1 /*
2 * Copyright (c) 2002, 2018, 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 java.util.Arrays;
29 import java.util.Map;
30 import java.util.HashMap;
31 import java.util.Locale;
32
33 import jdk.internal.HotSpotIntrinsicCandidate;
34 import jdk.internal.misc.VM;
35
36 /**
37 * The {@code Character} class wraps a value of the primitive
38 * type {@code char} in an object. An object of type
39 * {@code Character} contains a single field whose type is
40 * {@code char}.
41 * <p>
42 * In addition, this class provides several methods for determining
43 * a character's category (lowercase letter, digit, etc.) and for converting
44 * characters from uppercase to lowercase and vice versa.
45 * <p>
46 * Character information is based on <a id="UnicodeVer">the Unicode Standard,
47 * version 11.0.0</a>. Additional currency symbols (and Japanese Era Square
48 * character) defined subsequent to that Unicode version may be present.
49 * <p>
50 * The methods and data of class {@code Character} are defined by
51 * the information in the <i>UnicodeData</i> file that is part of the
52 * Unicode Character Database maintained by the Unicode
53 * Consortium. This file specifies various properties including name
54 * and general category for every defined Unicode code point or
55 * character range.
56 * <p>
57 * The file and its description are available from the Unicode Consortium at:
58 * <ul>
59 * <li><a href="http://www.unicode.org">http://www.unicode.org</a>
60 * </ul>
61 * <p>
62 * The code point, U+32FF, is reserved by the Unicode Consortium
63 * to represent the Japanese square character for the new era that begins
64 * May 2019. Relevant methods in the Character class return the same
65 * properties as for the existing Japanese era characters (e.g., U+337E for
66 * "Meizi"). For the details of the code point, refer to
67 * <a href="http://blog.unicode.org/2018/09/new-japanese-era.html">
68 * http://blog.unicode.org/2018/09/new-japanese-era.html</a>.
69 * <p>
70 * @implSpec The code points in {@link Character.UnicodeBlock#CURRENCY_SYMBOLS
71 * Currency Symbols} {@code UnicodeBlock} that are unassigned as of the
72 * <a href="#UnicodeVer">Unicode version noted above</a>,
73 * may be defined for currency symbols assigned by the Unicode
74 * Consortium from later updates. The definition of additionally assigned
75 * code points is implementation specific.
76 *
77 * <h3><a id="unicode">Unicode Character Representations</a></h3>
78 *
79 * <p>The {@code char} data type (and therefore the value that a
80 * {@code Character} object encapsulates) are based on the
81 * original Unicode specification, which defined characters as
82 * fixed-width 16-bit entities. The Unicode Standard has since been
83 * changed to allow for characters whose representation requires more
84 * than 16 bits. The range of legal <em>code point</em>s is now
85 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
86 * (Refer to the <a
87 * href="http://www.unicode.org/reports/tr27/#notation"><i>
88 * definition</i></a> of the U+<i>n</i> notation in the Unicode
89 * Standard.)
90 *
91 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
92 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
93 * <a id="supplementary">Characters</a> whose code points are greater
94 * than U+FFFF are called <em>supplementary character</em>s. The Java
95 * platform uses the UTF-16 representation in {@code char} arrays and
96 * in the {@code String} and {@code StringBuffer} classes. In
97 * this representation, supplementary characters are represented as a pair
98 * of {@code char} values, the first from the <em>high-surrogates</em>
99 * range, (\uD800-\uDBFF), the second from the
100 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
101 *
102 * <p>A {@code char} value, therefore, represents Basic
103 * Multilingual Plane (BMP) code points, including the surrogate
104 * code points, or code units of the UTF-16 encoding. An
105 * {@code int} value represents all Unicode code points,
106 * including supplementary code points. The lower (least significant)
107 * 21 bits of {@code int} are used to represent Unicode code
108 * points and the upper (most significant) 11 bits must be zero.
109 * Unless otherwise specified, the behavior with respect to
110 * supplementary characters and surrogate {@code char} values is
111 * as follows:
112 *
113 * <ul>
114 * <li>The methods that only accept a {@code char} value cannot support
115 * supplementary characters. They treat {@code char} values from the
116 * surrogate ranges as undefined characters. For example,
117 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
118 * this specific value if followed by any low-surrogate value in a string
119 * would represent a letter.
120 *
121 * <li>The methods that accept an {@code int} value support all
122 * Unicode characters, including supplementary characters. For
123 * example, {@code Character.isLetter(0x2F81A)} returns
124 * {@code true} because the code point value represents a letter
125 * (a CJK ideograph).
126 * </ul>
127 *
128 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
129 * used for character values in the range between U+0000 and U+10FFFF,
130 * and <em>Unicode code unit</em> is used for 16-bit
131 * {@code char} values that are code units of the <em>UTF-16</em>
132 * encoding. For more information on Unicode terminology, refer to the
133 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
134 *
135 * @author Lee Boynton
136 * @author Guy Steele
137 * @author Akira Tanaka
138 * @author Martin Buchholz
139 * @author Ulf Zibis
140 * @since 1.0
141 */
142 public final
143 class Character implements java.io.Serializable, Comparable<Character> {
144 /**
145 * The minimum radix available for conversion to and from strings.
146 * The constant value of this field is the smallest value permitted
147 * for the radix argument in radix-conversion methods such as the
148 * {@code digit} method, the {@code forDigit} method, and the
149 * {@code toString} method of class {@code Integer}.
150 *
151 * @see Character#digit(char, int)
152 * @see Character#forDigit(int, int)
153 * @see Integer#toString(int, int)
154 * @see Integer#valueOf(String)
155 */
156 public static final int MIN_RADIX = 2;
157
158 /**
159 * The maximum radix available for conversion to and from strings.
160 * The constant value of this field is the largest value permitted
161 * for the radix argument in radix-conversion methods such as the
162 * {@code digit} method, the {@code forDigit} method, and the
163 * {@code toString} method of class {@code Integer}.
164 *
165 * @see Character#digit(char, int)
166 * @see Character#forDigit(int, int)
167 * @see Integer#toString(int, int)
168 * @see Integer#valueOf(String)
169 */
170 public static final int MAX_RADIX = 36;
171
172 /**
173 * The constant value of this field is the smallest value of type
174 * {@code char}, {@code '\u005Cu0000'}.
175 *
176 * @since 1.0.2
177 */
178 public static final char MIN_VALUE = '\u0000';
179
180 /**
181 * The constant value of this field is the largest value of type
182 * {@code char}, {@code '\u005CuFFFF'}.
183 *
184 * @since 1.0.2
185 */
186 public static final char MAX_VALUE = '\uFFFF';
187
188 /**
189 * The {@code Class} instance representing the primitive type
190 * {@code char}.
191 *
192 * @since 1.1
193 */
194 @SuppressWarnings("unchecked")
195 public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char");
196
197 /*
198 * Normative general types
199 */
200
201 /*
202 * General character types
203 */
204
205 /**
206 * General category "Cn" in the Unicode specification.
207 * @since 1.1
208 */
209 public static final byte UNASSIGNED = 0;
210
211 /**
212 * General category "Lu" in the Unicode specification.
213 * @since 1.1
214 */
215 public static final byte UPPERCASE_LETTER = 1;
216
217 /**
218 * General category "Ll" in the Unicode specification.
219 * @since 1.1
220 */
221 public static final byte LOWERCASE_LETTER = 2;
222
223 /**
224 * General category "Lt" in the Unicode specification.
225 * @since 1.1
226 */
227 public static final byte TITLECASE_LETTER = 3;
228
229 /**
230 * General category "Lm" in the Unicode specification.
231 * @since 1.1
232 */
233 public static final byte MODIFIER_LETTER = 4;
234
235 /**
236 * General category "Lo" in the Unicode specification.
237 * @since 1.1
238 */
239 public static final byte OTHER_LETTER = 5;
240
241 /**
242 * General category "Mn" in the Unicode specification.
243 * @since 1.1
244 */
245 public static final byte NON_SPACING_MARK = 6;
246
247 /**
248 * General category "Me" in the Unicode specification.
249 * @since 1.1
250 */
251 public static final byte ENCLOSING_MARK = 7;
252
253 /**
254 * General category "Mc" in the Unicode specification.
255 * @since 1.1
256 */
257 public static final byte COMBINING_SPACING_MARK = 8;
258
259 /**
260 * General category "Nd" in the Unicode specification.
261 * @since 1.1
262 */
263 public static final byte DECIMAL_DIGIT_NUMBER = 9;
264
265 /**
266 * General category "Nl" in the Unicode specification.
267 * @since 1.1
268 */
269 public static final byte LETTER_NUMBER = 10;
270
271 /**
272 * General category "No" in the Unicode specification.
273 * @since 1.1
274 */
275 public static final byte OTHER_NUMBER = 11;
276
277 /**
278 * General category "Zs" in the Unicode specification.
279 * @since 1.1
280 */
281 public static final byte SPACE_SEPARATOR = 12;
282
283 /**
284 * General category "Zl" in the Unicode specification.
285 * @since 1.1
286 */
287 public static final byte LINE_SEPARATOR = 13;
288
289 /**
290 * General category "Zp" in the Unicode specification.
291 * @since 1.1
292 */
293 public static final byte PARAGRAPH_SEPARATOR = 14;
294
295 /**
296 * General category "Cc" in the Unicode specification.
297 * @since 1.1
298 */
299 public static final byte CONTROL = 15;
300
301 /**
302 * General category "Cf" in the Unicode specification.
303 * @since 1.1
304 */
305 public static final byte FORMAT = 16;
306
307 /**
308 * General category "Co" in the Unicode specification.
309 * @since 1.1
310 */
311 public static final byte PRIVATE_USE = 18;
312
313 /**
314 * General category "Cs" in the Unicode specification.
315 * @since 1.1
316 */
317 public static final byte SURROGATE = 19;
318
319 /**
320 * General category "Pd" in the Unicode specification.
321 * @since 1.1
322 */
323 public static final byte DASH_PUNCTUATION = 20;
324
325 /**
326 * General category "Ps" in the Unicode specification.
327 * @since 1.1
328 */
329 public static final byte START_PUNCTUATION = 21;
330
331 /**
332 * General category "Pe" in the Unicode specification.
333 * @since 1.1
334 */
335 public static final byte END_PUNCTUATION = 22;
336
337 /**
338 * General category "Pc" in the Unicode specification.
339 * @since 1.1
340 */
341 public static final byte CONNECTOR_PUNCTUATION = 23;
342
343 /**
344 * General category "Po" in the Unicode specification.
345 * @since 1.1
346 */
347 public static final byte OTHER_PUNCTUATION = 24;
348
349 /**
350 * General category "Sm" in the Unicode specification.
351 * @since 1.1
352 */
353 public static final byte MATH_SYMBOL = 25;
354
355 /**
356 * General category "Sc" in the Unicode specification.
357 * @since 1.1
358 */
359 public static final byte CURRENCY_SYMBOL = 26;
360
361 /**
362 * General category "Sk" in the Unicode specification.
363 * @since 1.1
364 */
365 public static final byte MODIFIER_SYMBOL = 27;
366
367 /**
368 * General category "So" in the Unicode specification.
369 * @since 1.1
370 */
371 public static final byte OTHER_SYMBOL = 28;
372
373 /**
374 * General category "Pi" in the Unicode specification.
375 * @since 1.4
376 */
377 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
378
379 /**
380 * General category "Pf" in the Unicode specification.
381 * @since 1.4
382 */
383 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
384
385 /**
386 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
387 */
388 static final int ERROR = 0xFFFFFFFF;
389
390
391 /**
392 * Undefined bidirectional character type. Undefined {@code char}
393 * values have undefined directionality in the Unicode specification.
394 * @since 1.4
395 */
396 public static final byte DIRECTIONALITY_UNDEFINED = -1;
397
398 /**
399 * Strong bidirectional character type "L" in the Unicode specification.
400 * @since 1.4
401 */
402 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
403
404 /**
405 * Strong bidirectional character type "R" in the Unicode specification.
406 * @since 1.4
407 */
408 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
409
410 /**
411 * Strong bidirectional character type "AL" in the Unicode specification.
412 * @since 1.4
413 */
414 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
415
416 /**
417 * Weak bidirectional character type "EN" in the Unicode specification.
418 * @since 1.4
419 */
420 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
421
422 /**
423 * Weak bidirectional character type "ES" in the Unicode specification.
424 * @since 1.4
425 */
426 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
427
428 /**
429 * Weak bidirectional character type "ET" in the Unicode specification.
430 * @since 1.4
431 */
432 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
433
434 /**
435 * Weak bidirectional character type "AN" in the Unicode specification.
436 * @since 1.4
437 */
438 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
439
440 /**
441 * Weak bidirectional character type "CS" in the Unicode specification.
442 * @since 1.4
443 */
444 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
445
446 /**
447 * Weak bidirectional character type "NSM" in the Unicode specification.
448 * @since 1.4
449 */
450 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
451
452 /**
453 * Weak bidirectional character type "BN" in the Unicode specification.
454 * @since 1.4
455 */
456 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
457
458 /**
459 * Neutral bidirectional character type "B" in the Unicode specification.
460 * @since 1.4
461 */
462 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
463
464 /**
465 * Neutral bidirectional character type "S" in the Unicode specification.
466 * @since 1.4
467 */
468 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
469
470 /**
471 * Neutral bidirectional character type "WS" in the Unicode specification.
472 * @since 1.4
473 */
474 public static final byte DIRECTIONALITY_WHITESPACE = 12;
475
476 /**
477 * Neutral bidirectional character type "ON" in the Unicode specification.
478 * @since 1.4
479 */
480 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
481
482 /**
483 * Strong bidirectional character type "LRE" in the Unicode specification.
484 * @since 1.4
485 */
486 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
487
488 /**
489 * Strong bidirectional character type "LRO" in the Unicode specification.
490 * @since 1.4
491 */
492 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
493
494 /**
495 * Strong bidirectional character type "RLE" in the Unicode specification.
496 * @since 1.4
497 */
498 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
499
500 /**
501 * Strong bidirectional character type "RLO" in the Unicode specification.
502 * @since 1.4
503 */
504 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
505
506 /**
507 * Weak bidirectional character type "PDF" in the Unicode specification.
508 * @since 1.4
509 */
510 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
511
512 /**
513 * Weak bidirectional character type "LRI" in the Unicode specification.
514 * @since 9
515 */
516 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
517
518 /**
519 * Weak bidirectional character type "RLI" in the Unicode specification.
520 * @since 9
521 */
522 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
523
524 /**
525 * Weak bidirectional character type "FSI" in the Unicode specification.
526 * @since 9
527 */
528 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
529
530 /**
531 * Weak bidirectional character type "PDI" in the Unicode specification.
532 * @since 9
533 */
534 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
535
536 /**
537 * The minimum value of a
538 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
539 * Unicode high-surrogate code unit</a>
540 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
541 * A high-surrogate is also known as a <i>leading-surrogate</i>.
542 *
543 * @since 1.5
544 */
545 public static final char MIN_HIGH_SURROGATE = '\uD800';
546
547 /**
548 * The maximum value of a
549 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
550 * Unicode high-surrogate code unit</a>
551 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
552 * A high-surrogate is also known as a <i>leading-surrogate</i>.
553 *
554 * @since 1.5
555 */
556 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
557
558 /**
559 * The minimum value of a
560 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
561 * Unicode low-surrogate code unit</a>
562 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
563 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
564 *
565 * @since 1.5
566 */
567 public static final char MIN_LOW_SURROGATE = '\uDC00';
568
569 /**
570 * The maximum value of a
571 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
572 * Unicode low-surrogate code unit</a>
573 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
574 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
575 *
576 * @since 1.5
577 */
578 public static final char MAX_LOW_SURROGATE = '\uDFFF';
579
580 /**
581 * The minimum value of a Unicode surrogate code unit in the
582 * UTF-16 encoding, constant {@code '\u005CuD800'}.
583 *
584 * @since 1.5
585 */
586 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
587
588 /**
589 * The maximum value of a Unicode surrogate code unit in the
590 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
591 *
592 * @since 1.5
593 */
594 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
595
596 /**
597 * The minimum value of a
598 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
599 * Unicode supplementary code point</a>, constant {@code U+10000}.
600 *
601 * @since 1.5
602 */
603 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
604
605 /**
606 * The minimum value of a
607 * <a href="http://www.unicode.org/glossary/#code_point">
608 * Unicode code point</a>, constant {@code U+0000}.
609 *
610 * @since 1.5
611 */
612 public static final int MIN_CODE_POINT = 0x000000;
613
614 /**
615 * The maximum value of a
616 * <a href="http://www.unicode.org/glossary/#code_point">
617 * Unicode code point</a>, constant {@code U+10FFFF}.
618 *
619 * @since 1.5
620 */
621 public static final int MAX_CODE_POINT = 0X10FFFF;
622
623
624 /**
625 * Instances of this class represent particular subsets of the Unicode
626 * character set. The only family of subsets defined in the
627 * {@code Character} class is {@link Character.UnicodeBlock}.
628 * Other portions of the Java API may define other subsets for their
629 * own purposes.
630 *
631 * @since 1.2
632 */
633 public static class Subset {
634
635 private String name;
636
637 /**
638 * Constructs a new {@code Subset} instance.
639 *
640 * @param name The name of this subset
641 * @throws NullPointerException if name is {@code null}
642 */
643 protected Subset(String name) {
644 if (name == null) {
645 throw new NullPointerException("name");
646 }
647 this.name = name;
648 }
649
650 /**
651 * Compares two {@code Subset} objects for equality.
652 * This method returns {@code true} if and only if
653 * {@code this} and the argument refer to the same
654 * object; since this method is {@code final}, this
655 * guarantee holds for all subclasses.
656 */
657 public final boolean equals(Object obj) {
658 return (this == obj);
659 }
660
661 /**
662 * Returns the standard hash code as defined by the
663 * {@link Object#hashCode} method. This method
664 * is {@code final} in order to ensure that the
665 * {@code equals} and {@code hashCode} methods will
666 * be consistent in all subclasses.
667 */
668 public final int hashCode() {
669 return super.hashCode();
670 }
671
672 /**
673 * Returns the name of this subset.
674 */
675 public final String toString() {
676 return name;
677 }
678 }
679
680 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
681 // for the latest specification of Unicode Blocks.
682
683 /**
684 * A family of character subsets representing the character blocks in the
685 * Unicode specification. Character blocks generally define characters
686 * used for a specific script or purpose. A character is contained by
687 * at most one Unicode block.
688 *
689 * @since 1.2
690 */
691 public static final class UnicodeBlock extends Subset {
692 /**
693 * 667 - the expected number of entities
694 * 0.75 - the default load factor of HashMap
695 */
696 private static final int NUM_ENTITIES = 667;
697 private static Map<String, UnicodeBlock> map =
698 new HashMap<>((int)(NUM_ENTITIES / 0.75f + 1.0f));
699
700 /**
701 * Creates a UnicodeBlock with the given identifier name.
702 * This name must be the same as the block identifier.
703 */
704 private UnicodeBlock(String idName) {
705 super(idName);
706 map.put(idName, this);
707 }
708
709 /**
710 * Creates a UnicodeBlock with the given identifier name and
711 * alias name.
712 */
713 private UnicodeBlock(String idName, String alias) {
714 this(idName);
715 map.put(alias, this);
716 }
717
718 /**
719 * Creates a UnicodeBlock with the given identifier name and
720 * alias names.
721 */
722 private UnicodeBlock(String idName, String... aliases) {
723 this(idName);
724 for (String alias : aliases)
725 map.put(alias, this);
726 }
727
728 /**
729 * Constant for the "Basic Latin" Unicode character block.
730 * @since 1.2
731 */
732 public static final UnicodeBlock BASIC_LATIN =
733 new UnicodeBlock("BASIC_LATIN",
734 "BASIC LATIN",
735 "BASICLATIN");
736
737 /**
738 * Constant for the "Latin-1 Supplement" Unicode character block.
739 * @since 1.2
740 */
741 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
742 new UnicodeBlock("LATIN_1_SUPPLEMENT",
743 "LATIN-1 SUPPLEMENT",
744 "LATIN-1SUPPLEMENT");
745
746 /**
747 * Constant for the "Latin Extended-A" Unicode character block.
748 * @since 1.2
749 */
750 public static final UnicodeBlock LATIN_EXTENDED_A =
751 new UnicodeBlock("LATIN_EXTENDED_A",
752 "LATIN EXTENDED-A",
753 "LATINEXTENDED-A");
754
755 /**
756 * Constant for the "Latin Extended-B" Unicode character block.
757 * @since 1.2
758 */
759 public static final UnicodeBlock LATIN_EXTENDED_B =
760 new UnicodeBlock("LATIN_EXTENDED_B",
761 "LATIN EXTENDED-B",
762 "LATINEXTENDED-B");
763
764 /**
765 * Constant for the "IPA Extensions" Unicode character block.
766 * @since 1.2
767 */
768 public static final UnicodeBlock IPA_EXTENSIONS =
769 new UnicodeBlock("IPA_EXTENSIONS",
770 "IPA EXTENSIONS",
771 "IPAEXTENSIONS");
772
773 /**
774 * Constant for the "Spacing Modifier Letters" Unicode character block.
775 * @since 1.2
776 */
777 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
778 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
779 "SPACING MODIFIER LETTERS",
780 "SPACINGMODIFIERLETTERS");
781
782 /**
783 * Constant for the "Combining Diacritical Marks" Unicode character block.
784 * @since 1.2
785 */
786 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
787 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
788 "COMBINING DIACRITICAL MARKS",
789 "COMBININGDIACRITICALMARKS");
790
791 /**
792 * Constant for the "Greek and Coptic" Unicode character block.
793 * <p>
794 * This block was previously known as the "Greek" block.
795 *
796 * @since 1.2
797 */
798 public static final UnicodeBlock GREEK =
799 new UnicodeBlock("GREEK",
800 "GREEK AND COPTIC",
801 "GREEKANDCOPTIC");
802
803 /**
804 * Constant for the "Cyrillic" Unicode character block.
805 * @since 1.2
806 */
807 public static final UnicodeBlock CYRILLIC =
808 new UnicodeBlock("CYRILLIC");
809
810 /**
811 * Constant for the "Armenian" Unicode character block.
812 * @since 1.2
813 */
814 public static final UnicodeBlock ARMENIAN =
815 new UnicodeBlock("ARMENIAN");
816
817 /**
818 * Constant for the "Hebrew" Unicode character block.
819 * @since 1.2
820 */
821 public static final UnicodeBlock HEBREW =
822 new UnicodeBlock("HEBREW");
823
824 /**
825 * Constant for the "Arabic" Unicode character block.
826 * @since 1.2
827 */
828 public static final UnicodeBlock ARABIC =
829 new UnicodeBlock("ARABIC");
830
831 /**
832 * Constant for the "Devanagari" Unicode character block.
833 * @since 1.2
834 */
835 public static final UnicodeBlock DEVANAGARI =
836 new UnicodeBlock("DEVANAGARI");
837
838 /**
839 * Constant for the "Bengali" Unicode character block.
840 * @since 1.2
841 */
842 public static final UnicodeBlock BENGALI =
843 new UnicodeBlock("BENGALI");
844
845 /**
846 * Constant for the "Gurmukhi" Unicode character block.
847 * @since 1.2
848 */
849 public static final UnicodeBlock GURMUKHI =
850 new UnicodeBlock("GURMUKHI");
851
852 /**
853 * Constant for the "Gujarati" Unicode character block.
854 * @since 1.2
855 */
856 public static final UnicodeBlock GUJARATI =
857 new UnicodeBlock("GUJARATI");
858
859 /**
860 * Constant for the "Oriya" Unicode character block.
861 * @since 1.2
862 */
863 public static final UnicodeBlock ORIYA =
864 new UnicodeBlock("ORIYA");
865
866 /**
867 * Constant for the "Tamil" Unicode character block.
868 * @since 1.2
869 */
870 public static final UnicodeBlock TAMIL =
871 new UnicodeBlock("TAMIL");
872
873 /**
874 * Constant for the "Telugu" Unicode character block.
875 * @since 1.2
876 */
877 public static final UnicodeBlock TELUGU =
878 new UnicodeBlock("TELUGU");
879
880 /**
881 * Constant for the "Kannada" Unicode character block.
882 * @since 1.2
883 */
884 public static final UnicodeBlock KANNADA =
885 new UnicodeBlock("KANNADA");
886
887 /**
888 * Constant for the "Malayalam" Unicode character block.
889 * @since 1.2
890 */
891 public static final UnicodeBlock MALAYALAM =
892 new UnicodeBlock("MALAYALAM");
893
894 /**
895 * Constant for the "Thai" Unicode character block.
896 * @since 1.2
897 */
898 public static final UnicodeBlock THAI =
899 new UnicodeBlock("THAI");
900
901 /**
902 * Constant for the "Lao" Unicode character block.
903 * @since 1.2
904 */
905 public static final UnicodeBlock LAO =
906 new UnicodeBlock("LAO");
907
908 /**
909 * Constant for the "Tibetan" Unicode character block.
910 * @since 1.2
911 */
912 public static final UnicodeBlock TIBETAN =
913 new UnicodeBlock("TIBETAN");
914
915 /**
916 * Constant for the "Georgian" Unicode character block.
917 * @since 1.2
918 */
919 public static final UnicodeBlock GEORGIAN =
920 new UnicodeBlock("GEORGIAN");
921
922 /**
923 * Constant for the "Hangul Jamo" Unicode character block.
924 * @since 1.2
925 */
926 public static final UnicodeBlock HANGUL_JAMO =
927 new UnicodeBlock("HANGUL_JAMO",
928 "HANGUL JAMO",
929 "HANGULJAMO");
930
931 /**
932 * Constant for the "Latin Extended Additional" Unicode character block.
933 * @since 1.2
934 */
935 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
936 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
937 "LATIN EXTENDED ADDITIONAL",
938 "LATINEXTENDEDADDITIONAL");
939
940 /**
941 * Constant for the "Greek Extended" Unicode character block.
942 * @since 1.2
943 */
944 public static final UnicodeBlock GREEK_EXTENDED =
945 new UnicodeBlock("GREEK_EXTENDED",
946 "GREEK EXTENDED",
947 "GREEKEXTENDED");
948
949 /**
950 * Constant for the "General Punctuation" Unicode character block.
951 * @since 1.2
952 */
953 public static final UnicodeBlock GENERAL_PUNCTUATION =
954 new UnicodeBlock("GENERAL_PUNCTUATION",
955 "GENERAL PUNCTUATION",
956 "GENERALPUNCTUATION");
957
958 /**
959 * Constant for the "Superscripts and Subscripts" Unicode character
960 * block.
961 * @since 1.2
962 */
963 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
964 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
965 "SUPERSCRIPTS AND SUBSCRIPTS",
966 "SUPERSCRIPTSANDSUBSCRIPTS");
967
968 /**
969 * Constant for the "Currency Symbols" Unicode character block.
970 * @since 1.2
971 */
972 public static final UnicodeBlock CURRENCY_SYMBOLS =
973 new UnicodeBlock("CURRENCY_SYMBOLS",
974 "CURRENCY SYMBOLS",
975 "CURRENCYSYMBOLS");
976
977 /**
978 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
979 * character block.
980 * <p>
981 * This block was previously known as "Combining Marks for Symbols".
982 * @since 1.2
983 */
984 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
985 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
986 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
987 "COMBININGDIACRITICALMARKSFORSYMBOLS",
988 "COMBINING MARKS FOR SYMBOLS",
989 "COMBININGMARKSFORSYMBOLS");
990
991 /**
992 * Constant for the "Letterlike Symbols" Unicode character block.
993 * @since 1.2
994 */
995 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
996 new UnicodeBlock("LETTERLIKE_SYMBOLS",
997 "LETTERLIKE SYMBOLS",
998 "LETTERLIKESYMBOLS");
999
1000 /**
1001 * Constant for the "Number Forms" Unicode character block.
1002 * @since 1.2
1003 */
1004 public static final UnicodeBlock NUMBER_FORMS =
1005 new UnicodeBlock("NUMBER_FORMS",
1006 "NUMBER FORMS",
1007 "NUMBERFORMS");
1008
1009 /**
1010 * Constant for the "Arrows" Unicode character block.
1011 * @since 1.2
1012 */
1013 public static final UnicodeBlock ARROWS =
1014 new UnicodeBlock("ARROWS");
1015
1016 /**
1017 * Constant for the "Mathematical Operators" Unicode character block.
1018 * @since 1.2
1019 */
1020 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1021 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1022 "MATHEMATICAL OPERATORS",
1023 "MATHEMATICALOPERATORS");
1024
1025 /**
1026 * Constant for the "Miscellaneous Technical" Unicode character block.
1027 * @since 1.2
1028 */
1029 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1030 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1031 "MISCELLANEOUS TECHNICAL",
1032 "MISCELLANEOUSTECHNICAL");
1033
1034 /**
1035 * Constant for the "Control Pictures" Unicode character block.
1036 * @since 1.2
1037 */
1038 public static final UnicodeBlock CONTROL_PICTURES =
1039 new UnicodeBlock("CONTROL_PICTURES",
1040 "CONTROL PICTURES",
1041 "CONTROLPICTURES");
1042
1043 /**
1044 * Constant for the "Optical Character Recognition" Unicode character block.
1045 * @since 1.2
1046 */
1047 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1048 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1049 "OPTICAL CHARACTER RECOGNITION",
1050 "OPTICALCHARACTERRECOGNITION");
1051
1052 /**
1053 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1054 * @since 1.2
1055 */
1056 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1057 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1058 "ENCLOSED ALPHANUMERICS",
1059 "ENCLOSEDALPHANUMERICS");
1060
1061 /**
1062 * Constant for the "Box Drawing" Unicode character block.
1063 * @since 1.2
1064 */
1065 public static final UnicodeBlock BOX_DRAWING =
1066 new UnicodeBlock("BOX_DRAWING",
1067 "BOX DRAWING",
1068 "BOXDRAWING");
1069
1070 /**
1071 * Constant for the "Block Elements" Unicode character block.
1072 * @since 1.2
1073 */
1074 public static final UnicodeBlock BLOCK_ELEMENTS =
1075 new UnicodeBlock("BLOCK_ELEMENTS",
1076 "BLOCK ELEMENTS",
1077 "BLOCKELEMENTS");
1078
1079 /**
1080 * Constant for the "Geometric Shapes" Unicode character block.
1081 * @since 1.2
1082 */
1083 public static final UnicodeBlock GEOMETRIC_SHAPES =
1084 new UnicodeBlock("GEOMETRIC_SHAPES",
1085 "GEOMETRIC SHAPES",
1086 "GEOMETRICSHAPES");
1087
1088 /**
1089 * Constant for the "Miscellaneous Symbols" Unicode character block.
1090 * @since 1.2
1091 */
1092 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1093 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1094 "MISCELLANEOUS SYMBOLS",
1095 "MISCELLANEOUSSYMBOLS");
1096
1097 /**
1098 * Constant for the "Dingbats" Unicode character block.
1099 * @since 1.2
1100 */
1101 public static final UnicodeBlock DINGBATS =
1102 new UnicodeBlock("DINGBATS");
1103
1104 /**
1105 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1106 * @since 1.2
1107 */
1108 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1109 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1110 "CJK SYMBOLS AND PUNCTUATION",
1111 "CJKSYMBOLSANDPUNCTUATION");
1112
1113 /**
1114 * Constant for the "Hiragana" Unicode character block.
1115 * @since 1.2
1116 */
1117 public static final UnicodeBlock HIRAGANA =
1118 new UnicodeBlock("HIRAGANA");
1119
1120 /**
1121 * Constant for the "Katakana" Unicode character block.
1122 * @since 1.2
1123 */
1124 public static final UnicodeBlock KATAKANA =
1125 new UnicodeBlock("KATAKANA");
1126
1127 /**
1128 * Constant for the "Bopomofo" Unicode character block.
1129 * @since 1.2
1130 */
1131 public static final UnicodeBlock BOPOMOFO =
1132 new UnicodeBlock("BOPOMOFO");
1133
1134 /**
1135 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1136 * @since 1.2
1137 */
1138 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1139 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1140 "HANGUL COMPATIBILITY JAMO",
1141 "HANGULCOMPATIBILITYJAMO");
1142
1143 /**
1144 * Constant for the "Kanbun" Unicode character block.
1145 * @since 1.2
1146 */
1147 public static final UnicodeBlock KANBUN =
1148 new UnicodeBlock("KANBUN");
1149
1150 /**
1151 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1152 * @since 1.2
1153 */
1154 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1155 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1156 "ENCLOSED CJK LETTERS AND MONTHS",
1157 "ENCLOSEDCJKLETTERSANDMONTHS");
1158
1159 /**
1160 * Constant for the "CJK Compatibility" Unicode character block.
1161 * @since 1.2
1162 */
1163 public static final UnicodeBlock CJK_COMPATIBILITY =
1164 new UnicodeBlock("CJK_COMPATIBILITY",
1165 "CJK COMPATIBILITY",
1166 "CJKCOMPATIBILITY");
1167
1168 /**
1169 * Constant for the "CJK Unified Ideographs" Unicode character block.
1170 * @since 1.2
1171 */
1172 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1173 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1174 "CJK UNIFIED IDEOGRAPHS",
1175 "CJKUNIFIEDIDEOGRAPHS");
1176
1177 /**
1178 * Constant for the "Hangul Syllables" Unicode character block.
1179 * @since 1.2
1180 */
1181 public static final UnicodeBlock HANGUL_SYLLABLES =
1182 new UnicodeBlock("HANGUL_SYLLABLES",
1183 "HANGUL SYLLABLES",
1184 "HANGULSYLLABLES");
1185
1186 /**
1187 * Constant for the "Private Use Area" Unicode character block.
1188 * @since 1.2
1189 */
1190 public static final UnicodeBlock PRIVATE_USE_AREA =
1191 new UnicodeBlock("PRIVATE_USE_AREA",
1192 "PRIVATE USE AREA",
1193 "PRIVATEUSEAREA");
1194
1195 /**
1196 * Constant for the "CJK Compatibility Ideographs" Unicode character
1197 * block.
1198 * @since 1.2
1199 */
1200 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1201 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1202 "CJK COMPATIBILITY IDEOGRAPHS",
1203 "CJKCOMPATIBILITYIDEOGRAPHS");
1204
1205 /**
1206 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1207 * @since 1.2
1208 */
1209 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1210 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1211 "ALPHABETIC PRESENTATION FORMS",
1212 "ALPHABETICPRESENTATIONFORMS");
1213
1214 /**
1215 * Constant for the "Arabic Presentation Forms-A" Unicode character
1216 * block.
1217 * @since 1.2
1218 */
1219 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1220 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1221 "ARABIC PRESENTATION FORMS-A",
1222 "ARABICPRESENTATIONFORMS-A");
1223
1224 /**
1225 * Constant for the "Combining Half Marks" Unicode character block.
1226 * @since 1.2
1227 */
1228 public static final UnicodeBlock COMBINING_HALF_MARKS =
1229 new UnicodeBlock("COMBINING_HALF_MARKS",
1230 "COMBINING HALF MARKS",
1231 "COMBININGHALFMARKS");
1232
1233 /**
1234 * Constant for the "CJK Compatibility Forms" Unicode character block.
1235 * @since 1.2
1236 */
1237 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1238 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1239 "CJK COMPATIBILITY FORMS",
1240 "CJKCOMPATIBILITYFORMS");
1241
1242 /**
1243 * Constant for the "Small Form Variants" Unicode character block.
1244 * @since 1.2
1245 */
1246 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1247 new UnicodeBlock("SMALL_FORM_VARIANTS",
1248 "SMALL FORM VARIANTS",
1249 "SMALLFORMVARIANTS");
1250
1251 /**
1252 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1253 * @since 1.2
1254 */
1255 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1256 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1257 "ARABIC PRESENTATION FORMS-B",
1258 "ARABICPRESENTATIONFORMS-B");
1259
1260 /**
1261 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1262 * block.
1263 * @since 1.2
1264 */
1265 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1266 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1267 "HALFWIDTH AND FULLWIDTH FORMS",
1268 "HALFWIDTHANDFULLWIDTHFORMS");
1269
1270 /**
1271 * Constant for the "Specials" Unicode character block.
1272 * @since 1.2
1273 */
1274 public static final UnicodeBlock SPECIALS =
1275 new UnicodeBlock("SPECIALS");
1276
1277 /**
1278 * @deprecated
1279 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1280 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1281 * These constants match the block definitions of the Unicode Standard.
1282 * The {@link #of(char)} and {@link #of(int)} methods return the
1283 * standard constants.
1284 */
1285 @Deprecated(since="1.5")
1286 public static final UnicodeBlock SURROGATES_AREA =
1287 new UnicodeBlock("SURROGATES_AREA");
1288
1289 /**
1290 * Constant for the "Syriac" Unicode character block.
1291 * @since 1.4
1292 */
1293 public static final UnicodeBlock SYRIAC =
1294 new UnicodeBlock("SYRIAC");
1295
1296 /**
1297 * Constant for the "Thaana" Unicode character block.
1298 * @since 1.4
1299 */
1300 public static final UnicodeBlock THAANA =
1301 new UnicodeBlock("THAANA");
1302
1303 /**
1304 * Constant for the "Sinhala" Unicode character block.
1305 * @since 1.4
1306 */
1307 public static final UnicodeBlock SINHALA =
1308 new UnicodeBlock("SINHALA");
1309
1310 /**
1311 * Constant for the "Myanmar" Unicode character block.
1312 * @since 1.4
1313 */
1314 public static final UnicodeBlock MYANMAR =
1315 new UnicodeBlock("MYANMAR");
1316
1317 /**
1318 * Constant for the "Ethiopic" Unicode character block.
1319 * @since 1.4
1320 */
1321 public static final UnicodeBlock ETHIOPIC =
1322 new UnicodeBlock("ETHIOPIC");
1323
1324 /**
1325 * Constant for the "Cherokee" Unicode character block.
1326 * @since 1.4
1327 */
1328 public static final UnicodeBlock CHEROKEE =
1329 new UnicodeBlock("CHEROKEE");
1330
1331 /**
1332 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1333 * @since 1.4
1334 */
1335 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1336 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1337 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1338 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1339
1340 /**
1341 * Constant for the "Ogham" Unicode character block.
1342 * @since 1.4
1343 */
1344 public static final UnicodeBlock OGHAM =
1345 new UnicodeBlock("OGHAM");
1346
1347 /**
1348 * Constant for the "Runic" Unicode character block.
1349 * @since 1.4
1350 */
1351 public static final UnicodeBlock RUNIC =
1352 new UnicodeBlock("RUNIC");
1353
1354 /**
1355 * Constant for the "Khmer" Unicode character block.
1356 * @since 1.4
1357 */
1358 public static final UnicodeBlock KHMER =
1359 new UnicodeBlock("KHMER");
1360
1361 /**
1362 * Constant for the "Mongolian" Unicode character block.
1363 * @since 1.4
1364 */
1365 public static final UnicodeBlock MONGOLIAN =
1366 new UnicodeBlock("MONGOLIAN");
1367
1368 /**
1369 * Constant for the "Braille Patterns" Unicode character block.
1370 * @since 1.4
1371 */
1372 public static final UnicodeBlock BRAILLE_PATTERNS =
1373 new UnicodeBlock("BRAILLE_PATTERNS",
1374 "BRAILLE PATTERNS",
1375 "BRAILLEPATTERNS");
1376
1377 /**
1378 * Constant for the "CJK Radicals Supplement" Unicode character block.
1379 * @since 1.4
1380 */
1381 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1382 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1383 "CJK RADICALS SUPPLEMENT",
1384 "CJKRADICALSSUPPLEMENT");
1385
1386 /**
1387 * Constant for the "Kangxi Radicals" Unicode character block.
1388 * @since 1.4
1389 */
1390 public static final UnicodeBlock KANGXI_RADICALS =
1391 new UnicodeBlock("KANGXI_RADICALS",
1392 "KANGXI RADICALS",
1393 "KANGXIRADICALS");
1394
1395 /**
1396 * Constant for the "Ideographic Description Characters" Unicode character block.
1397 * @since 1.4
1398 */
1399 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1400 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1401 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1402 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1403
1404 /**
1405 * Constant for the "Bopomofo Extended" Unicode character block.
1406 * @since 1.4
1407 */
1408 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1409 new UnicodeBlock("BOPOMOFO_EXTENDED",
1410 "BOPOMOFO EXTENDED",
1411 "BOPOMOFOEXTENDED");
1412
1413 /**
1414 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1415 * @since 1.4
1416 */
1417 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1418 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1419 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1420 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1421
1422 /**
1423 * Constant for the "Yi Syllables" Unicode character block.
1424 * @since 1.4
1425 */
1426 public static final UnicodeBlock YI_SYLLABLES =
1427 new UnicodeBlock("YI_SYLLABLES",
1428 "YI SYLLABLES",
1429 "YISYLLABLES");
1430
1431 /**
1432 * Constant for the "Yi Radicals" Unicode character block.
1433 * @since 1.4
1434 */
1435 public static final UnicodeBlock YI_RADICALS =
1436 new UnicodeBlock("YI_RADICALS",
1437 "YI RADICALS",
1438 "YIRADICALS");
1439
1440 /**
1441 * Constant for the "Cyrillic Supplement" Unicode character block.
1442 * This block was previously known as the "Cyrillic Supplementary" block.
1443 * @since 1.5
1444 */
1445 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1446 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1447 "CYRILLIC SUPPLEMENTARY",
1448 "CYRILLICSUPPLEMENTARY",
1449 "CYRILLIC SUPPLEMENT",
1450 "CYRILLICSUPPLEMENT");
1451
1452 /**
1453 * Constant for the "Tagalog" Unicode character block.
1454 * @since 1.5
1455 */
1456 public static final UnicodeBlock TAGALOG =
1457 new UnicodeBlock("TAGALOG");
1458
1459 /**
1460 * Constant for the "Hanunoo" Unicode character block.
1461 * @since 1.5
1462 */
1463 public static final UnicodeBlock HANUNOO =
1464 new UnicodeBlock("HANUNOO");
1465
1466 /**
1467 * Constant for the "Buhid" Unicode character block.
1468 * @since 1.5
1469 */
1470 public static final UnicodeBlock BUHID =
1471 new UnicodeBlock("BUHID");
1472
1473 /**
1474 * Constant for the "Tagbanwa" Unicode character block.
1475 * @since 1.5
1476 */
1477 public static final UnicodeBlock TAGBANWA =
1478 new UnicodeBlock("TAGBANWA");
1479
1480 /**
1481 * Constant for the "Limbu" Unicode character block.
1482 * @since 1.5
1483 */
1484 public static final UnicodeBlock LIMBU =
1485 new UnicodeBlock("LIMBU");
1486
1487 /**
1488 * Constant for the "Tai Le" Unicode character block.
1489 * @since 1.5
1490 */
1491 public static final UnicodeBlock TAI_LE =
1492 new UnicodeBlock("TAI_LE",
1493 "TAI LE",
1494 "TAILE");
1495
1496 /**
1497 * Constant for the "Khmer Symbols" Unicode character block.
1498 * @since 1.5
1499 */
1500 public static final UnicodeBlock KHMER_SYMBOLS =
1501 new UnicodeBlock("KHMER_SYMBOLS",
1502 "KHMER SYMBOLS",
1503 "KHMERSYMBOLS");
1504
1505 /**
1506 * Constant for the "Phonetic Extensions" Unicode character block.
1507 * @since 1.5
1508 */
1509 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1510 new UnicodeBlock("PHONETIC_EXTENSIONS",
1511 "PHONETIC EXTENSIONS",
1512 "PHONETICEXTENSIONS");
1513
1514 /**
1515 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1516 * @since 1.5
1517 */
1518 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1519 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1520 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1521 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1522
1523 /**
1524 * Constant for the "Supplemental Arrows-A" Unicode character block.
1525 * @since 1.5
1526 */
1527 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1528 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1529 "SUPPLEMENTAL ARROWS-A",
1530 "SUPPLEMENTALARROWS-A");
1531
1532 /**
1533 * Constant for the "Supplemental Arrows-B" Unicode character block.
1534 * @since 1.5
1535 */
1536 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1537 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1538 "SUPPLEMENTAL ARROWS-B",
1539 "SUPPLEMENTALARROWS-B");
1540
1541 /**
1542 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1543 * character block.
1544 * @since 1.5
1545 */
1546 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1547 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1548 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1549 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1550
1551 /**
1552 * Constant for the "Supplemental Mathematical Operators" Unicode
1553 * character block.
1554 * @since 1.5
1555 */
1556 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1557 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1558 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1559 "SUPPLEMENTALMATHEMATICALOPERATORS");
1560
1561 /**
1562 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1563 * block.
1564 * @since 1.5
1565 */
1566 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1567 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1568 "MISCELLANEOUS SYMBOLS AND ARROWS",
1569 "MISCELLANEOUSSYMBOLSANDARROWS");
1570
1571 /**
1572 * Constant for the "Katakana Phonetic Extensions" Unicode character
1573 * block.
1574 * @since 1.5
1575 */
1576 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1577 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1578 "KATAKANA PHONETIC EXTENSIONS",
1579 "KATAKANAPHONETICEXTENSIONS");
1580
1581 /**
1582 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1583 * @since 1.5
1584 */
1585 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1586 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1587 "YIJING HEXAGRAM SYMBOLS",
1588 "YIJINGHEXAGRAMSYMBOLS");
1589
1590 /**
1591 * Constant for the "Variation Selectors" Unicode character block.
1592 * @since 1.5
1593 */
1594 public static final UnicodeBlock VARIATION_SELECTORS =
1595 new UnicodeBlock("VARIATION_SELECTORS",
1596 "VARIATION SELECTORS",
1597 "VARIATIONSELECTORS");
1598
1599 /**
1600 * Constant for the "Linear B Syllabary" Unicode character block.
1601 * @since 1.5
1602 */
1603 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1604 new UnicodeBlock("LINEAR_B_SYLLABARY",
1605 "LINEAR B SYLLABARY",
1606 "LINEARBSYLLABARY");
1607
1608 /**
1609 * Constant for the "Linear B Ideograms" Unicode character block.
1610 * @since 1.5
1611 */
1612 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1613 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1614 "LINEAR B IDEOGRAMS",
1615 "LINEARBIDEOGRAMS");
1616
1617 /**
1618 * Constant for the "Aegean Numbers" Unicode character block.
1619 * @since 1.5
1620 */
1621 public static final UnicodeBlock AEGEAN_NUMBERS =
1622 new UnicodeBlock("AEGEAN_NUMBERS",
1623 "AEGEAN NUMBERS",
1624 "AEGEANNUMBERS");
1625
1626 /**
1627 * Constant for the "Old Italic" Unicode character block.
1628 * @since 1.5
1629 */
1630 public static final UnicodeBlock OLD_ITALIC =
1631 new UnicodeBlock("OLD_ITALIC",
1632 "OLD ITALIC",
1633 "OLDITALIC");
1634
1635 /**
1636 * Constant for the "Gothic" Unicode character block.
1637 * @since 1.5
1638 */
1639 public static final UnicodeBlock GOTHIC =
1640 new UnicodeBlock("GOTHIC");
1641
1642 /**
1643 * Constant for the "Ugaritic" Unicode character block.
1644 * @since 1.5
1645 */
1646 public static final UnicodeBlock UGARITIC =
1647 new UnicodeBlock("UGARITIC");
1648
1649 /**
1650 * Constant for the "Deseret" Unicode character block.
1651 * @since 1.5
1652 */
1653 public static final UnicodeBlock DESERET =
1654 new UnicodeBlock("DESERET");
1655
1656 /**
1657 * Constant for the "Shavian" Unicode character block.
1658 * @since 1.5
1659 */
1660 public static final UnicodeBlock SHAVIAN =
1661 new UnicodeBlock("SHAVIAN");
1662
1663 /**
1664 * Constant for the "Osmanya" Unicode character block.
1665 * @since 1.5
1666 */
1667 public static final UnicodeBlock OSMANYA =
1668 new UnicodeBlock("OSMANYA");
1669
1670 /**
1671 * Constant for the "Cypriot Syllabary" Unicode character block.
1672 * @since 1.5
1673 */
1674 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1675 new UnicodeBlock("CYPRIOT_SYLLABARY",
1676 "CYPRIOT SYLLABARY",
1677 "CYPRIOTSYLLABARY");
1678
1679 /**
1680 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1681 * @since 1.5
1682 */
1683 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1684 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1685 "BYZANTINE MUSICAL SYMBOLS",
1686 "BYZANTINEMUSICALSYMBOLS");
1687
1688 /**
1689 * Constant for the "Musical Symbols" Unicode character block.
1690 * @since 1.5
1691 */
1692 public static final UnicodeBlock MUSICAL_SYMBOLS =
1693 new UnicodeBlock("MUSICAL_SYMBOLS",
1694 "MUSICAL SYMBOLS",
1695 "MUSICALSYMBOLS");
1696
1697 /**
1698 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1699 * @since 1.5
1700 */
1701 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1702 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1703 "TAI XUAN JING SYMBOLS",
1704 "TAIXUANJINGSYMBOLS");
1705
1706 /**
1707 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1708 * character block.
1709 * @since 1.5
1710 */
1711 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1712 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1713 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1714 "MATHEMATICALALPHANUMERICSYMBOLS");
1715
1716 /**
1717 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1718 * character block.
1719 * @since 1.5
1720 */
1721 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1722 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1723 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1724 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1725
1726 /**
1727 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1728 * @since 1.5
1729 */
1730 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1731 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1732 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1733 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1734
1735 /**
1736 * Constant for the "Tags" Unicode character block.
1737 * @since 1.5
1738 */
1739 public static final UnicodeBlock TAGS =
1740 new UnicodeBlock("TAGS");
1741
1742 /**
1743 * Constant for the "Variation Selectors Supplement" Unicode character
1744 * block.
1745 * @since 1.5
1746 */
1747 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1748 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1749 "VARIATION SELECTORS SUPPLEMENT",
1750 "VARIATIONSELECTORSSUPPLEMENT");
1751
1752 /**
1753 * Constant for the "Supplementary Private Use Area-A" Unicode character
1754 * block.
1755 * @since 1.5
1756 */
1757 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1758 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1759 "SUPPLEMENTARY PRIVATE USE AREA-A",
1760 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1761
1762 /**
1763 * Constant for the "Supplementary Private Use Area-B" Unicode character
1764 * block.
1765 * @since 1.5
1766 */
1767 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1768 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1769 "SUPPLEMENTARY PRIVATE USE AREA-B",
1770 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1771
1772 /**
1773 * Constant for the "High Surrogates" Unicode character block.
1774 * This block represents codepoint values in the high surrogate
1775 * range: U+D800 through U+DB7F
1776 *
1777 * @since 1.5
1778 */
1779 public static final UnicodeBlock HIGH_SURROGATES =
1780 new UnicodeBlock("HIGH_SURROGATES",
1781 "HIGH SURROGATES",
1782 "HIGHSURROGATES");
1783
1784 /**
1785 * Constant for the "High Private Use Surrogates" Unicode character
1786 * block.
1787 * This block represents codepoint values in the private use high
1788 * surrogate range: U+DB80 through U+DBFF
1789 *
1790 * @since 1.5
1791 */
1792 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1793 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1794 "HIGH PRIVATE USE SURROGATES",
1795 "HIGHPRIVATEUSESURROGATES");
1796
1797 /**
1798 * Constant for the "Low Surrogates" Unicode character block.
1799 * This block represents codepoint values in the low surrogate
1800 * range: U+DC00 through U+DFFF
1801 *
1802 * @since 1.5
1803 */
1804 public static final UnicodeBlock LOW_SURROGATES =
1805 new UnicodeBlock("LOW_SURROGATES",
1806 "LOW SURROGATES",
1807 "LOWSURROGATES");
1808
1809 /**
1810 * Constant for the "Arabic Supplement" Unicode character block.
1811 * @since 1.7
1812 */
1813 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1814 new UnicodeBlock("ARABIC_SUPPLEMENT",
1815 "ARABIC SUPPLEMENT",
1816 "ARABICSUPPLEMENT");
1817
1818 /**
1819 * Constant for the "NKo" Unicode character block.
1820 * @since 1.7
1821 */
1822 public static final UnicodeBlock NKO =
1823 new UnicodeBlock("NKO");
1824
1825 /**
1826 * Constant for the "Samaritan" Unicode character block.
1827 * @since 1.7
1828 */
1829 public static final UnicodeBlock SAMARITAN =
1830 new UnicodeBlock("SAMARITAN");
1831
1832 /**
1833 * Constant for the "Mandaic" Unicode character block.
1834 * @since 1.7
1835 */
1836 public static final UnicodeBlock MANDAIC =
1837 new UnicodeBlock("MANDAIC");
1838
1839 /**
1840 * Constant for the "Ethiopic Supplement" Unicode character block.
