1 /*
2 * Copyright (c) 2002, 2019, 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 class
39 * {@code Character} contains a single field whose type is
40 * {@code char}.
41 * <p>
42 * In addition, this class provides a large number of static methods for
43 * determining a character's category (lowercase letter, digit, etc.)
44 * and for converting characters from uppercase to lowercase and vice
45 * versa.
46 *
47 * <h3><a id="conformance">Unicode Conformance</a></h3>
48 * <p>
49 * The fields and methods of class {@code Character} are defined in terms
50 * of character information from the Unicode Standard, specifically the
51 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
52 * This file specifies properties including name and category for every
53 * assigned Unicode code point or character range. The file is available
54 * from the Unicode Consortium at
55 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
56 * <p>
57 * The Java SE 12 Platform uses character information from version 11.0
58 * of the Unicode Standard, plus the Japanese Era code point,
59 * {@code U+32FF}, from the first version of the Unicode Standard
60 * after 11.0 that assigns the code point.
61 *
62 * <h3><a id="unicode">Unicode Character Representations</a></h3>
63 *
64 * <p>The {@code char} data type (and therefore the value that a
65 * {@code Character} object encapsulates) are based on the
66 * original Unicode specification, which defined characters as
67 * fixed-width 16-bit entities. The Unicode Standard has since been
68 * changed to allow for characters whose representation requires more
69 * than 16 bits. The range of legal <em>code point</em>s is now
70 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
71 * (Refer to the <a
72 * href="http://www.unicode.org/reports/tr27/#notation"><i>
73 * definition</i></a> of the U+<i>n</i> notation in the Unicode
74 * Standard.)
75 *
76 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
77 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
78 * <a id="supplementary">Characters</a> whose code points are greater
79 * than U+FFFF are called <em>supplementary character</em>s. The Java
80 * platform uses the UTF-16 representation in {@code char} arrays and
81 * in the {@code String} and {@code StringBuffer} classes. In
82 * this representation, supplementary characters are represented as a pair
83 * of {@code char} values, the first from the <em>high-surrogates</em>
84 * range, (\uD800-\uDBFF), the second from the
85 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
86 *
87 * <p>A {@code char} value, therefore, represents Basic
88 * Multilingual Plane (BMP) code points, including the surrogate
89 * code points, or code units of the UTF-16 encoding. An
90 * {@code int} value represents all Unicode code points,
91 * including supplementary code points. The lower (least significant)
92 * 21 bits of {@code int} are used to represent Unicode code
93 * points and the upper (most significant) 11 bits must be zero.
94 * Unless otherwise specified, the behavior with respect to
95 * supplementary characters and surrogate {@code char} values is
96 * as follows:
97 *
98 * <ul>
99 * <li>The methods that only accept a {@code char} value cannot support
100 * supplementary characters. They treat {@code char} values from the
101 * surrogate ranges as undefined characters. For example,
102 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
103 * this specific value if followed by any low-surrogate value in a string
104 * would represent a letter.
105 *
106 * <li>The methods that accept an {@code int} value support all
107 * Unicode characters, including supplementary characters. For
108 * example, {@code Character.isLetter(0x2F81A)} returns
109 * {@code true} because the code point value represents a letter
110 * (a CJK ideograph).
111 * </ul>
112 *
113 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
114 * used for character values in the range between U+0000 and U+10FFFF,
115 * and <em>Unicode code unit</em> is used for 16-bit
116 * {@code char} values that are code units of the <em>UTF-16</em>
117 * encoding. For more information on Unicode terminology, refer to the
118 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
119 *
120 * @author Lee Boynton
121 * @author Guy Steele
122 * @author Akira Tanaka
123 * @author Martin Buchholz
124 * @author Ulf Zibis
125 * @since 1.0
126 */
127 public final
128 class Character implements java.io.Serializable, Comparable<Character> {
129 /**
130 * The minimum radix available for conversion to and from strings.
131 * The constant value of this field is the smallest value permitted
132 * for the radix argument in radix-conversion methods such as the
133 * {@code digit} method, the {@code forDigit} method, and the
134 * {@code toString} method of class {@code Integer}.
135 *
136 * @see Character#digit(char, int)
137 * @see Character#forDigit(int, int)
138 * @see Integer#toString(int, int)
139 * @see Integer#valueOf(String)
140 */
141 public static final int MIN_RADIX = 2;
142
143 /**
144 * The maximum radix available for conversion to and from strings.
145 * The constant value of this field is the largest value permitted
146 * for the radix argument in radix-conversion methods such as the
147 * {@code digit} method, the {@code forDigit} method, and the
148 * {@code toString} method of class {@code Integer}.
149 *
150 * @see Character#digit(char, int)
151 * @see Character#forDigit(int, int)
152 * @see Integer#toString(int, int)
153 * @see Integer#valueOf(String)
154 */
155 public static final int MAX_RADIX = 36;
156
157 /**
158 * The constant value of this field is the smallest value of type
159 * {@code char}, {@code '\u005Cu0000'}.
160 *
161 * @since 1.0.2
162 */
163 public static final char MIN_VALUE = '\u0000';
164
165 /**
166 * The constant value of this field is the largest value of type
167 * {@code char}, {@code '\u005CuFFFF'}.
168 *
169 * @since 1.0.2
170 */
171 public static final char MAX_VALUE = '\uFFFF';
172
173 /**
174 * The {@code Class} instance representing the primitive type
175 * {@code char}.
176 *
177 * @since 1.1
178 */
179 @SuppressWarnings("unchecked")
180 public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char");
181
182 /*
183 * Normative general types
184 */
185
186 /*
187 * General character types
188 */
189
190 /**
191 * General category "Cn" in the Unicode specification.
192 * @since 1.1
193 */
194 public static final byte UNASSIGNED = 0;
195
196 /**
197 * General category "Lu" in the Unicode specification.
198 * @since 1.1
199 */
200 public static final byte UPPERCASE_LETTER = 1;
201
202 /**
203 * General category "Ll" in the Unicode specification.
204 * @since 1.1
205 */
206 public static final byte LOWERCASE_LETTER = 2;
207
208 /**
209 * General category "Lt" in the Unicode specification.
210 * @since 1.1
211 */
212 public static final byte TITLECASE_LETTER = 3;
213
214 /**
215 * General category "Lm" in the Unicode specification.
216 * @since 1.1
217 */
218 public static final byte MODIFIER_LETTER = 4;
219
220 /**
221 * General category "Lo" in the Unicode specification.
222 * @since 1.1
223 */
224 public static final byte OTHER_LETTER = 5;
225
226 /**
227 * General category "Mn" in the Unicode specification.
228 * @since 1.1
229 */
230 public static final byte NON_SPACING_MARK = 6;
231
232 /**
233 * General category "Me" in the Unicode specification.
234 * @since 1.1
235 */
236 public static final byte ENCLOSING_MARK = 7;
237
238 /**
239 * General category "Mc" in the Unicode specification.
240 * @since 1.1
241 */
242 public static final byte COMBINING_SPACING_MARK = 8;
243
244 /**
245 * General category "Nd" in the Unicode specification.
246 * @since 1.1
247 */
248 public static final byte DECIMAL_DIGIT_NUMBER = 9;
249
250 /**
251 * General category "Nl" in the Unicode specification.
252 * @since 1.1
253 */
254 public static final byte LETTER_NUMBER = 10;
255
256 /**
257 * General category "No" in the Unicode specification.
258 * @since 1.1
259 */
260 public static final byte OTHER_NUMBER = 11;
261
262 /**
263 * General category "Zs" in the Unicode specification.
264 * @since 1.1
265 */
266 public static final byte SPACE_SEPARATOR = 12;
267
268 /**
269 * General category "Zl" in the Unicode specification.
270 * @since 1.1
271 */
272 public static final byte LINE_SEPARATOR = 13;
273
274 /**
275 * General category "Zp" in the Unicode specification.
276 * @since 1.1
277 */
278 public static final byte PARAGRAPH_SEPARATOR = 14;
279
280 /**
281 * General category "Cc" in the Unicode specification.
282 * @since 1.1
283 */
284 public static final byte CONTROL = 15;
285
286 /**
287 * General category "Cf" in the Unicode specification.
288 * @since 1.1
289 */
290 public static final byte FORMAT = 16;
291
292 /**
293 * General category "Co" in the Unicode specification.
294 * @since 1.1
295 */
296 public static final byte PRIVATE_USE = 18;
297
298 /**
299 * General category "Cs" in the Unicode specification.
300 * @since 1.1
301 */
302 public static final byte SURROGATE = 19;
303
304 /**
305 * General category "Pd" in the Unicode specification.
306 * @since 1.1
307 */
308 public static final byte DASH_PUNCTUATION = 20;
309
310 /**
311 * General category "Ps" in the Unicode specification.
312 * @since 1.1
313 */
314 public static final byte START_PUNCTUATION = 21;
315
316 /**
317 * General category "Pe" in the Unicode specification.
318 * @since 1.1
319 */
320 public static final byte END_PUNCTUATION = 22;
321
322 /**
323 * General category "Pc" in the Unicode specification.
324 * @since 1.1
325 */
326 public static final byte CONNECTOR_PUNCTUATION = 23;
327
328 /**
329 * General category "Po" in the Unicode specification.
330 * @since 1.1
331 */
332 public static final byte OTHER_PUNCTUATION = 24;
333
334 /**
335 * General category "Sm" in the Unicode specification.
336 * @since 1.1
337 */
338 public static final byte MATH_SYMBOL = 25;
339
340 /**
341 * General category "Sc" in the Unicode specification.
342 * @since 1.1
343 */
344 public static final byte CURRENCY_SYMBOL = 26;
345
346 /**
347 * General category "Sk" in the Unicode specification.
348 * @since 1.1
349 */
350 public static final byte MODIFIER_SYMBOL = 27;
351
352 /**
353 * General category "So" in the Unicode specification.
354 * @since 1.1
355 */
356 public static final byte OTHER_SYMBOL = 28;
357
358 /**
359 * General category "Pi" in the Unicode specification.
360 * @since 1.4
361 */
362 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
363
364 /**
365 * General category "Pf" in the Unicode specification.
366 * @since 1.4
367 */
368 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
369
370 /**
371 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
372 */
373 static final int ERROR = 0xFFFFFFFF;
374
375
376 /**
377 * Undefined bidirectional character type. Undefined {@code char}
378 * values have undefined directionality in the Unicode specification.
379 * @since 1.4
380 */
381 public static final byte DIRECTIONALITY_UNDEFINED = -1;
382
383 /**
384 * Strong bidirectional character type "L" in the Unicode specification.
385 * @since 1.4
386 */
387 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
388
389 /**
390 * Strong bidirectional character type "R" in the Unicode specification.
391 * @since 1.4
392 */
393 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
394
395 /**
396 * Strong bidirectional character type "AL" in the Unicode specification.
397 * @since 1.4
398 */
399 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
400
401 /**
402 * Weak bidirectional character type "EN" in the Unicode specification.
403 * @since 1.4
404 */
405 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
406
407 /**
408 * Weak bidirectional character type "ES" in the Unicode specification.
409 * @since 1.4
410 */
411 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
412
413 /**
414 * Weak bidirectional character type "ET" in the Unicode specification.
415 * @since 1.4
416 */
417 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
418
419 /**
420 * Weak bidirectional character type "AN" in the Unicode specification.
421 * @since 1.4
422 */
423 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
424
425 /**
426 * Weak bidirectional character type "CS" in the Unicode specification.
427 * @since 1.4
428 */
429 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
430
431 /**
432 * Weak bidirectional character type "NSM" in the Unicode specification.
433 * @since 1.4
434 */
435 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
436
437 /**
438 * Weak bidirectional character type "BN" in the Unicode specification.
439 * @since 1.4
440 */
441 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
442
443 /**
444 * Neutral bidirectional character type "B" in the Unicode specification.
445 * @since 1.4
446 */
447 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
448
449 /**
450 * Neutral bidirectional character type "S" in the Unicode specification.
451 * @since 1.4
452 */
453 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
454
455 /**
456 * Neutral bidirectional character type "WS" in the Unicode specification.
457 * @since 1.4
458 */
459 public static final byte DIRECTIONALITY_WHITESPACE = 12;
460
461 /**
462 * Neutral bidirectional character type "ON" in the Unicode specification.
463 * @since 1.4
464 */
465 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
466
467 /**
468 * Strong bidirectional character type "LRE" in the Unicode specification.
469 * @since 1.4
470 */
471 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
472
473 /**
474 * Strong bidirectional character type "LRO" in the Unicode specification.
475 * @since 1.4
476 */
477 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
478
479 /**
480 * Strong bidirectional character type "RLE" in the Unicode specification.
481 * @since 1.4
482 */
483 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
484
485 /**
486 * Strong bidirectional character type "RLO" in the Unicode specification.
487 * @since 1.4
488 */
489 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
490
491 /**
492 * Weak bidirectional character type "PDF" in the Unicode specification.
493 * @since 1.4
494 */
495 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
496
497 /**
498 * Weak bidirectional character type "LRI" in the Unicode specification.
499 * @since 9
500 */
501 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
502
503 /**
504 * Weak bidirectional character type "RLI" in the Unicode specification.
505 * @since 9
506 */
507 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
508
509 /**
510 * Weak bidirectional character type "FSI" in the Unicode specification.
511 * @since 9
512 */
513 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
514
515 /**
516 * Weak bidirectional character type "PDI" in the Unicode specification.
517 * @since 9
518 */
519 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
520
521 /**
522 * The minimum value of a
523 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
524 * Unicode high-surrogate code unit</a>
525 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
526 * A high-surrogate is also known as a <i>leading-surrogate</i>.
527 *
528 * @since 1.5
529 */
530 public static final char MIN_HIGH_SURROGATE = '\uD800';
531
532 /**
533 * The maximum value of a
534 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
535 * Unicode high-surrogate code unit</a>
536 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
537 * A high-surrogate is also known as a <i>leading-surrogate</i>.
538 *
539 * @since 1.5
540 */
541 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
542
543 /**
544 * The minimum value of a
545 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
546 * Unicode low-surrogate code unit</a>
547 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
548 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
549 *
550 * @since 1.5
551 */
552 public static final char MIN_LOW_SURROGATE = '\uDC00';
553
554 /**
555 * The maximum value of a
556 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
557 * Unicode low-surrogate code unit</a>
558 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
559 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
560 *
561 * @since 1.5
562 */
563 public static final char MAX_LOW_SURROGATE = '\uDFFF';
564
565 /**
566 * The minimum value of a Unicode surrogate code unit in the
567 * UTF-16 encoding, constant {@code '\u005CuD800'}.
568 *
569 * @since 1.5
570 */
571 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
572
573 /**
574 * The maximum value of a Unicode surrogate code unit in the
575 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
576 *
577 * @since 1.5
578 */
579 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
580
581 /**
582 * The minimum value of a
583 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
584 * Unicode supplementary code point</a>, constant {@code U+10000}.
585 *
586 * @since 1.5
587 */
588 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
589
590 /**
591 * The minimum value of a
592 * <a href="http://www.unicode.org/glossary/#code_point">
593 * Unicode code point</a>, constant {@code U+0000}.
594 *
595 * @since 1.5
596 */
597 public static final int MIN_CODE_POINT = 0x000000;
598
599 /**
600 * The maximum value of a
601 * <a href="http://www.unicode.org/glossary/#code_point">
602 * Unicode code point</a>, constant {@code U+10FFFF}.
603 *
604 * @since 1.5
605 */
606 public static final int MAX_CODE_POINT = 0X10FFFF;
607
608
609 /**
610 * Instances of this class represent particular subsets of the Unicode
611 * character set. The only family of subsets defined in the
612 * {@code Character} class is {@link Character.UnicodeBlock}.
613 * Other portions of the Java API may define other subsets for their
614 * own purposes.
615 *
616 * @since 1.2
617 */
618 public static class Subset {
619
620 private String name;
621
622 /**
623 * Constructs a new {@code Subset} instance.
624 *
625 * @param name The name of this subset
626 * @throws NullPointerException if name is {@code null}
627 */
628 protected Subset(String name) {
629 if (name == null) {
630 throw new NullPointerException("name");
631 }
632 this.name = name;
633 }
634
635 /**
636 * Compares two {@code Subset} objects for equality.
637 * This method returns {@code true} if and only if
638 * {@code this} and the argument refer to the same
639 * object; since this method is {@code final}, this
640 * guarantee holds for all subclasses.
641 */
642 public final boolean equals(Object obj) {
643 return (this == obj);
644 }
645
646 /**
647 * Returns the standard hash code as defined by the
648 * {@link Object#hashCode} method. This method
649 * is {@code final} in order to ensure that the
650 * {@code equals} and {@code hashCode} methods will
651 * be consistent in all subclasses.
652 */
653 public final int hashCode() {
654 return super.hashCode();
655 }
656
657 /**
658 * Returns the name of this subset.
659 */
660 public final String toString() {
661 return name;
662 }
663 }
664
665 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
666 // for the latest specification of Unicode Blocks.
667
668 /**
669 * A family of character subsets representing the character blocks in the
670 * Unicode specification. Character blocks generally define characters
671 * used for a specific script or purpose. A character is contained by
672 * at most one Unicode block.
673 *
674 * @since 1.2
675 */
676 public static final class UnicodeBlock extends Subset {
677 /**
678 * 667 - the expected number of entities
679 * 0.75 - the default load factor of HashMap
680 */
681 private static final int NUM_ENTITIES = 667;
682 private static Map<String, UnicodeBlock> map =
683 new HashMap<>((int)(NUM_ENTITIES / 0.75f + 1.0f));
684
685 /**
686 * Creates a UnicodeBlock with the given identifier name.
687 * This name must be the same as the block identifier.
688 */
689 private UnicodeBlock(String idName) {
690 super(idName);
691 map.put(idName, this);
692 }
693
694 /**
695 * Creates a UnicodeBlock with the given identifier name and
696 * alias name.
697 */
698 private UnicodeBlock(String idName, String alias) {
699 this(idName);
700 map.put(alias, this);
701 }
702
703 /**
704 * Creates a UnicodeBlock with the given identifier name and
705 * alias names.
706 */
707 private UnicodeBlock(String idName, String... aliases) {
708 this(idName);
709 for (String alias : aliases)
710 map.put(alias, this);
711 }
712
713 /**
714 * Constant for the "Basic Latin" Unicode character block.
715 * @since 1.2
716 */
717 public static final UnicodeBlock BASIC_LATIN =
718 new UnicodeBlock("BASIC_LATIN",
719 "BASIC LATIN",
720 "BASICLATIN");
721
722 /**
723 * Constant for the "Latin-1 Supplement" Unicode character block.
724 * @since 1.2
725 */
726 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
727 new UnicodeBlock("LATIN_1_SUPPLEMENT",
728 "LATIN-1 SUPPLEMENT",
729 "LATIN-1SUPPLEMENT");
730
731 /**
732 * Constant for the "Latin Extended-A" Unicode character block.
733 * @since 1.2
734 */
735 public static final UnicodeBlock LATIN_EXTENDED_A =
736 new UnicodeBlock("LATIN_EXTENDED_A",
737 "LATIN EXTENDED-A",
738 "LATINEXTENDED-A");
739
740 /**
741 * Constant for the "Latin Extended-B" Unicode character block.
742 * @since 1.2
743 */
744 public static final UnicodeBlock LATIN_EXTENDED_B =
745 new UnicodeBlock("LATIN_EXTENDED_B",
746 "LATIN EXTENDED-B",
747 "LATINEXTENDED-B");
748
749 /**
750 * Constant for the "IPA Extensions" Unicode character block.
751 * @since 1.2
752 */
753 public static final UnicodeBlock IPA_EXTENSIONS =
754 new UnicodeBlock("IPA_EXTENSIONS",
755 "IPA EXTENSIONS",
756 "IPAEXTENSIONS");
757
758 /**
759 * Constant for the "Spacing Modifier Letters" Unicode character block.
760 * @since 1.2
761 */
762 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
763 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
764 "SPACING MODIFIER LETTERS",
765 "SPACINGMODIFIERLETTERS");
766
767 /**
768 * Constant for the "Combining Diacritical Marks" Unicode character block.
769 * @since 1.2
770 */
771 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
772 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
773 "COMBINING DIACRITICAL MARKS",
774 "COMBININGDIACRITICALMARKS");
775
776 /**
777 * Constant for the "Greek and Coptic" Unicode character block.
778 * <p>
779 * This block was previously known as the "Greek" block.
780 *
781 * @since 1.2
782 */
783 public static final UnicodeBlock GREEK =
784 new UnicodeBlock("GREEK",
785 "GREEK AND COPTIC",
786 "GREEKANDCOPTIC");
787
788 /**
789 * Constant for the "Cyrillic" Unicode character block.
790 * @since 1.2
791 */
792 public static final UnicodeBlock CYRILLIC =
793 new UnicodeBlock("CYRILLIC");
794
795 /**
796 * Constant for the "Armenian" Unicode character block.
797 * @since 1.2
798 */
799 public static final UnicodeBlock ARMENIAN =
800 new UnicodeBlock("ARMENIAN");
801
802 /**
803 * Constant for the "Hebrew" Unicode character block.
804 * @since 1.2
805 */
806 public static final UnicodeBlock HEBREW =
807 new UnicodeBlock("HEBREW");
808
809 /**
810 * Constant for the "Arabic" Unicode character block.
811 * @since 1.2
812 */
813 public static final UnicodeBlock ARABIC =
814 new UnicodeBlock("ARABIC");
815
816 /**
817 * Constant for the "Devanagari" Unicode character block.
818 * @since 1.2
819 */
820 public static final UnicodeBlock DEVANAGARI =
821 new UnicodeBlock("DEVANAGARI");
822
823 /**
824 * Constant for the "Bengali" Unicode character block.
825 * @since 1.2
826 */
827 public static final UnicodeBlock BENGALI =
828 new UnicodeBlock("BENGALI");
829
830 /**
831 * Constant for the "Gurmukhi" Unicode character block.
832 * @since 1.2
833 */
834 public static final UnicodeBlock GURMUKHI =
835 new UnicodeBlock("GURMUKHI");
836
837 /**
838 * Constant for the "Gujarati" Unicode character block.
839 * @since 1.2
840 */
841 public static final UnicodeBlock GUJARATI =
842 new UnicodeBlock("GUJARATI");
843
844 /**
845 * Constant for the "Oriya" Unicode character block.
846 * @since 1.2
847 */
848 public static final UnicodeBlock ORIYA =
849 new UnicodeBlock("ORIYA");
850
851 /**
852 * Constant for the "Tamil" Unicode character block.
853 * @since 1.2
854 */
855 public static final UnicodeBlock TAMIL =
856 new UnicodeBlock("TAMIL");
857
858 /**
859 * Constant for the "Telugu" Unicode character block.
860 * @since 1.2
861 */
862 public static final UnicodeBlock TELUGU =
863 new UnicodeBlock("TELUGU");
864
865 /**
866 * Constant for the "Kannada" Unicode character block.
867 * @since 1.2
868 */
869 public static final UnicodeBlock KANNADA =
870 new UnicodeBlock("KANNADA");
871
872 /**
873 * Constant for the "Malayalam" Unicode character block.
874 * @since 1.2
875 */
876 public static final UnicodeBlock MALAYALAM =
877 new UnicodeBlock("MALAYALAM");
878
879 /**
880 * Constant for the "Thai" Unicode character block.
881 * @since 1.2
882 */
883 public static final UnicodeBlock THAI =
884 new UnicodeBlock("THAI");
885
886 /**
887 * Constant for the "Lao" Unicode character block.
888 * @since 1.2
889 */
890 public static final UnicodeBlock LAO =
891 new UnicodeBlock("LAO");
892
893 /**
894 * Constant for the "Tibetan" Unicode character block.
895 * @since 1.2
896 */
897 public static final UnicodeBlock TIBETAN =
898 new UnicodeBlock("TIBETAN");
899
900 /**
901 * Constant for the "Georgian" Unicode character block.
902 * @since 1.2
903 */
904 public static final UnicodeBlock GEORGIAN =
905 new UnicodeBlock("GEORGIAN");
906
907 /**
908 * Constant for the "Hangul Jamo" Unicode character block.
909 * @since 1.2
910 */
911 public static final UnicodeBlock HANGUL_JAMO =
912 new UnicodeBlock("HANGUL_JAMO",
913 "HANGUL JAMO",
914 "HANGULJAMO");
915
916 /**
917 * Constant for the "Latin Extended Additional" Unicode character block.
918 * @since 1.2
919 */
920 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
921 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
922 "LATIN EXTENDED ADDITIONAL",
923 "LATINEXTENDEDADDITIONAL");
924
925 /**
926 * Constant for the "Greek Extended" Unicode character block.
927 * @since 1.2
928 */
929 public static final UnicodeBlock GREEK_EXTENDED =
930 new UnicodeBlock("GREEK_EXTENDED",
931 "GREEK EXTENDED",
932 "GREEKEXTENDED");
933
934 /**
935 * Constant for the "General Punctuation" Unicode character block.
936 * @since 1.2
937 */
938 public static final UnicodeBlock GENERAL_PUNCTUATION =
939 new UnicodeBlock("GENERAL_PUNCTUATION",
940 "GENERAL PUNCTUATION",
941 "GENERALPUNCTUATION");
942
943 /**
944 * Constant for the "Superscripts and Subscripts" Unicode character
945 * block.
946 * @since 1.2
947 */
948 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
949 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
950 "SUPERSCRIPTS AND SUBSCRIPTS",
951 "SUPERSCRIPTSANDSUBSCRIPTS");
952
953 /**
954 * Constant for the "Currency Symbols" Unicode character block.
955 * @since 1.2
956 */
957 public static final UnicodeBlock CURRENCY_SYMBOLS =
958 new UnicodeBlock("CURRENCY_SYMBOLS",
959 "CURRENCY SYMBOLS",
960 "CURRENCYSYMBOLS");
961
962 /**
963 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
964 * character block.
965 * <p>
966 * This block was previously known as "Combining Marks for Symbols".
967 * @since 1.2
968 */
969 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
970 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
971 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
972 "COMBININGDIACRITICALMARKSFORSYMBOLS",
973 "COMBINING MARKS FOR SYMBOLS",
974 "COMBININGMARKSFORSYMBOLS");
975
976 /**
977 * Constant for the "Letterlike Symbols" Unicode character block.
978 * @since 1.2
979 */
980 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
981 new UnicodeBlock("LETTERLIKE_SYMBOLS",
982 "LETTERLIKE SYMBOLS",
983 "LETTERLIKESYMBOLS");
984
985 /**
986 * Constant for the "Number Forms" Unicode character block.
987 * @since 1.2
988 */
989 public static final UnicodeBlock NUMBER_FORMS =
990 new UnicodeBlock("NUMBER_FORMS",
991 "NUMBER FORMS",
992 "NUMBERFORMS");
993
994 /**
995 * Constant for the "Arrows" Unicode character block.
996 * @since 1.2
997 */
998 public static final UnicodeBlock ARROWS =
999 new UnicodeBlock("ARROWS");
1000
1001 /**
1002 * Constant for the "Mathematical Operators" Unicode character block.
1003 * @since 1.2
1004 */
1005 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1006 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1007 "MATHEMATICAL OPERATORS",
1008 "MATHEMATICALOPERATORS");
1009
1010 /**
1011 * Constant for the "Miscellaneous Technical" Unicode character block.
1012 * @since 1.2
1013 */
1014 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1015 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1016 "MISCELLANEOUS TECHNICAL",
1017 "MISCELLANEOUSTECHNICAL");
1018
1019 /**
1020 * Constant for the "Control Pictures" Unicode character block.
1021 * @since 1.2
1022 */
1023 public static final UnicodeBlock CONTROL_PICTURES =
1024 new UnicodeBlock("CONTROL_PICTURES",
1025 "CONTROL PICTURES",
1026 "CONTROLPICTURES");
1027
1028 /**
1029 * Constant for the "Optical Character Recognition" Unicode character block.
1030 * @since 1.2
1031 */
1032 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1033 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1034 "OPTICAL CHARACTER RECOGNITION",
1035 "OPTICALCHARACTERRECOGNITION");
1036
1037 /**
1038 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1039 * @since 1.2
1040 */
1041 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1042 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1043 "ENCLOSED ALPHANUMERICS",
1044 "ENCLOSEDALPHANUMERICS");
1045
1046 /**
1047 * Constant for the "Box Drawing" Unicode character block.
1048 * @since 1.2
1049 */
1050 public static final UnicodeBlock BOX_DRAWING =
1051 new UnicodeBlock("BOX_DRAWING",
1052 "BOX DRAWING",
1053 "BOXDRAWING");
1054
1055 /**
1056 * Constant for the "Block Elements" Unicode character block.
1057 * @since 1.2
1058 */
1059 public static final UnicodeBlock BLOCK_ELEMENTS =
1060 new UnicodeBlock("BLOCK_ELEMENTS",
1061 "BLOCK ELEMENTS",
1062 "BLOCKELEMENTS");
1063
1064 /**
1065 * Constant for the "Geometric Shapes" Unicode character block.
1066 * @since 1.2
1067 */
1068 public static final UnicodeBlock GEOMETRIC_SHAPES =
1069 new UnicodeBlock("GEOMETRIC_SHAPES",
1070 "GEOMETRIC SHAPES",
1071 "GEOMETRICSHAPES");
1072
1073 /**
1074 * Constant for the "Miscellaneous Symbols" Unicode character block.
1075 * @since 1.2
1076 */
1077 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1078 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1079 "MISCELLANEOUS SYMBOLS",
1080 "MISCELLANEOUSSYMBOLS");
1081
1082 /**
1083 * Constant for the "Dingbats" Unicode character block.
1084 * @since 1.2
1085 */
1086 public static final UnicodeBlock DINGBATS =
1087 new UnicodeBlock("DINGBATS");
1088
1089 /**
1090 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1091 * @since 1.2
1092 */
1093 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1094 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1095 "CJK SYMBOLS AND PUNCTUATION",
1096 "CJKSYMBOLSANDPUNCTUATION");
1097
1098 /**
1099 * Constant for the "Hiragana" Unicode character block.
1100 * @since 1.2
1101 */
1102 public static final UnicodeBlock HIRAGANA =
1103 new UnicodeBlock("HIRAGANA");
1104
1105 /**
1106 * Constant for the "Katakana" Unicode character block.
1107 * @since 1.2
1108 */
1109 public static final UnicodeBlock KATAKANA =
1110 new UnicodeBlock("KATAKANA");
1111
1112 /**
1113 * Constant for the "Bopomofo" Unicode character block.
1114 * @since 1.2
1115 */
1116 public static final UnicodeBlock BOPOMOFO =
1117 new UnicodeBlock("BOPOMOFO");
1118
1119 /**
1120 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1121 * @since 1.2
1122 */
1123 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1124 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1125 "HANGUL COMPATIBILITY JAMO",
1126 "HANGULCOMPATIBILITYJAMO");
1127
1128 /**
1129 * Constant for the "Kanbun" Unicode character block.
1130 * @since 1.2
1131 */
1132 public static final UnicodeBlock KANBUN =
1133 new UnicodeBlock("KANBUN");
1134
1135 /**
1136 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1137 * @since 1.2
1138 */
1139 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1140 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1141 "ENCLOSED CJK LETTERS AND MONTHS",
1142 "ENCLOSEDCJKLETTERSANDMONTHS");
1143
1144 /**
1145 * Constant for the "CJK Compatibility" Unicode character block.
1146 * @since 1.2
1147 */
1148 public static final UnicodeBlock CJK_COMPATIBILITY =
1149 new UnicodeBlock("CJK_COMPATIBILITY",
1150 "CJK COMPATIBILITY",
1151 "CJKCOMPATIBILITY");
1152
1153 /**
1154 * Constant for the "CJK Unified Ideographs" Unicode character block.
1155 * @since 1.2
1156 */
1157 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1158 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1159 "CJK UNIFIED IDEOGRAPHS",
1160 "CJKUNIFIEDIDEOGRAPHS");
1161
1162 /**
1163 * Constant for the "Hangul Syllables" Unicode character block.
1164 * @since 1.2
1165 */
1166 public static final UnicodeBlock HANGUL_SYLLABLES =
1167 new UnicodeBlock("HANGUL_SYLLABLES",
1168 "HANGUL SYLLABLES",
1169 "HANGULSYLLABLES");
1170
1171 /**
1172 * Constant for the "Private Use Area" Unicode character block.
1173 * @since 1.2
1174 */
1175 public static final UnicodeBlock PRIVATE_USE_AREA =
1176 new UnicodeBlock("PRIVATE_USE_AREA",
1177 "PRIVATE USE AREA",
1178 "PRIVATEUSEAREA");
1179
1180 /**
1181 * Constant for the "CJK Compatibility Ideographs" Unicode character
1182 * block.
1183 * @since 1.2
1184 */
1185 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1186 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1187 "CJK COMPATIBILITY IDEOGRAPHS",
1188 "CJKCOMPATIBILITYIDEOGRAPHS");
1189
1190 /**
1191 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1192 * @since 1.2
1193 */
1194 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1195 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1196 "ALPHABETIC PRESENTATION FORMS",
1197 "ALPHABETICPRESENTATIONFORMS");
1198
1199 /**
1200 * Constant for the "Arabic Presentation Forms-A" Unicode character
1201 * block.
1202 * @since 1.2
1203 */
1204 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1205 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1206 "ARABIC PRESENTATION FORMS-A",
1207 "ARABICPRESENTATIONFORMS-A");
1208
1209 /**
1210 * Constant for the "Combining Half Marks" Unicode character block.
1211 * @since 1.2
1212 */
1213 public static final UnicodeBlock COMBINING_HALF_MARKS =
1214 new UnicodeBlock("COMBINING_HALF_MARKS",
1215 "COMBINING HALF MARKS",
1216 "COMBININGHALFMARKS");
1217
1218 /**
1219 * Constant for the "CJK Compatibility Forms" Unicode character block.
1220 * @since 1.2
1221 */
1222 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1223 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1224 "CJK COMPATIBILITY FORMS",
1225 "CJKCOMPATIBILITYFORMS");
1226
1227 /**
1228 * Constant for the "Small Form Variants" Unicode character block.
1229 * @since 1.2
1230 */
1231 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1232 new UnicodeBlock("SMALL_FORM_VARIANTS",
1233 "SMALL FORM VARIANTS",
1234 "SMALLFORMVARIANTS");
1235
1236 /**
1237 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1238 * @since 1.2
1239 */
1240 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1241 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1242 "ARABIC PRESENTATION FORMS-B",
1243 "ARABICPRESENTATIONFORMS-B");
1244
1245 /**
1246 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1247 * block.
1248 * @since 1.2
1249 */
1250 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1251 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1252 "HALFWIDTH AND FULLWIDTH FORMS",
1253 "HALFWIDTHANDFULLWIDTHFORMS");
1254
1255 /**
1256 * Constant for the "Specials" Unicode character block.
1257 * @since 1.2
1258 */
1259 public static final UnicodeBlock SPECIALS =
1260 new UnicodeBlock("SPECIALS");
1261
1262 /**
1263 * @deprecated
1264 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1265 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1266 * These constants match the block definitions of the Unicode Standard.
1267 * The {@link #of(char)} and {@link #of(int)} methods return the
1268 * standard constants.
1269 */
1270 @Deprecated(since="1.5")
1271 public static final UnicodeBlock SURROGATES_AREA =
1272 new UnicodeBlock("SURROGATES_AREA");
1273
1274 /**
1275 * Constant for the "Syriac" Unicode character block.
1276 * @since 1.4
1277 */
1278 public static final UnicodeBlock SYRIAC =
1279 new UnicodeBlock("SYRIAC");
1280
1281 /**
1282 * Constant for the "Thaana" Unicode character block.
1283 * @since 1.4
1284 */
1285 public static final UnicodeBlock THAANA =
1286 new UnicodeBlock("THAANA");
1287
1288 /**
1289 * Constant for the "Sinhala" Unicode character block.
1290 * @since 1.4
1291 */
1292 public static final UnicodeBlock SINHALA =
1293 new UnicodeBlock("SINHALA");
1294
1295 /**
1296 * Constant for the "Myanmar" Unicode character block.
1297 * @since 1.4
1298 */
1299 public static final UnicodeBlock MYANMAR =
1300 new UnicodeBlock("MYANMAR");
1301
1302 /**
1303 * Constant for the "Ethiopic" Unicode character block.
1304 * @since 1.4
1305 */
1306 public static final UnicodeBlock ETHIOPIC =
1307 new UnicodeBlock("ETHIOPIC");
1308
1309 /**
1310 * Constant for the "Cherokee" Unicode character block.
1311 * @since 1.4
1312 */
1313 public static final UnicodeBlock CHEROKEE =
1314 new UnicodeBlock("CHEROKEE");
1315
1316 /**
1317 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1318 * @since 1.4
1319 */
1320 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1321 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1322 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1323 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1324
1325 /**
1326 * Constant for the "Ogham" Unicode character block.
1327 * @since 1.4
1328 */
1329 public static final UnicodeBlock OGHAM =
1330 new UnicodeBlock("OGHAM");
1331
1332 /**
1333 * Constant for the "Runic" Unicode character block.
1334 * @since 1.4
1335 */
1336 public static final UnicodeBlock RUNIC =
1337 new UnicodeBlock("RUNIC");
1338
1339 /**
1340 * Constant for the "Khmer" Unicode character block.
1341 * @since 1.4
1342 */
1343 public static final UnicodeBlock KHMER =
1344 new UnicodeBlock("KHMER");
1345
1346 /**
1347 * Constant for the "Mongolian" Unicode character block.
1348 * @since 1.4
1349 */
1350 public static final UnicodeBlock MONGOLIAN =
1351 new UnicodeBlock("MONGOLIAN");
1352
1353 /**
1354 * Constant for the "Braille Patterns" Unicode character block.
1355 * @since 1.4
1356 */
1357 public static final UnicodeBlock BRAILLE_PATTERNS =
1358 new UnicodeBlock("BRAILLE_PATTERNS",
1359 "BRAILLE PATTERNS",
1360 "BRAILLEPATTERNS");
1361
1362 /**
1363 * Constant for the "CJK Radicals Supplement" Unicode character block.
1364 * @since 1.4
1365 */
1366 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1367 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1368 "CJK RADICALS SUPPLEMENT",
1369 "CJKRADICALSSUPPLEMENT");
1370
1371 /**
1372 * Constant for the "Kangxi Radicals" Unicode character block.
1373 * @since 1.4
1374 */
1375 public static final UnicodeBlock KANGXI_RADICALS =
1376 new UnicodeBlock("KANGXI_RADICALS",
1377 "KANGXI RADICALS",
1378 "KANGXIRADICALS");
1379
1380 /**
1381 * Constant for the "Ideographic Description Characters" Unicode character block.
1382 * @since 1.4
1383 */
1384 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1385 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1386 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1387 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1388
1389 /**
1390 * Constant for the "Bopomofo Extended" Unicode character block.
1391 * @since 1.4
1392 */
1393 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1394 new UnicodeBlock("BOPOMOFO_EXTENDED",
1395 "BOPOMOFO EXTENDED",
1396 "BOPOMOFOEXTENDED");
1397
1398 /**
1399 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1400 * @since 1.4
1401 */
1402 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1403 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1404 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1405 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1406
1407 /**
1408 * Constant for the "Yi Syllables" Unicode character block.
1409 * @since 1.4
1410 */
1411 public static final UnicodeBlock YI_SYLLABLES =
1412 new UnicodeBlock("YI_SYLLABLES",
1413 "YI SYLLABLES",
1414 "YISYLLABLES");
1415
1416 /**
1417 * Constant for the "Yi Radicals" Unicode character block.
1418 * @since 1.4
1419 */
1420 public static final UnicodeBlock YI_RADICALS =
1421 new UnicodeBlock("YI_RADICALS",
1422 "YI RADICALS",
1423 "YIRADICALS");
1424
1425 /**
1426 * Constant for the "Cyrillic Supplement" Unicode character block.
1427 * This block was previously known as the "Cyrillic Supplementary" block.
1428 * @since 1.5
1429 */
1430 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1431 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1432 "CYRILLIC SUPPLEMENTARY",
1433 "CYRILLICSUPPLEMENTARY",
1434 "CYRILLIC SUPPLEMENT",
1435 "CYRILLICSUPPLEMENT");
1436
1437 /**
1438 * Constant for the "Tagalog" Unicode character block.
1439 * @since 1.5
1440 */
1441 public static final UnicodeBlock TAGALOG =
1442 new UnicodeBlock("TAGALOG");
1443
1444 /**
1445 * Constant for the "Hanunoo" Unicode character block.
1446 * @since 1.5
1447 */
1448 public static final UnicodeBlock HANUNOO =
1449 new UnicodeBlock("HANUNOO");
1450
1451 /**
1452 * Constant for the "Buhid" Unicode character block.
1453 * @since 1.5
1454 */
1455 public static final UnicodeBlock BUHID =
1456 new UnicodeBlock("BUHID");
1457
1458 /**
1459 * Constant for the "Tagbanwa" Unicode character block.
1460 * @since 1.5
1461 */
1462 public static final UnicodeBlock TAGBANWA =
1463 new UnicodeBlock("TAGBANWA");
1464
1465 /**
1466 * Constant for the "Limbu" Unicode character block.
1467 * @since 1.5
1468 */
1469 public static final UnicodeBlock LIMBU =
1470 new UnicodeBlock("LIMBU");
1471
1472 /**
1473 * Constant for the "Tai Le" Unicode character block.
1474 * @since 1.5
1475 */
1476 public static final UnicodeBlock TAI_LE =
1477 new UnicodeBlock("TAI_LE",
1478 "TAI LE",
1479 "TAILE");
1480
1481 /**
1482 * Constant for the "Khmer Symbols" Unicode character block.
1483 * @since 1.5
1484 */
1485 public static final UnicodeBlock KHMER_SYMBOLS =
1486 new UnicodeBlock("KHMER_SYMBOLS",
1487 "KHMER SYMBOLS",
1488 "KHMERSYMBOLS");
1489
1490 /**
1491 * Constant for the "Phonetic Extensions" Unicode character block.
1492 * @since 1.5
1493 */
1494 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1495 new UnicodeBlock("PHONETIC_EXTENSIONS",
1496 "PHONETIC EXTENSIONS",
1497 "PHONETICEXTENSIONS");
1498
1499 /**
1500 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1501 * @since 1.5
1502 */
1503 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1504 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1505 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1506 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1507
1508 /**
1509 * Constant for the "Supplemental Arrows-A" Unicode character block.
1510 * @since 1.5
1511 */
1512 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1513 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1514 "SUPPLEMENTAL ARROWS-A",
1515 "SUPPLEMENTALARROWS-A");
1516
1517 /**
1518 * Constant for the "Supplemental Arrows-B" Unicode character block.
1519 * @since 1.5
1520 */
1521 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1522 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1523 "SUPPLEMENTAL ARROWS-B",
1524 "SUPPLEMENTALARROWS-B");
1525
1526 /**
1527 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1528 * character block.
1529 * @since 1.5
1530 */
1531 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1532 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1533 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1534 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1535
1536 /**
1537 * Constant for the "Supplemental Mathematical Operators" Unicode
1538 * character block.
1539 * @since 1.5
1540 */
1541 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1542 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1543 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1544 "SUPPLEMENTALMATHEMATICALOPERATORS");
1545
1546 /**
1547 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1548 * block.
1549 * @since 1.5
1550 */
1551 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1552 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1553 "MISCELLANEOUS SYMBOLS AND ARROWS",
1554 "MISCELLANEOUSSYMBOLSANDARROWS");
1555
1556 /**
1557 * Constant for the "Katakana Phonetic Extensions" Unicode character
1558 * block.
1559 * @since 1.5
1560 */
1561 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1562 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1563 "KATAKANA PHONETIC EXTENSIONS",
1564 "KATAKANAPHONETICEXTENSIONS");
1565
1566 /**
1567 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1568 * @since 1.5
1569 */
1570 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1571 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1572 "YIJING HEXAGRAM SYMBOLS",
1573 "YIJINGHEXAGRAMSYMBOLS");
1574
1575 /**
1576 * Constant for the "Variation Selectors" Unicode character block.
1577 * @since 1.5
1578 */
1579 public static final UnicodeBlock VARIATION_SELECTORS =
1580 new UnicodeBlock("VARIATION_SELECTORS",
1581 "VARIATION SELECTORS",
1582 "VARIATIONSELECTORS");
1583
1584 /**
1585 * Constant for the "Linear B Syllabary" Unicode character block.
1586 * @since 1.5
1587 */
1588 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1589 new UnicodeBlock("LINEAR_B_SYLLABARY",
1590 "LINEAR B SYLLABARY",
1591 "LINEARBSYLLABARY");
1592
1593 /**
1594 * Constant for the "Linear B Ideograms" Unicode character block.
1595 * @since 1.5
1596 */
1597 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1598 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1599 "LINEAR B IDEOGRAMS",
1600 "LINEARBIDEOGRAMS");
1601
1602 /**
1603 * Constant for the "Aegean Numbers" Unicode character block.
1604 * @since 1.5
1605 */
1606 public static final UnicodeBlock AEGEAN_NUMBERS =
1607 new UnicodeBlock("AEGEAN_NUMBERS",
1608 "AEGEAN NUMBERS",
1609 "AEGEANNUMBERS");
1610
1611 /**
1612 * Constant for the "Old Italic" Unicode character block.
1613 * @since 1.5
1614 */
1615 public static final UnicodeBlock OLD_ITALIC =
1616 new UnicodeBlock("OLD_ITALIC",
1617 "OLD ITALIC",
1618 "OLDITALIC");
1619
1620 /**
1621 * Constant for the "Gothic" Unicode character block.
1622 * @since 1.5
1623 */
1624 public static final UnicodeBlock GOTHIC =
1625 new UnicodeBlock("GOTHIC");
1626
1627 /**
1628 * Constant for the "Ugaritic" Unicode character block.
1629 * @since 1.5
1630 */
1631 public static final UnicodeBlock UGARITIC =
1632 new UnicodeBlock("UGARITIC");
1633
1634 /**
1635 * Constant for the "Deseret" Unicode character block.
1636 * @since 1.5
1637 */
1638 public static final UnicodeBlock DESERET =
1639 new UnicodeBlock("DESERET");
1640
1641 /**
1642 * Constant for the "Shavian" Unicode character block.
1643 * @since 1.5
1644 */
1645 public static final UnicodeBlock SHAVIAN =
1646 new UnicodeBlock("SHAVIAN");
1647
1648 /**
1649 * Constant for the "Osmanya" Unicode character block.
1650 * @since 1.5
1651 */
1652 public static final UnicodeBlock OSMANYA =
1653 new UnicodeBlock("OSMANYA");
1654
1655 /**
1656 * Constant for the "Cypriot Syllabary" Unicode character block.
1657 * @since 1.5
1658 */
1659 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1660 new UnicodeBlock("CYPRIOT_SYLLABARY",
1661 "CYPRIOT SYLLABARY",
1662 "CYPRIOTSYLLABARY");
1663
1664 /**
1665 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1666 * @since 1.5
1667 */
1668 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1669 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1670 "BYZANTINE MUSICAL SYMBOLS",
1671 "BYZANTINEMUSICALSYMBOLS");
1672
1673 /**
1674 * Constant for the "Musical Symbols" Unicode character block.
1675 * @since 1.5
1676 */
1677 public static final UnicodeBlock MUSICAL_SYMBOLS =
1678 new UnicodeBlock("MUSICAL_SYMBOLS",
1679 "MUSICAL SYMBOLS",
1680 "MUSICALSYMBOLS");
1681
1682 /**
1683 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1684 * @since 1.5
1685 */
1686 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1687 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1688 "TAI XUAN JING SYMBOLS",
1689 "TAIXUANJINGSYMBOLS");
1690
1691 /**
1692 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1693 * character block.
1694 * @since 1.5
1695 */
1696 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1697 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1698 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1699 "MATHEMATICALALPHANUMERICSYMBOLS");
1700
1701 /**
1702 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1703 * character block.
1704 * @since 1.5
1705 */
1706 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1707 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1708 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1709 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1710
1711 /**
1712 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1713 * @since 1.5
1714 */
1715 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1716 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1717 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1718 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1719
1720 /**
1721 * Constant for the "Tags" Unicode character block.
1722 * @since 1.5
1723 */
1724 public static final UnicodeBlock TAGS =
1725 new UnicodeBlock("TAGS");
1726
1727 /**
1728 * Constant for the "Variation Selectors Supplement" Unicode character
1729 * block.
1730 * @since 1.5
1731 */
1732 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1733 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1734 "VARIATION SELECTORS SUPPLEMENT",
1735 "VARIATIONSELECTORSSUPPLEMENT");
1736
1737 /**
1738 * Constant for the "Supplementary Private Use Area-A" Unicode character
1739 * block.
1740 * @since 1.5
1741 */
1742 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1743 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1744 "SUPPLEMENTARY PRIVATE USE AREA-A",
1745 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1746
1747 /**
1748 * Constant for the "Supplementary Private Use Area-B" Unicode character
1749 * block.
1750 * @since 1.5
1751 */
1752 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1753 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1754 "SUPPLEMENTARY PRIVATE USE AREA-B",
1755 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1756
1757 /**
1758 * Constant for the "High Surrogates" Unicode character block.
1759 * This block represents codepoint values in the high surrogate
1760 * range: U+D800 through U+DB7F
1761 *
1762 * @since 1.5
1763 */
1764 public static final UnicodeBlock HIGH_SURROGATES =
1765 new UnicodeBlock("HIGH_SURROGATES",
1766 "HIGH SURROGATES",
1767 "HIGHSURROGATES");
1768
1769 /**
1770 * Constant for the "High Private Use Surrogates" Unicode character
1771 * block.
1772 * This block represents codepoint values in the private use high
1773 * surrogate range: U+DB80 through U+DBFF
1774 *
1775 * @since 1.5
1776 */
1777 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1778 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1779 "HIGH PRIVATE USE SURROGATES",
1780 "HIGHPRIVATEUSESURROGATES");
1781
1782 /**
1783 * Constant for the "Low Surrogates" Unicode character block.
1784 * This block represents codepoint values in the low surrogate
1785 * range: U+DC00 through U+DFFF
1786 *
1787 * @since 1.5
1788 */
1789 public static final UnicodeBlock LOW_SURROGATES =
1790 new UnicodeBlock("LOW_SURROGATES",
1791 "LOW SURROGATES",
1792 "LOWSURROGATES");
1793
1794 /**
1795 * Constant for the "Arabic Supplement" Unicode character block.
1796 * @since 1.7
1797 */
1798 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1799 new UnicodeBlock("ARABIC_SUPPLEMENT",
1800 "ARABIC SUPPLEMENT",
1801 "ARABICSUPPLEMENT");
1802
1803 /**
1804 * Constant for the "NKo" Unicode character block.
1805 * @since 1.7
1806 */
1807 public static final UnicodeBlock NKO =
1808 new UnicodeBlock("NKO");
1809
1810 /**
1811 * Constant for the "Samaritan" Unicode character block.
1812 * @since 1.7
1813 */
1814 public static final UnicodeBlock SAMARITAN =
1815 new UnicodeBlock("SAMARITAN");
1816
1817 /**
1818 * Constant for the "Mandaic" Unicode character block.
1819 * @since 1.7
1820 */
1821 public static final UnicodeBlock MANDAIC =
1822 new UnicodeBlock("MANDAIC");
1823
1824 /**
1825 * Constant for the "Ethiopic Supplement" Unicode character block.
1826 * @since 1.7
1827 */
1828 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1829 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1830 "ETHIOPIC SUPPLEMENT",
1831 "ETHIOPICSUPPLEMENT");
1832
1833 /**
1834 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1835 * Unicode character block.
1836 * @since 1.7
1837 */
1838 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1839 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1840 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1841 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1842
1843 /**
1844 * Constant for the "New Tai Lue" Unicode character block.
1845 * @since 1.7
1846 */
1847 public static final UnicodeBlock NEW_TAI_LUE =
1848 new UnicodeBlock("NEW_TAI_LUE",
1849 "NEW TAI LUE",
1850 "NEWTAILUE");
1851
1852 /**
1853 * Constant for the "Buginese" Unicode character block.
1854 * @since 1.7
1855 */
1856 public static final UnicodeBlock BUGINESE =
1857 new UnicodeBlock("BUGINESE");
1858
1859 /**
1860 * Constant for the "Tai Tham" Unicode character block.
1861 * @since 1.7
1862 */
1863 public static final UnicodeBlock TAI_THAM =
1864 new UnicodeBlock("TAI_THAM",
1865 "TAI THAM",
1866 "TAITHAM");
1867
1868 /**
1869 * Constant for the "Balinese" Unicode character block.
