms:
4705 * <ol>
4706 * <li> Canonical block names as defined by the Unicode Standard.
4707 * For example, the standard defines a "Basic Latin" block. Therefore, this
4708 * method accepts "Basic Latin" as a valid block name. The documentation of
4709 * each UnicodeBlock provides the canonical name.
4710 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4711 * is a valid block name for the "Basic Latin" block.
4712 * <li>The text representation of each constant UnicodeBlock identifier.
4713 * For example, this method will return the {@link #BASIC_LATIN} block if
4714 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4715 * hyphens in the canonical name with underscores.
4716 * </ol>
4717 * Finally, character case is ignored for all of the valid block name forms.
4718 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4719 * The en_US locale's case mapping rules are used to provide case-insensitive
4720 * string comparisons for block name validation.
4721 * <p>
4722 * If the Unicode Standard changes block names, both the previous and
4723 * current names will be accepted.
4724 *
4725 * @param blockName A {@code UnicodeBlock} name.
4726 * @return The {@code UnicodeBlock} instance identified
4727 * by {@code blockName}
4728 * @throws IllegalArgumentException if {@code blockName} is an
4729 * invalid name
4730 * @throws NullPointerException if {@code blockName} is null
4731 * @since 1.5
4732 */
4733 public static final UnicodeBlock forName(String blockName) {
4734 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4735 if (block == null) {
4736 throw new IllegalArgumentException("Not a valid block name: "
4737 + blockName);
4738 }
4739 return block;
4740 }
4741 }
4742
4743
4744 /**
4745 * A family of character subsets representing the character scripts
4746 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4747 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4748 * character is assigned to a single Unicode script, either a specific
4749 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4750 * one of the following three special values,
4751 * {@link Character.UnicodeScript#INHERITED Inherited},
4752 * {@link Character.UnicodeScript#COMMON Common} or
4753 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4754 *
4755 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4756 * @since 1.7
4757 */
4758 public static enum UnicodeScript {
4759
4760 /**
4761 * Unicode script "Common".
4762 */
4763 COMMON,
4764
4765 /**
4766 * Unicode script "Latin".
4767 */
4768 LATIN,
4769
4770 /**
4771 * Unicode script "Greek".
4772 */
4773 GREEK,
4774
4775 /**
4776 * Unicode script "Cyrillic".
4777 */
4778 CYRILLIC,
4779
4780 /**
4781 * Unicode script "Armenian".
4782 */
4783 ARMENIAN,
4784
4785 /**
4786 * Unicode script "Hebrew".
4787 */
4788 HEBREW,
4789
4790 /**
4791 * Unicode script "Arabic".
4792 */
4793 ARABIC,
4794
4795 /**
4796 * Unicode script "Syriac".
4797 */
4798 SYRIAC,
4799
4800 /**
4801 * Unicode script "Thaana".
4802 */
4803 THAANA,
4804
4805 /**
4806 * Unicode script "Devanagari".
4807 */
4808 DEVANAGARI,
4809
4810 /**
4811 * Unicode script "Bengali".
4812 */
4813 BENGALI,
4814
4815 /**
4816 * Unicode script "Gurmukhi".
4817 */
4818 GURMUKHI,
4819
4820 /**
4821 * Unicode script "Gujarati".
4822 */
4823 GUJARATI,
4824
4825 /**
4826 * Unicode script "Oriya".
4827 */
4828 ORIYA,
4829
4830 /**
4831 * Unicode script "Tamil".
4832 */
4833 TAMIL,
4834
4835 /**
4836 * Unicode script "Telugu".
4837 */
4838 TELUGU,
4839
4840 /**
4841 * Unicode script "Kannada".
4842 */
4843 KANNADA,
4844
4845 /**
4846 * Unicode script "Malayalam".
4847 */
4848 MALAYALAM,
4849
4850 /**
4851 * Unicode script "Sinhala".
4852 */
4853 SINHALA,
4854
4855 /**
4856 * Unicode script "Thai".
4857 */
4858 THAI,
4859
4860 /**
4861 * Unicode script "Lao".
4862 */
4863 LAO,
4864
4865 /**
4866 * Unicode script "Tibetan".
4867 */
4868 TIBETAN,
4869
4870 /**
4871 * Unicode script "Myanmar".
4872 */
4873 MYANMAR,
4874
4875 /**
4876 * Unicode script "Georgian".
4877 */
4878 GEORGIAN,
4879
4880 /**
4881 * Unicode script "Hangul".
4882 */
4883 HANGUL,
4884
4885 /**
4886 * Unicode script "Ethiopic".
4887 */
4888 ETHIOPIC,
4889
4890 /**
4891 * Unicode script "Cherokee".
4892 */
4893 CHEROKEE,
4894
4895 /**
4896 * Unicode script "Canadian_Aboriginal".
4897 */
4898 CANADIAN_ABORIGINAL,
4899
4900 /**
4901 * Unicode script "Ogham".
4902 */
4903 OGHAM,
4904
4905 /**
4906 * Unicode script "Runic".
4907 */
4908 RUNIC,
4909
4910 /**
4911 * Unicode script "Khmer".
4912 */
4913 KHMER,
4914
4915 /**
4916 * Unicode script "Mongolian".
4917 */
4918 MONGOLIAN,
4919
4920 /**
4921 * Unicode script "Hiragana".
4922 */
4923 HIRAGANA,
4924
4925 /**
4926 * Unicode script "Katakana".
4927 */
4928 KATAKANA,
4929
4930 /**
4931 * Unicode script "Bopomofo".
4932 */
4933 BOPOMOFO,
4934
4935 /**
4936 * Unicode script "Han".
4937 */
4938 HAN,
4939
4940 /**
4941 * Unicode script "Yi".
4942 */
4943 YI,
4944
4945 /**
4946 * Unicode script "Old_Italic".
4947 */
4948 OLD_ITALIC,
4949
4950 /**
4951 * Unicode script "Gothic".
4952 */
4953 GOTHIC,
4954
4955 /**
4956 * Unicode script "Deseret".
4957 */
4958 DESERET,
4959
4960 /**
4961 * Unicode script "Inherited".
4962 */
4963 INHERITED,
4964
4965 /**
4966 * Unicode script "Tagalog".
4967 */
4968 TAGALOG,
4969
4970 /**
4971 * Unicode script "Hanunoo".
4972 */
4973 HANUNOO,
4974
4975 /**
4976 * Unicode script "Buhid".
4977 */
4978 BUHID,
4979
4980 /**
4981 * Unicode script "Tagbanwa".
4982 */
4983 TAGBANWA,
4984
4985 /**
4986 * Unicode script "Limbu".
4987 */
4988 LIMBU,
4989
4990 /**
4991 * Unicode script "Tai_Le".
4992 */
4993 TAI_LE,
4994
4995 /**
4996 * Unicode script "Linear_B".
4997 */
4998 LINEAR_B,
4999
5000 /**
5001 * Unicode script "Ugaritic".
5002 */
5003 UGARITIC,
5004
5005 /**
5006 * Unicode script "Shavian".
5007 */
5008 SHAVIAN,
5009
5010 /**
5011 * Unicode script "Osmanya".
5012 */
5013 OSMANYA,
5014
5015 /**
5016 * Unicode script "Cypriot".
5017 */
5018 CYPRIOT,
5019
5020 /**
5021 * Unicode script "Braille".
5022 */
5023 BRAILLE,
5024
5025 /**
5026 * Unicode script "Buginese".
5027 */
5028 BUGINESE,
5029
5030 /**
5031 * Unicode script "Coptic".
5032 */
5033 COPTIC,
5034
5035 /**
5036 * Unicode script "New_Tai_Lue".
5037 */
5038 NEW_TAI_LUE,
5039
5040 /**
5041 * Unicode script "Glagolitic".
5042 */
5043 GLAGOLITIC,
5044
5045 /**
5046 * Unicode script "Tifinagh".
5047 */
5048 TIFINAGH,
5049
5050 /**
5051 * Unicode script "Syloti_Nagri".
5052 */
5053 SYLOTI_NAGRI,
5054
5055 /**
5056 * Unicode script "Old_Persian".
5057 */
5058 OLD_PERSIAN,
5059
5060 /**
5061 * Unicode script "Kharoshthi".
5062 */
5063 KHAROSHTHI,
5064
5065 /**
5066 * Unicode script "Balinese".
5067 */
5068 BALINESE,
5069
5070 /**
5071 * Unicode script "Cuneiform".
5072 */
5073 CUNEIFORM,
5074
5075 /**
5076 * Unicode script "Phoenician".
5077 */
5078 PHOENICIAN,
5079
5080 /**
5081 * Unicode script "Phags_Pa".
5082 */
5083 PHAGS_PA,
5084
5085 /**
5086 * Unicode script "Nko".
5087 */
5088 NKO,
5089
5090 /**
5091 * Unicode script "Sundanese".
5092 */
5093 SUNDANESE,
5094
5095 /**
5096 * Unicode script "Batak".
5097 */
5098 BATAK,
5099
5100 /**
5101 * Unicode script "Lepcha".
5102 */
5103 LEPCHA,
5104
5105 /**
5106 * Unicode script "Ol_Chiki".
5107 */
5108 OL_CHIKI,
5109
5110 /**
5111 * Unicode script "Vai".
5112 */
5113 VAI,
5114
5115 /**
5116 * Unicode script "Saurashtra".
5117 */
5118 SAURASHTRA,
5119
5120 /**
5121 * Unicode script "Kayah_Li".
5122 */
5123 KAYAH_LI,
5124
5125 /**
5126 * Unicode script "Rejang".
5127 */
5128 REJANG,
5129
5130 /**
5131 * Unicode script "Lycian".
5132 */
5133 LYCIAN,
5134
5135 /**
5136 * Unicode script "Carian".
5137 */
5138 CARIAN,
5139
5140 /**
5141 * Unicode script "Lydian".
5142 */
5143 LYDIAN,
5144
5145 /**
5146 * Unicode script "Cham".
5147 */
5148 CHAM,
5149
5150 /**
5151 * Unicode script "Tai_Tham".
5152 */
5153 TAI_THAM,
5154
5155 /**
5156 * Unicode script "Tai_Viet".
5157 */
5158 TAI_VIET,
5159
5160 /**
5161 * Unicode script "Avestan".
5162 */
5163 AVESTAN,
5164
5165 /**
5166 * Unicode script "Egyptian_Hieroglyphs".
5167 */
5168 EGYPTIAN_HIEROGLYPHS,
5169
5170 /**
5171 * Unicode script "Samaritan".
5172 */
5173 SAMARITAN,
5174
5175 /**
5176 * Unicode script "Mandaic".
5177 */
5178 MANDAIC,
5179
5180 /**
5181 * Unicode script "Lisu".
5182 */
5183 LISU,
5184
5185 /**
5186 * Unicode script "Bamum".
5187 */
5188 BAMUM,
5189
5190 /**
5191 * Unicode script "Javanese".
5192 */
5193 JAVANESE,
5194
5195 /**
5196 * Unicode script "Meetei_Mayek".
5197 */
5198 MEETEI_MAYEK,
5199
5200 /**
5201 * Unicode script "Imperial_Aramaic".
5202 */
5203 IMPERIAL_ARAMAIC,
5204
5205 /**
5206 * Unicode script "Old_South_Arabian".
5207 */
5208 OLD_SOUTH_ARABIAN,
5209
5210 /**
5211 * Unicode script "Inscriptional_Parthian".
5212 */
5213 INSCRIPTIONAL_PARTHIAN,
5214
5215 /**
5216 * Unicode script "Inscriptional_Pahlavi".
5217 */
5218 INSCRIPTIONAL_PAHLAVI,
5219
5220 /**
5221 * Unicode script "Old_Turkic".
5222 */
5223 OLD_TURKIC,
5224
5225 /**
5226 * Unicode script "Brahmi".
5227 */
5228 BRAHMI,
5229
5230 /**
5231 * Unicode script "Kaithi".
5232 */
5233 KAITHI,
5234
5235 /**
5236 * Unicode script "Meroitic Hieroglyphs".
5237 * @since 1.8
5238 */
5239 MEROITIC_HIEROGLYPHS,
5240
5241 /**
5242 * Unicode script "Meroitic Cursive".
5243 * @since 1.8
5244 */
5245 MEROITIC_CURSIVE,
5246
5247 /**
5248 * Unicode script "Sora Sompeng".
5249 * @since 1.8
5250 */
5251 SORA_SOMPENG,
5252
5253 /**
5254 * Unicode script "Chakma".
5255 * @since 1.8
5256 */
5257 CHAKMA,
5258
5259 /**
5260 * Unicode script "Sharada".
5261 * @since 1.8
5262 */
5263 SHARADA,
5264
5265 /**
5266 * Unicode script "Takri".
5267 * @since 1.8
5268 */
5269 TAKRI,
5270
5271 /**
5272 * Unicode script "Miao".
5273 * @since 1.8
5274 */
5275 MIAO,
5276
5277 /**
5278 * Unicode script "Caucasian Albanian".
5279 * @since 9
5280 */
5281 CAUCASIAN_ALBANIAN,
5282
5283 /**
5284 * Unicode script "Bassa Vah".
5285 * @since 9
5286 */
5287 BASSA_VAH,
5288
5289 /**
5290 * Unicode script "Duployan".
5291 * @since 9
5292 */
5293 DUPLOYAN,
5294
5295 /**
5296 * Unicode script "Elbasan".
5297 * @since 9
5298 */
5299 ELBASAN,
5300
5301 /**
5302 * Unicode script "Grantha".
5303 * @since 9
5304 */
5305 GRANTHA,
5306
5307 /**
5308 * Unicode script "Pahawh Hmong".
5309 * @since 9
5310 */
5311 PAHAWH_HMONG,
5312
5313 /**
5314 * Unicode script "Khojki".
5315 * @since 9
5316 */
5317 KHOJKI,
5318
5319 /**
5320 * Unicode script "Linear A".
5321 * @since 9
5322 */
5323 LINEAR_A,
5324
5325 /**
5326 * Unicode script "Mahajani".
5327 * @since 9
5328 */
5329 MAHAJANI,
5330
5331 /**
5332 * Unicode script "Manichaean".
5333 * @since 9
5334 */
5335 MANICHAEAN,
5336
5337 /**
5338 * Unicode script "Mende Kikakui".
5339 * @since 9
5340 */
5341 MENDE_KIKAKUI,
5342
5343 /**
5344 * Unicode script "Modi".
5345 * @since 9
5346 */
5347 MODI,
5348
5349 /**
5350 * Unicode script "Mro".
5351 * @since 9
5352 */
5353 MRO,
5354
5355 /**
5356 * Unicode script "Old North Arabian".
5357 * @since 9
5358 */
5359 OLD_NORTH_ARABIAN,
5360
5361 /**
5362 * Unicode script "Nabataean".
5363 * @since 9
5364 */
5365 NABATAEAN,
5366
5367 /**
5368 * Unicode script "Palmyrene".
5369 * @since 9
5370 */
5371 PALMYRENE,
5372
5373 /**
5374 * Unicode script "Pau Cin Hau".
5375 * @since 9
5376 */
5377 PAU_CIN_HAU,
5378
5379 /**
5380 * Unicode script "Old Permic".
5381 * @since 9
5382 */
5383 OLD_PERMIC,
5384
5385 /**
5386 * Unicode script "Psalter Pahlavi".
5387 * @since 9
5388 */
5389 PSALTER_PAHLAVI,
5390
5391 /**
5392 * Unicode script "Siddham".
5393 * @since 9
5394 */
5395 SIDDHAM,
5396
5397 /**
5398 * Unicode script "Khudawadi".
5399 * @since 9
5400 */
5401 KHUDAWADI,
5402
5403 /**
5404 * Unicode script "Tirhuta".
5405 * @since 9
5406 */
5407 TIRHUTA,
5408
5409 /**
5410 * Unicode script "Warang Citi".
5411 * @since 9
5412 */
5413 WARANG_CITI,
5414
5415 /**
5416 * Unicode script "Ahom".
5417 * @since 9
5418 */
5419 AHOM,
5420
5421 /**
5422 * Unicode script "Anatolian Hieroglyphs".
5423 * @since 9
5424 */
5425 ANATOLIAN_HIEROGLYPHS,
5426
5427 /**
5428 * Unicode script "Hatran".
5429 * @since 9
5430 */
5431 HATRAN,
5432
5433 /**
5434 * Unicode script "Multani".
5435 * @since 9
5436 */
5437 MULTANI,
5438
5439 /**
5440 * Unicode script "Old Hungarian".
5441 * @since 9
5442 */
5443 OLD_HUNGARIAN,
5444
5445 /**
5446 * Unicode script "SignWriting".
5447 * @since 9
5448 */
5449 SIGNWRITING,
5450
5451 /**
5452 * Unicode script "Adlam".
5453 * @since 11
5454 */
5455 ADLAM,
5456
5457 /**
5458 * Unicode script "Bhaiksuki".
5459 * @since 11
5460 */
5461 BHAIKSUKI,
5462
5463 /**
5464 * Unicode script "Marchen".
5465 * @since 11
5466 */
5467 MARCHEN,
5468
5469 /**
5470 * Unicode script "Newa".
5471 * @since 11
5472 */
5473 NEWA,
5474
5475 /**
5476 * Unicode script "Osage".
5477 * @since 11
5478 */
5479 OSAGE,
5480
5481 /**
5482 * Unicode script "Tangut".
5483 * @since 11
5484 */
5485 TANGUT,
5486
5487 /**
5488 * Unicode script "Masaram Gondi".
5489 * @since 11
5490 */
5491 MASARAM_GONDI,
5492
5493 /**
5494 * Unicode script "Nushu".
5495 * @since 11
5496 */
5497 NUSHU,
5498
5499 /**
5500 * Unicode script "Soyombo".
5501 * @since 11
5502 */
5503 SOYOMBO,
5504
5505 /**
5506 * Unicode script "Zanabazar Square".
5507 * @since 11
5508 */
5509 ZANABAZAR_SQUARE,
5510
5511 /**
5512 * Unicode script "Hanifi Rohingya".
5513 * @since 12
5514 */
5515 HANIFI_ROHINGYA,
5516
5517 /**
5518 * Unicode script "Old Sogdian".
5519 * @since 12
5520 */
5521 OLD_SOGDIAN,
5522
5523 /**
5524 * Unicode script "Sogdian".
5525 * @since 12
5526 */
5527 SOGDIAN,
5528
5529 /**
5530 * Unicode script "Dogra".
5531 * @since 12
5532 */
5533 DOGRA,
5534
5535 /**
5536 * Unicode script "Gunjala Gondi".
5537 * @since 12
5538 */
5539 GUNJALA_GONDI,
5540
5541 /**
5542 * Unicode script "Makasar".
5543 * @since 12
5544 */
5545 MAKASAR,
5546
5547 /**
5548 * Unicode script "Medefaidrin".
5549 * @since 12
5550 */
5551 MEDEFAIDRIN,
5552
5553 /**
5554 * Unicode script "Elymaic".
5555 * @since 13
5556 */
5557 ELYMAIC,
5558
5559 /**
5560 * Unicode script "Nandinagari".
5561 * @since 13
5562 */
5563 NANDINAGARI,
5564
5565 /**
5566 * Unicode script "Nyiakeng Puachue Hmong".
5567 * @since 13
5568 */
5569 NYIAKENG_PUACHUE_HMONG,
5570
5571 /**
5572 * Unicode script "Wancho".
5573 * @since 13
5574 */
5575 WANCHO,
5576
5577 /**
5578 * Unicode script "Yezidi".
5579 * @since 15
5580 */
5581 YEZIDI,
5582
5583 /**
5584 * Unicode script "Chorasmian".
5585 * @since 15
5586 */
5587 CHORASMIAN,
5588
5589 /**
5590 * Unicode script "Dives Akuru".
5591 * @since 15
5592 */
5593 DIVES_AKURU,
5594
5595 /**
5596 * Unicode script "Khitan Small Script".
5597 * @since 15
5598 */
5599 KHITAN_SMALL_SCRIPT,
5600
5601 /**
5602 * Unicode script "Vithkuqi".
5603 * @since 19
5604 */
5605 VITHKUQI,
5606
5607 /**
5608 * Unicode script "Old Uyghur".
5609 * @since 19
5610 */
5611 OLD_UYGHUR,
5612
5613 /**
5614 * Unicode script "Cypro Minoan".
5615 * @since 19
5616 */
5617 CYPRO_MINOAN,
5618
5619 /**
5620 * Unicode script "Tangsa".
5621 * @since 19
5622 */
5623 TANGSA,
5624
5625 /**
5626 * Unicode script "Toto".
5627 * @since 19
5628 */
5629 TOTO,
5630
5631 /**
5632 * Unicode script "Kawi".
5633 * @since 20
5634 */
5635 KAWI,
5636
5637 /**
5638 * Unicode script "Nag Mundari".
5639 * @since 20
5640 */
5641 NAG_MUNDARI,
5642
5643 /**
5644 * Unicode script "Todhri".
5645 * @since 24
5646 */
5647 TODHRI,
5648
5649 /**
5650 * Unicode script "Garay".
5651 * @since 24
5652 */
5653 GARAY,
5654
5655 /**
5656 * Unicode script "Tulu Tigalari".
5657 * @since 24
5658 */
5659 TULU_TIGALARI,
5660
5661 /**
5662 * Unicode script "Sunuwar".
5663 * @since 24
5664 */
5665 SUNUWAR,
5666
5667 /**
5668 * Unicode script "Gurung Khema".
5669 * @since 24
5670 */
5671 GURUNG_KHEMA,
5672
5673 /**
5674 * Unicode script "Kirat Rai".
5675 * @since 24
5676 */
5677 KIRAT_RAI,
5678
5679 /**
5680 * Unicode script "Ol Onal".
5681 * @since 24
5682 */
5683 OL_ONAL,
5684
5685 /**
5686 * Unicode script "Sidetic".
5687 * @since 26
5688 */
5689 SIDETIC,
5690
5691 /**
5692 * Unicode script "Tolong Siki".
5693 * @since 26
5694 */
5695 TOLONG_SIKI,
5696
5697 /**
5698 * Unicode script "Beria Erfe".
5699 * @since 26
5700 */
5701 BERIA_ERFE,
5702
5703 /**
5704 * Unicode script "Tai Yo".
5705 * @since 26
5706 */
5707 TAI_YO,
5708
5709 /**
5710 * Unicode script "Unknown".
5711 */
5712 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5713
5714 private static final int[] scriptStarts = {
5715 0x0000, // 0000..0040; COMMON
5716 0x0041, // 0041..005A; LATIN
5717 0x005B, // 005B..0060; COMMON
5718 0x0061, // 0061..007A; LATIN
5719 0x007B, // 007B..00A9; COMMON
5720 0x00AA, // 00AA ; LATIN
5721 0x00AB, // 00AB..00B9; COMMON
5722 0x00BA, // 00BA ; LATIN
5723 0x00BB, // 00BB..00BF; COMMON
5724 0x00C0, // 00C0..00D6; LATIN
5725 0x00D7, // 00D7 ; COMMON
5726 0x00D8, // 00D8..00F6; LATIN
5727 0x00F7, // 00F7 ; COMMON
5728 0x00F8, // 00F8..02B8; LATIN
5729 0x02B9, // 02B9..02DF; COMMON
5730 0x02E0, // 02E0..02E4; LATIN
5731 0x02E5, // 02E5..02E9; COMMON
5732 0x02EA, // 02EA..02EB; BOPOMOFO
5733 0x02EC, // 02EC..02FF; COMMON
5734 0x0300, // 0300..036F; INHERITED
5735 0x0370, // 0370..0373; GREEK
5736 0x0374, // 0374 ; COMMON
5737 0x0375, // 0375..0377; GREEK
5738 0x0378, // 0378..0379; UNKNOWN
5739 0x037A, // 037A..037D; GREEK
5740 0x037E, // 037E ; COMMON
5741 0x037F, // 037F ; GREEK
5742 0x0380, // 0380..0383; UNKNOWN
5743 0x0384, // 0384 ; GREEK
5744 0x0385, // 0385 ; COMMON
5745 0x0386, // 0386 ; GREEK
5746 0x0387, // 0387 ; COMMON
5747 0x0388, // 0388..038A; GREEK
5748 0x038B, // 038B ; UNKNOWN
5749 0x038C, // 038C ; GREEK
5750 0x038D, // 038D ; UNKNOWN
5751 0x038E, // 038E..03A1; GREEK
5752 0x03A2, // 03A2 ; UNKNOWN
5753 0x03A3, // 03A3..03E1; GREEK
5754 0x03E2, // 03E2..03EF; COPTIC
5755 0x03F0, // 03F0..03FF; GREEK
5756 0x0400, // 0400..0484; CYRILLIC
5757 0x0485, // 0485..0486; INHERITED
5758 0x0487, // 0487..052F; CYRILLIC
5759 0x0530, // 0530 ; UNKNOWN
5760 0x0531, // 0531..0556; ARMENIAN
5761 0x0557, // 0557..0558; UNKNOWN
5762 0x0559, // 0559..058A; ARMENIAN
5763 0x058B, // 058B..058C; UNKNOWN
5764 0x058D, // 058D..058F; ARMENIAN
5765 0x0590, // 0590 ; UNKNOWN
5766 0x0591, // 0591..05C7; HEBREW
5767 0x05C8, // 05C8..05CF; UNKNOWN
5768 0x05D0, // 05D0..05EA; HEBREW
5769 0x05EB, // 05EB..05EE; UNKNOWN
5770 0x05EF, // 05EF..05F4; HEBREW
5771 0x05F5, // 05F5..05FF; UNKNOWN
5772 0x0600, // 0600..0604; ARABIC
5773 0x0605, // 0605 ; COMMON
5774 0x0606, // 0606..060B; ARABIC
5775 0x060C, // 060C ; COMMON
5776 0x060D, // 060D..061A; ARABIC
5777 0x061B, // 061B ; COMMON
5778 0x061C, // 061C..061E; ARABIC
5779 0x061F, // 061F ; COMMON
5780 0x0620, // 0620..063F; ARABIC
5781 0x0640, // 0640 ; COMMON
5782 0x0641, // 0641..064A; ARABIC
5783 0x064B, // 064B..0655; INHERITED
5784 0x0656, // 0656..066F; ARABIC
5785 0x0670, // 0670 ; INHERITED
5786 0x0671, // 0671..06DC; ARABIC
5787 0x06DD, // 06DD ; COMMON
5788 0x06DE, // 06DE..06FF; ARABIC
5789 0x0700, // 0700..070D; SYRIAC
5790 0x070E, // 070E ; UNKNOWN
5791 0x070F, // 070F..074A; SYRIAC
5792 0x074B, // 074B..074C; UNKNOWN
5793 0x074D, // 074D..074F; SYRIAC
5794 0x0750, // 0750..077F; ARABIC
5795 0x0780, // 0780..07B1; THAANA
5796 0x07B2, // 07B2..07BF; UNKNOWN
5797 0x07C0, // 07C0..07FA; NKO
5798 0x07FB, // 07FB..07FC; UNKNOWN
5799 0x07FD, // 07FD..07FF; NKO
5800 0x0800, // 0800..082D; SAMARITAN
5801 0x082E, // 082E..082F; UNKNOWN
5802 0x0830, // 0830..083E; SAMARITAN
5803 0x083F, // 083F ; UNKNOWN
5804 0x0840, // 0840..085B; MANDAIC
5805 0x085C, // 085C..085D; UNKNOWN
5806 0x085E, // 085E ; MANDAIC
5807 0x085F, // 085F ; UNKNOWN
5808 0x0860, // 0860..086A; SYRIAC
5809 0x086B, // 086B..086F; UNKNOWN
5810 0x0870, // 0870..0891; ARABIC
5811 0x0892, // 0892..0896; UNKNOWN
5812 0x0897, // 0897..08E1; ARABIC
5813 0x08E2, // 08E2 ; COMMON
5814 0x08E3, // 08E3..08FF; ARABIC
5815 0x0900, // 0900..0950; DEVANAGARI
5816 0x0951, // 0951..0954; INHERITED
5817 0x0955, // 0955..0963; DEVANAGARI
5818 0x0964, // 0964..0965; COMMON
5819 0x0966, // 0966..097F; DEVANAGARI
5820 0x0980, // 0980..0983; BENGALI
5821 0x0984, // 0984 ; UNKNOWN
5822 0x0985, // 0985..098C; BENGALI
5823 0x098D, // 098D..098E; UNKNOWN
5824 0x098F, // 098F..0990; BENGALI
5825 0x0991, // 0991..0992; UNKNOWN
5826 0x0993, // 0993..09A8; BENGALI
5827 0x09A9, // 09A9 ; UNKNOWN
5828 0x09AA, // 09AA..09B0; BENGALI
5829 0x09B1, // 09B1 ; UNKNOWN
5830 0x09B2, // 09B2 ; BENGALI
5831 0x09B3, // 09B3..09B5; UNKNOWN
5832 0x09B6, // 09B6..09B9; BENGALI
5833 0x09BA, // 09BA..09BB; UNKNOWN
5834 0x09BC, // 09BC..09C4; BENGALI
5835 0x09C5, // 09C5..09C6; UNKNOWN
5836 0x09C7, // 09C7..09C8; BENGALI
5837 0x09C9, // 09C9..09CA; UNKNOWN
5838 0x09CB, // 09CB..09CE; BENGALI
5839 0x09CF, // 09CF..09D6; UNKNOWN
5840 0x09D7, // 09D7 ; BENGALI
5841 0x09D8, // 09D8..09DB; UNKNOWN
5842 0x09DC, // 09DC..09DD; BENGALI
5843 0x09DE, // 09DE ; UNKNOWN
5844 0x09DF, // 09DF..09E3; BENGALI
5845 0x09E4, // 09E4..09E5; UNKNOWN
5846 0x09E6, // 09E6..09FE; BENGALI
5847 0x09FF, // 09FF..0A00; UNKNOWN
5848 0x0A01, // 0A01..0A03; GURMUKHI
5849 0x0A04, // 0A04 ; UNKNOWN
5850 0x0A05, // 0A05..0A0A; GURMUKHI
5851 0x0A0B, // 0A0B..0A0E; UNKNOWN
5852 0x0A0F, // 0A0F..0A10; GURMUKHI
5853 0x0A11, // 0A11..0A12; UNKNOWN
5854 0x0A13, // 0A13..0A28; GURMUKHI
5855 0x0A29, // 0A29 ; UNKNOWN
5856 0x0A2A, // 0A2A..0A30; GURMUKHI
5857 0x0A31, // 0A31 ; UNKNOWN
5858 0x0A32, // 0A32..0A33; GURMUKHI
5859 0x0A34, // 0A34 ; UNKNOWN
5860 0x0A35, // 0A35..0A36; GURMUKHI
5861 0x0A37, // 0A37 ; UNKNOWN
5862 0x0A38, // 0A38..0A39; GURMUKHI
5863 0x0A3A, // 0A3A..0A3B; UNKNOWN
5864 0x0A3C, // 0A3C ; GURMUKHI
5865 0x0A3D, // 0A3D ; UNKNOWN
5866 0x0A3E, // 0A3E..0A42; GURMUKHI
5867 0x0A43, // 0A43..0A46; UNKNOWN
5868 0x0A47, // 0A47..0A48; GURMUKHI
5869 0x0A49, // 0A49..0A4A; UNKNOWN
5870 0x0A4B, // 0A4B..0A4D; GURMUKHI
5871 0x0A4E, // 0A4E..0A50; UNKNOWN
5872 0x0A51, // 0A51 ; GURMUKHI
5873 0x0A52, // 0A52..0A58; UNKNOWN
5874 0x0A59, // 0A59..0A5C; GURMUKHI
5875 0x0A5D, // 0A5D ; UNKNOWN
5876 0x0A5E, // 0A5E ; GURMUKHI
5877 0x0A5F, // 0A5F..0A65; UNKNOWN
5878 0x0A66, // 0A66..0A76; GURMUKHI
5879 0x0A77, // 0A77..0A80; UNKNOWN
5880 0x0A81, // 0A81..0A83; GUJARATI
5881 0x0A84, // 0A84 ; UNKNOWN
5882 0x0A85, // 0A85..0A8D; GUJARATI
5883 0x0A8E, // 0A8E ; UNKNOWN
5884 0x0A8F, // 0A8F..0A91; GUJARATI
5885 0x0A92, // 0A92 ; UNKNOWN
5886 0x0A93, // 0A93..0AA8; GUJARATI
5887 0x0AA9, // 0AA9 ; UNKNOWN
5888 0x0AAA, // 0AAA..0AB0; GUJARATI
5889 0x0AB1, // 0AB1 ; UNKNOWN
5890 0x0AB2, // 0AB2..0AB3; GUJARATI
5891 0x0AB4, // 0AB4 ; UNKNOWN
5892 0x0AB5, // 0AB5..0AB9; GUJARATI
5893 0x0ABA, // 0ABA..0ABB; UNKNOWN
5894 0x0ABC, // 0ABC..0AC5; GUJARATI
5895 0x0AC6, // 0AC6 ; UNKNOWN
5896 0x0AC7, // 0AC7..0AC9; GUJARATI
5897 0x0ACA, // 0ACA ; UNKNOWN
5898 0x0ACB, // 0ACB..0ACD; GUJARATI
5899 0x0ACE, // 0ACE..0ACF; UNKNOWN
5900 0x0AD0, // 0AD0 ; GUJARATI
5901 0x0AD1, // 0AD1..0ADF; UNKNOWN
5902 0x0AE0, // 0AE0..0AE3; GUJARATI
5903 0x0AE4, // 0AE4..0AE5; UNKNOWN
5904 0x0AE6, // 0AE6..0AF1; GUJARATI
5905 0x0AF2, // 0AF2..0AF8; UNKNOWN
5906 0x0AF9, // 0AF9..0AFF; GUJARATI
5907 0x0B00, // 0B00 ; UNKNOWN
5908 0x0B01, // 0B01..0B03; ORIYA
5909 0x0B04, // 0B04 ; UNKNOWN
5910 0x0B05, // 0B05..0B0C; ORIYA
5911 0x0B0D, // 0B0D..0B0E; UNKNOWN
5912 0x0B0F, // 0B0F..0B10; ORIYA
5913 0x0B11, // 0B11..0B12; UNKNOWN
5914 0x0B13, // 0B13..0B28; ORIYA
5915 0x0B29, // 0B29 ; UNKNOWN
5916 0x0B2A, // 0B2A..0B30; ORIYA
5917 0x0B31, // 0B31 ; UNKNOWN
5918 0x0B32, // 0B32..0B33; ORIYA
5919 0x0B34, // 0B34 ; UNKNOWN
5920 0x0B35, // 0B35..0B39; ORIYA
5921 0x0B3A, // 0B3A..0B3B; UNKNOWN
5922 0x0B3C, // 0B3C..0B44; ORIYA
5923 0x0B45, // 0B45..0B46; UNKNOWN
5924 0x0B47, // 0B47..0B48; ORIYA
5925 0x0B49, // 0B49..0B4A; UNKNOWN
5926 0x0B4B, // 0B4B..0B4D; ORIYA
5927 0x0B4E, // 0B4E..0B54; UNKNOWN
5928 0x0B55, // 0B55..0B57; ORIYA
5929 0x0B58, // 0B58..0B5B; UNKNOWN
5930 0x0B5C, // 0B5C..0B5D; ORIYA
5931 0x0B5E, // 0B5E ; UNKNOWN
5932 0x0B5F, // 0B5F..0B63; ORIYA
5933 0x0B64, // 0B64..0B65; UNKNOWN
5934 0x0B66, // 0B66..0B77; ORIYA
5935 0x0B78, // 0B78..0B81; UNKNOWN
5936 0x0B82, // 0B82..0B83; TAMIL
5937 0x0B84, // 0B84 ; UNKNOWN
5938 0x0B85, // 0B85..0B8A; TAMIL
5939 0x0B8B, // 0B8B..0B8D; UNKNOWN
5940 0x0B8E, // 0B8E..0B90; TAMIL
5941 0x0B91, // 0B91 ; UNKNOWN
5942 0x0B92, // 0B92..0B95; TAMIL
5943 0x0B96, // 0B96..0B98; UNKNOWN
5944 0x0B99, // 0B99..0B9A; TAMIL
5945 0x0B9B, // 0B9B ; UNKNOWN
5946 0x0B9C, // 0B9C ; TAMIL
5947 0x0B9D, // 0B9D ; UNKNOWN
5948 0x0B9E, // 0B9E..0B9F; TAMIL
5949 0x0BA0, // 0BA0..0BA2; UNKNOWN
5950 0x0BA3, // 0BA3..0BA4; TAMIL
5951 0x0BA5, // 0BA5..0BA7; UNKNOWN
5952 0x0BA8, // 0BA8..0BAA; TAMIL
5953 0x0BAB, // 0BAB..0BAD; UNKNOWN
5954 0x0BAE, // 0BAE..0BB9; TAMIL
5955 0x0BBA, // 0BBA..0BBD; UNKNOWN
5956 0x0BBE, // 0BBE..0BC2; TAMIL
5957 0x0BC3, // 0BC3..0BC5; UNKNOWN
5958 0x0BC6, // 0BC6..0BC8; TAMIL
5959 0x0BC9, // 0BC9 ; UNKNOWN
5960 0x0BCA, // 0BCA..0BCD; TAMIL
5961 0x0BCE, // 0BCE..0BCF; UNKNOWN
5962 0x0BD0, // 0BD0 ; TAMIL
5963 0x0BD1, // 0BD1..0BD6; UNKNOWN
5964 0x0BD7, // 0BD7 ; TAMIL
5965 0x0BD8, // 0BD8..0BE5; UNKNOWN
5966 0x0BE6, // 0BE6..0BFA; TAMIL
5967 0x0BFB, // 0BFB..0BFF; UNKNOWN
5968 0x0C00, // 0C00..0C0C; TELUGU
5969 0x0C0D, // 0C0D ; UNKNOWN
5970 0x0C0E, // 0C0E..0C10; TELUGU
5971 0x0C11, // 0C11 ; UNKNOWN
5972 0x0C12, // 0C12..0C28; TELUGU
5973 0x0C29, // 0C29 ; UNKNOWN
5974 0x0C2A, // 0C2A..0C39; TELUGU
5975 0x0C3A, // 0C3A..0C3B; UNKNOWN
5976 0x0C3C, // 0C3C..0C44; TELUGU
5977 0x0C45, // 0C45 ; UNKNOWN
5978 0x0C46, // 0C46..0C48; TELUGU
5979 0x0C49, // 0C49 ; UNKNOWN
5980 0x0C4A, // 0C4A..0C4D; TELUGU
5981 0x0C4E, // 0C4E..0C54; UNKNOWN
5982 0x0C55, // 0C55..0C56; TELUGU
5983 0x0C57, // 0C57 ; UNKNOWN
5984 0x0C58, // 0C58..0C5A; TELUGU
5985 0x0C5B, // 0C5B ; UNKNOWN
5986 0x0C5C, // 0C5C..0C5D; TELUGU
5987 0x0C5E, // 0C5E..0C5F; UNKNOWN
5988 0x0C60, // 0C60..0C63; TELUGU
5989 0x0C64, // 0C64..0C65; UNKNOWN
5990 0x0C66, // 0C66..0C6F; TELUGU
5991 0x0C70, // 0C70..0C76; UNKNOWN
5992 0x0C77, // 0C77..0C7F; TELUGU
5993 0x0C80, // 0C80..0C8C; KANNADA
5994 0x0C8D, // 0C8D ; UNKNOWN
5995 0x0C8E, // 0C8E..0C90; KANNADA
5996 0x0C91, // 0C91 ; UNKNOWN
5997 0x0C92, // 0C92..0CA8; KANNADA
5998 0x0CA9, // 0CA9 ; UNKNOWN
5999 0x0CAA, // 0CAA..0CB3; KANNADA
6000 0x0CB4, // 0CB4 ; UNKNOWN
6001 0x0CB5, // 0CB5..0CB9; KANNADA
6002 0x0CBA, // 0CBA..0CBB; UNKNOWN
6003 0x0CBC, // 0CBC..0CC4; KANNADA
6004 0x0CC5, // 0CC5 ; UNKNOWN
6005 0x0CC6, // 0CC6..0CC8; KANNADA
6006 0x0CC9, // 0CC9 ; UNKNOWN
6007 0x0CCA, // 0CCA..0CCD; KANNADA
6008 0x0CCE, // 0CCE..0CD4; UNKNOWN
6009 0x0CD5, // 0CD5..0CD6; KANNADA
6010 0x0CD7, // 0CD7..0CDB; UNKNOWN
6011 0x0CDC, // 0CDC..0CDE; KANNADA
6012 0x0CDF, // 0CDF ; UNKNOWN
6013 0x0CE0, // 0CE0..0CE3; KANNADA
6014 0x0CE4, // 0CE4..0CE5; UNKNOWN
6015 0x0CE6, // 0CE6..0CEF; KANNADA
6016 0x0CF0, // 0CF0 ; UNKNOWN
6017 0x0CF1, // 0CF1..0CF3; KANNADA
6018 0x0CF4, // 0CF4..0CFF; UNKNOWN
6019 0x0D00, // 0D00..0D0C; MALAYALAM
6020 0x0D0D, // 0D0D ; UNKNOWN
6021 0x0D0E, // 0D0E..0D10; MALAYALAM
6022 0x0D11, // 0D11 ; UNKNOWN
6023 0x0D12, // 0D12..0D44; MALAYALAM
6024 0x0D45, // 0D45 ; UNKNOWN
6025 0x0D46, // 0D46..0D48; MALAYALAM
6026 0x0D49, // 0D49 ; UNKNOWN
6027 0x0D4A, // 0D4A..0D4F; MALAYALAM
6028 0x0D50, // 0D50..0D53; UNKNOWN
6029 0x0D54, // 0D54..0D63; MALAYALAM
6030 0x0D64, // 0D64..0D65; UNKNOWN
6031 0x0D66, // 0D66..0D7F; MALAYALAM
6032 0x0D80, // 0D80 ; UNKNOWN
6033 0x0D81, // 0D81..0D83; SINHALA
6034 0x0D84, // 0D84 ; UNKNOWN
6035 0x0D85, // 0D85..0D96; SINHALA
6036 0x0D97, // 0D97..0D99; UNKNOWN
6037 0x0D9A, // 0D9A..0DB1; SINHALA
6038 0x0DB2, // 0DB2 ; UNKNOWN
6039 0x0DB3, // 0DB3..0DBB; SINHALA
6040 0x0DBC, // 0DBC ; UNKNOWN
6041 0x0DBD, // 0DBD ; SINHALA
6042 0x0DBE, // 0DBE..0DBF; UNKNOWN
