1 /*
2 * Copyright (c) 2002, 2018, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import java.util.Arrays;
29 import java.util.Map;
30 import java.util.HashMap;
31 import java.util.Locale;
32
33 import jdk.internal.HotSpotIntrinsicCandidate;
34
35 /**
36 * The {@code Character} class wraps a value of the primitive
37 * type {@code char} in an object. An object of type
38 * {@code Character} contains a single field whose type is
39 * {@code char}.
40 * <p>
41 * In addition, this class provides several methods for determining
42 * a character's category (lowercase letter, digit, etc.) and for converting
43 * characters from uppercase to lowercase and vice versa.
44 * <p>
45 * Character information is based on the Unicode Standard, version 10.0.0.
46 * <p>
47 * The methods and data of class {@code Character} are defined by
48 * the information in the <i>UnicodeData</i> file that is part of the
49 * Unicode Character Database maintained by the Unicode
50 * Consortium. This file specifies various properties including name
51 * and general category for every defined Unicode code point or
52 * character range.
53 * <p>
54 * The file and its description are available from the Unicode Consortium at:
55 * <ul>
56 * <li><a href="http://www.unicode.org">http://www.unicode.org</a>
57 * </ul>
58 *
59 * <h3><a id="unicode">Unicode Character Representations</a></h3>
60 *
61 * <p>The {@code char} data type (and therefore the value that a
62 * {@code Character} object encapsulates) are based on the
63 * original Unicode specification, which defined characters as
64 * fixed-width 16-bit entities. The Unicode Standard has since been
65 * changed to allow for characters whose representation requires more
66 * than 16 bits. The range of legal <em>code point</em>s is now
67 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
68 * (Refer to the <a
69 * href="http://www.unicode.org/reports/tr27/#notation"><i>
70 * definition</i></a> of the U+<i>n</i> notation in the Unicode
71 * Standard.)
72 *
73 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
74 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
75 * <a id="supplementary">Characters</a> whose code points are greater
76 * than U+FFFF are called <em>supplementary character</em>s. The Java
77 * platform uses the UTF-16 representation in {@code char} arrays and
78 * in the {@code String} and {@code StringBuffer} classes. In
79 * this representation, supplementary characters are represented as a pair
80 * of {@code char} values, the first from the <em>high-surrogates</em>
81 * range, (\uD800-\uDBFF), the second from the
82 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
83 *
84 * <p>A {@code char} value, therefore, represents Basic
85 * Multilingual Plane (BMP) code points, including the surrogate
86 * code points, or code units of the UTF-16 encoding. An
87 * {@code int} value represents all Unicode code points,
88 * including supplementary code points. The lower (least significant)
89 * 21 bits of {@code int} are used to represent Unicode code
90 * points and the upper (most significant) 11 bits must be zero.
91 * Unless otherwise specified, the behavior with respect to
92 * supplementary characters and surrogate {@code char} values is
93 * as follows:
94 *
95 * <ul>
96 * <li>The methods that only accept a {@code char} value cannot support
97 * supplementary characters. They treat {@code char} values from the
98 * surrogate ranges as undefined characters. For example,
99 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
100 * this specific value if followed by any low-surrogate value in a string
101 * would represent a letter.
102 *
103 * <li>The methods that accept an {@code int} value support all
104 * Unicode characters, including supplementary characters. For
105 * example, {@code Character.isLetter(0x2F81A)} returns
106 * {@code true} because the code point value represents a letter
107 * (a CJK ideograph).
108 * </ul>
109 *
110 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
111 * used for character values in the range between U+0000 and U+10FFFF,
112 * and <em>Unicode code unit</em> is used for 16-bit
113 * {@code char} values that are code units of the <em>UTF-16</em>
114 * encoding. For more information on Unicode terminology, refer to the
115 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
116 *
117 * @author Lee Boynton
118 * @author Guy Steele
119 * @author Akira Tanaka
120 * @author Martin Buchholz
121 * @author Ulf Zibis
122 * @since 1.0
123 */
124 public final
125 class Character implements java.io.Serializable, Comparable<Character> {
126 /**
127 * The minimum radix available for conversion to and from strings.
128 * The constant value of this field is the smallest value permitted
129 * for the radix argument in radix-conversion methods such as the
130 * {@code digit} method, the {@code forDigit} method, and the
131 * {@code toString} method of class {@code Integer}.
132 *
133 * @see Character#digit(char, int)
134 * @see Character#forDigit(int, int)
135 * @see Integer#toString(int, int)
136 * @see Integer#valueOf(String)
137 */
138 public static final int MIN_RADIX = 2;
139
140 /**
141 * The maximum radix available for conversion to and from strings.
142 * The constant value of this field is the largest value permitted
143 * for the radix argument in radix-conversion methods such as the
144 * {@code digit} method, the {@code forDigit} method, and the
145 * {@code toString} method of class {@code Integer}.
146 *
147 * @see Character#digit(char, int)
148 * @see Character#forDigit(int, int)
149 * @see Integer#toString(int, int)
150 * @see Integer#valueOf(String)
151 */
152 public static final int MAX_RADIX = 36;
153
154 /**
155 * The constant value of this field is the smallest value of type
156 * {@code char}, {@code '\u005Cu0000'}.
157 *
158 * @since 1.0.2
159 */
160 public static final char MIN_VALUE = '\u0000';
161
162 /**
163 * The constant value of this field is the largest value of type
164 * {@code char}, {@code '\u005CuFFFF'}.
165 *
166 * @since 1.0.2
167 */
168 public static final char MAX_VALUE = '\uFFFF';
169
170 /**
171 * The {@code Class} instance representing the primitive type
172 * {@code char}.
173 *
174 * @since 1.1
175 */
176 @SuppressWarnings("unchecked")
177 public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char");
178
179 /*
180 * Normative general types
181 */
182
183 /*
184 * General character types
185 */
186
187 /**
188 * General category "Cn" in the Unicode specification.
189 * @since 1.1
190 */
191 public static final byte UNASSIGNED = 0;
192
193 /**
194 * General category "Lu" in the Unicode specification.
195 * @since 1.1
196 */
197 public static final byte UPPERCASE_LETTER = 1;
198
199 /**
200 * General category "Ll" in the Unicode specification.
201 * @since 1.1
202 */
203 public static final byte LOWERCASE_LETTER = 2;
204
205 /**
206 * General category "Lt" in the Unicode specification.
207 * @since 1.1
208 */
209 public static final byte TITLECASE_LETTER = 3;
210
211 /**
212 * General category "Lm" in the Unicode specification.
213 * @since 1.1
214 */
215 public static final byte MODIFIER_LETTER = 4;
216
217 /**
218 * General category "Lo" in the Unicode specification.
219 * @since 1.1
220 */
221 public static final byte OTHER_LETTER = 5;
222
223 /**
224 * General category "Mn" in the Unicode specification.
225 * @since 1.1
226 */
227 public static final byte NON_SPACING_MARK = 6;
228
229 /**
230 * General category "Me" in the Unicode specification.
231 * @since 1.1
232 */
233 public static final byte ENCLOSING_MARK = 7;
234
235 /**
236 * General category "Mc" in the Unicode specification.
237 * @since 1.1
238 */
239 public static final byte COMBINING_SPACING_MARK = 8;
240
241 /**
242 * General category "Nd" in the Unicode specification.
243 * @since 1.1
244 */
245 public static final byte DECIMAL_DIGIT_NUMBER = 9;
246
247 /**
248 * General category "Nl" in the Unicode specification.
249 * @since 1.1
250 */
251 public static final byte LETTER_NUMBER = 10;
252
253 /**
254 * General category "No" in the Unicode specification.
255 * @since 1.1
256 */
257 public static final byte OTHER_NUMBER = 11;
258
259 /**
260 * General category "Zs" in the Unicode specification.
261 * @since 1.1
262 */
263 public static final byte SPACE_SEPARATOR = 12;
264
265 /**
266 * General category "Zl" in the Unicode specification.
267 * @since 1.1
268 */
269 public static final byte LINE_SEPARATOR = 13;
270
271 /**
272 * General category "Zp" in the Unicode specification.
273 * @since 1.1
274 */
275 public static final byte PARAGRAPH_SEPARATOR = 14;
276
277 /**
278 * General category "Cc" in the Unicode specification.
279 * @since 1.1
280 */
281 public static final byte CONTROL = 15;
282
283 /**
284 * General category "Cf" in the Unicode specification.
285 * @since 1.1
286 */
287 public static final byte FORMAT = 16;
288
289 /**
290 * General category "Co" in the Unicode specification.
291 * @since 1.1
292 */
293 public static final byte PRIVATE_USE = 18;
294
295 /**
296 * General category "Cs" in the Unicode specification.
297 * @since 1.1
298 */
299 public static final byte SURROGATE = 19;
300
301 /**
302 * General category "Pd" in the Unicode specification.
303 * @since 1.1
304 */
305 public static final byte DASH_PUNCTUATION = 20;
306
307 /**
308 * General category "Ps" in the Unicode specification.
309 * @since 1.1
310 */
311 public static final byte START_PUNCTUATION = 21;
312
313 /**
314 * General category "Pe" in the Unicode specification.
315 * @since 1.1
316 */
317 public static final byte END_PUNCTUATION = 22;
318
319 /**
320 * General category "Pc" in the Unicode specification.
321 * @since 1.1
322 */
323 public static final byte CONNECTOR_PUNCTUATION = 23;
324
325 /**
326 * General category "Po" in the Unicode specification.
327 * @since 1.1
328 */
329 public static final byte OTHER_PUNCTUATION = 24;
330
331 /**
332 * General category "Sm" in the Unicode specification.
333 * @since 1.1
334 */
335 public static final byte MATH_SYMBOL = 25;
336
337 /**
338 * General category "Sc" in the Unicode specification.
339 * @since 1.1
340 */
341 public static final byte CURRENCY_SYMBOL = 26;
342
343 /**
344 * General category "Sk" in the Unicode specification.
345 * @since 1.1
346 */
347 public static final byte MODIFIER_SYMBOL = 27;
348
349 /**
350 * General category "So" in the Unicode specification.
351 * @since 1.1
352 */
353 public static final byte OTHER_SYMBOL = 28;
354
355 /**
356 * General category "Pi" in the Unicode specification.
357 * @since 1.4
358 */
359 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
360
361 /**
362 * General category "Pf" in the Unicode specification.
363 * @since 1.4
364 */
365 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
366
367 /**
368 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
369 */
370 static final int ERROR = 0xFFFFFFFF;
371
372
373 /**
374 * Undefined bidirectional character type. Undefined {@code char}
375 * values have undefined directionality in the Unicode specification.
376 * @since 1.4
377 */
378 public static final byte DIRECTIONALITY_UNDEFINED = -1;
379
380 /**
381 * Strong bidirectional character type "L" in the Unicode specification.
382 * @since 1.4
383 */
384 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
385
386 /**
387 * Strong bidirectional character type "R" in the Unicode specification.
388 * @since 1.4
389 */
390 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
391
392 /**
393 * Strong bidirectional character type "AL" in the Unicode specification.
394 * @since 1.4
395 */
396 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
397
398 /**
399 * Weak bidirectional character type "EN" in the Unicode specification.
400 * @since 1.4
401 */
402 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
403
404 /**
405 * Weak bidirectional character type "ES" in the Unicode specification.
406 * @since 1.4
407 */
408 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
409
410 /**
411 * Weak bidirectional character type "ET" in the Unicode specification.
412 * @since 1.4
413 */
414 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
415
416 /**
417 * Weak bidirectional character type "AN" in the Unicode specification.
418 * @since 1.4
419 */
420 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
421
422 /**
423 * Weak bidirectional character type "CS" in the Unicode specification.
424 * @since 1.4
425 */
426 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
427
428 /**
429 * Weak bidirectional character type "NSM" in the Unicode specification.
430 * @since 1.4
431 */
432 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
433
434 /**
435 * Weak bidirectional character type "BN" in the Unicode specification.
436 * @since 1.4
437 */
438 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
439
440 /**
441 * Neutral bidirectional character type "B" in the Unicode specification.
442 * @since 1.4
443 */
444 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
445
446 /**
447 * Neutral bidirectional character type "S" in the Unicode specification.
448 * @since 1.4
449 */
450 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
451
452 /**
453 * Neutral bidirectional character type "WS" in the Unicode specification.
454 * @since 1.4
455 */
456 public static final byte DIRECTIONALITY_WHITESPACE = 12;
457
458 /**
459 * Neutral bidirectional character type "ON" in the Unicode specification.
460 * @since 1.4
461 */
462 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
463
464 /**
465 * Strong bidirectional character type "LRE" in the Unicode specification.
466 * @since 1.4
467 */
468 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
469
470 /**
471 * Strong bidirectional character type "LRO" in the Unicode specification.
472 * @since 1.4
473 */
474 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
475
476 /**
477 * Strong bidirectional character type "RLE" in the Unicode specification.
478 * @since 1.4
479 */
480 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
481
482 /**
483 * Strong bidirectional character type "RLO" in the Unicode specification.
484 * @since 1.4
485 */
486 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
487
488 /**
489 * Weak bidirectional character type "PDF" in the Unicode specification.
490 * @since 1.4
491 */
492 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
493
494 /**
495 * Weak bidirectional character type "LRI" in the Unicode specification.
496 * @since 9
497 */
498 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
499
500 /**
501 * Weak bidirectional character type "RLI" in the Unicode specification.
502 * @since 9
503 */
504 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
505
506 /**
507 * Weak bidirectional character type "FSI" in the Unicode specification.
508 * @since 9
509 */
510 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
511
512 /**
513 * Weak bidirectional character type "PDI" in the Unicode specification.
514 * @since 9
515 */
516 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
517
518 /**
519 * The minimum value of a
520 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
521 * Unicode high-surrogate code unit</a>
522 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
523 * A high-surrogate is also known as a <i>leading-surrogate</i>.
524 *
525 * @since 1.5
526 */
527 public static final char MIN_HIGH_SURROGATE = '\uD800';
528
529 /**
530 * The maximum value of a
531 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
532 * Unicode high-surrogate code unit</a>
533 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
534 * A high-surrogate is also known as a <i>leading-surrogate</i>.
535 *
536 * @since 1.5
537 */
538 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
539
540 /**
541 * The minimum value of a
542 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
543 * Unicode low-surrogate code unit</a>
544 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
545 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
546 *
547 * @since 1.5
548 */
549 public static final char MIN_LOW_SURROGATE = '\uDC00';
550
551 /**
552 * The maximum value of a
553 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
554 * Unicode low-surrogate code unit</a>
555 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
556 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
557 *
558 * @since 1.5
559 */
560 public static final char MAX_LOW_SURROGATE = '\uDFFF';
561
562 /**
563 * The minimum value of a Unicode surrogate code unit in the
564 * UTF-16 encoding, constant {@code '\u005CuD800'}.
565 *
566 * @since 1.5
567 */
568 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
569
570 /**
571 * The maximum value of a Unicode surrogate code unit in the
572 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
573 *
574 * @since 1.5
575 */
576 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
577
578 /**
579 * The minimum value of a
580 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
581 * Unicode supplementary code point</a>, constant {@code U+10000}.
582 *
583 * @since 1.5
584 */
585 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
586
587 /**
588 * The minimum value of a
589 * <a href="http://www.unicode.org/glossary/#code_point">
590 * Unicode code point</a>, constant {@code U+0000}.
591 *
592 * @since 1.5
593 */
594 public static final int MIN_CODE_POINT = 0x000000;
595
596 /**
597 * The maximum value of a
598 * <a href="http://www.unicode.org/glossary/#code_point">
599 * Unicode code point</a>, constant {@code U+10FFFF}.
600 *
601 * @since 1.5
602 */
603 public static final int MAX_CODE_POINT = 0X10FFFF;
604
605
606 /**
607 * Instances of this class represent particular subsets of the Unicode
608 * character set. The only family of subsets defined in the
609 * {@code Character} class is {@link Character.UnicodeBlock}.
610 * Other portions of the Java API may define other subsets for their
611 * own purposes.
612 *
613 * @since 1.2
614 */
615 public static class Subset {
616
617 private String name;
618
619 /**
620 * Constructs a new {@code Subset} instance.
621 *
622 * @param name The name of this subset
623 * @throws NullPointerException if name is {@code null}
624 */
625 protected Subset(String name) {
626 if (name == null) {
627 throw new NullPointerException("name");
628 }
629 this.name = name;
630 }
631
632 /**
633 * Compares two {@code Subset} objects for equality.
634 * This method returns {@code true} if and only if
635 * {@code this} and the argument refer to the same
636 * object; since this method is {@code final}, this
637 * guarantee holds for all subclasses.
638 */
639 public final boolean equals(Object obj) {
640 return (this == obj);
641 }
642
643 /**
644 * Returns the standard hash code as defined by the
645 * {@link Object#hashCode} method. This method
646 * is {@code final} in order to ensure that the
647 * {@code equals} and {@code hashCode} methods will
648 * be consistent in all subclasses.
649 */
650 public final int hashCode() {
651 return super.hashCode();
652 }
653
654 /**
655 * Returns the name of this subset.
656 */
657 public final String toString() {
658 return name;
659 }
660 }
661
662 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
663 // for the latest specification of Unicode Blocks.
664
665 /**
666 * A family of character subsets representing the character blocks in the
667 * Unicode specification. Character blocks generally define characters
668 * used for a specific script or purpose. A character is contained by
669 * at most one Unicode block.
670 *
671 * @since 1.2
672 */
673 public static final class UnicodeBlock extends Subset {
674 /**
675 * 638 - the expected number of entities
676 * 0.75 - the default load factor of HashMap
677 */
678 private static Map<String, UnicodeBlock> map =
679 new HashMap<>((int)(638 / 0.75f + 1.0f));
680
681 /**
682 * Creates a UnicodeBlock with the given identifier name.
683 * This name must be the same as the block identifier.
684 */
685 private UnicodeBlock(String idName) {
686 super(idName);
687 map.put(idName, this);
688 }
689
690 /**
691 * Creates a UnicodeBlock with the given identifier name and
692 * alias name.
693 */
694 private UnicodeBlock(String idName, String alias) {
695 this(idName);
696 map.put(alias, this);
697 }
698
699 /**
700 * Creates a UnicodeBlock with the given identifier name and
701 * alias names.
702 */
703 private UnicodeBlock(String idName, String... aliases) {
704 this(idName);
705 for (String alias : aliases)
706 map.put(alias, this);
707 }
708
709 /**
710 * Constant for the "Basic Latin" Unicode character block.
711 * @since 1.2
712 */
713 public static final UnicodeBlock BASIC_LATIN =
714 new UnicodeBlock("BASIC_LATIN",
715 "BASIC LATIN",
716 "BASICLATIN");
717
718 /**
719 * Constant for the "Latin-1 Supplement" Unicode character block.
720 * @since 1.2
721 */
722 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
723 new UnicodeBlock("LATIN_1_SUPPLEMENT",
724 "LATIN-1 SUPPLEMENT",
725 "LATIN-1SUPPLEMENT");
726
727 /**
728 * Constant for the "Latin Extended-A" Unicode character block.
729 * @since 1.2
730 */
731 public static final UnicodeBlock LATIN_EXTENDED_A =
732 new UnicodeBlock("LATIN_EXTENDED_A",
733 "LATIN EXTENDED-A",
734 "LATINEXTENDED-A");
735
736 /**
737 * Constant for the "Latin Extended-B" Unicode character block.
738 * @since 1.2
739 */
740 public static final UnicodeBlock LATIN_EXTENDED_B =
741 new UnicodeBlock("LATIN_EXTENDED_B",
742 "LATIN EXTENDED-B",
743 "LATINEXTENDED-B");
744
745 /**
746 * Constant for the "IPA Extensions" Unicode character block.
747 * @since 1.2
748 */
749 public static final UnicodeBlock IPA_EXTENSIONS =
750 new UnicodeBlock("IPA_EXTENSIONS",
751 "IPA EXTENSIONS",
752 "IPAEXTENSIONS");
753
754 /**
755 * Constant for the "Spacing Modifier Letters" Unicode character block.
756 * @since 1.2
757 */
758 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
759 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
760 "SPACING MODIFIER LETTERS",
761 "SPACINGMODIFIERLETTERS");
762
763 /**
764 * Constant for the "Combining Diacritical Marks" Unicode character block.
765 * @since 1.2
766 */
767 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
768 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
769 "COMBINING DIACRITICAL MARKS",
770 "COMBININGDIACRITICALMARKS");
771
772 /**
773 * Constant for the "Greek and Coptic" Unicode character block.
774 * <p>
775 * This block was previously known as the "Greek" block.
776 *
777 * @since 1.2
778 */
779 public static final UnicodeBlock GREEK =
780 new UnicodeBlock("GREEK",
781 "GREEK AND COPTIC",
782 "GREEKANDCOPTIC");
783
784 /**
785 * Constant for the "Cyrillic" Unicode character block.
786 * @since 1.2
787 */
788 public static final UnicodeBlock CYRILLIC =
789 new UnicodeBlock("CYRILLIC");
790
791 /**
792 * Constant for the "Armenian" Unicode character block.
793 * @since 1.2
794 */
795 public static final UnicodeBlock ARMENIAN =
796 new UnicodeBlock("ARMENIAN");
797
798 /**
799 * Constant for the "Hebrew" Unicode character block.
800 * @since 1.2
801 */
802 public static final UnicodeBlock HEBREW =
803 new UnicodeBlock("HEBREW");
804
805 /**
806 * Constant for the "Arabic" Unicode character block.
807 * @since 1.2
808 */
809 public static final UnicodeBlock ARABIC =
810 new UnicodeBlock("ARABIC");
811
812 /**
813 * Constant for the "Devanagari" Unicode character block.
814 * @since 1.2
815 */
816 public static final UnicodeBlock DEVANAGARI =
817 new UnicodeBlock("DEVANAGARI");
818
819 /**
820 * Constant for the "Bengali" Unicode character block.
821 * @since 1.2
822 */
823 public static final UnicodeBlock BENGALI =
824 new UnicodeBlock("BENGALI");
825
826 /**
827 * Constant for the "Gurmukhi" Unicode character block.
828 * @since 1.2
829 */
830 public static final UnicodeBlock GURMUKHI =
831 new UnicodeBlock("GURMUKHI");
832
833 /**
834 * Constant for the "Gujarati" Unicode character block.
835 * @since 1.2
836 */
837 public static final UnicodeBlock GUJARATI =
838 new UnicodeBlock("GUJARATI");
839
840 /**
841 * Constant for the "Oriya" Unicode character block.
842 * @since 1.2
843 */
844 public static final UnicodeBlock ORIYA =
845 new UnicodeBlock("ORIYA");
846
847 /**
848 * Constant for the "Tamil" Unicode character block.
849 * @since 1.2
850 */
851 public static final UnicodeBlock TAMIL =
852 new UnicodeBlock("TAMIL");
853
854 /**
855 * Constant for the "Telugu" Unicode character block.
856 * @since 1.2
857 */
858 public static final UnicodeBlock TELUGU =
859 new UnicodeBlock("TELUGU");
860
861 /**
862 * Constant for the "Kannada" Unicode character block.
863 * @since 1.2
864 */
865 public static final UnicodeBlock KANNADA =
866 new UnicodeBlock("KANNADA");
867
868 /**
869 * Constant for the "Malayalam" Unicode character block.
870 * @since 1.2
871 */
872 public static final UnicodeBlock MALAYALAM =
873 new UnicodeBlock("MALAYALAM");
874
875 /**
876 * Constant for the "Thai" Unicode character block.
877 * @since 1.2
878 */
879 public static final UnicodeBlock THAI =
880 new UnicodeBlock("THAI");
881
882 /**
883 * Constant for the "Lao" Unicode character block.
884 * @since 1.2
885 */
886 public static final UnicodeBlock LAO =
887 new UnicodeBlock("LAO");
888
889 /**
890 * Constant for the "Tibetan" Unicode character block.
891 * @since 1.2
892 */
893 public static final UnicodeBlock TIBETAN =
894 new UnicodeBlock("TIBETAN");
895
896 /**
897 * Constant for the "Georgian" Unicode character block.
898 * @since 1.2
899 */
900 public static final UnicodeBlock GEORGIAN =
901 new UnicodeBlock("GEORGIAN");
902
903 /**
904 * Constant for the "Hangul Jamo" Unicode character block.
905 * @since 1.2
906 */
907 public static final UnicodeBlock HANGUL_JAMO =
908 new UnicodeBlock("HANGUL_JAMO",
909 "HANGUL JAMO",
910 "HANGULJAMO");
911
912 /**
913 * Constant for the "Latin Extended Additional" Unicode character block.
914 * @since 1.2
915 */
916 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
917 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
918 "LATIN EXTENDED ADDITIONAL",
919 "LATINEXTENDEDADDITIONAL");
920
921 /**
922 * Constant for the "Greek Extended" Unicode character block.
923 * @since 1.2
924 */
925 public static final UnicodeBlock GREEK_EXTENDED =
926 new UnicodeBlock("GREEK_EXTENDED",
927 "GREEK EXTENDED",
928 "GREEKEXTENDED");
929
930 /**
931 * Constant for the "General Punctuation" Unicode character block.
932 * @since 1.2
933 */
934 public static final UnicodeBlock GENERAL_PUNCTUATION =
935 new UnicodeBlock("GENERAL_PUNCTUATION",
936 "GENERAL PUNCTUATION",
937 "GENERALPUNCTUATION");
938
939 /**
940 * Constant for the "Superscripts and Subscripts" Unicode character
941 * block.
942 * @since 1.2
943 */
944 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
945 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
946 "SUPERSCRIPTS AND SUBSCRIPTS",
947 "SUPERSCRIPTSANDSUBSCRIPTS");
948
949 /**
950 * Constant for the "Currency Symbols" Unicode character block.
951 * @since 1.2
952 */
953 public static final UnicodeBlock CURRENCY_SYMBOLS =
954 new UnicodeBlock("CURRENCY_SYMBOLS",
955 "CURRENCY SYMBOLS",
956 "CURRENCYSYMBOLS");
957
958 /**
959 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
960 * character block.
961 * <p>
962 * This block was previously known as "Combining Marks for Symbols".
963 * @since 1.2
964 */
965 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
966 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
967 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
968 "COMBININGDIACRITICALMARKSFORSYMBOLS",
969 "COMBINING MARKS FOR SYMBOLS",
970 "COMBININGMARKSFORSYMBOLS");
971
972 /**
973 * Constant for the "Letterlike Symbols" Unicode character block.
974 * @since 1.2
975 */
976 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
977 new UnicodeBlock("LETTERLIKE_SYMBOLS",
978 "LETTERLIKE SYMBOLS",
979 "LETTERLIKESYMBOLS");
980
981 /**
982 * Constant for the "Number Forms" Unicode character block.
983 * @since 1.2
984 */
985 public static final UnicodeBlock NUMBER_FORMS =
986 new UnicodeBlock("NUMBER_FORMS",
987 "NUMBER FORMS",
988 "NUMBERFORMS");
989
990 /**
991 * Constant for the "Arrows" Unicode character block.
992 * @since 1.2
993 */
994 public static final UnicodeBlock ARROWS =
995 new UnicodeBlock("ARROWS");
996
997 /**
998 * Constant for the "Mathematical Operators" Unicode character block.
999 * @since 1.2
1000 */
1001 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1002 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1003 "MATHEMATICAL OPERATORS",
1004 "MATHEMATICALOPERATORS");
1005
1006 /**
1007 * Constant for the "Miscellaneous Technical" Unicode character block.
1008 * @since 1.2
1009 */
1010 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1011 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1012 "MISCELLANEOUS TECHNICAL",
1013 "MISCELLANEOUSTECHNICAL");
1014
1015 /**
1016 * Constant for the "Control Pictures" Unicode character block.
1017 * @since 1.2
1018 */
1019 public static final UnicodeBlock CONTROL_PICTURES =
1020 new UnicodeBlock("CONTROL_PICTURES",
1021 "CONTROL PICTURES",
1022 "CONTROLPICTURES");
1023
1024 /**
1025 * Constant for the "Optical Character Recognition" Unicode character block.
1026 * @since 1.2
1027 */
1028 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1029 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1030 "OPTICAL CHARACTER RECOGNITION",
1031 "OPTICALCHARACTERRECOGNITION");
1032
1033 /**
1034 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1035 * @since 1.2
1036 */
1037 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1038 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1039 "ENCLOSED ALPHANUMERICS",
1040 "ENCLOSEDALPHANUMERICS");
1041
1042 /**
1043 * Constant for the "Box Drawing" Unicode character block.
1044 * @since 1.2
1045 */
1046 public static final UnicodeBlock BOX_DRAWING =
1047 new UnicodeBlock("BOX_DRAWING",
1048 "BOX DRAWING",
1049 "BOXDRAWING");
1050
1051 /**
1052 * Constant for the "Block Elements" Unicode character block.
1053 * @since 1.2
1054 */
1055 public static final UnicodeBlock BLOCK_ELEMENTS =
1056 new UnicodeBlock("BLOCK_ELEMENTS",
1057 "BLOCK ELEMENTS",
1058 "BLOCKELEMENTS");
1059
1060 /**
1061 * Constant for the "Geometric Shapes" Unicode character block.
1062 * @since 1.2
1063 */
1064 public static final UnicodeBlock GEOMETRIC_SHAPES =
1065 new UnicodeBlock("GEOMETRIC_SHAPES",
1066 "GEOMETRIC SHAPES",
1067 "GEOMETRICSHAPES");
1068
1069 /**
1070 * Constant for the "Miscellaneous Symbols" Unicode character block.
1071 * @since 1.2
1072 */
1073 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1074 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1075 "MISCELLANEOUS SYMBOLS",
1076 "MISCELLANEOUSSYMBOLS");
1077
1078 /**
1079 * Constant for the "Dingbats" Unicode character block.
1080 * @since 1.2
1081 */
1082 public static final UnicodeBlock DINGBATS =
1083 new UnicodeBlock("DINGBATS");
1084
1085 /**
1086 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1087 * @since 1.2
1088 */
1089 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1090 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1091 "CJK SYMBOLS AND PUNCTUATION",
1092 "CJKSYMBOLSANDPUNCTUATION");
1093
1094 /**
1095 * Constant for the "Hiragana" Unicode character block.
1096 * @since 1.2
1097 */
1098 public static final UnicodeBlock HIRAGANA =
1099 new UnicodeBlock("HIRAGANA");
1100
1101 /**
1102 * Constant for the "Katakana" Unicode character block.
1103 * @since 1.2
1104 */
1105 public static final UnicodeBlock KATAKANA =
1106 new UnicodeBlock("KATAKANA");
1107
1108 /**
1109 * Constant for the "Bopomofo" Unicode character block.
1110 * @since 1.2
1111 */
1112 public static final UnicodeBlock BOPOMOFO =
1113 new UnicodeBlock("BOPOMOFO");
1114
1115 /**
1116 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1117 * @since 1.2
1118 */
1119 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1120 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1121 "HANGUL COMPATIBILITY JAMO",
1122 "HANGULCOMPATIBILITYJAMO");
1123
1124 /**
1125 * Constant for the "Kanbun" Unicode character block.
1126 * @since 1.2
1127 */
1128 public static final UnicodeBlock KANBUN =
1129 new UnicodeBlock("KANBUN");
1130
1131 /**
1132 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1133 * @since 1.2
1134 */
1135 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1136 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1137 "ENCLOSED CJK LETTERS AND MONTHS",
1138 "ENCLOSEDCJKLETTERSANDMONTHS");
1139
1140 /**
1141 * Constant for the "CJK Compatibility" Unicode character block.
1142 * @since 1.2
1143 */
1144 public static final UnicodeBlock CJK_COMPATIBILITY =
1145 new UnicodeBlock("CJK_COMPATIBILITY",
1146 "CJK COMPATIBILITY",
1147 "CJKCOMPATIBILITY");
1148
1149 /**
1150 * Constant for the "CJK Unified Ideographs" Unicode character block.
1151 * @since 1.2
1152 */
1153 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1154 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1155 "CJK UNIFIED IDEOGRAPHS",
1156 "CJKUNIFIEDIDEOGRAPHS");
1157
1158 /**
1159 * Constant for the "Hangul Syllables" Unicode character block.
1160 * @since 1.2
1161 */
1162 public static final UnicodeBlock HANGUL_SYLLABLES =
1163 new UnicodeBlock("HANGUL_SYLLABLES",
1164 "HANGUL SYLLABLES",
1165 "HANGULSYLLABLES");
1166
1167 /**
1168 * Constant for the "Private Use Area" Unicode character block.
1169 * @since 1.2
1170 */
1171 public static final UnicodeBlock PRIVATE_USE_AREA =
1172 new UnicodeBlock("PRIVATE_USE_AREA",
1173 "PRIVATE USE AREA",
1174 "PRIVATEUSEAREA");
1175
1176 /**
1177 * Constant for the "CJK Compatibility Ideographs" Unicode character
1178 * block.
1179 * @since 1.2
1180 */
1181 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1182 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1183 "CJK COMPATIBILITY IDEOGRAPHS",
1184 "CJKCOMPATIBILITYIDEOGRAPHS");
1185
1186 /**
1187 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1188 * @since 1.2
1189 */
1190 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1191 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1192 "ALPHABETIC PRESENTATION FORMS",
1193 "ALPHABETICPRESENTATIONFORMS");
1194
1195 /**
1196 * Constant for the "Arabic Presentation Forms-A" Unicode character
1197 * block.
1198 * @since 1.2
1199 */
1200 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1201 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1202 "ARABIC PRESENTATION FORMS-A",
1203 "ARABICPRESENTATIONFORMS-A");
1204
1205 /**
1206 * Constant for the "Combining Half Marks" Unicode character block.
1207 * @since 1.2
1208 */
1209 public static final UnicodeBlock COMBINING_HALF_MARKS =
1210 new UnicodeBlock("COMBINING_HALF_MARKS",
1211 "COMBINING HALF MARKS",
1212 "COMBININGHALFMARKS");
1213
1214 /**
1215 * Constant for the "CJK Compatibility Forms" Unicode character block.
1216 * @since 1.2
1217 */
1218 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1219 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1220 "CJK COMPATIBILITY FORMS",
1221 "CJKCOMPATIBILITYFORMS");
1222
1223 /**
1224 * Constant for the "Small Form Variants" Unicode character block.