1870 * @since 1.7
1871 */
1872 public static final UnicodeBlock BALINESE =
1873 new UnicodeBlock("BALINESE");
1874
1875 /**
1876 * Constant for the "Sundanese" Unicode character block.
1877 * @since 1.7
1878 */
1879 public static final UnicodeBlock SUNDANESE =
1880 new UnicodeBlock("SUNDANESE");
1881
1882 /**
1883 * Constant for the "Batak" Unicode character block.
1884 * @since 1.7
1885 */
1886 public static final UnicodeBlock BATAK =
1887 new UnicodeBlock("BATAK");
1888
1889 /**
1890 * Constant for the "Lepcha" Unicode character block.
1891 * @since 1.7
1892 */
1893 public static final UnicodeBlock LEPCHA =
1894 new UnicodeBlock("LEPCHA");
1895
1896 /**
1897 * Constant for the "Ol Chiki" Unicode character block.
1898 * @since 1.7
1899 */
1900 public static final UnicodeBlock OL_CHIKI =
1901 new UnicodeBlock("OL_CHIKI",
1902 "OL CHIKI",
1903 "OLCHIKI");
1904
1905 /**
1906 * Constant for the "Vedic Extensions" Unicode character block.
1907 * @since 1.7
1908 */
1909 public static final UnicodeBlock VEDIC_EXTENSIONS =
1910 new UnicodeBlock("VEDIC_EXTENSIONS",
1911 "VEDIC EXTENSIONS",
1912 "VEDICEXTENSIONS");
1913
1914 /**
1915 * Constant for the "Phonetic Extensions Supplement" Unicode character
1916 * block.
1917 * @since 1.7
1918 */
1919 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1920 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1921 "PHONETIC EXTENSIONS SUPPLEMENT",
1922 "PHONETICEXTENSIONSSUPPLEMENT");
1923
1924 /**
1925 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1926 * character block.
1927 * @since 1.7
1928 */
1929 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1930 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1931 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1932 "COMBININGDIACRITICALMARKSSUPPLEMENT");
1933
1934 /**
1935 * Constant for the "Glagolitic" Unicode character block.
1936 * @since 1.7
1937 */
1938 public static final UnicodeBlock GLAGOLITIC =
1939 new UnicodeBlock("GLAGOLITIC");
1940
1941 /**
1942 * Constant for the "Latin Extended-C" Unicode character block.
1943 * @since 1.7
1944 */
1945 public static final UnicodeBlock LATIN_EXTENDED_C =
1946 new UnicodeBlock("LATIN_EXTENDED_C",
1947 "LATIN EXTENDED-C",
1948 "LATINEXTENDED-C");
1949
1950 /**
1951 * Constant for the "Coptic" Unicode character block.
1952 * @since 1.7
1953 */
1954 public static final UnicodeBlock COPTIC =
1955 new UnicodeBlock("COPTIC");
1956
1957 /**
1958 * Constant for the "Georgian Supplement" Unicode character block.
1959 * @since 1.7
1960 */
1961 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
1962 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
1963 "GEORGIAN SUPPLEMENT",
1964 "GEORGIANSUPPLEMENT");
1965
1966 /**
1967 * Constant for the "Tifinagh" Unicode character block.
1968 * @since 1.7
1969 */
1970 public static final UnicodeBlock TIFINAGH =
1971 new UnicodeBlock("TIFINAGH");
1972
1973 /**
1974 * Constant for the "Ethiopic Extended" Unicode character block.
1975 * @since 1.7
1976 */
1977 public static final UnicodeBlock ETHIOPIC_EXTENDED =
1978 new UnicodeBlock("ETHIOPIC_EXTENDED",
1979 "ETHIOPIC EXTENDED",
1980 "ETHIOPICEXTENDED");
1981
1982 /**
1983 * Constant for the "Cyrillic Extended-A" Unicode character block.
1984 * @since 1.7
1985 */
1986 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
1987 new UnicodeBlock("CYRILLIC_EXTENDED_A",
1988 "CYRILLIC EXTENDED-A",
1989 "CYRILLICEXTENDED-A");
1990
1991 /**
1992 * Constant for the "Supplemental Punctuation" Unicode character block.
1993 * @since 1.7
1994 */
1995 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
1996 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
1997 "SUPPLEMENTAL PUNCTUATION",
1998 "SUPPLEMENTALPUNCTUATION");
1999
2000 /**
2001 * Constant for the "CJK Strokes" Unicode character block.
2002 * @since 1.7
2003 */
2004 public static final UnicodeBlock CJK_STROKES =
2005 new UnicodeBlock("CJK_STROKES",
2006 "CJK STROKES",
2007 "CJKSTROKES");
2008
2009 /**
2010 * Constant for the "Lisu" Unicode character block.
2011 * @since 1.7
2012 */
2013 public static final UnicodeBlock LISU =
2014 new UnicodeBlock("LISU");
2015
2016 /**
2017 * Constant for the "Vai" Unicode character block.
2018 * @since 1.7
2019 */
2020 public static final UnicodeBlock VAI =
2021 new UnicodeBlock("VAI");
2022
2023 /**
2024 * Constant for the "Cyrillic Extended-B" Unicode character block.
2025 * @since 1.7
2026 */
2027 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2028 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2029 "CYRILLIC EXTENDED-B",
2030 "CYRILLICEXTENDED-B");
2031
2032 /**
2033 * Constant for the "Bamum" Unicode character block.
2034 * @since 1.7
2035 */
2036 public static final UnicodeBlock BAMUM =
2037 new UnicodeBlock("BAMUM");
2038
2039 /**
2040 * Constant for the "Modifier Tone Letters" Unicode character block.
2041 * @since 1.7
2042 */
2043 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2044 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2045 "MODIFIER TONE LETTERS",
2046 "MODIFIERTONELETTERS");
2047
2048 /**
2049 * Constant for the "Latin Extended-D" Unicode character block.
2050 * @since 1.7
2051 */
2052 public static final UnicodeBlock LATIN_EXTENDED_D =
2053 new UnicodeBlock("LATIN_EXTENDED_D",
2054 "LATIN EXTENDED-D",
2055 "LATINEXTENDED-D");
2056
2057 /**
2058 * Constant for the "Syloti Nagri" Unicode character block.
2059 * @since 1.7
2060 */
2061 public static final UnicodeBlock SYLOTI_NAGRI =
2062 new UnicodeBlock("SYLOTI_NAGRI",
2063 "SYLOTI NAGRI",
2064 "SYLOTINAGRI");
2065
2066 /**
2067 * Constant for the "Common Indic Number Forms" Unicode character block.
2068 * @since 1.7
2069 */
2070 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2071 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2072 "COMMON INDIC NUMBER FORMS",
2073 "COMMONINDICNUMBERFORMS");
2074
2075 /**
2076 * Constant for the "Phags-pa" Unicode character block.
2077 * @since 1.7
2078 */
2079 public static final UnicodeBlock PHAGS_PA =
2080 new UnicodeBlock("PHAGS_PA",
2081 "PHAGS-PA");
2082
2083 /**
2084 * Constant for the "Saurashtra" Unicode character block.
2085 * @since 1.7
2086 */
2087 public static final UnicodeBlock SAURASHTRA =
2088 new UnicodeBlock("SAURASHTRA");
2089
2090 /**
2091 * Constant for the "Devanagari Extended" Unicode character block.
2092 * @since 1.7
2093 */
2094 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2095 new UnicodeBlock("DEVANAGARI_EXTENDED",
2096 "DEVANAGARI EXTENDED",
2097 "DEVANAGARIEXTENDED");
2098
2099 /**
2100 * Constant for the "Kayah Li" Unicode character block.
2101 * @since 1.7
2102 */
2103 public static final UnicodeBlock KAYAH_LI =
2104 new UnicodeBlock("KAYAH_LI",
2105 "KAYAH LI",
2106 "KAYAHLI");
2107
2108 /**
2109 * Constant for the "Rejang" Unicode character block.
2110 * @since 1.7
2111 */
2112 public static final UnicodeBlock REJANG =
2113 new UnicodeBlock("REJANG");
2114
2115 /**
2116 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2117 * @since 1.7
2118 */
2119 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2120 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2121 "HANGUL JAMO EXTENDED-A",
2122 "HANGULJAMOEXTENDED-A");
2123
2124 /**
2125 * Constant for the "Javanese" Unicode character block.
2126 * @since 1.7
2127 */
2128 public static final UnicodeBlock JAVANESE =
2129 new UnicodeBlock("JAVANESE");
2130
2131 /**
2132 * Constant for the "Cham" Unicode character block.
2133 * @since 1.7
2134 */
2135 public static final UnicodeBlock CHAM =
2136 new UnicodeBlock("CHAM");
2137
2138 /**
2139 * Constant for the "Myanmar Extended-A" Unicode character block.
2140 * @since 1.7
2141 */
2142 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2143 new UnicodeBlock("MYANMAR_EXTENDED_A",
2144 "MYANMAR EXTENDED-A",
2145 "MYANMAREXTENDED-A");
2146
2147 /**
2148 * Constant for the "Tai Viet" Unicode character block.
2149 * @since 1.7
2150 */
2151 public static final UnicodeBlock TAI_VIET =
2152 new UnicodeBlock("TAI_VIET",
2153 "TAI VIET",
2154 "TAIVIET");
2155
2156 /**
2157 * Constant for the "Ethiopic Extended-A" Unicode character block.
2158 * @since 1.7
2159 */
2160 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2161 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2162 "ETHIOPIC EXTENDED-A",
2163 "ETHIOPICEXTENDED-A");
2164
2165 /**
2166 * Constant for the "Meetei Mayek" Unicode character block.
2167 * @since 1.7
2168 */
2169 public static final UnicodeBlock MEETEI_MAYEK =
2170 new UnicodeBlock("MEETEI_MAYEK",
2171 "MEETEI MAYEK",
2172 "MEETEIMAYEK");
2173
2174 /**
2175 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2176 * @since 1.7
2177 */
2178 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2179 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2180 "HANGUL JAMO EXTENDED-B",
2181 "HANGULJAMOEXTENDED-B");
2182
2183 /**
2184 * Constant for the "Vertical Forms" Unicode character block.
2185 * @since 1.7
2186 */
2187 public static final UnicodeBlock VERTICAL_FORMS =
2188 new UnicodeBlock("VERTICAL_FORMS",
2189 "VERTICAL FORMS",
2190 "VERTICALFORMS");
2191
2192 /**
2193 * Constant for the "Ancient Greek Numbers" Unicode character block.
2194 * @since 1.7
2195 */
2196 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2197 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2198 "ANCIENT GREEK NUMBERS",
2199 "ANCIENTGREEKNUMBERS");
2200
2201 /**
2202 * Constant for the "Ancient Symbols" Unicode character block.
2203 * @since 1.7
2204 */
2205 public static final UnicodeBlock ANCIENT_SYMBOLS =
2206 new UnicodeBlock("ANCIENT_SYMBOLS",
2207 "ANCIENT SYMBOLS",
2208 "ANCIENTSYMBOLS");
2209
2210 /**
2211 * Constant for the "Phaistos Disc" Unicode character block.
2212 * @since 1.7
2213 */
2214 public static final UnicodeBlock PHAISTOS_DISC =
2215 new UnicodeBlock("PHAISTOS_DISC",
2216 "PHAISTOS DISC",
2217 "PHAISTOSDISC");
2218
2219 /**
2220 * Constant for the "Lycian" Unicode character block.
2221 * @since 1.7
2222 */
2223 public static final UnicodeBlock LYCIAN =
2224 new UnicodeBlock("LYCIAN");
2225
2226 /**
2227 * Constant for the "Carian" Unicode character block.
2228 * @since 1.7
2229 */
2230 public static final UnicodeBlock CARIAN =
2231 new UnicodeBlock("CARIAN");
2232
2233 /**
2234 * Constant for the "Old Persian" Unicode character block.
2235 * @since 1.7
2236 */
2237 public static final UnicodeBlock OLD_PERSIAN =
2238 new UnicodeBlock("OLD_PERSIAN",
2239 "OLD PERSIAN",
2240 "OLDPERSIAN");
2241
2242 /**
2243 * Constant for the "Imperial Aramaic" Unicode character block.
2244 * @since 1.7
2245 */
2246 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2247 new UnicodeBlock("IMPERIAL_ARAMAIC",
2248 "IMPERIAL ARAMAIC",
2249 "IMPERIALARAMAIC");
2250
2251 /**
2252 * Constant for the "Phoenician" Unicode character block.
2253 * @since 1.7
2254 */
2255 public static final UnicodeBlock PHOENICIAN =
2256 new UnicodeBlock("PHOENICIAN");
2257
2258 /**
2259 * Constant for the "Lydian" Unicode character block.
2260 * @since 1.7
2261 */
2262 public static final UnicodeBlock LYDIAN =
2263 new UnicodeBlock("LYDIAN");
2264
2265 /**
2266 * Constant for the "Kharoshthi" Unicode character block.
2267 * @since 1.7
2268 */
2269 public static final UnicodeBlock KHAROSHTHI =
2270 new UnicodeBlock("KHAROSHTHI");
2271
2272 /**
2273 * Constant for the "Old South Arabian" Unicode character block.
2274 * @since 1.7
2275 */
2276 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2277 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2278 "OLD SOUTH ARABIAN",
2279 "OLDSOUTHARABIAN");
2280
2281 /**
2282 * Constant for the "Avestan" Unicode character block.
2283 * @since 1.7
2284 */
2285 public static final UnicodeBlock AVESTAN =
2286 new UnicodeBlock("AVESTAN");
2287
2288 /**
2289 * Constant for the "Inscriptional Parthian" Unicode character block.
2290 * @since 1.7
2291 */
2292 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2293 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2294 "INSCRIPTIONAL PARTHIAN",
2295 "INSCRIPTIONALPARTHIAN");
2296
2297 /**
2298 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2299 * @since 1.7
2300 */
2301 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2302 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2303 "INSCRIPTIONAL PAHLAVI",
2304 "INSCRIPTIONALPAHLAVI");
2305
2306 /**
2307 * Constant for the "Old Turkic" Unicode character block.
2308 * @since 1.7
2309 */
2310 public static final UnicodeBlock OLD_TURKIC =
2311 new UnicodeBlock("OLD_TURKIC",
2312 "OLD TURKIC",
2313 "OLDTURKIC");
2314
2315 /**
2316 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2317 * @since 1.7
2318 */
2319 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2320 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2321 "RUMI NUMERAL SYMBOLS",
2322 "RUMINUMERALSYMBOLS");
2323
2324 /**
2325 * Constant for the "Brahmi" Unicode character block.
2326 * @since 1.7
2327 */
2328 public static final UnicodeBlock BRAHMI =
2329 new UnicodeBlock("BRAHMI");
2330
2331 /**
2332 * Constant for the "Kaithi" Unicode character block.
2333 * @since 1.7
2334 */
2335 public static final UnicodeBlock KAITHI =
2336 new UnicodeBlock("KAITHI");
2337
2338 /**
2339 * Constant for the "Cuneiform" Unicode character block.
2340 * @since 1.7
2341 */
2342 public static final UnicodeBlock CUNEIFORM =
2343 new UnicodeBlock("CUNEIFORM");
2344
2345 /**
2346 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2347 * character block.
2348 * @since 1.7
2349 */
2350 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2351 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2352 "CUNEIFORM NUMBERS AND PUNCTUATION",
2353 "CUNEIFORMNUMBERSANDPUNCTUATION");
2354
2355 /**
2356 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2357 * @since 1.7
2358 */
2359 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2360 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2361 "EGYPTIAN HIEROGLYPHS",
2362 "EGYPTIANHIEROGLYPHS");
2363
2364 /**
2365 * Constant for the "Bamum Supplement" Unicode character block.
2366 * @since 1.7
2367 */
2368 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2369 new UnicodeBlock("BAMUM_SUPPLEMENT",
2370 "BAMUM SUPPLEMENT",
2371 "BAMUMSUPPLEMENT");
2372
2373 /**
2374 * Constant for the "Kana Supplement" Unicode character block.
2375 * @since 1.7
2376 */
2377 public static final UnicodeBlock KANA_SUPPLEMENT =
2378 new UnicodeBlock("KANA_SUPPLEMENT",
2379 "KANA SUPPLEMENT",
2380 "KANASUPPLEMENT");
2381
2382 /**
2383 * Constant for the "Ancient Greek Musical Notation" Unicode character
2384 * block.
2385 * @since 1.7
2386 */
2387 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2388 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2389 "ANCIENT GREEK MUSICAL NOTATION",
2390 "ANCIENTGREEKMUSICALNOTATION");
2391
2392 /**
2393 * Constant for the "Counting Rod Numerals" Unicode character block.
2394 * @since 1.7
2395 */
2396 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2397 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2398 "COUNTING ROD NUMERALS",
2399 "COUNTINGRODNUMERALS");
2400
2401 /**
2402 * Constant for the "Mahjong Tiles" Unicode character block.
2403 * @since 1.7
2404 */
2405 public static final UnicodeBlock MAHJONG_TILES =
2406 new UnicodeBlock("MAHJONG_TILES",
2407 "MAHJONG TILES",
2408 "MAHJONGTILES");
2409
2410 /**
2411 * Constant for the "Domino Tiles" Unicode character block.
2412 * @since 1.7
2413 */
2414 public static final UnicodeBlock DOMINO_TILES =
2415 new UnicodeBlock("DOMINO_TILES",
2416 "DOMINO TILES",
2417 "DOMINOTILES");
2418
2419 /**
2420 * Constant for the "Playing Cards" Unicode character block.
2421 * @since 1.7
2422 */
2423 public static final UnicodeBlock PLAYING_CARDS =
2424 new UnicodeBlock("PLAYING_CARDS",
2425 "PLAYING CARDS",
2426 "PLAYINGCARDS");
2427
2428 /**
2429 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2430 * block.
2431 * @since 1.7
2432 */
2433 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2434 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2435 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2436 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2437
2438 /**
2439 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2440 * block.
2441 * @since 1.7
2442 */
2443 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2444 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2445 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2446 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2447
2448 /**
2449 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2450 * character block.
2451 * @since 1.7
2452 */
2453 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2454 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2455 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2456 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2457
2458 /**
2459 * Constant for the "Emoticons" Unicode character block.
2460 * @since 1.7
2461 */
2462 public static final UnicodeBlock EMOTICONS =
2463 new UnicodeBlock("EMOTICONS");
2464
2465 /**
2466 * Constant for the "Transport And Map Symbols" Unicode character block.
2467 * @since 1.7
2468 */
2469 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2470 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2471 "TRANSPORT AND MAP SYMBOLS",
2472 "TRANSPORTANDMAPSYMBOLS");
2473
2474 /**
2475 * Constant for the "Alchemical Symbols" Unicode character block.
2476 * @since 1.7
2477 */
2478 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2479 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2480 "ALCHEMICAL SYMBOLS",
2481 "ALCHEMICALSYMBOLS");
2482
2483 /**
2484 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2485 * character block.
2486 * @since 1.7
2487 */
2488 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2489 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2490 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2491 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2492
2493 /**
2494 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2495 * character block.
2496 * @since 1.7
2497 */
2498 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2499 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2500 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2501 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2502
2503 /**
2504 * Constant for the "Arabic Extended-A" Unicode character block.
2505 * @since 1.8
2506 */
2507 public static final UnicodeBlock ARABIC_EXTENDED_A =
2508 new UnicodeBlock("ARABIC_EXTENDED_A",
2509 "ARABIC EXTENDED-A",
2510 "ARABICEXTENDED-A");
2511
2512 /**
2513 * Constant for the "Sundanese Supplement" Unicode character block.
2514 * @since 1.8
2515 */
2516 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2517 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2518 "SUNDANESE SUPPLEMENT",
2519 "SUNDANESESUPPLEMENT");
2520
2521 /**
2522 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2523 * @since 1.8
2524 */
2525 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2526 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2527 "MEETEI MAYEK EXTENSIONS",
2528 "MEETEIMAYEKEXTENSIONS");
2529
2530 /**
2531 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2532 * @since 1.8
2533 */
2534 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2535 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2536 "MEROITIC HIEROGLYPHS",
2537 "MEROITICHIEROGLYPHS");
2538
2539 /**
2540 * Constant for the "Meroitic Cursive" Unicode character block.
2541 * @since 1.8
2542 */
2543 public static final UnicodeBlock MEROITIC_CURSIVE =
2544 new UnicodeBlock("MEROITIC_CURSIVE",
2545 "MEROITIC CURSIVE",
2546 "MEROITICCURSIVE");
2547
2548 /**
2549 * Constant for the "Sora Sompeng" Unicode character block.
2550 * @since 1.8
2551 */
2552 public static final UnicodeBlock SORA_SOMPENG =
2553 new UnicodeBlock("SORA_SOMPENG",
2554 "SORA SOMPENG",
2555 "SORASOMPENG");
2556
2557 /**
2558 * Constant for the "Chakma" Unicode character block.
2559 * @since 1.8
2560 */
2561 public static final UnicodeBlock CHAKMA =
2562 new UnicodeBlock("CHAKMA");
2563
2564 /**
2565 * Constant for the "Sharada" Unicode character block.
2566 * @since 1.8
2567 */
2568 public static final UnicodeBlock SHARADA =
2569 new UnicodeBlock("SHARADA");
2570
2571 /**
2572 * Constant for the "Takri" Unicode character block.
2573 * @since 1.8
2574 */
2575 public static final UnicodeBlock TAKRI =
2576 new UnicodeBlock("TAKRI");
2577
2578 /**
2579 * Constant for the "Miao" Unicode character block.
2580 * @since 1.8
2581 */
2582 public static final UnicodeBlock MIAO =
2583 new UnicodeBlock("MIAO");
2584
2585 /**
2586 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2587 * character block.
2588 * @since 1.8
2589 */
2590 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2591 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2592 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2593 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2594
2595 /**
2596 * Constant for the "Combining Diacritical Marks Extended" Unicode
2597 * character block.
2598 * @since 9
2599 */
2600 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2601 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2602 "COMBINING DIACRITICAL MARKS EXTENDED",
2603 "COMBININGDIACRITICALMARKSEXTENDED");
2604
2605 /**
2606 * Constant for the "Myanmar Extended-B" Unicode character block.
2607 * @since 9
2608 */
2609 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2610 new UnicodeBlock("MYANMAR_EXTENDED_B",
2611 "MYANMAR EXTENDED-B",
2612 "MYANMAREXTENDED-B");
2613
2614 /**
2615 * Constant for the "Latin Extended-E" Unicode character block.
2616 * @since 9
2617 */
2618 public static final UnicodeBlock LATIN_EXTENDED_E =
2619 new UnicodeBlock("LATIN_EXTENDED_E",
2620 "LATIN EXTENDED-E",
2621 "LATINEXTENDED-E");
2622
2623 /**
2624 * Constant for the "Coptic Epact Numbers" Unicode character block.
2625 * @since 9
2626 */
2627 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2628 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2629 "COPTIC EPACT NUMBERS",
2630 "COPTICEPACTNUMBERS");
2631
2632 /**
2633 * Constant for the "Old Permic" Unicode character block.
2634 * @since 9
2635 */
2636 public static final UnicodeBlock OLD_PERMIC =
2637 new UnicodeBlock("OLD_PERMIC",
2638 "OLD PERMIC",
2639 "OLDPERMIC");
2640
2641 /**
2642 * Constant for the "Elbasan" Unicode character block.
2643 * @since 9
2644 */
2645 public static final UnicodeBlock ELBASAN =
2646 new UnicodeBlock("ELBASAN");
2647
2648 /**
2649 * Constant for the "Caucasian Albanian" Unicode character block.
2650 * @since 9
2651 */
2652 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2653 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2654 "CAUCASIAN ALBANIAN",
2655 "CAUCASIANALBANIAN");
2656
2657 /**
2658 * Constant for the "Linear A" Unicode character block.
2659 * @since 9
2660 */
2661 public static final UnicodeBlock LINEAR_A =
2662 new UnicodeBlock("LINEAR_A",
2663 "LINEAR A",
2664 "LINEARA");
2665
2666 /**
2667 * Constant for the "Palmyrene" Unicode character block.
2668 * @since 9
2669 */
2670 public static final UnicodeBlock PALMYRENE =
2671 new UnicodeBlock("PALMYRENE");
2672
2673 /**
2674 * Constant for the "Nabataean" Unicode character block.
2675 * @since 9
2676 */
2677 public static final UnicodeBlock NABATAEAN =
2678 new UnicodeBlock("NABATAEAN");
2679
2680 /**
2681 * Constant for the "Old North Arabian" Unicode character block.
2682 * @since 9
2683 */
2684 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2685 new UnicodeBlock("OLD_NORTH_ARABIAN",
2686 "OLD NORTH ARABIAN",
2687 "OLDNORTHARABIAN");
2688
2689 /**
2690 * Constant for the "Manichaean" Unicode character block.
2691 * @since 9
2692 */
2693 public static final UnicodeBlock MANICHAEAN =
2694 new UnicodeBlock("MANICHAEAN");
2695
2696 /**
2697 * Constant for the "Psalter Pahlavi" Unicode character block.
2698 * @since 9
2699 */
2700 public static final UnicodeBlock PSALTER_PAHLAVI =
2701 new UnicodeBlock("PSALTER_PAHLAVI",
2702 "PSALTER PAHLAVI",
2703 "PSALTERPAHLAVI");
2704
2705 /**
2706 * Constant for the "Mahajani" Unicode character block.
2707 * @since 9
2708 */
2709 public static final UnicodeBlock MAHAJANI =
2710 new UnicodeBlock("MAHAJANI");
2711
2712 /**
2713 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2714 * @since 9
2715 */
2716 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2717 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2718 "SINHALA ARCHAIC NUMBERS",
2719 "SINHALAARCHAICNUMBERS");
2720
2721 /**
2722 * Constant for the "Khojki" Unicode character block.
2723 * @since 9
2724 */
2725 public static final UnicodeBlock KHOJKI =
2726 new UnicodeBlock("KHOJKI");
2727
2728 /**
2729 * Constant for the "Khudawadi" Unicode character block.
2730 * @since 9
2731 */
2732 public static final UnicodeBlock KHUDAWADI =
2733 new UnicodeBlock("KHUDAWADI");
2734
2735 /**
2736 * Constant for the "Grantha" Unicode character block.
2737 * @since 9
2738 */
2739 public static final UnicodeBlock GRANTHA =
2740 new UnicodeBlock("GRANTHA");
2741
2742 /**
2743 * Constant for the "Tirhuta" Unicode character block.
2744 * @since 9
2745 */
2746 public static final UnicodeBlock TIRHUTA =
2747 new UnicodeBlock("TIRHUTA");
2748
2749 /**
2750 * Constant for the "Siddham" Unicode character block.
2751 * @since 9
2752 */
2753 public static final UnicodeBlock SIDDHAM =
2754 new UnicodeBlock("SIDDHAM");
2755
2756 /**
2757 * Constant for the "Modi" Unicode character block.
2758 * @since 9
2759 */
2760 public static final UnicodeBlock MODI =
2761 new UnicodeBlock("MODI");
2762
2763 /**
2764 * Constant for the "Warang Citi" Unicode character block.
2765 * @since 9
2766 */
2767 public static final UnicodeBlock WARANG_CITI =
2768 new UnicodeBlock("WARANG_CITI",
2769 "WARANG CITI",
2770 "WARANGCITI");
2771
2772 /**
2773 * Constant for the "Pau Cin Hau" Unicode character block.
2774 * @since 9
2775 */
2776 public static final UnicodeBlock PAU_CIN_HAU =
2777 new UnicodeBlock("PAU_CIN_HAU",
2778 "PAU CIN HAU",
2779 "PAUCINHAU");
2780
2781 /**
2782 * Constant for the "Mro" Unicode character block.
2783 * @since 9
2784 */
2785 public static final UnicodeBlock MRO =
2786 new UnicodeBlock("MRO");
2787
2788 /**
2789 * Constant for the "Bassa Vah" Unicode character block.
2790 * @since 9
2791 */
2792 public static final UnicodeBlock BASSA_VAH =
2793 new UnicodeBlock("BASSA_VAH",
2794 "BASSA VAH",
2795 "BASSAVAH");
2796
2797 /**
2798 * Constant for the "Pahawh Hmong" Unicode character block.
2799 * @since 9
2800 */
2801 public static final UnicodeBlock PAHAWH_HMONG =
2802 new UnicodeBlock("PAHAWH_HMONG",
2803 "PAHAWH HMONG",
2804 "PAHAWHHMONG");
2805
2806 /**
2807 * Constant for the "Duployan" Unicode character block.
2808 * @since 9
2809 */
2810 public static final UnicodeBlock DUPLOYAN =
2811 new UnicodeBlock("DUPLOYAN");
2812
2813 /**
2814 * Constant for the "Shorthand Format Controls" Unicode character block.
2815 * @since 9
2816 */
2817 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2818 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2819 "SHORTHAND FORMAT CONTROLS",
2820 "SHORTHANDFORMATCONTROLS");
2821
2822 /**
2823 * Constant for the "Mende Kikakui" Unicode character block.
2824 * @since 9
2825 */
2826 public static final UnicodeBlock MENDE_KIKAKUI =
2827 new UnicodeBlock("MENDE_KIKAKUI",
2828 "MENDE KIKAKUI",
2829 "MENDEKIKAKUI");
2830
2831 /**
2832 * Constant for the "Ornamental Dingbats" Unicode character block.
2833 * @since 9
2834 */
2835 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2836 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2837 "ORNAMENTAL DINGBATS",
2838 "ORNAMENTALDINGBATS");
2839
2840 /**
2841 * Constant for the "Geometric Shapes Extended" Unicode character block.
2842 * @since 9
2843 */
2844 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2845 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2846 "GEOMETRIC SHAPES EXTENDED",
2847 "GEOMETRICSHAPESEXTENDED");
2848
2849 /**
2850 * Constant for the "Supplemental Arrows-C" Unicode character block.
2851 * @since 9
2852 */
2853 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2854 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2855 "SUPPLEMENTAL ARROWS-C",
2856 "SUPPLEMENTALARROWS-C");
2857
2858 /**
2859 * Constant for the "Cherokee Supplement" Unicode character block.
2860 * @since 9
2861 */
2862 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2863 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2864 "CHEROKEE SUPPLEMENT",
2865 "CHEROKEESUPPLEMENT");
2866
2867 /**
2868 * Constant for the "Hatran" Unicode character block.
2869 * @since 9
2870 */
2871 public static final UnicodeBlock HATRAN =
2872 new UnicodeBlock("HATRAN");
2873
2874 /**
2875 * Constant for the "Old Hungarian" Unicode character block.
2876 * @since 9
2877 */
2878 public static final UnicodeBlock OLD_HUNGARIAN =
2879 new UnicodeBlock("OLD_HUNGARIAN",
2880 "OLD HUNGARIAN",
2881 "OLDHUNGARIAN");
2882
2883 /**
2884 * Constant for the "Multani" Unicode character block.
2885 * @since 9
2886 */
2887 public static final UnicodeBlock MULTANI =
2888 new UnicodeBlock("MULTANI");
2889
2890 /**
2891 * Constant for the "Ahom" Unicode character block.
2892 * @since 9
2893 */
2894 public static final UnicodeBlock AHOM =
2895 new UnicodeBlock("AHOM");
2896
2897 /**
2898 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2899 * @since 9
2900 */
2901 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2902 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2903 "EARLY DYNASTIC CUNEIFORM",
2904 "EARLYDYNASTICCUNEIFORM");
2905
2906 /**
2907 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2908 * @since 9
2909 */
2910 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2911 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2912 "ANATOLIAN HIEROGLYPHS",
2913 "ANATOLIANHIEROGLYPHS");
2914
2915 /**
2916 * Constant for the "Sutton SignWriting" Unicode character block.
2917 * @since 9
2918 */
2919 public static final UnicodeBlock SUTTON_SIGNWRITING =
2920 new UnicodeBlock("SUTTON_SIGNWRITING",
2921 "SUTTON SIGNWRITING",
2922 "SUTTONSIGNWRITING");
2923
2924 /**
2925 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2926 * character block.
2927 * @since 9
2928 */
2929 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2930 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2931 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2932 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2933
2934 /**
2935 * Constant for the "CJK Unified Ideographs Extension E" Unicode
2936 * character block.
2937 * @since 9
2938 */
2939 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
2940 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
2941 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
2942 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
2943
2944 /**
2945 * Constant for the "Syriac Supplement" Unicode
2946 * character block.
2947 * @since 11
2948 */
2949 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
2950 new UnicodeBlock("SYRIAC_SUPPLEMENT",
2951 "SYRIAC SUPPLEMENT",
2952 "SYRIACSUPPLEMENT");
2953
2954 /**
2955 * Constant for the "Cyrillic Extended-C" Unicode
2956 * character block.
2957 * @since 11
2958 */
2959 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
2960 new UnicodeBlock("CYRILLIC_EXTENDED_C",
2961 "CYRILLIC EXTENDED-C",
2962 "CYRILLICEXTENDED-C");
2963
2964 /**
2965 * Constant for the "Osage" Unicode
2966 * character block.
2967 * @since 11
2968 */
2969 public static final UnicodeBlock OSAGE =
2970 new UnicodeBlock("OSAGE");
2971
2972 /**
2973 * Constant for the "Newa" Unicode
2974 * character block.
2975 * @since 11
2976 */
2977 public static final UnicodeBlock NEWA =
2978 new UnicodeBlock("NEWA");
2979
2980 /**
2981 * Constant for the "Mongolian Supplement" Unicode
2982 * character block.
2983 * @since 11
2984 */
2985 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
2986 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
2987 "MONGOLIAN SUPPLEMENT",
2988 "MONGOLIANSUPPLEMENT");
2989
2990 /**
2991 * Constant for the "Marchen" Unicode
2992 * character block.
2993 * @since 11
2994 */
2995 public static final UnicodeBlock MARCHEN =
2996 new UnicodeBlock("MARCHEN");
2997
2998 /**
2999 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3000 * character block.
3001 * @since 11
3002 */
3003 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3004 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3005 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3006 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3007
3008 /**
3009 * Constant for the "Tangut" Unicode
3010 * character block.
3011 * @since 11
3012 */
3013 public static final UnicodeBlock TANGUT =
3014 new UnicodeBlock("TANGUT");
3015
3016 /**
3017 * Constant for the "Tangut Components" Unicode
3018 * character block.
3019 * @since 11
3020 */
3021 public static final UnicodeBlock TANGUT_COMPONENTS =
3022 new UnicodeBlock("TANGUT_COMPONENTS",
3023 "TANGUT COMPONENTS",
3024 "TANGUTCOMPONENTS");
3025
3026 /**
3027 * Constant for the "Kana Extended-A" Unicode
3028 * character block.
3029 * @since 11
3030 */
3031 public static final UnicodeBlock KANA_EXTENDED_A =
3032 new UnicodeBlock("KANA_EXTENDED_A",
3033 "KANA EXTENDED-A",
3034 "KANAEXTENDED-A");
3035 /**
3036 * Constant for the "Glagolitic Supplement" Unicode
3037 * character block.
3038 * @since 11
3039 */
3040 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3041 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3042 "GLAGOLITIC SUPPLEMENT",
3043 "GLAGOLITICSUPPLEMENT");
3044 /**
3045 * Constant for the "Adlam" Unicode
3046 * character block.
3047 * @since 11
3048 */
3049 public static final UnicodeBlock ADLAM =
3050 new UnicodeBlock("ADLAM");
3051
3052 /**
3053 * Constant for the "Masaram Gondi" Unicode
3054 * character block.
3055 * @since 11
3056 */
3057 public static final UnicodeBlock MASARAM_GONDI =
3058 new UnicodeBlock("MASARAM_GONDI",
3059 "MASARAM GONDI",
3060 "MASARAMGONDI");
3061
3062 /**
3063 * Constant for the "Zanabazar Square" Unicode
3064 * character block.
3065 * @since 11
3066 */
3067 public static final UnicodeBlock ZANABAZAR_SQUARE =
3068 new UnicodeBlock("ZANABAZAR_SQUARE",
3069 "ZANABAZAR SQUARE",
3070 "ZANABAZARSQUARE");
3071
3072 /**
3073 * Constant for the "Nushu" Unicode
3074 * character block.
3075 * @since 11
3076 */
3077 public static final UnicodeBlock NUSHU =
3078 new UnicodeBlock("NUSHU");
3079
3080 /**
3081 * Constant for the "Soyombo" Unicode
3082 * character block.
3083 * @since 11
3084 */
3085 public static final UnicodeBlock SOYOMBO =
3086 new UnicodeBlock("SOYOMBO");
3087
3088 /**
3089 * Constant for the "Bhaiksuki" Unicode
3090 * character block.
3091 * @since 11
3092 */
3093 public static final UnicodeBlock BHAIKSUKI =
3094 new UnicodeBlock("BHAIKSUKI");
3095
3096 /**
3097 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3098 * character block.
3099 * @since 11
3100 */
3101 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3102 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3103 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3104 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3105 /**
3106 * Constant for the "Georgian Extended" Unicode
3107 * character block.
3108 * @since 12
3109 */
3110 public static final UnicodeBlock GEORGIAN_EXTENDED =
3111 new UnicodeBlock("GEORGIAN_EXTENDED",
3112 "GEORGIAN EXTENDED",
3113 "GEORGIANEXTENDED");
3114
3115 /**
3116 * Constant for the "Hanifi Rohingya" Unicode
3117 * character block.
3118 * @since 12
3119 */
3120 public static final UnicodeBlock HANIFI_ROHINGYA =
3121 new UnicodeBlock("HANIFI_ROHINGYA",
3122 "HANIFI ROHINGYA",
3123 "HANIFIROHINGYA");
3124
3125 /**
3126 * Constant for the "Old Sogdian" Unicode
3127 * character block.
3128 * @since 12
3129 */
3130 public static final UnicodeBlock OLD_SOGDIAN =
3131 new UnicodeBlock("OLD_SOGDIAN",
3132 "OLD SOGDIAN",
3133 "OLDSOGDIAN");
3134
3135 /**
3136 * Constant for the "Sogdian" Unicode
3137 * character block.
3138 * @since 12
3139 */
3140 public static final UnicodeBlock SOGDIAN =
3141 new UnicodeBlock("SOGDIAN");
3142
3143 /**
3144 * Constant for the "Dogra" Unicode
3145 * character block.
3146 * @since 12
3147 */
3148 public static final UnicodeBlock DOGRA =
3149 new UnicodeBlock("DOGRA");
3150
3151 /**
3152 * Constant for the "Gunjala Gondi" Unicode
3153 * character block.
3154 * @since 12
3155 */
3156 public static final UnicodeBlock GUNJALA_GONDI =
3157 new UnicodeBlock("GUNJALA_GONDI",
3158 "GUNJALA GONDI",
3159 "GUNJALAGONDI");
3160
3161 /**
3162 * Constant for the "Makasar" Unicode
3163 * character block.
3164 * @since 12
3165 */
3166 public static final UnicodeBlock MAKASAR =
3167 new UnicodeBlock("MAKASAR");
3168
3169 /**
3170 * Constant for the "Medefaidrin" Unicode
3171 * character block.
3172 * @since 12
3173 */
3174 public static final UnicodeBlock MEDEFAIDRIN =
3175 new UnicodeBlock("MEDEFAIDRIN");
3176
3177 /**
3178 * Constant for the "Mayan Numerals" Unicode
3179 * character block.
3180 * @since 12
3181 */
3182 public static final UnicodeBlock MAYAN_NUMERALS =
3183 new UnicodeBlock("MAYAN_NUMERALS",
3184 "MAYAN NUMERALS",
3185 "MAYANNUMERALS");
3186
3187 /**
3188 * Constant for the "Indic Siyaq Numbers" Unicode
3189 * character block.
3190 * @since 12
3191 */
3192 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3193 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3194 "INDIC SIYAQ NUMBERS",
3195 "INDICSIYAQNUMBERS");
3196
3197 /**
3198 * Constant for the "Chess Symbols" Unicode
3199 * character block.