6043 0x0DC0, // 0DC0..0DC6; SINHALA
6044 0x0DC7, // 0DC7..0DC9; UNKNOWN
6045 0x0DCA, // 0DCA ; SINHALA
6046 0x0DCB, // 0DCB..0DCE; UNKNOWN
6047 0x0DCF, // 0DCF..0DD4; SINHALA
6048 0x0DD5, // 0DD5 ; UNKNOWN
6049 0x0DD6, // 0DD6 ; SINHALA
6050 0x0DD7, // 0DD7 ; UNKNOWN
6051 0x0DD8, // 0DD8..0DDF; SINHALA
6052 0x0DE0, // 0DE0..0DE5; UNKNOWN
6053 0x0DE6, // 0DE6..0DEF; SINHALA
6054 0x0DF0, // 0DF0..0DF1; UNKNOWN
6055 0x0DF2, // 0DF2..0DF4; SINHALA
6056 0x0DF5, // 0DF5..0E00; UNKNOWN
6057 0x0E01, // 0E01..0E3A; THAI
6058 0x0E3B, // 0E3B..0E3E; UNKNOWN
6059 0x0E3F, // 0E3F ; COMMON
6060 0x0E40, // 0E40..0E5B; THAI
6061 0x0E5C, // 0E5C..0E80; UNKNOWN
6062 0x0E81, // 0E81..0E82; LAO
6063 0x0E83, // 0E83 ; UNKNOWN
6064 0x0E84, // 0E84 ; LAO
6065 0x0E85, // 0E85 ; UNKNOWN
6066 0x0E86, // 0E86..0E8A; LAO
6067 0x0E8B, // 0E8B ; UNKNOWN
6068 0x0E8C, // 0E8C..0EA3; LAO
6069 0x0EA4, // 0EA4 ; UNKNOWN
6070 0x0EA5, // 0EA5 ; LAO
6071 0x0EA6, // 0EA6 ; UNKNOWN
6072 0x0EA7, // 0EA7..0EBD; LAO
6073 0x0EBE, // 0EBE..0EBF; UNKNOWN
6074 0x0EC0, // 0EC0..0EC4; LAO
6075 0x0EC5, // 0EC5 ; UNKNOWN
6076 0x0EC6, // 0EC6 ; LAO
6077 0x0EC7, // 0EC7 ; UNKNOWN
6078 0x0EC8, // 0EC8..0ECE; LAO
6079 0x0ECF, // 0ECF ; UNKNOWN
6080 0x0ED0, // 0ED0..0ED9; LAO
6081 0x0EDA, // 0EDA..0EDB; UNKNOWN
6082 0x0EDC, // 0EDC..0EDF; LAO
6083 0x0EE0, // 0EE0..0EFF; UNKNOWN
6084 0x0F00, // 0F00..0F47; TIBETAN
6085 0x0F48, // 0F48 ; UNKNOWN
6086 0x0F49, // 0F49..0F6C; TIBETAN
6087 0x0F6D, // 0F6D..0F70; UNKNOWN
6088 0x0F71, // 0F71..0F97; TIBETAN
6089 0x0F98, // 0F98 ; UNKNOWN
6090 0x0F99, // 0F99..0FBC; TIBETAN
6091 0x0FBD, // 0FBD ; UNKNOWN
6092 0x0FBE, // 0FBE..0FCC; TIBETAN
6093 0x0FCD, // 0FCD ; UNKNOWN
6094 0x0FCE, // 0FCE..0FD4; TIBETAN
6095 0x0FD5, // 0FD5..0FD8; COMMON
6096 0x0FD9, // 0FD9..0FDA; TIBETAN
6097 0x0FDB, // 0FDB..0FFF; UNKNOWN
6098 0x1000, // 1000..109F; MYANMAR
6099 0x10A0, // 10A0..10C5; GEORGIAN
6100 0x10C6, // 10C6 ; UNKNOWN
6101 0x10C7, // 10C7 ; GEORGIAN
6102 0x10C8, // 10C8..10CC; UNKNOWN
6103 0x10CD, // 10CD ; GEORGIAN
6104 0x10CE, // 10CE..10CF; UNKNOWN
6105 0x10D0, // 10D0..10FA; GEORGIAN
6106 0x10FB, // 10FB ; COMMON
6107 0x10FC, // 10FC..10FF; GEORGIAN
6108 0x1100, // 1100..11FF; HANGUL
6109 0x1200, // 1200..1248; ETHIOPIC
6110 0x1249, // 1249 ; UNKNOWN
6111 0x124A, // 124A..124D; ETHIOPIC
6112 0x124E, // 124E..124F; UNKNOWN
6113 0x1250, // 1250..1256; ETHIOPIC
6114 0x1257, // 1257 ; UNKNOWN
6115 0x1258, // 1258 ; ETHIOPIC
6116 0x1259, // 1259 ; UNKNOWN
6117 0x125A, // 125A..125D; ETHIOPIC
6118 0x125E, // 125E..125F; UNKNOWN
6119 0x1260, // 1260..1288; ETHIOPIC
6120 0x1289, // 1289 ; UNKNOWN
6121 0x128A, // 128A..128D; ETHIOPIC
6122 0x128E, // 128E..128F; UNKNOWN
6123 0x1290, // 1290..12B0; ETHIOPIC
6124 0x12B1, // 12B1 ; UNKNOWN
6125 0x12B2, // 12B2..12B5; ETHIOPIC
6126 0x12B6, // 12B6..12B7; UNKNOWN
6127 0x12B8, // 12B8..12BE; ETHIOPIC
6128 0x12BF, // 12BF ; UNKNOWN
6129 0x12C0, // 12C0 ; ETHIOPIC
6130 0x12C1, // 12C1 ; UNKNOWN
6131 0x12C2, // 12C2..12C5; ETHIOPIC
6132 0x12C6, // 12C6..12C7; UNKNOWN
6133 0x12C8, // 12C8..12D6; ETHIOPIC
6134 0x12D7, // 12D7 ; UNKNOWN
6135 0x12D8, // 12D8..1310; ETHIOPIC
6136 0x1311, // 1311 ; UNKNOWN
6137 0x1312, // 1312..1315; ETHIOPIC
6138 0x1316, // 1316..1317; UNKNOWN
6139 0x1318, // 1318..135A; ETHIOPIC
6140 0x135B, // 135B..135C; UNKNOWN
6141 0x135D, // 135D..137C; ETHIOPIC
6142 0x137D, // 137D..137F; UNKNOWN
6143 0x1380, // 1380..1399; ETHIOPIC
6144 0x139A, // 139A..139F; UNKNOWN
6145 0x13A0, // 13A0..13F5; CHEROKEE
6146 0x13F6, // 13F6..13F7; UNKNOWN
6147 0x13F8, // 13F8..13FD; CHEROKEE
6148 0x13FE, // 13FE..13FF; UNKNOWN
6149 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
6150 0x1680, // 1680..169C; OGHAM
6151 0x169D, // 169D..169F; UNKNOWN
6152 0x16A0, // 16A0..16EA; RUNIC
6153 0x16EB, // 16EB..16ED; COMMON
6154 0x16EE, // 16EE..16F8; RUNIC
6155 0x16F9, // 16F9..16FF; UNKNOWN
6156 0x1700, // 1700..1715; TAGALOG
6157 0x1716, // 1716..171E; UNKNOWN
6158 0x171F, // 171F ; TAGALOG
6159 0x1720, // 1720..1734; HANUNOO
6160 0x1735, // 1735..1736; COMMON
6161 0x1737, // 1737..173F; UNKNOWN
6162 0x1740, // 1740..1753; BUHID
6163 0x1754, // 1754..175F; UNKNOWN
6164 0x1760, // 1760..176C; TAGBANWA
6165 0x176D, // 176D ; UNKNOWN
6166 0x176E, // 176E..1770; TAGBANWA
6167 0x1771, // 1771 ; UNKNOWN
6168 0x1772, // 1772..1773; TAGBANWA
6169 0x1774, // 1774..177F; UNKNOWN
6170 0x1780, // 1780..17DD; KHMER
6171 0x17DE, // 17DE..17DF; UNKNOWN
6172 0x17E0, // 17E0..17E9; KHMER
6173 0x17EA, // 17EA..17EF; UNKNOWN
6174 0x17F0, // 17F0..17F9; KHMER
6175 0x17FA, // 17FA..17FF; UNKNOWN
6176 0x1800, // 1800..1801; MONGOLIAN
6177 0x1802, // 1802..1803; COMMON
6178 0x1804, // 1804 ; MONGOLIAN
6179 0x1805, // 1805 ; COMMON
6180 0x1806, // 1806..1819; MONGOLIAN
6181 0x181A, // 181A..181F; UNKNOWN
6182 0x1820, // 1820..1878; MONGOLIAN
6183 0x1879, // 1879..187F; UNKNOWN
6184 0x1880, // 1880..18AA; MONGOLIAN
6185 0x18AB, // 18AB..18AF; UNKNOWN
6186 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
6187 0x18F6, // 18F6..18FF; UNKNOWN
6188 0x1900, // 1900..191E; LIMBU
6189 0x191F, // 191F ; UNKNOWN
6190 0x1920, // 1920..192B; LIMBU
6191 0x192C, // 192C..192F; UNKNOWN
6192 0x1930, // 1930..193B; LIMBU
6193 0x193C, // 193C..193F; UNKNOWN
6194 0x1940, // 1940 ; LIMBU
6195 0x1941, // 1941..1943; UNKNOWN
6196 0x1944, // 1944..194F; LIMBU
6197 0x1950, // 1950..196D; TAI_LE
6198 0x196E, // 196E..196F; UNKNOWN
6199 0x1970, // 1970..1974; TAI_LE
6200 0x1975, // 1975..197F; UNKNOWN
6201 0x1980, // 1980..19AB; NEW_TAI_LUE
6202 0x19AC, // 19AC..19AF; UNKNOWN
6203 0x19B0, // 19B0..19C9; NEW_TAI_LUE
6204 0x19CA, // 19CA..19CF; UNKNOWN
6205 0x19D0, // 19D0..19DA; NEW_TAI_LUE
6206 0x19DB, // 19DB..19DD; UNKNOWN
6207 0x19DE, // 19DE..19DF; NEW_TAI_LUE
6208 0x19E0, // 19E0..19FF; KHMER
6209 0x1A00, // 1A00..1A1B; BUGINESE
6210 0x1A1C, // 1A1C..1A1D; UNKNOWN
6211 0x1A1E, // 1A1E..1A1F; BUGINESE
6212 0x1A20, // 1A20..1A5E; TAI_THAM
6213 0x1A5F, // 1A5F ; UNKNOWN
6214 0x1A60, // 1A60..1A7C; TAI_THAM
6215 0x1A7D, // 1A7D..1A7E; UNKNOWN
6216 0x1A7F, // 1A7F..1A89; TAI_THAM
6217 0x1A8A, // 1A8A..1A8F; UNKNOWN
6218 0x1A90, // 1A90..1A99; TAI_THAM
6219 0x1A9A, // 1A9A..1A9F; UNKNOWN
6220 0x1AA0, // 1AA0..1AAD; TAI_THAM
6221 0x1AAE, // 1AAE..1AAF; UNKNOWN
6222 0x1AB0, // 1AB0..1ADD; INHERITED
6223 0x1ADE, // 1ADE..1ADF; UNKNOWN
6224 0x1AE0, // 1AE0..1AEB; INHERITED
6225 0x1AEC, // 1AEC..1AFF; UNKNOWN
6226 0x1B00, // 1B00..1B4C; BALINESE
6227 0x1B4D, // 1B4D ; UNKNOWN
6228 0x1B4E, // 1B4E..1B7F; BALINESE
6229 0x1B80, // 1B80..1BBF; SUNDANESE
6230 0x1BC0, // 1BC0..1BF3; BATAK
6231 0x1BF4, // 1BF4..1BFB; UNKNOWN
6232 0x1BFC, // 1BFC..1BFF; BATAK
6233 0x1C00, // 1C00..1C37; LEPCHA
6234 0x1C38, // 1C38..1C3A; UNKNOWN
6235 0x1C3B, // 1C3B..1C49; LEPCHA
6236 0x1C4A, // 1C4A..1C4C; UNKNOWN
6237 0x1C4D, // 1C4D..1C4F; LEPCHA
6238 0x1C50, // 1C50..1C7F; OL_CHIKI
6239 0x1C80, // 1C80..1C8A; CYRILLIC
6240 0x1C8B, // 1C8B..1C8F; UNKNOWN
6241 0x1C90, // 1C90..1CBA; GEORGIAN
6242 0x1CBB, // 1CBB..1CBC; UNKNOWN
6243 0x1CBD, // 1CBD..1CBF; GEORGIAN
6244 0x1CC0, // 1CC0..1CC7; SUNDANESE
6245 0x1CC8, // 1CC8..1CCF; UNKNOWN
6246 0x1CD0, // 1CD0..1CD2; INHERITED
6247 0x1CD3, // 1CD3 ; COMMON
6248 0x1CD4, // 1CD4..1CE0; INHERITED
6249 0x1CE1, // 1CE1 ; COMMON
6250 0x1CE2, // 1CE2..1CE8; INHERITED
6251 0x1CE9, // 1CE9..1CEC; COMMON
6252 0x1CED, // 1CED ; INHERITED
6253 0x1CEE, // 1CEE..1CF3; COMMON
6254 0x1CF4, // 1CF4 ; INHERITED
6255 0x1CF5, // 1CF5..1CF7; COMMON
6256 0x1CF8, // 1CF8..1CF9; INHERITED
6257 0x1CFA, // 1CFA ; COMMON
6258 0x1CFB, // 1CFB..1CFF; UNKNOWN
6259 0x1D00, // 1D00..1D25; LATIN
6260 0x1D26, // 1D26..1D2A; GREEK
6261 0x1D2B, // 1D2B ; CYRILLIC
6262 0x1D2C, // 1D2C..1D5C; LATIN
6263 0x1D5D, // 1D5D..1D61; GREEK
6264 0x1D62, // 1D62..1D65; LATIN
6265 0x1D66, // 1D66..1D6A; GREEK
6266 0x1D6B, // 1D6B..1D77; LATIN
6267 0x1D78, // 1D78 ; CYRILLIC
6268 0x1D79, // 1D79..1DBE; LATIN
6269 0x1DBF, // 1DBF ; GREEK
6270 0x1DC0, // 1DC0..1DFF; INHERITED
6271 0x1E00, // 1E00..1EFF; LATIN
6272 0x1F00, // 1F00..1F15; GREEK
6273 0x1F16, // 1F16..1F17; UNKNOWN
6274 0x1F18, // 1F18..1F1D; GREEK
6275 0x1F1E, // 1F1E..1F1F; UNKNOWN
6276 0x1F20, // 1F20..1F45; GREEK
6277 0x1F46, // 1F46..1F47; UNKNOWN
6278 0x1F48, // 1F48..1F4D; GREEK
6279 0x1F4E, // 1F4E..1F4F; UNKNOWN
6280 0x1F50, // 1F50..1F57; GREEK
6281 0x1F58, // 1F58 ; UNKNOWN
6282 0x1F59, // 1F59 ; GREEK
6283 0x1F5A, // 1F5A ; UNKNOWN
6284 0x1F5B, // 1F5B ; GREEK
6285 0x1F5C, // 1F5C ; UNKNOWN
6286 0x1F5D, // 1F5D ; GREEK
6287 0x1F5E, // 1F5E ; UNKNOWN
6288 0x1F5F, // 1F5F..1F7D; GREEK
6289 0x1F7E, // 1F7E..1F7F; UNKNOWN
6290 0x1F80, // 1F80..1FB4; GREEK
6291 0x1FB5, // 1FB5 ; UNKNOWN
6292 0x1FB6, // 1FB6..1FC4; GREEK
6293 0x1FC5, // 1FC5 ; UNKNOWN
6294 0x1FC6, // 1FC6..1FD3; GREEK
6295 0x1FD4, // 1FD4..1FD5; UNKNOWN
6296 0x1FD6, // 1FD6..1FDB; GREEK
6297 0x1FDC, // 1FDC ; UNKNOWN
6298 0x1FDD, // 1FDD..1FEF; GREEK
6299 0x1FF0, // 1FF0..1FF1; UNKNOWN
6300 0x1FF2, // 1FF2..1FF4; GREEK
6301 0x1FF5, // 1FF5 ; UNKNOWN
6302 0x1FF6, // 1FF6..1FFE; GREEK
6303 0x1FFF, // 1FFF ; UNKNOWN
6304 0x2000, // 2000..200B; COMMON
6305 0x200C, // 200C..200D; INHERITED
6306 0x200E, // 200E..2064; COMMON
6307 0x2065, // 2065 ; UNKNOWN
6308 0x2066, // 2066..2070; COMMON
6309 0x2071, // 2071 ; LATIN
6310 0x2072, // 2072..2073; UNKNOWN
6311 0x2074, // 2074..207E; COMMON
6312 0x207F, // 207F ; LATIN
6313 0x2080, // 2080..208E; COMMON
6314 0x208F, // 208F ; UNKNOWN
6315 0x2090, // 2090..209C; LATIN
6316 0x209D, // 209D..209F; UNKNOWN
6317 0x20A0, // 20A0..20C1; COMMON
6318 0x20C2, // 20C2..20CF; UNKNOWN
6319 0x20D0, // 20D0..20F0; INHERITED
6320 0x20F1, // 20F1..20FF; UNKNOWN
6321 0x2100, // 2100..2125; COMMON
6322 0x2126, // 2126 ; GREEK
6323 0x2127, // 2127..2129; COMMON
6324 0x212A, // 212A..212B; LATIN
6325 0x212C, // 212C..2131; COMMON
6326 0x2132, // 2132 ; LATIN
6327 0x2133, // 2133..214D; COMMON
6328 0x214E, // 214E ; LATIN
6329 0x214F, // 214F..215F; COMMON
6330 0x2160, // 2160..2188; LATIN
6331 0x2189, // 2189..218B; COMMON
6332 0x218C, // 218C..218F; UNKNOWN
6333 0x2190, // 2190..2429; COMMON
6334 0x242A, // 242A..243F; UNKNOWN
6335 0x2440, // 2440..244A; COMMON
6336 0x244B, // 244B..245F; UNKNOWN
6337 0x2460, // 2460..27FF; COMMON
6338 0x2800, // 2800..28FF; BRAILLE
6339 0x2900, // 2900..2B73; COMMON
6340 0x2B74, // 2B74..2B75; UNKNOWN
6341 0x2B76, // 2B76..2BFF; COMMON
6342 0x2C00, // 2C00..2C5F; GLAGOLITIC
6343 0x2C60, // 2C60..2C7F; LATIN
6344 0x2C80, // 2C80..2CF3; COPTIC
6345 0x2CF4, // 2CF4..2CF8; UNKNOWN
6346 0x2CF9, // 2CF9..2CFF; COPTIC
6347 0x2D00, // 2D00..2D25; GEORGIAN
6348 0x2D26, // 2D26 ; UNKNOWN
6349 0x2D27, // 2D27 ; GEORGIAN
6350 0x2D28, // 2D28..2D2C; UNKNOWN
6351 0x2D2D, // 2D2D ; GEORGIAN
6352 0x2D2E, // 2D2E..2D2F; UNKNOWN
6353 0x2D30, // 2D30..2D67; TIFINAGH
6354 0x2D68, // 2D68..2D6E; UNKNOWN
6355 0x2D6F, // 2D6F..2D70; TIFINAGH
6356 0x2D71, // 2D71..2D7E; UNKNOWN
6357 0x2D7F, // 2D7F ; TIFINAGH
6358 0x2D80, // 2D80..2D96; ETHIOPIC
6359 0x2D97, // 2D97..2D9F; UNKNOWN
6360 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6361 0x2DA7, // 2DA7 ; UNKNOWN
6362 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6363 0x2DAF, // 2DAF ; UNKNOWN
6364 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6365 0x2DB7, // 2DB7 ; UNKNOWN
6366 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6367 0x2DBF, // 2DBF ; UNKNOWN
6368 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6369 0x2DC7, // 2DC7 ; UNKNOWN
6370 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6371 0x2DCF, // 2DCF ; UNKNOWN
6372 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6373 0x2DD7, // 2DD7 ; UNKNOWN
6374 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6375 0x2DDF, // 2DDF ; UNKNOWN
6376 0x2DE0, // 2DE0..2DFF; CYRILLIC
6377 0x2E00, // 2E00..2E5D; COMMON
6378 0x2E5E, // 2E5E..2E7F; UNKNOWN
6379 0x2E80, // 2E80..2E99; HAN
6380 0x2E9A, // 2E9A ; UNKNOWN
6381 0x2E9B, // 2E9B..2EF3; HAN
6382 0x2EF4, // 2EF4..2EFF; UNKNOWN
6383 0x2F00, // 2F00..2FD5; HAN
6384 0x2FD6, // 2FD6..2FEF; UNKNOWN
6385 0x2FF0, // 2FF0..3004; COMMON
6386 0x3005, // 3005 ; HAN
6387 0x3006, // 3006 ; COMMON
6388 0x3007, // 3007 ; HAN
6389 0x3008, // 3008..3020; COMMON
6390 0x3021, // 3021..3029; HAN
6391 0x302A, // 302A..302D; INHERITED
6392 0x302E, // 302E..302F; HANGUL
6393 0x3030, // 3030..3037; COMMON
6394 0x3038, // 3038..303B; HAN
6395 0x303C, // 303C..303F; COMMON
6396 0x3040, // 3040 ; UNKNOWN
6397 0x3041, // 3041..3096; HIRAGANA
6398 0x3097, // 3097..3098; UNKNOWN
6399 0x3099, // 3099..309A; INHERITED
6400 0x309B, // 309B..309C; COMMON
6401 0x309D, // 309D..309F; HIRAGANA
6402 0x30A0, // 30A0 ; COMMON
6403 0x30A1, // 30A1..30FA; KATAKANA
6404 0x30FB, // 30FB..30FC; COMMON
6405 0x30FD, // 30FD..30FF; KATAKANA
6406 0x3100, // 3100..3104; UNKNOWN
6407 0x3105, // 3105..312F; BOPOMOFO
6408 0x3130, // 3130 ; UNKNOWN
6409 0x3131, // 3131..318E; HANGUL
6410 0x318F, // 318F ; UNKNOWN
6411 0x3190, // 3190..319F; COMMON
6412 0x31A0, // 31A0..31BF; BOPOMOFO
6413 0x31C0, // 31C0..31E5; COMMON
6414 0x31E6, // 31E6..31EE; UNKNOWN
6415 0x31EF, // 31EF ; COMMON
6416 0x31F0, // 31F0..31FF; KATAKANA
6417 0x3200, // 3200..321E; HANGUL
6418 0x321F, // 321F ; UNKNOWN
6419 0x3220, // 3220..325F; COMMON
6420 0x3260, // 3260..327E; HANGUL
6421 0x327F, // 327F..32CF; COMMON
6422 0x32D0, // 32D0..32FE; KATAKANA
6423 0x32FF, // 32FF ; COMMON
6424 0x3300, // 3300..3357; KATAKANA
6425 0x3358, // 3358..33FF; COMMON
6426 0x3400, // 3400..4DBF; HAN
6427 0x4DC0, // 4DC0..4DFF; COMMON
6428 0x4E00, // 4E00..9FFF; HAN
6429 0xA000, // A000..A48C; YI
6430 0xA48D, // A48D..A48F; UNKNOWN
6431 0xA490, // A490..A4C6; YI
6432 0xA4C7, // A4C7..A4CF; UNKNOWN
6433 0xA4D0, // A4D0..A4FF; LISU
6434 0xA500, // A500..A62B; VAI
6435 0xA62C, // A62C..A63F; UNKNOWN
6436 0xA640, // A640..A69F; CYRILLIC
6437 0xA6A0, // A6A0..A6F7; BAMUM
6438 0xA6F8, // A6F8..A6FF; UNKNOWN
6439 0xA700, // A700..A721; COMMON
6440 0xA722, // A722..A787; LATIN
6441 0xA788, // A788..A78A; COMMON
6442 0xA78B, // A78B..A7DC; LATIN
6443 0xA7DD, // A7DD..A7F0; UNKNOWN
6444 0xA7F1, // A7F1..A7FF; LATIN
6445 0xA800, // A800..A82C; SYLOTI_NAGRI
6446 0xA82D, // A82D..A82F; UNKNOWN
6447 0xA830, // A830..A839; COMMON
6448 0xA83A, // A83A..A83F; UNKNOWN
6449 0xA840, // A840..A877; PHAGS_PA
6450 0xA878, // A878..A87F; UNKNOWN
6451 0xA880, // A880..A8C5; SAURASHTRA
6452 0xA8C6, // A8C6..A8CD; UNKNOWN
6453 0xA8CE, // A8CE..A8D9; SAURASHTRA
6454 0xA8DA, // A8DA..A8DF; UNKNOWN
6455 0xA8E0, // A8E0..A8FF; DEVANAGARI
6456 0xA900, // A900..A92D; KAYAH_LI
6457 0xA92E, // A92E ; COMMON
6458 0xA92F, // A92F ; KAYAH_LI
6459 0xA930, // A930..A953; REJANG
6460 0xA954, // A954..A95E; UNKNOWN
6461 0xA95F, // A95F ; REJANG
6462 0xA960, // A960..A97C; HANGUL
6463 0xA97D, // A97D..A97F; UNKNOWN
6464 0xA980, // A980..A9CD; JAVANESE
6465 0xA9CE, // A9CE ; UNKNOWN
6466 0xA9CF, // A9CF ; COMMON
6467 0xA9D0, // A9D0..A9D9; JAVANESE
6468 0xA9DA, // A9DA..A9DD; UNKNOWN
6469 0xA9DE, // A9DE..A9DF; JAVANESE
6470 0xA9E0, // A9E0..A9FE; MYANMAR
6471 0xA9FF, // A9FF ; UNKNOWN
6472 0xAA00, // AA00..AA36; CHAM
6473 0xAA37, // AA37..AA3F; UNKNOWN
6474 0xAA40, // AA40..AA4D; CHAM
6475 0xAA4E, // AA4E..AA4F; UNKNOWN
6476 0xAA50, // AA50..AA59; CHAM
6477 0xAA5A, // AA5A..AA5B; UNKNOWN
6478 0xAA5C, // AA5C..AA5F; CHAM
6479 0xAA60, // AA60..AA7F; MYANMAR
6480 0xAA80, // AA80..AAC2; TAI_VIET
6481 0xAAC3, // AAC3..AADA; UNKNOWN
6482 0xAADB, // AADB..AADF; TAI_VIET
6483 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6484 0xAAF7, // AAF7..AB00; UNKNOWN
6485 0xAB01, // AB01..AB06; ETHIOPIC
6486 0xAB07, // AB07..AB08; UNKNOWN
6487 0xAB09, // AB09..AB0E; ETHIOPIC
6488 0xAB0F, // AB0F..AB10; UNKNOWN
6489 0xAB11, // AB11..AB16; ETHIOPIC
6490 0xAB17, // AB17..AB1F; UNKNOWN
6491 0xAB20, // AB20..AB26; ETHIOPIC
6492 0xAB27, // AB27 ; UNKNOWN
6493 0xAB28, // AB28..AB2E; ETHIOPIC
6494 0xAB2F, // AB2F ; UNKNOWN
6495 0xAB30, // AB30..AB5A; LATIN
6496 0xAB5B, // AB5B ; COMMON
6497 0xAB5C, // AB5C..AB64; LATIN
6498 0xAB65, // AB65 ; GREEK
6499 0xAB66, // AB66..AB69; LATIN
6500 0xAB6A, // AB6A..AB6B; COMMON
6501 0xAB6C, // AB6C..AB6F; UNKNOWN
6502 0xAB70, // AB70..ABBF; CHEROKEE
6503 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6504 0xABEE, // ABEE..ABEF; UNKNOWN
6505 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6506 0xABFA, // ABFA..ABFF; UNKNOWN
6507 0xAC00, // AC00..D7A3; HANGUL
6508 0xD7A4, // D7A4..D7AF; UNKNOWN
6509 0xD7B0, // D7B0..D7C6; HANGUL
6510 0xD7C7, // D7C7..D7CA; UNKNOWN
6511 0xD7CB, // D7CB..D7FB; HANGUL
6512 0xD7FC, // D7FC..F8FF; UNKNOWN
6513 0xF900, // F900..FA6D; HAN
6514 0xFA6E, // FA6E..FA6F; UNKNOWN
6515 0xFA70, // FA70..FAD9; HAN
6516 0xFADA, // FADA..FAFF; UNKNOWN
6517 0xFB00, // FB00..FB06; LATIN
6518 0xFB07, // FB07..FB12; UNKNOWN
6519 0xFB13, // FB13..FB17; ARMENIAN
6520 0xFB18, // FB18..FB1C; UNKNOWN
6521 0xFB1D, // FB1D..FB36; HEBREW
6522 0xFB37, // FB37 ; UNKNOWN
6523 0xFB38, // FB38..FB3C; HEBREW
6524 0xFB3D, // FB3D ; UNKNOWN
6525 0xFB3E, // FB3E ; HEBREW
6526 0xFB3F, // FB3F ; UNKNOWN
6527 0xFB40, // FB40..FB41; HEBREW
6528 0xFB42, // FB42 ; UNKNOWN
6529 0xFB43, // FB43..FB44; HEBREW
6530 0xFB45, // FB45 ; UNKNOWN
6531 0xFB46, // FB46..FB4F; HEBREW
6532 0xFB50, // FB50..FD3D; ARABIC
6533 0xFD3E, // FD3E..FD3F; COMMON
6534 0xFD40, // FD40..FDCF; ARABIC
6535 0xFDD0, // FDD0..FDEF; UNKNOWN
6536 0xFDF0, // FDF0..FDFF; ARABIC
6537 0xFE00, // FE00..FE0F; INHERITED
6538 0xFE10, // FE10..FE19; COMMON
6539 0xFE1A, // FE1A..FE1F; UNKNOWN
6540 0xFE20, // FE20..FE2D; INHERITED
6541 0xFE2E, // FE2E..FE2F; CYRILLIC
6542 0xFE30, // FE30..FE52; COMMON
6543 0xFE53, // FE53 ; UNKNOWN
6544 0xFE54, // FE54..FE66; COMMON
6545 0xFE67, // FE67 ; UNKNOWN
6546 0xFE68, // FE68..FE6B; COMMON
6547 0xFE6C, // FE6C..FE6F; UNKNOWN
6548 0xFE70, // FE70..FE74; ARABIC
6549 0xFE75, // FE75 ; UNKNOWN
6550 0xFE76, // FE76..FEFC; ARABIC
6551 0xFEFD, // FEFD..FEFE; UNKNOWN
6552 0xFEFF, // FEFF ; COMMON
6553 0xFF00, // FF00 ; UNKNOWN
6554 0xFF01, // FF01..FF20; COMMON
6555 0xFF21, // FF21..FF3A; LATIN
6556 0xFF3B, // FF3B..FF40; COMMON
6557 0xFF41, // FF41..FF5A; LATIN
6558 0xFF5B, // FF5B..FF65; COMMON
6559 0xFF66, // FF66..FF6F; KATAKANA
6560 0xFF70, // FF70 ; COMMON
6561 0xFF71, // FF71..FF9D; KATAKANA
6562 0xFF9E, // FF9E..FF9F; COMMON
6563 0xFFA0, // FFA0..FFBE; HANGUL
6564 0xFFBF, // FFBF..FFC1; UNKNOWN
6565 0xFFC2, // FFC2..FFC7; HANGUL
6566 0xFFC8, // FFC8..FFC9; UNKNOWN
6567 0xFFCA, // FFCA..FFCF; HANGUL
6568 0xFFD0, // FFD0..FFD1; UNKNOWN
6569 0xFFD2, // FFD2..FFD7; HANGUL
6570 0xFFD8, // FFD8..FFD9; UNKNOWN
6571 0xFFDA, // FFDA..FFDC; HANGUL
6572 0xFFDD, // FFDD..FFDF; UNKNOWN
6573 0xFFE0, // FFE0..FFE6; COMMON
6574 0xFFE7, // FFE7 ; UNKNOWN
6575 0xFFE8, // FFE8..FFEE; COMMON
6576 0xFFEF, // FFEF..FFF8; UNKNOWN
6577 0xFFF9, // FFF9..FFFD; COMMON
6578 0xFFFE, // FFFE..FFFF; UNKNOWN
6579 0x10000, // 10000..1000B; LINEAR_B
6580 0x1000C, // 1000C ; UNKNOWN
6581 0x1000D, // 1000D..10026; LINEAR_B
6582 0x10027, // 10027 ; UNKNOWN
6583 0x10028, // 10028..1003A; LINEAR_B
6584 0x1003B, // 1003B ; UNKNOWN
6585 0x1003C, // 1003C..1003D; LINEAR_B
6586 0x1003E, // 1003E ; UNKNOWN
6587 0x1003F, // 1003F..1004D; LINEAR_B
6588 0x1004E, // 1004E..1004F; UNKNOWN
6589 0x10050, // 10050..1005D; LINEAR_B
6590 0x1005E, // 1005E..1007F; UNKNOWN
6591 0x10080, // 10080..100FA; LINEAR_B
6592 0x100FB, // 100FB..100FF; UNKNOWN
6593 0x10100, // 10100..10102; COMMON
6594 0x10103, // 10103..10106; UNKNOWN
6595 0x10107, // 10107..10133; COMMON
6596 0x10134, // 10134..10136; UNKNOWN
6597 0x10137, // 10137..1013F; COMMON
6598 0x10140, // 10140..1018E; GREEK
6599 0x1018F, // 1018F ; UNKNOWN
6600 0x10190, // 10190..1019C; COMMON
6601 0x1019D, // 1019D..1019F; UNKNOWN
6602 0x101A0, // 101A0 ; GREEK
6603 0x101A1, // 101A1..101CF; UNKNOWN
6604 0x101D0, // 101D0..101FC; COMMON
6605 0x101FD, // 101FD ; INHERITED
6606 0x101FE, // 101FE..1027F; UNKNOWN
6607 0x10280, // 10280..1029C; LYCIAN
6608 0x1029D, // 1029D..1029F; UNKNOWN
6609 0x102A0, // 102A0..102D0; CARIAN
6610 0x102D1, // 102D1..102DF; UNKNOWN
6611 0x102E0, // 102E0 ; INHERITED
6612 0x102E1, // 102E1..102FB; COMMON
6613 0x102FC, // 102FC..102FF; UNKNOWN
6614 0x10300, // 10300..10323; OLD_ITALIC
6615 0x10324, // 10324..1032C; UNKNOWN
6616 0x1032D, // 1032D..1032F; OLD_ITALIC
6617 0x10330, // 10330..1034A; GOTHIC
6618 0x1034B, // 1034B..1034F; UNKNOWN
6619 0x10350, // 10350..1037A; OLD_PERMIC
6620 0x1037B, // 1037B..1037F; UNKNOWN
6621 0x10380, // 10380..1039D; UGARITIC
6622 0x1039E, // 1039E ; UNKNOWN
6623 0x1039F, // 1039F ; UGARITIC
6624 0x103A0, // 103A0..103C3; OLD_PERSIAN
6625 0x103C4, // 103C4..103C7; UNKNOWN
6626 0x103C8, // 103C8..103D5; OLD_PERSIAN
6627 0x103D6, // 103D6..103FF; UNKNOWN
6628 0x10400, // 10400..1044F; DESERET
6629 0x10450, // 10450..1047F; SHAVIAN
6630 0x10480, // 10480..1049D; OSMANYA
6631 0x1049E, // 1049E..1049F; UNKNOWN
6632 0x104A0, // 104A0..104A9; OSMANYA
6633 0x104AA, // 104AA..104AF; UNKNOWN
6634 0x104B0, // 104B0..104D3; OSAGE
6635 0x104D4, // 104D4..104D7; UNKNOWN
6636 0x104D8, // 104D8..104FB; OSAGE
6637 0x104FC, // 104FC..104FF; UNKNOWN
6638 0x10500, // 10500..10527; ELBASAN
6639 0x10528, // 10528..1052F; UNKNOWN
6640 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6641 0x10564, // 10564..1056E; UNKNOWN
6642 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6643 0x10570, // 10570..1057A; VITHKUQI
6644 0x1057B, // 1057B ; UNKNOWN
6645 0x1057C, // 1057C..1058A; VITHKUQI
6646 0x1058B, // 1058B ; UNKNOWN
6647 0x1058C, // 1058C..10592; VITHKUQI
6648 0x10593, // 10593 ; UNKNOWN
6649 0x10594, // 10594..10595; VITHKUQI
6650 0x10596, // 10596 ; UNKNOWN
6651 0x10597, // 10597..105A1; VITHKUQI
6652 0x105A2, // 105A2 ; UNKNOWN
6653 0x105A3, // 105A3..105B1; VITHKUQI
6654 0x105B2, // 105B2 ; UNKNOWN
6655 0x105B3, // 105B3..105B9; VITHKUQI
6656 0x105BA, // 105BA ; UNKNOWN
6657 0x105BB, // 105BB..105BC; VITHKUQI
6658 0x105BD, // 105BD..105BF; UNKNOWN
6659 0x105C0, // 105C0..105F3; TODHRI
6660 0x105F4, // 105F4..105FF; UNKNOWN
6661 0x10600, // 10600..10736; LINEAR_A
6662 0x10737, // 10737..1073F; UNKNOWN
6663 0x10740, // 10740..10755; LINEAR_A
6664 0x10756, // 10756..1075F; UNKNOWN
6665 0x10760, // 10760..10767; LINEAR_A
6666 0x10768, // 10768..1077F; UNKNOWN
6667 0x10780, // 10780..10785; LATIN
6668 0x10786, // 10786 ; UNKNOWN
6669 0x10787, // 10787..107B0; LATIN
6670 0x107B1, // 107B1 ; UNKNOWN
6671 0x107B2, // 107B2..107BA; LATIN
6672 0x107BB, // 107BB..107FF; UNKNOWN
6673 0x10800, // 10800..10805; CYPRIOT
6674 0x10806, // 10806..10807; UNKNOWN
6675 0x10808, // 10808 ; CYPRIOT
6676 0x10809, // 10809 ; UNKNOWN
6677 0x1080A, // 1080A..10835; CYPRIOT
6678 0x10836, // 10836 ; UNKNOWN
6679 0x10837, // 10837..10838; CYPRIOT
6680 0x10839, // 10839..1083B; UNKNOWN
6681 0x1083C, // 1083C ; CYPRIOT
6682 0x1083D, // 1083D..1083E; UNKNOWN
6683 0x1083F, // 1083F ; CYPRIOT
6684 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6685 0x10856, // 10856 ; UNKNOWN
6686 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6687 0x10860, // 10860..1087F; PALMYRENE
6688 0x10880, // 10880..1089E; NABATAEAN
6689 0x1089F, // 1089F..108A6; UNKNOWN
6690 0x108A7, // 108A7..108AF; NABATAEAN
6691 0x108B0, // 108B0..108DF; UNKNOWN
6692 0x108E0, // 108E0..108F2; HATRAN
6693 0x108F3, // 108F3 ; UNKNOWN
6694 0x108F4, // 108F4..108F5; HATRAN
6695 0x108F6, // 108F6..108FA; UNKNOWN
6696 0x108FB, // 108FB..108FF; HATRAN
6697 0x10900, // 10900..1091B; PHOENICIAN
6698 0x1091C, // 1091C..1091E; UNKNOWN
6699 0x1091F, // 1091F ; PHOENICIAN
6700 0x10920, // 10920..10939; LYDIAN
6701 0x1093A, // 1093A..1093E; UNKNOWN
6702 0x1093F, // 1093F ; LYDIAN
6703 0x10940, // 10940..10959; SIDETIC
6704 0x1095A, // 1095A..1097F; UNKNOWN
6705 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6706 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6707 0x109B8, // 109B8..109BB; UNKNOWN
6708 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6709 0x109D0, // 109D0..109D1; UNKNOWN
6710 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6711 0x10A00, // 10A00..10A03; KHAROSHTHI
6712 0x10A04, // 10A04 ; UNKNOWN
6713 0x10A05, // 10A05..10A06; KHAROSHTHI
6714 0x10A07, // 10A07..10A0B; UNKNOWN
6715 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6716 0x10A14, // 10A14 ; UNKNOWN
6717 0x10A15, // 10A15..10A17; KHAROSHTHI
6718 0x10A18, // 10A18 ; UNKNOWN
6719 0x10A19, // 10A19..10A35; KHAROSHTHI
6720 0x10A36, // 10A36..10A37; UNKNOWN
6721 0x10A38, // 10A38..10A3A; KHAROSHTHI
6722 0x10A3B, // 10A3B..10A3E; UNKNOWN
6723 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6724 0x10A49, // 10A49..10A4F; UNKNOWN
6725 0x10A50, // 10A50..10A58; KHAROSHTHI
6726 0x10A59, // 10A59..10A5F; UNKNOWN
6727 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6728 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6729 0x10AA0, // 10AA0..10ABF; UNKNOWN
6730 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6731 0x10AE7, // 10AE7..10AEA; UNKNOWN
6732 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6733 0x10AF7, // 10AF7..10AFF; UNKNOWN
6734 0x10B00, // 10B00..10B35; AVESTAN
6735 0x10B36, // 10B36..10B38; UNKNOWN
6736 0x10B39, // 10B39..10B3F; AVESTAN
6737 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6738 0x10B56, // 10B56..10B57; UNKNOWN
6739 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6740 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6741 0x10B73, // 10B73..10B77; UNKNOWN
6742 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6743 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6744 0x10B92, // 10B92..10B98; UNKNOWN
6745 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6746 0x10B9D, // 10B9D..10BA8; UNKNOWN
6747 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6748 0x10BB0, // 10BB0..10BFF; UNKNOWN
6749 0x10C00, // 10C00..10C48; OLD_TURKIC
6750 0x10C49, // 10C49..10C7F; UNKNOWN
6751 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6752 0x10CB3, // 10CB3..10CBF; UNKNOWN
6753 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6754 0x10CF3, // 10CF3..10CF9; UNKNOWN
6755 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6756 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6757 0x10D28, // 10D28..10D2F; UNKNOWN
6758 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6759 0x10D3A, // 10D3A..10D3F; UNKNOWN
6760 0x10D40, // 10D40..10D65; GARAY
6761 0x10D66, // 10D66..10D68; UNKNOWN
6762 0x10D69, // 10D69..10D85; GARAY
6763 0x10D86, // 10D86..10D8D; UNKNOWN
6764 0x10D8E, // 10D8E..10D8F; GARAY
6765 0x10D90, // 10D90..10E5F; UNKNOWN
6766 0x10E60, // 10E60..10E7E; ARABIC
6767 0x10E7F, // 10E7F ; UNKNOWN
6768 0x10E80, // 10E80..10EA9; YEZIDI
6769 0x10EAA, // 10EAA ; UNKNOWN
6770 0x10EAB, // 10EAB..10EAD; YEZIDI
6771 0x10EAE, // 10EAE..10EAF; UNKNOWN
6772 0x10EB0, // 10EB0..10EB1; YEZIDI
6773 0x10EB2, // 10EB2..10EC1; UNKNOWN
6774 0x10EC2, // 10EC2..10EC7; ARABIC
6775 0x10EC8, // 10EC8..10ECF; UNKNOWN
6776 0x10ED0, // 10ED0..10ED8; ARABIC
6777 0x10ED9, // 10ED9..10EF9; UNKNOWN
6778 0x10EFA, // 10EFA..10EFF; ARABIC
6779 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6780 0x10F28, // 10F28..10F2F; UNKNOWN
6781 0x10F30, // 10F30..10F59; SOGDIAN
6782 0x10F5A, // 10F5A..10F6F; UNKNOWN
6783 0x10F70, // 10F70..10F89; OLD_UYGHUR
6784 0x10F8A, // 10F8A..10FAF; UNKNOWN
6785 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6786 0x10FCC, // 10FCC..10FDF; UNKNOWN
6787 0x10FE0, // 10FE0..10FF6; ELYMAIC
6788 0x10FF7, // 10FF7..10FFF; UNKNOWN
6789 0x11000, // 11000..1104D; BRAHMI
6790 0x1104E, // 1104E..11051; UNKNOWN
6791 0x11052, // 11052..11075; BRAHMI
6792 0x11076, // 11076..1107E; UNKNOWN
6793 0x1107F, // 1107F ; BRAHMI
6794 0x11080, // 11080..110C2; KAITHI
6795 0x110C3, // 110C3..110CC; UNKNOWN