1225 * @since 1.2
1226 */
1227 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1228 new UnicodeBlock("SMALL_FORM_VARIANTS",
1229 "SMALL FORM VARIANTS",
1230 "SMALLFORMVARIANTS");
1231
1232 /**
1233 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1234 * @since 1.2
1235 */
1236 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1237 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1238 "ARABIC PRESENTATION FORMS-B",
1239 "ARABICPRESENTATIONFORMS-B");
1240
1241 /**
1242 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1243 * block.
1244 * @since 1.2
1245 */
1246 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1247 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1248 "HALFWIDTH AND FULLWIDTH FORMS",
1249 "HALFWIDTHANDFULLWIDTHFORMS");
1250
1251 /**
1252 * Constant for the "Specials" Unicode character block.
1253 * @since 1.2
1254 */
1255 public static final UnicodeBlock SPECIALS =
1256 new UnicodeBlock("SPECIALS");
1257
1258 /**
1259 * @deprecated
1260 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1261 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1262 * These constants match the block definitions of the Unicode Standard.
1263 * The {@link #of(char)} and {@link #of(int)} methods return the
1264 * standard constants.
1265 */
1266 @Deprecated(since="1.5")
1267 public static final UnicodeBlock SURROGATES_AREA =
1268 new UnicodeBlock("SURROGATES_AREA");
1269
1270 /**
1271 * Constant for the "Syriac" Unicode character block.
1272 * @since 1.4
1273 */
1274 public static final UnicodeBlock SYRIAC =
1275 new UnicodeBlock("SYRIAC");
1276
1277 /**
1278 * Constant for the "Thaana" Unicode character block.
1279 * @since 1.4
1280 */
1281 public static final UnicodeBlock THAANA =
1282 new UnicodeBlock("THAANA");
1283
1284 /**
1285 * Constant for the "Sinhala" Unicode character block.
1286 * @since 1.4
1287 */
1288 public static final UnicodeBlock SINHALA =
1289 new UnicodeBlock("SINHALA");
1290
1291 /**
1292 * Constant for the "Myanmar" Unicode character block.
1293 * @since 1.4
1294 */
1295 public static final UnicodeBlock MYANMAR =
1296 new UnicodeBlock("MYANMAR");
1297
1298 /**
1299 * Constant for the "Ethiopic" Unicode character block.
1300 * @since 1.4
1301 */
1302 public static final UnicodeBlock ETHIOPIC =
1303 new UnicodeBlock("ETHIOPIC");
1304
1305 /**
1306 * Constant for the "Cherokee" Unicode character block.
1307 * @since 1.4
1308 */
1309 public static final UnicodeBlock CHEROKEE =
1310 new UnicodeBlock("CHEROKEE");
1311
1312 /**
1313 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1314 * @since 1.4
1315 */
1316 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1317 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1318 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1319 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1320
1321 /**
1322 * Constant for the "Ogham" Unicode character block.
1323 * @since 1.4
1324 */
1325 public static final UnicodeBlock OGHAM =
1326 new UnicodeBlock("OGHAM");
1327
1328 /**
1329 * Constant for the "Runic" Unicode character block.
1330 * @since 1.4
1331 */
1332 public static final UnicodeBlock RUNIC =
1333 new UnicodeBlock("RUNIC");
1334
1335 /**
1336 * Constant for the "Khmer" Unicode character block.
1337 * @since 1.4
1338 */
1339 public static final UnicodeBlock KHMER =
1340 new UnicodeBlock("KHMER");
1341
1342 /**
1343 * Constant for the "Mongolian" Unicode character block.
1344 * @since 1.4
1345 */
1346 public static final UnicodeBlock MONGOLIAN =
1347 new UnicodeBlock("MONGOLIAN");
1348
1349 /**
1350 * Constant for the "Braille Patterns" Unicode character block.
1351 * @since 1.4
1352 */
1353 public static final UnicodeBlock BRAILLE_PATTERNS =
1354 new UnicodeBlock("BRAILLE_PATTERNS",
1355 "BRAILLE PATTERNS",
1356 "BRAILLEPATTERNS");
1357
1358 /**
1359 * Constant for the "CJK Radicals Supplement" Unicode character block.
1360 * @since 1.4
1361 */
1362 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1363 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1364 "CJK RADICALS SUPPLEMENT",
1365 "CJKRADICALSSUPPLEMENT");
1366
1367 /**
1368 * Constant for the "Kangxi Radicals" Unicode character block.
1369 * @since 1.4
1370 */
1371 public static final UnicodeBlock KANGXI_RADICALS =
1372 new UnicodeBlock("KANGXI_RADICALS",
1373 "KANGXI RADICALS",
1374 "KANGXIRADICALS");
1375
1376 /**
1377 * Constant for the "Ideographic Description Characters" Unicode character block.
1378 * @since 1.4
1379 */
1380 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1381 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1382 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1383 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1384
1385 /**
1386 * Constant for the "Bopomofo Extended" Unicode character block.
1387 * @since 1.4
1388 */
1389 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1390 new UnicodeBlock("BOPOMOFO_EXTENDED",
1391 "BOPOMOFO EXTENDED",
1392 "BOPOMOFOEXTENDED");
1393
1394 /**
1395 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1396 * @since 1.4
1397 */
1398 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1399 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1400 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1401 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1402
1403 /**
1404 * Constant for the "Yi Syllables" Unicode character block.
1405 * @since 1.4
1406 */
1407 public static final UnicodeBlock YI_SYLLABLES =
1408 new UnicodeBlock("YI_SYLLABLES",
1409 "YI SYLLABLES",
1410 "YISYLLABLES");
1411
1412 /**
1413 * Constant for the "Yi Radicals" Unicode character block.
1414 * @since 1.4
1415 */
1416 public static final UnicodeBlock YI_RADICALS =
1417 new UnicodeBlock("YI_RADICALS",
1418 "YI RADICALS",
1419 "YIRADICALS");
1420
1421 /**
1422 * Constant for the "Cyrillic Supplement" Unicode character block.
1423 * This block was previously known as the "Cyrillic Supplementary" block.
1424 * @since 1.5
1425 */
1426 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1427 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1428 "CYRILLIC SUPPLEMENTARY",
1429 "CYRILLICSUPPLEMENTARY",
1430 "CYRILLIC SUPPLEMENT",
1431 "CYRILLICSUPPLEMENT");
1432
1433 /**
1434 * Constant for the "Tagalog" Unicode character block.
1435 * @since 1.5
1436 */
1437 public static final UnicodeBlock TAGALOG =
1438 new UnicodeBlock("TAGALOG");
1439
1440 /**
1441 * Constant for the "Hanunoo" Unicode character block.
1442 * @since 1.5
1443 */
1444 public static final UnicodeBlock HANUNOO =
1445 new UnicodeBlock("HANUNOO");
1446
1447 /**
1448 * Constant for the "Buhid" Unicode character block.
1449 * @since 1.5
1450 */
1451 public static final UnicodeBlock BUHID =
1452 new UnicodeBlock("BUHID");
1453
1454 /**
1455 * Constant for the "Tagbanwa" Unicode character block.
1456 * @since 1.5
1457 */
1458 public static final UnicodeBlock TAGBANWA =
1459 new UnicodeBlock("TAGBANWA");
1460
1461 /**
1462 * Constant for the "Limbu" Unicode character block.
1463 * @since 1.5
1464 */
1465 public static final UnicodeBlock LIMBU =
1466 new UnicodeBlock("LIMBU");
1467
1468 /**
1469 * Constant for the "Tai Le" Unicode character block.
1470 * @since 1.5
1471 */
1472 public static final UnicodeBlock TAI_LE =
1473 new UnicodeBlock("TAI_LE",
1474 "TAI LE",
1475 "TAILE");
1476
1477 /**
1478 * Constant for the "Khmer Symbols" Unicode character block.
1479 * @since 1.5
1480 */
1481 public static final UnicodeBlock KHMER_SYMBOLS =
1482 new UnicodeBlock("KHMER_SYMBOLS",
1483 "KHMER SYMBOLS",
1484 "KHMERSYMBOLS");
1485
1486 /**
1487 * Constant for the "Phonetic Extensions" Unicode character block.
1488 * @since 1.5
1489 */
1490 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1491 new UnicodeBlock("PHONETIC_EXTENSIONS",
1492 "PHONETIC EXTENSIONS",
1493 "PHONETICEXTENSIONS");
1494
1495 /**
1496 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1497 * @since 1.5
1498 */
1499 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1500 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1501 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1502 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1503
1504 /**
1505 * Constant for the "Supplemental Arrows-A" Unicode character block.
1506 * @since 1.5
1507 */
1508 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1509 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1510 "SUPPLEMENTAL ARROWS-A",
1511 "SUPPLEMENTALARROWS-A");
1512
1513 /**
1514 * Constant for the "Supplemental Arrows-B" Unicode character block.
1515 * @since 1.5
1516 */
1517 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1518 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1519 "SUPPLEMENTAL ARROWS-B",
1520 "SUPPLEMENTALARROWS-B");
1521
1522 /**
1523 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1524 * character block.
1525 * @since 1.5
1526 */
1527 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1528 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1529 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1530 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1531
1532 /**
1533 * Constant for the "Supplemental Mathematical Operators" Unicode
1534 * character block.
1535 * @since 1.5
1536 */
1537 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1538 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1539 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1540 "SUPPLEMENTALMATHEMATICALOPERATORS");
1541
1542 /**
1543 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1544 * block.
1545 * @since 1.5
1546 */
1547 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1548 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1549 "MISCELLANEOUS SYMBOLS AND ARROWS",
1550 "MISCELLANEOUSSYMBOLSANDARROWS");
1551
1552 /**
1553 * Constant for the "Katakana Phonetic Extensions" Unicode character
1554 * block.
1555 * @since 1.5
1556 */
1557 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1558 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1559 "KATAKANA PHONETIC EXTENSIONS",
1560 "KATAKANAPHONETICEXTENSIONS");
1561
1562 /**
1563 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1564 * @since 1.5
1565 */
1566 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1567 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1568 "YIJING HEXAGRAM SYMBOLS",
1569 "YIJINGHEXAGRAMSYMBOLS");
1570
1571 /**
1572 * Constant for the "Variation Selectors" Unicode character block.
1573 * @since 1.5
1574 */
1575 public static final UnicodeBlock VARIATION_SELECTORS =
1576 new UnicodeBlock("VARIATION_SELECTORS",
1577 "VARIATION SELECTORS",
1578 "VARIATIONSELECTORS");
1579
1580 /**
1581 * Constant for the "Linear B Syllabary" Unicode character block.
1582 * @since 1.5
1583 */
1584 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1585 new UnicodeBlock("LINEAR_B_SYLLABARY",
1586 "LINEAR B SYLLABARY",
1587 "LINEARBSYLLABARY");
1588
1589 /**
1590 * Constant for the "Linear B Ideograms" Unicode character block.
1591 * @since 1.5
1592 */
1593 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1594 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1595 "LINEAR B IDEOGRAMS",
1596 "LINEARBIDEOGRAMS");
1597
1598 /**
1599 * Constant for the "Aegean Numbers" Unicode character block.
1600 * @since 1.5
1601 */
1602 public static final UnicodeBlock AEGEAN_NUMBERS =
1603 new UnicodeBlock("AEGEAN_NUMBERS",
1604 "AEGEAN NUMBERS",
1605 "AEGEANNUMBERS");
1606
1607 /**
1608 * Constant for the "Old Italic" Unicode character block.
1609 * @since 1.5
1610 */
1611 public static final UnicodeBlock OLD_ITALIC =
1612 new UnicodeBlock("OLD_ITALIC",
1613 "OLD ITALIC",
1614 "OLDITALIC");
1615
1616 /**
1617 * Constant for the "Gothic" Unicode character block.
1618 * @since 1.5
1619 */
1620 public static final UnicodeBlock GOTHIC =
1621 new UnicodeBlock("GOTHIC");
1622
1623 /**
1624 * Constant for the "Ugaritic" Unicode character block.
1625 * @since 1.5
1626 */
1627 public static final UnicodeBlock UGARITIC =
1628 new UnicodeBlock("UGARITIC");
1629
1630 /**
1631 * Constant for the "Deseret" Unicode character block.
1632 * @since 1.5
1633 */
1634 public static final UnicodeBlock DESERET =
1635 new UnicodeBlock("DESERET");
1636
1637 /**
1638 * Constant for the "Shavian" Unicode character block.
1639 * @since 1.5
1640 */
1641 public static final UnicodeBlock SHAVIAN =
1642 new UnicodeBlock("SHAVIAN");
1643
1644 /**
1645 * Constant for the "Osmanya" Unicode character block.
1646 * @since 1.5
1647 */
1648 public static final UnicodeBlock OSMANYA =
1649 new UnicodeBlock("OSMANYA");
1650
1651 /**
1652 * Constant for the "Cypriot Syllabary" Unicode character block.
1653 * @since 1.5
1654 */
1655 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1656 new UnicodeBlock("CYPRIOT_SYLLABARY",
1657 "CYPRIOT SYLLABARY",
1658 "CYPRIOTSYLLABARY");
1659
1660 /**
1661 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1662 * @since 1.5
1663 */
1664 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1665 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1666 "BYZANTINE MUSICAL SYMBOLS",
1667 "BYZANTINEMUSICALSYMBOLS");
1668
1669 /**
1670 * Constant for the "Musical Symbols" Unicode character block.
1671 * @since 1.5
1672 */
1673 public static final UnicodeBlock MUSICAL_SYMBOLS =
1674 new UnicodeBlock("MUSICAL_SYMBOLS",
1675 "MUSICAL SYMBOLS",
1676 "MUSICALSYMBOLS");
1677
1678 /**
1679 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1680 * @since 1.5
1681 */
1682 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1683 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1684 "TAI XUAN JING SYMBOLS",
1685 "TAIXUANJINGSYMBOLS");
1686
1687 /**
1688 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1689 * character block.
1690 * @since 1.5
1691 */
1692 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1693 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1694 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1695 "MATHEMATICALALPHANUMERICSYMBOLS");
1696
1697 /**
1698 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1699 * character block.
1700 * @since 1.5
1701 */
1702 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1703 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1704 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1705 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1706
1707 /**
1708 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1709 * @since 1.5
1710 */
1711 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1712 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1713 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1714 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1715
1716 /**
1717 * Constant for the "Tags" Unicode character block.
1718 * @since 1.5
1719 */
1720 public static final UnicodeBlock TAGS =
1721 new UnicodeBlock("TAGS");
1722
1723 /**
1724 * Constant for the "Variation Selectors Supplement" Unicode character
1725 * block.
1726 * @since 1.5
1727 */
1728 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1729 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1730 "VARIATION SELECTORS SUPPLEMENT",
1731 "VARIATIONSELECTORSSUPPLEMENT");
1732
1733 /**
1734 * Constant for the "Supplementary Private Use Area-A" Unicode character
1735 * block.
1736 * @since 1.5
1737 */
1738 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1739 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1740 "SUPPLEMENTARY PRIVATE USE AREA-A",
1741 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1742
1743 /**
1744 * Constant for the "Supplementary Private Use Area-B" Unicode character
1745 * block.
1746 * @since 1.5
1747 */
1748 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1749 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1750 "SUPPLEMENTARY PRIVATE USE AREA-B",
1751 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1752
1753 /**
1754 * Constant for the "High Surrogates" Unicode character block.
1755 * This block represents codepoint values in the high surrogate
1756 * range: U+D800 through U+DB7F
1757 *
1758 * @since 1.5
1759 */
1760 public static final UnicodeBlock HIGH_SURROGATES =
1761 new UnicodeBlock("HIGH_SURROGATES",
1762 "HIGH SURROGATES",
1763 "HIGHSURROGATES");
1764
1765 /**
1766 * Constant for the "High Private Use Surrogates" Unicode character
1767 * block.
1768 * This block represents codepoint values in the private use high
1769 * surrogate range: U+DB80 through U+DBFF
1770 *
1771 * @since 1.5
1772 */
1773 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1774 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1775 "HIGH PRIVATE USE SURROGATES",
1776 "HIGHPRIVATEUSESURROGATES");
1777
1778 /**
1779 * Constant for the "Low Surrogates" Unicode character block.
1780 * This block represents codepoint values in the low surrogate
1781 * range: U+DC00 through U+DFFF
1782 *
1783 * @since 1.5
1784 */
1785 public static final UnicodeBlock LOW_SURROGATES =
1786 new UnicodeBlock("LOW_SURROGATES",
1787 "LOW SURROGATES",
1788 "LOWSURROGATES");
1789
1790 /**
1791 * Constant for the "Arabic Supplement" Unicode character block.
1792 * @since 1.7
1793 */
1794 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1795 new UnicodeBlock("ARABIC_SUPPLEMENT",
1796 "ARABIC SUPPLEMENT",
1797 "ARABICSUPPLEMENT");
1798
1799 /**
1800 * Constant for the "NKo" Unicode character block.
1801 * @since 1.7
1802 */
1803 public static final UnicodeBlock NKO =
1804 new UnicodeBlock("NKO");
1805
1806 /**
1807 * Constant for the "Samaritan" Unicode character block.
1808 * @since 1.7
1809 */
1810 public static final UnicodeBlock SAMARITAN =
1811 new UnicodeBlock("SAMARITAN");
1812
1813 /**
1814 * Constant for the "Mandaic" Unicode character block.
1815 * @since 1.7
1816 */
1817 public static final UnicodeBlock MANDAIC =
1818 new UnicodeBlock("MANDAIC");
1819
1820 /**
1821 * Constant for the "Ethiopic Supplement" Unicode character block.
1822 * @since 1.7
1823 */
1824 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1825 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1826 "ETHIOPIC SUPPLEMENT",
1827 "ETHIOPICSUPPLEMENT");
1828
1829 /**
1830 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1831 * Unicode character block.
1832 * @since 1.7
1833 */
1834 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1835 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1836 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1837 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1838
1839 /**
1840 * Constant for the "New Tai Lue" Unicode character block.
1841 * @since 1.7
1842 */
1843 public static final UnicodeBlock NEW_TAI_LUE =
1844 new UnicodeBlock("NEW_TAI_LUE",
1845 "NEW TAI LUE",
1846 "NEWTAILUE");
1847
1848 /**
1849 * Constant for the "Buginese" Unicode character block.
1850 * @since 1.7
1851 */
1852 public static final UnicodeBlock BUGINESE =
1853 new UnicodeBlock("BUGINESE");
1854
1855 /**
1856 * Constant for the "Tai Tham" Unicode character block.
1857 * @since 1.7
1858 */
1859 public static final UnicodeBlock TAI_THAM =
1860 new UnicodeBlock("TAI_THAM",
1861 "TAI THAM",
1862 "TAITHAM");
1863
1864 /**
1865 * Constant for the "Balinese" Unicode character block.
1866 * @since 1.7
1867 */
1868 public static final UnicodeBlock BALINESE =
1869 new UnicodeBlock("BALINESE");
1870
1871 /**
1872 * Constant for the "Sundanese" Unicode character block.
1873 * @since 1.7
1874 */
1875 public static final UnicodeBlock SUNDANESE =
1876 new UnicodeBlock("SUNDANESE");
1877
1878 /**
1879 * Constant for the "Batak" Unicode character block.
1880 * @since 1.7
1881 */
1882 public static final UnicodeBlock BATAK =
1883 new UnicodeBlock("BATAK");
1884
1885 /**
1886 * Constant for the "Lepcha" Unicode character block.
1887 * @since 1.7
1888 */
1889 public static final UnicodeBlock LEPCHA =
1890 new UnicodeBlock("LEPCHA");
1891
1892 /**
1893 * Constant for the "Ol Chiki" Unicode character block.
1894 * @since 1.7
1895 */
1896 public static final UnicodeBlock OL_CHIKI =
1897 new UnicodeBlock("OL_CHIKI",
1898 "OL CHIKI",
1899 "OLCHIKI");
1900
1901 /**
1902 * Constant for the "Vedic Extensions" Unicode character block.
1903 * @since 1.7
1904 */
1905 public static final UnicodeBlock VEDIC_EXTENSIONS =
1906 new UnicodeBlock("VEDIC_EXTENSIONS",
1907 "VEDIC EXTENSIONS",
1908 "VEDICEXTENSIONS");
1909
1910 /**
1911 * Constant for the "Phonetic Extensions Supplement" Unicode character
1912 * block.
1913 * @since 1.7
1914 */
1915 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1916 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1917 "PHONETIC EXTENSIONS SUPPLEMENT",
1918 "PHONETICEXTENSIONSSUPPLEMENT");
1919
1920 /**
1921 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1922 * character block.
1923 * @since 1.7
1924 */
1925 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1926 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1927 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1928 "COMBININGDIACRITICALMARKSSUPPLEMENT");
1929
1930 /**
1931 * Constant for the "Glagolitic" Unicode character block.
1932 * @since 1.7
1933 */
1934 public static final UnicodeBlock GLAGOLITIC =
1935 new UnicodeBlock("GLAGOLITIC");
1936
1937 /**
1938 * Constant for the "Latin Extended-C" Unicode character block.
1939 * @since 1.7
1940 */
1941 public static final UnicodeBlock LATIN_EXTENDED_C =
1942 new UnicodeBlock("LATIN_EXTENDED_C",
1943 "LATIN EXTENDED-C",
1944 "LATINEXTENDED-C");
1945
1946 /**
1947 * Constant for the "Coptic" Unicode character block.
1948 * @since 1.7
1949 */
1950 public static final UnicodeBlock COPTIC =
1951 new UnicodeBlock("COPTIC");
1952
1953 /**
1954 * Constant for the "Georgian Supplement" Unicode character block.
1955 * @since 1.7
1956 */
1957 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
1958 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
1959 "GEORGIAN SUPPLEMENT",
1960 "GEORGIANSUPPLEMENT");
1961
1962 /**
1963 * Constant for the "Tifinagh" Unicode character block.
1964 * @since 1.7
1965 */
1966 public static final UnicodeBlock TIFINAGH =
1967 new UnicodeBlock("TIFINAGH");
1968
1969 /**
1970 * Constant for the "Ethiopic Extended" Unicode character block.
1971 * @since 1.7
1972 */
1973 public static final UnicodeBlock ETHIOPIC_EXTENDED =
1974 new UnicodeBlock("ETHIOPIC_EXTENDED",
1975 "ETHIOPIC EXTENDED",
1976 "ETHIOPICEXTENDED");
1977
1978 /**
1979 * Constant for the "Cyrillic Extended-A" Unicode character block.
1980 * @since 1.7
1981 */
1982 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
1983 new UnicodeBlock("CYRILLIC_EXTENDED_A",
1984 "CYRILLIC EXTENDED-A",
1985 "CYRILLICEXTENDED-A");
1986
1987 /**
1988 * Constant for the "Supplemental Punctuation" Unicode character block.
1989 * @since 1.7
1990 */
1991 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
1992 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
1993 "SUPPLEMENTAL PUNCTUATION",
1994 "SUPPLEMENTALPUNCTUATION");
1995
1996 /**
1997 * Constant for the "CJK Strokes" Unicode character block.
1998 * @since 1.7
1999 */
2000 public static final UnicodeBlock CJK_STROKES =
2001 new UnicodeBlock("CJK_STROKES",
2002 "CJK STROKES",
2003 "CJKSTROKES");
2004
2005 /**
2006 * Constant for the "Lisu" Unicode character block.
2007 * @since 1.7
2008 */
2009 public static final UnicodeBlock LISU =
2010 new UnicodeBlock("LISU");
2011
2012 /**
2013 * Constant for the "Vai" Unicode character block.
2014 * @since 1.7
2015 */
2016 public static final UnicodeBlock VAI =
2017 new UnicodeBlock("VAI");
2018
2019 /**
2020 * Constant for the "Cyrillic Extended-B" Unicode character block.
2021 * @since 1.7
2022 */
2023 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2024 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2025 "CYRILLIC EXTENDED-B",
2026 "CYRILLICEXTENDED-B");
2027
2028 /**
2029 * Constant for the "Bamum" Unicode character block.
2030 * @since 1.7
2031 */
2032 public static final UnicodeBlock BAMUM =
2033 new UnicodeBlock("BAMUM");
2034
2035 /**
2036 * Constant for the "Modifier Tone Letters" Unicode character block.
2037 * @since 1.7
2038 */
2039 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2040 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2041 "MODIFIER TONE LETTERS",
2042 "MODIFIERTONELETTERS");
2043
2044 /**
2045 * Constant for the "Latin Extended-D" Unicode character block.
2046 * @since 1.7
2047 */
2048 public static final UnicodeBlock LATIN_EXTENDED_D =
2049 new UnicodeBlock("LATIN_EXTENDED_D",
2050 "LATIN EXTENDED-D",
2051 "LATINEXTENDED-D");
2052
2053 /**
2054 * Constant for the "Syloti Nagri" Unicode character block.
2055 * @since 1.7
2056 */
2057 public static final UnicodeBlock SYLOTI_NAGRI =
2058 new UnicodeBlock("SYLOTI_NAGRI",
2059 "SYLOTI NAGRI",
2060 "SYLOTINAGRI");
2061
2062 /**
2063 * Constant for the "Common Indic Number Forms" Unicode character block.
2064 * @since 1.7
2065 */
2066 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2067 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2068 "COMMON INDIC NUMBER FORMS",
2069 "COMMONINDICNUMBERFORMS");
2070
2071 /**
2072 * Constant for the "Phags-pa" Unicode character block.
2073 * @since 1.7
2074 */
2075 public static final UnicodeBlock PHAGS_PA =
2076 new UnicodeBlock("PHAGS_PA",
2077 "PHAGS-PA");
2078
2079 /**
2080 * Constant for the "Saurashtra" Unicode character block.
2081 * @since 1.7
2082 */
2083 public static final UnicodeBlock SAURASHTRA =
2084 new UnicodeBlock("SAURASHTRA");
2085
2086 /**
2087 * Constant for the "Devanagari Extended" Unicode character block.
2088 * @since 1.7
2089 */
2090 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2091 new UnicodeBlock("DEVANAGARI_EXTENDED",
2092 "DEVANAGARI EXTENDED",
2093 "DEVANAGARIEXTENDED");
2094
2095 /**
2096 * Constant for the "Kayah Li" Unicode character block.
2097 * @since 1.7
2098 */
2099 public static final UnicodeBlock KAYAH_LI =
2100 new UnicodeBlock("KAYAH_LI",
2101 "KAYAH LI",
2102 "KAYAHLI");
2103
2104 /**
2105 * Constant for the "Rejang" Unicode character block.
2106 * @since 1.7
2107 */
2108 public static final UnicodeBlock REJANG =
2109 new UnicodeBlock("REJANG");
2110
2111 /**
2112 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2113 * @since 1.7
2114 */
2115 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2116 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2117 "HANGUL JAMO EXTENDED-A",
2118 "HANGULJAMOEXTENDED-A");
2119
2120 /**
2121 * Constant for the "Javanese" Unicode character block.
2122 * @since 1.7
2123 */
2124 public static final UnicodeBlock JAVANESE =
2125 new UnicodeBlock("JAVANESE");
2126
2127 /**
2128 * Constant for the "Cham" Unicode character block.
2129 * @since 1.7
2130 */
2131 public static final UnicodeBlock CHAM =
2132 new UnicodeBlock("CHAM");
2133
2134 /**
2135 * Constant for the "Myanmar Extended-A" Unicode character block.
2136 * @since 1.7
2137 */
2138 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2139 new UnicodeBlock("MYANMAR_EXTENDED_A",
2140 "MYANMAR EXTENDED-A",
2141 "MYANMAREXTENDED-A");
2142
2143 /**
2144 * Constant for the "Tai Viet" Unicode character block.
2145 * @since 1.7
2146 */
2147 public static final UnicodeBlock TAI_VIET =
2148 new UnicodeBlock("TAI_VIET",
2149 "TAI VIET",
2150 "TAIVIET");
2151
2152 /**
2153 * Constant for the "Ethiopic Extended-A" Unicode character block.
2154 * @since 1.7
2155 */
2156 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2157 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2158 "ETHIOPIC EXTENDED-A",
2159 "ETHIOPICEXTENDED-A");
2160
2161 /**
2162 * Constant for the "Meetei Mayek" Unicode character block.
2163 * @since 1.7
2164 */
2165 public static final UnicodeBlock MEETEI_MAYEK =
2166 new UnicodeBlock("MEETEI_MAYEK",
2167 "MEETEI MAYEK",
2168 "MEETEIMAYEK");
2169
2170 /**
2171 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2172 * @since 1.7
2173 */
2174 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2175 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2176 "HANGUL JAMO EXTENDED-B",
2177 "HANGULJAMOEXTENDED-B");
2178
2179 /**
2180 * Constant for the "Vertical Forms" Unicode character block.
2181 * @since 1.7
2182 */
2183 public static final UnicodeBlock VERTICAL_FORMS =
2184 new UnicodeBlock("VERTICAL_FORMS",
2185 "VERTICAL FORMS",
2186 "VERTICALFORMS");
2187
2188 /**
2189 * Constant for the "Ancient Greek Numbers" Unicode character block.
2190 * @since 1.7
2191 */
2192 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2193 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2194 "ANCIENT GREEK NUMBERS",
2195 "ANCIENTGREEKNUMBERS");
2196
2197 /**
2198 * Constant for the "Ancient Symbols" Unicode character block.
2199 * @since 1.7
2200 */
2201 public static final UnicodeBlock ANCIENT_SYMBOLS =
2202 new UnicodeBlock("ANCIENT_SYMBOLS",
2203 "ANCIENT SYMBOLS",
2204 "ANCIENTSYMBOLS");
2205
2206 /**
2207 * Constant for the "Phaistos Disc" Unicode character block.
2208 * @since 1.7
2209 */
2210 public static final UnicodeBlock PHAISTOS_DISC =
2211 new UnicodeBlock("PHAISTOS_DISC",
2212 "PHAISTOS DISC",
2213 "PHAISTOSDISC");
2214
2215 /**
2216 * Constant for the "Lycian" Unicode character block.
2217 * @since 1.7
2218 */
2219 public static final UnicodeBlock LYCIAN =
2220 new UnicodeBlock("LYCIAN");
2221
2222 /**
2223 * Constant for the "Carian" Unicode character block.
2224 * @since 1.7
2225 */
2226 public static final UnicodeBlock CARIAN =
2227 new UnicodeBlock("CARIAN");
2228
2229 /**
2230 * Constant for the "Old Persian" Unicode character block.
2231 * @since 1.7
2232 */
2233 public static final UnicodeBlock OLD_PERSIAN =
2234 new UnicodeBlock("OLD_PERSIAN",
2235 "OLD PERSIAN",
2236 "OLDPERSIAN");
2237
2238 /**
2239 * Constant for the "Imperial Aramaic" Unicode character block.
2240 * @since 1.7
2241 */
2242 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2243 new UnicodeBlock("IMPERIAL_ARAMAIC",
2244 "IMPERIAL ARAMAIC",
2245 "IMPERIALARAMAIC");
2246
2247 /**
2248 * Constant for the "Phoenician" Unicode character block.
2249 * @since 1.7
2250 */
2251 public static final UnicodeBlock PHOENICIAN =
2252 new UnicodeBlock("PHOENICIAN");
2253
2254 /**
2255 * Constant for the "Lydian" Unicode character block.
2256 * @since 1.7
2257 */
2258 public static final UnicodeBlock LYDIAN =
2259 new UnicodeBlock("LYDIAN");
2260
2261 /**
2262 * Constant for the "Kharoshthi" Unicode character block.
2263 * @since 1.7
2264 */
2265 public static final UnicodeBlock KHAROSHTHI =
2266 new UnicodeBlock("KHAROSHTHI");
2267
2268 /**
2269 * Constant for the "Old South Arabian" Unicode character block.
2270 * @since 1.7
2271 */
2272 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2273 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2274 "OLD SOUTH ARABIAN",
2275 "OLDSOUTHARABIAN");
2276
2277 /**
2278 * Constant for the "Avestan" Unicode character block.
2279 * @since 1.7
2280 */
2281 public static final UnicodeBlock AVESTAN =
2282 new UnicodeBlock("AVESTAN");
2283
2284 /**
2285 * Constant for the "Inscriptional Parthian" Unicode character block.
2286 * @since 1.7
2287 */
2288 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2289 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2290 "INSCRIPTIONAL PARTHIAN",
2291 "INSCRIPTIONALPARTHIAN");
2292
2293 /**
2294 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2295 * @since 1.7
2296 */
2297 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2298 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2299 "INSCRIPTIONAL PAHLAVI",
2300 "INSCRIPTIONALPAHLAVI");
2301
2302 /**
2303 * Constant for the "Old Turkic" Unicode character block.
2304 * @since 1.7
2305 */
2306 public static final UnicodeBlock OLD_TURKIC =
2307 new UnicodeBlock("OLD_TURKIC",
2308 "OLD TURKIC",
2309 "OLDTURKIC");
2310
2311 /**
2312 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2313 * @since 1.7
2314 */
2315 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2316 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2317 "RUMI NUMERAL SYMBOLS",
2318 "RUMINUMERALSYMBOLS");
2319
2320 /**
2321 * Constant for the "Brahmi" Unicode character block.
2322 * @since 1.7
2323 */
2324 public static final UnicodeBlock BRAHMI =
2325 new UnicodeBlock("BRAHMI");
2326
2327 /**
2328 * Constant for the "Kaithi" Unicode character block.
2329 * @since 1.7
2330 */
2331 public static final UnicodeBlock KAITHI =
2332 new UnicodeBlock("KAITHI");
2333
2334 /**
2335 * Constant for the "Cuneiform" Unicode character block.
2336 * @since 1.7
2337 */
2338 public static final UnicodeBlock CUNEIFORM =
2339 new UnicodeBlock("CUNEIFORM");
2340
2341 /**
2342 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2343 * character block.
2344 * @since 1.7
2345 */
2346 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2347 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2348 "CUNEIFORM NUMBERS AND PUNCTUATION",
2349 "CUNEIFORMNUMBERSANDPUNCTUATION");
2350
2351 /**
2352 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2353 * @since 1.7
2354 */
2355 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2356 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2357 "EGYPTIAN HIEROGLYPHS",
2358 "EGYPTIANHIEROGLYPHS");
2359
2360 /**
2361 * Constant for the "Bamum Supplement" Unicode character block.