3200 * @since 12
3201 */
3202 public static final UnicodeBlock CHESS_SYMBOLS =
3203 new UnicodeBlock("CHESS_SYMBOLS",
3204 "CHESS SYMBOLS",
3205 "CHESSSYMBOLS");
3206
3207
3208 private static final int blockStarts[] = {
3209 0x0000, // 0000..007F; Basic Latin
3210 0x0080, // 0080..00FF; Latin-1 Supplement
3211 0x0100, // 0100..017F; Latin Extended-A
3212 0x0180, // 0180..024F; Latin Extended-B
3213 0x0250, // 0250..02AF; IPA Extensions
3214 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3215 0x0300, // 0300..036F; Combining Diacritical Marks
3216 0x0370, // 0370..03FF; Greek and Coptic
3217 0x0400, // 0400..04FF; Cyrillic
3218 0x0500, // 0500..052F; Cyrillic Supplement
3219 0x0530, // 0530..058F; Armenian
3220 0x0590, // 0590..05FF; Hebrew
3221 0x0600, // 0600..06FF; Arabic
3222 0x0700, // 0700..074F; Syriac
3223 0x0750, // 0750..077F; Arabic Supplement
3224 0x0780, // 0780..07BF; Thaana
3225 0x07C0, // 07C0..07FF; NKo
3226 0x0800, // 0800..083F; Samaritan
3227 0x0840, // 0840..085F; Mandaic
3228 0x0860, // 0860..086F; Syriac Supplement
3229 0x0870, // unassigned
3230 0x08A0, // 08A0..08FF; Arabic Extended-A
3231 0x0900, // 0900..097F; Devanagari
3232 0x0980, // 0980..09FF; Bengali
3233 0x0A00, // 0A00..0A7F; Gurmukhi
3234 0x0A80, // 0A80..0AFF; Gujarati
3235 0x0B00, // 0B00..0B7F; Oriya
3236 0x0B80, // 0B80..0BFF; Tamil
3237 0x0C00, // 0C00..0C7F; Telugu
3238 0x0C80, // 0C80..0CFF; Kannada
3239 0x0D00, // 0D00..0D7F; Malayalam
3240 0x0D80, // 0D80..0DFF; Sinhala
3241 0x0E00, // 0E00..0E7F; Thai
3242 0x0E80, // 0E80..0EFF; Lao
3243 0x0F00, // 0F00..0FFF; Tibetan
3244 0x1000, // 1000..109F; Myanmar
3245 0x10A0, // 10A0..10FF; Georgian
3246 0x1100, // 1100..11FF; Hangul Jamo
3247 0x1200, // 1200..137F; Ethiopic
3248 0x1380, // 1380..139F; Ethiopic Supplement
3249 0x13A0, // 13A0..13FF; Cherokee
3250 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3251 0x1680, // 1680..169F; Ogham
3252 0x16A0, // 16A0..16FF; Runic
3253 0x1700, // 1700..171F; Tagalog
3254 0x1720, // 1720..173F; Hanunoo
3255 0x1740, // 1740..175F; Buhid
3256 0x1760, // 1760..177F; Tagbanwa
3257 0x1780, // 1780..17FF; Khmer
3258 0x1800, // 1800..18AF; Mongolian
3259 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3260 0x1900, // 1900..194F; Limbu
3261 0x1950, // 1950..197F; Tai Le
3262 0x1980, // 1980..19DF; New Tai Lue
3263 0x19E0, // 19E0..19FF; Khmer Symbols
3264 0x1A00, // 1A00..1A1F; Buginese
3265 0x1A20, // 1A20..1AAF; Tai Tham
3266 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3267 0x1B00, // 1B00..1B7F; Balinese
3268 0x1B80, // 1B80..1BBF; Sundanese
3269 0x1BC0, // 1BC0..1BFF; Batak
3270 0x1C00, // 1C00..1C4F; Lepcha
3271 0x1C50, // 1C50..1C7F; Ol Chiki
3272 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3273 0x1C90, // 1C90..1CBF; Georgian Extended
3274 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3275 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3276 0x1D00, // 1D00..1D7F; Phonetic Extensions
3277 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3278 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3279 0x1E00, // 1E00..1EFF; Latin Extended Additional
3280 0x1F00, // 1F00..1FFF; Greek Extended
3281 0x2000, // 2000..206F; General Punctuation
3282 0x2070, // 2070..209F; Superscripts and Subscripts
3283 0x20A0, // 20A0..20CF; Currency Symbols
3284 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3285 0x2100, // 2100..214F; Letterlike Symbols
3286 0x2150, // 2150..218F; Number Forms
3287 0x2190, // 2190..21FF; Arrows
3288 0x2200, // 2200..22FF; Mathematical Operators
3289 0x2300, // 2300..23FF; Miscellaneous Technical
3290 0x2400, // 2400..243F; Control Pictures
3291 0x2440, // 2440..245F; Optical Character Recognition
3292 0x2460, // 2460..24FF; Enclosed Alphanumerics
3293 0x2500, // 2500..257F; Box Drawing
3294 0x2580, // 2580..259F; Block Elements
3295 0x25A0, // 25A0..25FF; Geometric Shapes
3296 0x2600, // 2600..26FF; Miscellaneous Symbols
3297 0x2700, // 2700..27BF; Dingbats
3298 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3299 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3300 0x2800, // 2800..28FF; Braille Patterns
3301 0x2900, // 2900..297F; Supplemental Arrows-B
3302 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3303 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3304 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3305 0x2C00, // 2C00..2C5F; Glagolitic
3306 0x2C60, // 2C60..2C7F; Latin Extended-C
3307 0x2C80, // 2C80..2CFF; Coptic
3308 0x2D00, // 2D00..2D2F; Georgian Supplement
3309 0x2D30, // 2D30..2D7F; Tifinagh
3310 0x2D80, // 2D80..2DDF; Ethiopic Extended
3311 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3312 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3313 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3314 0x2F00, // 2F00..2FDF; Kangxi Radicals
3315 0x2FE0, // unassigned
3316 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3317 0x3000, // 3000..303F; CJK Symbols and Punctuation
3318 0x3040, // 3040..309F; Hiragana
3319 0x30A0, // 30A0..30FF; Katakana
3320 0x3100, // 3100..312F; Bopomofo
3321 0x3130, // 3130..318F; Hangul Compatibility Jamo
3322 0x3190, // 3190..319F; Kanbun
3323 0x31A0, // 31A0..31BF; Bopomofo Extended
3324 0x31C0, // 31C0..31EF; CJK Strokes
3325 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3326 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3327 0x3300, // 3300..33FF; CJK Compatibility
3328 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3329 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3330 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3331 0xA000, // A000..A48F; Yi Syllables
3332 0xA490, // A490..A4CF; Yi Radicals
3333 0xA4D0, // A4D0..A4FF; Lisu
3334 0xA500, // A500..A63F; Vai
3335 0xA640, // A640..A69F; Cyrillic Extended-B
3336 0xA6A0, // A6A0..A6FF; Bamum
3337 0xA700, // A700..A71F; Modifier Tone Letters
3338 0xA720, // A720..A7FF; Latin Extended-D
3339 0xA800, // A800..A82F; Syloti Nagri
3340 0xA830, // A830..A83F; Common Indic Number Forms
3341 0xA840, // A840..A87F; Phags-pa
3342 0xA880, // A880..A8DF; Saurashtra
3343 0xA8E0, // A8E0..A8FF; Devanagari Extended
3344 0xA900, // A900..A92F; Kayah Li
3345 0xA930, // A930..A95F; Rejang
3346 0xA960, // A960..A97F; Hangul Jamo Extended-A
3347 0xA980, // A980..A9DF; Javanese
3348 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3349 0xAA00, // AA00..AA5F; Cham
3350 0xAA60, // AA60..AA7F; Myanmar Extended-A
3351 0xAA80, // AA80..AADF; Tai Viet
3352 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3353 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3354 0xAB30, // AB30..AB6F; Latin Extended-E
3355 0xAB70, // AB70..ABBF; Cherokee Supplement
3356 0xABC0, // ABC0..ABFF; Meetei Mayek
3357 0xAC00, // AC00..D7AF; Hangul Syllables
3358 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3359 0xD800, // D800..DB7F; High Surrogates
3360 0xDB80, // DB80..DBFF; High Private Use Surrogates
3361 0xDC00, // DC00..DFFF; Low Surrogates
3362 0xE000, // E000..F8FF; Private Use Area
3363 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3364 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3365 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3366 0xFE00, // FE00..FE0F; Variation Selectors
3367 0xFE10, // FE10..FE1F; Vertical Forms
3368 0xFE20, // FE20..FE2F; Combining Half Marks
3369 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3370 0xFE50, // FE50..FE6F; Small Form Variants
3371 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3372 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3373 0xFFF0, // FFF0..FFFF; Specials
3374 0x10000, // 10000..1007F; Linear B Syllabary
3375 0x10080, // 10080..100FF; Linear B Ideograms
3376 0x10100, // 10100..1013F; Aegean Numbers
3377 0x10140, // 10140..1018F; Ancient Greek Numbers
3378 0x10190, // 10190..101CF; Ancient Symbols
3379 0x101D0, // 101D0..101FF; Phaistos Disc
3380 0x10200, // unassigned
3381 0x10280, // 10280..1029F; Lycian
3382 0x102A0, // 102A0..102DF; Carian
3383 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3384 0x10300, // 10300..1032F; Old Italic
3385 0x10330, // 10330..1034F; Gothic
3386 0x10350, // 10350..1037F; Old Permic
3387 0x10380, // 10380..1039F; Ugaritic
3388 0x103A0, // 103A0..103DF; Old Persian
3389 0x103E0, // unassigned
3390 0x10400, // 10400..1044F; Deseret
3391 0x10450, // 10450..1047F; Shavian
3392 0x10480, // 10480..104AF; Osmanya
3393 0x104B0, // 104B0..104FF; Osage
3394 0x10500, // 10500..1052F; Elbasan
3395 0x10530, // 10530..1056F; Caucasian Albanian
3396 0x10570, // unassigned
3397 0x10600, // 10600..1077F; Linear A
3398 0x10780, // unassigned
3399 0x10800, // 10800..1083F; Cypriot Syllabary
3400 0x10840, // 10840..1085F; Imperial Aramaic
3401 0x10860, // 10860..1087F; Palmyrene
3402 0x10880, // 10880..108AF; Nabataean
3403 0x108B0, // unassigned
3404 0x108E0, // 108E0..108FF; Hatran
3405 0x10900, // 10900..1091F; Phoenician
3406 0x10920, // 10920..1093F; Lydian
3407 0x10940, // unassigned
3408 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3409 0x109A0, // 109A0..109FF; Meroitic Cursive
3410 0x10A00, // 10A00..10A5F; Kharoshthi
3411 0x10A60, // 10A60..10A7F; Old South Arabian
3412 0x10A80, // 10A80..10A9F; Old North Arabian
3413 0x10AA0, // unassigned
3414 0x10AC0, // 10AC0..10AFF; Manichaean
3415 0x10B00, // 10B00..10B3F; Avestan
3416 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3417 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3418 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3419 0x10BB0, // unassigned
3420 0x10C00, // 10C00..10C4F; Old Turkic
3421 0x10C50, // unassigned
3422 0x10C80, // 10C80..10CFF; Old Hungarian
3423 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3424 0x10D40, // unassigned
3425 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3426 0x10E80, // unassigned
3427 0x10F00, // 10F00..10F2F; Old Sogdian
3428 0x10F30, // 10F30..10F6F; Sogdian
3429 0x10F70, // unassigned
3430 0x11000, // 11000..1107F; Brahmi
3431 0x11080, // 11080..110CF; Kaithi
3432 0x110D0, // 110D0..110FF; Sora Sompeng
3433 0x11100, // 11100..1114F; Chakma
3434 0x11150, // 11150..1117F; Mahajani
3435 0x11180, // 11180..111DF; Sharada
3436 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3437 0x11200, // 11200..1124F; Khojki
3438 0x11250, // unassigned
3439 0x11280, // 11280..112AF; Multani
3440 0x112B0, // 112B0..112FF; Khudawadi
3441 0x11300, // 11300..1137F; Grantha
3442 0x11380, // unassigned
3443 0x11400, // 11400..1147F; Newa
3444 0x11480, // 11480..114DF; Tirhuta
3445 0x114E0, // unassigned
3446 0x11580, // 11580..115FF; Siddham
3447 0x11600, // 11600..1165F; Modi
3448 0x11660, // 11660..1167F; Mongolian Supplement
3449 0x11680, // 11680..116CF; Takri
3450 0x116D0, // unassigned
3451 0x11700, // 11700..1173F; Ahom
3452 0x11740, // unassigned
3453 0x11800, // 11800..1184F; Dogra
3454 0x11850, // unassigned
3455 0x118A0, // 118A0..118FF; Warang Citi
3456 0x11900, // unassigned
3457 0x11A00, // 11A00..11A4F; Zanabazar Square
3458 0x11A50, // 11A50..11AAF; Soyombo
3459 0x11AB0, // unassigned
3460 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3461 0x11B00, // unassigned
3462 0x11C00, // 11C00..11C6F; Bhaiksuki
3463 0x11C70, // 11C70..11CBF; Marchen
3464 0x11CC0, // unassigned
3465 0x11D00, // 11D00..11D5F; Masaram Gondi
3466 0x11D60, // 11D60..11DAF; Gunjala Gondi
3467 0x11DB0, // unassigned
3468 0x11EE0, // 11EE0..11EFF; Makasar
3469 0x11F00, // unassigned
3470 0x12000, // 12000..123FF; Cuneiform
3471 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3472 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3473 0x12550, // unassigned
3474 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3475 0x13430, // unassigned
3476 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3477 0x14680, // unassigned
3478 0x16800, // 16800..16A3F; Bamum Supplement
3479 0x16A40, // 16A40..16A6F; Mro
3480 0x16A70, // unassigned
3481 0x16AD0, // 16AD0..16AFF; Bassa Vah
3482 0x16B00, // 16B00..16B8F; Pahawh Hmong
3483 0x16B90, // unassigned
3484 0x16E40, // 16E40..16E9F; Medefaidrin
3485 0x16EA0, // unassigned
3486 0x16F00, // 16F00..16F9F; Miao
3487 0x16FA0, // unassigned
3488 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
3489 0x17000, // 17000..187FF; Tangut
3490 0x18800, // 18800..18AFF; Tangut Components
3491 0x18B00, // unassigned
3492 0x1B000, // 1B000..1B0FF; Kana Supplement
3493 0x1B100, // 1B100..1B12F; Kana Extended-A
3494 0x1B130, // unassigned
3495 0x1B170, // 1B170..1B2FF; Nushu
3496 0x1B300, // unassigned
3497 0x1BC00, // 1BC00..1BC9F; Duployan
3498 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3499 0x1BCB0, // unassigned
3500 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3501 0x1D100, // 1D100..1D1FF; Musical Symbols
3502 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3503 0x1D250, // unassigned
3504 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
3505 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3506 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3507 0x1D380, // unassigned
3508 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3509 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3510 0x1DAB0, // unassigned
3511 0x1E000, // 1E000..1E02F; Glagolitic Supplement
3512 0x1E030, // unassigned
3513 0x1E800, // 1E800..1E8DF; Mende Kikakui
3514 0x1E8E0, // unassigned
3515 0x1E900, // 1E900..1E95F; Adlam
3516 0x1E960, // unassigned
3517 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
3518 0x1ECC0, // unassigned
3519 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3520 0x1EF00, // unassigned
3521 0x1F000, // 1F000..1F02F; Mahjong Tiles
3522 0x1F030, // 1F030..1F09F; Domino Tiles
3523 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3524 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3525 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3526 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3527 0x1F600, // 1F600..1F64F; Emoticons
3528 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3529 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3530 0x1F700, // 1F700..1F77F; Alchemical Symbols
3531 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3532 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3533 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3534 0x1FA00, // 1FA00..1FA6F; Chess Symbols
3535 0x1FA70, // unassigned
3536 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3537 0x2A6E0, // unassigned
3538 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3539 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3540 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
3541 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
3542 0x2EBF0, // unassigned
3543 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
3544 0x2FA20, // unassigned
3545 0xE0000, // E0000..E007F; Tags
3546 0xE0080, // unassigned
3547 0xE0100, // E0100..E01EF; Variation Selectors Supplement
3548 0xE01F0, // unassigned
3549 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
3550 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B
3551 };
3552
3553 private static final UnicodeBlock[] blocks = {
3554 BASIC_LATIN,
3555 LATIN_1_SUPPLEMENT,
3556 LATIN_EXTENDED_A,
3557 LATIN_EXTENDED_B,
3558 IPA_EXTENSIONS,
3559 SPACING_MODIFIER_LETTERS,
3560 COMBINING_DIACRITICAL_MARKS,
3561 GREEK,
3562 CYRILLIC,
3563 CYRILLIC_SUPPLEMENTARY,
3564 ARMENIAN,
3565 HEBREW,
3566 ARABIC,
3567 SYRIAC,
3568 ARABIC_SUPPLEMENT,
3569 THAANA,
3570 NKO,
3571 SAMARITAN,
3572 MANDAIC,
3573 SYRIAC_SUPPLEMENT,
3574 null,
3575 ARABIC_EXTENDED_A,
3576 DEVANAGARI,
3577 BENGALI,
3578 GURMUKHI,
3579 GUJARATI,
3580 ORIYA,
3581 TAMIL,
3582 TELUGU,
3583 KANNADA,
3584 MALAYALAM,
3585 SINHALA,
3586 THAI,
3587 LAO,
3588 TIBETAN,
3589 MYANMAR,
3590 GEORGIAN,
3591 HANGUL_JAMO,
3592 ETHIOPIC,
3593 ETHIOPIC_SUPPLEMENT,
3594 CHEROKEE,
3595 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
3596 OGHAM,
3597 RUNIC,
3598 TAGALOG,
3599 HANUNOO,
3600 BUHID,
3601 TAGBANWA,
3602 KHMER,
3603 MONGOLIAN,
3604 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
3605 LIMBU,
3606 TAI_LE,
3607 NEW_TAI_LUE,
3608 KHMER_SYMBOLS,
3609 BUGINESE,
3610 TAI_THAM,
3611 COMBINING_DIACRITICAL_MARKS_EXTENDED,
3612 BALINESE,
3613 SUNDANESE,
3614 BATAK,
3615 LEPCHA,
3616 OL_CHIKI,
3617 CYRILLIC_EXTENDED_C,
3618 GEORGIAN_EXTENDED,
3619 SUNDANESE_SUPPLEMENT,
3620 VEDIC_EXTENSIONS,
3621 PHONETIC_EXTENSIONS,
3622 PHONETIC_EXTENSIONS_SUPPLEMENT,
3623 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
3624 LATIN_EXTENDED_ADDITIONAL,
3625 GREEK_EXTENDED,
3626 GENERAL_PUNCTUATION,
3627 SUPERSCRIPTS_AND_SUBSCRIPTS,
3628 CURRENCY_SYMBOLS,
3629 COMBINING_MARKS_FOR_SYMBOLS,
3630 LETTERLIKE_SYMBOLS,
3631 NUMBER_FORMS,
3632 ARROWS,
3633 MATHEMATICAL_OPERATORS,
3634 MISCELLANEOUS_TECHNICAL,
3635 CONTROL_PICTURES,
3636 OPTICAL_CHARACTER_RECOGNITION,
3637 ENCLOSED_ALPHANUMERICS,
3638 BOX_DRAWING,
3639 BLOCK_ELEMENTS,
3640 GEOMETRIC_SHAPES,
3641 MISCELLANEOUS_SYMBOLS,
3642 DINGBATS,
3643 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
3644 SUPPLEMENTAL_ARROWS_A,
3645 BRAILLE_PATTERNS,
3646 SUPPLEMENTAL_ARROWS_B,
3647 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
3648 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
3649 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
3650 GLAGOLITIC,
3651 LATIN_EXTENDED_C,
3652 COPTIC,
3653 GEORGIAN_SUPPLEMENT,
3654 TIFINAGH,
3655 ETHIOPIC_EXTENDED,
3656 CYRILLIC_EXTENDED_A,
3657 SUPPLEMENTAL_PUNCTUATION,
3658 CJK_RADICALS_SUPPLEMENT,
3659 KANGXI_RADICALS,
3660 null,
3661 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
3662 CJK_SYMBOLS_AND_PUNCTUATION,
3663 HIRAGANA,
3664 KATAKANA,
3665 BOPOMOFO,
3666 HANGUL_COMPATIBILITY_JAMO,
3667 KANBUN,
3668 BOPOMOFO_EXTENDED,
3669 CJK_STROKES,
3670 KATAKANA_PHONETIC_EXTENSIONS,
3671 ENCLOSED_CJK_LETTERS_AND_MONTHS,
3672 CJK_COMPATIBILITY,
3673 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
3674 YIJING_HEXAGRAM_SYMBOLS,
3675 CJK_UNIFIED_IDEOGRAPHS,
3676 YI_SYLLABLES,
3677 YI_RADICALS,
3678 LISU,
3679 VAI,
3680 CYRILLIC_EXTENDED_B,
3681 BAMUM,
3682 MODIFIER_TONE_LETTERS,
3683 LATIN_EXTENDED_D,
3684 SYLOTI_NAGRI,
3685 COMMON_INDIC_NUMBER_FORMS,
3686 PHAGS_PA,
3687 SAURASHTRA,
3688 DEVANAGARI_EXTENDED,
3689 KAYAH_LI,
3690 REJANG,
3691 HANGUL_JAMO_EXTENDED_A,
3692 JAVANESE,
3693 MYANMAR_EXTENDED_B,
3694 CHAM,
3695 MYANMAR_EXTENDED_A,
3696 TAI_VIET,
3697 MEETEI_MAYEK_EXTENSIONS,
3698 ETHIOPIC_EXTENDED_A,
3699 LATIN_EXTENDED_E,
3700 CHEROKEE_SUPPLEMENT,
3701 MEETEI_MAYEK,
3702 HANGUL_SYLLABLES,
3703 HANGUL_JAMO_EXTENDED_B,
3704 HIGH_SURROGATES,
3705 HIGH_PRIVATE_USE_SURROGATES,
3706 LOW_SURROGATES,
3707 PRIVATE_USE_AREA,
3708 CJK_COMPATIBILITY_IDEOGRAPHS,
3709 ALPHABETIC_PRESENTATION_FORMS,
3710 ARABIC_PRESENTATION_FORMS_A,
3711 VARIATION_SELECTORS,
3712 VERTICAL_FORMS,
3713 COMBINING_HALF_MARKS,
3714 CJK_COMPATIBILITY_FORMS,
3715 SMALL_FORM_VARIANTS,
3716 ARABIC_PRESENTATION_FORMS_B,
3717 HALFWIDTH_AND_FULLWIDTH_FORMS,
3718 SPECIALS,
3719 LINEAR_B_SYLLABARY,
3720 LINEAR_B_IDEOGRAMS,
3721 AEGEAN_NUMBERS,
3722 ANCIENT_GREEK_NUMBERS,
3723 ANCIENT_SYMBOLS,
3724 PHAISTOS_DISC,
3725 null,
3726 LYCIAN,
3727 CARIAN,
3728 COPTIC_EPACT_NUMBERS,
3729 OLD_ITALIC,
3730 GOTHIC,
3731 OLD_PERMIC,
3732 UGARITIC,
3733 OLD_PERSIAN,
3734 null,
3735 DESERET,
3736 SHAVIAN,
3737 OSMANYA,
3738 OSAGE,
3739 ELBASAN,
3740 CAUCASIAN_ALBANIAN,
3741 null,
3742 LINEAR_A,
3743 null,
3744 CYPRIOT_SYLLABARY,
3745 IMPERIAL_ARAMAIC,
3746 PALMYRENE,
3747 NABATAEAN,
3748 null,
3749 HATRAN,
3750 PHOENICIAN,
3751 LYDIAN,
3752 null,
3753 MEROITIC_HIEROGLYPHS,
3754 MEROITIC_CURSIVE,
3755 KHAROSHTHI,
3756 OLD_SOUTH_ARABIAN,
3757 OLD_NORTH_ARABIAN,
3758 null,
3759 MANICHAEAN,
3760 AVESTAN,
3761 INSCRIPTIONAL_PARTHIAN,
3762 INSCRIPTIONAL_PAHLAVI,
3763 PSALTER_PAHLAVI,
3764 null,
3765 OLD_TURKIC,
3766 null,
3767 OLD_HUNGARIAN,
3768 HANIFI_ROHINGYA,
3769 null,
3770 RUMI_NUMERAL_SYMBOLS,
3771 null,
3772 OLD_SOGDIAN,
3773 SOGDIAN,
3774 null,
3775 BRAHMI,
3776 KAITHI,
3777 SORA_SOMPENG,
3778 CHAKMA,
3779 MAHAJANI,
3780 SHARADA,
3781 SINHALA_ARCHAIC_NUMBERS,
3782 KHOJKI,
3783 null,
3784 MULTANI,
3785 KHUDAWADI,
3786 GRANTHA,
3787 null,
3788 NEWA,
3789 TIRHUTA,
3790 null,
3791 SIDDHAM,
3792 MODI,
3793 MONGOLIAN_SUPPLEMENT,
3794 TAKRI,
3795 null,
3796 AHOM,
3797 null,
3798 DOGRA,
3799 null,
3800 WARANG_CITI,
3801 null,
3802 ZANABAZAR_SQUARE,
3803 SOYOMBO,
3804 null,
3805 PAU_CIN_HAU,
3806 null,
3807 BHAIKSUKI,
3808 MARCHEN,
3809 null,
3810 MASARAM_GONDI,
3811 GUNJALA_GONDI,
3812 null,
3813 MAKASAR,
3814 null,
3815 CUNEIFORM,
3816 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
3817 EARLY_DYNASTIC_CUNEIFORM,
3818 null,
3819 EGYPTIAN_HIEROGLYPHS,
3820 null,
3821 ANATOLIAN_HIEROGLYPHS,
3822 null,
3823 BAMUM_SUPPLEMENT,
3824 MRO,
3825 null,
3826 BASSA_VAH,
3827 PAHAWH_HMONG,
3828 null,
3829 MEDEFAIDRIN,
3830 null,
3831 MIAO,
3832 null,
3833 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
3834 TANGUT,
3835 TANGUT_COMPONENTS,
3836 null,
3837 KANA_SUPPLEMENT,
3838 KANA_EXTENDED_A,
3839 null,
3840 NUSHU,
3841 null,
3842 DUPLOYAN,
3843 SHORTHAND_FORMAT_CONTROLS,
3844 null,
3845 BYZANTINE_MUSICAL_SYMBOLS,
3846 MUSICAL_SYMBOLS,
3847 ANCIENT_GREEK_MUSICAL_NOTATION,
3848 null,
3849 MAYAN_NUMERALS,
3850 TAI_XUAN_JING_SYMBOLS,
3851 COUNTING_ROD_NUMERALS,
3852 null,
3853 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
3854 SUTTON_SIGNWRITING,
3855 null,
3856 GLAGOLITIC_SUPPLEMENT,
3857 null,
3858 MENDE_KIKAKUI,
3859 null,
3860 ADLAM,
3861 null,
3862 INDIC_SIYAQ_NUMBERS,
3863 null,
3864 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
3865 null,
3866 MAHJONG_TILES,
3867 DOMINO_TILES,
3868 PLAYING_CARDS,
3869 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
3870 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
3871 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
3872 EMOTICONS,
3873 ORNAMENTAL_DINGBATS,
3874 TRANSPORT_AND_MAP_SYMBOLS,
3875 ALCHEMICAL_SYMBOLS,
3876 GEOMETRIC_SHAPES_EXTENDED,
3877 SUPPLEMENTAL_ARROWS_C,
3878 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
3879 CHESS_SYMBOLS,
3880 null,
3881 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
3882 null,
3883 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
3884 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
3885 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
3886 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
3887 null,
3888 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
3889 null,
3890 TAGS,
3891 null,
3892 VARIATION_SELECTORS_SUPPLEMENT,
3893 null,
3894 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
3895 SUPPLEMENTARY_PRIVATE_USE_AREA_B
3896 };
3897
3898
3899 /**
3900 * Returns the object representing the Unicode block containing the
3901 * given character, or {@code null} if the character is not a
3902 * member of a defined block.
3903 *
3904 * <p><b>Note:</b> This method cannot handle
3905 * <a href="Character.html#supplementary"> supplementary
3906 * characters</a>. To support all Unicode characters, including
3907 * supplementary characters, use the {@link #of(int)} method.
3908 *
3909 * @param c The character in question
3910 * @return The {@code UnicodeBlock} instance representing the
3911 * Unicode block of which this character is a member, or
3912 * {@code null} if the character is not a member of any
3913 * Unicode block
3914 */
3915 public static UnicodeBlock of(char c) {
3916 return of((int)c);
3917 }
3918
3919 /**
3920 * Returns the object representing the Unicode block
3921 * containing the given character (Unicode code point), or
3922 * {@code null} if the character is not a member of a
3923 * defined block.
3924 *
3925 * @param codePoint the character (Unicode code point) in question.
3926 * @return The {@code UnicodeBlock} instance representing the
3927 * Unicode block of which this character is a member, or
3928 * {@code null} if the character is not a member of any
3929 * Unicode block
3930 * @throws IllegalArgumentException if the specified
3931 * {@code codePoint} is an invalid Unicode code point.
3932 * @see Character#isValidCodePoint(int)
3933 * @since 1.5
3934 */
3935 public static UnicodeBlock of(int codePoint) {
3936 if (!isValidCodePoint(codePoint)) {
3937 throw new IllegalArgumentException(
3938 String.format("Not a valid Unicode code point: 0x%X", codePoint));
3939 }
3940
3941 int top, bottom, current;
3942 bottom = 0;
3943 top = blockStarts.length;
3944 current = top/2;
3945
3946 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
3947 while (top - bottom > 1) {
3948 if (codePoint >= blockStarts[current]) {
3949 bottom = current;
3950 } else {
3951 top = current;
3952 }
3953 current = (top + bottom) / 2;
3954 }
3955 return blocks[current];
3956 }
3957
3958 /**
3959 * Returns the UnicodeBlock with the given name. Block
3960 * names are determined by The Unicode Standard. The file
3961 * {@code Blocks-<version>.txt} defines blocks for a particular
3962 * version of the standard. The {@link Character} class specifies
3963 * the version of the standard that it supports.
3964 * <p>
3965 * This method accepts block names in the following forms:
3966 * <ol>
3967 * <li> Canonical block names as defined by the Unicode Standard.
3968 * For example, the standard defines a "Basic Latin" block. Therefore, this
3969 * method accepts "Basic Latin" as a valid block name. The documentation of
3970 * each UnicodeBlock provides the canonical name.
3971 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
3972 * is a valid block name for the "Basic Latin" block.
3973 * <li>The text representation of each constant UnicodeBlock identifier.
3974 * For example, this method will return the {@link #BASIC_LATIN} block if
3975 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
3976 * hyphens in the canonical name with underscores.
3977 * </ol>
3978 * Finally, character case is ignored for all of the valid block name forms.
3979 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
3980 * The en_US locale's case mapping rules are used to provide case-insensitive
3981 * string comparisons for block name validation.
3982 * <p>
3983 * If the Unicode Standard changes block names, both the previous and
3984 * current names will be accepted.
3985 *
3986 * @param blockName A {@code UnicodeBlock} name.
3987 * @return The {@code UnicodeBlock} instance identified
3988 * by {@code blockName}
3989 * @throws IllegalArgumentException if {@code blockName} is an
3990 * invalid name
3991 * @throws NullPointerException if {@code blockName} is null
3992 * @since 1.5
3993 */
3994 public static final UnicodeBlock forName(String blockName) {
3995 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
3996 if (block == null) {
3997 throw new IllegalArgumentException("Not a valid block name: "
3998 + blockName);
3999 }
4000 return block;
4001 }
4002 }
4003
4004
4005 /**
4006 * A family of character subsets representing the character scripts
4007 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4008 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4009 * character is assigned to a single Unicode script, either a specific
4010 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4011 * one of the following three special values,
4012 * {@link Character.UnicodeScript#INHERITED Inherited},
4013 * {@link Character.UnicodeScript#COMMON Common} or
4014 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4015 *
4016 * @since 1.7
4017 */
4018 public static enum UnicodeScript {
4019 /**
4020 * Unicode script "Common".
4021 */
4022 COMMON,
4023
4024 /**
4025 * Unicode script "Latin".
4026 */
4027 LATIN,
4028
4029 /**
4030 * Unicode script "Greek".
4031 */
4032 GREEK,
4033
4034 /**
4035 * Unicode script "Cyrillic".
4036 */
4037 CYRILLIC,
4038
4039 /**
4040 * Unicode script "Armenian".
4041 */
4042 ARMENIAN,
4043
4044 /**
4045 * Unicode script "Hebrew".
4046 */
4047 HEBREW,
4048
4049 /**
4050 * Unicode script "Arabic".
4051 */
4052 ARABIC,
4053
4054 /**
4055 * Unicode script "Syriac".
4056 */
4057 SYRIAC,
4058
4059 /**
4060 * Unicode script "Thaana".
4061 */
4062 THAANA,
4063
4064 /**
4065 * Unicode script "Devanagari".
4066 */
4067 DEVANAGARI,
4068
4069 /**
4070 * Unicode script "Bengali".
4071 */
4072 BENGALI,
4073
4074 /**
4075 * Unicode script "Gurmukhi".
4076 */
4077 GURMUKHI,
4078
4079 /**
4080 * Unicode script "Gujarati".
4081 */
4082 GUJARATI,
4083
4084 /**
4085 * Unicode script "Oriya".
4086 */
4087 ORIYA,
4088
4089 /**
4090 * Unicode script "Tamil".
4091 */
4092 TAMIL,
4093
4094 /**
4095 * Unicode script "Telugu".
4096 */
4097 TELUGU,
4098
4099 /**
4100 * Unicode script "Kannada".
4101 */
4102 KANNADA,
4103
4104 /**
4105 * Unicode script "Malayalam".
4106 */
4107 MALAYALAM,
4108
4109 /**
4110 * Unicode script "Sinhala".
4111 */
4112 SINHALA,
4113
4114 /**
4115 * Unicode script "Thai".
4116 */
4117 THAI,
4118
4119 /**
4120 * Unicode script "Lao".
4121 */
4122 LAO,
4123
4124 /**
4125 * Unicode script "Tibetan".
4126 */
4127 TIBETAN,
4128
4129 /**
4130 * Unicode script "Myanmar".
4131 */
4132 MYANMAR,
4133
4134 /**
4135 * Unicode script "Georgian".
4136 */
4137 GEORGIAN,
4138
4139 /**
4140 * Unicode script "Hangul".
4141 */
4142 HANGUL,
4143
4144 /**
4145 * Unicode script "Ethiopic".
4146 */
4147 ETHIOPIC,
4148
4149 /**
4150 * Unicode script "Cherokee".
4151 */
4152 CHEROKEE,
4153
4154 /**
4155 * Unicode script "Canadian_Aboriginal".
4156 */
4157 CANADIAN_ABORIGINAL,
4158
4159 /**
4160 * Unicode script "Ogham".
4161 */
4162 OGHAM,
4163
4164 /**
4165 * Unicode script "Runic".
4166 */
4167 RUNIC,
4168
4169 /**
4170 * Unicode script "Khmer".
4171 */
4172 KHMER,
4173
4174 /**
4175 * Unicode script "Mongolian".
4176 */
4177 MONGOLIAN,
4178
4179 /**
4180 * Unicode script "Hiragana".
4181 */
4182 HIRAGANA,
4183
4184 /**
4185 * Unicode script "Katakana".
4186 */
4187 KATAKANA,
4188
4189 /**
4190 * Unicode script "Bopomofo".
4191 */
4192 BOPOMOFO,
4193
4194 /**
4195 * Unicode script "Han".
4196 */
4197 HAN,
4198
4199 /**
4200 * Unicode script "Yi".
4201 */
4202 YI,
4203
4204 /**
4205 * Unicode script "Old_Italic".
4206 */
4207 OLD_ITALIC,
4208
4209 /**
4210 * Unicode script "Gothic".
4211 */
4212 GOTHIC,
4213
4214 /**
4215 * Unicode script "Deseret".
4216 */
4217 DESERET,
4218
4219 /**
4220 * Unicode script "Inherited".
4221 */
4222 INHERITED,
4223
4224 /**
4225 * Unicode script "Tagalog".
4226 */
4227 TAGALOG,
4228
4229 /**
4230 * Unicode script "Hanunoo".
4231 */
4232 HANUNOO,
4233
4234 /**
4235 * Unicode script "Buhid".
4236 */
4237 BUHID,
4238
4239 /**
4240 * Unicode script "Tagbanwa".
4241 */
4242 TAGBANWA,
4243
4244 /**
4245 * Unicode script "Limbu".
4246 */
4247 LIMBU,
4248
4249 /**
4250 * Unicode script "Tai_Le".
4251 */
4252 TAI_LE,
4253
4254 /**
4255 * Unicode script "Linear_B".
4256 */
4257 LINEAR_B,
4258
4259 /**
4260 * Unicode script "Ugaritic".
4261 */
4262 UGARITIC,
4263
4264 /**
4265 * Unicode script "Shavian".
4266 */
4267 SHAVIAN,
4268
4269 /**
4270 * Unicode script "Osmanya".
4271 */
4272 OSMANYA,
4273
4274 /**
4275 * Unicode script "Cypriot".
4276 */
4277 CYPRIOT,
4278
4279 /**
4280 * Unicode script "Braille".
4281 */
4282 BRAILLE,
4283
4284 /**
4285 * Unicode script "Buginese".
4286 */
4287 BUGINESE,
4288
4289 /**
4290 * Unicode script "Coptic".
4291 */
4292 COPTIC,
4293
4294 /**
4295 * Unicode script "New_Tai_Lue".
4296 */
4297 NEW_TAI_LUE,
4298
4299 /**
4300 * Unicode script "Glagolitic".
4301 */
4302 GLAGOLITIC,
4303
4304 /**
4305 * Unicode script "Tifinagh".
4306 */
4307 TIFINAGH,
4308
4309 /**
4310 * Unicode script "Syloti_Nagri".
4311 */
4312 SYLOTI_NAGRI,
4313
4314 /**
4315 * Unicode script "Old_Persian".
4316 */
4317 OLD_PERSIAN,
4318
4319 /**
4320 * Unicode script "Kharoshthi".
4321 */
4322 KHAROSHTHI,
4323
4324 /**
4325 * Unicode script "Balinese".
4326 */
4327 BALINESE,
4328
4329 /**
4330 * Unicode script "Cuneiform".
4331 */
4332 CUNEIFORM,
4333
4334 /**
4335 * Unicode script "Phoenician".
4336 */
4337 PHOENICIAN,
4338
4339 /**
4340 * Unicode script "Phags_Pa".
4341 */
4342 PHAGS_PA,
4343
4344 /**
4345 * Unicode script "Nko".
4346 */
4347 NKO,
4348
4349 /**
4350 * Unicode script "Sundanese".
4351 */
4352 SUNDANESE,
4353
4354 /**
4355 * Unicode script "Batak".
4356 */
4357 BATAK,
4358
4359 /**
4360 * Unicode script "Lepcha".
4361 */
4362 LEPCHA,
4363
4364 /**
4365 * Unicode script "Ol_Chiki".
4366 */
4367 OL_CHIKI,
4368
4369 /**
4370 * Unicode script "Vai".
4371 */
4372 VAI,
4373
4374 /**
4375 * Unicode script "Saurashtra".
4376 */
4377 SAURASHTRA,
4378
4379 /**
4380 * Unicode script "Kayah_Li".
4381 */
4382 KAYAH_LI,
4383
4384 /**
4385 * Unicode script "Rejang".
4386 */
4387 REJANG,
4388
4389 /**
4390 * Unicode script "Lycian".
4391 */
4392 LYCIAN,
4393
4394 /**
4395 * Unicode script "Carian".
4396 */
4397 CARIAN,
4398
4399 /**
4400 * Unicode script "Lydian".
4401 */
4402 LYDIAN,
4403
4404 /**
4405 * Unicode script "Cham".
4406 */
4407 CHAM,
4408
4409 /**
4410 * Unicode script "Tai_Tham".
4411 */
4412 TAI_THAM,
4413
4414 /**
4415 * Unicode script "Tai_Viet".
4416 */
4417 TAI_VIET,
4418
4419 /**
4420 * Unicode script "Avestan".
4421 */
4422 AVESTAN,
4423
4424 /**
4425 * Unicode script "Egyptian_Hieroglyphs".
4426 */
4427 EGYPTIAN_HIEROGLYPHS,
4428
4429 /**
4430 * Unicode script "Samaritan".
4431 */
4432 SAMARITAN,
4433
4434 /**
4435 * Unicode script "Mandaic".
4436 */
4437 MANDAIC,
4438
4439 /**
4440 * Unicode script "Lisu".
4441 */
4442 LISU,
4443
4444 /**
4445 * Unicode script "Bamum".
4446 */
4447 BAMUM,
4448
4449 /**
4450 * Unicode script "Javanese".
4451 */
4452 JAVANESE,
4453
4454 /**
4455 * Unicode script "Meetei_Mayek".
4456 */
4457 MEETEI_MAYEK,
4458
4459 /**
4460 * Unicode script "Imperial_Aramaic".
4461 */
4462 IMPERIAL_ARAMAIC,
4463
4464 /**
4465 * Unicode script "Old_South_Arabian".
4466 */
4467 OLD_SOUTH_ARABIAN,
4468
4469 /**
4470 * Unicode script "Inscriptional_Parthian".
4471 */
4472 INSCRIPTIONAL_PARTHIAN,
4473
4474 /**
4475 * Unicode script "Inscriptional_Pahlavi".
4476 */
4477 INSCRIPTIONAL_PAHLAVI,
4478
4479 /**
4480 * Unicode script "Old_Turkic".
4481 */
4482 OLD_TURKIC,
4483
4484 /**
4485 * Unicode script "Brahmi".
4486 */
4487 BRAHMI,
4488
4489 /**
4490 * Unicode script "Kaithi".
4491 */
4492 KAITHI,
4493
4494 /**
4495 * Unicode script "Meroitic Hieroglyphs".
4496 * @since 1.8
4497 */
4498 MEROITIC_HIEROGLYPHS,
4499
4500 /**
4501 * Unicode script "Meroitic Cursive".
4502 * @since 1.8
4503 */
4504 MEROITIC_CURSIVE,
4505
4506 /**
4507 * Unicode script "Sora Sompeng".
4508 * @since 1.8
4509 */
4510 SORA_SOMPENG,
4511
4512 /**
4513 * Unicode script "Chakma".
4514 * @since 1.8
4515 */
4516 CHAKMA,
4517
4518 /**
4519 * Unicode script "Sharada".
4520 * @since 1.8
4521 */
4522 SHARADA,
4523
4524 /**
4525 * Unicode script "Takri".
4526 * @since 1.8
4527 */
4528 TAKRI,
4529
4530 /**
4531 * Unicode script "Miao".
4532 * @since 1.8
4533 */
4534 MIAO,
4535
4536 /**
4537 * Unicode script "Caucasian Albanian".
4538 * @since 9
4539 */
4540 CAUCASIAN_ALBANIAN,
4541
4542 /**
4543 * Unicode script "Bassa Vah".
4544 * @since 9
4545 */
4546 BASSA_VAH,
4547
4548 /**
4549 * Unicode script "Duployan".
4550 * @since 9
4551 */
4552 DUPLOYAN,
4553
4554 /**
4555 * Unicode script "Elbasan".
4556 * @since 9
4557 */
4558 ELBASAN,
4559
4560 /**
4561 * Unicode script "Grantha".
4562 * @since 9
4563 */
4564 GRANTHA,
4565
4566 /**
4567 * Unicode script "Pahawh Hmong".
4568 * @since 9
4569 */
4570 PAHAWH_HMONG,
4571
4572 /**
4573 * Unicode script "Khojki".
4574 * @since 9
4575 */
4576 KHOJKI,
4577
4578 /**
4579 * Unicode script "Linear A".
4580 * @since 9
4581 */
4582 LINEAR_A,
4583
4584 /**
4585 * Unicode script "Mahajani".
4586 * @since 9
4587 */
4588 MAHAJANI,
4589
4590 /**
4591 * Unicode script "Manichaean".
4592 * @since 9
4593 */
4594 MANICHAEAN,
4595
4596 /**
4597 * Unicode script "Mende Kikakui".
4598 * @since 9
4599 */
4600 MENDE_KIKAKUI,
4601
4602 /**
4603 * Unicode script "Modi".
4604 * @since 9
4605 */
4606 MODI,
4607
4608 /**
4609 * Unicode script "Mro".
4610 * @since 9