1841 * @since 1.7
1842 */
1843 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1844 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1845 "ETHIOPIC SUPPLEMENT",
1846 "ETHIOPICSUPPLEMENT");
1847
1848 /**
1849 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1850 * Unicode character block.
1851 * @since 1.7
1852 */
1853 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1854 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1855 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1856 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1857
1858 /**
1859 * Constant for the "New Tai Lue" Unicode character block.
1860 * @since 1.7
1861 */
1862 public static final UnicodeBlock NEW_TAI_LUE =
1863 new UnicodeBlock("NEW_TAI_LUE",
1864 "NEW TAI LUE",
1865 "NEWTAILUE");
1866
1867 /**
1868 * Constant for the "Buginese" Unicode character block.
1869 * @since 1.7
1870 */
1871 public static final UnicodeBlock BUGINESE =
1872 new UnicodeBlock("BUGINESE");
1873
1874 /**
1875 * Constant for the "Tai Tham" Unicode character block.
1876 * @since 1.7
1877 */
1878 public static final UnicodeBlock TAI_THAM =
1879 new UnicodeBlock("TAI_THAM",
1880 "TAI THAM",
1881 "TAITHAM");
1882
1883 /**
1884 * Constant for the "Balinese" Unicode character block.
1885 * @since 1.7
1886 */
1887 public static final UnicodeBlock BALINESE =
1888 new UnicodeBlock("BALINESE");
1889
1890 /**
1891 * Constant for the "Sundanese" Unicode character block.
1892 * @since 1.7
1893 */
1894 public static final UnicodeBlock SUNDANESE =
1895 new UnicodeBlock("SUNDANESE");
1896
1897 /**
1898 * Constant for the "Batak" Unicode character block.
1899 * @since 1.7
1900 */
1901 public static final UnicodeBlock BATAK =
1902 new UnicodeBlock("BATAK");
1903
1904 /**
1905 * Constant for the "Lepcha" Unicode character block.
1906 * @since 1.7
1907 */
1908 public static final UnicodeBlock LEPCHA =
1909 new UnicodeBlock("LEPCHA");
1910
1911 /**
1912 * Constant for the "Ol Chiki" Unicode character block.
1913 * @since 1.7
1914 */
1915 public static final UnicodeBlock OL_CHIKI =
1916 new UnicodeBlock("OL_CHIKI",
1917 "OL CHIKI",
1918 "OLCHIKI");
1919
1920 /**
1921 * Constant for the "Vedic Extensions" Unicode character block.
1922 * @since 1.7
1923 */
1924 public static final UnicodeBlock VEDIC_EXTENSIONS =
1925 new UnicodeBlock("VEDIC_EXTENSIONS",
1926 "VEDIC EXTENSIONS",
1927 "VEDICEXTENSIONS");
1928
1929 /**
1930 * Constant for the "Phonetic Extensions Supplement" Unicode character
1931 * block.
1932 * @since 1.7
1933 */
1934 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1935 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1936 "PHONETIC EXTENSIONS SUPPLEMENT",
1937 "PHONETICEXTENSIONSSUPPLEMENT");
1938
1939 /**
1940 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1941 * character block.
1942 * @since 1.7
1943 */
1944 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1945 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1946 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1947 "COMBININGDIACRITICALMARKSSUPPLEMENT");
1948
1949 /**
1950 * Constant for the "Glagolitic" Unicode character block.
1951 * @since 1.7
1952 */
1953 public static final UnicodeBlock GLAGOLITIC =
1954 new UnicodeBlock("GLAGOLITIC");
1955
1956 /**
1957 * Constant for the "Latin Extended-C" Unicode character block.
1958 * @since 1.7
1959 */
1960 public static final UnicodeBlock LATIN_EXTENDED_C =
1961 new UnicodeBlock("LATIN_EXTENDED_C",
1962 "LATIN EXTENDED-C",
1963 "LATINEXTENDED-C");
1964
1965 /**
1966 * Constant for the "Coptic" Unicode character block.
1967 * @since 1.7
1968 */
1969 public static final UnicodeBlock COPTIC =
1970 new UnicodeBlock("COPTIC");
1971
1972 /**
1973 * Constant for the "Georgian Supplement" Unicode character block.
1974 * @since 1.7
1975 */
1976 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
1977 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
1978 "GEORGIAN SUPPLEMENT",
1979 "GEORGIANSUPPLEMENT");
1980
1981 /**
1982 * Constant for the "Tifinagh" Unicode character block.
1983 * @since 1.7
1984 */
1985 public static final UnicodeBlock TIFINAGH =
1986 new UnicodeBlock("TIFINAGH");
1987
1988 /**
1989 * Constant for the "Ethiopic Extended" Unicode character block.
1990 * @since 1.7
1991 */
1992 public static final UnicodeBlock ETHIOPIC_EXTENDED =
1993 new UnicodeBlock("ETHIOPIC_EXTENDED",
1994 "ETHIOPIC EXTENDED",
1995 "ETHIOPICEXTENDED");
1996
1997 /**
1998 * Constant for the "Cyrillic Extended-A" Unicode character block.
1999 * @since 1.7
2000 */
2001 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2002 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2003 "CYRILLIC EXTENDED-A",
2004 "CYRILLICEXTENDED-A");
2005
2006 /**
2007 * Constant for the "Supplemental Punctuation" Unicode character block.
2008 * @since 1.7
2009 */
2010 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2011 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2012 "SUPPLEMENTAL PUNCTUATION",
2013 "SUPPLEMENTALPUNCTUATION");
2014
2015 /**
2016 * Constant for the "CJK Strokes" Unicode character block.
2017 * @since 1.7
2018 */
2019 public static final UnicodeBlock CJK_STROKES =
2020 new UnicodeBlock("CJK_STROKES",
2021 "CJK STROKES",
2022 "CJKSTROKES");
2023
2024 /**
2025 * Constant for the "Lisu" Unicode character block.
2026 * @since 1.7
2027 */
2028 public static final UnicodeBlock LISU =
2029 new UnicodeBlock("LISU");
2030
2031 /**
2032 * Constant for the "Vai" Unicode character block.
2033 * @since 1.7
2034 */
2035 public static final UnicodeBlock VAI =
2036 new UnicodeBlock("VAI");
2037
2038 /**
2039 * Constant for the "Cyrillic Extended-B" Unicode character block.
2040 * @since 1.7
2041 */
2042 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2043 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2044 "CYRILLIC EXTENDED-B",
2045 "CYRILLICEXTENDED-B");
2046
2047 /**
2048 * Constant for the "Bamum" Unicode character block.
2049 * @since 1.7
2050 */
2051 public static final UnicodeBlock BAMUM =
2052 new UnicodeBlock("BAMUM");
2053
2054 /**
2055 * Constant for the "Modifier Tone Letters" Unicode character block.
2056 * @since 1.7
2057 */
2058 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2059 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2060 "MODIFIER TONE LETTERS",
2061 "MODIFIERTONELETTERS");
2062
2063 /**
2064 * Constant for the "Latin Extended-D" Unicode character block.
2065 * @since 1.7
2066 */
2067 public static final UnicodeBlock LATIN_EXTENDED_D =
2068 new UnicodeBlock("LATIN_EXTENDED_D",
2069 "LATIN EXTENDED-D",
2070 "LATINEXTENDED-D");
2071
2072 /**
2073 * Constant for the "Syloti Nagri" Unicode character block.
2074 * @since 1.7
2075 */
2076 public static final UnicodeBlock SYLOTI_NAGRI =
2077 new UnicodeBlock("SYLOTI_NAGRI",
2078 "SYLOTI NAGRI",
2079 "SYLOTINAGRI");
2080
2081 /**
2082 * Constant for the "Common Indic Number Forms" Unicode character block.
2083 * @since 1.7
2084 */
2085 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2086 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2087 "COMMON INDIC NUMBER FORMS",
2088 "COMMONINDICNUMBERFORMS");
2089
2090 /**
2091 * Constant for the "Phags-pa" Unicode character block.
2092 * @since 1.7
2093 */
2094 public static final UnicodeBlock PHAGS_PA =
2095 new UnicodeBlock("PHAGS_PA",
2096 "PHAGS-PA");
2097
2098 /**
2099 * Constant for the "Saurashtra" Unicode character block.
2100 * @since 1.7
2101 */
2102 public static final UnicodeBlock SAURASHTRA =
2103 new UnicodeBlock("SAURASHTRA");
2104
2105 /**
2106 * Constant for the "Devanagari Extended" Unicode character block.
2107 * @since 1.7
2108 */
2109 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2110 new UnicodeBlock("DEVANAGARI_EXTENDED",
2111 "DEVANAGARI EXTENDED",
2112 "DEVANAGARIEXTENDED");
2113
2114 /**
2115 * Constant for the "Kayah Li" Unicode character block.
2116 * @since 1.7
2117 */
2118 public static final UnicodeBlock KAYAH_LI =
2119 new UnicodeBlock("KAYAH_LI",
2120 "KAYAH LI",
2121 "KAYAHLI");
2122
2123 /**
2124 * Constant for the "Rejang" Unicode character block.
2125 * @since 1.7
2126 */
2127 public static final UnicodeBlock REJANG =
2128 new UnicodeBlock("REJANG");
2129
2130 /**
2131 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2132 * @since 1.7
2133 */
2134 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2135 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2136 "HANGUL JAMO EXTENDED-A",
2137 "HANGULJAMOEXTENDED-A");
2138
2139 /**
2140 * Constant for the "Javanese" Unicode character block.
2141 * @since 1.7
2142 */
2143 public static final UnicodeBlock JAVANESE =
2144 new UnicodeBlock("JAVANESE");
2145
2146 /**
2147 * Constant for the "Cham" Unicode character block.
2148 * @since 1.7
2149 */
2150 public static final UnicodeBlock CHAM =
2151 new UnicodeBlock("CHAM");
2152
2153 /**
2154 * Constant for the "Myanmar Extended-A" Unicode character block.
2155 * @since 1.7
2156 */
2157 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2158 new UnicodeBlock("MYANMAR_EXTENDED_A",
2159 "MYANMAR EXTENDED-A",
2160 "MYANMAREXTENDED-A");
2161
2162 /**
2163 * Constant for the "Tai Viet" Unicode character block.
2164 * @since 1.7
2165 */
2166 public static final UnicodeBlock TAI_VIET =
2167 new UnicodeBlock("TAI_VIET",
2168 "TAI VIET",
2169 "TAIVIET");
2170
2171 /**
2172 * Constant for the "Ethiopic Extended-A" Unicode character block.
2173 * @since 1.7
2174 */
2175 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2176 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2177 "ETHIOPIC EXTENDED-A",
2178 "ETHIOPICEXTENDED-A");
2179
2180 /**
2181 * Constant for the "Meetei Mayek" Unicode character block.
2182 * @since 1.7
2183 */
2184 public static final UnicodeBlock MEETEI_MAYEK =
2185 new UnicodeBlock("MEETEI_MAYEK",
2186 "MEETEI MAYEK",
2187 "MEETEIMAYEK");
2188
2189 /**
2190 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2191 * @since 1.7
2192 */
2193 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2194 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2195 "HANGUL JAMO EXTENDED-B",
2196 "HANGULJAMOEXTENDED-B");
2197
2198 /**
2199 * Constant for the "Vertical Forms" Unicode character block.
2200 * @since 1.7
2201 */
2202 public static final UnicodeBlock VERTICAL_FORMS =
2203 new UnicodeBlock("VERTICAL_FORMS",
2204 "VERTICAL FORMS",
2205 "VERTICALFORMS");
2206
2207 /**
2208 * Constant for the "Ancient Greek Numbers" Unicode character block.
2209 * @since 1.7
2210 */
2211 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2212 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2213 "ANCIENT GREEK NUMBERS",
2214 "ANCIENTGREEKNUMBERS");
2215
2216 /**
2217 * Constant for the "Ancient Symbols" Unicode character block.
2218 * @since 1.7
2219 */
2220 public static final UnicodeBlock ANCIENT_SYMBOLS =
2221 new UnicodeBlock("ANCIENT_SYMBOLS",
2222 "ANCIENT SYMBOLS",
2223 "ANCIENTSYMBOLS");
2224
2225 /**
2226 * Constant for the "Phaistos Disc" Unicode character block.
2227 * @since 1.7
2228 */
2229 public static final UnicodeBlock PHAISTOS_DISC =
2230 new UnicodeBlock("PHAISTOS_DISC",
2231 "PHAISTOS DISC",
2232 "PHAISTOSDISC");
2233
2234 /**
2235 * Constant for the "Lycian" Unicode character block.
2236 * @since 1.7
2237 */
2238 public static final UnicodeBlock LYCIAN =
2239 new UnicodeBlock("LYCIAN");
2240
2241 /**
2242 * Constant for the "Carian" Unicode character block.
2243 * @since 1.7
2244 */
2245 public static final UnicodeBlock CARIAN =
2246 new UnicodeBlock("CARIAN");
2247
2248 /**
2249 * Constant for the "Old Persian" Unicode character block.
2250 * @since 1.7
2251 */
2252 public static final UnicodeBlock OLD_PERSIAN =
2253 new UnicodeBlock("OLD_PERSIAN",
2254 "OLD PERSIAN",
2255 "OLDPERSIAN");
2256
2257 /**
2258 * Constant for the "Imperial Aramaic" Unicode character block.
2259 * @since 1.7
2260 */
2261 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2262 new UnicodeBlock("IMPERIAL_ARAMAIC",
2263 "IMPERIAL ARAMAIC",
2264 "IMPERIALARAMAIC");
2265
2266 /**
2267 * Constant for the "Phoenician" Unicode character block.
2268 * @since 1.7
2269 */
2270 public static final UnicodeBlock PHOENICIAN =
2271 new UnicodeBlock("PHOENICIAN");
2272
2273 /**
2274 * Constant for the "Lydian" Unicode character block.
2275 * @since 1.7
2276 */
2277 public static final UnicodeBlock LYDIAN =
2278 new UnicodeBlock("LYDIAN");
2279
2280 /**
2281 * Constant for the "Kharoshthi" Unicode character block.
2282 * @since 1.7
2283 */
2284 public static final UnicodeBlock KHAROSHTHI =
2285 new UnicodeBlock("KHAROSHTHI");
2286
2287 /**
2288 * Constant for the "Old South Arabian" Unicode character block.
2289 * @since 1.7
2290 */
2291 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2292 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2293 "OLD SOUTH ARABIAN",
2294 "OLDSOUTHARABIAN");
2295
2296 /**
2297 * Constant for the "Avestan" Unicode character block.
2298 * @since 1.7
2299 */
2300 public static final UnicodeBlock AVESTAN =
2301 new UnicodeBlock("AVESTAN");
2302
2303 /**
2304 * Constant for the "Inscriptional Parthian" Unicode character block.
2305 * @since 1.7
2306 */
2307 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2308 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2309 "INSCRIPTIONAL PARTHIAN",
2310 "INSCRIPTIONALPARTHIAN");
2311
2312 /**
2313 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2314 * @since 1.7
2315 */
2316 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2317 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2318 "INSCRIPTIONAL PAHLAVI",
2319 "INSCRIPTIONALPAHLAVI");
2320
2321 /**
2322 * Constant for the "Old Turkic" Unicode character block.
2323 * @since 1.7
2324 */
2325 public static final UnicodeBlock OLD_TURKIC =
2326 new UnicodeBlock("OLD_TURKIC",
2327 "OLD TURKIC",
2328 "OLDTURKIC");
2329
2330 /**
2331 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2332 * @since 1.7
2333 */
2334 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2335 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2336 "RUMI NUMERAL SYMBOLS",
2337 "RUMINUMERALSYMBOLS");
2338
2339 /**
2340 * Constant for the "Brahmi" Unicode character block.
2341 * @since 1.7
2342 */
2343 public static final UnicodeBlock BRAHMI =
2344 new UnicodeBlock("BRAHMI");
2345
2346 /**
2347 * Constant for the "Kaithi" Unicode character block.
2348 * @since 1.7
2349 */
2350 public static final UnicodeBlock KAITHI =
2351 new UnicodeBlock("KAITHI");
2352
2353 /**
2354 * Constant for the "Cuneiform" Unicode character block.
2355 * @since 1.7
2356 */
2357 public static final UnicodeBlock CUNEIFORM =
2358 new UnicodeBlock("CUNEIFORM");
2359
2360 /**
2361 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2362 * character block.
2363 * @since 1.7
2364 */
2365 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2366 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2367 "CUNEIFORM NUMBERS AND PUNCTUATION",
2368 "CUNEIFORMNUMBERSANDPUNCTUATION");
2369
2370 /**
2371 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2372 * @since 1.7
2373 */
2374 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2375 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2376 "EGYPTIAN HIEROGLYPHS",
2377 "EGYPTIANHIEROGLYPHS");
2378
2379 /**
2380 * Constant for the "Bamum Supplement" Unicode character block.
2381 * @since 1.7
2382 */
2383 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2384 new UnicodeBlock("BAMUM_SUPPLEMENT",
2385 "BAMUM SUPPLEMENT",
2386 "BAMUMSUPPLEMENT");
2387
2388 /**
2389 * Constant for the "Kana Supplement" Unicode character block.
2390 * @since 1.7
2391 */
2392 public static final UnicodeBlock KANA_SUPPLEMENT =
2393 new UnicodeBlock("KANA_SUPPLEMENT",
2394 "KANA SUPPLEMENT",
2395 "KANASUPPLEMENT");
2396
2397 /**
2398 * Constant for the "Ancient Greek Musical Notation" Unicode character
2399 * block.
2400 * @since 1.7
2401 */
2402 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2403 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2404 "ANCIENT GREEK MUSICAL NOTATION",
2405 "ANCIENTGREEKMUSICALNOTATION");
2406
2407 /**
2408 * Constant for the "Counting Rod Numerals" Unicode character block.
2409 * @since 1.7
2410 */
2411 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2412 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2413 "COUNTING ROD NUMERALS",
2414 "COUNTINGRODNUMERALS");
2415
2416 /**
2417 * Constant for the "Mahjong Tiles" Unicode character block.
2418 * @since 1.7
2419 */
2420 public static final UnicodeBlock MAHJONG_TILES =
2421 new UnicodeBlock("MAHJONG_TILES",
2422 "MAHJONG TILES",
2423 "MAHJONGTILES");
2424
2425 /**
2426 * Constant for the "Domino Tiles" Unicode character block.
2427 * @since 1.7
2428 */
2429 public static final UnicodeBlock DOMINO_TILES =
2430 new UnicodeBlock("DOMINO_TILES",
2431 "DOMINO TILES",
2432 "DOMINOTILES");
2433
2434 /**
2435 * Constant for the "Playing Cards" Unicode character block.
2436 * @since 1.7
2437 */
2438 public static final UnicodeBlock PLAYING_CARDS =
2439 new UnicodeBlock("PLAYING_CARDS",
2440 "PLAYING CARDS",
2441 "PLAYINGCARDS");
2442
2443 /**
2444 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2445 * block.
2446 * @since 1.7
2447 */
2448 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2449 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2450 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2451 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2452
2453 /**
2454 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2455 * block.
2456 * @since 1.7
2457 */
2458 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2459 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2460 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2461 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2462
2463 /**
2464 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2465 * character block.
2466 * @since 1.7
2467 */
2468 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2469 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2470 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2471 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2472
2473 /**
2474 * Constant for the "Emoticons" Unicode character block.
2475 * @since 1.7
2476 */
2477 public static final UnicodeBlock EMOTICONS =
2478 new UnicodeBlock("EMOTICONS");
2479
2480 /**
2481 * Constant for the "Transport And Map Symbols" Unicode character block.
2482 * @since 1.7
2483 */
2484 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2485 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2486 "TRANSPORT AND MAP SYMBOLS",
2487 "TRANSPORTANDMAPSYMBOLS");
2488
2489 /**
2490 * Constant for the "Alchemical Symbols" Unicode character block.
2491 * @since 1.7
2492 */
2493 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2494 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2495 "ALCHEMICAL SYMBOLS",
2496 "ALCHEMICALSYMBOLS");
2497
2498 /**
2499 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2500 * character block.
2501 * @since 1.7
2502 */
2503 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2504 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2505 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2506 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2507
2508 /**
2509 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2510 * character block.
2511 * @since 1.7
2512 */
2513 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2514 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2515 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2516 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2517
2518 /**
2519 * Constant for the "Arabic Extended-A" Unicode character block.
2520 * @since 1.8
2521 */
2522 public static final UnicodeBlock ARABIC_EXTENDED_A =
2523 new UnicodeBlock("ARABIC_EXTENDED_A",
2524 "ARABIC EXTENDED-A",
2525 "ARABICEXTENDED-A");
2526
2527 /**
2528 * Constant for the "Sundanese Supplement" Unicode character block.
2529 * @since 1.8
2530 */
2531 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2532 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2533 "SUNDANESE SUPPLEMENT",
2534 "SUNDANESESUPPLEMENT");
2535
2536 /**
2537 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2538 * @since 1.8
2539 */
2540 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2541 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2542 "MEETEI MAYEK EXTENSIONS",
2543 "MEETEIMAYEKEXTENSIONS");
2544
2545 /**
2546 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2547 * @since 1.8
2548 */
2549 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2550 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2551 "MEROITIC HIEROGLYPHS",
2552 "MEROITICHIEROGLYPHS");
2553
2554 /**
2555 * Constant for the "Meroitic Cursive" Unicode character block.
2556 * @since 1.8
2557 */
2558 public static final UnicodeBlock MEROITIC_CURSIVE =
2559 new UnicodeBlock("MEROITIC_CURSIVE",
2560 "MEROITIC CURSIVE",
2561 "MEROITICCURSIVE");
2562
2563 /**
2564 * Constant for the "Sora Sompeng" Unicode character block.
2565 * @since 1.8
2566 */
2567 public static final UnicodeBlock SORA_SOMPENG =
2568 new UnicodeBlock("SORA_SOMPENG",
2569 "SORA SOMPENG",
2570 "SORASOMPENG");
2571
2572 /**
2573 * Constant for the "Chakma" Unicode character block.
2574 * @since 1.8
2575 */
2576 public static final UnicodeBlock CHAKMA =
2577 new UnicodeBlock("CHAKMA");
2578
2579 /**
2580 * Constant for the "Sharada" Unicode character block.
2581 * @since 1.8
2582 */
2583 public static final UnicodeBlock SHARADA =
2584 new UnicodeBlock("SHARADA");
2585
2586 /**
2587 * Constant for the "Takri" Unicode character block.
2588 * @since 1.8
2589 */
2590 public static final UnicodeBlock TAKRI =
2591 new UnicodeBlock("TAKRI");
2592
2593 /**
2594 * Constant for the "Miao" Unicode character block.
2595 * @since 1.8
2596 */
2597 public static final UnicodeBlock MIAO =
2598 new UnicodeBlock("MIAO");
2599
2600 /**
2601 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2602 * character block.
2603 * @since 1.8
2604 */
2605 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2606 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2607 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2608 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2609
2610 /**
2611 * Constant for the "Combining Diacritical Marks Extended" Unicode
2612 * character block.
2613 * @since 9
2614 */
2615 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2616 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2617 "COMBINING DIACRITICAL MARKS EXTENDED",
2618 "COMBININGDIACRITICALMARKSEXTENDED");
2619
2620 /**
2621 * Constant for the "Myanmar Extended-B" Unicode character block.
2622 * @since 9
2623 */
2624 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2625 new UnicodeBlock("MYANMAR_EXTENDED_B",
2626 "MYANMAR EXTENDED-B",
2627 "MYANMAREXTENDED-B");
2628
2629 /**
2630 * Constant for the "Latin Extended-E" Unicode character block.
2631 * @since 9
2632 */
2633 public static final UnicodeBlock LATIN_EXTENDED_E =
2634 new UnicodeBlock("LATIN_EXTENDED_E",
2635 "LATIN EXTENDED-E",
2636 "LATINEXTENDED-E");
2637
2638 /**
2639 * Constant for the "Coptic Epact Numbers" Unicode character block.
2640 * @since 9
2641 */
2642 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2643 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2644 "COPTIC EPACT NUMBERS",
2645 "COPTICEPACTNUMBERS");
2646
2647 /**
2648 * Constant for the "Old Permic" Unicode character block.
2649 * @since 9
2650 */
2651 public static final UnicodeBlock OLD_PERMIC =
2652 new UnicodeBlock("OLD_PERMIC",
2653 "OLD PERMIC",
2654 "OLDPERMIC");
2655
2656 /**
2657 * Constant for the "Elbasan" Unicode character block.
2658 * @since 9
2659 */
2660 public static final UnicodeBlock ELBASAN =
2661 new UnicodeBlock("ELBASAN");
2662
2663 /**
2664 * Constant for the "Caucasian Albanian" Unicode character block.
2665 * @since 9
2666 */
2667 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2668 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2669 "CAUCASIAN ALBANIAN",
2670 "CAUCASIANALBANIAN");
2671
2672 /**
2673 * Constant for the "Linear A" Unicode character block.
2674 * @since 9
2675 */
2676 public static final UnicodeBlock LINEAR_A =
2677 new UnicodeBlock("LINEAR_A",
2678 "LINEAR A",
2679 "LINEARA");
2680
2681 /**
2682 * Constant for the "Palmyrene" Unicode character block.
2683 * @since 9
2684 */
2685 public static final UnicodeBlock PALMYRENE =
2686 new UnicodeBlock("PALMYRENE");
2687
2688 /**
2689 * Constant for the "Nabataean" Unicode character block.
2690 * @since 9
2691 */
2692 public static final UnicodeBlock NABATAEAN =
2693 new UnicodeBlock("NABATAEAN");
2694
2695 /**
2696 * Constant for the "Old North Arabian" Unicode character block.
2697 * @since 9
2698 */
2699 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2700 new UnicodeBlock("OLD_NORTH_ARABIAN",
2701 "OLD NORTH ARABIAN",
2702 "OLDNORTHARABIAN");
2703
2704 /**
2705 * Constant for the "Manichaean" Unicode character block.
2706 * @since 9
2707 */
2708 public static final UnicodeBlock MANICHAEAN =
2709 new UnicodeBlock("MANICHAEAN");
2710
2711 /**
2712 * Constant for the "Psalter Pahlavi" Unicode character block.
2713 * @since 9
2714 */
2715 public static final UnicodeBlock PSALTER_PAHLAVI =
2716 new UnicodeBlock("PSALTER_PAHLAVI",
2717 "PSALTER PAHLAVI",
2718 "PSALTERPAHLAVI");
2719
2720 /**
2721 * Constant for the "Mahajani" Unicode character block.
2722 * @since 9
2723 */
2724 public static final UnicodeBlock MAHAJANI =
2725 new UnicodeBlock("MAHAJANI");
2726
2727 /**
2728 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2729 * @since 9
2730 */
2731 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2732 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2733 "SINHALA ARCHAIC NUMBERS",
2734 "SINHALAARCHAICNUMBERS");
2735
2736 /**
2737 * Constant for the "Khojki" Unicode character block.
2738 * @since 9
2739 */
2740 public static final UnicodeBlock KHOJKI =
2741 new UnicodeBlock("KHOJKI");
2742
2743 /**
2744 * Constant for the "Khudawadi" Unicode character block.
2745 * @since 9
2746 */
2747 public static final UnicodeBlock KHUDAWADI =
2748 new UnicodeBlock("KHUDAWADI");
2749
2750 /**
2751 * Constant for the "Grantha" Unicode character block.
2752 * @since 9
2753 */
2754 public static final UnicodeBlock GRANTHA =
2755 new UnicodeBlock("GRANTHA");
2756
2757 /**
2758 * Constant for the "Tirhuta" Unicode character block.
2759 * @since 9
2760 */
2761 public static final UnicodeBlock TIRHUTA =
2762 new UnicodeBlock("TIRHUTA");
2763
2764 /**
2765 * Constant for the "Siddham" Unicode character block.
2766 * @since 9
2767 */
2768 public static final UnicodeBlock SIDDHAM =
2769 new UnicodeBlock("SIDDHAM");
2770
2771 /**
2772 * Constant for the "Modi" Unicode character block.
2773 * @since 9
2774 */
2775 public static final UnicodeBlock MODI =
2776 new UnicodeBlock("MODI");
2777
2778 /**
2779 * Constant for the "Warang Citi" Unicode character block.
2780 * @since 9
2781 */
2782 public static final UnicodeBlock WARANG_CITI =
2783 new UnicodeBlock("WARANG_CITI",
2784 "WARANG CITI",
2785 "WARANGCITI");
2786
2787 /**
2788 * Constant for the "Pau Cin Hau" Unicode character block.
2789 * @since 9
2790 */
2791 public static final UnicodeBlock PAU_CIN_HAU =
2792 new UnicodeBlock("PAU_CIN_HAU",
2793 "PAU CIN HAU",
2794 "PAUCINHAU");
2795
2796 /**
2797 * Constant for the "Mro" Unicode character block.
2798 * @since 9
2799 */
2800 public static final UnicodeBlock MRO =
2801 new UnicodeBlock("MRO");
2802
2803 /**
2804 * Constant for the "Bassa Vah" Unicode character block.
2805 * @since 9
2806 */
2807 public static final UnicodeBlock BASSA_VAH =
2808 new UnicodeBlock("BASSA_VAH",
2809 "BASSA VAH",
2810 "BASSAVAH");
2811
2812 /**
2813 * Constant for the "Pahawh Hmong" Unicode character block.
2814 * @since 9
2815 */
2816 public static final UnicodeBlock PAHAWH_HMONG =
2817 new UnicodeBlock("PAHAWH_HMONG",
2818 "PAHAWH HMONG",
2819 "PAHAWHHMONG");
2820
2821 /**
2822 * Constant for the "Duployan" Unicode character block.
2823 * @since 9
2824 */
2825 public static final UnicodeBlock DUPLOYAN =
2826 new UnicodeBlock("DUPLOYAN");
2827
2828 /**
2829 * Constant for the "Shorthand Format Controls" Unicode character block.
2830 * @since 9
2831 */
2832 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2833 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2834 "SHORTHAND FORMAT CONTROLS",
2835 "SHORTHANDFORMATCONTROLS");
2836
2837 /**
2838 * Constant for the "Mende Kikakui" Unicode character block.
2839 * @since 9
2840 */
2841 public static final UnicodeBlock MENDE_KIKAKUI =
2842 new UnicodeBlock("MENDE_KIKAKUI",
2843 "MENDE KIKAKUI",
2844 "MENDEKIKAKUI");
2845
2846 /**
2847 * Constant for the "Ornamental Dingbats" Unicode character block.
2848 * @since 9
2849 */
2850 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2851 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2852 "ORNAMENTAL DINGBATS",
2853 "ORNAMENTALDINGBATS");
2854
2855 /**
2856 * Constant for the "Geometric Shapes Extended" Unicode character block.
2857 * @since 9
2858 */
2859 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2860 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2861 "GEOMETRIC SHAPES EXTENDED",
2862 "GEOMETRICSHAPESEXTENDED");
2863
2864 /**
2865 * Constant for the "Supplemental Arrows-C" Unicode character block.
2866 * @since 9
2867 */
2868 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2869 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2870 "SUPPLEMENTAL ARROWS-C",
2871 "SUPPLEMENTALARROWS-C");
2872
2873 /**
2874 * Constant for the "Cherokee Supplement" Unicode character block.
2875 * @since 9
2876 */
2877 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2878 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2879 "CHEROKEE SUPPLEMENT",
2880 "CHEROKEESUPPLEMENT");
2881
2882 /**
2883 * Constant for the "Hatran" Unicode character block.
2884 * @since 9
2885 */
2886 public static final UnicodeBlock HATRAN =
2887 new UnicodeBlock("HATRAN");
2888
2889 /**
2890 * Constant for the "Old Hungarian" Unicode character block.
2891 * @since 9
2892 */
2893 public static final UnicodeBlock OLD_HUNGARIAN =
2894 new UnicodeBlock("OLD_HUNGARIAN",
2895 "OLD HUNGARIAN",
2896 "OLDHUNGARIAN");
2897
2898 /**
2899 * Constant for the "Multani" Unicode character block.
2900 * @since 9
2901 */
2902 public static final UnicodeBlock MULTANI =
2903 new UnicodeBlock("MULTANI");
2904
2905 /**
2906 * Constant for the "Ahom" Unicode character block.
2907 * @since 9
2908 */
2909 public static final UnicodeBlock AHOM =
2910 new UnicodeBlock("AHOM");
2911
2912 /**
2913 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2914 * @since 9
2915 */
2916 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2917 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2918 "EARLY DYNASTIC CUNEIFORM",
2919 "EARLYDYNASTICCUNEIFORM");
2920
2921 /**
2922 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2923 * @since 9
2924 */
2925 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2926 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2927 "ANATOLIAN HIEROGLYPHS",
2928 "ANATOLIANHIEROGLYPHS");
2929
2930 /**
2931 * Constant for the "Sutton SignWriting" Unicode character block.
2932 * @since 9
2933 */
2934 public static final UnicodeBlock SUTTON_SIGNWRITING =
2935 new UnicodeBlock("SUTTON_SIGNWRITING",
2936 "SUTTON SIGNWRITING",
2937 "SUTTONSIGNWRITING");
2938
2939 /**
2940 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2941 * character block.
2942 * @since 9
2943 */
2944 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2945 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2946 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2947 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2948
2949 /**
2950 * Constant for the "CJK Unified Ideographs Extension E" Unicode
2951 * character block.
2952 * @since 9
2953 */
2954 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
2955 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
2956 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
2957 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
2958
2959 /**
2960 * Constant for the "Syriac Supplement" Unicode
2961 * character block.
2962 * @since 11
2963 */
2964 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
2965 new UnicodeBlock("SYRIAC_SUPPLEMENT",
2966 "SYRIAC SUPPLEMENT",
2967 "SYRIACSUPPLEMENT");
2968
2969 /**
2970 * Constant for the "Cyrillic Extended-C" Unicode
2971 * character block.
2972 * @since 11
2973 */
2974 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
2975 new UnicodeBlock("CYRILLIC_EXTENDED_C",
2976 "CYRILLIC EXTENDED-C",
2977 "CYRILLICEXTENDED-C");
2978
2979 /**
2980 * Constant for the "Osage" Unicode
2981 * character block.
2982 * @since 11
2983 */
2984 public static final UnicodeBlock OSAGE =
2985 new UnicodeBlock("OSAGE");
2986
2987 /**
2988 * Constant for the "Newa" Unicode
2989 * character block.
2990 * @since 11
2991 */
2992 public static final UnicodeBlock NEWA =
2993 new UnicodeBlock("NEWA");
2994
2995 /**
2996 * Constant for the "Mongolian Supplement" Unicode
2997 * character block.
2998 * @since 11
2999 */
3000 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3001 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3002 "MONGOLIAN SUPPLEMENT",
3003 "MONGOLIANSUPPLEMENT");
3004
3005 /**
3006 * Constant for the "Marchen" Unicode
3007 * character block.
3008 * @since 11
3009 */
3010 public static final UnicodeBlock MARCHEN =
3011 new UnicodeBlock("MARCHEN");
3012
3013 /**
3014 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3015 * character block.
3016 * @since 11
3017 */
3018 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3019 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3020 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3021 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3022
3023 /**
3024 * Constant for the "Tangut" Unicode
3025 * character block.
3026 * @since 11
3027 */
3028 public static final UnicodeBlock TANGUT =
3029 new UnicodeBlock("TANGUT");
3030
3031 /**
3032 * Constant for the "Tangut Components" Unicode
3033 * character block.
3034 * @since 11
3035 */
3036 public static final UnicodeBlock TANGUT_COMPONENTS =
3037 new UnicodeBlock("TANGUT_COMPONENTS",
3038 "TANGUT COMPONENTS",
3039 "TANGUTCOMPONENTS");
3040
3041 /**
3042 * Constant for the "Kana Extended-A" Unicode
3043 * character block.
3044 * @since 11
3045 */
3046 public static final UnicodeBlock KANA_EXTENDED_A =
3047 new UnicodeBlock("KANA_EXTENDED_A",
3048 "KANA EXTENDED-A",
3049 "KANAEXTENDED-A");
3050 /**
3051 * Constant for the "Glagolitic Supplement" Unicode
3052 * character block.
3053 * @since 11
3054 */
3055 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3056 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3057 "GLAGOLITIC SUPPLEMENT",
3058 "GLAGOLITICSUPPLEMENT");
3059 /**
3060 * Constant for the "Adlam" Unicode
3061 * character block.
3062 * @since 11
3063 */
3064 public static final UnicodeBlock ADLAM =
3065 new UnicodeBlock("ADLAM");
3066
3067 /**
3068 * Constant for the "Masaram Gondi" Unicode
3069 * character block.
3070 * @since 11
3071 */
3072 public static final UnicodeBlock MASARAM_GONDI =
3073 new UnicodeBlock("MASARAM_GONDI",
3074 "MASARAM GONDI",
3075 "MASARAMGONDI");
3076
3077 /**
3078 * Constant for the "Zanabazar Square" Unicode
3079 * character block.
3080 * @since 11
3081 */
3082 public static final UnicodeBlock ZANABAZAR_SQUARE =
3083 new UnicodeBlock("ZANABAZAR_SQUARE",
3084 "ZANABAZAR SQUARE",
3085 "ZANABAZARSQUARE");
3086
3087 /**
3088 * Constant for the "Nushu" Unicode
3089 * character block.
3090 * @since 11
3091 */
3092 public static final UnicodeBlock NUSHU =
3093 new UnicodeBlock("NUSHU");
3094
3095 /**
3096 * Constant for the "Soyombo" Unicode
3097 * character block.
3098 * @since 11
3099 */
3100 public static final UnicodeBlock SOYOMBO =
3101 new UnicodeBlock("SOYOMBO");
3102
3103 /**
3104 * Constant for the "Bhaiksuki" Unicode
3105 * character block.
3106 * @since 11
3107 */
3108 public static final UnicodeBlock BHAIKSUKI =
3109 new UnicodeBlock("BHAIKSUKI");
3110
3111 /**
3112 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3113 * character block.
3114 * @since 11
3115 */
3116 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3117 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3118 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3119 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3120 /**
3121 * Constant for the "Georgian Extended" Unicode
3122 * character block.
3123 * @since 12
3124 */
3125 public static final UnicodeBlock GEORGIAN_EXTENDED =
3126 new UnicodeBlock("GEORGIAN_EXTENDED",
3127 "GEORGIAN EXTENDED",
3128 "GEORGIANEXTENDED");
3129
3130 /**
3131 * Constant for the "Hanifi Rohingya" Unicode
3132 * character block.
3133 * @since 12
3134 */
3135 public static final UnicodeBlock HANIFI_ROHINGYA =
3136 new UnicodeBlock("HANIFI_ROHINGYA",
3137 "HANIFI ROHINGYA",
3138 "HANIFIROHINGYA");
3139
3140 /**
3141 * Constant for the "Old Sogdian" Unicode
3142 * character block.
3143 * @since 12
3144 */
3145 public static final UnicodeBlock OLD_SOGDIAN =
3146 new UnicodeBlock("OLD_SOGDIAN",
3147 "OLD SOGDIAN",
3148 "OLDSOGDIAN");
3149
3150 /**
3151 * Constant for the "Sogdian" Unicode
3152 * character block.
3153 * @since 12
3154 */
3155 public static final UnicodeBlock SOGDIAN =
3156 new UnicodeBlock("SOGDIAN");
3157
3158 /**
3159 * Constant for the "Dogra" Unicode
3160 * character block.
3161 * @since 12
3162 */
3163 public static final UnicodeBlock DOGRA =
3164 new UnicodeBlock("DOGRA");
3165
3166 /**
3167 * Constant for the "Gunjala Gondi" Unicode
3168 * character block.
3169 * @since 12
3170 */
3171 public static final UnicodeBlock GUNJALA_GONDI =
3172 new UnicodeBlock("GUNJALA_GONDI",
3173 "GUNJALA GONDI",
3174 "GUNJALAGONDI");
3175
3176 /**
3177 * Constant for the "Makasar" Unicode
3178 * character block.
3179 * @since 12
3180 */
3181 public static final UnicodeBlock MAKASAR =
3182 new UnicodeBlock("MAKASAR");
3183
3184 /**
3185 * Constant for the "Medefaidrin" Unicode
3186 * character block.
3187 * @since 12
3188 */
3189 public static final UnicodeBlock MEDEFAIDRIN =
3190 new UnicodeBlock("MEDEFAIDRIN");
3191
3192 /**
3193 * Constant for the "Mayan Numerals" Unicode
3194 * character block.
3195 * @since 12
3196 */
3197 public static final UnicodeBlock MAYAN_NUMERALS =
3198 new UnicodeBlock("MAYAN_NUMERALS",
3199 "MAYAN NUMERALS",
3200 "MAYANNUMERALS");
3201
3202 /**
3203 * Constant for the "Indic Siyaq Numbers" Unicode
3204 * character block.
3205 * @since 12
3206 */
3207 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3208 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3209 "INDIC SIYAQ NUMBERS",
3210 "INDICSIYAQNUMBERS");
3211
3212 /**
3213 * Constant for the "Chess Symbols" Unicode
3214 * character block.