2362 * @since 1.7
2363 */
2364 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2365 new UnicodeBlock("BAMUM_SUPPLEMENT",
2366 "BAMUM SUPPLEMENT",
2367 "BAMUMSUPPLEMENT");
2368
2369 /**
2370 * Constant for the "Kana Supplement" Unicode character block.
2371 * @since 1.7
2372 */
2373 public static final UnicodeBlock KANA_SUPPLEMENT =
2374 new UnicodeBlock("KANA_SUPPLEMENT",
2375 "KANA SUPPLEMENT",
2376 "KANASUPPLEMENT");
2377
2378 /**
2379 * Constant for the "Ancient Greek Musical Notation" Unicode character
2380 * block.
2381 * @since 1.7
2382 */
2383 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2384 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2385 "ANCIENT GREEK MUSICAL NOTATION",
2386 "ANCIENTGREEKMUSICALNOTATION");
2387
2388 /**
2389 * Constant for the "Counting Rod Numerals" Unicode character block.
2390 * @since 1.7
2391 */
2392 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2393 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2394 "COUNTING ROD NUMERALS",
2395 "COUNTINGRODNUMERALS");
2396
2397 /**
2398 * Constant for the "Mahjong Tiles" Unicode character block.
2399 * @since 1.7
2400 */
2401 public static final UnicodeBlock MAHJONG_TILES =
2402 new UnicodeBlock("MAHJONG_TILES",
2403 "MAHJONG TILES",
2404 "MAHJONGTILES");
2405
2406 /**
2407 * Constant for the "Domino Tiles" Unicode character block.
2408 * @since 1.7
2409 */
2410 public static final UnicodeBlock DOMINO_TILES =
2411 new UnicodeBlock("DOMINO_TILES",
2412 "DOMINO TILES",
2413 "DOMINOTILES");
2414
2415 /**
2416 * Constant for the "Playing Cards" Unicode character block.
2417 * @since 1.7
2418 */
2419 public static final UnicodeBlock PLAYING_CARDS =
2420 new UnicodeBlock("PLAYING_CARDS",
2421 "PLAYING CARDS",
2422 "PLAYINGCARDS");
2423
2424 /**
2425 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2426 * block.
2427 * @since 1.7
2428 */
2429 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2430 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2431 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2432 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2433
2434 /**
2435 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2436 * block.
2437 * @since 1.7
2438 */
2439 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2440 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2441 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2442 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2443
2444 /**
2445 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2446 * character block.
2447 * @since 1.7
2448 */
2449 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2450 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2451 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2452 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2453
2454 /**
2455 * Constant for the "Emoticons" Unicode character block.
2456 * @since 1.7
2457 */
2458 public static final UnicodeBlock EMOTICONS =
2459 new UnicodeBlock("EMOTICONS");
2460
2461 /**
2462 * Constant for the "Transport And Map Symbols" Unicode character block.
2463 * @since 1.7
2464 */
2465 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2466 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2467 "TRANSPORT AND MAP SYMBOLS",
2468 "TRANSPORTANDMAPSYMBOLS");
2469
2470 /**
2471 * Constant for the "Alchemical Symbols" Unicode character block.
2472 * @since 1.7
2473 */
2474 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2475 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2476 "ALCHEMICAL SYMBOLS",
2477 "ALCHEMICALSYMBOLS");
2478
2479 /**
2480 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2481 * character block.
2482 * @since 1.7
2483 */
2484 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2485 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2486 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2487 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2488
2489 /**
2490 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2491 * character block.
2492 * @since 1.7
2493 */
2494 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2495 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2496 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2497 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2498
2499 /**
2500 * Constant for the "Arabic Extended-A" Unicode character block.
2501 * @since 1.8
2502 */
2503 public static final UnicodeBlock ARABIC_EXTENDED_A =
2504 new UnicodeBlock("ARABIC_EXTENDED_A",
2505 "ARABIC EXTENDED-A",
2506 "ARABICEXTENDED-A");
2507
2508 /**
2509 * Constant for the "Sundanese Supplement" Unicode character block.
2510 * @since 1.8
2511 */
2512 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2513 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2514 "SUNDANESE SUPPLEMENT",
2515 "SUNDANESESUPPLEMENT");
2516
2517 /**
2518 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2519 * @since 1.8
2520 */
2521 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2522 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2523 "MEETEI MAYEK EXTENSIONS",
2524 "MEETEIMAYEKEXTENSIONS");
2525
2526 /**
2527 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2528 * @since 1.8
2529 */
2530 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2531 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2532 "MEROITIC HIEROGLYPHS",
2533 "MEROITICHIEROGLYPHS");
2534
2535 /**
2536 * Constant for the "Meroitic Cursive" Unicode character block.
2537 * @since 1.8
2538 */
2539 public static final UnicodeBlock MEROITIC_CURSIVE =
2540 new UnicodeBlock("MEROITIC_CURSIVE",
2541 "MEROITIC CURSIVE",
2542 "MEROITICCURSIVE");
2543
2544 /**
2545 * Constant for the "Sora Sompeng" Unicode character block.
2546 * @since 1.8
2547 */
2548 public static final UnicodeBlock SORA_SOMPENG =
2549 new UnicodeBlock("SORA_SOMPENG",
2550 "SORA SOMPENG",
2551 "SORASOMPENG");
2552
2553 /**
2554 * Constant for the "Chakma" Unicode character block.
2555 * @since 1.8
2556 */
2557 public static final UnicodeBlock CHAKMA =
2558 new UnicodeBlock("CHAKMA");
2559
2560 /**
2561 * Constant for the "Sharada" Unicode character block.
2562 * @since 1.8
2563 */
2564 public static final UnicodeBlock SHARADA =
2565 new UnicodeBlock("SHARADA");
2566
2567 /**
2568 * Constant for the "Takri" Unicode character block.
2569 * @since 1.8
2570 */
2571 public static final UnicodeBlock TAKRI =
2572 new UnicodeBlock("TAKRI");
2573
2574 /**
2575 * Constant for the "Miao" Unicode character block.
2576 * @since 1.8
2577 */
2578 public static final UnicodeBlock MIAO =
2579 new UnicodeBlock("MIAO");
2580
2581 /**
2582 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2583 * character block.
2584 * @since 1.8
2585 */
2586 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2587 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2588 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2589 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2590
2591 /**
2592 * Constant for the "Combining Diacritical Marks Extended" Unicode
2593 * character block.
2594 * @since 9
2595 */
2596 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2597 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2598 "COMBINING DIACRITICAL MARKS EXTENDED",
2599 "COMBININGDIACRITICALMARKSEXTENDED");
2600
2601 /**
2602 * Constant for the "Myanmar Extended-B" Unicode character block.
2603 * @since 9
2604 */
2605 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2606 new UnicodeBlock("MYANMAR_EXTENDED_B",
2607 "MYANMAR EXTENDED-B",
2608 "MYANMAREXTENDED-B");
2609
2610 /**
2611 * Constant for the "Latin Extended-E" Unicode character block.
2612 * @since 9
2613 */
2614 public static final UnicodeBlock LATIN_EXTENDED_E =
2615 new UnicodeBlock("LATIN_EXTENDED_E",
2616 "LATIN EXTENDED-E",
2617 "LATINEXTENDED-E");
2618
2619 /**
2620 * Constant for the "Coptic Epact Numbers" Unicode character block.
2621 * @since 9
2622 */
2623 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2624 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2625 "COPTIC EPACT NUMBERS",
2626 "COPTICEPACTNUMBERS");
2627
2628 /**
2629 * Constant for the "Old Permic" Unicode character block.
2630 * @since 9
2631 */
2632 public static final UnicodeBlock OLD_PERMIC =
2633 new UnicodeBlock("OLD_PERMIC",
2634 "OLD PERMIC",
2635 "OLDPERMIC");
2636
2637 /**
2638 * Constant for the "Elbasan" Unicode character block.
2639 * @since 9
2640 */
2641 public static final UnicodeBlock ELBASAN =
2642 new UnicodeBlock("ELBASAN");
2643
2644 /**
2645 * Constant for the "Caucasian Albanian" Unicode character block.
2646 * @since 9
2647 */
2648 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2649 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2650 "CAUCASIAN ALBANIAN",
2651 "CAUCASIANALBANIAN");
2652
2653 /**
2654 * Constant for the "Linear A" Unicode character block.
2655 * @since 9
2656 */
2657 public static final UnicodeBlock LINEAR_A =
2658 new UnicodeBlock("LINEAR_A",
2659 "LINEAR A",
2660 "LINEARA");
2661
2662 /**
2663 * Constant for the "Palmyrene" Unicode character block.
2664 * @since 9
2665 */
2666 public static final UnicodeBlock PALMYRENE =
2667 new UnicodeBlock("PALMYRENE");
2668
2669 /**
2670 * Constant for the "Nabataean" Unicode character block.
2671 * @since 9
2672 */
2673 public static final UnicodeBlock NABATAEAN =
2674 new UnicodeBlock("NABATAEAN");
2675
2676 /**
2677 * Constant for the "Old North Arabian" Unicode character block.
2678 * @since 9
2679 */
2680 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2681 new UnicodeBlock("OLD_NORTH_ARABIAN",
2682 "OLD NORTH ARABIAN",
2683 "OLDNORTHARABIAN");
2684
2685 /**
2686 * Constant for the "Manichaean" Unicode character block.
2687 * @since 9
2688 */
2689 public static final UnicodeBlock MANICHAEAN =
2690 new UnicodeBlock("MANICHAEAN");
2691
2692 /**
2693 * Constant for the "Psalter Pahlavi" Unicode character block.
2694 * @since 9
2695 */
2696 public static final UnicodeBlock PSALTER_PAHLAVI =
2697 new UnicodeBlock("PSALTER_PAHLAVI",
2698 "PSALTER PAHLAVI",
2699 "PSALTERPAHLAVI");
2700
2701 /**
2702 * Constant for the "Mahajani" Unicode character block.
2703 * @since 9
2704 */
2705 public static final UnicodeBlock MAHAJANI =
2706 new UnicodeBlock("MAHAJANI");
2707
2708 /**
2709 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2710 * @since 9
2711 */
2712 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2713 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2714 "SINHALA ARCHAIC NUMBERS",
2715 "SINHALAARCHAICNUMBERS");
2716
2717 /**
2718 * Constant for the "Khojki" Unicode character block.
2719 * @since 9
2720 */
2721 public static final UnicodeBlock KHOJKI =
2722 new UnicodeBlock("KHOJKI");
2723
2724 /**
2725 * Constant for the "Khudawadi" Unicode character block.
2726 * @since 9
2727 */
2728 public static final UnicodeBlock KHUDAWADI =
2729 new UnicodeBlock("KHUDAWADI");
2730
2731 /**
2732 * Constant for the "Grantha" Unicode character block.
2733 * @since 9
2734 */
2735 public static final UnicodeBlock GRANTHA =
2736 new UnicodeBlock("GRANTHA");
2737
2738 /**
2739 * Constant for the "Tirhuta" Unicode character block.
2740 * @since 9
2741 */
2742 public static final UnicodeBlock TIRHUTA =
2743 new UnicodeBlock("TIRHUTA");
2744
2745 /**
2746 * Constant for the "Siddham" Unicode character block.
2747 * @since 9
2748 */
2749 public static final UnicodeBlock SIDDHAM =
2750 new UnicodeBlock("SIDDHAM");
2751
2752 /**
2753 * Constant for the "Modi" Unicode character block.
2754 * @since 9
2755 */
2756 public static final UnicodeBlock MODI =
2757 new UnicodeBlock("MODI");
2758
2759 /**
2760 * Constant for the "Warang Citi" Unicode character block.
2761 * @since 9
2762 */
2763 public static final UnicodeBlock WARANG_CITI =
2764 new UnicodeBlock("WARANG_CITI",
2765 "WARANG CITI",
2766 "WARANGCITI");
2767
2768 /**
2769 * Constant for the "Pau Cin Hau" Unicode character block.
2770 * @since 9
2771 */
2772 public static final UnicodeBlock PAU_CIN_HAU =
2773 new UnicodeBlock("PAU_CIN_HAU",
2774 "PAU CIN HAU",
2775 "PAUCINHAU");
2776
2777 /**
2778 * Constant for the "Mro" Unicode character block.
2779 * @since 9
2780 */
2781 public static final UnicodeBlock MRO =
2782 new UnicodeBlock("MRO");
2783
2784 /**
2785 * Constant for the "Bassa Vah" Unicode character block.
2786 * @since 9
2787 */
2788 public static final UnicodeBlock BASSA_VAH =
2789 new UnicodeBlock("BASSA_VAH",
2790 "BASSA VAH",
2791 "BASSAVAH");
2792
2793 /**
2794 * Constant for the "Pahawh Hmong" Unicode character block.
2795 * @since 9
2796 */
2797 public static final UnicodeBlock PAHAWH_HMONG =
2798 new UnicodeBlock("PAHAWH_HMONG",
2799 "PAHAWH HMONG",
2800 "PAHAWHHMONG");
2801
2802 /**
2803 * Constant for the "Duployan" Unicode character block.
2804 * @since 9
2805 */
2806 public static final UnicodeBlock DUPLOYAN =
2807 new UnicodeBlock("DUPLOYAN");
2808
2809 /**
2810 * Constant for the "Shorthand Format Controls" Unicode character block.
2811 * @since 9
2812 */
2813 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2814 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2815 "SHORTHAND FORMAT CONTROLS",
2816 "SHORTHANDFORMATCONTROLS");
2817
2818 /**
2819 * Constant for the "Mende Kikakui" Unicode character block.
2820 * @since 9
2821 */
2822 public static final UnicodeBlock MENDE_KIKAKUI =
2823 new UnicodeBlock("MENDE_KIKAKUI",
2824 "MENDE KIKAKUI",
2825 "MENDEKIKAKUI");
2826
2827 /**
2828 * Constant for the "Ornamental Dingbats" Unicode character block.
2829 * @since 9
2830 */
2831 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2832 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2833 "ORNAMENTAL DINGBATS",
2834 "ORNAMENTALDINGBATS");
2835
2836 /**
2837 * Constant for the "Geometric Shapes Extended" Unicode character block.
2838 * @since 9
2839 */
2840 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2841 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2842 "GEOMETRIC SHAPES EXTENDED",
2843 "GEOMETRICSHAPESEXTENDED");
2844
2845 /**
2846 * Constant for the "Supplemental Arrows-C" Unicode character block.
2847 * @since 9
2848 */
2849 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2850 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2851 "SUPPLEMENTAL ARROWS-C",
2852 "SUPPLEMENTALARROWS-C");
2853
2854 /**
2855 * Constant for the "Cherokee Supplement" Unicode character block.
2856 * @since 9
2857 */
2858 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2859 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2860 "CHEROKEE SUPPLEMENT",
2861 "CHEROKEESUPPLEMENT");
2862
2863 /**
2864 * Constant for the "Hatran" Unicode character block.
2865 * @since 9
2866 */
2867 public static final UnicodeBlock HATRAN =
2868 new UnicodeBlock("HATRAN");
2869
2870 /**
2871 * Constant for the "Old Hungarian" Unicode character block.
2872 * @since 9
2873 */
2874 public static final UnicodeBlock OLD_HUNGARIAN =
2875 new UnicodeBlock("OLD_HUNGARIAN",
2876 "OLD HUNGARIAN",
2877 "OLDHUNGARIAN");
2878
2879 /**
2880 * Constant for the "Multani" Unicode character block.
2881 * @since 9
2882 */
2883 public static final UnicodeBlock MULTANI =
2884 new UnicodeBlock("MULTANI");
2885
2886 /**
2887 * Constant for the "Ahom" Unicode character block.
2888 * @since 9
2889 */
2890 public static final UnicodeBlock AHOM =
2891 new UnicodeBlock("AHOM");
2892
2893 /**
2894 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2895 * @since 9
2896 */
2897 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2898 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2899 "EARLY DYNASTIC CUNEIFORM",
2900 "EARLYDYNASTICCUNEIFORM");
2901
2902 /**
2903 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2904 * @since 9
2905 */
2906 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2907 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2908 "ANATOLIAN HIEROGLYPHS",
2909 "ANATOLIANHIEROGLYPHS");
2910
2911 /**
2912 * Constant for the "Sutton SignWriting" Unicode character block.
2913 * @since 9
2914 */
2915 public static final UnicodeBlock SUTTON_SIGNWRITING =
2916 new UnicodeBlock("SUTTON_SIGNWRITING",
2917 "SUTTON SIGNWRITING",
2918 "SUTTONSIGNWRITING");
2919
2920 /**
2921 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2922 * character block.
2923 * @since 9
2924 */
2925 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2926 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2927 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2928 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2929
2930 /**
2931 * Constant for the "CJK Unified Ideographs Extension E" Unicode
2932 * character block.
2933 * @since 9
2934 */
2935 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
2936 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
2937 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
2938 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
2939
2940 /**
2941 * Constant for the "Syriac Supplement" Unicode
2942 * character block.
2943 * @since 11
2944 */
2945 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
2946 new UnicodeBlock("SYRIAC_SUPPLEMENT",
2947 "SYRIAC SUPPLEMENT",
2948 "SYRIACSUPPLEMENT");
2949
2950 /**
2951 * Constant for the "Cyrillic Extended-C" Unicode
2952 * character block.
2953 * @since 11
2954 */
2955 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
2956 new UnicodeBlock("CYRILLIC_EXTENDED_C",
2957 "CYRILLIC EXTENDED-C",
2958 "CYRILLICEXTENDED-C");
2959
2960 /**
2961 * Constant for the "Osage" Unicode
2962 * character block.
2963 * @since 11
2964 */
2965 public static final UnicodeBlock OSAGE =
2966 new UnicodeBlock("OSAGE");
2967
2968 /**
2969 * Constant for the "Newa" Unicode
2970 * character block.
2971 * @since 11
2972 */
2973 public static final UnicodeBlock NEWA =
2974 new UnicodeBlock("NEWA");
2975
2976 /**
2977 * Constant for the "Mongolian Supplement" Unicode
2978 * character block.
2979 * @since 11
2980 */
2981 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
2982 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
2983 "MONGOLIAN SUPPLEMENT",
2984 "MONGOLIANSUPPLEMENT");
2985
2986 /**
2987 * Constant for the "Marchen" Unicode
2988 * character block.
2989 * @since 11
2990 */
2991 public static final UnicodeBlock MARCHEN =
2992 new UnicodeBlock("MARCHEN");
2993
2994 /**
2995 * Constant for the "Ideographic Symbols and Punctuation" Unicode
2996 * character block.
2997 * @since 11
2998 */
2999 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3000 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3001 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3002 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3003
3004 /**
3005 * Constant for the "Tangut" Unicode
3006 * character block.
3007 * @since 11
3008 */
3009 public static final UnicodeBlock TANGUT =
3010 new UnicodeBlock("TANGUT");
3011
3012 /**
3013 * Constant for the "Tangut Components" Unicode
3014 * character block.
3015 * @since 11
3016 */
3017 public static final UnicodeBlock TANGUT_COMPONENTS =
3018 new UnicodeBlock("TANGUT_COMPONENTS",
3019 "TANGUT COMPONENTS",
3020 "TANGUTCOMPONENTS");
3021
3022 /**
3023 * Constant for the "Kana Extended-A" Unicode
3024 * character block.
3025 * @since 11
3026 */
3027 public static final UnicodeBlock KANA_EXTENDED_A =
3028 new UnicodeBlock("KANA_EXTENDED_A",
3029 "KANA EXTENDED-A",
3030 "KANAEXTENDED-A");
3031 /**
3032 * Constant for the "Glagolitic Supplement" Unicode
3033 * character block.
3034 * @since 11
3035 */
3036 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3037 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3038 "GLAGOLITIC SUPPLEMENT",
3039 "GLAGOLITICSUPPLEMENT");
3040 /**
3041 * Constant for the "Adlam" Unicode
3042 * character block.
3043 * @since 11
3044 */
3045 public static final UnicodeBlock ADLAM =
3046 new UnicodeBlock("ADLAM");
3047
3048 /**
3049 * Constant for the "Masaram Gondi" Unicode
3050 * character block.
3051 * @since 11
3052 */
3053 public static final UnicodeBlock MASARAM_GONDI =
3054 new UnicodeBlock("MASARAM_GONDI",
3055 "MASARAM GONDI",
3056 "MASARAMGONDI");
3057
3058 /**
3059 * Constant for the "Zanabazar Square" Unicode
3060 * character block.
3061 * @since 11
3062 */
3063 public static final UnicodeBlock ZANABAZAR_SQUARE =
3064 new UnicodeBlock("ZANABAZAR_SQUARE",
3065 "ZANABAZAR SQUARE",
3066 "ZANABAZARSQUARE");
3067
3068 /**
3069 * Constant for the "Nushu" Unicode
3070 * character block.
3071 * @since 11
3072 */
3073 public static final UnicodeBlock NUSHU =
3074 new UnicodeBlock("NUSHU");
3075
3076 /**
3077 * Constant for the "Soyombo" Unicode
3078 * character block.
3079 * @since 11
3080 */
3081 public static final UnicodeBlock SOYOMBO =
3082 new UnicodeBlock("SOYOMBO");
3083
3084 /**
3085 * Constant for the "Bhaiksuki" Unicode
3086 * character block.
3087 * @since 11
3088 */
3089 public static final UnicodeBlock BHAIKSUKI =
3090 new UnicodeBlock("BHAIKSUKI");
3091
3092 /**
3093 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3094 * character block.
3095 * @since 11
3096 */
3097 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3098 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3099 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3100 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3101
3102 private static final int blockStarts[] = {
3103 0x0000, // 0000..007F; Basic Latin
3104 0x0080, // 0080..00FF; Latin-1 Supplement
3105 0x0100, // 0100..017F; Latin Extended-A
3106 0x0180, // 0180..024F; Latin Extended-B
3107 0x0250, // 0250..02AF; IPA Extensions
3108 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3109 0x0300, // 0300..036F; Combining Diacritical Marks
3110 0x0370, // 0370..03FF; Greek and Coptic
3111 0x0400, // 0400..04FF; Cyrillic
3112 0x0500, // 0500..052F; Cyrillic Supplement
3113 0x0530, // 0530..058F; Armenian
3114 0x0590, // 0590..05FF; Hebrew
3115 0x0600, // 0600..06FF; Arabic
3116 0x0700, // 0700..074F; Syriac
3117 0x0750, // 0750..077F; Arabic Supplement
3118 0x0780, // 0780..07BF; Thaana
3119 0x07C0, // 07C0..07FF; NKo
3120 0x0800, // 0800..083F; Samaritan
3121 0x0840, // 0840..085F; Mandaic
3122 0x0860, // 0860..086F; Syriac Supplement
3123 0x0870, // unassigned
3124 0x08A0, // 08A0..08FF; Arabic Extended-A
3125 0x0900, // 0900..097F; Devanagari
3126 0x0980, // 0980..09FF; Bengali
3127 0x0A00, // 0A00..0A7F; Gurmukhi
3128 0x0A80, // 0A80..0AFF; Gujarati
3129 0x0B00, // 0B00..0B7F; Oriya
3130 0x0B80, // 0B80..0BFF; Tamil
3131 0x0C00, // 0C00..0C7F; Telugu
3132 0x0C80, // 0C80..0CFF; Kannada
3133 0x0D00, // 0D00..0D7F; Malayalam
3134 0x0D80, // 0D80..0DFF; Sinhala
3135 0x0E00, // 0E00..0E7F; Thai
3136 0x0E80, // 0E80..0EFF; Lao
3137 0x0F00, // 0F00..0FFF; Tibetan
3138 0x1000, // 1000..109F; Myanmar
3139 0x10A0, // 10A0..10FF; Georgian
3140 0x1100, // 1100..11FF; Hangul Jamo
3141 0x1200, // 1200..137F; Ethiopic
3142 0x1380, // 1380..139F; Ethiopic Supplement
3143 0x13A0, // 13A0..13FF; Cherokee
3144 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3145 0x1680, // 1680..169F; Ogham
3146 0x16A0, // 16A0..16FF; Runic
3147 0x1700, // 1700..171F; Tagalog
3148 0x1720, // 1720..173F; Hanunoo
3149 0x1740, // 1740..175F; Buhid
3150 0x1760, // 1760..177F; Tagbanwa
3151 0x1780, // 1780..17FF; Khmer
3152 0x1800, // 1800..18AF; Mongolian
3153 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3154 0x1900, // 1900..194F; Limbu
3155 0x1950, // 1950..197F; Tai Le
3156 0x1980, // 1980..19DF; New Tai Lue
3157 0x19E0, // 19E0..19FF; Khmer Symbols
3158 0x1A00, // 1A00..1A1F; Buginese
3159 0x1A20, // 1A20..1AAF; Tai Tham
3160 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3161 0x1B00, // 1B00..1B7F; Balinese
3162 0x1B80, // 1B80..1BBF; Sundanese
3163 0x1BC0, // 1BC0..1BFF; Batak
3164 0x1C00, // 1C00..1C4F; Lepcha
3165 0x1C50, // 1C50..1C7F; Ol Chiki
3166 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3167 0x1C90, // unassigned
3168 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3169 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3170 0x1D00, // 1D00..1D7F; Phonetic Extensions
3171 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3172 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3173 0x1E00, // 1E00..1EFF; Latin Extended Additional
3174 0x1F00, // 1F00..1FFF; Greek Extended
3175 0x2000, // 2000..206F; General Punctuation
3176 0x2070, // 2070..209F; Superscripts and Subscripts
3177 0x20A0, // 20A0..20CF; Currency Symbols
3178 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3179 0x2100, // 2100..214F; Letterlike Symbols
3180 0x2150, // 2150..218F; Number Forms
3181 0x2190, // 2190..21FF; Arrows
3182 0x2200, // 2200..22FF; Mathematical Operators
3183 0x2300, // 2300..23FF; Miscellaneous Technical
3184 0x2400, // 2400..243F; Control Pictures
3185 0x2440, // 2440..245F; Optical Character Recognition
3186 0x2460, // 2460..24FF; Enclosed Alphanumerics
3187 0x2500, // 2500..257F; Box Drawing
3188 0x2580, // 2580..259F; Block Elements
3189 0x25A0, // 25A0..25FF; Geometric Shapes
3190 0x2600, // 2600..26FF; Miscellaneous Symbols
3191 0x2700, // 2700..27BF; Dingbats
3192 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3193 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3194 0x2800, // 2800..28FF; Braille Patterns
3195 0x2900, // 2900..297F; Supplemental Arrows-B
3196 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3197 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3198 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3199 0x2C00, // 2C00..2C5F; Glagolitic
3200 0x2C60, // 2C60..2C7F; Latin Extended-C
3201 0x2C80, // 2C80..2CFF; Coptic
3202 0x2D00, // 2D00..2D2F; Georgian Supplement
3203 0x2D30, // 2D30..2D7F; Tifinagh
3204 0x2D80, // 2D80..2DDF; Ethiopic Extended
3205 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3206 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3207 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3208 0x2F00, // 2F00..2FDF; Kangxi Radicals
3209 0x2FE0, // unassigned
3210 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3211 0x3000, // 3000..303F; CJK Symbols and Punctuation
3212 0x3040, // 3040..309F; Hiragana
3213 0x30A0, // 30A0..30FF; Katakana
3214 0x3100, // 3100..312F; Bopomofo
3215 0x3130, // 3130..318F; Hangul Compatibility Jamo
3216 0x3190, // 3190..319F; Kanbun
3217 0x31A0, // 31A0..31BF; Bopomofo Extended
3218 0x31C0, // 31C0..31EF; CJK Strokes
3219 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3220 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3221 0x3300, // 3300..33FF; CJK Compatibility
3222 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3223 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3224 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3225 0xA000, // A000..A48F; Yi Syllables
3226 0xA490, // A490..A4CF; Yi Radicals
3227 0xA4D0, // A4D0..A4FF; Lisu
3228 0xA500, // A500..A63F; Vai
3229 0xA640, // A640..A69F; Cyrillic Extended-B
3230 0xA6A0, // A6A0..A6FF; Bamum
3231 0xA700, // A700..A71F; Modifier Tone Letters
3232 0xA720, // A720..A7FF; Latin Extended-D
3233 0xA800, // A800..A82F; Syloti Nagri
3234 0xA830, // A830..A83F; Common Indic Number Forms
3235 0xA840, // A840..A87F; Phags-pa
3236 0xA880, // A880..A8DF; Saurashtra
3237 0xA8E0, // A8E0..A8FF; Devanagari Extended
3238 0xA900, // A900..A92F; Kayah Li
3239 0xA930, // A930..A95F; Rejang
3240 0xA960, // A960..A97F; Hangul Jamo Extended-A
3241 0xA980, // A980..A9DF; Javanese
3242 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3243 0xAA00, // AA00..AA5F; Cham
3244 0xAA60, // AA60..AA7F; Myanmar Extended-A
3245 0xAA80, // AA80..AADF; Tai Viet
3246 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3247 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3248 0xAB30, // AB30..AB6F; Latin Extended-E
3249 0xAB70, // AB70..ABBF; Cherokee Supplement
3250 0xABC0, // ABC0..ABFF; Meetei Mayek
3251 0xAC00, // AC00..D7AF; Hangul Syllables
3252 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3253 0xD800, // D800..DB7F; High Surrogates
3254 0xDB80, // DB80..DBFF; High Private Use Surrogates
3255 0xDC00, // DC00..DFFF; Low Surrogates
3256 0xE000, // E000..F8FF; Private Use Area
3257 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3258 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3259 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3260 0xFE00, // FE00..FE0F; Variation Selectors
3261 0xFE10, // FE10..FE1F; Vertical Forms
3262 0xFE20, // FE20..FE2F; Combining Half Marks
3263 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3264 0xFE50, // FE50..FE6F; Small Form Variants
3265 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3266 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3267 0xFFF0, // FFF0..FFFF; Specials
3268 0x10000, // 10000..1007F; Linear B Syllabary
3269 0x10080, // 10080..100FF; Linear B Ideograms
3270 0x10100, // 10100..1013F; Aegean Numbers
3271 0x10140, // 10140..1018F; Ancient Greek Numbers
3272 0x10190, // 10190..101CF; Ancient Symbols
3273 0x101D0, // 101D0..101FF; Phaistos Disc
3274 0x10200, // unassigned
3275 0x10280, // 10280..1029F; Lycian
3276 0x102A0, // 102A0..102DF; Carian
3277 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3278 0x10300, // 10300..1032F; Old Italic
3279 0x10330, // 10330..1034F; Gothic
3280 0x10350, // 10350..1037F; Old Permic
3281 0x10380, // 10380..1039F; Ugaritic
3282 0x103A0, // 103A0..103DF; Old Persian