4611 */
4612 MRO,
4613
4614 /**
4615 * Unicode script "Old North Arabian".
4616 * @since 9
4617 */
4618 OLD_NORTH_ARABIAN,
4619
4620 /**
4621 * Unicode script "Nabataean".
4622 * @since 9
4623 */
4624 NABATAEAN,
4625
4626 /**
4627 * Unicode script "Palmyrene".
4628 * @since 9
4629 */
4630 PALMYRENE,
4631
4632 /**
4633 * Unicode script "Pau Cin Hau".
4634 * @since 9
4635 */
4636 PAU_CIN_HAU,
4637
4638 /**
4639 * Unicode script "Old Permic".
4640 * @since 9
4641 */
4642 OLD_PERMIC,
4643
4644 /**
4645 * Unicode script "Psalter Pahlavi".
4646 * @since 9
4647 */
4648 PSALTER_PAHLAVI,
4649
4650 /**
4651 * Unicode script "Siddham".
4652 * @since 9
4653 */
4654 SIDDHAM,
4655
4656 /**
4657 * Unicode script "Khudawadi".
4658 * @since 9
4659 */
4660 KHUDAWADI,
4661
4662 /**
4663 * Unicode script "Tirhuta".
4664 * @since 9
4665 */
4666 TIRHUTA,
4667
4668 /**
4669 * Unicode script "Warang Citi".
4670 * @since 9
4671 */
4672 WARANG_CITI,
4673
4674 /**
4675 * Unicode script "Ahom".
4676 * @since 9
4677 */
4678 AHOM,
4679
4680 /**
4681 * Unicode script "Anatolian Hieroglyphs".
4682 * @since 9
4683 */
4684 ANATOLIAN_HIEROGLYPHS,
4685
4686 /**
4687 * Unicode script "Hatran".
4688 * @since 9
4689 */
4690 HATRAN,
4691
4692 /**
4693 * Unicode script "Multani".
4694 * @since 9
4695 */
4696 MULTANI,
4697
4698 /**
4699 * Unicode script "Old Hungarian".
4700 * @since 9
4701 */
4702 OLD_HUNGARIAN,
4703
4704 /**
4705 * Unicode script "SignWriting".
4706 * @since 9
4707 */
4708 SIGNWRITING,
4709
4710 /**
4711 * Unicode script "Adlam".
4712 * @since 11
4713 */
4714 ADLAM,
4715
4716 /**
4717 * Unicode script "Bhaiksuki".
4718 * @since 11
4719 */
4720 BHAIKSUKI,
4721
4722 /**
4723 * Unicode script "Marchen".
4724 * @since 11
4725 */
4726 MARCHEN,
4727
4728 /**
4729 * Unicode script "Newa".
4730 * @since 11
4731 */
4732 NEWA,
4733
4734 /**
4735 * Unicode script "Osage".
4736 * @since 11
4737 */
4738 OSAGE,
4739
4740 /**
4741 * Unicode script "Tangut".
4742 * @since 11
4743 */
4744 TANGUT,
4745
4746 /**
4747 * Unicode script "Masaram Gondi".
4748 * @since 11
4749 */
4750 MASARAM_GONDI,
4751
4752 /**
4753 * Unicode script "Nushu".
4754 * @since 11
4755 */
4756 NUSHU,
4757
4758 /**
4759 * Unicode script "Soyombo".
4760 * @since 11
4761 */
4762 SOYOMBO,
4763
4764 /**
4765 * Unicode script "Zanabazar Square".
4766 * @since 11
4767 */
4768 ZANABAZAR_SQUARE,
4769
4770 /**
4771 * Unicode script "Hanifi Rohingya".
4772 * @since 12
4773 */
4774 HANIFI_ROHINGYA,
4775
4776 /**
4777 * Unicode script "Old Sogdian".
4778 * @since 12
4779 */
4780 OLD_SOGDIAN,
4781
4782 /**
4783 * Unicode script "Sogdian".
4784 * @since 12
4785 */
4786 SOGDIAN,
4787
4788 /**
4789 * Unicode script "Dogra".
4790 * @since 12
4791 */
4792 DOGRA,
4793
4794 /**
4795 * Unicode script "Gunjala Gondi".
4796 * @since 12
4797 */
4798 GUNJALA_GONDI,
4799
4800 /**
4801 * Unicode script "Makasar".
4802 * @since 12
4803 */
4804 MAKASAR,
4805
4806 /**
4807 * Unicode script "Medefaidrin".
4808 * @since 12
4809 */
4810 MEDEFAIDRIN,
4811
4812 /**
4813 * Unicode script "Unknown".
4814 */
4815 UNKNOWN;
4816
4817 private static final int[] scriptStarts = {
4818 0x0000, // 0000..0040; COMMON
4819 0x0041, // 0041..005A; LATIN
4820 0x005B, // 005B..0060; COMMON
4821 0x0061, // 0061..007A; LATIN
4822 0x007B, // 007B..00A9; COMMON
4823 0x00AA, // 00AA ; LATIN
4824 0x00AB, // 00AB..00B9; COMMON
4825 0x00BA, // 00BA ; LATIN
4826 0x00BB, // 00BB..00BF; COMMON
4827 0x00C0, // 00C0..00D6; LATIN
4828 0x00D7, // 00D7 ; COMMON
4829 0x00D8, // 00D8..00F6; LATIN
4830 0x00F7, // 00F7 ; COMMON
4831 0x00F8, // 00F8..02B8; LATIN
4832 0x02B9, // 02B9..02DF; COMMON
4833 0x02E0, // 02E0..02E4; LATIN
4834 0x02E5, // 02E5..02E9; COMMON
4835 0x02EA, // 02EA..02EB; BOPOMOFO
4836 0x02EC, // 02EC..02FF; COMMON
4837 0x0300, // 0300..036F; INHERITED
4838 0x0370, // 0370..0373; GREEK
4839 0x0374, // 0374 ; COMMON
4840 0x0375, // 0375..0377; GREEK
4841 0x0378, // 0378..0379; UNKNOWN
4842 0x037A, // 037A..037D; GREEK
4843 0x037E, // 037E ; COMMON
4844 0x037F, // 037F ; GREEK
4845 0x0380, // 0380..0383; UNKNOWN
4846 0x0384, // 0384 ; GREEK
4847 0x0385, // 0385 ; COMMON
4848 0x0386, // 0386 ; GREEK
4849 0x0387, // 0387 ; COMMON
4850 0x0388, // 0388..038A; GREEK
4851 0x038B, // 038B ; UNKNOWN
4852 0x038C, // 038C ; GREEK
4853 0x038D, // 038D ; UNKNOWN
4854 0x038E, // 038E..03A1; GREEK
4855 0x03A2, // 03A2 ; UNKNOWN
4856 0x03A3, // 03A3..03E1; GREEK
4857 0x03E2, // 03E2..03EF; COPTIC
4858 0x03F0, // 03F0..03FF; GREEK
4859 0x0400, // 0400..0484; CYRILLIC
4860 0x0485, // 0485..0486; INHERITED
4861 0x0487, // 0487..052F; CYRILLIC
4862 0x0530, // 0530 ; UNKNOWN
4863 0x0531, // 0531..0556; ARMENIAN
4864 0x0557, // 0557..0558; UNKNOWN
4865 0x0559, // 0559..0588; ARMENIAN
4866 0x0589, // 0589 ; COMMON
4867 0x058A, // 058A ; ARMENIAN
4868 0x058B, // 058B..058C; UNKNOWN
4869 0x058D, // 058D..058F; ARMENIAN
4870 0x0590, // 0590 ; UNKNOWN
4871 0x0591, // 0591..05C7; HEBREW
4872 0x05C8, // 05C8..05CF; UNKNOWN
4873 0x05D0, // 05D0..05EA; HEBREW
4874 0x05EB, // 05EB..05EE; UNKNOWN
4875 0x05EF, // 05EF..05F4; HEBREW
4876 0x05F5, // 05F5..05FF; UNKNOWN
4877 0x0600, // 0600..0604; ARABIC
4878 0x0605, // 0605 ; COMMON
4879 0x0606, // 0606..060B; ARABIC
4880 0x060C, // 060C ; COMMON
4881 0x060D, // 060D..061A; ARABIC
4882 0x061B, // 061B ; COMMON
4883 0x061C, // 061C ; ARABIC
4884 0x061D, // 061D ; UNKNOWN
4885 0x061E, // 061E ; ARABIC
4886 0x061F, // 061F ; COMMON
4887 0x0620, // 0620..063F; ARABIC
4888 0x0640, // 0640 ; COMMON
4889 0x0641, // 0641..064A; ARABIC
4890 0x064B, // 064B..0655; INHERITED
4891 0x0656, // 0656..066F; ARABIC
4892 0x0670, // 0670 ; INHERITED
4893 0x0671, // 0671..06DC; ARABIC
4894 0x06DD, // 06DD ; COMMON
4895 0x06DE, // 06DE..06FF; ARABIC
4896 0x0700, // 0700..070D; SYRIAC
4897 0x070E, // 070E ; UNKNOWN
4898 0x070F, // 070F..074A; SYRIAC
4899 0x074B, // 074B..074C; UNKNOWN
4900 0x074D, // 074D..074F; SYRIAC
4901 0x0750, // 0750..077F; ARABIC
4902 0x0780, // 0780..07B1; THAANA
4903 0x07B2, // 07B2..07BF; UNKNOWN
4904 0x07C0, // 07C0..07FA; NKO
4905 0x07FB, // 07FB..07FC; UNKNOWN
4906 0X07FD, // 07FD..07FF; NKO
4907 0x0800, // 0800..082D; SAMARITAN
4908 0x082E, // 082E..082F; UNKNOWN
4909 0x0830, // 0830..083E; SAMARITAN
4910 0x083F, // 083F ; UNKNOWN
4911 0x0840, // 0840..085B; MANDAIC
4912 0x085C, // 085C..085D; UNKNOWN
4913 0x085E, // 085E ; MANDAIC
4914 0x085F, // 085F ; UNKNOWN
4915 0x0860, // 0860..086A; SYRIAC
4916 0x086B, // 086B..089F; UNKNOWN
4917 0x08A0, // 08A0..08B4; ARABIC
4918 0x08B5, // 08B5 ; UNKNOWN
4919 0x08B6, // 08B6..08BD; ARABIC
4920 0x08BE, // 08BE..08D2; UNKNOWN
4921 0x08D3, // 08D3..08E1; ARABIC
4922 0x08E2, // 08E2 ; COMMON
4923 0x08E3, // 08E3..08FF; ARABIC
4924 0x0900, // 0900..0950; DEVANAGARI
4925 0x0951, // 0951..0952; INHERITED
4926 0x0953, // 0953..0963; DEVANAGARI
4927 0x0964, // 0964..0965; COMMON
4928 0x0966, // 0966..097F; DEVANAGARI
4929 0x0980, // 0980..0983; BENGALI
4930 0x0984, // 0984 ; UNKNOWN
4931 0x0985, // 0985..098C; BENGALI
4932 0x098D, // 098D..098E; UNKNOWN
4933 0x098F, // 098F..0990; BENGALI
4934 0x0991, // 0991..0992; UNKNOWN
4935 0x0993, // 0993..09A8; BENGALI
4936 0x09A9, // 09A9 ; UNKNOWN
4937 0x09AA, // 09AA..09B0; BENGALI
4938 0x09B1, // 09B1 ; UNKNOWN
4939 0x09B2, // 09B2 ; BENGALI
4940 0x09B3, // 09B3..09B5; UNKNOWN
4941 0x09B6, // 09B6..09B9; BENGALI
4942 0x09BA, // 09BA..09BB; UNKNOWN
4943 0x09BC, // 09BC..09C4; BENGALI
4944 0x09C5, // 09C5..09C6; UNKNOWN
4945 0x09C7, // 09C7..09C8; BENGALI
4946 0x09C9, // 09C9..09CA; UNKNOWN
4947 0x09CB, // 09CB..09CE; BENGALI
4948 0x09CF, // 09CF..09D6; UNKNOWN
4949 0x09D7, // 09D7 ; BENGALI
4950 0x09D8, // 09D8..09DB; UNKNOWN
4951 0x09DC, // 09DC..09DD; BENGALI
4952 0x09DE, // 09DE ; UNKNOWN
4953 0x09DF, // 09DF..09E3; BENGALI
4954 0x09E4, // 09E4..09E5; UNKNOWN
4955 0x09E6, // 09E6..09FE; BENGALI
4956 0x09FF, // 09FF..0A00; UNKNOWN
4957 0x0A01, // 0A01..0A03; GURMUKHI
4958 0x0A04, // 0A04 ; UNKNOWN
4959 0x0A05, // 0A05..0A0A; GURMUKHI
4960 0x0A0B, // 0A0B..0A0E; UNKNOWN
4961 0x0A0F, // 0A0F..0A10; GURMUKHI
4962 0x0A11, // 0A11..0A12; UNKNOWN
4963 0x0A13, // 0A13..0A28; GURMUKHI
4964 0x0A29, // 0A29 ; UNKNOWN
4965 0x0A2A, // 0A2A..0A30; GURMUKHI
4966 0x0A31, // 0A31 ; UNKNOWN
4967 0x0A32, // 0A32..0A33; GURMUKHI
4968 0x0A34, // 0A34 ; UNKNOWN
4969 0x0A35, // 0A35..0A36; GURMUKHI
4970 0x0A37, // 0A37 ; UNKNOWN
4971 0x0A38, // 0A38..0A39; GURMUKHI
4972 0x0A3A, // 0A3A..0A3B; UNKNOWN
4973 0x0A3C, // 0A3C ; GURMUKHI
4974 0x0A3D, // 0A3D ; UNKNOWN
4975 0x0A3E, // 0A3E..0A42; GURMUKHI
4976 0x0A43, // 0A43..0A46; UNKNOWN
4977 0x0A47, // 0A47..0A48; GURMUKHI
4978 0x0A49, // 0A49..0A4A; UNKNOWN
4979 0x0A4B, // 0A4B..0A4D; GURMUKHI
4980 0x0A4E, // 0A4E..0A50; UNKNOWN
4981 0x0A51, // 0A51 ; GURMUKHI
4982 0x0A52, // 0A52..0A58; UNKNOWN
4983 0x0A59, // 0A59..0A5C; GURMUKHI
4984 0x0A5D, // 0A5D ; UNKNOWN
4985 0x0A5E, // 0A5E ; GURMUKHI
4986 0x0A5F, // 0A5F..0A65; UNKNOWN
4987 0x0A66, // 0A66..0A76; GURMUKHI
4988 0x0A77, // 0A77..0A80; UNKNOWN
4989 0x0A81, // 0A81..0A83; GUJARATI
4990 0x0A84, // 0A84 ; UNKNOWN
4991 0x0A85, // 0A85..0A8D; GUJARATI
4992 0x0A8E, // 0A8E ; UNKNOWN
4993 0x0A8F, // 0A8F..0A91; GUJARATI
4994 0x0A92, // 0A92 ; UNKNOWN
4995 0x0A93, // 0A93..0AA8; GUJARATI
4996 0x0AA9, // 0AA9 ; UNKNOWN
4997 0x0AAA, // 0AAA..0AB0; GUJARATI
4998 0x0AB1, // 0AB1 ; UNKNOWN
4999 0x0AB2, // 0AB2..0AB3; GUJARATI
5000 0x0AB4, // 0AB4 ; UNKNOWN
5001 0x0AB5, // 0AB5..0AB9; GUJARATI
5002 0x0ABA, // 0ABA..0ABB; UNKNOWN
5003 0x0ABC, // 0ABC..0AC5; GUJARATI
5004 0x0AC6, // 0AC6 ; UNKNOWN
5005 0x0AC7, // 0AC7..0AC9; GUJARATI
5006 0x0ACA, // 0ACA ; UNKNOWN
5007 0x0ACB, // 0ACB..0ACD; GUJARATI
5008 0x0ACE, // 0ACE..0ACF; UNKNOWN
5009 0x0AD0, // 0AD0 ; GUJARATI
5010 0x0AD1, // 0AD1..0ADF; UNKNOWN
5011 0x0AE0, // 0AE0..0AE3; GUJARATI
5012 0x0AE4, // 0AE4..0AE5; UNKNOWN
5013 0x0AE6, // 0AE6..0AF1; GUJARATI
5014 0x0AF2, // 0AF2..0AF8; UNKNOWN
5015 0x0AF9, // 0AF9..0AFF; GUJARATI
5016 0x0B00, // 0B00 ; UNKNOWN
5017 0x0B01, // 0B01..0B03; ORIYA
5018 0x0B04, // 0B04 ; UNKNOWN
5019 0x0B05, // 0B05..0B0C; ORIYA
5020 0x0B0D, // 0B0D..0B0E; UNKNOWN
5021 0x0B0F, // 0B0F..0B10; ORIYA
5022 0x0B11, // 0B11..0B12; UNKNOWN
5023 0x0B13, // 0B13..0B28; ORIYA
5024 0x0B29, // 0B29 ; UNKNOWN
5025 0x0B2A, // 0B2A..0B30; ORIYA
5026 0x0B31, // 0B31 ; UNKNOWN
5027 0x0B32, // 0B32..0B33; ORIYA
5028 0x0B34, // 0B34 ; UNKNOWN
5029 0x0B35, // 0B35..0B39; ORIYA
5030 0x0B3A, // 0B3A..0B3B; UNKNOWN
5031 0x0B3C, // 0B3C..0B44; ORIYA
5032 0x0B45, // 0B45..0B46; UNKNOWN
5033 0x0B47, // 0B47..0B48; ORIYA
5034 0x0B49, // 0B49..0B4A; UNKNOWN
5035 0x0B4B, // 0B4B..0B4D; ORIYA
5036 0x0B4E, // 0B4E..0B55; UNKNOWN
5037 0x0B56, // 0B56..0B57; ORIYA
5038 0x0B58, // 0B58..0B5B; UNKNOWN
5039 0x0B5C, // 0B5C..0B5D; ORIYA
5040 0x0B5E, // 0B5E ; UNKNOWN
5041 0x0B5F, // 0B5F..0B63; ORIYA
5042 0x0B64, // 0B64..0B65; UNKNOWN
5043 0x0B66, // 0B66..0B77; ORIYA
5044 0x0B78, // 0B78..0B81; UNKNOWN
5045 0x0B82, // 0B82..0B83; TAMIL
5046 0x0B84, // 0B84 ; UNKNOWN
5047 0x0B85, // 0B85..0B8A; TAMIL
5048 0x0B8B, // 0B8B..0B8D; UNKNOWN
5049 0x0B8E, // 0B8E..0B90; TAMIL
5050 0x0B91, // 0B91 ; UNKNOWN
5051 0x0B92, // 0B92..0B95; TAMIL
5052 0x0B96, // 0B96..0B98; UNKNOWN
5053 0x0B99, // 0B99..0B9A; TAMIL
5054 0x0B9B, // 0B9B ; UNKNOWN
5055 0x0B9C, // 0B9C ; TAMIL
5056 0x0B9D, // 0B9D ; UNKNOWN
5057 0x0B9E, // 0B9E..0B9F; TAMIL
5058 0x0BA0, // 0BA0..0BA2; UNKNOWN
5059 0x0BA3, // 0BA3..0BA4; TAMIL
5060 0x0BA5, // 0BA5..0BA7; UNKNOWN
5061 0x0BA8, // 0BA8..0BAA; TAMIL
5062 0x0BAB, // 0BAB..0BAD; UNKNOWN
5063 0x0BAE, // 0BAE..0BB9; TAMIL
5064 0x0BBA, // 0BBA..0BBD; UNKNOWN
5065 0x0BBE, // 0BBE..0BC2; TAMIL
5066 0x0BC3, // 0BC3..0BC5; UNKNOWN
5067 0x0BC6, // 0BC6..0BC8; TAMIL
5068 0x0BC9, // 0BC9 ; UNKNOWN
5069 0x0BCA, // 0BCA..0BCD; TAMIL
5070 0x0BCE, // 0BCE..0BCF; UNKNOWN
5071 0x0BD0, // 0BD0 ; TAMIL
5072 0x0BD1, // 0BD1..0BD6; UNKNOWN
5073 0x0BD7, // 0BD7 ; TAMIL
5074 0x0BD8, // 0BD8..0BE5; UNKNOWN
5075 0x0BE6, // 0BE6..0BFA; TAMIL
5076 0x0BFB, // 0BFB..0BFF; UNKNOWN
5077 0x0C00, // 0C00..0C0C; TELUGU
5078 0x0C0D, // 0C0D ; UNKNOWN
5079 0x0C0E, // 0C0E..0C10; TELUGU
5080 0x0C11, // 0C11 ; UNKNOWN
5081 0x0C12, // 0C12..0C28; TELUGU
5082 0x0C29, // 0C29 ; UNKNOWN
5083 0x0C2A, // 0C2A..0C39; TELUGU
5084 0x0C3A, // 0C3A..0C3C; UNKNOWN
5085 0x0C3D, // 0C3D..0C44; TELUGU
5086 0x0C45, // 0C45 ; UNKNOWN
5087 0x0C46, // 0C46..0C48; TELUGU
5088 0x0C49, // 0C49 ; UNKNOWN
5089 0x0C4A, // 0C4A..0C4D; TELUGU
5090 0x0C4E, // 0C4E..0C54; UNKNOWN
5091 0x0C55, // 0C55..0C56; TELUGU
5092 0x0C57, // 0C57 ; UNKNOWN
5093 0x0C58, // 0C58..0C5A; TELUGU
5094 0x0C5B, // 0C5B..0C5F; UNKNOWN
5095 0x0C60, // 0C60..0C63; TELUGU
5096 0x0C64, // 0C64..0C65; UNKNOWN
5097 0x0C66, // 0C66..0C6F; TELUGU
5098 0x0C70, // 0C70..0C77; UNKNOWN
5099 0x0C78, // 0C78..0C7F; TELUGU
5100 0x0C80, // 0C80..0C8C; KANNADA
5101 0x0C8D, // 0C8D ; UNKNOWN
5102 0x0C8E, // 0C8E..0C90; KANNADA
5103 0x0C91, // 0C91 ; UNKNOWN
5104 0x0C92, // 0C92..0CA8; KANNADA
5105 0x0CA9, // 0CA9 ; UNKNOWN
5106 0x0CAA, // 0CAA..0CB3; KANNADA
5107 0x0CB4, // 0CB4 ; UNKNOWN
5108 0x0CB5, // 0CB5..0CB9; KANNADA
5109 0x0CBA, // 0CBA..0CBB; UNKNOWN
5110 0x0CBC, // 0CBC..0CC4; KANNADA
5111 0x0CC5, // 0CC5 ; UNKNOWN
5112 0x0CC6, // 0CC6..0CC8; KANNADA
5113 0x0CC9, // 0CC9 ; UNKNOWN
5114 0x0CCA, // 0CCA..0CCD; KANNADA
5115 0x0CCE, // 0CCE..0CD4; UNKNOWN
5116 0x0CD5, // 0CD5..0CD6; KANNADA
5117 0x0CD7, // 0CD7..0CDD; UNKNOWN
5118 0x0CDE, // 0CDE ; KANNADA
5119 0x0CDF, // 0CDF ; UNKNOWN
5120 0x0CE0, // 0CE0..0CE3; KANNADA
5121 0x0CE4, // 0CE4..0CE5; UNKNOWN
5122 0x0CE6, // 0CE6..0CEF; KANNADA
5123 0x0CF0, // 0CF0 ; UNKNOWN
5124 0x0CF1, // 0CF1..0CF2; KANNADA
5125 0x0CF3, // 0CF3..0CFF; UNKNOWN
5126 0x0D00, // 0D00..0D03; MALAYALAM
5127 0x0D04, // 0D04 ; UNKNOWN
5128 0x0D05, // 0D05..0D0C; MALAYALAM
5129 0x0D0D, // 0D0D ; UNKNOWN
5130 0x0D0E, // 0D0E..0D10; MALAYALAM
5131 0x0D11, // 0D11 ; UNKNOWN
5132 0x0D12, // 0D12..0D44; MALAYALAM
5133 0x0D45, // 0D45 ; UNKNOWN
5134 0x0D46, // 0D46..0D48; MALAYALAM
5135 0x0D49, // 0D49 ; UNKNOWN
5136 0x0D4A, // 0D4A..0D4F; MALAYALAM
5137 0x0D50, // 0D50..0D53; UNKNOWN
5138 0x0D54, // 0D54..0D63; MALAYALAM
5139 0x0D64, // 0D64..0D65; UNKNOWN
5140 0x0D66, // 0D66..0D7F; MALAYALAM
5141 0x0D80, // 0D80..0D81; UNKNOWN
5142 0x0D82, // 0D82..0D83; SINHALA
5143 0x0D84, // 0D84 ; UNKNOWN
5144 0x0D85, // 0D85..0D96; SINHALA
5145 0x0D97, // 0D97..0D99; UNKNOWN
5146 0x0D9A, // 0D9A..0DB1; SINHALA
5147 0x0DB2, // 0DB2 ; UNKNOWN
5148 0x0DB3, // 0DB3..0DBB; SINHALA
5149 0x0DBC, // 0DBC ; UNKNOWN
5150 0x0DBD, // 0DBD ; SINHALA
5151 0x0DBE, // 0DBE..0DBF; UNKNOWN
5152 0x0DC0, // 0DC0..0DC6; SINHALA
5153 0x0DC7, // 0DC7..0DC9; UNKNOWN
5154 0x0DCA, // 0DCA ; SINHALA
5155 0x0DCB, // 0DCB..0DCE; UNKNOWN
5156 0x0DCF, // 0DCF..0DD4; SINHALA
5157 0x0DD5, // 0DD5 ; UNKNOWN
5158 0x0DD6, // 0DD6 ; SINHALA
5159 0x0DD7, // 0DD7 ; UNKNOWN
5160 0x0DD8, // 0DD8..0DDF; SINHALA
5161 0x0DE0, // 0DE0..0DE5; UNKNOWN
5162 0x0DE6, // 0DE6..0DEF; SINHALA
5163 0x0DF0, // 0DF0..0DF1; UNKNOWN
5164 0x0DF2, // 0DF2..0DF4; SINHALA
5165 0x0DF5, // 0DF5..0E00; UNKNOWN
5166 0x0E01, // 0E01..0E3A; THAI
5167 0x0E3B, // 0E3B..0E3E; UNKNOWN
5168 0x0E3F, // 0E3F ; COMMON
5169 0x0E40, // 0E40..0E5B; THAI
5170 0x0E5C, // 0E5C..0E80; UNKNOWN
5171 0x0E81, // 0E81..0E82; LAO
5172 0x0E83, // 0E83 ; UNKNOWN
5173 0x0E84, // 0E84 ; LAO
5174 0x0E85, // 0E85..0E86; UNKNOWN
5175 0x0E87, // 0E87..0E88; LAO
5176 0x0E89, // 0E89 ; UNKNOWN
5177 0x0E8A, // 0E8A ; LAO
5178 0x0E8B, // 0E8B..0E8C; UNKNOWN
5179 0x0E8D, // 0E8D ; LAO
5180 0x0E8E, // 0E8E..0E93; UNKNOWN
5181 0x0E94, // 0E94..0E97; LAO
5182 0x0E98, // 0E98 ; UNKNOWN
5183 0x0E99, // 0E99..0E9F; LAO
5184 0x0EA0, // 0EA0 ; UNKNOWN
5185 0x0EA1, // 0EA1..0EA3; LAO
5186 0x0EA4, // 0EA4 ; UNKNOWN
5187 0x0EA5, // 0EA5 ; LAO
5188 0x0EA6, // 0EA6 ; UNKNOWN
5189 0x0EA7, // 0EA7 ; LAO
5190 0x0EA8, // 0EA8..0EA9; UNKNOWN
5191 0x0EAA, // 0EAA..0EAB; LAO
5192 0x0EAC, // 0EAC ; UNKNOWN
5193 0x0EAD, // 0EAD..0EB9; LAO
5194 0x0EBA, // 0EBA ; UNKNOWN
5195 0x0EBB, // 0EBB..0EBD; LAO
5196 0x0EBE, // 0EBE..0EBF; UNKNOWN
5197 0x0EC0, // 0EC0..0EC4; LAO
5198 0x0EC5, // 0EC5 ; UNKNOWN
5199 0x0EC6, // 0EC6 ; LAO
5200 0x0EC7, // 0EC7 ; UNKNOWN
5201 0x0EC8, // 0EC8..0ECD; LAO
5202 0x0ECE, // 0ECE..0ECF; UNKNOWN
5203 0x0ED0, // 0ED0..0ED9; LAO
5204 0x0EDA, // 0EDA..0EDB; UNKNOWN
5205 0x0EDC, // 0EDC..0EDF; LAO
5206 0x0EE0, // 0EE0..0EFF; UNKNOWN
5207 0x0F00, // 0F00..0F47; TIBETAN
5208 0x0F48, // 0F48 ; UNKNOWN
5209 0x0F49, // 0F49..0F6C; TIBETAN
5210 0x0F6D, // 0F6D..0F70; UNKNOWN
5211 0x0F71, // 0F71..0F97; TIBETAN
5212 0x0F98, // 0F98 ; UNKNOWN
5213 0x0F99, // 0F99..0FBC; TIBETAN
5214 0x0FBD, // 0FBD ; UNKNOWN
5215 0x0FBE, // 0FBE..0FCC; TIBETAN
5216 0x0FCD, // 0FCD ; UNKNOWN
5217 0x0FCE, // 0FCE..0FD4; TIBETAN
5218 0x0FD5, // 0FD5..0FD8; COMMON
5219 0x0FD9, // 0FD9..0FDA; TIBETAN
5220 0x0FDB, // 0FDB..FFF; UNKNOWN
5221 0x1000, // 1000..109F; MYANMAR
5222 0x10A0, // 10A0..10C5; GEORGIAN
5223 0x10C6, // 10C6 ; UNKNOWN
5224 0x10C7, // 10C7 ; GEORGIAN
5225 0x10C8, // 10C8..10CC; UNKNOWN
5226 0x10CD, // 10CD ; GEORGIAN
5227 0x10CE, // 10CE..10CF; UNKNOWN
5228 0x10D0, // 10D0..10FA; GEORGIAN
5229 0x10FB, // 10FB ; COMMON
5230 0x10FC, // 10FC..10FF; GEORGIAN
5231 0x1100, // 1100..11FF; HANGUL
5232 0x1200, // 1200..1248; ETHIOPIC
5233 0x1249, // 1249 ; UNKNOWN
5234 0x124A, // 124A..124D; ETHIOPIC
5235 0x124E, // 124E..124F; UNKNOWN
5236 0x1250, // 1250..1256; ETHIOPIC
5237 0x1257, // 1257 ; UNKNOWN
5238 0x1258, // 1258 ; ETHIOPIC
5239 0x1259, // 1259 ; UNKNOWN
5240 0x125A, // 125A..125D; ETHIOPIC
5241 0x125E, // 125E..125F; UNKNOWN
5242 0x1260, // 1260..1288; ETHIOPIC
5243 0x1289, // 1289 ; UNKNOWN
5244 0x128A, // 128A..128D; ETHIOPIC
5245 0x128E, // 128E..128F; UNKNOWN
5246 0x1290, // 1290..12B0; ETHIOPIC
5247 0x12B1, // 12B1 ; UNKNOWN
5248 0x12B2, // 12B2..12B5; ETHIOPIC
5249 0x12B6, // 12B6..12B7; UNKNOWN
5250 0x12B8, // 12B8..12BE; ETHIOPIC
5251 0x12BF, // 12BF ; UNKNOWN
5252 0x12C0, // 12C0 ; ETHIOPIC
5253 0x12C1, // 12C1 ; UNKNOWN
5254 0x12C2, // 12C2..12C5; ETHIOPIC
5255 0x12C6, // 12C6..12C7; UNKNOWN
5256 0x12C8, // 12C8..12D6; ETHIOPIC
5257 0x12D7, // 12D7 ; UNKNOWN
5258 0x12D8, // 12D8..1310; ETHIOPIC
5259 0x1311, // 1311 ; UNKNOWN
5260 0x1312, // 1312..1315; ETHIOPIC
5261 0x1316, // 1316..1317; UNKNOWN
5262 0x1318, // 1318..135A; ETHIOPIC
5263 0x135B, // 135B..135C; UNKNOWN
5264 0x135D, // 135D..137C; ETHIOPIC
5265 0x137D, // 137D..137F; UNKNOWN
5266 0x1380, // 1380..1399; ETHIOPIC
5267 0x139A, // 139A..139F; UNKNOWN
5268 0x13A0, // 13A0..13F5; CHEROKEE
5269 0x13F6, // 13F6..13F7; UNKNOWN
5270 0x13F8, // 13F8..13FD; CHEROKEE
5271 0x13FE, // 13FE..13FF; UNKNOWN
5272 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5273 0x1680, // 1680..169C; OGHAM
5274 0x169D, // 169D..169F; UNKNOWN
5275 0x16A0, // 16A0..16EA; RUNIC
5276 0x16EB, // 16EB..16ED; COMMON
5277 0x16EE, // 16EE..16F8; RUNIC
5278 0x16F9, // 16F9..16FF; UNKNOWN
5279 0x1700, // 1700..170C; TAGALOG
5280 0x170D, // 170D ; UNKNOWN
5281 0x170E, // 170E..1714; TAGALOG
5282 0x1715, // 1715..171F; UNKNOWN
5283 0x1720, // 1720..1734; HANUNOO
5284 0x1735, // 1735..1736; COMMON
5285 0x1737, // 1737..173F; UNKNOWN
5286 0x1740, // 1740..1753; BUHID
5287 0x1754, // 1754..175F; UNKNOWN
5288 0x1760, // 1760..176C; TAGBANWA
5289 0x176D, // 176D ; UNKNOWN
5290 0x176E, // 176E..1770; TAGBANWA
5291 0x1771, // 1771 ; UNKNOWN
5292 0x1772, // 1772..1773; TAGBANWA
5293 0x1774, // 1774..177F; UNKNOWN
5294 0x1780, // 1780..17DD; KHMER
5295 0x17DE, // 17DE..17DF; UNKNOWN
5296 0x17E0, // 17E0..17E9; KHMER
5297 0x17EA, // 17EA..17EF; UNKNOWN
5298 0x17F0, // 17F0..17F9; KHMER
5299 0x17FA, // 17FA..17FF; UNKNOWN
5300 0x1800, // 1800..1801; MONGOLIAN
5301 0x1802, // 1802..1803; COMMON
5302 0x1804, // 1804 ; MONGOLIAN
5303 0x1805, // 1805 ; COMMON
5304 0x1806, // 1806..180E; MONGOLIAN
5305 0x180F, // 180F ; UNKNOWN
5306 0x1810, // 1810..1819; MONGOLIAN
5307 0x181A, // 181A..181F; UNKNOWN
5308 0x1820, // 1820..1878; MONGOLIAN
5309 0x1879, // 1879..187F; UNKNOWN
5310 0x1880, // 1880..18AA; MONGOLIAN
5311 0x18AB, // 18AB..18AF; UNKNOWN
5312 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
5313 0x18F6, // 18F6..18FF; UNKNOWN
5314 0x1900, // 1900..191E; LIMBU
5315 0x191F, // 191F ; UNKNOWN
5316 0x1920, // 1920..192B; LIMBU
5317 0x192C, // 192C..192F; UNKNOWN
5318 0x1930, // 1930..193B; LIMBU
5319 0x193C, // 193C..193F; UNKNOWN
5320 0x1940, // 1940 ; LIMBU
5321 0x1941, // 1941..1943; UNKNOWN
5322 0x1944, // 1944..194F; LIMBU
5323 0x1950, // 1950..196D; TAI_LE
5324 0x196E, // 196E..196F; UNKNOWN
5325 0x1970, // 1970..1974; TAI_LE
5326 0x1975, // 1975..197F; UNKNOWN
5327 0x1980, // 1980..19AB; NEW_TAI_LUE
5328 0x19AC, // 19AC..19AF; UNKNOWN
5329 0x19B0, // 19B0..19C9; NEW_TAI_LUE
5330 0x19CA, // 19CA..19CF; UNKNOWN
5331 0x19D0, // 19D0..19DA; NEW_TAI_LUE
5332 0x19DB, // 19DB..19DD; UNKNOWN
5333 0x19DE, // 19DE..19DF; NEW_TAI_LUE
5334 0x19E0, // 19E0..19FF; KHMER
5335 0x1A00, // 1A00..1A1B; BUGINESE
5336 0x1A1C, // 1A1C..1A1D; UNKNOWN
5337 0x1A1E, // 1A1E..1A1F; BUGINESE
5338 0x1A20, // 1A20..1A5E; TAI_THAM
5339 0x1A5F, // 1A5F ; UNKNOWN
5340 0x1A60, // 1A60..1A7C; TAI_THAM
5341 0x1A7D, // 1A7D..1A7E; UNKNOWN
5342 0x1A7F, // 1A7F..1A89; TAI_THAM
5343 0x1A8A, // 1A8A..1A8F; UNKNOWN
5344 0x1A90, // 1A90..1A99; TAI_THAM
5345 0x1A9A, // 1A9A..1A9F; UNKNOWN
5346 0x1AA0, // 1AA0..1AAD; TAI_THAM
5347 0x1AAE, // 1AAE..1AAF; UNKNOWN
5348 0x1AB0, // 1AB0..1ABE; INHERITED
5349 0x1ABF, // 1ABF..1AFF; UNKNOWN
5350 0x1B00, // 1B00..1B4B; BALINESE
5351 0x1B4C, // 1B4C..1B4F; UNKNOWN
5352 0x1B50, // 1B50..1B7C; BALINESE
5353 0x1B7D, // 1B7D..1B7F; UNKNOWN
5354 0x1B80, // 1B80..1BBF; SUNDANESE
5355 0x1BC0, // 1BC0..1BF3; BATAK
5356 0x1BF4, // 1BF4..1BFB; UNKNOWN
5357 0x1BFC, // 1BFC..1BFF; BATAK
5358 0x1C00, // 1C00..1C37; LEPCHA
5359 0x1C38, // 1C38..1C3A; UNKNOWN
5360 0x1C3B, // 1C3B..1C49; LEPCHA
5361 0x1C4A, // 1C4A..1C4C; UNKNOWN
5362 0x1C4D, // 1C4D..1C4F; LEPCHA
5363 0x1C50, // 1C50..1C7F; OL_CHIKI
5364 0x1C80, // 1C80..1C88; CYRILLIC
5365 0x1C89, // 1C89 ; UNKNOWN
5366 0x1C90, // 1C90..1CBA; GEORGIAN
5367 0x1CBB, // 1CBB..1CBC; UNKNOWN
5368 0x1CBD, // 1CBD..1CBF; GEORGIAN
5369 0x1CC0, // 1CC0..1CC7; SUNDANESE
5370 0x1CC8, // 1CC8..1CCF; UNKNOWN
5371 0x1CD0, // 1CD0..1CD2; INHERITED
5372 0x1CD3, // 1CD3 ; COMMON
5373 0x1CD4, // 1CD4..1CE0; INHERITED
5374 0x1CE1, // 1CE1 ; COMMON
5375 0x1CE2, // 1CE2..1CE8; INHERITED
5376 0x1CE9, // 1CE9..1CEC; COMMON
5377 0x1CED, // 1CED ; INHERITED
5378 0x1CEE, // 1CEE..1CF3; COMMON
5379 0x1CF4, // 1CF4 ; INHERITED
5380 0x1CF5, // 1CF5..1CF7; COMMON
5381 0x1CF8, // 1CF8..1CF9; INHERITED
5382 0x1CFA, // 1CFA..1CFF; UNKNOWN
5383 0x1D00, // 1D00..1D25; LATIN
5384 0x1D26, // 1D26..1D2A; GREEK
5385 0x1D2B, // 1D2B ; CYRILLIC
5386 0x1D2C, // 1D2C..1D5C; LATIN
5387 0x1D5D, // 1D5D..1D61; GREEK
5388 0x1D62, // 1D62..1D65; LATIN
5389 0x1D66, // 1D66..1D6A; GREEK
5390 0x1D6B, // 1D6B..1D77; LATIN
5391 0x1D78, // 1D78 ; CYRILLIC
5392 0x1D79, // 1D79..1DBE; LATIN
5393 0x1DBF, // 1DBF ; GREEK
5394 0x1DC0, // 1DC0..1DF9; INHERITED
5395 0x1DFA, // 1DFA ; UNKNOWN
5396 0x1DFB, // 1DFB..1DFF; INHERITED
5397 0x1E00, // 1E00..1EFF; LATIN
5398 0x1F00, // 1F00..1F15; GREEK
5399 0x1F16, // 1F16..1F17; UNKNOWN
5400 0x1F18, // 1F18..1F1D; GREEK
5401 0x1F1E, // 1F1E..1F1F; UNKNOWN
5402 0x1F20, // 1F20..1F45; GREEK
5403 0x1F46, // 1F46..1F47; UNKNOWN
5404 0x1F48, // 1F48..1F4D; GREEK
5405 0x1F4E, // 1F4E..1F4F; UNKNOWN
5406 0x1F50, // 1F50..1F57; GREEK
5407 0x1F58, // 1F58 ; UNKNOWN
5408 0x1F59, // 1F59 ; GREEK
5409 0x1F5A, // 1F5A ; UNKNOWN
5410 0x1F5B, // 1F5B ; GREEK
5411 0x1F5C, // 1F5C ; UNKNOWN
5412 0x1F5D, // 1F5D ; GREEK
5413 0x1F5E, // 1F5E ; UNKNOWN
5414 0x1F5F, // 1F5F..1F7D; GREEK
5415 0x1F7E, // 1F7E..1F7F; UNKNOWN
5416 0x1F80, // 1F80..1FB4; GREEK
5417 0x1FB5, // 1FB5 ; UNKNOWN
5418 0x1FB6, // 1FB6..1FC4; GREEK
5419 0x1FC5, // 1FC5 ; UNKNOWN
5420 0x1FC6, // 1FC6..1FD3; GREEK
5421 0x1FD4, // 1FD4..1FD5; UNKNOWN
5422 0x1FD6, // 1FD6..1FDB; GREEK
5423 0x1FDC, // 1FDC ; UNKNOWN
5424 0x1FDD, // 1FDD..1FEF; GREEK
5425 0x1FF0, // 1FF0..1FF1; UNKNOWN
5426 0x1FF2, // 1FF2..1FF4; GREEK
5427 0x1FF5, // 1FF5 ; UNKNOWN
5428 0x1FF6, // 1FF6..1FFE; GREEK
5429 0x1FFF, // 1FFF ; UNKNOWN
5430 0x2000, // 2000..200B; COMMON
5431 0x200C, // 200C..200D; INHERITED
5432 0x200E, // 200E..2064; COMMON
5433 0x2065, // 2065 ; UNKNOWN
5434 0x2066, // 2066..2070; COMMON
5435 0x2071, // 2071 ; LATIN
5436 0x2072, // 2072..2073; UNKNOWN
5437 0x2074, // 2074..207E; COMMON
5438 0x207F, // 207F ; LATIN
5439 0x2080, // 2080..208E; COMMON
5440 0x208F, // 208F ; UNKNOWN
5441 0x2090, // 2090..209C; LATIN
5442 0x209D, // 209D..209F; UNKNOWN
5443 0x20A0, // 20A0..20BF; COMMON
5444 0x20C0, // 20C0..20CF; UNKNOWN
5445 0x20D0, // 20D0..20F0; INHERITED
5446 0x20F1, // 20F1..20FF; UNKNOWN
5447 0x2100, // 2100..2125; COMMON
5448 0x2126, // 2126 ; GREEK
5449 0x2127, // 2127..2129; COMMON
5450 0x212A, // 212A..212B; LATIN
5451 0x212C, // 212C..2131; COMMON
5452 0x2132, // 2132 ; LATIN
5453 0x2133, // 2133..214D; COMMON
5454 0x214E, // 214E ; LATIN
5455 0x214F, // 214F..215F; COMMON
5456 0x2160, // 2160..2188; LATIN
5457 0x2189, // 2189..218B; COMMON
5458 0x218C, // 218C..218F; UNKNOWN
5459 0x2190, // 2190..2426; COMMON
5460 0x2427, // 2427..243F; UNKNOWN
5461 0x2440, // 2440..244A; COMMON
5462 0x244B, // 244B..245F; UNKNOWN
5463 0x2460, // 2460..27FF; COMMON
5464 0x2800, // 2800..28FF; BRAILLE
5465 0x2900, // 2900..2B73; COMMON
5466 0x2B74, // 2B74..2B75; UNKNOWN
5467 0x2B76, // 2B76..2B95; COMMON
5468 0x2B96, // 2B96..2B97; UNKNOWN
5469 0x2B98, // 2B98..2BC8; COMMON
5470 0x2BC9, // 2BC9 ; UNKNOWN
5471 0x2BCA, // 2BCA..2BFE; COMMON
5472 0x2BFF, // 2BFF; UNKNOWN
5473 0x2C00, // 2C00..2C2E; GLAGOLITIC
5474 0x2C2F, // 2C2F ; UNKNOWN
5475 0x2C30, // 2C30..2C5E; GLAGOLITIC
5476 0x2C5F, // 2C5F ; UNKNOWN
5477 0x2C60, // 2C60..2C7F; LATIN
5478 0x2C80, // 2C80..2CF3; COPTIC
5479 0x2CF4, // 2CF4..2CF8; UNKNOWN
5480 0x2CF9, // 2CF9..2CFF; COPTIC
5481 0x2D00, // 2D00..2D25; GEORGIAN
5482 0x2D26, // 2D26 ; UNKNOWN
5483 0x2D27, // 2D27 ; GEORGIAN
5484 0x2D28, // 2D28..2D2C; UNKNOWN
5485 0x2D2D, // 2D2D ; GEORGIAN
5486 0x2D2E, // 2D2E..2D2F; UNKNOWN
5487 0x2D30, // 2D30..2D67; TIFINAGH
5488 0x2D68, // 2D68..2D6E; UNKNOWN
5489 0x2D6F, // 2D6F..2D70; TIFINAGH
5490 0x2D71, // 2D71..2D7E; UNKNOWN
5491 0x2D7F, // 2D7F ; TIFINAGH
5492 0x2D80, // 2D80..2D96; ETHIOPIC
5493 0x2D97, // 2D97..2D9F; UNKNOWN
5494 0x2DA0, // 2DA0..2DA6; ETHIOPIC
5495 0x2DA7, // 2DA7 ; UNKNOWN
5496 0x2DA8, // 2DA8..2DAE; ETHIOPIC
5497 0x2DAF, // 2DAF ; UNKNOWN
5498 0x2DB0, // 2DB0..2DB6; ETHIOPIC
5499 0x2DB7, // 2DB7 ; UNKNOWN
5500 0x2DB8, // 2DB8..2DBE; ETHIOPIC
5501 0x2DBF, // 2DBF ; UNKNOWN
5502 0x2DC0, // 2DC0..2DC6; ETHIOPIC
5503 0x2DC7, // 2DC7 ; UNKNOWN
5504 0x2DC8, // 2DC8..2DCE; ETHIOPIC
5505 0x2DCF, // 2DCF ; UNKNOWN
5506 0x2DD0, // 2DD0..2DD6; ETHIOPIC
5507 0x2DD7, // 2DD7 ; UNKNOWN
5508 0x2DD8, // 2DD8..2DDE; ETHIOPIC
5509 0x2DDF, // 2DDF ; UNKNOWN
5510 0x2DE0, // 2DE0..2DFF; CYRILLIC
5511 0x2E00, // 2E00..2E4E; COMMON
5512 0x2E4F, // 2E4F..2E7F; UNKNOWN
5513 0x2E80, // 2E80..2E99; HAN
5514 0x2E9A, // 2E9A ; UNKNOWN
5515 0x2E9B, // 2E9B..2EF3; HAN
5516 0x2EF4, // 2EF4..2EFF; UNKNOWN
5517 0x2F00, // 2F00..2FD5; HAN
5518 0x2FD6, // 2FD6..2FEF; UNKNOWN
5519 0x2FF0, // 2FF0..2FFB; COMMON
5520 0x2FFC, // 2FFC..2FFF; UNKNOWN
5521 0x3000, // 3000..3004; COMMON
5522 0x3005, // 3005 ; HAN
5523 0x3006, // 3006 ; COMMON
5524 0x3007, // 3007 ; HAN
5525 0x3008, // 3008..3020; COMMON
5526 0x3021, // 3021..3029; HAN
5527 0x302A, // 302A..302D; INHERITED
5528 0x302E, // 302E..302F; HANGUL
5529 0x3030, // 3030..3037; COMMON
5530 0x3038, // 3038..303B; HAN
5531 0x303C, // 303C..303F; COMMON
5532 0x3040, // 3040 ; UNKNOWN
5533 0x3041, // 3041..3096; HIRAGANA
5534 0x3097, // 3097..3098; UNKNOWN
5535 0x3099, // 3099..309A; INHERITED
5536 0x309B, // 309B..309C; COMMON
5537 0x309D, // 309D..309F; HIRAGANA
5538 0x30A0, // 30A0 ; COMMON
5539 0x30A1, // 30A1..30FA; KATAKANA
5540 0x30FB, // 30FB..30FC; COMMON
5541 0x30FD, // 30FD..30FF; KATAKANA
5542 0x3100, // 3100..3104; UNKNOWN
5543 0x3105, // 3105..312F; BOPOMOFO
5544 0x3130, // 3130; UNKNOWN
5545 0x3131, // 3131..318E; HANGUL
5546 0x318F, // 318F ; UNKNOWN
5547 0x3190, // 3190..319F; COMMON
5548 0x31A0, // 31A0..31BA; BOPOMOFO
5549 0x31BB, // 31BB..31BF; UNKNOWN
5550 0x31C0, // 31C0..31E3; COMMON
5551 0x31E4, // 31E4..31EF; UNKNOWN
5552 0x31F0, // 31F0..31FF; KATAKANA
5553 0x3200, // 3200..321E; HANGUL
5554 0x321F, // 321F ; UNKNOWN
5555 0x3220, // 3220..325F; COMMON
5556 0x3260, // 3260..327E; HANGUL
5557 0x327F, // 327F..32CF; COMMON
5558 0x32D0, // 32D0..32FE; KATAKANA
5559 0x32FF, // 32FF ; COMMON
5560 0x3300, // 3300..3357; KATAKANA
5561 0x3358, // 3358..33FF; COMMON
5562 0x3400, // 3400..4DB5; HAN
5563 0x4DB6, // 4DB6..4DBF; UNKNOWN
5564 0x4DC0, // 4DC0..4DFF; COMMON
5565 0x4E00, // 4E00..9FEF; HAN
5566 0x9FF0, // 9FF0..9FFF; UNKNOWN
5567 0xA000, // A000..A48C; YI
5568 0xA48D, // A48D..A48F; UNKNOWN
5569 0xA490, // A490..A4C6; YI
5570 0xA4C7, // A4C7..A4CF; UNKNOWN
5571 0xA4D0, // A4D0..A4FF; LISU
5572 0xA500, // A500..A62B; VAI
5573 0xA62C, // A62C..A63F; UNKNOWN
5574 0xA640, // A640..A69F; CYRILLIC
5575 0xA6A0, // A6A0..A6F7; BAMUM
5576 0xA6F8, // A6F8..A6FF; UNKNOWN
5577 0xA700, // A700..A721; COMMON
5578 0xA722, // A722..A787; LATIN
5579 0xA788, // A788..A78A; COMMON
5580 0xA78B, // A78B..A7B9; LATIN
5581 0xA7C0, // A7C0..A7F6; UNKNOWN
5582 0xA7F7, // A7F7..A7FF; LATIN
5583 0xA800, // A800..A82B; SYLOTI_NAGRI
5584 0xA82C, // A82C..A82F; UNKNOWN
5585 0xA830, // A830..A839; COMMON
5586 0xA83A, // A83A..A83F; UNKNOWN
5587 0xA840, // A840..A877; PHAGS_PA
5588 0xA878, // A878..A87F; UNKNOWN
5589 0xA880, // A880..A8C5; SAURASHTRA
5590 0xA8C6, // A8C6..A8CD; UNKNOWN
5591 0xA8CE, // A8CE..A8D9; SAURASHTRA
5592 0xA8DA, // A8DA..A8DF; UNKNOWN
5593 0xA8E0, // A8E0..A8FF; DEVANAGARI
5594 0xA900, // A900..A92D; KAYAH_LI
5595 0xA92E, // A92E ; COMMON
5596 0xA92F, // A92F ; KAYAH_LI
5597 0xA930, // A930..A953; REJANG
5598 0xA954, // A954..A95E; UNKNOWN
5599 0xA95F, // A95F ; REJANG
5600 0xA960, // A960..A97C; HANGUL
5601 0xA97D, // A97D..A97F; UNKNOWN
5602 0xA980, // A980..A9CD; JAVANESE
5603 0xA9CE, // A9CE ; UNKNOWN
5604 0xA9CF, // A9CF ; COMMON
5605 0xA9D0, // A9D0..A9D9; JAVANESE
5606 0xA9DA, // A9DA..A9DD; UNKNOWN
5607 0xA9DE, // A9DE..A9DF; JAVANESE
5608 0xA9E0, // A9E0..A9FE; MYANMAR
5609 0xA9FF, // A9FF ; UNKNOWN
5610 0xAA00, // AA00..AA36; CHAM
5611 0xAA37, // AA37..AA3F; UNKNOWN
5612 0xAA40, // AA40..AA4D; CHAM
5613 0xAA4E, // AA4E..AA4F; UNKNOWN
5614 0xAA50, // AA50..AA59; CHAM
5615 0xAA5A, // AA5A..AA5B; UNKNOWN
5616 0xAA5C, // AA5C..AA5F; CHAM
5617 0xAA60, // AA60..AA7F; MYANMAR
5618 0xAA80, // AA80..AAC2; TAI_VIET
5619 0xAAC3, // AAC3..AADA; UNKNOWN
5620 0xAADB, // AADB..AADF; TAI_VIET
5621 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
5622 0xAAF7, // AAF7..AB00; UNKNOWN
5623 0xAB01, // AB01..AB06; ETHIOPIC
5624 0xAB07, // AB07..AB08; UNKNOWN
5625 0xAB09, // AB09..AB0E; ETHIOPIC
5626 0xAB0F, // AB0F..AB10; UNKNOWN
5627 0xAB11, // AB11..AB16; ETHIOPIC
5628 0xAB17, // AB17..AB1F; UNKNOWN
5629 0xAB20, // AB20..AB26; ETHIOPIC
5630 0xAB27, // AB27 ; UNKNOWN
5631 0xAB28, // AB28..AB2E; ETHIOPIC
5632 0xAB2F, // AB2F ; UNKNOWN
5633 0xAB30, // AB30..AB5A; LATIN
5634 0xAB5B, // AB5B ; COMMON
5635 0xAB5C, // AB5C..AB64; LATIN
5636 0xAB65, // AB65 ; GREEK
5637 0xAB66, // AB66..AB6F; UNKNOWN
5638 0xAB70, // AB70..ABBF; CHEROKEE
5639 0xABC0, // ABC0..ABED; MEETEI_MAYEK
5640 0xABEE, // ABEE..ABEF; UNKNOWN
5641 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
5642 0xABFA, // ABFA..ABFF; UNKNOWN
5643 0xAC00, // AC00..D7A3; HANGUL
5644 0xD7A4, // D7A4..D7AF; UNKNOWN
5645 0xD7B0, // D7B0..D7C6; HANGUL
5646 0xD7C7, // D7C7..D7CA; UNKNOWN
5647 0xD7CB, // D7CB..D7FB; HANGUL
5648 0xD7FC, // D7FC..F8FF; UNKNOWN
5649 0xF900, // F900..FA6D; HAN
5650 0xFA6E, // FA6E..FA6F; UNKNOWN
5651 0xFA70, // FA70..FAD9; HAN
5652 0xFADA, // FADA..FAFF; UNKNOWN
5653 0xFB00, // FB00..FB06; LATIN
5654 0xFB07, // FB07..FB12; UNKNOWN
5655 0xFB13, // FB13..FB17; ARMENIAN
5656 0xFB18, // FB18..FB1C; UNKNOWN
5657 0xFB1D, // FB1D..FB36; HEBREW
5658 0xFB37, // FB37 ; UNKNOWN
5659 0xFB38, // FB38..FB3C; HEBREW
5660 0xFB3D, // FB3D ; UNKNOWN
5661 0xFB3E, // FB3E ; HEBREW
5662 0xFB3F, // FB3F ; UNKNOWN
5663 0xFB40, // FB40..FB41; HEBREW
5664 0xFB42, // FB42 ; UNKNOWN
5665 0xFB43, // FB43..FB44; HEBREW
5666 0xFB45, // FB45 ; UNKNOWN
5667 0xFB46, // FB46..FB4F; HEBREW
5668 0xFB50, // FB50..FBC1; ARABIC
5669 0xFBC2, // FBC2..FBD2; UNKNOWN
5670 0xFBD3, // FBD3..FD3D; ARABIC
5671 0xFD3E, // FD3E..FD3F; COMMON
5672 0xFD40, // FD40..FD4F; UNKNOWN
5673 0xFD50, // FD50..FD8F; ARABIC
5674 0xFD90, // FD90..FD91; UNKNOWN
5675 0xFD92, // FD92..FDC7; ARABIC
5676 0xFDC8, // FDC8..FDEF; UNKNOWN
5677 0xFDF0, // FDF0..FDFD; ARABIC
5678 0xFDFE, // FDFE..FDFF; UNKNOWN
5679 0xFE00, // FE00..FE0F; INHERITED
5680 0xFE10, // FE10..FE19; COMMON
5681 0xFE1A, // FE1A..FE1F; UNKNOWN
5682 0xFE20, // FE20..FE2D; INHERITED
5683 0xFE2E, // FE2E..FE2F; CYRILLIC
5684 0xFE30, // FE30..FE52; COMMON
5685 0xFE53, // FE53 ; UNKNOWN
5686 0xFE54, // FE54..FE66; COMMON
5687 0xFE67, // FE67 ; UNKNOWN
5688 0xFE68, // FE68..FE6B; COMMON
5689 0xFE6C, // FE6C..FE6F; UNKNOWN
5690 0xFE70, // FE70..FE74; ARABIC
5691 0xFE75, // FE75 ; UNKNOWN
5692 0xFE76, // FE76..FEFC; ARABIC
5693 0xFEFD, // FEFD..FEFE; UNKNOWN
5694 0xFEFF, // FEFF ; COMMON
5695 0xFF00, // FF00 ; UNKNOWN
5696 0xFF01, // FF01..FF20; COMMON
5697 0xFF21, // FF21..FF3A; LATIN
5698 0xFF3B, // FF3B..FF40; COMMON
5699 0xFF41, // FF41..FF5A; LATIN
5700 0xFF5B, // FF5B..FF65; COMMON
5701 0xFF66, // FF66..FF6F; KATAKANA
5702 0xFF70, // FF70 ; COMMON
5703 0xFF71, // FF71..FF9D; KATAKANA
5704 0xFF9E, // FF9E..FF9F; COMMON
5705 0xFFA0, // FFA0..FFBE; HANGUL
5706 0xFFBF, // FFBF..FFC1; UNKNOWN
5707 0xFFC2, // FFC2..FFC7; HANGUL
5708 0xFFC8, // FFC8..FFC9; UNKNOWN
5709 0xFFCA, // FFCA..FFCF; HANGUL
5710 0xFFD0, // FFD0..FFD1; UNKNOWN
5711 0xFFD2, // FFD2..FFD7; HANGUL
5712 0xFFD8, // FFD8..FFD9; UNKNOWN
5713 0xFFDA, // FFDA..FFDC; HANGUL
5714 0xFFDD, // FFDD..FFDF; UNKNOWN
5715 0xFFE0, // FFE0..FFE6; COMMON
5716 0xFFE7, // FFE7 ; UNKNOWN
5717 0xFFE8, // FFE8..FFEE; COMMON
5718 0xFFEF, // FFEF..FFF8; UNKNOWN
5719 0xFFF9, // FFF9..FFFD; COMMON
5720 0xFFFE, // FFFE..FFFF; UNKNOWN
5721 0x10000, // 10000..1000B; LINEAR_B
5722 0x1000C, // 1000C ; UNKNOWN
5723 0x1000D, // 1000D..10026; LINEAR_B
5724 0x10027, // 10027 ; UNKNOWN
5725 0x10028, // 10028..1003A; LINEAR_B
5726 0x1003B, // 1003B ; UNKNOWN
5727 0x1003C, // 1003C..1003D; LINEAR_B
5728 0x1003E, // 1003E ; UNKNOWN
5729 0x1003F, // 1003F..1004D; LINEAR_B
5730 0x1004E, // 1004E..1004F; UNKNOWN
5731 0x10050, // 10050..1005D; LINEAR_B
5732 0x1005E, // 1005E..1007F; UNKNOWN
5733 0x10080, // 10080..100FA; LINEAR_B
5734 0x100FB, // 100FB..100FF; UNKNOWN
5735 0x10100, // 10100..10102; COMMON
5736 0x10103, // 10103..10106; UNKNOWN
5737 0x10107, // 10107..10133; COMMON
5738 0x10134, // 10134..10136; UNKNOWN
5739 0x10137, // 10137..1013F; COMMON
5740 0x10140, // 10140..1018E; GREEK
5741 0x1018F, // 1018F ; UNKNOWN
5742 0x10190, // 10190..1019B; COMMON
5743 0x1019C, // 1019C..1019F; UNKNOWN
5744 0x101A0, // 101A0 ; GREEK
5745 0x101A1, // 101A1..101CF; UNKNOWN
5746 0x101D0, // 101D0..101FC; COMMON
5747 0x101FD, // 101FD ; INHERITED
5748 0x101FE, // 101FE..1027F; UNKNOWN
5749 0x10280, // 10280..1029C; LYCIAN
5750 0x1029D, // 1029D..1029F; UNKNOWN
5751 0x102A0, // 102A0..102D0; CARIAN
5752 0x102D1, // 102D1..102DF; UNKNOWN
5753 0x102E0, // 102E0 ; INHERITED
5754 0x102E1, // 102E1..102FB; COMMON
5755 0x102FC, // 102FC..102FF; UNKNOWN
5756 0x10300, // 10300..10323; OLD_ITALIC
5757 0x10324, // 10324..1032C; UNKNOWN
5758 0x1032D, // 1032D..1032F; OLD_ITALIC
5759 0x10330, // 10330..1034A; GOTHIC
5760 0x1034B, // 1034B..1034F; UNKNOWN
5761 0x10350, // 10350..1037A; OLD_PERMIC