6796 0x110CD, // 110CD ; KAITHI
6797 0x110CE, // 110CE..110CF; UNKNOWN
6798 0x110D0, // 110D0..110E8; SORA_SOMPENG
6799 0x110E9, // 110E9..110EF; UNKNOWN
6800 0x110F0, // 110F0..110F9; SORA_SOMPENG
6801 0x110FA, // 110FA..110FF; UNKNOWN
6802 0x11100, // 11100..11134; CHAKMA
6803 0x11135, // 11135 ; UNKNOWN
6804 0x11136, // 11136..11147; CHAKMA
6805 0x11148, // 11148..1114F; UNKNOWN
6806 0x11150, // 11150..11176; MAHAJANI
6807 0x11177, // 11177..1117F; UNKNOWN
6808 0x11180, // 11180..111DF; SHARADA
6809 0x111E0, // 111E0 ; UNKNOWN
6810 0x111E1, // 111E1..111F4; SINHALA
6811 0x111F5, // 111F5..111FF; UNKNOWN
6812 0x11200, // 11200..11211; KHOJKI
6813 0x11212, // 11212 ; UNKNOWN
6814 0x11213, // 11213..11241; KHOJKI
6815 0x11242, // 11242..1127F; UNKNOWN
6816 0x11280, // 11280..11286; MULTANI
6817 0x11287, // 11287 ; UNKNOWN
6818 0x11288, // 11288 ; MULTANI
6819 0x11289, // 11289 ; UNKNOWN
6820 0x1128A, // 1128A..1128D; MULTANI
6821 0x1128E, // 1128E ; UNKNOWN
6822 0x1128F, // 1128F..1129D; MULTANI
6823 0x1129E, // 1129E ; UNKNOWN
6824 0x1129F, // 1129F..112A9; MULTANI
6825 0x112AA, // 112AA..112AF; UNKNOWN
6826 0x112B0, // 112B0..112EA; KHUDAWADI
6827 0x112EB, // 112EB..112EF; UNKNOWN
6828 0x112F0, // 112F0..112F9; KHUDAWADI
6829 0x112FA, // 112FA..112FF; UNKNOWN
6830 0x11300, // 11300..11303; GRANTHA
6831 0x11304, // 11304 ; UNKNOWN
6832 0x11305, // 11305..1130C; GRANTHA
6833 0x1130D, // 1130D..1130E; UNKNOWN
6834 0x1130F, // 1130F..11310; GRANTHA
6835 0x11311, // 11311..11312; UNKNOWN
6836 0x11313, // 11313..11328; GRANTHA
6837 0x11329, // 11329 ; UNKNOWN
6838 0x1132A, // 1132A..11330; GRANTHA
6839 0x11331, // 11331 ; UNKNOWN
6840 0x11332, // 11332..11333; GRANTHA
6841 0x11334, // 11334 ; UNKNOWN
6842 0x11335, // 11335..11339; GRANTHA
6843 0x1133A, // 1133A ; UNKNOWN
6844 0x1133B, // 1133B ; INHERITED
6845 0x1133C, // 1133C..11344; GRANTHA
6846 0x11345, // 11345..11346; UNKNOWN
6847 0x11347, // 11347..11348; GRANTHA
6848 0x11349, // 11349..1134A; UNKNOWN
6849 0x1134B, // 1134B..1134D; GRANTHA
6850 0x1134E, // 1134E..1134F; UNKNOWN
6851 0x11350, // 11350 ; GRANTHA
6852 0x11351, // 11351..11356; UNKNOWN
6853 0x11357, // 11357 ; GRANTHA
6854 0x11358, // 11358..1135C; UNKNOWN
6855 0x1135D, // 1135D..11363; GRANTHA
6856 0x11364, // 11364..11365; UNKNOWN
6857 0x11366, // 11366..1136C; GRANTHA
6858 0x1136D, // 1136D..1136F; UNKNOWN
6859 0x11370, // 11370..11374; GRANTHA
6860 0x11375, // 11375..1137F; UNKNOWN
6861 0x11380, // 11380..11389; TULU_TIGALARI
6862 0x1138A, // 1138A ; UNKNOWN
6863 0x1138B, // 1138B ; TULU_TIGALARI
6864 0x1138C, // 1138C..1138D; UNKNOWN
6865 0x1138E, // 1138E ; TULU_TIGALARI
6866 0x1138F, // 1138F ; UNKNOWN
6867 0x11390, // 11390..113B5; TULU_TIGALARI
6868 0x113B6, // 113B6 ; UNKNOWN
6869 0x113B7, // 113B7..113C0; TULU_TIGALARI
6870 0x113C1, // 113C1 ; UNKNOWN
6871 0x113C2, // 113C2 ; TULU_TIGALARI
6872 0x113C3, // 113C3..113C4; UNKNOWN
6873 0x113C5, // 113C5 ; TULU_TIGALARI
6874 0x113C6, // 113C6 ; UNKNOWN
6875 0x113C7, // 113C7..113CA; TULU_TIGALARI
6876 0x113CB, // 113CB ; UNKNOWN
6877 0x113CC, // 113CC..113D5; TULU_TIGALARI
6878 0x113D6, // 113D6 ; UNKNOWN
6879 0x113D7, // 113D7..113D8; TULU_TIGALARI
6880 0x113D9, // 113D9..113E0; UNKNOWN
6881 0x113E1, // 113E1..113E2; TULU_TIGALARI
6882 0x113E3, // 113E3..113FF; UNKNOWN
6883 0x11400, // 11400..1145B; NEWA
6884 0x1145C, // 1145C ; UNKNOWN
6885 0x1145D, // 1145D..11461; NEWA
6886 0x11462, // 11462..1147F; UNKNOWN
6887 0x11480, // 11480..114C7; TIRHUTA
6888 0x114C8, // 114C8..114CF; UNKNOWN
6889 0x114D0, // 114D0..114D9; TIRHUTA
6890 0x114DA, // 114DA..1157F; UNKNOWN
6891 0x11580, // 11580..115B5; SIDDHAM
6892 0x115B6, // 115B6..115B7; UNKNOWN
6893 0x115B8, // 115B8..115DD; SIDDHAM
6894 0x115DE, // 115DE..115FF; UNKNOWN
6895 0x11600, // 11600..11644; MODI
6896 0x11645, // 11645..1164F; UNKNOWN
6897 0x11650, // 11650..11659; MODI
6898 0x1165A, // 1165A..1165F; UNKNOWN
6899 0x11660, // 11660..1166C; MONGOLIAN
6900 0x1166D, // 1166D..1167F; UNKNOWN
6901 0x11680, // 11680..116B9; TAKRI
6902 0x116BA, // 116BA..116BF; UNKNOWN
6903 0x116C0, // 116C0..116C9; TAKRI
6904 0x116CA, // 116CA..116CF; UNKNOWN
6905 0x116D0, // 116D0..116E3; MYANMAR
6906 0x116E4, // 116E4..116FF; UNKNOWN
6907 0x11700, // 11700..1171A; AHOM
6908 0x1171B, // 1171B..1171C; UNKNOWN
6909 0x1171D, // 1171D..1172B; AHOM
6910 0x1172C, // 1172C..1172F; UNKNOWN
6911 0x11730, // 11730..11746; AHOM
6912 0x11747, // 11747..117FF; UNKNOWN
6913 0x11800, // 11800..1183B; DOGRA
6914 0x1183C, // 1183C..1189F; UNKNOWN
6915 0x118A0, // 118A0..118F2; WARANG_CITI
6916 0x118F3, // 118F3..118FE; UNKNOWN
6917 0x118FF, // 118FF ; WARANG_CITI
6918 0x11900, // 11900..11906; DIVES_AKURU
6919 0x11907, // 11907..11908; UNKNOWN
6920 0x11909, // 11909 ; DIVES_AKURU
6921 0x1190A, // 1190A..1190B; UNKNOWN
6922 0x1190C, // 1190C..11913; DIVES_AKURU
6923 0x11914, // 11914 ; UNKNOWN
6924 0x11915, // 11915..11916; DIVES_AKURU
6925 0x11917, // 11917 ; UNKNOWN
6926 0x11918, // 11918..11935; DIVES_AKURU
6927 0x11936, // 11936 ; UNKNOWN
6928 0x11937, // 11937..11938; DIVES_AKURU
6929 0x11939, // 11939..1193A; UNKNOWN
6930 0x1193B, // 1193B..11946; DIVES_AKURU
6931 0x11947, // 11947..1194F; UNKNOWN
6932 0x11950, // 11950..11959; DIVES_AKURU
6933 0x1195A, // 1195A..1199F; UNKNOWN
6934 0x119A0, // 119A0..119A7; NANDINAGARI
6935 0x119A8, // 119A8..119A9; UNKNOWN
6936 0x119AA, // 119AA..119D7; NANDINAGARI
6937 0x119D8, // 119D8..119D9; UNKNOWN
6938 0x119DA, // 119DA..119E4; NANDINAGARI
6939 0x119E5, // 119E5..119FF; UNKNOWN
6940 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6941 0x11A48, // 11A48..11A4F; UNKNOWN
6942 0x11A50, // 11A50..11AA2; SOYOMBO
6943 0x11AA3, // 11AA3..11AAF; UNKNOWN
6944 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6945 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6946 0x11AF9, // 11AF9..11AFF; UNKNOWN
6947 0x11B00, // 11B00..11B09; DEVANAGARI
6948 0x11B0A, // 11B0A..11B5F; UNKNOWN
6949 0x11B60, // 11B60..11B67; SHARADA
6950 0x11B68, // 11B68..11BBF; UNKNOWN
6951 0x11BC0, // 11BC0..11BE1; SUNUWAR
6952 0x11BE2, // 11BE2..11BEF; UNKNOWN
6953 0x11BF0, // 11BF0..11BF9; SUNUWAR
6954 0x11BFA, // 11BFA..11BFF; UNKNOWN
6955 0x11C00, // 11C00..11C08; BHAIKSUKI
6956 0x11C09, // 11C09 ; UNKNOWN
6957 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6958 0x11C37, // 11C37 ; UNKNOWN
6959 0x11C38, // 11C38..11C45; BHAIKSUKI
6960 0x11C46, // 11C46..11C4F; UNKNOWN
6961 0x11C50, // 11C50..11C6C; BHAIKSUKI
6962 0x11C6D, // 11C6D..11C6F; UNKNOWN
6963 0x11C70, // 11C70..11C8F; MARCHEN
6964 0x11C90, // 11C90..11C91; UNKNOWN
6965 0x11C92, // 11C92..11CA7; MARCHEN
6966 0x11CA8, // 11CA8 ; UNKNOWN
6967 0x11CA9, // 11CA9..11CB6; MARCHEN
6968 0x11CB7, // 11CB7..11CFF; UNKNOWN
6969 0x11D00, // 11D00..11D06; MASARAM_GONDI
6970 0x11D07, // 11D07 ; UNKNOWN
6971 0x11D08, // 11D08..11D09; MASARAM_GONDI
6972 0x11D0A, // 11D0A ; UNKNOWN
6973 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6974 0x11D37, // 11D37..11D39; UNKNOWN
6975 0x11D3A, // 11D3A ; MASARAM_GONDI
6976 0x11D3B, // 11D3B ; UNKNOWN
6977 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6978 0x11D3E, // 11D3E ; UNKNOWN
6979 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6980 0x11D48, // 11D48..11D4F; UNKNOWN
6981 0x11D50, // 11D50..11D59; MASARAM_GONDI
6982 0x11D5A, // 11D5A..11D5F; UNKNOWN
6983 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6984 0x11D66, // 11D66 ; UNKNOWN
6985 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6986 0x11D69, // 11D69 ; UNKNOWN
6987 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6988 0x11D8F, // 11D8F ; UNKNOWN
6989 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6990 0x11D92, // 11D92 ; UNKNOWN
6991 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6992 0x11D99, // 11D99..11D9F; UNKNOWN
6993 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6994 0x11DAA, // 11DAA..11DAF; UNKNOWN
6995 0x11DB0, // 11DB0..11DDB; TOLONG_SIKI
6996 0x11DDC, // 11DDC..11DDF; UNKNOWN
6997 0x11DE0, // 11DE0..11DE9; TOLONG_SIKI
6998 0x11DEA, // 11DEA..11EDF; UNKNOWN
6999 0x11EE0, // 11EE0..11EF8; MAKASAR
7000 0x11EF9, // 11EF9..11EFF; UNKNOWN
7001 0x11F00, // 11F00..11F10; KAWI
7002 0x11F11, // 11F11 ; UNKNOWN
7003 0x11F12, // 11F12..11F3A; KAWI
7004 0x11F3B, // 11F3B..11F3D; UNKNOWN
7005 0x11F3E, // 11F3E..11F5A; KAWI
7006 0x11F5B, // 11F5B..11FAF; UNKNOWN
7007 0x11FB0, // 11FB0 ; LISU
7008 0x11FB1, // 11FB1..11FBF; UNKNOWN
7009 0x11FC0, // 11FC0..11FF1; TAMIL
7010 0x11FF2, // 11FF2..11FFE; UNKNOWN
7011 0x11FFF, // 11FFF ; TAMIL
7012 0x12000, // 12000..12399; CUNEIFORM
7013 0x1239A, // 1239A..123FF; UNKNOWN
7014 0x12400, // 12400..1246E; CUNEIFORM
7015 0x1246F, // 1246F ; UNKNOWN
7016 0x12470, // 12470..12474; CUNEIFORM
7017 0x12475, // 12475..1247F; UNKNOWN
7018 0x12480, // 12480..12543; CUNEIFORM
7019 0x12544, // 12544..12F8F; UNKNOWN
7020 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
7021 0x12FF3, // 12FF3..12FFF; UNKNOWN
7022 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
7023 0x13456, // 13456..1345F; UNKNOWN
7024 0x13460, // 13460..143FA; EGYPTIAN_HIEROGLYPHS
7025 0x143FB, // 143FB..143FF; UNKNOWN
7026 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
7027 0x14647, // 14647..160FF; UNKNOWN
7028 0x16100, // 16100..16139; GURUNG_KHEMA
7029 0x1613A, // 1613A..167FF; UNKNOWN
7030 0x16800, // 16800..16A38; BAMUM
7031 0x16A39, // 16A39..16A3F; UNKNOWN
7032 0x16A40, // 16A40..16A5E; MRO
7033 0x16A5F, // 16A5F ; UNKNOWN
7034 0x16A60, // 16A60..16A69; MRO
7035 0x16A6A, // 16A6A..16A6D; UNKNOWN
7036 0x16A6E, // 16A6E..16A6F; MRO
7037 0x16A70, // 16A70..16ABE; TANGSA
7038 0x16ABF, // 16ABF ; UNKNOWN
7039 0x16AC0, // 16AC0..16AC9; TANGSA
7040 0x16ACA, // 16ACA..16ACF; UNKNOWN
7041 0x16AD0, // 16AD0..16AED; BASSA_VAH
7042 0x16AEE, // 16AEE..16AEF; UNKNOWN
7043 0x16AF0, // 16AF0..16AF5; BASSA_VAH
7044 0x16AF6, // 16AF6..16AFF; UNKNOWN
7045 0x16B00, // 16B00..16B45; PAHAWH_HMONG
7046 0x16B46, // 16B46..16B4F; UNKNOWN
7047 0x16B50, // 16B50..16B59; PAHAWH_HMONG
7048 0x16B5A, // 16B5A ; UNKNOWN
7049 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
7050 0x16B62, // 16B62 ; UNKNOWN
7051 0x16B63, // 16B63..16B77; PAHAWH_HMONG
7052 0x16B78, // 16B78..16B7C; UNKNOWN
7053 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
7054 0x16B90, // 16B90..16D3F; UNKNOWN
7055 0x16D40, // 16D40..16D79; KIRAT_RAI
7056 0x16D7A, // 16D7A..16E3F; UNKNOWN
7057 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
7058 0x16E9B, // 16E9B..16E9F; UNKNOWN
7059 0x16EA0, // 16EA0..16EB8; BERIA_ERFE
7060 0x16EB9, // 16EB9..16EBA; UNKNOWN
7061 0x16EBB, // 16EBB..16ED3; BERIA_ERFE
7062 0x16ED4, // 16ED4..16EFF; UNKNOWN
7063 0x16F00, // 16F00..16F4A; MIAO
7064 0x16F4B, // 16F4B..16F4E; UNKNOWN
7065 0x16F4F, // 16F4F..16F87; MIAO
7066 0x16F88, // 16F88..16F8E; UNKNOWN
7067 0x16F8F, // 16F8F..16F9F; MIAO
7068 0x16FA0, // 16FA0..16FDF; UNKNOWN
7069 0x16FE0, // 16FE0 ; TANGUT
7070 0x16FE1, // 16FE1 ; NUSHU
7071 0x16FE2, // 16FE2..16FE3; HAN
7072 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
7073 0x16FE5, // 16FE5..16FEF; UNKNOWN
7074 0x16FF0, // 16FF0..16FF6; HAN
7075 0x16FF7, // 16FF7..16FFF; UNKNOWN
7076 0x17000, // 17000..18AFF; TANGUT
7077 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
7078 0x18CD6, // 18CD6..18CFE; UNKNOWN
7079 0x18CFF, // 18CFF ; KHITAN_SMALL_SCRIPT
7080 0x18D00, // 18D00..18D1E; TANGUT
7081 0x18D1F, // 18D1F..18D7F; UNKNOWN
7082 0x18D80, // 18D80..18DF2; TANGUT
7083 0x18DF3, // 18DF3..1AFEF; UNKNOWN
7084 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
7085 0x1AFF4, // 1AFF4 ; UNKNOWN
7086 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
7087 0x1AFFC, // 1AFFC ; UNKNOWN
7088 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
7089 0x1AFFF, // 1AFFF ; UNKNOWN
7090 0x1B000, // 1B000 ; KATAKANA
7091 0x1B001, // 1B001..1B11F; HIRAGANA
7092 0x1B120, // 1B120..1B122; KATAKANA
7093 0x1B123, // 1B123..1B131; UNKNOWN
7094 0x1B132, // 1B132 ; HIRAGANA
7095 0x1B133, // 1B133..1B14F; UNKNOWN
7096 0x1B150, // 1B150..1B152; HIRAGANA
7097 0x1B153, // 1B153..1B154; UNKNOWN
7098 0x1B155, // 1B155 ; KATAKANA
7099 0x1B156, // 1B156..1B163; UNKNOWN
7100 0x1B164, // 1B164..1B167; KATAKANA
7101 0x1B168, // 1B168..1B16F; UNKNOWN
7102 0x1B170, // 1B170..1B2FB; NUSHU
7103 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
7104 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
7105 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
7106 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
7107 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
7108 0x1BC80, // 1BC80..1BC88; DUPLOYAN
7109 0x1BC89, // 1BC89..1BC8F; UNKNOWN
7110 0x1BC90, // 1BC90..1BC99; DUPLOYAN
7111 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
7112 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
7113 0x1BCA0, // 1BCA0..1BCA3; COMMON
7114 0x1BCA4, // 1BCA4..1CBFF; UNKNOWN
7115 0x1CC00, // 1CC00..1CCFC; COMMON
7116 0x1CCFD, // 1CCFD..1CCFF; UNKNOWN
7117 0x1CD00, // 1CD00..1CEB3; COMMON
7118 0x1CEB4, // 1CEB4..1CEB9; UNKNOWN
7119 0x1CEBA, // 1CEBA..1CED0; COMMON
7120 0x1CED1, // 1CED1..1CEDF; UNKNOWN
7121 0x1CEE0, // 1CEE0..1CEF0; COMMON
7122 0x1CEF1, // 1CEF1..1CEFF; UNKNOWN
7123 0x1CF00, // 1CF00..1CF2D; INHERITED
7124 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
7125 0x1CF30, // 1CF30..1CF46; INHERITED
7126 0x1CF47, // 1CF47..1CF4F; UNKNOWN
7127 0x1CF50, // 1CF50..1CFC3; COMMON
7128 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
7129 0x1D000, // 1D000..1D0F5; COMMON
7130 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
7131 0x1D100, // 1D100..1D126; COMMON
7132 0x1D127, // 1D127..1D128; UNKNOWN
7133 0x1D129, // 1D129..1D166; COMMON
7134 0x1D167, // 1D167..1D169; INHERITED
7135 0x1D16A, // 1D16A..1D17A; COMMON
7136 0x1D17B, // 1D17B..1D182; INHERITED
7137 0x1D183, // 1D183..1D184; COMMON
7138 0x1D185, // 1D185..1D18B; INHERITED
7139 0x1D18C, // 1D18C..1D1A9; COMMON
7140 0x1D1AA, // 1D1AA..1D1AD; INHERITED
7141 0x1D1AE, // 1D1AE..1D1EA; COMMON
7142 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
7143 0x1D200, // 1D200..1D245; GREEK
7144 0x1D246, // 1D246..1D2BF; UNKNOWN
7145 0x1D2C0, // 1D2C0..1D2D3; COMMON
7146 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
7147 0x1D2E0, // 1D2E0..1D2F3; COMMON
7148 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
7149 0x1D300, // 1D300..1D356; COMMON
7150 0x1D357, // 1D357..1D35F; UNKNOWN
7151 0x1D360, // 1D360..1D378; COMMON
7152 0x1D379, // 1D379..1D3FF; UNKNOWN
7153 0x1D400, // 1D400..1D454; COMMON
7154 0x1D455, // 1D455 ; UNKNOWN
7155 0x1D456, // 1D456..1D49C; COMMON
7156 0x1D49D, // 1D49D ; UNKNOWN
7157 0x1D49E, // 1D49E..1D49F; COMMON
7158 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
7159 0x1D4A2, // 1D4A2 ; COMMON
7160 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
7161 0x1D4A5, // 1D4A5..1D4A6; COMMON
7162 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
7163 0x1D4A9, // 1D4A9..1D4AC; COMMON
7164 0x1D4AD, // 1D4AD ; UNKNOWN
7165 0x1D4AE, // 1D4AE..1D4B9; COMMON
7166 0x1D4BA, // 1D4BA ; UNKNOWN
7167 0x1D4BB, // 1D4BB ; COMMON
7168 0x1D4BC, // 1D4BC ; UNKNOWN
7169 0x1D4BD, // 1D4BD..1D4C3; COMMON
7170 0x1D4C4, // 1D4C4 ; UNKNOWN
7171 0x1D4C5, // 1D4C5..1D505; COMMON
7172 0x1D506, // 1D506 ; UNKNOWN
7173 0x1D507, // 1D507..1D50A; COMMON
7174 0x1D50B, // 1D50B..1D50C; UNKNOWN
7175 0x1D50D, // 1D50D..1D514; COMMON
7176 0x1D515, // 1D515 ; UNKNOWN
7177 0x1D516, // 1D516..1D51C; COMMON
7178 0x1D51D, // 1D51D ; UNKNOWN
7179 0x1D51E, // 1D51E..1D539; COMMON
7180 0x1D53A, // 1D53A ; UNKNOWN
7181 0x1D53B, // 1D53B..1D53E; COMMON
7182 0x1D53F, // 1D53F ; UNKNOWN
7183 0x1D540, // 1D540..1D544; COMMON
7184 0x1D545, // 1D545 ; UNKNOWN
7185 0x1D546, // 1D546 ; COMMON
7186 0x1D547, // 1D547..1D549; UNKNOWN
7187 0x1D54A, // 1D54A..1D550; COMMON
7188 0x1D551, // 1D551 ; UNKNOWN
7189 0x1D552, // 1D552..1D6A5; COMMON
7190 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
7191 0x1D6A8, // 1D6A8..1D7CB; COMMON
7192 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
7193 0x1D7CE, // 1D7CE..1D7FF; COMMON
7194 0x1D800, // 1D800..1DA8B; SIGNWRITING
7195 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
7196 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
7197 0x1DAA0, // 1DAA0 ; UNKNOWN
7198 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
7199 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
7200 0x1DF00, // 1DF00..1DF1E; LATIN
7201 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
7202 0x1DF25, // 1DF25..1DF2A; LATIN
7203 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
7204 0x1E000, // 1E000..1E006; GLAGOLITIC
7205 0x1E007, // 1E007 ; UNKNOWN
7206 0x1E008, // 1E008..1E018; GLAGOLITIC
7207 0x1E019, // 1E019..1E01A; UNKNOWN
7208 0x1E01B, // 1E01B..1E021; GLAGOLITIC
7209 0x1E022, // 1E022 ; UNKNOWN
7210 0x1E023, // 1E023..1E024; GLAGOLITIC
7211 0x1E025, // 1E025 ; UNKNOWN
7212 0x1E026, // 1E026..1E02A; GLAGOLITIC
7213 0x1E02B, // 1E02B..1E02F; UNKNOWN
7214 0x1E030, // 1E030..1E06D; CYRILLIC
7215 0x1E06E, // 1E06E..1E08E; UNKNOWN
7216 0x1E08F, // 1E08F ; CYRILLIC
7217 0x1E090, // 1E090..1E0FF; UNKNOWN
7218 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
7219 0x1E12D, // 1E12D..1E12F; UNKNOWN
7220 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
7221 0x1E13E, // 1E13E..1E13F; UNKNOWN
7222 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
7223 0x1E14A, // 1E14A..1E14D; UNKNOWN
7224 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
7225 0x1E150, // 1E150..1E28F; UNKNOWN
7226 0x1E290, // 1E290..1E2AE; TOTO
7227 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
7228 0x1E2C0, // 1E2C0..1E2F9; WANCHO
7229 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
7230 0x1E2FF, // 1E2FF ; WANCHO
7231 0x1E300, // 1E300..1E4CF; UNKNOWN
7232 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
7233 0x1E4FA, // 1E4FA..1E5CF; UNKNOWN
7234 0x1E5D0, // 1E5D0..1E5FA; OL_ONAL
7235 0x1E5FB, // 1E5FB..1E5FE; UNKNOWN
7236 0x1E5FF, // 1E5FF ; OL_ONAL
7237 0x1E600, // 1E600..1E6BF; UNKNOWN
7238 0x1E6C0, // 1E6C0..1E6DE; TAI_YO
7239 0x1E6DF, // 1E6DF ; UNKNOWN
7240 0x1E6E0, // 1E6E0..1E6F5; TAI_YO
7241 0x1E6F6, // 1E6F6..1E6FD; UNKNOWN
7242 0x1E6FE, // 1E6FE..1E6FF; TAI_YO
7243 0x1E700, // 1E700..1E7DF; UNKNOWN
7244 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
7245 0x1E7E7, // 1E7E7 ; UNKNOWN
7246 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
7247 0x1E7EC, // 1E7EC ; UNKNOWN
7248 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
7249 0x1E7EF, // 1E7EF ; UNKNOWN
7250 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
7251 0x1E7FF, // 1E7FF ; UNKNOWN
7252 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
7253 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
7254 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
7255 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
7256 0x1E900, // 1E900..1E94B; ADLAM
7257 0x1E94C, // 1E94C..1E94F; UNKNOWN
7258 0x1E950, // 1E950..1E959; ADLAM
7259 0x1E95A, // 1E95A..1E95D; UNKNOWN
7260 0x1E95E, // 1E95E..1E95F; ADLAM
7261 0x1E960, // 1E960..1EC70; UNKNOWN
7262 0x1EC71, // 1EC71..1ECB4; COMMON
7263 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
7264 0x1ED01, // 1ED01..1ED3D; COMMON
7265 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
7266 0x1EE00, // 1EE00..1EE03; ARABIC
7267 0x1EE04, // 1EE04 ; UNKNOWN
7268 0x1EE05, // 1EE05..1EE1F; ARABIC
7269 0x1EE20, // 1EE20 ; UNKNOWN
7270 0x1EE21, // 1EE21..1EE22; ARABIC
7271 0x1EE23, // 1EE23 ; UNKNOWN
7272 0x1EE24, // 1EE24 ; ARABIC
7273 0x1EE25, // 1EE25..1EE26; UNKNOWN
7274 0x1EE27, // 1EE27 ; ARABIC
7275 0x1EE28, // 1EE28 ; UNKNOWN
7276 0x1EE29, // 1EE29..1EE32; ARABIC
7277 0x1EE33, // 1EE33 ; UNKNOWN
7278 0x1EE34, // 1EE34..1EE37; ARABIC
7279 0x1EE38, // 1EE38 ; UNKNOWN
7280 0x1EE39, // 1EE39 ; ARABIC
7281 0x1EE3A, // 1EE3A ; UNKNOWN
7282 0x1EE3B, // 1EE3B ; ARABIC
7283 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
7284 0x1EE42, // 1EE42 ; ARABIC
7285 0x1EE43, // 1EE43..1EE46; UNKNOWN
7286 0x1EE47, // 1EE47 ; ARABIC
7287 0x1EE48, // 1EE48 ; UNKNOWN
7288 0x1EE49, // 1EE49 ; ARABIC
7289 0x1EE4A, // 1EE4A ; UNKNOWN
7290 0x1EE4B, // 1EE4B ; ARABIC
7291 0x1EE4C, // 1EE4C ; UNKNOWN
7292 0x1EE4D, // 1EE4D..1EE4F; ARABIC
7293 0x1EE50, // 1EE50 ; UNKNOWN
7294 0x1EE51, // 1EE51..1EE52; ARABIC
7295 0x1EE53, // 1EE53 ; UNKNOWN
7296 0x1EE54, // 1EE54 ; ARABIC
7297 0x1EE55, // 1EE55..1EE56; UNKNOWN
7298 0x1EE57, // 1EE57 ; ARABIC
7299 0x1EE58, // 1EE58 ; UNKNOWN
7300 0x1EE59, // 1EE59 ; ARABIC
7301 0x1EE5A, // 1EE5A ; UNKNOWN
7302 0x1EE5B, // 1EE5B ; ARABIC
7303 0x1EE5C, // 1EE5C ; UNKNOWN
7304 0x1EE5D, // 1EE5D ; ARABIC
7305 0x1EE5E, // 1EE5E ; UNKNOWN
7306 0x1EE5F, // 1EE5F ; ARABIC
7307 0x1EE60, // 1EE60 ; UNKNOWN
7308 0x1EE61, // 1EE61..1EE62; ARABIC
7309 0x1EE63, // 1EE63 ; UNKNOWN
7310 0x1EE64, // 1EE64 ; ARABIC
7311 0x1EE65, // 1EE65..1EE66; UNKNOWN
7312 0x1EE67, // 1EE67..1EE6A; ARABIC
7313 0x1EE6B, // 1EE6B ; UNKNOWN
7314 0x1EE6C, // 1EE6C..1EE72; ARABIC
7315 0x1EE73, // 1EE73 ; UNKNOWN
7316 0x1EE74, // 1EE74..1EE77; ARABIC
7317 0x1EE78, // 1EE78 ; UNKNOWN
7318 0x1EE79, // 1EE79..1EE7C; ARABIC
7319 0x1EE7D, // 1EE7D ; UNKNOWN
7320 0x1EE7E, // 1EE7E ; ARABIC
7321 0x1EE7F, // 1EE7F ; UNKNOWN
7322 0x1EE80, // 1EE80..1EE89; ARABIC
7323 0x1EE8A, // 1EE8A ; UNKNOWN
7324 0x1EE8B, // 1EE8B..1EE9B; ARABIC
7325 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
7326 0x1EEA1, // 1EEA1..1EEA3; ARABIC
7327 0x1EEA4, // 1EEA4 ; UNKNOWN
7328 0x1EEA5, // 1EEA5..1EEA9; ARABIC
7329 0x1EEAA, // 1EEAA ; UNKNOWN
7330 0x1EEAB, // 1EEAB..1EEBB; ARABIC
7331 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
7332 0x1EEF0, // 1EEF0..1EEF1; ARABIC
7333 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
7334 0x1F000, // 1F000..1F02B; COMMON
7335 0x1F02C, // 1F02C..1F02F; UNKNOWN
7336 0x1F030, // 1F030..1F093; COMMON
7337 0x1F094, // 1F094..1F09F; UNKNOWN
7338 0x1F0A0, // 1F0A0..1F0AE; COMMON
7339 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
7340 0x1F0B1, // 1F0B1..1F0BF; COMMON
7341 0x1F0C0, // 1F0C0 ; UNKNOWN
7342 0x1F0C1, // 1F0C1..1F0CF; COMMON
7343 0x1F0D0, // 1F0D0 ; UNKNOWN
7344 0x1F0D1, // 1F0D1..1F0F5; COMMON
7345 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
7346 0x1F100, // 1F100..1F1AD; COMMON
7347 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
7348 0x1F1E6, // 1F1E6..1F1FF; COMMON
7349 0x1F200, // 1F200 ; HIRAGANA
7350 0x1F201, // 1F201..1F202; COMMON
7351 0x1F203, // 1F203..1F20F; UNKNOWN
7352 0x1F210, // 1F210..1F23B; COMMON
7353 0x1F23C, // 1F23C..1F23F; UNKNOWN
7354 0x1F240, // 1F240..1F248; COMMON
7355 0x1F249, // 1F249..1F24F; UNKNOWN
7356 0x1F250, // 1F250..1F251; COMMON
7357 0x1F252, // 1F252..1F25F; UNKNOWN
7358 0x1F260, // 1F260..1F265; COMMON
7359 0x1F266, // 1F266..1F2FF; UNKNOWN
7360 0x1F300, // 1F300..1F6D8; COMMON
7361 0x1F6D9, // 1F6D9..1F6DB; UNKNOWN
7362 0x1F6DC, // 1F6DC..1F6EC; COMMON
7363 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
7364 0x1F6F0, // 1F6F0..1F6FC; COMMON
7365 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
7366 0x1F700, // 1F700..1F7D9; COMMON
7367 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
7368 0x1F7E0, // 1F7E0..1F7EB; COMMON
7369 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
7370 0x1F7F0, // 1F7F0 ; COMMON
7371 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7372 0x1F800, // 1F800..1F80B; COMMON
7373 0x1F80C, // 1F80C..1F80F; UNKNOWN
7374 0x1F810, // 1F810..1F847; COMMON
7375 0x1F848, // 1F848..1F84F; UNKNOWN
7376 0x1F850, // 1F850..1F859; COMMON
7377 0x1F85A, // 1F85A..1F85F; UNKNOWN
7378 0x1F860, // 1F860..1F887; COMMON
7379 0x1F888, // 1F888..1F88F; UNKNOWN
7380 0x1F890, // 1F890..1F8AD; COMMON
7381 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7382 0x1F8B0, // 1F8B0..1F8BB; COMMON
7383 0x1F8BC, // 1F8BC..1F8BF; UNKNOWN
7384 0x1F8C0, // 1F8C0..1F8C1; COMMON
7385 0x1F8C2, // 1F8C2..1F8CF; UNKNOWN
7386 0x1F8D0, // 1F8D0..1F8D8; COMMON
7387 0x1F8D9, // 1F8D9..1F8FF; UNKNOWN
7388 0x1F900, // 1F900..1FA57; COMMON
7389 0x1FA58, // 1FA58..1FA5F; UNKNOWN
7390 0x1FA60, // 1FA60..1FA6D; COMMON
7391 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7392 0x1FA70, // 1FA70..1FA7C; COMMON
7393 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7394 0x1FA80, // 1FA80..1FA8A; COMMON
7395 0x1FA8B, // 1FA8B..1FA8D; UNKNOWN
7396 0x1FA8E, // 1FA8E..1FAC6; COMMON
7397 0x1FAC7, // 1FAC7 ; UNKNOWN
7398 0x1FAC8, // 1FAC8 ; COMMON
7399 0x1FAC9, // 1FAC9..1FACC; UNKNOWN
7400 0x1FACD, // 1FACD..1FADC; COMMON
7401 0x1FADD, // 1FADD..1FADE; UNKNOWN
7402 0x1FADF, // 1FADF..1FAEA; COMMON
7403 0x1FAEB, // 1FAEB..1FAEE; UNKNOWN
7404 0x1FAEF, // 1FAEF..1FAF8; COMMON
7405 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7406 0x1FB00, // 1FB00..1FB92; COMMON
7407 0x1FB93, // 1FB93 ; UNKNOWN
7408 0x1FB94, // 1FB94..1FBFA; COMMON
7409 0x1FBFB, // 1FBFB..1FFFF; UNKNOWN
7410 0x20000, // 20000..2A6DF; HAN
7411 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7412 0x2A700, // 2A700..2B81D; HAN
7413 0x2B81E, // 2B81E..2B81F; UNKNOWN
7414 0x2B820, // 2B820..2CEAD; HAN
7415 0x2CEAE, // 2CEAE..2CEAF; UNKNOWN
7416 0x2CEB0, // 2CEB0..2EBE0; HAN
7417 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7418 0x2EBF0, // 2EBF0..2EE5D; HAN
7419 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7420 0x2F800, // 2F800..2FA1D; HAN
7421 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7422 0x30000, // 30000..3134A; HAN
7423 0x3134B, // 3134B..3134F; UNKNOWN
7424 0x31350, // 31350..33479; HAN
7425 0x3347A, // 3347A..E0000; UNKNOWN
7426 0xE0001, // E0001 ; COMMON
7427 0xE0002, // E0002..E001F; UNKNOWN
7428 0xE0020, // E0020..E007F; COMMON
7429 0xE0080, // E0080..E00FF; UNKNOWN
7430 0xE0100, // E0100..E01EF; INHERITED
7431 0xE01F0, // E01F0..10FFFF; UNKNOWN
7432 };
7433
7434 private static final UnicodeScript[] scripts = {
7435 COMMON, // 0000..0040
7436 LATIN, // 0041..005A
7437 COMMON, // 005B..0060
7438 LATIN, // 0061..007A
7439 COMMON, // 007B..00A9
7440 LATIN, // 00AA
7441 COMMON, // 00AB..00B9
7442 LATIN, // 00BA
7443 COMMON, // 00BB..00BF
7444 LATIN, // 00C0..00D6
7445 COMMON, // 00D7
7446 LATIN, // 00D8..00F6
7447 COMMON, // 00F7
7448 LATIN, // 00F8..02B8
7449 COMMON, // 02B9..02DF
7450 LATIN, // 02E0..02E4
7451 COMMON, // 02E5..02E9
7452 BOPOMOFO, // 02EA..02EB
7453 COMMON, // 02EC..02FF
7454 INHERITED, // 0300..036F
7455 GREEK, // 0370..0373
7456 COMMON, // 0374
7457 GREEK, // 0375..0377
7458 UNKNOWN, // 0378..0379
7459 GREEK, // 037A..037D
7460 COMMON, // 037E
7461 GREEK, // 037F
7462 UNKNOWN, // 0380..0383
7463 GREEK, // 0384
7464 COMMON, // 0385
7465 GREEK, // 0386
7466 COMMON, // 0387
7467 GREEK, // 0388..038A
7468 UNKNOWN, // 038B
7469 GREEK, // 038C
7470 UNKNOWN, // 038D
7471 GREEK, // 038E..03A1
7472 UNKNOWN, // 03A2
7473 GREEK, // 03A3..03E1
7474 COPTIC, // 03E2..03EF
7475 GREEK, // 03F0..03FF
7476 CYRILLIC, // 0400..0484
7477 INHERITED, // 0485..0486
7478 CYRILLIC, // 0487..052F
7479 UNKNOWN, // 0530
7480 ARMENIAN, // 0531..0556
7481 UNKNOWN, // 0557..0558
7482 ARMENIAN, // 0559..058A
7483 UNKNOWN, // 058B..058C
7484 ARMENIAN, // 058D..058F
7485 UNKNOWN, // 0590
7486 HEBREW, // 0591..05C7
7487 UNKNOWN, // 05C8..05CF
7488 HEBREW, // 05D0..05EA
7489 UNKNOWN, // 05EB..05EE
7490 HEBREW, // 05EF..05F4
7491 UNKNOWN, // 05F5..05FF
7492 ARABIC, // 0600..0604
7493 COMMON, // 0605
7494 ARABIC, // 0606..060B
7495 COMMON, // 060C
7496 ARABIC, // 060D..061A
7497 COMMON, // 061B
7498 ARABIC, // 061C..061E
7499 COMMON, // 061F
7500 ARABIC, // 0620..063F
7501 COMMON, // 0640
7502 ARABIC, // 0641..064A
7503 INHERITED, // 064B..0655
7504 ARABIC, // 0656..066F
7505 INHERITED, // 0670
7506 ARABIC, // 0671..06DC
7507 COMMON, // 06DD
7508 ARABIC, // 06DE..06FF
7509 SYRIAC, // 0700..070D
7510 UNKNOWN, // 070E