3215 * @since 12
3216 */
3217 public static final UnicodeBlock CHESS_SYMBOLS =
3218 new UnicodeBlock("CHESS_SYMBOLS",
3219 "CHESS SYMBOLS",
3220 "CHESSSYMBOLS");
3221
3222
3223 private static final int blockStarts[] = {
3224 0x0000, // 0000..007F; Basic Latin
3225 0x0080, // 0080..00FF; Latin-1 Supplement
3226 0x0100, // 0100..017F; Latin Extended-A
3227 0x0180, // 0180..024F; Latin Extended-B
3228 0x0250, // 0250..02AF; IPA Extensions
3229 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3230 0x0300, // 0300..036F; Combining Diacritical Marks
3231 0x0370, // 0370..03FF; Greek and Coptic
3232 0x0400, // 0400..04FF; Cyrillic
3233 0x0500, // 0500..052F; Cyrillic Supplement
3234 0x0530, // 0530..058F; Armenian
3235 0x0590, // 0590..05FF; Hebrew
3236 0x0600, // 0600..06FF; Arabic
3237 0x0700, // 0700..074F; Syriac
3238 0x0750, // 0750..077F; Arabic Supplement
3239 0x0780, // 0780..07BF; Thaana
3240 0x07C0, // 07C0..07FF; NKo
3241 0x0800, // 0800..083F; Samaritan
3242 0x0840, // 0840..085F; Mandaic
3243 0x0860, // 0860..086F; Syriac Supplement
3244 0x0870, // unassigned
3245 0x08A0, // 08A0..08FF; Arabic Extended-A
3246 0x0900, // 0900..097F; Devanagari
3247 0x0980, // 0980..09FF; Bengali
3248 0x0A00, // 0A00..0A7F; Gurmukhi
3249 0x0A80, // 0A80..0AFF; Gujarati
3250 0x0B00, // 0B00..0B7F; Oriya
3251 0x0B80, // 0B80..0BFF; Tamil
3252 0x0C00, // 0C00..0C7F; Telugu
3253 0x0C80, // 0C80..0CFF; Kannada
3254 0x0D00, // 0D00..0D7F; Malayalam
3255 0x0D80, // 0D80..0DFF; Sinhala
3256 0x0E00, // 0E00..0E7F; Thai
3257 0x0E80, // 0E80..0EFF; Lao
3258 0x0F00, // 0F00..0FFF; Tibetan
3259 0x1000, // 1000..109F; Myanmar
3260 0x10A0, // 10A0..10FF; Georgian
3261 0x1100, // 1100..11FF; Hangul Jamo
3262 0x1200, // 1200..137F; Ethiopic
3263 0x1380, // 1380..139F; Ethiopic Supplement
3264 0x13A0, // 13A0..13FF; Cherokee
3265 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3266 0x1680, // 1680..169F; Ogham
3267 0x16A0, // 16A0..16FF; Runic
3268 0x1700, // 1700..171F; Tagalog
3269 0x1720, // 1720..173F; Hanunoo
3270 0x1740, // 1740..175F; Buhid
3271 0x1760, // 1760..177F; Tagbanwa
3272 0x1780, // 1780..17FF; Khmer
3273 0x1800, // 1800..18AF; Mongolian
3274 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3275 0x1900, // 1900..194F; Limbu
3276 0x1950, // 1950..197F; Tai Le
3277 0x1980, // 1980..19DF; New Tai Lue
3278 0x19E0, // 19E0..19FF; Khmer Symbols
3279 0x1A00, // 1A00..1A1F; Buginese
3280 0x1A20, // 1A20..1AAF; Tai Tham
3281 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3282 0x1B00, // 1B00..1B7F; Balinese
3283 0x1B80, // 1B80..1BBF; Sundanese
3284 0x1BC0, // 1BC0..1BFF; Batak
3285 0x1C00, // 1C00..1C4F; Lepcha
3286 0x1C50, // 1C50..1C7F; Ol Chiki
3287 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3288 0x1C90, // 1C90..1CBF; Georgian Extended
3289 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3290 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3291 0x1D00, // 1D00..1D7F; Phonetic Extensions
3292 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3293 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3294 0x1E00, // 1E00..1EFF; Latin Extended Additional
3295 0x1F00, // 1F00..1FFF; Greek Extended
3296 0x2000, // 2000..206F; General Punctuation
3297 0x2070, // 2070..209F; Superscripts and Subscripts
3298 0x20A0, // 20A0..20CF; Currency Symbols
3299 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3300 0x2100, // 2100..214F; Letterlike Symbols
3301 0x2150, // 2150..218F; Number Forms
3302 0x2190, // 2190..21FF; Arrows
3303 0x2200, // 2200..22FF; Mathematical Operators
3304 0x2300, // 2300..23FF; Miscellaneous Technical
3305 0x2400, // 2400..243F; Control Pictures
3306 0x2440, // 2440..245F; Optical Character Recognition
3307 0x2460, // 2460..24FF; Enclosed Alphanumerics
3308 0x2500, // 2500..257F; Box Drawing
3309 0x2580, // 2580..259F; Block Elements
3310 0x25A0, // 25A0..25FF; Geometric Shapes
3311 0x2600, // 2600..26FF; Miscellaneous Symbols
3312 0x2700, // 2700..27BF; Dingbats
3313 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3314 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3315 0x2800, // 2800..28FF; Braille Patterns
3316 0x2900, // 2900..297F; Supplemental Arrows-B
3317 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3318 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3319 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3320 0x2C00, // 2C00..2C5F; Glagolitic
3321 0x2C60, // 2C60..2C7F; Latin Extended-C
3322 0x2C80, // 2C80..2CFF; Coptic
3323 0x2D00, // 2D00..2D2F; Georgian Supplement
3324 0x2D30, // 2D30..2D7F; Tifinagh
3325 0x2D80, // 2D80..2DDF; Ethiopic Extended
3326 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3327 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3328 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3329 0x2F00, // 2F00..2FDF; Kangxi Radicals
3330 0x2FE0, // unassigned
3331 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3332 0x3000, // 3000..303F; CJK Symbols and Punctuation
3333 0x3040, // 3040..309F; Hiragana
3334 0x30A0, // 30A0..30FF; Katakana
3335 0x3100, // 3100..312F; Bopomofo
3336 0x3130, // 3130..318F; Hangul Compatibility Jamo
3337 0x3190, // 3190..319F; Kanbun
3338 0x31A0, // 31A0..31BF; Bopomofo Extended
3339 0x31C0, // 31C0..31EF; CJK Strokes
3340 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3341 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3342 0x3300, // 3300..33FF; CJK Compatibility
3343 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3344 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3345 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3346 0xA000, // A000..A48F; Yi Syllables
3347 0xA490, // A490..A4CF; Yi Radicals
3348 0xA4D0, // A4D0..A4FF; Lisu
3349 0xA500, // A500..A63F; Vai
3350 0xA640, // A640..A69F; Cyrillic Extended-B
3351 0xA6A0, // A6A0..A6FF; Bamum
3352 0xA700, // A700..A71F; Modifier Tone Letters
3353 0xA720, // A720..A7FF; Latin Extended-D
3354 0xA800, // A800..A82F; Syloti Nagri
3355 0xA830, // A830..A83F; Common Indic Number Forms
3356 0xA840, // A840..A87F; Phags-pa
3357 0xA880, // A880..A8DF; Saurashtra
3358 0xA8E0, // A8E0..A8FF; Devanagari Extended
3359 0xA900, // A900..A92F; Kayah Li
3360 0xA930, // A930..A95F; Rejang
3361 0xA960, // A960..A97F; Hangul Jamo Extended-A
3362 0xA980, // A980..A9DF; Javanese
3363 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3364 0xAA00, // AA00..AA5F; Cham
3365 0xAA60, // AA60..AA7F; Myanmar Extended-A
3366 0xAA80, // AA80..AADF; Tai Viet
3367 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3368 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3369 0xAB30, // AB30..AB6F; Latin Extended-E
3370 0xAB70, // AB70..ABBF; Cherokee Supplement
3371 0xABC0, // ABC0..ABFF; Meetei Mayek
3372 0xAC00, // AC00..D7AF; Hangul Syllables
3373 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3374 0xD800, // D800..DB7F; High Surrogates
3375 0xDB80, // DB80..DBFF; High Private Use Surrogates
3376 0xDC00, // DC00..DFFF; Low Surrogates
3377 0xE000, // E000..F8FF; Private Use Area
3378 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3379 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3380 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3381 0xFE00, // FE00..FE0F; Variation Selectors
3382 0xFE10, // FE10..FE1F; Vertical Forms
3383 0xFE20, // FE20..FE2F; Combining Half Marks
3384 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3385 0xFE50, // FE50..FE6F; Small Form Variants
3386 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3387 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3388 0xFFF0, // FFF0..FFFF; Specials
3389 0x10000, // 10000..1007F; Linear B Syllabary
3390 0x10080, // 10080..100FF; Linear B Ideograms
3391 0x10100, // 10100..1013F; Aegean Numbers
3392 0x10140, // 10140..1018F; Ancient Greek Numbers
3393 0x10190, // 10190..101CF; Ancient Symbols
3394 0x101D0, // 101D0..101FF; Phaistos Disc
3395 0x10200, // unassigned
3396 0x10280, // 10280..1029F; Lycian
3397 0x102A0, // 102A0..102DF; Carian
3398 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3399 0x10300, // 10300..1032F; Old Italic
3400 0x10330, // 10330..1034F; Gothic
3401 0x10350, // 10350..1037F; Old Permic
3402 0x10380, // 10380..1039F; Ugaritic
3403 0x103A0, // 103A0..103DF; Old Persian
3404 0x103E0, // unassigned
3405 0x10400, // 10400..1044F; Deseret
3406 0x10450, // 10450..1047F; Shavian
3407 0x10480, // 10480..104AF; Osmanya
3408 0x104B0, // 104B0..104FF; Osage
3409 0x10500, // 10500..1052F; Elbasan
3410 0x10530, // 10530..1056F; Caucasian Albanian
3411 0x10570, // unassigned
3412 0x10600, // 10600..1077F; Linear A
3413 0x10780, // unassigned
3414 0x10800, // 10800..1083F; Cypriot Syllabary
3415 0x10840, // 10840..1085F; Imperial Aramaic
3416 0x10860, // 10860..1087F; Palmyrene
3417 0x10880, // 10880..108AF; Nabataean
3418 0x108B0, // unassigned
3419 0x108E0, // 108E0..108FF; Hatran
3420 0x10900, // 10900..1091F; Phoenician
3421 0x10920, // 10920..1093F; Lydian
3422 0x10940, // unassigned
3423 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3424 0x109A0, // 109A0..109FF; Meroitic Cursive
3425 0x10A00, // 10A00..10A5F; Kharoshthi
3426 0x10A60, // 10A60..10A7F; Old South Arabian
3427 0x10A80, // 10A80..10A9F; Old North Arabian
3428 0x10AA0, // unassigned
3429 0x10AC0, // 10AC0..10AFF; Manichaean
3430 0x10B00, // 10B00..10B3F; Avestan
3431 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3432 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3433 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3434 0x10BB0, // unassigned
3435 0x10C00, // 10C00..10C4F; Old Turkic
3436 0x10C50, // unassigned
3437 0x10C80, // 10C80..10CFF; Old Hungarian
3438 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3439 0x10D40, // unassigned
3440 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3441 0x10E80, // unassigned
3442 0x10F00, // 10F00..10F2F; Old Sogdian
3443 0x10F30, // 10F30..10F6F; Sogdian
3444 0x10F70, // unassigned
3445 0x11000, // 11000..1107F; Brahmi
3446 0x11080, // 11080..110CF; Kaithi
3447 0x110D0, // 110D0..110FF; Sora Sompeng
3448 0x11100, // 11100..1114F; Chakma
3449 0x11150, // 11150..1117F; Mahajani
3450 0x11180, // 11180..111DF; Sharada
3451 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3452 0x11200, // 11200..1124F; Khojki
3453 0x11250, // unassigned
3454 0x11280, // 11280..112AF; Multani
3455 0x112B0, // 112B0..112FF; Khudawadi
3456 0x11300, // 11300..1137F; Grantha
3457 0x11380, // unassigned
3458 0x11400, // 11400..1147F; Newa
3459 0x11480, // 11480..114DF; Tirhuta
3460 0x114E0, // unassigned
3461 0x11580, // 11580..115FF; Siddham
3462 0x11600, // 11600..1165F; Modi
3463 0x11660, // 11660..1167F; Mongolian Supplement
3464 0x11680, // 11680..116CF; Takri
3465 0x116D0, // unassigned
3466 0x11700, // 11700..1173F; Ahom
3467 0x11740, // unassigned
3468 0x11800, // 11800..1184F; Dogra
3469 0x11850, // unassigned
3470 0x118A0, // 118A0..118FF; Warang Citi
3471 0x11900, // unassigned
3472 0x11A00, // 11A00..11A4F; Zanabazar Square
3473 0x11A50, // 11A50..11AAF; Soyombo
3474 0x11AB0, // unassigned
3475 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3476 0x11B00, // unassigned
3477 0x11C00, // 11C00..11C6F; Bhaiksuki
3478 0x11C70, // 11C70..11CBF; Marchen
3479 0x11CC0, // unassigned
3480 0x11D00, // 11D00..11D5F; Masaram Gondi
3481 0x11D60, // 11D60..11DAF; Gunjala Gondi
3482 0x11DB0, // unassigned
3483 0x11EE0, // 11EE0..11EFF; Makasar
3484 0x11F00, // unassigned
3485 0x12000, // 12000..123FF; Cuneiform
3486 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3487 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3488 0x12550, // unassigned
3489 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3490 0x13430, // unassigned
3491 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3492 0x14680, // unassigned
3493 0x16800, // 16800..16A3F; Bamum Supplement
3494 0x16A40, // 16A40..16A6F; Mro
3495 0x16A70, // unassigned
3496 0x16AD0, // 16AD0..16AFF; Bassa Vah
3497 0x16B00, // 16B00..16B8F; Pahawh Hmong
3498 0x16B90, // unassigned
3499 0x16E40, // 16E40..16E9F; Medefaidrin
3500 0x16EA0, // unassigned
3501 0x16F00, // 16F00..16F9F; Miao
3502 0x16FA0, // unassigned
3503 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
3504 0x17000, // 17000..187FF; Tangut
3505 0x18800, // 18800..18AFF; Tangut Components
3506 0x18B00, // unassigned
3507 0x1B000, // 1B000..1B0FF; Kana Supplement
3508 0x1B100, // 1B100..1B12F; Kana Extended-A
3509 0x1B130, // unassigned
3510 0x1B170, // 1B170..1B2FF; Nushu
3511 0x1B300, // unassigned
3512 0x1BC00, // 1BC00..1BC9F; Duployan
3513 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3514 0x1BCB0, // unassigned
3515 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3516 0x1D100, // 1D100..1D1FF; Musical Symbols
3517 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3518 0x1D250, // unassigned
3519 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
3520 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3521 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3522 0x1D380, // unassigned
3523 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3524 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3525 0x1DAB0, // unassigned
3526 0x1E000, // 1E000..1E02F; Glagolitic Supplement
3527 0x1E030, // unassigned
3528 0x1E800, // 1E800..1E8DF; Mende Kikakui
3529 0x1E8E0, // unassigned
3530 0x1E900, // 1E900..1E95F; Adlam
3531 0x1E960, // unassigned
3532 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
3533 0x1ECC0, // unassigned
3534 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3535 0x1EF00, // unassigned
3536 0x1F000, // 1F000..1F02F; Mahjong Tiles
3537 0x1F030, // 1F030..1F09F; Domino Tiles
3538 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3539 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3540 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3541 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3542 0x1F600, // 1F600..1F64F; Emoticons
3543 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3544 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3545 0x1F700, // 1F700..1F77F; Alchemical Symbols
3546 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3547 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3548 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3549 0x1FA00, // 1FA00..1FA6F; Chess Symbols
3550 0x1FA70, // unassigned
3551 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3552 0x2A6E0, // unassigned
3553 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3554 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3555 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
3556 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
3557 0x2EBF0, // unassigned
3558 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
3559 0x2FA20, // unassigned
3560 0xE0000, // E0000..E007F; Tags
3561 0xE0080, // unassigned
3562 0xE0100, // E0100..E01EF; Variation Selectors Supplement
3563 0xE01F0, // unassigned
3564 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
3565 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B
3566 };
3567
3568 private static final UnicodeBlock[] blocks = {
3569 BASIC_LATIN,
3570 LATIN_1_SUPPLEMENT,
3571 LATIN_EXTENDED_A,
3572 LATIN_EXTENDED_B,
3573 IPA_EXTENSIONS,
3574 SPACING_MODIFIER_LETTERS,
3575 COMBINING_DIACRITICAL_MARKS,
3576 GREEK,
3577 CYRILLIC,
3578 CYRILLIC_SUPPLEMENTARY,
3579 ARMENIAN,
3580 HEBREW,
3581 ARABIC,
3582 SYRIAC,
3583 ARABIC_SUPPLEMENT,
3584 THAANA,
3585 NKO,
3586 SAMARITAN,
3587 MANDAIC,
3588 SYRIAC_SUPPLEMENT,
3589 null,
3590 ARABIC_EXTENDED_A,
3591 DEVANAGARI,
3592 BENGALI,
3593 GURMUKHI,
3594 GUJARATI,
3595 ORIYA,
3596 TAMIL,
3597 TELUGU,
3598 KANNADA,
3599 MALAYALAM,
3600 SINHALA,
3601 THAI,
3602 LAO,
3603 TIBETAN,
3604 MYANMAR,
3605 GEORGIAN,
3606 HANGUL_JAMO,
3607 ETHIOPIC,
3608 ETHIOPIC_SUPPLEMENT,
3609 CHEROKEE,
3610 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
3611 OGHAM,
3612 RUNIC,
3613 TAGALOG,
3614 HANUNOO,
3615 BUHID,
3616 TAGBANWA,
3617 KHMER,
3618 MONGOLIAN,
3619 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
3620 LIMBU,
3621 TAI_LE,
3622 NEW_TAI_LUE,
3623 KHMER_SYMBOLS,
3624 BUGINESE,
3625 TAI_THAM,
3626 COMBINING_DIACRITICAL_MARKS_EXTENDED,
3627 BALINESE,
3628 SUNDANESE,
3629 BATAK,
3630 LEPCHA,
3631 OL_CHIKI,
3632 CYRILLIC_EXTENDED_C,
3633 GEORGIAN_EXTENDED,
3634 SUNDANESE_SUPPLEMENT,
3635 VEDIC_EXTENSIONS,
3636 PHONETIC_EXTENSIONS,
3637 PHONETIC_EXTENSIONS_SUPPLEMENT,
3638 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
3639 LATIN_EXTENDED_ADDITIONAL,
3640 GREEK_EXTENDED,
3641 GENERAL_PUNCTUATION,
3642 SUPERSCRIPTS_AND_SUBSCRIPTS,
3643 CURRENCY_SYMBOLS,
3644 COMBINING_MARKS_FOR_SYMBOLS,
3645 LETTERLIKE_SYMBOLS,
3646 NUMBER_FORMS,
3647 ARROWS,
3648 MATHEMATICAL_OPERATORS,
3649 MISCELLANEOUS_TECHNICAL,
3650 CONTROL_PICTURES,
3651 OPTICAL_CHARACTER_RECOGNITION,
3652 ENCLOSED_ALPHANUMERICS,
3653 BOX_DRAWING,
3654 BLOCK_ELEMENTS,
3655 GEOMETRIC_SHAPES,
3656 MISCELLANEOUS_SYMBOLS,
3657 DINGBATS,
3658 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
3659 SUPPLEMENTAL_ARROWS_A,
3660 BRAILLE_PATTERNS,
3661 SUPPLEMENTAL_ARROWS_B,
3662 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
3663 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
3664 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
3665 GLAGOLITIC,
3666 LATIN_EXTENDED_C,
3667 COPTIC,
3668 GEORGIAN_SUPPLEMENT,
3669 TIFINAGH,
3670 ETHIOPIC_EXTENDED,
3671 CYRILLIC_EXTENDED_A,
3672 SUPPLEMENTAL_PUNCTUATION,
3673 CJK_RADICALS_SUPPLEMENT,
3674 KANGXI_RADICALS,
3675 null,
3676 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
3677 CJK_SYMBOLS_AND_PUNCTUATION,
3678 HIRAGANA,
3679 KATAKANA,
3680 BOPOMOFO,
3681 HANGUL_COMPATIBILITY_JAMO,
3682 KANBUN,
3683 BOPOMOFO_EXTENDED,
3684 CJK_STROKES,
3685 KATAKANA_PHONETIC_EXTENSIONS,
3686 ENCLOSED_CJK_LETTERS_AND_MONTHS,
3687 CJK_COMPATIBILITY,
3688 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
3689 YIJING_HEXAGRAM_SYMBOLS,
3690 CJK_UNIFIED_IDEOGRAPHS,
3691 YI_SYLLABLES,
3692 YI_RADICALS,
3693 LISU,
3694 VAI,
3695 CYRILLIC_EXTENDED_B,
3696 BAMUM,
3697 MODIFIER_TONE_LETTERS,
3698 LATIN_EXTENDED_D,
3699 SYLOTI_NAGRI,
3700 COMMON_INDIC_NUMBER_FORMS,
3701 PHAGS_PA,
3702 SAURASHTRA,
3703 DEVANAGARI_EXTENDED,
3704 KAYAH_LI,
3705 REJANG,
3706 HANGUL_JAMO_EXTENDED_A,
3707 JAVANESE,
3708 MYANMAR_EXTENDED_B,
3709 CHAM,
3710 MYANMAR_EXTENDED_A,
3711 TAI_VIET,
3712 MEETEI_MAYEK_EXTENSIONS,
3713 ETHIOPIC_EXTENDED_A,
3714 LATIN_EXTENDED_E,
3715 CHEROKEE_SUPPLEMENT,
3716 MEETEI_MAYEK,
3717 HANGUL_SYLLABLES,
3718 HANGUL_JAMO_EXTENDED_B,
3719 HIGH_SURROGATES,
3720 HIGH_PRIVATE_USE_SURROGATES,
3721 LOW_SURROGATES,
3722 PRIVATE_USE_AREA,
3723 CJK_COMPATIBILITY_IDEOGRAPHS,
3724 ALPHABETIC_PRESENTATION_FORMS,
3725 ARABIC_PRESENTATION_FORMS_A,
3726 VARIATION_SELECTORS,
3727 VERTICAL_FORMS,
3728 COMBINING_HALF_MARKS,
3729 CJK_COMPATIBILITY_FORMS,
3730 SMALL_FORM_VARIANTS,
3731 ARABIC_PRESENTATION_FORMS_B,
3732 HALFWIDTH_AND_FULLWIDTH_FORMS,
3733 SPECIALS,
3734 LINEAR_B_SYLLABARY,
3735 LINEAR_B_IDEOGRAMS,
3736 AEGEAN_NUMBERS,
3737 ANCIENT_GREEK_NUMBERS,
3738 ANCIENT_SYMBOLS,
3739 PHAISTOS_DISC,
3740 null,
3741 LYCIAN,
3742 CARIAN,
3743 COPTIC_EPACT_NUMBERS,
3744 OLD_ITALIC,
3745 GOTHIC,
3746 OLD_PERMIC,
3747 UGARITIC,
3748 OLD_PERSIAN,
3749 null,
3750 DESERET,
3751 SHAVIAN,
3752 OSMANYA,
3753 OSAGE,
3754 ELBASAN,
3755 CAUCASIAN_ALBANIAN,
3756 null,
3757 LINEAR_A,
3758 null,
3759 CYPRIOT_SYLLABARY,
3760 IMPERIAL_ARAMAIC,
3761 PALMYRENE,
3762 NABATAEAN,
3763 null,
3764 HATRAN,
3765 PHOENICIAN,
3766 LYDIAN,
3767 null,
3768 MEROITIC_HIEROGLYPHS,
3769 MEROITIC_CURSIVE,
3770 KHAROSHTHI,
3771 OLD_SOUTH_ARABIAN,
3772 OLD_NORTH_ARABIAN,
3773 null,
3774 MANICHAEAN,
3775 AVESTAN,
3776 INSCRIPTIONAL_PARTHIAN,
3777 INSCRIPTIONAL_PAHLAVI,
3778 PSALTER_PAHLAVI,
3779 null,
3780 OLD_TURKIC,
3781 null,
3782 OLD_HUNGARIAN,
3783 HANIFI_ROHINGYA,
3784 null,
3785 RUMI_NUMERAL_SYMBOLS,
3786 null,
3787 OLD_SOGDIAN,
3788 SOGDIAN,
3789 null,
3790 BRAHMI,
3791 KAITHI,
3792 SORA_SOMPENG,
3793 CHAKMA,
3794 MAHAJANI,
3795 SHARADA,
3796 SINHALA_ARCHAIC_NUMBERS,
3797 KHOJKI,
3798 null,
3799 MULTANI,
3800 KHUDAWADI,
3801 GRANTHA,
3802 null,
3803 NEWA,
3804 TIRHUTA,
3805 null,
3806 SIDDHAM,
3807 MODI,
3808 MONGOLIAN_SUPPLEMENT,
3809 TAKRI,
3810 null,
3811 AHOM,
3812 null,
3813 DOGRA,
3814 null,
3815 WARANG_CITI,
3816 null,
3817 ZANABAZAR_SQUARE,
3818 SOYOMBO,
3819 null,
3820 PAU_CIN_HAU,
3821 null,
3822 BHAIKSUKI,
3823 MARCHEN,
3824 null,
3825 MASARAM_GONDI,
3826 GUNJALA_GONDI,
3827 null,
3828 MAKASAR,
3829 null,
3830 CUNEIFORM,
3831 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
3832 EARLY_DYNASTIC_CUNEIFORM,
3833 null,
3834 EGYPTIAN_HIEROGLYPHS,
3835 null,
3836 ANATOLIAN_HIEROGLYPHS,
3837 null,
3838 BAMUM_SUPPLEMENT,
3839 MRO,
3840 null,
3841 BASSA_VAH,
3842 PAHAWH_HMONG,
3843 null,
3844 MEDEFAIDRIN,
3845 null,
3846 MIAO,
3847 null,
3848 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
3849 TANGUT,
3850 TANGUT_COMPONENTS,
3851 null,
3852 KANA_SUPPLEMENT,
3853 KANA_EXTENDED_A,
3854 null,
3855 NUSHU,
3856 null,
3857 DUPLOYAN,
3858 SHORTHAND_FORMAT_CONTROLS,
3859 null,
3860 BYZANTINE_MUSICAL_SYMBOLS,
3861 MUSICAL_SYMBOLS,
3862 ANCIENT_GREEK_MUSICAL_NOTATION,
3863 null,
3864 MAYAN_NUMERALS,
3865 TAI_XUAN_JING_SYMBOLS,
3866 COUNTING_ROD_NUMERALS,
3867 null,
3868 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
3869 SUTTON_SIGNWRITING,
3870 null,
3871 GLAGOLITIC_SUPPLEMENT,
3872 null,
3873 MENDE_KIKAKUI,
3874 null,
3875 ADLAM,
3876 null,
3877 INDIC_SIYAQ_NUMBERS,
3878 null,
3879 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
3880 null,
3881 MAHJONG_TILES,
3882 DOMINO_TILES,
3883 PLAYING_CARDS,
3884 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
3885 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
3886 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
3887 EMOTICONS,
3888 ORNAMENTAL_DINGBATS,
3889 TRANSPORT_AND_MAP_SYMBOLS,
3890 ALCHEMICAL_SYMBOLS,
3891 GEOMETRIC_SHAPES_EXTENDED,
3892 SUPPLEMENTAL_ARROWS_C,
3893 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
3894 CHESS_SYMBOLS,
3895 null,
3896 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
3897 null,
3898 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
3899 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
3900 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
3901 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
3902 null,
3903 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
3904 null,
3905 TAGS,
3906 null,
3907 VARIATION_SELECTORS_SUPPLEMENT,
3908 null,
3909 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
3910 SUPPLEMENTARY_PRIVATE_USE_AREA_B
3911 };
3912
3913
3914 /**
3915 * Returns the object representing the Unicode block containing the
3916 * given character, or {@code null} if the character is not a
3917 * member of a defined block.
3918 *
3919 * <p><b>Note:</b> This method cannot handle
3920 * <a href="Character.html#supplementary"> supplementary
3921 * characters</a>. To support all Unicode characters, including
3922 * supplementary characters, use the {@link #of(int)} method.
3923 *
3924 * @param c The character in question
3925 * @return The {@code UnicodeBlock} instance representing the
3926 * Unicode block of which this character is a member, or
3927 * {@code null} if the character is not a member of any
3928 * Unicode block
3929 */
3930 public static UnicodeBlock of(char c) {
3931 return of((int)c);
3932 }
3933
3934 /**
3935 * Returns the object representing the Unicode block
3936 * containing the given character (Unicode code point), or
3937 * {@code null} if the character is not a member of a
3938 * defined block.
3939 *
3940 * @param codePoint the character (Unicode code point) in question.
3941 * @return The {@code UnicodeBlock} instance representing the
3942 * Unicode block of which this character is a member, or
3943 * {@code null} if the character is not a member of any
3944 * Unicode block
3945 * @throws IllegalArgumentException if the specified
3946 * {@code codePoint} is an invalid Unicode code point.
3947 * @see Character#isValidCodePoint(int)
3948 * @since 1.5
3949 */
3950 public static UnicodeBlock of(int codePoint) {
3951 if (!isValidCodePoint(codePoint)) {
3952 throw new IllegalArgumentException(
3953 String.format("Not a valid Unicode code point: 0x%X", codePoint));
3954 }
3955
3956 int top, bottom, current;
3957 bottom = 0;
3958 top = blockStarts.length;
3959 current = top/2;
3960
3961 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
3962 while (top - bottom > 1) {
3963 if (codePoint >= blockStarts[current]) {
3964 bottom = current;
3965 } else {
3966 top = current;
3967 }
3968 current = (top + bottom) / 2;
3969 }
3970 return blocks[current];
3971 }
3972
3973 /**
3974 * Returns the UnicodeBlock with the given name. Block
3975 * names are determined by The Unicode Standard. The file
3976 * {@code Blocks-<version>.txt} defines blocks for a particular
3977 * version of the standard. The {@link Character} class specifies
3978 * the version of the standard that it supports.
3979 * <p>
3980 * This method accepts block names in the following forms:
3981 * <ol>
3982 * <li> Canonical block names as defined by the Unicode Standard.
3983 * For example, the standard defines a "Basic Latin" block. Therefore, this
3984 * method accepts "Basic Latin" as a valid block name. The documentation of
3985 * each UnicodeBlock provides the canonical name.
3986 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
3987 * is a valid block name for the "Basic Latin" block.
3988 * <li>The text representation of each constant UnicodeBlock identifier.
3989 * For example, this method will return the {@link #BASIC_LATIN} block if
3990 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
3991 * hyphens in the canonical name with underscores.
3992 * </ol>
3993 * Finally, character case is ignored for all of the valid block name forms.
3994 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
3995 * The en_US locale's case mapping rules are used to provide case-insensitive
3996 * string comparisons for block name validation.
3997 * <p>
3998 * If the Unicode Standard changes block names, both the previous and
3999 * current names will be accepted.
4000 *
4001 * @param blockName A {@code UnicodeBlock} name.
4002 * @return The {@code UnicodeBlock} instance identified
4003 * by {@code blockName}
4004 * @throws IllegalArgumentException if {@code blockName} is an
4005 * invalid name
4006 * @throws NullPointerException if {@code blockName} is null
4007 * @since 1.5
4008 */
4009 public static final UnicodeBlock forName(String blockName) {
4010 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4011 if (block == null) {
4012 throw new IllegalArgumentException("Not a valid block name: "
4013 + blockName);
4014 }
4015 return block;
4016 }
4017 }
4018
4019
4020 /**
4021 * A family of character subsets representing the character scripts
4022 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4023 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4024 * character is assigned to a single Unicode script, either a specific
4025 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4026 * one of the following three special values,
4027 * {@link Character.UnicodeScript#INHERITED Inherited},
4028 * {@link Character.UnicodeScript#COMMON Common} or
4029 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4030 *
4031 * @since 1.7
4032 */
4033 public static enum UnicodeScript {
4034 /**
4035 * Unicode script "Common".
4036 */
4037 COMMON,
4038
4039 /**
4040 * Unicode script "Latin".
4041 */
4042 LATIN,
4043
4044 /**
4045 * Unicode script "Greek".
4046 */
4047 GREEK,
4048
4049 /**
4050 * Unicode script "Cyrillic".
4051 */
4052 CYRILLIC,
4053
4054 /**
4055 * Unicode script "Armenian".
4056 */
4057 ARMENIAN,
4058
4059 /**
4060 * Unicode script "Hebrew".
4061 */
4062 HEBREW,
4063
4064 /**
4065 * Unicode script "Arabic".
4066 */
4067 ARABIC,
4068
4069 /**
4070 * Unicode script "Syriac".
4071 */
4072 SYRIAC,
4073
4074 /**
4075 * Unicode script "Thaana".
4076 */
4077 THAANA,
4078
4079 /**
4080 * Unicode script "Devanagari".
4081 */
4082 DEVANAGARI,
4083
4084 /**
4085 * Unicode script "Bengali".
4086 */
4087 BENGALI,
4088
4089 /**
4090 * Unicode script "Gurmukhi".
4091 */
4092 GURMUKHI,
4093
4094 /**
4095 * Unicode script "Gujarati".
4096 */
4097 GUJARATI,
4098
4099 /**
4100 * Unicode script "Oriya".
4101 */
4102 ORIYA,
4103
4104 /**
4105 * Unicode script "Tamil".
4106 */
4107 TAMIL,
4108
4109 /**
4110 * Unicode script "Telugu".
4111 */
4112 TELUGU,
4113
4114 /**
4115 * Unicode script "Kannada".
4116 */
4117 KANNADA,
4118
4119 /**
4120 * Unicode script "Malayalam".
4121 */
4122 MALAYALAM,
4123
4124 /**
4125 * Unicode script "Sinhala".
4126 */
4127 SINHALA,
4128
4129 /**
4130 * Unicode script "Thai".
4131 */
4132 THAI,
4133
4134 /**
4135 * Unicode script "Lao".
4136 */
4137 LAO,
4138
4139 /**
4140 * Unicode script "Tibetan".
4141 */
4142 TIBETAN,
4143
4144 /**
4145 * Unicode script "Myanmar".
4146 */
4147 MYANMAR,
4148
4149 /**
4150 * Unicode script "Georgian".
4151 */
4152 GEORGIAN,
4153
4154 /**
4155 * Unicode script "Hangul".
4156 */
4157 HANGUL,
4158
4159 /**
4160 * Unicode script "Ethiopic".
4161 */
4162 ETHIOPIC,
4163
4164 /**
4165 * Unicode script "Cherokee".
4166 */
4167 CHEROKEE,
4168
4169 /**
4170 * Unicode script "Canadian_Aboriginal".
4171 */
4172 CANADIAN_ABORIGINAL,
4173
4174 /**
4175 * Unicode script "Ogham".
4176 */
4177 OGHAM,
4178
4179 /**
4180 * Unicode script "Runic".
4181 */
4182 RUNIC,
4183
4184 /**
4185 * Unicode script "Khmer".
4186 */
4187 KHMER,
4188
4189 /**
4190 * Unicode script "Mongolian".
4191 */
4192 MONGOLIAN,
4193
4194 /**
4195 * Unicode script "Hiragana".
4196 */
4197 HIRAGANA,
4198
4199 /**
4200 * Unicode script "Katakana".
4201 */
4202 KATAKANA,
4203
4204 /**
4205 * Unicode script "Bopomofo".
4206 */
4207 BOPOMOFO,
4208
4209 /**
4210 * Unicode script "Han".
4211 */
4212 HAN,
4213
4214 /**
4215 * Unicode script "Yi".
4216 */
4217 YI,
4218
4219 /**
4220 * Unicode script "Old_Italic".
4221 */
4222 OLD_ITALIC,
4223
4224 /**
4225 * Unicode script "Gothic".
4226 */
4227 GOTHIC,
4228
4229 /**
4230 * Unicode script "Deseret".
4231 */
4232 DESERET,
4233
4234 /**
4235 * Unicode script "Inherited".
4236 */
4237 INHERITED,
4238
4239 /**
4240 * Unicode script "Tagalog".
4241 */
4242 TAGALOG,
4243
4244 /**
4245 * Unicode script "Hanunoo".
4246 */
4247 HANUNOO,
4248
4249 /**
4250 * Unicode script "Buhid".
4251 */
4252 BUHID,
4253
4254 /**
4255 * Unicode script "Tagbanwa".
4256 */
4257 TAGBANWA,
4258
4259 /**
4260 * Unicode script "Limbu".
4261 */
4262 LIMBU,
4263
4264 /**
4265 * Unicode script "Tai_Le".
4266 */
4267 TAI_LE,
4268
4269 /**
4270 * Unicode script "Linear_B".
4271 */
4272 LINEAR_B,
4273
4274 /**
4275 * Unicode script "Ugaritic".
4276 */
4277 UGARITIC,
4278
4279 /**
4280 * Unicode script "Shavian".
4281 */
4282 SHAVIAN,
4283
4284 /**
4285 * Unicode script "Osmanya".
4286 */
4287 OSMANYA,
4288
4289 /**
4290 * Unicode script "Cypriot".
4291 */
4292 CYPRIOT,
4293
4294 /**
4295 * Unicode script "Braille".
4296 */
4297 BRAILLE,
4298
4299 /**
4300 * Unicode script "Buginese".
4301 */
4302 BUGINESE,
4303
4304 /**
4305 * Unicode script "Coptic".
4306 */
4307 COPTIC,
4308
4309 /**
4310 * Unicode script "New_Tai_Lue".
4311 */
4312 NEW_TAI_LUE,
4313
4314 /**
4315 * Unicode script "Glagolitic".
4316 */
4317 GLAGOLITIC,
4318
4319 /**
4320 * Unicode script "Tifinagh".
4321 */
4322 TIFINAGH,
4323
4324 /**
4325 * Unicode script "Syloti_Nagri".
4326 */
4327 SYLOTI_NAGRI,
4328
4329 /**
4330 * Unicode script "Old_Persian".
4331 */
4332 OLD_PERSIAN,
4333
4334 /**
4335 * Unicode script "Kharoshthi".
4336 */
4337 KHAROSHTHI,
4338
4339 /**
4340 * Unicode script "Balinese".
4341 */
4342 BALINESE,
4343
4344 /**
4345 * Unicode script "Cuneiform".
4346 */
4347 CUNEIFORM,
4348
4349 /**
4350 * Unicode script "Phoenician".
4351 */
4352 PHOENICIAN,
4353
4354 /**
4355 * Unicode script "Phags_Pa".
4356 */
4357 PHAGS_PA,
4358
4359 /**
4360 * Unicode script "Nko".
4361 */
4362 NKO,
4363
4364 /**
4365 * Unicode script "Sundanese".
4366 */
4367 SUNDANESE,
4368
4369 /**
4370 * Unicode script "Batak".
4371 */
4372 BATAK,
4373
4374 /**
4375 * Unicode script "Lepcha".
4376 */
4377 LEPCHA,
4378
4379 /**
4380 * Unicode script "Ol_Chiki".
4381 */
4382 OL_CHIKI,
4383
4384 /**
4385 * Unicode script "Vai".
4386 */
4387 VAI,
4388
4389 /**
4390 * Unicode script "Saurashtra".
4391 */
4392 SAURASHTRA,
4393
4394 /**
4395 * Unicode script "Kayah_Li".
4396 */
4397 KAYAH_LI,
4398
4399 /**
4400 * Unicode script "Rejang".
4401 */
4402 REJANG,
4403
4404 /**
4405 * Unicode script "Lycian".
4406 */
4407 LYCIAN,
4408
4409 /**
4410 * Unicode script "Carian".
4411 */
4412 CARIAN,
4413
4414 /**
4415 * Unicode script "Lydian".
4416 */
4417 LYDIAN,
4418
4419 /**
4420 * Unicode script "Cham".
4421 */
4422 CHAM,
4423
4424 /**
4425 * Unicode script "Tai_Tham".
4426 */
4427 TAI_THAM,
4428
4429 /**
4430 * Unicode script "Tai_Viet".
4431 */
4432 TAI_VIET,
4433
4434 /**
4435 * Unicode script "Avestan".
4436 */
4437 AVESTAN,
4438
4439 /**
4440 * Unicode script "Egyptian_Hieroglyphs".
4441 */
4442 EGYPTIAN_HIEROGLYPHS,
4443
4444 /**
4445 * Unicode script "Samaritan".
4446 */
4447 SAMARITAN,
4448
4449 /**
4450 * Unicode script "Mandaic".
4451 */
4452 MANDAIC,
4453
4454 /**
4455 * Unicode script "Lisu".
4456 */
4457 LISU,
4458
4459 /**
4460 * Unicode script "Bamum".
4461 */
4462 BAMUM,
4463
4464 /**
4465 * Unicode script "Javanese".
4466 */
4467 JAVANESE,
4468
4469 /**
4470 * Unicode script "Meetei_Mayek".
4471 */
4472 MEETEI_MAYEK,
4473
4474 /**
4475 * Unicode script "Imperial_Aramaic".
4476 */
4477 IMPERIAL_ARAMAIC,
4478
4479 /**
4480 * Unicode script "Old_South_Arabian".
4481 */
4482 OLD_SOUTH_ARABIAN,
4483
4484 /**
4485 * Unicode script "Inscriptional_Parthian".
4486 */
4487 INSCRIPTIONAL_PARTHIAN,
4488
4489 /**
4490 * Unicode script "Inscriptional_Pahlavi".
4491 */
4492 INSCRIPTIONAL_PAHLAVI,
4493
4494 /**
4495 * Unicode script "Old_Turkic".
4496 */
4497 OLD_TURKIC,
4498
4499 /**
4500 * Unicode script "Brahmi".
4501 */
4502 BRAHMI,
4503
4504 /**
4505 * Unicode script "Kaithi".
4506 */
4507 KAITHI,
4508
4509 /**
4510 * Unicode script "Meroitic Hieroglyphs".
4511 * @since 1.8
4512 */
4513 MEROITIC_HIEROGLYPHS,
4514
4515 /**
4516 * Unicode script "Meroitic Cursive".
4517 * @since 1.8
4518 */
4519 MEROITIC_CURSIVE,
4520
4521 /**
4522 * Unicode script "Sora Sompeng".
4523 * @since 1.8
4524 */
4525 SORA_SOMPENG,
4526
4527 /**
4528 * Unicode script "Chakma".
4529 * @since 1.8
4530 */
4531 CHAKMA,
4532
4533 /**
4534 * Unicode script "Sharada".
4535 * @since 1.8
4536 */
4537 SHARADA,
4538
4539 /**
4540 * Unicode script "Takri".
4541 * @since 1.8
4542 */
4543 TAKRI,
4544
4545 /**
4546 * Unicode script "Miao".
4547 * @since 1.8
4548 */
4549 MIAO,
4550
4551 /**
4552 * Unicode script "Caucasian Albanian".
4553 * @since 9
4554 */
4555 CAUCASIAN_ALBANIAN,
4556
4557 /**
4558 * Unicode script "Bassa Vah".
4559 * @since 9
4560 */
4561 BASSA_VAH,
4562
4563 /**
4564 * Unicode script "Duployan".
4565 * @since 9
4566 */
4567 DUPLOYAN,
4568
4569 /**
4570 * Unicode script "Elbasan".
4571 * @since 9
4572 */
4573 ELBASAN,
4574
4575 /**
4576 * Unicode script "Grantha".
4577 * @since 9
4578 */
4579 GRANTHA,
4580
4581 /**
4582 * Unicode script "Pahawh Hmong".
4583 * @since 9
4584 */
4585 PAHAWH_HMONG,
4586
4587 /**
4588 * Unicode script "Khojki".
4589 * @since 9
4590 */
4591 KHOJKI,
4592
4593 /**
4594 * Unicode script "Linear A".
4595 * @since 9
4596 */
4597 LINEAR_A,
4598
4599 /**
4600 * Unicode script "Mahajani".
4601 * @since 9
4602 */
4603 MAHAJANI,
4604
4605 /**
4606 * Unicode script "Manichaean".
4607 * @since 9
4608 */
4609 MANICHAEAN,
4610
4611 /**
4612 * Unicode script "Mende Kikakui".
4613 * @since 9
4614 */
4615 MENDE_KIKAKUI,
4616
4617 /**
4618 * Unicode script "Modi".
4619 * @since 9
4620 */
4621 MODI,
4622
4623 /**
4624 * Unicode script "Mro".
4625 * @since 9
4626 */
4627 MRO,
4628
4629 /**
4630 * Unicode script "Old North Arabian".
4631 * @since 9
4632 */
4633 OLD_NORTH_ARABIAN,
4634
4635 /**
4636 * Unicode script "Nabataean".
4637 * @since 9
4638 */
4639 NABATAEAN,
4640
4641 /**
4642 * Unicode script "Palmyrene".
4643 * @since 9
4644 */
4645 PALMYRENE,
4646
4647 /**
4648 * Unicode script "Pau Cin Hau".
4649 * @since 9
4650 */
4651 PAU_CIN_HAU,
4652
4653 /**
4654 * Unicode script "Old Permic".
4655 * @since 9
4656 */
4657 OLD_PERMIC,
4658
4659 /**
4660 * Unicode script "Psalter Pahlavi".
4661 * @since 9
4662 */
4663 PSALTER_PAHLAVI,
4664
4665 /**
4666 * Unicode script "Siddham".
4667 * @since 9
4668 */
4669 SIDDHAM,
4670
4671 /**
4672 * Unicode script "Khudawadi".
4673 * @since 9
4674 */
4675 KHUDAWADI,
4676
4677 /**
4678 * Unicode script "Tirhuta".
4679 * @since 9
4680 */
4681 TIRHUTA,
4682
4683 /**
4684 * Unicode script "Warang Citi".
4685 * @since 9
4686 */
4687 WARANG_CITI,
4688
4689 /**
4690 * Unicode script "Ahom".
4691 * @since 9
4692 */
4693 AHOM,
4694
4695 /**
4696 * Unicode script "Anatolian Hieroglyphs".
4697 * @since 9
4698 */
4699 ANATOLIAN_HIEROGLYPHS,
4700
4701 /**
4702 * Unicode script "Hatran".
4703 * @since 9
4704 */
4705 HATRAN,
4706
4707 /**
4708 * Unicode script "Multani".
4709 * @since 9
4710 */
4711 MULTANI,
4712
4713 /**
4714 * Unicode script "Old Hungarian".
4715 * @since 9
4716 */
4717 OLD_HUNGARIAN,
4718
4719 /**
4720 * Unicode script "SignWriting".
4721 * @since 9
4722 */
4723 SIGNWRITING,
4724
4725 /**
4726 * Unicode script "Adlam".
4727 * @since 11
4728 */
4729 ADLAM,
4730
4731 /**
4732 * Unicode script "Bhaiksuki".
4733 * @since 11
4734 */
4735 BHAIKSUKI,
4736
4737 /**
4738 * Unicode script "Marchen".
4739 * @since 11
4740 */
4741 MARCHEN,
4742
4743 /**
4744 * Unicode script "Newa".
4745 * @since 11
4746 */
4747 NEWA,
4748
4749 /**
4750 * Unicode script "Osage".
4751 * @since 11
4752 */
4753 OSAGE,
4754
4755 /**
4756 * Unicode script "Tangut".
4757 * @since 11
4758 */
4759 TANGUT,
4760
4761 /**
4762 * Unicode script "Masaram Gondi".
4763 * @since 11
4764 */
4765 MASARAM_GONDI,
4766
4767 /**
4768 * Unicode script "Nushu".
4769 * @since 11
4770 */
4771 NUSHU,
4772
4773 /**
4774 * Unicode script "Soyombo".
4775 * @since 11
4776 */
4777 SOYOMBO,
4778
4779 /**
4780 * Unicode script "Zanabazar Square".
4781 * @since 11
4782 */
4783 ZANABAZAR_SQUARE,
4784
4785 /**
4786 * Unicode script "Hanifi Rohingya".
4787 * @since 12
4788 */
4789 HANIFI_ROHINGYA,
4790
4791 /**
4792 * Unicode script "Old Sogdian".
4793 * @since 12
4794 */
4795 OLD_SOGDIAN,
4796
4797 /**
4798 * Unicode script "Sogdian".
4799 * @since 12
4800 */
4801 SOGDIAN,
4802
4803 /**
4804 * Unicode script "Dogra".
4805 * @since 12
4806 */
4807 DOGRA,
4808
4809 /**
4810 * Unicode script "Gunjala Gondi".
4811 * @since 12
4812 */
4813 GUNJALA_GONDI,
4814
4815 /**
4816 * Unicode script "Makasar".
4817 * @since 12
4818 */
4819 MAKASAR,
4820
4821 /**
4822 * Unicode script "Medefaidrin".
4823 * @since 12
4824 */
4825 MEDEFAIDRIN,
4826
4827 /**
4828 * Unicode script "Unknown".