5762 0x1037B, // 1037B..1037F; UNKNOWN
5763 0x10380, // 10380..1039D; UGARITIC
5764 0x1039E, // 1039E ; UNKNOWN
5765 0x1039F, // 1039F ; UGARITIC
5766 0x103A0, // 103A0..103C3; OLD_PERSIAN
5767 0x103C4, // 103C4..103C7; UNKNOWN
5768 0x103C8, // 103C8..103D5; OLD_PERSIAN
5769 0x103D6, // 103D6..103FF; UNKNOWN
5770 0x10400, // 10400..1044F; DESERET
5771 0x10450, // 10450..1047F; SHAVIAN
5772 0x10480, // 10480..1049D; OSMANYA
5773 0x1049E, // 1049E..1049F; UNKNOWN
5774 0x104A0, // 104A0..104A9; OSMANYA
5775 0x104AA, // 104AA..104AF; UNKNOWN
5776 0x104B0, // 104B0..104D3; OSAGE
5777 0x104D4, // 104D4..104D7; UNKNOWN
5778 0x104D8, // 104D8..104FB; OSAGE
5779 0x104FC, // 104FC..104FF; UNKNOWN
5780 0x10500, // 10500..10527; ELBASAN
5781 0x10528, // 10528..1052F; UNKNOWN
5782 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
5783 0x10564, // 10564..1056E; UNKNOWN
5784 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
5785 0x10570, // 10570..105FF; UNKNOWN
5786 0x10600, // 10600..10736; LINEAR_A
5787 0x10737, // 10737..1073F; UNKNOWN
5788 0x10740, // 10740..10755; LINEAR_A
5789 0x10756, // 10756..1075F; UNKNOWN
5790 0x10760, // 10760..10767; LINEAR_A
5791 0x10768, // 10768..107FF; UNKNOWN
5792 0x10800, // 10800..10805; CYPRIOT
5793 0x10806, // 10806..10807; UNKNOWN
5794 0x10808, // 10808 ; CYPRIOT
5795 0x10809, // 10809 ; UNKNOWN
5796 0x1080A, // 1080A..10835; CYPRIOT
5797 0x10836, // 10836 ; UNKNOWN
5798 0x10837, // 10837..10838; CYPRIOT
5799 0x10839, // 10839..1083B; UNKNOWN
5800 0x1083C, // 1083C ; CYPRIOT
5801 0x1083D, // 1083D..1083E; UNKNOWN
5802 0x1083F, // 1083F ; CYPRIOT
5803 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
5804 0x10856, // 10856 ; UNKNOWN
5805 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
5806 0x10860, // 10860..1087F; PALMYRENE
5807 0x10880, // 10880..1089E; NABATAEAN
5808 0x1089F, // 1089F..108A6; UNKNOWN
5809 0x108A7, // 108A7..108AF; NABATAEAN
5810 0x108B0, // 108B0..108DF; UNKNOWN
5811 0x108E0, // 108E0..108F2; HATRAN
5812 0x108F3, // 108F3 ; UNKNOWN
5813 0x108F4, // 108F4..108F5; HATRAN
5814 0x108F6, // 108F6..108FA; UNKNOWN
5815 0x108FB, // 108FB..108FF; HATRAN
5816 0x10900, // 10900..1091B; PHOENICIAN
5817 0x1091C, // 1091C..1091E; UNKNOWN
5818 0x1091F, // 1091F ; PHOENICIAN
5819 0x10920, // 10920..10939; LYDIAN
5820 0x1093A, // 1093A..1093E; UNKNOWN
5821 0x1093F, // 1093F ; LYDIAN
5822 0x10940, // 10940..1097F; UNKNOWN
5823 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
5824 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
5825 0x109B8, // 109B8..109BB; UNKNOWN
5826 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
5827 0x109D0, // 109D0..109D1; UNKNOWN
5828 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
5829 0x10A00, // 10A00..10A03; KHAROSHTHI
5830 0x10A04, // 10A04 ; UNKNOWN
5831 0x10A05, // 10A05..10A06; KHAROSHTHI
5832 0x10A07, // 10A07..10A0B; UNKNOWN
5833 0x10A0C, // 10A0C..10A13; KHAROSHTHI
5834 0x10A14, // 10A14 ; UNKNOWN
5835 0x10A15, // 10A15..10A17; KHAROSHTHI
5836 0x10A18, // 10A18 ; UNKNOWN
5837 0x10A19, // 10A19..10A35; KHAROSHTHI
5838 0x10A36, // 10A36..10A37; UNKNOWN
5839 0x10A38, // 10A38..10A3A; KHAROSHTHI
5840 0x10A3B, // 10A3B..10A3E; UNKNOWN
5841 0x10A3F, // 10A3F..10A48; KHAROSHTHI
5842 0x10A49, // 10A49..10A4F; UNKNOWN
5843 0x10A50, // 10A50..10A58; KHAROSHTHI
5844 0x10A59, // 10A59..10A5F; UNKNOWN
5845 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
5846 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
5847 0x10AA0, // 10AA0..10ABF; UNKNOWN
5848 0x10AC0, // 10AC0..10AE6; MANICHAEAN
5849 0x10AE7, // 10AE7..10AEA; UNKNOWN
5850 0x10AEB, // 10AEB..10AF6; MANICHAEAN
5851 0x10AF7, // 10AF7..10AFF; UNKNOWN
5852 0x10B00, // 10B00..10B35; AVESTAN
5853 0x10B36, // 10B36..10B38; UNKNOWN
5854 0x10B39, // 10B39..10B3F; AVESTAN
5855 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
5856 0x10B56, // 10B56..10B57; UNKNOWN
5857 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
5858 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
5859 0x10B73, // 10B73..10B77; UNKNOWN
5860 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
5861 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
5862 0x10B92, // 10B92..10B98; UNKNOWN
5863 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
5864 0x10B9D, // 10B9D..10BA8; UNKNOWN
5865 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
5866 0x10BB0, // 10BB0..10BFF; UNKNOWN
5867 0x10C00, // 10C00..10C48; OLD_TURKIC
5868 0x10C49, // 10C49..10C7F; UNKNOWN
5869 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
5870 0x10CB3, // 10CB3..10CBF; UNKNOWN
5871 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
5872 0x10CF3, // 10CF3..10CF9; UNKNOWN
5873 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
5874 0x10D00, // 10D00..10D27; HANIFI ROHINGYA
5875 0x10D28, // 10D28..10D29; UNKNOWN
5876 0x10D30, // 10D30..10D39; HANIFI ROHINGYA
5877 0x10D3A, // 10D3A..10E5F; UNKNOWN
5878 0x10E60, // 10E60..10E7E; ARABIC
5879 0x10E7F, // 10E7F..10EFF; UNKNOWN
5880 0x10F00, // 10F00..10F27; OLD SOGDIAN
5881 0x10F28, // 10F28..10F2F; UNKNOWN
5882 0x10F30, // 10F30..10F59; SOGDIAN
5883 0x10F5A, // 10F5A..10FFF; UNKNOWN
5884 0x11000, // 11000..1104D; BRAHMI
5885 0x1104E, // 1104E..11051; UNKNOWN
5886 0x11052, // 11052..1106F; BRAHMI
5887 0x11070, // 11070..1107E; UNKNOWN
5888 0x1107F, // 1107F ; BRAHMI
5889 0x11080, // 11080..110C1; KAITHI
5890 0x110C2, // 110C2..110CC; UNKNOWN
5891 0x110CD, // 110CD ; KAITHI
5892 0x110CE, // 110CE..110CF; UNKNOWN
5893 0x110D0, // 110D0..110E8; SORA_SOMPENG
5894 0x110E9, // 110E9..110EF; UNKNOWN
5895 0x110F0, // 110F0..110F9; SORA_SOMPENG
5896 0x110FA, // 110FA..110FF; UNKNOWN
5897 0x11100, // 11100..11134; CHAKMA
5898 0x11135, // 11135 ; UNKNOWN
5899 0x11136, // 11136..11146; CHAKMA
5900 0x11147, // 11147..1114F; UNKNOWN
5901 0x11150, // 11150..11176; MAHAJANI
5902 0x11177, // 11177..1117F; UNKNOWN
5903 0x11180, // 11180..111CD; SHARADA
5904 0x111CE, // 111CE..111CF; UNKNOWN
5905 0x111D0, // 111D0..111DF; SHARADA
5906 0x111E0, // 111E0 ; UNKNOWN
5907 0x111E1, // 111E1..111F4; SINHALA
5908 0x111F5, // 111F5..111FF; UNKNOWN
5909 0x11200, // 11200..11211; KHOJKI
5910 0x11212, // 11212 ; UNKNOWN
5911 0x11213, // 11213..1123E; KHOJKI
5912 0x1123F, // 1123F..1127F; UNKNOWN
5913 0x11280, // 11280..11286; MULTANI
5914 0x11287, // 11287 ; UNKNOWN
5915 0x11288, // 11288 ; MULTANI
5916 0x11289, // 11289 ; UNKNOWN
5917 0x1128A, // 1128A..1128D; MULTANI
5918 0x1128E, // 1128E ; UNKNOWN
5919 0x1128F, // 1128F..1129D; MULTANI
5920 0x1129E, // 1129E ; UNKNOWN
5921 0x1129F, // 1129F..112A9; MULTANI
5922 0x112AA, // 112AA..112AF; UNKNOWN
5923 0x112B0, // 112B0..112EA; KHUDAWADI
5924 0x112EB, // 112EB..112EF; UNKNOWN
5925 0x112F0, // 112F0..112F9; KHUDAWADI
5926 0x112FA, // 112FA..112FF; UNKNOWN
5927 0x11300, // 11300..11303; GRANTHA
5928 0x11304, // 11304 ; UNKNOWN
5929 0x11305, // 11305..1130C; GRANTHA
5930 0x1130D, // 1130D..1130E; UNKNOWN
5931 0x1130F, // 1130F..11310; GRANTHA
5932 0x11311, // 11311..11312; UNKNOWN
5933 0x11313, // 11313..11328; GRANTHA
5934 0x11329, // 11329 ; UNKNOWN
5935 0x1132A, // 1132A..11330; GRANTHA
5936 0x11331, // 11331 ; UNKNOWN
5937 0x11332, // 11332..11333; GRANTHA
5938 0x11334, // 11334 ; UNKNOWN
5939 0x11335, // 11335..11339; GRANTHA
5940 0x1133A, // 1133A ; UNKNOWN
5941 0x1133B, // 1133B ; INHERITED
5942 0x1133C, // 1133C..11344; GRANTHA
5943 0x11345, // 11345..11346; UNKNOWN
5944 0x11347, // 11347..11348; GRANTHA
5945 0x11349, // 11349..1134A; UNKNOWN
5946 0x1134B, // 1134B..1134D; GRANTHA
5947 0x1134E, // 1134E..1134F; UNKNOWN
5948 0x11350, // 11350 ; GRANTHA
5949 0x11351, // 11351..11356; UNKNOWN
5950 0x11357, // 11357 ; GRANTHA
5951 0x11358, // 11358..1135C; UNKNOWN
5952 0x1135D, // 1135D..11363; GRANTHA
5953 0x11364, // 11364..11365; UNKNOWN
5954 0x11366, // 11366..1136C; GRANTHA
5955 0x1136D, // 1136D..1136F; UNKNOWN
5956 0x11370, // 11370..11374; GRANTHA
5957 0x11375, // 11375..113FF; UNKNOWN
5958 0x11400, // 11400..11459; NEWA
5959 0x1145A, // 1145A ; UNKNOWN
5960 0x1145B, // 1145B ; NEWA
5961 0x1145C, // 1145C ; UNKNOWN
5962 0x1145D, // 1145D..1145E; NEWA
5963 0x1145F, // 1145F..1147F; UNKNOWN
5964 0x11480, // 11480..114C7; TIRHUTA
5965 0x114C8, // 114C8..114CF; UNKNOWN
5966 0x114D0, // 114D0..114D9; TIRHUTA
5967 0x114DA, // 114DA..1157F; UNKNOWN
5968 0x11580, // 11580..115B5; SIDDHAM
5969 0x115B6, // 115B6..115B7; UNKNOWN
5970 0x115B8, // 115B8..115DD; SIDDHAM
5971 0x115DE, // 115DE..115FF; UNKNOWN
5972 0x11600, // 11600..11644; MODI
5973 0x11645, // 11645..1164F; UNKNOWN
5974 0x11650, // 11650..11659; MODI
5975 0x1165A, // 1165A..1165F; UNKNOWN
5976 0x11660, // 11660..1166C; MONGOLIAN
5977 0X1166D, // 1166D..1167F; UNKNOWN
5978 0x11680, // 11680..116B7; TAKRI
5979 0x116B8, // 116B8..116BF; UNKNOWN
5980 0x116C0, // 116C0..116C9; TAKRI
5981 0x116CA, // 116CA..116FF; UNKNOWN
5982 0x11700, // 11700..1171A; AHOM
5983 0x1171B, // 1171B..1171C; UNKNOWN
5984 0x1171D, // 1171D..1172B; AHOM
5985 0x1172C, // 1172C..1172F; UNKNOWN
5986 0x11730, // 11730..1173F; AHOM
5987 0x11740, // 11740..117FF; UNKNOWN
5988 0x11800, // 11800..1183B; DOGRA
5989 0x1183C, // 1183C..1189F; UNKNOWN
5990 0x118A0, // 118A0..118F2; WARANG_CITI
5991 0x118F3, // 118F3..118FE; UNKNOWN
5992 0x118FF, // 118FF ; WARANG_CITI
5993 0x11900, // 11900..119FF; UNKNOWN
5994 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
5995 0X11A48, // 11A48..11A4F; UNKNOWN
5996 0x11A50, // 11A50..11A83; SOYOMBO
5997 0x11A84, // 11A84..11A85; UNKNOWN
5998 0x11A86, // 11A86..11AA2; SOYOMBO
5999 0x11AA3, // 11AA3..11ABF; UNKNOWN
6000 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6001 0x11AF9, // 11AF9..11BFF; UNKNOWN
6002 0x11C00, // 11C00..11C08; BHAIKSUKI
6003 0x11C09, // 11C09 ; UNKNOWN
6004 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6005 0x11C37, // 11C37 ; UNKNOWN
6006 0x11C38, // 11C38..11C45; BHAIKSUKI
6007 0x11C46, // 11C46..11C49; UNKNOWN
6008 0x11C50, // 11C50..11C6C; BHAIKSUKI
6009 0x11C6D, // 11C6D..11C6F; UNKNOWN
6010 0x11C70, // 11C70..11C8F; MARCHEN
6011 0x11C90, // 11C90..11C91; UNKNOWN
6012 0x11C92, // 11C92..11CA7; MARCHEN
6013 0x11CA8, // 11CA8 ; UNKNOWN
6014 0x11CA9, // 11CA9..11CB6; MARCHEN
6015 0x11CB7, // 11CB7..11CFF; UNKNOWN
6016 0x11D00, // 11D00..11D06; MASARAM_GONDI
6017 0x11D07, // 11D07 ; UNKNOWN
6018 0x11D08, // 11D08..11D09; MASARAM_GONDI
6019 0x11D0A, // 11D0A ; UNKNOWN
6020 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6021 0x11D37, // 11D37..11D39; UNKNOWN
6022 0x11D3A, // 11D3A ; MASARAM_GONDI
6023 0x11D3B, // 11D3B ; UNKNOWN
6024 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6025 0x11D3E, // 11D3E ; UNKNOWN
6026 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6027 0x11D48, // 11D48..11D49, UNKNOWN
6028 0x11D50, // 11D50..11D59; MASARAM_GONDI
6029 0x11D5A, // 11D5A..11D5F; UNKNOWN
6030 0x11D60, // 11D60..11D68; GUNJALA GONDI
6031 0x11D69, // ; UNKNOWN
6032 0x11D6A, // 11D6A..11D8E; GUNJALA GONDI
6033 0x11D8F, // ; UNKNOWN
6034 0x11D90, // 11D90..11D91; GUNJALA GONDI
6035 0x11D92, // ; UNKNOWN
6036 0x11D93, // 11D93..11D98; GUNJALA GONDI
6037 0x11D99, // 11D99 ; UNKNOWN
6038 0x11DA0, // 11DA0..11DA9; GUNJALA GONDI
6039 0x11DAA, // 11DAA..11DFF; UNKNOWN
6040 0x11EE0, // 11EE0..11EF8; MAKASAR
6041 0x11EF9, // 11EF9..11FFF; UNKNOWN
6042 0x12000, // 12000..12399; CUNEIFORM
6043 0x1239A, // 1239A..123FF; UNKNOWN
6044 0x12400, // 12400..1246E; CUNEIFORM
6045 0x1246F, // 1246F ; UNKNOWN
6046 0x12470, // 12470..12474; CUNEIFORM
6047 0x12475, // 12475..1247F; UNKNOWN
6048 0x12480, // 12480..12543; CUNEIFORM
6049 0x12544, // 12544..12FFF; UNKNOWN
6050 0x13000, // 13000..1342E; EGYPTIAN_HIEROGLYPHS
6051 0x1342F, // 1342F..143FF; UNKNOWN
6052 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6053 0x14647, // 14647..167FF; UNKNOWN
6054 0x16800, // 16800..16A38; BAMUM
6055 0x16A39, // 16A39..16A3F; UNKNOWN
6056 0x16A40, // 16A40..16A5E; MRO
6057 0x16A5F, // 16A5F ; UNKNOWN
6058 0x16A60, // 16A60..16A69; MRO
6059 0x16A6A, // 16A6A..16A6D; UNKNOWN
6060 0x16A6E, // 16A6E..16A6F; MRO
6061 0x16A70, // 16A70..16ACF; UNKNOWN
6062 0x16AD0, // 16AD0..16AED; BASSA_VAH
6063 0x16AEE, // 16AEE..16AEF; UNKNOWN
6064 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6065 0x16AF6, // 16AF6..16AFF; UNKNOWN
6066 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6067 0x16B46, // 16B46..16B4F; UNKNOWN
6068 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6069 0x16B5A, // 16B5A ; UNKNOWN
6070 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6071 0x16B62, // 16B62 ; UNKNOWN
6072 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6073 0x16B78, // 16B78..16B7C; UNKNOWN
6074 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6075 0x16B90, // 16B90..16E3F; UNKNOWN
6076 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6077 0x16E9B, // 16E9B..16EFF; UNKNOWN
6078 0x16F00, // 16F00..16F44; MIAO
6079 0x16F45, // 16F45..16F4F; UNKNOWN
6080 0x16F50, // 16F50..16F7E; MIAO
6081 0x16F7F, // 16F7F..16F8E; UNKNOWN
6082 0x16F8F, // 16F8F..16F9F; MIAO
6083 0x16FA0, // 16FA0..16FDF; UNKNOWN
6084 0x16FE0, // 16FE0 ; TANGUT
6085 0x16FE1, // 16FE1 ; NUSHU
6086 0x16FE2, // 16FE2..16FFF; UNKNOWN
6087 0x17000, // 17000..187F1; TANGUT
6088 0x187F2, // 187F2..187FF; UNKNOWN
6089 0x18800, // 18800..18AF2; TANGUT
6090 0x18AF3, // 18AF3..1AFFF; UNKNOWN
6091 0x1B000, // 1B000 ; KATAKANA
6092 0x1B001, // 1B001..1B11E; HIRAGANA
6093 0x1B11F, // 1B11F..1B16F; UNKNOWN
6094 0x1B170, // 1B170..1B2FB; NUSHU
6095 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6096 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6097 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6098 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6099 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6100 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6101 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6102 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6103 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6104 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6105 0x1BCA0, // 1BCA0..1BCA3; COMMON
6106 0x1BCA4, // 1BCA4..1CFFF; UNKNOWN
6107 0x1D000, // 1D000..1D0F5; COMMON
6108 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6109 0x1D100, // 1D100..1D126; COMMON
6110 0x1D127, // 1D127..1D128; UNKNOWN
6111 0x1D129, // 1D129..1D166; COMMON
6112 0x1D167, // 1D167..1D169; INHERITED
6113 0x1D16A, // 1D16A..1D17A; COMMON
6114 0x1D17B, // 1D17B..1D182; INHERITED
6115 0x1D183, // 1D183..1D184; COMMON
6116 0x1D185, // 1D185..1D18B; INHERITED
6117 0x1D18C, // 1D18C..1D1A9; COMMON
6118 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6119 0x1D1AE, // 1D1AE..1D1E8; COMMON
6120 0x1D1E9, // 1D1E9..1D1FF; UNKNOWN
6121 0x1D200, // 1D200..1D245; GREEK
6122 0x1D246, // 1D246..1D2DF; UNKNOWN
6123 0x1D2E0, // 1D2E0..1D2F3; COMMON
6124 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6125 0x1D300, // 1D300..1D356; COMMON
6126 0x1D357, // 1D357..1D35F; UNKNOWN
6127 0x1D360, // 1D360..1D378; COMMON
6128 0x1D379, // 1D379..1D3FF; UNKNOWN
6129 0x1D400, // 1D400..1D454; COMMON
6130 0x1D455, // 1D455 ; UNKNOWN
6131 0x1D456, // 1D456..1D49C; COMMON
6132 0x1D49D, // 1D49D ; UNKNOWN
6133 0x1D49E, // 1D49E..1D49F; COMMON
6134 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
6135 0x1D4A2, // 1D4A2 ; COMMON
6136 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
6137 0x1D4A5, // 1D4A5..1D4A6; COMMON
6138 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
6139 0x1D4A9, // 1D4A9..1D4AC; COMMON
6140 0x1D4AD, // 1D4AD ; UNKNOWN
6141 0x1D4AE, // 1D4AE..1D4B9; COMMON
6142 0x1D4BA, // 1D4BA ; UNKNOWN
6143 0x1D4BB, // 1D4BB ; COMMON
6144 0x1D4BC, // 1D4BC ; UNKNOWN
6145 0x1D4BD, // 1D4BD..1D4C3; COMMON
6146 0x1D4C4, // 1D4C4 ; UNKNOWN
6147 0x1D4C5, // 1D4C5..1D505; COMMON
6148 0x1D506, // 1D506 ; UNKNOWN
6149 0x1D507, // 1D507..1D50A; COMMON
6150 0x1D50B, // 1D50B..1D50C; UNKNOWN
6151 0x1D50D, // 1D50D..1D514; COMMON
6152 0x1D515, // 1D515 ; UNKNOWN
6153 0x1D516, // 1D516..1D51C; COMMON
6154 0x1D51D, // 1D51D ; UNKNOWN
6155 0x1D51E, // 1D51E..1D539; COMMON
6156 0x1D53A, // 1D53A ; UNKNOWN
6157 0x1D53B, // 1D53B..1D53E; COMMON
6158 0x1D53F, // 1D53F ; UNKNOWN
6159 0x1D540, // 1D540..1D544; COMMON
6160 0x1D545, // 1D545 ; UNKNOWN
6161 0x1D546, // 1D546 ; COMMON
6162 0x1D547, // 1D547..1D549; UNKNOWN
6163 0x1D54A, // 1D54A..1D550; COMMON
6164 0x1D551, // 1D551 ; UNKNOWN
6165 0x1D552, // 1D552..1D6A5; COMMON
6166 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
6167 0x1D6A8, // 1D6A8..1D7CB; COMMON
6168 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
6169 0x1D7CE, // 1D7CE..1D7FF; COMMON
6170 0x1D800, // 1D800..1DA8B; SIGNWRITING
6171 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
6172 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
6173 0x1DAA0, // 1DAA0 ; UNKNOWN
6174 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
6175 0x1DAB0, // 1DAB0..1DFFF; UNKNOWN
6176 0x1E000, // 1E000..1E006; GLAGOLITIC
6177 0x1E007, // 1E007 ; UNKNOWN
6178 0x1E008, // 1E008..1E018; GLAGOLITIC
6179 0x1E019, // 1E019..1E01A; UNKNOWN
6180 0x1E01B, // 1E01B..1E021; GLAGOLITIC
6181 0x1E022, // 1E022 ; UNKNOWN
6182 0x1E023, // 1E023..1E024; GLAGOLITIC
6183 0x1E025, // 1E025 ; UNKNOWN
6184 0x1E026, // 1E026..1E02A; GLAGOLITIC
6185 0x1E02B, // 1E02B..1E7FF; UNKNOWN
6186 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
6187 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
6188 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
6189 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
6190 0x1E900, // 1E900..1E94A; ADLAM
6191 0x1E94B, // 1E94B..1E94F; UNKNOWN
6192 0x1E950, // 1E950..1E959; ADLAM
6193 0x1E95A, // 1E95A..1E95D; UNKNOWN
6194 0x1E95E, // 1E95E..1E95F; ADLAM
6195 0x1E960, // 1E960..1EC70; UNKNOWN
6196 0x1EC71, // 1EC71..1ECB4; COMMON
6197 0x1ECB5, // 1ECB5..1EDFF; UNKNOWN
6198 0x1EE00, // 1EE00..1EE03; ARABIC
6199 0x1EE04, // 1EE04 ; UNKNOWN
6200 0x1EE05, // 1EE05..1EE1F; ARABIC
6201 0x1EE20, // 1EE20 ; UNKNOWN
6202 0x1EE21, // 1EE21..1EE22; ARABIC
6203 0x1EE23, // 1EE23 ; UNKNOWN
6204 0x1EE24, // 1EE24 ; ARABIC
6205 0x1EE25, // 1EE25..1EE26; UNKNOWN
6206 0x1EE27, // 1EE27 ; ARABIC
6207 0x1EE28, // 1EE28 ; UNKNOWN
6208 0x1EE29, // 1EE29..1EE32; ARABIC
6209 0x1EE33, // 1EE33 ; UNKNOWN
6210 0x1EE34, // 1EE34..1EE37; ARABIC
6211 0x1EE38, // 1EE38 ; UNKNOWN
6212 0x1EE39, // 1EE39 ; ARABIC
6213 0x1EE3A, // 1EE3A ; UNKNOWN
6214 0x1EE3B, // 1EE3B ; ARABIC
6215 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
6216 0x1EE42, // 1EE42 ; ARABIC
6217 0x1EE43, // 1EE43..1EE46; UNKNOWN
6218 0x1EE47, // 1EE47 ; ARABIC
6219 0x1EE48, // 1EE48 ; UNKNOWN
6220 0x1EE49, // 1EE49 ; ARABIC
6221 0x1EE4A, // 1EE4A ; UNKNOWN
6222 0x1EE4B, // 1EE4B ; ARABIC
6223 0x1EE4C, // 1EE4C ; UNKNOWN
6224 0x1EE4D, // 1EE4D..1EE4F; ARABIC
6225 0x1EE50, // 1EE50 ; UNKNOWN
6226 0x1EE51, // 1EE51..1EE52; ARABIC
6227 0x1EE53, // 1EE53 ; UNKNOWN
6228 0x1EE54, // 1EE54 ; ARABIC
6229 0x1EE55, // 1EE55..1EE56; UNKNOWN
6230 0x1EE57, // 1EE57 ; ARABIC
6231 0x1EE58, // 1EE58 ; UNKNOWN
6232 0x1EE59, // 1EE59 ; ARABIC
6233 0x1EE5A, // 1EE5A ; UNKNOWN
6234 0x1EE5B, // 1EE5B ; ARABIC
6235 0x1EE5C, // 1EE5C ; UNKNOWN
6236 0x1EE5D, // 1EE5D ; ARABIC
6237 0x1EE5E, // 1EE5E ; UNKNOWN
6238 0x1EE5F, // 1EE5F ; ARABIC
6239 0x1EE60, // 1EE60 ; UNKNOWN
6240 0x1EE61, // 1EE61..1EE62; ARABIC
6241 0x1EE63, // 1EE63 ; UNKNOWN
6242 0x1EE64, // 1EE64 ; ARABIC
6243 0x1EE65, // 1EE65..1EE66; UNKNOWN
6244 0x1EE67, // 1EE67..1EE6A; ARABIC
6245 0x1EE6B, // 1EE6B ; UNKNOWN
6246 0x1EE6C, // 1EE6C..1EE72; ARABIC
6247 0x1EE73, // 1EE73 ; UNKNOWN
6248 0x1EE74, // 1EE74..1EE77; ARABIC
6249 0x1EE78, // 1EE78 ; UNKNOWN
6250 0x1EE79, // 1EE79..1EE7C; ARABIC
6251 0x1EE7D, // 1EE7D ; UNKNOWN
6252 0x1EE7E, // 1EE7E ; ARABIC
6253 0x1EE7F, // 1EE7F ; UNKNOWN
6254 0x1EE80, // 1EE80..1EE89; ARABIC
6255 0x1EE8A, // 1EE8A ; UNKNOWN
6256 0x1EE8B, // 1EE8B..1EE9B; ARABIC
6257 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
6258 0x1EEA1, // 1EEA1..1EEA3; ARABIC
6259 0x1EEA4, // 1EEA4 ; UNKNOWN
6260 0x1EEA5, // 1EEA5..1EEA9; ARABIC
6261 0x1EEAA, // 1EEAA ; UNKNOWN
6262 0x1EEAB, // 1EEAB..1EEBB; ARABIC
6263 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
6264 0x1EEF0, // 1EEF0..1EEF1; ARABIC
6265 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
6266 0x1F000, // 1F000..1F02B; COMMON
6267 0x1F02C, // 1F02C..1F02F; UNKNOWN
6268 0x1F030, // 1F030..1F093; COMMON
6269 0x1F094, // 1F094..1F09F; UNKNOWN
6270 0x1F0A0, // 1F0A0..1F0AE; COMMON
6271 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
6272 0x1F0B1, // 1F0B1..1F0BF; COMMON
6273 0x1F0C0, // 1F0C0 ; UNKNOWN
6274 0x1F0C1, // 1F0C1..1F0CF; COMMON
6275 0x1F0D0, // 1F0D0 ; UNKNOWN
6276 0x1F0D1, // 1F0D1..1F0F5; COMMON
6277 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
6278 0x1F100, // 1F100..1F10C; COMMON
6279 0x1F10D, // 1F10D..1F10F; UNKNOWN
6280 0x1F110, // 1F110..1F16B; COMMON
6281 0x1F16C, // 1F16C..1F16F; UNKNOWN
6282 0x1F170, // 1F170..1F1AC; COMMON
6283 0x1F1AD, // 1F1AD..1F1E5; UNKNOWN
6284 0x1F1E6, // 1F1E6..1F1FF; COMMON
6285 0x1F200, // 1F200 ; HIRAGANA
6286 0x1F201, // 1F201..1F202; COMMON
6287 0x1F203, // 1F203..1F20F; UNKNOWN
6288 0x1F210, // 1F210..1F23B; COMMON
6289 0x1F23C, // 1F23C..1F23F; UNKNOWN
6290 0x1F240, // 1F240..1F248; COMMON
6291 0x1F249, // 1F249..1F24F; UNKNOWN
6292 0x1F250, // 1F250..1F251; COMMON
6293 0x1F252, // 1F252..1F25F; UNKNOWN
6294 0x1F260, // 1F260..1F265; COMMON
6295 0x1F266, // 1F266..1F2FF; UNKNOWN
6296 0x1F300, // 1F300..1F6D4; COMMON
6297 0x1F6D5, // 1F6D5..1F6DF; UNKNOWN
6298 0x1F6E0, // 1F6E0..1F6EC; COMMON
6299 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
6300 0x1F6F0, // 1F6F0..1F6F9; COMMON
6301 0x1F6FA, // 1F6FA..1F6FF; UNKNOWN
6302 0x1F700, // 1F700..1F773; COMMON
6303 0x1F774, // 1F774..1F77F; UNKNOWN
6304 0x1F780, // 1F780..1F7D8; COMMON
6305 0x1F7D9, // 1F7D9..1F7FF; UNKNOWN
6306 0x1F800, // 1F800..1F80B; COMMON
6307 0x1F80C, // 1F80C..1F80F; UNKNOWN
6308 0x1F810, // 1F810..1F847; COMMON
6309 0x1F848, // 1F848..1F84F; UNKNOWN
6310 0x1F850, // 1F850..1F859; COMMON
6311 0x1F85A, // 1F85A..1F85F; UNKNOWN
6312 0x1F860, // 1F860..1F887; COMMON
6313 0x1F888, // 1F888..1F88F; UNKNOWN
6314 0x1F890, // 1F890..1F8AD; COMMON
6315 0x1F8AE, // 1F8AE..1F8FF; UNKNOWN
6316 0x1F900, // 1F900..1F90B; COMMON
6317 0x1F90C, // 1F90C..1F90F; UNKNOWN
6318 0x1F910, // 1F910..1F93E; COMMON
6319 0x1F93F, // 1F93F ; UNKNOWN
6320 0x1F940, // 1F940..1F970; COMMON
6321 0x1F971, // 1F971..1F972; UNKNOWN
6322 0x1F973, // 1F973..1F976; COMMON
6323 0x1F977, // 1F977..1F979; UNKNOWN
6324 0x1F97A, // 1F97A ; COMMON
6325 0x1F97B, // 1F97B ; UNKNOWN
6326 0x1F97C, // 1F97C..1F9A2; COMMON
6327 0x1F9A3, // 1F9A3..1F9AF; UNKNOWN
6328 0x1F9B0, // 1F9B0..1F9B9; COMMON
6329 0x1F9BA, // 1F9BA..1F9BF; UNKNOWN
6330 0x1F9C0, // 1F9C0..1F9C2; COMMON
6331 0x1F9C3, // 1F9C3..1F9CF; UNKNOWN
6332 0x1F9D0, // 1F9D0..1F9FF; COMMON
6333 0x1FA00, // 1FA00..1FA5F; UNKNOWN
6334 0x1FA60, // 1FA60..1FA6D; COMMON
6335 0x1FA6E, // 1FA6E..1FFFF; UNKNOWN
6336 0x20000, // 20000..2A6D6; HAN
6337 0x2A6D7, // 2A6D7..2A6FF; UNKNOWN
6338 0x2A700, // 2A700..2B734; HAN
6339 0x2B735, // 2B735..2B73F; UNKNOWN
6340 0x2B740, // 2B740..2B81D; HAN
6341 0x2B81E, // 2B81E..2B81F; UNKNOWN
6342 0x2B820, // 2B820..2CEA1; HAN
6343 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
6344 0x2CEB0, // 2CEB0..2EBE0; HAN
6345 0x2EBE1, // 2EBE1..2F7FF; UNKNOWN
6346 0x2F800, // 2F800..2FA1D; HAN
6347 0x2FA1E, // 2FA1E..E0000; UNKNOWN
6348 0xE0001, // E0001 ; COMMON
6349 0xE0002, // E0002..E001F; UNKNOWN
6350 0xE0020, // E0020..E007F; COMMON
6351 0xE0080, // E0080..E00FF; UNKNOWN
6352 0xE0100, // E0100..E01EF; INHERITED
6353 0xE01F0 // E01F0..10FFFF; UNKNOWN
6354 };
6355
6356 private static final UnicodeScript[] scripts = {
6357 COMMON, // 0000..0040
6358 LATIN, // 0041..005A
6359 COMMON, // 005B..0060
6360 LATIN, // 0061..007A
6361 COMMON, // 007B..00A9
6362 LATIN, // 00AA
6363 COMMON, // 00AB..00B9
6364 LATIN, // 00BA
6365 COMMON, // 00BB..00BF
6366 LATIN, // 00C0..00D6
6367 COMMON, // 00D7
6368 LATIN, // 00D8..00F6
6369 COMMON, // 00F7
6370 LATIN, // 00F8..02B8
6371 COMMON, // 02B9..02DF
6372 LATIN, // 02E0..02E4
6373 COMMON, // 02E5..02E9
6374 BOPOMOFO, // 02EA..02EB
6375 COMMON, // 02EC..02FF
6376 INHERITED, // 0300..036F
6377 GREEK, // 0370..0373
6378 COMMON, // 0374
6379 GREEK, // 0375..0377
6380 UNKNOWN, // 0378..0379
6381 GREEK, // 037A..037D
6382 COMMON, // 037E
6383 GREEK, // 037F
6384 UNKNOWN, // 0380..0383
6385 GREEK, // 0384
6386 COMMON, // 0385
6387 GREEK, // 0386
6388 COMMON, // 0387
6389 GREEK, // 0388..038A
6390 UNKNOWN, // 038B
6391 GREEK, // 038C
6392 UNKNOWN, // 038D
6393 GREEK, // 038E..03A1
6394 UNKNOWN, // 03A2
6395 GREEK, // 03A3..03E1
6396 COPTIC, // 03E2..03EF
6397 GREEK, // 03F0..03FF
6398 CYRILLIC, // 0400..0484
6399 INHERITED, // 0485..0486
6400 CYRILLIC, // 0487..052F
6401 UNKNOWN, // 0530
6402 ARMENIAN, // 0531..0556
6403 UNKNOWN, // 0557..0558
6404 ARMENIAN, // 0559..0588
6405 COMMON, // 0589
6406 ARMENIAN, // 058A
6407 UNKNOWN, // 058B..058C
6408 ARMENIAN, // 058D..058F
6409 UNKNOWN, // 0590
6410 HEBREW, // 0591..05C7
6411 UNKNOWN, // 05C8..05CF
6412 HEBREW, // 05D0..05EA
6413 UNKNOWN, // 05EB..05EE
6414 HEBREW, // 05EF..05F4
6415 UNKNOWN, // 05F5..05FF
6416 ARABIC, // 0600..0604
6417 COMMON, // 0605
6418 ARABIC, // 0606..060B
6419 COMMON, // 060C
6420 ARABIC, // 060D..061A
6421 COMMON, // 061B
6422 ARABIC, // 061C
6423 UNKNOWN, // 061D
6424 ARABIC, // 061E
6425 COMMON, // 061F
6426 ARABIC, // 0620..063F
6427 COMMON, // 0640
6428 ARABIC, // 0641..064A
6429 INHERITED, // 064B..0655
6430 ARABIC, // 0656..066F
6431 INHERITED, // 0670
6432 ARABIC, // 0671..06DC
6433 COMMON, // 06DD
6434 ARABIC, // 06DE..06FF
6435 SYRIAC, // 0700..070D
6436 UNKNOWN, // 070E
6437 SYRIAC, // 070F..074A
6438 UNKNOWN, // 074B..074C
6439 SYRIAC, // 074D..074F
6440 ARABIC, // 0750..077F
6441 THAANA, // 0780..07B1
6442 UNKNOWN, // 07B2..07BF
6443 NKO, // 07C0..07FA
6444 UNKNOWN, // 07FB..07FC
6445 NKO, // 07FD..07FF
6446 SAMARITAN, // 0800..082D
6447 UNKNOWN, // 082E..082F
6448 SAMARITAN, // 0830..083E
6449 UNKNOWN, // 083F
6450 MANDAIC, // 0840..085B
6451 UNKNOWN, // 085C..085D
6452 MANDAIC, // 085E
6453 UNKNOWN, // 085F
6454 SYRIAC, // 0860..086A
6455 UNKNOWN, // 086B..089F
6456 ARABIC, // 08A0..08B4
6457 UNKNOWN, // 08B5
6458 ARABIC, // 08B6..08BD
6459 UNKNOWN, // 08BE..08D2
6460 ARABIC, // 08D3..08E1
6461 COMMON, // 08E2
6462 ARABIC, // 08E3..08FF
6463 DEVANAGARI, // 0900..0950
6464 INHERITED, // 0951..0952
6465 DEVANAGARI, // 0953..0963
6466 COMMON, // 0964..0965
6467 DEVANAGARI, // 0966..097F
6468 BENGALI, // 0980..0983
6469 UNKNOWN, // 0984
6470 BENGALI, // 0985..098C
6471 UNKNOWN, // 098D..098E
6472 BENGALI, // 098F..0990
6473 UNKNOWN, // 0991..0992
6474 BENGALI, // 0993..09A8
6475 UNKNOWN, // 09A9
6476 BENGALI, // 09AA..09B0
6477 UNKNOWN, // 09B1
6478 BENGALI, // 09B2
6479 UNKNOWN, // 09B3..09B5
6480 BENGALI, // 09B6..09B9
6481 UNKNOWN, // 09BA..09BB
6482 BENGALI, // 09BC..09C4
6483 UNKNOWN, // 09C5..09C6
6484 BENGALI, // 09C7..09C8
6485 UNKNOWN, // 09C9..09CA
6486 BENGALI, // 09CB..09CE
6487 UNKNOWN, // 09CF..09D6
6488 BENGALI, // 09D7
6489 UNKNOWN, // 09D8..09DB
6490 BENGALI, // 09DC..09DD
6491 UNKNOWN, // 09DE
6492 BENGALI, // 09DF..09E3
6493 UNKNOWN, // 09E4..09E5
6494 BENGALI, // 09E6..09FE
6495 UNKNOWN, // 09FF..0A00
6496 GURMUKHI, // 0A01..0A03
6497 UNKNOWN, // 0A04
6498 GURMUKHI, // 0A05..0A0A
6499 UNKNOWN, // 0A0B..0A0E
6500 GURMUKHI, // 0A0F..0A10
6501 UNKNOWN, // 0A11..0A12
6502 GURMUKHI, // 0A13..0A28
6503 UNKNOWN, // 0A29
6504 GURMUKHI, // 0A2A..0A30
6505 UNKNOWN, // 0A31
6506 GURMUKHI, // 0A32..0A33
6507 UNKNOWN, // 0A34
6508 GURMUKHI, // 0A35..0A36
6509 UNKNOWN, // 0A37
6510 GURMUKHI, // 0A38..0A39
6511 UNKNOWN, // 0A3A..0A3B
6512 GURMUKHI, // 0A3C
6513 UNKNOWN, // 0A3D
6514 GURMUKHI, // 0A3E..0A42
6515 UNKNOWN, // 0A43..0A46
6516 GURMUKHI, // 0A47..0A48
6517 UNKNOWN, // 0A49..0A4A
6518 GURMUKHI, // 0A4B..0A4D
6519 UNKNOWN, // 0A4E..0A50
6520 GURMUKHI, // 0A51
6521 UNKNOWN, // 0A52..0A58
6522 GURMUKHI, // 0A59..0A5C
6523 UNKNOWN, // 0A5D
6524 GURMUKHI, // 0A5E
6525 UNKNOWN, // 0A5F..0A65
6526 GURMUKHI, // 0A66..0A76
6527 UNKNOWN, // 0A77..0A80
6528 GUJARATI, // 0A81..0A83
6529 UNKNOWN, // 0A84
6530 GUJARATI, // 0A85..0A8D
6531 UNKNOWN, // 0A8E
6532 GUJARATI, // 0A8F..0A91
6533 UNKNOWN, // 0A92
6534 GUJARATI, // 0A93..0AA8
6535 UNKNOWN, // 0AA9
6536 GUJARATI, // 0AAA..0AB0
6537 UNKNOWN, // 0AB1
6538 GUJARATI, // 0AB2..0AB3
6539 UNKNOWN, // 0AB4
6540 GUJARATI, // 0AB5..0AB9
6541 UNKNOWN, // 0ABA..0ABB
6542 GUJARATI, // 0ABC..0AC5
6543 UNKNOWN, // 0AC6
6544 GUJARATI, // 0AC7..0AC9
6545 UNKNOWN, // 0ACA
6546 GUJARATI, // 0ACB..0ACD
6547 UNKNOWN, // 0ACE..0ACF
6548 GUJARATI, // 0AD0
6549 UNKNOWN, // 0AD1..0ADF
6550 GUJARATI, // 0AE0..0AE3
6551 UNKNOWN, // 0AE4..0AE5
6552 GUJARATI, // 0AE6..0AF1
6553 UNKNOWN, // 0AF2..0AF8
6554 GUJARATI, // 0AF9..0AFF
6555 UNKNOWN, // 0B00
6556 ORIYA, // 0B01..0B03
6557 UNKNOWN, // 0B04
6558 ORIYA, // 0B05..0B0C
6559 UNKNOWN, // 0B0D..0B0E
6560 ORIYA, // 0B0F..0B10
6561 UNKNOWN, // 0B11..0B12
6562 ORIYA, // 0B13..0B28
6563 UNKNOWN, // 0B29
6564 ORIYA, // 0B2A..0B30
6565 UNKNOWN, // 0B31
6566 ORIYA, // 0B32..0B33
6567 UNKNOWN, // 0B34
6568 ORIYA, // 0B35..0B39
6569 UNKNOWN, // 0B3A..0B3B
6570 ORIYA, // 0B3C..0B44
6571 UNKNOWN, // 0B45..0B46
6572 ORIYA, // 0B47..0B48
6573 UNKNOWN, // 0B49..0B4A
6574 ORIYA, // 0B4B..0B4D
6575 UNKNOWN, // 0B4E..0B55
6576 ORIYA, // 0B56..0B57
6577 UNKNOWN, // 0B58..0B5B
6578 ORIYA, // 0B5C..0B5D
6579 UNKNOWN, // 0B5E
6580 ORIYA, // 0B5F..0B63
6581 UNKNOWN, // 0B64..0B65
6582 ORIYA, // 0B66..0B77
6583 UNKNOWN, // 0B78..0B81
6584 TAMIL, // 0B82..0B83
6585 UNKNOWN, // 0B84
6586 TAMIL, // 0B85..0B8A
6587 UNKNOWN, // 0B8B..0B8D
6588 TAMIL, // 0B8E..0B90
6589 UNKNOWN, // 0B91
6590 TAMIL, // 0B92..0B95
6591 UNKNOWN, // 0B96..0B98
6592 TAMIL, // 0B99..0B9A
6593 UNKNOWN, // 0B9B
6594 TAMIL, // 0B9C
6595 UNKNOWN, // 0B9D
6596 TAMIL, // 0B9E..0B9F
6597 UNKNOWN, // 0BA0..0BA2
6598 TAMIL, // 0BA3..0BA4
6599 UNKNOWN, // 0BA5..0BA7
6600 TAMIL, // 0BA8..0BAA
6601 UNKNOWN, // 0BAB..0BAD
6602 TAMIL, // 0BAE..0BB9
6603 UNKNOWN, // 0BBA..0BBD
6604 TAMIL, // 0BBE..0BC2
6605 UNKNOWN, // 0BC3..0BC5
6606 TAMIL, // 0BC6..0BC8
6607 UNKNOWN, // 0BC9
6608 TAMIL, // 0BCA..0BCD
6609 UNKNOWN, // 0BCE..0BCF
6610 TAMIL, // 0BD0
6611 UNKNOWN, // 0BD1..0BD6
6612 TAMIL, // 0BD7
6613 UNKNOWN, // 0BD8..0BE5
6614 TAMIL, // 0BE6..0BFA
6615 UNKNOWN, // 0BFB..0BFF
6616 TELUGU, // 0C00..0C0C
6617 UNKNOWN, // 0C0D
6618 TELUGU, // 0C0E..0C10
6619 UNKNOWN, // 0C11
6620 TELUGU, // 0C12..0C28
6621 UNKNOWN, // 0C29
6622 TELUGU, // 0C2A..0C39
6623 UNKNOWN, // 0C3A..0C3C
6624 TELUGU, // 0C3D..0C44
6625 UNKNOWN, // 0C45
6626 TELUGU, // 0C46..0C48
6627 UNKNOWN, // 0C49
6628 TELUGU, // 0C4A..0C4D
6629 UNKNOWN, // 0C4E..0C54
6630 TELUGU, // 0C55..0C56
6631 UNKNOWN, // 0C57
6632 TELUGU, // 0C58..0C5A
6633 UNKNOWN, // 0C5B..0C5F
6634 TELUGU, // 0C60..0C63
6635 UNKNOWN, // 0C64..0C65
6636 TELUGU, // 0C66..0C6F
6637 UNKNOWN, // 0C70..0C77
6638 TELUGU, // 0C78..0C7F
6639 KANNADA, // 0C80..0C8C
6640 UNKNOWN, // 0C8D
6641 KANNADA, // 0C8E..0C90
6642 UNKNOWN, // 0C91
6643 KANNADA, // 0C92..0CA8
6644 UNKNOWN, // 0CA9
6645 KANNADA, // 0CAA..0CB3
6646 UNKNOWN, // 0CB4
6647 KANNADA, // 0CB5..0CB9
6648 UNKNOWN, // 0CBA..0CBB
6649 KANNADA, // 0CBC..0CC4
6650 UNKNOWN, // 0CC5
6651 KANNADA, // 0CC6..0CC8
6652 UNKNOWN, // 0CC9
6653 KANNADA, // 0CCA..0CCD
6654 UNKNOWN, // 0CCE..0CD4
6655 KANNADA, // 0CD5..0CD6
6656 UNKNOWN, // 0CD7..0CDD
6657 KANNADA, // 0CDE
6658 UNKNOWN, // 0CDF
6659 KANNADA, // 0CE0..0CE3
6660 UNKNOWN, // 0CE4..0CE5
6661 KANNADA, // 0CE6..0CEF
6662 UNKNOWN, // 0CF0
6663 KANNADA, // 0CF1..0CF2
6664 UNKNOWN, // 0CF3..0CFF
6665 MALAYALAM, // 0D00..0D03
6666 UNKNOWN, // 0D04
6667 MALAYALAM, // 0D05..0D0C
6668 UNKNOWN, // 0D0D
6669 MALAYALAM, // 0D0E..0D10
6670 UNKNOWN, // 0D11
6671 MALAYALAM, // 0D12..0D44
6672 UNKNOWN, // 0D45
6673 MALAYALAM, // 0D46..0D48
6674 UNKNOWN, // 0D49
6675 MALAYALAM, // 0D4A..0D4F
6676 UNKNOWN, // 0D50..0D53
6677 MALAYALAM, // 0D54..0D63
6678 UNKNOWN, // 0D64..0D65
6679 MALAYALAM, // 0D66..0D7F
6680 UNKNOWN, // 0D80..0D81
6681 SINHALA, // 0D82..0D83
6682 UNKNOWN, // 0D84
6683 SINHALA, // 0D85..0D96
6684 UNKNOWN, // 0D97..0D99
6685 SINHALA, // 0D9A..0DB1
6686 UNKNOWN, // 0DB2
6687 SINHALA, // 0DB3..0DBB
6688 UNKNOWN, // 0DBC
6689 SINHALA, // 0DBD
6690 UNKNOWN, // 0DBE..0DBF
6691 SINHALA, // 0DC0..0DC6
6692 UNKNOWN, // 0DC7..0DC9
6693 SINHALA, // 0DCA
6694 UNKNOWN, // 0DCB..0DCE
6695 SINHALA, // 0DCF..0DD4
6696 UNKNOWN, // 0DD5
6697 SINHALA, // 0DD6
6698 UNKNOWN, // 0DD7
6699 SINHALA, // 0DD8..0DDF
6700 UNKNOWN, // 0DE0..0DE5
6701 SINHALA, // 0DE6..0DEF
6702 UNKNOWN, // 0DF0..0DF1
6703 SINHALA, // 0DF2..0DF4
6704 UNKNOWN, // 0DF5..0E00
6705 THAI, // 0E01..0E3A
6706 UNKNOWN, // 0E3B..0E3E
6707 COMMON, // 0E3F
6708 THAI, // 0E40..0E5B
6709 UNKNOWN, // 0E5C..0E80
6710 LAO, // 0E81..0E82
6711 UNKNOWN, // 0E83
6712 LAO, // 0E84
6713 UNKNOWN, // 0E85..0E86
6714 LAO, // 0E87..0E88
6715 UNKNOWN, // 0E89
6716 LAO, // 0E8A
6717 UNKNOWN, // 0E8B..0E8C
6718 LAO, // 0E8D
6719 UNKNOWN, // 0E8E..0E93
6720 LAO, // 0E94..0E97
6721 UNKNOWN, // 0E98
6722 LAO, // 0E99..0E9F
6723 UNKNOWN, // 0EA0
6724 LAO, // 0EA1..0EA3
6725 UNKNOWN, // 0EA4
6726 LAO, // 0EA5
6727 UNKNOWN, // 0EA6
6728 LAO, // 0EA7
6729 UNKNOWN, // 0EA8..0EA9
6730 LAO, // 0EAA..0EAB
6731 UNKNOWN, // 0EAC
6732 LAO, // 0EAD..0EB9
6733 UNKNOWN, // 0EBA
6734 LAO, // 0EBB..0EBD
6735 UNKNOWN, // 0EBE..0EBF
6736 LAO, // 0EC0..0EC4
6737 UNKNOWN, // 0EC5
6738 LAO, // 0EC6
6739 UNKNOWN, // 0EC7
6740 LAO, // 0EC8..0ECD
6741 UNKNOWN, // 0ECE..0ECF
6742 LAO, // 0ED0..0ED9
6743 UNKNOWN, // 0EDA..0EDB
6744 LAO, // 0EDC..0EDF
6745 UNKNOWN, // 0EE0..0EFF
6746 TIBETAN, // 0F00..0F47
6747 UNKNOWN, // 0F48
6748 TIBETAN, // 0F49..0F6C
6749 UNKNOWN, // 0F6D..0F70
6750 TIBETAN, // 0F71..0F97
6751 UNKNOWN, // 0F98
6752 TIBETAN, // 0F99..0FBC
6753 UNKNOWN, // 0FBD
6754 TIBETAN, // 0FBE..0FCC
6755 UNKNOWN, // 0FCD
6756 TIBETAN, // 0FCE..0FD4
6757 COMMON, // 0FD5..0FD8
6758 TIBETAN, // 0FD9..0FDA
6759 UNKNOWN, // 0FDB..FFF
6760 MYANMAR, // 1000..109F
6761 GEORGIAN, // 10A0..10C5
6762 UNKNOWN, // 10C6
6763 GEORGIAN, // 10C7
6764 UNKNOWN, // 10C8..10CC
6765 GEORGIAN, // 10CD
6766 UNKNOWN, // 10CE..10CF
6767 GEORGIAN, // 10D0..10FA
6768 COMMON, // 10FB
6769 GEORGIAN, // 10FC..10FF
6770 HANGUL, // 1100..11FF
6771 ETHIOPIC, // 1200..1248
6772 UNKNOWN, // 1249
6773 ETHIOPIC, // 124A..124D
6774 UNKNOWN, // 124E..124F
6775 ETHIOPIC, // 1250..1256
6776 UNKNOWN, // 1257
6777 ETHIOPIC, // 1258
6778 UNKNOWN, // 1259
6779 ETHIOPIC, // 125A..125D
6780 UNKNOWN, // 125E..125F
6781 ETHIOPIC, // 1260..1288
6782 UNKNOWN, // 1289
6783 ETHIOPIC, // 128A..128D
6784 UNKNOWN, // 128E..128F
6785 ETHIOPIC, // 1290..12B0
6786 UNKNOWN, // 12B1
6787 ETHIOPIC, // 12B2..12B5
6788 UNKNOWN, // 12B6..12B7
6789 ETHIOPIC, // 12B8..12BE
6790 UNKNOWN, // 12BF
6791 ETHIOPIC, // 12C0
6792 UNKNOWN, // 12C1
6793 ETHIOPIC, // 12C2..12C5
6794 UNKNOWN, // 12C6..12C7
6795 ETHIOPIC, // 12C8..12D6
6796 UNKNOWN, // 12D7
6797 ETHIOPIC, // 12D8..1310
6798 UNKNOWN, // 1311
6799 ETHIOPIC, // 1312..1315
6800 UNKNOWN, // 1316..1317
6801 ETHIOPIC, // 1318..135A
6802 UNKNOWN, // 135B..135C
6803 ETHIOPIC, // 135D..137C
6804 UNKNOWN, // 137D..137F
6805 ETHIOPIC, // 1380..1399
6806 UNKNOWN, // 139A..139F
6807 CHEROKEE, // 13A0..13F5
6808 UNKNOWN, // 13F6..13F7
6809 CHEROKEE, // 13F8..13FD
6810 UNKNOWN, // 13FE..13FF
6811 CANADIAN_ABORIGINAL, // 1400..167F
6812 OGHAM, // 1680..169C
6813 UNKNOWN, // 169D..169F
6814 RUNIC, // 16A0..16EA
6815 COMMON, // 16EB..16ED
6816 RUNIC, // 16EE..16F8
6817 UNKNOWN, // 16F9..16FF
6818 TAGALOG, // 1700..170C
6819 UNKNOWN, // 170D
6820 TAGALOG, // 170E..1714
6821 UNKNOWN, // 1715..171F
6822 HANUNOO, // 1720..1734
6823 COMMON, // 1735..1736
6824 UNKNOWN, // 1737..173F
6825 BUHID, // 1740..1753