7511 SYRIAC, // 070F..074A
7512 UNKNOWN, // 074B..074C
7513 SYRIAC, // 074D..074F
7514 ARABIC, // 0750..077F
7515 THAANA, // 0780..07B1
7516 UNKNOWN, // 07B2..07BF
7517 NKO, // 07C0..07FA
7518 UNKNOWN, // 07FB..07FC
7519 NKO, // 07FD..07FF
7520 SAMARITAN, // 0800..082D
7521 UNKNOWN, // 082E..082F
7522 SAMARITAN, // 0830..083E
7523 UNKNOWN, // 083F
7524 MANDAIC, // 0840..085B
7525 UNKNOWN, // 085C..085D
7526 MANDAIC, // 085E
7527 UNKNOWN, // 085F
7528 SYRIAC, // 0860..086A
7529 UNKNOWN, // 086B..086F
7530 ARABIC, // 0870..0891
7531 UNKNOWN, // 0892..0896
7532 ARABIC, // 0897..08E1
7533 COMMON, // 08E2
7534 ARABIC, // 08E3..08FF
7535 DEVANAGARI, // 0900..0950
7536 INHERITED, // 0951..0954
7537 DEVANAGARI, // 0955..0963
7538 COMMON, // 0964..0965
7539 DEVANAGARI, // 0966..097F
7540 BENGALI, // 0980..0983
7541 UNKNOWN, // 0984
7542 BENGALI, // 0985..098C
7543 UNKNOWN, // 098D..098E
7544 BENGALI, // 098F..0990
7545 UNKNOWN, // 0991..0992
7546 BENGALI, // 0993..09A8
7547 UNKNOWN, // 09A9
7548 BENGALI, // 09AA..09B0
7549 UNKNOWN, // 09B1
7550 BENGALI, // 09B2
7551 UNKNOWN, // 09B3..09B5
7552 BENGALI, // 09B6..09B9
7553 UNKNOWN, // 09BA..09BB
7554 BENGALI, // 09BC..09C4
7555 UNKNOWN, // 09C5..09C6
7556 BENGALI, // 09C7..09C8
7557 UNKNOWN, // 09C9..09CA
7558 BENGALI, // 09CB..09CE
7559 UNKNOWN, // 09CF..09D6
7560 BENGALI, // 09D7
7561 UNKNOWN, // 09D8..09DB
7562 BENGALI, // 09DC..09DD
7563 UNKNOWN, // 09DE
7564 BENGALI, // 09DF..09E3
7565 UNKNOWN, // 09E4..09E5
7566 BENGALI, // 09E6..09FE
7567 UNKNOWN, // 09FF..0A00
7568 GURMUKHI, // 0A01..0A03
7569 UNKNOWN, // 0A04
7570 GURMUKHI, // 0A05..0A0A
7571 UNKNOWN, // 0A0B..0A0E
7572 GURMUKHI, // 0A0F..0A10
7573 UNKNOWN, // 0A11..0A12
7574 GURMUKHI, // 0A13..0A28
7575 UNKNOWN, // 0A29
7576 GURMUKHI, // 0A2A..0A30
7577 UNKNOWN, // 0A31
7578 GURMUKHI, // 0A32..0A33
7579 UNKNOWN, // 0A34
7580 GURMUKHI, // 0A35..0A36
7581 UNKNOWN, // 0A37
7582 GURMUKHI, // 0A38..0A39
7583 UNKNOWN, // 0A3A..0A3B
7584 GURMUKHI, // 0A3C
7585 UNKNOWN, // 0A3D
7586 GURMUKHI, // 0A3E..0A42
7587 UNKNOWN, // 0A43..0A46
7588 GURMUKHI, // 0A47..0A48
7589 UNKNOWN, // 0A49..0A4A
7590 GURMUKHI, // 0A4B..0A4D
7591 UNKNOWN, // 0A4E..0A50
7592 GURMUKHI, // 0A51
7593 UNKNOWN, // 0A52..0A58
7594 GURMUKHI, // 0A59..0A5C
7595 UNKNOWN, // 0A5D
7596 GURMUKHI, // 0A5E
7597 UNKNOWN, // 0A5F..0A65
7598 GURMUKHI, // 0A66..0A76
7599 UNKNOWN, // 0A77..0A80
7600 GUJARATI, // 0A81..0A83
7601 UNKNOWN, // 0A84
7602 GUJARATI, // 0A85..0A8D
7603 UNKNOWN, // 0A8E
7604 GUJARATI, // 0A8F..0A91
7605 UNKNOWN, // 0A92
7606 GUJARATI, // 0A93..0AA8
7607 UNKNOWN, // 0AA9
7608 GUJARATI, // 0AAA..0AB0
7609 UNKNOWN, // 0AB1
7610 GUJARATI, // 0AB2..0AB3
7611 UNKNOWN, // 0AB4
7612 GUJARATI, // 0AB5..0AB9
7613 UNKNOWN, // 0ABA..0ABB
7614 GUJARATI, // 0ABC..0AC5
7615 UNKNOWN, // 0AC6
7616 GUJARATI, // 0AC7..0AC9
7617 UNKNOWN, // 0ACA
7618 GUJARATI, // 0ACB..0ACD
7619 UNKNOWN, // 0ACE..0ACF
7620 GUJARATI, // 0AD0
7621 UNKNOWN, // 0AD1..0ADF
7622 GUJARATI, // 0AE0..0AE3
7623 UNKNOWN, // 0AE4..0AE5
7624 GUJARATI, // 0AE6..0AF1
7625 UNKNOWN, // 0AF2..0AF8
7626 GUJARATI, // 0AF9..0AFF
7627 UNKNOWN, // 0B00
7628 ORIYA, // 0B01..0B03
7629 UNKNOWN, // 0B04
7630 ORIYA, // 0B05..0B0C
7631 UNKNOWN, // 0B0D..0B0E
7632 ORIYA, // 0B0F..0B10
7633 UNKNOWN, // 0B11..0B12
7634 ORIYA, // 0B13..0B28
7635 UNKNOWN, // 0B29
7636 ORIYA, // 0B2A..0B30
7637 UNKNOWN, // 0B31
7638 ORIYA, // 0B32..0B33
7639 UNKNOWN, // 0B34
7640 ORIYA, // 0B35..0B39
7641 UNKNOWN, // 0B3A..0B3B
7642 ORIYA, // 0B3C..0B44
7643 UNKNOWN, // 0B45..0B46
7644 ORIYA, // 0B47..0B48
7645 UNKNOWN, // 0B49..0B4A
7646 ORIYA, // 0B4B..0B4D
7647 UNKNOWN, // 0B4E..0B54
7648 ORIYA, // 0B55..0B57
7649 UNKNOWN, // 0B58..0B5B
7650 ORIYA, // 0B5C..0B5D
7651 UNKNOWN, // 0B5E
7652 ORIYA, // 0B5F..0B63
7653 UNKNOWN, // 0B64..0B65
7654 ORIYA, // 0B66..0B77
7655 UNKNOWN, // 0B78..0B81
7656 TAMIL, // 0B82..0B83
7657 UNKNOWN, // 0B84
7658 TAMIL, // 0B85..0B8A
7659 UNKNOWN, // 0B8B..0B8D
7660 TAMIL, // 0B8E..0B90
7661 UNKNOWN, // 0B91
7662 TAMIL, // 0B92..0B95
7663 UNKNOWN, // 0B96..0B98
7664 TAMIL, // 0B99..0B9A
7665 UNKNOWN, // 0B9B
7666 TAMIL, // 0B9C
7667 UNKNOWN, // 0B9D
7668 TAMIL, // 0B9E..0B9F
7669 UNKNOWN, // 0BA0..0BA2
7670 TAMIL, // 0BA3..0BA4
7671 UNKNOWN, // 0BA5..0BA7
7672 TAMIL, // 0BA8..0BAA
7673 UNKNOWN, // 0BAB..0BAD
7674 TAMIL, // 0BAE..0BB9
7675 UNKNOWN, // 0BBA..0BBD
7676 TAMIL, // 0BBE..0BC2
7677 UNKNOWN, // 0BC3..0BC5
7678 TAMIL, // 0BC6..0BC8
7679 UNKNOWN, // 0BC9
7680 TAMIL, // 0BCA..0BCD
7681 UNKNOWN, // 0BCE..0BCF
7682 TAMIL, // 0BD0
7683 UNKNOWN, // 0BD1..0BD6
7684 TAMIL, // 0BD7
7685 UNKNOWN, // 0BD8..0BE5
7686 TAMIL, // 0BE6..0BFA
7687 UNKNOWN, // 0BFB..0BFF
7688 TELUGU, // 0C00..0C0C
7689 UNKNOWN, // 0C0D
7690 TELUGU, // 0C0E..0C10
7691 UNKNOWN, // 0C11
7692 TELUGU, // 0C12..0C28
7693 UNKNOWN, // 0C29
7694 TELUGU, // 0C2A..0C39
7695 UNKNOWN, // 0C3A..0C3B
7696 TELUGU, // 0C3C..0C44
7697 UNKNOWN, // 0C45
7698 TELUGU, // 0C46..0C48
7699 UNKNOWN, // 0C49
7700 TELUGU, // 0C4A..0C4D
7701 UNKNOWN, // 0C4E..0C54
7702 TELUGU, // 0C55..0C56
7703 UNKNOWN, // 0C57
7704 TELUGU, // 0C58..0C5A
7705 UNKNOWN, // 0C5B
7706 TELUGU, // 0C5C..0C5D
7707 UNKNOWN, // 0C5E..0C5F
7708 TELUGU, // 0C60..0C63
7709 UNKNOWN, // 0C64..0C65
7710 TELUGU, // 0C66..0C6F
7711 UNKNOWN, // 0C70..0C76
7712 TELUGU, // 0C77..0C7F
7713 KANNADA, // 0C80..0C8C
7714 UNKNOWN, // 0C8D
7715 KANNADA, // 0C8E..0C90
7716 UNKNOWN, // 0C91
7717 KANNADA, // 0C92..0CA8
7718 UNKNOWN, // 0CA9
7719 KANNADA, // 0CAA..0CB3
7720 UNKNOWN, // 0CB4
7721 KANNADA, // 0CB5..0CB9
7722 UNKNOWN, // 0CBA..0CBB
7723 KANNADA, // 0CBC..0CC4
7724 UNKNOWN, // 0CC5
7725 KANNADA, // 0CC6..0CC8
7726 UNKNOWN, // 0CC9
7727 KANNADA, // 0CCA..0CCD
7728 UNKNOWN, // 0CCE..0CD4
7729 KANNADA, // 0CD5..0CD6
7730 UNKNOWN, // 0CD7..0CDB
7731 KANNADA, // 0CDC..0CDE
7732 UNKNOWN, // 0CDF
7733 KANNADA, // 0CE0..0CE3
7734 UNKNOWN, // 0CE4..0CE5
7735 KANNADA, // 0CE6..0CEF
7736 UNKNOWN, // 0CF0
7737 KANNADA, // 0CF1..0CF3
7738 UNKNOWN, // 0CF4..0CFF
7739 MALAYALAM, // 0D00..0D0C
7740 UNKNOWN, // 0D0D
7741 MALAYALAM, // 0D0E..0D10
7742 UNKNOWN, // 0D11
7743 MALAYALAM, // 0D12..0D44
7744 UNKNOWN, // 0D45
7745 MALAYALAM, // 0D46..0D48
7746 UNKNOWN, // 0D49
7747 MALAYALAM, // 0D4A..0D4F
7748 UNKNOWN, // 0D50..0D53
7749 MALAYALAM, // 0D54..0D63
7750 UNKNOWN, // 0D64..0D65
7751 MALAYALAM, // 0D66..0D7F
7752 UNKNOWN, // 0D80
7753 SINHALA, // 0D81..0D83
7754 UNKNOWN, // 0D84
7755 SINHALA, // 0D85..0D96
7756 UNKNOWN, // 0D97..0D99
7757 SINHALA, // 0D9A..0DB1
7758 UNKNOWN, // 0DB2
7759 SINHALA, // 0DB3..0DBB
7760 UNKNOWN, // 0DBC
7761 SINHALA, // 0DBD
7762 UNKNOWN, // 0DBE..0DBF
7763 SINHALA, // 0DC0..0DC6
7764 UNKNOWN, // 0DC7..0DC9
7765 SINHALA, // 0DCA
7766 UNKNOWN, // 0DCB..0DCE
7767 SINHALA, // 0DCF..0DD4
7768 UNKNOWN, // 0DD5
7769 SINHALA, // 0DD6
7770 UNKNOWN, // 0DD7
7771 SINHALA, // 0DD8..0DDF
7772 UNKNOWN, // 0DE0..0DE5
7773 SINHALA, // 0DE6..0DEF
7774 UNKNOWN, // 0DF0..0DF1
7775 SINHALA, // 0DF2..0DF4
7776 UNKNOWN, // 0DF5..0E00
7777 THAI, // 0E01..0E3A
7778 UNKNOWN, // 0E3B..0E3E
7779 COMMON, // 0E3F
7780 THAI, // 0E40..0E5B
7781 UNKNOWN, // 0E5C..0E80
7782 LAO, // 0E81..0E82
7783 UNKNOWN, // 0E83
7784 LAO, // 0E84
7785 UNKNOWN, // 0E85
7786 LAO, // 0E86..0E8A
7787 UNKNOWN, // 0E8B
7788 LAO, // 0E8C..0EA3
7789 UNKNOWN, // 0EA4
7790 LAO, // 0EA5
7791 UNKNOWN, // 0EA6
7792 LAO, // 0EA7..0EBD
7793 UNKNOWN, // 0EBE..0EBF
7794 LAO, // 0EC0..0EC4
7795 UNKNOWN, // 0EC5
7796 LAO, // 0EC6
7797 UNKNOWN, // 0EC7
7798 LAO, // 0EC8..0ECE
7799 UNKNOWN, // 0ECF
7800 LAO, // 0ED0..0ED9
7801 UNKNOWN, // 0EDA..0EDB
7802 LAO, // 0EDC..0EDF
7803 UNKNOWN, // 0EE0..0EFF
7804 TIBETAN, // 0F00..0F47
7805 UNKNOWN, // 0F48
7806 TIBETAN, // 0F49..0F6C
7807 UNKNOWN, // 0F6D..0F70
7808 TIBETAN, // 0F71..0F97
7809 UNKNOWN, // 0F98
7810 TIBETAN, // 0F99..0FBC
7811 UNKNOWN, // 0FBD
7812 TIBETAN, // 0FBE..0FCC
7813 UNKNOWN, // 0FCD
7814 TIBETAN, // 0FCE..0FD4
7815 COMMON, // 0FD5..0FD8
7816 TIBETAN, // 0FD9..0FDA
7817 UNKNOWN, // 0FDB..0FFF
7818 MYANMAR, // 1000..109F
7819 GEORGIAN, // 10A0..10C5
7820 UNKNOWN, // 10C6
7821 GEORGIAN, // 10C7
7822 UNKNOWN, // 10C8..10CC
7823 GEORGIAN, // 10CD
7824 UNKNOWN, // 10CE..10CF
7825 GEORGIAN, // 10D0..10FA
7826 COMMON, // 10FB
7827 GEORGIAN, // 10FC..10FF
7828 HANGUL, // 1100..11FF
7829 ETHIOPIC, // 1200..1248
7830 UNKNOWN, // 1249
7831 ETHIOPIC, // 124A..124D
7832 UNKNOWN, // 124E..124F
7833 ETHIOPIC, // 1250..1256
7834 UNKNOWN, // 1257
7835 ETHIOPIC, // 1258
7836 UNKNOWN, // 1259
7837 ETHIOPIC, // 125A..125D
7838 UNKNOWN, // 125E..125F
7839 ETHIOPIC, // 1260..1288
7840 UNKNOWN, // 1289
7841 ETHIOPIC, // 128A..128D
7842 UNKNOWN, // 128E..128F
7843 ETHIOPIC, // 1290..12B0
7844 UNKNOWN, // 12B1
7845 ETHIOPIC, // 12B2..12B5
7846 UNKNOWN, // 12B6..12B7
7847 ETHIOPIC, // 12B8..12BE
7848 UNKNOWN, // 12BF
7849 ETHIOPIC, // 12C0
7850 UNKNOWN, // 12C1
7851 ETHIOPIC, // 12C2..12C5
7852 UNKNOWN, // 12C6..12C7
7853 ETHIOPIC, // 12C8..12D6
7854 UNKNOWN, // 12D7
7855 ETHIOPIC, // 12D8..1310
7856 UNKNOWN, // 1311
7857 ETHIOPIC, // 1312..1315
7858 UNKNOWN, // 1316..1317
7859 ETHIOPIC, // 1318..135A
7860 UNKNOWN, // 135B..135C
7861 ETHIOPIC, // 135D..137C
7862 UNKNOWN, // 137D..137F
7863 ETHIOPIC, // 1380..1399
7864 UNKNOWN, // 139A..139F
7865 CHEROKEE, // 13A0..13F5
7866 UNKNOWN, // 13F6..13F7
7867 CHEROKEE, // 13F8..13FD
7868 UNKNOWN, // 13FE..13FF
7869 CANADIAN_ABORIGINAL, // 1400..167F
7870 OGHAM, // 1680..169C
7871 UNKNOWN, // 169D..169F
7872 RUNIC, // 16A0..16EA
7873 COMMON, // 16EB..16ED
7874 RUNIC, // 16EE..16F8
7875 UNKNOWN, // 16F9..16FF
7876 TAGALOG, // 1700..1715
7877 UNKNOWN, // 1716..171E
7878 TAGALOG, // 171F
7879 HANUNOO, // 1720..1734
7880 COMMON, // 1735..1736
7881 UNKNOWN, // 1737..173F
7882 BUHID, // 1740..1753
7883 UNKNOWN, // 1754..175F
7884 TAGBANWA, // 1760..176C
7885 UNKNOWN, // 176D
7886 TAGBANWA, // 176E..1770
7887 UNKNOWN, // 1771
7888 TAGBANWA, // 1772..1773
7889 UNKNOWN, // 1774..177F
7890 KHMER, // 1780..17DD
7891 UNKNOWN, // 17DE..17DF
7892 KHMER, // 17E0..17E9
7893 UNKNOWN, // 17EA..17EF
7894 KHMER, // 17F0..17F9
7895 UNKNOWN, // 17FA..17FF
7896 MONGOLIAN, // 1800..1801
7897 COMMON, // 1802..1803
7898 MONGOLIAN, // 1804
7899 COMMON, // 1805
7900 MONGOLIAN, // 1806..1819
7901 UNKNOWN, // 181A..181F
7902 MONGOLIAN, // 1820..1878
7903 UNKNOWN, // 1879..187F
7904 MONGOLIAN, // 1880..18AA
7905 UNKNOWN, // 18AB..18AF
7906 CANADIAN_ABORIGINAL, // 18B0..18F5
7907 UNKNOWN, // 18F6..18FF
7908 LIMBU, // 1900..191E
7909 UNKNOWN, // 191F
7910 LIMBU, // 1920..192B
7911 UNKNOWN, // 192C..192F
7912 LIMBU, // 1930..193B
7913 UNKNOWN, // 193C..193F
7914 LIMBU, // 1940
7915 UNKNOWN, // 1941..1943
7916 LIMBU, // 1944..194F
7917 TAI_LE, // 1950..196D
7918 UNKNOWN, // 196E..196F
7919 TAI_LE, // 1970..1974
7920 UNKNOWN, // 1975..197F
7921 NEW_TAI_LUE, // 1980..19AB
7922 UNKNOWN, // 19AC..19AF
7923 NEW_TAI_LUE, // 19B0..19C9
7924 UNKNOWN, // 19CA..19CF
7925 NEW_TAI_LUE, // 19D0..19DA
7926 UNKNOWN, // 19DB..19DD
7927 NEW_TAI_LUE, // 19DE..19DF
7928 KHMER, // 19E0..19FF
7929 BUGINESE, // 1A00..1A1B
7930 UNKNOWN, // 1A1C..1A1D
7931 BUGINESE, // 1A1E..1A1F
7932 TAI_THAM, // 1A20..1A5E
7933 UNKNOWN, // 1A5F
7934 TAI_THAM, // 1A60..1A7C
7935 UNKNOWN, // 1A7D..1A7E
7936 TAI_THAM, // 1A7F..1A89
7937 UNKNOWN, // 1A8A..1A8F
7938 TAI_THAM, // 1A90..1A99
7939 UNKNOWN, // 1A9A..1A9F
7940 TAI_THAM, // 1AA0..1AAD
7941 UNKNOWN, // 1AAE..1AAF
7942 INHERITED, // 1AB0..1ADD
7943 UNKNOWN, // 1ADE..1ADF
7944 INHERITED, // 1AE0..1AEB
7945 UNKNOWN, // 1AEC..1AFF
7946 BALINESE, // 1B00..1B4C
7947 UNKNOWN, // 1B4D
7948 BALINESE, // 1B4E..1B7F
7949 SUNDANESE, // 1B80..1BBF
7950 BATAK, // 1BC0..1BF3
7951 UNKNOWN, // 1BF4..1BFB
7952 BATAK, // 1BFC..1BFF
7953 LEPCHA, // 1C00..1C37
7954 UNKNOWN, // 1C38..1C3A
7955 LEPCHA, // 1C3B..1C49
7956 UNKNOWN, // 1C4A..1C4C
7957 LEPCHA, // 1C4D..1C4F
7958 OL_CHIKI, // 1C50..1C7F
7959 CYRILLIC, // 1C80..1C8A
7960 UNKNOWN, // 1C8B..1C8F
7961 GEORGIAN, // 1C90..1CBA
7962 UNKNOWN, // 1CBB..1CBC
7963 GEORGIAN, // 1CBD..1CBF
7964 SUNDANESE, // 1CC0..1CC7
7965 UNKNOWN, // 1CC8..1CCF
7966 INHERITED, // 1CD0..1CD2
7967 COMMON, // 1CD3
7968 INHERITED, // 1CD4..1CE0
7969 COMMON, // 1CE1
7970 INHERITED, // 1CE2..1CE8
7971 COMMON, // 1CE9..1CEC
7972 INHERITED, // 1CED
7973 COMMON, // 1CEE..1CF3
7974 INHERITED, // 1CF4
7975 COMMON, // 1CF5..1CF7
7976 INHERITED, // 1CF8..1CF9
7977 COMMON, // 1CFA
7978 UNKNOWN, // 1CFB..1CFF
7979 LATIN, // 1D00..1D25
7980 GREEK, // 1D26..1D2A
7981 CYRILLIC, // 1D2B
7982 LATIN, // 1D2C..1D5C
7983 GREEK, // 1D5D..1D61
7984 LATIN, // 1D62..1D65
7985 GREEK, // 1D66..1D6A
7986 LATIN, // 1D6B..1D77
7987 CYRILLIC, // 1D78
7988 LATIN, // 1D79..1DBE
7989 GREEK, // 1DBF
7990 INHERITED, // 1DC0..1DFF
7991 LATIN, // 1E00..1EFF
7992 GREEK, // 1F00..1F15
7993 UNKNOWN, // 1F16..1F17
7994 GREEK, // 1F18..1F1D
7995 UNKNOWN, // 1F1E..1F1F
7996 GREEK, // 1F20..1F45
7997 UNKNOWN, // 1F46..1F47
7998 GREEK, // 1F48..1F4D
7999 UNKNOWN, // 1F4E..1F4F
8000 GREEK, // 1F50..1F57
8001 UNKNOWN, // 1F58
8002 GREEK, // 1F59
8003 UNKNOWN, // 1F5A
8004 GREEK, // 1F5B
8005 UNKNOWN, // 1F5C
8006 GREEK, // 1F5D
8007 UNKNOWN, // 1F5E
8008 GREEK, // 1F5F..1F7D
8009 UNKNOWN, // 1F7E..1F7F
8010 GREEK, // 1F80..1FB4
8011 UNKNOWN, // 1FB5
8012 GREEK, // 1FB6..1FC4
8013 UNKNOWN, // 1FC5
8014 GREEK, // 1FC6..1FD3
8015 UNKNOWN, // 1FD4..1FD5
8016 GREEK, // 1FD6..1FDB
8017 UNKNOWN, // 1FDC
8018 GREEK, // 1FDD..1FEF
8019 UNKNOWN, // 1FF0..1FF1
8020 GREEK, // 1FF2..1FF4
8021 UNKNOWN, // 1FF5
8022 GREEK, // 1FF6..1FFE
8023 UNKNOWN, // 1FFF
8024 COMMON, // 2000..200B
8025 INHERITED, // 200C..200D
8026 COMMON, // 200E..2064
8027 UNKNOWN, // 2065
8028 COMMON, // 2066..2070
8029 LATIN, // 2071
8030 UNKNOWN, // 2072..2073
8031 COMMON, // 2074..207E
8032 LATIN, // 207F
8033 COMMON, // 2080..208E
8034 UNKNOWN, // 208F
8035 LATIN, // 2090..209C
8036 UNKNOWN, // 209D..209F
8037 COMMON, // 20A0..20C1
8038 UNKNOWN, // 20C2..20CF
8039 INHERITED, // 20D0..20F0
8040 UNKNOWN, // 20F1..20FF
8041 COMMON, // 2100..2125
8042 GREEK, // 2126
8043 COMMON, // 2127..2129
8044 LATIN, // 212A..212B
8045 COMMON, // 212C..2131
8046 LATIN, // 2132
8047 COMMON, // 2133..214D
8048 LATIN, // 214E
8049 COMMON, // 214F..215F
8050 LATIN, // 2160..2188
8051 COMMON, // 2189..218B
8052 UNKNOWN, // 218C..218F
8053 COMMON, // 2190..2429
8054 UNKNOWN, // 242A..243F
8055 COMMON, // 2440..244A
8056 UNKNOWN, // 244B..245F
8057 COMMON, // 2460..27FF
8058 BRAILLE, // 2800..28FF
8059 COMMON, // 2900..2B73
8060 UNKNOWN, // 2B74..2B75
8061 COMMON, // 2B76..2BFF
8062 GLAGOLITIC, // 2C00..2C5F
8063 LATIN, // 2C60..2C7F
8064 COPTIC, // 2C80..2CF3
8065 UNKNOWN, // 2CF4..2CF8
8066 COPTIC, // 2CF9..2CFF
8067 GEORGIAN, // 2D00..2D25
8068 UNKNOWN, // 2D26
8069 GEORGIAN, // 2D27
8070 UNKNOWN, // 2D28..2D2C
8071 GEORGIAN, // 2D2D
8072 UNKNOWN, // 2D2E..2D2F
8073 TIFINAGH, // 2D30..2D67
8074 UNKNOWN, // 2D68..2D6E
8075 TIFINAGH, // 2D6F..2D70
8076 UNKNOWN, // 2D71..2D7E
8077 TIFINAGH, // 2D7F
8078 ETHIOPIC, // 2D80..2D96
8079 UNKNOWN, // 2D97..2D9F
8080 ETHIOPIC, // 2DA0..2DA6
8081 UNKNOWN, // 2DA7
8082 ETHIOPIC, // 2DA8..2DAE
8083 UNKNOWN, // 2DAF
8084 ETHIOPIC, // 2DB0..2DB6
8085 UNKNOWN, // 2DB7
8086 ETHIOPIC, // 2DB8..2DBE
8087 UNKNOWN, // 2DBF
8088 ETHIOPIC, // 2DC0..2DC6
8089 UNKNOWN, // 2DC7
8090 ETHIOPIC, // 2DC8..2DCE
8091 UNKNOWN, // 2DCF
8092 ETHIOPIC, // 2DD0..2DD6
8093 UNKNOWN, // 2DD7
8094 ETHIOPIC, // 2DD8..2DDE
8095 UNKNOWN, // 2DDF
8096 CYRILLIC, // 2DE0..2DFF
8097 COMMON, // 2E00..2E5D
8098 UNKNOWN, // 2E5E..2E7F
8099 HAN, // 2E80..2E99
8100 UNKNOWN, // 2E9A
8101 HAN, // 2E9B..2EF3
8102 UNKNOWN, // 2EF4..2EFF
8103 HAN, // 2F00..2FD5
8104 UNKNOWN, // 2FD6..2FEF
8105 COMMON, // 2FF0..3004
8106 HAN, // 3005
8107 COMMON, // 3006
8108 HAN, // 3007
8109 COMMON, // 3008..3020
8110 HAN, // 3021..3029
8111 INHERITED, // 302A..302D
8112 HANGUL, // 302E..302F
8113 COMMON, // 3030..3037
8114 HAN, // 3038..303B
8115 COMMON, // 303C..303F
8116 UNKNOWN, // 3040
8117 HIRAGANA, // 3041..3096
8118 UNKNOWN, // 3097..3098
8119 INHERITED, // 3099..309A
8120 COMMON, // 309B..309C
8121 HIRAGANA, // 309D..309F
8122 COMMON, // 30A0
8123 KATAKANA, // 30A1..30FA
8124 COMMON, // 30FB..30FC
8125 KATAKANA, // 30FD..30FF
8126 UNKNOWN, // 3100..3104
8127 BOPOMOFO, // 3105..312F
8128 UNKNOWN, // 3130
8129 HANGUL, // 3131..318E
8130 UNKNOWN, // 318F
8131 COMMON, // 3190..319F
8132 BOPOMOFO, // 31A0..31BF
8133 COMMON, // 31C0..31E5
8134 UNKNOWN, // 31E6..31EE
8135 COMMON, // 31EF
8136 KATAKANA, // 31F0..31FF
8137 HANGUL, // 3200..321E
8138 UNKNOWN, // 321F
8139 COMMON, // 3220..325F
8140 HANGUL, // 3260..327E
8141 COMMON, // 327F..32CF
8142 KATAKANA, // 32D0..32FE
8143 COMMON, // 32FF
8144 KATAKANA, // 3300..3357
8145 COMMON, // 3358..33FF
8146 HAN, // 3400..4DBF
8147 COMMON, // 4DC0..4DFF
8148 HAN, // 4E00..9FFF
8149 YI, // A000..A48C
8150 UNKNOWN, // A48D..A48F
8151 YI, // A490..A4C6
8152 UNKNOWN, // A4C7..A4CF
8153 LISU, // A4D0..A4FF
8154 VAI, // A500..A62B
8155 UNKNOWN, // A62C..A63F
8156 CYRILLIC, // A640..A69F
8157 BAMUM, // A6A0..A6F7
8158 UNKNOWN, // A6F8..A6FF
8159 COMMON, // A700..A721
8160 LATIN, // A722..A787
8161 COMMON, // A788..A78A
8162 LATIN, // A78B..A7DC
8163 UNKNOWN, // A7DD..A7F0
8164 LATIN, // A7F1..A7FF
8165 SYLOTI_NAGRI, // A800..A82C
8166 UNKNOWN, // A82D..A82F
8167 COMMON, // A830..A839
8168 UNKNOWN, // A83A..A83F
8169 PHAGS_PA, // A840..A877
8170 UNKNOWN, // A878..A87F
8171 SAURASHTRA, // A880..A8C5
8172 UNKNOWN, // A8C6..A8CD
8173 SAURASHTRA, // A8CE..A8D9
8174 UNKNOWN, // A8DA..A8DF
8175 DEVANAGARI, // A8E0..A8FF
8176 KAYAH_LI, // A900..A92D
8177 COMMON, // A92E
8178 KAYAH_LI, // A92F
8179 REJANG, // A930..A953
8180 UNKNOWN, // A954..A95E
8181 REJANG, // A95F
8182 HANGUL, // A960..A97C
8183 UNKNOWN, // A97D..A97F
8184 JAVANESE, // A980..A9CD
8185 UNKNOWN, // A9CE
8186 COMMON, // A9CF
8187 JAVANESE, // A9D0..A9D9
8188 UNKNOWN, // A9DA..A9DD
8189 JAVANESE, // A9DE..A9DF
8190 MYANMAR, // A9E0..A9FE
8191 UNKNOWN, // A9FF
8192 CHAM, // AA00..AA36
8193 UNKNOWN, // AA37..AA3F
8194 CHAM, // AA40..AA4D
8195 UNKNOWN, // AA4E..AA4F
8196 CHAM, // AA50..AA59
8197 UNKNOWN, // AA5A..AA5B
8198 CHAM, // AA5C..AA5F
8199 MYANMAR, // AA60..AA7F
8200 TAI_VIET, // AA80..AAC2
8201 UNKNOWN, // AAC3..AADA
8202 TAI_VIET, // AADB..AADF
8203 MEETEI_MAYEK, // AAE0..AAF6
8204 UNKNOWN, // AAF7..AB00
8205 ETHIOPIC, // AB01..AB06
8206 UNKNOWN, // AB07..AB08
8207 ETHIOPIC, // AB09..AB0E
8208 UNKNOWN, // AB0F..AB10
8209 ETHIOPIC, // AB11..AB16
8210 UNKNOWN, // AB17..AB1F
8211 ETHIOPIC, // AB20..AB26
8212 UNKNOWN, // AB27
8213 ETHIOPIC, // AB28..AB2E
8214 UNKNOWN, // AB2F
8215 LATIN, // AB30..AB5A
8216 COMMON, // AB5B
8217 LATIN, // AB5C..AB64
8218 GREEK, // AB65
8219 LATIN, // AB66..AB69
8220 COMMON, // AB6A..AB6B
8221 UNKNOWN, // AB6C..AB6F
8222 CHEROKEE, // AB70..ABBF
8223 MEETEI_MAYEK, // ABC0..ABED
8224 UNKNOWN, // ABEE..ABEF
8225 MEETEI_MAYEK, // ABF0..ABF9
8226 UNKNOWN, // ABFA..ABFF
8227 HANGUL, // AC00..D7A3
8228 UNKNOWN, // D7A4..D7AF
8229 HANGUL, // D7B0..D7C6
8230 UNKNOWN, // D7C7..D7CA
8231 HANGUL, // D7CB..D7FB
8232 UNKNOWN, // D7FC..F8FF
8233 HAN, // F900..FA6D
8234 UNKNOWN, // FA6E..FA6F
8235 HAN, // FA70..FAD9
8236 UNKNOWN, // FADA..FAFF
8237 LATIN, // FB00..FB06
8238 UNKNOWN, // FB07..FB12
8239 ARMENIAN, // FB13..FB17
8240 UNKNOWN, // FB18..FB1C
8241 HEBREW, // FB1D..FB36
8242 UNKNOWN, // FB37
8243 HEBREW, // FB38..FB3C
8244 UNKNOWN, // FB3D
8245 HEBREW, // FB3E
8246 UNKNOWN, // FB3F
8247 HEBREW, // FB40..FB41
8248 UNKNOWN, // FB42
8249 HEBREW, // FB43..FB44
8250 UNKNOWN, // FB45
8251 HEBREW, // FB46..FB4F
8252 ARABIC, // FB50..FD3D
8253 COMMON, // FD3E..FD3F
8254 ARABIC, // FD40..FDCF
8255 UNKNOWN, // FDD0..FDEF
8256 ARABIC, // FDF0..FDFF
8257 INHERITED, // FE00..FE0F
8258 COMMON, // FE10..FE19
8259 UNKNOWN, // FE1A..FE1F
8260 INHERITED, // FE20..FE2D
8261 CYRILLIC, // FE2E..FE2F
8262 COMMON, // FE30..FE52
8263 UNKNOWN, // FE53
8264 COMMON, // FE54..FE66
8265 UNKNOWN, // FE67
8266 COMMON, // FE68..FE6B
8267 UNKNOWN, // FE6C..FE6F
8268 ARABIC, // FE70..FE74
8269 UNKNOWN, // FE75
8270 ARABIC, // FE76..FEFC
8271 UNKNOWN, // FEFD..FEFE
8272 COMMON, // FEFF
8273 UNKNOWN, // FF00
8274 COMMON, // FF01..FF20
8275 LATIN, // FF21..FF3A
8276 COMMON, // FF3B..FF40
8277 LATIN, // FF41..FF5A
8278 COMMON, // FF5B..FF65
8279 KATAKANA, // FF66..FF6F
8280 COMMON, // FF70
8281 KATAKANA, // FF71..FF9D
8282 COMMON, // FF9E..FF9F
8283 HANGUL, // FFA0..FFBE
8284 UNKNOWN, // FFBF..FFC1
8285 HANGUL, // FFC2..FFC7
8286 UNKNOWN, // FFC8..FFC9
8287 HANGUL, // FFCA..FFCF
8288 UNKNOWN, // FFD0..FFD1
8289 HANGUL, // FFD2..FFD7
8290 UNKNOWN, // FFD8..FFD9
8291 HANGUL, // FFDA..FFDC
8292 UNKNOWN, // FFDD..FFDF
8293 COMMON, // FFE0..FFE6
8294 UNKNOWN, // FFE7
8295 COMMON, // FFE8..FFEE
8296 UNKNOWN, // FFEF..FFF8
8297 COMMON, // FFF9..FFFD
8298 UNKNOWN, // FFFE..FFFF
8299 LINEAR_B, // 10000..1000B
8300 UNKNOWN, // 1000C
8301 LINEAR_B, // 1000D..10026
8302 UNKNOWN, // 10027
8303 LINEAR_B, // 10028..1003A
8304 UNKNOWN, // 1003B
8305 LINEAR_B, // 1003C..1003D
8306 UNKNOWN, // 1003E
8307 LINEAR_B, // 1003F..1004D
8308 UNKNOWN, // 1004E..1004F
8309 LINEAR_B, // 10050..1005D
8310 UNKNOWN, // 1005E..1007F
8311 LINEAR_B, // 10080..100FA
8312 UNKNOWN, // 100FB..100FF
8313 COMMON, // 10100..10102
8314 UNKNOWN, // 10103..10106
8315 COMMON, // 10107..10133
8316 UNKNOWN, // 10134..10136
8317 COMMON, // 10137..1013F
8318 GREEK, // 10140..1018E
8319 UNKNOWN, // 1018F
8320 COMMON, // 10190..1019C
8321 UNKNOWN, // 1019D..1019F
8322 GREEK, // 101A0
8323 UNKNOWN, // 101A1..101CF
8324 COMMON, // 101D0..101FC
8325 INHERITED, // 101FD
8326 UNKNOWN, // 101FE..1027F
8327 LYCIAN, // 10280..1029C
8328 UNKNOWN, // 1029D..1029F
8329 CARIAN, // 102A0..102D0
8330 UNKNOWN, // 102D1..102DF
8331 INHERITED, // 102E0
8332 COMMON, // 102E1..102FB
8333 UNKNOWN, // 102FC..102FF
8334 OLD_ITALIC, // 10300..10323
8335 UNKNOWN, // 10324..1032C
8336 OLD_ITALIC, // 1032D..1032F
8337 GOTHIC, // 10330..1034A
8338 UNKNOWN, // 1034B..1034F
8339 OLD_PERMIC, // 10350..1037A
8340 UNKNOWN, // 1037B..1037F
8341 UGARITIC, // 10380..1039D
8342 UNKNOWN, // 1039E
8343 UGARITIC, // 1039F
8344 OLD_PERSIAN, // 103A0..103C3
8345 UNKNOWN, // 103C4..103C7
8346 OLD_PERSIAN, // 103C8..103D5
8347 UNKNOWN, // 103D6..103FF
8348 DESERET, // 10400..1044F
8349 SHAVIAN, // 10450..1047F
8350 OSMANYA, // 10480..1049D
8351 UNKNOWN, // 1049E..1049F
8352 OSMANYA, // 104A0..104A9
8353 UNKNOWN, // 104AA..104AF
8354 OSAGE, // 104B0..104D3
8355 UNKNOWN, // 104D4..104D7
8356 OSAGE, // 104D8..104FB
8357 UNKNOWN, // 104FC..104FF
8358 ELBASAN, // 10500..10527
8359 UNKNOWN, // 10528..1052F
8360 CAUCASIAN_ALBANIAN, // 10530..10563
8361 UNKNOWN, // 10564..1056E
8362 CAUCASIAN_ALBANIAN, // 1056F
8363 VITHKUQI, // 10570..1057A
8364 UNKNOWN, // 1057B
8365 VITHKUQI, // 1057C..1058A
8366 UNKNOWN, // 1058B
8367 VITHKUQI, // 1058C..10592
8368 UNKNOWN, // 10593
8369 VITHKUQI, // 10594..10595
8370 UNKNOWN, // 10596
8371 VITHKUQI, // 10597..105A1
8372 UNKNOWN, // 105A2
8373 VITHKUQI, // 105A3..105B1
8374 UNKNOWN, // 105B2
8375 VITHKUQI, // 105B3..105B9
8376 UNKNOWN, // 105BA
8377 VITHKUQI, // 105BB..105BC
8378 UNKNOWN, // 105BD..105BF
8379 TODHRI, // 105C0..105F3
8380 UNKNOWN, // 105F4..105FF
8381 LINEAR_A, // 10600..10736
8382 UNKNOWN, // 10737..1073F
8383 LINEAR_A, // 10740..10755
8384 UNKNOWN, // 10756..1075F
8385 LINEAR_A, // 10760..10767
8386 UNKNOWN, // 10768..1077F
8387 LATIN, // 10780..10785
8388 UNKNOWN, // 10786
8389 LATIN, // 10787..107B0
8390 UNKNOWN, // 107B1
8391 LATIN, // 107B2..107BA
8392 UNKNOWN, // 107BB..107FF
8393 CYPRIOT, // 10800..10805
8394 UNKNOWN, // 10806..10807
8395 CYPRIOT, // 10808
8396 UNKNOWN, // 10809
8397 CYPRIOT, // 1080A..10835
8398 UNKNOWN, // 10836
8399 CYPRIOT, // 10837..10838
8400 UNKNOWN, // 10839..1083B
8401 CYPRIOT, // 1083C
8402 UNKNOWN, // 1083D..1083E
8403 CYPRIOT, // 1083F
8404 IMPERIAL_ARAMAIC, // 10840..10855
8405 UNKNOWN, // 10856
8406 IMPERIAL_ARAMAIC, // 10857..1085F
8407 PALMYRENE, // 10860..1087F
8408 NABATAEAN, // 10880..1089E
8409 UNKNOWN, // 1089F..108A6
8410 NABATAEAN, // 108A7..108AF
8411 UNKNOWN, // 108B0..108DF
8412 HATRAN, // 108E0..108F2
8413 UNKNOWN, // 108F3
8414 HATRAN, // 108F4..108F5
8415 UNKNOWN, // 108F6..108FA
8416 HATRAN, // 108FB..108FF
8417 PHOENICIAN, // 10900..1091B
8418 UNKNOWN, // 1091C..1091E
8419 PHOENICIAN, // 1091F
8420 LYDIAN, // 10920..10939
8421 UNKNOWN, // 1093A..1093E
8422 LYDIAN, // 1093F
8423 SIDETIC, // 10940..10959
8424 UNKNOWN, // 1095A..1097F
8425 MEROITIC_HIEROGLYPHS, // 10980..1099F
8426 MEROITIC_CURSIVE, // 109A0..109B7
8427 UNKNOWN, // 109B8..109BB
8428 MEROITIC_CURSIVE, // 109BC..109CF
8429 UNKNOWN, // 109D0..109D1
8430 MEROITIC_CURSIVE, // 109D2..109FF
8431 KHAROSHTHI, // 10A00..10A03
8432 UNKNOWN, // 10A04
8433 KHAROSHTHI, // 10A05..10A06
8434 UNKNOWN, // 10A07..10A0B
8435 KHAROSHTHI, // 10A0C..10A13
8436 UNKNOWN, // 10A14
8437 KHAROSHTHI, // 10A15..10A17
8438 UNKNOWN, // 10A18
8439 KHAROSHTHI, // 10A19..10A35
8440 UNKNOWN, // 10A36..10A37
8441 KHAROSHTHI, // 10A38..10A3A
8442 UNKNOWN, // 10A3B..10A3E
8443 KHAROSHTHI, // 10A3F..10A48
8444 UNKNOWN, // 10A49..10A4F
8445 KHAROSHTHI, // 10A50..10A58
8446 UNKNOWN, // 10A59..10A5F
8447 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8448 OLD_NORTH_ARABIAN, // 10A80..10A9F
8449 UNKNOWN, // 10AA0..10ABF
8450 MANICHAEAN, // 10AC0..10AE6
8451 UNKNOWN, // 10AE7..10AEA
8452 MANICHAEAN, // 10AEB..10AF6
8453 UNKNOWN, // 10AF7..10AFF
8454 AVESTAN, // 10B00..10B35
8455 UNKNOWN, // 10B36..10B38
8456 AVESTAN, // 10B39..10B3F
8457 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8458 UNKNOWN, // 10B56..10B57
8459 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8460 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8461 UNKNOWN, // 10B73..10B77
8462 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8463 PSALTER_PAHLAVI, // 10B80..10B91
8464 UNKNOWN, // 10B92..10B98
8465 PSALTER_PAHLAVI, // 10B99..10B9C
8466 UNKNOWN, // 10B9D..10BA8
8467 PSALTER_PAHLAVI, // 10BA9..10BAF
8468 UNKNOWN, // 10BB0..10BFF
8469 OLD_TURKIC, // 10C00..10C48
8470 UNKNOWN, // 10C49..10C7F
8471 OLD_HUNGARIAN, // 10C80..10CB2
8472 UNKNOWN, // 10CB3..10CBF
8473 OLD_HUNGARIAN, // 10CC0..10CF2
8474 UNKNOWN, // 10CF3..10CF9
8475 OLD_HUNGARIAN, // 10CFA..10CFF
8476 HANIFI_ROHINGYA, // 10D00..10D27
8477 UNKNOWN, // 10D28..10D2F
8478 HANIFI_ROHINGYA, // 10D30..10D39
8479 UNKNOWN, // 10D3A..10D3F
8480 GARAY, // 10D40..10D65
8481 UNKNOWN, // 10D66..10D68
8482 GARAY, // 10D69..10D85
8483 UNKNOWN, // 10D86..10D8D
8484 GARAY, // 10D8E..10D8F
8485 UNKNOWN, // 10D90..10E5F
8486 ARABIC, // 10E60..10E7E
8487 UNKNOWN, // 10E7F
8488 YEZIDI, // 10E80..10EA9
8489 UNKNOWN, // 10EAA
8490 YEZIDI, // 10EAB..10EAD
8491 UNKNOWN, // 10EAE..10EAF
8492 YEZIDI, // 10EB0..10EB1
8493 UNKNOWN, // 10EB2..10EC1
8494 ARABIC, // 10EC2..10EC7
8495 UNKNOWN, // 10EC8..10ECF
8496 ARABIC, // 10ED0..10ED8
8497 UNKNOWN, // 10ED9..10EF9
8498 ARABIC, // 10EFA..10EFF
8499 OLD_SOGDIAN, // 10F00..10F27
8500 UNKNOWN, // 10F28..10F2F
8501 SOGDIAN, // 10F30..10F59
8502 UNKNOWN, // 10F5A..10F6F
8503 OLD_UYGHUR, // 10F70..10F89
8504 UNKNOWN, // 10F8A..10FAF
8505 CHORASMIAN, // 10FB0..10FCB
8506 UNKNOWN, // 10FCC..10FDF
8507 ELYMAIC, // 10FE0..10FF6
8508 UNKNOWN, // 10FF7..10FFF
8509 BRAHMI, // 11000..1104D
8510 UNKNOWN, // 1104E..11051
8511 BRAHMI, // 11052..11075
8512 UNKNOWN, // 11076..1107E
8513 BRAHMI, // 1107F
8514 KAITHI, // 11080..110C2
8515 UNKNOWN, // 110C3..110CC
8516 KAITHI, // 110CD
8517 UNKNOWN, // 110CE..110CF
8518 SORA_SOMPENG, // 110D0..110E8
8519 UNKNOWN, // 110E9..110EF
8520 SORA_SOMPENG, // 110F0..110F9
8521 UNKNOWN, // 110FA..110FF
8522 CHAKMA, // 11100..11134
8523 UNKNOWN, // 11135
8524 CHAKMA, // 11136..11147