3283 0x103E0, // unassigned
3284 0x10400, // 10400..1044F; Deseret
3285 0x10450, // 10450..1047F; Shavian
3286 0x10480, // 10480..104AF; Osmanya
3287 0x104B0, // 104B0..104FF; Osage
3288 0x10500, // 10500..1052F; Elbasan
3289 0x10530, // 10530..1056F; Caucasian Albanian
3290 0x10570, // unassigned
3291 0x10600, // 10600..1077F; Linear A
3292 0x10780, // unassigned
3293 0x10800, // 10800..1083F; Cypriot Syllabary
3294 0x10840, // 10840..1085F; Imperial Aramaic
3295 0x10860, // 10860..1087F; Palmyrene
3296 0x10880, // 10880..108AF; Nabataean
3297 0x108B0, // unassigned
3298 0x108E0, // 108E0..108FF; Hatran
3299 0x10900, // 10900..1091F; Phoenician
3300 0x10920, // 10920..1093F; Lydian
3301 0x10940, // unassigned
3302 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3303 0x109A0, // 109A0..109FF; Meroitic Cursive
3304 0x10A00, // 10A00..10A5F; Kharoshthi
3305 0x10A60, // 10A60..10A7F; Old South Arabian
3306 0x10A80, // 10A80..10A9F; Old North Arabian
3307 0x10AA0, // unassigned
3308 0x10AC0, // 10AC0..10AFF; Manichaean
3309 0x10B00, // 10B00..10B3F; Avestan
3310 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3311 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3312 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3313 0x10BB0, // unassigned
3314 0x10C00, // 10C00..10C4F; Old Turkic
3315 0x10C50, // unassigned
3316 0x10C80, // 10C80..10CFF; Old Hungarian
3317 0x10D00, // unassigned
3318 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3319 0x10E80, // unassigned
3320 0x11000, // 11000..1107F; Brahmi
3321 0x11080, // 11080..110CF; Kaithi
3322 0x110D0, // 110D0..110FF; Sora Sompeng
3323 0x11100, // 11100..1114F; Chakma
3324 0x11150, // 11150..1117F; Mahajani
3325 0x11180, // 11180..111DF; Sharada
3326 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3327 0x11200, // 11200..1124F; Khojki
3328 0x11250, // unassigned
3329 0x11280, // 11280..112AF; Multani
3330 0x112B0, // 112B0..112FF; Khudawadi
3331 0x11300, // 11300..1137F; Grantha
3332 0x11380, // unassigned
3333 0x11400, // 11400..1147F; Newa
3334 0x11480, // 11480..114DF; Tirhuta
3335 0x114E0, // unassigned
3336 0x11580, // 11580..115FF; Siddham
3337 0x11600, // 11600..1165F; Modi
3338 0x11660, // 11660..1167F; Mongolian Supplement
3339 0x11680, // 11680..116CF; Takri
3340 0x116D0, // unassigned
3341 0x11700, // 11700..1173F; Ahom
3342 0x11740, // unassigned
3343 0x118A0, // 118A0..118FF; Warang Citi
3344 0x11900, // unassigned
3345 0x11A00, // 11A00..11A4F; Zanabazar Square
3346 0x11A50, // 11A50..11AAF; Soyombo
3347 0x11AB0, // unassigned
3348 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3349 0x11B00, // unassigned
3350 0x11C00, // 11C00..11C6F; Bhaiksuki
3351 0x11C70, // 11C70..11CBF; Marchen
3352 0x11CC0, // unassigned
3353 0x11D00, // 11D00..11D5F; Masaram Gondi
3354 0x11D60, // unassigned
3355 0x12000, // 12000..123FF; Cuneiform
3356 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3357 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3358 0x12550, // unassigned
3359 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3360 0x13430, // unassigned
3361 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3362 0x14680, // unassigned
3363 0x16800, // 16800..16A3F; Bamum Supplement
3364 0x16A40, // 16A40..16A6F; Mro
3365 0x16A70, // unassigned
3366 0x16AD0, // 16AD0..16AFF; Bassa Vah
3367 0x16B00, // 16B00..16B8F; Pahawh Hmong
3368 0x16B90, // unassigned
3369 0x16F00, // 16F00..16F9F; Miao
3370 0x16FA0, // unassigned
3371 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
3372 0x17000, // 17000..187FF; Tangut
3373 0x18800, // 18800..18AFF; Tangut Components
3374 0x18B00, // unassigned
3375 0x1B000, // 1B000..1B0FF; Kana Supplement
3376 0x1B100, // 1B100..1B12F; Kana Extended-A
3377 0x1B130, // unassigned
3378 0x1B170, // 1B170..1B2FF; Nushu
3379 0x1B300, // unassigned
3380 0x1BC00, // 1BC00..1BC9F; Duployan
3381 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3382 0x1BCB0, // unassigned
3383 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3384 0x1D100, // 1D100..1D1FF; Musical Symbols
3385 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3386 0x1D250, // unassigned
3387 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3388 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3389 0x1D380, // unassigned
3390 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3391 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3392 0x1DAB0, // unassigned
3393 0x1E000, // 1E000..1E02F; Glagolitic Supplement
3394 0x1E030, // unassigned
3395 0x1E800, // 1E800..1E8DF; Mende Kikakui
3396 0x1E8E0, // unassigned
3397 0x1E900, // 1E900..1E95F; Adlam
3398 0x1E960, // unassigned
3399 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3400 0x1EF00, // unassigned
3401 0x1F000, // 1F000..1F02F; Mahjong Tiles
3402 0x1F030, // 1F030..1F09F; Domino Tiles
3403 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3404 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3405 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3406 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3407 0x1F600, // 1F600..1F64F; Emoticons
3408 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3409 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3410 0x1F700, // 1F700..1F77F; Alchemical Symbols
3411 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3412 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3413 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3414 0x1FA00, // unassigned
3415 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3416 0x2A6E0, // unassigned
3417 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3418 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3419 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
3420 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
3421 0x2EBF0, // unassigned
3422 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
3423 0x2FA20, // unassigned
3424 0xE0000, // E0000..E007F; Tags
3425 0xE0080, // unassigned
3426 0xE0100, // E0100..E01EF; Variation Selectors Supplement
3427 0xE01F0, // unassigned
3428 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
3429 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B
3430 };
3431
3432 private static final UnicodeBlock[] blocks = {
3433 BASIC_LATIN,
3434 LATIN_1_SUPPLEMENT,
3435 LATIN_EXTENDED_A,
3436 LATIN_EXTENDED_B,
3437 IPA_EXTENSIONS,
3438 SPACING_MODIFIER_LETTERS,
3439 COMBINING_DIACRITICAL_MARKS,
3440 GREEK,
3441 CYRILLIC,
3442 CYRILLIC_SUPPLEMENTARY,
3443 ARMENIAN,
3444 HEBREW,
3445 ARABIC,
3446 SYRIAC,
3447 ARABIC_SUPPLEMENT,
3448 THAANA,
3449 NKO,
3450 SAMARITAN,
3451 MANDAIC,
3452 SYRIAC_SUPPLEMENT,
3453 null,
3454 ARABIC_EXTENDED_A,
3455 DEVANAGARI,
3456 BENGALI,
3457 GURMUKHI,
3458 GUJARATI,
3459 ORIYA,
3460 TAMIL,
3461 TELUGU,
3462 KANNADA,
3463 MALAYALAM,
3464 SINHALA,
3465 THAI,
3466 LAO,
3467 TIBETAN,
3468 MYANMAR,
3469 GEORGIAN,
3470 HANGUL_JAMO,
3471 ETHIOPIC,
3472 ETHIOPIC_SUPPLEMENT,
3473 CHEROKEE,
3474 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
3475 OGHAM,
3476 RUNIC,
3477 TAGALOG,
3478 HANUNOO,
3479 BUHID,
3480 TAGBANWA,
3481 KHMER,
3482 MONGOLIAN,
3483 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
3484 LIMBU,
3485 TAI_LE,
3486 NEW_TAI_LUE,
3487 KHMER_SYMBOLS,
3488 BUGINESE,
3489 TAI_THAM,
3490 COMBINING_DIACRITICAL_MARKS_EXTENDED,
3491 BALINESE,
3492 SUNDANESE,
3493 BATAK,
3494 LEPCHA,
3495 OL_CHIKI,
3496 CYRILLIC_EXTENDED_C,
3497 null,
3498 SUNDANESE_SUPPLEMENT,
3499 VEDIC_EXTENSIONS,
3500 PHONETIC_EXTENSIONS,
3501 PHONETIC_EXTENSIONS_SUPPLEMENT,
3502 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
3503 LATIN_EXTENDED_ADDITIONAL,
3504 GREEK_EXTENDED,
3505 GENERAL_PUNCTUATION,
3506 SUPERSCRIPTS_AND_SUBSCRIPTS,
3507 CURRENCY_SYMBOLS,
3508 COMBINING_MARKS_FOR_SYMBOLS,
3509 LETTERLIKE_SYMBOLS,
3510 NUMBER_FORMS,
3511 ARROWS,
3512 MATHEMATICAL_OPERATORS,
3513 MISCELLANEOUS_TECHNICAL,
3514 CONTROL_PICTURES,
3515 OPTICAL_CHARACTER_RECOGNITION,
3516 ENCLOSED_ALPHANUMERICS,
3517 BOX_DRAWING,
3518 BLOCK_ELEMENTS,
3519 GEOMETRIC_SHAPES,
3520 MISCELLANEOUS_SYMBOLS,
3521 DINGBATS,
3522 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
3523 SUPPLEMENTAL_ARROWS_A,
3524 BRAILLE_PATTERNS,
3525 SUPPLEMENTAL_ARROWS_B,
3526 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
3527 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
3528 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
3529 GLAGOLITIC,
3530 LATIN_EXTENDED_C,
3531 COPTIC,
3532 GEORGIAN_SUPPLEMENT,
3533 TIFINAGH,
3534 ETHIOPIC_EXTENDED,
3535 CYRILLIC_EXTENDED_A,
3536 SUPPLEMENTAL_PUNCTUATION,
3537 CJK_RADICALS_SUPPLEMENT,
3538 KANGXI_RADICALS,
3539 null,
3540 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
3541 CJK_SYMBOLS_AND_PUNCTUATION,
3542 HIRAGANA,
3543 KATAKANA,
3544 BOPOMOFO,
3545 HANGUL_COMPATIBILITY_JAMO,
3546 KANBUN,
3547 BOPOMOFO_EXTENDED,
3548 CJK_STROKES,
3549 KATAKANA_PHONETIC_EXTENSIONS,
3550 ENCLOSED_CJK_LETTERS_AND_MONTHS,
3551 CJK_COMPATIBILITY,
3552 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
3553 YIJING_HEXAGRAM_SYMBOLS,
3554 CJK_UNIFIED_IDEOGRAPHS,
3555 YI_SYLLABLES,
3556 YI_RADICALS,
3557 LISU,
3558 VAI,
3559 CYRILLIC_EXTENDED_B,
3560 BAMUM,
3561 MODIFIER_TONE_LETTERS,
3562 LATIN_EXTENDED_D,
3563 SYLOTI_NAGRI,
3564 COMMON_INDIC_NUMBER_FORMS,
3565 PHAGS_PA,
3566 SAURASHTRA,
3567 DEVANAGARI_EXTENDED,
3568 KAYAH_LI,
3569 REJANG,
3570 HANGUL_JAMO_EXTENDED_A,
3571 JAVANESE,
3572 MYANMAR_EXTENDED_B,
3573 CHAM,
3574 MYANMAR_EXTENDED_A,
3575 TAI_VIET,
3576 MEETEI_MAYEK_EXTENSIONS,
3577 ETHIOPIC_EXTENDED_A,
3578 LATIN_EXTENDED_E,
3579 CHEROKEE_SUPPLEMENT,
3580 MEETEI_MAYEK,
3581 HANGUL_SYLLABLES,
3582 HANGUL_JAMO_EXTENDED_B,
3583 HIGH_SURROGATES,
3584 HIGH_PRIVATE_USE_SURROGATES,
3585 LOW_SURROGATES,
3586 PRIVATE_USE_AREA,
3587 CJK_COMPATIBILITY_IDEOGRAPHS,
3588 ALPHABETIC_PRESENTATION_FORMS,
3589 ARABIC_PRESENTATION_FORMS_A,
3590 VARIATION_SELECTORS,
3591 VERTICAL_FORMS,
3592 COMBINING_HALF_MARKS,
3593 CJK_COMPATIBILITY_FORMS,
3594 SMALL_FORM_VARIANTS,
3595 ARABIC_PRESENTATION_FORMS_B,
3596 HALFWIDTH_AND_FULLWIDTH_FORMS,
3597 SPECIALS,
3598 LINEAR_B_SYLLABARY,
3599 LINEAR_B_IDEOGRAMS,
3600 AEGEAN_NUMBERS,
3601 ANCIENT_GREEK_NUMBERS,
3602 ANCIENT_SYMBOLS,
3603 PHAISTOS_DISC,
3604 null,
3605 LYCIAN,
3606 CARIAN,
3607 COPTIC_EPACT_NUMBERS,
3608 OLD_ITALIC,
3609 GOTHIC,
3610 OLD_PERMIC,
3611 UGARITIC,
3612 OLD_PERSIAN,
3613 null,
3614 DESERET,
3615 SHAVIAN,
3616 OSMANYA,
3617 OSAGE,
3618 ELBASAN,
3619 CAUCASIAN_ALBANIAN,
3620 null,
3621 LINEAR_A,
3622 null,
3623 CYPRIOT_SYLLABARY,
3624 IMPERIAL_ARAMAIC,
3625 PALMYRENE,
3626 NABATAEAN,
3627 null,
3628 HATRAN,
3629 PHOENICIAN,
3630 LYDIAN,
3631 null,
3632 MEROITIC_HIEROGLYPHS,
3633 MEROITIC_CURSIVE,
3634 KHAROSHTHI,
3635 OLD_SOUTH_ARABIAN,
3636 OLD_NORTH_ARABIAN,
3637 null,
3638 MANICHAEAN,
3639 AVESTAN,
3640 INSCRIPTIONAL_PARTHIAN,
3641 INSCRIPTIONAL_PAHLAVI,
3642 PSALTER_PAHLAVI,
3643 null,
3644 OLD_TURKIC,
3645 null,
3646 OLD_HUNGARIAN,
3647 null,
3648 RUMI_NUMERAL_SYMBOLS,
3649 null,
3650 BRAHMI,
3651 KAITHI,
3652 SORA_SOMPENG,
3653 CHAKMA,
3654 MAHAJANI,
3655 SHARADA,
3656 SINHALA_ARCHAIC_NUMBERS,
3657 KHOJKI,
3658 null,
3659 MULTANI,
3660 KHUDAWADI,
3661 GRANTHA,
3662 null,
3663 NEWA,
3664 TIRHUTA,
3665 null,
3666 SIDDHAM,
3667 MODI,
3668 MONGOLIAN_SUPPLEMENT,
3669 TAKRI,
3670 null,
3671 AHOM,
3672 null,
3673 WARANG_CITI,
3674 null,
3675 ZANABAZAR_SQUARE,
3676 SOYOMBO,
3677 null,
3678 PAU_CIN_HAU,
3679 null,
3680 BHAIKSUKI,
3681 MARCHEN,
3682 null,
3683 MASARAM_GONDI,
3684 null,
3685 CUNEIFORM,
3686 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
3687 EARLY_DYNASTIC_CUNEIFORM,
3688 null,
3689 EGYPTIAN_HIEROGLYPHS,
3690 null,
3691 ANATOLIAN_HIEROGLYPHS,
3692 null,
3693 BAMUM_SUPPLEMENT,
3694 MRO,
3695 null,
3696 BASSA_VAH,
3697 PAHAWH_HMONG,
3698 null,
3699 MIAO,
3700 null,
3701 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
3702 TANGUT,
3703 TANGUT_COMPONENTS,
3704 null,
3705 KANA_SUPPLEMENT,
3706 KANA_EXTENDED_A,
3707 null,
3708 NUSHU,
3709 null,
3710 DUPLOYAN,
3711 SHORTHAND_FORMAT_CONTROLS,
3712 null,
3713 BYZANTINE_MUSICAL_SYMBOLS,
3714 MUSICAL_SYMBOLS,
3715 ANCIENT_GREEK_MUSICAL_NOTATION,
3716 null,
3717 TAI_XUAN_JING_SYMBOLS,
3718 COUNTING_ROD_NUMERALS,
3719 null,
3720 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
3721 SUTTON_SIGNWRITING,
3722 null,
3723 GLAGOLITIC_SUPPLEMENT,
3724 null,
3725 MENDE_KIKAKUI,
3726 null,
3727 ADLAM,
3728 null,
3729 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
3730 null,
3731 MAHJONG_TILES,
3732 DOMINO_TILES,
3733 PLAYING_CARDS,
3734 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
3735 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
3736 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
3737 EMOTICONS,
3738 ORNAMENTAL_DINGBATS,
3739 TRANSPORT_AND_MAP_SYMBOLS,
3740 ALCHEMICAL_SYMBOLS,
3741 GEOMETRIC_SHAPES_EXTENDED,
3742 SUPPLEMENTAL_ARROWS_C,
3743 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
3744 null,
3745 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
3746 null,
3747 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
3748 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
3749 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
3750 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
3751 null,
3752 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
3753 null,
3754 TAGS,
3755 null,
3756 VARIATION_SELECTORS_SUPPLEMENT,
3757 null,
3758 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
3759 SUPPLEMENTARY_PRIVATE_USE_AREA_B
3760 };
3761
3762
3763 /**
3764 * Returns the object representing the Unicode block containing the
3765 * given character, or {@code null} if the character is not a
3766 * member of a defined block.
3767 *
3768 * <p><b>Note:</b> This method cannot handle
3769 * <a href="Character.html#supplementary"> supplementary
3770 * characters</a>. To support all Unicode characters, including
3771 * supplementary characters, use the {@link #of(int)} method.
3772 *
3773 * @param c The character in question
3774 * @return The {@code UnicodeBlock} instance representing the
3775 * Unicode block of which this character is a member, or
3776 * {@code null} if the character is not a member of any
3777 * Unicode block
3778 */
3779 public static UnicodeBlock of(char c) {
3780 return of((int)c);
3781 }
3782
3783 /**
3784 * Returns the object representing the Unicode block
3785 * containing the given character (Unicode code point), or
3786 * {@code null} if the character is not a member of a
3787 * defined block.
3788 *
3789 * @param codePoint the character (Unicode code point) in question.
3790 * @return The {@code UnicodeBlock} instance representing the
3791 * Unicode block of which this character is a member, or
3792 * {@code null} if the character is not a member of any
3793 * Unicode block
3794 * @throws IllegalArgumentException if the specified
3795 * {@code codePoint} is an invalid Unicode code point.
3796 * @see Character#isValidCodePoint(int)
3797 * @since 1.5
3798 */
3799 public static UnicodeBlock of(int codePoint) {
3800 if (!isValidCodePoint(codePoint)) {
3801 throw new IllegalArgumentException(
3802 String.format("Not a valid Unicode code point: 0x%X", codePoint));
3803 }
3804
3805 int top, bottom, current;
3806 bottom = 0;
3807 top = blockStarts.length;
3808 current = top/2;
3809
3810 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
3811 while (top - bottom > 1) {
3812 if (codePoint >= blockStarts[current]) {
3813 bottom = current;
3814 } else {
3815 top = current;
3816 }
3817 current = (top + bottom) / 2;
3818 }
3819 return blocks[current];
3820 }
3821
3822 /**
3823 * Returns the UnicodeBlock with the given name. Block
3824 * names are determined by The Unicode Standard. The file
3825 * {@code Blocks-<version>.txt} defines blocks for a particular
3826 * version of the standard. The {@link Character} class specifies
3827 * the version of the standard that it supports.
3828 * <p>
3829 * This method accepts block names in the following forms:
3830 * <ol>
3831 * <li> Canonical block names as defined by the Unicode Standard.
3832 * For example, the standard defines a "Basic Latin" block. Therefore, this
3833 * method accepts "Basic Latin" as a valid block name. The documentation of
3834 * each UnicodeBlock provides the canonical name.
3835 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
3836 * is a valid block name for the "Basic Latin" block.
3837 * <li>The text representation of each constant UnicodeBlock identifier.
3838 * For example, this method will return the {@link #BASIC_LATIN} block if
3839 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
3840 * hyphens in the canonical name with underscores.
3841 * </ol>
3842 * Finally, character case is ignored for all of the valid block name forms.
3843 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
3844 * The en_US locale's case mapping rules are used to provide case-insensitive
3845 * string comparisons for block name validation.
3846 * <p>
3847 * If the Unicode Standard changes block names, both the previous and
3848 * current names will be accepted.
3849 *
3850 * @param blockName A {@code UnicodeBlock} name.
3851 * @return The {@code UnicodeBlock} instance identified
3852 * by {@code blockName}
3853 * @throws IllegalArgumentException if {@code blockName} is an
3854 * invalid name
3855 * @throws NullPointerException if {@code blockName} is null
3856 * @since 1.5
3857 */
3858 public static final UnicodeBlock forName(String blockName) {
3859 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
3860 if (block == null) {
3861 throw new IllegalArgumentException("Not a valid block name: "
3862 + blockName);
3863 }
3864 return block;
3865 }
3866 }
3867
3868
3869 /**
3870 * A family of character subsets representing the character scripts
3871 * defined in the <a href="http://www.unicode.org/reports/tr24/">
3872 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
3873 * character is assigned to a single Unicode script, either a specific
3874 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
3875 * one of the following three special values,
3876 * {@link Character.UnicodeScript#INHERITED Inherited},
3877 * {@link Character.UnicodeScript#COMMON Common} or
3878 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
3879 *
3880 * @since 1.7
3881 */
3882 public static enum UnicodeScript {
3883 /**
3884 * Unicode script "Common".
3885 */
3886 COMMON,
3887
3888 /**
3889 * Unicode script "Latin".
3890 */
3891 LATIN,
3892
3893 /**
3894 * Unicode script "Greek".
3895 */
3896 GREEK,
3897
3898 /**
3899 * Unicode script "Cyrillic".
3900 */
3901 CYRILLIC,
3902
3903 /**
3904 * Unicode script "Armenian".
3905 */
3906 ARMENIAN,
3907
3908 /**
3909 * Unicode script "Hebrew".
3910 */
3911 HEBREW,
3912
3913 /**
3914 * Unicode script "Arabic".
3915 */
3916 ARABIC,
3917
3918 /**
3919 * Unicode script "Syriac".
3920 */
3921 SYRIAC,
3922
3923 /**
3924 * Unicode script "Thaana".
3925 */
3926 THAANA,
3927
3928 /**
3929 * Unicode script "Devanagari".
3930 */
3931 DEVANAGARI,
3932
3933 /**
3934 * Unicode script "Bengali".
3935 */
3936 BENGALI,
3937
3938 /**
3939 * Unicode script "Gurmukhi".
3940 */
3941 GURMUKHI,
3942
3943 /**
3944 * Unicode script "Gujarati".
3945 */
3946 GUJARATI,
3947
3948 /**
3949 * Unicode script "Oriya".
3950 */
3951 ORIYA,
3952
3953 /**
3954 * Unicode script "Tamil".
3955 */
3956 TAMIL,
3957
3958 /**
3959 * Unicode script "Telugu".
3960 */
3961 TELUGU,
3962
3963 /**
3964 * Unicode script "Kannada".
3965 */
3966 KANNADA,
3967
3968 /**
3969 * Unicode script "Malayalam".
3970 */
3971 MALAYALAM,
3972
3973 /**
3974 * Unicode script "Sinhala".
3975 */
3976 SINHALA,
3977
3978 /**
3979 * Unicode script "Thai".
3980 */
3981 THAI,
3982
3983 /**
3984 * Unicode script "Lao".
3985 */
3986 LAO,
3987
3988 /**
3989 * Unicode script "Tibetan".
3990 */
3991 TIBETAN,
3992
3993 /**
3994 * Unicode script "Myanmar".
3995 */
3996 MYANMAR,
3997
3998 /**
3999 * Unicode script "Georgian".
4000 */
4001 GEORGIAN,
4002
4003 /**
4004 * Unicode script "Hangul".
4005 */
4006 HANGUL,
4007
4008 /**
4009 * Unicode script "Ethiopic".
4010 */
4011 ETHIOPIC,
4012
4013 /**
4014 * Unicode script "Cherokee".
4015 */
4016 CHEROKEE,
4017
4018 /**
4019 * Unicode script "Canadian_Aboriginal".
4020 */
4021 CANADIAN_ABORIGINAL,
4022
4023 /**
4024 * Unicode script "Ogham".
4025 */
4026 OGHAM,
4027
4028 /**
4029 * Unicode script "Runic".
4030 */
4031 RUNIC,
4032
4033 /**
4034 * Unicode script "Khmer".
4035 */
4036 KHMER,
4037
4038 /**
4039 * Unicode script "Mongolian".
4040 */
4041 MONGOLIAN,
4042
4043 /**
4044 * Unicode script "Hiragana".
4045 */
4046 HIRAGANA,
4047
4048 /**
4049 * Unicode script "Katakana".
4050 */
4051 KATAKANA,
4052
4053 /**
4054 * Unicode script "Bopomofo".
4055 */
4056 BOPOMOFO,
4057
4058 /**
4059 * Unicode script "Han".
4060 */
4061 HAN,
4062
4063 /**
4064 * Unicode script "Yi".
4065 */
4066 YI,
4067
4068 /**
4069 * Unicode script "Old_Italic".
4070 */
4071 OLD_ITALIC,
4072
4073 /**
4074 * Unicode script "Gothic".
4075 */
4076 GOTHIC,
4077
4078 /**
4079 * Unicode script "Deseret".
4080 */
4081 DESERET,
4082
4083 /**
4084 * Unicode script "Inherited".
4085 */
4086 INHERITED,
4087
4088 /**
4089 * Unicode script "Tagalog".
4090 */
4091 TAGALOG,
4092
4093 /**
4094 * Unicode script "Hanunoo".
4095 */
4096 HANUNOO,
4097
4098 /**
4099 * Unicode script "Buhid".
4100 */
4101 BUHID,
4102
4103 /**
4104 * Unicode script "Tagbanwa".
4105 */
4106 TAGBANWA,
4107
4108 /**
4109 * Unicode script "Limbu".
4110 */
4111 LIMBU,
4112
4113 /**
4114 * Unicode script "Tai_Le".
4115 */
4116 TAI_LE,
4117
4118 /**
4119 * Unicode script "Linear_B".
4120 */
4121 LINEAR_B,
4122
4123 /**
4124 * Unicode script "Ugaritic".
4125 */
4126 UGARITIC,
4127
4128 /**
4129 * Unicode script "Shavian".
4130 */
4131 SHAVIAN,
4132
4133 /**
4134 * Unicode script "Osmanya".
4135 */
4136 OSMANYA,
4137
4138 /**
4139 * Unicode script "Cypriot".
4140 */
4141 CYPRIOT,
4142
4143 /**
4144 * Unicode script "Braille".
4145 */
4146 BRAILLE,
4147
4148 /**
4149 * Unicode script "Buginese".
4150 */
4151 BUGINESE,
4152
4153 /**
4154 * Unicode script "Coptic".
4155 */
4156 COPTIC,
4157
4158 /**
4159 * Unicode script "New_Tai_Lue".
4160 */
4161 NEW_TAI_LUE,
4162
4163 /**
4164 * Unicode script "Glagolitic".
4165 */
4166 GLAGOLITIC,
4167
4168 /**
4169 * Unicode script "Tifinagh".
4170 */
4171 TIFINAGH,
4172
4173 /**
4174 * Unicode script "Syloti_Nagri".
4175 */
4176 SYLOTI_NAGRI,
4177
4178 /**
4179 * Unicode script "Old_Persian".
4180 */
4181 OLD_PERSIAN,
4182
4183 /**
4184 * Unicode script "Kharoshthi".
4185 */
4186 KHAROSHTHI,
4187
4188 /**
4189 * Unicode script "Balinese".
4190 */
4191 BALINESE,
4192
4193 /**
4194 * Unicode script "Cuneiform".
4195 */
4196 CUNEIFORM,
4197
4198 /**
4199 * Unicode script "Phoenician".
4200 */
4201 PHOENICIAN,
4202
4203 /**
4204 * Unicode script "Phags_Pa".
4205 */
4206 PHAGS_PA,
4207
4208 /**
4209 * Unicode script "Nko".
4210 */
4211 NKO,
4212
4213 /**
4214 * Unicode script "Sundanese".
4215 */
4216 SUNDANESE,
4217
4218 /**
4219 * Unicode script "Batak".
4220 */
4221 BATAK,
4222
4223 /**
4224 * Unicode script "Lepcha".
4225 */
4226 LEPCHA,
4227
4228 /**
4229 * Unicode script "Ol_Chiki".
4230 */
4231 OL_CHIKI,
4232
4233 /**
4234 * Unicode script "Vai".
4235 */
4236 VAI,
4237
4238 /**
4239 * Unicode script "Saurashtra".
4240 */
4241 SAURASHTRA,
4242
4243 /**
4244 * Unicode script "Kayah_Li".
4245 */
4246 KAYAH_LI,
4247
4248 /**
4249 * Unicode script "Rejang".
4250 */
4251 REJANG,
4252
4253 /**
4254 * Unicode script "Lycian".
4255 */
4256 LYCIAN,
4257
4258 /**
4259 * Unicode script "Carian".
4260 */
4261 CARIAN,
4262
4263 /**
4264 * Unicode script "Lydian".
4265 */
4266 LYDIAN,
4267
4268 /**
4269 * Unicode script "Cham".
4270 */
4271 CHAM,
4272
4273 /**
4274 * Unicode script "Tai_Tham".
4275 */
4276 TAI_THAM,
4277
4278 /**
4279 * Unicode script "Tai_Viet".
4280 */
4281 TAI_VIET,
4282
4283 /**
4284 * Unicode script "Avestan".
4285 */
4286 AVESTAN,
4287
4288 /**
4289 * Unicode script "Egyptian_Hieroglyphs".
4290 */
4291 EGYPTIAN_HIEROGLYPHS,
4292
4293 /**
4294 * Unicode script "Samaritan".
4295 */
4296 SAMARITAN,
4297
4298 /**
4299 * Unicode script "Mandaic".
4300 */
4301 MANDAIC,
4302
4303 /**
4304 * Unicode script "Lisu".
4305 */
4306 LISU,
4307
4308 /**
4309 * Unicode script "Bamum".
4310 */
4311 BAMUM,
4312
4313 /**
4314 * Unicode script "Javanese".
4315 */
4316 JAVANESE,
4317
4318 /**
4319 * Unicode script "Meetei_Mayek".
4320 */
4321 MEETEI_MAYEK,
4322
4323 /**
4324 * Unicode script "Imperial_Aramaic".
4325 */
4326 IMPERIAL_ARAMAIC,
4327
4328 /**
4329 * Unicode script "Old_South_Arabian".
4330 */
4331 OLD_SOUTH_ARABIAN,
4332
4333 /**
4334 * Unicode script "Inscriptional_Parthian".
4335 */
4336 INSCRIPTIONAL_PARTHIAN,
4337
4338 /**
4339 * Unicode script "Inscriptional_Pahlavi".
4340 */
4341 INSCRIPTIONAL_PAHLAVI,
4342
4343 /**
4344 * Unicode script "Old_Turkic".
4345 */
4346 OLD_TURKIC,
4347
4348 /**
4349 * Unicode script "Brahmi".
4350 */
4351 BRAHMI,
4352
4353 /**
4354 * Unicode script "Kaithi".
4355 */
4356 KAITHI,
4357
4358 /**
4359 * Unicode script "Meroitic Hieroglyphs".
4360 * @since 1.8
4361 */
4362 MEROITIC_HIEROGLYPHS,
4363
4364 /**
4365 * Unicode script "Meroitic Cursive".
4366 * @since 1.8
4367 */
4368 MEROITIC_CURSIVE,
4369
4370 /**
4371 * Unicode script "Sora Sompeng".
4372 * @since 1.8
4373 */
4374 SORA_SOMPENG,
4375
4376 /**
4377 * Unicode script "Chakma".
4378 * @since 1.8
4379 */
4380 CHAKMA,
4381
4382 /**
4383 * Unicode script "Sharada".
4384 * @since 1.8
4385 */
4386 SHARADA,
4387
4388 /**
4389 * Unicode script "Takri".
4390 * @since 1.8
4391 */
4392 TAKRI,
4393
4394 /**
4395 * Unicode script "Miao".
4396 * @since 1.8
4397 */
4398 MIAO,
4399
4400 /**
4401 * Unicode script "Caucasian Albanian".
4402 * @since 9
4403 */
4404 CAUCASIAN_ALBANIAN,
4405
4406 /**
4407 * Unicode script "Bassa Vah".
4408 * @since 9
4409 */
4410 BASSA_VAH,
4411
4412 /**
4413 * Unicode script "Duployan".
4414 * @since 9
4415 */
4416 DUPLOYAN,
4417
4418 /**
4419 * Unicode script "Elbasan".
4420 * @since 9
4421 */
4422 ELBASAN,
4423
4424 /**
4425 * Unicode script "Grantha".
4426 * @since 9
4427 */
4428 GRANTHA,
4429
4430 /**
4431 * Unicode script "Pahawh Hmong".
4432 * @since 9
4433 */
4434 PAHAWH_HMONG,
4435
4436 /**
4437 * Unicode script "Khojki".
4438 * @since 9
4439 */
4440 KHOJKI,
4441
4442 /**
4443 * Unicode script "Linear A".
4444 * @since 9
4445 */
4446 LINEAR_A,
4447
4448 /**
4449 * Unicode script "Mahajani".
4450 * @since 9
4451 */
4452 MAHAJANI,
4453
4454 /**
4455 * Unicode script "Manichaean".
4456 * @since 9
4457 */
4458 MANICHAEAN,
4459
4460 /**
4461 * Unicode script "Mende Kikakui".
4462 * @since 9
4463 */
4464 MENDE_KIKAKUI,
4465
4466 /**
4467 * Unicode script "Modi".
4468 * @since 9
4469 */
4470 MODI,
4471
4472 /**
4473 * Unicode script "Mro".
4474 * @since 9
4475 */
4476 MRO,
4477
4478 /**
4479 * Unicode script "Old North Arabian".
4480 * @since 9
4481 */
4482 OLD_NORTH_ARABIAN,
4483
4484 /**
4485 * Unicode script "Nabataean".
4486 * @since 9
4487 */
4488 NABATAEAN,
4489
4490 /**
4491 * Unicode script "Palmyrene".
4492 * @since 9
4493 */
4494 PALMYRENE,
4495
4496 /**
4497 * Unicode script "Pau Cin Hau".
4498 * @since 9
4499 */
4500 PAU_CIN_HAU,
4501
4502 /**
4503 * Unicode script "Old Permic".
4504 * @since 9
4505 */
4506 OLD_PERMIC,
4507
4508 /**
4509 * Unicode script "Psalter Pahlavi".
4510 * @since 9
4511 */
4512 PSALTER_PAHLAVI,
4513
4514 /**
4515 * Unicode script "Siddham".
4516 * @since 9
4517 */
4518 SIDDHAM,
4519
4520 /**
4521 * Unicode script "Khudawadi".
4522 * @since 9
4523 */
4524 KHUDAWADI,
4525
4526 /**
4527 * Unicode script "Tirhuta".
4528 * @since 9
4529 */
4530 TIRHUTA,
4531
4532 /**
4533 * Unicode script "Warang Citi".
4534 * @since 9
4535 */
4536 WARANG_CITI,
4537
4538 /**
4539 * Unicode script "Ahom".
4540 * @since 9
4541 */
4542 AHOM,
4543
4544 /**
4545 * Unicode script "Anatolian Hieroglyphs".
4546 * @since 9
4547 */
4548 ANATOLIAN_HIEROGLYPHS,
4549
4550 /**
4551 * Unicode script "Hatran".
4552 * @since 9
4553 */
4554 HATRAN,
4555
4556 /**
4557 * Unicode script "Multani".
4558 * @since 9
4559 */
4560 MULTANI,
4561
4562 /**
4563 * Unicode script "Old Hungarian".
4564 * @since 9
4565 */
4566 OLD_HUNGARIAN,
4567
4568 /**
4569 * Unicode script "SignWriting".
4570 * @since 9
4571 */
4572 SIGNWRITING,
4573
4574 /**
4575 * Unicode script "Adlam".
4576 * @since 11
4577 */
4578 ADLAM,
4579
4580 /**
4581 * Unicode script "Bhaiksuki".
4582 * @since 11
4583 */
4584 BHAIKSUKI,
4585
4586 /**
4587 * Unicode script "Marchen".
4588 * @since 11
4589 */
4590 MARCHEN,
4591
4592 /**
4593 * Unicode script "Newa".
4594 * @since 11
4595 */
4596 NEWA,
4597
4598 /**
4599 * Unicode script "Osage".
4600 * @since 11
4601 */
4602 OSAGE,
4603
4604 /**
4605 * Unicode script "Tangut".
4606 * @since 11
4607 */
4608 TANGUT,
4609
4610 /**
4611 * Unicode script "Masaram Gondi".
4612 * @since 11
4613 */
4614 MASARAM_GONDI,
4615
4616 /**
4617 * Unicode script "Nushu".
4618 * @since 11
4619 */
4620 NUSHU,
4621
4622 /**
4623 * Unicode script "Soyombo".
4624 * @since 11
4625 */
4626 SOYOMBO,
4627
4628 /**
4629 * Unicode script "Zanabazar Square".
4630 * @since 11
4631 */
4632 ZANABAZAR_SQUARE,
4633
4634 /**
4635 * Unicode script "Unknown".