6826 UNKNOWN, // 1754..175F
6827 TAGBANWA, // 1760..176C
6828 UNKNOWN, // 176D
6829 TAGBANWA, // 176E..1770
6830 UNKNOWN, // 1771
6831 TAGBANWA, // 1772..1773
6832 UNKNOWN, // 1774..177F
6833 KHMER, // 1780..17DD
6834 UNKNOWN, // 17DE..17DF
6835 KHMER, // 17E0..17E9
6836 UNKNOWN, // 17EA..17EF
6837 KHMER, // 17F0..17F9
6838 UNKNOWN, // 17FA..17FF
6839 MONGOLIAN, // 1800..1801
6840 COMMON, // 1802..1803
6841 MONGOLIAN, // 1804
6842 COMMON, // 1805
6843 MONGOLIAN, // 1806..180E
6844 UNKNOWN, // 180F
6845 MONGOLIAN, // 1810..1819
6846 UNKNOWN, // 181A..181F
6847 MONGOLIAN, // 1820..1878
6848 UNKNOWN, // 1879..187F
6849 MONGOLIAN, // 1880..18AA
6850 UNKNOWN, // 18AB..18AF
6851 CANADIAN_ABORIGINAL, // 18B0..18F5
6852 UNKNOWN, // 18F6..18FF
6853 LIMBU, // 1900..191E
6854 UNKNOWN, // 191F
6855 LIMBU, // 1920..192B
6856 UNKNOWN, // 192C..192F
6857 LIMBU, // 1930..193B
6858 UNKNOWN, // 193C..193F
6859 LIMBU, // 1940
6860 UNKNOWN, // 1941..1943
6861 LIMBU, // 1944..194F
6862 TAI_LE, // 1950..196D
6863 UNKNOWN, // 196E..196F
6864 TAI_LE, // 1970..1974
6865 UNKNOWN, // 1975..197F
6866 NEW_TAI_LUE, // 1980..19AB
6867 UNKNOWN, // 19AC..19AF
6868 NEW_TAI_LUE, // 19B0..19C9
6869 UNKNOWN, // 19CA..19CF
6870 NEW_TAI_LUE, // 19D0..19DA
6871 UNKNOWN, // 19DB..19DD
6872 NEW_TAI_LUE, // 19DE..19DF
6873 KHMER, // 19E0..19FF
6874 BUGINESE, // 1A00..1A1B
6875 UNKNOWN, // 1A1C..1A1D
6876 BUGINESE, // 1A1E..1A1F
6877 TAI_THAM, // 1A20..1A5E
6878 UNKNOWN, // 1A5F
6879 TAI_THAM, // 1A60..1A7C
6880 UNKNOWN, // 1A7D..1A7E
6881 TAI_THAM, // 1A7F..1A89
6882 UNKNOWN, // 1A8A..1A8F
6883 TAI_THAM, // 1A90..1A99
6884 UNKNOWN, // 1A9A..1A9F
6885 TAI_THAM, // 1AA0..1AAD
6886 UNKNOWN, // 1AAE..1AAF
6887 INHERITED, // 1AB0..1ABE
6888 UNKNOWN, // 1ABF..1AFF
6889 BALINESE, // 1B00..1B4B
6890 UNKNOWN, // 1B4C..1B4F
6891 BALINESE, // 1B50..1B7C
6892 UNKNOWN, // 1B7D..1B7F
6893 SUNDANESE, // 1B80..1BBF
6894 BATAK, // 1BC0..1BF3
6895 UNKNOWN, // 1BF4..1BFB
6896 BATAK, // 1BFC..1BFF
6897 LEPCHA, // 1C00..1C37
6898 UNKNOWN, // 1C38..1C3A
6899 LEPCHA, // 1C3B..1C49
6900 UNKNOWN, // 1C4A..1C4C
6901 LEPCHA, // 1C4D..1C4F
6902 OL_CHIKI, // 1C50..1C7F
6903 CYRILLIC, // 1C80..1C88
6904 UNKNOWN, // 1C89
6905 GEORGIAN, // 1C90..1CBA
6906 UNKNOWN, // 1CBB..1CBC
6907 GEORGIAN, // 1CBD..1CBF
6908 SUNDANESE, // 1CC0..1CC7
6909 UNKNOWN, // 1CC8..1CCF
6910 INHERITED, // 1CD0..1CD2
6911 COMMON, // 1CD3
6912 INHERITED, // 1CD4..1CE0
6913 COMMON, // 1CE1
6914 INHERITED, // 1CE2..1CE8
6915 COMMON, // 1CE9..1CEC
6916 INHERITED, // 1CED
6917 COMMON, // 1CEE..1CF3
6918 INHERITED, // 1CF4
6919 COMMON, // 1CF5..1CF7
6920 INHERITED, // 1CF8..1CF9
6921 UNKNOWN, // 1CFA..1CFF
6922 LATIN, // 1D00..1D25
6923 GREEK, // 1D26..1D2A
6924 CYRILLIC, // 1D2B
6925 LATIN, // 1D2C..1D5C
6926 GREEK, // 1D5D..1D61
6927 LATIN, // 1D62..1D65
6928 GREEK, // 1D66..1D6A
6929 LATIN, // 1D6B..1D77
6930 CYRILLIC, // 1D78
6931 LATIN, // 1D79..1DBE
6932 GREEK, // 1DBF
6933 INHERITED, // 1DC0..1DF9
6934 UNKNOWN, // 1DFA
6935 INHERITED, // 1DFB..1DFF
6936 LATIN, // 1E00..1EFF
6937 GREEK, // 1F00..1F15
6938 UNKNOWN, // 1F16..1F17
6939 GREEK, // 1F18..1F1D
6940 UNKNOWN, // 1F1E..1F1F
6941 GREEK, // 1F20..1F45
6942 UNKNOWN, // 1F46..1F47
6943 GREEK, // 1F48..1F4D
6944 UNKNOWN, // 1F4E..1F4F
6945 GREEK, // 1F50..1F57
6946 UNKNOWN, // 1F58
6947 GREEK, // 1F59
6948 UNKNOWN, // 1F5A
6949 GREEK, // 1F5B
6950 UNKNOWN, // 1F5C
6951 GREEK, // 1F5D
6952 UNKNOWN, // 1F5E
6953 GREEK, // 1F5F..1F7D
6954 UNKNOWN, // 1F7E..1F7F
6955 GREEK, // 1F80..1FB4
6956 UNKNOWN, // 1FB5
6957 GREEK, // 1FB6..1FC4
6958 UNKNOWN, // 1FC5
6959 GREEK, // 1FC6..1FD3
6960 UNKNOWN, // 1FD4..1FD5
6961 GREEK, // 1FD6..1FDB
6962 UNKNOWN, // 1FDC
6963 GREEK, // 1FDD..1FEF
6964 UNKNOWN, // 1FF0..1FF1
6965 GREEK, // 1FF2..1FF4
6966 UNKNOWN, // 1FF5
6967 GREEK, // 1FF6..1FFE
6968 UNKNOWN, // 1FFF
6969 COMMON, // 2000..200B
6970 INHERITED, // 200C..200D
6971 COMMON, // 200E..2064
6972 UNKNOWN, // 2065
6973 COMMON, // 2066..2070
6974 LATIN, // 2071
6975 UNKNOWN, // 2072..2073
6976 COMMON, // 2074..207E
6977 LATIN, // 207F
6978 COMMON, // 2080..208E
6979 UNKNOWN, // 208F
6980 LATIN, // 2090..209C
6981 UNKNOWN, // 209D..209F
6982 COMMON, // 20A0..20BF
6983 UNKNOWN, // 20C0..20CF
6984 INHERITED, // 20D0..20F0
6985 UNKNOWN, // 20F1..20FF
6986 COMMON, // 2100..2125
6987 GREEK, // 2126
6988 COMMON, // 2127..2129
6989 LATIN, // 212A..212B
6990 COMMON, // 212C..2131
6991 LATIN, // 2132
6992 COMMON, // 2133..214D
6993 LATIN, // 214E
6994 COMMON, // 214F..215F
6995 LATIN, // 2160..2188
6996 COMMON, // 2189..218B
6997 UNKNOWN, // 218C..218F
6998 COMMON, // 2190..2426
6999 UNKNOWN, // 2427..243F
7000 COMMON, // 2440..244A
7001 UNKNOWN, // 244B..245F
7002 COMMON, // 2460..27FF
7003 BRAILLE, // 2800..28FF
7004 COMMON, // 2900..2B73
7005 UNKNOWN, // 2B74..2B75
7006 COMMON, // 2B76..2B95
7007 UNKNOWN, // 2B96..2B97
7008 COMMON, // 2B98..2BC8
7009 UNKNOWN, // 2BC9
7010 COMMON, // 2BCA..2BFE
7011 UNKNOWN, // 0x2BFF
7012 GLAGOLITIC, // 2C00..2C2E
7013 UNKNOWN, // 2C2F
7014 GLAGOLITIC, // 2C30..2C5E
7015 UNKNOWN, // 2C5F
7016 LATIN, // 2C60..2C7F
7017 COPTIC, // 2C80..2CF3
7018 UNKNOWN, // 2CF4..2CF8
7019 COPTIC, // 2CF9..2CFF
7020 GEORGIAN, // 2D00..2D25
7021 UNKNOWN, // 2D26
7022 GEORGIAN, // 2D27
7023 UNKNOWN, // 2D28..2D2C
7024 GEORGIAN, // 2D2D
7025 UNKNOWN, // 2D2E..2D2F
7026 TIFINAGH, // 2D30..2D67
7027 UNKNOWN, // 2D68..2D6E
7028 TIFINAGH, // 2D6F..2D70
7029 UNKNOWN, // 2D71..2D7E
7030 TIFINAGH, // 2D7F
7031 ETHIOPIC, // 2D80..2D96
7032 UNKNOWN, // 2D97..2D9F
7033 ETHIOPIC, // 2DA0..2DA6
7034 UNKNOWN, // 2DA7
7035 ETHIOPIC, // 2DA8..2DAE
7036 UNKNOWN, // 2DAF
7037 ETHIOPIC, // 2DB0..2DB6
7038 UNKNOWN, // 2DB7
7039 ETHIOPIC, // 2DB8..2DBE
7040 UNKNOWN, // 2DBF
7041 ETHIOPIC, // 2DC0..2DC6
7042 UNKNOWN, // 2DC7
7043 ETHIOPIC, // 2DC8..2DCE
7044 UNKNOWN, // 2DCF
7045 ETHIOPIC, // 2DD0..2DD6
7046 UNKNOWN, // 2DD7
7047 ETHIOPIC, // 2DD8..2DDE
7048 UNKNOWN, // 2DDF
7049 CYRILLIC, // 2DE0..2DFF
7050 COMMON, // 2E00..2E4E
7051 UNKNOWN, // 2E4F..2E7F
7052 HAN, // 2E80..2E99
7053 UNKNOWN, // 2E9A
7054 HAN, // 2E9B..2EF3
7055 UNKNOWN, // 2EF4..2EFF
7056 HAN, // 2F00..2FD5
7057 UNKNOWN, // 2FD6..2FEF
7058 COMMON, // 2FF0..2FFB
7059 UNKNOWN, // 2FFC..2FFF
7060 COMMON, // 3000..3004
7061 HAN, // 3005
7062 COMMON, // 3006
7063 HAN, // 3007
7064 COMMON, // 3008..3020
7065 HAN, // 3021..3029
7066 INHERITED, // 302A..302D
7067 HANGUL, // 302E..302F
7068 COMMON, // 3030..3037
7069 HAN, // 3038..303B
7070 COMMON, // 303C..303F
7071 UNKNOWN, // 3040
7072 HIRAGANA, // 3041..3096
7073 UNKNOWN, // 3097..3098
7074 INHERITED, // 3099..309A
7075 COMMON, // 309B..309C
7076 HIRAGANA, // 309D..309F
7077 COMMON, // 30A0
7078 KATAKANA, // 30A1..30FA
7079 COMMON, // 30FB..30FC
7080 KATAKANA, // 30FD..30FF
7081 UNKNOWN, // 3100..3104
7082 BOPOMOFO, // 3105..312F
7083 UNKNOWN, // 3130
7084 HANGUL, // 3131..318E
7085 UNKNOWN, // 318F
7086 COMMON, // 3190..319F
7087 BOPOMOFO, // 31A0..31BA
7088 UNKNOWN, // 31BB..31BF
7089 COMMON, // 31C0..31E3
7090 UNKNOWN, // 31E4..31EF
7091 KATAKANA, // 31F0..31FF
7092 HANGUL, // 3200..321E
7093 UNKNOWN, // 321F
7094 COMMON, // 3220..325F
7095 HANGUL, // 3260..327E
7096 COMMON, // 327F..32CF
7097 KATAKANA, // 32D0..32FE
7098 COMMON, // 32FF
7099 KATAKANA, // 3300..3357
7100 COMMON, // 3358..33FF
7101 HAN, // 3400..4DB5
7102 UNKNOWN, // 4DB6..4DBF
7103 COMMON, // 4DC0..4DFF
7104 HAN, // 4E00..9FEF
7105 UNKNOWN, // 9FF0..9FFF
7106 YI, // A000..A48C
7107 UNKNOWN, // A48D..A48F
7108 YI, // A490..A4C6
7109 UNKNOWN, // A4C7..A4CF
7110 LISU, // A4D0..A4FF
7111 VAI, // A500..A62B
7112 UNKNOWN, // A62C..A63F
7113 CYRILLIC, // A640..A69F
7114 BAMUM, // A6A0..A6F7
7115 UNKNOWN, // A6F8..A6FF
7116 COMMON, // A700..A721
7117 LATIN, // A722..A787
7118 COMMON, // A788..A78A
7119 LATIN, // A78B..A7B9
7120 UNKNOWN, // A7C0..A7F6
7121 LATIN, // A7F7..A7FF
7122 SYLOTI_NAGRI, // A800..A82B
7123 UNKNOWN, // A82C..A82F
7124 COMMON, // A830..A839
7125 UNKNOWN, // A83A..A83F
7126 PHAGS_PA, // A840..A877
7127 UNKNOWN, // A878..A87F
7128 SAURASHTRA, // A880..A8C5
7129 UNKNOWN, // A8C6..A8CD
7130 SAURASHTRA, // A8CE..A8D9
7131 UNKNOWN, // A8DA..A8DF
7132 DEVANAGARI, // A8E0..A8FF
7133 KAYAH_LI, // A900..A92D
7134 COMMON, // A92E
7135 KAYAH_LI, // A92F
7136 REJANG, // A930..A953
7137 UNKNOWN, // A954..A95E
7138 REJANG, // A95F
7139 HANGUL, // A960..A97C
7140 UNKNOWN, // A97D..A97F
7141 JAVANESE, // A980..A9CD
7142 UNKNOWN, // A9CE
7143 COMMON, // A9CF
7144 JAVANESE, // A9D0..A9D9
7145 UNKNOWN, // A9DA..A9DD
7146 JAVANESE, // A9DE..A9DF
7147 MYANMAR, // A9E0..A9FE
7148 UNKNOWN, // A9FF
7149 CHAM, // AA00..AA36
7150 UNKNOWN, // AA37..AA3F
7151 CHAM, // AA40..AA4D
7152 UNKNOWN, // AA4E..AA4F
7153 CHAM, // AA50..AA59
7154 UNKNOWN, // AA5A..AA5B
7155 CHAM, // AA5C..AA5F
7156 MYANMAR, // AA60..AA7F
7157 TAI_VIET, // AA80..AAC2
7158 UNKNOWN, // AAC3..AADA
7159 TAI_VIET, // AADB..AADF
7160 MEETEI_MAYEK, // AAE0..AAF6
7161 UNKNOWN, // AAF7..AB00
7162 ETHIOPIC, // AB01..AB06
7163 UNKNOWN, // AB07..AB08
7164 ETHIOPIC, // AB09..AB0E
7165 UNKNOWN, // AB0F..AB10
7166 ETHIOPIC, // AB11..AB16
7167 UNKNOWN, // AB17..AB1F
7168 ETHIOPIC, // AB20..AB26
7169 UNKNOWN, // AB27
7170 ETHIOPIC, // AB28..AB2E
7171 UNKNOWN, // AB2F
7172 LATIN, // AB30..AB5A
7173 COMMON, // AB5B
7174 LATIN, // AB5C..AB64
7175 GREEK, // AB65
7176 UNKNOWN, // AB66..AB6F
7177 CHEROKEE, // AB70..ABBF
7178 MEETEI_MAYEK, // ABC0..ABED
7179 UNKNOWN, // ABEE..ABEF
7180 MEETEI_MAYEK, // ABF0..ABF9
7181 UNKNOWN, // ABFA..ABFF
7182 HANGUL, // AC00..D7A3
7183 UNKNOWN, // D7A4..D7AF
7184 HANGUL, // D7B0..D7C6
7185 UNKNOWN, // D7C7..D7CA
7186 HANGUL, // D7CB..D7FB
7187 UNKNOWN, // D7FC..F8FF
7188 HAN, // F900..FA6D
7189 UNKNOWN, // FA6E..FA6F
7190 HAN, // FA70..FAD9
7191 UNKNOWN, // FADA..FAFF
7192 LATIN, // FB00..FB06
7193 UNKNOWN, // FB07..FB12
7194 ARMENIAN, // FB13..FB17
7195 UNKNOWN, // FB18..FB1C
7196 HEBREW, // FB1D..FB36
7197 UNKNOWN, // FB37
7198 HEBREW, // FB38..FB3C
7199 UNKNOWN, // FB3D
7200 HEBREW, // FB3E
7201 UNKNOWN, // FB3F
7202 HEBREW, // FB40..FB41
7203 UNKNOWN, // FB42
7204 HEBREW, // FB43..FB44
7205 UNKNOWN, // FB45
7206 HEBREW, // FB46..FB4F
7207 ARABIC, // FB50..FBC1
7208 UNKNOWN, // FBC2..FBD2
7209 ARABIC, // FBD3..FD3D
7210 COMMON, // FD3E..FD3F
7211 UNKNOWN, // FD40..FD4F
7212 ARABIC, // FD50..FD8F
7213 UNKNOWN, // FD90..FD91
7214 ARABIC, // FD92..FDC7
7215 UNKNOWN, // FDC8..FDEF
7216 ARABIC, // FDF0..FDFD
7217 UNKNOWN, // FDFE..FDFF
7218 INHERITED, // FE00..FE0F
7219 COMMON, // FE10..FE19
7220 UNKNOWN, // FE1A..FE1F
7221 INHERITED, // FE20..FE2D
7222 CYRILLIC, // FE2E..FE2F
7223 COMMON, // FE30..FE52
7224 UNKNOWN, // FE53
7225 COMMON, // FE54..FE66
7226 UNKNOWN, // FE67
7227 COMMON, // FE68..FE6B
7228 UNKNOWN, // FE6C..FE6F
7229 ARABIC, // FE70..FE74
7230 UNKNOWN, // FE75
7231 ARABIC, // FE76..FEFC
7232 UNKNOWN, // FEFD..FEFE
7233 COMMON, // FEFF
7234 UNKNOWN, // FF00
7235 COMMON, // FF01..FF20
7236 LATIN, // FF21..FF3A
7237 COMMON, // FF3B..FF40
7238 LATIN, // FF41..FF5A
7239 COMMON, // FF5B..FF65
7240 KATAKANA, // FF66..FF6F
7241 COMMON, // FF70
7242 KATAKANA, // FF71..FF9D
7243 COMMON, // FF9E..FF9F
7244 HANGUL, // FFA0..FFBE
7245 UNKNOWN, // FFBF..FFC1
7246 HANGUL, // FFC2..FFC7
7247 UNKNOWN, // FFC8..FFC9
7248 HANGUL, // FFCA..FFCF
7249 UNKNOWN, // FFD0..FFD1
7250 HANGUL, // FFD2..FFD7
7251 UNKNOWN, // FFD8..FFD9
7252 HANGUL, // FFDA..FFDC
7253 UNKNOWN, // FFDD..FFDF
7254 COMMON, // FFE0..FFE6
7255 UNKNOWN, // FFE7
7256 COMMON, // FFE8..FFEE
7257 UNKNOWN, // FFEF..FFF8
7258 COMMON, // FFF9..FFFD
7259 UNKNOWN, // FFFE..FFFF
7260 LINEAR_B, // 10000..1000B
7261 UNKNOWN, // 1000C
7262 LINEAR_B, // 1000D..10026
7263 UNKNOWN, // 10027
7264 LINEAR_B, // 10028..1003A
7265 UNKNOWN, // 1003B
7266 LINEAR_B, // 1003C..1003D
7267 UNKNOWN, // 1003E
7268 LINEAR_B, // 1003F..1004D
7269 UNKNOWN, // 1004E..1004F
7270 LINEAR_B, // 10050..1005D
7271 UNKNOWN, // 1005E..1007F
7272 LINEAR_B, // 10080..100FA
7273 UNKNOWN, // 100FB..100FF
7274 COMMON, // 10100..10102
7275 UNKNOWN, // 10103..10106
7276 COMMON, // 10107..10133
7277 UNKNOWN, // 10134..10136
7278 COMMON, // 10137..1013F
7279 GREEK, // 10140..1018E
7280 UNKNOWN, // 1018F
7281 COMMON, // 10190..1019B
7282 UNKNOWN, // 1019C..1019F
7283 GREEK, // 101A0
7284 UNKNOWN, // 101A1..101CF
7285 COMMON, // 101D0..101FC
7286 INHERITED, // 101FD
7287 UNKNOWN, // 101FE..1027F
7288 LYCIAN, // 10280..1029C
7289 UNKNOWN, // 1029D..1029F
7290 CARIAN, // 102A0..102D0
7291 UNKNOWN, // 102D1..102DF
7292 INHERITED, // 102E0
7293 COMMON, // 102E1..102FB
7294 UNKNOWN, // 102FC..102FF
7295 OLD_ITALIC, // 10300..10323
7296 UNKNOWN, // 10324..1032C
7297 OLD_ITALIC, // 1032D..1032F
7298 GOTHIC, // 10330..1034A
7299 UNKNOWN, // 1034B..1034F
7300 OLD_PERMIC, // 10350..1037A
7301 UNKNOWN, // 1037B..1037F
7302 UGARITIC, // 10380..1039D
7303 UNKNOWN, // 1039E
7304 UGARITIC, // 1039F
7305 OLD_PERSIAN, // 103A0..103C3
7306 UNKNOWN, // 103C4..103C7
7307 OLD_PERSIAN, // 103C8..103D5
7308 UNKNOWN, // 103D6..103FF
7309 DESERET, // 10400..1044F
7310 SHAVIAN, // 10450..1047F
7311 OSMANYA, // 10480..1049D
7312 UNKNOWN, // 1049E..1049F
7313 OSMANYA, // 104A0..104A9
7314 UNKNOWN, // 104AA..104AF
7315 OSAGE, // 104B0..104D3;
7316 UNKNOWN, // 104D4..104D7;
7317 OSAGE, // 104D8..104FB;
7318 UNKNOWN, // 104FC..104FF;
7319 ELBASAN, // 10500..10527
7320 UNKNOWN, // 10528..1052F
7321 CAUCASIAN_ALBANIAN, // 10530..10563
7322 UNKNOWN, // 10564..1056E
7323 CAUCASIAN_ALBANIAN, // 1056F
7324 UNKNOWN, // 10570..105FF
7325 LINEAR_A, // 10600..10736
7326 UNKNOWN, // 10737..1073F
7327 LINEAR_A, // 10740..10755
7328 UNKNOWN, // 10756..1075F
7329 LINEAR_A, // 10760..10767
7330 UNKNOWN, // 10768..107FF
7331 CYPRIOT, // 10800..10805
7332 UNKNOWN, // 10806..10807
7333 CYPRIOT, // 10808
7334 UNKNOWN, // 10809
7335 CYPRIOT, // 1080A..10835
7336 UNKNOWN, // 10836
7337 CYPRIOT, // 10837..10838
7338 UNKNOWN, // 10839..1083B
7339 CYPRIOT, // 1083C
7340 UNKNOWN, // 1083D..1083E
7341 CYPRIOT, // 1083F
7342 IMPERIAL_ARAMAIC, // 10840..10855
7343 UNKNOWN, // 10856
7344 IMPERIAL_ARAMAIC, // 10857..1085F
7345 PALMYRENE, // 10860..1087F
7346 NABATAEAN, // 10880..1089E
7347 UNKNOWN, // 1089F..108A6
7348 NABATAEAN, // 108A7..108AF
7349 UNKNOWN, // 108B0..108DF
7350 HATRAN, // 108E0..108F2
7351 UNKNOWN, // 108F3
7352 HATRAN, // 108F4..108F5
7353 UNKNOWN, // 108F6..108FA
7354 HATRAN, // 108FB..108FF
7355 PHOENICIAN, // 10900..1091B
7356 UNKNOWN, // 1091C..1091E
7357 PHOENICIAN, // 1091F
7358 LYDIAN, // 10920..10939
7359 UNKNOWN, // 1093A..1093E
7360 LYDIAN, // 1093F
7361 UNKNOWN, // 10940..1097F
7362 MEROITIC_HIEROGLYPHS, // 10980..1099F
7363 MEROITIC_CURSIVE, // 109A0..109B7
7364 UNKNOWN, // 109B8..109BB
7365 MEROITIC_CURSIVE, // 109BC..109CF
7366 UNKNOWN, // 109D0..109D1
7367 MEROITIC_CURSIVE, // 109D2..109FF
7368 KHAROSHTHI, // 10A00..10A03
7369 UNKNOWN, // 10A04
7370 KHAROSHTHI, // 10A05..10A06
7371 UNKNOWN, // 10A07..10A0B
7372 KHAROSHTHI, // 10A0C..10A13
7373 UNKNOWN, // 10A14
7374 KHAROSHTHI, // 10A15..10A17
7375 UNKNOWN, // 10A18
7376 KHAROSHTHI, // 10A19..10A35
7377 UNKNOWN, // 10A36..10A37
7378 KHAROSHTHI, // 10A38..10A3A
7379 UNKNOWN, // 10A3B..10A3E
7380 KHAROSHTHI, // 10A3F..10A48
7381 UNKNOWN, // 10A49..10A4F
7382 KHAROSHTHI, // 10A50..10A58
7383 UNKNOWN, // 10A59..10A5F
7384 OLD_SOUTH_ARABIAN, // 10A60..10A7F
7385 OLD_NORTH_ARABIAN, // 10A80..10A9F
7386 UNKNOWN, // 10AA0..10ABF
7387 MANICHAEAN, // 10AC0..10AE6
7388 UNKNOWN, // 10AE7..10AEA
7389 MANICHAEAN, // 10AEB..10AF6
7390 UNKNOWN, // 10AF7..10AFF
7391 AVESTAN, // 10B00..10B35
7392 UNKNOWN, // 10B36..10B38
7393 AVESTAN, // 10B39..10B3F
7394 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
7395 UNKNOWN, // 10B56..10B57
7396 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
7397 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
7398 UNKNOWN, // 10B73..10B77
7399 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
7400 PSALTER_PAHLAVI, // 10B80..10B91
7401 UNKNOWN, // 10B92..10B98
7402 PSALTER_PAHLAVI, // 10B99..10B9C
7403 UNKNOWN, // 10B9D..10BA8
7404 PSALTER_PAHLAVI, // 10BA9..10BAF
7405 UNKNOWN, // 10BB0..10BFF
7406 OLD_TURKIC, // 10C00..10C48
7407 UNKNOWN, // 10C49..10C7F
7408 OLD_HUNGARIAN, // 10C80..10CB2
7409 UNKNOWN, // 10CB3..10CBF
7410 OLD_HUNGARIAN, // 10CC0..10CF2
7411 UNKNOWN, // 10CF3..10CF9
7412 OLD_HUNGARIAN, // 10CFA..10CFF
7413 HANIFI_ROHINGYA, // 10D00..10D27
7414 UNKNOWN, // 10D28..10D29
7415 HANIFI_ROHINGYA, // 10D30..10D39
7416 UNKNOWN, // 10D3A..10E5F
7417 ARABIC, // 10E60..10E7E
7418 UNKNOWN, // 10E7F..10EFF
7419 OLD_SOGDIAN, // 10F00..10F27
7420 UNKNOWN, // 10F28..10F2F
7421 SOGDIAN, // 10F30..10F59
7422 UNKNOWN, // 10F5A..10FFF
7423 BRAHMI, // 11000..1104D
7424 UNKNOWN, // 1104E..11051
7425 BRAHMI, // 11052..1106F
7426 UNKNOWN, // 11070..1107E
7427 BRAHMI, // 1107F
7428 KAITHI, // 11080..110C1
7429 UNKNOWN, // 110C2..110CC
7430 KAITHI, // 110CD
7431 UNKNOWN, // 110CE..110CF
7432 SORA_SOMPENG, // 110D0..110E8
7433 UNKNOWN, // 110E9..110EF
7434 SORA_SOMPENG, // 110F0..110F9
7435 UNKNOWN, // 110FA..110FF
7436 CHAKMA, // 11100..11134
7437 UNKNOWN, // 11135
7438 CHAKMA, // 11136..11146
7439 UNKNOWN, // 11147..1114F
7440 MAHAJANI, // 11150..11176
7441 UNKNOWN, // 11177..1117F
7442 SHARADA, // 11180..111CD
7443 UNKNOWN, // 111CE..111CF
7444 SHARADA, // 111D0..111DF
7445 UNKNOWN, // 111E0
7446 SINHALA, // 111E1..111F4
7447 UNKNOWN, // 111F5..111FF
7448 KHOJKI, // 11200..11211
7449 UNKNOWN, // 11212
7450 KHOJKI, // 11213..1123E
7451 UNKNOWN, // 1123F..1127F
7452 MULTANI, // 11280..11286
7453 UNKNOWN, // 11287
7454 MULTANI, // 11288
7455 UNKNOWN, // 11289
7456 MULTANI, // 1128A..1128D
7457 UNKNOWN, // 1128E
7458 MULTANI, // 1128F..1129D
7459 UNKNOWN, // 1129E
7460 MULTANI, // 1129F..112A9
7461 UNKNOWN, // 112AA..112AF
7462 KHUDAWADI, // 112B0..112EA
7463 UNKNOWN, // 112EB..112EF
7464 KHUDAWADI, // 112F0..112F9
7465 UNKNOWN, // 112FA..112FF
7466 GRANTHA, // 11300..11303
7467 UNKNOWN, // 11304
7468 GRANTHA, // 11305..1130C
7469 UNKNOWN, // 1130D..1130E
7470 GRANTHA, // 1130F..11310
7471 UNKNOWN, // 11311..11312
7472 GRANTHA, // 11313..11328
7473 UNKNOWN, // 11329
7474 GRANTHA, // 1132A..11330
7475 UNKNOWN, // 11331
7476 GRANTHA, // 11332..11333
7477 UNKNOWN, // 11334
7478 GRANTHA, // 11335..11339
7479 UNKNOWN, // 1133A
7480 INHERITED, // 1133B
7481 GRANTHA, // 1133C..11344
7482 UNKNOWN, // 11345..11346
7483 GRANTHA, // 11347..11348
7484 UNKNOWN, // 11349..1134A
7485 GRANTHA, // 1134B..1134D
7486 UNKNOWN, // 1134E..1134F
7487 GRANTHA, // 11350
7488 UNKNOWN, // 11351..11356
7489 GRANTHA, // 11357
7490 UNKNOWN, // 11358..1135C
7491 GRANTHA, // 1135D..11363
7492 UNKNOWN, // 11364..11365
7493 GRANTHA, // 11366..1136C
7494 UNKNOWN, // 1136D..1136F
7495 GRANTHA, // 11370..11374
7496 UNKNOWN, // 11375..113FF
7497 NEWA, // 11400..11459
7498 UNKNOWN, // 1145A
7499 NEWA, // 1145B
7500 UNKNOWN, // 1145C
7501 NEWA, // 1145D..1145E
7502 UNKNOWN, // 1145F..1147F
7503 TIRHUTA, // 11480..114C7
7504 UNKNOWN, // 114C8..114CF
7505 TIRHUTA, // 114D0..114D9
7506 UNKNOWN, // 114DA..1157F
7507 SIDDHAM, // 11580..115B5
7508 UNKNOWN, // 115B6..115B7
7509 SIDDHAM, // 115B8..115DD
7510 UNKNOWN, // 115DE..115FF
7511 MODI, // 11600..11644
7512 UNKNOWN, // 11645..1164F
7513 MODI, // 11650..11659
7514 UNKNOWN, // 1165A..1165F
7515 MONGOLIAN, // 11660..1166C
7516 UNKNOWN, // 1166D..1167F
7517 TAKRI, // 11680..116B7
7518 UNKNOWN, // 116B8..116BF
7519 TAKRI, // 116C0..116C9
7520 UNKNOWN, // 116CA..116FF
7521 AHOM, // 11700..1171A
7522 UNKNOWN, // 1171B..1171C
7523 AHOM, // 1171D..1172B
7524 UNKNOWN, // 1172C..1172F
7525 AHOM, // 11730..1173F
7526 UNKNOWN, // 11740..117FF
7527 DOGRA, // 11800..1183B
7528 UNKNOWN, // 1183C..1189F
7529 WARANG_CITI, // 118A0..118F2
7530 UNKNOWN, // 118F3..118FE
7531 WARANG_CITI, // 118FF
7532 UNKNOWN, // 11900..119FF
7533 ZANABAZAR_SQUARE, // 11A00..11A47
7534 UNKNOWN, // 11A48..11A4F
7535 SOYOMBO, // 11A50..11A83
7536 UNKNOWN, // 11A84..11A85
7537 SOYOMBO, // 11A86..11AA2
7538 UNKNOWN, // 11AA3..11ABF
7539 PAU_CIN_HAU, // 11AC0..11AF8
7540 UNKNOWN, // 11AF9..11BFF
7541 BHAIKSUKI, // 11C00..11C08
7542 UNKNOWN, // 11C09
7543 BHAIKSUKI, // 11C0A..11C36
7544 UNKNOWN, // 11C37
7545 BHAIKSUKI, // 11C38..11C45
7546 UNKNOWN, // 11C46..11C49
7547 BHAIKSUKI, // 11C50..11C6C
7548 UNKNOWN, // 11C6D..11C6F
7549 MARCHEN, // 11C70..11C8F
7550 UNKNOWN, // 11C90..11C91
7551 MARCHEN, // 11C92..11CA7
7552 UNKNOWN, // 11CA8
7553 MARCHEN, // 11CA9..11CB6
7554 UNKNOWN, // 11CB7..11CFF
7555 MASARAM_GONDI, // 11D00..11D06
7556 UNKNOWN, // 11D07
7557 MASARAM_GONDI, // 11D08..11D09
7558 UNKNOWN, // 11D0A
7559 MASARAM_GONDI, // 11D0B..11D36
7560 UNKNOWN, // 11D37..11D39
7561 MASARAM_GONDI, // 11D3A
7562 UNKNOWN, // 11D3B
7563 MASARAM_GONDI, // 11D3C..11D3D
7564 UNKNOWN, // 11D3E
7565 MASARAM_GONDI, // 11D3F..11D47
7566 UNKNOWN, // 11D48..11D49
7567 MASARAM_GONDI, // 11D50..11D59
7568 UNKNOWN, // 11D5A..11D5F
7569 GUNJALA_GONDI, // 11D60..11D68
7570 UNKNOWN, // 11D69
7571 GUNJALA_GONDI, // 11D6A..11D8E
7572 UNKNOWN, // 11D8F
7573 GUNJALA_GONDI, // 11D90..11D91
7574 UNKNOWN, // 11D92
7575 GUNJALA_GONDI, // 11D93..11D98
7576 UNKNOWN, // 11D99
7577 GUNJALA_GONDI, // 11DA0..11DA9
7578 UNKNOWN, // 11DAA..11DFF
7579 MAKASAR, // 11EE0..11EF8
7580 UNKNOWN, // 11EF9..11FFF
7581 CUNEIFORM, // 12000..12399
7582 UNKNOWN, // 1239A..123FF
7583 CUNEIFORM, // 12400..1246E
7584 UNKNOWN, // 1246F
7585 CUNEIFORM, // 12470..12474
7586 UNKNOWN, // 12475..1247F
7587 CUNEIFORM, // 12480..12543
7588 UNKNOWN, // 12544..12FFF
7589 EGYPTIAN_HIEROGLYPHS, // 13000..1342E
7590 UNKNOWN, // 1342F..143FF
7591 ANATOLIAN_HIEROGLYPHS, // 14400..14646
7592 UNKNOWN, // 14647..167FF
7593 BAMUM, // 16800..16A38
7594 UNKNOWN, // 16A39..16A3F
7595 MRO, // 16A40..16A5E
7596 UNKNOWN, // 16A5F
7597 MRO, // 16A60..16A69
7598 UNKNOWN, // 16A6A..16A6D
7599 MRO, // 16A6E..16A6F
7600 UNKNOWN, // 16A70..16ACF
7601 BASSA_VAH, // 16AD0..16AED
7602 UNKNOWN, // 16AEE..16AEF
7603 BASSA_VAH, // 16AF0..16AF5
7604 UNKNOWN, // 16AF6..16AFF
7605 PAHAWH_HMONG, // 16B00..16B45
7606 UNKNOWN, // 16B46..16B4F
7607 PAHAWH_HMONG, // 16B50..16B59
7608 UNKNOWN, // 16B5A
7609 PAHAWH_HMONG, // 16B5B..16B61
7610 UNKNOWN, // 16B62
7611 PAHAWH_HMONG, // 16B63..16B77
7612 UNKNOWN, // 16B78..16B7C
7613 PAHAWH_HMONG, // 16B7D..16B8F
7614 UNKNOWN, // 16B90..16E3F
7615 MEDEFAIDRIN, // 16E40..16E9A
7616 UNKNOWN, // 16E9B..16EFF
7617 MIAO, // 16F00..16F44
7618 UNKNOWN, // 16F45..16F4F
7619 MIAO, // 16F50..16F7E
7620 UNKNOWN, // 16F7F..16F8E
7621 MIAO, // 16F8F..16F9F
7622 UNKNOWN, // 16FA0..16FDF
7623 TANGUT, // 16FE0
7624 NUSHU, // 16FE1
7625 UNKNOWN, // 16FE2..16FFF
7626 TANGUT, // 17000..187F1
7627 UNKNOWN, // 187F2..187FF
7628 TANGUT, // 18800..18AF2
7629 UNKNOWN, // 18AF3..1AFFF
7630 KATAKANA, // 1B000
7631 HIRAGANA, // 1B001..1B11E
7632 UNKNOWN, // 1B11F..1B16F
7633 NUSHU, // 1B170..1B2FB
7634 UNKNOWN, // 1B2FC..1BBFF
7635 DUPLOYAN, // 1BC00..1BC6A
7636 UNKNOWN, // 1BC6B..1BC6F
7637 DUPLOYAN, // 1BC70..1BC7C
7638 UNKNOWN, // 1BC7D..1BC7F
7639 DUPLOYAN, // 1BC80..1BC88
7640 UNKNOWN, // 1BC89..1BC8F
7641 DUPLOYAN, // 1BC90..1BC99
7642 UNKNOWN, // 1BC9A..1BC9B
7643 DUPLOYAN, // 1BC9C..1BC9F
7644 COMMON, // 1BCA0..1BCA3
7645 UNKNOWN, // 1BCA4..1CFFF
7646 COMMON, // 1D000..1D0F5
7647 UNKNOWN, // 1D0F6..1D0FF
7648 COMMON, // 1D100..1D126
7649 UNKNOWN, // 1D127..1D128
7650 COMMON, // 1D129..1D166
7651 INHERITED, // 1D167..1D169
7652 COMMON, // 1D16A..1D17A
7653 INHERITED, // 1D17B..1D182
7654 COMMON, // 1D183..1D184
7655 INHERITED, // 1D185..1D18B
7656 COMMON, // 1D18C..1D1A9
7657 INHERITED, // 1D1AA..1D1AD
7658 COMMON, // 1D1AE..1D1E8
7659 UNKNOWN, // 1D1E9..1D1FF
7660 GREEK, // 1D200..1D245
7661 UNKNOWN, // 1D246..1D2DF
7662 COMMON, // 1D2E0..1D2F3
7663 UNKNOWN, // 1D2F4..1D2FF
7664 COMMON, // 1D300..1D356
7665 UNKNOWN, // 1D357..1D35F
7666 COMMON, // 1D360..1D378
7667 UNKNOWN, // 1D379..1D3FF
7668 COMMON, // 1D400..1D454
7669 UNKNOWN, // 1D455
7670 COMMON, // 1D456..1D49C
7671 UNKNOWN, // 1D49D
7672 COMMON, // 1D49E..1D49F
7673 UNKNOWN, // 1D4A0..1D4A1
7674 COMMON, // 1D4A2
7675 UNKNOWN, // 1D4A3..1D4A4
7676 COMMON, // 1D4A5..1D4A6
7677 UNKNOWN, // 1D4A7..1D4A8
7678 COMMON, // 1D4A9..1D4AC
7679 UNKNOWN, // 1D4AD
7680 COMMON, // 1D4AE..1D4B9
7681 UNKNOWN, // 1D4BA
7682 COMMON, // 1D4BB
7683 UNKNOWN, // 1D4BC
7684 COMMON, // 1D4BD..1D4C3
7685 UNKNOWN, // 1D4C4
7686 COMMON, // 1D4C5..1D505
7687 UNKNOWN, // 1D506
7688 COMMON, // 1D507..1D50A
7689 UNKNOWN, // 1D50B..1D50C
7690 COMMON, // 1D50D..1D514
7691 UNKNOWN, // 1D515
7692 COMMON, // 1D516..1D51C
7693 UNKNOWN, // 1D51D
7694 COMMON, // 1D51E..1D539
7695 UNKNOWN, // 1D53A
7696 COMMON, // 1D53B..1D53E
7697 UNKNOWN, // 1D53F
7698 COMMON, // 1D540..1D544
7699 UNKNOWN, // 1D545
7700 COMMON, // 1D546
7701 UNKNOWN, // 1D547..1D549
7702 COMMON, // 1D54A..1D550
7703 UNKNOWN, // 1D551
7704 COMMON, // 1D552..1D6A5
7705 UNKNOWN, // 1D6A6..1D6A7
7706 COMMON, // 1D6A8..1D7CB
7707 UNKNOWN, // 1D7CC..1D7CD
7708 COMMON, // 1D7CE..1D7FF
7709 SIGNWRITING, // 1D800..1DA8B
7710 UNKNOWN, // 1DA8C..1DA9A
7711 SIGNWRITING, // 1DA9B..1DA9F
7712 UNKNOWN, // 1DAA0
7713 SIGNWRITING, // 1DAA1..1DAAF
7714 UNKNOWN, // 1DAB0..1DFFF
7715 GLAGOLITIC, // 1E000..1E006
7716 UNKNOWN, // 1E007
7717 GLAGOLITIC, // 1E008..1E018
7718 UNKNOWN, // 1E019..1E01A
7719 GLAGOLITIC, // 1E01B..1E021
7720 UNKNOWN, // 1E022
7721 GLAGOLITIC, // 1E023..1E024
7722 UNKNOWN, // 1E025
7723 GLAGOLITIC, // 1E026..1E02A
7724 UNKNOWN, // 1E02B..1E7FF
7725 MENDE_KIKAKUI, // 1E800..1E8C4
7726 UNKNOWN, // 1E8C5..1E8C6
7727 MENDE_KIKAKUI, // 1E8C7..1E8D6
7728 UNKNOWN, // 1E8D7..1E8FF
7729 ADLAM, // 1E900..1E94A
7730 UNKNOWN, // 1E94B..1E94F
7731 ADLAM, // 1E950..1E959
7732 UNKNOWN, // 1E95A..1E95D
7733 ADLAM, // 1E95E..1E95F
7734 UNKNOWN, // 1E960..1EC70
7735 COMMON, // 1EC71..1ECB4
7736 UNKNOWN, // 1ECB5..1EDFF
7737 ARABIC, // 1EE00..1EE03
7738 UNKNOWN, // 1EE04
7739 ARABIC, // 1EE05..1EE1F
7740 UNKNOWN, // 1EE20
7741 ARABIC, // 1EE21..1EE22
7742 UNKNOWN, // 1EE23
7743 ARABIC, // 1EE24
7744 UNKNOWN, // 1EE25..1EE26
7745 ARABIC, // 1EE27
7746 UNKNOWN, // 1EE28
7747 ARABIC, // 1EE29..1EE32
7748 UNKNOWN, // 1EE33
7749 ARABIC, // 1EE34..1EE37
7750 UNKNOWN, // 1EE38
7751 ARABIC, // 1EE39
7752 UNKNOWN, // 1EE3A
7753 ARABIC, // 1EE3B
7754 UNKNOWN, // 1EE3C..1EE41
7755 ARABIC, // 1EE42
7756 UNKNOWN, // 1EE43..1EE46
7757 ARABIC, // 1EE47
7758 UNKNOWN, // 1EE48
7759 ARABIC, // 1EE49
7760 UNKNOWN, // 1EE4A
7761 ARABIC, // 1EE4B
7762 UNKNOWN, // 1EE4C
7763 ARABIC, // 1EE4D..1EE4F
7764 UNKNOWN, // 1EE50
7765 ARABIC, // 1EE51..1EE52
7766 UNKNOWN, // 1EE53
7767 ARABIC, // 1EE54
7768 UNKNOWN, // 1EE55..1EE56
7769 ARABIC, // 1EE57
7770 UNKNOWN, // 1EE58
7771 ARABIC, // 1EE59
7772 UNKNOWN, // 1EE5A
7773 ARABIC, // 1EE5B
7774 UNKNOWN, // 1EE5C
7775 ARABIC, // 1EE5D
7776 UNKNOWN, // 1EE5E
7777 ARABIC, // 1EE5F
7778 UNKNOWN, // 1EE60
7779 ARABIC, // 1EE61..1EE62
7780 UNKNOWN, // 1EE63
7781 ARABIC, // 1EE64
7782 UNKNOWN, // 1EE65..1EE66
7783 ARABIC, // 1EE67..1EE6A
7784 UNKNOWN, // 1EE6B
7785 ARABIC, // 1EE6C..1EE72
7786 UNKNOWN, // 1EE73
7787 ARABIC, // 1EE74..1EE77
7788 UNKNOWN, // 1EE78
7789 ARABIC, // 1EE79..1EE7C
7790 UNKNOWN, // 1EE7D
7791 ARABIC, // 1EE7E
7792 UNKNOWN, // 1EE7F
7793 ARABIC, // 1EE80..1EE89
7794 UNKNOWN, // 1EE8A
7795 ARABIC, // 1EE8B..1EE9B
7796 UNKNOWN, // 1EE9C..1EEA0
7797 ARABIC, // 1EEA1..1EEA3
7798 UNKNOWN, // 1EEA4
7799 ARABIC, // 1EEA5..1EEA9
7800 UNKNOWN, // 1EEAA
7801 ARABIC, // 1EEAB..1EEBB
7802 UNKNOWN, // 1EEBC..1EEEF
7803 ARABIC, // 1EEF0..1EEF1
7804 UNKNOWN, // 1EEF2..1EFFF
7805 COMMON, // 1F000..1F02B
7806 UNKNOWN, // 1F02C..1F02F
7807 COMMON, // 1F030..1F093
7808 UNKNOWN, // 1F094..1F09F
7809 COMMON, // 1F0A0..1F0AE
7810 UNKNOWN, // 1F0AF..1F0B0
7811 COMMON, // 1F0B1..1F0BF
7812 UNKNOWN, // 1F0C0
7813 COMMON, // 1F0C1..1F0CF
7814 UNKNOWN, // 1F0D0
7815 COMMON, // 1F0D1..1F0F5
7816 UNKNOWN, // 1F0F6..1F0FF
7817 COMMON, // 1F100..1F10C
7818 UNKNOWN, // 1F10D..1F10F
7819 COMMON, // 1F110..1F16B
7820 UNKNOWN, // 1F16C..1F16F
7821 COMMON, // 1F170..1F1AC
7822 UNKNOWN, // 1F1AD..1F1E5
7823 COMMON, // 1F1E6..1F1FF
7824 HIRAGANA, // 1F200
7825 COMMON, // 1F201..1F202
7826 UNKNOWN, // 1F203..1F20F
7827 COMMON, // 1F210..1F23B
7828 UNKNOWN, // 1F23C..1F23F
7829 COMMON, // 1F240..1F248
7830 UNKNOWN, // 1F249..1F24F
7831 COMMON, // 1F250..1F251
7832 UNKNOWN, // 1F252..1F25F
7833 COMMON, // 1F260..1F265
7834 UNKNOWN, // 1F266..1F2FF
7835 COMMON, // 1F300..1F6D4
7836 UNKNOWN, // 1F6D5..1F6DF
7837 COMMON, // 1F6E0..1F6EC
7838 UNKNOWN, // 1F6ED..1F6EF
7839 COMMON, // 1F6F0..1F6F9
7840 UNKNOWN, // 1F6FA..1F6FF
7841 COMMON, // 1F700..1F773
7842 UNKNOWN, // 1F774..1F77F
7843 COMMON, // 1F780..1F7D8
7844 UNKNOWN, // 1F7D9..1F7FF
7845 COMMON, // 1F800..1F80B
7846 UNKNOWN, // 1F80C..1F80F
7847 COMMON, // 1F810..1F847
7848 UNKNOWN, // 1F848..1F84F
7849 COMMON, // 1F850..1F859
7850 UNKNOWN, // 1F85A..1F85F
7851 COMMON, // 1F860..1F887
7852 UNKNOWN, // 1F888..1F88F
7853 COMMON, // 1F890..1F8AD
7854 UNKNOWN, // 1F8AE..1F8FF
7855 COMMON, // 1F900..1F90B
7856 UNKNOWN, // 1F90C..1F90F
7857 COMMON, // 1F910..1F93E
7858 UNKNOWN, // 1F93F
7859 COMMON, // 1F940..1F970
7860 UNKNOWN, // 1F971..1F972
7861 COMMON, // 1F973..1F976
7862 UNKNOWN, // 1F977..1F979
7863 COMMON, // 1F97A
7864 UNKNOWN, // 1F97B
7865 COMMON, // 1F97C..1F9A2
7866 UNKNOWN, // 1F9A3..1F9AF
7867 COMMON, // 1F9B0..1F9B9
7868 UNKNOWN, // 1F9BA..1F9BF
7869 COMMON, // 1F9C0..1F9C2
7870 UNKNOWN, // 1F9C3..1F9CF
7871 COMMON, // 1F9D0..1F9FF
7872 UNKNOWN, // 1FA00..1FA5F
7873 COMMON, // 1FA60..1FA6D
7874 UNKNOWN, // 1FA6E..1FFFF
7875 HAN, // 20000..2A6D6
7876 UNKNOWN, // 2A6D7..2A6FF
7877 HAN, // 2A700..2B734
7878 UNKNOWN, // 2B735..2B73F
7879 HAN, // 2B740..2B81D
7880 UNKNOWN, // 2B81E..2B81F
7881 HAN, // 2B820..2CEA1
7882 UNKNOWN, // 2CEA2..2CEAF
7883 HAN, // 2CEB0..2EBE0
7884 UNKNOWN, // 2EBE1..2F7FF
7885 HAN, // 2F800..2FA1D
7886 UNKNOWN, // 2FA1E..E0000
7887 COMMON, // E0001
7888 UNKNOWN, // E0002..E001F
7889 COMMON, // E0020..E007F
7890 UNKNOWN, // E0080..E00FF
7891 INHERITED, // E0100..E01EF
7892 UNKNOWN // E01F0..10FFFF
7893 };
7894
7895 private static HashMap<String, Character.UnicodeScript> aliases;
7896 static {
7897 aliases = new HashMap<>((int)(149 / 0.75f + 1.0f));
7898 aliases.put("ADLM", ADLAM);
7899 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
7900 aliases.put("AHOM", AHOM);
7901 aliases.put("ARAB", ARABIC);
7902 aliases.put("ARMI", IMPERIAL_ARAMAIC);
7903 aliases.put("ARMN", ARMENIAN);
7904 aliases.put("AVST", AVESTAN);
7905 aliases.put("BALI", BALINESE);
7906 aliases.put("BAMU", BAMUM);
7907 aliases.put("BASS", BASSA_VAH);
7908 aliases.put("BATK", BATAK);
7909 aliases.put("BENG", BENGALI);
7910 aliases.put("BHKS", BHAIKSUKI);
7911 aliases.put("BOPO", BOPOMOFO);
7912 aliases.put("BRAH", BRAHMI);
7913 aliases.put("BRAI", BRAILLE);
7914 aliases.put("BUGI", BUGINESE);
7915 aliases.put("BUHD", BUHID);
7916 aliases.put("CAKM", CHAKMA);
7917 aliases.put("CANS", CANADIAN_ABORIGINAL);
7918 aliases.put("CARI", CARIAN);
7919 aliases.put("CHAM", CHAM);
7920 aliases.put("CHER", CHEROKEE);
7921 aliases.put("COPT", COPTIC);
7922 aliases.put("CPRT", CYPRIOT);
7923 aliases.put("CYRL", CYRILLIC);
7924 aliases.put("DEVA", DEVANAGARI);
7925 aliases.put("DOGR", DOGRA);
7926 aliases.put("DSRT", DESERET);
7927 aliases.put("DUPL", DUPLOYAN);
7928 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
7929 aliases.put("ELBA", ELBASAN);
7930 aliases.put("ETHI", ETHIOPIC);
7931 aliases.put("GEOR", GEORGIAN);
7932 aliases.put("GLAG", GLAGOLITIC);
7933 aliases.put("GONM", MASARAM_GONDI);
7934 aliases.put("GOTH", GOTHIC);
7935 aliases.put("GONG", GUNJALA_GONDI);
7936 aliases.put("GRAN", GRANTHA);
7937 aliases.put("GREK", GREEK);
7938 aliases.put("GUJR", GUJARATI);
7939 aliases.put("GURU", GURMUKHI);
7940 aliases.put("HANG", HANGUL);
7941 aliases.put("HANI", HAN);
7942 aliases.put("HANO", HANUNOO);
7943 aliases.put("HATR", HATRAN);
7944 aliases.put("HEBR", HEBREW);
7945 aliases.put("HIRA", HIRAGANA);
7946 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
7947 aliases.put("HMNG", PAHAWH_HMONG);
7948 // it appears we don't have the KATAKANA_OR_HIRAGANA
7949 //aliases.put("HRKT", KATAKANA_OR_HIRAGANA);
7950 aliases.put("HUNG", OLD_HUNGARIAN);
7951 aliases.put("ITAL", OLD_ITALIC);
7952 aliases.put("JAVA", JAVANESE);
7953 aliases.put("KALI", KAYAH_LI);
7954 aliases.put("KANA", KATAKANA);
7955 aliases.put("KHAR", KHAROSHTHI);
7956 aliases.put("KHMR", KHMER);
7957 aliases.put("KHOJ", KHOJKI);
7958 aliases.put("KNDA", KANNADA);
7959 aliases.put("KTHI", KAITHI);
7960 aliases.put("LANA", TAI_THAM);
7961 aliases.put("LAOO", LAO);
7962 aliases.put("LATN", LATIN);
7963 aliases.put("LEPC", LEPCHA);
7964 aliases.put("LIMB", LIMBU);
7965 aliases.put("LINA", LINEAR_A);
7966 aliases.put("LINB", LINEAR_B);
7967 aliases.put("LISU", LISU);
7968 aliases.put("LYCI", LYCIAN);
7969 aliases.put("LYDI", LYDIAN);
7970 aliases.put("MAHJ", MAHAJANI);
7971 aliases.put("MAKA", MAKASAR);
7972 aliases.put("MARC", MARCHEN);
7973 aliases.put("MAND", MANDAIC);
7974 aliases.put("MANI", MANICHAEAN);
7975 aliases.put("MEDF", MEDEFAIDRIN);
7976 aliases.put("MEND", MENDE_KIKAKUI);
7977 aliases.put("MERC", MEROITIC_CURSIVE);
7978 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
7979 aliases.put("MLYM", MALAYALAM);
7980 aliases.put("MODI", MODI);
7981 aliases.put("MONG", MONGOLIAN);
7982 aliases.put("MROO", MRO);
7983 aliases.put("MTEI", MEETEI_MAYEK);
7984 aliases.put("MULT", MULTANI);
7985 aliases.put("MYMR", MYANMAR);
7986 aliases.put("NARB", OLD_NORTH_ARABIAN);
7987 aliases.put("NBAT", NABATAEAN);
7988 aliases.put("NEWA", NEWA);
7989 aliases.put("NKOO", NKO);
7990 aliases.put("NSHU", NUSHU);
7991 aliases.put("OGAM", OGHAM);
7992 aliases.put("OLCK", OL_CHIKI);
7993 aliases.put("ORKH", OLD_TURKIC);
7994 aliases.put("ORYA", ORIYA);
7995 aliases.put("OSGE", OSAGE);
7996 aliases.put("OSMA", OSMANYA);
7997 aliases.put("PALM", PALMYRENE);
7998 aliases.put("PAUC", PAU_CIN_HAU);
7999 aliases.put("PERM", OLD_PERMIC);
8000 aliases.put("PHAG", PHAGS_PA);
8001 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
8002 aliases.put("PHLP", PSALTER_PAHLAVI);
8003 aliases.put("PHNX", PHOENICIAN);
8004 aliases.put("PLRD", MIAO);
8005 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
8006 aliases.put("RJNG", REJANG);
8007 aliases.put("ROHG", HANIFI_ROHINGYA);
8008 aliases.put("RUNR", RUNIC);
8009 aliases.put("SAMR", SAMARITAN);
8010 aliases.put("SARB", OLD_SOUTH_ARABIAN);
8011 aliases.put("SAUR", SAURASHTRA);
8012 aliases.put("SGNW", SIGNWRITING);
8013 aliases.put("SHAW", SHAVIAN);
8014 aliases.put("SHRD", SHARADA);
8015 aliases.put("SIDD", SIDDHAM);
8016 aliases.put("SIND", KHUDAWADI);
8017 aliases.put("SINH", SINHALA);
8018 aliases.put("SOGD", SOGDIAN);
8019 aliases.put("SOGO", OLD_SOGDIAN);
8020 aliases.put("SORA", SORA_SOMPENG);
8021 aliases.put("SOYO", SOYOMBO);
8022 aliases.put("SUND", SUNDANESE);
8023 aliases.put("SYLO", SYLOTI_NAGRI);
8024 aliases.put("SYRC", SYRIAC);
8025 aliases.put("TAGB", TAGBANWA);
8026 aliases.put("TAKR", TAKRI);
8027 aliases.put("TALE", TAI_LE);
8028 aliases.put("TALU", NEW_TAI_LUE);
8029 aliases.put("TAML", TAMIL);
8030 aliases.put("TANG", TANGUT);
8031 aliases.put("TAVT", TAI_VIET);
8032 aliases.put("TELU", TELUGU);
8033 aliases.put("TFNG", TIFINAGH);
8034 aliases.put("TGLG", TAGALOG);
8035 aliases.put("THAA", THAANA);
8036 aliases.put("THAI", THAI);
8037 aliases.put("TIBT", TIBETAN);
8038 aliases.put("TIRH", TIRHUTA);
8039 aliases.put("UGAR", UGARITIC);
8040 aliases.put("VAII", VAI);
8041 aliases.put("WARA", WARANG_CITI);
8042 aliases.put("XPEO", OLD_PERSIAN);
8043 aliases.put("XSUX", CUNEIFORM);
8044 aliases.put("YIII", YI);
8045 aliases.put("ZANB", ZANABAZAR_SQUARE);
8046 aliases.put("ZINH", INHERITED);
8047 aliases.put("ZYYY", COMMON);
8048 aliases.put("ZZZZ", UNKNOWN);
8049 }
8050
8051 /**
8052 * Returns the enum constant representing the Unicode script of which
8053 * the given character (Unicode code point) is assigned to.