8525 UNKNOWN, // 11148..1114F
8526 MAHAJANI, // 11150..11176
8527 UNKNOWN, // 11177..1117F
8528 SHARADA, // 11180..111DF
8529 UNKNOWN, // 111E0
8530 SINHALA, // 111E1..111F4
8531 UNKNOWN, // 111F5..111FF
8532 KHOJKI, // 11200..11211
8533 UNKNOWN, // 11212
8534 KHOJKI, // 11213..11241
8535 UNKNOWN, // 11242..1127F
8536 MULTANI, // 11280..11286
8537 UNKNOWN, // 11287
8538 MULTANI, // 11288
8539 UNKNOWN, // 11289
8540 MULTANI, // 1128A..1128D
8541 UNKNOWN, // 1128E
8542 MULTANI, // 1128F..1129D
8543 UNKNOWN, // 1129E
8544 MULTANI, // 1129F..112A9
8545 UNKNOWN, // 112AA..112AF
8546 KHUDAWADI, // 112B0..112EA
8547 UNKNOWN, // 112EB..112EF
8548 KHUDAWADI, // 112F0..112F9
8549 UNKNOWN, // 112FA..112FF
8550 GRANTHA, // 11300..11303
8551 UNKNOWN, // 11304
8552 GRANTHA, // 11305..1130C
8553 UNKNOWN, // 1130D..1130E
8554 GRANTHA, // 1130F..11310
8555 UNKNOWN, // 11311..11312
8556 GRANTHA, // 11313..11328
8557 UNKNOWN, // 11329
8558 GRANTHA, // 1132A..11330
8559 UNKNOWN, // 11331
8560 GRANTHA, // 11332..11333
8561 UNKNOWN, // 11334
8562 GRANTHA, // 11335..11339
8563 UNKNOWN, // 1133A
8564 INHERITED, // 1133B
8565 GRANTHA, // 1133C..11344
8566 UNKNOWN, // 11345..11346
8567 GRANTHA, // 11347..11348
8568 UNKNOWN, // 11349..1134A
8569 GRANTHA, // 1134B..1134D
8570 UNKNOWN, // 1134E..1134F
8571 GRANTHA, // 11350
8572 UNKNOWN, // 11351..11356
8573 GRANTHA, // 11357
8574 UNKNOWN, // 11358..1135C
8575 GRANTHA, // 1135D..11363
8576 UNKNOWN, // 11364..11365
8577 GRANTHA, // 11366..1136C
8578 UNKNOWN, // 1136D..1136F
8579 GRANTHA, // 11370..11374
8580 UNKNOWN, // 11375..1137F
8581 TULU_TIGALARI, // 11380..11389
8582 UNKNOWN, // 1138A
8583 TULU_TIGALARI, // 1138B
8584 UNKNOWN, // 1138C..1138D
8585 TULU_TIGALARI, // 1138E
8586 UNKNOWN, // 1138F
8587 TULU_TIGALARI, // 11390..113B5
8588 UNKNOWN, // 113B6
8589 TULU_TIGALARI, // 113B7..113C0
8590 UNKNOWN, // 113C1
8591 TULU_TIGALARI, // 113C2
8592 UNKNOWN, // 113C3..113C4
8593 TULU_TIGALARI, // 113C5
8594 UNKNOWN, // 113C6
8595 TULU_TIGALARI, // 113C7..113CA
8596 UNKNOWN, // 113CB
8597 TULU_TIGALARI, // 113CC..113D5
8598 UNKNOWN, // 113D6
8599 TULU_TIGALARI, // 113D7..113D8
8600 UNKNOWN, // 113D9..113E0
8601 TULU_TIGALARI, // 113E1..113E2
8602 UNKNOWN, // 113E3..113FF
8603 NEWA, // 11400..1145B
8604 UNKNOWN, // 1145C
8605 NEWA, // 1145D..11461
8606 UNKNOWN, // 11462..1147F
8607 TIRHUTA, // 11480..114C7
8608 UNKNOWN, // 114C8..114CF
8609 TIRHUTA, // 114D0..114D9
8610 UNKNOWN, // 114DA..1157F
8611 SIDDHAM, // 11580..115B5
8612 UNKNOWN, // 115B6..115B7
8613 SIDDHAM, // 115B8..115DD
8614 UNKNOWN, // 115DE..115FF
8615 MODI, // 11600..11644
8616 UNKNOWN, // 11645..1164F
8617 MODI, // 11650..11659
8618 UNKNOWN, // 1165A..1165F
8619 MONGOLIAN, // 11660..1166C
8620 UNKNOWN, // 1166D..1167F
8621 TAKRI, // 11680..116B9
8622 UNKNOWN, // 116BA..116BF
8623 TAKRI, // 116C0..116C9
8624 UNKNOWN, // 116CA..116CF
8625 MYANMAR, // 116D0..116E3
8626 UNKNOWN, // 116E4..116FF
8627 AHOM, // 11700..1171A
8628 UNKNOWN, // 1171B..1171C
8629 AHOM, // 1171D..1172B
8630 UNKNOWN, // 1172C..1172F
8631 AHOM, // 11730..11746
8632 UNKNOWN, // 11747..117FF
8633 DOGRA, // 11800..1183B
8634 UNKNOWN, // 1183C..1189F
8635 WARANG_CITI, // 118A0..118F2
8636 UNKNOWN, // 118F3..118FE
8637 WARANG_CITI, // 118FF
8638 DIVES_AKURU, // 11900..11906
8639 UNKNOWN, // 11907..11908
8640 DIVES_AKURU, // 11909
8641 UNKNOWN, // 1190A..1190B
8642 DIVES_AKURU, // 1190C..11913
8643 UNKNOWN, // 11914
8644 DIVES_AKURU, // 11915..11916
8645 UNKNOWN, // 11917
8646 DIVES_AKURU, // 11918..11935
8647 UNKNOWN, // 11936
8648 DIVES_AKURU, // 11937..11938
8649 UNKNOWN, // 11939..1193A
8650 DIVES_AKURU, // 1193B..11946
8651 UNKNOWN, // 11947..1194F
8652 DIVES_AKURU, // 11950..11959
8653 UNKNOWN, // 1195A..1199F
8654 NANDINAGARI, // 119A0..119A7
8655 UNKNOWN, // 119A8..119A9
8656 NANDINAGARI, // 119AA..119D7
8657 UNKNOWN, // 119D8..119D9
8658 NANDINAGARI, // 119DA..119E4
8659 UNKNOWN, // 119E5..119FF
8660 ZANABAZAR_SQUARE, // 11A00..11A47
8661 UNKNOWN, // 11A48..11A4F
8662 SOYOMBO, // 11A50..11AA2
8663 UNKNOWN, // 11AA3..11AAF
8664 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8665 PAU_CIN_HAU, // 11AC0..11AF8
8666 UNKNOWN, // 11AF9..11AFF
8667 DEVANAGARI, // 11B00..11B09
8668 UNKNOWN, // 11B0A..11B5F
8669 SHARADA, // 11B60..11B67
8670 UNKNOWN, // 11B68..11BBF
8671 SUNUWAR, // 11BC0..11BE1
8672 UNKNOWN, // 11BE2..11BEF
8673 SUNUWAR, // 11BF0..11BF9
8674 UNKNOWN, // 11BFA..11BFF
8675 BHAIKSUKI, // 11C00..11C08
8676 UNKNOWN, // 11C09
8677 BHAIKSUKI, // 11C0A..11C36
8678 UNKNOWN, // 11C37
8679 BHAIKSUKI, // 11C38..11C45
8680 UNKNOWN, // 11C46..11C4F
8681 BHAIKSUKI, // 11C50..11C6C
8682 UNKNOWN, // 11C6D..11C6F
8683 MARCHEN, // 11C70..11C8F
8684 UNKNOWN, // 11C90..11C91
8685 MARCHEN, // 11C92..11CA7
8686 UNKNOWN, // 11CA8
8687 MARCHEN, // 11CA9..11CB6
8688 UNKNOWN, // 11CB7..11CFF
8689 MASARAM_GONDI, // 11D00..11D06
8690 UNKNOWN, // 11D07
8691 MASARAM_GONDI, // 11D08..11D09
8692 UNKNOWN, // 11D0A
8693 MASARAM_GONDI, // 11D0B..11D36
8694 UNKNOWN, // 11D37..11D39
8695 MASARAM_GONDI, // 11D3A
8696 UNKNOWN, // 11D3B
8697 MASARAM_GONDI, // 11D3C..11D3D
8698 UNKNOWN, // 11D3E
8699 MASARAM_GONDI, // 11D3F..11D47
8700 UNKNOWN, // 11D48..11D4F
8701 MASARAM_GONDI, // 11D50..11D59
8702 UNKNOWN, // 11D5A..11D5F
8703 GUNJALA_GONDI, // 11D60..11D65
8704 UNKNOWN, // 11D66
8705 GUNJALA_GONDI, // 11D67..11D68
8706 UNKNOWN, // 11D69
8707 GUNJALA_GONDI, // 11D6A..11D8E
8708 UNKNOWN, // 11D8F
8709 GUNJALA_GONDI, // 11D90..11D91
8710 UNKNOWN, // 11D92
8711 GUNJALA_GONDI, // 11D93..11D98
8712 UNKNOWN, // 11D99..11D9F
8713 GUNJALA_GONDI, // 11DA0..11DA9
8714 UNKNOWN, // 11DAA..11DAF
8715 TOLONG_SIKI, // 11DB0..11DDB
8716 UNKNOWN, // 11DDC..11DDF
8717 TOLONG_SIKI, // 11DE0..11DE9
8718 UNKNOWN, // 11DEA..11EDF
8719 MAKASAR, // 11EE0..11EF8
8720 UNKNOWN, // 11EF9..11EFF
8721 KAWI, // 11F00..11F10
8722 UNKNOWN, // 11F11
8723 KAWI, // 11F12..11F3A
8724 UNKNOWN, // 11F3B..11F3D
8725 KAWI, // 11F3E..11F5A
8726 UNKNOWN, // 11F5B..11FAF
8727 LISU, // 11FB0
8728 UNKNOWN, // 11FB1..11FBF
8729 TAMIL, // 11FC0..11FF1
8730 UNKNOWN, // 11FF2..11FFE
8731 TAMIL, // 11FFF
8732 CUNEIFORM, // 12000..12399
8733 UNKNOWN, // 1239A..123FF
8734 CUNEIFORM, // 12400..1246E
8735 UNKNOWN, // 1246F
8736 CUNEIFORM, // 12470..12474
8737 UNKNOWN, // 12475..1247F
8738 CUNEIFORM, // 12480..12543
8739 UNKNOWN, // 12544..12F8F
8740 CYPRO_MINOAN, // 12F90..12FF2
8741 UNKNOWN, // 12FF3..12FFF
8742 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8743 UNKNOWN, // 13456..1345F
8744 EGYPTIAN_HIEROGLYPHS, // 13460..143FA
8745 UNKNOWN, // 143FB..143FF
8746 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8747 UNKNOWN, // 14647..160FF
8748 GURUNG_KHEMA, // 16100..16139
8749 UNKNOWN, // 1613A..167FF
8750 BAMUM, // 16800..16A38
8751 UNKNOWN, // 16A39..16A3F
8752 MRO, // 16A40..16A5E
8753 UNKNOWN, // 16A5F
8754 MRO, // 16A60..16A69
8755 UNKNOWN, // 16A6A..16A6D
8756 MRO, // 16A6E..16A6F
8757 TANGSA, // 16A70..16ABE
8758 UNKNOWN, // 16ABF
8759 TANGSA, // 16AC0..16AC9
8760 UNKNOWN, // 16ACA..16ACF
8761 BASSA_VAH, // 16AD0..16AED
8762 UNKNOWN, // 16AEE..16AEF
8763 BASSA_VAH, // 16AF0..16AF5
8764 UNKNOWN, // 16AF6..16AFF
8765 PAHAWH_HMONG, // 16B00..16B45
8766 UNKNOWN, // 16B46..16B4F
8767 PAHAWH_HMONG, // 16B50..16B59
8768 UNKNOWN, // 16B5A
8769 PAHAWH_HMONG, // 16B5B..16B61
8770 UNKNOWN, // 16B62
8771 PAHAWH_HMONG, // 16B63..16B77
8772 UNKNOWN, // 16B78..16B7C
8773 PAHAWH_HMONG, // 16B7D..16B8F
8774 UNKNOWN, // 16B90..16D3F
8775 KIRAT_RAI, // 16D40..16D79
8776 UNKNOWN, // 16D7A..16E3F
8777 MEDEFAIDRIN, // 16E40..16E9A
8778 UNKNOWN, // 16E9B..16E9F
8779 BERIA_ERFE, // 16EA0..16EB8
8780 UNKNOWN, // 16EB9..16EBA
8781 BERIA_ERFE, // 16EBB..16ED3
8782 UNKNOWN, // 16ED4..16EFF
8783 MIAO, // 16F00..16F4A
8784 UNKNOWN, // 16F4B..16F4E
8785 MIAO, // 16F4F..16F87
8786 UNKNOWN, // 16F88..16F8E
8787 MIAO, // 16F8F..16F9F
8788 UNKNOWN, // 16FA0..16FDF
8789 TANGUT, // 16FE0
8790 NUSHU, // 16FE1
8791 HAN, // 16FE2..16FE3
8792 KHITAN_SMALL_SCRIPT, // 16FE4
8793 UNKNOWN, // 16FE5..16FEF
8794 HAN, // 16FF0..16FF6
8795 UNKNOWN, // 16FF7..16FFF
8796 TANGUT, // 17000..18AFF
8797 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8798 UNKNOWN, // 18CD6..18CFE
8799 KHITAN_SMALL_SCRIPT, // 18CFF
8800 TANGUT, // 18D00..18D1E
8801 UNKNOWN, // 18D1F..18D7F
8802 TANGUT, // 18D80..18DF2
8803 UNKNOWN, // 18DF3..1AFEF
8804 KATAKANA, // 1AFF0..1AFF3
8805 UNKNOWN, // 1AFF4
8806 KATAKANA, // 1AFF5..1AFFB
8807 UNKNOWN, // 1AFFC
8808 KATAKANA, // 1AFFD..1AFFE
8809 UNKNOWN, // 1AFFF
8810 KATAKANA, // 1B000
8811 HIRAGANA, // 1B001..1B11F
8812 KATAKANA, // 1B120..1B122
8813 UNKNOWN, // 1B123..1B131
8814 HIRAGANA, // 1B132
8815 UNKNOWN, // 1B133..1B14F
8816 HIRAGANA, // 1B150..1B152
8817 UNKNOWN, // 1B153..1B154
8818 KATAKANA, // 1B155
8819 UNKNOWN, // 1B156..1B163
8820 KATAKANA, // 1B164..1B167
8821 UNKNOWN, // 1B168..1B16F
8822 NUSHU, // 1B170..1B2FB
8823 UNKNOWN, // 1B2FC..1BBFF
8824 DUPLOYAN, // 1BC00..1BC6A
8825 UNKNOWN, // 1BC6B..1BC6F
8826 DUPLOYAN, // 1BC70..1BC7C
8827 UNKNOWN, // 1BC7D..1BC7F
8828 DUPLOYAN, // 1BC80..1BC88
8829 UNKNOWN, // 1BC89..1BC8F
8830 DUPLOYAN, // 1BC90..1BC99
8831 UNKNOWN, // 1BC9A..1BC9B
8832 DUPLOYAN, // 1BC9C..1BC9F
8833 COMMON, // 1BCA0..1BCA3
8834 UNKNOWN, // 1BCA4..1CBFF
8835 COMMON, // 1CC00..1CCFC
8836 UNKNOWN, // 1CCFD..1CCFF
8837 COMMON, // 1CD00..1CEB3
8838 UNKNOWN, // 1CEB4..1CEB9
8839 COMMON, // 1CEBA..1CED0
8840 UNKNOWN, // 1CED1..1CEDF
8841 COMMON, // 1CEE0..1CEF0
8842 UNKNOWN, // 1CEF1..1CEFF
8843 INHERITED, // 1CF00..1CF2D
8844 UNKNOWN, // 1CF2E..1CF2F
8845 INHERITED, // 1CF30..1CF46
8846 UNKNOWN, // 1CF47..1CF4F
8847 COMMON, // 1CF50..1CFC3
8848 UNKNOWN, // 1CFC4..1CFFF
8849 COMMON, // 1D000..1D0F5
8850 UNKNOWN, // 1D0F6..1D0FF
8851 COMMON, // 1D100..1D126
8852 UNKNOWN, // 1D127..1D128
8853 COMMON, // 1D129..1D166
8854 INHERITED, // 1D167..1D169
8855 COMMON, // 1D16A..1D17A
8856 INHERITED, // 1D17B..1D182
8857 COMMON, // 1D183..1D184
8858 INHERITED, // 1D185..1D18B
8859 COMMON, // 1D18C..1D1A9
8860 INHERITED, // 1D1AA..1D1AD
8861 COMMON, // 1D1AE..1D1EA
8862 UNKNOWN, // 1D1EB..1D1FF
8863 GREEK, // 1D200..1D245
8864 UNKNOWN, // 1D246..1D2BF
8865 COMMON, // 1D2C0..1D2D3
8866 UNKNOWN, // 1D2D4..1D2DF
8867 COMMON, // 1D2E0..1D2F3
8868 UNKNOWN, // 1D2F4..1D2FF
8869 COMMON, // 1D300..1D356
8870 UNKNOWN, // 1D357..1D35F
8871 COMMON, // 1D360..1D378
8872 UNKNOWN, // 1D379..1D3FF
8873 COMMON, // 1D400..1D454
8874 UNKNOWN, // 1D455
8875 COMMON, // 1D456..1D49C
8876 UNKNOWN, // 1D49D
8877 COMMON, // 1D49E..1D49F
8878 UNKNOWN, // 1D4A0..1D4A1
8879 COMMON, // 1D4A2
8880 UNKNOWN, // 1D4A3..1D4A4
8881 COMMON, // 1D4A5..1D4A6
8882 UNKNOWN, // 1D4A7..1D4A8
8883 COMMON, // 1D4A9..1D4AC
8884 UNKNOWN, // 1D4AD
8885 COMMON, // 1D4AE..1D4B9
8886 UNKNOWN, // 1D4BA
8887 COMMON, // 1D4BB
8888 UNKNOWN, // 1D4BC
8889 COMMON, // 1D4BD..1D4C3
8890 UNKNOWN, // 1D4C4
8891 COMMON, // 1D4C5..1D505
8892 UNKNOWN, // 1D506
8893 COMMON, // 1D507..1D50A
8894 UNKNOWN, // 1D50B..1D50C
8895 COMMON, // 1D50D..1D514
8896 UNKNOWN, // 1D515
8897 COMMON, // 1D516..1D51C
8898 UNKNOWN, // 1D51D
8899 COMMON, // 1D51E..1D539
8900 UNKNOWN, // 1D53A
8901 COMMON, // 1D53B..1D53E
8902 UNKNOWN, // 1D53F
8903 COMMON, // 1D540..1D544
8904 UNKNOWN, // 1D545
8905 COMMON, // 1D546
8906 UNKNOWN, // 1D547..1D549
8907 COMMON, // 1D54A..1D550
8908 UNKNOWN, // 1D551
8909 COMMON, // 1D552..1D6A5
8910 UNKNOWN, // 1D6A6..1D6A7
8911 COMMON, // 1D6A8..1D7CB
8912 UNKNOWN, // 1D7CC..1D7CD
8913 COMMON, // 1D7CE..1D7FF
8914 SIGNWRITING, // 1D800..1DA8B
8915 UNKNOWN, // 1DA8C..1DA9A
8916 SIGNWRITING, // 1DA9B..1DA9F
8917 UNKNOWN, // 1DAA0
8918 SIGNWRITING, // 1DAA1..1DAAF
8919 UNKNOWN, // 1DAB0..1DEFF
8920 LATIN, // 1DF00..1DF1E
8921 UNKNOWN, // 1DF1F..1DF24
8922 LATIN, // 1DF25..1DF2A
8923 UNKNOWN, // 1DF2B..1DFFF
8924 GLAGOLITIC, // 1E000..1E006
8925 UNKNOWN, // 1E007
8926 GLAGOLITIC, // 1E008..1E018
8927 UNKNOWN, // 1E019..1E01A
8928 GLAGOLITIC, // 1E01B..1E021
8929 UNKNOWN, // 1E022
8930 GLAGOLITIC, // 1E023..1E024
8931 UNKNOWN, // 1E025
8932 GLAGOLITIC, // 1E026..1E02A
8933 UNKNOWN, // 1E02B..1E02F
8934 CYRILLIC, // 1E030..1E06D
8935 UNKNOWN, // 1E06E..1E08E
8936 CYRILLIC, // 1E08F
8937 UNKNOWN, // 1E090..1E0FF
8938 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8939 UNKNOWN, // 1E12D..1E12F
8940 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8941 UNKNOWN, // 1E13E..1E13F
8942 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8943 UNKNOWN, // 1E14A..1E14D
8944 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8945 UNKNOWN, // 1E150..1E28F
8946 TOTO, // 1E290..1E2AE
8947 UNKNOWN, // 1E2AF..1E2BF
8948 WANCHO, // 1E2C0..1E2F9
8949 UNKNOWN, // 1E2FA..1E2FE
8950 WANCHO, // 1E2FF
8951 UNKNOWN, // 1E300..1E4CF
8952 NAG_MUNDARI, // 1E4D0..1E4F9
8953 UNKNOWN, // 1E4FA..1E5CF
8954 OL_ONAL, // 1E5D0..1E5FA
8955 UNKNOWN, // 1E5FB..1E5FE
8956 OL_ONAL, // 1E5FF
8957 UNKNOWN, // 1E600..1E6BF
8958 TAI_YO, // 1E6C0..1E6DE
8959 UNKNOWN, // 1E6DF
8960 TAI_YO, // 1E6E0..1E6F5
8961 UNKNOWN, // 1E6F6..1E6FD
8962 TAI_YO, // 1E6FE..1E6FF
8963 UNKNOWN, // 1E700..1E7DF
8964 ETHIOPIC, // 1E7E0..1E7E6
8965 UNKNOWN, // 1E7E7
8966 ETHIOPIC, // 1E7E8..1E7EB
8967 UNKNOWN, // 1E7EC
8968 ETHIOPIC, // 1E7ED..1E7EE
8969 UNKNOWN, // 1E7EF
8970 ETHIOPIC, // 1E7F0..1E7FE
8971 UNKNOWN, // 1E7FF
8972 MENDE_KIKAKUI, // 1E800..1E8C4
8973 UNKNOWN, // 1E8C5..1E8C6
8974 MENDE_KIKAKUI, // 1E8C7..1E8D6
8975 UNKNOWN, // 1E8D7..1E8FF
8976 ADLAM, // 1E900..1E94B
8977 UNKNOWN, // 1E94C..1E94F
8978 ADLAM, // 1E950..1E959
8979 UNKNOWN, // 1E95A..1E95D
8980 ADLAM, // 1E95E..1E95F
8981 UNKNOWN, // 1E960..1EC70
8982 COMMON, // 1EC71..1ECB4
8983 UNKNOWN, // 1ECB5..1ED00
8984 COMMON, // 1ED01..1ED3D
8985 UNKNOWN, // 1ED3E..1EDFF
8986 ARABIC, // 1EE00..1EE03
8987 UNKNOWN, // 1EE04
8988 ARABIC, // 1EE05..1EE1F
8989 UNKNOWN, // 1EE20
8990 ARABIC, // 1EE21..1EE22
8991 UNKNOWN, // 1EE23
8992 ARABIC, // 1EE24
8993 UNKNOWN, // 1EE25..1EE26
8994 ARABIC, // 1EE27
8995 UNKNOWN, // 1EE28
8996 ARABIC, // 1EE29..1EE32
8997 UNKNOWN, // 1EE33
8998 ARABIC, // 1EE34..1EE37
8999 UNKNOWN, // 1EE38
9000 ARABIC, // 1EE39
9001 UNKNOWN, // 1EE3A
9002 ARABIC, // 1EE3B
9003 UNKNOWN, // 1EE3C..1EE41
9004 ARABIC, // 1EE42
9005 UNKNOWN, // 1EE43..1EE46
9006 ARABIC, // 1EE47
9007 UNKNOWN, // 1EE48
9008 ARABIC, // 1EE49
9009 UNKNOWN, // 1EE4A
9010 ARABIC, // 1EE4B
9011 UNKNOWN, // 1EE4C
9012 ARABIC, // 1EE4D..1EE4F
9013 UNKNOWN, // 1EE50
9014 ARABIC, // 1EE51..1EE52
9015 UNKNOWN, // 1EE53
9016 ARABIC, // 1EE54
9017 UNKNOWN, // 1EE55..1EE56
9018 ARABIC, // 1EE57
9019 UNKNOWN, // 1EE58
9020 ARABIC, // 1EE59
9021 UNKNOWN, // 1EE5A
9022 ARABIC, // 1EE5B
9023 UNKNOWN, // 1EE5C
9024 ARABIC, // 1EE5D
9025 UNKNOWN, // 1EE5E
9026 ARABIC, // 1EE5F
9027 UNKNOWN, // 1EE60
9028 ARABIC, // 1EE61..1EE62
9029 UNKNOWN, // 1EE63
9030 ARABIC, // 1EE64
9031 UNKNOWN, // 1EE65..1EE66
9032 ARABIC, // 1EE67..1EE6A
9033 UNKNOWN, // 1EE6B
9034 ARABIC, // 1EE6C..1EE72
9035 UNKNOWN, // 1EE73
9036 ARABIC, // 1EE74..1EE77
9037 UNKNOWN, // 1EE78
9038 ARABIC, // 1EE79..1EE7C
9039 UNKNOWN, // 1EE7D
9040 ARABIC, // 1EE7E
9041 UNKNOWN, // 1EE7F
9042 ARABIC, // 1EE80..1EE89
9043 UNKNOWN, // 1EE8A
9044 ARABIC, // 1EE8B..1EE9B
9045 UNKNOWN, // 1EE9C..1EEA0
9046 ARABIC, // 1EEA1..1EEA3
9047 UNKNOWN, // 1EEA4
9048 ARABIC, // 1EEA5..1EEA9
9049 UNKNOWN, // 1EEAA
9050 ARABIC, // 1EEAB..1EEBB
9051 UNKNOWN, // 1EEBC..1EEEF
9052 ARABIC, // 1EEF0..1EEF1
9053 UNKNOWN, // 1EEF2..1EFFF
9054 COMMON, // 1F000..1F02B
9055 UNKNOWN, // 1F02C..1F02F
9056 COMMON, // 1F030..1F093
9057 UNKNOWN, // 1F094..1F09F
9058 COMMON, // 1F0A0..1F0AE
9059 UNKNOWN, // 1F0AF..1F0B0
9060 COMMON, // 1F0B1..1F0BF
9061 UNKNOWN, // 1F0C0
9062 COMMON, // 1F0C1..1F0CF
9063 UNKNOWN, // 1F0D0
9064 COMMON, // 1F0D1..1F0F5
9065 UNKNOWN, // 1F0F6..1F0FF
9066 COMMON, // 1F100..1F1AD
9067 UNKNOWN, // 1F1AE..1F1E5
9068 COMMON, // 1F1E6..1F1FF
9069 HIRAGANA, // 1F200
9070 COMMON, // 1F201..1F202
9071 UNKNOWN, // 1F203..1F20F
9072 COMMON, // 1F210..1F23B
9073 UNKNOWN, // 1F23C..1F23F
9074 COMMON, // 1F240..1F248
9075 UNKNOWN, // 1F249..1F24F
9076 COMMON, // 1F250..1F251
9077 UNKNOWN, // 1F252..1F25F
9078 COMMON, // 1F260..1F265
9079 UNKNOWN, // 1F266..1F2FF
9080 COMMON, // 1F300..1F6D8
9081 UNKNOWN, // 1F6D9..1F6DB
9082 COMMON, // 1F6DC..1F6EC
9083 UNKNOWN, // 1F6ED..1F6EF
9084 COMMON, // 1F6F0..1F6FC
9085 UNKNOWN, // 1F6FD..1F6FF
9086 COMMON, // 1F700..1F7D9
9087 UNKNOWN, // 1F7DA..1F7DF
9088 COMMON, // 1F7E0..1F7EB
9089 UNKNOWN, // 1F7EC..1F7EF
9090 COMMON, // 1F7F0
9091 UNKNOWN, // 1F7F1..1F7FF
9092 COMMON, // 1F800..1F80B
9093 UNKNOWN, // 1F80C..1F80F
9094 COMMON, // 1F810..1F847
9095 UNKNOWN, // 1F848..1F84F
9096 COMMON, // 1F850..1F859
9097 UNKNOWN, // 1F85A..1F85F
9098 COMMON, // 1F860..1F887
9099 UNKNOWN, // 1F888..1F88F
9100 COMMON, // 1F890..1F8AD
9101 UNKNOWN, // 1F8AE..1F8AF
9102 COMMON, // 1F8B0..1F8BB
9103 UNKNOWN, // 1F8BC..1F8BF
9104 COMMON, // 1F8C0..1F8C1
9105 UNKNOWN, // 1F8C2..1F8CF
9106 COMMON, // 1F8D0..1F8D8
9107 UNKNOWN, // 1F8D9..1F8FF
9108 COMMON, // 1F900..1FA57
9109 UNKNOWN, // 1FA58..1FA5F
9110 COMMON, // 1FA60..1FA6D
9111 UNKNOWN, // 1FA6E..1FA6F
9112 COMMON, // 1FA70..1FA7C
9113 UNKNOWN, // 1FA7D..1FA7F
9114 COMMON, // 1FA80..1FA8A
9115 UNKNOWN, // 1FA8B..1FA8D
9116 COMMON, // 1FA8E..1FAC6
9117 UNKNOWN, // 1FAC7
9118 COMMON, // 1FAC8
9119 UNKNOWN, // 1FAC9..1FACC
9120 COMMON, // 1FACD..1FADC
9121 UNKNOWN, // 1FADD..1FADE
9122 COMMON, // 1FADF..1FAEA
9123 UNKNOWN, // 1FAEB..1FAEE
9124 COMMON, // 1FAEF..1FAF8
9125 UNKNOWN, // 1FAF9..1FAFF
9126 COMMON, // 1FB00..1FB92
9127 UNKNOWN, // 1FB93
9128 COMMON, // 1FB94..1FBFA
9129 UNKNOWN, // 1FBFB..1FFFF
9130 HAN, // 20000..2A6DF
9131 UNKNOWN, // 2A6E0..2A6FF
9132 HAN, // 2A700..2B81D
9133 UNKNOWN, // 2B81E..2B81F
9134 HAN, // 2B820..2CEAD
9135 UNKNOWN, // 2CEAE..2CEAF
9136 HAN, // 2CEB0..2EBE0
9137 UNKNOWN, // 2EBE1..2EBEF
9138 HAN, // 2EBF0..2EE5D
9139 UNKNOWN, // 2EE5E..2F7FF
9140 HAN, // 2F800..2FA1D
9141 UNKNOWN, // 2FA1E..2FFFF
9142 HAN, // 30000..3134A
9143 UNKNOWN, // 3134B..3134F
9144 HAN, // 31350..33479
9145 UNKNOWN, // 3347A..E0000
9146 COMMON, // E0001
9147 UNKNOWN, // E0002..E001F
9148 COMMON, // E0020..E007F
9149 UNKNOWN, // E0080..E00FF
9150 INHERITED, // E0100..E01EF
9151 UNKNOWN, // E01F0..10FFFF
9152 };
9153
9154 private static final HashMap<String, Character.UnicodeScript> aliases;
9155 static {
9156 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
9157 aliases.put("ADLM", ADLAM);
9158 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
9159 aliases.put("AHOM", AHOM);
9160 aliases.put("ARAB", ARABIC);
9161 aliases.put("ARMI", IMPERIAL_ARAMAIC);
9162 aliases.put("ARMN", ARMENIAN);
9163 aliases.put("AVST", AVESTAN);
9164 aliases.put("BALI", BALINESE);
9165 aliases.put("BAMU", BAMUM);
9166 aliases.put("BASS", BASSA_VAH);
9167 aliases.put("BATK", BATAK);
9168 aliases.put("BENG", BENGALI);
9169 aliases.put("BERF", BERIA_ERFE);
9170 aliases.put("BHKS", BHAIKSUKI);
9171 aliases.put("BOPO", BOPOMOFO);
9172 aliases.put("BRAH", BRAHMI);
9173 aliases.put("BRAI", BRAILLE);
9174 aliases.put("BUGI", BUGINESE);
9175 aliases.put("BUHD", BUHID);
9176 aliases.put("CAKM", CHAKMA);
9177 aliases.put("CANS", CANADIAN_ABORIGINAL);
9178 aliases.put("CARI", CARIAN);
9179 aliases.put("CHAM", CHAM);
9180 aliases.put("CHER", CHEROKEE);
9181 aliases.put("CHRS", CHORASMIAN);
9182 aliases.put("COPT", COPTIC);
9183 aliases.put("CPMN", CYPRO_MINOAN);
9184 aliases.put("CPRT", CYPRIOT);
9185 aliases.put("CYRL", CYRILLIC);
9186 aliases.put("DEVA", DEVANAGARI);
9187 aliases.put("DIAK", DIVES_AKURU);
9188 aliases.put("DOGR", DOGRA);
9189 aliases.put("DSRT", DESERET);
9190 aliases.put("DUPL", DUPLOYAN);
9191 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
9192 aliases.put("ELBA", ELBASAN);
9193 aliases.put("ELYM", ELYMAIC);
9194 aliases.put("ETHI", ETHIOPIC);
9195 aliases.put("GARA", GARAY);
9196 aliases.put("GEOR", GEORGIAN);
9197 aliases.put("GLAG", GLAGOLITIC);
9198 aliases.put("GONG", GUNJALA_GONDI);
9199 aliases.put("GONM", MASARAM_GONDI);
9200 aliases.put("GOTH", GOTHIC);
9201 aliases.put("GRAN", GRANTHA);
9202 aliases.put("GREK", GREEK);
9203 aliases.put("GUJR", GUJARATI);
9204 aliases.put("GUKH", GURUNG_KHEMA);
9205 aliases.put("GURU", GURMUKHI);
9206 aliases.put("HANG", HANGUL);
9207 aliases.put("HANI", HAN);
9208 aliases.put("HANO", HANUNOO);
9209 aliases.put("HATR", HATRAN);
9210 aliases.put("HEBR", HEBREW);
9211 aliases.put("HIRA", HIRAGANA);
9212 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
9213 aliases.put("HMNG", PAHAWH_HMONG);
9214 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
9215 aliases.put("HUNG", OLD_HUNGARIAN);
9216 aliases.put("ITAL", OLD_ITALIC);
9217 aliases.put("JAVA", JAVANESE);
9218 aliases.put("KALI", KAYAH_LI);
9219 aliases.put("KANA", KATAKANA);
9220 aliases.put("KAWI", KAWI);
9221 aliases.put("KHAR", KHAROSHTHI);
9222 aliases.put("KHMR", KHMER);
9223 aliases.put("KHOJ", KHOJKI);
9224 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
9225 aliases.put("KNDA", KANNADA);
9226 aliases.put("KRAI", KIRAT_RAI);
9227 aliases.put("KTHI", KAITHI);
9228 aliases.put("LANA", TAI_THAM);
9229 aliases.put("LAOO", LAO);
9230 aliases.put("LATN", LATIN);
9231 aliases.put("LEPC", LEPCHA);
9232 aliases.put("LIMB", LIMBU);
9233 aliases.put("LINA", LINEAR_A);
9234 aliases.put("LINB", LINEAR_B);
9235 aliases.put("LISU", LISU);
9236 aliases.put("LYCI", LYCIAN);
9237 aliases.put("LYDI", LYDIAN);
9238 aliases.put("MAHJ", MAHAJANI);
9239 aliases.put("MAKA", MAKASAR);
9240 aliases.put("MAND", MANDAIC);
9241 aliases.put("MANI", MANICHAEAN);
9242 aliases.put("MARC", MARCHEN);
9243 aliases.put("MEDF", MEDEFAIDRIN);
9244 aliases.put("MEND", MENDE_KIKAKUI);
9245 aliases.put("MERC", MEROITIC_CURSIVE);
9246 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
9247 aliases.put("MLYM", MALAYALAM);
9248 aliases.put("MODI", MODI);
9249 aliases.put("MONG", MONGOLIAN);
9250 aliases.put("MROO", MRO);
9251 aliases.put("MTEI", MEETEI_MAYEK);
9252 aliases.put("MULT", MULTANI);
9253 aliases.put("MYMR", MYANMAR);
9254 aliases.put("NAGM", NAG_MUNDARI);
9255 aliases.put("NAND", NANDINAGARI);
9256 aliases.put("NARB", OLD_NORTH_ARABIAN);
9257 aliases.put("NBAT", NABATAEAN);
9258 aliases.put("NEWA", NEWA);
9259 aliases.put("NKOO", NKO);
9260 aliases.put("NSHU", NUSHU);
9261 aliases.put("OGAM", OGHAM);
9262 aliases.put("OLCK", OL_CHIKI);
9263 aliases.put("ONAO", OL_ONAL);
9264 aliases.put("ORKH", OLD_TURKIC);
9265 aliases.put("ORYA", ORIYA);
9266 aliases.put("OSGE", OSAGE);
9267 aliases.put("OSMA", OSMANYA);
9268 aliases.put("OUGR", OLD_UYGHUR);
9269 aliases.put("PALM", PALMYRENE);
9270 aliases.put("PAUC", PAU_CIN_HAU);
9271 aliases.put("PERM", OLD_PERMIC);
9272 aliases.put("PHAG", PHAGS_PA);
9273 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
9274 aliases.put("PHLP", PSALTER_PAHLAVI);
9275 aliases.put("PHNX", PHOENICIAN);
9276 aliases.put("PLRD", MIAO);
9277 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
9278 aliases.put("RJNG", REJANG);
9279 aliases.put("ROHG", HANIFI_ROHINGYA);
9280 aliases.put("RUNR", RUNIC);
9281 aliases.put("SAMR", SAMARITAN);
9282 aliases.put("SARB", OLD_SOUTH_ARABIAN);
9283 aliases.put("SAUR", SAURASHTRA);
9284 aliases.put("SGNW", SIGNWRITING);
9285 aliases.put("SHAW", SHAVIAN);
9286 aliases.put("SHRD", SHARADA);
9287 aliases.put("SIDD", SIDDHAM);
9288 aliases.put("SIDT", SIDETIC);
9289 aliases.put("SIND", KHUDAWADI);
9290 aliases.put("SINH", SINHALA);
9291 aliases.put("SOGD", SOGDIAN);
9292 aliases.put("SOGO", OLD_SOGDIAN);
9293 aliases.put("SORA", SORA_SOMPENG);
9294 aliases.put("SOYO", SOYOMBO);
9295 aliases.put("SUND", SUNDANESE);
9296 aliases.put("SUNU", SUNUWAR);
9297 aliases.put("SYLO", SYLOTI_NAGRI);
9298 aliases.put("SYRC", SYRIAC);
9299 aliases.put("TAGB", TAGBANWA);
9300 aliases.put("TAKR", TAKRI);
9301 aliases.put("TALE", TAI_LE);
9302 aliases.put("TALU", NEW_TAI_LUE);
9303 aliases.put("TAML", TAMIL);
9304 aliases.put("TANG", TANGUT);
9305 aliases.put("TAVT", TAI_VIET);
9306 aliases.put("TAYO", TAI_YO);
9307 aliases.put("TELU", TELUGU);
9308 aliases.put("TFNG", TIFINAGH);
9309 aliases.put("TGLG", TAGALOG);
9310 aliases.put("THAA", THAANA);
9311 aliases.put("THAI", THAI);
9312 aliases.put("TIBT", TIBETAN);
9313 aliases.put("TIRH", TIRHUTA);
9314 aliases.put("TNSA", TANGSA);
9315 aliases.put("TODR", TODHRI);
9316 aliases.put("TOLS", TOLONG_SIKI);
9317 aliases.put("TOTO", TOTO);
9318 aliases.put("TUTG", TULU_TIGALARI);
9319 aliases.put("UGAR", UGARITIC);
9320 aliases.put("VAII", VAI);
9321 aliases.put("VITH", VITHKUQI);
9322 aliases.put("WARA", WARANG_CITI);
9323 aliases.put("WCHO", WANCHO);
9324 aliases.put("XPEO", OLD_PERSIAN);
9325 aliases.put("XSUX", CUNEIFORM);
9326 aliases.put("YEZI", YEZIDI);
9327 aliases.put("YIII", YI);
9328 aliases.put("ZANB", ZANABAZAR_SQUARE);
9329 aliases.put("ZINH", INHERITED);
9330 aliases.put("ZYYY", COMMON);
9331 aliases.put("ZZZZ", UNKNOWN);
9332 }
9333
9334 /**
9335 * Returns the enum constant representing the Unicode script of which
9336 * the given character (Unicode code point) is assigned to.
9337 *
9338 * @param codePoint the character (Unicode code point) in question.
9339 * @return The {@code UnicodeScript} constant representing the
9340 * Unicode script of which this character is assigned to.
9341 *
9342 * @throws IllegalArgumentException if the specified
9343 * {@code codePoint} is an invalid Unicode code point.
9344 * @see Character#isValidCodePoint(int)
9345 *
9346 */
9347 public static UnicodeScript of(int codePoint) {
9348 if (!isValidCodePoint(codePoint))
9349 throw new IllegalArgumentException(
9350 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9351 int type = getType(codePoint);
9352 // leave SURROGATE and PRIVATE_USE for table lookup
9353 if (type == UNASSIGNED)
9354 return UNKNOWN;
9355 int index = Arrays.binarySearch(scriptStarts, codePoint);
9356 if (index < 0)
9357 index = -index - 2;
9358 return scripts[index];
9359 }
9360
9361 /**
9362 * Returns the UnicodeScript constant with the given Unicode script
9363 * name or the script name alias. Script names and their aliases are
9364 * determined by The Unicode Standard. The files {@code Scripts.txt}
9365 * and {@code PropertyValueAliases.txt} define script names
9366 * and the script name aliases for a particular version of the
9367 * standard. The {@link Character} class specifies the version of
9368 * the standard that it supports.
9369 * <p>
9370 * Character case is ignored for all of the valid script names.
9371 * The en_US locale's case mapping rules are used to provide
9372 * case-insensitive string comparisons for script name validation.
9373 *
9374 * @param scriptName A {@code UnicodeScript} name.
9375 * @return The {@code UnicodeScript} constant identified
9376 * by {@code scriptName}
9377 * @throws IllegalArgumentException if {@code scriptName} is an
9378 * invalid name
9379 * @throws NullPointerException if {@code scriptName} is null
9380 */
9381 public static final UnicodeScript forName(String scriptName) {
9382 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
9383 //.replace(' ', '_'));
9384 UnicodeScript sc = aliases.get(scriptName);
9385 if (sc != null)
9386 return sc;
9387 return valueOf(scriptName);
9388 }
9389 }
9390
9391 /**
9392 * The value of the {@code Character}.
9393 *
9394 * @serial
9395 */
9396 private final char value;
9397
9398 /** use serialVersionUID from JDK 1.0.2 for interoperability */
9399 @java.io.Serial
9400 private static final long serialVersionUID = 3786198910865385080L;
9401
9402 /**
9403 * Constructs a newly allocated {@code Character} object that
9404 * represents the specified {@code char} value.
9405 *
9406 * @param value the value to be represented by the
9407 * {@code Character} object.