4636 */
4637 UNKNOWN;
4638
4639 private static final int[] scriptStarts = {
4640 0x0000, // 0000..0040; COMMON
4641 0x0041, // 0041..005A; LATIN
4642 0x005B, // 005B..0060; COMMON
4643 0x0061, // 0061..007A; LATIN
4644 0x007B, // 007B..00A9; COMMON
4645 0x00AA, // 00AA ; LATIN
4646 0x00AB, // 00AB..00B9; COMMON
4647 0x00BA, // 00BA ; LATIN
4648 0x00BB, // 00BB..00BF; COMMON
4649 0x00C0, // 00C0..00D6; LATIN
4650 0x00D7, // 00D7 ; COMMON
4651 0x00D8, // 00D8..00F6; LATIN
4652 0x00F7, // 00F7 ; COMMON
4653 0x00F8, // 00F8..02B8; LATIN
4654 0x02B9, // 02B9..02DF; COMMON
4655 0x02E0, // 02E0..02E4; LATIN
4656 0x02E5, // 02E5..02E9; COMMON
4657 0x02EA, // 02EA..02EB; BOPOMOFO
4658 0x02EC, // 02EC..02FF; COMMON
4659 0x0300, // 0300..036F; INHERITED
4660 0x0370, // 0370..0373; GREEK
4661 0x0374, // 0374 ; COMMON
4662 0x0375, // 0375..0377; GREEK
4663 0x0378, // 0378..0379; UNKNOWN
4664 0x037A, // 037A..037D; GREEK
4665 0x037E, // 037E ; COMMON
4666 0x037F, // 037F ; GREEK
4667 0x0380, // 0380..0383; UNKNOWN
4668 0x0384, // 0384 ; GREEK
4669 0x0385, // 0385 ; COMMON
4670 0x0386, // 0386 ; GREEK
4671 0x0387, // 0387 ; COMMON
4672 0x0388, // 0388..038A; GREEK
4673 0x038B, // 038B ; UNKNOWN
4674 0x038C, // 038C ; GREEK
4675 0x038D, // 038D ; UNKNOWN
4676 0x038E, // 038E..03A1; GREEK
4677 0x03A2, // 03A2 ; UNKNOWN
4678 0x03A3, // 03A3..03E1; GREEK
4679 0x03E2, // 03E2..03EF; COPTIC
4680 0x03F0, // 03F0..03FF; GREEK
4681 0x0400, // 0400..0484; CYRILLIC
4682 0x0485, // 0485..0486; INHERITED
4683 0x0487, // 0487..052F; CYRILLIC
4684 0x0530, // 0530 ; UNKNOWN
4685 0x0531, // 0531..0556; ARMENIAN
4686 0x0557, // 0557..0558; UNKNOWN
4687 0x0559, // 0559..055F; ARMENIAN
4688 0x0560, // 0560 ; UNKNOWN
4689 0x0561, // 0561..0587; ARMENIAN
4690 0x0588, // 0588 ; UNKNOWN
4691 0x0589, // 0589 ; COMMON
4692 0x058A, // 058A ; ARMENIAN
4693 0x058B, // 058B..058C; UNKNOWN
4694 0x058D, // 058D..058F; ARMENIAN
4695 0x0590, // 0590 ; UNKNOWN
4696 0x0591, // 0591..05C7; HEBREW
4697 0x05C8, // 05C8..05CF; UNKNOWN
4698 0x05D0, // 05D0..05EA; HEBREW
4699 0x05EB, // 05EB..05EF; UNKNOWN
4700 0x05F0, // 05F0..05F4; HEBREW
4701 0x05F5, // 05F5..05FF; UNKNOWN
4702 0x0600, // 0600..0604; ARABIC
4703 0x0605, // 0605 ; COMMON
4704 0x0606, // 0606..060B; ARABIC
4705 0x060C, // 060C ; COMMON
4706 0x060D, // 060D..061A; ARABIC
4707 0x061B, // 061B ; COMMON
4708 0x061C, // 061C ; ARABIC
4709 0x061D, // 061D ; UNKNOWN
4710 0x061E, // 061E ; ARABIC
4711 0x061F, // 061F ; COMMON
4712 0x0620, // 0620..063F; ARABIC
4713 0x0640, // 0640 ; COMMON
4714 0x0641, // 0641..064A; ARABIC
4715 0x064B, // 064B..0655; INHERITED
4716 0x0656, // 0656..066F; ARABIC
4717 0x0670, // 0670 ; INHERITED
4718 0x0671, // 0671..06DC; ARABIC
4719 0x06DD, // 06DD ; COMMON
4720 0x06DE, // 06DE..06FF; ARABIC
4721 0x0700, // 0700..070D; SYRIAC
4722 0x070E, // 070E ; UNKNOWN
4723 0x070F, // 070F..074A; SYRIAC
4724 0x074B, // 074B..074C; UNKNOWN
4725 0x074D, // 074D..074F; SYRIAC
4726 0x0750, // 0750..077F; ARABIC
4727 0x0780, // 0780..07B1; THAANA
4728 0x07B2, // 07B2..07BF; UNKNOWN
4729 0x07C0, // 07C0..07FA; NKO
4730 0x07FB, // 07FB..07FF; UNKNOWN
4731 0x0800, // 0800..082D; SAMARITAN
4732 0x082E, // 082E..082F; UNKNOWN
4733 0x0830, // 0830..083E; SAMARITAN
4734 0x083F, // 083F ; UNKNOWN
4735 0x0840, // 0840..085B; MANDAIC
4736 0x085C, // 085C..085D; UNKNOWN
4737 0x085E, // 085E ; MANDAIC
4738 0x085F, // 085F ; UNKNOWN
4739 0x0860, // 0860..086A; SYRIAC
4740 0x086B, // 086B..089F; UNKNOWN
4741 0x08A0, // 08A0..08B4; ARABIC
4742 0x08B5, // 08B5 ; UNKNOWN
4743 0x08B6, // 08B6..08BD; ARABIC
4744 0x08BE, // 08BE..08D3; UNKNOWN
4745 0x08D4, // 08D4..08E1; ARABIC
4746 0x08E2, // 08E2 ; COMMON
4747 0x08E3, // 08E3..08FF; ARABIC
4748 0x0900, // 0900..0950; DEVANAGARI
4749 0x0951, // 0951..0952; INHERITED
4750 0x0953, // 0953..0963; DEVANAGARI
4751 0x0964, // 0964..0965; COMMON
4752 0x0966, // 0966..097F; DEVANAGARI
4753 0x0980, // 0980..0983; BENGALI
4754 0x0984, // 0984 ; UNKNOWN
4755 0x0985, // 0985..098C; BENGALI
4756 0x098D, // 098D..098E; UNKNOWN
4757 0x098F, // 098F..0990; BENGALI
4758 0x0991, // 0991..0992; UNKNOWN
4759 0x0993, // 0993..09A8; BENGALI
4760 0x09A9, // 09A9 ; UNKNOWN
4761 0x09AA, // 09AA..09B0; BENGALI
4762 0x09B1, // 09B1 ; UNKNOWN
4763 0x09B2, // 09B2 ; BENGALI
4764 0x09B3, // 09B3..09B5; UNKNOWN
4765 0x09B6, // 09B6..09B9; BENGALI
4766 0x09BA, // 09BA..09BB; UNKNOWN
4767 0x09BC, // 09BC..09C4; BENGALI
4768 0x09C5, // 09C5..09C6; UNKNOWN
4769 0x09C7, // 09C7..09C8; BENGALI
4770 0x09C9, // 09C9..09CA; UNKNOWN
4771 0x09CB, // 09CB..09CE; BENGALI
4772 0x09CF, // 09CF..09D6; UNKNOWN
4773 0x09D7, // 09D7 ; BENGALI
4774 0x09D8, // 09D8..09DB; UNKNOWN
4775 0x09DC, // 09DC..09DD; BENGALI
4776 0x09DE, // 09DE ; UNKNOWN
4777 0x09DF, // 09DF..09E3; BENGALI
4778 0x09E4, // 09E4..09E5; UNKNOWN
4779 0x09E6, // 09E6..09FD; BENGALI
4780 0x09FE, // 09FE..0A00; UNKNOWN
4781 0x0A01, // 0A01..0A03; GURMUKHI
4782 0x0A04, // 0A04 ; UNKNOWN
4783 0x0A05, // 0A05..0A0A; GURMUKHI
4784 0x0A0B, // 0A0B..0A0E; UNKNOWN
4785 0x0A0F, // 0A0F..0A10; GURMUKHI
4786 0x0A11, // 0A11..0A12; UNKNOWN
4787 0x0A13, // 0A13..0A28; GURMUKHI
4788 0x0A29, // 0A29 ; UNKNOWN
4789 0x0A2A, // 0A2A..0A30; GURMUKHI
4790 0x0A31, // 0A31 ; UNKNOWN
4791 0x0A32, // 0A32..0A33; GURMUKHI
4792 0x0A34, // 0A34 ; UNKNOWN
4793 0x0A35, // 0A35..0A36; GURMUKHI
4794 0x0A37, // 0A37 ; UNKNOWN
4795 0x0A38, // 0A38..0A39; GURMUKHI
4796 0x0A3A, // 0A3A..0A3B; UNKNOWN
4797 0x0A3C, // 0A3C ; GURMUKHI
4798 0x0A3D, // 0A3D ; UNKNOWN
4799 0x0A3E, // 0A3E..0A42; GURMUKHI
4800 0x0A43, // 0A43..0A46; UNKNOWN
4801 0x0A47, // 0A47..0A48; GURMUKHI
4802 0x0A49, // 0A49..0A4A; UNKNOWN
4803 0x0A4B, // 0A4B..0A4D; GURMUKHI
4804 0x0A4E, // 0A4E..0A50; UNKNOWN
4805 0x0A51, // 0A51 ; GURMUKHI
4806 0x0A52, // 0A52..0A58; UNKNOWN
4807 0x0A59, // 0A59..0A5C; GURMUKHI
4808 0x0A5D, // 0A5D ; UNKNOWN
4809 0x0A5E, // 0A5E ; GURMUKHI
4810 0x0A5F, // 0A5F..0A65; UNKNOWN
4811 0x0A66, // 0A66..0A75; GURMUKHI
4812 0x0A76, // 0A76..0A80; UNKNOWN
4813 0x0A81, // 0A81..0A83; GUJARATI
4814 0x0A84, // 0A84 ; UNKNOWN
4815 0x0A85, // 0A85..0A8D; GUJARATI
4816 0x0A8E, // 0A8E ; UNKNOWN
4817 0x0A8F, // 0A8F..0A91; GUJARATI
4818 0x0A92, // 0A92 ; UNKNOWN
4819 0x0A93, // 0A93..0AA8; GUJARATI
4820 0x0AA9, // 0AA9 ; UNKNOWN
4821 0x0AAA, // 0AAA..0AB0; GUJARATI
4822 0x0AB1, // 0AB1 ; UNKNOWN
4823 0x0AB2, // 0AB2..0AB3; GUJARATI
4824 0x0AB4, // 0AB4 ; UNKNOWN
4825 0x0AB5, // 0AB5..0AB9; GUJARATI
4826 0x0ABA, // 0ABA..0ABB; UNKNOWN
4827 0x0ABC, // 0ABC..0AC5; GUJARATI
4828 0x0AC6, // 0AC6 ; UNKNOWN
4829 0x0AC7, // 0AC7..0AC9; GUJARATI
4830 0x0ACA, // 0ACA ; UNKNOWN
4831 0x0ACB, // 0ACB..0ACD; GUJARATI
4832 0x0ACE, // 0ACE..0ACF; UNKNOWN
4833 0x0AD0, // 0AD0 ; GUJARATI
4834 0x0AD1, // 0AD1..0ADF; UNKNOWN
4835 0x0AE0, // 0AE0..0AE3; GUJARATI
4836 0x0AE4, // 0AE4..0AE5; UNKNOWN
4837 0x0AE6, // 0AE6..0AF1; GUJARATI
4838 0x0AF2, // 0AF2..0AF8; UNKNOWN
4839 0x0AF9, // 0AF9..0AFF; GUJARATI
4840 0x0B00, // 0B00 ; UNKNOWN
4841 0x0B01, // 0B01..0B03; ORIYA
4842 0x0B04, // 0B04 ; UNKNOWN
4843 0x0B05, // 0B05..0B0C; ORIYA
4844 0x0B0D, // 0B0D..0B0E; UNKNOWN
4845 0x0B0F, // 0B0F..0B10; ORIYA
4846 0x0B11, // 0B11..0B12; UNKNOWN
4847 0x0B13, // 0B13..0B28; ORIYA
4848 0x0B29, // 0B29 ; UNKNOWN
4849 0x0B2A, // 0B2A..0B30; ORIYA
4850 0x0B31, // 0B31 ; UNKNOWN
4851 0x0B32, // 0B32..0B33; ORIYA
4852 0x0B34, // 0B34 ; UNKNOWN
4853 0x0B35, // 0B35..0B39; ORIYA
4854 0x0B3A, // 0B3A..0B3B; UNKNOWN
4855 0x0B3C, // 0B3C..0B44; ORIYA
4856 0x0B45, // 0B45..0B46; UNKNOWN
4857 0x0B47, // 0B47..0B48; ORIYA
4858 0x0B49, // 0B49..0B4A; UNKNOWN
4859 0x0B4B, // 0B4B..0B4D; ORIYA
4860 0x0B4E, // 0B4E..0B55; UNKNOWN
4861 0x0B56, // 0B56..0B57; ORIYA
4862 0x0B58, // 0B58..0B5B; UNKNOWN
4863 0x0B5C, // 0B5C..0B5D; ORIYA
4864 0x0B5E, // 0B5E ; UNKNOWN
4865 0x0B5F, // 0B5F..0B63; ORIYA
4866 0x0B64, // 0B64..0B65; UNKNOWN
4867 0x0B66, // 0B66..0B77; ORIYA
4868 0x0B78, // 0B78..0B81; UNKNOWN
4869 0x0B82, // 0B82..0B83; TAMIL
4870 0x0B84, // 0B84 ; UNKNOWN
4871 0x0B85, // 0B85..0B8A; TAMIL
4872 0x0B8B, // 0B8B..0B8D; UNKNOWN
4873 0x0B8E, // 0B8E..0B90; TAMIL
4874 0x0B91, // 0B91 ; UNKNOWN
4875 0x0B92, // 0B92..0B95; TAMIL
4876 0x0B96, // 0B96..0B98; UNKNOWN
4877 0x0B99, // 0B99..0B9A; TAMIL
4878 0x0B9B, // 0B9B ; UNKNOWN
4879 0x0B9C, // 0B9C ; TAMIL
4880 0x0B9D, // 0B9D ; UNKNOWN
4881 0x0B9E, // 0B9E..0B9F; TAMIL
4882 0x0BA0, // 0BA0..0BA2; UNKNOWN
4883 0x0BA3, // 0BA3..0BA4; TAMIL
4884 0x0BA5, // 0BA5..0BA7; UNKNOWN
4885 0x0BA8, // 0BA8..0BAA; TAMIL
4886 0x0BAB, // 0BAB..0BAD; UNKNOWN
4887 0x0BAE, // 0BAE..0BB9; TAMIL
4888 0x0BBA, // 0BBA..0BBD; UNKNOWN
4889 0x0BBE, // 0BBE..0BC2; TAMIL
4890 0x0BC3, // 0BC3..0BC5; UNKNOWN
4891 0x0BC6, // 0BC6..0BC8; TAMIL
4892 0x0BC9, // 0BC9 ; UNKNOWN
4893 0x0BCA, // 0BCA..0BCD; TAMIL
4894 0x0BCE, // 0BCE..0BCF; UNKNOWN
4895 0x0BD0, // 0BD0 ; TAMIL
4896 0x0BD1, // 0BD1..0BD6; UNKNOWN
4897 0x0BD7, // 0BD7 ; TAMIL
4898 0x0BD8, // 0BD8..0BE5; UNKNOWN
4899 0x0BE6, // 0BE6..0BFA; TAMIL
4900 0x0BFB, // 0BFB..0BFF; UNKNOWN
4901 0x0C00, // 0C00..0C03; TELUGU
4902 0x0C04, // 0C04 ; UNKNOWN
4903 0x0C05, // 0C05..0C0C; TELUGU
4904 0x0C0D, // 0C0D ; UNKNOWN
4905 0x0C0E, // 0C0E..0C10; TELUGU
4906 0x0C11, // 0C11 ; UNKNOWN
4907 0x0C12, // 0C12..0C28; TELUGU
4908 0x0C29, // 0C29 ; UNKNOWN
4909 0x0C2A, // 0C2A..0C39; TELUGU
4910 0x0C3A, // 0C3A..0C3C; UNKNOWN
4911 0x0C3D, // 0C3D..0C44; TELUGU
4912 0x0C45, // 0C45 ; UNKNOWN
4913 0x0C46, // 0C46..0C48; TELUGU
4914 0x0C49, // 0C49 ; UNKNOWN
4915 0x0C4A, // 0C4A..0C4D; TELUGU
4916 0x0C4E, // 0C4E..0C54; UNKNOWN
4917 0x0C55, // 0C55..0C56; TELUGU
4918 0x0C57, // 0C57 ; UNKNOWN
4919 0x0C58, // 0C58..0C5A; TELUGU
4920 0x0C5B, // 0C5B..0C5F; UNKNOWN
4921 0x0C60, // 0C60..0C63; TELUGU
4922 0x0C64, // 0C64..0C65; UNKNOWN
4923 0x0C66, // 0C66..0C6F; TELUGU
4924 0x0C70, // 0C70..0C77; UNKNOWN
4925 0x0C78, // 0C78..0C7F; TELUGU
4926 0x0C80, // 0C80..0C83; KANNADA
4927 0x0C84, // 0C84 ; UNKNOWN
4928 0x0C85, // 0C85..0C8C; KANNADA
4929 0x0C8D, // 0C8D ; UNKNOWN
4930 0x0C8E, // 0C8E..0C90; KANNADA
4931 0x0C91, // 0C91 ; UNKNOWN
4932 0x0C92, // 0C92..0CA8; KANNADA
4933 0x0CA9, // 0CA9 ; UNKNOWN
4934 0x0CAA, // 0CAA..0CB3; KANNADA
4935 0x0CB4, // 0CB4 ; UNKNOWN
4936 0x0CB5, // 0CB5..0CB9; KANNADA
4937 0x0CBA, // 0CBA..0CBB; UNKNOWN
4938 0x0CBC, // 0CBC..0CC4; KANNADA
4939 0x0CC5, // 0CC5 ; UNKNOWN
4940 0x0CC6, // 0CC6..0CC8; KANNADA
4941 0x0CC9, // 0CC9 ; UNKNOWN
4942 0x0CCA, // 0CCA..0CCD; KANNADA
4943 0x0CCE, // 0CCE..0CD4; UNKNOWN
4944 0x0CD5, // 0CD5..0CD6; KANNADA
4945 0x0CD7, // 0CD7..0CDD; UNKNOWN
4946 0x0CDE, // 0CDE ; KANNADA
4947 0x0CDF, // 0CDF ; UNKNOWN
4948 0x0CE0, // 0CE0..0CE3; KANNADA
4949 0x0CE4, // 0CE4..0CE5; UNKNOWN
4950 0x0CE6, // 0CE6..0CEF; KANNADA
4951 0x0CF0, // 0CF0 ; UNKNOWN
4952 0x0CF1, // 0CF1..0CF2; KANNADA
4953 0x0CF3, // 0CF3..0CFF; UNKNOWN
4954 0x0D00, // 0D00..0D03; MALAYALAM
4955 0x0D04, // 0D04 ; UNKNOWN
4956 0x0D05, // 0D05..0D0C; MALAYALAM
4957 0x0D0D, // 0D0D ; UNKNOWN
4958 0x0D0E, // 0D0E..0D10; MALAYALAM
4959 0x0D11, // 0D11 ; UNKNOWN
4960 0x0D12, // 0D12..0D44; MALAYALAM
4961 0x0D45, // 0D45 ; UNKNOWN
4962 0x0D46, // 0D46..0D48; MALAYALAM
4963 0x0D49, // 0D49 ; UNKNOWN
4964 0x0D4A, // 0D4A..0D4F; MALAYALAM
4965 0x0D50, // 0D50..0D53; UNKNOWN
4966 0x0D54, // 0D54..0D63; MALAYALAM
4967 0x0D64, // 0D64..0D65; UNKNOWN
4968 0x0D66, // 0D66..0D7F; MALAYALAM
4969 0x0D80, // 0D80..0D81; UNKNOWN
4970 0x0D82, // 0D82..0D83; SINHALA
4971 0x0D84, // 0D84 ; UNKNOWN
4972 0x0D85, // 0D85..0D96; SINHALA
4973 0x0D97, // 0D97..0D99; UNKNOWN
4974 0x0D9A, // 0D9A..0DB1; SINHALA
4975 0x0DB2, // 0DB2 ; UNKNOWN
4976 0x0DB3, // 0DB3..0DBB; SINHALA
4977 0x0DBC, // 0DBC ; UNKNOWN
4978 0x0DBD, // 0DBD ; SINHALA
4979 0x0DBE, // 0DBE..0DBF; UNKNOWN
4980 0x0DC0, // 0DC0..0DC6; SINHALA
4981 0x0DC7, // 0DC7..0DC9; UNKNOWN
4982 0x0DCA, // 0DCA ; SINHALA
4983 0x0DCB, // 0DCB..0DCE; UNKNOWN
4984 0x0DCF, // 0DCF..0DD4; SINHALA
4985 0x0DD5, // 0DD5 ; UNKNOWN
4986 0x0DD6, // 0DD6 ; SINHALA
4987 0x0DD7, // 0DD7 ; UNKNOWN
4988 0x0DD8, // 0DD8..0DDF; SINHALA
4989 0x0DE0, // 0DE0..0DE5; UNKNOWN
4990 0x0DE6, // 0DE6..0DEF; SINHALA
4991 0x0DF0, // 0DF0..0DF1; UNKNOWN
4992 0x0DF2, // 0DF2..0DF4; SINHALA
4993 0x0DF5, // 0DF5..0E00; UNKNOWN
4994 0x0E01, // 0E01..0E3A; THAI
4995 0x0E3B, // 0E3B..0E3E; UNKNOWN
4996 0x0E3F, // 0E3F ; COMMON
4997 0x0E40, // 0E40..0E5B; THAI
4998 0x0E5C, // 0E5C..0E80; UNKNOWN
4999 0x0E81, // 0E81..0E82; LAO
5000 0x0E83, // 0E83 ; UNKNOWN
5001 0x0E84, // 0E84 ; LAO
5002 0x0E85, // 0E85..0E86; UNKNOWN
5003 0x0E87, // 0E87..0E88; LAO
5004 0x0E89, // 0E89 ; UNKNOWN
5005 0x0E8A, // 0E8A ; LAO
5006 0x0E8B, // 0E8B..0E8C; UNKNOWN
5007 0x0E8D, // 0E8D ; LAO
5008 0x0E8E, // 0E8E..0E93; UNKNOWN
5009 0x0E94, // 0E94..0E97; LAO
5010 0x0E98, // 0E98 ; UNKNOWN
5011 0x0E99, // 0E99..0E9F; LAO
5012 0x0EA0, // 0EA0 ; UNKNOWN
5013 0x0EA1, // 0EA1..0EA3; LAO
5014 0x0EA4, // 0EA4 ; UNKNOWN
5015 0x0EA5, // 0EA5 ; LAO
5016 0x0EA6, // 0EA6 ; UNKNOWN
5017 0x0EA7, // 0EA7 ; LAO
5018 0x0EA8, // 0EA8..0EA9; UNKNOWN
5019 0x0EAA, // 0EAA..0EAB; LAO
5020 0x0EAC, // 0EAC ; UNKNOWN
5021 0x0EAD, // 0EAD..0EB9; LAO
5022 0x0EBA, // 0EBA ; UNKNOWN
5023 0x0EBB, // 0EBB..0EBD; LAO
5024 0x0EBE, // 0EBE..0EBF; UNKNOWN
5025 0x0EC0, // 0EC0..0EC4; LAO
5026 0x0EC5, // 0EC5 ; UNKNOWN
5027 0x0EC6, // 0EC6 ; LAO
5028 0x0EC7, // 0EC7 ; UNKNOWN
5029 0x0EC8, // 0EC8..0ECD; LAO
5030 0x0ECE, // 0ECE..0ECF; UNKNOWN
5031 0x0ED0, // 0ED0..0ED9; LAO
5032 0x0EDA, // 0EDA..0EDB; UNKNOWN
5033 0x0EDC, // 0EDC..0EDF; LAO
5034 0x0EE0, // 0EE0..0EFF; UNKNOWN
5035 0x0F00, // 0F00..0F47; TIBETAN
5036 0x0F48, // 0F48 ; UNKNOWN
5037 0x0F49, // 0F49..0F6C; TIBETAN
5038 0x0F6D, // 0F6D..0F70; UNKNOWN
5039 0x0F71, // 0F71..0F97; TIBETAN
5040 0x0F98, // 0F98 ; UNKNOWN
5041 0x0F99, // 0F99..0FBC; TIBETAN
5042 0x0FBD, // 0FBD ; UNKNOWN
5043 0x0FBE, // 0FBE..0FCC; TIBETAN
5044 0x0FCD, // 0FCD ; UNKNOWN
5045 0x0FCE, // 0FCE..0FD4; TIBETAN
5046 0x0FD5, // 0FD5..0FD8; COMMON
5047 0x0FD9, // 0FD9..0FDA; TIBETAN
5048 0x0FDB, // 0FDB..FFF; UNKNOWN
5049 0x1000, // 1000..109F; MYANMAR
5050 0x10A0, // 10A0..10C5; GEORGIAN
5051 0x10C6, // 10C6 ; UNKNOWN
5052 0x10C7, // 10C7 ; GEORGIAN
5053 0x10C8, // 10C8..10CC; UNKNOWN
5054 0x10CD, // 10CD ; GEORGIAN
5055 0x10CE, // 10CE..10CF; UNKNOWN
5056 0x10D0, // 10D0..10FA; GEORGIAN
5057 0x10FB, // 10FB ; COMMON
5058 0x10FC, // 10FC..10FF; GEORGIAN
5059 0x1100, // 1100..11FF; HANGUL
5060 0x1200, // 1200..1248; ETHIOPIC
5061 0x1249, // 1249 ; UNKNOWN
5062 0x124A, // 124A..124D; ETHIOPIC
5063 0x124E, // 124E..124F; UNKNOWN
5064 0x1250, // 1250..1256; ETHIOPIC
5065 0x1257, // 1257 ; UNKNOWN
5066 0x1258, // 1258 ; ETHIOPIC
5067 0x1259, // 1259 ; UNKNOWN
5068 0x125A, // 125A..125D; ETHIOPIC
5069 0x125E, // 125E..125F; UNKNOWN
5070 0x1260, // 1260..1288; ETHIOPIC
5071 0x1289, // 1289 ; UNKNOWN
5072 0x128A, // 128A..128D; ETHIOPIC
5073 0x128E, // 128E..128F; UNKNOWN
5074 0x1290, // 1290..12B0; ETHIOPIC
5075 0x12B1, // 12B1 ; UNKNOWN
5076 0x12B2, // 12B2..12B5; ETHIOPIC
5077 0x12B6, // 12B6..12B7; UNKNOWN
5078 0x12B8, // 12B8..12BE; ETHIOPIC
5079 0x12BF, // 12BF ; UNKNOWN
5080 0x12C0, // 12C0 ; ETHIOPIC
5081 0x12C1, // 12C1 ; UNKNOWN
5082 0x12C2, // 12C2..12C5; ETHIOPIC
5083 0x12C6, // 12C6..12C7; UNKNOWN
5084 0x12C8, // 12C8..12D6; ETHIOPIC
5085 0x12D7, // 12D7 ; UNKNOWN
5086 0x12D8, // 12D8..1310; ETHIOPIC
5087 0x1311, // 1311 ; UNKNOWN
5088 0x1312, // 1312..1315; ETHIOPIC
5089 0x1316, // 1316..1317; UNKNOWN
5090 0x1318, // 1318..135A; ETHIOPIC
5091 0x135B, // 135B..135C; UNKNOWN
5092 0x135D, // 135D..137C; ETHIOPIC
5093 0x137D, // 137D..137F; UNKNOWN
5094 0x1380, // 1380..1399; ETHIOPIC
5095 0x139A, // 139A..139F; UNKNOWN
5096 0x13A0, // 13A0..13F5; CHEROKEE
5097 0x13F6, // 13F6..13F7; UNKNOWN
5098 0x13F8, // 13F8..13FD; CHEROKEE
5099 0x13FE, // 13FE..13FF; UNKNOWN
5100 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5101 0x1680, // 1680..169C; OGHAM
5102 0x169D, // 169D..169F; UNKNOWN
5103 0x16A0, // 16A0..16EA; RUNIC
5104 0x16EB, // 16EB..16ED; COMMON
5105 0x16EE, // 16EE..16F8; RUNIC
5106 0x16F9, // 16F9..16FF; UNKNOWN
5107 0x1700, // 1700..170C; TAGALOG
5108 0x170D, // 170D ; UNKNOWN
5109 0x170E, // 170E..1714; TAGALOG
5110 0x1715, // 1715..171F; UNKNOWN
5111 0x1720, // 1720..1734; HANUNOO
5112 0x1735, // 1735..1736; COMMON
5113 0x1737, // 1737..173F; UNKNOWN
5114 0x1740, // 1740..1753; BUHID
5115 0x1754, // 1754..175F; UNKNOWN
5116 0x1760, // 1760..176C; TAGBANWA
5117 0x176D, // 176D ; UNKNOWN
5118 0x176E, // 176E..1770; TAGBANWA
5119 0x1771, // 1771 ; UNKNOWN
5120 0x1772, // 1772..1773; TAGBANWA
5121 0x1774, // 1774..177F; UNKNOWN
5122 0x1780, // 1780..17DD; KHMER
5123 0x17DE, // 17DE..17DF; UNKNOWN
5124 0x17E0, // 17E0..17E9; KHMER
5125 0x17EA, // 17EA..17EF; UNKNOWN
5126 0x17F0, // 17F0..17F9; KHMER
5127 0x17FA, // 17FA..17FF; UNKNOWN
5128 0x1800, // 1800..1801; MONGOLIAN
5129 0x1802, // 1802..1803; COMMON
5130 0x1804, // 1804 ; MONGOLIAN
5131 0x1805, // 1805 ; COMMON
5132 0x1806, // 1806..180E; MONGOLIAN
5133 0x180F, // 180F ; UNKNOWN
5134 0x1810, // 1810..1819; MONGOLIAN
5135 0x181A, // 181A..181F; UNKNOWN
5136 0x1820, // 1820..1877; MONGOLIAN
5137 0x1878, // 1878..187F; UNKNOWN
5138 0x1880, // 1880..18AA; MONGOLIAN
5139 0x18AB, // 18AB..18AF; UNKNOWN
5140 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
5141 0x18F6, // 18F6..18FF; UNKNOWN
5142 0x1900, // 1900..191E; LIMBU
5143 0x191F, // 191F ; UNKNOWN
5144 0x1920, // 1920..192B; LIMBU
5145 0x192C, // 192C..192F; UNKNOWN
5146 0x1930, // 1930..193B; LIMBU
5147 0x193C, // 193C..193F; UNKNOWN
5148 0x1940, // 1940 ; LIMBU
5149 0x1941, // 1941..1943; UNKNOWN
5150 0x1944, // 1944..194F; LIMBU
5151 0x1950, // 1950..196D; TAI_LE
5152 0x196E, // 196E..196F; UNKNOWN
5153 0x1970, // 1970..1974; TAI_LE
5154 0x1975, // 1975..197F; UNKNOWN
5155 0x1980, // 1980..19AB; NEW_TAI_LUE
5156 0x19AC, // 19AC..19AF; UNKNOWN
5157 0x19B0, // 19B0..19C9; NEW_TAI_LUE
5158 0x19CA, // 19CA..19CF; UNKNOWN
5159 0x19D0, // 19D0..19DA; NEW_TAI_LUE
5160 0x19DB, // 19DB..19DD; UNKNOWN
5161 0x19DE, // 19DE..19DF; NEW_TAI_LUE
5162 0x19E0, // 19E0..19FF; KHMER
5163 0x1A00, // 1A00..1A1B; BUGINESE
5164 0x1A1C, // 1A1C..1A1D; UNKNOWN
5165 0x1A1E, // 1A1E..1A1F; BUGINESE
5166 0x1A20, // 1A20..1A5E; TAI_THAM
5167 0x1A5F, // 1A5F ; UNKNOWN
5168 0x1A60, // 1A60..1A7C; TAI_THAM
5169 0x1A7D, // 1A7D..1A7E; UNKNOWN
5170 0x1A7F, // 1A7F..1A89; TAI_THAM
5171 0x1A8A, // 1A8A..1A8F; UNKNOWN
5172 0x1A90, // 1A90..1A99; TAI_THAM
5173 0x1A9A, // 1A9A..1A9F; UNKNOWN
5174 0x1AA0, // 1AA0..1AAD; TAI_THAM
5175 0x1AAE, // 1AAE..1AAF; UNKNOWN
5176 0x1AB0, // 1AB0..1ABE; INHERITED
5177 0x1ABF, // 1ABF..1AFF; UNKNOWN
5178 0x1B00, // 1B00..1B4B; BALINESE
5179 0x1B4C, // 1B4C..1B4F; UNKNOWN
5180 0x1B50, // 1B50..1B7C; BALINESE
5181 0x1B7D, // 1B7D..1B7F; UNKNOWN
5182 0x1B80, // 1B80..1BBF; SUNDANESE
5183 0x1BC0, // 1BC0..1BF3; BATAK
5184 0x1BF4, // 1BF4..1BFB; UNKNOWN
5185 0x1BFC, // 1BFC..1BFF; BATAK
5186 0x1C00, // 1C00..1C37; LEPCHA
5187 0x1C38, // 1C38..1C3A; UNKNOWN
5188 0x1C3B, // 1C3B..1C49; LEPCHA
5189 0x1C4A, // 1C4A..1C4C; UNKNOWN
5190 0x1C4D, // 1C4D..1C4F; LEPCHA
5191 0x1C50, // 1C50..1C7F; OL_CHIKI
5192 0x1C80, // 1C80..1C88; CYRILLIC
5193 0x1C89, // 1C89..1CBF; UNKNOWN
5194 0x1CC0, // 1CC0..1CC7; SUNDANESE
5195 0x1CC8, // 1CC8..1CCF; UNKNOWN
5196 0x1CD0, // 1CD0..1CD2; INHERITED
5197 0x1CD3, // 1CD3 ; COMMON
5198 0x1CD4, // 1CD4..1CE0; INHERITED
5199 0x1CE1, // 1CE1 ; COMMON
5200 0x1CE2, // 1CE2..1CE8; INHERITED
5201 0x1CE9, // 1CE9..1CEC; COMMON
5202 0x1CED, // 1CED ; INHERITED
5203 0x1CEE, // 1CEE..1CF3; COMMON
5204 0x1CF4, // 1CF4 ; INHERITED
5205 0x1CF5, // 1CF5..1CF7; COMMON
5206 0x1CF8, // 1CF8..1CF9; INHERITED
5207 0x1CFA, // 1CFA..1CFF; UNKNOWN
5208 0x1D00, // 1D00..1D25; LATIN
5209 0x1D26, // 1D26..1D2A; GREEK
5210 0x1D2B, // 1D2B ; CYRILLIC
5211 0x1D2C, // 1D2C..1D5C; LATIN
5212 0x1D5D, // 1D5D..1D61; GREEK
5213 0x1D62, // 1D62..1D65; LATIN
5214 0x1D66, // 1D66..1D6A; GREEK
5215 0x1D6B, // 1D6B..1D77; LATIN
5216 0x1D78, // 1D78 ; CYRILLIC
5217 0x1D79, // 1D79..1DBE; LATIN
5218 0x1DBF, // 1DBF ; GREEK
5219 0x1DC0, // 1DC0..1DF9; INHERITED
5220 0x1DFA, // 1DFA ; UNKNOWN
5221 0x1DFB, // 1DFB..1DFF; INHERITED
5222 0x1E00, // 1E00..1EFF; LATIN
5223 0x1F00, // 1F00..1F15; GREEK
5224 0x1F16, // 1F16..1F17; UNKNOWN
5225 0x1F18, // 1F18..1F1D; GREEK
5226 0x1F1E, // 1F1E..1F1F; UNKNOWN
5227 0x1F20, // 1F20..1F45; GREEK