4829 */
4830 UNKNOWN;
4831
4832 private static final int[] scriptStarts = {
4833 0x0000, // 0000..0040; COMMON
4834 0x0041, // 0041..005A; LATIN
4835 0x005B, // 005B..0060; COMMON
4836 0x0061, // 0061..007A; LATIN
4837 0x007B, // 007B..00A9; COMMON
4838 0x00AA, // 00AA ; LATIN
4839 0x00AB, // 00AB..00B9; COMMON
4840 0x00BA, // 00BA ; LATIN
4841 0x00BB, // 00BB..00BF; COMMON
4842 0x00C0, // 00C0..00D6; LATIN
4843 0x00D7, // 00D7 ; COMMON
4844 0x00D8, // 00D8..00F6; LATIN
4845 0x00F7, // 00F7 ; COMMON
4846 0x00F8, // 00F8..02B8; LATIN
4847 0x02B9, // 02B9..02DF; COMMON
4848 0x02E0, // 02E0..02E4; LATIN
4849 0x02E5, // 02E5..02E9; COMMON
4850 0x02EA, // 02EA..02EB; BOPOMOFO
4851 0x02EC, // 02EC..02FF; COMMON
4852 0x0300, // 0300..036F; INHERITED
4853 0x0370, // 0370..0373; GREEK
4854 0x0374, // 0374 ; COMMON
4855 0x0375, // 0375..0377; GREEK
4856 0x0378, // 0378..0379; UNKNOWN
4857 0x037A, // 037A..037D; GREEK
4858 0x037E, // 037E ; COMMON
4859 0x037F, // 037F ; GREEK
4860 0x0380, // 0380..0383; UNKNOWN
4861 0x0384, // 0384 ; GREEK
4862 0x0385, // 0385 ; COMMON
4863 0x0386, // 0386 ; GREEK
4864 0x0387, // 0387 ; COMMON
4865 0x0388, // 0388..038A; GREEK
4866 0x038B, // 038B ; UNKNOWN
4867 0x038C, // 038C ; GREEK
4868 0x038D, // 038D ; UNKNOWN
4869 0x038E, // 038E..03A1; GREEK
4870 0x03A2, // 03A2 ; UNKNOWN
4871 0x03A3, // 03A3..03E1; GREEK
4872 0x03E2, // 03E2..03EF; COPTIC
4873 0x03F0, // 03F0..03FF; GREEK
4874 0x0400, // 0400..0484; CYRILLIC
4875 0x0485, // 0485..0486; INHERITED
4876 0x0487, // 0487..052F; CYRILLIC
4877 0x0530, // 0530 ; UNKNOWN
4878 0x0531, // 0531..0556; ARMENIAN
4879 0x0557, // 0557..0558; UNKNOWN
4880 0x0559, // 0559..0588; ARMENIAN
4881 0x0589, // 0589 ; COMMON
4882 0x058A, // 058A ; ARMENIAN
4883 0x058B, // 058B..058C; UNKNOWN
4884 0x058D, // 058D..058F; ARMENIAN
4885 0x0590, // 0590 ; UNKNOWN
4886 0x0591, // 0591..05C7; HEBREW
4887 0x05C8, // 05C8..05CF; UNKNOWN
4888 0x05D0, // 05D0..05EA; HEBREW
4889 0x05EB, // 05EB..05EE; UNKNOWN
4890 0x05EF, // 05EF..05F4; HEBREW
4891 0x05F5, // 05F5..05FF; UNKNOWN
4892 0x0600, // 0600..0604; ARABIC
4893 0x0605, // 0605 ; COMMON
4894 0x0606, // 0606..060B; ARABIC
4895 0x060C, // 060C ; COMMON
4896 0x060D, // 060D..061A; ARABIC
4897 0x061B, // 061B ; COMMON
4898 0x061C, // 061C ; ARABIC
4899 0x061D, // 061D ; UNKNOWN
4900 0x061E, // 061E ; ARABIC
4901 0x061F, // 061F ; COMMON
4902 0x0620, // 0620..063F; ARABIC
4903 0x0640, // 0640 ; COMMON
4904 0x0641, // 0641..064A; ARABIC
4905 0x064B, // 064B..0655; INHERITED
4906 0x0656, // 0656..066F; ARABIC
4907 0x0670, // 0670 ; INHERITED
4908 0x0671, // 0671..06DC; ARABIC
4909 0x06DD, // 06DD ; COMMON
4910 0x06DE, // 06DE..06FF; ARABIC
4911 0x0700, // 0700..070D; SYRIAC
4912 0x070E, // 070E ; UNKNOWN
4913 0x070F, // 070F..074A; SYRIAC
4914 0x074B, // 074B..074C; UNKNOWN
4915 0x074D, // 074D..074F; SYRIAC
4916 0x0750, // 0750..077F; ARABIC
4917 0x0780, // 0780..07B1; THAANA
4918 0x07B2, // 07B2..07BF; UNKNOWN
4919 0x07C0, // 07C0..07FA; NKO
4920 0x07FB, // 07FB..07FC; UNKNOWN
4921 0X07FD, // 07FD..07FF; NKO
4922 0x0800, // 0800..082D; SAMARITAN
4923 0x082E, // 082E..082F; UNKNOWN
4924 0x0830, // 0830..083E; SAMARITAN
4925 0x083F, // 083F ; UNKNOWN
4926 0x0840, // 0840..085B; MANDAIC
4927 0x085C, // 085C..085D; UNKNOWN
4928 0x085E, // 085E ; MANDAIC
4929 0x085F, // 085F ; UNKNOWN
4930 0x0860, // 0860..086A; SYRIAC
4931 0x086B, // 086B..089F; UNKNOWN
4932 0x08A0, // 08A0..08B4; ARABIC
4933 0x08B5, // 08B5 ; UNKNOWN
4934 0x08B6, // 08B6..08BD; ARABIC
4935 0x08BE, // 08BE..08D2; UNKNOWN
4936 0x08D3, // 08D3..08E1; ARABIC
4937 0x08E2, // 08E2 ; COMMON
4938 0x08E3, // 08E3..08FF; ARABIC
4939 0x0900, // 0900..0950; DEVANAGARI
4940 0x0951, // 0951..0952; INHERITED
4941 0x0953, // 0953..0963; DEVANAGARI
4942 0x0964, // 0964..0965; COMMON
4943 0x0966, // 0966..097F; DEVANAGARI
4944 0x0980, // 0980..0983; BENGALI
4945 0x0984, // 0984 ; UNKNOWN
4946 0x0985, // 0985..098C; BENGALI
4947 0x098D, // 098D..098E; UNKNOWN
4948 0x098F, // 098F..0990; BENGALI
4949 0x0991, // 0991..0992; UNKNOWN
4950 0x0993, // 0993..09A8; BENGALI
4951 0x09A9, // 09A9 ; UNKNOWN
4952 0x09AA, // 09AA..09B0; BENGALI
4953 0x09B1, // 09B1 ; UNKNOWN
4954 0x09B2, // 09B2 ; BENGALI
4955 0x09B3, // 09B3..09B5; UNKNOWN
4956 0x09B6, // 09B6..09B9; BENGALI
4957 0x09BA, // 09BA..09BB; UNKNOWN
4958 0x09BC, // 09BC..09C4; BENGALI
4959 0x09C5, // 09C5..09C6; UNKNOWN
4960 0x09C7, // 09C7..09C8; BENGALI
4961 0x09C9, // 09C9..09CA; UNKNOWN
4962 0x09CB, // 09CB..09CE; BENGALI
4963 0x09CF, // 09CF..09D6; UNKNOWN
4964 0x09D7, // 09D7 ; BENGALI
4965 0x09D8, // 09D8..09DB; UNKNOWN
4966 0x09DC, // 09DC..09DD; BENGALI
4967 0x09DE, // 09DE ; UNKNOWN
4968 0x09DF, // 09DF..09E3; BENGALI
4969 0x09E4, // 09E4..09E5; UNKNOWN
4970 0x09E6, // 09E6..09FE; BENGALI
4971 0x09FF, // 09FF..0A00; UNKNOWN
4972 0x0A01, // 0A01..0A03; GURMUKHI
4973 0x0A04, // 0A04 ; UNKNOWN
4974 0x0A05, // 0A05..0A0A; GURMUKHI
4975 0x0A0B, // 0A0B..0A0E; UNKNOWN
4976 0x0A0F, // 0A0F..0A10; GURMUKHI
4977 0x0A11, // 0A11..0A12; UNKNOWN
4978 0x0A13, // 0A13..0A28; GURMUKHI
4979 0x0A29, // 0A29 ; UNKNOWN
4980 0x0A2A, // 0A2A..0A30; GURMUKHI
4981 0x0A31, // 0A31 ; UNKNOWN
4982 0x0A32, // 0A32..0A33; GURMUKHI
4983 0x0A34, // 0A34 ; UNKNOWN
4984 0x0A35, // 0A35..0A36; GURMUKHI
4985 0x0A37, // 0A37 ; UNKNOWN
4986 0x0A38, // 0A38..0A39; GURMUKHI
4987 0x0A3A, // 0A3A..0A3B; UNKNOWN
4988 0x0A3C, // 0A3C ; GURMUKHI
4989 0x0A3D, // 0A3D ; UNKNOWN
4990 0x0A3E, // 0A3E..0A42; GURMUKHI
4991 0x0A43, // 0A43..0A46; UNKNOWN
4992 0x0A47, // 0A47..0A48; GURMUKHI
4993 0x0A49, // 0A49..0A4A; UNKNOWN
4994 0x0A4B, // 0A4B..0A4D; GURMUKHI
4995 0x0A4E, // 0A4E..0A50; UNKNOWN
4996 0x0A51, // 0A51 ; GURMUKHI
4997 0x0A52, // 0A52..0A58; UNKNOWN
4998 0x0A59, // 0A59..0A5C; GURMUKHI
4999 0x0A5D, // 0A5D ; UNKNOWN
5000 0x0A5E, // 0A5E ; GURMUKHI
5001 0x0A5F, // 0A5F..0A65; UNKNOWN
5002 0x0A66, // 0A66..0A76; GURMUKHI
5003 0x0A77, // 0A77..0A80; UNKNOWN
5004 0x0A81, // 0A81..0A83; GUJARATI
5005 0x0A84, // 0A84 ; UNKNOWN
5006 0x0A85, // 0A85..0A8D; GUJARATI
5007 0x0A8E, // 0A8E ; UNKNOWN
5008 0x0A8F, // 0A8F..0A91; GUJARATI
5009 0x0A92, // 0A92 ; UNKNOWN
5010 0x0A93, // 0A93..0AA8; GUJARATI
5011 0x0AA9, // 0AA9 ; UNKNOWN
5012 0x0AAA, // 0AAA..0AB0; GUJARATI
5013 0x0AB1, // 0AB1 ; UNKNOWN
5014 0x0AB2, // 0AB2..0AB3; GUJARATI
5015 0x0AB4, // 0AB4 ; UNKNOWN
5016 0x0AB5, // 0AB5..0AB9; GUJARATI
5017 0x0ABA, // 0ABA..0ABB; UNKNOWN
5018 0x0ABC, // 0ABC..0AC5; GUJARATI
5019 0x0AC6, // 0AC6 ; UNKNOWN
5020 0x0AC7, // 0AC7..0AC9; GUJARATI
5021 0x0ACA, // 0ACA ; UNKNOWN
5022 0x0ACB, // 0ACB..0ACD; GUJARATI
5023 0x0ACE, // 0ACE..0ACF; UNKNOWN
5024 0x0AD0, // 0AD0 ; GUJARATI
5025 0x0AD1, // 0AD1..0ADF; UNKNOWN
5026 0x0AE0, // 0AE0..0AE3; GUJARATI
5027 0x0AE4, // 0AE4..0AE5; UNKNOWN
5028 0x0AE6, // 0AE6..0AF1; GUJARATI
5029 0x0AF2, // 0AF2..0AF8; UNKNOWN
5030 0x0AF9, // 0AF9..0AFF; GUJARATI
5031 0x0B00, // 0B00 ; UNKNOWN
5032 0x0B01, // 0B01..0B03; ORIYA
5033 0x0B04, // 0B04 ; UNKNOWN
5034 0x0B05, // 0B05..0B0C; ORIYA
5035 0x0B0D, // 0B0D..0B0E; UNKNOWN
5036 0x0B0F, // 0B0F..0B10; ORIYA
5037 0x0B11, // 0B11..0B12; UNKNOWN
5038 0x0B13, // 0B13..0B28; ORIYA
5039 0x0B29, // 0B29 ; UNKNOWN
5040 0x0B2A, // 0B2A..0B30; ORIYA
5041 0x0B31, // 0B31 ; UNKNOWN
5042 0x0B32, // 0B32..0B33; ORIYA
5043 0x0B34, // 0B34 ; UNKNOWN
5044 0x0B35, // 0B35..0B39; ORIYA
5045 0x0B3A, // 0B3A..0B3B; UNKNOWN
5046 0x0B3C, // 0B3C..0B44; ORIYA
5047 0x0B45, // 0B45..0B46; UNKNOWN
5048 0x0B47, // 0B47..0B48; ORIYA
5049 0x0B49, // 0B49..0B4A; UNKNOWN
5050 0x0B4B, // 0B4B..0B4D; ORIYA
5051 0x0B4E, // 0B4E..0B55; UNKNOWN
5052 0x0B56, // 0B56..0B57; ORIYA
5053 0x0B58, // 0B58..0B5B; UNKNOWN
5054 0x0B5C, // 0B5C..0B5D; ORIYA
5055 0x0B5E, // 0B5E ; UNKNOWN
5056 0x0B5F, // 0B5F..0B63; ORIYA
5057 0x0B64, // 0B64..0B65; UNKNOWN
5058 0x0B66, // 0B66..0B77; ORIYA
5059 0x0B78, // 0B78..0B81; UNKNOWN
5060 0x0B82, // 0B82..0B83; TAMIL
5061 0x0B84, // 0B84 ; UNKNOWN
5062 0x0B85, // 0B85..0B8A; TAMIL
5063 0x0B8B, // 0B8B..0B8D; UNKNOWN
5064 0x0B8E, // 0B8E..0B90; TAMIL
5065 0x0B91, // 0B91 ; UNKNOWN
5066 0x0B92, // 0B92..0B95; TAMIL
5067 0x0B96, // 0B96..0B98; UNKNOWN
5068 0x0B99, // 0B99..0B9A; TAMIL
5069 0x0B9B, // 0B9B ; UNKNOWN
5070 0x0B9C, // 0B9C ; TAMIL
5071 0x0B9D, // 0B9D ; UNKNOWN
5072 0x0B9E, // 0B9E..0B9F; TAMIL
5073 0x0BA0, // 0BA0..0BA2; UNKNOWN
5074 0x0BA3, // 0BA3..0BA4; TAMIL
5075 0x0BA5, // 0BA5..0BA7; UNKNOWN
5076 0x0BA8, // 0BA8..0BAA; TAMIL
5077 0x0BAB, // 0BAB..0BAD; UNKNOWN
5078 0x0BAE, // 0BAE..0BB9; TAMIL
5079 0x0BBA, // 0BBA..0BBD; UNKNOWN
5080 0x0BBE, // 0BBE..0BC2; TAMIL
5081 0x0BC3, // 0BC3..0BC5; UNKNOWN
5082 0x0BC6, // 0BC6..0BC8; TAMIL
5083 0x0BC9, // 0BC9 ; UNKNOWN
5084 0x0BCA, // 0BCA..0BCD; TAMIL
5085 0x0BCE, // 0BCE..0BCF; UNKNOWN
5086 0x0BD0, // 0BD0 ; TAMIL
5087 0x0BD1, // 0BD1..0BD6; UNKNOWN
5088 0x0BD7, // 0BD7 ; TAMIL
5089 0x0BD8, // 0BD8..0BE5; UNKNOWN
5090 0x0BE6, // 0BE6..0BFA; TAMIL
5091 0x0BFB, // 0BFB..0BFF; UNKNOWN
5092 0x0C00, // 0C00..0C0C; TELUGU
5093 0x0C0D, // 0C0D ; UNKNOWN
5094 0x0C0E, // 0C0E..0C10; TELUGU
5095 0x0C11, // 0C11 ; UNKNOWN
5096 0x0C12, // 0C12..0C28; TELUGU
5097 0x0C29, // 0C29 ; UNKNOWN
5098 0x0C2A, // 0C2A..0C39; TELUGU
5099 0x0C3A, // 0C3A..0C3C; UNKNOWN
5100 0x0C3D, // 0C3D..0C44; TELUGU
5101 0x0C45, // 0C45 ; UNKNOWN
5102 0x0C46, // 0C46..0C48; TELUGU
5103 0x0C49, // 0C49 ; UNKNOWN
5104 0x0C4A, // 0C4A..0C4D; TELUGU
5105 0x0C4E, // 0C4E..0C54; UNKNOWN
5106 0x0C55, // 0C55..0C56; TELUGU
5107 0x0C57, // 0C57 ; UNKNOWN
5108 0x0C58, // 0C58..0C5A; TELUGU
5109 0x0C5B, // 0C5B..0C5F; UNKNOWN
5110 0x0C60, // 0C60..0C63; TELUGU
5111 0x0C64, // 0C64..0C65; UNKNOWN
5112 0x0C66, // 0C66..0C6F; TELUGU
5113 0x0C70, // 0C70..0C77; UNKNOWN
5114 0x0C78, // 0C78..0C7F; TELUGU
5115 0x0C80, // 0C80..0C8C; KANNADA
5116 0x0C8D, // 0C8D ; UNKNOWN
5117 0x0C8E, // 0C8E..0C90; KANNADA
5118 0x0C91, // 0C91 ; UNKNOWN
5119 0x0C92, // 0C92..0CA8; KANNADA
5120 0x0CA9, // 0CA9 ; UNKNOWN
5121 0x0CAA, // 0CAA..0CB3; KANNADA
5122 0x0CB4, // 0CB4 ; UNKNOWN
5123 0x0CB5, // 0CB5..0CB9; KANNADA
5124 0x0CBA, // 0CBA..0CBB; UNKNOWN
5125 0x0CBC, // 0CBC..0CC4; KANNADA
5126 0x0CC5, // 0CC5 ; UNKNOWN
5127 0x0CC6, // 0CC6..0CC8; KANNADA
5128 0x0CC9, // 0CC9 ; UNKNOWN
5129 0x0CCA, // 0CCA..0CCD; KANNADA
5130 0x0CCE, // 0CCE..0CD4; UNKNOWN
5131 0x0CD5, // 0CD5..0CD6; KANNADA
5132 0x0CD7, // 0CD7..0CDD; UNKNOWN
5133 0x0CDE, // 0CDE ; KANNADA
5134 0x0CDF, // 0CDF ; UNKNOWN
5135 0x0CE0, // 0CE0..0CE3; KANNADA
5136 0x0CE4, // 0CE4..0CE5; UNKNOWN
5137 0x0CE6, // 0CE6..0CEF; KANNADA
5138 0x0CF0, // 0CF0 ; UNKNOWN
5139 0x0CF1, // 0CF1..0CF2; KANNADA
5140 0x0CF3, // 0CF3..0CFF; UNKNOWN
5141 0x0D00, // 0D00..0D03; MALAYALAM
5142 0x0D04, // 0D04 ; UNKNOWN
5143 0x0D05, // 0D05..0D0C; MALAYALAM
5144 0x0D0D, // 0D0D ; UNKNOWN
5145 0x0D0E, // 0D0E..0D10; MALAYALAM
5146 0x0D11, // 0D11 ; UNKNOWN
5147 0x0D12, // 0D12..0D44; MALAYALAM
5148 0x0D45, // 0D45 ; UNKNOWN
5149 0x0D46, // 0D46..0D48; MALAYALAM
5150 0x0D49, // 0D49 ; UNKNOWN
5151 0x0D4A, // 0D4A..0D4F; MALAYALAM
5152 0x0D50, // 0D50..0D53; UNKNOWN
5153 0x0D54, // 0D54..0D63; MALAYALAM
5154 0x0D64, // 0D64..0D65; UNKNOWN
5155 0x0D66, // 0D66..0D7F; MALAYALAM
5156 0x0D80, // 0D80..0D81; UNKNOWN
5157 0x0D82, // 0D82..0D83; SINHALA
5158 0x0D84, // 0D84 ; UNKNOWN
5159 0x0D85, // 0D85..0D96; SINHALA
5160 0x0D97, // 0D97..0D99; UNKNOWN
5161 0x0D9A, // 0D9A..0DB1; SINHALA
5162 0x0DB2, // 0DB2 ; UNKNOWN
5163 0x0DB3, // 0DB3..0DBB; SINHALA
5164 0x0DBC, // 0DBC ; UNKNOWN
5165 0x0DBD, // 0DBD ; SINHALA
5166 0x0DBE, // 0DBE..0DBF; UNKNOWN
5167 0x0DC0, // 0DC0..0DC6; SINHALA
5168 0x0DC7, // 0DC7..0DC9; UNKNOWN
5169 0x0DCA, // 0DCA ; SINHALA
5170 0x0DCB, // 0DCB..0DCE; UNKNOWN
5171 0x0DCF, // 0DCF..0DD4; SINHALA
5172 0x0DD5, // 0DD5 ; UNKNOWN
5173 0x0DD6, // 0DD6 ; SINHALA
5174 0x0DD7, // 0DD7 ; UNKNOWN
5175 0x0DD8, // 0DD8..0DDF; SINHALA
5176 0x0DE0, // 0DE0..0DE5; UNKNOWN
5177 0x0DE6, // 0DE6..0DEF; SINHALA
5178 0x0DF0, // 0DF0..0DF1; UNKNOWN
5179 0x0DF2, // 0DF2..0DF4; SINHALA
5180 0x0DF5, // 0DF5..0E00; UNKNOWN
5181 0x0E01, // 0E01..0E3A; THAI
5182 0x0E3B, // 0E3B..0E3E; UNKNOWN
5183 0x0E3F, // 0E3F ; COMMON
5184 0x0E40, // 0E40..0E5B; THAI
5185 0x0E5C, // 0E5C..0E80; UNKNOWN
5186 0x0E81, // 0E81..0E82; LAO
5187 0x0E83, // 0E83 ; UNKNOWN
5188 0x0E84, // 0E84 ; LAO
5189 0x0E85, // 0E85..0E86; UNKNOWN
5190 0x0E87, // 0E87..0E88; LAO
5191 0x0E89, // 0E89 ; UNKNOWN
5192 0x0E8A, // 0E8A ; LAO
5193 0x0E8B, // 0E8B..0E8C; UNKNOWN
5194 0x0E8D, // 0E8D ; LAO
5195 0x0E8E, // 0E8E..0E93; UNKNOWN
5196 0x0E94, // 0E94..0E97; LAO
5197 0x0E98, // 0E98 ; UNKNOWN
5198 0x0E99, // 0E99..0E9F; LAO
5199 0x0EA0, // 0EA0 ; UNKNOWN
5200 0x0EA1, // 0EA1..0EA3; LAO
5201 0x0EA4, // 0EA4 ; UNKNOWN
5202 0x0EA5, // 0EA5 ; LAO
5203 0x0EA6, // 0EA6 ; UNKNOWN
5204 0x0EA7, // 0EA7 ; LAO
5205 0x0EA8, // 0EA8..0EA9; UNKNOWN
5206 0x0EAA, // 0EAA..0EAB; LAO
5207 0x0EAC, // 0EAC ; UNKNOWN
5208 0x0EAD, // 0EAD..0EB9; LAO
5209 0x0EBA, // 0EBA ; UNKNOWN
5210 0x0EBB, // 0EBB..0EBD; LAO
5211 0x0EBE, // 0EBE..0EBF; UNKNOWN
5212 0x0EC0, // 0EC0..0EC4; LAO
5213 0x0EC5, // 0EC5 ; UNKNOWN
5214 0x0EC6, // 0EC6 ; LAO
5215 0x0EC7, // 0EC7 ; UNKNOWN
5216 0x0EC8, // 0EC8..0ECD; LAO
5217 0x0ECE, // 0ECE..0ECF; UNKNOWN
5218 0x0ED0, // 0ED0..0ED9; LAO
5219 0x0EDA, // 0EDA..0EDB; UNKNOWN
5220 0x0EDC, // 0EDC..0EDF; LAO
5221 0x0EE0, // 0EE0..0EFF; UNKNOWN
5222 0x0F00, // 0F00..0F47; TIBETAN
5223 0x0F48, // 0F48 ; UNKNOWN
5224 0x0F49, // 0F49..0F6C; TIBETAN
5225 0x0F6D, // 0F6D..0F70; UNKNOWN
5226 0x0F71, // 0F71..0F97; TIBETAN
5227 0x0F98, // 0F98 ; UNKNOWN
5228 0x0F99, // 0F99..0FBC; TIBETAN
5229 0x0FBD, // 0FBD ; UNKNOWN
5230 0x0FBE, // 0FBE..0FCC; TIBETAN
5231 0x0FCD, // 0FCD ; UNKNOWN
5232 0x0FCE, // 0FCE..0FD4; TIBETAN
5233 0x0FD5, // 0FD5..0FD8; COMMON
5234 0x0FD9, // 0FD9..0FDA; TIBETAN
5235 0x0FDB, // 0FDB..FFF; UNKNOWN
5236 0x1000, // 1000..109F; MYANMAR
5237 0x10A0, // 10A0..10C5; GEORGIAN
5238 0x10C6, // 10C6 ; UNKNOWN
5239 0x10C7, // 10C7 ; GEORGIAN
5240 0x10C8, // 10C8..10CC; UNKNOWN
5241 0x10CD, // 10CD ; GEORGIAN
5242 0x10CE, // 10CE..10CF; UNKNOWN
5243 0x10D0, // 10D0..10FA; GEORGIAN
5244 0x10FB, // 10FB ; COMMON
5245 0x10FC, // 10FC..10FF; GEORGIAN
5246 0x1100, // 1100..11FF; HANGUL
5247 0x1200, // 1200..1248; ETHIOPIC
5248 0x1249, // 1249 ; UNKNOWN
5249 0x124A, // 124A..124D; ETHIOPIC
5250 0x124E, // 124E..124F; UNKNOWN
5251 0x1250, // 1250..1256; ETHIOPIC
5252 0x1257, // 1257 ; UNKNOWN
5253 0x1258, // 1258 ; ETHIOPIC
5254 0x1259, // 1259 ; UNKNOWN
5255 0x125A, // 125A..125D; ETHIOPIC
5256 0x125E, // 125E..125F; UNKNOWN
5257 0x1260, // 1260..1288; ETHIOPIC
5258 0x1289, // 1289 ; UNKNOWN
5259 0x128A, // 128A..128D; ETHIOPIC
5260 0x128E, // 128E..128F; UNKNOWN
5261 0x1290, // 1290..12B0; ETHIOPIC
5262 0x12B1, // 12B1 ; UNKNOWN
5263 0x12B2, // 12B2..12B5; ETHIOPIC
5264 0x12B6, // 12B6..12B7; UNKNOWN
5265 0x12B8, // 12B8..12BE; ETHIOPIC
5266 0x12BF, // 12BF ; UNKNOWN
5267 0x12C0, // 12C0 ; ETHIOPIC
5268 0x12C1, // 12C1 ; UNKNOWN
5269 0x12C2, // 12C2..12C5; ETHIOPIC
5270 0x12C6, // 12C6..12C7; UNKNOWN
5271 0x12C8, // 12C8..12D6; ETHIOPIC
5272 0x12D7, // 12D7 ; UNKNOWN
5273 0x12D8, // 12D8..1310; ETHIOPIC
5274 0x1311, // 1311 ; UNKNOWN
5275 0x1312, // 1312..1315; ETHIOPIC
5276 0x1316, // 1316..1317; UNKNOWN
5277 0x1318, // 1318..135A; ETHIOPIC
5278 0x135B, // 135B..135C; UNKNOWN
5279 0x135D, // 135D..137C; ETHIOPIC
5280 0x137D, // 137D..137F; UNKNOWN
5281 0x1380, // 1380..1399; ETHIOPIC
5282 0x139A, // 139A..139F; UNKNOWN
5283 0x13A0, // 13A0..13F5; CHEROKEE
5284 0x13F6, // 13F6..13F7; UNKNOWN
5285 0x13F8, // 13F8..13FD; CHEROKEE
5286 0x13FE, // 13FE..13FF; UNKNOWN
5287 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5288 0x1680, // 1680..169C; OGHAM
5289 0x169D, // 169D..169F; UNKNOWN
5290 0x16A0, // 16A0..16EA; RUNIC
5291 0x16EB, // 16EB..16ED; COMMON
5292 0x16EE, // 16EE..16F8; RUNIC
5293 0x16F9, // 16F9..16FF; UNKNOWN
5294 0x1700, // 1700..170C; TAGALOG
5295 0x170D, // 170D ; UNKNOWN
5296 0x170E, // 170E..1714; TAGALOG
5297 0x1715, // 1715..171F; UNKNOWN
5298 0x1720, // 1720..1734; HANUNOO
5299 0x1735, // 1735..1736; COMMON
5300 0x1737, // 1737..173F; UNKNOWN
5301 0x1740, // 1740..1753; BUHID
5302 0x1754, // 1754..175F; UNKNOWN
5303 0x1760, // 1760..176C; TAGBANWA
5304 0x176D, // 176D ; UNKNOWN
5305 0x176E, // 176E..1770; TAGBANWA
5306 0x1771, // 1771 ; UNKNOWN
5307 0x1772, // 1772..1773; TAGBANWA
5308 0x1774, // 1774..177F; UNKNOWN
5309 0x1780, // 1780..17DD; KHMER
5310 0x17DE, // 17DE..17DF; UNKNOWN
5311 0x17E0, // 17E0..17E9; KHMER
5312 0x17EA, // 17EA..17EF; UNKNOWN
5313 0x17F0, // 17F0..17F9; KHMER
5314 0x17FA, // 17FA..17FF; UNKNOWN
5315 0x1800, // 1800..1801; MONGOLIAN
5316 0x1802, // 1802..1803; COMMON
5317 0x1804, // 1804 ; MONGOLIAN
5318 0x1805, // 1805 ; COMMON
5319 0x1806, // 1806..180E; MONGOLIAN
5320 0x180F, // 180F ; UNKNOWN
5321 0x1810, // 1810..1819; MONGOLIAN
5322 0x181A, // 181A..181F; UNKNOWN
5323 0x1820, // 1820..1878; MONGOLIAN
5324 0x1879, // 1879..187F; UNKNOWN
5325 0x1880, // 1880..18AA; MONGOLIAN
5326 0x18AB, // 18AB..18AF; UNKNOWN
5327 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
5328 0x18F6, // 18F6..18FF; UNKNOWN
5329 0x1900, // 1900..191E; LIMBU
5330 0x191F, // 191F ; UNKNOWN
5331 0x1920, // 1920..192B; LIMBU
5332 0x192C, // 192C..192F; UNKNOWN
5333 0x1930, // 1930..193B; LIMBU
5334 0x193C, // 193C..193F; UNKNOWN
5335 0x1940, // 1940 ; LIMBU
5336 0x1941, // 1941..1943; UNKNOWN
5337 0x1944, // 1944..194F; LIMBU
5338 0x1950, // 1950..196D; TAI_LE
5339 0x196E, // 196E..196F; UNKNOWN
5340 0x1970, // 1970..1974; TAI_LE
5341 0x1975, // 1975..197F; UNKNOWN
5342 0x1980, // 1980..19AB; NEW_TAI_LUE
5343 0x19AC, // 19AC..19AF; UNKNOWN
5344 0x19B0, // 19B0..19C9; NEW_TAI_LUE
5345 0x19CA, // 19CA..19CF; UNKNOWN
5346 0x19D0, // 19D0..19DA; NEW_TAI_LUE
5347 0x19DB, // 19DB..19DD; UNKNOWN
5348 0x19DE, // 19DE..19DF; NEW_TAI_LUE
5349 0x19E0, // 19E0..19FF; KHMER
5350 0x1A00, // 1A00..1A1B; BUGINESE
5351 0x1A1C, // 1A1C..1A1D; UNKNOWN
5352 0x1A1E, // 1A1E..1A1F; BUGINESE
5353 0x1A20, // 1A20..1A5E; TAI_THAM
5354 0x1A5F, // 1A5F ; UNKNOWN
5355 0x1A60, // 1A60..1A7C; TAI_THAM
5356 0x1A7D, // 1A7D..1A7E; UNKNOWN
5357 0x1A7F, // 1A7F..1A89; TAI_THAM
5358 0x1A8A, // 1A8A..1A8F; UNKNOWN
5359 0x1A90, // 1A90..1A99; TAI_THAM
5360 0x1A9A, // 1A9A..1A9F; UNKNOWN
5361 0x1AA0, // 1AA0..1AAD; TAI_THAM
5362 0x1AAE, // 1AAE..1AAF; UNKNOWN
5363 0x1AB0, // 1AB0..1ABE; INHERITED
5364 0x1ABF, // 1ABF..1AFF; UNKNOWN
5365 0x1B00, // 1B00..1B4B; BALINESE
5366 0x1B4C, // 1B4C..1B4F; UNKNOWN
5367 0x1B50, // 1B50..1B7C; BALINESE
5368 0x1B7D, // 1B7D..1B7F; UNKNOWN
5369 0x1B80, // 1B80..1BBF; SUNDANESE
5370 0x1BC0, // 1BC0..1BF3; BATAK
5371 0x1BF4, // 1BF4..1BFB; UNKNOWN
5372 0x1BFC, // 1BFC..1BFF; BATAK
5373 0x1C00, // 1C00..1C37; LEPCHA
5374 0x1C38, // 1C38..1C3A; UNKNOWN
5375 0x1C3B, // 1C3B..1C49; LEPCHA
5376 0x1C4A, // 1C4A..1C4C; UNKNOWN
5377 0x1C4D, // 1C4D..1C4F; LEPCHA
5378 0x1C50, // 1C50..1C7F; OL_CHIKI
5379 0x1C80, // 1C80..1C88; CYRILLIC
5380 0x1C89, // 1C89 ; UNKNOWN
5381 0x1C90, // 1C90..1CBA; GEORGIAN
5382 0x1CBB, // 1CBB..1CBC; UNKNOWN
5383 0x1CBD, // 1CBD..1CBF; GEORGIAN
5384 0x1CC0, // 1CC0..1CC7; SUNDANESE
5385 0x1CC8, // 1CC8..1CCF; UNKNOWN
5386 0x1CD0, // 1CD0..1CD2; INHERITED
5387 0x1CD3, // 1CD3 ; COMMON
5388 0x1CD4, // 1CD4..1CE0; INHERITED
5389 0x1CE1, // 1CE1 ; COMMON
5390 0x1CE2, // 1CE2..1CE8; INHERITED
5391 0x1CE9, // 1CE9..1CEC; COMMON
5392 0x1CED, // 1CED ; INHERITED
5393 0x1CEE, // 1CEE..1CF3; COMMON
5394 0x1CF4, // 1CF4 ; INHERITED
5395 0x1CF5, // 1CF5..1CF7; COMMON
5396 0x1CF8, // 1CF8..1CF9; INHERITED
5397 0x1CFA, // 1CFA..1CFF; UNKNOWN
5398 0x1D00, // 1D00..1D25; LATIN
5399 0x1D26, // 1D26..1D2A; GREEK
5400 0x1D2B, // 1D2B ; CYRILLIC
5401 0x1D2C, // 1D2C..1D5C; LATIN
5402 0x1D5D, // 1D5D..1D61; GREEK
5403 0x1D62, // 1D62..1D65; LATIN
5404 0x1D66, // 1D66..1D6A; GREEK
5405 0x1D6B, // 1D6B..1D77; LATIN
5406 0x1D78, // 1D78 ; CYRILLIC
5407 0x1D79, // 1D79..1DBE; LATIN
5408 0x1DBF, // 1DBF ; GREEK
5409 0x1DC0, // 1DC0..1DF9; INHERITED
5410 0x1DFA, // 1DFA ; UNKNOWN
5411 0x1DFB, // 1DFB..1DFF; INHERITED
5412 0x1E00, // 1E00..1EFF; LATIN
5413 0x1F00, // 1F00..1F15; GREEK
5414 0x1F16, // 1F16..1F17; UNKNOWN
5415 0x1F18, // 1F18..1F1D; GREEK
5416 0x1F1E, // 1F1E..1F1F; UNKNOWN
5417 0x1F20, // 1F20..1F45; GREEK
5418 0x1F46, // 1F46..1F47; UNKNOWN
5419 0x1F48, // 1F48..1F4D; GREEK
5420 0x1F4E, // 1F4E..1F4F; UNKNOWN
5421 0x1F50, // 1F50..1F57; GREEK
5422 0x1F58, // 1F58 ; UNKNOWN
5423 0x1F59, // 1F59 ; GREEK
5424 0x1F5A, // 1F5A ; UNKNOWN
5425 0x1F5B, // 1F5B ; GREEK
5426 0x1F5C, // 1F5C ; UNKNOWN
5427 0x1F5D, // 1F5D ; GREEK
5428 0x1F5E, // 1F5E ; UNKNOWN
5429 0x1F5F, // 1F5F..1F7D; GREEK
5430 0x1F7E, // 1F7E..1F7F; UNKNOWN
5431 0x1F80, // 1F80..1FB4; GREEK
5432 0x1FB5, // 1FB5 ; UNKNOWN
5433 0x1FB6, // 1FB6..1FC4; GREEK
5434 0x1FC5, // 1FC5 ; UNKNOWN
5435 0x1FC6, // 1FC6..1FD3; GREEK
5436 0x1FD4, // 1FD4..1FD5; UNKNOWN
5437 0x1FD6, // 1FD6..1FDB; GREEK
5438 0x1FDC, // 1FDC ; UNKNOWN
5439 0x1FDD, // 1FDD..1FEF; GREEK
5440 0x1FF0, // 1FF0..1FF1; UNKNOWN
5441 0x1FF2, // 1FF2..1FF4; GREEK
5442 0x1FF5, // 1FF5 ; UNKNOWN
5443 0x1FF6, // 1FF6..1FFE; GREEK
5444 0x1FFF, // 1FFF ; UNKNOWN
5445 0x2000, // 2000..200B; COMMON
5446 0x200C, // 200C..200D; INHERITED
5447 0x200E, // 200E..2064; COMMON
5448 0x2065, // 2065 ; UNKNOWN
5449 0x2066, // 2066..2070; COMMON
5450 0x2071, // 2071 ; LATIN
5451 0x2072, // 2072..2073; UNKNOWN
5452 0x2074, // 2074..207E; COMMON
5453 0x207F, // 207F ; LATIN
5454 0x2080, // 2080..208E; COMMON
5455 0x208F, // 208F ; UNKNOWN
5456 0x2090, // 2090..209C; LATIN
5457 0x209D, // 209D..209F; UNKNOWN
5458 0x20A0, // 20A0..20BF; COMMON
5459 0x20C0, // 20C0..20CF; UNKNOWN
5460 0x20D0, // 20D0..20F0; INHERITED
5461 0x20F1, // 20F1..20FF; UNKNOWN
5462 0x2100, // 2100..2125; COMMON
5463 0x2126, // 2126 ; GREEK
5464 0x2127, // 2127..2129; COMMON
5465 0x212A, // 212A..212B; LATIN
5466 0x212C, // 212C..2131; COMMON
5467 0x2132, // 2132 ; LATIN
5468 0x2133, // 2133..214D; COMMON
5469 0x214E, // 214E ; LATIN
5470 0x214F, // 214F..215F; COMMON
5471 0x2160, // 2160..2188; LATIN
5472 0x2189, // 2189..218B; COMMON
5473 0x218C, // 218C..218F; UNKNOWN
5474 0x2190, // 2190..2426; COMMON
5475 0x2427, // 2427..243F; UNKNOWN
5476 0x2440, // 2440..244A; COMMON
5477 0x244B, // 244B..245F; UNKNOWN
5478 0x2460, // 2460..27FF; COMMON
5479 0x2800, // 2800..28FF; BRAILLE
5480 0x2900, // 2900..2B73; COMMON
5481 0x2B74, // 2B74..2B75; UNKNOWN
5482 0x2B76, // 2B76..2B95; COMMON
5483 0x2B96, // 2B96..2B97; UNKNOWN
5484 0x2B98, // 2B98..2BC8; COMMON
5485 0x2BC9, // 2BC9 ; UNKNOWN
5486 0x2BCA, // 2BCA..2BFE; COMMON
5487 0x2BFF, // 2BFF; UNKNOWN
5488 0x2C00, // 2C00..2C2E; GLAGOLITIC
5489 0x2C2F, // 2C2F ; UNKNOWN
5490 0x2C30, // 2C30..2C5E; GLAGOLITIC
5491 0x2C5F, // 2C5F ; UNKNOWN
5492 0x2C60, // 2C60..2C7F; LATIN
5493 0x2C80, // 2C80..2CF3; COPTIC
5494 0x2CF4, // 2CF4..2CF8; UNKNOWN
5495 0x2CF9, // 2CF9..2CFF; COPTIC
5496 0x2D00, // 2D00..2D25; GEORGIAN
5497 0x2D26, // 2D26 ; UNKNOWN
5498 0x2D27, // 2D27 ; GEORGIAN
5499 0x2D28, // 2D28..2D2C; UNKNOWN
5500 0x2D2D, // 2D2D ; GEORGIAN
5501 0x2D2E, // 2D2E..2D2F; UNKNOWN
5502 0x2D30, // 2D30..2D67; TIFINAGH
5503 0x2D68, // 2D68..2D6E; UNKNOWN
5504 0x2D6F, // 2D6F..2D70; TIFINAGH
5505 0x2D71, // 2D71..2D7E; UNKNOWN
5506 0x2D7F, // 2D7F ; TIFINAGH
5507 0x2D80, // 2D80..2D96; ETHIOPIC
5508 0x2D97, // 2D97..2D9F; UNKNOWN
5509 0x2DA0, // 2DA0..2DA6; ETHIOPIC
5510 0x2DA7, // 2DA7 ; UNKNOWN
5511 0x2DA8, // 2DA8..2DAE; ETHIOPIC
5512 0x2DAF, // 2DAF ; UNKNOWN
5513 0x2DB0, // 2DB0..2DB6; ETHIOPIC
5514 0x2DB7, // 2DB7 ; UNKNOWN
5515 0x2DB8, // 2DB8..2DBE; ETHIOPIC
5516 0x2DBF, // 2DBF ; UNKNOWN
5517 0x2DC0, // 2DC0..2DC6; ETHIOPIC
5518 0x2DC7, // 2DC7 ; UNKNOWN
5519 0x2DC8, // 2DC8..2DCE; ETHIOPIC
5520 0x2DCF, // 2DCF ; UNKNOWN
5521 0x2DD0, // 2DD0..2DD6; ETHIOPIC
5522 0x2DD7, // 2DD7 ; UNKNOWN
5523 0x2DD8, // 2DD8..2DDE; ETHIOPIC
5524 0x2DDF, // 2DDF ; UNKNOWN
5525 0x2DE0, // 2DE0..2DFF; CYRILLIC
5526 0x2E00, // 2E00..2E4E; COMMON
5527 0x2E4F, // 2E4F..2E7F; UNKNOWN
5528 0x2E80, // 2E80..2E99; HAN
5529 0x2E9A, // 2E9A ; UNKNOWN
5530 0x2E9B, // 2E9B..2EF3; HAN
5531 0x2EF4, // 2EF4..2EFF; UNKNOWN
5532 0x2F00, // 2F00..2FD5; HAN
5533 0x2FD6, // 2FD6..2FEF; UNKNOWN
5534 0x2FF0, // 2FF0..2FFB; COMMON
5535 0x2FFC, // 2FFC..2FFF; UNKNOWN
5536 0x3000, // 3000..3004; COMMON
5537 0x3005, // 3005 ; HAN
5538 0x3006, // 3006 ; COMMON
5539 0x3007, // 3007 ; HAN
5540 0x3008, // 3008..3020; COMMON
5541 0x3021, // 3021..3029; HAN
5542 0x302A, // 302A..302D; INHERITED
5543 0x302E, // 302E..302F; HANGUL
5544 0x3030, // 3030..3037; COMMON
5545 0x3038, // 3038..303B; HAN
5546 0x303C, // 303C..303F; COMMON
5547 0x3040, // 3040 ; UNKNOWN
5548 0x3041, // 3041..3096; HIRAGANA
5549 0x3097, // 3097..3098; UNKNOWN
5550 0x3099, // 3099..309A; INHERITED
5551 0x309B, // 309B..309C; COMMON
5552 0x309D, // 309D..309F; HIRAGANA
5553 0x30A0, // 30A0 ; COMMON
5554 0x30A1, // 30A1..30FA; KATAKANA
5555 0x30FB, // 30FB..30FC; COMMON
5556 0x30FD, // 30FD..30FF; KATAKANA
5557 0x3100, // 3100..3104; UNKNOWN
5558 0x3105, // 3105..312F; BOPOMOFO
5559 0x3130, // 3130; UNKNOWN
5560 0x3131, // 3131..318E; HANGUL
5561 0x318F, // 318F ; UNKNOWN
5562 0x3190, // 3190..319F; COMMON
5563 0x31A0, // 31A0..31BA; BOPOMOFO
5564 0x31BB, // 31BB..31BF; UNKNOWN
5565 0x31C0, // 31C0..31E3; COMMON
5566 0x31E4, // 31E4..31EF; UNKNOWN
5567 0x31F0, // 31F0..31FF; KATAKANA
5568 0x3200, // 3200..321E; HANGUL
5569 0x321F, // 321F ; UNKNOWN
5570 0x3220, // 3220..325F; COMMON
5571 0x3260, // 3260..327E; HANGUL
5572 0x327F, // 327F..32CF; COMMON
5573 0x32D0, // 32D0..32FE; KATAKANA
5574 0x32FF, // 32FF ; COMMON
5575 0x3300, // 3300..3357; KATAKANA
5576 0x3358, // 3358..33FF; COMMON
5577 0x3400, // 3400..4DB5; HAN
5578 0x4DB6, // 4DB6..4DBF; UNKNOWN
5579 0x4DC0, // 4DC0..4DFF; COMMON
5580 0x4E00, // 4E00..9FEF; HAN
5581 0x9FF0, // 9FF0..9FFF; UNKNOWN
5582 0xA000, // A000..A48C; YI
5583 0xA48D, // A48D..A48F; UNKNOWN
5584 0xA490, // A490..A4C6; YI
5585 0xA4C7, // A4C7..A4CF; UNKNOWN
5586 0xA4D0, // A4D0..A4FF; LISU
5587 0xA500, // A500..A62B; VAI
5588 0xA62C, // A62C..A63F; UNKNOWN
5589 0xA640, // A640..A69F; CYRILLIC
5590 0xA6A0, // A6A0..A6F7; BAMUM
5591 0xA6F8, // A6F8..A6FF; UNKNOWN
5592 0xA700, // A700..A721; COMMON
5593 0xA722, // A722..A787; LATIN
5594 0xA788, // A788..A78A; COMMON
5595 0xA78B, // A78B..A7B9; LATIN
5596 0xA7C0, // A7C0..A7F6; UNKNOWN
5597 0xA7F7, // A7F7..A7FF; LATIN
5598 0xA800, // A800..A82B; SYLOTI_NAGRI
5599 0xA82C, // A82C..A82F; UNKNOWN
5600 0xA830, // A830..A839; COMMON
5601 0xA83A, // A83A..A83F; UNKNOWN
5602 0xA840, // A840..A877; PHAGS_PA
5603 0xA878, // A878..A87F; UNKNOWN
5604 0xA880, // A880..A8C5; SAURASHTRA
5605 0xA8C6, // A8C6..A8CD; UNKNOWN
5606 0xA8CE, // A8CE..A8D9; SAURASHTRA
5607 0xA8DA, // A8DA..A8DF; UNKNOWN
5608 0xA8E0, // A8E0..A8FF; DEVANAGARI
5609 0xA900, // A900..A92D; KAYAH_LI
5610 0xA92E, // A92E ; COMMON
5611 0xA92F, // A92F ; KAYAH_LI
5612 0xA930, // A930..A953; REJANG
5613 0xA954, // A954..A95E; UNKNOWN
5614 0xA95F, // A95F ; REJANG
5615 0xA960, // A960..A97C; HANGUL
5616 0xA97D, // A97D..A97F; UNKNOWN
5617 0xA980, // A980..A9CD; JAVANESE
5618 0xA9CE, // A9CE ; UNKNOWN
5619 0xA9CF, // A9CF ; COMMON
5620 0xA9D0, // A9D0..A9D9; JAVANESE
5621 0xA9DA, // A9DA..A9DD; UNKNOWN
5622 0xA9DE, // A9DE..A9DF; JAVANESE
5623 0xA9E0, // A9E0..A9FE; MYANMAR
5624 0xA9FF, // A9FF ; UNKNOWN
5625 0xAA00, // AA00..AA36; CHAM
5626 0xAA37, // AA37..AA3F; UNKNOWN
5627 0xAA40, // AA40..AA4D; CHAM
5628 0xAA4E, // AA4E..AA4F; UNKNOWN
5629 0xAA50, // AA50..AA59; CHAM
5630 0xAA5A, // AA5A..AA5B; UNKNOWN
5631 0xAA5C, // AA5C..AA5F; CHAM
5632 0xAA60, // AA60..AA7F; MYANMAR
5633 0xAA80, // AA80..AAC2; TAI_VIET
5634 0xAAC3, // AAC3..AADA; UNKNOWN
5635 0xAADB, // AADB..AADF; TAI_VIET
5636 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
5637 0xAAF7, // AAF7..AB00; UNKNOWN
5638 0xAB01, // AB01..AB06; ETHIOPIC
5639 0xAB07, // AB07..AB08; UNKNOWN
5640 0xAB09, // AB09..AB0E; ETHIOPIC
5641 0xAB0F, // AB0F..AB10; UNKNOWN
5642 0xAB11, // AB11..AB16; ETHIOPIC
5643 0xAB17, // AB17..AB1F; UNKNOWN
5644 0xAB20, // AB20..AB26; ETHIOPIC
5645 0xAB27, // AB27 ; UNKNOWN
5646 0xAB28, // AB28..AB2E; ETHIOPIC
5647 0xAB2F, // AB2F ; UNKNOWN
5648 0xAB30, // AB30..AB5A; LATIN
5649 0xAB5B, // AB5B ; COMMON
5650 0xAB5C, // AB5C..AB64; LATIN
5651 0xAB65, // AB65 ; GREEK
5652 0xAB66, // AB66..AB6F; UNKNOWN
5653 0xAB70, // AB70..ABBF; CHEROKEE
5654 0xABC0, // ABC0..ABED; MEETEI_MAYEK
5655 0xABEE, // ABEE..ABEF; UNKNOWN
5656 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
5657 0xABFA, // ABFA..ABFF; UNKNOWN
5658 0xAC00, // AC00..D7A3; HANGUL
5659 0xD7A4, // D7A4..D7AF; UNKNOWN
5660 0xD7B0, // D7B0..D7C6; HANGUL
5661 0xD7C7, // D7C7..D7CA; UNKNOWN
5662 0xD7CB, // D7CB..D7FB; HANGUL
5663 0xD7FC, // D7FC..F8FF; UNKNOWN
5664 0xF900, // F900..FA6D; HAN
5665 0xFA6E, // FA6E..FA6F; UNKNOWN
5666 0xFA70, // FA70..FAD9; HAN
5667 0xFADA, // FADA..FAFF; UNKNOWN
5668 0xFB00, // FB00..FB06; LATIN
5669 0xFB07, // FB07..FB12; UNKNOWN
5670 0xFB13, // FB13..FB17; ARMENIAN
5671 0xFB18, // FB18..FB1C; UNKNOWN
5672 0xFB1D, // FB1D..FB36; HEBREW
5673 0xFB37, // FB37 ; UNKNOWN
5674 0xFB38, // FB38..FB3C; HEBREW
5675 0xFB3D, // FB3D ; UNKNOWN
5676 0xFB3E, // FB3E ; HEBREW
5677 0xFB3F, // FB3F ; UNKNOWN
5678 0xFB40, // FB40..FB41; HEBREW
5679 0xFB42, // FB42 ; UNKNOWN
5680 0xFB43, // FB43..FB44; HEBREW
5681 0xFB45, // FB45 ; UNKNOWN
5682 0xFB46, // FB46..FB4F; HEBREW
5683 0xFB50, // FB50..FBC1; ARABIC
5684 0xFBC2, // FBC2..FBD2; UNKNOWN
5685 0xFBD3, // FBD3..FD3D; ARABIC
5686 0xFD3E, // FD3E..FD3F; COMMON
5687 0xFD40, // FD40..FD4F; UNKNOWN
5688 0xFD50, // FD50..FD8F; ARABIC
5689 0xFD90, // FD90..FD91; UNKNOWN
5690 0xFD92, // FD92..FDC7; ARABIC
5691 0xFDC8, // FDC8..FDEF; UNKNOWN
5692 0xFDF0, // FDF0..FDFD; ARABIC
5693 0xFDFE, // FDFE..FDFF; UNKNOWN
5694 0xFE00, // FE00..FE0F; INHERITED
5695 0xFE10, // FE10..FE19; COMMON
5696 0xFE1A, // FE1A..FE1F; UNKNOWN
5697 0xFE20, // FE20..FE2D; INHERITED
5698 0xFE2E, // FE2E..FE2F; CYRILLIC
5699 0xFE30, // FE30..FE52; COMMON
5700 0xFE53, // FE53 ; UNKNOWN
5701 0xFE54, // FE54..FE66; COMMON
5702 0xFE67, // FE67 ; UNKNOWN
5703 0xFE68, // FE68..FE6B; COMMON
5704 0xFE6C, // FE6C..FE6F; UNKNOWN
5705 0xFE70, // FE70..FE74; ARABIC
5706 0xFE75, // FE75 ; UNKNOWN
5707 0xFE76, // FE76..FEFC; ARABIC
5708 0xFEFD, // FEFD..FEFE; UNKNOWN
5709 0xFEFF, // FEFF ; COMMON
5710 0xFF00, // FF00 ; UNKNOWN
5711 0xFF01, // FF01..FF20; COMMON
5712 0xFF21, // FF21..FF3A; LATIN
5713 0xFF3B, // FF3B..FF40; COMMON
5714 0xFF41, // FF41..FF5A; LATIN
5715 0xFF5B, // FF5B..FF65; COMMON
5716 0xFF66, // FF66..FF6F; KATAKANA
5717 0xFF70, // FF70 ; COMMON
5718 0xFF71, // FF71..FF9D; KATAKANA
5719 0xFF9E, // FF9E..FF9F; COMMON
5720 0xFFA0, // FFA0..FFBE; HANGUL
5721 0xFFBF, // FFBF..FFC1; UNKNOWN
5722 0xFFC2, // FFC2..FFC7; HANGUL
5723 0xFFC8, // FFC8..FFC9; UNKNOWN
5724 0xFFCA, // FFCA..FFCF; HANGUL
5725 0xFFD0, // FFD0..FFD1; UNKNOWN
5726 0xFFD2, // FFD2..FFD7; HANGUL
5727 0xFFD8, // FFD8..FFD9; UNKNOWN
5728 0xFFDA, // FFDA..FFDC; HANGUL
5729 0xFFDD, // FFDD..FFDF; UNKNOWN
5730 0xFFE0, // FFE0..FFE6; COMMON
5731 0xFFE7, // FFE7 ; UNKNOWN
5732 0xFFE8, // FFE8..FFEE; COMMON
5733 0xFFEF, // FFEF..FFF8; UNKNOWN
5734 0xFFF9, // FFF9..FFFD; COMMON
5735 0xFFFE, // FFFE..FFFF; UNKNOWN
5736 0x10000, // 10000..1000B; LINEAR_B
5737 0x1000C, // 1000C ; UNKNOWN
5738 0x1000D, // 1000D..10026; LINEAR_B
5739 0x10027, // 10027 ; UNKNOWN
5740 0x10028, // 10028..1003A; LINEAR_B
5741 0x1003B, // 1003B ; UNKNOWN
5742 0x1003C, // 1003C..1003D; LINEAR_B
5743 0x1003E, // 1003E ; UNKNOWN
5744 0x1003F, // 1003F..1004D; LINEAR_B
5745 0x1004E, // 1004E..1004F; UNKNOWN
5746 0x10050, // 10050..1005D; LINEAR_B
5747 0x1005E, // 1005E..1007F; UNKNOWN
5748 0x10080, // 10080..100FA; LINEAR_B
5749 0x100FB, // 100FB..100FF; UNKNOWN
5750 0x10100, // 10100..10102; COMMON
5751 0x10103, // 10103..10106; UNKNOWN
5752 0x10107, // 10107..10133; COMMON
5753 0x10134, // 10134..10136; UNKNOWN
5754 0x10137, // 10137..1013F; COMMON
5755 0x10140, // 10140..1018E; GREEK
5756 0x1018F, // 1018F ; UNKNOWN
5757 0x10190, // 10190..1019B; COMMON
5758 0x1019C, // 1019C..1019F; UNKNOWN
5759 0x101A0, // 101A0 ; GREEK
5760 0x101A1, // 101A1..101CF; UNKNOWN
5761 0x101D0, // 101D0..101FC; COMMON
5762 0x101FD, // 101FD ; INHERITED
5763 0x101FE, // 101FE..1027F; UNKNOWN
5764 0x10280, // 10280..1029C; LYCIAN
5765 0x1029D, // 1029D..1029F; UNKNOWN
5766 0x102A0, // 102A0..102D0; CARIAN
5767 0x102D1, // 102D1..102DF; UNKNOWN
5768 0x102E0, // 102E0 ; INHERITED
5769 0x102E1, // 102E1..102FB; COMMON
5770 0x102FC, // 102FC..102FF; UNKNOWN
5771 0x10300, // 10300..10323; OLD_ITALIC
5772 0x10324, // 10324..1032C; UNKNOWN
5773 0x1032D, // 1032D..1032F; OLD_ITALIC
5774 0x10330, // 10330..1034A; GOTHIC
5775 0x1034B, // 1034B..1034F; UNKNOWN
5776 0x10350, // 10350..1037A; OLD_PERMIC
5777 0x1037B, // 1037B..1037F; UNKNOWN
5778 0x10380, // 10380..1039D; UGARITIC
5779 0x1039E, // 1039E ; UNKNOWN
5780 0x1039F, // 1039F ; UGARITIC
5781 0x103A0, // 103A0..103C3; OLD_PERSIAN
5782 0x103C4, // 103C4..103C7; UNKNOWN
5783 0x103C8, // 103C8..103D5; OLD_PERSIAN
5784 0x103D6, // 103D6..103FF; UNKNOWN
5785 0x10400, // 10400..1044F; DESERET
5786 0x10450, // 10450..1047F; SHAVIAN
5787 0x10480, // 10480..1049D; OSMANYA
5788 0x1049E, // 1049E..1049F; UNKNOWN
5789 0x104A0, // 104A0..104A9; OSMANYA
5790 0x104AA, // 104AA..104AF; UNKNOWN
5791 0x104B0, // 104B0..104D3; OSAGE
5792 0x104D4, // 104D4..104D7; UNKNOWN
5793 0x104D8, // 104D8..104FB; OSAGE
5794 0x104FC, // 104FC..104FF; UNKNOWN
5795 0x10500, // 10500..10527; ELBASAN
5796 0x10528, // 10528..1052F; UNKNOWN
5797 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
5798 0x10564, // 10564..1056E; UNKNOWN
5799 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
5800 0x10570, // 10570..105FF; UNKNOWN
5801 0x10600, // 10600..10736; LINEAR_A
5802 0x10737, // 10737..1073F; UNKNOWN
5803 0x10740, // 10740..10755; LINEAR_A
5804 0x10756, // 10756..1075F; UNKNOWN
5805 0x10760, // 10760..10767; LINEAR_A
5806 0x10768, // 10768..107FF; UNKNOWN
5807 0x10800, // 10800..10805; CYPRIOT
5808 0x10806, // 10806..10807; UNKNOWN
5809 0x10808, // 10808 ; CYPRIOT
5810 0x10809, // 10809 ; UNKNOWN
5811 0x1080A, // 1080A..10835; CYPRIOT
5812 0x10836, // 10836 ; UNKNOWN
5813 0x10837, // 10837..10838; CYPRIOT
5814 0x10839, // 10839..1083B; UNKNOWN
5815 0x1083C, // 1083C ; CYPRIOT
5816 0x1083D, // 1083D..1083E; UNKNOWN
5817 0x1083F, // 1083F ; CYPRIOT
5818 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
5819 0x10856, // 10856 ; UNKNOWN
5820 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
5821 0x10860, // 10860..1087F; PALMYRENE
5822 0x10880, // 10880..1089E; NABATAEAN
5823 0x1089F, // 1089F..108A6; UNKNOWN
5824 0x108A7, // 108A7..108AF; NABATAEAN
5825 0x108B0, // 108B0..108DF; UNKNOWN
5826 0x108E0, // 108E0..108F2; HATRAN
5827 0x108F3, // 108F3 ; UNKNOWN