9408 *
9409 * @deprecated
9410 * It is rarely appropriate to use this constructor. The static factory
9411 * {@link #valueOf(char)} is generally a better choice, as it is
9412 * likely to yield significantly better space and time performance.
9413 */
9414 @Deprecated(since="9")
9415 public Character(char value) {
9416 this.value = value;
9417 }
9418
9419 @AOTSafeClassInitializer
9420 private static final class CharacterCache {
9421 private CharacterCache(){}
9422
9423 @Stable
9424 static final Character[] cache;
9425 static Character[] archivedCache;
9426
9427 static {
9428 int size = 127 + 1;
9429
9430 // Load and use the archived cache if it exists
9431 CDS.initializeFromArchive(CharacterCache.class);
9432 if (archivedCache == null) {
9433 Character[] c = new Character[size];
9434 for (int i = 0; i < size; i++) {
9435 c[i] = new Character((char) i);
9436 }
9437 archivedCache = c;
9438 }
9439 cache = archivedCache;
9440 assert cache.length == size;
9441 }
9442 }
9443
9444 /**
9445 * Returns a {@code Character} instance representing the specified
9446 * {@code char} value.
9447 * If a new {@code Character} instance is not required, this method
9448 * should generally be used in preference to the constructor
9449 * {@link #Character(char)}, as this method is likely to yield
9450 * significantly better space and time performance by caching
9451 * frequently requested values.
9452 *
9453 * This method will always cache values in the range {@code
9454 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9455 * cache other values outside of this range.
9456 *
9457 * @param c a char value.
9458 * @return a {@code Character} instance representing {@code c}.
9459 * @since 1.5
9460 */
9461 @IntrinsicCandidate
9462 public static Character valueOf(char c) {
9463 if (c <= 127) { // must cache
9464 return CharacterCache.cache[(int)c];
9465 }
9466 return new Character(c);
9467 }
9468
9469 /**
9470 * Returns the value of this {@code Character} object.
9471 * @return the primitive {@code char} value represented by
9472 * this object.
9473 */
9474 @IntrinsicCandidate
9475 public char charValue() {
9476 return value;
9477 }
9478
9479 /**
9480 * Returns a hash code for this {@code Character}; equal to the result
9481 * of invoking {@code charValue()}.
9482 *
9483 * @return a hash code value for this {@code Character}
9484 */
9485 @Override
9486 public int hashCode() {
9487 return Character.hashCode(value);
9488 }
9489
9490 /**
9491 * Returns a hash code for a {@code char} value; compatible with
9492 * {@code Character.hashCode()}.
9493 *
9494 * @since 1.8
9495 *
9496 * @param value The {@code char} for which to return a hash code.
9497 * @return a hash code value for a {@code char} value.
9498 */
9499 public static int hashCode(char value) {
9500 return (int)value;
9501 }
9502
9503 /**
9504 * Compares this object against the specified object.
9505 * The result is {@code true} if and only if the argument is not
9506 * {@code null} and is a {@code Character} object that
9507 * represents the same {@code char} value as this object.
9508 *
9509 * @param obj the object to compare with.
9510 * @return {@code true} if the objects are the same;
9511 * {@code false} otherwise.
9512 */
9513 public boolean equals(Object obj) {
9514 if (obj instanceof Character c) {
9515 return value == c.charValue();
9516 }
9517 return false;
9518 }
9519
9520 /**
9521 * Returns a {@code String} object representing this
9522 * {@code Character}'s value. The result is a string of
9523 * length 1 whose sole component is the primitive
9524 * {@code char} value represented by this
9525 * {@code Character} object.
9526 *
9527 * @return a string representation of this object.
9528 */
9529 @Override
9530 public String toString() {
9531 return String.valueOf(value);
9532 }
9533
9534 /**
9535 * Returns a {@code String} object representing the
9536 * specified {@code char}. The result is a string of length
9537 * 1 consisting solely of the specified {@code char}.
9538 *
9539 * @apiNote This method cannot handle <a
9540 * href="#supplementary"> supplementary characters</a>. To support
9541 * all Unicode characters, including supplementary characters, use
9542 * the {@link #toString(int)} method.
9543 *
9544 * @param c the {@code char} to be converted
9545 * @return the string representation of the specified {@code char}
9546 * @since 1.4
9547 */
9548 public static String toString(char c) {
9549 return String.valueOf(c);
9550 }
9551
9552 /**
9553 * Returns a {@code String} object representing the
9554 * specified character (Unicode code point). The result is a string of
9555 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9556 *
9557 * @param codePoint the {@code codePoint} to be converted
9558 * @return the string representation of the specified {@code codePoint}
9559 * @throws IllegalArgumentException if the specified
9560 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9561 * valid Unicode code point}.
9562 * @since 11
9563 */
9564 public static String toString(int codePoint) {
9565 return String.valueOfCodePoint(codePoint);
9566 }
9567
9568 /**
9569 * Determines whether the specified code point is a valid
9570 * <a href="http://www.unicode.org/glossary/#code_point">
9571 * Unicode code point value</a>.
9572 *
9573 * @param codePoint the Unicode code point to be tested
9574 * @return {@code true} if the specified code point value is between
9575 * {@link #MIN_CODE_POINT} and
9576 * {@link #MAX_CODE_POINT} inclusive;
9577 * {@code false} otherwise.
9578 * @since 1.5
9579 */
9580 public static boolean isValidCodePoint(int codePoint) {
9581 // Optimized form of:
9582 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9583 int plane = codePoint >>> 16;
9584 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9585 }
9586
9587 /**
9588 * Determines whether the specified character (Unicode code point)
9589 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9590 * Such code points can be represented using a single {@code char}.
9591 *
9592 * @param codePoint the character (Unicode code point) to be tested
9593 * @return {@code true} if the specified code point is between
9594 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9595 * {@code false} otherwise.
9596 * @since 1.7
9597 */
9598 public static boolean isBmpCodePoint(int codePoint) {
9599 return codePoint >>> 16 == 0;
9600 // Optimized form of:
9601 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9602 // We consistently use logical shift (>>>) to facilitate
9603 // additional runtime optimizations.
9604 }
9605
9606 /**
9607 * Determines whether the specified character (Unicode code point)
9608 * is in the <a href="#supplementary">supplementary character</a> range.
9609 *
9610 * @param codePoint the character (Unicode code point) to be tested
9611 * @return {@code true} if the specified code point is between
9612 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9613 * {@link #MAX_CODE_POINT} inclusive;
9614 * {@code false} otherwise.
9615 * @since 1.5
9616 */
9617 public static boolean isSupplementaryCodePoint(int codePoint) {
9618 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9619 && codePoint < MAX_CODE_POINT + 1;
9620 }
9621
9622 /**
9623 * Determines if the given {@code char} value is a
9624 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9625 * Unicode high-surrogate code unit</a>
9626 * (also known as <i>leading-surrogate code unit</i>).
9627 *
9628 * <p>Such values do not represent characters by themselves,
9629 * but are used in the representation of
9630 * <a href="#supplementary">supplementary characters</a>
9631 * in the UTF-16 encoding.
9632 *
9633 * @param ch the {@code char} value to be tested.
9634 * @return {@code true} if the {@code char} value is between
9635 * {@link #MIN_HIGH_SURROGATE} and
9636 * {@link #MAX_HIGH_SURROGATE} inclusive;
9637 * {@code false} otherwise.
9638 * @see Character#isLowSurrogate(char)
9639 * @see Character.UnicodeBlock#of(int)
9640 * @since 1.5
9641 */
9642 public static boolean isHighSurrogate(char ch) {
9643 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9644 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9645 }
9646
9647 /**
9648 * Determines if the given {@code char} value is a
9649 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9650 * Unicode low-surrogate code unit</a>
9651 * (also known as <i>trailing-surrogate code unit</i>).
9652 *
9653 * <p>Such values do not represent characters by themselves,
9654 * but are used in the representation of
9655 * <a href="#supplementary">supplementary characters</a>
9656 * in the UTF-16 encoding.
9657 *
9658 * @param ch the {@code char} value to be tested.
9659 * @return {@code true} if the {@code char} value is between
9660 * {@link #MIN_LOW_SURROGATE} and
9661 * {@link #MAX_LOW_SURROGATE} inclusive;
9662 * {@code false} otherwise.
9663 * @see Character#isHighSurrogate(char)
9664 * @since 1.5
9665 */
9666 public static boolean isLowSurrogate(char ch) {
9667 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9668 }
9669
9670 /**
9671 * Determines if the given {@code char} value is a Unicode
9672 * <i>surrogate code unit</i>.
9673 *
9674 * <p>Such values do not represent characters by themselves,
9675 * but are used in the representation of
9676 * <a href="#supplementary">supplementary characters</a>
9677 * in the UTF-16 encoding.
9678 *
9679 * <p>A char value is a surrogate code unit if and only if it is either
9680 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9681 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9682 *
9683 * @param ch the {@code char} value to be tested.
9684 * @return {@code true} if the {@code char} value is between
9685 * {@link #MIN_SURROGATE} and
9686 * {@link #MAX_SURROGATE} inclusive;
9687 * {@code false} otherwise.
9688 * @since 1.7
9689 */
9690 public static boolean isSurrogate(char ch) {
9691 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9692 }
9693
9694 /**
9695 * Determines whether the specified pair of {@code char}
9696 * values is a valid
9697 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9698 * Unicode surrogate pair</a>.
9699 *
9700 * <p>This method is equivalent to the expression:
9701 * <blockquote><pre>{@code
9702 * isHighSurrogate(high) && isLowSurrogate(low)
9703 * }</pre></blockquote>
9704 *
9705 * @param high the high-surrogate code value to be tested
9706 * @param low the low-surrogate code value to be tested
9707 * @return {@code true} if the specified high and
9708 * low-surrogate code values represent a valid surrogate pair;
9709 * {@code false} otherwise.
9710 * @since 1.5
9711 */
9712 public static boolean isSurrogatePair(char high, char low) {
9713 return isHighSurrogate(high) && isLowSurrogate(low);
9714 }
9715
9716 /**
9717 * Determines the number of {@code char} values needed to
9718 * represent the specified character (Unicode code point). If the
9719 * specified character is equal to or greater than 0x10000, then
9720 * the method returns 2. Otherwise, the method returns 1.
9721 *
9722 * <p>This method doesn't validate the specified character to be a
9723 * valid Unicode code point. The caller must validate the
9724 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9725 * if necessary.
9726 *
9727 * @param codePoint the character (Unicode code point) to be tested.
9728 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9729 * @see Character#isSupplementaryCodePoint(int)
9730 * @since 1.5
9731 */
9732 public static int charCount(int codePoint) {
9733 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9734 }
9735
9736 /**
9737 * Converts the specified surrogate pair to its supplementary code
9738 * point value. This method does not validate the specified
9739 * surrogate pair. The caller must validate it using {@link
9740 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9741 *
9742 * @param high the high-surrogate code unit
9743 * @param low the low-surrogate code unit
9744 * @return the supplementary code point composed from the
9745 * specified surrogate pair.
9746 * @since 1.5
9747 */
9748 public static int toCodePoint(char high, char low) {
9749 // Optimized form of:
9750 // return ((high - MIN_HIGH_SURROGATE) << 10)
9751 // + (low - MIN_LOW_SURROGATE)
9752 // + MIN_SUPPLEMENTARY_CODE_POINT;
9753 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9754 - (MIN_HIGH_SURROGATE << 10)
9755 - MIN_LOW_SURROGATE);
9756 }
9757
9758 /**
9759 * Returns the code point at the given index of the
9760 * {@code CharSequence}. If the {@code char} value at
9761 * the given index in the {@code CharSequence} is in the
9762 * high-surrogate range, the following index is less than the
9763 * length of the {@code CharSequence}, and the
9764 * {@code char} value at the following index is in the
9765 * low-surrogate range, then the supplementary code point
9766 * corresponding to this surrogate pair is returned. Otherwise,
9767 * the {@code char} value at the given index is returned.
9768 *
9769 * @param seq a sequence of {@code char} values (Unicode code
9770 * units)
9771 * @param index the index to the {@code char} values (Unicode
9772 * code units) in {@code seq} to be converted
9773 * @return the Unicode code point at the given index
9774 * @throws NullPointerException if {@code seq} is null.
9775 * @throws IndexOutOfBoundsException if the value
9776 * {@code index} is negative or not less than
9777 * {@link CharSequence#length() seq.length()}.
9778 * @since 1.5
9779 */
9780 public static int codePointAt(CharSequence seq, int index) {
9781 char c1 = seq.charAt(index);
9782 if (isHighSurrogate(c1) && ++index < seq.length()) {
9783 char c2 = seq.charAt(index);
9784 if (isLowSurrogate(c2)) {
9785 return toCodePoint(c1, c2);
9786 }
9787 }
9788 return c1;
9789 }
9790
9791 /**
9792 * Returns the code point at the given index of the
9793 * {@code char} array. If the {@code char} value at
9794 * the given index in the {@code char} array is in the
9795 * high-surrogate range, the following index is less than the
9796 * length of the {@code char} array, and the
9797 * {@code char} value at the following index is in the
9798 * low-surrogate range, then the supplementary code point
9799 * corresponding to this surrogate pair is returned. Otherwise,
9800 * the {@code char} value at the given index is returned.
9801 *
9802 * @param a the {@code char} array
9803 * @param index the index to the {@code char} values (Unicode
9804 * code units) in the {@code char} array to be converted
9805 * @return the Unicode code point at the given index
9806 * @throws NullPointerException if {@code a} is null.
9807 * @throws IndexOutOfBoundsException if the value
9808 * {@code index} is negative or not less than
9809 * the length of the {@code char} array.
9810 * @since 1.5
9811 */
9812 public static int codePointAt(char[] a, int index) {
9813 return codePointAtImpl(a, index, a.length);
9814 }
9815
9816 /**
9817 * Returns the code point at the given index of the
9818 * {@code char} array, where only array elements with
9819 * {@code index} less than {@code limit} can be used. If
9820 * the {@code char} value at the given index in the
9821 * {@code char} array is in the high-surrogate range, the
9822 * following index is less than the {@code limit}, and the
9823 * {@code char} value at the following index is in the
9824 * low-surrogate range, then the supplementary code point
9825 * corresponding to this surrogate pair is returned. Otherwise,
9826 * the {@code char} value at the given index is returned.
9827 *
9828 * @param a the {@code char} array
9829 * @param index the index to the {@code char} values (Unicode
9830 * code units) in the {@code char} array to be converted
9831 * @param limit the index after the last array element that
9832 * can be used in the {@code char} array
9833 * @return the Unicode code point at the given index
9834 * @throws NullPointerException if {@code a} is null.
9835 * @throws IndexOutOfBoundsException if the {@code index}
9836 * argument is negative or not less than the {@code limit}
9837 * argument, or if the {@code limit} argument is negative or
9838 * greater than the length of the {@code char} array.
9839 * @since 1.5
9840 */
9841 public static int codePointAt(char[] a, int index, int limit) {
9842 if (index >= limit || index < 0 || limit > a.length) {
9843 throw new IndexOutOfBoundsException();
9844 }
9845 return codePointAtImpl(a, index, limit);
9846 }
9847
9848 // throws ArrayIndexOutOfBoundsException if index out of bounds
9849 static int codePointAtImpl(char[] a, int index, int limit) {
9850 char c1 = a[index];
9851 if (isHighSurrogate(c1) && ++index < limit) {
9852 char c2 = a[index];
9853 if (isLowSurrogate(c2)) {
9854 return toCodePoint(c1, c2);
9855 }
9856 }
9857 return c1;
9858 }
9859
9860 /**
9861 * Returns the code point preceding the given index of the
9862 * {@code CharSequence}. If the {@code char} value at
9863 * {@code (index - 1)} in the {@code CharSequence} is in
9864 * the low-surrogate range, {@code (index - 2)} is not
9865 * negative, and the {@code char} value at {@code (index - 2)}
9866 * in the {@code CharSequence} is in the
9867 * high-surrogate range, then the supplementary code point
9868 * corresponding to this surrogate pair is returned. Otherwise,
9869 * the {@code char} value at {@code (index - 1)} is
9870 * returned.
9871 *
9872 * @param seq the {@code CharSequence} instance
9873 * @param index the index following the code point that should be returned
9874 * @return the Unicode code point value before the given index.
9875 * @throws NullPointerException if {@code seq} is null.
9876 * @throws IndexOutOfBoundsException if the {@code index}
9877 * argument is less than 1 or greater than {@link
9878 * CharSequence#length() seq.length()}.
9879 * @since 1.5
9880 */
9881 public static int codePointBefore(CharSequence seq, int index) {
9882 char c2 = seq.charAt(--index);
9883 if (isLowSurrogate(c2) && index > 0) {
9884 char c1 = seq.charAt(--index);
9885 if (isHighSurrogate(c1)) {
9886 return toCodePoint(c1, c2);
9887 }
9888 }
9889 return c2;
9890 }
9891
9892 /**
9893 * Returns the code point preceding the given index of the
9894 * {@code char} array. If the {@code char} value at
9895 * {@code (index - 1)} in the {@code char} array is in
9896 * the low-surrogate range, {@code (index - 2)} is not
9897 * negative, and the {@code char} value at {@code (index - 2)}
9898 * in the {@code char} array is in the
9899 * high-surrogate range, then the supplementary code point
9900 * corresponding to this surrogate pair is returned. Otherwise,
9901 * the {@code char} value at {@code (index - 1)} is
9902 * returned.
9903 *
9904 * @param a the {@code char} array
9905 * @param index the index following the code point that should be returned
9906 * @return the Unicode code point value before the given index.
9907 * @throws NullPointerException if {@code a} is null.
9908 * @throws IndexOutOfBoundsException if the {@code index}
9909 * argument is less than 1 or greater than the length of the
9910 * {@code char} array
9911 * @since 1.5
9912 */
9913 public static int codePointBefore(char[] a, int index) {
9914 return codePointBeforeImpl(a, index, 0);
9915 }
9916
9917 /**
9918 * Returns the code point preceding the given index of the
9919 * {@code char} array, where only array elements with
9920 * {@code index} greater than or equal to {@code start}
9921 * can be used. If the {@code char} value at {@code (index - 1)}
9922 * in the {@code char} array is in the
9923 * low-surrogate range, {@code (index - 2)} is not less than
9924 * {@code start}, and the {@code char} value at
9925 * {@code (index - 2)} in the {@code char} array is in
9926 * the high-surrogate range, then the supplementary code point
9927 * corresponding to this surrogate pair is returned. Otherwise,
9928 * the {@code char} value at {@code (index - 1)} is
9929 * returned.
9930 *
9931 * @param a the {@code char} array
9932 * @param index the index following the code point that should be returned
9933 * @param start the index of the first array element in the
9934 * {@code char} array
9935 * @return the Unicode code point value before the given index.
9936 * @throws NullPointerException if {@code a} is null.
9937 * @throws IndexOutOfBoundsException if the {@code index}
9938 * argument is not greater than the {@code start} argument or
9939 * is greater than the length of the {@code char} array, or
9940 * if the {@code start} argument is negative or not less than
9941 * the length of the {@code char} array.
9942 * @since 1.5
9943 */
9944 public static int codePointBefore(char[] a, int index, int start) {
9945 if (index <= start || start < 0 || index > a.length) {
9946 throw new IndexOutOfBoundsException();
9947 }
9948 return codePointBeforeImpl(a, index, start);
9949 }
9950
9951 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9952 static int codePointBeforeImpl(char[] a, int index, int start) {
9953 char c2 = a[--index];
9954 if (isLowSurrogate(c2) && index > start) {
9955 char c1 = a[--index];
9956 if (isHighSurrogate(c1)) {
9957 return toCodePoint(c1, c2);
9958 }
9959 }
9960 return c2;
9961 }
9962
9963 /**
9964 * Returns the leading surrogate (a
9965 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9966 * high surrogate code unit</a>) of the
9967 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9968 * surrogate pair</a>
9969 * representing the specified supplementary character (Unicode
9970 * code point) in the UTF-16 encoding. If the specified character
9971 * is not a
9972 * <a href="Character.html#supplementary">supplementary character</a>,
9973 * an unspecified {@code char} is returned.
9974 *
9975 * <p>If
9976 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9977 * is {@code true}, then
9978 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9979 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9980 * are also always {@code true}.
9981 *
9982 * @param codePoint a supplementary character (Unicode code point)
9983 * @return the leading surrogate code unit used to represent the
9984 * character in the UTF-16 encoding
9985 * @since 1.7
9986 */
9987 public static char highSurrogate(int codePoint) {
9988 return (char) ((codePoint >>> 10)
9989 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9990 }
9991
9992 /**
9993 * Returns the trailing surrogate (a
9994 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9995 * low surrogate code unit</a>) of the
9996 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9997 * surrogate pair</a>
9998 * representing the specified supplementary character (Unicode
9999 * code point) in the UTF-16 encoding. If the specified character
10000 * is not a
10001 * <a href="Character.html#supplementary">supplementary character</a>,
10002 * an unspecified {@code char} is returned.
10003 *
10004 * <p>If
10005 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
10006 * is {@code true}, then
10007 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
10008 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
10009 * are also always {@code true}.
10010 *
10011 * @param codePoint a supplementary character (Unicode code point)
10012 * @return the trailing surrogate code unit used to represent the
10013 * character in the UTF-16 encoding
10014 * @since 1.7
10015 */
10016 public static char lowSurrogate(int codePoint) {
10017 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
10018 }
10019
10020 /**
10021 * Converts the specified character (Unicode code point) to its
10022 * UTF-16 representation. If the specified code point is a BMP
10023 * (Basic Multilingual Plane or Plane 0) value, the same value is
10024 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
10025 * specified code point is a supplementary character, its
10026 * surrogate values are stored in {@code dst[dstIndex]}
10027 * (high-surrogate) and {@code dst[dstIndex+1]}
10028 * (low-surrogate), and 2 is returned.
10029 *
10030 * @param codePoint the character (Unicode code point) to be converted.
10031 * @param dst an array of {@code char} in which the
10032 * {@code codePoint}'s UTF-16 value is stored.
10033 * @param dstIndex the start index into the {@code dst}
10034 * array where the converted value is stored.
10035 * @return 1 if the code point is a BMP code point, 2 if the
10036 * code point is a supplementary code point.
10037 * @throws IllegalArgumentException if the specified
10038 * {@code codePoint} is not a valid Unicode code point.
10039 * @throws NullPointerException if the specified {@code dst} is null.
10040 * @throws IndexOutOfBoundsException if {@code dstIndex}
10041 * is negative or not less than {@code dst.length}, or if
10042 * {@code dst} at {@code dstIndex} doesn't have enough
10043 * array element(s) to store the resulting {@code char}
10044 * value(s). (If {@code dstIndex} is equal to
10045 * {@code dst.length-1} and the specified
10046 * {@code codePoint} is a supplementary character, the
10047 * high-surrogate value is not stored in
10048 * {@code dst[dstIndex]}.)
10049 * @since 1.5
10050 */
10051 public static int toChars(int codePoint, char[] dst, int dstIndex) {
10052 if (isBmpCodePoint(codePoint)) {
10053 dst[dstIndex] = (char) codePoint;
10054 return 1;
10055 } else if (isValidCodePoint(codePoint)) {
10056 toSurrogates(codePoint, dst, dstIndex);
10057 return 2;
10058 } else {
10059 throw new IllegalArgumentException(
10060 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10061 }
10062 }
10063
10064 /**
10065 * Converts the specified character (Unicode code point) to its
10066 * UTF-16 representation stored in a {@code char} array. If
10067 * the specified code point is a BMP (Basic Multilingual Plane or
10068 * Plane 0) value, the resulting {@code char} array has
10069 * the same value as {@code codePoint}. If the specified code
10070 * point is a supplementary code point, the resulting
10071 * {@code char} array has the corresponding surrogate pair.
10072 *
10073 * @param codePoint a Unicode code point
10074 * @return a {@code char} array having
10075 * {@code codePoint}'s UTF-16 representation.
10076 * @throws IllegalArgumentException if the specified
10077 * {@code codePoint} is not a valid Unicode code point.
10078 * @since 1.5
10079 */
10080 public static char[] toChars(int codePoint) {
10081 if (isBmpCodePoint(codePoint)) {
10082 return new char[] { (char) codePoint };
10083 } else if (isValidCodePoint(codePoint)) {
10084 char[] result = new char[2];
10085 toSurrogates(codePoint, result, 0);
10086 return result;
10087 } else {
10088 throw new IllegalArgumentException(
10089 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10090 }
10091 }
10092
10093 static void toSurrogates(int codePoint, char[] dst, int index) {
10094 // We write elements "backwards" to guarantee all-or-nothing
10095 dst[index+1] = lowSurrogate(codePoint);
10096 dst[index] = highSurrogate(codePoint);
10097 }
10098
10099 /**
10100 * Returns the number of Unicode code points in the text range of
10101 * the specified char sequence. The text range begins at the
10102 * specified {@code beginIndex} and extends to the
10103 * {@code char} at index {@code endIndex - 1}. Thus the
10104 * length (in {@code char}s) of the text range is
10105 * {@code endIndex-beginIndex}. Unpaired surrogates within
10106 * the text range count as one code point each.
10107 *
10108 * @param seq the char sequence
10109 * @param beginIndex the index to the first {@code char} of
10110 * the text range.
10111 * @param endIndex the index after the last {@code char} of
10112 * the text range.
10113 * @return the number of Unicode code points in the specified text
10114 * range
10115 * @throws NullPointerException if {@code seq} is null.