5228 0x1F46, // 1F46..1F47; UNKNOWN
5229 0x1F48, // 1F48..1F4D; GREEK
5230 0x1F4E, // 1F4E..1F4F; UNKNOWN
5231 0x1F50, // 1F50..1F57; GREEK
5232 0x1F58, // 1F58 ; UNKNOWN
5233 0x1F59, // 1F59 ; GREEK
5234 0x1F5A, // 1F5A ; UNKNOWN
5235 0x1F5B, // 1F5B ; GREEK
5236 0x1F5C, // 1F5C ; UNKNOWN
5237 0x1F5D, // 1F5D ; GREEK
5238 0x1F5E, // 1F5E ; UNKNOWN
5239 0x1F5F, // 1F5F..1F7D; GREEK
5240 0x1F7E, // 1F7E..1F7F; UNKNOWN
5241 0x1F80, // 1F80..1FB4; GREEK
5242 0x1FB5, // 1FB5 ; UNKNOWN
5243 0x1FB6, // 1FB6..1FC4; GREEK
5244 0x1FC5, // 1FC5 ; UNKNOWN
5245 0x1FC6, // 1FC6..1FD3; GREEK
5246 0x1FD4, // 1FD4..1FD5; UNKNOWN
5247 0x1FD6, // 1FD6..1FDB; GREEK
5248 0x1FDC, // 1FDC ; UNKNOWN
5249 0x1FDD, // 1FDD..1FEF; GREEK
5250 0x1FF0, // 1FF0..1FF1; UNKNOWN
5251 0x1FF2, // 1FF2..1FF4; GREEK
5252 0x1FF5, // 1FF5 ; UNKNOWN
5253 0x1FF6, // 1FF6..1FFE; GREEK
5254 0x1FFF, // 1FFF ; UNKNOWN
5255 0x2000, // 2000..200B; COMMON
5256 0x200C, // 200C..200D; INHERITED
5257 0x200E, // 200E..2064; COMMON
5258 0x2065, // 2065 ; UNKNOWN
5259 0x2066, // 2066..2070; COMMON
5260 0x2071, // 2071 ; LATIN
5261 0x2072, // 2072..2073; UNKNOWN
5262 0x2074, // 2074..207E; COMMON
5263 0x207F, // 207F ; LATIN
5264 0x2080, // 2080..208E; COMMON
5265 0x208F, // 208F ; UNKNOWN
5266 0x2090, // 2090..209C; LATIN
5267 0x209D, // 209D..209F; UNKNOWN
5268 0x20A0, // 20A0..20BF; COMMON
5269 0x20C0, // 20C0..20CF; UNKNOWN
5270 0x20D0, // 20D0..20F0; INHERITED
5271 0x20F1, // 20F1..20FF; UNKNOWN
5272 0x2100, // 2100..2125; COMMON
5273 0x2126, // 2126 ; GREEK
5274 0x2127, // 2127..2129; COMMON
5275 0x212A, // 212A..212B; LATIN
5276 0x212C, // 212C..2131; COMMON
5277 0x2132, // 2132 ; LATIN
5278 0x2133, // 2133..214D; COMMON
5279 0x214E, // 214E ; LATIN
5280 0x214F, // 214F..215F; COMMON
5281 0x2160, // 2160..2188; LATIN
5282 0x2189, // 2189..218B; COMMON
5283 0x218C, // 218C..218F; UNKNOWN
5284 0x2190, // 2190..2426; COMMON
5285 0x2427, // 2427..243F; UNKNOWN
5286 0x2440, // 2440..244A; COMMON
5287 0x244B, // 244B..245F; UNKNOWN
5288 0x2460, // 2460..27FF; COMMON
5289 0x2800, // 2800..28FF; BRAILLE
5290 0x2900, // 2900..2B73; COMMON
5291 0x2B74, // 2B74..2B75; UNKNOWN
5292 0x2B76, // 2B76..2B95; COMMON
5293 0x2B96, // 2B96..2B97; UNKNOWN
5294 0x2B98, // 2B98..2BB9; COMMON
5295 0x2BBA, // 2BBA..2BBC; UNKNOWN
5296 0x2BBD, // 2BBD..2BC8; COMMON
5297 0x2BC9, // 2BC9 ; UNKNOWN
5298 0x2BCA, // 2BCA..2BD2; COMMON
5299 0x2BD3, // 2BD3..2BEB; UNKNOWN
5300 0x2BEC, // 2BEC..2BEF; COMMON
5301 0x2BF0, // 2BF0..2BFF; UNKNOWN
5302 0x2C00, // 2C00..2C2E; GLAGOLITIC
5303 0x2C2F, // 2C2F ; UNKNOWN
5304 0x2C30, // 2C30..2C5E; GLAGOLITIC
5305 0x2C5F, // 2C5F ; UNKNOWN
5306 0x2C60, // 2C60..2C7F; LATIN
5307 0x2C80, // 2C80..2CF3; COPTIC
5308 0x2CF4, // 2CF4..2CF8; UNKNOWN
5309 0x2CF9, // 2CF9..2CFF; COPTIC
5310 0x2D00, // 2D00..2D25; GEORGIAN
5311 0x2D26, // 2D26 ; UNKNOWN
5312 0x2D27, // 2D27 ; GEORGIAN
5313 0x2D28, // 2D28..2D2C; UNKNOWN
5314 0x2D2D, // 2D2D ; GEORGIAN
5315 0x2D2E, // 2D2E..2D2F; UNKNOWN
5316 0x2D30, // 2D30..2D67; TIFINAGH
5317 0x2D68, // 2D68..2D6E; UNKNOWN
5318 0x2D6F, // 2D6F..2D70; TIFINAGH
5319 0x2D71, // 2D71..2D7E; UNKNOWN
5320 0x2D7F, // 2D7F ; TIFINAGH
5321 0x2D80, // 2D80..2D96; ETHIOPIC
5322 0x2D97, // 2D97..2D9F; UNKNOWN
5323 0x2DA0, // 2DA0..2DA6; ETHIOPIC
5324 0x2DA7, // 2DA7 ; UNKNOWN
5325 0x2DA8, // 2DA8..2DAE; ETHIOPIC
5326 0x2DAF, // 2DAF ; UNKNOWN
5327 0x2DB0, // 2DB0..2DB6; ETHIOPIC
5328 0x2DB7, // 2DB7 ; UNKNOWN
5329 0x2DB8, // 2DB8..2DBE; ETHIOPIC
5330 0x2DBF, // 2DBF ; UNKNOWN
5331 0x2DC0, // 2DC0..2DC6; ETHIOPIC
5332 0x2DC7, // 2DC7 ; UNKNOWN
5333 0x2DC8, // 2DC8..2DCE; ETHIOPIC
5334 0x2DCF, // 2DCF ; UNKNOWN
5335 0x2DD0, // 2DD0..2DD6; ETHIOPIC
5336 0x2DD7, // 2DD7 ; UNKNOWN
5337 0x2DD8, // 2DD8..2DDE; ETHIOPIC
5338 0x2DDF, // 2DDF ; UNKNOWN
5339 0x2DE0, // 2DE0..2DFF; CYRILLIC
5340 0x2E00, // 2E00..2E49; COMMON
5341 0x2E50, // 2E50..2E7F; UNKNOWN
5342 0x2E80, // 2E80..2E99; HAN
5343 0x2E9A, // 2E9A ; UNKNOWN
5344 0x2E9B, // 2E9B..2EF3; HAN
5345 0x2EF4, // 2EF4..2EFF; UNKNOWN
5346 0x2F00, // 2F00..2FD5; HAN
5347 0x2FD6, // 2FD6..2FEF; UNKNOWN
5348 0x2FF0, // 2FF0..2FFB; COMMON
5349 0x2FFC, // 2FFC..2FFF; UNKNOWN
5350 0x3000, // 3000..3004; COMMON
5351 0x3005, // 3005 ; HAN
5352 0x3006, // 3006 ; COMMON
5353 0x3007, // 3007 ; HAN
5354 0x3008, // 3008..3020; COMMON
5355 0x3021, // 3021..3029; HAN
5356 0x302A, // 302A..302D; INHERITED
5357 0x302E, // 302E..302F; HANGUL
5358 0x3030, // 3030..3037; COMMON
5359 0x3038, // 3038..303B; HAN
5360 0x303C, // 303C..303F; COMMON
5361 0x3040, // 3040 ; UNKNOWN
5362 0x3041, // 3041..3096; HIRAGANA
5363 0x3097, // 3097..3098; UNKNOWN
5364 0x3099, // 3099..309A; INHERITED
5365 0x309B, // 309B..309C; COMMON
5366 0x309D, // 309D..309F; HIRAGANA
5367 0x30A0, // 30A0 ; COMMON
5368 0x30A1, // 30A1..30FA; KATAKANA
5369 0x30FB, // 30FB..30FC; COMMON
5370 0x30FD, // 30FD..30FF; KATAKANA
5371 0x3100, // 3100..3104; UNKNOWN
5372 0x3105, // 3105..312E; BOPOMOFO
5373 0x312F, // 312F..3130; UNKNOWN
5374 0x3131, // 3131..318E; HANGUL
5375 0x318F, // 318F ; UNKNOWN
5376 0x3190, // 3190..319F; COMMON
5377 0x31A0, // 31A0..31BA; BOPOMOFO
5378 0x31BB, // 31BB..31BF; UNKNOWN
5379 0x31C0, // 31C0..31E3; COMMON
5380 0x31E4, // 31E4..31EF; UNKNOWN
5381 0x31F0, // 31F0..31FF; KATAKANA
5382 0x3200, // 3200..321E; HANGUL
5383 0x321F, // 321F ; UNKNOWN
5384 0x3220, // 3220..325F; COMMON
5385 0x3260, // 3260..327E; HANGUL
5386 0x327F, // 327F..32CF; COMMON
5387 0x32D0, // 32D0..32FE; KATAKANA
5388 0x32FF, // 32FF ; UNKNOWN
5389 0x3300, // 3300..3357; KATAKANA
5390 0x3358, // 3358..33FF; COMMON
5391 0x3400, // 3400..4DB5; HAN
5392 0x4DB6, // 4DB6..4DBF; UNKNOWN
5393 0x4DC0, // 4DC0..4DFF; COMMON
5394 0x4E00, // 4E00..9FEA; HAN
5395 0x9FEB, // 9FEB..9FFF; UNKNOWN
5396 0xA000, // A000..A48C; YI
5397 0xA48D, // A48D..A48F; UNKNOWN
5398 0xA490, // A490..A4C6; YI
5399 0xA4C7, // A4C7..A4CF; UNKNOWN
5400 0xA4D0, // A4D0..A4FF; LISU
5401 0xA500, // A500..A62B; VAI
5402 0xA62C, // A62C..A63F; UNKNOWN
5403 0xA640, // A640..A69F; CYRILLIC
5404 0xA6A0, // A6A0..A6F7; BAMUM
5405 0xA6F8, // A6F8..A6FF; UNKNOWN
5406 0xA700, // A700..A721; COMMON
5407 0xA722, // A722..A787; LATIN
5408 0xA788, // A788..A78A; COMMON
5409 0xA78B, // A78B..A7AE; LATIN
5410 0xA7AF, // A7AF ; UNKNOWN
5411 0xA7B0, // A7B0..A7B7; LATIN
5412 0xA7B8, // A7B8..A7F6; UNKNOWN
5413 0xA7F7, // A7F7..A7FF; LATIN
5414 0xA800, // A800..A82B; SYLOTI_NAGRI
5415 0xA82C, // A82C..A82F; UNKNOWN
5416 0xA830, // A830..A839; COMMON
5417 0xA83A, // A83A..A83F; UNKNOWN
5418 0xA840, // A840..A877; PHAGS_PA
5419 0xA878, // A878..A87F; UNKNOWN
5420 0xA880, // A880..A8C5; SAURASHTRA
5421 0xA8C6, // A8C6..A8CD; UNKNOWN
5422 0xA8CE, // A8CE..A8D9; SAURASHTRA
5423 0xA8DA, // A8DA..A8DF; UNKNOWN
5424 0xA8E0, // A8E0..A8FD; DEVANAGARI
5425 0xA8FE, // A8FE..A8FF; UNKNOWN
5426 0xA900, // A900..A92D; KAYAH_LI
5427 0xA92E, // A92E ; COMMON
5428 0xA92F, // A92F ; KAYAH_LI
5429 0xA930, // A930..A953; REJANG
5430 0xA954, // A954..A95E; UNKNOWN
5431 0xA95F, // A95F ; REJANG
5432 0xA960, // A960..A97C; HANGUL
5433 0xA97D, // A97D..A97F; UNKNOWN
5434 0xA980, // A980..A9CD; JAVANESE
5435 0xA9CE, // A9CE ; UNKNOWN
5436 0xA9CF, // A9CF ; COMMON
5437 0xA9D0, // A9D0..A9D9; JAVANESE
5438 0xA9DA, // A9DA..A9DD; UNKNOWN
5439 0xA9DE, // A9DE..A9DF; JAVANESE
5440 0xA9E0, // A9E0..A9FE; MYANMAR
5441 0xA9FF, // A9FF ; UNKNOWN
5442 0xAA00, // AA00..AA36; CHAM
5443 0xAA37, // AA37..AA3F; UNKNOWN
5444 0xAA40, // AA40..AA4D; CHAM
5445 0xAA4E, // AA4E..AA4F; UNKNOWN
5446 0xAA50, // AA50..AA59; CHAM
5447 0xAA5A, // AA5A..AA5B; UNKNOWN
5448 0xAA5C, // AA5C..AA5F; CHAM
5449 0xAA60, // AA60..AA7F; MYANMAR
5450 0xAA80, // AA80..AAC2; TAI_VIET
5451 0xAAC3, // AAC3..AADA; UNKNOWN
5452 0xAADB, // AADB..AADF; TAI_VIET
5453 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
5454 0xAAF7, // AAF7..AB00; UNKNOWN
5455 0xAB01, // AB01..AB06; ETHIOPIC
5456 0xAB07, // AB07..AB08; UNKNOWN
5457 0xAB09, // AB09..AB0E; ETHIOPIC
5458 0xAB0F, // AB0F..AB10; UNKNOWN
5459 0xAB11, // AB11..AB16; ETHIOPIC
5460 0xAB17, // AB17..AB1F; UNKNOWN
5461 0xAB20, // AB20..AB26; ETHIOPIC
5462 0xAB27, // AB27 ; UNKNOWN
5463 0xAB28, // AB28..AB2E; ETHIOPIC
5464 0xAB2F, // AB2F ; UNKNOWN
5465 0xAB30, // AB30..AB5A; LATIN
5466 0xAB5B, // AB5B ; COMMON
5467 0xAB5C, // AB5C..AB64; LATIN
5468 0xAB65, // AB65 ; GREEK
5469 0xAB66, // AB66..AB6F; UNKNOWN
5470 0xAB70, // AB70..ABBF; CHEROKEE
5471 0xABC0, // ABC0..ABED; MEETEI_MAYEK
5472 0xABEE, // ABEE..ABEF; UNKNOWN
5473 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
5474 0xABFA, // ABFA..ABFF; UNKNOWN
5475 0xAC00, // AC00..D7A3; HANGUL
5476 0xD7A4, // D7A4..D7AF; UNKNOWN
5477 0xD7B0, // D7B0..D7C6; HANGUL
5478 0xD7C7, // D7C7..D7CA; UNKNOWN
5479 0xD7CB, // D7CB..D7FB; HANGUL
5480 0xD7FC, // D7FC..F8FF; UNKNOWN
5481 0xF900, // F900..FA6D; HAN
5482 0xFA6E, // FA6E..FA6F; UNKNOWN
5483 0xFA70, // FA70..FAD9; HAN
5484 0xFADA, // FADA..FAFF; UNKNOWN
5485 0xFB00, // FB00..FB06; LATIN
5486 0xFB07, // FB07..FB12; UNKNOWN
5487 0xFB13, // FB13..FB17; ARMENIAN
5488 0xFB18, // FB18..FB1C; UNKNOWN
5489 0xFB1D, // FB1D..FB36; HEBREW
5490 0xFB37, // FB37 ; UNKNOWN
5491 0xFB38, // FB38..FB3C; HEBREW
5492 0xFB3D, // FB3D ; UNKNOWN
5493 0xFB3E, // FB3E ; HEBREW
5494 0xFB3F, // FB3F ; UNKNOWN
5495 0xFB40, // FB40..FB41; HEBREW
5496 0xFB42, // FB42 ; UNKNOWN
5497 0xFB43, // FB43..FB44; HEBREW
5498 0xFB45, // FB45 ; UNKNOWN
5499 0xFB46, // FB46..FB4F; HEBREW
5500 0xFB50, // FB50..FBC1; ARABIC
5501 0xFBC2, // FBC2..FBD2; UNKNOWN
5502 0xFBD3, // FBD3..FD3D; ARABIC
5503 0xFD3E, // FD3E..FD3F; COMMON
5504 0xFD40, // FD40..FD4F; UNKNOWN
5505 0xFD50, // FD50..FD8F; ARABIC
5506 0xFD90, // FD90..FD91; UNKNOWN
5507 0xFD92, // FD92..FDC7; ARABIC
5508 0xFDC8, // FDC8..FDEF; UNKNOWN
5509 0xFDF0, // FDF0..FDFD; ARABIC
5510 0xFDFE, // FDFE..FDFF; UNKNOWN
5511 0xFE00, // FE00..FE0F; INHERITED
5512 0xFE10, // FE10..FE19; COMMON
5513 0xFE1A, // FE1A..FE1F; UNKNOWN
5514 0xFE20, // FE20..FE2D; INHERITED
5515 0xFE2E, // FE2E..FE2F; CYRILLIC
5516 0xFE30, // FE30..FE52; COMMON
5517 0xFE53, // FE53 ; UNKNOWN
5518 0xFE54, // FE54..FE66; COMMON
5519 0xFE67, // FE67 ; UNKNOWN
5520 0xFE68, // FE68..FE6B; COMMON
5521 0xFE6C, // FE6C..FE6F; UNKNOWN
5522 0xFE70, // FE70..FE74; ARABIC
5523 0xFE75, // FE75 ; UNKNOWN
5524 0xFE76, // FE76..FEFC; ARABIC
5525 0xFEFD, // FEFD..FEFE; UNKNOWN
5526 0xFEFF, // FEFF ; COMMON
5527 0xFF00, // FF00 ; UNKNOWN
5528 0xFF01, // FF01..FF20; COMMON
5529 0xFF21, // FF21..FF3A; LATIN
5530 0xFF3B, // FF3B..FF40; COMMON
5531 0xFF41, // FF41..FF5A; LATIN
5532 0xFF5B, // FF5B..FF65; COMMON
5533 0xFF66, // FF66..FF6F; KATAKANA
5534 0xFF70, // FF70 ; COMMON
5535 0xFF71, // FF71..FF9D; KATAKANA
5536 0xFF9E, // FF9E..FF9F; COMMON
5537 0xFFA0, // FFA0..FFBE; HANGUL
5538 0xFFBF, // FFBF..FFC1; UNKNOWN
5539 0xFFC2, // FFC2..FFC7; HANGUL
5540 0xFFC8, // FFC8..FFC9; UNKNOWN
5541 0xFFCA, // FFCA..FFCF; HANGUL
5542 0xFFD0, // FFD0..FFD1; UNKNOWN
5543 0xFFD2, // FFD2..FFD7; HANGUL
5544 0xFFD8, // FFD8..FFD9; UNKNOWN
5545 0xFFDA, // FFDA..FFDC; HANGUL
5546 0xFFDD, // FFDD..FFDF; UNKNOWN
5547 0xFFE0, // FFE0..FFE6; COMMON
5548 0xFFE7, // FFE7 ; UNKNOWN
5549 0xFFE8, // FFE8..FFEE; COMMON
5550 0xFFEF, // FFEF..FFF8; UNKNOWN
5551 0xFFF9, // FFF9..FFFD; COMMON
5552 0xFFFE, // FFFE..FFFF; UNKNOWN
5553 0x10000, // 10000..1000B; LINEAR_B
5554 0x1000C, // 1000C ; UNKNOWN
5555 0x1000D, // 1000D..10026; LINEAR_B
5556 0x10027, // 10027 ; UNKNOWN
5557 0x10028, // 10028..1003A; LINEAR_B
5558 0x1003B, // 1003B ; UNKNOWN
5559 0x1003C, // 1003C..1003D; LINEAR_B
5560 0x1003E, // 1003E ; UNKNOWN
5561 0x1003F, // 1003F..1004D; LINEAR_B
5562 0x1004E, // 1004E..1004F; UNKNOWN
5563 0x10050, // 10050..1005D; LINEAR_B
5564 0x1005E, // 1005E..1007F; UNKNOWN
5565 0x10080, // 10080..100FA; LINEAR_B
5566 0x100FB, // 100FB..100FF; UNKNOWN
5567 0x10100, // 10100..10102; COMMON
5568 0x10103, // 10103..10106; UNKNOWN
5569 0x10107, // 10107..10133; COMMON
5570 0x10134, // 10134..10136; UNKNOWN
5571 0x10137, // 10137..1013F; COMMON
5572 0x10140, // 10140..1018E; GREEK
5573 0x1018F, // 1018F ; UNKNOWN
5574 0x10190, // 10190..1019B; COMMON
5575 0x1019C, // 1019C..1019F; UNKNOWN
5576 0x101A0, // 101A0 ; GREEK
5577 0x101A1, // 101A1..101CF; UNKNOWN
5578 0x101D0, // 101D0..101FC; COMMON
5579 0x101FD, // 101FD ; INHERITED
5580 0x101FE, // 101FE..1027F; UNKNOWN
5581 0x10280, // 10280..1029C; LYCIAN
5582 0x1029D, // 1029D..1029F; UNKNOWN
5583 0x102A0, // 102A0..102D0; CARIAN
5584 0x102D1, // 102D1..102DF; UNKNOWN
5585 0x102E0, // 102E0 ; INHERITED
5586 0x102E1, // 102E1..102FB; COMMON
5587 0x102FC, // 102FC..102FF; UNKNOWN
5588 0x10300, // 10300..10323; OLD_ITALIC
5589 0x10324, // 10324..1032C; UNKNOWN
5590 0x1032D, // 1032D..1032F; OLD_ITALIC
5591 0x10330, // 10330..1034A; GOTHIC
5592 0x1034B, // 1034B..1034F; UNKNOWN
5593 0x10350, // 10350..1037A; OLD_PERMIC
5594 0x1037B, // 1037B..1037F; UNKNOWN
5595 0x10380, // 10380..1039D; UGARITIC
5596 0x1039E, // 1039E ; UNKNOWN
5597 0x1039F, // 1039F ; UGARITIC
5598 0x103A0, // 103A0..103C3; OLD_PERSIAN
5599 0x103C4, // 103C4..103C7; UNKNOWN
5600 0x103C8, // 103C8..103D5; OLD_PERSIAN
5601 0x103D6, // 103D6..103FF; UNKNOWN
5602 0x10400, // 10400..1044F; DESERET
5603 0x10450, // 10450..1047F; SHAVIAN
5604 0x10480, // 10480..1049D; OSMANYA
5605 0x1049E, // 1049E..1049F; UNKNOWN
5606 0x104A0, // 104A0..104A9; OSMANYA
5607 0x104AA, // 104AA..104AF; UNKNOWN
5608 0x104B0, // 104B0..104D3; OSAGE
5609 0x104D4, // 104D4..104D7; UNKNOWN
5610 0x104D8, // 104D8..104FB; OSAGE
5611 0x104FC, // 104FC..104FF; UNKNOWN
5612 0x10500, // 10500..10527; ELBASAN
5613 0x10528, // 10528..1052F; UNKNOWN
5614 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
5615 0x10564, // 10564..1056E; UNKNOWN
5616 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
5617 0x10570, // 10570..105FF; UNKNOWN
5618 0x10600, // 10600..10736; LINEAR_A
5619 0x10737, // 10737..1073F; UNKNOWN
5620 0x10740, // 10740..10755; LINEAR_A
5621 0x10756, // 10756..1075F; UNKNOWN
5622 0x10760, // 10760..10767; LINEAR_A
5623 0x10768, // 10768..107FF; UNKNOWN
5624 0x10800, // 10800..10805; CYPRIOT
5625 0x10806, // 10806..10807; UNKNOWN
5626 0x10808, // 10808 ; CYPRIOT
5627 0x10809, // 10809 ; UNKNOWN
5628 0x1080A, // 1080A..10835; CYPRIOT
5629 0x10836, // 10836 ; UNKNOWN
5630 0x10837, // 10837..10838; CYPRIOT
5631 0x10839, // 10839..1083B; UNKNOWN
5632 0x1083C, // 1083C ; CYPRIOT
5633 0x1083D, // 1083D..1083E; UNKNOWN
5634 0x1083F, // 1083F ; CYPRIOT
5635 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
5636 0x10856, // 10856 ; UNKNOWN
5637 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
5638 0x10860, // 10860..1087F; PALMYRENE
5639 0x10880, // 10880..1089E; NABATAEAN
5640 0x1089F, // 1089F..108A6; UNKNOWN
5641 0x108A7, // 108A7..108AF; NABATAEAN
5642 0x108B0, // 108B0..108DF; UNKNOWN
5643 0x108E0, // 108E0..108F2; HATRAN
5644 0x108F3, // 108F3 ; UNKNOWN
5645 0x108F4, // 108F4..108F5; HATRAN
5646 0x108F6, // 108F6..108FA; UNKNOWN
5647 0x108FB, // 108FB..108FF; HATRAN
5648 0x10900, // 10900..1091B; PHOENICIAN
5649 0x1091C, // 1091C..1091E; UNKNOWN
5650 0x1091F, // 1091F ; PHOENICIAN
5651 0x10920, // 10920..10939; LYDIAN
5652 0x1093A, // 1093A..1093E; UNKNOWN
5653 0x1093F, // 1093F ; LYDIAN
5654 0x10940, // 10940..1097F; UNKNOWN
5655 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
5656 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
5657 0x109B8, // 109B8..109BB; UNKNOWN
5658 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
5659 0x109D0, // 109D0..109D1; UNKNOWN
5660 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
5661 0x10A00, // 10A00..10A03; KHAROSHTHI
5662 0x10A04, // 10A04 ; UNKNOWN
5663 0x10A05, // 10A05..10A06; KHAROSHTHI
5664 0x10A07, // 10A07..10A0B; UNKNOWN
5665 0x10A0C, // 10A0C..10A13; KHAROSHTHI
5666 0x10A14, // 10A14 ; UNKNOWN
5667 0x10A15, // 10A15..10A17; KHAROSHTHI
5668 0x10A18, // 10A18 ; UNKNOWN
5669 0x10A19, // 10A19..10A33; KHAROSHTHI
5670 0x10A34, // 10A34..10A37; UNKNOWN
5671 0x10A38, // 10A38..10A3A; KHAROSHTHI
5672 0x10A3B, // 10A3B..10A3E; UNKNOWN
5673 0x10A3F, // 10A3F..10A47; KHAROSHTHI
5674 0x10A48, // 10A48..10A4F; UNKNOWN
5675 0x10A50, // 10A50..10A58; KHAROSHTHI
5676 0x10A59, // 10A59..10A5F; UNKNOWN
5677 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
5678 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
5679 0x10AA0, // 10AA0..10ABF; UNKNOWN
5680 0x10AC0, // 10AC0..10AE6; MANICHAEAN
5681 0x10AE7, // 10AE7..10AEA; UNKNOWN
5682 0x10AEB, // 10AEB..10AF6; MANICHAEAN
5683 0x10AF7, // 10AF7..10AFF; UNKNOWN
5684 0x10B00, // 10B00..10B35; AVESTAN
5685 0x10B36, // 10B36..10B38; UNKNOWN
5686 0x10B39, // 10B39..10B3F; AVESTAN
5687 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
5688 0x10B56, // 10B56..10B57; UNKNOWN
5689 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
5690 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
5691 0x10B73, // 10B73..10B77; UNKNOWN
5692 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
5693 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
5694 0x10B92, // 10B92..10B98; UNKNOWN
5695 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
5696 0x10B9D, // 10B9D..10BA8; UNKNOWN
5697 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
5698 0x10BB0, // 10BB0..10BFF; UNKNOWN
5699 0x10C00, // 10C00..10C48; OLD_TURKIC
5700 0x10C49, // 10C49..10C7F; UNKNOWN
5701 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
5702 0x10CB3, // 10CB3..10CBF; UNKNOWN
5703 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
5704 0x10CF3, // 10CF3..10CF9; UNKNOWN
5705 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
5706 0x10D00, // 10D00..10E5F; UNKNOWN
5707 0x10E60, // 10E60..10E7E; ARABIC
5708 0x10E7F, // 10E7F..10FFF; UNKNOWN
5709 0x11000, // 11000..1104D; BRAHMI
5710 0x1104E, // 1104E..11051; UNKNOWN
5711 0x11052, // 11052..1106F; BRAHMI
5712 0x11070, // 11070..1107E; UNKNOWN
5713 0x1107F, // 1107F ; BRAHMI
5714 0x11080, // 11080..110C1; KAITHI
5715 0x110C2, // 110C2..110CF; UNKNOWN
5716 0x110D0, // 110D0..110E8; SORA_SOMPENG
5717 0x110E9, // 110E9..110EF; UNKNOWN
5718 0x110F0, // 110F0..110F9; SORA_SOMPENG
5719 0x110FA, // 110FA..110FF; UNKNOWN
5720 0x11100, // 11100..11134; CHAKMA
5721 0x11135, // 11135 ; UNKNOWN
5722 0x11136, // 11136..11143; CHAKMA
5723 0x11144, // 11144..1114F; UNKNOWN
5724 0x11150, // 11150..11176; MAHAJANI
5725 0x11177, // 11177..1117F; UNKNOWN
5726 0x11180, // 11180..111CD; SHARADA
5727 0x111CE, // 111CE..111CF; UNKNOWN
5728 0x111D0, // 111D0..111DF; SHARADA
5729 0x111E0, // 111E0 ; UNKNOWN
5730 0x111E1, // 111E1..111F4; SINHALA
5731 0x111F5, // 111F5..111FF; UNKNOWN
5732 0x11200, // 11200..11211; KHOJKI
5733 0x11212, // 11212 ; UNKNOWN
5734 0x11213, // 11213..1123E; KHOJKI
5735 0x1123F, // 1123F..1127F; UNKNOWN
5736 0x11280, // 11280..11286; MULTANI
5737 0x11287, // 11287 ; UNKNOWN
5738 0x11288, // 11288 ; MULTANI
5739 0x11289, // 11289 ; UNKNOWN
5740 0x1128A, // 1128A..1128D; MULTANI
5741 0x1128E, // 1128E ; UNKNOWN
5742 0x1128F, // 1128F..1129D; MULTANI
5743 0x1129E, // 1129E ; UNKNOWN
5744 0x1129F, // 1129F..112A9; MULTANI
5745 0x112AA, // 112AA..112AF; UNKNOWN
5746 0x112B0, // 112B0..112EA; KHUDAWADI
5747 0x112EB, // 112EB..112EF; UNKNOWN
5748 0x112F0, // 112F0..112F9; KHUDAWADI
5749 0x112FA, // 112FA..112FF; UNKNOWN
5750 0x11300, // 11300..11303; GRANTHA
5751 0x11304, // 11304 ; UNKNOWN
5752 0x11305, // 11305..1130C; GRANTHA
5753 0x1130D, // 1130D..1130E; UNKNOWN
5754 0x1130F, // 1130F..11310; GRANTHA
5755 0x11311, // 11311..11312; UNKNOWN
5756 0x11313, // 11313..11328; GRANTHA
5757 0x11329, // 11329 ; UNKNOWN
5758 0x1132A, // 1132A..11330; GRANTHA
5759 0x11331, // 11331 ; UNKNOWN
5760 0x11332, // 11332..11333; GRANTHA
5761 0x11334, // 11334 ; UNKNOWN
5762 0x11335, // 11335..11339; GRANTHA
5763 0x1133A, // 1133A..1133B; UNKNOWN
5764 0x1133C, // 1133C..11344; GRANTHA
5765 0x11345, // 11345..11346; UNKNOWN
5766 0x11347, // 11347..11348; GRANTHA
5767 0x11349, // 11349..1134A; UNKNOWN
5768 0x1134B, // 1134B..1134D; GRANTHA
5769 0x1134E, // 1134E..1134F; UNKNOWN
5770 0x11350, // 11350 ; GRANTHA
5771 0x11351, // 11351..11356; UNKNOWN
5772 0x11357, // 11357 ; GRANTHA
5773 0x11358, // 11358..1135C; UNKNOWN
5774 0x1135D, // 1135D..11363; GRANTHA
5775 0x11364, // 11364..11365; UNKNOWN
5776 0x11366, // 11366..1136C; GRANTHA
5777 0x1136D, // 1136D..1136F; UNKNOWN
5778 0x11370, // 11370..11374; GRANTHA
5779 0x11375, // 11375..113FF; UNKNOWN