5828 0x108F4, // 108F4..108F5; HATRAN
5829 0x108F6, // 108F6..108FA; UNKNOWN
5830 0x108FB, // 108FB..108FF; HATRAN
5831 0x10900, // 10900..1091B; PHOENICIAN
5832 0x1091C, // 1091C..1091E; UNKNOWN
5833 0x1091F, // 1091F ; PHOENICIAN
5834 0x10920, // 10920..10939; LYDIAN
5835 0x1093A, // 1093A..1093E; UNKNOWN
5836 0x1093F, // 1093F ; LYDIAN
5837 0x10940, // 10940..1097F; UNKNOWN
5838 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
5839 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
5840 0x109B8, // 109B8..109BB; UNKNOWN
5841 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
5842 0x109D0, // 109D0..109D1; UNKNOWN
5843 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
5844 0x10A00, // 10A00..10A03; KHAROSHTHI
5845 0x10A04, // 10A04 ; UNKNOWN
5846 0x10A05, // 10A05..10A06; KHAROSHTHI
5847 0x10A07, // 10A07..10A0B; UNKNOWN
5848 0x10A0C, // 10A0C..10A13; KHAROSHTHI
5849 0x10A14, // 10A14 ; UNKNOWN
5850 0x10A15, // 10A15..10A17; KHAROSHTHI
5851 0x10A18, // 10A18 ; UNKNOWN
5852 0x10A19, // 10A19..10A35; KHAROSHTHI
5853 0x10A36, // 10A36..10A37; UNKNOWN
5854 0x10A38, // 10A38..10A3A; KHAROSHTHI
5855 0x10A3B, // 10A3B..10A3E; UNKNOWN
5856 0x10A3F, // 10A3F..10A48; KHAROSHTHI
5857 0x10A49, // 10A49..10A4F; UNKNOWN
5858 0x10A50, // 10A50..10A58; KHAROSHTHI
5859 0x10A59, // 10A59..10A5F; UNKNOWN
5860 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
5861 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
5862 0x10AA0, // 10AA0..10ABF; UNKNOWN
5863 0x10AC0, // 10AC0..10AE6; MANICHAEAN
5864 0x10AE7, // 10AE7..10AEA; UNKNOWN
5865 0x10AEB, // 10AEB..10AF6; MANICHAEAN
5866 0x10AF7, // 10AF7..10AFF; UNKNOWN
5867 0x10B00, // 10B00..10B35; AVESTAN
5868 0x10B36, // 10B36..10B38; UNKNOWN
5869 0x10B39, // 10B39..10B3F; AVESTAN
5870 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
5871 0x10B56, // 10B56..10B57; UNKNOWN
5872 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
5873 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
5874 0x10B73, // 10B73..10B77; UNKNOWN
5875 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
5876 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
5877 0x10B92, // 10B92..10B98; UNKNOWN
5878 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
5879 0x10B9D, // 10B9D..10BA8; UNKNOWN
5880 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
5881 0x10BB0, // 10BB0..10BFF; UNKNOWN
5882 0x10C00, // 10C00..10C48; OLD_TURKIC
5883 0x10C49, // 10C49..10C7F; UNKNOWN
5884 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
5885 0x10CB3, // 10CB3..10CBF; UNKNOWN
5886 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
5887 0x10CF3, // 10CF3..10CF9; UNKNOWN
5888 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
5889 0x10D00, // 10D00..10D27; HANIFI ROHINGYA
5890 0x10D28, // 10D28..10D29; UNKNOWN
5891 0x10D30, // 10D30..10D39; HANIFI ROHINGYA
5892 0x10D3A, // 10D3A..10E5F; UNKNOWN
5893 0x10E60, // 10E60..10E7E; ARABIC
5894 0x10E7F, // 10E7F..10EFF; UNKNOWN
5895 0x10F00, // 10F00..10F27; OLD SOGDIAN
5896 0x10F28, // 10F28..10F2F; UNKNOWN
5897 0x10F30, // 10F30..10F59; SOGDIAN
5898 0x10F5A, // 10F5A..10FFF; UNKNOWN
5899 0x11000, // 11000..1104D; BRAHMI
5900 0x1104E, // 1104E..11051; UNKNOWN
5901 0x11052, // 11052..1106F; BRAHMI
5902 0x11070, // 11070..1107E; UNKNOWN
5903 0x1107F, // 1107F ; BRAHMI
5904 0x11080, // 11080..110C1; KAITHI
5905 0x110C2, // 110C2..110CC; UNKNOWN
5906 0x110CD, // 110CD ; KAITHI
5907 0x110CE, // 110CE..110CF; UNKNOWN
5908 0x110D0, // 110D0..110E8; SORA_SOMPENG
5909 0x110E9, // 110E9..110EF; UNKNOWN
5910 0x110F0, // 110F0..110F9; SORA_SOMPENG
5911 0x110FA, // 110FA..110FF; UNKNOWN
5912 0x11100, // 11100..11134; CHAKMA
5913 0x11135, // 11135 ; UNKNOWN
5914 0x11136, // 11136..11146; CHAKMA
5915 0x11147, // 11147..1114F; UNKNOWN
5916 0x11150, // 11150..11176; MAHAJANI
5917 0x11177, // 11177..1117F; UNKNOWN
5918 0x11180, // 11180..111CD; SHARADA
5919 0x111CE, // 111CE..111CF; UNKNOWN
5920 0x111D0, // 111D0..111DF; SHARADA
5921 0x111E0, // 111E0 ; UNKNOWN
5922 0x111E1, // 111E1..111F4; SINHALA
5923 0x111F5, // 111F5..111FF; UNKNOWN
5924 0x11200, // 11200..11211; KHOJKI
5925 0x11212, // 11212 ; UNKNOWN
5926 0x11213, // 11213..1123E; KHOJKI
5927 0x1123F, // 1123F..1127F; UNKNOWN
5928 0x11280, // 11280..11286; MULTANI
5929 0x11287, // 11287 ; UNKNOWN
5930 0x11288, // 11288 ; MULTANI
5931 0x11289, // 11289 ; UNKNOWN
5932 0x1128A, // 1128A..1128D; MULTANI
5933 0x1128E, // 1128E ; UNKNOWN
5934 0x1128F, // 1128F..1129D; MULTANI
5935 0x1129E, // 1129E ; UNKNOWN
5936 0x1129F, // 1129F..112A9; MULTANI
5937 0x112AA, // 112AA..112AF; UNKNOWN
5938 0x112B0, // 112B0..112EA; KHUDAWADI
5939 0x112EB, // 112EB..112EF; UNKNOWN
5940 0x112F0, // 112F0..112F9; KHUDAWADI
5941 0x112FA, // 112FA..112FF; UNKNOWN
5942 0x11300, // 11300..11303; GRANTHA
5943 0x11304, // 11304 ; UNKNOWN
5944 0x11305, // 11305..1130C; GRANTHA
5945 0x1130D, // 1130D..1130E; UNKNOWN
5946 0x1130F, // 1130F..11310; GRANTHA
5947 0x11311, // 11311..11312; UNKNOWN
5948 0x11313, // 11313..11328; GRANTHA
5949 0x11329, // 11329 ; UNKNOWN
5950 0x1132A, // 1132A..11330; GRANTHA
5951 0x11331, // 11331 ; UNKNOWN
5952 0x11332, // 11332..11333; GRANTHA
5953 0x11334, // 11334 ; UNKNOWN
5954 0x11335, // 11335..11339; GRANTHA
5955 0x1133A, // 1133A ; UNKNOWN
5956 0x1133B, // 1133B ; INHERITED
5957 0x1133C, // 1133C..11344; GRANTHA
5958 0x11345, // 11345..11346; UNKNOWN
5959 0x11347, // 11347..11348; GRANTHA
5960 0x11349, // 11349..1134A; UNKNOWN
5961 0x1134B, // 1134B..1134D; GRANTHA
5962 0x1134E, // 1134E..1134F; UNKNOWN
5963 0x11350, // 11350 ; GRANTHA
5964 0x11351, // 11351..11356; UNKNOWN
5965 0x11357, // 11357 ; GRANTHA
5966 0x11358, // 11358..1135C; UNKNOWN
5967 0x1135D, // 1135D..11363; GRANTHA
5968 0x11364, // 11364..11365; UNKNOWN
5969 0x11366, // 11366..1136C; GRANTHA
5970 0x1136D, // 1136D..1136F; UNKNOWN
5971 0x11370, // 11370..11374; GRANTHA
5972 0x11375, // 11375..113FF; UNKNOWN
5973 0x11400, // 11400..11459; NEWA
5974 0x1145A, // 1145A ; UNKNOWN
5975 0x1145B, // 1145B ; NEWA
5976 0x1145C, // 1145C ; UNKNOWN
5977 0x1145D, // 1145D..1145E; NEWA
5978 0x1145F, // 1145F..1147F; UNKNOWN
5979 0x11480, // 11480..114C7; TIRHUTA
5980 0x114C8, // 114C8..114CF; UNKNOWN
5981 0x114D0, // 114D0..114D9; TIRHUTA
5982 0x114DA, // 114DA..1157F; UNKNOWN
5983 0x11580, // 11580..115B5; SIDDHAM
5984 0x115B6, // 115B6..115B7; UNKNOWN
5985 0x115B8, // 115B8..115DD; SIDDHAM
5986 0x115DE, // 115DE..115FF; UNKNOWN
5987 0x11600, // 11600..11644; MODI
5988 0x11645, // 11645..1164F; UNKNOWN
5989 0x11650, // 11650..11659; MODI
5990 0x1165A, // 1165A..1165F; UNKNOWN
5991 0x11660, // 11660..1166C; MONGOLIAN
5992 0X1166D, // 1166D..1167F; UNKNOWN
5993 0x11680, // 11680..116B7; TAKRI
5994 0x116B8, // 116B8..116BF; UNKNOWN
5995 0x116C0, // 116C0..116C9; TAKRI
5996 0x116CA, // 116CA..116FF; UNKNOWN
5997 0x11700, // 11700..1171A; AHOM
5998 0x1171B, // 1171B..1171C; UNKNOWN
5999 0x1171D, // 1171D..1172B; AHOM
6000 0x1172C, // 1172C..1172F; UNKNOWN
6001 0x11730, // 11730..1173F; AHOM
6002 0x11740, // 11740..117FF; UNKNOWN
6003 0x11800, // 11800..1183B; DOGRA
6004 0x1183C, // 1183C..1189F; UNKNOWN
6005 0x118A0, // 118A0..118F2; WARANG_CITI
6006 0x118F3, // 118F3..118FE; UNKNOWN
6007 0x118FF, // 118FF ; WARANG_CITI
6008 0x11900, // 11900..119FF; UNKNOWN
6009 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6010 0X11A48, // 11A48..11A4F; UNKNOWN
6011 0x11A50, // 11A50..11A83; SOYOMBO
6012 0x11A84, // 11A84..11A85; UNKNOWN
6013 0x11A86, // 11A86..11AA2; SOYOMBO
6014 0x11AA3, // 11AA3..11ABF; UNKNOWN
6015 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6016 0x11AF9, // 11AF9..11BFF; UNKNOWN
6017 0x11C00, // 11C00..11C08; BHAIKSUKI
6018 0x11C09, // 11C09 ; UNKNOWN
6019 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6020 0x11C37, // 11C37 ; UNKNOWN
6021 0x11C38, // 11C38..11C45; BHAIKSUKI
6022 0x11C46, // 11C46..11C49; UNKNOWN
6023 0x11C50, // 11C50..11C6C; BHAIKSUKI
6024 0x11C6D, // 11C6D..11C6F; UNKNOWN
6025 0x11C70, // 11C70..11C8F; MARCHEN
6026 0x11C90, // 11C90..11C91; UNKNOWN
6027 0x11C92, // 11C92..11CA7; MARCHEN
6028 0x11CA8, // 11CA8 ; UNKNOWN
6029 0x11CA9, // 11CA9..11CB6; MARCHEN
6030 0x11CB7, // 11CB7..11CFF; UNKNOWN
6031 0x11D00, // 11D00..11D06; MASARAM_GONDI
6032 0x11D07, // 11D07 ; UNKNOWN
6033 0x11D08, // 11D08..11D09; MASARAM_GONDI
6034 0x11D0A, // 11D0A ; UNKNOWN
6035 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6036 0x11D37, // 11D37..11D39; UNKNOWN
6037 0x11D3A, // 11D3A ; MASARAM_GONDI
6038 0x11D3B, // 11D3B ; UNKNOWN
6039 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6040 0x11D3E, // 11D3E ; UNKNOWN
6041 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6042 0x11D48, // 11D48..11D49, UNKNOWN
6043 0x11D50, // 11D50..11D59; MASARAM_GONDI
6044 0x11D5A, // 11D5A..11D5F; UNKNOWN
6045 0x11D60, // 11D60..11D68; GUNJALA GONDI
6046 0x11D69, // ; UNKNOWN
6047 0x11D6A, // 11D6A..11D8E; GUNJALA GONDI
6048 0x11D8F, // ; UNKNOWN
6049 0x11D90, // 11D90..11D91; GUNJALA GONDI
6050 0x11D92, // ; UNKNOWN
6051 0x11D93, // 11D93..11D98; GUNJALA GONDI
6052 0x11D99, // 11D99 ; UNKNOWN
6053 0x11DA0, // 11DA0..11DA9; GUNJALA GONDI
6054 0x11DAA, // 11DAA..11DFF; UNKNOWN
6055 0x11EE0, // 11EE0..11EF8; MAKASAR
6056 0x11EF9, // 11EF9..11FFF; UNKNOWN
6057 0x12000, // 12000..12399; CUNEIFORM
6058 0x1239A, // 1239A..123FF; UNKNOWN
6059 0x12400, // 12400..1246E; CUNEIFORM
6060 0x1246F, // 1246F ; UNKNOWN
6061 0x12470, // 12470..12474; CUNEIFORM
6062 0x12475, // 12475..1247F; UNKNOWN
6063 0x12480, // 12480..12543; CUNEIFORM
6064 0x12544, // 12544..12FFF; UNKNOWN
6065 0x13000, // 13000..1342E; EGYPTIAN_HIEROGLYPHS
6066 0x1342F, // 1342F..143FF; UNKNOWN
6067 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6068 0x14647, // 14647..167FF; UNKNOWN
6069 0x16800, // 16800..16A38; BAMUM
6070 0x16A39, // 16A39..16A3F; UNKNOWN
6071 0x16A40, // 16A40..16A5E; MRO
6072 0x16A5F, // 16A5F ; UNKNOWN
6073 0x16A60, // 16A60..16A69; MRO
6074 0x16A6A, // 16A6A..16A6D; UNKNOWN
6075 0x16A6E, // 16A6E..16A6F; MRO
6076 0x16A70, // 16A70..16ACF; UNKNOWN
6077 0x16AD0, // 16AD0..16AED; BASSA_VAH
6078 0x16AEE, // 16AEE..16AEF; UNKNOWN
6079 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6080 0x16AF6, // 16AF6..16AFF; UNKNOWN
6081 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6082 0x16B46, // 16B46..16B4F; UNKNOWN
6083 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6084 0x16B5A, // 16B5A ; UNKNOWN
6085 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6086 0x16B62, // 16B62 ; UNKNOWN
6087 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6088 0x16B78, // 16B78..16B7C; UNKNOWN
6089 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6090 0x16B90, // 16B90..16E3F; UNKNOWN
6091 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6092 0x16E9B, // 16E9B..16EFF; UNKNOWN
6093 0x16F00, // 16F00..16F44; MIAO
6094 0x16F45, // 16F45..16F4F; UNKNOWN
6095 0x16F50, // 16F50..16F7E; MIAO
6096 0x16F7F, // 16F7F..16F8E; UNKNOWN
6097 0x16F8F, // 16F8F..16F9F; MIAO
6098 0x16FA0, // 16FA0..16FDF; UNKNOWN
6099 0x16FE0, // 16FE0 ; TANGUT
6100 0x16FE1, // 16FE1 ; NUSHU
6101 0x16FE2, // 16FE2..16FFF; UNKNOWN
6102 0x17000, // 17000..187F1; TANGUT
6103 0x187F2, // 187F2..187FF; UNKNOWN
6104 0x18800, // 18800..18AF2; TANGUT
6105 0x18AF3, // 18AF3..1AFFF; UNKNOWN
6106 0x1B000, // 1B000 ; KATAKANA
6107 0x1B001, // 1B001..1B11E; HIRAGANA
6108 0x1B11F, // 1B11F..1B16F; UNKNOWN
6109 0x1B170, // 1B170..1B2FB; NUSHU
6110 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6111 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6112 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6113 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6114 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6115 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6116 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6117 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6118 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6119 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6120 0x1BCA0, // 1BCA0..1BCA3; COMMON
6121 0x1BCA4, // 1BCA4..1CFFF; UNKNOWN
6122 0x1D000, // 1D000..1D0F5; COMMON
6123 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6124 0x1D100, // 1D100..1D126; COMMON
6125 0x1D127, // 1D127..1D128; UNKNOWN
6126 0x1D129, // 1D129..1D166; COMMON
6127 0x1D167, // 1D167..1D169; INHERITED
6128 0x1D16A, // 1D16A..1D17A; COMMON
6129 0x1D17B, // 1D17B..1D182; INHERITED
6130 0x1D183, // 1D183..1D184; COMMON
6131 0x1D185, // 1D185..1D18B; INHERITED
6132 0x1D18C, // 1D18C..1D1A9; COMMON
6133 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6134 0x1D1AE, // 1D1AE..1D1E8; COMMON
6135 0x1D1E9, // 1D1E9..1D1FF; UNKNOWN
6136 0x1D200, // 1D200..1D245; GREEK
6137 0x1D246, // 1D246..1D2DF; UNKNOWN
6138 0x1D2E0, // 1D2E0..1D2F3; COMMON
6139 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6140 0x1D300, // 1D300..1D356; COMMON
6141 0x1D357, // 1D357..1D35F; UNKNOWN
6142 0x1D360, // 1D360..1D378; COMMON
6143 0x1D379, // 1D379..1D3FF; UNKNOWN
6144 0x1D400, // 1D400..1D454; COMMON
6145 0x1D455, // 1D455 ; UNKNOWN
6146 0x1D456, // 1D456..1D49C; COMMON
6147 0x1D49D, // 1D49D ; UNKNOWN
6148 0x1D49E, // 1D49E..1D49F; COMMON
6149 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
6150 0x1D4A2, // 1D4A2 ; COMMON
6151 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
6152 0x1D4A5, // 1D4A5..1D4A6; COMMON
6153 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
6154 0x1D4A9, // 1D4A9..1D4AC; COMMON
6155 0x1D4AD, // 1D4AD ; UNKNOWN
6156 0x1D4AE, // 1D4AE..1D4B9; COMMON
6157 0x1D4BA, // 1D4BA ; UNKNOWN
6158 0x1D4BB, // 1D4BB ; COMMON
6159 0x1D4BC, // 1D4BC ; UNKNOWN
6160 0x1D4BD, // 1D4BD..1D4C3; COMMON
6161 0x1D4C4, // 1D4C4 ; UNKNOWN
6162 0x1D4C5, // 1D4C5..1D505; COMMON
6163 0x1D506, // 1D506 ; UNKNOWN
6164 0x1D507, // 1D507..1D50A; COMMON
6165 0x1D50B, // 1D50B..1D50C; UNKNOWN
6166 0x1D50D, // 1D50D..1D514; COMMON
6167 0x1D515, // 1D515 ; UNKNOWN
6168 0x1D516, // 1D516..1D51C; COMMON
6169 0x1D51D, // 1D51D ; UNKNOWN
6170 0x1D51E, // 1D51E..1D539; COMMON
6171 0x1D53A, // 1D53A ; UNKNOWN
6172 0x1D53B, // 1D53B..1D53E; COMMON
6173 0x1D53F, // 1D53F ; UNKNOWN
6174 0x1D540, // 1D540..1D544; COMMON
6175 0x1D545, // 1D545 ; UNKNOWN
6176 0x1D546, // 1D546 ; COMMON
6177 0x1D547, // 1D547..1D549; UNKNOWN
6178 0x1D54A, // 1D54A..1D550; COMMON
6179 0x1D551, // 1D551 ; UNKNOWN
6180 0x1D552, // 1D552..1D6A5; COMMON
6181 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
6182 0x1D6A8, // 1D6A8..1D7CB; COMMON
6183 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
6184 0x1D7CE, // 1D7CE..1D7FF; COMMON
6185 0x1D800, // 1D800..1DA8B; SIGNWRITING
6186 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
6187 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
6188 0x1DAA0, // 1DAA0 ; UNKNOWN
6189 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
6190 0x1DAB0, // 1DAB0..1DFFF; UNKNOWN
6191 0x1E000, // 1E000..1E006; GLAGOLITIC
6192 0x1E007, // 1E007 ; UNKNOWN
6193 0x1E008, // 1E008..1E018; GLAGOLITIC
6194 0x1E019, // 1E019..1E01A; UNKNOWN
6195 0x1E01B, // 1E01B..1E021; GLAGOLITIC
6196 0x1E022, // 1E022 ; UNKNOWN
6197 0x1E023, // 1E023..1E024; GLAGOLITIC
6198 0x1E025, // 1E025 ; UNKNOWN
6199 0x1E026, // 1E026..1E02A; GLAGOLITIC
6200 0x1E02B, // 1E02B..1E7FF; UNKNOWN
6201 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
6202 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
6203 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
6204 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
6205 0x1E900, // 1E900..1E94A; ADLAM
6206 0x1E94B, // 1E94B..1E94F; UNKNOWN
6207 0x1E950, // 1E950..1E959; ADLAM
6208 0x1E95A, // 1E95A..1E95D; UNKNOWN
6209 0x1E95E, // 1E95E..1E95F; ADLAM
6210 0x1E960, // 1E960..1EC70; UNKNOWN
6211 0x1EC71, // 1EC71..1ECB4; COMMON
6212 0x1ECB5, // 1ECB5..1EDFF; UNKNOWN
6213 0x1EE00, // 1EE00..1EE03; ARABIC
6214 0x1EE04, // 1EE04 ; UNKNOWN
6215 0x1EE05, // 1EE05..1EE1F; ARABIC
6216 0x1EE20, // 1EE20 ; UNKNOWN
6217 0x1EE21, // 1EE21..1EE22; ARABIC
6218 0x1EE23, // 1EE23 ; UNKNOWN
6219 0x1EE24, // 1EE24 ; ARABIC
6220 0x1EE25, // 1EE25..1EE26; UNKNOWN
6221 0x1EE27, // 1EE27 ; ARABIC
6222 0x1EE28, // 1EE28 ; UNKNOWN
6223 0x1EE29, // 1EE29..1EE32; ARABIC
6224 0x1EE33, // 1EE33 ; UNKNOWN
6225 0x1EE34, // 1EE34..1EE37; ARABIC
6226 0x1EE38, // 1EE38 ; UNKNOWN
6227 0x1EE39, // 1EE39 ; ARABIC
6228 0x1EE3A, // 1EE3A ; UNKNOWN
6229 0x1EE3B, // 1EE3B ; ARABIC
6230 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
6231 0x1EE42, // 1EE42 ; ARABIC
6232 0x1EE43, // 1EE43..1EE46; UNKNOWN
6233 0x1EE47, // 1EE47 ; ARABIC
6234 0x1EE48, // 1EE48 ; UNKNOWN
6235 0x1EE49, // 1EE49 ; ARABIC
6236 0x1EE4A, // 1EE4A ; UNKNOWN
6237 0x1EE4B, // 1EE4B ; ARABIC
6238 0x1EE4C, // 1EE4C ; UNKNOWN
6239 0x1EE4D, // 1EE4D..1EE4F; ARABIC
6240 0x1EE50, // 1EE50 ; UNKNOWN
6241 0x1EE51, // 1EE51..1EE52; ARABIC
6242 0x1EE53, // 1EE53 ; UNKNOWN
6243 0x1EE54, // 1EE54 ; ARABIC
6244 0x1EE55, // 1EE55..1EE56; UNKNOWN
6245 0x1EE57, // 1EE57 ; ARABIC
6246 0x1EE58, // 1EE58 ; UNKNOWN
6247 0x1EE59, // 1EE59 ; ARABIC
6248 0x1EE5A, // 1EE5A ; UNKNOWN
6249 0x1EE5B, // 1EE5B ; ARABIC
6250 0x1EE5C, // 1EE5C ; UNKNOWN
6251 0x1EE5D, // 1EE5D ; ARABIC
6252 0x1EE5E, // 1EE5E ; UNKNOWN
6253 0x1EE5F, // 1EE5F ; ARABIC
6254 0x1EE60, // 1EE60 ; UNKNOWN
6255 0x1EE61, // 1EE61..1EE62; ARABIC
6256 0x1EE63, // 1EE63 ; UNKNOWN
6257 0x1EE64, // 1EE64 ; ARABIC
6258 0x1EE65, // 1EE65..1EE66; UNKNOWN
6259 0x1EE67, // 1EE67..1EE6A; ARABIC
6260 0x1EE6B, // 1EE6B ; UNKNOWN
6261 0x1EE6C, // 1EE6C..1EE72; ARABIC
6262 0x1EE73, // 1EE73 ; UNKNOWN
6263 0x1EE74, // 1EE74..1EE77; ARABIC
6264 0x1EE78, // 1EE78 ; UNKNOWN
6265 0x1EE79, // 1EE79..1EE7C; ARABIC
6266 0x1EE7D, // 1EE7D ; UNKNOWN
6267 0x1EE7E, // 1EE7E ; ARABIC
6268 0x1EE7F, // 1EE7F ; UNKNOWN
6269 0x1EE80, // 1EE80..1EE89; ARABIC
6270 0x1EE8A, // 1EE8A ; UNKNOWN
6271 0x1EE8B, // 1EE8B..1EE9B; ARABIC
6272 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
6273 0x1EEA1, // 1EEA1..1EEA3; ARABIC
6274 0x1EEA4, // 1EEA4 ; UNKNOWN
6275 0x1EEA5, // 1EEA5..1EEA9; ARABIC
6276 0x1EEAA, // 1EEAA ; UNKNOWN
6277 0x1EEAB, // 1EEAB..1EEBB; ARABIC
6278 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
6279 0x1EEF0, // 1EEF0..1EEF1; ARABIC
6280 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
6281 0x1F000, // 1F000..1F02B; COMMON
6282 0x1F02C, // 1F02C..1F02F; UNKNOWN
6283 0x1F030, // 1F030..1F093; COMMON
6284 0x1F094, // 1F094..1F09F; UNKNOWN
6285 0x1F0A0, // 1F0A0..1F0AE; COMMON
6286 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
6287 0x1F0B1, // 1F0B1..1F0BF; COMMON
6288 0x1F0C0, // 1F0C0 ; UNKNOWN
6289 0x1F0C1, // 1F0C1..1F0CF; COMMON
6290 0x1F0D0, // 1F0D0 ; UNKNOWN
6291 0x1F0D1, // 1F0D1..1F0F5; COMMON
6292 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
6293 0x1F100, // 1F100..1F10C; COMMON
6294 0x1F10D, // 1F10D..1F10F; UNKNOWN
6295 0x1F110, // 1F110..1F16B; COMMON
6296 0x1F16C, // 1F16C..1F16F; UNKNOWN
6297 0x1F170, // 1F170..1F1AC; COMMON
6298 0x1F1AD, // 1F1AD..1F1E5; UNKNOWN
6299 0x1F1E6, // 1F1E6..1F1FF; COMMON
6300 0x1F200, // 1F200 ; HIRAGANA
6301 0x1F201, // 1F201..1F202; COMMON
6302 0x1F203, // 1F203..1F20F; UNKNOWN
6303 0x1F210, // 1F210..1F23B; COMMON
6304 0x1F23C, // 1F23C..1F23F; UNKNOWN
6305 0x1F240, // 1F240..1F248; COMMON
6306 0x1F249, // 1F249..1F24F; UNKNOWN
6307 0x1F250, // 1F250..1F251; COMMON
6308 0x1F252, // 1F252..1F25F; UNKNOWN
6309 0x1F260, // 1F260..1F265; COMMON
6310 0x1F266, // 1F266..1F2FF; UNKNOWN
6311 0x1F300, // 1F300..1F6D4; COMMON
6312 0x1F6D5, // 1F6D5..1F6DF; UNKNOWN
6313 0x1F6E0, // 1F6E0..1F6EC; COMMON
6314 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
6315 0x1F6F0, // 1F6F0..1F6F9; COMMON
6316 0x1F6FA, // 1F6FA..1F6FF; UNKNOWN
6317 0x1F700, // 1F700..1F773; COMMON
6318 0x1F774, // 1F774..1F77F; UNKNOWN
6319 0x1F780, // 1F780..1F7D8; COMMON
6320 0x1F7D9, // 1F7D9..1F7FF; UNKNOWN
6321 0x1F800, // 1F800..1F80B; COMMON
6322 0x1F80C, // 1F80C..1F80F; UNKNOWN
6323 0x1F810, // 1F810..1F847; COMMON
6324 0x1F848, // 1F848..1F84F; UNKNOWN
6325 0x1F850, // 1F850..1F859; COMMON
6326 0x1F85A, // 1F85A..1F85F; UNKNOWN
6327 0x1F860, // 1F860..1F887; COMMON
6328 0x1F888, // 1F888..1F88F; UNKNOWN
6329 0x1F890, // 1F890..1F8AD; COMMON
6330 0x1F8AE, // 1F8AE..1F8FF; UNKNOWN
6331 0x1F900, // 1F900..1F90B; COMMON
6332 0x1F90C, // 1F90C..1F90F; UNKNOWN
6333 0x1F910, // 1F910..1F93E; COMMON
6334 0x1F93F, // 1F93F ; UNKNOWN
6335 0x1F940, // 1F940..1F970; COMMON
6336 0x1F971, // 1F971..1F972; UNKNOWN
6337 0x1F973, // 1F973..1F976; COMMON
6338 0x1F977, // 1F977..1F979; UNKNOWN
6339 0x1F97A, // 1F97A ; COMMON
6340 0x1F97B, // 1F97B ; UNKNOWN
6341 0x1F97C, // 1F97C..1F9A2; COMMON
6342 0x1F9A3, // 1F9A3..1F9AF; UNKNOWN
6343 0x1F9B0, // 1F9B0..1F9B9; COMMON
6344 0x1F9BA, // 1F9BA..1F9BF; UNKNOWN
6345 0x1F9C0, // 1F9C0..1F9C2; COMMON
6346 0x1F9C3, // 1F9C3..1F9CF; UNKNOWN
6347 0x1F9D0, // 1F9D0..1F9FF; COMMON
6348 0x1FA00, // 1FA00..1FA5F; UNKNOWN
6349 0x1FA60, // 1FA60..1FA6D; COMMON
6350 0x1FA6E, // 1FA6E..1FFFF; UNKNOWN
6351 0x20000, // 20000..2A6D6; HAN
6352 0x2A6D7, // 2A6D7..2A6FF; UNKNOWN
6353 0x2A700, // 2A700..2B734; HAN
6354 0x2B735, // 2B735..2B73F; UNKNOWN
6355 0x2B740, // 2B740..2B81D; HAN
6356 0x2B81E, // 2B81E..2B81F; UNKNOWN
6357 0x2B820, // 2B820..2CEA1; HAN
6358 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
6359 0x2CEB0, // 2CEB0..2EBE0; HAN
6360 0x2EBE1, // 2EBE1..2F7FF; UNKNOWN
6361 0x2F800, // 2F800..2FA1D; HAN
6362 0x2FA1E, // 2FA1E..E0000; UNKNOWN
6363 0xE0001, // E0001 ; COMMON
6364 0xE0002, // E0002..E001F; UNKNOWN
6365 0xE0020, // E0020..E007F; COMMON
6366 0xE0080, // E0080..E00FF; UNKNOWN
6367 0xE0100, // E0100..E01EF; INHERITED
6368 0xE01F0 // E01F0..10FFFF; UNKNOWN
6369 };
6370
6371 private static final UnicodeScript[] scripts = {
6372 COMMON, // 0000..0040
6373 LATIN, // 0041..005A
6374 COMMON, // 005B..0060
6375 LATIN, // 0061..007A
6376 COMMON, // 007B..00A9
6377 LATIN, // 00AA
6378 COMMON, // 00AB..00B9
6379 LATIN, // 00BA
6380 COMMON, // 00BB..00BF
6381 LATIN, // 00C0..00D6
6382 COMMON, // 00D7
6383 LATIN, // 00D8..00F6
6384 COMMON, // 00F7
6385 LATIN, // 00F8..02B8
6386 COMMON, // 02B9..02DF
6387 LATIN, // 02E0..02E4
6388 COMMON, // 02E5..02E9
6389 BOPOMOFO, // 02EA..02EB
6390 COMMON, // 02EC..02FF
6391 INHERITED, // 0300..036F
6392 GREEK, // 0370..0373
6393 COMMON, // 0374
6394 GREEK, // 0375..0377
6395 UNKNOWN, // 0378..0379
6396 GREEK, // 037A..037D
6397 COMMON, // 037E
6398 GREEK, // 037F
6399 UNKNOWN, // 0380..0383
6400 GREEK, // 0384
6401 COMMON, // 0385
6402 GREEK, // 0386
6403 COMMON, // 0387
6404 GREEK, // 0388..038A
6405 UNKNOWN, // 038B
6406 GREEK, // 038C
6407 UNKNOWN, // 038D
6408 GREEK, // 038E..03A1
6409 UNKNOWN, // 03A2
6410 GREEK, // 03A3..03E1
6411 COPTIC, // 03E2..03EF
6412 GREEK, // 03F0..03FF
6413 CYRILLIC, // 0400..0484
6414 INHERITED, // 0485..0486
6415 CYRILLIC, // 0487..052F
6416 UNKNOWN, // 0530
6417 ARMENIAN, // 0531..0556
6418 UNKNOWN, // 0557..0558
6419 ARMENIAN, // 0559..0588
6420 COMMON, // 0589
6421 ARMENIAN, // 058A
6422 UNKNOWN, // 058B..058C
6423 ARMENIAN, // 058D..058F
6424 UNKNOWN, // 0590
6425 HEBREW, // 0591..05C7
6426 UNKNOWN, // 05C8..05CF
6427 HEBREW, // 05D0..05EA
6428 UNKNOWN, // 05EB..05EE
6429 HEBREW, // 05EF..05F4
6430 UNKNOWN, // 05F5..05FF
6431 ARABIC, // 0600..0604
6432 COMMON, // 0605
6433 ARABIC, // 0606..060B
6434 COMMON, // 060C
6435 ARABIC, // 060D..061A
6436 COMMON, // 061B
6437 ARABIC, // 061C
6438 UNKNOWN, // 061D
6439 ARABIC, // 061E
6440 COMMON, // 061F
6441 ARABIC, // 0620..063F
6442 COMMON, // 0640
6443 ARABIC, // 0641..064A
6444 INHERITED, // 064B..0655
6445 ARABIC, // 0656..066F
6446 INHERITED, // 0670
6447 ARABIC, // 0671..06DC
6448 COMMON, // 06DD
6449 ARABIC, // 06DE..06FF
6450 SYRIAC, // 0700..070D
6451 UNKNOWN, // 070E
6452 SYRIAC, // 070F..074A
6453 UNKNOWN, // 074B..074C
6454 SYRIAC, // 074D..074F
6455 ARABIC, // 0750..077F
6456 THAANA, // 0780..07B1
6457 UNKNOWN, // 07B2..07BF
6458 NKO, // 07C0..07FA
6459 UNKNOWN, // 07FB..07FC
6460 NKO, // 07FD..07FF
6461 SAMARITAN, // 0800..082D
6462 UNKNOWN, // 082E..082F
6463 SAMARITAN, // 0830..083E
6464 UNKNOWN, // 083F
6465 MANDAIC, // 0840..085B
6466 UNKNOWN, // 085C..085D
6467 MANDAIC, // 085E
6468 UNKNOWN, // 085F
6469 SYRIAC, // 0860..086A
6470 UNKNOWN, // 086B..089F
6471 ARABIC, // 08A0..08B4
6472 UNKNOWN, // 08B5
6473 ARABIC, // 08B6..08BD
6474 UNKNOWN, // 08BE..08D2
6475 ARABIC, // 08D3..08E1
6476 COMMON, // 08E2
6477 ARABIC, // 08E3..08FF
6478 DEVANAGARI, // 0900..0950
6479 INHERITED, // 0951..0952
6480 DEVANAGARI, // 0953..0963
6481 COMMON, // 0964..0965
6482 DEVANAGARI, // 0966..097F
6483 BENGALI, // 0980..0983
6484 UNKNOWN, // 0984
6485 BENGALI, // 0985..098C
6486 UNKNOWN, // 098D..098E
6487 BENGALI, // 098F..0990
6488 UNKNOWN, // 0991..0992
6489 BENGALI, // 0993..09A8
6490 UNKNOWN, // 09A9
6491 BENGALI, // 09AA..09B0
6492 UNKNOWN, // 09B1
6493 BENGALI, // 09B2
6494 UNKNOWN, // 09B3..09B5
6495 BENGALI, // 09B6..09B9
6496 UNKNOWN, // 09BA..09BB
6497 BENGALI, // 09BC..09C4
6498 UNKNOWN, // 09C5..09C6
6499 BENGALI, // 09C7..09C8
6500 UNKNOWN, // 09C9..09CA
6501 BENGALI, // 09CB..09CE
6502 UNKNOWN, // 09CF..09D6
6503 BENGALI, // 09D7
6504 UNKNOWN, // 09D8..09DB
6505 BENGALI, // 09DC..09DD
6506 UNKNOWN, // 09DE
6507 BENGALI, // 09DF..09E3
6508 UNKNOWN, // 09E4..09E5
6509 BENGALI, // 09E6..09FE
6510 UNKNOWN, // 09FF..0A00
6511 GURMUKHI, // 0A01..0A03
6512 UNKNOWN, // 0A04
6513 GURMUKHI, // 0A05..0A0A
6514 UNKNOWN, // 0A0B..0A0E
6515 GURMUKHI, // 0A0F..0A10
6516 UNKNOWN, // 0A11..0A12
6517 GURMUKHI, // 0A13..0A28
6518 UNKNOWN, // 0A29
6519 GURMUKHI, // 0A2A..0A30
6520 UNKNOWN, // 0A31
6521 GURMUKHI, // 0A32..0A33
6522 UNKNOWN, // 0A34
6523 GURMUKHI, // 0A35..0A36
6524 UNKNOWN, // 0A37
6525 GURMUKHI, // 0A38..0A39
6526 UNKNOWN, // 0A3A..0A3B
6527 GURMUKHI, // 0A3C
6528 UNKNOWN, // 0A3D
6529 GURMUKHI, // 0A3E..0A42
6530 UNKNOWN, // 0A43..0A46
6531 GURMUKHI, // 0A47..0A48
6532 UNKNOWN, // 0A49..0A4A
6533 GURMUKHI, // 0A4B..0A4D
6534 UNKNOWN, // 0A4E..0A50
6535 GURMUKHI, // 0A51
6536 UNKNOWN, // 0A52..0A58
6537 GURMUKHI, // 0A59..0A5C
6538 UNKNOWN, // 0A5D
6539 GURMUKHI, // 0A5E
6540 UNKNOWN, // 0A5F..0A65
6541 GURMUKHI, // 0A66..0A76
6542 UNKNOWN, // 0A77..0A80
6543 GUJARATI, // 0A81..0A83
6544 UNKNOWN, // 0A84
6545 GUJARATI, // 0A85..0A8D
6546 UNKNOWN, // 0A8E
6547 GUJARATI, // 0A8F..0A91
6548 UNKNOWN, // 0A92
6549 GUJARATI, // 0A93..0AA8
6550 UNKNOWN, // 0AA9
6551 GUJARATI, // 0AAA..0AB0
6552 UNKNOWN, // 0AB1
6553 GUJARATI, // 0AB2..0AB3
6554 UNKNOWN, // 0AB4
6555 GUJARATI, // 0AB5..0AB9
6556 UNKNOWN, // 0ABA..0ABB
6557 GUJARATI, // 0ABC..0AC5
6558 UNKNOWN, // 0AC6
6559 GUJARATI, // 0AC7..0AC9
6560 UNKNOWN, // 0ACA
6561 GUJARATI, // 0ACB..0ACD
6562 UNKNOWN, // 0ACE..0ACF
6563 GUJARATI, // 0AD0
6564 UNKNOWN, // 0AD1..0ADF
6565 GUJARATI, // 0AE0..0AE3
6566 UNKNOWN, // 0AE4..0AE5
6567 GUJARATI, // 0AE6..0AF1
6568 UNKNOWN, // 0AF2..0AF8
6569 GUJARATI, // 0AF9..0AFF
6570 UNKNOWN, // 0B00
6571 ORIYA, // 0B01..0B03
6572 UNKNOWN, // 0B04
6573 ORIYA, // 0B05..0B0C
6574 UNKNOWN, // 0B0D..0B0E
6575 ORIYA, // 0B0F..0B10
6576 UNKNOWN, // 0B11..0B12
6577 ORIYA, // 0B13..0B28
6578 UNKNOWN, // 0B29
6579 ORIYA, // 0B2A..0B30
6580 UNKNOWN, // 0B31
6581 ORIYA, // 0B32..0B33
6582 UNKNOWN, // 0B34
6583 ORIYA, // 0B35..0B39
6584 UNKNOWN, // 0B3A..0B3B
6585 ORIYA, // 0B3C..0B44
6586 UNKNOWN, // 0B45..0B46
6587 ORIYA, // 0B47..0B48
6588 UNKNOWN, // 0B49..0B4A
6589 ORIYA, // 0B4B..0B4D
6590 UNKNOWN, // 0B4E..0B55
6591 ORIYA, // 0B56..0B57
6592 UNKNOWN, // 0B58..0B5B
6593 ORIYA, // 0B5C..0B5D
6594 UNKNOWN, // 0B5E
6595 ORIYA, // 0B5F..0B63
6596 UNKNOWN, // 0B64..0B65
6597 ORIYA, // 0B66..0B77
6598 UNKNOWN, // 0B78..0B81
6599 TAMIL, // 0B82..0B83
6600 UNKNOWN, // 0B84
6601 TAMIL, // 0B85..0B8A
6602 UNKNOWN, // 0B8B..0B8D
6603 TAMIL, // 0B8E..0B90
6604 UNKNOWN, // 0B91
6605 TAMIL, // 0B92..0B95
6606 UNKNOWN, // 0B96..0B98
6607 TAMIL, // 0B99..0B9A
6608 UNKNOWN, // 0B9B
6609 TAMIL, // 0B9C
6610 UNKNOWN, // 0B9D
6611 TAMIL, // 0B9E..0B9F
6612 UNKNOWN, // 0BA0..0BA2
6613 TAMIL, // 0BA3..0BA4
6614 UNKNOWN, // 0BA5..0BA7
6615 TAMIL, // 0BA8..0BAA
6616 UNKNOWN, // 0BAB..0BAD
6617 TAMIL, // 0BAE..0BB9
6618 UNKNOWN, // 0BBA..0BBD
6619 TAMIL, // 0BBE..0BC2
6620 UNKNOWN, // 0BC3..0BC5
6621 TAMIL, // 0BC6..0BC8
6622 UNKNOWN, // 0BC9
6623 TAMIL, // 0BCA..0BCD
6624 UNKNOWN, // 0BCE..0BCF
6625 TAMIL, // 0BD0
6626 UNKNOWN, // 0BD1..0BD6
6627 TAMIL, // 0BD7
6628 UNKNOWN, // 0BD8..0BE5
6629 TAMIL, // 0BE6..0BFA
6630 UNKNOWN, // 0BFB..0BFF
6631 TELUGU, // 0C00..0C0C
6632 UNKNOWN, // 0C0D
6633 TELUGU, // 0C0E..0C10
6634 UNKNOWN, // 0C11
6635 TELUGU, // 0C12..0C28
6636 UNKNOWN, // 0C29
6637 TELUGU, // 0C2A..0C39
6638 UNKNOWN, // 0C3A..0C3C
6639 TELUGU, // 0C3D..0C44
6640 UNKNOWN, // 0C45
6641 TELUGU, // 0C46..0C48
6642 UNKNOWN, // 0C49
6643 TELUGU, // 0C4A..0C4D
6644 UNKNOWN, // 0C4E..0C54
6645 TELUGU, // 0C55..0C56
6646 UNKNOWN, // 0C57
6647 TELUGU, // 0C58..0C5A
6648 UNKNOWN, // 0C5B..0C5F
6649 TELUGU, // 0C60..0C63
6650 UNKNOWN, // 0C64..0C65
6651 TELUGU, // 0C66..0C6F
6652 UNKNOWN, // 0C70..0C77
6653 TELUGU, // 0C78..0C7F
6654 KANNADA, // 0C80..0C8C
6655 UNKNOWN, // 0C8D
6656 KANNADA, // 0C8E..0C90
6657 UNKNOWN, // 0C91
6658 KANNADA, // 0C92..0CA8
6659 UNKNOWN, // 0CA9
6660 KANNADA, // 0CAA..0CB3
6661 UNKNOWN, // 0CB4
6662 KANNADA, // 0CB5..0CB9
6663 UNKNOWN, // 0CBA..0CBB
6664 KANNADA, // 0CBC..0CC4
6665 UNKNOWN, // 0CC5
6666 KANNADA, // 0CC6..0CC8
6667 UNKNOWN, // 0CC9
6668 KANNADA, // 0CCA..0CCD
6669 UNKNOWN, // 0CCE..0CD4
6670 KANNADA, // 0CD5..0CD6
6671 UNKNOWN, // 0CD7..0CDD
6672 KANNADA, // 0CDE
6673 UNKNOWN, // 0CDF
6674 KANNADA, // 0CE0..0CE3
6675 UNKNOWN, // 0CE4..0CE5
6676 KANNADA, // 0CE6..0CEF
6677 UNKNOWN, // 0CF0
6678 KANNADA, // 0CF1..0CF2
6679 UNKNOWN, // 0CF3..0CFF
6680 MALAYALAM, // 0D00..0D03
6681 UNKNOWN, // 0D04
6682 MALAYALAM, // 0D05..0D0C
6683 UNKNOWN, // 0D0D
6684 MALAYALAM, // 0D0E..0D10
6685 UNKNOWN, // 0D11
6686 MALAYALAM, // 0D12..0D44
6687 UNKNOWN, // 0D45
6688 MALAYALAM, // 0D46..0D48
6689 UNKNOWN, // 0D49
6690 MALAYALAM, // 0D4A..0D4F
6691 UNKNOWN, // 0D50..0D53
6692 MALAYALAM, // 0D54..0D63
6693 UNKNOWN, // 0D64..0D65
6694 MALAYALAM, // 0D66..0D7F
6695 UNKNOWN, // 0D80..0D81
6696 SINHALA, // 0D82..0D83
6697 UNKNOWN, // 0D84
6698 SINHALA, // 0D85..0D96
6699 UNKNOWN, // 0D97..0D99
6700 SINHALA, // 0D9A..0DB1
6701 UNKNOWN, // 0DB2
6702 SINHALA, // 0DB3..0DBB
6703 UNKNOWN, // 0DBC
6704 SINHALA, // 0DBD
6705 UNKNOWN, // 0DBE..0DBF
6706 SINHALA, // 0DC0..0DC6
6707 UNKNOWN, // 0DC7..0DC9
6708 SINHALA, // 0DCA
6709 UNKNOWN, // 0DCB..0DCE
6710 SINHALA, // 0DCF..0DD4
6711 UNKNOWN, // 0DD5
6712 SINHALA, // 0DD6
6713 UNKNOWN, // 0DD7
6714 SINHALA, // 0DD8..0DDF
6715 UNKNOWN, // 0DE0..0DE5
6716 SINHALA, // 0DE6..0DEF
6717 UNKNOWN, // 0DF0..0DF1
6718 SINHALA, // 0DF2..0DF4
6719 UNKNOWN, // 0DF5..0E00
6720 THAI, // 0E01..0E3A
6721 UNKNOWN, // 0E3B..0E3E
6722 COMMON, // 0E3F
6723 THAI, // 0E40..0E5B
6724 UNKNOWN, // 0E5C..0E80
6725 LAO, // 0E81..0E82
6726 UNKNOWN, // 0E83
6727 LAO, // 0E84
6728 UNKNOWN, // 0E85..0E86
6729 LAO, // 0E87..0E88
6730 UNKNOWN, // 0E89
6731 LAO, // 0E8A
6732 UNKNOWN, // 0E8B..0E8C
6733 LAO, // 0E8D
6734 UNKNOWN, // 0E8E..0E93
6735 LAO, // 0E94..0E97
6736 UNKNOWN, // 0E98
6737 LAO, // 0E99..0E9F
6738 UNKNOWN, // 0EA0
6739 LAO, // 0EA1..0EA3
6740 UNKNOWN, // 0EA4
6741 LAO, // 0EA5
6742 UNKNOWN, // 0EA6
6743 LAO, // 0EA7
6744 UNKNOWN, // 0EA8..0EA9
6745 LAO, // 0EAA..0EAB
6746 UNKNOWN, // 0EAC
6747 LAO, // 0EAD..0EB9
6748 UNKNOWN, // 0EBA
6749 LAO, // 0EBB..0EBD
6750 UNKNOWN, // 0EBE..0EBF
6751 LAO, // 0EC0..0EC4
6752 UNKNOWN, // 0EC5
6753 LAO, // 0EC6
6754 UNKNOWN, // 0EC7
6755 LAO, // 0EC8..0ECD
6756 UNKNOWN, // 0ECE..0ECF
6757 LAO, // 0ED0..0ED9
6758 UNKNOWN, // 0EDA..0EDB
6759 LAO, // 0EDC..0EDF
6760 UNKNOWN, // 0EE0..0EFF
6761 TIBETAN, // 0F00..0F47
6762 UNKNOWN, // 0F48
6763 TIBETAN, // 0F49..0F6C
6764 UNKNOWN, // 0F6D..0F70
6765 TIBETAN, // 0F71..0F97
6766 UNKNOWN, // 0F98
6767 TIBETAN, // 0F99..0FBC
6768 UNKNOWN, // 0FBD
6769 TIBETAN, // 0FBE..0FCC
6770 UNKNOWN, // 0FCD
6771 TIBETAN, // 0FCE..0FD4
6772 COMMON, // 0FD5..0FD8
6773 TIBETAN, // 0FD9..0FDA
6774 UNKNOWN, // 0FDB..FFF
6775 MYANMAR, // 1000..109F
6776 GEORGIAN, // 10A0..10C5
6777 UNKNOWN, // 10C6
6778 GEORGIAN, // 10C7
6779 UNKNOWN, // 10C8..10CC
6780 GEORGIAN, // 10CD
6781 UNKNOWN, // 10CE..10CF
6782 GEORGIAN, // 10D0..10FA
6783 COMMON, // 10FB
6784 GEORGIAN, // 10FC..10FF
6785 HANGUL, // 1100..11FF
6786 ETHIOPIC, // 1200..1248
6787 UNKNOWN, // 1249
6788 ETHIOPIC, // 124A..124D
6789 UNKNOWN, // 124E..124F
6790 ETHIOPIC, // 1250..1256
6791 UNKNOWN, // 1257
6792 ETHIOPIC, // 1258
6793 UNKNOWN, // 1259
6794 ETHIOPIC, // 125A..125D
6795 UNKNOWN, // 125E..125F
6796 ETHIOPIC, // 1260..1288
6797 UNKNOWN, // 1289
6798 ETHIOPIC, // 128A..128D
6799 UNKNOWN, // 128E..128F
6800 ETHIOPIC, // 1290..12B0
6801 UNKNOWN, // 12B1
6802 ETHIOPIC, // 12B2..12B5
6803 UNKNOWN, // 12B6..12B7
6804 ETHIOPIC, // 12B8..12BE
6805 UNKNOWN, // 12BF
6806 ETHIOPIC, // 12C0
6807 UNKNOWN, // 12C1
6808 ETHIOPIC, // 12C2..12C5
6809 UNKNOWN, // 12C6..12C7
6810 ETHIOPIC, // 12C8..12D6
6811 UNKNOWN, // 12D7
6812 ETHIOPIC, // 12D8..1310
6813 UNKNOWN, // 1311
6814 ETHIOPIC, // 1312..1315
6815 UNKNOWN, // 1316..1317
6816 ETHIOPIC, // 1318..135A
6817 UNKNOWN, // 135B..135C
6818 ETHIOPIC, // 135D..137C
6819 UNKNOWN, // 137D..137F
6820 ETHIOPIC, // 1380..1399
6821 UNKNOWN, // 139A..139F
6822 CHEROKEE, // 13A0..13F5
6823 UNKNOWN, // 13F6..13F7
6824 CHEROKEE, // 13F8..13FD
6825 UNKNOWN, // 13FE..13FF
6826 CANADIAN_ABORIGINAL, // 1400..167F
6827 OGHAM, // 1680..169C
6828 UNKNOWN, // 169D..169F
6829 RUNIC, // 16A0..16EA
6830 COMMON, // 16EB..16ED
6831 RUNIC, // 16EE..16F8
6832 UNKNOWN, // 16F9..16FF
6833 TAGALOG, // 1700..170C
6834 UNKNOWN, // 170D
6835 TAGALOG, // 170E..1714
6836 UNKNOWN, // 1715..171F
6837 HANUNOO, // 1720..1734
6838 COMMON, // 1735..1736
6839 UNKNOWN, // 1737..173F
6840 BUHID, // 1740..1753
6841 UNKNOWN, // 1754..175F
6842 TAGBANWA, // 1760..176C
6843 UNKNOWN, // 176D
6844 TAGBANWA, // 176E..1770
6845 UNKNOWN, // 1771
6846 TAGBANWA, // 1772..1773
6847 UNKNOWN, // 1774..177F
6848 KHMER, // 1780..17DD
6849 UNKNOWN, // 17DE..17DF
6850 KHMER, // 17E0..17E9
6851 UNKNOWN, // 17EA..17EF
6852 KHMER, // 17F0..17F9
6853 UNKNOWN, // 17FA..17FF
6854 MONGOLIAN, // 1800..1801
6855 COMMON, // 1802..1803
6856 MONGOLIAN, // 1804
6857 COMMON, // 1805
6858 MONGOLIAN, // 1806..180E
6859 UNKNOWN, // 180F
6860 MONGOLIAN, // 1810..1819
6861 UNKNOWN, // 181A..181F
6862 MONGOLIAN, // 1820..1878
6863 UNKNOWN, // 1879..187F
6864 MONGOLIAN, // 1880..18AA
6865 UNKNOWN, // 18AB..18AF
6866 CANADIAN_ABORIGINAL, // 18B0..18F5
6867 UNKNOWN, // 18F6..18FF
6868 LIMBU, // 1900..191E
6869 UNKNOWN, // 191F
6870 LIMBU, // 1920..192B
6871 UNKNOWN, // 192C..192F
6872 LIMBU, // 1930..193B
6873 UNKNOWN, // 193C..193F
6874 LIMBU, // 1940
6875 UNKNOWN, // 1941..1943
6876 LIMBU, // 1944..194F
6877 TAI_LE, // 1950..196D
6878 UNKNOWN, // 196E..196F