8054 *
8055 * @param codePoint the character (Unicode code point) in question.
8056 * @return The {@code UnicodeScript} constant representing the
8057 * Unicode script of which this character is assigned to.
8058 *
8059 * @throws IllegalArgumentException if the specified
8060 * {@code codePoint} is an invalid Unicode code point.
8061 * @see Character#isValidCodePoint(int)
8062 *
8063 */
8064 public static UnicodeScript of(int codePoint) {
8065 if (!isValidCodePoint(codePoint))
8066 throw new IllegalArgumentException(
8067 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8068 int type = getType(codePoint);
8069 // leave SURROGATE and PRIVATE_USE for table lookup
8070 if (type == UNASSIGNED)
8071 return UNKNOWN;
8072 int index = Arrays.binarySearch(scriptStarts, codePoint);
8073 if (index < 0)
8074 index = -index - 2;
8075 return scripts[index];
8076 }
8077
8078 /**
8079 * Returns the UnicodeScript constant with the given Unicode script
8080 * name or the script name alias. Script names and their aliases are
8081 * determined by The Unicode Standard. The files {@code Scripts<version>.txt}
8082 * and {@code PropertyValueAliases<version>.txt} define script names
8083 * and the script name aliases for a particular version of the
8084 * standard. The {@link Character} class specifies the version of
8085 * the standard that it supports.
8086 * <p>
8087 * Character case is ignored for all of the valid script names.
8088 * The en_US locale's case mapping rules are used to provide
8089 * case-insensitive string comparisons for script name validation.
8090 *
8091 * @param scriptName A {@code UnicodeScript} name.
8092 * @return The {@code UnicodeScript} constant identified
8093 * by {@code scriptName}
8094 * @throws IllegalArgumentException if {@code scriptName} is an
8095 * invalid name
8096 * @throws NullPointerException if {@code scriptName} is null
8097 */
8098 public static final UnicodeScript forName(String scriptName) {
8099 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
8100 //.replace(' ', '_'));
8101 UnicodeScript sc = aliases.get(scriptName);
8102 if (sc != null)
8103 return sc;
8104 return valueOf(scriptName);
8105 }
8106 }
8107
8108 /**
8109 * The value of the {@code Character}.
8110 *
8111 * @serial
8112 */
8113 private final char value;
8114
8115 /** use serialVersionUID from JDK 1.0.2 for interoperability */
8116 private static final long serialVersionUID = 3786198910865385080L;
8117
8118 /**
8119 * Constructs a newly allocated {@code Character} object that
8120 * represents the specified {@code char} value.
8121 *
8122 * @param value the value to be represented by the
8123 * {@code Character} object.
8124 *
8125 * @deprecated
8126 * It is rarely appropriate to use this constructor. The static factory
8127 * {@link #valueOf(char)} is generally a better choice, as it is
8128 * likely to yield significantly better space and time performance.
8129 */
8130 @Deprecated(since="9")
8131 public Character(char value) {
8132 this.value = value;
8133 }
8134
8135 private static class CharacterCache {
8136 private CharacterCache(){}
8137
8138 static final Character[] cache;
8139 static Character[] archivedCache;
8140
8141 static {
8142 int size = 127 + 1;
8143
8144 // Load and use the archived cache if it exists
8145 VM.initializeFromArchive(CharacterCache.class);
8146 if (archivedCache == null || archivedCache.length != size) {
8147 Character[] c = new Character[size];
8148 for (int i = 0; i < size; i++) {
8149 c[i] = new Character((char) i);
8150 }
8151 archivedCache = c;
8152 }
8153 cache = archivedCache;
8154 }
8155 }
8156
8157 /**
8158 * Returns a {@code Character} instance representing the specified
8159 * {@code char} value.
8160 * If a new {@code Character} instance is not required, this method
8161 * should generally be used in preference to the constructor
8162 * {@link #Character(char)}, as this method is likely to yield
8163 * significantly better space and time performance by caching
8164 * frequently requested values.
8165 *
8166 * This method will always cache values in the range {@code
8167 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
8168 * cache other values outside of this range.
8169 *
8170 * @param c a char value.
8171 * @return a {@code Character} instance representing {@code c}.
8172 * @since 1.5
8173 */
8174 @HotSpotIntrinsicCandidate
8175 public static Character valueOf(char c) {
8176 if (c <= 127) { // must cache
8177 return CharacterCache.cache[(int)c];
8178 }
8179 return new Character(c);
8180 }
8181
8182 /**
8183 * Returns the value of this {@code Character} object.
8184 * @return the primitive {@code char} value represented by
8185 * this object.
8186 */
8187 @HotSpotIntrinsicCandidate
8188 public char charValue() {
8189 return value;
8190 }
8191
8192 /**
8193 * Returns a hash code for this {@code Character}; equal to the result
8194 * of invoking {@code charValue()}.
8195 *
8196 * @return a hash code value for this {@code Character}
8197 */
8198 @Override
8199 public int hashCode() {
8200 return Character.hashCode(value);
8201 }
8202
8203 /**
8204 * Returns a hash code for a {@code char} value; compatible with
8205 * {@code Character.hashCode()}.
8206 *
8207 * @since 1.8
8208 *
8209 * @param value The {@code char} for which to return a hash code.
8210 * @return a hash code value for a {@code char} value.
8211 */
8212 public static int hashCode(char value) {
8213 return (int)value;
8214 }
8215
8216 /**
8217 * Compares this object against the specified object.
8218 * The result is {@code true} if and only if the argument is not
8219 * {@code null} and is a {@code Character} object that
8220 * represents the same {@code char} value as this object.
8221 *
8222 * @param obj the object to compare with.
8223 * @return {@code true} if the objects are the same;
8224 * {@code false} otherwise.
8225 */
8226 public boolean equals(Object obj) {
8227 if (obj instanceof Character) {
8228 return value == ((Character)obj).charValue();
8229 }
8230 return false;
8231 }
8232
8233 /**
8234 * Returns a {@code String} object representing this
8235 * {@code Character}'s value. The result is a string of
8236 * length 1 whose sole component is the primitive
8237 * {@code char} value represented by this
8238 * {@code Character} object.
8239 *
8240 * @return a string representation of this object.
8241 */
8242 public String toString() {
8243 char buf[] = {value};
8244 return String.valueOf(buf);
8245 }
8246
8247 /**
8248 * Returns a {@code String} object representing the
8249 * specified {@code char}. The result is a string of length
8250 * 1 consisting solely of the specified {@code char}.
8251 *
8252 * @apiNote This method cannot handle <a
8253 * href="#supplementary"> supplementary characters</a>. To support
8254 * all Unicode characters, including supplementary characters, use
8255 * the {@link #toString(int)} method.
8256 *
8257 * @param c the {@code char} to be converted
8258 * @return the string representation of the specified {@code char}
8259 * @since 1.4
8260 */
8261 public static String toString(char c) {
8262 return String.valueOf(c);
8263 }
8264
8265 /**
8266 * Returns a {@code String} object representing the
8267 * specified character (Unicode code point). The result is a string of
8268 * length 1 or 2, consisting solely of the specified {@code codePoint}.
8269 *
8270 * @param codePoint the {@code codePoint} to be converted
8271 * @return the string representation of the specified {@code codePoint}
8272 * @throws IllegalArgumentException if the specified
8273 * {@code codePoint} is not a {@linkplain #isValidCodePoint
8274 * valid Unicode code point}.
8275 * @since 11
8276 */
8277 public static String toString(int codePoint) {
8278 return String.valueOfCodePoint(codePoint);
8279 }
8280
8281 /**
8282 * Determines whether the specified code point is a valid
8283 * <a href="http://www.unicode.org/glossary/#code_point">
8284 * Unicode code point value</a>.
8285 *
8286 * @param codePoint the Unicode code point to be tested
8287 * @return {@code true} if the specified code point value is between
8288 * {@link #MIN_CODE_POINT} and
8289 * {@link #MAX_CODE_POINT} inclusive;
8290 * {@code false} otherwise.
8291 * @since 1.5
8292 */
8293 public static boolean isValidCodePoint(int codePoint) {
8294 // Optimized form of:
8295 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
8296 int plane = codePoint >>> 16;
8297 return plane < ((MAX_CODE_POINT + 1) >>> 16);
8298 }
8299
8300 /**
8301 * Determines whether the specified character (Unicode code point)
8302 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
8303 * Such code points can be represented using a single {@code char}.
8304 *
8305 * @param codePoint the character (Unicode code point) to be tested
8306 * @return {@code true} if the specified code point is between
8307 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
8308 * {@code false} otherwise.
8309 * @since 1.7
8310 */
8311 public static boolean isBmpCodePoint(int codePoint) {
8312 return codePoint >>> 16 == 0;
8313 // Optimized form of:
8314 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
8315 // We consistently use logical shift (>>>) to facilitate
8316 // additional runtime optimizations.
8317 }
8318
8319 /**
8320 * Determines whether the specified character (Unicode code point)
8321 * is in the <a href="#supplementary">supplementary character</a> range.
8322 *
8323 * @param codePoint the character (Unicode code point) to be tested
8324 * @return {@code true} if the specified code point is between
8325 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
8326 * {@link #MAX_CODE_POINT} inclusive;
8327 * {@code false} otherwise.
8328 * @since 1.5
8329 */
8330 public static boolean isSupplementaryCodePoint(int codePoint) {
8331 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
8332 && codePoint < MAX_CODE_POINT + 1;
8333 }
8334
8335 /**
8336 * Determines if the given {@code char} value is a
8337 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
8338 * Unicode high-surrogate code unit</a>
8339 * (also known as <i>leading-surrogate code unit</i>).
8340 *
8341 * <p>Such values do not represent characters by themselves,
8342 * but are used in the representation of
8343 * <a href="#supplementary">supplementary characters</a>
8344 * in the UTF-16 encoding.
8345 *
8346 * @param ch the {@code char} value to be tested.
8347 * @return {@code true} if the {@code char} value is between
8348 * {@link #MIN_HIGH_SURROGATE} and
8349 * {@link #MAX_HIGH_SURROGATE} inclusive;
8350 * {@code false} otherwise.
8351 * @see Character#isLowSurrogate(char)
8352 * @see Character.UnicodeBlock#of(int)
8353 * @since 1.5
8354 */
8355 public static boolean isHighSurrogate(char ch) {
8356 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
8357 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
8358 }
8359
8360 /**
8361 * Determines if the given {@code char} value is a
8362 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
8363 * Unicode low-surrogate code unit</a>
8364 * (also known as <i>trailing-surrogate code unit</i>).
8365 *
8366 * <p>Such values do not represent characters by themselves,
8367 * but are used in the representation of
8368 * <a href="#supplementary">supplementary characters</a>
8369 * in the UTF-16 encoding.
8370 *
8371 * @param ch the {@code char} value to be tested.
8372 * @return {@code true} if the {@code char} value is between
8373 * {@link #MIN_LOW_SURROGATE} and
8374 * {@link #MAX_LOW_SURROGATE} inclusive;
8375 * {@code false} otherwise.
8376 * @see Character#isHighSurrogate(char)
8377 * @since 1.5
8378 */
8379 public static boolean isLowSurrogate(char ch) {
8380 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
8381 }
8382
8383 /**
8384 * Determines if the given {@code char} value is a Unicode
8385 * <i>surrogate code unit</i>.
8386 *
8387 * <p>Such values do not represent characters by themselves,
8388 * but are used in the representation of
8389 * <a href="#supplementary">supplementary characters</a>
8390 * in the UTF-16 encoding.
8391 *
8392 * <p>A char value is a surrogate code unit if and only if it is either
8393 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
8394 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
8395 *
8396 * @param ch the {@code char} value to be tested.
8397 * @return {@code true} if the {@code char} value is between
8398 * {@link #MIN_SURROGATE} and
8399 * {@link #MAX_SURROGATE} inclusive;
8400 * {@code false} otherwise.
8401 * @since 1.7
8402 */
8403 public static boolean isSurrogate(char ch) {
8404 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
8405 }
8406
8407 /**
8408 * Determines whether the specified pair of {@code char}
8409 * values is a valid
8410 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8411 * Unicode surrogate pair</a>.
8412
8413 * <p>This method is equivalent to the expression:
8414 * <blockquote><pre>{@code
8415 * isHighSurrogate(high) && isLowSurrogate(low)
8416 * }</pre></blockquote>
8417 *
8418 * @param high the high-surrogate code value to be tested
8419 * @param low the low-surrogate code value to be tested
8420 * @return {@code true} if the specified high and
8421 * low-surrogate code values represent a valid surrogate pair;
8422 * {@code false} otherwise.
8423 * @since 1.5
8424 */
8425 public static boolean isSurrogatePair(char high, char low) {
8426 return isHighSurrogate(high) && isLowSurrogate(low);
8427 }
8428
8429 /**
8430 * Determines the number of {@code char} values needed to
8431 * represent the specified character (Unicode code point). If the
8432 * specified character is equal to or greater than 0x10000, then
8433 * the method returns 2. Otherwise, the method returns 1.
8434 *
8435 * <p>This method doesn't validate the specified character to be a
8436 * valid Unicode code point. The caller must validate the
8437 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
8438 * if necessary.
8439 *
8440 * @param codePoint the character (Unicode code point) to be tested.
8441 * @return 2 if the character is a valid supplementary character; 1 otherwise.
8442 * @see Character#isSupplementaryCodePoint(int)
8443 * @since 1.5
8444 */
8445 public static int charCount(int codePoint) {
8446 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
8447 }
8448
8449 /**
8450 * Converts the specified surrogate pair to its supplementary code
8451 * point value. This method does not validate the specified
8452 * surrogate pair. The caller must validate it using {@link
8453 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
8454 *
8455 * @param high the high-surrogate code unit
8456 * @param low the low-surrogate code unit
8457 * @return the supplementary code point composed from the
8458 * specified surrogate pair.
8459 * @since 1.5
8460 */
8461 public static int toCodePoint(char high, char low) {
8462 // Optimized form of:
8463 // return ((high - MIN_HIGH_SURROGATE) << 10)
8464 // + (low - MIN_LOW_SURROGATE)
8465 // + MIN_SUPPLEMENTARY_CODE_POINT;
8466 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
8467 - (MIN_HIGH_SURROGATE << 10)
8468 - MIN_LOW_SURROGATE);
8469 }
8470
8471 /**
8472 * Returns the code point at the given index of the
8473 * {@code CharSequence}. If the {@code char} value at
8474 * the given index in the {@code CharSequence} is in the
8475 * high-surrogate range, the following index is less than the
8476 * length of the {@code CharSequence}, and the
8477 * {@code char} value at the following index is in the
8478 * low-surrogate range, then the supplementary code point
8479 * corresponding to this surrogate pair is returned. Otherwise,
8480 * the {@code char} value at the given index is returned.
8481 *
8482 * @param seq a sequence of {@code char} values (Unicode code
8483 * units)
8484 * @param index the index to the {@code char} values (Unicode
8485 * code units) in {@code seq} to be converted
8486 * @return the Unicode code point at the given index
8487 * @throws NullPointerException if {@code seq} is null.
8488 * @throws IndexOutOfBoundsException if the value
8489 * {@code index} is negative or not less than
8490 * {@link CharSequence#length() seq.length()}.
8491 * @since 1.5
8492 */
8493 public static int codePointAt(CharSequence seq, int index) {
8494 char c1 = seq.charAt(index);
8495 if (isHighSurrogate(c1) && ++index < seq.length()) {
8496 char c2 = seq.charAt(index);
8497 if (isLowSurrogate(c2)) {
8498 return toCodePoint(c1, c2);
8499 }
8500 }
8501 return c1;
8502 }
8503
8504 /**
8505 * Returns the code point at the given index of the
8506 * {@code char} array. If the {@code char} value at
8507 * the given index in the {@code char} array is in the
8508 * high-surrogate range, the following index is less than the
8509 * length of the {@code char} array, and the
8510 * {@code char} value at the following index is in the
8511 * low-surrogate range, then the supplementary code point
8512 * corresponding to this surrogate pair is returned. Otherwise,
8513 * the {@code char} value at the given index is returned.
8514 *
8515 * @param a the {@code char} array
8516 * @param index the index to the {@code char} values (Unicode
8517 * code units) in the {@code char} array to be converted
8518 * @return the Unicode code point at the given index
8519 * @throws NullPointerException if {@code a} is null.
8520 * @throws IndexOutOfBoundsException if the value
8521 * {@code index} is negative or not less than
8522 * the length of the {@code char} array.
8523 * @since 1.5
8524 */
8525 public static int codePointAt(char[] a, int index) {
8526 return codePointAtImpl(a, index, a.length);
8527 }
8528
8529 /**
8530 * Returns the code point at the given index of the
8531 * {@code char} array, where only array elements with
8532 * {@code index} less than {@code limit} can be used. If
8533 * the {@code char} value at the given index in the
8534 * {@code char} array is in the high-surrogate range, the
8535 * following index is less than the {@code limit}, and the
8536 * {@code char} value at the following index is in the
8537 * low-surrogate range, then the supplementary code point
8538 * corresponding to this surrogate pair is returned. Otherwise,
8539 * the {@code char} value at the given index is returned.
8540 *
8541 * @param a the {@code char} array
8542 * @param index the index to the {@code char} values (Unicode
8543 * code units) in the {@code char} array to be converted
8544 * @param limit the index after the last array element that
8545 * can be used in the {@code char} array
8546 * @return the Unicode code point at the given index
8547 * @throws NullPointerException if {@code a} is null.
8548 * @throws IndexOutOfBoundsException if the {@code index}
8549 * argument is negative or not less than the {@code limit}
8550 * argument, or if the {@code limit} argument is negative or
8551 * greater than the length of the {@code char} array.
8552 * @since 1.5
8553 */
8554 public static int codePointAt(char[] a, int index, int limit) {
8555 if (index >= limit || limit < 0 || limit > a.length) {
8556 throw new IndexOutOfBoundsException();
8557 }
8558 return codePointAtImpl(a, index, limit);
8559 }
8560
8561 // throws ArrayIndexOutOfBoundsException if index out of bounds
8562 static int codePointAtImpl(char[] a, int index, int limit) {
8563 char c1 = a[index];
8564 if (isHighSurrogate(c1) && ++index < limit) {
8565 char c2 = a[index];
8566 if (isLowSurrogate(c2)) {
8567 return toCodePoint(c1, c2);
8568 }
8569 }
8570 return c1;
8571 }
8572
8573 /**
8574 * Returns the code point preceding the given index of the
8575 * {@code CharSequence}. If the {@code char} value at
8576 * {@code (index - 1)} in the {@code CharSequence} is in
8577 * the low-surrogate range, {@code (index - 2)} is not
8578 * negative, and the {@code char} value at {@code (index - 2)}
8579 * in the {@code CharSequence} is in the
8580 * high-surrogate range, then the supplementary code point
8581 * corresponding to this surrogate pair is returned. Otherwise,
8582 * the {@code char} value at {@code (index - 1)} is
8583 * returned.
8584 *
8585 * @param seq the {@code CharSequence} instance
8586 * @param index the index following the code point that should be returned
8587 * @return the Unicode code point value before the given index.
8588 * @throws NullPointerException if {@code seq} is null.
8589 * @throws IndexOutOfBoundsException if the {@code index}
8590 * argument is less than 1 or greater than {@link
8591 * CharSequence#length() seq.length()}.
8592 * @since 1.5
8593 */
8594 public static int codePointBefore(CharSequence seq, int index) {
8595 char c2 = seq.charAt(--index);
8596 if (isLowSurrogate(c2) && index > 0) {
8597 char c1 = seq.charAt(--index);
8598 if (isHighSurrogate(c1)) {
8599 return toCodePoint(c1, c2);
8600 }
8601 }
8602 return c2;
8603 }
8604
8605 /**
8606 * Returns the code point preceding the given index of the
8607 * {@code char} array. If the {@code char} value at
8608 * {@code (index - 1)} in the {@code char} array is in
8609 * the low-surrogate range, {@code (index - 2)} is not
8610 * negative, and the {@code char} value at {@code (index - 2)}
8611 * in the {@code char} array is in the
8612 * high-surrogate range, then the supplementary code point
8613 * corresponding to this surrogate pair is returned. Otherwise,
8614 * the {@code char} value at {@code (index - 1)} is
8615 * returned.
8616 *
8617 * @param a the {@code char} array
8618 * @param index the index following the code point that should be returned
8619 * @return the Unicode code point value before the given index.
8620 * @throws NullPointerException if {@code a} is null.
8621 * @throws IndexOutOfBoundsException if the {@code index}
8622 * argument is less than 1 or greater than the length of the
8623 * {@code char} array
8624 * @since 1.5
8625 */
8626 public static int codePointBefore(char[] a, int index) {
8627 return codePointBeforeImpl(a, index, 0);
8628 }
8629
8630 /**
8631 * Returns the code point preceding the given index of the
8632 * {@code char} array, where only array elements with
8633 * {@code index} greater than or equal to {@code start}
8634 * can be used. If the {@code char} value at {@code (index - 1)}
8635 * in the {@code char} array is in the
8636 * low-surrogate range, {@code (index - 2)} is not less than
8637 * {@code start}, and the {@code char} value at
8638 * {@code (index - 2)} in the {@code char} array is in
8639 * the high-surrogate range, then the supplementary code point
8640 * corresponding to this surrogate pair is returned. Otherwise,
8641 * the {@code char} value at {@code (index - 1)} is
8642 * returned.
8643 *
8644 * @param a the {@code char} array
8645 * @param index the index following the code point that should be returned
8646 * @param start the index of the first array element in the
8647 * {@code char} array
8648 * @return the Unicode code point value before the given index.
8649 * @throws NullPointerException if {@code a} is null.
8650 * @throws IndexOutOfBoundsException if the {@code index}
8651 * argument is not greater than the {@code start} argument or
8652 * is greater than the length of the {@code char} array, or
8653 * if the {@code start} argument is negative or not less than
8654 * the length of the {@code char} array.
8655 * @since 1.5
8656 */
8657 public static int codePointBefore(char[] a, int index, int start) {
8658 if (index <= start || start < 0 || start >= a.length) {
8659 throw new IndexOutOfBoundsException();
8660 }
8661 return codePointBeforeImpl(a, index, start);
8662 }
8663
8664 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
8665 static int codePointBeforeImpl(char[] a, int index, int start) {
8666 char c2 = a[--index];
8667 if (isLowSurrogate(c2) && index > start) {
8668 char c1 = a[--index];
8669 if (isHighSurrogate(c1)) {
8670 return toCodePoint(c1, c2);
8671 }
8672 }
8673 return c2;
8674 }
8675
8676 /**
8677 * Returns the leading surrogate (a
8678 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
8679 * high surrogate code unit</a>) of the
8680 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8681 * surrogate pair</a>
8682 * representing the specified supplementary character (Unicode
8683 * code point) in the UTF-16 encoding. If the specified character
8684 * is not a
8685 * <a href="Character.html#supplementary">supplementary character</a>,
8686 * an unspecified {@code char} is returned.
8687 *
8688 * <p>If
8689 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
8690 * is {@code true}, then
8691 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
8692 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
8693 * are also always {@code true}.
8694 *
8695 * @param codePoint a supplementary character (Unicode code point)
8696 * @return the leading surrogate code unit used to represent the
8697 * character in the UTF-16 encoding
8698 * @since 1.7
8699 */
8700 public static char highSurrogate(int codePoint) {
8701 return (char) ((codePoint >>> 10)
8702 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
8703 }
8704
8705 /**
8706 * Returns the trailing surrogate (a
8707 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
8708 * low surrogate code unit</a>) of the
8709 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8710 * surrogate pair</a>
8711 * representing the specified supplementary character (Unicode
8712 * code point) in the UTF-16 encoding. If the specified character
8713 * is not a
8714 * <a href="Character.html#supplementary">supplementary character</a>,
8715 * an unspecified {@code char} is returned.
8716 *
8717 * <p>If
8718 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
8719 * is {@code true}, then
8720 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
8721 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
8722 * are also always {@code true}.
8723 *
8724 * @param codePoint a supplementary character (Unicode code point)
8725 * @return the trailing surrogate code unit used to represent the
8726 * character in the UTF-16 encoding
8727 * @since 1.7
8728 */
8729 public static char lowSurrogate(int codePoint) {
8730 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
8731 }
8732
8733 /**
8734 * Converts the specified character (Unicode code point) to its
8735 * UTF-16 representation. If the specified code point is a BMP
8736 * (Basic Multilingual Plane or Plane 0) value, the same value is
8737 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
8738 * specified code point is a supplementary character, its
8739 * surrogate values are stored in {@code dst[dstIndex]}
8740 * (high-surrogate) and {@code dst[dstIndex+1]}
8741 * (low-surrogate), and 2 is returned.
8742 *
8743 * @param codePoint the character (Unicode code point) to be converted.
8744 * @param dst an array of {@code char} in which the
8745 * {@code codePoint}'s UTF-16 value is stored.
8746 * @param dstIndex the start index into the {@code dst}
8747 * array where the converted value is stored.
8748 * @return 1 if the code point is a BMP code point, 2 if the
8749 * code point is a supplementary code point.
8750 * @throws IllegalArgumentException if the specified
8751 * {@code codePoint} is not a valid Unicode code point.
8752 * @throws NullPointerException if the specified {@code dst} is null.
8753 * @throws IndexOutOfBoundsException if {@code dstIndex}
8754 * is negative or not less than {@code dst.length}, or if
8755 * {@code dst} at {@code dstIndex} doesn't have enough
8756 * array element(s) to store the resulting {@code char}
8757 * value(s). (If {@code dstIndex} is equal to
8758 * {@code dst.length-1} and the specified
8759 * {@code codePoint} is a supplementary character, the
8760 * high-surrogate value is not stored in
8761 * {@code dst[dstIndex]}.)
8762 * @since 1.5
8763 */
8764 public static int toChars(int codePoint, char[] dst, int dstIndex) {
8765 if (isBmpCodePoint(codePoint)) {
8766 dst[dstIndex] = (char) codePoint;
8767 return 1;
8768 } else if (isValidCodePoint(codePoint)) {
8769 toSurrogates(codePoint, dst, dstIndex);
8770 return 2;
8771 } else {
8772 throw new IllegalArgumentException(
8773 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8774 }
8775 }
8776
8777 /**
8778 * Converts the specified character (Unicode code point) to its
8779 * UTF-16 representation stored in a {@code char} array. If
8780 * the specified code point is a BMP (Basic Multilingual Plane or
8781 * Plane 0) value, the resulting {@code char} array has
8782 * the same value as {@code codePoint}. If the specified code
8783 * point is a supplementary code point, the resulting
8784 * {@code char} array has the corresponding surrogate pair.
8785 *
8786 * @param codePoint a Unicode code point
8787 * @return a {@code char} array having
8788 * {@code codePoint}'s UTF-16 representation.
8789 * @throws IllegalArgumentException if the specified
8790 * {@code codePoint} is not a valid Unicode code point.
8791 * @since 1.5
8792 */
8793 public static char[] toChars(int codePoint) {
8794 if (isBmpCodePoint(codePoint)) {
8795 return new char[] { (char) codePoint };
8796 } else if (isValidCodePoint(codePoint)) {
8797 char[] result = new char[2];
8798 toSurrogates(codePoint, result, 0);
8799 return result;
8800 } else {
8801 throw new IllegalArgumentException(
8802 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8803 }
8804 }
8805
8806 static void toSurrogates(int codePoint, char[] dst, int index) {
8807 // We write elements "backwards" to guarantee all-or-nothing
8808 dst[index+1] = lowSurrogate(codePoint);
8809 dst[index] = highSurrogate(codePoint);
8810 }
8811
8812 /**
8813 * Returns the number of Unicode code points in the text range of
8814 * the specified char sequence. The text range begins at the
8815 * specified {@code beginIndex} and extends to the
8816 * {@code char} at index {@code endIndex - 1}. Thus the
8817 * length (in {@code char}s) of the text range is
8818 * {@code endIndex-beginIndex}. Unpaired surrogates within
8819 * the text range count as one code point each.
8820 *
8821 * @param seq the char sequence
8822 * @param beginIndex the index to the first {@code char} of
8823 * the text range.
8824 * @param endIndex the index after the last {@code char} of
8825 * the text range.
8826 * @return the number of Unicode code points in the specified text
8827 * range
8828 * @throws NullPointerException if {@code seq} is null.
8829 * @throws IndexOutOfBoundsException if the
8830 * {@code beginIndex} is negative, or {@code endIndex}
8831 * is larger than the length of the given sequence, or
8832 * {@code beginIndex} is larger than {@code endIndex}.
8833 * @since 1.5
8834 */
8835 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
8836 int length = seq.length();
8837 if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) {
8838 throw new IndexOutOfBoundsException();
8839 }
8840 int n = endIndex - beginIndex;
8841 for (int i = beginIndex; i < endIndex; ) {
8842 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
8843 isLowSurrogate(seq.charAt(i))) {
8844 n--;
8845 i++;
8846 }
8847 }
8848 return n;
8849 }
8850
8851 /**
8852 * Returns the number of Unicode code points in a subarray of the
8853 * {@code char} array argument. The {@code offset}
8854 * argument is the index of the first {@code char} of the
8855 * subarray and the {@code count} argument specifies the
8856 * length of the subarray in {@code char}s. Unpaired
8857 * surrogates within the subarray count as one code point each.
8858 *
8859 * @param a the {@code char} array
8860 * @param offset the index of the first {@code char} in the
8861 * given {@code char} array
8862 * @param count the length of the subarray in {@code char}s
8863 * @return the number of Unicode code points in the specified subarray
8864 * @throws NullPointerException if {@code a} is null.
8865 * @throws IndexOutOfBoundsException if {@code offset} or
8866 * {@code count} is negative, or if {@code offset +
8867 * count} is larger than the length of the given array.
8868 * @since 1.5
8869 */
8870 public static int codePointCount(char[] a, int offset, int count) {
8871 if (count > a.length - offset || offset < 0 || count < 0) {
8872 throw new IndexOutOfBoundsException();
8873 }
8874 return codePointCountImpl(a, offset, count);
8875 }
8876
8877 static int codePointCountImpl(char[] a, int offset, int count) {
8878 int endIndex = offset + count;
8879 int n = count;
8880 for (int i = offset; i < endIndex; ) {
8881 if (isHighSurrogate(a[i++]) && i < endIndex &&
8882 isLowSurrogate(a[i])) {
8883 n--;
8884 i++;
8885 }
8886 }
8887 return n;
8888 }
8889
8890 /**
8891 * Returns the index within the given char sequence that is offset
8892 * from the given {@code index} by {@code codePointOffset}
8893 * code points. Unpaired surrogates within the text range given by
8894 * {@code index} and {@code codePointOffset} count as
8895 * one code point each.
8896 *
8897 * @param seq the char sequence
8898 * @param index the index to be offset
8899 * @param codePointOffset the offset in code points
8900 * @return the index within the char sequence
8901 * @throws NullPointerException if {@code seq} is null.
8902 * @throws IndexOutOfBoundsException if {@code index}
8903 * is negative or larger then the length of the char sequence,
8904 * or if {@code codePointOffset} is positive and the
8905 * subsequence starting with {@code index} has fewer than
8906 * {@code codePointOffset} code points, or if
8907 * {@code codePointOffset} is negative and the subsequence
8908 * before {@code index} has fewer than the absolute value
8909 * of {@code codePointOffset} code points.
8910 * @since 1.5
8911 */
8912 public static int offsetByCodePoints(CharSequence seq, int index,
8913 int codePointOffset) {
8914 int length = seq.length();
8915 if (index < 0 || index > length) {
8916 throw new IndexOutOfBoundsException();
8917 }
8918
8919 int x = index;
8920 if (codePointOffset >= 0) {
8921 int i;
8922 for (i = 0; x < length && i < codePointOffset; i++) {
8923 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
8924 isLowSurrogate(seq.charAt(x))) {
8925 x++;
8926 }
8927 }
8928 if (i < codePointOffset) {
8929 throw new IndexOutOfBoundsException();
8930 }
8931 } else {
8932 int i;
8933 for (i = codePointOffset; x > 0 && i < 0; i++) {
8934 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
8935 isHighSurrogate(seq.charAt(x-1))) {
8936 x--;
8937 }
8938 }
8939 if (i < 0) {
8940 throw new IndexOutOfBoundsException();
8941 }
8942 }
8943 return x;
8944 }
8945
8946 /**
8947 * Returns the index within the given {@code char} subarray
8948 * that is offset from the given {@code index} by
8949 * {@code codePointOffset} code points. The
8950 * {@code start} and {@code count} arguments specify a
8951 * subarray of the {@code char} array. Unpaired surrogates
8952 * within the text range given by {@code index} and
8953 * {@code codePointOffset} count as one code point each.
8954 *
8955 * @param a the {@code char} array
8956 * @param start the index of the first {@code char} of the
8957 * subarray
8958 * @param count the length of the subarray in {@code char}s
8959 * @param index the index to be offset
8960 * @param codePointOffset the offset in code points
8961 * @return the index within the subarray
8962 * @throws NullPointerException if {@code a} is null.
8963 * @throws IndexOutOfBoundsException
8964 * if {@code start} or {@code count} is negative,
8965 * or if {@code start + count} is larger than the length of
8966 * the given array,
8967 * or if {@code index} is less than {@code start} or
8968 * larger then {@code start + count},
8969 * or if {@code codePointOffset} is positive and the text range
8970 * starting with {@code index} and ending with {@code start + count - 1}
8971 * has fewer than {@code codePointOffset} code
8972 * points,
8973 * or if {@code codePointOffset} is negative and the text range
8974 * starting with {@code start} and ending with {@code index - 1}
8975 * has fewer than the absolute value of
8976 * {@code codePointOffset} code points.
8977 * @since 1.5
8978 */
8979 public static int offsetByCodePoints(char[] a, int start, int count,
8980 int index, int codePointOffset) {
8981 if (count > a.length-start || start < 0 || count < 0
8982 || index < start || index > start+count) {
8983 throw new IndexOutOfBoundsException();
8984 }
8985 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
8986 }
8987
8988 static int offsetByCodePointsImpl(char[]a, int start, int count,
8989 int index, int codePointOffset) {
8990 int x = index;
8991 if (codePointOffset >= 0) {
8992 int limit = start + count;
8993 int i;
8994 for (i = 0; x < limit && i < codePointOffset; i++) {
8995 if (isHighSurrogate(a[x++]) && x < limit &&
8996 isLowSurrogate(a[x])) {
8997 x++;
8998 }
8999 }
9000 if (i < codePointOffset) {
9001 throw new IndexOutOfBoundsException();
9002 }
9003 } else {
9004 int i;
9005 for (i = codePointOffset; x > start && i < 0; i++) {
9006 if (isLowSurrogate(a[--x]) && x > start &&
9007 isHighSurrogate(a[x-1])) {
9008 x--;
9009 }
9010 }
9011 if (i < 0) {
9012 throw new IndexOutOfBoundsException();
9013 }
9014 }
9015 return x;
9016 }
9017
9018 /**
9019 * Determines if the specified character is a lowercase character.
9020 * <p>
9021 * A character is lowercase if its general category type, provided
9022 * by {@code Character.getType(ch)}, is
9023 * {@code LOWERCASE_LETTER}, or it has contributory property
9024 * Other_Lowercase as defined by the Unicode Standard.
9025 * <p>
9026 * The following are examples of lowercase characters:
9027 * <blockquote><pre>
9028 * 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
9029 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9030 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9031 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9032 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9033 * </pre></blockquote>
9034 * <p> Many other Unicode characters are lowercase too.
9035 *
9036 * <p><b>Note:</b> This method cannot handle <a
9037 * href="#supplementary"> supplementary characters</a>. To support
9038 * all Unicode characters, including supplementary characters, use
9039 * the {@link #isLowerCase(int)} method.
9040 *
9041 * @param ch the character to be tested.
9042 * @return {@code true} if the character is lowercase;
9043 * {@code false} otherwise.
9044 * @see Character#isLowerCase(char)
9045 * @see Character#isTitleCase(char)
9046 * @see Character#toLowerCase(char)
9047 * @see Character#getType(char)
9048 */
9049 public static boolean isLowerCase(char ch) {
9050 return isLowerCase((int)ch);
9051 }
9052
9053 /**
9054 * Determines if the specified character (Unicode code point) is a
9055 * lowercase character.
9056 * <p>
9057 * A character is lowercase if its general category type, provided
9058 * by {@link Character#getType getType(codePoint)}, is
9059 * {@code LOWERCASE_LETTER}, or it has contributory property
9060 * Other_Lowercase as defined by the Unicode Standard.
9061 * <p>
9062 * The following are examples of lowercase characters:
9063 * <blockquote><pre>
9064 * 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
9065 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9066 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9067 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9068 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9069 * </pre></blockquote>
9070 * <p> Many other Unicode characters are lowercase too.
9071 *
9072 * @param codePoint the character (Unicode code point) to be tested.
9073 * @return {@code true} if the character is lowercase;
9074 * {@code false} otherwise.
9075 * @see Character#isLowerCase(int)
9076 * @see Character#isTitleCase(int)
9077 * @see Character#toLowerCase(int)
9078 * @see Character#getType(int)
9079 * @since 1.5
9080 */
9081 public static boolean isLowerCase(int codePoint) {
9082 return CharacterData.of(codePoint).isLowerCase(codePoint) ||
9083 CharacterData.of(codePoint).isOtherLowercase(codePoint);
9084 }
9085
9086 /**
9087 * Determines if the specified character is an uppercase character.
9088 * <p>
9089 * A character is uppercase if its general category type, provided by
9090 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
9091 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9092 * <p>
9093 * The following are examples of uppercase characters:
9094 * <blockquote><pre>
9095 * 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
9096 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9097 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9098 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9099 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9100 * </pre></blockquote>
9101 * <p> Many other Unicode characters are uppercase too.
9102 *
9103 * <p><b>Note:</b> This method cannot handle <a
9104 * href="#supplementary"> supplementary characters</a>. To support
9105 * all Unicode characters, including supplementary characters, use
9106 * the {@link #isUpperCase(int)} method.
9107 *
9108 * @param ch the character to be tested.
9109 * @return {@code true} if the character is uppercase;
9110 * {@code false} otherwise.
9111 * @see Character#isLowerCase(char)
9112 * @see Character#isTitleCase(char)
9113 * @see Character#toUpperCase(char)
9114 * @see Character#getType(char)
9115 * @since 1.0
9116 */
9117 public static boolean isUpperCase(char ch) {
9118 return isUpperCase((int)ch);
9119 }
9120
9121 /**
9122 * Determines if the specified character (Unicode code point) is an uppercase character.
9123 * <p>
9124 * A character is uppercase if its general category type, provided by
9125 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
9126 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9127 * <p>
9128 * The following are examples of uppercase characters:
9129 * <blockquote><pre>
9130 * 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
9131 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9132 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9133 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9134 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9135 * </pre></blockquote>
9136 * <p> Many other Unicode characters are uppercase too.
9137 *
9138 * @param codePoint the character (Unicode code point) to be tested.
9139 * @return {@code true} if the character is uppercase;
9140 * {@code false} otherwise.
9141 * @see Character#isLowerCase(int)
9142 * @see Character#isTitleCase(int)
9143 * @see Character#toUpperCase(int)
9144 * @see Character#getType(int)
9145 * @since 1.5
9146 */
9147 public static boolean isUpperCase(int codePoint) {
9148 return CharacterData.of(codePoint).isUpperCase(codePoint) ||
9149 CharacterData.of(codePoint).isOtherUppercase(codePoint);
9150 }
9151
9152 /**
9153 * Determines if the specified character is a titlecase character.
9154 * <p>
9155 * A character is a titlecase character if its general
9156 * category type, provided by {@code Character.getType(ch)},
9157 * is {@code TITLECASE_LETTER}.
9158 * <p>
9159 * Some characters look like pairs of Latin letters. For example, there
9160 * is an uppercase letter that looks like "LJ" and has a corresponding
9161 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
9162 * is the appropriate form to use when rendering a word in lowercase
9163 * with initial capitals, as for a book title.
9164 * <p>
9165 * These are some of the Unicode characters for which this method returns
9166 * {@code true}:
9167 * <ul>
9168 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
9169 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
9170 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
9171 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
9172 * </ul>
9173 * <p> Many other Unicode characters are titlecase too.
9174 *
9175 * <p><b>Note:</b> This method cannot handle <a
9176 * href="#supplementary"> supplementary characters</a>. To support
9177 * all Unicode characters, including supplementary characters, use
9178 * the {@link #isTitleCase(int)} method.
9179 *
9180 * @param ch the character to be tested.
9181 * @return {@code true} if the character is titlecase;
9182 * {@code false} otherwise.
9183 * @see Character#isLowerCase(char)
9184 * @see Character#isUpperCase(char)
9185 * @see Character#toTitleCase(char)
9186 * @see Character#getType(char)
9187 * @since 1.0.2
9188 */
9189 public static boolean isTitleCase(char ch) {
9190 return isTitleCase((int)ch);
9191 }
9192
9193 /**
9194 * Determines if the specified character (Unicode code point) is a titlecase character.
9195 * <p>
9196 * A character is a titlecase character if its general
9197 * category type, provided by {@link Character#getType(int) getType(codePoint)},
9198 * is {@code TITLECASE_LETTER}.
9199 * <p>
9200 * Some characters look like pairs of Latin letters. For example, there
9201 * is an uppercase letter that looks like "LJ" and has a corresponding
9202 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
9203 * is the appropriate form to use when rendering a word in lowercase
9204 * with initial capitals, as for a book title.
9205 * <p>
9206 * These are some of the Unicode characters for which this method returns
9207 * {@code true}:
9208 * <ul>
9209 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
9210 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
9211 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
9212 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
9213 * </ul>
9214 * <p> Many other Unicode characters are titlecase too.
9215 *
9216 * @param codePoint the character (Unicode code point) to be tested.
9217 * @return {@code true} if the character is titlecase;
9218 * {@code false} otherwise.
9219 * @see Character#isLowerCase(int)
9220 * @see Character#isUpperCase(int)
9221 * @see Character#toTitleCase(int)
9222 * @see Character#getType(int)
9223 * @since 1.5
9224 */
9225 public static boolean isTitleCase(int codePoint) {
9226 return getType(codePoint) == Character.TITLECASE_LETTER;
9227 }
9228
9229 /**
9230 * Determines if the specified character is a digit.
9231 * <p>
9232 * A character is a digit if its general category type, provided
9233 * by {@code Character.getType(ch)}, is
9234 * {@code DECIMAL_DIGIT_NUMBER}.
9235 * <p>
9236 * Some Unicode character ranges that contain digits:
9237 * <ul>
9238 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
9239 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
9240 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
9241 * Arabic-Indic digits
9242 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
9243 * Extended Arabic-Indic digits
9244 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
9245 * Devanagari digits
9246 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
9247 * Fullwidth digits
9248 * </ul>
9249 *
9250 * Many other character ranges contain digits as well.
9251 *
9252 * <p><b>Note:</b> This method cannot handle <a
9253 * href="#supplementary"> supplementary characters</a>. To support
9254 * all Unicode characters, including supplementary characters, use
9255 * the {@link #isDigit(int)} method.
9256 *
9257 * @param ch the character to be tested.
9258 * @return {@code true} if the character is a digit;
9259 * {@code false} otherwise.
9260 * @see Character#digit(char, int)
9261 * @see Character#forDigit(int, int)
9262 * @see Character#getType(char)
9263 */
9264 public static boolean isDigit(char ch) {
9265 return isDigit((int)ch);
9266 }
9267
9268 /**
9269 * Determines if the specified character (Unicode code point) is a digit.
9270 * <p>
9271 * A character is a digit if its general category type, provided
9272 * by {@link Character#getType(int) getType(codePoint)}, is
9273 * {@code DECIMAL_DIGIT_NUMBER}.
9274 * <p>
9275 * Some Unicode character ranges that contain digits:
9276 * <ul>
9277 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
9278 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
9279 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
9280 * Arabic-Indic digits
9281 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
9282 * Extended Arabic-Indic digits
9283 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
9284 * Devanagari digits
9285 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
9286 * Fullwidth digits
9287 * </ul>
9288 *
9289 * Many other character ranges contain digits as well.
9290 *
9291 * @param codePoint the character (Unicode code point) to be tested.
9292 * @return {@code true} if the character is a digit;
9293 * {@code false} otherwise.
9294 * @see Character#forDigit(int, int)
9295 * @see Character#getType(int)
9296 * @since 1.5
9297 */
9298 public static boolean isDigit(int codePoint) {
9299 return CharacterData.of(codePoint).isDigit(codePoint);
9300 }
9301
9302 /**
9303 * Determines if a character is defined in Unicode.
9304 * <p>
9305 * A character is defined if at least one of the following is true:
9306 * <ul>
9307 * <li>It has an entry in the UnicodeData file.
9308 * <li>It has a value in a range defined by the UnicodeData file.
9309 * </ul>
9310 *
9311 * <p><b>Note:</b> This method cannot handle <a
9312 * href="#supplementary"> supplementary characters</a>. To support
9313 * all Unicode characters, including supplementary characters, use
9314 * the {@link #isDefined(int)} method.
9315 *
9316 * @param ch the character to be tested
9317 * @return {@code true} if the character has a defined meaning
9318 * in Unicode; {@code false} otherwise.
9319 * @see Character#isDigit(char)
9320 * @see Character#isLetter(char)
9321 * @see Character#isLetterOrDigit(char)
9322 * @see Character#isLowerCase(char)
9323 * @see Character#isTitleCase(char)
9324 * @see Character#isUpperCase(char)
9325 * @since 1.0.2
9326 */
9327 public static boolean isDefined(char ch) {
9328 return isDefined((int)ch);
9329 }
9330
9331 /**
9332 * Determines if a character (Unicode code point) is defined in Unicode.
9333 * <p>
9334 * A character is defined if at least one of the following is true:
9335 * <ul>
9336 * <li>It has an entry in the UnicodeData file.
9337 * <li>It has a value in a range defined by the UnicodeData file.
9338 * </ul>
9339 *
9340 * @param codePoint the character (Unicode code point) to be tested.
9341 * @return {@code true} if the character has a defined meaning
9342 * in Unicode; {@code false} otherwise.
9343 * @see Character#isDigit(int)
9344 * @see Character#isLetter(int)
9345 * @see Character#isLetterOrDigit(int)
9346 * @see Character#isLowerCase(int)
9347 * @see Character#isTitleCase(int)
9348 * @see Character#isUpperCase(int)
9349 * @since 1.5
9350 */
9351 public static boolean isDefined(int codePoint) {
9352 return getType(codePoint) != Character.UNASSIGNED;
9353 }
9354
9355 /**
9356 * Determines if the specified character is a letter.
9357 * <p>
9358 * A character is considered to be a letter if its general
9359 * category type, provided by {@code Character.getType(ch)},
9360 * is any of the following:
9361 * <ul>
9362 * <li> {@code UPPERCASE_LETTER}
9363 * <li> {@code LOWERCASE_LETTER}
9364 * <li> {@code TITLECASE_LETTER}
9365 * <li> {@code MODIFIER_LETTER}
9366 * <li> {@code OTHER_LETTER}
9367 * </ul>
9368 *
9369 * Not all letters have case. Many characters are
9370 * letters but are neither uppercase nor lowercase nor titlecase.
9371 *
9372 * <p><b>Note:</b> This method cannot handle <a
9373 * href="#supplementary"> supplementary characters</a>. To support
9374 * all Unicode characters, including supplementary characters, use
9375 * the {@link #isLetter(int)} method.
9376 *
9377 * @param ch the character to be tested.
9378 * @return {@code true} if the character is a letter;
9379 * {@code false} otherwise.
9380 * @see Character#isDigit(char)
9381 * @see Character#isJavaIdentifierStart(char)
9382 * @see Character#isJavaLetter(char)
9383 * @see Character#isJavaLetterOrDigit(char)
9384 * @see Character#isLetterOrDigit(char)
9385 * @see Character#isLowerCase(char)
9386 * @see Character#isTitleCase(char)
9387 * @see Character#isUnicodeIdentifierStart(char)
9388 * @see Character#isUpperCase(char)
9389 */
9390 public static boolean isLetter(char ch) {
9391 return isLetter((int)ch);
9392 }
9393
9394 /**
9395 * Determines if the specified character (Unicode code point) is a letter.
9396 * <p>
9397 * A character is considered to be a letter if its general
9398 * category type, provided by {@link Character#getType(int) getType(codePoint)},
9399 * is any of the following:
9400 * <ul>
9401 * <li> {@code UPPERCASE_LETTER}
9402 * <li> {@code LOWERCASE_LETTER}
9403 * <li> {@code TITLECASE_LETTER}
9404 * <li> {@code MODIFIER_LETTER}
9405 * <li> {@code OTHER_LETTER}
9406 * </ul>
9407 *
9408 * Not all letters have case. Many characters are
9409 * letters but are neither uppercase nor lowercase nor titlecase.
9410 *
9411 * @param codePoint the character (Unicode code point) to be tested.
9412 * @return {@code true} if the character is a letter;
9413 * {@code false} otherwise.
9414 * @see Character#isDigit(int)
9415 * @see Character#isJavaIdentifierStart(int)
9416 * @see Character#isLetterOrDigit(int)
9417 * @see Character#isLowerCase(int)
9418 * @see Character#isTitleCase(int)
9419 * @see Character#isUnicodeIdentifierStart(int)
9420 * @see Character#isUpperCase(int)
9421 * @since 1.5
9422 */
9423 public static boolean isLetter(int codePoint) {
9424 return ((((1 << Character.UPPERCASE_LETTER) |
9425 (1 << Character.LOWERCASE_LETTER) |
9426 (1 << Character.TITLECASE_LETTER) |
9427 (1 << Character.MODIFIER_LETTER) |
9428 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
9429 != 0;
9430 }
9431
9432 /**
9433 * Determines if the specified character is a letter or digit.
9434 * <p>
9435 * A character is considered to be a letter or digit if either
9436 * {@code Character.isLetter(char ch)} or
9437 * {@code Character.isDigit(char ch)} returns
9438 * {@code true} for the character.
9439 *
9440 * <p><b>Note:</b> This method cannot handle <a
9441 * href="#supplementary"> supplementary characters</a>. To support
9442 * all Unicode characters, including supplementary characters, use
9443 * the {@link #isLetterOrDigit(int)} method.
9444 *
9445 * @param ch the character to be tested.
9446 * @return {@code true} if the character is a letter or digit;
9447 * {@code false} otherwise.
9448 * @see Character#isDigit(char)
9449 * @see Character#isJavaIdentifierPart(char)
9450 * @see Character#isJavaLetter(char)
9451 * @see Character#isJavaLetterOrDigit(char)
9452 * @see Character#isLetter(char)
9453 * @see Character#isUnicodeIdentifierPart(char)
9454 * @since 1.0.2
9455 */
9456 public static boolean isLetterOrDigit(char ch) {
9457 return isLetterOrDigit((int)ch);
9458 }
9459
9460 /**
9461 * Determines if the specified character (Unicode code point) is a letter or digit.
9462 * <p>
9463 * A character is considered to be a letter or digit if either
9464 * {@link #isLetter(int) isLetter(codePoint)} or
9465 * {@link #isDigit(int) isDigit(codePoint)} returns
9466 * {@code true} for the character.
9467 *
9468 * @param codePoint the character (Unicode code point) to be tested.
9469 * @return {@code true} if the character is a letter or digit;
9470 * {@code false} otherwise.
9471 * @see Character#isDigit(int)
9472 * @see Character#isJavaIdentifierPart(int)
9473 * @see Character#isLetter(int)
9474 * @see Character#isUnicodeIdentifierPart(int)
9475 * @since 1.5
9476 */
9477 public static boolean isLetterOrDigit(int codePoint) {
9478 return ((((1 << Character.UPPERCASE_LETTER) |
9479 (1 << Character.LOWERCASE_LETTER) |
9480 (1 << Character.TITLECASE_LETTER) |
9481 (1 << Character.MODIFIER_LETTER) |
9482 (1 << Character.OTHER_LETTER) |
9483 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
9484 != 0;
9485 }
9486
9487 /**
9488 * Determines if the specified character is permissible as the first
9489 * character in a Java identifier.