5780 0x11400, // 11400..11459; NEWA
5781 0x1145A, // 1145A ; UNKNOWN
5782 0x1145B, // 1145B ; NEWA
5783 0x1145C, // 1145C ; UNKNOWN
5784 0x1145D, // 1145D ; NEWA
5785 0x1145E, // 1145E..1147F; UNKNOWN
5786 0x11480, // 11480..114C7; TIRHUTA
5787 0x114C8, // 114C8..114CF; UNKNOWN
5788 0x114D0, // 114D0..114D9; TIRHUTA
5789 0x114DA, // 114DA..1157F; UNKNOWN
5790 0x11580, // 11580..115B5; SIDDHAM
5791 0x115B6, // 115B6..115B7; UNKNOWN
5792 0x115B8, // 115B8..115DD; SIDDHAM
5793 0x115DE, // 115DE..115FF; UNKNOWN
5794 0x11600, // 11600..11644; MODI
5795 0x11645, // 11645..1164F; UNKNOWN
5796 0x11650, // 11650..11659; MODI
5797 0x1165A, // 1165A..1165F; UNKNOWN
5798 0x11660, // 11660..1166C; MONGOLIAN
5799 0X1166D, // 1166D..1167F; UNKNOWN
5800 0x11680, // 11680..116B7; TAKRI
5801 0x116B8, // 116B8..116BF; UNKNOWN
5802 0x116C0, // 116C0..116C9; TAKRI
5803 0x116CA, // 116CA..116FF; UNKNOWN
5804 0x11700, // 11700..11719; AHOM
5805 0x1171A, // 1171A..1171C; UNKNOWN
5806 0x1171D, // 1171D..1172B; AHOM
5807 0x1172C, // 1172C..1172F; UNKNOWN
5808 0x11730, // 11730..1173F; AHOM
5809 0x11740, // 11740..1189F; UNKNOWN
5810 0x118A0, // 118A0..118F2; WARANG_CITI
5811 0x118F3, // 118F3..118FE; UNKNOWN
5812 0x118FF, // 118FF ; WARANG_CITI
5813 0x11900, // 11900..119FF; UNKNOWN
5814 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
5815 0X11A48, // 11A48..11A4F; UNKNOWN
5816 0x11A50, // 11A50..11A83; SOYOMBO
5817 0x11A84, // 11A84..11A85; UNKNOWN
5818 0x11A86, // 11A86..11A9C; SOYOMBO
5819 0x11A9D, // 11A9D ; UNKNOWN
5820 0x11A9E, // 11A9E..11AA2; SOYOMBO
5821 0x11AA3, // 11AA3..11ABF; UNKNOWN
5822 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
5823 0x11AF9, // 11AF9..11BFF; UNKNOWN
5824 0x11C00, // 11C00..11C08; BHAIKSUKI
5825 0x11C09, // 11C09 ; UNKNOWN
5826 0x11C0A, // 11C0A..11C36; BHAIKSUKI
5827 0x11C37, // 11C37 ; UNKNOWN
5828 0x11C38, // 11C38..11C45; BHAIKSUKI
5829 0x11C46, // 11C46..11C49; UNKNOWN
5830 0x11C50, // 11C50..11C6C; BHAIKSUKI
5831 0x11C6D, // 11C6D..11C6F; UNKNOWN
5832 0x11C70, // 11C70..11C8F; MARCHEN
5833 0x11C90, // 11C90..11C91; UNKNOWN
5834 0x11C92, // 11C92..11CA7; MARCHEN
5835 0x11CA8, // 11CA8 ; UNKNOWN
5836 0x11CA9, // 11CA9..11CB6; MARCHEN
5837 0x11CB7, // 11CB7..11CFF; UNKNOWN
5838 0x11D00, // 11D00..11D06; MASARAM_GONDI
5839 0x11D07, // 11D07 ; UNKNOWN
5840 0x11D08, // 11D08..11D09; MASARAM_GONDI
5841 0x11D0A, // 11D0A ; UNKNOWN
5842 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
5843 0x11D37, // 11D37..11D39; UNKNOWN
5844 0x11D3A, // 11D3A ; MASARAM_GONDI
5845 0x11D3B, // 11D3B ; UNKNOWN
5846 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
5847 0x11D3E, // 11D3E ; UNKNOWN
5848 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
5849 0x11D48, // 11D48..11D49, UNKNOWN
5850 0x11D50, // 11D50..11D59; MASARAM_GONDI
5851 0x11D5A, // 11D5A..1AFFF; UNKNOWN
5852 0x12000, // 12000..12399; CUNEIFORM
5853 0x1239A, // 1239A..123FF; UNKNOWN
5854 0x12400, // 12400..1246E; CUNEIFORM
5855 0x1246F, // 1246F ; UNKNOWN
5856 0x12470, // 12470..12474; CUNEIFORM
5857 0x12475, // 12475..1247F; UNKNOWN
5858 0x12480, // 12480..12543; CUNEIFORM
5859 0x12544, // 12544..12FFF; UNKNOWN
5860 0x13000, // 13000..1342E; EGYPTIAN_HIEROGLYPHS
5861 0x1342F, // 1342F..143FF; UNKNOWN
5862 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
5863 0x14647, // 14647..167FF; UNKNOWN
5864 0x16800, // 16800..16A38; BAMUM
5865 0x16A39, // 16A39..16A3F; UNKNOWN
5866 0x16A40, // 16A40..16A5E; MRO
5867 0x16A5F, // 16A5F ; UNKNOWN
5868 0x16A60, // 16A60..16A69; MRO
5869 0x16A6A, // 16A6A..16A6D; UNKNOWN
5870 0x16A6E, // 16A6E..16A6F; MRO
5871 0x16A70, // 16A70..16ACF; UNKNOWN
5872 0x16AD0, // 16AD0..16AED; BASSA_VAH
5873 0x16AEE, // 16AEE..16AEF; UNKNOWN
5874 0x16AF0, // 16AF0..16AF5; BASSA_VAH
5875 0x16AF6, // 16AF6..16AFF; UNKNOWN
5876 0x16B00, // 16B00..16B45; PAHAWH_HMONG
5877 0x16B46, // 16B46..16B4F; UNKNOWN
5878 0x16B50, // 16B50..16B59; PAHAWH_HMONG
5879 0x16B5A, // 16B5A ; UNKNOWN
5880 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
5881 0x16B62, // 16B62 ; UNKNOWN
5882 0x16B63, // 16B63..16B77; PAHAWH_HMONG
5883 0x16B78, // 16B78..16B7C; UNKNOWN
5884 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
5885 0x16B90, // 16B90..16EFF; UNKNOWN
5886 0x16F00, // 16F00..16F44; MIAO
5887 0x16F45, // 16F45..16F4F; UNKNOWN
5888 0x16F50, // 16F50..16F7E; MIAO
5889 0x16F7F, // 16F7F..16F8E; UNKNOWN
5890 0x16F8F, // 16F8F..16F9F; MIAO
5891 0x16FA0, // 16FA0..16FDF; UNKNOWN
5892 0x16FE0, // 16FE0 ; TANGUT
5893 0x16FE1, // 16FE1 ; NUSHU
5894 0x16FE2, // 16FE2..16FFF; UNKNOWN
5895 0x17000, // 17000..187EC; TANGUT
5896 0x187ED, // 187ED..187FF; UNKNOWN
5897 0x18800, // 18800..18AF2; TANGUT
5898 0x18AF3, // 18AF3..1AFFF; UNKNOWN
5899 0x1B000, // 1B000 ; KATAKANA
5900 0x1B001, // 1B001..1B11E; HIRAGANA
5901 0x1B11F, // 1B11F..1B16F; UNKNOWN
5902 0x1B170, // 1B170..1B2FB; NUSHU
5903 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
5904 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
5905 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
5906 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
5907 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
5908 0x1BC80, // 1BC80..1BC88; DUPLOYAN
5909 0x1BC89, // 1BC89..1BC8F; UNKNOWN
5910 0x1BC90, // 1BC90..1BC99; DUPLOYAN
5911 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
5912 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
5913 0x1BCA0, // 1BCA0..1BCA3; COMMON
5914 0x1BCA4, // 1BCA4..1CFFF; UNKNOWN
5915 0x1D000, // 1D000..1D0F5; COMMON
5916 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
5917 0x1D100, // 1D100..1D126; COMMON
5918 0x1D127, // 1D127..1D128; UNKNOWN
5919 0x1D129, // 1D129..1D166; COMMON
5920 0x1D167, // 1D167..1D169; INHERITED
5921 0x1D16A, // 1D16A..1D17A; COMMON
5922 0x1D17B, // 1D17B..1D182; INHERITED
5923 0x1D183, // 1D183..1D184; COMMON
5924 0x1D185, // 1D185..1D18B; INHERITED
5925 0x1D18C, // 1D18C..1D1A9; COMMON
5926 0x1D1AA, // 1D1AA..1D1AD; INHERITED
5927 0x1D1AE, // 1D1AE..1D1E8; COMMON
5928 0x1D1E9, // 1D1E9..1D1FF; UNKNOWN
5929 0x1D200, // 1D200..1D245; GREEK
5930 0x1D246, // 1D246..1D2FF; UNKNOWN
5931 0x1D300, // 1D300..1D356; COMMON
5932 0x1D357, // 1D357..1D35F; UNKNOWN
5933 0x1D360, // 1D360..1D371; COMMON
5934 0x1D372, // 1D372..1D3FF; UNKNOWN
5935 0x1D400, // 1D400..1D454; COMMON
5936 0x1D455, // 1D455 ; UNKNOWN
5937 0x1D456, // 1D456..1D49C; COMMON
5938 0x1D49D, // 1D49D ; UNKNOWN
5939 0x1D49E, // 1D49E..1D49F; COMMON
5940 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
5941 0x1D4A2, // 1D4A2 ; COMMON
5942 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
5943 0x1D4A5, // 1D4A5..1D4A6; COMMON
5944 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
5945 0x1D4A9, // 1D4A9..1D4AC; COMMON
5946 0x1D4AD, // 1D4AD ; UNKNOWN
5947 0x1D4AE, // 1D4AE..1D4B9; COMMON
5948 0x1D4BA, // 1D4BA ; UNKNOWN
5949 0x1D4BB, // 1D4BB ; COMMON
5950 0x1D4BC, // 1D4BC ; UNKNOWN
5951 0x1D4BD, // 1D4BD..1D4C3; COMMON
5952 0x1D4C4, // 1D4C4 ; UNKNOWN
5953 0x1D4C5, // 1D4C5..1D505; COMMON
5954 0x1D506, // 1D506 ; UNKNOWN
5955 0x1D507, // 1D507..1D50A; COMMON
5956 0x1D50B, // 1D50B..1D50C; UNKNOWN
5957 0x1D50D, // 1D50D..1D514; COMMON
5958 0x1D515, // 1D515 ; UNKNOWN
5959 0x1D516, // 1D516..1D51C; COMMON
5960 0x1D51D, // 1D51D ; UNKNOWN
5961 0x1D51E, // 1D51E..1D539; COMMON
5962 0x1D53A, // 1D53A ; UNKNOWN
5963 0x1D53B, // 1D53B..1D53E; COMMON
5964 0x1D53F, // 1D53F ; UNKNOWN
5965 0x1D540, // 1D540..1D544; COMMON
5966 0x1D545, // 1D545 ; UNKNOWN
5967 0x1D546, // 1D546 ; COMMON
5968 0x1D547, // 1D547..1D549; UNKNOWN
5969 0x1D54A, // 1D54A..1D550; COMMON
5970 0x1D551, // 1D551 ; UNKNOWN
5971 0x1D552, // 1D552..1D6A5; COMMON
5972 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
5973 0x1D6A8, // 1D6A8..1D7CB; COMMON
5974 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
5975 0x1D7CE, // 1D7CE..1D7FF; COMMON
5976 0x1D800, // 1D800..1DA8B; SIGNWRITING
5977 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
5978 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
5979 0x1DAA0, // 1DAA0 ; UNKNOWN
5980 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
5981 0x1DAB0, // 1DAB0..1DFFF; UNKNOWN
5982 0x1E000, // 1E000..1E006; GLAGOLITIC
5983 0x1E007, // 1E007 ; UNKNOWN
5984 0x1E008, // 1E008..1E018; GLAGOLITIC
5985 0x1E019, // 1E019..1E01A; UNKNOWN
5986 0x1E01B, // 1E01B..1E021; GLAGOLITIC
5987 0x1E022, // 1E022 ; UNKNOWN
5988 0x1E023, // 1E023..1E024; GLAGOLITIC
5989 0x1E025, // 1E025 ; UNKNOWN
5990 0x1E026, // 1E026..1E02A; GLAGOLITIC
5991 0x1E02B, // 1E02B..1E7FF; UNKNOWN
5992 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
5993 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
5994 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
5995 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
5996 0x1E900, // 1E900..1E94A; ADLAM
5997 0x1E94B, // 1E94B..1E94F; UNKNOWN
5998 0x1E950, // 1E950..1E959; ADLAM
5999 0x1E95A, // 1E95A..1E95D; UNKNOWN
6000 0x1E95E, // 1E95E..1E95F; ADLAM
6001 0x1E960, // 1E960..1EDFF; UNKNOWN
6002 0x1EE00, // 1EE00..1EE03; ARABIC
6003 0x1EE04, // 1EE04 ; UNKNOWN
6004 0x1EE05, // 1EE05..1EE1F; ARABIC
6005 0x1EE20, // 1EE20 ; UNKNOWN
6006 0x1EE21, // 1EE21..1EE22; ARABIC
6007 0x1EE23, // 1EE23 ; UNKNOWN
6008 0x1EE24, // 1EE24 ; ARABIC
6009 0x1EE25, // 1EE25..1EE26; UNKNOWN
6010 0x1EE27, // 1EE27 ; ARABIC
6011 0x1EE28, // 1EE28 ; UNKNOWN
6012 0x1EE29, // 1EE29..1EE32; ARABIC
6013 0x1EE33, // 1EE33 ; UNKNOWN
6014 0x1EE34, // 1EE34..1EE37; ARABIC
6015 0x1EE38, // 1EE38 ; UNKNOWN
6016 0x1EE39, // 1EE39 ; ARABIC
6017 0x1EE3A, // 1EE3A ; UNKNOWN
6018 0x1EE3B, // 1EE3B ; ARABIC
6019 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
6020 0x1EE42, // 1EE42 ; ARABIC
6021 0x1EE43, // 1EE43..1EE46; UNKNOWN
6022 0x1EE47, // 1EE47 ; ARABIC
6023 0x1EE48, // 1EE48 ; UNKNOWN
6024 0x1EE49, // 1EE49 ; ARABIC
6025 0x1EE4A, // 1EE4A ; UNKNOWN
6026 0x1EE4B, // 1EE4B ; ARABIC
6027 0x1EE4C, // 1EE4C ; UNKNOWN
6028 0x1EE4D, // 1EE4D..1EE4F; ARABIC
6029 0x1EE50, // 1EE50 ; UNKNOWN
6030 0x1EE51, // 1EE51..1EE52; ARABIC
6031 0x1EE53, // 1EE53 ; UNKNOWN
6032 0x1EE54, // 1EE54 ; ARABIC
6033 0x1EE55, // 1EE55..1EE56; UNKNOWN
6034 0x1EE57, // 1EE57 ; ARABIC
6035 0x1EE58, // 1EE58 ; UNKNOWN
6036 0x1EE59, // 1EE59 ; ARABIC
6037 0x1EE5A, // 1EE5A ; UNKNOWN
6038 0x1EE5B, // 1EE5B ; ARABIC
6039 0x1EE5C, // 1EE5C ; UNKNOWN
6040 0x1EE5D, // 1EE5D ; ARABIC
6041 0x1EE5E, // 1EE5E ; UNKNOWN
6042 0x1EE5F, // 1EE5F ; ARABIC
6043 0x1EE60, // 1EE60 ; UNKNOWN
6044 0x1EE61, // 1EE61..1EE62; ARABIC
6045 0x1EE63, // 1EE63 ; UNKNOWN
6046 0x1EE64, // 1EE64 ; ARABIC
6047 0x1EE65, // 1EE65..1EE66; UNKNOWN
6048 0x1EE67, // 1EE67..1EE6A; ARABIC
6049 0x1EE6B, // 1EE6B ; UNKNOWN
6050 0x1EE6C, // 1EE6C..1EE72; ARABIC
6051 0x1EE73, // 1EE73 ; UNKNOWN
6052 0x1EE74, // 1EE74..1EE77; ARABIC
6053 0x1EE78, // 1EE78 ; UNKNOWN
6054 0x1EE79, // 1EE79..1EE7C; ARABIC
6055 0x1EE7D, // 1EE7D ; UNKNOWN
6056 0x1EE7E, // 1EE7E ; ARABIC
6057 0x1EE7F, // 1EE7F ; UNKNOWN
6058 0x1EE80, // 1EE80..1EE89; ARABIC
6059 0x1EE8A, // 1EE8A ; UNKNOWN
6060 0x1EE8B, // 1EE8B..1EE9B; ARABIC
6061 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
6062 0x1EEA1, // 1EEA1..1EEA3; ARABIC
6063 0x1EEA4, // 1EEA4 ; UNKNOWN
6064 0x1EEA5, // 1EEA5..1EEA9; ARABIC
6065 0x1EEAA, // 1EEAA ; UNKNOWN
6066 0x1EEAB, // 1EEAB..1EEBB; ARABIC
6067 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
6068 0x1EEF0, // 1EEF0..1EEF1; ARABIC
6069 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
6070 0x1F000, // 1F000..1F02B; COMMON
6071 0x1F02C, // 1F02C..1F02F; UNKNOWN
6072 0x1F030, // 1F030..1F093; COMMON
6073 0x1F094, // 1F094..1F09F; UNKNOWN
6074 0x1F0A0, // 1F0A0..1F0AE; COMMON
6075 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
6076 0x1F0B1, // 1F0B1..1F0BF; COMMON
6077 0x1F0C0, // 1F0C0 ; UNKNOWN
6078 0x1F0C1, // 1F0C1..1F0CF; COMMON
6079 0x1F0D0, // 1F0D0 ; UNKNOWN
6080 0x1F0D1, // 1F0D1..1F0F5; COMMON
6081 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
6082 0x1F100, // 1F100..1F10C; COMMON
6083 0x1F10D, // 1F10D..1F10F; UNKNOWN
6084 0x1F110, // 1F110..1F12E; COMMON
6085 0x1F12F, // 1F12F ; UNKNOWN
6086 0x1F130, // 1F130..1F16B; COMMON
6087 0x1F16C, // 1F16C..1F16F; UNKNOWN
6088 0x1F170, // 1F170..1F1AC; COMMON
6089 0x1F1AD, // 1F1AD..1F1E5; UNKNOWN
6090 0x1F1E6, // 1F1E6..1F1FF; COMMON
6091 0x1F200, // 1F200 ; HIRAGANA
6092 0x1F201, // 1F201..1F202; COMMON
6093 0x1F203, // 1F203..1F20F; UNKNOWN
6094 0x1F210, // 1F210..1F23B; COMMON
6095 0x1F23C, // 1F23C..1F23F; UNKNOWN
6096 0x1F240, // 1F240..1F248; COMMON
6097 0x1F249, // 1F249..1F24F; UNKNOWN
6098 0x1F250, // 1F250..1F251; COMMON
6099 0x1F252, // 1F252..1F25F; UNKNOWN
6100 0x1F260, // 1F260..1F265; COMMON
6101 0x1F266, // 1F266..1F2FF; UNKNOWN
6102 0x1F300, // 1F300..1F6D4; COMMON
6103 0x1F6D5, // 1F6D5..1F6DF; UNKNOWN
6104 0x1F6E0, // 1F6E0..1F6EC; COMMON
6105 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
6106 0x1F6F0, // 1F6F0..1F6F8; COMMON
6107 0x1F6F9, // 1F6F9..1F6FF; UNKNOWN
6108 0x1F700, // 1F700..1F773; COMMON
6109 0x1F774, // 1F774..1F77F; UNKNOWN
6110 0x1F780, // 1F780..1F7D4; COMMON
6111 0x1F7D5, // 1F7D5..1F7FF; UNKNOWN
6112 0x1F800, // 1F800..1F80B; COMMON
6113 0x1F80C, // 1F80C..1F80F; UNKNOWN
6114 0x1F810, // 1F810..1F847; COMMON
6115 0x1F848, // 1F848..1F84F; UNKNOWN
6116 0x1F850, // 1F850..1F859; COMMON
6117 0x1F85A, // 1F85A..1F85F; UNKNOWN
6118 0x1F860, // 1F860..1F887; COMMON
6119 0x1F888, // 1F888..1F88F; UNKNOWN
6120 0x1F890, // 1F890..1F8AD; COMMON
6121 0x1F8AE, // 1F8AE..1F8FF; UNKNOWN
6122 0x1F900, // 1F900..1F90B; COMMON
6123 0x1F90C, // 1F90C..1F90F; UNKNOWN
6124 0x1F910, // 1F910..1F93E; COMMON
6125 0x1F93F, // 1F93F ; UNKNOWN
6126 0x1F940, // 1F940..1F94C; COMMON
6127 0x1F94D, // 1F94D..1F94F; UNKNOWN
6128 0x1F950, // 1F950..1F96B; COMMON
6129 0x1F96C, // 1F96C..1F97F; UNKNOWN
6130 0x1F980, // 1F980..1F997; COMMON
6131 0x1F998, // 1F998..1F9BF; UNKNOWN
6132 0x1F9C0, // 1F9C0 ; COMMON
6133 0x1F9C1, // 1F9C1..1F9CF; UNKNOWN
6134 0x1F9D0, // 1F9D0..1F9E6; COMMON
6135 0x1F9E7, // 1F9E7..1FFFF; UNKNOWN
6136 0x20000, // 20000..2A6D6; HAN
6137 0x2A6D7, // 2A6D7..2A6FF; UNKNOWN
6138 0x2A700, // 2A700..2B734; HAN
6139 0x2B735, // 2B735..2B73F; UNKNOWN
6140 0x2B740, // 2B740..2B81D; HAN
6141 0x2B81E, // 2B81E..2B81F; UNKNOWN
6142 0x2B820, // 2B820..2CEA1; HAN
6143 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
6144 0x2CEB0, // 2CEB0..2EBE0; HAN
6145 0x2EBE1, // 2EBE1..2F7FF; UNKNOWN
6146 0x2F800, // 2F800..2FA1D; HAN
6147 0x2FA1E, // 2FA1E..E0000; UNKNOWN
6148 0xE0001, // E0001 ; COMMON
6149 0xE0002, // E0002..E001F; UNKNOWN
6150 0xE0020, // E0020..E007F; COMMON
6151 0xE0080, // E0080..E00FF; UNKNOWN
6152 0xE0100, // E0100..E01EF; INHERITED
6153 0xE01F0 // E01F0..10FFFF; UNKNOWN
6154 };
6155
6156 private static final UnicodeScript[] scripts = {
6157 COMMON, // 0000..0040
6158 LATIN, // 0041..005A
6159 COMMON, // 005B..0060
6160 LATIN, // 0061..007A
6161 COMMON, // 007B..00A9
6162 LATIN, // 00AA
6163 COMMON, // 00AB..00B9
6164 LATIN, // 00BA
6165 COMMON, // 00BB..00BF
6166 LATIN, // 00C0..00D6
6167 COMMON, // 00D7
6168 LATIN, // 00D8..00F6
6169 COMMON, // 00F7
6170 LATIN, // 00F8..02B8
6171 COMMON, // 02B9..02DF
6172 LATIN, // 02E0..02E4
6173 COMMON, // 02E5..02E9
6174 BOPOMOFO, // 02EA..02EB
6175 COMMON, // 02EC..02FF
6176 INHERITED, // 0300..036F
6177 GREEK, // 0370..0373
6178 COMMON, // 0374
6179 GREEK, // 0375..0377
6180 UNKNOWN, // 0378..0379
6181 GREEK, // 037A..037D
6182 COMMON, // 037E
6183 GREEK, // 037F
6184 UNKNOWN, // 0380..0383
6185 GREEK, // 0384
6186 COMMON, // 0385
6187 GREEK, // 0386
6188 COMMON, // 0387
6189 GREEK, // 0388..038A
6190 UNKNOWN, // 038B
6191 GREEK, // 038C
6192 UNKNOWN, // 038D
6193 GREEK, // 038E..03A1
6194 UNKNOWN, // 03A2
6195 GREEK, // 03A3..03E1
6196 COPTIC, // 03E2..03EF
6197 GREEK, // 03F0..03FF
6198 CYRILLIC, // 0400..0484
6199 INHERITED, // 0485..0486
6200 CYRILLIC, // 0487..052F
6201 UNKNOWN, // 0530
6202 ARMENIAN, // 0531..0556
6203 UNKNOWN, // 0557..0558
6204 ARMENIAN, // 0559..055F
6205 UNKNOWN, // 0560
6206 ARMENIAN, // 0561..0587
6207 UNKNOWN, // 0588
6208 COMMON, // 0589
6209 ARMENIAN, // 058A
6210 UNKNOWN, // 058B..058C
6211 ARMENIAN, // 058D..058F
6212 UNKNOWN, // 0590
6213 HEBREW, // 0591..05C7
6214 UNKNOWN, // 05C8..05CF
6215 HEBREW, // 05D0..05EA
6216 UNKNOWN, // 05EB..05EF
6217 HEBREW, // 05F0..05F4
6218 UNKNOWN, // 05F5..05FF
6219 ARABIC, // 0600..0604
6220 COMMON, // 0605
6221 ARABIC, // 0606..060B
6222 COMMON, // 060C
6223 ARABIC, // 060D..061A
6224 COMMON, // 061B
6225 ARABIC, // 061C
6226 UNKNOWN, // 061D
6227 ARABIC, // 061E
6228 COMMON, // 061F
6229 ARABIC, // 0620..063F
6230 COMMON, // 0640
6231 ARABIC, // 0641..064A
6232 INHERITED, // 064B..0655
6233 ARABIC, // 0656..066F
6234 INHERITED, // 0670
6235 ARABIC, // 0671..06DC
6236 COMMON, // 06DD
6237 ARABIC, // 06DE..06FF
6238 SYRIAC, // 0700..070D
6239 UNKNOWN, // 070E
6240 SYRIAC, // 070F..074A
6241 UNKNOWN, // 074B..074C
6242 SYRIAC, // 074D..074F
6243 ARABIC, // 0750..077F
6244 THAANA, // 0780..07B1
6245 UNKNOWN, // 07B2..07BF
6246 NKO, // 07C0..07FA
6247 UNKNOWN, // 07FB..07FF
6248 SAMARITAN, // 0800..082D
6249 UNKNOWN, // 082E..082F
6250 SAMARITAN, // 0830..083E
6251 UNKNOWN, // 083F
6252 MANDAIC, // 0840..085B
6253 UNKNOWN, // 085C..085D
6254 MANDAIC, // 085E
6255 UNKNOWN, // 085F
6256 SYRIAC, // 0860..086A
6257 UNKNOWN, // 086B..089F
6258 ARABIC, // 08A0..08B4
6259 UNKNOWN, // 08B5
6260 ARABIC, // 08B6..08BD
6261 UNKNOWN, // 08BE..08D3
6262 ARABIC, // 08D4..08E1
6263 COMMON, // 08E2
6264 ARABIC, // 08E3..08FF
6265 DEVANAGARI, // 0900..0950
6266 INHERITED, // 0951..0952
6267 DEVANAGARI, // 0953..0963
6268 COMMON, // 0964..0965
6269 DEVANAGARI, // 0966..097F
6270 BENGALI, // 0980..0983
6271 UNKNOWN, // 0984
6272 BENGALI, // 0985..098C
6273 UNKNOWN, // 098D..098E
6274 BENGALI, // 098F..0990
6275 UNKNOWN, // 0991..0992
6276 BENGALI, // 0993..09A8
6277 UNKNOWN, // 09A9
6278 BENGALI, // 09AA..09B0
6279 UNKNOWN, // 09B1
6280 BENGALI, // 09B2
6281 UNKNOWN, // 09B3..09B5
6282 BENGALI, // 09B6..09B9
6283 UNKNOWN, // 09BA..09BB
6284 BENGALI, // 09BC..09C4
6285 UNKNOWN, // 09C5..09C6
6286 BENGALI, // 09C7..09C8
6287 UNKNOWN, // 09C9..09CA
6288 BENGALI, // 09CB..09CE
6289 UNKNOWN, // 09CF..09D6
6290 BENGALI, // 09D7
6291 UNKNOWN, // 09D8..09DB
6292 BENGALI, // 09DC..09DD
6293 UNKNOWN, // 09DE
6294 BENGALI, // 09DF..09E3
6295 UNKNOWN, // 09E4..09E5
6296 BENGALI, // 09E6..09FD
6297 UNKNOWN, // 09FE..0A00
6298 GURMUKHI, // 0A01..0A03
6299 UNKNOWN, // 0A04
6300 GURMUKHI, // 0A05..0A0A
6301 UNKNOWN, // 0A0B..0A0E
6302 GURMUKHI, // 0A0F..0A10
6303 UNKNOWN, // 0A11..0A12
6304 GURMUKHI, // 0A13..0A28
6305 UNKNOWN, // 0A29
6306 GURMUKHI, // 0A2A..0A30
6307 UNKNOWN, // 0A31
6308 GURMUKHI, // 0A32..0A33
6309 UNKNOWN, // 0A34
6310 GURMUKHI, // 0A35..0A36
6311 UNKNOWN, // 0A37
6312 GURMUKHI, // 0A38..0A39
6313 UNKNOWN, // 0A3A..0A3B
6314 GURMUKHI, // 0A3C
6315 UNKNOWN, // 0A3D
6316 GURMUKHI, // 0A3E..0A42
6317 UNKNOWN, // 0A43..0A46
6318 GURMUKHI, // 0A47..0A48
6319 UNKNOWN, // 0A49..0A4A
6320 GURMUKHI, // 0A4B..0A4D
6321 UNKNOWN, // 0A4E..0A50
6322 GURMUKHI, // 0A51
6323 UNKNOWN, // 0A52..0A58
6324 GURMUKHI, // 0A59..0A5C
6325 UNKNOWN, // 0A5D
6326 GURMUKHI, // 0A5E
6327 UNKNOWN, // 0A5F..0A65
6328 GURMUKHI, // 0A66..0A75
6329 UNKNOWN, // 0A76..0A80
6330 GUJARATI, // 0A81..0A83
6331 UNKNOWN, // 0A84
6332 GUJARATI, // 0A85..0A8D
6333 UNKNOWN, // 0A8E
6334 GUJARATI, // 0A8F..0A91
6335 UNKNOWN, // 0A92
6336 GUJARATI, // 0A93..0AA8
6337 UNKNOWN, // 0AA9
6338 GUJARATI, // 0AAA..0AB0
6339 UNKNOWN, // 0AB1
6340 GUJARATI, // 0AB2..0AB3
6341 UNKNOWN, // 0AB4
6342 GUJARATI, // 0AB5..0AB9
6343 UNKNOWN, // 0ABA..0ABB
6344 GUJARATI, // 0ABC..0AC5
6345 UNKNOWN, // 0AC6
6346 GUJARATI, // 0AC7..0AC9
6347 UNKNOWN, // 0ACA
6348 GUJARATI, // 0ACB..0ACD
6349 UNKNOWN, // 0ACE..0ACF
6350 GUJARATI, // 0AD0
6351 UNKNOWN, // 0AD1..0ADF
6352 GUJARATI, // 0AE0..0AE3
6353 UNKNOWN, // 0AE4..0AE5
6354 GUJARATI, // 0AE6..0AF1
6355 UNKNOWN, // 0AF2..0AF8
6356 GUJARATI, // 0AF9..0AFF
6357 UNKNOWN, // 0B00
6358 ORIYA, // 0B01..0B03
6359 UNKNOWN, // 0B04
6360 ORIYA, // 0B05..0B0C
6361 UNKNOWN, // 0B0D..0B0E
6362 ORIYA, // 0B0F..0B10
6363 UNKNOWN, // 0B11..0B12
6364 ORIYA, // 0B13..0B28
6365 UNKNOWN, // 0B29
6366 ORIYA, // 0B2A..0B30
6367 UNKNOWN, // 0B31
6368 ORIYA, // 0B32..0B33
6369 UNKNOWN, // 0B34
6370 ORIYA, // 0B35..0B39
6371 UNKNOWN, // 0B3A..0B3B