6879 TAI_LE, // 1970..1974
6880 UNKNOWN, // 1975..197F
6881 NEW_TAI_LUE, // 1980..19AB
6882 UNKNOWN, // 19AC..19AF
6883 NEW_TAI_LUE, // 19B0..19C9
6884 UNKNOWN, // 19CA..19CF
6885 NEW_TAI_LUE, // 19D0..19DA
6886 UNKNOWN, // 19DB..19DD
6887 NEW_TAI_LUE, // 19DE..19DF
6888 KHMER, // 19E0..19FF
6889 BUGINESE, // 1A00..1A1B
6890 UNKNOWN, // 1A1C..1A1D
6891 BUGINESE, // 1A1E..1A1F
6892 TAI_THAM, // 1A20..1A5E
6893 UNKNOWN, // 1A5F
6894 TAI_THAM, // 1A60..1A7C
6895 UNKNOWN, // 1A7D..1A7E
6896 TAI_THAM, // 1A7F..1A89
6897 UNKNOWN, // 1A8A..1A8F
6898 TAI_THAM, // 1A90..1A99
6899 UNKNOWN, // 1A9A..1A9F
6900 TAI_THAM, // 1AA0..1AAD
6901 UNKNOWN, // 1AAE..1AAF
6902 INHERITED, // 1AB0..1ABE
6903 UNKNOWN, // 1ABF..1AFF
6904 BALINESE, // 1B00..1B4B
6905 UNKNOWN, // 1B4C..1B4F
6906 BALINESE, // 1B50..1B7C
6907 UNKNOWN, // 1B7D..1B7F
6908 SUNDANESE, // 1B80..1BBF
6909 BATAK, // 1BC0..1BF3
6910 UNKNOWN, // 1BF4..1BFB
6911 BATAK, // 1BFC..1BFF
6912 LEPCHA, // 1C00..1C37
6913 UNKNOWN, // 1C38..1C3A
6914 LEPCHA, // 1C3B..1C49
6915 UNKNOWN, // 1C4A..1C4C
6916 LEPCHA, // 1C4D..1C4F
6917 OL_CHIKI, // 1C50..1C7F
6918 CYRILLIC, // 1C80..1C88
6919 UNKNOWN, // 1C89
6920 GEORGIAN, // 1C90..1CBA
6921 UNKNOWN, // 1CBB..1CBC
6922 GEORGIAN, // 1CBD..1CBF
6923 SUNDANESE, // 1CC0..1CC7
6924 UNKNOWN, // 1CC8..1CCF
6925 INHERITED, // 1CD0..1CD2
6926 COMMON, // 1CD3
6927 INHERITED, // 1CD4..1CE0
6928 COMMON, // 1CE1
6929 INHERITED, // 1CE2..1CE8
6930 COMMON, // 1CE9..1CEC
6931 INHERITED, // 1CED
6932 COMMON, // 1CEE..1CF3
6933 INHERITED, // 1CF4
6934 COMMON, // 1CF5..1CF7
6935 INHERITED, // 1CF8..1CF9
6936 UNKNOWN, // 1CFA..1CFF
6937 LATIN, // 1D00..1D25
6938 GREEK, // 1D26..1D2A
6939 CYRILLIC, // 1D2B
6940 LATIN, // 1D2C..1D5C
6941 GREEK, // 1D5D..1D61
6942 LATIN, // 1D62..1D65
6943 GREEK, // 1D66..1D6A
6944 LATIN, // 1D6B..1D77
6945 CYRILLIC, // 1D78
6946 LATIN, // 1D79..1DBE
6947 GREEK, // 1DBF
6948 INHERITED, // 1DC0..1DF9
6949 UNKNOWN, // 1DFA
6950 INHERITED, // 1DFB..1DFF
6951 LATIN, // 1E00..1EFF
6952 GREEK, // 1F00..1F15
6953 UNKNOWN, // 1F16..1F17
6954 GREEK, // 1F18..1F1D
6955 UNKNOWN, // 1F1E..1F1F
6956 GREEK, // 1F20..1F45
6957 UNKNOWN, // 1F46..1F47
6958 GREEK, // 1F48..1F4D
6959 UNKNOWN, // 1F4E..1F4F
6960 GREEK, // 1F50..1F57
6961 UNKNOWN, // 1F58
6962 GREEK, // 1F59
6963 UNKNOWN, // 1F5A
6964 GREEK, // 1F5B
6965 UNKNOWN, // 1F5C
6966 GREEK, // 1F5D
6967 UNKNOWN, // 1F5E
6968 GREEK, // 1F5F..1F7D
6969 UNKNOWN, // 1F7E..1F7F
6970 GREEK, // 1F80..1FB4
6971 UNKNOWN, // 1FB5
6972 GREEK, // 1FB6..1FC4
6973 UNKNOWN, // 1FC5
6974 GREEK, // 1FC6..1FD3
6975 UNKNOWN, // 1FD4..1FD5
6976 GREEK, // 1FD6..1FDB
6977 UNKNOWN, // 1FDC
6978 GREEK, // 1FDD..1FEF
6979 UNKNOWN, // 1FF0..1FF1
6980 GREEK, // 1FF2..1FF4
6981 UNKNOWN, // 1FF5
6982 GREEK, // 1FF6..1FFE
6983 UNKNOWN, // 1FFF
6984 COMMON, // 2000..200B
6985 INHERITED, // 200C..200D
6986 COMMON, // 200E..2064
6987 UNKNOWN, // 2065
6988 COMMON, // 2066..2070
6989 LATIN, // 2071
6990 UNKNOWN, // 2072..2073
6991 COMMON, // 2074..207E
6992 LATIN, // 207F
6993 COMMON, // 2080..208E
6994 UNKNOWN, // 208F
6995 LATIN, // 2090..209C
6996 UNKNOWN, // 209D..209F
6997 COMMON, // 20A0..20BF
6998 UNKNOWN, // 20C0..20CF
6999 INHERITED, // 20D0..20F0
7000 UNKNOWN, // 20F1..20FF
7001 COMMON, // 2100..2125
7002 GREEK, // 2126
7003 COMMON, // 2127..2129
7004 LATIN, // 212A..212B
7005 COMMON, // 212C..2131
7006 LATIN, // 2132
7007 COMMON, // 2133..214D
7008 LATIN, // 214E
7009 COMMON, // 214F..215F
7010 LATIN, // 2160..2188
7011 COMMON, // 2189..218B
7012 UNKNOWN, // 218C..218F
7013 COMMON, // 2190..2426
7014 UNKNOWN, // 2427..243F
7015 COMMON, // 2440..244A
7016 UNKNOWN, // 244B..245F
7017 COMMON, // 2460..27FF
7018 BRAILLE, // 2800..28FF
7019 COMMON, // 2900..2B73
7020 UNKNOWN, // 2B74..2B75
7021 COMMON, // 2B76..2B95
7022 UNKNOWN, // 2B96..2B97
7023 COMMON, // 2B98..2BC8
7024 UNKNOWN, // 2BC9
7025 COMMON, // 2BCA..2BFE
7026 UNKNOWN, // 0x2BFF
7027 GLAGOLITIC, // 2C00..2C2E
7028 UNKNOWN, // 2C2F
7029 GLAGOLITIC, // 2C30..2C5E
7030 UNKNOWN, // 2C5F
7031 LATIN, // 2C60..2C7F
7032 COPTIC, // 2C80..2CF3
7033 UNKNOWN, // 2CF4..2CF8
7034 COPTIC, // 2CF9..2CFF
7035 GEORGIAN, // 2D00..2D25
7036 UNKNOWN, // 2D26
7037 GEORGIAN, // 2D27
7038 UNKNOWN, // 2D28..2D2C
7039 GEORGIAN, // 2D2D
7040 UNKNOWN, // 2D2E..2D2F
7041 TIFINAGH, // 2D30..2D67
7042 UNKNOWN, // 2D68..2D6E
7043 TIFINAGH, // 2D6F..2D70
7044 UNKNOWN, // 2D71..2D7E
7045 TIFINAGH, // 2D7F
7046 ETHIOPIC, // 2D80..2D96
7047 UNKNOWN, // 2D97..2D9F
7048 ETHIOPIC, // 2DA0..2DA6
7049 UNKNOWN, // 2DA7
7050 ETHIOPIC, // 2DA8..2DAE
7051 UNKNOWN, // 2DAF
7052 ETHIOPIC, // 2DB0..2DB6
7053 UNKNOWN, // 2DB7
7054 ETHIOPIC, // 2DB8..2DBE
7055 UNKNOWN, // 2DBF
7056 ETHIOPIC, // 2DC0..2DC6
7057 UNKNOWN, // 2DC7
7058 ETHIOPIC, // 2DC8..2DCE
7059 UNKNOWN, // 2DCF
7060 ETHIOPIC, // 2DD0..2DD6
7061 UNKNOWN, // 2DD7
7062 ETHIOPIC, // 2DD8..2DDE
7063 UNKNOWN, // 2DDF
7064 CYRILLIC, // 2DE0..2DFF
7065 COMMON, // 2E00..2E4E
7066 UNKNOWN, // 2E4F..2E7F
7067 HAN, // 2E80..2E99
7068 UNKNOWN, // 2E9A
7069 HAN, // 2E9B..2EF3
7070 UNKNOWN, // 2EF4..2EFF
7071 HAN, // 2F00..2FD5
7072 UNKNOWN, // 2FD6..2FEF
7073 COMMON, // 2FF0..2FFB
7074 UNKNOWN, // 2FFC..2FFF
7075 COMMON, // 3000..3004
7076 HAN, // 3005
7077 COMMON, // 3006
7078 HAN, // 3007
7079 COMMON, // 3008..3020
7080 HAN, // 3021..3029
7081 INHERITED, // 302A..302D
7082 HANGUL, // 302E..302F
7083 COMMON, // 3030..3037
7084 HAN, // 3038..303B
7085 COMMON, // 303C..303F
7086 UNKNOWN, // 3040
7087 HIRAGANA, // 3041..3096
7088 UNKNOWN, // 3097..3098
7089 INHERITED, // 3099..309A
7090 COMMON, // 309B..309C
7091 HIRAGANA, // 309D..309F
7092 COMMON, // 30A0
7093 KATAKANA, // 30A1..30FA
7094 COMMON, // 30FB..30FC
7095 KATAKANA, // 30FD..30FF
7096 UNKNOWN, // 3100..3104
7097 BOPOMOFO, // 3105..312F
7098 UNKNOWN, // 3130
7099 HANGUL, // 3131..318E
7100 UNKNOWN, // 318F
7101 COMMON, // 3190..319F
7102 BOPOMOFO, // 31A0..31BA
7103 UNKNOWN, // 31BB..31BF
7104 COMMON, // 31C0..31E3
7105 UNKNOWN, // 31E4..31EF
7106 KATAKANA, // 31F0..31FF
7107 HANGUL, // 3200..321E
7108 UNKNOWN, // 321F
7109 COMMON, // 3220..325F
7110 HANGUL, // 3260..327E
7111 COMMON, // 327F..32CF
7112 KATAKANA, // 32D0..32FE
7113 COMMON, // 32FF
7114 KATAKANA, // 3300..3357
7115 COMMON, // 3358..33FF
7116 HAN, // 3400..4DB5
7117 UNKNOWN, // 4DB6..4DBF
7118 COMMON, // 4DC0..4DFF
7119 HAN, // 4E00..9FEF
7120 UNKNOWN, // 9FF0..9FFF
7121 YI, // A000..A48C
7122 UNKNOWN, // A48D..A48F
7123 YI, // A490..A4C6
7124 UNKNOWN, // A4C7..A4CF
7125 LISU, // A4D0..A4FF
7126 VAI, // A500..A62B
7127 UNKNOWN, // A62C..A63F
7128 CYRILLIC, // A640..A69F
7129 BAMUM, // A6A0..A6F7
7130 UNKNOWN, // A6F8..A6FF
7131 COMMON, // A700..A721
7132 LATIN, // A722..A787
7133 COMMON, // A788..A78A
7134 LATIN, // A78B..A7B9
7135 UNKNOWN, // A7C0..A7F6
7136 LATIN, // A7F7..A7FF
7137 SYLOTI_NAGRI, // A800..A82B
7138 UNKNOWN, // A82C..A82F
7139 COMMON, // A830..A839
7140 UNKNOWN, // A83A..A83F
7141 PHAGS_PA, // A840..A877
7142 UNKNOWN, // A878..A87F
7143 SAURASHTRA, // A880..A8C5
7144 UNKNOWN, // A8C6..A8CD
7145 SAURASHTRA, // A8CE..A8D9
7146 UNKNOWN, // A8DA..A8DF
7147 DEVANAGARI, // A8E0..A8FF
7148 KAYAH_LI, // A900..A92D
7149 COMMON, // A92E
7150 KAYAH_LI, // A92F
7151 REJANG, // A930..A953
7152 UNKNOWN, // A954..A95E
7153 REJANG, // A95F
7154 HANGUL, // A960..A97C
7155 UNKNOWN, // A97D..A97F
7156 JAVANESE, // A980..A9CD
7157 UNKNOWN, // A9CE
7158 COMMON, // A9CF
7159 JAVANESE, // A9D0..A9D9
7160 UNKNOWN, // A9DA..A9DD
7161 JAVANESE, // A9DE..A9DF
7162 MYANMAR, // A9E0..A9FE
7163 UNKNOWN, // A9FF
7164 CHAM, // AA00..AA36
7165 UNKNOWN, // AA37..AA3F
7166 CHAM, // AA40..AA4D
7167 UNKNOWN, // AA4E..AA4F
7168 CHAM, // AA50..AA59
7169 UNKNOWN, // AA5A..AA5B
7170 CHAM, // AA5C..AA5F
7171 MYANMAR, // AA60..AA7F
7172 TAI_VIET, // AA80..AAC2
7173 UNKNOWN, // AAC3..AADA
7174 TAI_VIET, // AADB..AADF
7175 MEETEI_MAYEK, // AAE0..AAF6
7176 UNKNOWN, // AAF7..AB00
7177 ETHIOPIC, // AB01..AB06
7178 UNKNOWN, // AB07..AB08
7179 ETHIOPIC, // AB09..AB0E
7180 UNKNOWN, // AB0F..AB10
7181 ETHIOPIC, // AB11..AB16
7182 UNKNOWN, // AB17..AB1F
7183 ETHIOPIC, // AB20..AB26
7184 UNKNOWN, // AB27
7185 ETHIOPIC, // AB28..AB2E
7186 UNKNOWN, // AB2F
7187 LATIN, // AB30..AB5A
7188 COMMON, // AB5B
7189 LATIN, // AB5C..AB64
7190 GREEK, // AB65
7191 UNKNOWN, // AB66..AB6F
7192 CHEROKEE, // AB70..ABBF
7193 MEETEI_MAYEK, // ABC0..ABED
7194 UNKNOWN, // ABEE..ABEF
7195 MEETEI_MAYEK, // ABF0..ABF9
7196 UNKNOWN, // ABFA..ABFF
7197 HANGUL, // AC00..D7A3
7198 UNKNOWN, // D7A4..D7AF
7199 HANGUL, // D7B0..D7C6
7200 UNKNOWN, // D7C7..D7CA
7201 HANGUL, // D7CB..D7FB
7202 UNKNOWN, // D7FC..F8FF
7203 HAN, // F900..FA6D
7204 UNKNOWN, // FA6E..FA6F
7205 HAN, // FA70..FAD9
7206 UNKNOWN, // FADA..FAFF
7207 LATIN, // FB00..FB06
7208 UNKNOWN, // FB07..FB12
7209 ARMENIAN, // FB13..FB17
7210 UNKNOWN, // FB18..FB1C
7211 HEBREW, // FB1D..FB36
7212 UNKNOWN, // FB37
7213 HEBREW, // FB38..FB3C
7214 UNKNOWN, // FB3D
7215 HEBREW, // FB3E
7216 UNKNOWN, // FB3F
7217 HEBREW, // FB40..FB41
7218 UNKNOWN, // FB42
7219 HEBREW, // FB43..FB44
7220 UNKNOWN, // FB45
7221 HEBREW, // FB46..FB4F
7222 ARABIC, // FB50..FBC1
7223 UNKNOWN, // FBC2..FBD2
7224 ARABIC, // FBD3..FD3D
7225 COMMON, // FD3E..FD3F
7226 UNKNOWN, // FD40..FD4F
7227 ARABIC, // FD50..FD8F
7228 UNKNOWN, // FD90..FD91
7229 ARABIC, // FD92..FDC7
7230 UNKNOWN, // FDC8..FDEF
7231 ARABIC, // FDF0..FDFD
7232 UNKNOWN, // FDFE..FDFF
7233 INHERITED, // FE00..FE0F
7234 COMMON, // FE10..FE19
7235 UNKNOWN, // FE1A..FE1F
7236 INHERITED, // FE20..FE2D
7237 CYRILLIC, // FE2E..FE2F
7238 COMMON, // FE30..FE52
7239 UNKNOWN, // FE53
7240 COMMON, // FE54..FE66
7241 UNKNOWN, // FE67
7242 COMMON, // FE68..FE6B
7243 UNKNOWN, // FE6C..FE6F
7244 ARABIC, // FE70..FE74
7245 UNKNOWN, // FE75
7246 ARABIC, // FE76..FEFC
7247 UNKNOWN, // FEFD..FEFE
7248 COMMON, // FEFF
7249 UNKNOWN, // FF00
7250 COMMON, // FF01..FF20
7251 LATIN, // FF21..FF3A
7252 COMMON, // FF3B..FF40
7253 LATIN, // FF41..FF5A
7254 COMMON, // FF5B..FF65
7255 KATAKANA, // FF66..FF6F
7256 COMMON, // FF70
7257 KATAKANA, // FF71..FF9D
7258 COMMON, // FF9E..FF9F
7259 HANGUL, // FFA0..FFBE
7260 UNKNOWN, // FFBF..FFC1
7261 HANGUL, // FFC2..FFC7
7262 UNKNOWN, // FFC8..FFC9
7263 HANGUL, // FFCA..FFCF
7264 UNKNOWN, // FFD0..FFD1
7265 HANGUL, // FFD2..FFD7
7266 UNKNOWN, // FFD8..FFD9
7267 HANGUL, // FFDA..FFDC
7268 UNKNOWN, // FFDD..FFDF
7269 COMMON, // FFE0..FFE6
7270 UNKNOWN, // FFE7
7271 COMMON, // FFE8..FFEE
7272 UNKNOWN, // FFEF..FFF8
7273 COMMON, // FFF9..FFFD
7274 UNKNOWN, // FFFE..FFFF
7275 LINEAR_B, // 10000..1000B
7276 UNKNOWN, // 1000C
7277 LINEAR_B, // 1000D..10026
7278 UNKNOWN, // 10027
7279 LINEAR_B, // 10028..1003A
7280 UNKNOWN, // 1003B
7281 LINEAR_B, // 1003C..1003D
7282 UNKNOWN, // 1003E
7283 LINEAR_B, // 1003F..1004D
7284 UNKNOWN, // 1004E..1004F
7285 LINEAR_B, // 10050..1005D
7286 UNKNOWN, // 1005E..1007F
7287 LINEAR_B, // 10080..100FA
7288 UNKNOWN, // 100FB..100FF
7289 COMMON, // 10100..10102
7290 UNKNOWN, // 10103..10106
7291 COMMON, // 10107..10133
7292 UNKNOWN, // 10134..10136
7293 COMMON, // 10137..1013F
7294 GREEK, // 10140..1018E
7295 UNKNOWN, // 1018F
7296 COMMON, // 10190..1019B
7297 UNKNOWN, // 1019C..1019F
7298 GREEK, // 101A0
7299 UNKNOWN, // 101A1..101CF
7300 COMMON, // 101D0..101FC
7301 INHERITED, // 101FD
7302 UNKNOWN, // 101FE..1027F
7303 LYCIAN, // 10280..1029C
7304 UNKNOWN, // 1029D..1029F
7305 CARIAN, // 102A0..102D0
7306 UNKNOWN, // 102D1..102DF
7307 INHERITED, // 102E0
7308 COMMON, // 102E1..102FB
7309 UNKNOWN, // 102FC..102FF
7310 OLD_ITALIC, // 10300..10323
7311 UNKNOWN, // 10324..1032C
7312 OLD_ITALIC, // 1032D..1032F
7313 GOTHIC, // 10330..1034A
7314 UNKNOWN, // 1034B..1034F
7315 OLD_PERMIC, // 10350..1037A
7316 UNKNOWN, // 1037B..1037F
7317 UGARITIC, // 10380..1039D
7318 UNKNOWN, // 1039E
7319 UGARITIC, // 1039F
7320 OLD_PERSIAN, // 103A0..103C3
7321 UNKNOWN, // 103C4..103C7
7322 OLD_PERSIAN, // 103C8..103D5
7323 UNKNOWN, // 103D6..103FF
7324 DESERET, // 10400..1044F
7325 SHAVIAN, // 10450..1047F
7326 OSMANYA, // 10480..1049D
7327 UNKNOWN, // 1049E..1049F
7328 OSMANYA, // 104A0..104A9
7329 UNKNOWN, // 104AA..104AF
7330 OSAGE, // 104B0..104D3;
7331 UNKNOWN, // 104D4..104D7;
7332 OSAGE, // 104D8..104FB;
7333 UNKNOWN, // 104FC..104FF;
7334 ELBASAN, // 10500..10527
7335 UNKNOWN, // 10528..1052F
7336 CAUCASIAN_ALBANIAN, // 10530..10563
7337 UNKNOWN, // 10564..1056E
7338 CAUCASIAN_ALBANIAN, // 1056F
7339 UNKNOWN, // 10570..105FF
7340 LINEAR_A, // 10600..10736
7341 UNKNOWN, // 10737..1073F
7342 LINEAR_A, // 10740..10755
7343 UNKNOWN, // 10756..1075F
7344 LINEAR_A, // 10760..10767
7345 UNKNOWN, // 10768..107FF
7346 CYPRIOT, // 10800..10805
7347 UNKNOWN, // 10806..10807
7348 CYPRIOT, // 10808
7349 UNKNOWN, // 10809
7350 CYPRIOT, // 1080A..10835
7351 UNKNOWN, // 10836
7352 CYPRIOT, // 10837..10838
7353 UNKNOWN, // 10839..1083B
7354 CYPRIOT, // 1083C
7355 UNKNOWN, // 1083D..1083E
7356 CYPRIOT, // 1083F
7357 IMPERIAL_ARAMAIC, // 10840..10855
7358 UNKNOWN, // 10856
7359 IMPERIAL_ARAMAIC, // 10857..1085F
7360 PALMYRENE, // 10860..1087F
7361 NABATAEAN, // 10880..1089E
7362 UNKNOWN, // 1089F..108A6
7363 NABATAEAN, // 108A7..108AF
7364 UNKNOWN, // 108B0..108DF
7365 HATRAN, // 108E0..108F2
7366 UNKNOWN, // 108F3
7367 HATRAN, // 108F4..108F5
7368 UNKNOWN, // 108F6..108FA
7369 HATRAN, // 108FB..108FF
7370 PHOENICIAN, // 10900..1091B
7371 UNKNOWN, // 1091C..1091E
7372 PHOENICIAN, // 1091F
7373 LYDIAN, // 10920..10939
7374 UNKNOWN, // 1093A..1093E
7375 LYDIAN, // 1093F
7376 UNKNOWN, // 10940..1097F
7377 MEROITIC_HIEROGLYPHS, // 10980..1099F
7378 MEROITIC_CURSIVE, // 109A0..109B7
7379 UNKNOWN, // 109B8..109BB
7380 MEROITIC_CURSIVE, // 109BC..109CF
7381 UNKNOWN, // 109D0..109D1
7382 MEROITIC_CURSIVE, // 109D2..109FF
7383 KHAROSHTHI, // 10A00..10A03
7384 UNKNOWN, // 10A04
7385 KHAROSHTHI, // 10A05..10A06
7386 UNKNOWN, // 10A07..10A0B
7387 KHAROSHTHI, // 10A0C..10A13
7388 UNKNOWN, // 10A14
7389 KHAROSHTHI, // 10A15..10A17
7390 UNKNOWN, // 10A18
7391 KHAROSHTHI, // 10A19..10A35
7392 UNKNOWN, // 10A36..10A37
7393 KHAROSHTHI, // 10A38..10A3A
7394 UNKNOWN, // 10A3B..10A3E
7395 KHAROSHTHI, // 10A3F..10A48
7396 UNKNOWN, // 10A49..10A4F
7397 KHAROSHTHI, // 10A50..10A58
7398 UNKNOWN, // 10A59..10A5F
7399 OLD_SOUTH_ARABIAN, // 10A60..10A7F
7400 OLD_NORTH_ARABIAN, // 10A80..10A9F
7401 UNKNOWN, // 10AA0..10ABF
7402 MANICHAEAN, // 10AC0..10AE6
7403 UNKNOWN, // 10AE7..10AEA
7404 MANICHAEAN, // 10AEB..10AF6
7405 UNKNOWN, // 10AF7..10AFF
7406 AVESTAN, // 10B00..10B35
7407 UNKNOWN, // 10B36..10B38
7408 AVESTAN, // 10B39..10B3F
7409 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
7410 UNKNOWN, // 10B56..10B57
7411 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
7412 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
7413 UNKNOWN, // 10B73..10B77
7414 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
7415 PSALTER_PAHLAVI, // 10B80..10B91
7416 UNKNOWN, // 10B92..10B98
7417 PSALTER_PAHLAVI, // 10B99..10B9C
7418 UNKNOWN, // 10B9D..10BA8
7419 PSALTER_PAHLAVI, // 10BA9..10BAF
7420 UNKNOWN, // 10BB0..10BFF
7421 OLD_TURKIC, // 10C00..10C48
7422 UNKNOWN, // 10C49..10C7F
7423 OLD_HUNGARIAN, // 10C80..10CB2
7424 UNKNOWN, // 10CB3..10CBF
7425 OLD_HUNGARIAN, // 10CC0..10CF2
7426 UNKNOWN, // 10CF3..10CF9
7427 OLD_HUNGARIAN, // 10CFA..10CFF
7428 HANIFI_ROHINGYA, // 10D00..10D27
7429 UNKNOWN, // 10D28..10D29
7430 HANIFI_ROHINGYA, // 10D30..10D39
7431 UNKNOWN, // 10D3A..10E5F
7432 ARABIC, // 10E60..10E7E
7433 UNKNOWN, // 10E7F..10EFF
7434 OLD_SOGDIAN, // 10F00..10F27
7435 UNKNOWN, // 10F28..10F2F
7436 SOGDIAN, // 10F30..10F59
7437 UNKNOWN, // 10F5A..10FFF
7438 BRAHMI, // 11000..1104D
7439 UNKNOWN, // 1104E..11051
7440 BRAHMI, // 11052..1106F
7441 UNKNOWN, // 11070..1107E
7442 BRAHMI, // 1107F
7443 KAITHI, // 11080..110C1
7444 UNKNOWN, // 110C2..110CC
7445 KAITHI, // 110CD
7446 UNKNOWN, // 110CE..110CF
7447 SORA_SOMPENG, // 110D0..110E8
7448 UNKNOWN, // 110E9..110EF
7449 SORA_SOMPENG, // 110F0..110F9
7450 UNKNOWN, // 110FA..110FF
7451 CHAKMA, // 11100..11134
7452 UNKNOWN, // 11135
7453 CHAKMA, // 11136..11146
7454 UNKNOWN, // 11147..1114F
7455 MAHAJANI, // 11150..11176
7456 UNKNOWN, // 11177..1117F
7457 SHARADA, // 11180..111CD
7458 UNKNOWN, // 111CE..111CF
7459 SHARADA, // 111D0..111DF
7460 UNKNOWN, // 111E0
7461 SINHALA, // 111E1..111F4
7462 UNKNOWN, // 111F5..111FF
7463 KHOJKI, // 11200..11211
7464 UNKNOWN, // 11212
7465 KHOJKI, // 11213..1123E
7466 UNKNOWN, // 1123F..1127F
7467 MULTANI, // 11280..11286
7468 UNKNOWN, // 11287
7469 MULTANI, // 11288
7470 UNKNOWN, // 11289
7471 MULTANI, // 1128A..1128D
7472 UNKNOWN, // 1128E
7473 MULTANI, // 1128F..1129D
7474 UNKNOWN, // 1129E
7475 MULTANI, // 1129F..112A9
7476 UNKNOWN, // 112AA..112AF
7477 KHUDAWADI, // 112B0..112EA
7478 UNKNOWN, // 112EB..112EF
7479 KHUDAWADI, // 112F0..112F9
7480 UNKNOWN, // 112FA..112FF
7481 GRANTHA, // 11300..11303
7482 UNKNOWN, // 11304
7483 GRANTHA, // 11305..1130C
7484 UNKNOWN, // 1130D..1130E
7485 GRANTHA, // 1130F..11310
7486 UNKNOWN, // 11311..11312
7487 GRANTHA, // 11313..11328
7488 UNKNOWN, // 11329
7489 GRANTHA, // 1132A..11330
7490 UNKNOWN, // 11331
7491 GRANTHA, // 11332..11333
7492 UNKNOWN, // 11334
7493 GRANTHA, // 11335..11339
7494 UNKNOWN, // 1133A
7495 INHERITED, // 1133B
7496 GRANTHA, // 1133C..11344
7497 UNKNOWN, // 11345..11346
7498 GRANTHA, // 11347..11348
7499 UNKNOWN, // 11349..1134A
7500 GRANTHA, // 1134B..1134D
7501 UNKNOWN, // 1134E..1134F
7502 GRANTHA, // 11350
7503 UNKNOWN, // 11351..11356
7504 GRANTHA, // 11357
7505 UNKNOWN, // 11358..1135C
7506 GRANTHA, // 1135D..11363
7507 UNKNOWN, // 11364..11365
7508 GRANTHA, // 11366..1136C
7509 UNKNOWN, // 1136D..1136F
7510 GRANTHA, // 11370..11374
7511 UNKNOWN, // 11375..113FF
7512 NEWA, // 11400..11459
7513 UNKNOWN, // 1145A
7514 NEWA, // 1145B
7515 UNKNOWN, // 1145C
7516 NEWA, // 1145D..1145E
7517 UNKNOWN, // 1145F..1147F
7518 TIRHUTA, // 11480..114C7
7519 UNKNOWN, // 114C8..114CF
7520 TIRHUTA, // 114D0..114D9
7521 UNKNOWN, // 114DA..1157F
7522 SIDDHAM, // 11580..115B5
7523 UNKNOWN, // 115B6..115B7
7524 SIDDHAM, // 115B8..115DD
7525 UNKNOWN, // 115DE..115FF
7526 MODI, // 11600..11644
7527 UNKNOWN, // 11645..1164F
7528 MODI, // 11650..11659
7529 UNKNOWN, // 1165A..1165F
7530 MONGOLIAN, // 11660..1166C
7531 UNKNOWN, // 1166D..1167F
7532 TAKRI, // 11680..116B7
7533 UNKNOWN, // 116B8..116BF
7534 TAKRI, // 116C0..116C9
7535 UNKNOWN, // 116CA..116FF
7536 AHOM, // 11700..1171A
7537 UNKNOWN, // 1171B..1171C
7538 AHOM, // 1171D..1172B
7539 UNKNOWN, // 1172C..1172F
7540 AHOM, // 11730..1173F
7541 UNKNOWN, // 11740..117FF
7542 DOGRA, // 11800..1183B
7543 UNKNOWN, // 1183C..1189F
7544 WARANG_CITI, // 118A0..118F2
7545 UNKNOWN, // 118F3..118FE
7546 WARANG_CITI, // 118FF
7547 UNKNOWN, // 11900..119FF
7548 ZANABAZAR_SQUARE, // 11A00..11A47
7549 UNKNOWN, // 11A48..11A4F
7550 SOYOMBO, // 11A50..11A83
7551 UNKNOWN, // 11A84..11A85
7552 SOYOMBO, // 11A86..11AA2
7553 UNKNOWN, // 11AA3..11ABF
7554 PAU_CIN_HAU, // 11AC0..11AF8
7555 UNKNOWN, // 11AF9..11BFF
7556 BHAIKSUKI, // 11C00..11C08
7557 UNKNOWN, // 11C09
7558 BHAIKSUKI, // 11C0A..11C36
7559 UNKNOWN, // 11C37
7560 BHAIKSUKI, // 11C38..11C45
7561 UNKNOWN, // 11C46..11C49
7562 BHAIKSUKI, // 11C50..11C6C
7563 UNKNOWN, // 11C6D..11C6F
7564 MARCHEN, // 11C70..11C8F
7565 UNKNOWN, // 11C90..11C91
7566 MARCHEN, // 11C92..11CA7
7567 UNKNOWN, // 11CA8
7568 MARCHEN, // 11CA9..11CB6
7569 UNKNOWN, // 11CB7..11CFF
7570 MASARAM_GONDI, // 11D00..11D06
7571 UNKNOWN, // 11D07
7572 MASARAM_GONDI, // 11D08..11D09
7573 UNKNOWN, // 11D0A
7574 MASARAM_GONDI, // 11D0B..11D36
7575 UNKNOWN, // 11D37..11D39
7576 MASARAM_GONDI, // 11D3A
7577 UNKNOWN, // 11D3B
7578 MASARAM_GONDI, // 11D3C..11D3D
7579 UNKNOWN, // 11D3E
7580 MASARAM_GONDI, // 11D3F..11D47
7581 UNKNOWN, // 11D48..11D49
7582 MASARAM_GONDI, // 11D50..11D59
7583 UNKNOWN, // 11D5A..11D5F
7584 GUNJALA_GONDI, // 11D60..11D68
7585 UNKNOWN, // 11D69
7586 GUNJALA_GONDI, // 11D6A..11D8E
7587 UNKNOWN, // 11D8F
7588 GUNJALA_GONDI, // 11D90..11D91
7589 UNKNOWN, // 11D92
7590 GUNJALA_GONDI, // 11D93..11D98
7591 UNKNOWN, // 11D99
7592 GUNJALA_GONDI, // 11DA0..11DA9
7593 UNKNOWN, // 11DAA..11DFF
7594 MAKASAR, // 11EE0..11EF8
7595 UNKNOWN, // 11EF9..11FFF
7596 CUNEIFORM, // 12000..12399
7597 UNKNOWN, // 1239A..123FF
7598 CUNEIFORM, // 12400..1246E
7599 UNKNOWN, // 1246F
7600 CUNEIFORM, // 12470..12474
7601 UNKNOWN, // 12475..1247F
7602 CUNEIFORM, // 12480..12543
7603 UNKNOWN, // 12544..12FFF
7604 EGYPTIAN_HIEROGLYPHS, // 13000..1342E
7605 UNKNOWN, // 1342F..143FF
7606 ANATOLIAN_HIEROGLYPHS, // 14400..14646
7607 UNKNOWN, // 14647..167FF
7608 BAMUM, // 16800..16A38
7609 UNKNOWN, // 16A39..16A3F
7610 MRO, // 16A40..16A5E
7611 UNKNOWN, // 16A5F
7612 MRO, // 16A60..16A69
7613 UNKNOWN, // 16A6A..16A6D
7614 MRO, // 16A6E..16A6F
7615 UNKNOWN, // 16A70..16ACF
7616 BASSA_VAH, // 16AD0..16AED
7617 UNKNOWN, // 16AEE..16AEF
7618 BASSA_VAH, // 16AF0..16AF5
7619 UNKNOWN, // 16AF6..16AFF
7620 PAHAWH_HMONG, // 16B00..16B45
7621 UNKNOWN, // 16B46..16B4F
7622 PAHAWH_HMONG, // 16B50..16B59
7623 UNKNOWN, // 16B5A
7624 PAHAWH_HMONG, // 16B5B..16B61
7625 UNKNOWN, // 16B62
7626 PAHAWH_HMONG, // 16B63..16B77
7627 UNKNOWN, // 16B78..16B7C
7628 PAHAWH_HMONG, // 16B7D..16B8F
7629 UNKNOWN, // 16B90..16E3F
7630 MEDEFAIDRIN, // 16E40..16E9A
7631 UNKNOWN, // 16E9B..16EFF
7632 MIAO, // 16F00..16F44
7633 UNKNOWN, // 16F45..16F4F
7634 MIAO, // 16F50..16F7E
7635 UNKNOWN, // 16F7F..16F8E
7636 MIAO, // 16F8F..16F9F
7637 UNKNOWN, // 16FA0..16FDF
7638 TANGUT, // 16FE0
7639 NUSHU, // 16FE1
7640 UNKNOWN, // 16FE2..16FFF
7641 TANGUT, // 17000..187F1
7642 UNKNOWN, // 187F2..187FF
7643 TANGUT, // 18800..18AF2
7644 UNKNOWN, // 18AF3..1AFFF
7645 KATAKANA, // 1B000
7646 HIRAGANA, // 1B001..1B11E
7647 UNKNOWN, // 1B11F..1B16F
7648 NUSHU, // 1B170..1B2FB
7649 UNKNOWN, // 1B2FC..1BBFF
7650 DUPLOYAN, // 1BC00..1BC6A
7651 UNKNOWN, // 1BC6B..1BC6F
7652 DUPLOYAN, // 1BC70..1BC7C
7653 UNKNOWN, // 1BC7D..1BC7F
7654 DUPLOYAN, // 1BC80..1BC88
7655 UNKNOWN, // 1BC89..1BC8F
7656 DUPLOYAN, // 1BC90..1BC99
7657 UNKNOWN, // 1BC9A..1BC9B
7658 DUPLOYAN, // 1BC9C..1BC9F
7659 COMMON, // 1BCA0..1BCA3
7660 UNKNOWN, // 1BCA4..1CFFF
7661 COMMON, // 1D000..1D0F5
7662 UNKNOWN, // 1D0F6..1D0FF
7663 COMMON, // 1D100..1D126
7664 UNKNOWN, // 1D127..1D128
7665 COMMON, // 1D129..1D166
7666 INHERITED, // 1D167..1D169
7667 COMMON, // 1D16A..1D17A
7668 INHERITED, // 1D17B..1D182
7669 COMMON, // 1D183..1D184
7670 INHERITED, // 1D185..1D18B
7671 COMMON, // 1D18C..1D1A9
7672 INHERITED, // 1D1AA..1D1AD
7673 COMMON, // 1D1AE..1D1E8
7674 UNKNOWN, // 1D1E9..1D1FF
7675 GREEK, // 1D200..1D245
7676 UNKNOWN, // 1D246..1D2DF
7677 COMMON, // 1D2E0..1D2F3
7678 UNKNOWN, // 1D2F4..1D2FF
7679 COMMON, // 1D300..1D356
7680 UNKNOWN, // 1D357..1D35F
7681 COMMON, // 1D360..1D378
7682 UNKNOWN, // 1D379..1D3FF
7683 COMMON, // 1D400..1D454
7684 UNKNOWN, // 1D455
7685 COMMON, // 1D456..1D49C
7686 UNKNOWN, // 1D49D
7687 COMMON, // 1D49E..1D49F
7688 UNKNOWN, // 1D4A0..1D4A1
7689 COMMON, // 1D4A2
7690 UNKNOWN, // 1D4A3..1D4A4
7691 COMMON, // 1D4A5..1D4A6
7692 UNKNOWN, // 1D4A7..1D4A8
7693 COMMON, // 1D4A9..1D4AC
7694 UNKNOWN, // 1D4AD
7695 COMMON, // 1D4AE..1D4B9
7696 UNKNOWN, // 1D4BA
7697 COMMON, // 1D4BB
7698 UNKNOWN, // 1D4BC
7699 COMMON, // 1D4BD..1D4C3
7700 UNKNOWN, // 1D4C4
7701 COMMON, // 1D4C5..1D505
7702 UNKNOWN, // 1D506
7703 COMMON, // 1D507..1D50A
7704 UNKNOWN, // 1D50B..1D50C
7705 COMMON, // 1D50D..1D514
7706 UNKNOWN, // 1D515
7707 COMMON, // 1D516..1D51C
7708 UNKNOWN, // 1D51D
7709 COMMON, // 1D51E..1D539
7710 UNKNOWN, // 1D53A
7711 COMMON, // 1D53B..1D53E
7712 UNKNOWN, // 1D53F
7713 COMMON, // 1D540..1D544
7714 UNKNOWN, // 1D545
7715 COMMON, // 1D546
7716 UNKNOWN, // 1D547..1D549
7717 COMMON, // 1D54A..1D550
7718 UNKNOWN, // 1D551
7719 COMMON, // 1D552..1D6A5
7720 UNKNOWN, // 1D6A6..1D6A7
7721 COMMON, // 1D6A8..1D7CB
7722 UNKNOWN, // 1D7CC..1D7CD
7723 COMMON, // 1D7CE..1D7FF
7724 SIGNWRITING, // 1D800..1DA8B
7725 UNKNOWN, // 1DA8C..1DA9A
7726 SIGNWRITING, // 1DA9B..1DA9F
7727 UNKNOWN, // 1DAA0
7728 SIGNWRITING, // 1DAA1..1DAAF
7729 UNKNOWN, // 1DAB0..1DFFF
7730 GLAGOLITIC, // 1E000..1E006
7731 UNKNOWN, // 1E007
7732 GLAGOLITIC, // 1E008..1E018
7733 UNKNOWN, // 1E019..1E01A
7734 GLAGOLITIC, // 1E01B..1E021
7735 UNKNOWN, // 1E022
7736 GLAGOLITIC, // 1E023..1E024
7737 UNKNOWN, // 1E025
7738 GLAGOLITIC, // 1E026..1E02A
7739 UNKNOWN, // 1E02B..1E7FF
7740 MENDE_KIKAKUI, // 1E800..1E8C4
7741 UNKNOWN, // 1E8C5..1E8C6
7742 MENDE_KIKAKUI, // 1E8C7..1E8D6
7743 UNKNOWN, // 1E8D7..1E8FF
7744 ADLAM, // 1E900..1E94A
7745 UNKNOWN, // 1E94B..1E94F
7746 ADLAM, // 1E950..1E959
7747 UNKNOWN, // 1E95A..1E95D
7748 ADLAM, // 1E95E..1E95F
7749 UNKNOWN, // 1E960..1EC70
7750 COMMON, // 1EC71..1ECB4
7751 UNKNOWN, // 1ECB5..1EDFF
7752 ARABIC, // 1EE00..1EE03
7753 UNKNOWN, // 1EE04
7754 ARABIC, // 1EE05..1EE1F
7755 UNKNOWN, // 1EE20
7756 ARABIC, // 1EE21..1EE22
7757 UNKNOWN, // 1EE23
7758 ARABIC, // 1EE24
7759 UNKNOWN, // 1EE25..1EE26
7760 ARABIC, // 1EE27
7761 UNKNOWN, // 1EE28
7762 ARABIC, // 1EE29..1EE32
7763 UNKNOWN, // 1EE33
7764 ARABIC, // 1EE34..1EE37
7765 UNKNOWN, // 1EE38
7766 ARABIC, // 1EE39
7767 UNKNOWN, // 1EE3A
7768 ARABIC, // 1EE3B
7769 UNKNOWN, // 1EE3C..1EE41
7770 ARABIC, // 1EE42
7771 UNKNOWN, // 1EE43..1EE46
7772 ARABIC, // 1EE47
7773 UNKNOWN, // 1EE48
7774 ARABIC, // 1EE49
7775 UNKNOWN, // 1EE4A
7776 ARABIC, // 1EE4B
7777 UNKNOWN, // 1EE4C
7778 ARABIC, // 1EE4D..1EE4F
7779 UNKNOWN, // 1EE50
7780 ARABIC, // 1EE51..1EE52
7781 UNKNOWN, // 1EE53
7782 ARABIC, // 1EE54
7783 UNKNOWN, // 1EE55..1EE56
7784 ARABIC, // 1EE57
7785 UNKNOWN, // 1EE58
7786 ARABIC, // 1EE59
7787 UNKNOWN, // 1EE5A
7788 ARABIC, // 1EE5B
7789 UNKNOWN, // 1EE5C
7790 ARABIC, // 1EE5D
7791 UNKNOWN, // 1EE5E
7792 ARABIC, // 1EE5F
7793 UNKNOWN, // 1EE60
7794 ARABIC, // 1EE61..1EE62
7795 UNKNOWN, // 1EE63
7796 ARABIC, // 1EE64
7797 UNKNOWN, // 1EE65..1EE66
7798 ARABIC, // 1EE67..1EE6A
7799 UNKNOWN, // 1EE6B
7800 ARABIC, // 1EE6C..1EE72
7801 UNKNOWN, // 1EE73
7802 ARABIC, // 1EE74..1EE77
7803 UNKNOWN, // 1EE78
7804 ARABIC, // 1EE79..1EE7C
7805 UNKNOWN, // 1EE7D
7806 ARABIC, // 1EE7E
7807 UNKNOWN, // 1EE7F
7808 ARABIC, // 1EE80..1EE89
7809 UNKNOWN, // 1EE8A
7810 ARABIC, // 1EE8B..1EE9B
7811 UNKNOWN, // 1EE9C..1EEA0
7812 ARABIC, // 1EEA1..1EEA3
7813 UNKNOWN, // 1EEA4
7814 ARABIC, // 1EEA5..1EEA9
7815 UNKNOWN, // 1EEAA
7816 ARABIC, // 1EEAB..1EEBB
7817 UNKNOWN, // 1EEBC..1EEEF
7818 ARABIC, // 1EEF0..1EEF1
7819 UNKNOWN, // 1EEF2..1EFFF
7820 COMMON, // 1F000..1F02B
7821 UNKNOWN, // 1F02C..1F02F
7822 COMMON, // 1F030..1F093
7823 UNKNOWN, // 1F094..1F09F
7824 COMMON, // 1F0A0..1F0AE
7825 UNKNOWN, // 1F0AF..1F0B0
7826 COMMON, // 1F0B1..1F0BF
7827 UNKNOWN, // 1F0C0
7828 COMMON, // 1F0C1..1F0CF
7829 UNKNOWN, // 1F0D0
7830 COMMON, // 1F0D1..1F0F5
7831 UNKNOWN, // 1F0F6..1F0FF
7832 COMMON, // 1F100..1F10C
7833 UNKNOWN, // 1F10D..1F10F
7834 COMMON, // 1F110..1F16B
7835 UNKNOWN, // 1F16C..1F16F
7836 COMMON, // 1F170..1F1AC
7837 UNKNOWN, // 1F1AD..1F1E5
7838 COMMON, // 1F1E6..1F1FF
7839 HIRAGANA, // 1F200
7840 COMMON, // 1F201..1F202
7841 UNKNOWN, // 1F203..1F20F
7842 COMMON, // 1F210..1F23B
7843 UNKNOWN, // 1F23C..1F23F
7844 COMMON, // 1F240..1F248
7845 UNKNOWN, // 1F249..1F24F
7846 COMMON, // 1F250..1F251
7847 UNKNOWN, // 1F252..1F25F
7848 COMMON, // 1F260..1F265
7849 UNKNOWN, // 1F266..1F2FF
7850 COMMON, // 1F300..1F6D4
7851 UNKNOWN, // 1F6D5..1F6DF
7852 COMMON, // 1F6E0..1F6EC
7853 UNKNOWN, // 1F6ED..1F6EF
7854 COMMON, // 1F6F0..1F6F9
7855 UNKNOWN, // 1F6FA..1F6FF
7856 COMMON, // 1F700..1F773
7857 UNKNOWN, // 1F774..1F77F
7858 COMMON, // 1F780..1F7D8
7859 UNKNOWN, // 1F7D9..1F7FF
7860 COMMON, // 1F800..1F80B
7861 UNKNOWN, // 1F80C..1F80F
7862 COMMON, // 1F810..1F847
7863 UNKNOWN, // 1F848..1F84F
7864 COMMON, // 1F850..1F859
7865 UNKNOWN, // 1F85A..1F85F
7866 COMMON, // 1F860..1F887
7867 UNKNOWN, // 1F888..1F88F
7868 COMMON, // 1F890..1F8AD
7869 UNKNOWN, // 1F8AE..1F8FF
7870 COMMON, // 1F900..1F90B
7871 UNKNOWN, // 1F90C..1F90F
7872 COMMON, // 1F910..1F93E
7873 UNKNOWN, // 1F93F
7874 COMMON, // 1F940..1F970
7875 UNKNOWN, // 1F971..1F972
7876 COMMON, // 1F973..1F976
7877 UNKNOWN, // 1F977..1F979
7878 COMMON, // 1F97A
7879 UNKNOWN, // 1F97B
7880 COMMON, // 1F97C..1F9A2
7881 UNKNOWN, // 1F9A3..1F9AF
7882 COMMON, // 1F9B0..1F9B9
7883 UNKNOWN, // 1F9BA..1F9BF
7884 COMMON, // 1F9C0..1F9C2
7885 UNKNOWN, // 1F9C3..1F9CF
7886 COMMON, // 1F9D0..1F9FF
7887 UNKNOWN, // 1FA00..1FA5F
7888 COMMON, // 1FA60..1FA6D
7889 UNKNOWN, // 1FA6E..1FFFF
7890 HAN, // 20000..2A6D6
7891 UNKNOWN, // 2A6D7..2A6FF
7892 HAN, // 2A700..2B734
7893 UNKNOWN, // 2B735..2B73F
7894 HAN, // 2B740..2B81D
7895 UNKNOWN, // 2B81E..2B81F
7896 HAN, // 2B820..2CEA1
7897 UNKNOWN, // 2CEA2..2CEAF
7898 HAN, // 2CEB0..2EBE0
7899 UNKNOWN, // 2EBE1..2F7FF
7900 HAN, // 2F800..2FA1D
7901 UNKNOWN, // 2FA1E..E0000
7902 COMMON, // E0001
7903 UNKNOWN, // E0002..E001F
7904 COMMON, // E0020..E007F
7905 UNKNOWN, // E0080..E00FF
7906 INHERITED, // E0100..E01EF
7907 UNKNOWN // E01F0..10FFFF
7908 };
7909
7910 private static HashMap<String, Character.UnicodeScript> aliases;
7911 static {
7912 aliases = new HashMap<>((int)(149 / 0.75f + 1.0f));
7913 aliases.put("ADLM", ADLAM);
7914 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
7915 aliases.put("AHOM", AHOM);
7916 aliases.put("ARAB", ARABIC);
7917 aliases.put("ARMI", IMPERIAL_ARAMAIC);
7918 aliases.put("ARMN", ARMENIAN);
7919 aliases.put("AVST", AVESTAN);
7920 aliases.put("BALI", BALINESE);
7921 aliases.put("BAMU", BAMUM);
7922 aliases.put("BASS", BASSA_VAH);
7923 aliases.put("BATK", BATAK);
7924 aliases.put("BENG", BENGALI);
7925 aliases.put("BHKS", BHAIKSUKI);
7926 aliases.put("BOPO", BOPOMOFO);
7927 aliases.put("BRAH", BRAHMI);
7928 aliases.put("BRAI", BRAILLE);
7929 aliases.put("BUGI", BUGINESE);
7930 aliases.put("BUHD", BUHID);
7931 aliases.put("CAKM", CHAKMA);
7932 aliases.put("CANS", CANADIAN_ABORIGINAL);
7933 aliases.put("CARI", CARIAN);
7934 aliases.put("CHAM", CHAM);
7935 aliases.put("CHER", CHEROKEE);
7936 aliases.put("COPT", COPTIC);
7937 aliases.put("CPRT", CYPRIOT);
7938 aliases.put("CYRL", CYRILLIC);
7939 aliases.put("DEVA", DEVANAGARI);
7940 aliases.put("DOGR", DOGRA);
7941 aliases.put("DSRT", DESERET);
7942 aliases.put("DUPL", DUPLOYAN);
7943 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
7944 aliases.put("ELBA", ELBASAN);
7945 aliases.put("ETHI", ETHIOPIC);
7946 aliases.put("GEOR", GEORGIAN);
7947 aliases.put("GLAG", GLAGOLITIC);
7948 aliases.put("GONM", MASARAM_GONDI);
7949 aliases.put("GOTH", GOTHIC);
7950 aliases.put("GONG", GUNJALA_GONDI);
7951 aliases.put("GRAN", GRANTHA);
7952 aliases.put("GREK", GREEK);
7953 aliases.put("GUJR", GUJARATI);
7954 aliases.put("GURU", GURMUKHI);
7955 aliases.put("HANG", HANGUL);
7956 aliases.put("HANI", HAN);
7957 aliases.put("HANO", HANUNOO);
7958 aliases.put("HATR", HATRAN);
7959 aliases.put("HEBR", HEBREW);
7960 aliases.put("HIRA", HIRAGANA);
7961 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
7962 aliases.put("HMNG", PAHAWH_HMONG);
7963 // it appears we don't have the KATAKANA_OR_HIRAGANA
7964 //aliases.put("HRKT", KATAKANA_OR_HIRAGANA);
7965 aliases.put("HUNG", OLD_HUNGARIAN);
7966 aliases.put("ITAL", OLD_ITALIC);
7967 aliases.put("JAVA", JAVANESE);
7968 aliases.put("KALI", KAYAH_LI);
7969 aliases.put("KANA", KATAKANA);
7970 aliases.put("KHAR", KHAROSHTHI);
7971 aliases.put("KHMR", KHMER);
7972 aliases.put("KHOJ", KHOJKI);
7973 aliases.put("KNDA", KANNADA);
7974 aliases.put("KTHI", KAITHI);
7975 aliases.put("LANA", TAI_THAM);
7976 aliases.put("LAOO", LAO);
7977 aliases.put("LATN", LATIN);
7978 aliases.put("LEPC", LEPCHA);
7979 aliases.put("LIMB", LIMBU);
7980 aliases.put("LINA", LINEAR_A);
7981 aliases.put("LINB", LINEAR_B);
7982 aliases.put("LISU", LISU);
7983 aliases.put("LYCI", LYCIAN);
7984 aliases.put("LYDI", LYDIAN);
7985 aliases.put("MAHJ", MAHAJANI);
7986 aliases.put("MAKA", MAKASAR);
7987 aliases.put("MARC", MARCHEN);
7988 aliases.put("MAND", MANDAIC);
7989 aliases.put("MANI", MANICHAEAN);
7990 aliases.put("MEDF", MEDEFAIDRIN);
7991 aliases.put("MEND", MENDE_KIKAKUI);
7992 aliases.put("MERC", MEROITIC_CURSIVE);
7993 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
7994 aliases.put("MLYM", MALAYALAM);
7995 aliases.put("MODI", MODI);
7996 aliases.put("MONG", MONGOLIAN);
7997 aliases.put("MROO", MRO);
7998 aliases.put("MTEI", MEETEI_MAYEK);
7999 aliases.put("MULT", MULTANI);
8000 aliases.put("MYMR", MYANMAR);
8001 aliases.put("NARB", OLD_NORTH_ARABIAN);
8002 aliases.put("NBAT", NABATAEAN);
8003 aliases.put("NEWA", NEWA);
8004 aliases.put("NKOO", NKO);
8005 aliases.put("NSHU", NUSHU);
8006 aliases.put("OGAM", OGHAM);
8007 aliases.put("OLCK", OL_CHIKI);
8008 aliases.put("ORKH", OLD_TURKIC);
8009 aliases.put("ORYA", ORIYA);
8010 aliases.put("OSGE", OSAGE);
8011 aliases.put("OSMA", OSMANYA);
8012 aliases.put("PALM", PALMYRENE);
8013 aliases.put("PAUC", PAU_CIN_HAU);
8014 aliases.put("PERM", OLD_PERMIC);
8015 aliases.put("PHAG", PHAGS_PA);
8016 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
8017 aliases.put("PHLP", PSALTER_PAHLAVI);
8018 aliases.put("PHNX", PHOENICIAN);
8019 aliases.put("PLRD", MIAO);
8020 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
8021 aliases.put("RJNG", REJANG);
8022 aliases.put("ROHG", HANIFI_ROHINGYA);
8023 aliases.put("RUNR", RUNIC);
8024 aliases.put("SAMR", SAMARITAN);
8025 aliases.put("SARB", OLD_SOUTH_ARABIAN);
8026 aliases.put("SAUR", SAURASHTRA);
8027 aliases.put("SGNW", SIGNWRITING);
8028 aliases.put("SHAW", SHAVIAN);
8029 aliases.put("SHRD", SHARADA);
8030 aliases.put("SIDD", SIDDHAM);
8031 aliases.put("SIND", KHUDAWADI);
8032 aliases.put("SINH", SINHALA);
8033 aliases.put("SOGD", SOGDIAN);
8034 aliases.put("SOGO", OLD_SOGDIAN);
8035 aliases.put("SORA", SORA_SOMPENG);
8036 aliases.put("SOYO", SOYOMBO);
8037 aliases.put("SUND", SUNDANESE);
8038 aliases.put("SYLO", SYLOTI_NAGRI);
8039 aliases.put("SYRC", SYRIAC);
8040 aliases.put("TAGB", TAGBANWA);
8041 aliases.put("TAKR", TAKRI);
8042 aliases.put("TALE", TAI_LE);
8043 aliases.put("TALU", NEW_TAI_LUE);
8044 aliases.put("TAML", TAMIL);
8045 aliases.put("TANG", TANGUT);
8046 aliases.put("TAVT", TAI_VIET);
8047 aliases.put("TELU", TELUGU);
8048 aliases.put("TFNG", TIFINAGH);
8049 aliases.put("TGLG", TAGALOG);
8050 aliases.put("THAA", THAANA);
8051 aliases.put("THAI", THAI);
8052 aliases.put("TIBT", TIBETAN);
8053 aliases.put("TIRH", TIRHUTA);
8054 aliases.put("UGAR", UGARITIC);
8055 aliases.put("VAII", VAI);
8056 aliases.put("WARA", WARANG_CITI);
8057 aliases.put("XPEO", OLD_PERSIAN);
8058 aliases.put("XSUX", CUNEIFORM);
8059 aliases.put("YIII", YI);
8060 aliases.put("ZANB", ZANABAZAR_SQUARE);
8061 aliases.put("ZINH", INHERITED);
8062 aliases.put("ZYYY", COMMON);
8063 aliases.put("ZZZZ", UNKNOWN);
8064 }
8065
8066 /**
8067 * Returns the enum constant representing the Unicode script of which
8068 * the given character (Unicode code point) is assigned to.