10116 * @throws IndexOutOfBoundsException if the
10117 * {@code beginIndex} is negative, or {@code endIndex}
10118 * is larger than the length of the given sequence, or
10119 * {@code beginIndex} is larger than {@code endIndex}.
10120 * @since 1.5
10121 */
10122 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
10123 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
10124 int n = endIndex - beginIndex;
10125 for (int i = beginIndex; i < endIndex; ) {
10126 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
10127 isLowSurrogate(seq.charAt(i))) {
10128 n--;
10129 i++;
10130 }
10131 }
10132 return n;
10133 }
10134
10135 /**
10136 * Returns the number of Unicode code points in a subarray of the
10137 * {@code char} array argument. The {@code offset}
10138 * argument is the index of the first {@code char} of the
10139 * subarray and the {@code count} argument specifies the
10140 * length of the subarray in {@code char}s. Unpaired
10141 * surrogates within the subarray count as one code point each.
10142 *
10143 * @param a the {@code char} array
10144 * @param offset the index of the first {@code char} in the
10145 * given {@code char} array
10146 * @param count the length of the subarray in {@code char}s
10147 * @return the number of Unicode code points in the specified subarray
10148 * @throws NullPointerException if {@code a} is null.
10149 * @throws IndexOutOfBoundsException if {@code offset} or
10150 * {@code count} is negative, or if {@code offset +
10151 * count} is larger than the length of the given array.
10152 * @since 1.5
10153 */
10154 public static int codePointCount(char[] a, int offset, int count) {
10155 Objects.checkFromIndexSize(offset, count, a.length);
10156 return codePointCountImpl(a, offset, count);
10157 }
10158
10159 static int codePointCountImpl(char[] a, int offset, int count) {
10160 int endIndex = offset + count;
10161 int n = count;
10162 for (int i = offset; i < endIndex; ) {
10163 if (isHighSurrogate(a[i++]) && i < endIndex &&
10164 isLowSurrogate(a[i])) {
10165 n--;
10166 i++;
10167 }
10168 }
10169 return n;
10170 }
10171
10172 /**
10173 * Returns the index within the given char sequence that is offset
10174 * from the given {@code index} by {@code codePointOffset}
10175 * code points. Unpaired surrogates within the text range given by
10176 * {@code index} and {@code codePointOffset} count as
10177 * one code point each.
10178 *
10179 * @param seq the char sequence
10180 * @param index the index to be offset
10181 * @param codePointOffset the offset in code points
10182 * @return the index within the char sequence
10183 * @throws NullPointerException if {@code seq} is null.
10184 * @throws IndexOutOfBoundsException if {@code index}
10185 * is negative or larger than the length of the char sequence,
10186 * or if {@code codePointOffset} is positive and the
10187 * subsequence starting with {@code index} has fewer than
10188 * {@code codePointOffset} code points, or if
10189 * {@code codePointOffset} is negative and the subsequence
10190 * before {@code index} has fewer than the absolute value
10191 * of {@code codePointOffset} code points.
10192 * @since 1.5
10193 */
10194 public static int offsetByCodePoints(CharSequence seq, int index,
10195 int codePointOffset) {
10196 int length = seq.length();
10197 if (index < 0 || index > length) {
10198 throw new IndexOutOfBoundsException();
10199 }
10200
10201 int x = index;
10202 if (codePointOffset >= 0) {
10203 int i;
10204 for (i = 0; x < length && i < codePointOffset; i++) {
10205 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
10206 isLowSurrogate(seq.charAt(x))) {
10207 x++;
10208 }
10209 }
10210 if (i < codePointOffset) {
10211 throw new IndexOutOfBoundsException();
10212 }
10213 } else {
10214 int i;
10215 for (i = codePointOffset; x > 0 && i < 0; i++) {
10216 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
10217 isHighSurrogate(seq.charAt(x-1))) {
10218 x--;
10219 }
10220 }
10221 if (i < 0) {
10222 throw new IndexOutOfBoundsException();
10223 }
10224 }
10225 return x;
10226 }
10227
10228 /**
10229 * Returns the index within the given {@code char} subarray
10230 * that is offset from the given {@code index} by
10231 * {@code codePointOffset} code points. The
10232 * {@code start} and {@code count} arguments specify a
10233 * subarray of the {@code char} array. Unpaired surrogates
10234 * within the text range given by {@code index} and
10235 * {@code codePointOffset} count as one code point each.
10236 *
10237 * @param a the {@code char} array
10238 * @param start the index of the first {@code char} of the
10239 * subarray
10240 * @param count the length of the subarray in {@code char}s
10241 * @param index the index to be offset
10242 * @param codePointOffset the offset in code points
10243 * @return the index within the subarray
10244 * @throws NullPointerException if {@code a} is null.
10245 * @throws IndexOutOfBoundsException
10246 * if {@code start} or {@code count} is negative,
10247 * or if {@code start + count} is larger than the length of
10248 * the given array,
10249 * or if {@code index} is less than {@code start} or
10250 * larger then {@code start + count},
10251 * or if {@code codePointOffset} is positive and the text range
10252 * starting with {@code index} and ending with {@code start + count - 1}
10253 * has fewer than {@code codePointOffset} code
10254 * points,
10255 * or if {@code codePointOffset} is negative and the text range
10256 * starting with {@code start} and ending with {@code index - 1}
10257 * has fewer than the absolute value of
10258 * {@code codePointOffset} code points.
10259 * @since 1.5
10260 */
10261 public static int offsetByCodePoints(char[] a, int start, int count,
10262 int index, int codePointOffset) {
10263 if (count > a.length-start || start < 0 || count < 0
10264 || index < start || index > start+count) {
10265 throw new IndexOutOfBoundsException();
10266 }
10267 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
10268 }
10269
10270 static int offsetByCodePointsImpl(char[]a, int start, int count,
10271 int index, int codePointOffset) {
10272 int x = index;
10273 if (codePointOffset >= 0) {
10274 int limit = start + count;
10275 int i;
10276 for (i = 0; x < limit && i < codePointOffset; i++) {
10277 if (isHighSurrogate(a[x++]) && x < limit &&
10278 isLowSurrogate(a[x])) {
10279 x++;
10280 }
10281 }
10282 if (i < codePointOffset) {
10283 throw new IndexOutOfBoundsException();
10284 }
10285 } else {
10286 int i;
10287 for (i = codePointOffset; x > start && i < 0; i++) {
10288 if (isLowSurrogate(a[--x]) && x > start &&
10289 isHighSurrogate(a[x-1])) {
10290 x--;
10291 }
10292 }
10293 if (i < 0) {
10294 throw new IndexOutOfBoundsException();
10295 }
10296 }
10297 return x;
10298 }
10299
10300 /**
10301 * Determines if the specified character is a lowercase character.
10302 * <p>
10303 * A character is lowercase if its general category type, provided
10304 * by {@code Character.getType(ch)}, is
10305 * {@code LOWERCASE_LETTER}, or it has contributory property
10306 * Other_Lowercase as defined by the Unicode Standard.
10307 * <p>
10308 * The following are examples of lowercase characters:
10309 * <blockquote><pre>
10310 * a b c d e f g h i j k l m n o p q r s t u v w x y z
10311 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10312 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10313 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10314 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10315 * </pre></blockquote>
10316 * <p> Many other Unicode characters are lowercase too.
10317 *
10318 * <p><b>Note:</b> This method cannot handle <a
10319 * href="#supplementary"> supplementary characters</a>. To support
10320 * all Unicode characters, including supplementary characters, use
10321 * the {@link #isLowerCase(int)} method.
10322 *
10323 * @param ch the character to be tested.
10324 * @return {@code true} if the character is lowercase;
10325 * {@code false} otherwise.
10326 * @see Character#isLowerCase(char)
10327 * @see Character#isTitleCase(char)
10328 * @see Character#toLowerCase(char)
10329 * @see Character#getType(char)
10330 */
10331 public static boolean isLowerCase(char ch) {
10332 return isLowerCase((int)ch);
10333 }
10334
10335 /**
10336 * Determines if the specified character (Unicode code point) is a
10337 * lowercase character.
10338 * <p>
10339 * A character is lowercase if its general category type, provided
10340 * by {@link Character#getType getType(codePoint)}, is
10341 * {@code LOWERCASE_LETTER}, or it has contributory property
10342 * Other_Lowercase as defined by the Unicode Standard.
10343 * <p>
10344 * The following are examples of lowercase characters:
10345 * <blockquote><pre>
10346 * 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
10347 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10348 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10349 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10350 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10351 * </pre></blockquote>
10352 * <p> Many other Unicode characters are lowercase too.
10353 *
10354 * @param codePoint the character (Unicode code point) to be tested.
10355 * @return {@code true} if the character is lowercase;
10356 * {@code false} otherwise.
10357 * @see Character#isLowerCase(int)
10358 * @see Character#isTitleCase(int)
10359 * @see Character#toLowerCase(int)
10360 * @see Character#getType(int)
10361 * @since 1.5
10362 */
10363 public static boolean isLowerCase(int codePoint) {
10364 return CharacterData.of(codePoint).isLowerCase(codePoint);
10365 }
10366
10367 /**
10368 * Determines if the specified character is an uppercase character.
10369 * <p>
10370 * A character is uppercase if its general category type, provided by
10371 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
10372 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10373 * <p>
10374 * The following are examples of uppercase characters:
10375 * <blockquote><pre>
10376 * 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
10377 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10378 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10379 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10380 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10381 * </pre></blockquote>
10382 * <p> Many other Unicode characters are uppercase too.
10383 *
10384 * <p><b>Note:</b> This method cannot handle <a
10385 * href="#supplementary"> supplementary characters</a>. To support
10386 * all Unicode characters, including supplementary characters, use
10387 * the {@link #isUpperCase(int)} method.
10388 *
10389 * @param ch the character to be tested.
10390 * @return {@code true} if the character is uppercase;
10391 * {@code false} otherwise.
10392 * @see Character#isLowerCase(char)
10393 * @see Character#isTitleCase(char)
10394 * @see Character#toUpperCase(char)
10395 * @see Character#getType(char)
10396 * @since 1.0
10397 */
10398 public static boolean isUpperCase(char ch) {
10399 return isUpperCase((int)ch);
10400 }
10401
10402 /**
10403 * Determines if the specified character (Unicode code point) is an uppercase character.
10404 * <p>
10405 * A character is uppercase if its general category type, provided by
10406 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
10407 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10408 * <p>
10409 * The following are examples of uppercase characters:
10410 * <blockquote><pre>
10411 * 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
10412 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10413 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10414 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10415 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10416 * </pre></blockquote>
10417 * <p> Many other Unicode characters are uppercase too.
10418 *
10419 * @param codePoint the character (Unicode code point) to be tested.
10420 * @return {@code true} if the character is uppercase;
10421 * {@code false} otherwise.
10422 * @see Character#isLowerCase(int)
10423 * @see Character#isTitleCase(int)
10424 * @see Character#toUpperCase(int)
10425 * @see Character#getType(int)
10426 * @since 1.5
10427 */
10428 public static boolean isUpperCase(int codePoint) {
10429 return CharacterData.of(codePoint).isUpperCase(codePoint);
10430 }
10431
10432 /**
10433 * Determines if the specified character is a titlecase character.
10434 * <p>
10435 * A character is a titlecase character if its general
10436 * category type, provided by {@code Character.getType(ch)},
10437 * is {@code TITLECASE_LETTER}.
10438 * <p>
10439 * Some characters look like pairs of Latin letters. For example, there
10440 * is an uppercase letter that looks like "LJ" and has a corresponding
10441 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10442 * is the appropriate form to use when rendering a word in lowercase
10443 * with initial capitals, as for a book title.
10444 * <p>
10445 * These are some of the Unicode characters for which this method returns
10446 * {@code true}:
10447 * <ul>
10448 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10449 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10450 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10451 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10452 * </ul>
10453 * <p> Many other Unicode characters are titlecase too.
10454 *
10455 * <p><b>Note:</b> This method cannot handle <a
10456 * href="#supplementary"> supplementary characters</a>. To support
10457 * all Unicode characters, including supplementary characters, use
10458 * the {@link #isTitleCase(int)} method.
10459 *
10460 * @param ch the character to be tested.
10461 * @return {@code true} if the character is titlecase;
10462 * {@code false} otherwise.
10463 * @see Character#isLowerCase(char)
10464 * @see Character#isUpperCase(char)
10465 * @see Character#toTitleCase(char)
10466 * @see Character#getType(char)
10467 * @since 1.0.2
10468 */
10469 public static boolean isTitleCase(char ch) {
10470 return isTitleCase((int)ch);
10471 }
10472
10473 /**
10474 * Determines if the specified character (Unicode code point) is a titlecase character.
10475 * <p>
10476 * A character is a titlecase character if its general
10477 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10478 * is {@code TITLECASE_LETTER}.
10479 * <p>
10480 * Some characters look like pairs of Latin letters. For example, there
10481 * is an uppercase letter that looks like "LJ" and has a corresponding
10482 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10483 * is the appropriate form to use when rendering a word in lowercase
10484 * with initial capitals, as for a book title.
10485 * <p>
10486 * These are some of the Unicode characters for which this method returns
10487 * {@code true}:
10488 * <ul>
10489 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10490 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10491 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10492 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10493 * </ul>
10494 * <p> Many other Unicode characters are titlecase too.
10495 *
10496 * @param codePoint the character (Unicode code point) to be tested.
10497 * @return {@code true} if the character is titlecase;
10498 * {@code false} otherwise.
10499 * @see Character#isLowerCase(int)
10500 * @see Character#isUpperCase(int)
10501 * @see Character#toTitleCase(int)
10502 * @see Character#getType(int)
10503 * @since 1.5
10504 */
10505 public static boolean isTitleCase(int codePoint) {
10506 return getType(codePoint) == Character.TITLECASE_LETTER;
10507 }
10508
10509 /**
10510 * Determines if the specified character is a digit.
10511 * <p>
10512 * A character is a digit if its general category type, provided
10513 * by {@code Character.getType(ch)}, is
10514 * {@code DECIMAL_DIGIT_NUMBER}.
10515 * <p>
10516 * Some Unicode character ranges that contain digits:
10517 * <ul>
10518 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10519 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10520 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10521 * Arabic-Indic digits
10522 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10523 * Extended Arabic-Indic digits
10524 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10525 * Devanagari digits
10526 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10527 * Fullwidth digits
10528 * </ul>
10529 *
10530 * Many other character ranges contain digits as well.
10531 *
10532 * <p><b>Note:</b> This method cannot handle <a
10533 * href="#supplementary"> supplementary characters</a>. To support
10534 * all Unicode characters, including supplementary characters, use
10535 * the {@link #isDigit(int)} method.
10536 *
10537 * @param ch the character to be tested.
10538 * @return {@code true} if the character is a digit;
10539 * {@code false} otherwise.
10540 * @see Character#digit(char, int)
10541 * @see Character#forDigit(int, int)
10542 * @see Character#getType(char)
10543 */
10544 public static boolean isDigit(char ch) {
10545 return isDigit((int)ch);
10546 }
10547
10548 /**
10549 * Determines if the specified character (Unicode code point) is a digit.
10550 * <p>
10551 * A character is a digit if its general category type, provided
10552 * by {@link Character#getType(int) getType(codePoint)}, is
10553 * {@code DECIMAL_DIGIT_NUMBER}.
10554 * <p>
10555 * Some Unicode character ranges that contain digits:
10556 * <ul>
10557 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10558 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10559 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10560 * Arabic-Indic digits
10561 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10562 * Extended Arabic-Indic digits
10563 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10564 * Devanagari digits
10565 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10566 * Fullwidth digits
10567 * </ul>
10568 *
10569 * Many other character ranges contain digits as well.
10570 *
10571 * @param codePoint the character (Unicode code point) to be tested.
10572 * @return {@code true} if the character is a digit;
10573 * {@code false} otherwise.
10574 * @see Character#forDigit(int, int)
10575 * @see Character#getType(int)
10576 * @since 1.5
10577 */
10578 public static boolean isDigit(int codePoint) {
10579 return CharacterData.of(codePoint).isDigit(codePoint);
10580 }
10581
10582 /**
10583 * Determines if a character is defined in Unicode.
10584 * <p>
10585 * A character is defined if at least one of the following is true:
10586 * <ul>
10587 * <li>It has an entry in the UnicodeData file.
10588 * <li>It has a value in a range defined by the UnicodeData file.
10589 * </ul>
10590 *
10591 * <p><b>Note:</b> This method cannot handle <a
10592 * href="#supplementary"> supplementary characters</a>. To support
10593 * all Unicode characters, including supplementary characters, use
10594 * the {@link #isDefined(int)} method.
10595 *
10596 * @param ch the character to be tested
10597 * @return {@code true} if the character has a defined meaning
10598 * in Unicode; {@code false} otherwise.
10599 * @see Character#isDigit(char)
10600 * @see Character#isLetter(char)
10601 * @see Character#isLetterOrDigit(char)
10602 * @see Character#isLowerCase(char)
10603 * @see Character#isTitleCase(char)
10604 * @see Character#isUpperCase(char)
10605 * @since 1.0.2
10606 */
10607 public static boolean isDefined(char ch) {
10608 return isDefined((int)ch);
10609 }
10610
10611 /**
10612 * Determines if a character (Unicode code point) is defined in Unicode.
10613 * <p>
10614 * A character is defined if at least one of the following is true:
10615 * <ul>
10616 * <li>It has an entry in the UnicodeData file.
10617 * <li>It has a value in a range defined by the UnicodeData file.
10618 * </ul>
10619 *
10620 * @param codePoint the character (Unicode code point) to be tested.
10621 * @return {@code true} if the character has a defined meaning
10622 * in Unicode; {@code false} otherwise.
10623 * @see Character#isDigit(int)
10624 * @see Character#isLetter(int)
10625 * @see Character#isLetterOrDigit(int)
10626 * @see Character#isLowerCase(int)
10627 * @see Character#isTitleCase(int)
10628 * @see Character#isUpperCase(int)
10629 * @since 1.5
10630 */
10631 public static boolean isDefined(int codePoint) {
10632 return getType(codePoint) != Character.UNASSIGNED;
10633 }
10634
10635 /**
10636 * Determines if the specified character is a letter.
10637 * <p>
10638 * A character is considered to be a letter if its general
10639 * category type, provided by {@code Character.getType(ch)},
10640 * is any of the following:
10641 * <ul>
10642 * <li> {@code UPPERCASE_LETTER}
10643 * <li> {@code LOWERCASE_LETTER}
10644 * <li> {@code TITLECASE_LETTER}
10645 * <li> {@code MODIFIER_LETTER}
10646 * <li> {@code OTHER_LETTER}
10647 * </ul>
10648 *
10649 * Not all letters have case. Many characters are
10650 * letters but are neither uppercase nor lowercase nor titlecase.
10651 *
10652 * <p><b>Note:</b> This method cannot handle <a
10653 * href="#supplementary"> supplementary characters</a>. To support
10654 * all Unicode characters, including supplementary characters, use
10655 * the {@link #isLetter(int)} method.
10656 *
10657 * @param ch the character to be tested.
10658 * @return {@code true} if the character is a letter;
10659 * {@code false} otherwise.
10660 * @see Character#isDigit(char)
10661 * @see Character#isJavaIdentifierStart(char)
10662 * @see Character#isJavaLetter(char)
10663 * @see Character#isJavaLetterOrDigit(char)
10664 * @see Character#isLetterOrDigit(char)
10665 * @see Character#isLowerCase(char)
10666 * @see Character#isTitleCase(char)
10667 * @see Character#isUnicodeIdentifierStart(char)
10668 * @see Character#isUpperCase(char)
10669 */
10670 public static boolean isLetter(char ch) {
10671 return isLetter((int)ch);
10672 }
10673
10674 /**
10675 * Determines if the specified character (Unicode code point) is a letter.
10676 * <p>
10677 * A character is considered to be a letter if its general
10678 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10679 * is any of the following:
10680 * <ul>
10681 * <li> {@code UPPERCASE_LETTER}
10682 * <li> {@code LOWERCASE_LETTER}
10683 * <li> {@code TITLECASE_LETTER}
10684 * <li> {@code MODIFIER_LETTER}
10685 * <li> {@code OTHER_LETTER}
10686 * </ul>
10687 *
10688 * Not all letters have case. Many characters are
10689 * letters but are neither uppercase nor lowercase nor titlecase.
10690 *
10691 * @param codePoint the character (Unicode code point) to be tested.
10692 * @return {@code true} if the character is a letter;
10693 * {@code false} otherwise.
10694 * @see Character#isDigit(int)
10695 * @see Character#isJavaIdentifierStart(int)
10696 * @see Character#isLetterOrDigit(int)
10697 * @see Character#isLowerCase(int)
10698 * @see Character#isTitleCase(int)
10699 * @see Character#isUnicodeIdentifierStart(int)
10700 * @see Character#isUpperCase(int)
10701 * @since 1.5
10702 */
10703 public static boolean isLetter(int codePoint) {
10704 return ((((1 << Character.UPPERCASE_LETTER) |
10705 (1 << Character.LOWERCASE_LETTER) |
10706 (1 << Character.TITLECASE_LETTER) |
10707 (1 << Character.MODIFIER_LETTER) |
10708 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10709 != 0;
10710 }
10711
10712 /**
10713 * Determines if the specified character is a letter or digit.
10714 * <p>
10715 * A character is considered to be a letter or digit if either
10716 * {@code Character.isLetter(char ch)} or
10717 * {@code Character.isDigit(char ch)} returns
10718 * {@code true} for the character.
10719 *
10720 * <p><b>Note:</b> This method cannot handle <a
10721 * href="#supplementary"> supplementary characters</a>. To support
10722 * all Unicode characters, including supplementary characters, use
10723 * the {@link #isLetterOrDigit(int)} method.
10724 *
10725 * @param ch the character to be tested.
10726 * @return {@code true} if the character is a letter or digit;
10727 * {@code false} otherwise.
10728 * @see Character#isDigit(char)
10729 * @see Character#isJavaIdentifierPart(char)
10730 * @see Character#isJavaLetter(char)
10731 * @see Character#isJavaLetterOrDigit(char)
10732 * @see Character#isLetter(char)
10733 * @see Character#isUnicodeIdentifierPart(char)
10734 * @since 1.0.2
10735 */
10736 public static boolean isLetterOrDigit(char ch) {
10737 return isLetterOrDigit((int)ch);
10738 }
10739
10740 /**
10741 * Determines if the specified character (Unicode code point) is a letter or digit.
10742 * <p>
10743 * A character is considered to be a letter or digit if either
10744 * {@link #isLetter(int) isLetter(codePoint)} or
10745 * {@link #isDigit(int) isDigit(codePoint)} returns
10746 * {@code true} for the character.
10747 *
10748 * @param codePoint the character (Unicode code point) to be tested.
10749 * @return {@code true} if the character is a letter or digit;
10750 * {@code false} otherwise.
10751 * @see Character#isDigit(int)
10752 * @see Character#isJavaIdentifierPart(int)
10753 * @see Character#isLetter(int)
10754 * @see Character#isUnicodeIdentifierPart(int)
10755 * @since 1.5
10756 */
10757 public static boolean isLetterOrDigit(int codePoint) {
10758 return ((((1 << Character.UPPERCASE_LETTER) |
10759 (1 << Character.LOWERCASE_LETTER) |
10760 (1 << Character.TITLECASE_LETTER) |
10761 (1 << Character.MODIFIER_LETTER) |
10762 (1 << Character.OTHER_LETTER) |
10763 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10764 != 0;
10765 }
10766
10767 /**
10768 * Determines if the specified character is permissible as the first
10769 * character in a Java identifier.
10770 * <p>
10771 * A character may start a Java identifier if and only if
10772 * one of the following conditions is true:
10773 * <ul>
10774 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10775 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10776 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10777 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10778 * </ul>
10779 *
10780 * @param ch the character to be tested.
10781 * @return {@code true} if the character may start a Java
10782 * identifier; {@code false} otherwise.
10783 * @see Character#isJavaLetterOrDigit(char)
10784 * @see Character#isJavaIdentifierStart(char)
10785 * @see Character#isJavaIdentifierPart(char)
10786 * @see Character#isLetter(char)
10787 * @see Character#isLetterOrDigit(char)
10788 * @see Character#isUnicodeIdentifierStart(char)
10789 * @since 1.0.2
10790 * @deprecated Replaced by isJavaIdentifierStart(char).
10791 */
10792 @Deprecated(since="1.1")
10793 public static boolean isJavaLetter(char ch) {
10794 return isJavaIdentifierStart(ch);
10795 }
10796
10797 /**
10798 * Determines if the specified character may be part of a Java
10799 * identifier as other than the first character.
10800 * <p>
10801 * A character may be part of a Java identifier if and only if one
10802 * of the following conditions is true:
10803 * <ul>
10804 * <li> it is a letter
10805 * <li> it is a currency symbol (such as {@code '$'})
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> {@code isIdentifierIgnorable} returns
10812 * {@code true} for the character.
10813 * </ul>
10814 *
10815 * @param ch the character to be tested.
10816 * @return {@code true} if the character may be part of a
10817 * Java identifier; {@code false} otherwise.
10818 * @see Character#isJavaLetter(char)
10819 * @see Character#isJavaIdentifierStart(char)
10820 * @see Character#isJavaIdentifierPart(char)
10821 * @see Character#isLetter(char)
10822 * @see Character#isLetterOrDigit(char)
10823 * @see Character#isUnicodeIdentifierPart(char)
10824 * @see Character#isIdentifierIgnorable(char)
10825 * @since 1.0.2
10826 * @deprecated Replaced by isJavaIdentifierPart(char).
10827 */
10828 @Deprecated(since="1.1")
10829 public static boolean isJavaLetterOrDigit(char ch) {
10830 return isJavaIdentifierPart(ch);
10831 }
10832
10833 /**
10834 * Determines if the specified character (Unicode code point) is alphabetic.
10835 * <p>
10836 * A character is considered to be alphabetic if its general category type,
10837 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10838 * the following:
10839 * <ul>
10840 * <li> {@code UPPERCASE_LETTER}
10841 * <li> {@code LOWERCASE_LETTER}
10842 * <li> {@code TITLECASE_LETTER}
10843 * <li> {@code MODIFIER_LETTER}
10844 * <li> {@code OTHER_LETTER}
10845 * <li> {@code LETTER_NUMBER}
10846 * </ul>
10847 * or it has contributory property Other_Alphabetic as defined by the
10848 * Unicode Standard.
10849 *
10850 * @param codePoint the character (Unicode code point) to be tested.
10851 * @return {@code true} if the character is a Unicode alphabet
10852 * character, {@code false} otherwise.
10853 * @since 1.7
10854 */
10855 public static boolean isAlphabetic(int codePoint) {
10856 return (((((1 << Character.UPPERCASE_LETTER) |
10857 (1 << Character.LOWERCASE_LETTER) |
10858 (1 << Character.TITLECASE_LETTER) |
10859 (1 << Character.MODIFIER_LETTER) |
10860 (1 << Character.OTHER_LETTER) |
10861 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10862 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10863 }
10864
10865 /**
10866 * Determines if the specified character (Unicode code point) is a CJKV
10867 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10868 * the Unicode Standard.
10869 *
10870 * @param codePoint the character (Unicode code point) to be tested.
10871 * @return {@code true} if the character is a Unicode ideograph
10872 * character, {@code false} otherwise.
10873 * @since 1.7
10874 */
10875 public static boolean isIdeographic(int codePoint) {
10876 return CharacterData.of(codePoint).isIdeographic(codePoint);
10877 }
10878
10879 /**
10880 * Determines if the specified character is
10881 * permissible as the first character in a Java identifier.
10882 * <p>
10883 * A character may start a Java identifier if and only if
10884 * one of the following conditions is true:
10885 * <ul>
10886 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10887 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10888 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10889 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10890 * </ul>
10891 *
10892 * <p><b>Note:</b> This method cannot handle <a
10893 * href="#supplementary"> supplementary characters</a>. To support
10894 * all Unicode characters, including supplementary characters, use
10895 * the {@link #isJavaIdentifierStart(int)} method.
10896 *
10897 * @param ch the character to be tested.
10898 * @return {@code true} if the character may start a Java identifier;
10899 * {@code false} otherwise.
10900 * @see Character#isJavaIdentifierPart(char)
10901 * @see Character#isLetter(char)
10902 * @see Character#isUnicodeIdentifierStart(char)
10903 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10904 * @since 1.1
10905 */
10906 @SuppressWarnings("doclint:reference") // cross-module links
10907 public static boolean isJavaIdentifierStart(char ch) {
10908 return isJavaIdentifierStart((int)ch);
10909 }
10910
10911 /**
10912 * Determines if the character (Unicode code point) is
10913 * permissible as the first character in a Java identifier.
10914 * <p>
10915 * A character may start a Java identifier if and only if
10916 * one of the following conditions is true:
10917 * <ul>
10918 * <li> {@link #isLetter(int) isLetter(codePoint)}
10919 * returns {@code true}
10920 * <li> {@link #getType(int) getType(codePoint)}
10921 * returns {@code LETTER_NUMBER}
10922 * <li> the referenced character is a currency symbol (such as {@code '$'})
10923 * <li> the referenced character is a connecting punctuation character
10924 * (such as {@code '_'}).
10925 * </ul>
10926 *
10927 * @param codePoint the character (Unicode code point) to be tested.
10928 * @return {@code true} if the character may start a Java identifier;
10929 * {@code false} otherwise.
10930 * @see Character#isJavaIdentifierPart(int)
10931 * @see Character#isLetter(int)
10932 * @see Character#isUnicodeIdentifierStart(int)
10933 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10934 * @since 1.5
10935 */
10936 @SuppressWarnings("doclint:reference") // cross-module links
10937 public static boolean isJavaIdentifierStart(int codePoint) {
10938 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10939 }
10940
10941 /**
10942 * Determines if the specified character may be part of a Java
10943 * identifier as other than the first character.
10944 * <p>
10945 * A character may be part of a Java identifier if any of the following
10946 * conditions are true:
10947 * <ul>
10948 * <li> it is a letter
10949 * <li> it is a currency symbol (such as {@code '$'})
10950 * <li> it is a connecting punctuation character (such as {@code '_'})
10951 * <li> it is a digit
10952 * <li> it is a numeric letter (such as a Roman numeral character)
10953 * <li> it is a combining mark
10954 * <li> it is a non-spacing mark
10955 * <li> {@code isIdentifierIgnorable} returns
10956 * {@code true} for the character
10957 * </ul>
10958 *
10959 * <p><b>Note:</b> This method cannot handle <a
10960 * href="#supplementary"> supplementary characters</a>. To support
10961 * all Unicode characters, including supplementary characters, use
10962 * the {@link #isJavaIdentifierPart(int)} method.
10963 *
10964 * @param ch the character to be tested.
10965 * @return {@code true} if the character may be part of a
10966 * Java identifier; {@code false} otherwise.
10967 * @see Character#isIdentifierIgnorable(char)
10968 * @see Character#isJavaIdentifierStart(char)
10969 * @see Character#isLetterOrDigit(char)
10970 * @see Character#isUnicodeIdentifierPart(char)
10971 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10972 * @since 1.1
10973 */
10974 @SuppressWarnings("doclint:reference") // cross-module links
10975 public static boolean isJavaIdentifierPart(char ch) {
10976 return isJavaIdentifierPart((int)ch);
10977 }
10978
10979 /**
10980 * Determines if the character (Unicode code point) may be part of a Java
10981 * identifier as other than the first character.
10982 * <p>
10983 * A character may be part of a Java identifier if any of the following
10984 * conditions are true:
10985 * <ul>
10986 * <li> it is a letter
10987 * <li> it is a currency symbol (such as {@code '$'})
10988 * <li> it is a connecting punctuation character (such as {@code '_'})
10989 * <li> it is a digit
10990 * <li> it is a numeric letter (such as a Roman numeral character)
10991 * <li> it is a combining mark
10992 * <li> it is a non-spacing mark
10993 * <li> {@link #isIdentifierIgnorable(int)
10994 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10995 * the code point
10996 * </ul>
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 * Java identifier; {@code false} otherwise.
11001 * @see Character#isIdentifierIgnorable(int)
11002 * @see Character#isJavaIdentifierStart(int)
11003 * @see Character#isLetterOrDigit(int)
11004 * @see Character#isUnicodeIdentifierPart(int)
11005 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
11006 * @since 1.5
11007 */
11008 @SuppressWarnings("doclint:reference") // cross-module links
11009 public static boolean isJavaIdentifierPart(int codePoint) {
11010 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
11011 }
11012
11013 /**
11014 * Determines if the specified character is permissible as the
11015 * first character in a Unicode identifier.
11016 * <p>
11017 * A character may start a Unicode identifier if and only if
11018 * one of the following conditions is true:
11019 * <ul>
11020 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
11021 * <li> {@link #getType(char) getType(ch)} returns
11022 * {@code LETTER_NUMBER}.
11023 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11024 * {@code Other_ID_Start}</a> character.
11025 * </ul>
11026 * <p>
11027 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11028 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11029 * with the following profile of UAX31:
11030 * <pre>
11031 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
11032 * </pre>
11033 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
11034 * compatibility.
11035 *
11036 * <p><b>Note:</b> This method cannot handle <a
11037 * href="#supplementary"> supplementary characters</a>. To support
11038 * all Unicode characters, including supplementary characters, use
11039 * the {@link #isUnicodeIdentifierStart(int)} method.
11040 *
11041 * @param ch the character to be tested.
11042 * @return {@code true} if the character may start a Unicode
11043 * identifier; {@code false} otherwise.
11044 *
11045 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11046 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11047 * @see Character#isJavaIdentifierStart(char)
11048 * @see Character#isLetter(char)
11049 * @see Character#isUnicodeIdentifierPart(char)
11050 * @since 1.1
11051 */
11052 public static boolean isUnicodeIdentifierStart(char ch) {
11053 return isUnicodeIdentifierStart((int)ch);
11054 }
11055
11056 /**
11057 * Determines if the specified character (Unicode code point) is permissible as the
11058 * first character in a Unicode identifier.
11059 * <p>
11060 * A character may start a Unicode identifier if and only if
11061 * one of the following conditions is true:
11062 * <ul>
11063 * <li> {@link #isLetter(int) isLetter(codePoint)}
11064 * returns {@code true}
11065 * <li> {@link #getType(int) getType(codePoint)}
11066 * returns {@code LETTER_NUMBER}.
11067 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11068 * {@code Other_ID_Start}</a> character.
11069 * </ul>
11070 * <p>
11071 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11072 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11073 * with the following profile of UAX31:
11074 * <pre>
11075 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
11076 * </pre>
11077 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
11078 * compatibility.
11079 *
11080 * @param codePoint the character (Unicode code point) to be tested.
11081 * @return {@code true} if the character may start a Unicode
11082 * identifier; {@code false} otherwise.
11083 *
11084 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11085 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11086 * @see Character#isJavaIdentifierStart(int)
11087 * @see Character#isLetter(int)
11088 * @see Character#isUnicodeIdentifierPart(int)
11089 * @since 1.5
11090 */
11091 public static boolean isUnicodeIdentifierStart(int codePoint) {
11092 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
11093 }
11094
11095 /**
11096 * Determines if the specified character may be part of a Unicode
11097 * identifier as other than the first character.
11098 * <p>
11099 * A character may be part of a Unicode identifier if and only if
11100 * one of the following statements is true:
11101 * <ul>
11102 * <li> it is a letter
11103 * <li> it is a connecting punctuation character (such as {@code '_'})
11104 * <li> it is a digit
11105 * <li> it is a numeric letter (such as a Roman numeral character)
11106 * <li> it is a combining mark
11107 * <li> it is a non-spacing mark
11108 * <li> {@code isIdentifierIgnorable} returns
11109 * {@code true} for this character.
11110 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11111 * {@code Other_ID_Start}</a> character.
11112 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
11113 * {@code Other_ID_Continue}</a> character.
11114 * </ul>
11115 * <p>
11116 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11117 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11118 * with the following profile of UAX31:
11119 * <pre>
11120 * Continue := Start + ID_Continue + ignorable
11121 * Medial := empty
11122 * ignorable := isIdentifierIgnorable(char) returns true for the character
11123 * </pre>
11124 * {@code ignorable} is added to {@code Continue} for backward
11125 * compatibility.
11126 *
11127 * <p><b>Note:</b> This method cannot handle <a
11128 * href="#supplementary"> supplementary characters</a>. To support
11129 * all Unicode characters, including supplementary characters, use
11130 * the {@link #isUnicodeIdentifierPart(int)} method.
11131 *
11132 * @param ch the character to be tested.
11133 * @return {@code true} if the character may be part of a
11134 * Unicode identifier; {@code false} otherwise.
11135 *
11136 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11137 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11138 * @see Character#isIdentifierIgnorable(char)
11139 * @see Character#isJavaIdentifierPart(char)
11140 * @see Character#isLetterOrDigit(char)
11141 * @see Character#isUnicodeIdentifierStart(char)
11142 * @since 1.1
11143 */
11144 public static boolean isUnicodeIdentifierPart(char ch) {
11145 return isUnicodeIdentifierPart((int)ch);
11146 }
11147
11148 /**
11149 * Determines if the specified character (Unicode code point) may be part of a Unicode
11150 * identifier as other than the first character.
11151 * <p>
11152 * A character may be part of a Unicode identifier if and only if
11153 * one of the following statements is true:
11154 * <ul>
11155 * <li> it is a letter
11156 * <li> it is a connecting punctuation character (such as {@code '_'})
11157 * <li> it is a digit
11158 * <li> it is a numeric letter (such as a Roman numeral character)
11159 * <li> it is a combining mark
11160 * <li> it is a non-spacing mark
11161 * <li> {@code isIdentifierIgnorable} returns
11162 * {@code true} for this character.
11163 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
11164 * {@code Other_ID_Start}</a> character.
11165 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
11166 * {@code Other_ID_Continue}</a> character.
11167 * </ul>
11168 * <p>
11169 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11170 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11171 * with the following profile of UAX31:
11172 * <pre>
11173 * Continue := Start + ID_Continue + ignorable
11174 * Medial := empty
11175 * ignorable := isIdentifierIgnorable(int) returns true for the character
11176 * </pre>
11177 * {@code ignorable} is added to {@code Continue} for backward
11178 * compatibility.
11179 *
11180 * @param codePoint the character (Unicode code point) to be tested.
11181 * @return {@code true} if the character may be part of a
11182 * Unicode identifier; {@code false} otherwise.
11183 *
11184 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11185 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11186 * @see Character#isIdentifierIgnorable(int)
11187 * @see Character#isJavaIdentifierPart(int)
11188 * @see Character#isLetterOrDigit(int)
11189 * @see Character#isUnicodeIdentifierStart(int)
11190 * @since 1.5
11191 */
11192 public static boolean isUnicodeIdentifierPart(int codePoint) {
11193 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
11194 }
11195
11196 /**
11197 * Determines if the specified character should be regarded as
11198 * an ignorable character in a Java identifier or a Unicode identifier.
11199 * <p>
11200 * The following Unicode characters are ignorable in a Java identifier
11201 * or a Unicode identifier:
11202 * <ul>
11203 * <li>ISO control characters that are not whitespace
11204 * <ul>
11205 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11206 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11207 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11208 * </ul>
11209 *
11210 * <li>all characters that have the {@code FORMAT} general
11211 * category value
11212 * </ul>
11213 *
11214 * <p><b>Note:</b> This method cannot handle <a
11215 * href="#supplementary"> supplementary characters</a>. To support
11216 * all Unicode characters, including supplementary characters, use
11217 * the {@link #isIdentifierIgnorable(int)} method.
11218 *
11219 * @param ch the character to be tested.
11220 * @return {@code true} if the character is an ignorable control
11221 * character that may be part of a Java or Unicode identifier;
11222 * {@code false} otherwise.
11223 * @see Character#isJavaIdentifierPart(char)
11224 * @see Character#isUnicodeIdentifierPart(char)
11225 * @since 1.1
11226 */
11227 public static boolean isIdentifierIgnorable(char ch) {
11228 return isIdentifierIgnorable((int)ch);
11229 }
11230
11231 /**
11232 * Determines if the specified character (Unicode code point) should be regarded as
11233 * an ignorable character in a Java identifier or a Unicode identifier.
11234 * <p>
11235 * The following Unicode characters are ignorable in a Java identifier
11236 * or a Unicode identifier:
11237 * <ul>
11238 * <li>ISO control characters that are not whitespace
11239 * <ul>
11240 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11241 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11242 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11243 * </ul>
11244 *
11245 * <li>all characters that have the {@code FORMAT} general
11246 * category value
11247 * </ul>
11248 *
11249 * @param codePoint the character (Unicode code point) to be tested.
11250 * @return {@code true} if the character is an ignorable control
11251 * character that may be part of a Java or Unicode identifier;
11252 * {@code false} otherwise.