9490 * <p>
9491 * A character may start a Java identifier if and only if
9492 * one of the following is true:
9493 * <ul>
9494 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9495 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
9496 * <li> {@code ch} is a currency symbol (such as {@code '$'})
9497 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
9498 * </ul>
9499 *
9500 * @param ch the character to be tested.
9501 * @return {@code true} if the character may start a Java
9502 * identifier; {@code false} otherwise.
9503 * @see Character#isJavaLetterOrDigit(char)
9504 * @see Character#isJavaIdentifierStart(char)
9505 * @see Character#isJavaIdentifierPart(char)
9506 * @see Character#isLetter(char)
9507 * @see Character#isLetterOrDigit(char)
9508 * @see Character#isUnicodeIdentifierStart(char)
9509 * @since 1.0.2
9510 * @deprecated Replaced by isJavaIdentifierStart(char).
9511 */
9512 @Deprecated(since="1.1")
9513 public static boolean isJavaLetter(char ch) {
9514 return isJavaIdentifierStart(ch);
9515 }
9516
9517 /**
9518 * Determines if the specified character may be part of a Java
9519 * identifier as other than the first character.
9520 * <p>
9521 * A character may be part of a Java identifier if and only if any
9522 * of the following are true:
9523 * <ul>
9524 * <li> it is a letter
9525 * <li> it is a currency symbol (such as {@code '$'})
9526 * <li> it is a connecting punctuation character (such as {@code '_'})
9527 * <li> it is a digit
9528 * <li> it is a numeric letter (such as a Roman numeral character)
9529 * <li> it is a combining mark
9530 * <li> it is a non-spacing mark
9531 * <li> {@code isIdentifierIgnorable} returns
9532 * {@code true} for the character.
9533 * </ul>
9534 *
9535 * @param ch the character to be tested.
9536 * @return {@code true} if the character may be part of a
9537 * Java identifier; {@code false} otherwise.
9538 * @see Character#isJavaLetter(char)
9539 * @see Character#isJavaIdentifierStart(char)
9540 * @see Character#isJavaIdentifierPart(char)
9541 * @see Character#isLetter(char)
9542 * @see Character#isLetterOrDigit(char)
9543 * @see Character#isUnicodeIdentifierPart(char)
9544 * @see Character#isIdentifierIgnorable(char)
9545 * @since 1.0.2
9546 * @deprecated Replaced by isJavaIdentifierPart(char).
9547 */
9548 @Deprecated(since="1.1")
9549 public static boolean isJavaLetterOrDigit(char ch) {
9550 return isJavaIdentifierPart(ch);
9551 }
9552
9553 /**
9554 * Determines if the specified character (Unicode code point) is an alphabet.
9555 * <p>
9556 * A character is considered to be alphabetic if its general category type,
9557 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
9558 * the following:
9559 * <ul>
9560 * <li> {@code UPPERCASE_LETTER}
9561 * <li> {@code LOWERCASE_LETTER}
9562 * <li> {@code TITLECASE_LETTER}
9563 * <li> {@code MODIFIER_LETTER}
9564 * <li> {@code OTHER_LETTER}
9565 * <li> {@code LETTER_NUMBER}
9566 * </ul>
9567 * or it has contributory property Other_Alphabetic as defined by the
9568 * Unicode Standard.
9569 *
9570 * @param codePoint the character (Unicode code point) to be tested.
9571 * @return {@code true} if the character is a Unicode alphabet
9572 * character, {@code false} otherwise.
9573 * @since 1.7
9574 */
9575 public static boolean isAlphabetic(int codePoint) {
9576 return (((((1 << Character.UPPERCASE_LETTER) |
9577 (1 << Character.LOWERCASE_LETTER) |
9578 (1 << Character.TITLECASE_LETTER) |
9579 (1 << Character.MODIFIER_LETTER) |
9580 (1 << Character.OTHER_LETTER) |
9581 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
9582 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
9583 }
9584
9585 /**
9586 * Determines if the specified character (Unicode code point) is a CJKV
9587 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
9588 * the Unicode Standard.
9589 *
9590 * @param codePoint the character (Unicode code point) to be tested.
9591 * @return {@code true} if the character is a Unicode ideograph
9592 * character, {@code false} otherwise.
9593 * @since 1.7
9594 */
9595 public static boolean isIdeographic(int codePoint) {
9596 return CharacterData.of(codePoint).isIdeographic(codePoint);
9597 }
9598
9599 /**
9600 * Determines if the specified character is
9601 * permissible as the first character in a Java identifier.
9602 * <p>
9603 * A character may start a Java identifier if and only if
9604 * one of the following conditions is true:
9605 * <ul>
9606 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9607 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
9608 * <li> {@code ch} is a currency symbol (such as {@code '$'})
9609 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
9610 * </ul>
9611 *
9612 * <p><b>Note:</b> This method cannot handle <a
9613 * href="#supplementary"> supplementary characters</a>. To support
9614 * all Unicode characters, including supplementary characters, use
9615 * the {@link #isJavaIdentifierStart(int)} method.
9616 *
9617 * @param ch the character to be tested.
9618 * @return {@code true} if the character may start a Java identifier;
9619 * {@code false} otherwise.
9620 * @see Character#isJavaIdentifierPart(char)
9621 * @see Character#isLetter(char)
9622 * @see Character#isUnicodeIdentifierStart(char)
9623 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9624 * @since 1.1
9625 */
9626 public static boolean isJavaIdentifierStart(char ch) {
9627 return isJavaIdentifierStart((int)ch);
9628 }
9629
9630 /**
9631 * Determines if the character (Unicode code point) is
9632 * permissible as the first character in a Java identifier.
9633 * <p>
9634 * A character may start a Java identifier if and only if
9635 * one of the following conditions is true:
9636 * <ul>
9637 * <li> {@link #isLetter(int) isLetter(codePoint)}
9638 * returns {@code true}
9639 * <li> {@link #getType(int) getType(codePoint)}
9640 * returns {@code LETTER_NUMBER}
9641 * <li> the referenced character is a currency symbol (such as {@code '$'})
9642 * <li> the referenced character is a connecting punctuation character
9643 * (such as {@code '_'}).
9644 * </ul>
9645 *
9646 * @param codePoint the character (Unicode code point) to be tested.
9647 * @return {@code true} if the character may start a Java identifier;
9648 * {@code false} otherwise.
9649 * @see Character#isJavaIdentifierPart(int)
9650 * @see Character#isLetter(int)
9651 * @see Character#isUnicodeIdentifierStart(int)
9652 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9653 * @since 1.5
9654 */
9655 public static boolean isJavaIdentifierStart(int codePoint) {
9656 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
9657 }
9658
9659 /**
9660 * Determines if the specified character may be part of a Java
9661 * identifier as other than the first character.
9662 * <p>
9663 * A character may be part of a Java identifier if any of the following
9664 * are true:
9665 * <ul>
9666 * <li> it is a letter
9667 * <li> it is a currency symbol (such as {@code '$'})
9668 * <li> it is a connecting punctuation character (such as {@code '_'})
9669 * <li> it is a digit
9670 * <li> it is a numeric letter (such as a Roman numeral character)
9671 * <li> it is a combining mark
9672 * <li> it is a non-spacing mark
9673 * <li> {@code isIdentifierIgnorable} returns
9674 * {@code true} for the character
9675 * </ul>
9676 *
9677 * <p><b>Note:</b> This method cannot handle <a
9678 * href="#supplementary"> supplementary characters</a>. To support
9679 * all Unicode characters, including supplementary characters, use
9680 * the {@link #isJavaIdentifierPart(int)} method.
9681 *
9682 * @param ch the character to be tested.
9683 * @return {@code true} if the character may be part of a
9684 * Java identifier; {@code false} otherwise.
9685 * @see Character#isIdentifierIgnorable(char)
9686 * @see Character#isJavaIdentifierStart(char)
9687 * @see Character#isLetterOrDigit(char)
9688 * @see Character#isUnicodeIdentifierPart(char)
9689 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9690 * @since 1.1
9691 */
9692 public static boolean isJavaIdentifierPart(char ch) {
9693 return isJavaIdentifierPart((int)ch);
9694 }
9695
9696 /**
9697 * Determines if the character (Unicode code point) may be part of a Java
9698 * identifier as other than the first character.
9699 * <p>
9700 * A character may be part of a Java identifier if any of the following
9701 * are true:
9702 * <ul>
9703 * <li> it is a letter
9704 * <li> it is a currency symbol (such as {@code '$'})
9705 * <li> it is a connecting punctuation character (such as {@code '_'})
9706 * <li> it is a digit
9707 * <li> it is a numeric letter (such as a Roman numeral character)
9708 * <li> it is a combining mark
9709 * <li> it is a non-spacing mark
9710 * <li> {@link #isIdentifierIgnorable(int)
9711 * isIdentifierIgnorable(codePoint)} returns {@code true} for
9712 * the character
9713 * </ul>
9714 *
9715 * @param codePoint the character (Unicode code point) to be tested.
9716 * @return {@code true} if the character may be part of a
9717 * Java identifier; {@code false} otherwise.
9718 * @see Character#isIdentifierIgnorable(int)
9719 * @see Character#isJavaIdentifierStart(int)
9720 * @see Character#isLetterOrDigit(int)
9721 * @see Character#isUnicodeIdentifierPart(int)
9722 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9723 * @since 1.5
9724 */
9725 public static boolean isJavaIdentifierPart(int codePoint) {
9726 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
9727 }
9728
9729 /**
9730 * Determines if the specified character is permissible as the
9731 * first character in a Unicode identifier.
9732 * <p>
9733 * A character may start a Unicode identifier if and only if
9734 * one of the following conditions is true:
9735 * <ul>
9736 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9737 * <li> {@link #getType(char) getType(ch)} returns
9738 * {@code LETTER_NUMBER}.
9739 * </ul>
9740 *
9741 * <p><b>Note:</b> This method cannot handle <a
9742 * href="#supplementary"> supplementary characters</a>. To support
9743 * all Unicode characters, including supplementary characters, use
9744 * the {@link #isUnicodeIdentifierStart(int)} method.
9745 *
9746 * @param ch the character to be tested.
9747 * @return {@code true} if the character may start a Unicode
9748 * identifier; {@code false} otherwise.
9749 * @see Character#isJavaIdentifierStart(char)
9750 * @see Character#isLetter(char)
9751 * @see Character#isUnicodeIdentifierPart(char)
9752 * @since 1.1
9753 */
9754 public static boolean isUnicodeIdentifierStart(char ch) {
9755 return isUnicodeIdentifierStart((int)ch);
9756 }
9757
9758 /**
9759 * Determines if the specified character (Unicode code point) is permissible as the
9760 * first character in a Unicode identifier.
9761 * <p>
9762 * A character may start a Unicode identifier if and only if
9763 * one of the following conditions is true:
9764 * <ul>
9765 * <li> {@link #isLetter(int) isLetter(codePoint)}
9766 * returns {@code true}
9767 * <li> {@link #getType(int) getType(codePoint)}
9768 * returns {@code LETTER_NUMBER}.
9769 * </ul>
9770 * @param codePoint the character (Unicode code point) to be tested.
9771 * @return {@code true} if the character may start a Unicode
9772 * identifier; {@code false} otherwise.
9773 * @see Character#isJavaIdentifierStart(int)
9774 * @see Character#isLetter(int)
9775 * @see Character#isUnicodeIdentifierPart(int)
9776 * @since 1.5
9777 */
9778 public static boolean isUnicodeIdentifierStart(int codePoint) {
9779 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
9780 }
9781
9782 /**
9783 * Determines if the specified character may be part of a Unicode
9784 * identifier as other than the first character.
9785 * <p>
9786 * A character may be part of a Unicode identifier if and only if
9787 * one of the following statements is true:
9788 * <ul>
9789 * <li> it is a letter
9790 * <li> it is a connecting punctuation character (such as {@code '_'})
9791 * <li> it is a digit
9792 * <li> it is a numeric letter (such as a Roman numeral character)
9793 * <li> it is a combining mark
9794 * <li> it is a non-spacing mark
9795 * <li> {@code isIdentifierIgnorable} returns
9796 * {@code true} for this character.
9797 * </ul>
9798 *
9799 * <p><b>Note:</b> This method cannot handle <a
9800 * href="#supplementary"> supplementary characters</a>. To support
9801 * all Unicode characters, including supplementary characters, use
9802 * the {@link #isUnicodeIdentifierPart(int)} method.
9803 *
9804 * @param ch the character to be tested.
9805 * @return {@code true} if the character may be part of a
9806 * Unicode identifier; {@code false} otherwise.
9807 * @see Character#isIdentifierIgnorable(char)
9808 * @see Character#isJavaIdentifierPart(char)
9809 * @see Character#isLetterOrDigit(char)
9810 * @see Character#isUnicodeIdentifierStart(char)
9811 * @since 1.1
9812 */
9813 public static boolean isUnicodeIdentifierPart(char ch) {
9814 return isUnicodeIdentifierPart((int)ch);
9815 }
9816
9817 /**
9818 * Determines if the specified character (Unicode code point) may be part of a Unicode
9819 * identifier as other than the first character.
9820 * <p>
9821 * A character may be part of a Unicode identifier if and only if
9822 * one of the following statements is true:
9823 * <ul>
9824 * <li> it is a letter
9825 * <li> it is a connecting punctuation character (such as {@code '_'})
9826 * <li> it is a digit
9827 * <li> it is a numeric letter (such as a Roman numeral character)
9828 * <li> it is a combining mark
9829 * <li> it is a non-spacing mark
9830 * <li> {@code isIdentifierIgnorable} returns
9831 * {@code true} for this character.
9832 * </ul>
9833 * @param codePoint the character (Unicode code point) to be tested.
9834 * @return {@code true} if the character may be part of a
9835 * Unicode identifier; {@code false} otherwise.
9836 * @see Character#isIdentifierIgnorable(int)
9837 * @see Character#isJavaIdentifierPart(int)
9838 * @see Character#isLetterOrDigit(int)
9839 * @see Character#isUnicodeIdentifierStart(int)
9840 * @since 1.5
9841 */
9842 public static boolean isUnicodeIdentifierPart(int codePoint) {
9843 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
9844 }
9845
9846 /**
9847 * Determines if the specified character should be regarded as
9848 * an ignorable character in a Java identifier or a Unicode identifier.
9849 * <p>
9850 * The following Unicode characters are ignorable in a Java identifier
9851 * or a Unicode identifier:
9852 * <ul>
9853 * <li>ISO control characters that are not whitespace
9854 * <ul>
9855 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9856 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9857 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9858 * </ul>
9859 *
9860 * <li>all characters that have the {@code FORMAT} general
9861 * category value
9862 * </ul>
9863 *
9864 * <p><b>Note:</b> This method cannot handle <a
9865 * href="#supplementary"> supplementary characters</a>. To support
9866 * all Unicode characters, including supplementary characters, use
9867 * the {@link #isIdentifierIgnorable(int)} method.
9868 *
9869 * @param ch the character to be tested.
9870 * @return {@code true} if the character is an ignorable control
9871 * character that may be part of a Java or Unicode identifier;
9872 * {@code false} otherwise.
9873 * @see Character#isJavaIdentifierPart(char)
9874 * @see Character#isUnicodeIdentifierPart(char)
9875 * @since 1.1
9876 */
9877 public static boolean isIdentifierIgnorable(char ch) {
9878 return isIdentifierIgnorable((int)ch);
9879 }
9880
9881 /**
9882 * Determines if the specified character (Unicode code point) should be regarded as
9883 * an ignorable character in a Java identifier or a Unicode identifier.
9884 * <p>
9885 * The following Unicode characters are ignorable in a Java identifier
9886 * or a Unicode identifier:
9887 * <ul>
9888 * <li>ISO control characters that are not whitespace
9889 * <ul>
9890 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9891 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9892 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9893 * </ul>
9894 *
9895 * <li>all characters that have the {@code FORMAT} general
9896 * category value
9897 * </ul>
9898 *
9899 * @param codePoint the character (Unicode code point) to be tested.
9900 * @return {@code true} if the character is an ignorable control
9901 * character that may be part of a Java or Unicode identifier;
9902 * {@code false} otherwise.
9903 * @see Character#isJavaIdentifierPart(int)
9904 * @see Character#isUnicodeIdentifierPart(int)
9905 * @since 1.5
9906 */
9907 public static boolean isIdentifierIgnorable(int codePoint) {
9908 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
9909 }
9910
9911 /**
9912 * Converts the character argument to lowercase using case
9913 * mapping information from the UnicodeData file.
9914 * <p>
9915 * Note that
9916 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
9917 * does not always return {@code true} for some ranges of
9918 * characters, particularly those that are symbols or ideographs.
9919 *
9920 * <p>In general, {@link String#toLowerCase()} should be used to map
9921 * characters to lowercase. {@code String} case mapping methods
9922 * have several benefits over {@code Character} case mapping methods.
9923 * {@code String} case mapping methods can perform locale-sensitive
9924 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9925 * the {@code Character} case mapping methods cannot.
9926 *
9927 * <p><b>Note:</b> This method cannot handle <a
9928 * href="#supplementary"> supplementary characters</a>. To support
9929 * all Unicode characters, including supplementary characters, use
9930 * the {@link #toLowerCase(int)} method.
9931 *
9932 * @param ch the character to be converted.
9933 * @return the lowercase equivalent of the character, if any;
9934 * otherwise, the character itself.
9935 * @see Character#isLowerCase(char)
9936 * @see String#toLowerCase()
9937 */
9938 public static char toLowerCase(char ch) {
9939 return (char)toLowerCase((int)ch);
9940 }
9941
9942 /**
9943 * Converts the character (Unicode code point) argument to
9944 * lowercase using case mapping information from the UnicodeData
9945 * file.
9946 *
9947 * <p> Note that
9948 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
9949 * does not always return {@code true} for some ranges of
9950 * characters, particularly those that are symbols or ideographs.
9951 *
9952 * <p>In general, {@link String#toLowerCase()} should be used to map
9953 * characters to lowercase. {@code String} case mapping methods
9954 * have several benefits over {@code Character} case mapping methods.
9955 * {@code String} case mapping methods can perform locale-sensitive
9956 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9957 * the {@code Character} case mapping methods cannot.
9958 *
9959 * @param codePoint the character (Unicode code point) to be converted.
9960 * @return the lowercase equivalent of the character (Unicode code
9961 * point), if any; otherwise, the character itself.
9962 * @see Character#isLowerCase(int)
9963 * @see String#toLowerCase()
9964 *
9965 * @since 1.5
9966 */
9967 public static int toLowerCase(int codePoint) {
9968 return CharacterData.of(codePoint).toLowerCase(codePoint);
9969 }
9970
9971 /**
9972 * Converts the character argument to uppercase using case mapping
9973 * information from the UnicodeData file.
9974 * <p>
9975 * Note that
9976 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
9977 * does not always return {@code true} for some ranges of
9978 * characters, particularly those that are symbols or ideographs.
9979 *
9980 * <p>In general, {@link String#toUpperCase()} should be used to map
9981 * characters to uppercase. {@code String} case mapping methods
9982 * have several benefits over {@code Character} case mapping methods.
9983 * {@code String} case mapping methods can perform locale-sensitive
9984 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9985 * the {@code Character} case mapping methods cannot.
9986 *
9987 * <p><b>Note:</b> This method cannot handle <a
9988 * href="#supplementary"> supplementary characters</a>. To support
9989 * all Unicode characters, including supplementary characters, use
9990 * the {@link #toUpperCase(int)} method.
9991 *
9992 * @param ch the character to be converted.
9993 * @return the uppercase equivalent of the character, if any;
9994 * otherwise, the character itself.
9995 * @see Character#isUpperCase(char)
9996 * @see String#toUpperCase()
9997 */
9998 public static char toUpperCase(char ch) {
9999 return (char)toUpperCase((int)ch);
10000 }
10001
10002 /**
10003 * Converts the character (Unicode code point) argument to
10004 * uppercase using case mapping information from the UnicodeData
10005 * file.
10006 *
10007 * <p>Note that
10008 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
10009 * does not always return {@code true} for some ranges of
10010 * characters, particularly those that are symbols or ideographs.
10011 *
10012 * <p>In general, {@link String#toUpperCase()} should be used to map
10013 * characters to uppercase. {@code String} case mapping methods
10014 * have several benefits over {@code Character} case mapping methods.
10015 * {@code String} case mapping methods can perform locale-sensitive
10016 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10017 * the {@code Character} case mapping methods cannot.
10018 *
10019 * @param codePoint the character (Unicode code point) to be converted.
10020 * @return the uppercase equivalent of the character, if any;
10021 * otherwise, the character itself.
10022 * @see Character#isUpperCase(int)
10023 * @see String#toUpperCase()
10024 *
10025 * @since 1.5
10026 */
10027 public static int toUpperCase(int codePoint) {
10028 return CharacterData.of(codePoint).toUpperCase(codePoint);
10029 }
10030
10031 /**
10032 * Converts the character argument to titlecase using case mapping
10033 * information from the UnicodeData file. If a character has no
10034 * explicit titlecase mapping and is not itself a titlecase char
10035 * according to UnicodeData, then the uppercase mapping is
10036 * returned as an equivalent titlecase mapping. If the
10037 * {@code char} argument is already a titlecase
10038 * {@code char}, the same {@code char} value will be
10039 * returned.
10040 * <p>
10041 * Note that
10042 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
10043 * does not always return {@code true} for some ranges of
10044 * characters.
10045 *
10046 * <p><b>Note:</b> This method cannot handle <a
10047 * href="#supplementary"> supplementary characters</a>. To support
10048 * all Unicode characters, including supplementary characters, use
10049 * the {@link #toTitleCase(int)} method.
10050 *
10051 * @param ch the character to be converted.
10052 * @return the titlecase equivalent of the character, if any;
10053 * otherwise, the character itself.
10054 * @see Character#isTitleCase(char)
10055 * @see Character#toLowerCase(char)
10056 * @see Character#toUpperCase(char)
10057 * @since 1.0.2
10058 */
10059 public static char toTitleCase(char ch) {
10060 return (char)toTitleCase((int)ch);
10061 }
10062
10063 /**
10064 * Converts the character (Unicode code point) argument to titlecase using case mapping
10065 * information from the UnicodeData file. If a character has no
10066 * explicit titlecase mapping and is not itself a titlecase char
10067 * according to UnicodeData, then the uppercase mapping is
10068 * returned as an equivalent titlecase mapping. If the
10069 * character argument is already a titlecase
10070 * character, the same character value will be
10071 * returned.
10072 *
10073 * <p>Note that
10074 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
10075 * does not always return {@code true} for some ranges of
10076 * characters.
10077 *
10078 * @param codePoint the character (Unicode code point) to be converted.
10079 * @return the titlecase equivalent of the character, if any;
10080 * otherwise, the character itself.
10081 * @see Character#isTitleCase(int)
10082 * @see Character#toLowerCase(int)
10083 * @see Character#toUpperCase(int)
10084 * @since 1.5
10085 */
10086 public static int toTitleCase(int codePoint) {
10087 return CharacterData.of(codePoint).toTitleCase(codePoint);
10088 }
10089
10090 /**
10091 * Returns the numeric value of the character {@code ch} in the
10092 * specified radix.
10093 * <p>
10094 * If the radix is not in the range {@code MIN_RADIX} ≤
10095 * {@code radix} ≤ {@code MAX_RADIX} or if the
10096 * value of {@code ch} is not a valid digit in the specified
10097 * radix, {@code -1} is returned. A character is a valid digit
10098 * if at least one of the following is true:
10099 * <ul>
10100 * <li>The method {@code isDigit} is {@code true} of the character
10101 * and the Unicode decimal digit value of the character (or its
10102 * single-character decomposition) is less than the specified radix.
10103 * In this case the decimal digit value is returned.
10104 * <li>The character is one of the uppercase Latin letters
10105 * {@code 'A'} through {@code 'Z'} and its code is less than
10106 * {@code radix + 'A' - 10}.
10107 * In this case, {@code ch - 'A' + 10}
10108 * is returned.
10109 * <li>The character is one of the lowercase Latin letters
10110 * {@code 'a'} through {@code 'z'} and its code is less than
10111 * {@code radix + 'a' - 10}.
10112 * In this case, {@code ch - 'a' + 10}
10113 * is returned.
10114 * <li>The character is one of the fullwidth uppercase Latin letters A
10115 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
10116 * and its code is less than
10117 * {@code radix + '\u005CuFF21' - 10}.
10118 * In this case, {@code ch - '\u005CuFF21' + 10}
10119 * is returned.
10120 * <li>The character is one of the fullwidth lowercase Latin letters a
10121 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
10122 * and its code is less than
10123 * {@code radix + '\u005CuFF41' - 10}.
10124 * In this case, {@code ch - '\u005CuFF41' + 10}
10125 * is returned.
10126 * </ul>
10127 *
10128 * <p><b>Note:</b> This method cannot handle <a
10129 * href="#supplementary"> supplementary characters</a>. To support
10130 * all Unicode characters, including supplementary characters, use
10131 * the {@link #digit(int, int)} method.
10132 *
10133 * @param ch the character to be converted.
10134 * @param radix the radix.
10135 * @return the numeric value represented by the character in the
10136 * specified radix.
10137 * @see Character#forDigit(int, int)
10138 * @see Character#isDigit(char)
10139 */
10140 public static int digit(char ch, int radix) {
10141 return digit((int)ch, radix);
10142 }
10143
10144 /**
10145 * Returns the numeric value of the specified character (Unicode
10146 * code point) in the specified radix.
10147 *
10148 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
10149 * {@code radix} ≤ {@code MAX_RADIX} or if the
10150 * character is not a valid digit in the specified
10151 * radix, {@code -1} is returned. A character is a valid digit
10152 * if at least one of the following is true:
10153 * <ul>
10154 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
10155 * and the Unicode decimal digit value of the character (or its
10156 * single-character decomposition) is less than the specified radix.
10157 * In this case the decimal digit value is returned.
10158 * <li>The character is one of the uppercase Latin letters
10159 * {@code 'A'} through {@code 'Z'} and its code is less than
10160 * {@code radix + 'A' - 10}.
10161 * In this case, {@code codePoint - 'A' + 10}
10162 * is returned.
10163 * <li>The character is one of the lowercase Latin letters
10164 * {@code 'a'} through {@code 'z'} and its code is less than
10165 * {@code radix + 'a' - 10}.
10166 * In this case, {@code codePoint - 'a' + 10}
10167 * is returned.
10168 * <li>The character is one of the fullwidth uppercase Latin letters A
10169 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
10170 * and its code is less than
10171 * {@code radix + '\u005CuFF21' - 10}.
10172 * In this case,
10173 * {@code codePoint - '\u005CuFF21' + 10}
10174 * is returned.
10175 * <li>The character is one of the fullwidth lowercase Latin letters a
10176 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
10177 * and its code is less than
10178 * {@code radix + '\u005CuFF41'- 10}.
10179 * In this case,
10180 * {@code codePoint - '\u005CuFF41' + 10}
10181 * is returned.
10182 * </ul>
10183 *
10184 * @param codePoint the character (Unicode code point) to be converted.
10185 * @param radix the radix.
10186 * @return the numeric value represented by the character in the
10187 * specified radix.
10188 * @see Character#forDigit(int, int)
10189 * @see Character#isDigit(int)
10190 * @since 1.5
10191 */
10192 public static int digit(int codePoint, int radix) {
10193 return CharacterData.of(codePoint).digit(codePoint, radix);
10194 }
10195
10196 /**
10197 * Returns the {@code int} value that the specified Unicode
10198 * character represents. For example, the character
10199 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
10200 * an int with a value of 50.
10201 * <p>
10202 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
10203 * {@code '\u005Cu005A'}), lowercase
10204 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
10205 * full width variant ({@code '\u005CuFF21'} through
10206 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
10207 * {@code '\u005CuFF5A'}) forms have numeric values from 10
10208 * through 35. This is independent of the Unicode specification,
10209 * which does not assign numeric values to these {@code char}
10210 * values.
10211 * <p>
10212 * If the character does not have a numeric value, then -1 is returned.
10213 * If the character has a numeric value that cannot be represented as a
10214 * nonnegative integer (for example, a fractional value), then -2
10215 * is returned.
10216 *
10217 * <p><b>Note:</b> This method cannot handle <a
10218 * href="#supplementary"> supplementary characters</a>. To support
10219 * all Unicode characters, including supplementary characters, use
10220 * the {@link #getNumericValue(int)} method.
10221 *
10222 * @param ch the character to be converted.
10223 * @return the numeric value of the character, as a nonnegative {@code int}
10224 * value; -2 if the character has a numeric value but the value
10225 * can not be represented as a nonnegative {@code int} value;
10226 * -1 if the character has no numeric value.
10227 * @see Character#forDigit(int, int)
10228 * @see Character#isDigit(char)
10229 * @since 1.1
10230 */
10231 public static int getNumericValue(char ch) {
10232 return getNumericValue((int)ch);
10233 }
10234
10235 /**
10236 * Returns the {@code int} value that the specified
10237 * character (Unicode code point) represents. For example, the character
10238 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
10239 * an {@code int} with a value of 50.
10240 * <p>
10241 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
10242 * {@code '\u005Cu005A'}), lowercase
10243 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
10244 * full width variant ({@code '\u005CuFF21'} through
10245 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
10246 * {@code '\u005CuFF5A'}) forms have numeric values from 10
10247 * through 35. This is independent of the Unicode specification,
10248 * which does not assign numeric values to these {@code char}
10249 * values.
10250 * <p>
10251 * If the character does not have a numeric value, then -1 is returned.
10252 * If the character has a numeric value that cannot be represented as a
10253 * nonnegative integer (for example, a fractional value), then -2
10254 * is returned.
10255 *
10256 * @param codePoint the character (Unicode code point) to be converted.
10257 * @return the numeric value of the character, as a nonnegative {@code int}
10258 * value; -2 if the character has a numeric value but the value
10259 * can not be represented as a nonnegative {@code int} value;
10260 * -1 if the character has no numeric value.
10261 * @see Character#forDigit(int, int)
10262 * @see Character#isDigit(int)
10263 * @since 1.5
10264 */
10265 public static int getNumericValue(int codePoint) {
10266 return CharacterData.of(codePoint).getNumericValue(codePoint);
10267 }
10268
10269 /**
10270 * Determines if the specified character is ISO-LATIN-1 white space.
10271 * This method returns {@code true} for the following five
10272 * characters only:
10273 * <table class="striped">
10274 * <caption style="display:none">truechars</caption>
10275 * <thead>
10276 * <tr><th scope="col">Character
10277 * <th scope="col">Code
10278 * <th scope="col">Name
10279 * </thead>
10280 * <tbody>
10281 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
10282 * <td>{@code HORIZONTAL TABULATION}</td></tr>
10283 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
10284 * <td>{@code NEW LINE}</td></tr>
10285 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
10286 * <td>{@code FORM FEED}</td></tr>
10287 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
10288 * <td>{@code CARRIAGE RETURN}</td></tr>
10289 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
10290 * <td>{@code SPACE}</td></tr>
10291 * </tbody>
10292 * </table>
10293 *
10294 * @param ch the character to be tested.
10295 * @return {@code true} if the character is ISO-LATIN-1 white
10296 * space; {@code false} otherwise.
10297 * @see Character#isSpaceChar(char)
10298 * @see Character#isWhitespace(char)
10299 * @deprecated Replaced by isWhitespace(char).
10300 */
10301 @Deprecated(since="1.1")
10302 public static boolean isSpace(char ch) {
10303 return (ch <= 0x0020) &&
10304 (((((1L << 0x0009) |
10305 (1L << 0x000A) |
10306 (1L << 0x000C) |
10307 (1L << 0x000D) |
10308 (1L << 0x0020)) >> ch) & 1L) != 0);
10309 }
10310
10311
10312 /**
10313 * Determines if the specified character is a Unicode space character.
10314 * A character is considered to be a space character if and only if
10315 * it is specified to be a space character by the Unicode Standard. This
10316 * method returns true if the character's general category type is any of
10317 * the following:
10318 * <ul>
10319 * <li> {@code SPACE_SEPARATOR}
10320 * <li> {@code LINE_SEPARATOR}
10321 * <li> {@code PARAGRAPH_SEPARATOR}
10322 * </ul>
10323 *
10324 * <p><b>Note:</b> This method cannot handle <a
10325 * href="#supplementary"> supplementary characters</a>. To support
10326 * all Unicode characters, including supplementary characters, use
10327 * the {@link #isSpaceChar(int)} method.
10328 *
10329 * @param ch the character to be tested.
10330 * @return {@code true} if the character is a space character;
10331 * {@code false} otherwise.
10332 * @see Character#isWhitespace(char)
10333 * @since 1.1
10334 */
10335 public static boolean isSpaceChar(char ch) {
10336 return isSpaceChar((int)ch);
10337 }
10338
10339 /**
10340 * Determines if the specified character (Unicode code point) is a
10341 * Unicode space character. A character is considered to be a
10342 * space character if and only if it is specified to be a space
10343 * character by the Unicode Standard. This method returns true if
10344 * the character's general category type is any of the following:
10345 *
10346 * <ul>
10347 * <li> {@link #SPACE_SEPARATOR}
10348 * <li> {@link #LINE_SEPARATOR}
10349 * <li> {@link #PARAGRAPH_SEPARATOR}
10350 * </ul>
10351 *
10352 * @param codePoint the character (Unicode code point) to be tested.
10353 * @return {@code true} if the character is a space character;
10354 * {@code false} otherwise.
10355 * @see Character#isWhitespace(int)
10356 * @since 1.5
10357 */
10358 public static boolean isSpaceChar(int codePoint) {
10359 return ((((1 << Character.SPACE_SEPARATOR) |
10360 (1 << Character.LINE_SEPARATOR) |
10361 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
10362 != 0;
10363 }
10364
10365 /**
10366 * Determines if the specified character is white space according to Java.
10367 * A character is a Java whitespace character if and only if it satisfies
10368 * one of the following criteria:
10369 * <ul>
10370 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
10371 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
10372 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
10373 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
10374 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
10375 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
10376 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
10377 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
10378 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
10379 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
10380 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
10381 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
10382 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
10383 * </ul>
10384 *
10385 * <p><b>Note:</b> This method cannot handle <a
10386 * href="#supplementary"> supplementary characters</a>. To support
10387 * all Unicode characters, including supplementary characters, use
10388 * the {@link #isWhitespace(int)} method.
10389 *
10390 * @param ch the character to be tested.
10391 * @return {@code true} if the character is a Java whitespace
10392 * character; {@code false} otherwise.
10393 * @see Character#isSpaceChar(char)
10394 * @since 1.1
10395 */
10396 public static boolean isWhitespace(char ch) {
10397 return isWhitespace((int)ch);
10398 }
10399
10400 /**
10401 * Determines if the specified character (Unicode code point) is
10402 * white space according to Java. A character is a Java
10403 * whitespace character if and only if it satisfies one of the
10404 * following criteria:
10405 * <ul>
10406 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
10407 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
10408 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
10409 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
10410 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
10411 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
10412 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
10413 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
10414 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
10415 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
10416 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
10417 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
10418 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
10419 * </ul>
10420 *
10421 * @param codePoint the character (Unicode code point) to be tested.
10422 * @return {@code true} if the character is a Java whitespace
10423 * character; {@code false} otherwise.
10424 * @see Character#isSpaceChar(int)
10425 * @since 1.5
10426 */
10427 public static boolean isWhitespace(int codePoint) {
10428 return CharacterData.of(codePoint).isWhitespace(codePoint);
10429 }
10430
10431 /**
10432 * Determines if the specified character is an ISO control
10433 * character. A character is considered to be an ISO control
10434 * character if its code is in the range {@code '\u005Cu0000'}
10435 * through {@code '\u005Cu001F'} or in the range
10436 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
10437 *
10438 * <p><b>Note:</b> This method cannot handle <a
10439 * href="#supplementary"> supplementary characters</a>. To support
10440 * all Unicode characters, including supplementary characters, use
10441 * the {@link #isISOControl(int)} method.
10442 *
10443 * @param ch the character to be tested.
10444 * @return {@code true} if the character is an ISO control character;
10445 * {@code false} otherwise.
10446 *
10447 * @see Character#isSpaceChar(char)
10448 * @see Character#isWhitespace(char)
10449 * @since 1.1
10450 */
10451 public static boolean isISOControl(char ch) {
10452 return isISOControl((int)ch);
10453 }
10454
10455 /**
10456 * Determines if the referenced character (Unicode code point) is an ISO control
10457 * character. A character is considered to be an ISO control
10458 * character if its code is in the range {@code '\u005Cu0000'}
10459 * through {@code '\u005Cu001F'} or in the range
10460 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
10461 *
10462 * @param codePoint the character (Unicode code point) to be tested.
10463 * @return {@code true} if the character is an ISO control character;
10464 * {@code false} otherwise.
10465 * @see Character#isSpaceChar(int)
10466 * @see Character#isWhitespace(int)
10467 * @since 1.5
10468 */
10469 public static boolean isISOControl(int codePoint) {
10470 // Optimized form of:
10471 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
10472 // (codePoint >= 0x7F && codePoint <= 0x9F);
10473 return codePoint <= 0x9F &&
10474 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
10475 }
10476
10477 /**
10478 * Returns a value indicating a character's general category.
10479 *
10480 * <p><b>Note:</b> This method cannot handle <a
10481 * href="#supplementary"> supplementary characters</a>. To support
10482 * all Unicode characters, including supplementary characters, use
10483 * the {@link #getType(int)} method.
10484 *
10485 * @param ch the character to be tested.
10486 * @return a value of type {@code int} representing the
10487 * character's general category.
10488 * @see Character#COMBINING_SPACING_MARK
10489 * @see Character#CONNECTOR_PUNCTUATION
10490 * @see Character#CONTROL
10491 * @see Character#CURRENCY_SYMBOL
10492 * @see Character#DASH_PUNCTUATION
10493 * @see Character#DECIMAL_DIGIT_NUMBER
10494 * @see Character#ENCLOSING_MARK
10495 * @see Character#END_PUNCTUATION
10496 * @see Character#FINAL_QUOTE_PUNCTUATION
10497 * @see Character#FORMAT
10498 * @see Character#INITIAL_QUOTE_PUNCTUATION
10499 * @see Character#LETTER_NUMBER
10500 * @see Character#LINE_SEPARATOR
10501 * @see Character#LOWERCASE_LETTER
10502 * @see Character#MATH_SYMBOL
10503 * @see Character#MODIFIER_LETTER
10504 * @see Character#MODIFIER_SYMBOL
10505 * @see Character#NON_SPACING_MARK
10506 * @see Character#OTHER_LETTER
10507 * @see Character#OTHER_NUMBER
10508 * @see Character#OTHER_PUNCTUATION
10509 * @see Character#OTHER_SYMBOL
10510 * @see Character#PARAGRAPH_SEPARATOR
10511 * @see Character#PRIVATE_USE
10512 * @see Character#SPACE_SEPARATOR
10513 * @see Character#START_PUNCTUATION
10514 * @see Character#SURROGATE
10515 * @see Character#TITLECASE_LETTER
10516 * @see Character#UNASSIGNED
10517 * @see Character#UPPERCASE_LETTER
10518 * @since 1.1
10519 */
10520 public static int getType(char ch) {
10521 return getType((int)ch);
10522 }
10523
10524 /**
10525 * Returns a value indicating a character's general category.
10526 *
10527 * @param codePoint the character (Unicode code point) to be tested.
10528 * @return a value of type {@code int} representing the
10529 * character's general category.
10530 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
10531 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
10532 * @see Character#CONTROL CONTROL
10533 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
10534 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
10535 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
10536 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
10537 * @see Character#END_PUNCTUATION END_PUNCTUATION
10538 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
10539 * @see Character#FORMAT FORMAT
10540 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
10541 * @see Character#LETTER_NUMBER LETTER_NUMBER
10542 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
10543 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
10544 * @see Character#MATH_SYMBOL MATH_SYMBOL
10545 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
10546 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
10547 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
10548 * @see Character#OTHER_LETTER OTHER_LETTER
10549 * @see Character#OTHER_NUMBER OTHER_NUMBER
10550 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
10551 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
10552 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
10553 * @see Character#PRIVATE_USE PRIVATE_USE
10554 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
10555 * @see Character#START_PUNCTUATION START_PUNCTUATION
10556 * @see Character#SURROGATE SURROGATE
10557 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
10558 * @see Character#UNASSIGNED UNASSIGNED
10559 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
10560 * @since 1.5
10561 */
10562 public static int getType(int codePoint) {
10563 return CharacterData.of(codePoint).getType(codePoint);
10564 }
10565
10566 /**
10567 * Determines the character representation for a specific digit in
10568 * the specified radix. If the value of {@code radix} is not a
10569 * valid radix, or the value of {@code digit} is not a valid
10570 * digit in the specified radix, the null character
10571 * ({@code '\u005Cu0000'}) is returned.
10572 * <p>
10573 * The {@code radix} argument is valid if it is greater than or
10574 * equal to {@code MIN_RADIX} and less than or equal to
10575 * {@code MAX_RADIX}. The {@code digit} argument is valid if
10576 * {@code 0 <= digit < radix}.
10577 * <p>
10578 * If the digit is less than 10, then
10579 * {@code '0' + digit} is returned. Otherwise, the value
10580 * {@code 'a' + digit - 10} is returned.
10581 *
10582 * @param digit the number to convert to a character.
10583 * @param radix the radix.
10584 * @return the {@code char} representation of the specified digit
10585 * in the specified radix.
10586 * @see Character#MIN_RADIX
10587 * @see Character#MAX_RADIX
10588 * @see Character#digit(char, int)
10589 */
10590 public static char forDigit(int digit, int radix) {
10591 if ((digit >= radix) || (digit < 0)) {
10592 return '\0';
10593 }
10594 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
10595 return '\0';
10596 }
10597 if (digit < 10) {
10598 return (char)('0' + digit);
10599 }
10600 return (char)('a' - 10 + digit);
10601 }
10602
10603 /**
10604 * Returns the Unicode directionality property for the given
10605 * character. Character directionality is used to calculate the
10606 * visual ordering of text. The directionality value of undefined
10607 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
10608 *
10609 * <p><b>Note:</b> This method cannot handle <a
10610 * href="#supplementary"> supplementary characters</a>. To support
10611 * all Unicode characters, including supplementary characters, use
10612 * the {@link #getDirectionality(int)} method.
10613 *
10614 * @param ch {@code char} for which the directionality property
10615 * is requested.
10616 * @return the directionality property of the {@code char} value.
10617 *
10618 * @see Character#DIRECTIONALITY_UNDEFINED
10619 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
10620 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
10621 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
10622 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
10623 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
10624 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
10625 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
10626 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
10627 * @see Character#DIRECTIONALITY_NONSPACING_MARK
10628 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
10629 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
10630 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
10631 * @see Character#DIRECTIONALITY_WHITESPACE
10632 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
10633 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
10634 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
10635 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
10636 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
10637 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
10638 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
10639 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
10640 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
10641 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
10642 * @since 1.4
10643 */
10644 public static byte getDirectionality(char ch) {
10645 return getDirectionality((int)ch);
10646 }
10647
10648 /**
10649 * Returns the Unicode directionality property for the given
10650 * character (Unicode code point). Character directionality is
10651 * used to calculate the visual ordering of text. The
10652 * directionality value of undefined character is {@link
10653 * #DIRECTIONALITY_UNDEFINED}.
10654 *
10655 * @param codePoint the character (Unicode code point) for which
10656 * the directionality property is requested.
10657 * @return the directionality property of the character.
10658 *
10659 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
10660 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
10661 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
10662 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
10663 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
10664 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
10665 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
10666 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
10667 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
10668 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
10669 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
10670 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
10671 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
10672 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
10673 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
10674 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
10675 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
10676 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
10677 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
10678 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
10679 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
10680 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
10681 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
10682 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
10683 * @since 1.5
10684 */
10685 public static byte getDirectionality(int codePoint) {
10686 return CharacterData.of(codePoint).getDirectionality(codePoint);
10687 }
10688
10689 /**
10690 * Determines whether the character is mirrored according to the
10691 * Unicode specification. Mirrored characters should have their
10692 * glyphs horizontally mirrored when displayed in text that is
10693 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
10694 * PARENTHESIS is semantically defined to be an <i>opening
10695 * parenthesis</i>. This will appear as a "(" in text that is
10696 * left-to-right but as a ")" in text that is right-to-left.
10697 *
10698 * <p><b>Note:</b> This method cannot handle <a
10699 * href="#supplementary"> supplementary characters</a>. To support
10700 * all Unicode characters, including supplementary characters, use
10701 * the {@link #isMirrored(int)} method.
10702 *
10703 * @param ch {@code char} for which the mirrored property is requested
10704 * @return {@code true} if the char is mirrored, {@code false}
10705 * if the {@code char} is not mirrored or is not defined.
10706 * @since 1.4
10707 */
10708 public static boolean isMirrored(char ch) {
10709 return isMirrored((int)ch);
10710 }
10711
10712 /**
10713 * Determines whether the specified character (Unicode code point)
10714 * is mirrored according to the Unicode specification. Mirrored
10715 * characters should have their glyphs horizontally mirrored when
10716 * displayed in text that is right-to-left. For example,
10717 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
10718 * defined to be an <i>opening parenthesis</i>. This will appear
10719 * as a "(" in text that is left-to-right but as a ")" in text
10720 * that is right-to-left.
10721 *
10722 * @param codePoint the character (Unicode code point) to be tested.
10723 * @return {@code true} if the character is mirrored, {@code false}
10724 * if the character is not mirrored or is not defined.
10725 * @since 1.5
10726 */
10727 public static boolean isMirrored(int codePoint) {
10728 return CharacterData.of(codePoint).isMirrored(codePoint);
10729 }
10730
10731 /**
10732 * Compares two {@code Character} objects numerically.
10733 *
10734 * @param anotherCharacter the {@code Character} to be compared.
10735
10736 * @return the value {@code 0} if the argument {@code Character}
10737 * is equal to this {@code Character}; a value less than
10738 * {@code 0} if this {@code Character} is numerically less
10739 * than the {@code Character} argument; and a value greater than
10740 * {@code 0} if this {@code Character} is numerically greater
10741 * than the {@code Character} argument (unsigned comparison).
10742 * Note that this is strictly a numerical comparison; it is not
10743 * locale-dependent.
10744 * @since 1.2
10745 */
10746 public int compareTo(Character anotherCharacter) {
10747 return compare(this.value, anotherCharacter.value);
10748 }
10749
10750 /**
10751 * Compares two {@code char} values numerically.
10752 * The value returned is identical to what would be returned by:
10753 * <pre>
10754 * Character.valueOf(x).compareTo(Character.valueOf(y))
10755 * </pre>
10756 *
10757 * @param x the first {@code char} to compare
10758 * @param y the second {@code char} to compare
10759 * @return the value {@code 0} if {@code x == y};
10760 * a value less than {@code 0} if {@code x < y}; and
10761 * a value greater than {@code 0} if {@code x > y}
10762 * @since 1.7
10763 */
10764 public static int compare(char x, char y) {
10765 return x - y;
10766 }
10767
10768 /**
10769 * Converts the character (Unicode code point) argument to uppercase using
10770 * information from the UnicodeData file.
10771 *
10772 * @param codePoint the character (Unicode code point) to be converted.
10773 * @return either the uppercase equivalent of the character, if
10774 * any, or an error flag ({@code Character.ERROR})
10775 * that indicates that a 1:M {@code char} mapping exists.
10776 * @see Character#isLowerCase(char)
10777 * @see Character#isUpperCase(char)
10778 * @see Character#toLowerCase(char)
10779 * @see Character#toTitleCase(char)
10780 * @since 1.4
10781 */
10782 static int toUpperCaseEx(int codePoint) {
10783 assert isValidCodePoint(codePoint);
10784 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
10785 }
10786
10787 /**
10788 * Converts the character (Unicode code point) argument to uppercase using case
10789 * mapping information from the SpecialCasing file in the Unicode
10790 * specification. If a character has no explicit uppercase
10791 * mapping, then the {@code char} itself is returned in the
10792 * {@code char[]}.
10793 *
10794 * @param codePoint the character (Unicode code point) to be converted.
10795 * @return a {@code char[]} with the uppercased character.
10796 * @since 1.4
10797 */
10798 static char[] toUpperCaseCharArray(int codePoint) {
10799 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
10800 assert isBmpCodePoint(codePoint);
10801 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
10802 }
10803
10804 /**
10805 * The number of bits used to represent a {@code char} value in unsigned
10806 * binary form, constant {@code 16}.
10807 *
10808 * @since 1.5
10809 */
10810 public static final int SIZE = 16;
10811
10812 /**
10813 * The number of bytes used to represent a {@code char} value in unsigned
10814 * binary form.
10815 *
10816 * @since 1.8
10817 */
10818 public static final int BYTES = SIZE / Byte.SIZE;
10819
10820 /**
10821 * Returns the value obtained by reversing the order of the bytes in the
10822 * specified {@code char} value.
10823 *
10824 * @param ch The {@code char} of which to reverse the byte order.
10825 * @return the value obtained by reversing (or, equivalently, swapping)
10826 * the bytes in the specified {@code char} value.
10827 * @since 1.5
10828 */
10829 @HotSpotIntrinsicCandidate
10830 public static char reverseBytes(char ch) {
10831 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
10832 }
10833
10834 /**
10835 * Returns the Unicode name of the specified character
10836 * {@code codePoint}, or null if the code point is
10837 * {@link #UNASSIGNED unassigned}.
10838 * <p>
10839 * Note: if the specified character is not assigned a name by
10840 * the <i>UnicodeData</i> file (part of the Unicode Character
10841 * Database maintained by the Unicode Consortium), the returned
10842 * name is the same as the result of expression.
10843 *
10844 * <blockquote>{@code
10845 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
10846 * + " "
10847 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10848 *
10849 * }</blockquote>
10850 *
10851 * @param codePoint the character (Unicode code point)
10852 *
10853 * @return the Unicode name of the specified character, or null if
10854 * the code point is unassigned.
10855 *
10856 * @throws IllegalArgumentException if the specified
10857 * {@code codePoint} is not a valid Unicode
10858 * code point.
10859 *
10860 * @since 1.7
10861 */
10862 public static String getName(int codePoint) {
10863 if (!isValidCodePoint(codePoint)) {
10864 throw new IllegalArgumentException(
10865 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10866 }
10867 String name = CharacterName.getInstance().getName(codePoint);
10868 if (name != null)
10869 return name;
10870 if (getType(codePoint) == UNASSIGNED)
10871 return null;
10872 UnicodeBlock block = UnicodeBlock.of(codePoint);
10873 if (block != null)
10874 return block.toString().replace('_', ' ') + " "
10875 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10876 // should never come here
10877 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10878 }
10879
10880 /**
10881 * Returns the code point value of the Unicode character specified by
10882 * the given Unicode character name.
10883 * <p>
10884 * Note: if a character is not assigned a name by the <i>UnicodeData</i>
10885 * file (part of the Unicode Character Database maintained by the Unicode
10886 * Consortium), its name is defined as the result of expression
10887 *
10888 * <blockquote>{@code
10889 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
10890 * + " "
10891 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10892 *
10893 * }</blockquote>
10894 * <p>
10895 * The {@code name} matching is case insensitive, with any leading and
10896 * trailing whitespace character removed.
10897 *
10898 * @param name the Unicode character name
10899 *
10900 * @return the code point value of the character specified by its name.
10901 *
10902 * @throws IllegalArgumentException if the specified {@code name}
10903 * is not a valid Unicode character name.
10904 * @throws NullPointerException if {@code name} is {@code null}
10905 *
10906 * @since 9
10907 */
10908 public static int codePointOf(String name) {
10909 name = name.trim().toUpperCase(Locale.ROOT);
10910 int cp = CharacterName.getInstance().getCodePoint(name);
10911 if (cp != -1)
10912 return cp;
10913 try {
10914 int off = name.lastIndexOf(' ');
10915 if (off != -1) {
10916 cp = Integer.parseInt(name, off + 1, name.length(), 16);
10917 if (isValidCodePoint(cp) && name.equals(getName(cp)))
10918 return cp;
10919 }
10920 } catch (Exception x) {}
10921 throw new IllegalArgumentException("Unrecognized character name :" + name);
10922 }
10923 }