8069 *
8070 * @param codePoint the character (Unicode code point) in question.
8071 * @return The {@code UnicodeScript} constant representing the
8072 * Unicode script of which this character is assigned to.
8073 *
8074 * @throws IllegalArgumentException if the specified
8075 * {@code codePoint} is an invalid Unicode code point.
8076 * @see Character#isValidCodePoint(int)
8077 *
8078 */
8079 public static UnicodeScript of(int codePoint) {
8080 if (!isValidCodePoint(codePoint))
8081 throw new IllegalArgumentException(
8082 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8083 int type = getType(codePoint);
8084 // leave SURROGATE and PRIVATE_USE for table lookup
8085 if (type == UNASSIGNED)
8086 return UNKNOWN;
8087 int index = Arrays.binarySearch(scriptStarts, codePoint);
8088 if (index < 0)
8089 index = -index - 2;
8090 return scripts[index];
8091 }
8092
8093 /**
8094 * Returns the UnicodeScript constant with the given Unicode script
8095 * name or the script name alias. Script names and their aliases are
8096 * determined by The Unicode Standard. The files {@code Scripts<version>.txt}
8097 * and {@code PropertyValueAliases<version>.txt} define script names
8098 * and the script name aliases for a particular version of the
8099 * standard. The {@link Character} class specifies the version of
8100 * the standard that it supports.
8101 * <p>
8102 * Character case is ignored for all of the valid script names.
8103 * The en_US locale's case mapping rules are used to provide
8104 * case-insensitive string comparisons for script name validation.
8105 *
8106 * @param scriptName A {@code UnicodeScript} name.
8107 * @return The {@code UnicodeScript} constant identified
8108 * by {@code scriptName}
8109 * @throws IllegalArgumentException if {@code scriptName} is an
8110 * invalid name
8111 * @throws NullPointerException if {@code scriptName} is null
8112 */
8113 public static final UnicodeScript forName(String scriptName) {
8114 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
8115 //.replace(' ', '_'));
8116 UnicodeScript sc = aliases.get(scriptName);
8117 if (sc != null)
8118 return sc;
8119 return valueOf(scriptName);
8120 }
8121 }
8122
8123 /**
8124 * The value of the {@code Character}.
8125 *
8126 * @serial
8127 */
8128 private final char value;
8129
8130 /** use serialVersionUID from JDK 1.0.2 for interoperability */
8131 private static final long serialVersionUID = 3786198910865385080L;
8132
8133 /**
8134 * Constructs a newly allocated {@code Character} object that
8135 * represents the specified {@code char} value.
8136 *
8137 * @param value the value to be represented by the
8138 * {@code Character} object.
8139 *
8140 * @deprecated
8141 * It is rarely appropriate to use this constructor. The static factory
8142 * {@link #valueOf(char)} is generally a better choice, as it is
8143 * likely to yield significantly better space and time performance.
8144 */
8145 @Deprecated(since="9")
8146 public Character(char value) {
8147 this.value = value;
8148 }
8149
8150 private static class CharacterCache {
8151 private CharacterCache(){}
8152
8153 static final Character[] cache;
8154 static Character[] archivedCache;
8155
8156 static {
8157 int size = 127 + 1;
8158
8159 // Load and use the archived cache if it exists
8160 VM.initializeFromArchive(CharacterCache.class);
8161 if (archivedCache == null || archivedCache.length != size) {
8162 Character[] c = new Character[size];
8163 for (int i = 0; i < size; i++) {
8164 c[i] = new Character((char) i);
8165 }
8166 archivedCache = c;
8167 }
8168 cache = archivedCache;
8169 }
8170 }
8171
8172 /**
8173 * Returns a {@code Character} instance representing the specified
8174 * {@code char} value.
8175 * If a new {@code Character} instance is not required, this method
8176 * should generally be used in preference to the constructor
8177 * {@link #Character(char)}, as this method is likely to yield
8178 * significantly better space and time performance by caching
8179 * frequently requested values.
8180 *
8181 * This method will always cache values in the range {@code
8182 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
8183 * cache other values outside of this range.
8184 *
8185 * @param c a char value.
8186 * @return a {@code Character} instance representing {@code c}.
8187 * @since 1.5
8188 */
8189 @HotSpotIntrinsicCandidate
8190 public static Character valueOf(char c) {
8191 if (c <= 127) { // must cache
8192 return CharacterCache.cache[(int)c];
8193 }
8194 return new Character(c);
8195 }
8196
8197 /**
8198 * Returns the value of this {@code Character} object.
8199 * @return the primitive {@code char} value represented by
8200 * this object.
8201 */
8202 @HotSpotIntrinsicCandidate
8203 public char charValue() {
8204 return value;
8205 }
8206
8207 /**
8208 * Returns a hash code for this {@code Character}; equal to the result
8209 * of invoking {@code charValue()}.
8210 *
8211 * @return a hash code value for this {@code Character}
8212 */
8213 @Override
8214 public int hashCode() {
8215 return Character.hashCode(value);
8216 }
8217
8218 /**
8219 * Returns a hash code for a {@code char} value; compatible with
8220 * {@code Character.hashCode()}.
8221 *
8222 * @since 1.8
8223 *
8224 * @param value The {@code char} for which to return a hash code.
8225 * @return a hash code value for a {@code char} value.
8226 */
8227 public static int hashCode(char value) {
8228 return (int)value;
8229 }
8230
8231 /**
8232 * Compares this object against the specified object.
8233 * The result is {@code true} if and only if the argument is not
8234 * {@code null} and is a {@code Character} object that
8235 * represents the same {@code char} value as this object.
8236 *
8237 * @param obj the object to compare with.
8238 * @return {@code true} if the objects are the same;
8239 * {@code false} otherwise.
8240 */
8241 public boolean equals(Object obj) {
8242 if (obj instanceof Character) {
8243 return value == ((Character)obj).charValue();
8244 }
8245 return false;
8246 }
8247
8248 /**
8249 * Returns a {@code String} object representing this
8250 * {@code Character}'s value. The result is a string of
8251 * length 1 whose sole component is the primitive
8252 * {@code char} value represented by this
8253 * {@code Character} object.
8254 *
8255 * @return a string representation of this object.
8256 */
8257 public String toString() {
8258 char buf[] = {value};
8259 return String.valueOf(buf);
8260 }
8261
8262 /**
8263 * Returns a {@code String} object representing the
8264 * specified {@code char}. The result is a string of length
8265 * 1 consisting solely of the specified {@code char}.
8266 *
8267 * @apiNote This method cannot handle <a
8268 * href="#supplementary"> supplementary characters</a>. To support
8269 * all Unicode characters, including supplementary characters, use
8270 * the {@link #toString(int)} method.
8271 *
8272 * @param c the {@code char} to be converted
8273 * @return the string representation of the specified {@code char}
8274 * @since 1.4
8275 */
8276 public static String toString(char c) {
8277 return String.valueOf(c);
8278 }
8279
8280 /**
8281 * Returns a {@code String} object representing the
8282 * specified character (Unicode code point). The result is a string of
8283 * length 1 or 2, consisting solely of the specified {@code codePoint}.
8284 *
8285 * @param codePoint the {@code codePoint} to be converted
8286 * @return the string representation of the specified {@code codePoint}
8287 * @throws IllegalArgumentException if the specified
8288 * {@code codePoint} is not a {@linkplain #isValidCodePoint
8289 * valid Unicode code point}.
8290 * @since 11
8291 */
8292 public static String toString(int codePoint) {
8293 return String.valueOfCodePoint(codePoint);
8294 }
8295
8296 /**
8297 * Determines whether the specified code point is a valid
8298 * <a href="http://www.unicode.org/glossary/#code_point">
8299 * Unicode code point value</a>.
8300 *
8301 * @param codePoint the Unicode code point to be tested
8302 * @return {@code true} if the specified code point value is between
8303 * {@link #MIN_CODE_POINT} and
8304 * {@link #MAX_CODE_POINT} inclusive;
8305 * {@code false} otherwise.
8306 * @since 1.5
8307 */
8308 public static boolean isValidCodePoint(int codePoint) {
8309 // Optimized form of:
8310 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
8311 int plane = codePoint >>> 16;
8312 return plane < ((MAX_CODE_POINT + 1) >>> 16);
8313 }
8314
8315 /**
8316 * Determines whether the specified character (Unicode code point)
8317 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
8318 * Such code points can be represented using a single {@code char}.
8319 *
8320 * @param codePoint the character (Unicode code point) to be tested
8321 * @return {@code true} if the specified code point is between
8322 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
8323 * {@code false} otherwise.
8324 * @since 1.7
8325 */
8326 public static boolean isBmpCodePoint(int codePoint) {
8327 return codePoint >>> 16 == 0;
8328 // Optimized form of:
8329 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
8330 // We consistently use logical shift (>>>) to facilitate
8331 // additional runtime optimizations.
8332 }
8333
8334 /**
8335 * Determines whether the specified character (Unicode code point)
8336 * is in the <a href="#supplementary">supplementary character</a> range.
8337 *
8338 * @param codePoint the character (Unicode code point) to be tested
8339 * @return {@code true} if the specified code point is between
8340 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
8341 * {@link #MAX_CODE_POINT} inclusive;
8342 * {@code false} otherwise.
8343 * @since 1.5
8344 */
8345 public static boolean isSupplementaryCodePoint(int codePoint) {
8346 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
8347 && codePoint < MAX_CODE_POINT + 1;
8348 }
8349
8350 /**
8351 * Determines if the given {@code char} value is a
8352 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
8353 * Unicode high-surrogate code unit</a>
8354 * (also known as <i>leading-surrogate code unit</i>).
8355 *
8356 * <p>Such values do not represent characters by themselves,
8357 * but are used in the representation of
8358 * <a href="#supplementary">supplementary characters</a>
8359 * in the UTF-16 encoding.
8360 *
8361 * @param ch the {@code char} value to be tested.
8362 * @return {@code true} if the {@code char} value is between
8363 * {@link #MIN_HIGH_SURROGATE} and
8364 * {@link #MAX_HIGH_SURROGATE} inclusive;
8365 * {@code false} otherwise.
8366 * @see Character#isLowSurrogate(char)
8367 * @see Character.UnicodeBlock#of(int)
8368 * @since 1.5
8369 */
8370 public static boolean isHighSurrogate(char ch) {
8371 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
8372 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
8373 }
8374
8375 /**
8376 * Determines if the given {@code char} value is a
8377 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
8378 * Unicode low-surrogate code unit</a>
8379 * (also known as <i>trailing-surrogate code unit</i>).
8380 *
8381 * <p>Such values do not represent characters by themselves,
8382 * but are used in the representation of
8383 * <a href="#supplementary">supplementary characters</a>
8384 * in the UTF-16 encoding.
8385 *
8386 * @param ch the {@code char} value to be tested.
8387 * @return {@code true} if the {@code char} value is between
8388 * {@link #MIN_LOW_SURROGATE} and
8389 * {@link #MAX_LOW_SURROGATE} inclusive;
8390 * {@code false} otherwise.
8391 * @see Character#isHighSurrogate(char)
8392 * @since 1.5
8393 */
8394 public static boolean isLowSurrogate(char ch) {
8395 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
8396 }
8397
8398 /**
8399 * Determines if the given {@code char} value is a Unicode
8400 * <i>surrogate code unit</i>.
8401 *
8402 * <p>Such values do not represent characters by themselves,
8403 * but are used in the representation of
8404 * <a href="#supplementary">supplementary characters</a>
8405 * in the UTF-16 encoding.
8406 *
8407 * <p>A char value is a surrogate code unit if and only if it is either
8408 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
8409 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
8410 *
8411 * @param ch the {@code char} value to be tested.
8412 * @return {@code true} if the {@code char} value is between
8413 * {@link #MIN_SURROGATE} and
8414 * {@link #MAX_SURROGATE} inclusive;
8415 * {@code false} otherwise.
8416 * @since 1.7
8417 */
8418 public static boolean isSurrogate(char ch) {
8419 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
8420 }
8421
8422 /**
8423 * Determines whether the specified pair of {@code char}
8424 * values is a valid
8425 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8426 * Unicode surrogate pair</a>.
8427
8428 * <p>This method is equivalent to the expression:
8429 * <blockquote><pre>{@code
8430 * isHighSurrogate(high) && isLowSurrogate(low)
8431 * }</pre></blockquote>
8432 *
8433 * @param high the high-surrogate code value to be tested
8434 * @param low the low-surrogate code value to be tested
8435 * @return {@code true} if the specified high and
8436 * low-surrogate code values represent a valid surrogate pair;
8437 * {@code false} otherwise.
8438 * @since 1.5
8439 */
8440 public static boolean isSurrogatePair(char high, char low) {
8441 return isHighSurrogate(high) && isLowSurrogate(low);
8442 }
8443
8444 /**
8445 * Determines the number of {@code char} values needed to
8446 * represent the specified character (Unicode code point). If the
8447 * specified character is equal to or greater than 0x10000, then
8448 * the method returns 2. Otherwise, the method returns 1.
8449 *
8450 * <p>This method doesn't validate the specified character to be a
8451 * valid Unicode code point. The caller must validate the
8452 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
8453 * if necessary.
8454 *
8455 * @param codePoint the character (Unicode code point) to be tested.
8456 * @return 2 if the character is a valid supplementary character; 1 otherwise.
8457 * @see Character#isSupplementaryCodePoint(int)
8458 * @since 1.5
8459 */
8460 public static int charCount(int codePoint) {
8461 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
8462 }
8463
8464 /**
8465 * Converts the specified surrogate pair to its supplementary code
8466 * point value. This method does not validate the specified
8467 * surrogate pair. The caller must validate it using {@link
8468 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
8469 *
8470 * @param high the high-surrogate code unit
8471 * @param low the low-surrogate code unit
8472 * @return the supplementary code point composed from the
8473 * specified surrogate pair.
8474 * @since 1.5
8475 */
8476 public static int toCodePoint(char high, char low) {
8477 // Optimized form of:
8478 // return ((high - MIN_HIGH_SURROGATE) << 10)
8479 // + (low - MIN_LOW_SURROGATE)
8480 // + MIN_SUPPLEMENTARY_CODE_POINT;
8481 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
8482 - (MIN_HIGH_SURROGATE << 10)
8483 - MIN_LOW_SURROGATE);
8484 }
8485
8486 /**
8487 * Returns the code point at the given index of the
8488 * {@code CharSequence}. If the {@code char} value at
8489 * the given index in the {@code CharSequence} is in the
8490 * high-surrogate range, the following index is less than the
8491 * length of the {@code CharSequence}, and the
8492 * {@code char} value at the following index is in the
8493 * low-surrogate range, then the supplementary code point
8494 * corresponding to this surrogate pair is returned. Otherwise,
8495 * the {@code char} value at the given index is returned.
8496 *
8497 * @param seq a sequence of {@code char} values (Unicode code
8498 * units)
8499 * @param index the index to the {@code char} values (Unicode
8500 * code units) in {@code seq} to be converted
8501 * @return the Unicode code point at the given index
8502 * @throws NullPointerException if {@code seq} is null.
8503 * @throws IndexOutOfBoundsException if the value
8504 * {@code index} is negative or not less than
8505 * {@link CharSequence#length() seq.length()}.
8506 * @since 1.5
8507 */
8508 public static int codePointAt(CharSequence seq, int index) {
8509 char c1 = seq.charAt(index);
8510 if (isHighSurrogate(c1) && ++index < seq.length()) {
8511 char c2 = seq.charAt(index);
8512 if (isLowSurrogate(c2)) {
8513 return toCodePoint(c1, c2);
8514 }
8515 }
8516 return c1;
8517 }
8518
8519 /**
8520 * Returns the code point at the given index of the
8521 * {@code char} array. If the {@code char} value at
8522 * the given index in the {@code char} array is in the
8523 * high-surrogate range, the following index is less than the
8524 * length of the {@code char} array, and the
8525 * {@code char} value at the following index is in the
8526 * low-surrogate range, then the supplementary code point
8527 * corresponding to this surrogate pair is returned. Otherwise,
8528 * the {@code char} value at the given index is returned.
8529 *
8530 * @param a the {@code char} array
8531 * @param index the index to the {@code char} values (Unicode
8532 * code units) in the {@code char} array to be converted
8533 * @return the Unicode code point at the given index
8534 * @throws NullPointerException if {@code a} is null.
8535 * @throws IndexOutOfBoundsException if the value
8536 * {@code index} is negative or not less than
8537 * the length of the {@code char} array.
8538 * @since 1.5
8539 */
8540 public static int codePointAt(char[] a, int index) {
8541 return codePointAtImpl(a, index, a.length);
8542 }
8543
8544 /**
8545 * Returns the code point at the given index of the
8546 * {@code char} array, where only array elements with
8547 * {@code index} less than {@code limit} can be used. If
8548 * the {@code char} value at the given index in the
8549 * {@code char} array is in the high-surrogate range, the
8550 * following index is less than the {@code limit}, and the
8551 * {@code char} value at the following index is in the
8552 * low-surrogate range, then the supplementary code point
8553 * corresponding to this surrogate pair is returned. Otherwise,
8554 * the {@code char} value at the given index is returned.
8555 *
8556 * @param a the {@code char} array
8557 * @param index the index to the {@code char} values (Unicode
8558 * code units) in the {@code char} array to be converted
8559 * @param limit the index after the last array element that
8560 * can be used in the {@code char} array
8561 * @return the Unicode code point at the given index
8562 * @throws NullPointerException if {@code a} is null.
8563 * @throws IndexOutOfBoundsException if the {@code index}
8564 * argument is negative or not less than the {@code limit}
8565 * argument, or if the {@code limit} argument is negative or
8566 * greater than the length of the {@code char} array.
8567 * @since 1.5
8568 */
8569 public static int codePointAt(char[] a, int index, int limit) {
8570 if (index >= limit || limit < 0 || limit > a.length) {
8571 throw new IndexOutOfBoundsException();
8572 }
8573 return codePointAtImpl(a, index, limit);
8574 }
8575
8576 // throws ArrayIndexOutOfBoundsException if index out of bounds
8577 static int codePointAtImpl(char[] a, int index, int limit) {
8578 char c1 = a[index];
8579 if (isHighSurrogate(c1) && ++index < limit) {
8580 char c2 = a[index];
8581 if (isLowSurrogate(c2)) {
8582 return toCodePoint(c1, c2);
8583 }
8584 }
8585 return c1;
8586 }
8587
8588 /**
8589 * Returns the code point preceding the given index of the
8590 * {@code CharSequence}. If the {@code char} value at
8591 * {@code (index - 1)} in the {@code CharSequence} is in
8592 * the low-surrogate range, {@code (index - 2)} is not
8593 * negative, and the {@code char} value at {@code (index - 2)}
8594 * in the {@code CharSequence} is in the
8595 * high-surrogate range, then the supplementary code point
8596 * corresponding to this surrogate pair is returned. Otherwise,
8597 * the {@code char} value at {@code (index - 1)} is
8598 * returned.
8599 *
8600 * @param seq the {@code CharSequence} instance
8601 * @param index the index following the code point that should be returned
8602 * @return the Unicode code point value before the given index.
8603 * @throws NullPointerException if {@code seq} is null.
8604 * @throws IndexOutOfBoundsException if the {@code index}
8605 * argument is less than 1 or greater than {@link
8606 * CharSequence#length() seq.length()}.
8607 * @since 1.5
8608 */
8609 public static int codePointBefore(CharSequence seq, int index) {
8610 char c2 = seq.charAt(--index);
8611 if (isLowSurrogate(c2) && index > 0) {
8612 char c1 = seq.charAt(--index);
8613 if (isHighSurrogate(c1)) {
8614 return toCodePoint(c1, c2);
8615 }
8616 }
8617 return c2;
8618 }
8619
8620 /**
8621 * Returns the code point preceding the given index of the
8622 * {@code char} array. If the {@code char} value at
8623 * {@code (index - 1)} in the {@code char} array is in
8624 * the low-surrogate range, {@code (index - 2)} is not
8625 * negative, and the {@code char} value at {@code (index - 2)}
8626 * in the {@code char} array is in the
8627 * high-surrogate range, then the supplementary code point
8628 * corresponding to this surrogate pair is returned. Otherwise,
8629 * the {@code char} value at {@code (index - 1)} is
8630 * returned.
8631 *
8632 * @param a the {@code char} array
8633 * @param index the index following the code point that should be returned
8634 * @return the Unicode code point value before the given index.
8635 * @throws NullPointerException if {@code a} is null.
8636 * @throws IndexOutOfBoundsException if the {@code index}
8637 * argument is less than 1 or greater than the length of the
8638 * {@code char} array
8639 * @since 1.5
8640 */
8641 public static int codePointBefore(char[] a, int index) {
8642 return codePointBeforeImpl(a, index, 0);
8643 }
8644
8645 /**
8646 * Returns the code point preceding the given index of the
8647 * {@code char} array, where only array elements with
8648 * {@code index} greater than or equal to {@code start}
8649 * can be used. If the {@code char} value at {@code (index - 1)}
8650 * in the {@code char} array is in the
8651 * low-surrogate range, {@code (index - 2)} is not less than
8652 * {@code start}, and the {@code char} value at
8653 * {@code (index - 2)} in the {@code char} array is in
8654 * the high-surrogate range, then the supplementary code point
8655 * corresponding to this surrogate pair is returned. Otherwise,
8656 * the {@code char} value at {@code (index - 1)} is
8657 * returned.
8658 *
8659 * @param a the {@code char} array
8660 * @param index the index following the code point that should be returned
8661 * @param start the index of the first array element in the
8662 * {@code char} array
8663 * @return the Unicode code point value before the given index.
8664 * @throws NullPointerException if {@code a} is null.
8665 * @throws IndexOutOfBoundsException if the {@code index}
8666 * argument is not greater than the {@code start} argument or
8667 * is greater than the length of the {@code char} array, or
8668 * if the {@code start} argument is negative or not less than
8669 * the length of the {@code char} array.
8670 * @since 1.5
8671 */
8672 public static int codePointBefore(char[] a, int index, int start) {
8673 if (index <= start || start < 0 || start >= a.length) {
8674 throw new IndexOutOfBoundsException();
8675 }
8676 return codePointBeforeImpl(a, index, start);
8677 }
8678
8679 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
8680 static int codePointBeforeImpl(char[] a, int index, int start) {
8681 char c2 = a[--index];
8682 if (isLowSurrogate(c2) && index > start) {
8683 char c1 = a[--index];
8684 if (isHighSurrogate(c1)) {
8685 return toCodePoint(c1, c2);
8686 }
8687 }
8688 return c2;
8689 }
8690
8691 /**
8692 * Returns the leading surrogate (a
8693 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
8694 * high surrogate code unit</a>) of the
8695 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8696 * surrogate pair</a>
8697 * representing the specified supplementary character (Unicode
8698 * code point) in the UTF-16 encoding. If the specified character
8699 * is not a
8700 * <a href="Character.html#supplementary">supplementary character</a>,
8701 * an unspecified {@code char} is returned.
8702 *
8703 * <p>If
8704 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
8705 * is {@code true}, then
8706 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
8707 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
8708 * are also always {@code true}.
8709 *
8710 * @param codePoint a supplementary character (Unicode code point)
8711 * @return the leading surrogate code unit used to represent the
8712 * character in the UTF-16 encoding
8713 * @since 1.7
8714 */
8715 public static char highSurrogate(int codePoint) {
8716 return (char) ((codePoint >>> 10)
8717 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
8718 }
8719
8720 /**
8721 * Returns the trailing surrogate (a
8722 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
8723 * low surrogate code unit</a>) of the
8724 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8725 * surrogate pair</a>
8726 * representing the specified supplementary character (Unicode
8727 * code point) in the UTF-16 encoding. If the specified character
8728 * is not a
8729 * <a href="Character.html#supplementary">supplementary character</a>,
8730 * an unspecified {@code char} is returned.
8731 *
8732 * <p>If
8733 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
8734 * is {@code true}, then
8735 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
8736 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
8737 * are also always {@code true}.
8738 *
8739 * @param codePoint a supplementary character (Unicode code point)
8740 * @return the trailing surrogate code unit used to represent the
8741 * character in the UTF-16 encoding
8742 * @since 1.7
8743 */
8744 public static char lowSurrogate(int codePoint) {
8745 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
8746 }
8747
8748 /**
8749 * Converts the specified character (Unicode code point) to its
8750 * UTF-16 representation. If the specified code point is a BMP
8751 * (Basic Multilingual Plane or Plane 0) value, the same value is
8752 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
8753 * specified code point is a supplementary character, its
8754 * surrogate values are stored in {@code dst[dstIndex]}
8755 * (high-surrogate) and {@code dst[dstIndex+1]}
8756 * (low-surrogate), and 2 is returned.
8757 *
8758 * @param codePoint the character (Unicode code point) to be converted.
8759 * @param dst an array of {@code char} in which the
8760 * {@code codePoint}'s UTF-16 value is stored.
8761 * @param dstIndex the start index into the {@code dst}
8762 * array where the converted value is stored.
8763 * @return 1 if the code point is a BMP code point, 2 if the
8764 * code point is a supplementary code point.
8765 * @throws IllegalArgumentException if the specified
8766 * {@code codePoint} is not a valid Unicode code point.
8767 * @throws NullPointerException if the specified {@code dst} is null.
8768 * @throws IndexOutOfBoundsException if {@code dstIndex}
8769 * is negative or not less than {@code dst.length}, or if
8770 * {@code dst} at {@code dstIndex} doesn't have enough
8771 * array element(s) to store the resulting {@code char}
8772 * value(s). (If {@code dstIndex} is equal to
8773 * {@code dst.length-1} and the specified
8774 * {@code codePoint} is a supplementary character, the
8775 * high-surrogate value is not stored in
8776 * {@code dst[dstIndex]}.)
8777 * @since 1.5
8778 */
8779 public static int toChars(int codePoint, char[] dst, int dstIndex) {
8780 if (isBmpCodePoint(codePoint)) {
8781 dst[dstIndex] = (char) codePoint;
8782 return 1;
8783 } else if (isValidCodePoint(codePoint)) {
8784 toSurrogates(codePoint, dst, dstIndex);
8785 return 2;
8786 } else {
8787 throw new IllegalArgumentException(
8788 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8789 }
8790 }
8791
8792 /**
8793 * Converts the specified character (Unicode code point) to its
8794 * UTF-16 representation stored in a {@code char} array. If
8795 * the specified code point is a BMP (Basic Multilingual Plane or
8796 * Plane 0) value, the resulting {@code char} array has
8797 * the same value as {@code codePoint}. If the specified code
8798 * point is a supplementary code point, the resulting
8799 * {@code char} array has the corresponding surrogate pair.
8800 *
8801 * @param codePoint a Unicode code point
8802 * @return a {@code char} array having
8803 * {@code codePoint}'s UTF-16 representation.
8804 * @throws IllegalArgumentException if the specified
8805 * {@code codePoint} is not a valid Unicode code point.
8806 * @since 1.5
8807 */
8808 public static char[] toChars(int codePoint) {
8809 if (isBmpCodePoint(codePoint)) {
8810 return new char[] { (char) codePoint };
8811 } else if (isValidCodePoint(codePoint)) {
8812 char[] result = new char[2];
8813 toSurrogates(codePoint, result, 0);
8814 return result;
8815 } else {
8816 throw new IllegalArgumentException(
8817 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8818 }
8819 }
8820
8821 static void toSurrogates(int codePoint, char[] dst, int index) {
8822 // We write elements "backwards" to guarantee all-or-nothing
8823 dst[index+1] = lowSurrogate(codePoint);
8824 dst[index] = highSurrogate(codePoint);
8825 }
8826
8827 /**
8828 * Returns the number of Unicode code points in the text range of
8829 * the specified char sequence. The text range begins at the
8830 * specified {@code beginIndex} and extends to the
8831 * {@code char} at index {@code endIndex - 1}. Thus the
8832 * length (in {@code char}s) of the text range is
8833 * {@code endIndex-beginIndex}. Unpaired surrogates within
8834 * the text range count as one code point each.
8835 *
8836 * @param seq the char sequence
8837 * @param beginIndex the index to the first {@code char} of
8838 * the text range.
8839 * @param endIndex the index after the last {@code char} of
8840 * the text range.
8841 * @return the number of Unicode code points in the specified text
8842 * range
8843 * @throws NullPointerException if {@code seq} is null.
8844 * @throws IndexOutOfBoundsException if the
8845 * {@code beginIndex} is negative, or {@code endIndex}
8846 * is larger than the length of the given sequence, or
8847 * {@code beginIndex} is larger than {@code endIndex}.
8848 * @since 1.5
8849 */
8850 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
8851 int length = seq.length();
8852 if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) {
8853 throw new IndexOutOfBoundsException();
8854 }
8855 int n = endIndex - beginIndex;
8856 for (int i = beginIndex; i < endIndex; ) {
8857 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
8858 isLowSurrogate(seq.charAt(i))) {
8859 n--;
8860 i++;
8861 }
8862 }
8863 return n;
8864 }
8865
8866 /**
8867 * Returns the number of Unicode code points in a subarray of the
8868 * {@code char} array argument. The {@code offset}
8869 * argument is the index of the first {@code char} of the
8870 * subarray and the {@code count} argument specifies the
8871 * length of the subarray in {@code char}s. Unpaired
8872 * surrogates within the subarray count as one code point each.
8873 *
8874 * @param a the {@code char} array
8875 * @param offset the index of the first {@code char} in the
8876 * given {@code char} array
8877 * @param count the length of the subarray in {@code char}s
8878 * @return the number of Unicode code points in the specified subarray
8879 * @throws NullPointerException if {@code a} is null.
8880 * @throws IndexOutOfBoundsException if {@code offset} or
8881 * {@code count} is negative, or if {@code offset +
8882 * count} is larger than the length of the given array.
8883 * @since 1.5
8884 */
8885 public static int codePointCount(char[] a, int offset, int count) {
8886 if (count > a.length - offset || offset < 0 || count < 0) {
8887 throw new IndexOutOfBoundsException();
8888 }
8889 return codePointCountImpl(a, offset, count);
8890 }
8891
8892 static int codePointCountImpl(char[] a, int offset, int count) {
8893 int endIndex = offset + count;
8894 int n = count;
8895 for (int i = offset; i < endIndex; ) {
8896 if (isHighSurrogate(a[i++]) && i < endIndex &&
8897 isLowSurrogate(a[i])) {
8898 n--;
8899 i++;
8900 }
8901 }
8902 return n;
8903 }
8904
8905 /**
8906 * Returns the index within the given char sequence that is offset
8907 * from the given {@code index} by {@code codePointOffset}
8908 * code points. Unpaired surrogates within the text range given by
8909 * {@code index} and {@code codePointOffset} count as
8910 * one code point each.
8911 *
8912 * @param seq the char sequence
8913 * @param index the index to be offset
8914 * @param codePointOffset the offset in code points
8915 * @return the index within the char sequence
8916 * @throws NullPointerException if {@code seq} is null.
8917 * @throws IndexOutOfBoundsException if {@code index}
8918 * is negative or larger then the length of the char sequence,
8919 * or if {@code codePointOffset} is positive and the
8920 * subsequence starting with {@code index} has fewer than
8921 * {@code codePointOffset} code points, or if
8922 * {@code codePointOffset} is negative and the subsequence
8923 * before {@code index} has fewer than the absolute value
8924 * of {@code codePointOffset} code points.
8925 * @since 1.5
8926 */
8927 public static int offsetByCodePoints(CharSequence seq, int index,
8928 int codePointOffset) {
8929 int length = seq.length();
8930 if (index < 0 || index > length) {
8931 throw new IndexOutOfBoundsException();
8932 }
8933
8934 int x = index;
8935 if (codePointOffset >= 0) {
8936 int i;
8937 for (i = 0; x < length && i < codePointOffset; i++) {
8938 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
8939 isLowSurrogate(seq.charAt(x))) {
8940 x++;
8941 }
8942 }
8943 if (i < codePointOffset) {
8944 throw new IndexOutOfBoundsException();
8945 }
8946 } else {
8947 int i;
8948 for (i = codePointOffset; x > 0 && i < 0; i++) {
8949 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
8950 isHighSurrogate(seq.charAt(x-1))) {
8951 x--;
8952 }
8953 }
8954 if (i < 0) {
8955 throw new IndexOutOfBoundsException();
8956 }
8957 }
8958 return x;
8959 }
8960
8961 /**
8962 * Returns the index within the given {@code char} subarray
8963 * that is offset from the given {@code index} by
8964 * {@code codePointOffset} code points. The
8965 * {@code start} and {@code count} arguments specify a
8966 * subarray of the {@code char} array. Unpaired surrogates
8967 * within the text range given by {@code index} and
8968 * {@code codePointOffset} count as one code point each.
8969 *
8970 * @param a the {@code char} array
8971 * @param start the index of the first {@code char} of the
8972 * subarray
8973 * @param count the length of the subarray in {@code char}s
8974 * @param index the index to be offset
8975 * @param codePointOffset the offset in code points
8976 * @return the index within the subarray
8977 * @throws NullPointerException if {@code a} is null.
8978 * @throws IndexOutOfBoundsException
8979 * if {@code start} or {@code count} is negative,
8980 * or if {@code start + count} is larger than the length of
8981 * the given array,
8982 * or if {@code index} is less than {@code start} or
8983 * larger then {@code start + count},
8984 * or if {@code codePointOffset} is positive and the text range
8985 * starting with {@code index} and ending with {@code start + count - 1}
8986 * has fewer than {@code codePointOffset} code
8987 * points,
8988 * or if {@code codePointOffset} is negative and the text range
8989 * starting with {@code start} and ending with {@code index - 1}
8990 * has fewer than the absolute value of
8991 * {@code codePointOffset} code points.
8992 * @since 1.5
8993 */
8994 public static int offsetByCodePoints(char[] a, int start, int count,
8995 int index, int codePointOffset) {
8996 if (count > a.length-start || start < 0 || count < 0
8997 || index < start || index > start+count) {
8998 throw new IndexOutOfBoundsException();
8999 }
9000 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
9001 }
9002
9003 static int offsetByCodePointsImpl(char[]a, int start, int count,
9004 int index, int codePointOffset) {
9005 int x = index;
9006 if (codePointOffset >= 0) {
9007 int limit = start + count;
9008 int i;
9009 for (i = 0; x < limit && i < codePointOffset; i++) {
9010 if (isHighSurrogate(a[x++]) && x < limit &&
9011 isLowSurrogate(a[x])) {
9012 x++;
9013 }
9014 }
9015 if (i < codePointOffset) {
9016 throw new IndexOutOfBoundsException();
9017 }
9018 } else {
9019 int i;
9020 for (i = codePointOffset; x > start && i < 0; i++) {
9021 if (isLowSurrogate(a[--x]) && x > start &&
9022 isHighSurrogate(a[x-1])) {
9023 x--;
9024 }
9025 }
9026 if (i < 0) {
9027 throw new IndexOutOfBoundsException();
9028 }
9029 }
9030 return x;
9031 }
9032
9033 /**
9034 * Determines if the specified character is a lowercase character.
9035 * <p>
9036 * A character is lowercase if its general category type, provided
9037 * by {@code Character.getType(ch)}, is
9038 * {@code LOWERCASE_LETTER}, or it has contributory property
9039 * Other_Lowercase as defined by the Unicode Standard.
9040 * <p>
9041 * The following are examples of lowercase characters:
9042 * <blockquote><pre>
9043 * 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
9044 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9045 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9046 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9047 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9048 * </pre></blockquote>
9049 * <p> Many other Unicode characters are lowercase too.
9050 *
9051 * <p><b>Note:</b> This method cannot handle <a
9052 * href="#supplementary"> supplementary characters</a>. To support
9053 * all Unicode characters, including supplementary characters, use
9054 * the {@link #isLowerCase(int)} method.
9055 *
9056 * @param ch the character to be tested.
9057 * @return {@code true} if the character is lowercase;
9058 * {@code false} otherwise.
9059 * @see Character#isLowerCase(char)
9060 * @see Character#isTitleCase(char)
9061 * @see Character#toLowerCase(char)
9062 * @see Character#getType(char)
9063 */
9064 public static boolean isLowerCase(char ch) {
9065 return isLowerCase((int)ch);
9066 }
9067
9068 /**
9069 * Determines if the specified character (Unicode code point) is a
9070 * lowercase character.
9071 * <p>
9072 * A character is lowercase if its general category type, provided
9073 * by {@link Character#getType getType(codePoint)}, is
9074 * {@code LOWERCASE_LETTER}, or it has contributory property
9075 * Other_Lowercase as defined by the Unicode Standard.
9076 * <p>
9077 * The following are examples of lowercase characters:
9078 * <blockquote><pre>
9079 * 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
9080 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9081 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9082 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9083 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9084 * </pre></blockquote>
9085 * <p> Many other Unicode characters are lowercase too.
9086 *
9087 * @param codePoint the character (Unicode code point) to be tested.
9088 * @return {@code true} if the character is lowercase;
9089 * {@code false} otherwise.
9090 * @see Character#isLowerCase(int)
9091 * @see Character#isTitleCase(int)
9092 * @see Character#toLowerCase(int)
9093 * @see Character#getType(int)
9094 * @since 1.5
9095 */
9096 public static boolean isLowerCase(int codePoint) {
9097 return CharacterData.of(codePoint).isLowerCase(codePoint) ||
9098 CharacterData.of(codePoint).isOtherLowercase(codePoint);
9099 }
9100
9101 /**
9102 * Determines if the specified character is an uppercase character.
9103 * <p>
9104 * A character is uppercase if its general category type, provided by
9105 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
9106 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9107 * <p>
9108 * The following are examples of uppercase characters:
9109 * <blockquote><pre>
9110 * 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
9111 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9112 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9113 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9114 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9115 * </pre></blockquote>
9116 * <p> Many other Unicode characters are uppercase too.
9117 *
9118 * <p><b>Note:</b> This method cannot handle <a
9119 * href="#supplementary"> supplementary characters</a>. To support
9120 * all Unicode characters, including supplementary characters, use
9121 * the {@link #isUpperCase(int)} method.
9122 *
9123 * @param ch the character to be tested.
9124 * @return {@code true} if the character is uppercase;
9125 * {@code false} otherwise.
9126 * @see Character#isLowerCase(char)
9127 * @see Character#isTitleCase(char)
9128 * @see Character#toUpperCase(char)
9129 * @see Character#getType(char)
9130 * @since 1.0
9131 */
9132 public static boolean isUpperCase(char ch) {
9133 return isUpperCase((int)ch);
9134 }
9135
9136 /**
9137 * Determines if the specified character (Unicode code point) is an uppercase character.
9138 * <p>
9139 * A character is uppercase if its general category type, provided by
9140 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
9141 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9142 * <p>
9143 * The following are examples of uppercase characters:
9144 * <blockquote><pre>
9145 * 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
9146 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9147 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9148 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9149 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9150 * </pre></blockquote>
9151 * <p> Many other Unicode characters are uppercase too.
9152 *
9153 * @param codePoint the character (Unicode code point) to be tested.
9154 * @return {@code true} if the character is uppercase;
9155 * {@code false} otherwise.
9156 * @see Character#isLowerCase(int)
9157 * @see Character#isTitleCase(int)
9158 * @see Character#toUpperCase(int)
9159 * @see Character#getType(int)
9160 * @since 1.5
9161 */
9162 public static boolean isUpperCase(int codePoint) {
9163 return CharacterData.of(codePoint).isUpperCase(codePoint) ||
9164 CharacterData.of(codePoint).isOtherUppercase(codePoint);
9165 }
9166
9167 /**
9168 * Determines if the specified character is a titlecase character.
9169 * <p>
9170 * A character is a titlecase character if its general
9171 * category type, provided by {@code Character.getType(ch)},
9172 * is {@code TITLECASE_LETTER}.
9173 * <p>
9174 * Some characters look like pairs of Latin letters. For example, there
9175 * is an uppercase letter that looks like "LJ" and has a corresponding
9176 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
9177 * is the appropriate form to use when rendering a word in lowercase
9178 * with initial capitals, as for a book title.
9179 * <p>
9180 * These are some of the Unicode characters for which this method returns
9181 * {@code true}:
9182 * <ul>
9183 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
9184 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
9185 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
9186 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
9187 * </ul>
9188 * <p> Many other Unicode characters are titlecase too.
9189 *
9190 * <p><b>Note:</b> This method cannot handle <a
9191 * href="#supplementary"> supplementary characters</a>. To support
9192 * all Unicode characters, including supplementary characters, use
9193 * the {@link #isTitleCase(int)} method.
9194 *
9195 * @param ch the character to be tested.
9196 * @return {@code true} if the character is titlecase;
9197 * {@code false} otherwise.
9198 * @see Character#isLowerCase(char)
9199 * @see Character#isUpperCase(char)
9200 * @see Character#toTitleCase(char)
9201 * @see Character#getType(char)
9202 * @since 1.0.2
9203 */
9204 public static boolean isTitleCase(char ch) {
9205 return isTitleCase((int)ch);
9206 }
9207
9208 /**
9209 * Determines if the specified character (Unicode code point) is a titlecase character.
9210 * <p>
9211 * A character is a titlecase character if its general
9212 * category type, provided by {@link Character#getType(int) getType(codePoint)},
9213 * is {@code TITLECASE_LETTER}.
9214 * <p>
9215 * Some characters look like pairs of Latin letters. For example, there
9216 * is an uppercase letter that looks like "LJ" and has a corresponding
9217 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
9218 * is the appropriate form to use when rendering a word in lowercase
9219 * with initial capitals, as for a book title.
9220 * <p>
9221 * These are some of the Unicode characters for which this method returns
9222 * {@code true}:
9223 * <ul>
9224 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
9225 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
9226 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
9227 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
9228 * </ul>
9229 * <p> Many other Unicode characters are titlecase too.
9230 *
9231 * @param codePoint the character (Unicode code point) to be tested.
9232 * @return {@code true} if the character is titlecase;
9233 * {@code false} otherwise.
9234 * @see Character#isLowerCase(int)
9235 * @see Character#isUpperCase(int)
9236 * @see Character#toTitleCase(int)
9237 * @see Character#getType(int)
9238 * @since 1.5
9239 */
9240 public static boolean isTitleCase(int codePoint) {
9241 return getType(codePoint) == Character.TITLECASE_LETTER;
9242 }
9243
9244 /**
9245 * Determines if the specified character is a digit.
9246 * <p>
9247 * A character is a digit if its general category type, provided
9248 * by {@code Character.getType(ch)}, is
9249 * {@code DECIMAL_DIGIT_NUMBER}.
9250 * <p>
9251 * Some Unicode character ranges that contain digits:
9252 * <ul>
9253 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
9254 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
9255 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
9256 * Arabic-Indic digits
9257 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
9258 * Extended Arabic-Indic digits
9259 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
9260 * Devanagari digits
9261 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
9262 * Fullwidth digits
9263 * </ul>
9264 *
9265 * Many other character ranges contain digits as well.
9266 *
9267 * <p><b>Note:</b> This method cannot handle <a
9268 * href="#supplementary"> supplementary characters</a>. To support
9269 * all Unicode characters, including supplementary characters, use
9270 * the {@link #isDigit(int)} method.
9271 *
9272 * @param ch the character to be tested.
9273 * @return {@code true} if the character is a digit;
9274 * {@code false} otherwise.
9275 * @see Character#digit(char, int)
9276 * @see Character#forDigit(int, int)
9277 * @see Character#getType(char)
9278 */
9279 public static boolean isDigit(char ch) {
9280 return isDigit((int)ch);
9281 }
9282
9283 /**
9284 * Determines if the specified character (Unicode code point) is a digit.
9285 * <p>
9286 * A character is a digit if its general category type, provided
9287 * by {@link Character#getType(int) getType(codePoint)}, is
9288 * {@code DECIMAL_DIGIT_NUMBER}.
9289 * <p>
9290 * Some Unicode character ranges that contain digits:
9291 * <ul>
9292 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
9293 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
9294 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
9295 * Arabic-Indic digits
9296 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
9297 * Extended Arabic-Indic digits
9298 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
9299 * Devanagari digits
9300 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
9301 * Fullwidth digits
9302 * </ul>
9303 *
9304 * Many other character ranges contain digits as well.
9305 *
9306 * @param codePoint the character (Unicode code point) to be tested.
9307 * @return {@code true} if the character is a digit;
9308 * {@code false} otherwise.
9309 * @see Character#forDigit(int, int)
9310 * @see Character#getType(int)
9311 * @since 1.5
9312 */
9313 public static boolean isDigit(int codePoint) {
9314 return CharacterData.of(codePoint).isDigit(codePoint);
9315 }
9316
9317 /**
9318 * Determines if a character is defined in Unicode.
9319 * <p>
9320 * A character is defined if at least one of the following is true:
9321 * <ul>
9322 * <li>It has an entry in the UnicodeData file.
9323 * <li>It has a value in a range defined by the UnicodeData file.
9324 * </ul>
9325 *
9326 * <p><b>Note:</b> This method cannot handle <a
9327 * href="#supplementary"> supplementary characters</a>. To support
9328 * all Unicode characters, including supplementary characters, use
9329 * the {@link #isDefined(int)} method.
9330 *
9331 * @param ch the character to be tested
9332 * @return {@code true} if the character has a defined meaning
9333 * in Unicode; {@code false} otherwise.
9334 * @see Character#isDigit(char)
9335 * @see Character#isLetter(char)
9336 * @see Character#isLetterOrDigit(char)
9337 * @see Character#isLowerCase(char)
9338 * @see Character#isTitleCase(char)
9339 * @see Character#isUpperCase(char)
9340 * @since 1.0.2
9341 */
9342 public static boolean isDefined(char ch) {
9343 return isDefined((int)ch);
9344 }
9345
9346 /**
9347 * Determines if a character (Unicode code point) is defined in Unicode.
9348 * <p>
9349 * A character is defined if at least one of the following is true:
9350 * <ul>
9351 * <li>It has an entry in the UnicodeData file.
9352 * <li>It has a value in a range defined by the UnicodeData file.
9353 * </ul>
9354 *
9355 * @param codePoint the character (Unicode code point) to be tested.
9356 * @return {@code true} if the character has a defined meaning
9357 * in Unicode; {@code false} otherwise.
9358 * @see Character#isDigit(int)
9359 * @see Character#isLetter(int)
9360 * @see Character#isLetterOrDigit(int)
9361 * @see Character#isLowerCase(int)
9362 * @see Character#isTitleCase(int)
9363 * @see Character#isUpperCase(int)
9364 * @since 1.5
9365 */
9366 public static boolean isDefined(int codePoint) {
9367 return getType(codePoint) != Character.UNASSIGNED;
9368 }
9369
9370 /**
9371 * Determines if the specified character is a letter.
9372 * <p>
9373 * A character is considered to be a letter if its general
9374 * category type, provided by {@code Character.getType(ch)},
9375 * is any of the following:
9376 * <ul>
9377 * <li> {@code UPPERCASE_LETTER}
9378 * <li> {@code LOWERCASE_LETTER}
9379 * <li> {@code TITLECASE_LETTER}
9380 * <li> {@code MODIFIER_LETTER}
9381 * <li> {@code OTHER_LETTER}
9382 * </ul>
9383 *
9384 * Not all letters have case. Many characters are
9385 * letters but are neither uppercase nor lowercase nor titlecase.
9386 *
9387 * <p><b>Note:</b> This method cannot handle <a
9388 * href="#supplementary"> supplementary characters</a>. To support
9389 * all Unicode characters, including supplementary characters, use
9390 * the {@link #isLetter(int)} method.
9391 *
9392 * @param ch the character to be tested.
9393 * @return {@code true} if the character is a letter;
9394 * {@code false} otherwise.
9395 * @see Character#isDigit(char)
9396 * @see Character#isJavaIdentifierStart(char)
9397 * @see Character#isJavaLetter(char)
9398 * @see Character#isJavaLetterOrDigit(char)
9399 * @see Character#isLetterOrDigit(char)
9400 * @see Character#isLowerCase(char)
9401 * @see Character#isTitleCase(char)
9402 * @see Character#isUnicodeIdentifierStart(char)
9403 * @see Character#isUpperCase(char)
9404 */
9405 public static boolean isLetter(char ch) {
9406 return isLetter((int)ch);
9407 }
9408
9409 /**
9410 * Determines if the specified character (Unicode code point) is a letter.
9411 * <p>
9412 * A character is considered to be a letter if its general
9413 * category type, provided by {@link Character#getType(int) getType(codePoint)},
9414 * is any of the following:
9415 * <ul>
9416 * <li> {@code UPPERCASE_LETTER}
9417 * <li> {@code LOWERCASE_LETTER}
9418 * <li> {@code TITLECASE_LETTER}
9419 * <li> {@code MODIFIER_LETTER}
9420 * <li> {@code OTHER_LETTER}
9421 * </ul>
9422 *
9423 * Not all letters have case. Many characters are
9424 * letters but are neither uppercase nor lowercase nor titlecase.
9425 *
9426 * @param codePoint the character (Unicode code point) to be tested.
9427 * @return {@code true} if the character is a letter;
9428 * {@code false} otherwise.
9429 * @see Character#isDigit(int)
9430 * @see Character#isJavaIdentifierStart(int)
9431 * @see Character#isLetterOrDigit(int)
9432 * @see Character#isLowerCase(int)
9433 * @see Character#isTitleCase(int)
9434 * @see Character#isUnicodeIdentifierStart(int)
9435 * @see Character#isUpperCase(int)
9436 * @since 1.5
9437 */
9438 public static boolean isLetter(int codePoint) {
9439 return ((((1 << Character.UPPERCASE_LETTER) |
9440 (1 << Character.LOWERCASE_LETTER) |
9441 (1 << Character.TITLECASE_LETTER) |
9442 (1 << Character.MODIFIER_LETTER) |
9443 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
9444 != 0;
9445 }
9446
9447 /**
9448 * Determines if the specified character is a letter or digit.
9449 * <p>
9450 * A character is considered to be a letter or digit if either
9451 * {@code Character.isLetter(char ch)} or
9452 * {@code Character.isDigit(char ch)} returns
9453 * {@code true} for the character.
9454 *
9455 * <p><b>Note:</b> This method cannot handle <a
9456 * href="#supplementary"> supplementary characters</a>. To support
9457 * all Unicode characters, including supplementary characters, use
9458 * the {@link #isLetterOrDigit(int)} method.
9459 *
9460 * @param ch the character to be tested.
9461 * @return {@code true} if the character is a letter or digit;
9462 * {@code false} otherwise.
9463 * @see Character#isDigit(char)
9464 * @see Character#isJavaIdentifierPart(char)
9465 * @see Character#isJavaLetter(char)
9466 * @see Character#isJavaLetterOrDigit(char)
9467 * @see Character#isLetter(char)
9468 * @see Character#isUnicodeIdentifierPart(char)
9469 * @since 1.0.2
9470 */
9471 public static boolean isLetterOrDigit(char ch) {
9472 return isLetterOrDigit((int)ch);
9473 }
9474
9475 /**
9476 * Determines if the specified character (Unicode code point) is a letter or digit.
9477 * <p>
9478 * A character is considered to be a letter or digit if either
9479 * {@link #isLetter(int) isLetter(codePoint)} or
9480 * {@link #isDigit(int) isDigit(codePoint)} returns
9481 * {@code true} for the character.
9482 *
9483 * @param codePoint the character (Unicode code point) to be tested.
9484 * @return {@code true} if the character is a letter or digit;
9485 * {@code false} otherwise.