11253 * @see Character#isJavaIdentifierPart(int)
11254 * @see Character#isUnicodeIdentifierPart(int)
11255 * @since 1.5
11256 */
11257 public static boolean isIdentifierIgnorable(int codePoint) {
11258 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
11259 }
11260
11261 /**
11262 * Determines if the specified character (Unicode code point) is an Emoji.
11263 * <p>
11264 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
11265 * property, defined in
11266 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11267 * Unicode Emoji (Technical Standard #51)</a>.
11268 *
11269 * @param codePoint the character (Unicode code point) to be tested.
11270 * @return {@code true} if the character is an Emoji;
11271 * {@code false} otherwise.
11272 * @spec https://www.unicode.org/reports/tr51/ Unicode Emoji
11273 * @since 21
11274 */
11275 public static boolean isEmoji(int codePoint) {
11276 return CharacterData.of(codePoint).isEmoji(codePoint);
11277 }
11278
11279 /**
11280 * Determines if the specified character (Unicode code point) has the
11281 * Emoji Presentation property by default.
11282 * <p>
11283 * A character is considered to have the Emoji Presentation property if and
11284 * only if it has the {@code Emoji_Presentation} property, defined in
11285 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11286 * Unicode Emoji (Technical Standard #51)</a>.
11287 *
11288 * @param codePoint the character (Unicode code point) to be tested.
11289 * @return {@code true} if the character has the Emoji Presentation
11290 * property; {@code false} otherwise.
11291 * @spec https://www.unicode.org/reports/tr51/ Unicode Emoji
11292 * @since 21
11293 */
11294 public static boolean isEmojiPresentation(int codePoint) {
11295 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
11296 }
11297
11298 /**
11299 * Determines if the specified character (Unicode code point) is an
11300 * Emoji Modifier.
11301 * <p>
11302 * A character is considered to be an Emoji Modifier if and only if it has
11303 * the {@code Emoji_Modifier} property, defined in
11304 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11305 * Unicode Emoji (Technical Standard #51)</a>.
11306 *
11307 * @param codePoint the character (Unicode code point) to be tested.
11308 * @return {@code true} if the character is an Emoji Modifier;
11309 * {@code false} otherwise.
11310 * @spec https://www.unicode.org/reports/tr51/ Unicode Emoji
11311 * @since 21
11312 */
11313 public static boolean isEmojiModifier(int codePoint) {
11314 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
11315 }
11316
11317 /**
11318 * Determines if the specified character (Unicode code point) is an
11319 * Emoji Modifier Base.
11320 * <p>
11321 * A character is considered to be an Emoji Modifier Base if and only if it has
11322 * the {@code Emoji_Modifier_Base} property, defined in
11323 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11324 * Unicode Emoji (Technical Standard #51)</a>.
11325 *
11326 * @param codePoint the character (Unicode code point) to be tested.
11327 * @return {@code true} if the character is an Emoji Modifier Base;
11328 * {@code false} otherwise.
11329 * @spec https://www.unicode.org/reports/tr51/ Unicode Emoji
11330 * @since 21
11331 */
11332 public static boolean isEmojiModifierBase(int codePoint) {
11333 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
11334 }
11335
11336 /**
11337 * Determines if the specified character (Unicode code point) is an
11338 * Emoji Component.
11339 * <p>
11340 * A character is considered to be an Emoji Component if and only if it has
11341 * the {@code Emoji_Component} property, defined in
11342 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11343 * Unicode Emoji (Technical Standard #51)</a>.
11344 *
11345 * @param codePoint the character (Unicode code point) to be tested.
11346 * @return {@code true} if the character is an Emoji Component;
11347 * {@code false} otherwise.
11348 * @spec https://www.unicode.org/reports/tr51/ Unicode Emoji
11349 * @since 21
11350 */
11351 public static boolean isEmojiComponent(int codePoint) {
11352 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
11353 }
11354
11355 /**
11356 * Determines if the specified character (Unicode code point) is
11357 * an Extended Pictographic.
11358 * <p>
11359 * A character is considered to be an Extended Pictographic if and only if it has
11360 * the {@code Extended_Pictographic} property, defined in
11361 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11362 * Unicode Emoji (Technical Standard #51)</a>.
11363 *
11364 * @param codePoint the character (Unicode code point) to be tested.
11365 * @return {@code true} if the character is an Extended Pictographic;
11366 * {@code false} otherwise.
11367 * @spec https://www.unicode.org/reports/tr51/ Unicode Emoji
11368 * @since 21
11369 */
11370 public static boolean isExtendedPictographic(int codePoint) {
11371 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
11372 }
11373
11374 /**
11375 * Converts the character argument to lowercase using case
11376 * mapping information from the UnicodeData file.
11377 * <p>
11378 * Note that
11379 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
11380 * does not always return {@code true} for some ranges of
11381 * characters, particularly those that are symbols or ideographs.
11382 *
11383 * <p>In general, {@link String#toLowerCase()} should be used to map
11384 * characters to lowercase. {@code String} case mapping methods
11385 * have several benefits over {@code Character} case mapping methods.
11386 * {@code String} case mapping methods can perform locale-sensitive
11387 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11388 * the {@code Character} case mapping methods cannot.
11389 *
11390 * <p><b>Note:</b> This method cannot handle <a
11391 * href="#supplementary"> supplementary characters</a>. To support
11392 * all Unicode characters, including supplementary characters, use
11393 * the {@link #toLowerCase(int)} method.
11394 *
11395 * @param ch the character to be converted.
11396 * @return the lowercase equivalent of the character, if any;
11397 * otherwise, the character itself.
11398 * @see Character#isLowerCase(char)
11399 * @see String#toLowerCase()
11400 */
11401 public static char toLowerCase(char ch) {
11402 return (char)toLowerCase((int)ch);
11403 }
11404
11405 /**
11406 * Converts the character (Unicode code point) argument to
11407 * lowercase using case mapping information from the UnicodeData
11408 * file.
11409 *
11410 * <p> Note that
11411 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
11412 * does not always return {@code true} for some ranges of
11413 * characters, particularly those that are symbols or ideographs.
11414 *
11415 * <p>In general, {@link String#toLowerCase()} should be used to map
11416 * characters to lowercase. {@code String} case mapping methods
11417 * have several benefits over {@code Character} case mapping methods.
11418 * {@code String} case mapping methods can perform locale-sensitive
11419 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11420 * the {@code Character} case mapping methods cannot.
11421 *
11422 * @param codePoint the character (Unicode code point) to be converted.
11423 * @return the lowercase equivalent of the character (Unicode code
11424 * point), if any; otherwise, the character itself.
11425 * @see Character#isLowerCase(int)
11426 * @see String#toLowerCase()
11427 *
11428 * @since 1.5
11429 */
11430 public static int toLowerCase(int codePoint) {
11431 return CharacterData.of(codePoint).toLowerCase(codePoint);
11432 }
11433
11434 /**
11435 * Converts the character argument to uppercase using case mapping
11436 * information from the UnicodeData file.
11437 * <p>
11438 * Note that
11439 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
11440 * does not always return {@code true} for some ranges of
11441 * characters, particularly those that are symbols or ideographs.
11442 *
11443 * <p>In general, {@link String#toUpperCase()} should be used to map
11444 * characters to uppercase. {@code String} case mapping methods
11445 * have several benefits over {@code Character} case mapping methods.
11446 * {@code String} case mapping methods can perform locale-sensitive
11447 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11448 * the {@code Character} case mapping methods cannot.
11449 *
11450 * <p><b>Note:</b> This method cannot handle <a
11451 * href="#supplementary"> supplementary characters</a>. To support
11452 * all Unicode characters, including supplementary characters, use
11453 * the {@link #toUpperCase(int)} method.
11454 *
11455 * @param ch the character to be converted.
11456 * @return the uppercase equivalent of the character, if any;
11457 * otherwise, the character itself.
11458 * @see Character#isUpperCase(char)
11459 * @see String#toUpperCase()
11460 */
11461 public static char toUpperCase(char ch) {
11462 return (char)toUpperCase((int)ch);
11463 }
11464
11465 /**
11466 * Converts the character (Unicode code point) argument to
11467 * uppercase using case mapping information from the UnicodeData
11468 * file.
11469 *
11470 * <p>Note that
11471 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11472 * does not always return {@code true} for some ranges of
11473 * characters, particularly those that are symbols or ideographs.
11474 *
11475 * <p>In general, {@link String#toUpperCase()} should be used to map
11476 * characters to uppercase. {@code String} case mapping methods
11477 * have several benefits over {@code Character} case mapping methods.
11478 * {@code String} case mapping methods can perform locale-sensitive
11479 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11480 * the {@code Character} case mapping methods cannot.
11481 *
11482 * @param codePoint the character (Unicode code point) to be converted.
11483 * @return the uppercase equivalent of the character, if any;
11484 * otherwise, the character itself.
11485 * @see Character#isUpperCase(int)
11486 * @see String#toUpperCase()
11487 *
11488 * @since 1.5
11489 */
11490 public static int toUpperCase(int codePoint) {
11491 return CharacterData.of(codePoint).toUpperCase(codePoint);
11492 }
11493
11494 /**
11495 * Converts the character argument to titlecase using case mapping
11496 * information from the UnicodeData file. If a character has no
11497 * explicit titlecase mapping and is not itself a titlecase char
11498 * according to UnicodeData, then the uppercase mapping is
11499 * returned as an equivalent titlecase mapping. If the
11500 * {@code char} argument is already a titlecase
11501 * {@code char}, the same {@code char} value will be
11502 * returned.
11503 * <p>
11504 * Note that
11505 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11506 * does not always return {@code true} for some ranges of
11507 * characters.
11508 *
11509 * <p><b>Note:</b> This method cannot handle <a
11510 * href="#supplementary"> supplementary characters</a>. To support
11511 * all Unicode characters, including supplementary characters, use
11512 * the {@link #toTitleCase(int)} method.
11513 *
11514 * @param ch the character to be converted.
11515 * @return the titlecase equivalent of the character, if any;
11516 * otherwise, the character itself.
11517 * @see Character#isTitleCase(char)
11518 * @see Character#toLowerCase(char)
11519 * @see Character#toUpperCase(char)
11520 * @since 1.0.2
11521 */
11522 public static char toTitleCase(char ch) {
11523 return (char)toTitleCase((int)ch);
11524 }
11525
11526 /**
11527 * Converts the character (Unicode code point) argument to titlecase using case mapping
11528 * information from the UnicodeData file. If a character has no
11529 * explicit titlecase mapping and is not itself a titlecase char
11530 * according to UnicodeData, then the uppercase mapping is
11531 * returned as an equivalent titlecase mapping. If the
11532 * character argument is already a titlecase
11533 * character, the same character value will be
11534 * returned.
11535 *
11536 * <p>Note that
11537 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11538 * does not always return {@code true} for some ranges of
11539 * characters.
11540 *
11541 * @param codePoint the character (Unicode code point) to be converted.
11542 * @return the titlecase equivalent of the character, if any;
11543 * otherwise, the character itself.
11544 * @see Character#isTitleCase(int)
11545 * @see Character#toLowerCase(int)
11546 * @see Character#toUpperCase(int)
11547 * @since 1.5
11548 */
11549 public static int toTitleCase(int codePoint) {
11550 return CharacterData.of(codePoint).toTitleCase(codePoint);
11551 }
11552
11553 /**
11554 * Returns the numeric value of the character {@code ch} in the
11555 * specified radix.
11556 * <p>
11557 * If the radix is not in the range {@code MIN_RADIX} ≤
11558 * {@code radix} ≤ {@code MAX_RADIX} or if the
11559 * value of {@code ch} is not a valid digit in the specified
11560 * radix, {@code -1} is returned. A character is a valid digit
11561 * if at least one of the following is true:
11562 * <ul>
11563 * <li>The method {@code isDigit} is {@code true} of the character
11564 * and the Unicode decimal digit value of the character (or its
11565 * single-character decomposition) is less than the specified radix.
11566 * In this case the decimal digit value is returned.
11567 * <li>The character is one of the uppercase Latin letters
11568 * {@code 'A'} through {@code 'Z'} and its code is less than
11569 * {@code radix + 'A' - 10}.
11570 * In this case, {@code ch - 'A' + 10}
11571 * is returned.
11572 * <li>The character is one of the lowercase Latin letters
11573 * {@code 'a'} through {@code 'z'} and its code is less than
11574 * {@code radix + 'a' - 10}.
11575 * In this case, {@code ch - 'a' + 10}
11576 * is returned.
11577 * <li>The character is one of the fullwidth uppercase Latin letters A
11578 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11579 * and its code is less than
11580 * {@code radix + '\u005CuFF21' - 10}.
11581 * In this case, {@code ch - '\u005CuFF21' + 10}
11582 * is returned.
11583 * <li>The character is one of the fullwidth lowercase Latin letters a
11584 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11585 * and its code is less than
11586 * {@code radix + '\u005CuFF41' - 10}.
11587 * In this case, {@code ch - '\u005CuFF41' + 10}
11588 * is returned.
11589 * </ul>
11590 *
11591 * <p><b>Note:</b> This method cannot handle <a
11592 * href="#supplementary"> supplementary characters</a>. To support
11593 * all Unicode characters, including supplementary characters, use
11594 * the {@link #digit(int, int)} method.
11595 *
11596 * @param ch the character to be converted.
11597 * @param radix the radix.
11598 * @return the numeric value represented by the character in the
11599 * specified radix.
11600 * @see Character#forDigit(int, int)
11601 * @see Character#isDigit(char)
11602 */
11603 public static int digit(char ch, int radix) {
11604 return digit((int)ch, radix);
11605 }
11606
11607 /**
11608 * Returns the numeric value of the specified character (Unicode
11609 * code point) in the specified radix.
11610 *
11611 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11612 * {@code radix} ≤ {@code MAX_RADIX} or if the
11613 * character is not a valid digit in the specified
11614 * radix, {@code -1} is returned. A character is a valid digit
11615 * if at least one of the following is true:
11616 * <ul>
11617 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11618 * and the Unicode decimal digit value of the character (or its
11619 * single-character decomposition) is less than the specified radix.
11620 * In this case the decimal digit value is returned.
11621 * <li>The character is one of the uppercase Latin letters
11622 * {@code 'A'} through {@code 'Z'} and its code is less than
11623 * {@code radix + 'A' - 10}.
11624 * In this case, {@code codePoint - 'A' + 10}
11625 * is returned.
11626 * <li>The character is one of the lowercase Latin letters
11627 * {@code 'a'} through {@code 'z'} and its code is less than
11628 * {@code radix + 'a' - 10}.
11629 * In this case, {@code codePoint - 'a' + 10}
11630 * is returned.
11631 * <li>The character is one of the fullwidth uppercase Latin letters A
11632 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11633 * and its code is less than
11634 * {@code radix + '\u005CuFF21' - 10}.
11635 * In this case,
11636 * {@code codePoint - '\u005CuFF21' + 10}
11637 * is returned.
11638 * <li>The character is one of the fullwidth lowercase Latin letters a
11639 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11640 * and its code is less than
11641 * {@code radix + '\u005CuFF41'- 10}.
11642 * In this case,
11643 * {@code codePoint - '\u005CuFF41' + 10}
11644 * is returned.
11645 * </ul>
11646 *
11647 * @param codePoint the character (Unicode code point) to be converted.
11648 * @param radix the radix.
11649 * @return the numeric value represented by the character in the
11650 * specified radix.
11651 * @see Character#forDigit(int, int)
11652 * @see Character#isDigit(int)
11653 * @since 1.5
11654 */
11655 public static int digit(int codePoint, int radix) {
11656 return CharacterData.of(codePoint).digit(codePoint, radix);
11657 }
11658
11659 /**
11660 * Returns the {@code int} value that the specified Unicode
11661 * character represents. For example, the character
11662 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11663 * an int with a value of 50.
11664 * <p>
11665 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11666 * {@code '\u005Cu005A'}), lowercase
11667 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11668 * full width variant ({@code '\u005CuFF21'} through
11669 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11670 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11671 * through 35. This is independent of the Unicode specification,
11672 * which does not assign numeric values to these {@code char}
11673 * values.
11674 * <p>
11675 * If the character does not have a numeric value, then -1 is returned.
11676 * If the character has a numeric value that cannot be represented as a
11677 * nonnegative integer (for example, a fractional value), then -2
11678 * is returned.
11679 *
11680 * <p><b>Note:</b> This method cannot handle <a
11681 * href="#supplementary"> supplementary characters</a>. To support
11682 * all Unicode characters, including supplementary characters, use
11683 * the {@link #getNumericValue(int)} method.
11684 *
11685 * @param ch the character to be converted.
11686 * @return the numeric value of the character, as a nonnegative {@code int}
11687 * value; -2 if the character has a numeric value but the value
11688 * can not be represented as a nonnegative {@code int} value;
11689 * -1 if the character has no numeric value.
11690 * @see Character#forDigit(int, int)
11691 * @see Character#isDigit(char)
11692 * @since 1.1
11693 */
11694 public static int getNumericValue(char ch) {
11695 return getNumericValue((int)ch);
11696 }
11697
11698 /**
11699 * Returns the {@code int} value that the specified
11700 * character (Unicode code point) represents. For example, the character
11701 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11702 * an {@code int} with a value of 50.
11703 * <p>
11704 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11705 * {@code '\u005Cu005A'}), lowercase
11706 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11707 * full width variant ({@code '\u005CuFF21'} through
11708 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11709 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11710 * through 35. This is independent of the Unicode specification,
11711 * which does not assign numeric values to these {@code char}
11712 * values.
11713 * <p>
11714 * If the character does not have a numeric value, then -1 is returned.
11715 * If the character has a numeric value that cannot be represented as a
11716 * nonnegative integer (for example, a fractional value), then -2
11717 * is returned.
11718 *
11719 * @param codePoint the character (Unicode code point) to be converted.
11720 * @return the numeric value of the character, as a nonnegative {@code int}
11721 * value; -2 if the character has a numeric value but the value
11722 * can not be represented as a nonnegative {@code int} value;
11723 * -1 if the character has no numeric value.
11724 * @see Character#forDigit(int, int)
11725 * @see Character#isDigit(int)
11726 * @since 1.5
11727 */
11728 public static int getNumericValue(int codePoint) {
11729 return CharacterData.of(codePoint).getNumericValue(codePoint);
11730 }
11731
11732 /**
11733 * Determines if the specified character is ISO-LATIN-1 white space.
11734 * This method returns {@code true} for the following five
11735 * characters only:
11736 * <table class="striped">
11737 * <caption style="display:none">truechars</caption>
11738 * <thead>
11739 * <tr><th scope="col">Character
11740 * <th scope="col">Code
11741 * <th scope="col">Name
11742 * </thead>
11743 * <tbody>
11744 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11745 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11746 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11747 * <td>{@code NEW LINE}</td></tr>
11748 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11749 * <td>{@code FORM FEED}</td></tr>
11750 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11751 * <td>{@code CARRIAGE RETURN}</td></tr>
11752 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11753 * <td>{@code SPACE}</td></tr>
11754 * </tbody>
11755 * </table>
11756 *
11757 * @param ch the character to be tested.
11758 * @return {@code true} if the character is ISO-LATIN-1 white
11759 * space; {@code false} otherwise.
11760 * @see Character#isSpaceChar(char)
11761 * @see Character#isWhitespace(char)
11762 * @deprecated Replaced by isWhitespace(char).
11763 */
11764 @Deprecated(since="1.1")
11765 public static boolean isSpace(char ch) {
11766 return (ch <= 0x0020) &&
11767 (((((1L << 0x0009) |
11768 (1L << 0x000A) |
11769 (1L << 0x000C) |
11770 (1L << 0x000D) |
11771 (1L << 0x0020)) >> ch) & 1L) != 0);
11772 }
11773
11774
11775 /**
11776 * Determines if the specified character is a Unicode space character.
11777 * A character is considered to be a space character if and only if
11778 * it is specified to be a space character by the Unicode Standard. This
11779 * method returns true if the character's general category type is any of
11780 * the following:
11781 * <ul>
11782 * <li> {@code SPACE_SEPARATOR}
11783 * <li> {@code LINE_SEPARATOR}
11784 * <li> {@code PARAGRAPH_SEPARATOR}
11785 * </ul>
11786 *
11787 * <p><b>Note:</b> This method cannot handle <a
11788 * href="#supplementary"> supplementary characters</a>. To support
11789 * all Unicode characters, including supplementary characters, use
11790 * the {@link #isSpaceChar(int)} method.
11791 *
11792 * @param ch the character to be tested.
11793 * @return {@code true} if the character is a space character;
11794 * {@code false} otherwise.
11795 * @see Character#isWhitespace(char)
11796 * @since 1.1
11797 */
11798 public static boolean isSpaceChar(char ch) {
11799 return isSpaceChar((int)ch);
11800 }
11801
11802 /**
11803 * Determines if the specified character (Unicode code point) is a
11804 * Unicode space character. A character is considered to be a
11805 * space character if and only if it is specified to be a space
11806 * character by the Unicode Standard. This method returns true if
11807 * the character's general category type is any of the following:
11808 *
11809 * <ul>
11810 * <li> {@link #SPACE_SEPARATOR}
11811 * <li> {@link #LINE_SEPARATOR}
11812 * <li> {@link #PARAGRAPH_SEPARATOR}
11813 * </ul>
11814 *
11815 * @param codePoint the character (Unicode code point) to be tested.
11816 * @return {@code true} if the character is a space character;
11817 * {@code false} otherwise.
11818 * @see Character#isWhitespace(int)
11819 * @since 1.5
11820 */
11821 public static boolean isSpaceChar(int codePoint) {
11822 return ((((1 << Character.SPACE_SEPARATOR) |
11823 (1 << Character.LINE_SEPARATOR) |
11824 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11825 != 0;
11826 }
11827
11828 /**
11829 * Determines if the specified character is white space according to Java.
11830 * A character is a Java whitespace character if and only if it satisfies
11831 * one of the following criteria:
11832 * <ul>
11833 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11834 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11835 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11836 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11837 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11838 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11839 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11840 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11841 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11842 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11843 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11844 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11845 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11846 * </ul>
11847 *
11848 * <p><b>Note:</b> This method cannot handle <a
11849 * href="#supplementary"> supplementary characters</a>. To support
11850 * all Unicode characters, including supplementary characters, use
11851 * the {@link #isWhitespace(int)} method.
11852 *
11853 * @param ch the character to be tested.
11854 * @return {@code true} if the character is a Java whitespace
11855 * character; {@code false} otherwise.
11856 * @see Character#isSpaceChar(char)
11857 * @since 1.1
11858 */
11859 public static boolean isWhitespace(char ch) {
11860 return isWhitespace((int)ch);
11861 }
11862
11863 /**
11864 * Determines if the specified character (Unicode code point) is
11865 * white space according to Java. A character is a Java
11866 * whitespace character if and only if it satisfies one of the
11867 * following criteria:
11868 * <ul>
11869 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11870 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11871 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11872 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11873 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11874 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11875 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11876 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11877 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11878 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11879 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11880 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11881 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11882 * </ul>
11883 *
11884 * @param codePoint the character (Unicode code point) to be tested.
11885 * @return {@code true} if the character is a Java whitespace
11886 * character; {@code false} otherwise.
11887 * @see Character#isSpaceChar(int)
11888 * @since 1.5
11889 */
11890 public static boolean isWhitespace(int codePoint) {
11891 return CharacterData.of(codePoint).isWhitespace(codePoint);
11892 }
11893
11894 /**
11895 * Determines if the specified character is an ISO control
11896 * character. A character is considered to be an ISO control
11897 * character if its code is in the range {@code '\u005Cu0000'}
11898 * through {@code '\u005Cu001F'} or in the range
11899 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11900 *
11901 * <p><b>Note:</b> This method cannot handle <a
11902 * href="#supplementary"> supplementary characters</a>. To support
11903 * all Unicode characters, including supplementary characters, use
11904 * the {@link #isISOControl(int)} method.
11905 *
11906 * @param ch the character to be tested.
11907 * @return {@code true} if the character is an ISO control character;
11908 * {@code false} otherwise.
11909 *
11910 * @see Character#isSpaceChar(char)
11911 * @see Character#isWhitespace(char)
11912 * @since 1.1
11913 */
11914 public static boolean isISOControl(char ch) {
11915 return isISOControl((int)ch);
11916 }
11917
11918 /**
11919 * Determines if the referenced character (Unicode code point) is an ISO control
11920 * character. A character is considered to be an ISO control
11921 * character if its code is in the range {@code '\u005Cu0000'}
11922 * through {@code '\u005Cu001F'} or in the range
11923 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11924 *
11925 * @param codePoint the character (Unicode code point) to be tested.
11926 * @return {@code true} if the character is an ISO control character;
11927 * {@code false} otherwise.
11928 * @see Character#isSpaceChar(int)
11929 * @see Character#isWhitespace(int)
11930 * @since 1.5
11931 */
11932 public static boolean isISOControl(int codePoint) {
11933 // Optimized form of:
11934 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11935 // (codePoint >= 0x7F && codePoint <= 0x9F);
11936 return codePoint <= 0x9F &&
11937 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11938 }
11939
11940 /**
11941 * Returns a value indicating a character's general category.
11942 *
11943 * <p><b>Note:</b> This method cannot handle <a
11944 * href="#supplementary"> supplementary characters</a>. To support
11945 * all Unicode characters, including supplementary characters, use
11946 * the {@link #getType(int)} method.
11947 *
11948 * @param ch the character to be tested.
11949 * @return a value of type {@code int} representing the
11950 * character's general category.
11951 * @see Character#COMBINING_SPACING_MARK
11952 * @see Character#CONNECTOR_PUNCTUATION
11953 * @see Character#CONTROL
11954 * @see Character#CURRENCY_SYMBOL
11955 * @see Character#DASH_PUNCTUATION
11956 * @see Character#DECIMAL_DIGIT_NUMBER
11957 * @see Character#ENCLOSING_MARK
11958 * @see Character#END_PUNCTUATION
11959 * @see Character#FINAL_QUOTE_PUNCTUATION
11960 * @see Character#FORMAT
11961 * @see Character#INITIAL_QUOTE_PUNCTUATION
11962 * @see Character#LETTER_NUMBER
11963 * @see Character#LINE_SEPARATOR
11964 * @see Character#LOWERCASE_LETTER
11965 * @see Character#MATH_SYMBOL
11966 * @see Character#MODIFIER_LETTER
11967 * @see Character#MODIFIER_SYMBOL
11968 * @see Character#NON_SPACING_MARK
11969 * @see Character#OTHER_LETTER
11970 * @see Character#OTHER_NUMBER
11971 * @see Character#OTHER_PUNCTUATION
11972 * @see Character#OTHER_SYMBOL
11973 * @see Character#PARAGRAPH_SEPARATOR
11974 * @see Character#PRIVATE_USE
11975 * @see Character#SPACE_SEPARATOR
11976 * @see Character#START_PUNCTUATION
11977 * @see Character#SURROGATE
11978 * @see Character#TITLECASE_LETTER
11979 * @see Character#UNASSIGNED
11980 * @see Character#UPPERCASE_LETTER
11981 * @since 1.1
11982 */
11983 public static int getType(char ch) {
11984 return getType((int)ch);
11985 }
11986
11987 /**
11988 * Returns a value indicating a character's general category.
11989 *
11990 * @param codePoint the character (Unicode code point) to be tested.
11991 * @return a value of type {@code int} representing the
11992 * character's general category.
11993 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11994 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11995 * @see Character#CONTROL CONTROL
11996 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11997 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11998 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11999 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
12000 * @see Character#END_PUNCTUATION END_PUNCTUATION
12001 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
12002 * @see Character#FORMAT FORMAT
12003 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
12004 * @see Character#LETTER_NUMBER LETTER_NUMBER
12005 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
12006 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
12007 * @see Character#MATH_SYMBOL MATH_SYMBOL
12008 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
12009 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
12010 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
12011 * @see Character#OTHER_LETTER OTHER_LETTER
12012 * @see Character#OTHER_NUMBER OTHER_NUMBER
12013 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
12014 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
12015 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
12016 * @see Character#PRIVATE_USE PRIVATE_USE
12017 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
12018 * @see Character#START_PUNCTUATION START_PUNCTUATION
12019 * @see Character#SURROGATE SURROGATE
12020 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
12021 * @see Character#UNASSIGNED UNASSIGNED
12022 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
12023 * @since 1.5
12024 */
12025 public static int getType(int codePoint) {
12026 return CharacterData.of(codePoint).getType(codePoint);
12027 }
12028
12029 /**
12030 * Determines the character representation for a specific digit in
12031 * the specified radix. If the value of {@code radix} is not a
12032 * valid radix, or the value of {@code digit} is not a valid
12033 * digit in the specified radix, the null character
12034 * ({@code '\u005Cu0000'}) is returned.
12035 * <p>
12036 * The {@code radix} argument is valid if it is greater than or
12037 * equal to {@code MIN_RADIX} and less than or equal to
12038 * {@code MAX_RADIX}. The {@code digit} argument is valid if
12039 * {@code 0 <= digit < radix}.
12040 * <p>
12041 * If the digit is less than 10, then
12042 * {@code '0' + digit} is returned. Otherwise, the value
12043 * {@code 'a' + digit - 10} is returned.
12044 *
12045 * @param digit the number to convert to a character.
12046 * @param radix the radix.
12047 * @return the {@code char} representation of the specified digit
12048 * in the specified radix.
12049 * @see Character#MIN_RADIX
12050 * @see Character#MAX_RADIX
12051 * @see Character#digit(char, int)
12052 */
12053 public static char forDigit(int digit, int radix) {
12054 if ((digit >= radix) || (digit < 0)) {
12055 return '\0';
12056 }
12057 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
12058 return '\0';
12059 }
12060 if (digit < 10) {
12061 return (char)('0' + digit);
12062 }
12063 return (char)('a' - 10 + digit);
12064 }
12065
12066 /**
12067 * Returns the Unicode directionality property for the given
12068 * character. Character directionality is used to calculate the
12069 * visual ordering of text. The directionality value of undefined
12070 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
12071 *
12072 * <p><b>Note:</b> This method cannot handle <a
12073 * href="#supplementary"> supplementary characters</a>. To support
12074 * all Unicode characters, including supplementary characters, use
12075 * the {@link #getDirectionality(int)} method.
12076 *
12077 * @param ch {@code char} for which the directionality property
12078 * is requested.
12079 * @return the directionality property of the {@code char} value.
12080 *
12081 * @see Character#DIRECTIONALITY_UNDEFINED
12082 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
12083 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
12084 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
12085 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
12086 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
12087 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
12088 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
12089 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
12090 * @see Character#DIRECTIONALITY_NONSPACING_MARK
12091 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
12092 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
12093 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
12094 * @see Character#DIRECTIONALITY_WHITESPACE
12095 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
12096 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
12097 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
12098 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
12099 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
12100 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
12101 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
12102 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
12103 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
12104 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
12105 * @since 1.4
12106 */
12107 public static byte getDirectionality(char ch) {
12108 return getDirectionality((int)ch);
12109 }
12110
12111 /**
12112 * Returns the Unicode directionality property for the given
12113 * character (Unicode code point). Character directionality is
12114 * used to calculate the visual ordering of text. The
12115 * directionality value of undefined character is {@link
12116 * #DIRECTIONALITY_UNDEFINED}.
12117 *
12118 * @param codePoint the character (Unicode code point) for which
12119 * the directionality property is requested.
12120 * @return the directionality property of the character.
12121 *
12122 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
12123 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
12124 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
12125 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
12126 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
12127 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
12128 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
12129 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
12130 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
12131 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
12132 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
12133 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
12134 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
12135 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
12136 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
12137 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
12138 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
12139 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
12140 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
12141 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
12142 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
12143 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
12144 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
12145 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
12146 * @since 1.5
12147 */
12148 public static byte getDirectionality(int codePoint) {
12149 return CharacterData.of(codePoint).getDirectionality(codePoint);
12150 }
12151
12152 /**
12153 * Determines whether the character is mirrored according to the
12154 * Unicode specification. Mirrored characters should have their
12155 * glyphs horizontally mirrored when displayed in text that is
12156 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
12157 * PARENTHESIS is semantically defined to be an <i>opening
12158 * parenthesis</i>. This will appear as a "(" in text that is
12159 * left-to-right but as a ")" in text that is right-to-left.
12160 *
12161 * <p><b>Note:</b> This method cannot handle <a
12162 * href="#supplementary"> supplementary characters</a>. To support
12163 * all Unicode characters, including supplementary characters, use
12164 * the {@link #isMirrored(int)} method.
12165 *
12166 * @param ch {@code char} for which the mirrored property is requested
12167 * @return {@code true} if the char is mirrored, {@code false}
12168 * if the {@code char} is not mirrored or is not defined.
12169 * @since 1.4
12170 */
12171 public static boolean isMirrored(char ch) {
12172 return isMirrored((int)ch);
12173 }
12174
12175 /**
12176 * Determines whether the specified character (Unicode code point)
12177 * is mirrored according to the Unicode specification. Mirrored
12178 * characters should have their glyphs horizontally mirrored when
12179 * displayed in text that is right-to-left. For example,
12180 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
12181 * defined to be an <i>opening parenthesis</i>. This will appear
12182 * as a "(" in text that is left-to-right but as a ")" in text
12183 * that is right-to-left.
12184 *
12185 * @param codePoint the character (Unicode code point) to be tested.
12186 * @return {@code true} if the character is mirrored, {@code false}
12187 * if the character is not mirrored or is not defined.
12188 * @since 1.5
12189 */
12190 public static boolean isMirrored(int codePoint) {
12191 return CharacterData.of(codePoint).isMirrored(codePoint);
12192 }
12193
12194 /**
12195 * Compares two {@code Character} objects numerically.
12196 *
12197 * @param anotherCharacter the {@code Character} to be compared.
12198 * @return the value {@code 0} if the argument {@code Character}
12199 * is equal to this {@code Character}; a value less than
12200 * {@code 0} if this {@code Character} is numerically less
12201 * than the {@code Character} argument; and a value greater than
12202 * {@code 0} if this {@code Character} is numerically greater
12203 * than the {@code Character} argument (unsigned comparison).
12204 * Note that this is strictly a numerical comparison; it is not
12205 * locale-dependent.
12206 * @since 1.2
12207 */
12208 public int compareTo(Character anotherCharacter) {
12209 return compare(this.value, anotherCharacter.value);
12210 }
12211
12212 /**
12213 * Compares two {@code char} values numerically.
12214 * The value returned is identical to what would be returned by:
12215 * <pre>
12216 * Character.valueOf(x).compareTo(Character.valueOf(y))
12217 * </pre>
12218 *
12219 * @param x the first {@code char} to compare
12220 * @param y the second {@code char} to compare
12221 * @return the value {@code 0} if {@code x == y};
12222 * a value less than {@code 0} if {@code x < y}; and
12223 * a value greater than {@code 0} if {@code x > y}
12224 * @since 1.7
12225 */
12226 public static int compare(char x, char y) {
12227 return x - y;
12228 }
12229
12230 /**
12231 * Converts the character (Unicode code point) argument to uppercase using
12232 * information from the UnicodeData file.
12233 *
12234 * @param codePoint the character (Unicode code point) to be converted.
12235 * @return either the uppercase equivalent of the character, if
12236 * any, or an error flag ({@code Character.ERROR})
12237 * that indicates that a 1:M {@code char} mapping exists.
12238 * @see Character#isLowerCase(char)
12239 * @see Character#isUpperCase(char)
12240 * @see Character#toLowerCase(char)
12241 * @see Character#toTitleCase(char)
12242 * @since 1.4
12243 */
12244 static int toUpperCaseEx(int codePoint) {
12245 assert isValidCodePoint(codePoint);
12246 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
12247 }
12248
12249 /**
12250 * Converts the character (Unicode code point) argument to uppercase using case
12251 * mapping information from the SpecialCasing file in the Unicode
12252 * specification. If a character has no explicit uppercase
12253 * mapping, then the {@code char} itself is returned in the
12254 * {@code char[]}.
12255 *
12256 * @param codePoint the character (Unicode code point) to be converted.
12257 * @return a {@code char[]} with the uppercased character.
12258 * @since 1.4
12259 */
12260 static char[] toUpperCaseCharArray(int codePoint) {
12261 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
12262 assert isBmpCodePoint(codePoint);
12263 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
12264 }
12265
12266 /**
12267 * The number of bits used to represent a {@code char} value in unsigned
12268 * binary form, constant {@code 16}.
12269 *
12270 * @since 1.5
12271 */
12272 public static final int SIZE = 16;
12273
12274 /**
12275 * The number of bytes used to represent a {@code char} value in unsigned
12276 * binary form.
12277 *
12278 * @since 1.8
12279 */
12280 public static final int BYTES = SIZE / Byte.SIZE;
12281
12282 /**
12283 * Returns the value obtained by reversing the order of the bytes in the
12284 * specified {@code char} value.
12285 *
12286 * @param ch The {@code char} of which to reverse the byte order.
12287 * @return the value obtained by reversing (or, equivalently, swapping)
12288 * the bytes in the specified {@code char} value.
12289 * @since 1.5
12290 */
12291 @IntrinsicCandidate
12292 public static char reverseBytes(char ch) {
12293 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
12294 }
12295
12296 /**
12297 * Returns the name of the specified character
12298 * {@code codePoint}, or null if the code point is
12299 * {@link #UNASSIGNED unassigned}.
12300 * <p>
12301 * If the specified character is not assigned a name by
12302 * the <i>UnicodeData</i> file (part of the Unicode Character
12303 * Database maintained by the Unicode Consortium), the returned
12304 * name is the same as the result of the expression:
12305 *
12306 * <blockquote>{@code
12307 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12308 * + " "
12309 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12310 *
12311 * }</blockquote>
12312 *
12313 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
12314 * returned by this method follows the naming scheme in the
12315 * "Unicode Name Property" section of the Unicode Standard. For other
12316 * code points, such as Hangul/Ideographs, The name generation rule above
12317 * differs from the one defined in the Unicode Standard.
12318 *
12319 * @param codePoint the character (Unicode code point)
12320 *
12321 * @return the name of the specified character, or null if
12322 * the code point is unassigned.
12323 *
12324 * @throws IllegalArgumentException if the specified
12325 * {@code codePoint} is not a valid Unicode
12326 * code point.
12327 *
12328 * @since 1.7
12329 */
12330 public static String getName(int codePoint) {
12331 if (!isValidCodePoint(codePoint)) {
12332 throw new IllegalArgumentException(
12333 String.format("Not a valid Unicode code point: 0x%X", codePoint));
12334 }
12335 String name = CharacterName.getInstance().getName(codePoint);
12336 if (name != null)
12337 return name;
12338 if (getType(codePoint) == UNASSIGNED)
12339 return null;
12340 UnicodeBlock block = UnicodeBlock.of(codePoint);
12341 if (block != null)
12342 return block.toString().replace('_', ' ') + " "
12343 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12344 // should never come here
12345 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12346 }
12347
12348 /**
12349 * Returns the code point value of the Unicode character specified by
12350 * the given character name.
12351 * <p>
12352 * If a character is not assigned a name by the <i>UnicodeData</i>
12353 * file (part of the Unicode Character Database maintained by the Unicode
12354 * Consortium), its name is defined as the result of the expression:
12355 *
12356 * <blockquote>{@code
12357 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12358 * + " "
12359 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12360 *
12361 * }</blockquote>
12362 * <p>
12363 * The {@code name} matching is case insensitive, with any leading and
12364 * trailing whitespace character removed.
12365 *
12366 * For the code points in the <i>UnicodeData</i> file, this method
12367 * recognizes the name which conforms to the name defined in the
12368 * "Unicode Name Property" section in the Unicode Standard. For other
12369 * code points, this method recognizes the name generated with
12370 * {@link #getName(int)} method.
12371 *
12372 * @param name the character name
12373 *
12374 * @return the code point value of the character specified by its name.
12375 *
12376 * @throws IllegalArgumentException if the specified {@code name}
12377 * is not a valid character name.
12378 * @throws NullPointerException if {@code name} is {@code null}
12379 *
12380 * @since 9
12381 */
12382 public static int codePointOf(String name) {
12383 name = name.trim().toUpperCase(Locale.ROOT);
12384 int cp = CharacterName.getInstance().getCodePoint(name);
12385 if (cp != -1)
12386 return cp;
12387 try {
12388 int off = name.lastIndexOf(' ');
12389 if (off != -1) {
12390 cp = Integer.parseInt(name, off + 1, name.length(), 16);
12391 if (isValidCodePoint(cp) && name.equals(getName(cp)))
12392 return cp;
12393 }
12394 } catch (Exception x) {}
12395 throw new IllegalArgumentException("Unrecognized character name :" + name);
12396 }
12397 }