9486 * @see Character#isDigit(int)
9487 * @see Character#isJavaIdentifierPart(int)
9488 * @see Character#isLetter(int)
9489 * @see Character#isUnicodeIdentifierPart(int)
9490 * @since 1.5
9491 */
9492 public static boolean isLetterOrDigit(int codePoint) {
9493 return ((((1 << Character.UPPERCASE_LETTER) |
9494 (1 << Character.LOWERCASE_LETTER) |
9495 (1 << Character.TITLECASE_LETTER) |
9496 (1 << Character.MODIFIER_LETTER) |
9497 (1 << Character.OTHER_LETTER) |
9498 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
9499 != 0;
9500 }
9501
9502 /**
9503 * Determines if the specified character is permissible as the first
9504 * character in a Java identifier.
9505 * <p>
9506 * A character may start a Java identifier if and only if
9507 * one of the following is true:
9508 * <ul>
9509 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9510 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
9511 * <li> {@code ch} is a currency symbol (such as {@code '$'})
9512 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
9513 * </ul>
9514 *
9515 * @param ch the character to be tested.
9516 * @return {@code true} if the character may start a Java
9517 * identifier; {@code false} otherwise.
9518 * @see Character#isJavaLetterOrDigit(char)
9519 * @see Character#isJavaIdentifierStart(char)
9520 * @see Character#isJavaIdentifierPart(char)
9521 * @see Character#isLetter(char)
9522 * @see Character#isLetterOrDigit(char)
9523 * @see Character#isUnicodeIdentifierStart(char)
9524 * @since 1.0.2
9525 * @deprecated Replaced by isJavaIdentifierStart(char).
9526 */
9527 @Deprecated(since="1.1")
9528 public static boolean isJavaLetter(char ch) {
9529 return isJavaIdentifierStart(ch);
9530 }
9531
9532 /**
9533 * Determines if the specified character may be part of a Java
9534 * identifier as other than the first character.
9535 * <p>
9536 * A character may be part of a Java identifier if and only if any
9537 * of the following are true:
9538 * <ul>
9539 * <li> it is a letter
9540 * <li> it is a currency symbol (such as {@code '$'})
9541 * <li> it is a connecting punctuation character (such as {@code '_'})
9542 * <li> it is a digit
9543 * <li> it is a numeric letter (such as a Roman numeral character)
9544 * <li> it is a combining mark
9545 * <li> it is a non-spacing mark
9546 * <li> {@code isIdentifierIgnorable} returns
9547 * {@code true} for the character.
9548 * </ul>
9549 *
9550 * @param ch the character to be tested.
9551 * @return {@code true} if the character may be part of a
9552 * Java identifier; {@code false} otherwise.
9553 * @see Character#isJavaLetter(char)
9554 * @see Character#isJavaIdentifierStart(char)
9555 * @see Character#isJavaIdentifierPart(char)
9556 * @see Character#isLetter(char)
9557 * @see Character#isLetterOrDigit(char)
9558 * @see Character#isUnicodeIdentifierPart(char)
9559 * @see Character#isIdentifierIgnorable(char)
9560 * @since 1.0.2
9561 * @deprecated Replaced by isJavaIdentifierPart(char).
9562 */
9563 @Deprecated(since="1.1")
9564 public static boolean isJavaLetterOrDigit(char ch) {
9565 return isJavaIdentifierPart(ch);
9566 }
9567
9568 /**
9569 * Determines if the specified character (Unicode code point) is an alphabet.
9570 * <p>
9571 * A character is considered to be alphabetic if its general category type,
9572 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
9573 * the following:
9574 * <ul>
9575 * <li> {@code UPPERCASE_LETTER}
9576 * <li> {@code LOWERCASE_LETTER}
9577 * <li> {@code TITLECASE_LETTER}
9578 * <li> {@code MODIFIER_LETTER}
9579 * <li> {@code OTHER_LETTER}
9580 * <li> {@code LETTER_NUMBER}
9581 * </ul>
9582 * or it has contributory property Other_Alphabetic as defined by the
9583 * Unicode Standard.
9584 *
9585 * @param codePoint the character (Unicode code point) to be tested.
9586 * @return {@code true} if the character is a Unicode alphabet
9587 * character, {@code false} otherwise.
9588 * @since 1.7
9589 */
9590 public static boolean isAlphabetic(int codePoint) {
9591 return (((((1 << Character.UPPERCASE_LETTER) |
9592 (1 << Character.LOWERCASE_LETTER) |
9593 (1 << Character.TITLECASE_LETTER) |
9594 (1 << Character.MODIFIER_LETTER) |
9595 (1 << Character.OTHER_LETTER) |
9596 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
9597 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
9598 }
9599
9600 /**
9601 * Determines if the specified character (Unicode code point) is a CJKV
9602 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
9603 * the Unicode Standard.
9604 *
9605 * @param codePoint the character (Unicode code point) to be tested.
9606 * @return {@code true} if the character is a Unicode ideograph
9607 * character, {@code false} otherwise.
9608 * @since 1.7
9609 */
9610 public static boolean isIdeographic(int codePoint) {
9611 return CharacterData.of(codePoint).isIdeographic(codePoint);
9612 }
9613
9614 /**
9615 * Determines if the specified character is
9616 * permissible as the first character in a Java identifier.
9617 * <p>
9618 * A character may start a Java identifier if and only if
9619 * one of the following conditions is true:
9620 * <ul>
9621 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9622 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
9623 * <li> {@code ch} is a currency symbol (such as {@code '$'})
9624 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
9625 * </ul>
9626 *
9627 * <p><b>Note:</b> This method cannot handle <a
9628 * href="#supplementary"> supplementary characters</a>. To support
9629 * all Unicode characters, including supplementary characters, use
9630 * the {@link #isJavaIdentifierStart(int)} method.
9631 *
9632 * @param ch the character to be tested.
9633 * @return {@code true} if the character may start a Java identifier;
9634 * {@code false} otherwise.
9635 * @see Character#isJavaIdentifierPart(char)
9636 * @see Character#isLetter(char)
9637 * @see Character#isUnicodeIdentifierStart(char)
9638 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9639 * @since 1.1
9640 */
9641 public static boolean isJavaIdentifierStart(char ch) {
9642 return isJavaIdentifierStart((int)ch);
9643 }
9644
9645 /**
9646 * Determines if the character (Unicode code point) is
9647 * permissible as the first character in a Java identifier.
9648 * <p>
9649 * A character may start a Java identifier if and only if
9650 * one of the following conditions is true:
9651 * <ul>
9652 * <li> {@link #isLetter(int) isLetter(codePoint)}
9653 * returns {@code true}
9654 * <li> {@link #getType(int) getType(codePoint)}
9655 * returns {@code LETTER_NUMBER}
9656 * <li> the referenced character is a currency symbol (such as {@code '$'})
9657 * <li> the referenced character is a connecting punctuation character
9658 * (such as {@code '_'}).
9659 * </ul>
9660 *
9661 * @param codePoint the character (Unicode code point) to be tested.
9662 * @return {@code true} if the character may start a Java identifier;
9663 * {@code false} otherwise.
9664 * @see Character#isJavaIdentifierPart(int)
9665 * @see Character#isLetter(int)
9666 * @see Character#isUnicodeIdentifierStart(int)
9667 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9668 * @since 1.5
9669 */
9670 public static boolean isJavaIdentifierStart(int codePoint) {
9671 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
9672 }
9673
9674 /**
9675 * Determines if the specified character may be part of a Java
9676 * identifier as other than the first character.
9677 * <p>
9678 * A character may be part of a Java identifier if any of the following
9679 * are true:
9680 * <ul>
9681 * <li> it is a letter
9682 * <li> it is a currency symbol (such as {@code '$'})
9683 * <li> it is a connecting punctuation character (such as {@code '_'})
9684 * <li> it is a digit
9685 * <li> it is a numeric letter (such as a Roman numeral character)
9686 * <li> it is a combining mark
9687 * <li> it is a non-spacing mark
9688 * <li> {@code isIdentifierIgnorable} returns
9689 * {@code true} for the character
9690 * </ul>
9691 *
9692 * <p><b>Note:</b> This method cannot handle <a
9693 * href="#supplementary"> supplementary characters</a>. To support
9694 * all Unicode characters, including supplementary characters, use
9695 * the {@link #isJavaIdentifierPart(int)} method.
9696 *
9697 * @param ch the character to be tested.
9698 * @return {@code true} if the character may be part of a
9699 * Java identifier; {@code false} otherwise.
9700 * @see Character#isIdentifierIgnorable(char)
9701 * @see Character#isJavaIdentifierStart(char)
9702 * @see Character#isLetterOrDigit(char)
9703 * @see Character#isUnicodeIdentifierPart(char)
9704 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9705 * @since 1.1
9706 */
9707 public static boolean isJavaIdentifierPart(char ch) {
9708 return isJavaIdentifierPart((int)ch);
9709 }
9710
9711 /**
9712 * Determines if the character (Unicode code point) may be part of a Java
9713 * identifier as other than the first character.
9714 * <p>
9715 * A character may be part of a Java identifier if any of the following
9716 * are true:
9717 * <ul>
9718 * <li> it is a letter
9719 * <li> it is a currency symbol (such as {@code '$'})
9720 * <li> it is a connecting punctuation character (such as {@code '_'})
9721 * <li> it is a digit
9722 * <li> it is a numeric letter (such as a Roman numeral character)
9723 * <li> it is a combining mark
9724 * <li> it is a non-spacing mark
9725 * <li> {@link #isIdentifierIgnorable(int)
9726 * isIdentifierIgnorable(codePoint)} returns {@code true} for
9727 * the character
9728 * </ul>
9729 *
9730 * @param codePoint the character (Unicode code point) to be tested.
9731 * @return {@code true} if the character may be part of a
9732 * Java identifier; {@code false} otherwise.
9733 * @see Character#isIdentifierIgnorable(int)
9734 * @see Character#isJavaIdentifierStart(int)
9735 * @see Character#isLetterOrDigit(int)
9736 * @see Character#isUnicodeIdentifierPart(int)
9737 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9738 * @since 1.5
9739 */
9740 public static boolean isJavaIdentifierPart(int codePoint) {
9741 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
9742 }
9743
9744 /**
9745 * Determines if the specified character is permissible as the
9746 * first character in a Unicode identifier.
9747 * <p>
9748 * A character may start a Unicode identifier if and only if
9749 * one of the following conditions is true:
9750 * <ul>
9751 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9752 * <li> {@link #getType(char) getType(ch)} returns
9753 * {@code LETTER_NUMBER}.
9754 * </ul>
9755 *
9756 * <p><b>Note:</b> This method cannot handle <a
9757 * href="#supplementary"> supplementary characters</a>. To support
9758 * all Unicode characters, including supplementary characters, use
9759 * the {@link #isUnicodeIdentifierStart(int)} method.
9760 *
9761 * @param ch the character to be tested.
9762 * @return {@code true} if the character may start a Unicode
9763 * identifier; {@code false} otherwise.
9764 * @see Character#isJavaIdentifierStart(char)
9765 * @see Character#isLetter(char)
9766 * @see Character#isUnicodeIdentifierPart(char)
9767 * @since 1.1
9768 */
9769 public static boolean isUnicodeIdentifierStart(char ch) {
9770 return isUnicodeIdentifierStart((int)ch);
9771 }
9772
9773 /**
9774 * Determines if the specified character (Unicode code point) is permissible as the
9775 * first character in a Unicode identifier.
9776 * <p>
9777 * A character may start a Unicode identifier if and only if
9778 * one of the following conditions is true:
9779 * <ul>
9780 * <li> {@link #isLetter(int) isLetter(codePoint)}
9781 * returns {@code true}
9782 * <li> {@link #getType(int) getType(codePoint)}
9783 * returns {@code LETTER_NUMBER}.
9784 * </ul>
9785 * @param codePoint the character (Unicode code point) to be tested.
9786 * @return {@code true} if the character may start a Unicode
9787 * identifier; {@code false} otherwise.
9788 * @see Character#isJavaIdentifierStart(int)
9789 * @see Character#isLetter(int)
9790 * @see Character#isUnicodeIdentifierPart(int)
9791 * @since 1.5
9792 */
9793 public static boolean isUnicodeIdentifierStart(int codePoint) {
9794 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
9795 }
9796
9797 /**
9798 * Determines if the specified character may be part of a Unicode
9799 * identifier as other than the first character.
9800 * <p>
9801 * A character may be part of a Unicode identifier if and only if
9802 * one of the following statements is true:
9803 * <ul>
9804 * <li> it is a letter
9805 * <li> it is a connecting punctuation character (such as {@code '_'})
9806 * <li> it is a digit
9807 * <li> it is a numeric letter (such as a Roman numeral character)
9808 * <li> it is a combining mark
9809 * <li> it is a non-spacing mark
9810 * <li> {@code isIdentifierIgnorable} returns
9811 * {@code true} for this character.
9812 * </ul>
9813 *
9814 * <p><b>Note:</b> This method cannot handle <a
9815 * href="#supplementary"> supplementary characters</a>. To support
9816 * all Unicode characters, including supplementary characters, use
9817 * the {@link #isUnicodeIdentifierPart(int)} method.
9818 *
9819 * @param ch the character to be tested.
9820 * @return {@code true} if the character may be part of a
9821 * Unicode identifier; {@code false} otherwise.
9822 * @see Character#isIdentifierIgnorable(char)
9823 * @see Character#isJavaIdentifierPart(char)
9824 * @see Character#isLetterOrDigit(char)
9825 * @see Character#isUnicodeIdentifierStart(char)
9826 * @since 1.1
9827 */
9828 public static boolean isUnicodeIdentifierPart(char ch) {
9829 return isUnicodeIdentifierPart((int)ch);
9830 }
9831
9832 /**
9833 * Determines if the specified character (Unicode code point) may be part of a Unicode
9834 * identifier as other than the first character.
9835 * <p>
9836 * A character may be part of a Unicode identifier if and only if
9837 * one of the following statements is true:
9838 * <ul>
9839 * <li> it is a letter
9840 * <li> it is a connecting punctuation character (such as {@code '_'})
9841 * <li> it is a digit
9842 * <li> it is a numeric letter (such as a Roman numeral character)
9843 * <li> it is a combining mark
9844 * <li> it is a non-spacing mark
9845 * <li> {@code isIdentifierIgnorable} returns
9846 * {@code true} for this character.
9847 * </ul>
9848 * @param codePoint the character (Unicode code point) to be tested.
9849 * @return {@code true} if the character may be part of a
9850 * Unicode identifier; {@code false} otherwise.
9851 * @see Character#isIdentifierIgnorable(int)
9852 * @see Character#isJavaIdentifierPart(int)
9853 * @see Character#isLetterOrDigit(int)
9854 * @see Character#isUnicodeIdentifierStart(int)
9855 * @since 1.5
9856 */
9857 public static boolean isUnicodeIdentifierPart(int codePoint) {
9858 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
9859 }
9860
9861 /**
9862 * Determines if the specified character should be regarded as
9863 * an ignorable character in a Java identifier or a Unicode identifier.
9864 * <p>
9865 * The following Unicode characters are ignorable in a Java identifier
9866 * or a Unicode identifier:
9867 * <ul>
9868 * <li>ISO control characters that are not whitespace
9869 * <ul>
9870 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9871 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9872 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9873 * </ul>
9874 *
9875 * <li>all characters that have the {@code FORMAT} general
9876 * category value
9877 * </ul>
9878 *
9879 * <p><b>Note:</b> This method cannot handle <a
9880 * href="#supplementary"> supplementary characters</a>. To support
9881 * all Unicode characters, including supplementary characters, use
9882 * the {@link #isIdentifierIgnorable(int)} method.
9883 *
9884 * @param ch the character to be tested.
9885 * @return {@code true} if the character is an ignorable control
9886 * character that may be part of a Java or Unicode identifier;
9887 * {@code false} otherwise.
9888 * @see Character#isJavaIdentifierPart(char)
9889 * @see Character#isUnicodeIdentifierPart(char)
9890 * @since 1.1
9891 */
9892 public static boolean isIdentifierIgnorable(char ch) {
9893 return isIdentifierIgnorable((int)ch);
9894 }
9895
9896 /**
9897 * Determines if the specified character (Unicode code point) should be regarded as
9898 * an ignorable character in a Java identifier or a Unicode identifier.
9899 * <p>
9900 * The following Unicode characters are ignorable in a Java identifier
9901 * or a Unicode identifier:
9902 * <ul>
9903 * <li>ISO control characters that are not whitespace
9904 * <ul>
9905 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9906 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9907 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9908 * </ul>
9909 *
9910 * <li>all characters that have the {@code FORMAT} general
9911 * category value
9912 * </ul>
9913 *
9914 * @param codePoint the character (Unicode code point) to be tested.
9915 * @return {@code true} if the character is an ignorable control
9916 * character that may be part of a Java or Unicode identifier;
9917 * {@code false} otherwise.
9918 * @see Character#isJavaIdentifierPart(int)
9919 * @see Character#isUnicodeIdentifierPart(int)
9920 * @since 1.5
9921 */
9922 public static boolean isIdentifierIgnorable(int codePoint) {
9923 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
9924 }
9925
9926 /**
9927 * Converts the character argument to lowercase using case
9928 * mapping information from the UnicodeData file.
9929 * <p>
9930 * Note that
9931 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
9932 * does not always return {@code true} for some ranges of
9933 * characters, particularly those that are symbols or ideographs.
9934 *
9935 * <p>In general, {@link String#toLowerCase()} should be used to map
9936 * characters to lowercase. {@code String} case mapping methods
9937 * have several benefits over {@code Character} case mapping methods.
9938 * {@code String} case mapping methods can perform locale-sensitive
9939 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9940 * the {@code Character} case mapping methods cannot.
9941 *
9942 * <p><b>Note:</b> This method cannot handle <a
9943 * href="#supplementary"> supplementary characters</a>. To support
9944 * all Unicode characters, including supplementary characters, use
9945 * the {@link #toLowerCase(int)} method.
9946 *
9947 * @param ch the character to be converted.
9948 * @return the lowercase equivalent of the character, if any;
9949 * otherwise, the character itself.
9950 * @see Character#isLowerCase(char)
9951 * @see String#toLowerCase()
9952 */
9953 public static char toLowerCase(char ch) {
9954 return (char)toLowerCase((int)ch);
9955 }
9956
9957 /**
9958 * Converts the character (Unicode code point) argument to
9959 * lowercase using case mapping information from the UnicodeData
9960 * file.
9961 *
9962 * <p> Note that
9963 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
9964 * does not always return {@code true} for some ranges of
9965 * characters, particularly those that are symbols or ideographs.
9966 *
9967 * <p>In general, {@link String#toLowerCase()} should be used to map
9968 * characters to lowercase. {@code String} case mapping methods
9969 * have several benefits over {@code Character} case mapping methods.
9970 * {@code String} case mapping methods can perform locale-sensitive
9971 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9972 * the {@code Character} case mapping methods cannot.
9973 *
9974 * @param codePoint the character (Unicode code point) to be converted.
9975 * @return the lowercase equivalent of the character (Unicode code
9976 * point), if any; otherwise, the character itself.
9977 * @see Character#isLowerCase(int)
9978 * @see String#toLowerCase()
9979 *
9980 * @since 1.5
9981 */
9982 public static int toLowerCase(int codePoint) {
9983 return CharacterData.of(codePoint).toLowerCase(codePoint);
9984 }
9985
9986 /**
9987 * Converts the character argument to uppercase using case mapping
9988 * information from the UnicodeData file.
9989 * <p>
9990 * Note that
9991 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
9992 * does not always return {@code true} for some ranges of
9993 * characters, particularly those that are symbols or ideographs.
9994 *
9995 * <p>In general, {@link String#toUpperCase()} should be used to map
9996 * characters to uppercase. {@code String} case mapping methods
9997 * have several benefits over {@code Character} case mapping methods.
9998 * {@code String} case mapping methods can perform locale-sensitive
9999 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10000 * the {@code Character} case mapping methods cannot.
10001 *
10002 * <p><b>Note:</b> This method cannot handle <a
10003 * href="#supplementary"> supplementary characters</a>. To support
10004 * all Unicode characters, including supplementary characters, use
10005 * the {@link #toUpperCase(int)} method.
10006 *
10007 * @param ch the character to be converted.
10008 * @return the uppercase equivalent of the character, if any;
10009 * otherwise, the character itself.
10010 * @see Character#isUpperCase(char)
10011 * @see String#toUpperCase()
10012 */
10013 public static char toUpperCase(char ch) {
10014 return (char)toUpperCase((int)ch);
10015 }
10016
10017 /**
10018 * Converts the character (Unicode code point) argument to
10019 * uppercase using case mapping information from the UnicodeData
10020 * file.
10021 *
10022 * <p>Note that
10023 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
10024 * does not always return {@code true} for some ranges of
10025 * characters, particularly those that are symbols or ideographs.
10026 *
10027 * <p>In general, {@link String#toUpperCase()} should be used to map
10028 * characters to uppercase. {@code String} case mapping methods
10029 * have several benefits over {@code Character} case mapping methods.
10030 * {@code String} case mapping methods can perform locale-sensitive
10031 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10032 * the {@code Character} case mapping methods cannot.
10033 *
10034 * @param codePoint the character (Unicode code point) to be converted.
10035 * @return the uppercase equivalent of the character, if any;
10036 * otherwise, the character itself.
10037 * @see Character#isUpperCase(int)
10038 * @see String#toUpperCase()
10039 *
10040 * @since 1.5
10041 */
10042 public static int toUpperCase(int codePoint) {
10043 return CharacterData.of(codePoint).toUpperCase(codePoint);
10044 }
10045
10046 /**
10047 * Converts the character argument to titlecase using case mapping
10048 * information from the UnicodeData file. If a character has no
10049 * explicit titlecase mapping and is not itself a titlecase char
10050 * according to UnicodeData, then the uppercase mapping is
10051 * returned as an equivalent titlecase mapping. If the
10052 * {@code char} argument is already a titlecase
10053 * {@code char}, the same {@code char} value will be
10054 * returned.
10055 * <p>
10056 * Note that
10057 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
10058 * does not always return {@code true} for some ranges of
10059 * characters.
10060 *
10061 * <p><b>Note:</b> This method cannot handle <a
10062 * href="#supplementary"> supplementary characters</a>. To support
10063 * all Unicode characters, including supplementary characters, use
10064 * the {@link #toTitleCase(int)} method.
10065 *
10066 * @param ch the character to be converted.
10067 * @return the titlecase equivalent of the character, if any;
10068 * otherwise, the character itself.
10069 * @see Character#isTitleCase(char)
10070 * @see Character#toLowerCase(char)
10071 * @see Character#toUpperCase(char)
10072 * @since 1.0.2
10073 */
10074 public static char toTitleCase(char ch) {
10075 return (char)toTitleCase((int)ch);
10076 }
10077
10078 /**
10079 * Converts the character (Unicode code point) argument to titlecase using case mapping
10080 * information from the UnicodeData file. If a character has no
10081 * explicit titlecase mapping and is not itself a titlecase char
10082 * according to UnicodeData, then the uppercase mapping is
10083 * returned as an equivalent titlecase mapping. If the
10084 * character argument is already a titlecase
10085 * character, the same character value will be
10086 * returned.
10087 *
10088 * <p>Note that
10089 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
10090 * does not always return {@code true} for some ranges of
10091 * characters.
10092 *
10093 * @param codePoint the character (Unicode code point) to be converted.
10094 * @return the titlecase equivalent of the character, if any;
10095 * otherwise, the character itself.
10096 * @see Character#isTitleCase(int)
10097 * @see Character#toLowerCase(int)
10098 * @see Character#toUpperCase(int)
10099 * @since 1.5
10100 */
10101 public static int toTitleCase(int codePoint) {
10102 return CharacterData.of(codePoint).toTitleCase(codePoint);
10103 }
10104
10105 /**
10106 * Returns the numeric value of the character {@code ch} in the
10107 * specified radix.
10108 * <p>
10109 * If the radix is not in the range {@code MIN_RADIX} ≤
10110 * {@code radix} ≤ {@code MAX_RADIX} or if the
10111 * value of {@code ch} is not a valid digit in the specified
10112 * radix, {@code -1} is returned. A character is a valid digit
10113 * if at least one of the following is true:
10114 * <ul>
10115 * <li>The method {@code isDigit} is {@code true} of the character
10116 * and the Unicode decimal digit value of the character (or its
10117 * single-character decomposition) is less than the specified radix.
10118 * In this case the decimal digit value is returned.
10119 * <li>The character is one of the uppercase Latin letters
10120 * {@code 'A'} through {@code 'Z'} and its code is less than
10121 * {@code radix + 'A' - 10}.
10122 * In this case, {@code ch - 'A' + 10}
10123 * is returned.
10124 * <li>The character is one of the lowercase Latin letters
10125 * {@code 'a'} through {@code 'z'} and its code is less than
10126 * {@code radix + 'a' - 10}.
10127 * In this case, {@code ch - 'a' + 10}
10128 * is returned.
10129 * <li>The character is one of the fullwidth uppercase Latin letters A
10130 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
10131 * and its code is less than
10132 * {@code radix + '\u005CuFF21' - 10}.
10133 * In this case, {@code ch - '\u005CuFF21' + 10}
10134 * is returned.
10135 * <li>The character is one of the fullwidth lowercase Latin letters a
10136 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
10137 * and its code is less than
10138 * {@code radix + '\u005CuFF41' - 10}.
10139 * In this case, {@code ch - '\u005CuFF41' + 10}
10140 * is returned.
10141 * </ul>
10142 *
10143 * <p><b>Note:</b> This method cannot handle <a
10144 * href="#supplementary"> supplementary characters</a>. To support
10145 * all Unicode characters, including supplementary characters, use
10146 * the {@link #digit(int, int)} method.
10147 *
10148 * @param ch the character to be converted.
10149 * @param radix the radix.
10150 * @return the numeric value represented by the character in the
10151 * specified radix.
10152 * @see Character#forDigit(int, int)
10153 * @see Character#isDigit(char)
10154 */
10155 public static int digit(char ch, int radix) {
10156 return digit((int)ch, radix);
10157 }
10158
10159 /**
10160 * Returns the numeric value of the specified character (Unicode
10161 * code point) in the specified radix.
10162 *
10163 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
10164 * {@code radix} ≤ {@code MAX_RADIX} or if the
10165 * character is not a valid digit in the specified
10166 * radix, {@code -1} is returned. A character is a valid digit
10167 * if at least one of the following is true:
10168 * <ul>
10169 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
10170 * and the Unicode decimal digit value of the character (or its
10171 * single-character decomposition) is less than the specified radix.
10172 * In this case the decimal digit value is returned.
10173 * <li>The character is one of the uppercase Latin letters
10174 * {@code 'A'} through {@code 'Z'} and its code is less than
10175 * {@code radix + 'A' - 10}.
10176 * In this case, {@code codePoint - 'A' + 10}
10177 * is returned.
10178 * <li>The character is one of the lowercase Latin letters
10179 * {@code 'a'} through {@code 'z'} and its code is less than
10180 * {@code radix + 'a' - 10}.
10181 * In this case, {@code codePoint - 'a' + 10}
10182 * is returned.
10183 * <li>The character is one of the fullwidth uppercase Latin letters A
10184 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
10185 * and its code is less than
10186 * {@code radix + '\u005CuFF21' - 10}.
10187 * In this case,
10188 * {@code codePoint - '\u005CuFF21' + 10}
10189 * is returned.
10190 * <li>The character is one of the fullwidth lowercase Latin letters a
10191 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
10192 * and its code is less than
10193 * {@code radix + '\u005CuFF41'- 10}.
10194 * In this case,
10195 * {@code codePoint - '\u005CuFF41' + 10}
10196 * is returned.
10197 * </ul>
10198 *
10199 * @param codePoint the character (Unicode code point) to be converted.
10200 * @param radix the radix.
10201 * @return the numeric value represented by the character in the
10202 * specified radix.
10203 * @see Character#forDigit(int, int)
10204 * @see Character#isDigit(int)
10205 * @since 1.5
10206 */
10207 public static int digit(int codePoint, int radix) {
10208 return CharacterData.of(codePoint).digit(codePoint, radix);
10209 }
10210
10211 /**
10212 * Returns the {@code int} value that the specified Unicode
10213 * character represents. For example, the character
10214 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
10215 * an int with a value of 50.
10216 * <p>
10217 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
10218 * {@code '\u005Cu005A'}), lowercase
10219 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
10220 * full width variant ({@code '\u005CuFF21'} through
10221 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
10222 * {@code '\u005CuFF5A'}) forms have numeric values from 10
10223 * through 35. This is independent of the Unicode specification,
10224 * which does not assign numeric values to these {@code char}
10225 * values.
10226 * <p>
10227 * If the character does not have a numeric value, then -1 is returned.
10228 * If the character has a numeric value that cannot be represented as a
10229 * nonnegative integer (for example, a fractional value), then -2
10230 * is returned.
10231 *
10232 * <p><b>Note:</b> This method cannot handle <a
10233 * href="#supplementary"> supplementary characters</a>. To support
10234 * all Unicode characters, including supplementary characters, use
10235 * the {@link #getNumericValue(int)} method.
10236 *
10237 * @param ch the character to be converted.
10238 * @return the numeric value of the character, as a nonnegative {@code int}
10239 * value; -2 if the character has a numeric value but the value
10240 * can not be represented as a nonnegative {@code int} value;
10241 * -1 if the character has no numeric value.
10242 * @see Character#forDigit(int, int)
10243 * @see Character#isDigit(char)
10244 * @since 1.1
10245 */
10246 public static int getNumericValue(char ch) {
10247 return getNumericValue((int)ch);
10248 }
10249
10250 /**
10251 * Returns the {@code int} value that the specified
10252 * character (Unicode code point) represents. For example, the character
10253 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
10254 * an {@code int} with a value of 50.
10255 * <p>
10256 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
10257 * {@code '\u005Cu005A'}), lowercase
10258 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
10259 * full width variant ({@code '\u005CuFF21'} through
10260 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
10261 * {@code '\u005CuFF5A'}) forms have numeric values from 10
10262 * through 35. This is independent of the Unicode specification,
10263 * which does not assign numeric values to these {@code char}
10264 * values.
10265 * <p>
10266 * If the character does not have a numeric value, then -1 is returned.
10267 * If the character has a numeric value that cannot be represented as a
10268 * nonnegative integer (for example, a fractional value), then -2
10269 * is returned.
10270 *
10271 * @param codePoint the character (Unicode code point) to be converted.
10272 * @return the numeric value of the character, as a nonnegative {@code int}
10273 * value; -2 if the character has a numeric value but the value
10274 * can not be represented as a nonnegative {@code int} value;
10275 * -1 if the character has no numeric value.
10276 * @see Character#forDigit(int, int)
10277 * @see Character#isDigit(int)
10278 * @since 1.5
10279 */
10280 public static int getNumericValue(int codePoint) {
10281 return CharacterData.of(codePoint).getNumericValue(codePoint);
10282 }
10283
10284 /**
10285 * Determines if the specified character is ISO-LATIN-1 white space.
10286 * This method returns {@code true} for the following five
10287 * characters only:
10288 * <table class="striped">
10289 * <caption style="display:none">truechars</caption>
10290 * <thead>
10291 * <tr><th scope="col">Character
10292 * <th scope="col">Code
10293 * <th scope="col">Name
10294 * </thead>
10295 * <tbody>
10296 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
10297 * <td>{@code HORIZONTAL TABULATION}</td></tr>
10298 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
10299 * <td>{@code NEW LINE}</td></tr>
10300 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
10301 * <td>{@code FORM FEED}</td></tr>
10302 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
10303 * <td>{@code CARRIAGE RETURN}</td></tr>
10304 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
10305 * <td>{@code SPACE}</td></tr>
10306 * </tbody>
10307 * </table>
10308 *
10309 * @param ch the character to be tested.
10310 * @return {@code true} if the character is ISO-LATIN-1 white
10311 * space; {@code false} otherwise.
10312 * @see Character#isSpaceChar(char)
10313 * @see Character#isWhitespace(char)
10314 * @deprecated Replaced by isWhitespace(char).
10315 */
10316 @Deprecated(since="1.1")
10317 public static boolean isSpace(char ch) {
10318 return (ch <= 0x0020) &&
10319 (((((1L << 0x0009) |
10320 (1L << 0x000A) |
10321 (1L << 0x000C) |
10322 (1L << 0x000D) |
10323 (1L << 0x0020)) >> ch) & 1L) != 0);
10324 }
10325
10326
10327 /**
10328 * Determines if the specified character is a Unicode space character.
10329 * A character is considered to be a space character if and only if
10330 * it is specified to be a space character by the Unicode Standard. This
10331 * method returns true if the character's general category type is any of
10332 * the following:
10333 * <ul>
10334 * <li> {@code SPACE_SEPARATOR}
10335 * <li> {@code LINE_SEPARATOR}
10336 * <li> {@code PARAGRAPH_SEPARATOR}
10337 * </ul>
10338 *
10339 * <p><b>Note:</b> This method cannot handle <a
10340 * href="#supplementary"> supplementary characters</a>. To support
10341 * all Unicode characters, including supplementary characters, use
10342 * the {@link #isSpaceChar(int)} method.
10343 *
10344 * @param ch the character to be tested.
10345 * @return {@code true} if the character is a space character;
10346 * {@code false} otherwise.
10347 * @see Character#isWhitespace(char)
10348 * @since 1.1
10349 */
10350 public static boolean isSpaceChar(char ch) {
10351 return isSpaceChar((int)ch);
10352 }
10353
10354 /**
10355 * Determines if the specified character (Unicode code point) is a
10356 * Unicode space character. A character is considered to be a
10357 * space character if and only if it is specified to be a space
10358 * character by the Unicode Standard. This method returns true if
10359 * the character's general category type is any of the following:
10360 *
10361 * <ul>
10362 * <li> {@link #SPACE_SEPARATOR}
10363 * <li> {@link #LINE_SEPARATOR}
10364 * <li> {@link #PARAGRAPH_SEPARATOR}
10365 * </ul>
10366 *
10367 * @param codePoint the character (Unicode code point) to be tested.
10368 * @return {@code true} if the character is a space character;
10369 * {@code false} otherwise.
10370 * @see Character#isWhitespace(int)
10371 * @since 1.5
10372 */
10373 public static boolean isSpaceChar(int codePoint) {
10374 return ((((1 << Character.SPACE_SEPARATOR) |
10375 (1 << Character.LINE_SEPARATOR) |
10376 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
10377 != 0;
10378 }
10379
10380 /**
10381 * Determines if the specified character is white space according to Java.
10382 * A character is a Java whitespace character if and only if it satisfies
10383 * one of the following criteria:
10384 * <ul>
10385 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
10386 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
10387 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
10388 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
10389 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
10390 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
10391 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
10392 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
10393 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
10394 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
10395 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
10396 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
10397 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
10398 * </ul>
10399 *
10400 * <p><b>Note:</b> This method cannot handle <a
10401 * href="#supplementary"> supplementary characters</a>. To support
10402 * all Unicode characters, including supplementary characters, use
10403 * the {@link #isWhitespace(int)} method.
10404 *
10405 * @param ch the character to be tested.
10406 * @return {@code true} if the character is a Java whitespace
10407 * character; {@code false} otherwise.
10408 * @see Character#isSpaceChar(char)
10409 * @since 1.1
10410 */
10411 public static boolean isWhitespace(char ch) {
10412 return isWhitespace((int)ch);
10413 }
10414
10415 /**
10416 * Determines if the specified character (Unicode code point) is
10417 * white space according to Java. A character is a Java
10418 * whitespace character if and only if it satisfies one of the
10419 * following criteria:
10420 * <ul>
10421 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
10422 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
10423 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
10424 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
10425 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
10426 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
10427 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
10428 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
10429 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
10430 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
10431 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
10432 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
10433 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
10434 * </ul>
10435 *
10436 * @param codePoint the character (Unicode code point) to be tested.
10437 * @return {@code true} if the character is a Java whitespace
10438 * character; {@code false} otherwise.
10439 * @see Character#isSpaceChar(int)
10440 * @since 1.5
10441 */
10442 public static boolean isWhitespace(int codePoint) {
10443 return CharacterData.of(codePoint).isWhitespace(codePoint);
10444 }
10445
10446 /**
10447 * Determines if the specified character is an ISO control
10448 * character. A character is considered to be an ISO control
10449 * character if its code is in the range {@code '\u005Cu0000'}
10450 * through {@code '\u005Cu001F'} or in the range
10451 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
10452 *
10453 * <p><b>Note:</b> This method cannot handle <a
10454 * href="#supplementary"> supplementary characters</a>. To support
10455 * all Unicode characters, including supplementary characters, use
10456 * the {@link #isISOControl(int)} method.
10457 *
10458 * @param ch the character to be tested.
10459 * @return {@code true} if the character is an ISO control character;
10460 * {@code false} otherwise.
10461 *
10462 * @see Character#isSpaceChar(char)
10463 * @see Character#isWhitespace(char)
10464 * @since 1.1
10465 */
10466 public static boolean isISOControl(char ch) {
10467 return isISOControl((int)ch);
10468 }
10469
10470 /**
10471 * Determines if the referenced character (Unicode code point) is an ISO control
10472 * character. A character is considered to be an ISO control
10473 * character if its code is in the range {@code '\u005Cu0000'}
10474 * through {@code '\u005Cu001F'} or in the range
10475 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
10476 *
10477 * @param codePoint the character (Unicode code point) to be tested.
10478 * @return {@code true} if the character is an ISO control character;
10479 * {@code false} otherwise.
10480 * @see Character#isSpaceChar(int)
10481 * @see Character#isWhitespace(int)
10482 * @since 1.5
10483 */
10484 public static boolean isISOControl(int codePoint) {
10485 // Optimized form of:
10486 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
10487 // (codePoint >= 0x7F && codePoint <= 0x9F);
10488 return codePoint <= 0x9F &&
10489 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
10490 }
10491
10492 /**
10493 * Returns a value indicating a character's general category.
10494 *
10495 * <p><b>Note:</b> This method cannot handle <a
10496 * href="#supplementary"> supplementary characters</a>. To support
10497 * all Unicode characters, including supplementary characters, use
10498 * the {@link #getType(int)} method.
10499 *
10500 * @param ch the character to be tested.
10501 * @return a value of type {@code int} representing the
10502 * character's general category.
10503 * @see Character#COMBINING_SPACING_MARK
10504 * @see Character#CONNECTOR_PUNCTUATION
10505 * @see Character#CONTROL
10506 * @see Character#CURRENCY_SYMBOL
10507 * @see Character#DASH_PUNCTUATION
10508 * @see Character#DECIMAL_DIGIT_NUMBER
10509 * @see Character#ENCLOSING_MARK
10510 * @see Character#END_PUNCTUATION
10511 * @see Character#FINAL_QUOTE_PUNCTUATION
10512 * @see Character#FORMAT
10513 * @see Character#INITIAL_QUOTE_PUNCTUATION
10514 * @see Character#LETTER_NUMBER
10515 * @see Character#LINE_SEPARATOR
10516 * @see Character#LOWERCASE_LETTER
10517 * @see Character#MATH_SYMBOL
10518 * @see Character#MODIFIER_LETTER
10519 * @see Character#MODIFIER_SYMBOL
10520 * @see Character#NON_SPACING_MARK
10521 * @see Character#OTHER_LETTER
10522 * @see Character#OTHER_NUMBER
10523 * @see Character#OTHER_PUNCTUATION
10524 * @see Character#OTHER_SYMBOL
10525 * @see Character#PARAGRAPH_SEPARATOR
10526 * @see Character#PRIVATE_USE
10527 * @see Character#SPACE_SEPARATOR
10528 * @see Character#START_PUNCTUATION
10529 * @see Character#SURROGATE
10530 * @see Character#TITLECASE_LETTER
10531 * @see Character#UNASSIGNED
10532 * @see Character#UPPERCASE_LETTER
10533 * @since 1.1
10534 */
10535 public static int getType(char ch) {
10536 return getType((int)ch);
10537 }
10538
10539 /**
10540 * Returns a value indicating a character's general category.
10541 *
10542 * @param codePoint the character (Unicode code point) to be tested.
10543 * @return a value of type {@code int} representing the
10544 * character's general category.
10545 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
10546 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
10547 * @see Character#CONTROL CONTROL
10548 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
10549 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
10550 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
10551 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
10552 * @see Character#END_PUNCTUATION END_PUNCTUATION
10553 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
10554 * @see Character#FORMAT FORMAT
10555 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
10556 * @see Character#LETTER_NUMBER LETTER_NUMBER
10557 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
10558 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
10559 * @see Character#MATH_SYMBOL MATH_SYMBOL
10560 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
10561 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
10562 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
10563 * @see Character#OTHER_LETTER OTHER_LETTER
10564 * @see Character#OTHER_NUMBER OTHER_NUMBER
10565 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
10566 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
10567 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
10568 * @see Character#PRIVATE_USE PRIVATE_USE
10569 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
10570 * @see Character#START_PUNCTUATION START_PUNCTUATION
10571 * @see Character#SURROGATE SURROGATE
10572 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
10573 * @see Character#UNASSIGNED UNASSIGNED
10574 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
10575 * @since 1.5
10576 */
10577 public static int getType(int codePoint) {
10578 return CharacterData.of(codePoint).getType(codePoint);
10579 }
10580
10581 /**
10582 * Determines the character representation for a specific digit in
10583 * the specified radix. If the value of {@code radix} is not a
10584 * valid radix, or the value of {@code digit} is not a valid
10585 * digit in the specified radix, the null character
10586 * ({@code '\u005Cu0000'}) is returned.
10587 * <p>
10588 * The {@code radix} argument is valid if it is greater than or
10589 * equal to {@code MIN_RADIX} and less than or equal to
10590 * {@code MAX_RADIX}. The {@code digit} argument is valid if
10591 * {@code 0 <= digit < radix}.
10592 * <p>
10593 * If the digit is less than 10, then
10594 * {@code '0' + digit} is returned. Otherwise, the value
10595 * {@code 'a' + digit - 10} is returned.
10596 *
10597 * @param digit the number to convert to a character.
10598 * @param radix the radix.
10599 * @return the {@code char} representation of the specified digit
10600 * in the specified radix.
10601 * @see Character#MIN_RADIX
10602 * @see Character#MAX_RADIX
10603 * @see Character#digit(char, int)
10604 */
10605 public static char forDigit(int digit, int radix) {
10606 if ((digit >= radix) || (digit < 0)) {
10607 return '\0';
10608 }
10609 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
10610 return '\0';
10611 }
10612 if (digit < 10) {
10613 return (char)('0' + digit);
10614 }
10615 return (char)('a' - 10 + digit);
10616 }
10617
10618 /**
10619 * Returns the Unicode directionality property for the given
10620 * character. Character directionality is used to calculate the
10621 * visual ordering of text. The directionality value of undefined
10622 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
10623 *
10624 * <p><b>Note:</b> This method cannot handle <a
10625 * href="#supplementary"> supplementary characters</a>. To support
10626 * all Unicode characters, including supplementary characters, use
10627 * the {@link #getDirectionality(int)} method.
10628 *
10629 * @param ch {@code char} for which the directionality property
10630 * is requested.
10631 * @return the directionality property of the {@code char} value.
10632 *
10633 * @see Character#DIRECTIONALITY_UNDEFINED
10634 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
10635 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
10636 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
10637 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
10638 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
10639 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
10640 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
10641 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
10642 * @see Character#DIRECTIONALITY_NONSPACING_MARK
10643 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
10644 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
10645 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
10646 * @see Character#DIRECTIONALITY_WHITESPACE
10647 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
10648 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
10649 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
10650 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
10651 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
10652 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
10653 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
10654 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
10655 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
10656 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
10657 * @since 1.4
10658 */
10659 public static byte getDirectionality(char ch) {
10660 return getDirectionality((int)ch);
10661 }
10662
10663 /**
10664 * Returns the Unicode directionality property for the given
10665 * character (Unicode code point). Character directionality is
10666 * used to calculate the visual ordering of text. The
10667 * directionality value of undefined character is {@link
10668 * #DIRECTIONALITY_UNDEFINED}.
10669 *
10670 * @param codePoint the character (Unicode code point) for which
10671 * the directionality property is requested.
10672 * @return the directionality property of the character.
10673 *
10674 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
10675 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
10676 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
10677 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
10678 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
10679 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
10680 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
10681 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
10682 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
10683 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
10684 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
10685 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
10686 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
10687 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
10688 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
10689 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
10690 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
10691 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
10692 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
10693 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
10694 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
10695 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
10696 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
10697 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
10698 * @since 1.5
10699 */
10700 public static byte getDirectionality(int codePoint) {
10701 return CharacterData.of(codePoint).getDirectionality(codePoint);
10702 }
10703
10704 /**
10705 * Determines whether the character is mirrored according to the
10706 * Unicode specification. Mirrored characters should have their
10707 * glyphs horizontally mirrored when displayed in text that is
10708 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
10709 * PARENTHESIS is semantically defined to be an <i>opening
10710 * parenthesis</i>. This will appear as a "(" in text that is
10711 * left-to-right but as a ")" in text that is right-to-left.
10712 *
10713 * <p><b>Note:</b> This method cannot handle <a
10714 * href="#supplementary"> supplementary characters</a>. To support
10715 * all Unicode characters, including supplementary characters, use
10716 * the {@link #isMirrored(int)} method.
10717 *
10718 * @param ch {@code char} for which the mirrored property is requested
10719 * @return {@code true} if the char is mirrored, {@code false}
10720 * if the {@code char} is not mirrored or is not defined.
10721 * @since 1.4
10722 */
10723 public static boolean isMirrored(char ch) {
10724 return isMirrored((int)ch);
10725 }
10726
10727 /**
10728 * Determines whether the specified character (Unicode code point)
10729 * is mirrored according to the Unicode specification. Mirrored
10730 * characters should have their glyphs horizontally mirrored when
10731 * displayed in text that is right-to-left. For example,
10732 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
10733 * defined to be an <i>opening parenthesis</i>. This will appear
10734 * as a "(" in text that is left-to-right but as a ")" in text
10735 * that is right-to-left.
10736 *
10737 * @param codePoint the character (Unicode code point) to be tested.
10738 * @return {@code true} if the character is mirrored, {@code false}
10739 * if the character is not mirrored or is not defined.
10740 * @since 1.5
10741 */
10742 public static boolean isMirrored(int codePoint) {
10743 return CharacterData.of(codePoint).isMirrored(codePoint);
10744 }
10745
10746 /**
10747 * Compares two {@code Character} objects numerically.
10748 *
10749 * @param anotherCharacter the {@code Character} to be compared.
10750
10751 * @return the value {@code 0} if the argument {@code Character}
10752 * is equal to this {@code Character}; a value less than
10753 * {@code 0} if this {@code Character} is numerically less
10754 * than the {@code Character} argument; and a value greater than
10755 * {@code 0} if this {@code Character} is numerically greater
10756 * than the {@code Character} argument (unsigned comparison).
10757 * Note that this is strictly a numerical comparison; it is not
10758 * locale-dependent.
10759 * @since 1.2
10760 */
10761 public int compareTo(Character anotherCharacter) {
10762 return compare(this.value, anotherCharacter.value);
10763 }
10764
10765 /**
10766 * Compares two {@code char} values numerically.
10767 * The value returned is identical to what would be returned by:
10768 * <pre>
10769 * Character.valueOf(x).compareTo(Character.valueOf(y))
10770 * </pre>
10771 *
10772 * @param x the first {@code char} to compare
10773 * @param y the second {@code char} to compare
10774 * @return the value {@code 0} if {@code x == y};
10775 * a value less than {@code 0} if {@code x < y}; and
10776 * a value greater than {@code 0} if {@code x > y}
10777 * @since 1.7
10778 */
10779 public static int compare(char x, char y) {
10780 return x - y;
10781 }
10782
10783 /**
10784 * Converts the character (Unicode code point) argument to uppercase using
10785 * information from the UnicodeData file.
10786 *
10787 * @param codePoint the character (Unicode code point) to be converted.
10788 * @return either the uppercase equivalent of the character, if
10789 * any, or an error flag ({@code Character.ERROR})
10790 * that indicates that a 1:M {@code char} mapping exists.
10791 * @see Character#isLowerCase(char)
10792 * @see Character#isUpperCase(char)
10793 * @see Character#toLowerCase(char)
10794 * @see Character#toTitleCase(char)
10795 * @since 1.4
10796 */
10797 static int toUpperCaseEx(int codePoint) {
10798 assert isValidCodePoint(codePoint);
10799 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
10800 }
10801
10802 /**
10803 * Converts the character (Unicode code point) argument to uppercase using case
10804 * mapping information from the SpecialCasing file in the Unicode
10805 * specification. If a character has no explicit uppercase
10806 * mapping, then the {@code char} itself is returned in the
10807 * {@code char[]}.
10808 *
10809 * @param codePoint the character (Unicode code point) to be converted.
10810 * @return a {@code char[]} with the uppercased character.
10811 * @since 1.4
10812 */
10813 static char[] toUpperCaseCharArray(int codePoint) {
10814 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
10815 assert isBmpCodePoint(codePoint);
10816 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
10817 }
10818
10819 /**
10820 * The number of bits used to represent a {@code char} value in unsigned
10821 * binary form, constant {@code 16}.
10822 *
10823 * @since 1.5
10824 */
10825 public static final int SIZE = 16;
10826
10827 /**
10828 * The number of bytes used to represent a {@code char} value in unsigned
10829 * binary form.
10830 *
10831 * @since 1.8
10832 */
10833 public static final int BYTES = SIZE / Byte.SIZE;
10834
10835 /**
10836 * Returns the value obtained by reversing the order of the bytes in the
10837 * specified {@code char} value.
10838 *
10839 * @param ch The {@code char} of which to reverse the byte order.
10840 * @return the value obtained by reversing (or, equivalently, swapping)
10841 * the bytes in the specified {@code char} value.
10842 * @since 1.5
10843 */
10844 @HotSpotIntrinsicCandidate
10845 public static char reverseBytes(char ch) {
10846 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
10847 }
10848
10849 /**
10850 * Returns the Unicode name of the specified character
10851 * {@code codePoint}, or null if the code point is
10852 * {@link #UNASSIGNED unassigned}.
10853 * <p>
10854 * Note: if the specified character is not assigned a name by
10855 * the <i>UnicodeData</i> file (part of the Unicode Character
10856 * Database maintained by the Unicode Consortium), the returned
10857 * name is the same as the result of expression.
10858 *
10859 * <blockquote>{@code
10860 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
10861 * + " "
10862 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10863 *
10864 * }</blockquote>
10865 *
10866 * @param codePoint the character (Unicode code point)
10867 *
10868 * @return the Unicode name of the specified character, or null if
10869 * the code point is unassigned.
10870 *
10871 * @throws IllegalArgumentException if the specified
10872 * {@code codePoint} is not a valid Unicode
10873 * code point.
10874 *
10875 * @since 1.7
10876 */
10877 public static String getName(int codePoint) {
10878 if (!isValidCodePoint(codePoint)) {
10879 throw new IllegalArgumentException(
10880 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10881 }
10882 String name = CharacterName.getInstance().getName(codePoint);
10883 if (name != null)
10884 return name;
10885 if (getType(codePoint) == UNASSIGNED)
10886 return null;
10887 UnicodeBlock block = UnicodeBlock.of(codePoint);
10888 if (block != null)
10889 return block.toString().replace('_', ' ') + " "
10890 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10891 // should never come here
10892 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10893 }
10894
10895 /**
10896 * Returns the code point value of the Unicode character specified by
10897 * the given Unicode character name.
10898 * <p>
10899 * Note: if a character is not assigned a name by the <i>UnicodeData</i>
10900 * file (part of the Unicode Character Database maintained by the Unicode
10901 * Consortium), its name is defined as the result of expression
10902 *
10903 * <blockquote>{@code
10904 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
10905 * + " "
10906 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10907 *
10908 * }</blockquote>
10909 * <p>
10910 * The {@code name} matching is case insensitive, with any leading and
10911 * trailing whitespace character removed.
10912 *
10913 * @param name the Unicode character name
10914 *
10915 * @return the code point value of the character specified by its name.
10916 *
10917 * @throws IllegalArgumentException if the specified {@code name}
10918 * is not a valid Unicode character name.
10919 * @throws NullPointerException if {@code name} is {@code null}
10920 *
10921 * @since 9
10922 */
10923 public static int codePointOf(String name) {
10924 name = name.trim().toUpperCase(Locale.ROOT);
10925 int cp = CharacterName.getInstance().getCodePoint(name);
10926 if (cp != -1)
10927 return cp;
10928 try {
10929 int off = name.lastIndexOf(' ');
10930 if (off != -1) {
10931 cp = Integer.parseInt(name, off + 1, name.length(), 16);
10932 if (isValidCodePoint(cp) && name.equals(getName(cp)))
10933 return cp;
10934 }
10935 } catch (Exception x) {}
10936 throw new IllegalArgumentException("Unrecognized character name :" + name);
10937 }
10938 }