6372 ORIYA, // 0B3C..0B44
6373 UNKNOWN, // 0B45..0B46
6374 ORIYA, // 0B47..0B48
6375 UNKNOWN, // 0B49..0B4A
6376 ORIYA, // 0B4B..0B4D
6377 UNKNOWN, // 0B4E..0B55
6378 ORIYA, // 0B56..0B57
6379 UNKNOWN, // 0B58..0B5B
6380 ORIYA, // 0B5C..0B5D
6381 UNKNOWN, // 0B5E
6382 ORIYA, // 0B5F..0B63
6383 UNKNOWN, // 0B64..0B65
6384 ORIYA, // 0B66..0B77
6385 UNKNOWN, // 0B78..0B81
6386 TAMIL, // 0B82..0B83
6387 UNKNOWN, // 0B84
6388 TAMIL, // 0B85..0B8A
6389 UNKNOWN, // 0B8B..0B8D
6390 TAMIL, // 0B8E..0B90
6391 UNKNOWN, // 0B91
6392 TAMIL, // 0B92..0B95
6393 UNKNOWN, // 0B96..0B98
6394 TAMIL, // 0B99..0B9A
6395 UNKNOWN, // 0B9B
6396 TAMIL, // 0B9C
6397 UNKNOWN, // 0B9D
6398 TAMIL, // 0B9E..0B9F
6399 UNKNOWN, // 0BA0..0BA2
6400 TAMIL, // 0BA3..0BA4
6401 UNKNOWN, // 0BA5..0BA7
6402 TAMIL, // 0BA8..0BAA
6403 UNKNOWN, // 0BAB..0BAD
6404 TAMIL, // 0BAE..0BB9
6405 UNKNOWN, // 0BBA..0BBD
6406 TAMIL, // 0BBE..0BC2
6407 UNKNOWN, // 0BC3..0BC5
6408 TAMIL, // 0BC6..0BC8
6409 UNKNOWN, // 0BC9
6410 TAMIL, // 0BCA..0BCD
6411 UNKNOWN, // 0BCE..0BCF
6412 TAMIL, // 0BD0
6413 UNKNOWN, // 0BD1..0BD6
6414 TAMIL, // 0BD7
6415 UNKNOWN, // 0BD8..0BE5
6416 TAMIL, // 0BE6..0BFA
6417 UNKNOWN, // 0BFB..0BFF
6418 TELUGU, // 0C00..0C03
6419 UNKNOWN, // 0C04
6420 TELUGU, // 0C05..0C0C
6421 UNKNOWN, // 0C0D
6422 TELUGU, // 0C0E..0C10
6423 UNKNOWN, // 0C11
6424 TELUGU, // 0C12..0C28
6425 UNKNOWN, // 0C29
6426 TELUGU, // 0C2A..0C39
6427 UNKNOWN, // 0C3A..0C3C
6428 TELUGU, // 0C3D..0C44
6429 UNKNOWN, // 0C45
6430 TELUGU, // 0C46..0C48
6431 UNKNOWN, // 0C49
6432 TELUGU, // 0C4A..0C4D
6433 UNKNOWN, // 0C4E..0C54
6434 TELUGU, // 0C55..0C56
6435 UNKNOWN, // 0C57
6436 TELUGU, // 0C58..0C5A
6437 UNKNOWN, // 0C5B..0C5F
6438 TELUGU, // 0C60..0C63
6439 UNKNOWN, // 0C64..0C65
6440 TELUGU, // 0C66..0C6F
6441 UNKNOWN, // 0C70..0C77
6442 TELUGU, // 0C78..0C7F
6443 KANNADA, // 0C80..0C83
6444 UNKNOWN, // 0C84
6445 KANNADA, // 0C85..0C8C
6446 UNKNOWN, // 0C8D
6447 KANNADA, // 0C8E..0C90
6448 UNKNOWN, // 0C91
6449 KANNADA, // 0C92..0CA8
6450 UNKNOWN, // 0CA9
6451 KANNADA, // 0CAA..0CB3
6452 UNKNOWN, // 0CB4
6453 KANNADA, // 0CB5..0CB9
6454 UNKNOWN, // 0CBA..0CBB
6455 KANNADA, // 0CBC..0CC4
6456 UNKNOWN, // 0CC5
6457 KANNADA, // 0CC6..0CC8
6458 UNKNOWN, // 0CC9
6459 KANNADA, // 0CCA..0CCD
6460 UNKNOWN, // 0CCE..0CD4
6461 KANNADA, // 0CD5..0CD6
6462 UNKNOWN, // 0CD7..0CDD
6463 KANNADA, // 0CDE
6464 UNKNOWN, // 0CDF
6465 KANNADA, // 0CE0..0CE3
6466 UNKNOWN, // 0CE4..0CE5
6467 KANNADA, // 0CE6..0CEF
6468 UNKNOWN, // 0CF0
6469 KANNADA, // 0CF1..0CF2
6470 UNKNOWN, // 0CF3..0CFF
6471 MALAYALAM, // 0D00..0D03
6472 UNKNOWN, // 0D04
6473 MALAYALAM, // 0D05..0D0C
6474 UNKNOWN, // 0D0D
6475 MALAYALAM, // 0D0E..0D10
6476 UNKNOWN, // 0D11
6477 MALAYALAM, // 0D12..0D44
6478 UNKNOWN, // 0D45
6479 MALAYALAM, // 0D46..0D48
6480 UNKNOWN, // 0D49
6481 MALAYALAM, // 0D4A..0D4F
6482 UNKNOWN, // 0D50..0D53
6483 MALAYALAM, // 0D54..0D63
6484 UNKNOWN, // 0D64..0D65
6485 MALAYALAM, // 0D66..0D7F
6486 UNKNOWN, // 0D80..0D81
6487 SINHALA, // 0D82..0D83
6488 UNKNOWN, // 0D84
6489 SINHALA, // 0D85..0D96
6490 UNKNOWN, // 0D97..0D99
6491 SINHALA, // 0D9A..0DB1
6492 UNKNOWN, // 0DB2
6493 SINHALA, // 0DB3..0DBB
6494 UNKNOWN, // 0DBC
6495 SINHALA, // 0DBD
6496 UNKNOWN, // 0DBE..0DBF
6497 SINHALA, // 0DC0..0DC6
6498 UNKNOWN, // 0DC7..0DC9
6499 SINHALA, // 0DCA
6500 UNKNOWN, // 0DCB..0DCE
6501 SINHALA, // 0DCF..0DD4
6502 UNKNOWN, // 0DD5
6503 SINHALA, // 0DD6
6504 UNKNOWN, // 0DD7
6505 SINHALA, // 0DD8..0DDF
6506 UNKNOWN, // 0DE0..0DE5
6507 SINHALA, // 0DE6..0DEF
6508 UNKNOWN, // 0DF0..0DF1
6509 SINHALA, // 0DF2..0DF4
6510 UNKNOWN, // 0DF5..0E00
6511 THAI, // 0E01..0E3A
6512 UNKNOWN, // 0E3B..0E3E
6513 COMMON, // 0E3F
6514 THAI, // 0E40..0E5B
6515 UNKNOWN, // 0E5C..0E80
6516 LAO, // 0E81..0E82
6517 UNKNOWN, // 0E83
6518 LAO, // 0E84
6519 UNKNOWN, // 0E85..0E86
6520 LAO, // 0E87..0E88
6521 UNKNOWN, // 0E89
6522 LAO, // 0E8A
6523 UNKNOWN, // 0E8B..0E8C
6524 LAO, // 0E8D
6525 UNKNOWN, // 0E8E..0E93
6526 LAO, // 0E94..0E97
6527 UNKNOWN, // 0E98
6528 LAO, // 0E99..0E9F
6529 UNKNOWN, // 0EA0
6530 LAO, // 0EA1..0EA3
6531 UNKNOWN, // 0EA4
6532 LAO, // 0EA5
6533 UNKNOWN, // 0EA6
6534 LAO, // 0EA7
6535 UNKNOWN, // 0EA8..0EA9
6536 LAO, // 0EAA..0EAB
6537 UNKNOWN, // 0EAC
6538 LAO, // 0EAD..0EB9
6539 UNKNOWN, // 0EBA
6540 LAO, // 0EBB..0EBD
6541 UNKNOWN, // 0EBE..0EBF
6542 LAO, // 0EC0..0EC4
6543 UNKNOWN, // 0EC5
6544 LAO, // 0EC6
6545 UNKNOWN, // 0EC7
6546 LAO, // 0EC8..0ECD
6547 UNKNOWN, // 0ECE..0ECF
6548 LAO, // 0ED0..0ED9
6549 UNKNOWN, // 0EDA..0EDB
6550 LAO, // 0EDC..0EDF
6551 UNKNOWN, // 0EE0..0EFF
6552 TIBETAN, // 0F00..0F47
6553 UNKNOWN, // 0F48
6554 TIBETAN, // 0F49..0F6C
6555 UNKNOWN, // 0F6D..0F70
6556 TIBETAN, // 0F71..0F97
6557 UNKNOWN, // 0F98
6558 TIBETAN, // 0F99..0FBC
6559 UNKNOWN, // 0FBD
6560 TIBETAN, // 0FBE..0FCC
6561 UNKNOWN, // 0FCD
6562 TIBETAN, // 0FCE..0FD4
6563 COMMON, // 0FD5..0FD8
6564 TIBETAN, // 0FD9..0FDA
6565 UNKNOWN, // 0FDB..FFF
6566 MYANMAR, // 1000..109F
6567 GEORGIAN, // 10A0..10C5
6568 UNKNOWN, // 10C6
6569 GEORGIAN, // 10C7
6570 UNKNOWN, // 10C8..10CC
6571 GEORGIAN, // 10CD
6572 UNKNOWN, // 10CE..10CF
6573 GEORGIAN, // 10D0..10FA
6574 COMMON, // 10FB
6575 GEORGIAN, // 10FC..10FF
6576 HANGUL, // 1100..11FF
6577 ETHIOPIC, // 1200..1248
6578 UNKNOWN, // 1249
6579 ETHIOPIC, // 124A..124D
6580 UNKNOWN, // 124E..124F
6581 ETHIOPIC, // 1250..1256
6582 UNKNOWN, // 1257
6583 ETHIOPIC, // 1258
6584 UNKNOWN, // 1259
6585 ETHIOPIC, // 125A..125D
6586 UNKNOWN, // 125E..125F
6587 ETHIOPIC, // 1260..1288
6588 UNKNOWN, // 1289
6589 ETHIOPIC, // 128A..128D
6590 UNKNOWN, // 128E..128F
6591 ETHIOPIC, // 1290..12B0
6592 UNKNOWN, // 12B1
6593 ETHIOPIC, // 12B2..12B5
6594 UNKNOWN, // 12B6..12B7
6595 ETHIOPIC, // 12B8..12BE
6596 UNKNOWN, // 12BF
6597 ETHIOPIC, // 12C0
6598 UNKNOWN, // 12C1
6599 ETHIOPIC, // 12C2..12C5
6600 UNKNOWN, // 12C6..12C7
6601 ETHIOPIC, // 12C8..12D6
6602 UNKNOWN, // 12D7
6603 ETHIOPIC, // 12D8..1310
6604 UNKNOWN, // 1311
6605 ETHIOPIC, // 1312..1315
6606 UNKNOWN, // 1316..1317
6607 ETHIOPIC, // 1318..135A
6608 UNKNOWN, // 135B..135C
6609 ETHIOPIC, // 135D..137C
6610 UNKNOWN, // 137D..137F
6611 ETHIOPIC, // 1380..1399
6612 UNKNOWN, // 139A..139F
6613 CHEROKEE, // 13A0..13F5
6614 UNKNOWN, // 13F6..13F7
6615 CHEROKEE, // 13F8..13FD
6616 UNKNOWN, // 13FE..13FF
6617 CANADIAN_ABORIGINAL, // 1400..167F
6618 OGHAM, // 1680..169C
6619 UNKNOWN, // 169D..169F
6620 RUNIC, // 16A0..16EA
6621 COMMON, // 16EB..16ED
6622 RUNIC, // 16EE..16F8
6623 UNKNOWN, // 16F9..16FF
6624 TAGALOG, // 1700..170C
6625 UNKNOWN, // 170D
6626 TAGALOG, // 170E..1714
6627 UNKNOWN, // 1715..171F
6628 HANUNOO, // 1720..1734
6629 COMMON, // 1735..1736
6630 UNKNOWN, // 1737..173F
6631 BUHID, // 1740..1753
6632 UNKNOWN, // 1754..175F
6633 TAGBANWA, // 1760..176C
6634 UNKNOWN, // 176D
6635 TAGBANWA, // 176E..1770
6636 UNKNOWN, // 1771
6637 TAGBANWA, // 1772..1773
6638 UNKNOWN, // 1774..177F
6639 KHMER, // 1780..17DD
6640 UNKNOWN, // 17DE..17DF
6641 KHMER, // 17E0..17E9
6642 UNKNOWN, // 17EA..17EF
6643 KHMER, // 17F0..17F9
6644 UNKNOWN, // 17FA..17FF
6645 MONGOLIAN, // 1800..1801
6646 COMMON, // 1802..1803
6647 MONGOLIAN, // 1804
6648 COMMON, // 1805
6649 MONGOLIAN, // 1806..180E
6650 UNKNOWN, // 180F
6651 MONGOLIAN, // 1810..1819
6652 UNKNOWN, // 181A..181F
6653 MONGOLIAN, // 1820..1877
6654 UNKNOWN, // 1878..187F
6655 MONGOLIAN, // 1880..18AA
6656 UNKNOWN, // 18AB..18AF
6657 CANADIAN_ABORIGINAL, // 18B0..18F5
6658 UNKNOWN, // 18F6..18FF
6659 LIMBU, // 1900..191E
6660 UNKNOWN, // 191F
6661 LIMBU, // 1920..192B
6662 UNKNOWN, // 192C..192F
6663 LIMBU, // 1930..193B
6664 UNKNOWN, // 193C..193F
6665 LIMBU, // 1940
6666 UNKNOWN, // 1941..1943
6667 LIMBU, // 1944..194F
6668 TAI_LE, // 1950..196D
6669 UNKNOWN, // 196E..196F
6670 TAI_LE, // 1970..1974
6671 UNKNOWN, // 1975..197F
6672 NEW_TAI_LUE, // 1980..19AB
6673 UNKNOWN, // 19AC..19AF
6674 NEW_TAI_LUE, // 19B0..19C9
6675 UNKNOWN, // 19CA..19CF
6676 NEW_TAI_LUE, // 19D0..19DA
6677 UNKNOWN, // 19DB..19DD
6678 NEW_TAI_LUE, // 19DE..19DF
6679 KHMER, // 19E0..19FF
6680 BUGINESE, // 1A00..1A1B
6681 UNKNOWN, // 1A1C..1A1D
6682 BUGINESE, // 1A1E..1A1F
6683 TAI_THAM, // 1A20..1A5E
6684 UNKNOWN, // 1A5F
6685 TAI_THAM, // 1A60..1A7C
6686 UNKNOWN, // 1A7D..1A7E
6687 TAI_THAM, // 1A7F..1A89
6688 UNKNOWN, // 1A8A..1A8F
6689 TAI_THAM, // 1A90..1A99
6690 UNKNOWN, // 1A9A..1A9F
6691 TAI_THAM, // 1AA0..1AAD
6692 UNKNOWN, // 1AAE..1AAF
6693 INHERITED, // 1AB0..1ABE
6694 UNKNOWN, // 1ABF..1AFF
6695 BALINESE, // 1B00..1B4B
6696 UNKNOWN, // 1B4C..1B4F
6697 BALINESE, // 1B50..1B7C
6698 UNKNOWN, // 1B7D..1B7F
6699 SUNDANESE, // 1B80..1BBF
6700 BATAK, // 1BC0..1BF3
6701 UNKNOWN, // 1BF4..1BFB
6702 BATAK, // 1BFC..1BFF
6703 LEPCHA, // 1C00..1C37
6704 UNKNOWN, // 1C38..1C3A
6705 LEPCHA, // 1C3B..1C49
6706 UNKNOWN, // 1C4A..1C4C
6707 LEPCHA, // 1C4D..1C4F
6708 OL_CHIKI, // 1C50..1C7F
6709 CYRILLIC, // 1C80..1C88
6710 UNKNOWN, // 1C89..1CBF
6711 SUNDANESE, // 1CC0..1CC7
6712 UNKNOWN, // 1CC8..1CCF
6713 INHERITED, // 1CD0..1CD2
6714 COMMON, // 1CD3
6715 INHERITED, // 1CD4..1CE0
6716 COMMON, // 1CE1
6717 INHERITED, // 1CE2..1CE8
6718 COMMON, // 1CE9..1CEC
6719 INHERITED, // 1CED
6720 COMMON, // 1CEE..1CF3
6721 INHERITED, // 1CF4
6722 COMMON, // 1CF5..1CF7
6723 INHERITED, // 1CF8..1CF9
6724 UNKNOWN, // 1CFA..1CFF
6725 LATIN, // 1D00..1D25
6726 GREEK, // 1D26..1D2A
6727 CYRILLIC, // 1D2B
6728 LATIN, // 1D2C..1D5C
6729 GREEK, // 1D5D..1D61
6730 LATIN, // 1D62..1D65
6731 GREEK, // 1D66..1D6A
6732 LATIN, // 1D6B..1D77
6733 CYRILLIC, // 1D78
6734 LATIN, // 1D79..1DBE
6735 GREEK, // 1DBF
6736 INHERITED, // 1DC0..1DF9
6737 UNKNOWN, // 1DFA
6738 INHERITED, // 1DFB..1DFF
6739 LATIN, // 1E00..1EFF
6740 GREEK, // 1F00..1F15
6741 UNKNOWN, // 1F16..1F17
6742 GREEK, // 1F18..1F1D
6743 UNKNOWN, // 1F1E..1F1F
6744 GREEK, // 1F20..1F45
6745 UNKNOWN, // 1F46..1F47
6746 GREEK, // 1F48..1F4D
6747 UNKNOWN, // 1F4E..1F4F
6748 GREEK, // 1F50..1F57
6749 UNKNOWN, // 1F58
6750 GREEK, // 1F59
6751 UNKNOWN, // 1F5A
6752 GREEK, // 1F5B
6753 UNKNOWN, // 1F5C
6754 GREEK, // 1F5D
6755 UNKNOWN, // 1F5E
6756 GREEK, // 1F5F..1F7D
6757 UNKNOWN, // 1F7E..1F7F
6758 GREEK, // 1F80..1FB4
6759 UNKNOWN, // 1FB5
6760 GREEK, // 1FB6..1FC4
6761 UNKNOWN, // 1FC5
6762 GREEK, // 1FC6..1FD3
6763 UNKNOWN, // 1FD4..1FD5
6764 GREEK, // 1FD6..1FDB
6765 UNKNOWN, // 1FDC
6766 GREEK, // 1FDD..1FEF
6767 UNKNOWN, // 1FF0..1FF1
6768 GREEK, // 1FF2..1FF4
6769 UNKNOWN, // 1FF5
6770 GREEK, // 1FF6..1FFE
6771 UNKNOWN, // 1FFF
6772 COMMON, // 2000..200B
6773 INHERITED, // 200C..200D
6774 COMMON, // 200E..2064
6775 UNKNOWN, // 2065
6776 COMMON, // 2066..2070
6777 LATIN, // 2071
6778 UNKNOWN, // 2072..2073
6779 COMMON, // 2074..207E
6780 LATIN, // 207F
6781 COMMON, // 2080..208E
6782 UNKNOWN, // 208F
6783 LATIN, // 2090..209C
6784 UNKNOWN, // 209D..209F
6785 COMMON, // 20A0..20BF
6786 UNKNOWN, // 20C0..20CF
6787 INHERITED, // 20D0..20F0
6788 UNKNOWN, // 20F1..20FF
6789 COMMON, // 2100..2125
6790 GREEK, // 2126
6791 COMMON, // 2127..2129
6792 LATIN, // 212A..212B
6793 COMMON, // 212C..2131
6794 LATIN, // 2132
6795 COMMON, // 2133..214D
6796 LATIN, // 214E
6797 COMMON, // 214F..215F
6798 LATIN, // 2160..2188
6799 COMMON, // 2189..218B
6800 UNKNOWN, // 218C..218F
6801 COMMON, // 2190..2426
6802 UNKNOWN, // 2427..243F
6803 COMMON, // 2440..244A
6804 UNKNOWN, // 244B..245F
6805 COMMON, // 2460..27FF
6806 BRAILLE, // 2800..28FF
6807 COMMON, // 2900..2B73
6808 UNKNOWN, // 2B74..2B75
6809 COMMON, // 2B76..2B95
6810 UNKNOWN, // 2B96..2B97
6811 COMMON, // 2B98..2BB9
6812 UNKNOWN, // 2BBA..2BBC
6813 COMMON, // 2BBD..2BC8
6814 UNKNOWN, // 2BC9
6815 COMMON, // 2BCA..2BD2
6816 UNKNOWN, // 2BD3..2BEB
6817 COMMON, // 2BEC..2BEF
6818 UNKNOWN, // 2BF0..2BFF
6819 GLAGOLITIC, // 2C00..2C2E
6820 UNKNOWN, // 2C2F
6821 GLAGOLITIC, // 2C30..2C5E
6822 UNKNOWN, // 2C5F
6823 LATIN, // 2C60..2C7F
6824 COPTIC, // 2C80..2CF3
6825 UNKNOWN, // 2CF4..2CF8
6826 COPTIC, // 2CF9..2CFF
6827 GEORGIAN, // 2D00..2D25
6828 UNKNOWN, // 2D26
6829 GEORGIAN, // 2D27
6830 UNKNOWN, // 2D28..2D2C
6831 GEORGIAN, // 2D2D
6832 UNKNOWN, // 2D2E..2D2F
6833 TIFINAGH, // 2D30..2D67
6834 UNKNOWN, // 2D68..2D6E
6835 TIFINAGH, // 2D6F..2D70
6836 UNKNOWN, // 2D71..2D7E
6837 TIFINAGH, // 2D7F
6838 ETHIOPIC, // 2D80..2D96
6839 UNKNOWN, // 2D97..2D9F
6840 ETHIOPIC, // 2DA0..2DA6
6841 UNKNOWN, // 2DA7
6842 ETHIOPIC, // 2DA8..2DAE
6843 UNKNOWN, // 2DAF
6844 ETHIOPIC, // 2DB0..2DB6
6845 UNKNOWN, // 2DB7
6846 ETHIOPIC, // 2DB8..2DBE
6847 UNKNOWN, // 2DBF
6848 ETHIOPIC, // 2DC0..2DC6
6849 UNKNOWN, // 2DC7
6850 ETHIOPIC, // 2DC8..2DCE
6851 UNKNOWN, // 2DCF
6852 ETHIOPIC, // 2DD0..2DD6
6853 UNKNOWN, // 2DD7
6854 ETHIOPIC, // 2DD8..2DDE
6855 UNKNOWN, // 2DDF
6856 CYRILLIC, // 2DE0..2DFF
6857 COMMON, // 2E00..2E49
6858 UNKNOWN, // 2E50..2E7F
6859 HAN, // 2E80..2E99
6860 UNKNOWN, // 2E9A
6861 HAN, // 2E9B..2EF3
6862 UNKNOWN, // 2EF4..2EFF
6863 HAN, // 2F00..2FD5
6864 UNKNOWN, // 2FD6..2FEF
6865 COMMON, // 2FF0..2FFB
6866 UNKNOWN, // 2FFC..2FFF
6867 COMMON, // 3000..3004
6868 HAN, // 3005
6869 COMMON, // 3006
6870 HAN, // 3007
6871 COMMON, // 3008..3020
6872 HAN, // 3021..3029
6873 INHERITED, // 302A..302D
6874 HANGUL, // 302E..302F
6875 COMMON, // 3030..3037
6876 HAN, // 3038..303B
6877 COMMON, // 303C..303F
6878 UNKNOWN, // 3040
6879 HIRAGANA, // 3041..3096
6880 UNKNOWN, // 3097..3098
6881 INHERITED, // 3099..309A
6882 COMMON, // 309B..309C
6883 HIRAGANA, // 309D..309F
6884 COMMON, // 30A0
6885 KATAKANA, // 30A1..30FA
6886 COMMON, // 30FB..30FC
6887 KATAKANA, // 30FD..30FF
6888 UNKNOWN, // 3100..3104
6889 BOPOMOFO, // 3105..312E
6890 UNKNOWN, // 312F..3130
6891 HANGUL, // 3131..318E
6892 UNKNOWN, // 318F
6893 COMMON, // 3190..319F
6894 BOPOMOFO, // 31A0..31BA
6895 UNKNOWN, // 31BB..31BF
6896 COMMON, // 31C0..31E3
6897 UNKNOWN, // 31E4..31EF
6898 KATAKANA, // 31F0..31FF
6899 HANGUL, // 3200..321E
6900 UNKNOWN, // 321F
6901 COMMON, // 3220..325F
6902 HANGUL, // 3260..327E
6903 COMMON, // 327F..32CF
6904 KATAKANA, // 32D0..32FE
6905 UNKNOWN, // 32FF
6906 KATAKANA, // 3300..3357
6907 COMMON, // 3358..33FF
6908 HAN, // 3400..4DB5
6909 UNKNOWN, // 4DB6..4DBF
6910 COMMON, // 4DC0..4DFF
6911 HAN, // 4E00..9FEA
6912 UNKNOWN, // 9FEB..9FFF
6913 YI, // A000..A48C
6914 UNKNOWN, // A48D..A48F
6915 YI, // A490..A4C6
6916 UNKNOWN, // A4C7..A4CF
6917 LISU, // A4D0..A4FF
6918 VAI, // A500..A62B
6919 UNKNOWN, // A62C..A63F
6920 CYRILLIC, // A640..A69F
6921 BAMUM, // A6A0..A6F7
6922 UNKNOWN, // A6F8..A6FF
6923 COMMON, // A700..A721
6924 LATIN, // A722..A787
6925 COMMON, // A788..A78A
6926 LATIN, // A78B..A7AE
6927 UNKNOWN, // A7AF
6928 LATIN, // A7B0..A7B7
6929 UNKNOWN, // A7B8..A7F6
6930 LATIN, // A7F7..A7FF
6931 SYLOTI_NAGRI, // A800..A82B
6932 UNKNOWN, // A82C..A82F
6933 COMMON, // A830..A839
6934 UNKNOWN, // A83A..A83F
6935 PHAGS_PA, // A840..A877
6936 UNKNOWN, // A878..A87F
6937 SAURASHTRA, // A880..A8C5
6938 UNKNOWN, // A8C6..A8CD
6939 SAURASHTRA, // A8CE..A8D9
6940 UNKNOWN, // A8DA..A8DF
6941 DEVANAGARI, // A8E0..A8FD
6942 UNKNOWN, // A8FE..A8FF
6943 KAYAH_LI, // A900..A92D
6944 COMMON, // A92E
6945 KAYAH_LI, // A92F
6946 REJANG, // A930..A953
6947 UNKNOWN, // A954..A95E
6948 REJANG, // A95F
6949 HANGUL, // A960..A97C
6950 UNKNOWN, // A97D..A97F
6951 JAVANESE, // A980..A9CD
6952 UNKNOWN, // A9CE
6953 COMMON, // A9CF
6954 JAVANESE, // A9D0..A9D9
6955 UNKNOWN, // A9DA..A9DD
6956 JAVANESE, // A9DE..A9DF
6957 MYANMAR, // A9E0..A9FE
6958 UNKNOWN, // A9FF
6959 CHAM, // AA00..AA36
6960 UNKNOWN, // AA37..AA3F
6961 CHAM, // AA40..AA4D
6962 UNKNOWN, // AA4E..AA4F
6963 CHAM, // AA50..AA59
6964 UNKNOWN, // AA5A..AA5B
6965 CHAM, // AA5C..AA5F
6966 MYANMAR, // AA60..AA7F
6967 TAI_VIET, // AA80..AAC2
6968 UNKNOWN, // AAC3..AADA
6969 TAI_VIET, // AADB..AADF
6970 MEETEI_MAYEK, // AAE0..AAF6
6971 UNKNOWN, // AAF7..AB00
6972 ETHIOPIC, // AB01..AB06
6973 UNKNOWN, // AB07..AB08
6974 ETHIOPIC, // AB09..AB0E
6975 UNKNOWN, // AB0F..AB10
6976 ETHIOPIC, // AB11..AB16
6977 UNKNOWN, // AB17..AB1F
6978 ETHIOPIC, // AB20..AB26
6979 UNKNOWN, // AB27
6980 ETHIOPIC, // AB28..AB2E
6981 UNKNOWN, // AB2F
6982 LATIN, // AB30..AB5A
6983 COMMON, // AB5B
6984 LATIN, // AB5C..AB64
6985 GREEK, // AB65
6986 UNKNOWN, // AB66..AB6F
6987 CHEROKEE, // AB70..ABBF
6988 MEETEI_MAYEK, // ABC0..ABED
6989 UNKNOWN, // ABEE..ABEF
6990 MEETEI_MAYEK, // ABF0..ABF9
6991 UNKNOWN, // ABFA..ABFF
6992 HANGUL, // AC00..D7A3
6993 UNKNOWN, // D7A4..D7AF
6994 HANGUL, // D7B0..D7C6
6995 UNKNOWN, // D7C7..D7CA
6996 HANGUL, // D7CB..D7FB
6997 UNKNOWN, // D7FC..F8FF
6998 HAN, // F900..FA6D
6999 UNKNOWN, // FA6E..FA6F
7000 HAN, // FA70..FAD9
7001 UNKNOWN, // FADA..FAFF
7002 LATIN, // FB00..FB06
7003 UNKNOWN, // FB07..FB12
7004 ARMENIAN, // FB13..FB17
7005 UNKNOWN, // FB18..FB1C
7006 HEBREW, // FB1D..FB36
7007 UNKNOWN, // FB37
7008 HEBREW, // FB38..FB3C
7009 UNKNOWN, // FB3D
7010 HEBREW, // FB3E
7011 UNKNOWN, // FB3F
7012 HEBREW, // FB40..FB41
7013 UNKNOWN, // FB42
7014 HEBREW, // FB43..FB44
7015 UNKNOWN, // FB45
7016 HEBREW, // FB46..FB4F
7017 ARABIC, // FB50..FBC1
7018 UNKNOWN, // FBC2..FBD2
7019 ARABIC, // FBD3..FD3D
7020 COMMON, // FD3E..FD3F
7021 UNKNOWN, // FD40..FD4F
7022 ARABIC, // FD50..FD8F
7023 UNKNOWN, // FD90..FD91
7024 ARABIC, // FD92..FDC7
7025 UNKNOWN, // FDC8..FDEF
7026 ARABIC, // FDF0..FDFD
7027 UNKNOWN, // FDFE..FDFF
7028 INHERITED, // FE00..FE0F
7029 COMMON, // FE10..FE19
7030 UNKNOWN, // FE1A..FE1F
7031 INHERITED, // FE20..FE2D
7032 CYRILLIC, // FE2E..FE2F
7033 COMMON, // FE30..FE52
7034 UNKNOWN, // FE53
7035 COMMON, // FE54..FE66
7036 UNKNOWN, // FE67
7037 COMMON, // FE68..FE6B
7038 UNKNOWN, // FE6C..FE6F
7039 ARABIC, // FE70..FE74
7040 UNKNOWN, // FE75
7041 ARABIC, // FE76..FEFC
7042 UNKNOWN, // FEFD..FEFE
7043 COMMON, // FEFF
7044 UNKNOWN, // FF00
7045 COMMON, // FF01..FF20
7046 LATIN, // FF21..FF3A
7047 COMMON, // FF3B..FF40
7048 LATIN, // FF41..FF5A
7049 COMMON, // FF5B..FF65
7050 KATAKANA, // FF66..FF6F
7051 COMMON, // FF70
7052 KATAKANA, // FF71..FF9D
7053 COMMON, // FF9E..FF9F
7054 HANGUL, // FFA0..FFBE
7055 UNKNOWN, // FFBF..FFC1
7056 HANGUL, // FFC2..FFC7
7057 UNKNOWN, // FFC8..FFC9
7058 HANGUL, // FFCA..FFCF
7059 UNKNOWN, // FFD0..FFD1
7060 HANGUL, // FFD2..FFD7
7061 UNKNOWN, // FFD8..FFD9
7062 HANGUL, // FFDA..FFDC
7063 UNKNOWN, // FFDD..FFDF
7064 COMMON, // FFE0..FFE6
7065 UNKNOWN, // FFE7
7066 COMMON, // FFE8..FFEE
7067 UNKNOWN, // FFEF..FFF8
7068 COMMON, // FFF9..FFFD
7069 UNKNOWN, // FFFE..FFFF
7070 LINEAR_B, // 10000..1000B
7071 UNKNOWN, // 1000C
7072 LINEAR_B, // 1000D..10026
7073 UNKNOWN, // 10027
7074 LINEAR_B, // 10028..1003A
7075 UNKNOWN, // 1003B
7076 LINEAR_B, // 1003C..1003D
7077 UNKNOWN, // 1003E
7078 LINEAR_B, // 1003F..1004D
7079 UNKNOWN, // 1004E..1004F
7080 LINEAR_B, // 10050..1005D
7081 UNKNOWN, // 1005E..1007F
7082 LINEAR_B, // 10080..100FA
7083 UNKNOWN, // 100FB..100FF
7084 COMMON, // 10100..10102
7085 UNKNOWN, // 10103..10106
7086 COMMON, // 10107..10133
7087 UNKNOWN, // 10134..10136
7088 COMMON, // 10137..1013F
7089 GREEK, // 10140..1018E
7090 UNKNOWN, // 1018F
7091 COMMON, // 10190..1019B
7092 UNKNOWN, // 1019C..1019F
7093 GREEK, // 101A0
7094 UNKNOWN, // 101A1..101CF
7095 COMMON, // 101D0..101FC
7096 INHERITED, // 101FD
7097 UNKNOWN, // 101FE..1027F
7098 LYCIAN, // 10280..1029C
7099 UNKNOWN, // 1029D..1029F
7100 CARIAN, // 102A0..102D0
7101 UNKNOWN, // 102D1..102DF
7102 INHERITED, // 102E0
7103 COMMON, // 102E1..102FB
7104 UNKNOWN, // 102FC..102FF
7105 OLD_ITALIC, // 10300..10323
7106 UNKNOWN, // 10324..1032C
7107 OLD_ITALIC, // 1032D..1032F
7108 GOTHIC, // 10330..1034A
7109 UNKNOWN, // 1034B..1034F
7110 OLD_PERMIC, // 10350..1037A
7111 UNKNOWN, // 1037B..1037F
7112 UGARITIC, // 10380..1039D
7113 UNKNOWN, // 1039E
7114 UGARITIC, // 1039F
7115 OLD_PERSIAN, // 103A0..103C3
7116 UNKNOWN, // 103C4..103C7
7117 OLD_PERSIAN, // 103C8..103D5
7118 UNKNOWN, // 103D6..103FF
7119 DESERET, // 10400..1044F
7120 SHAVIAN, // 10450..1047F
7121 OSMANYA, // 10480..1049D
7122 UNKNOWN, // 1049E..1049F
7123 OSMANYA, // 104A0..104A9
7124 UNKNOWN, // 104AA..104AF
7125 OSAGE, // 104B0..104D3;
7126 UNKNOWN, // 104D4..104D7;
7127 OSAGE, // 104D8..104FB;
7128 UNKNOWN, // 104FC..104FF;
7129 ELBASAN, // 10500..10527
7130 UNKNOWN, // 10528..1052F
7131 CAUCASIAN_ALBANIAN, // 10530..10563
7132 UNKNOWN, // 10564..1056E
7133 CAUCASIAN_ALBANIAN, // 1056F
7134 UNKNOWN, // 10570..105FF
7135 LINEAR_A, // 10600..10736
7136 UNKNOWN, // 10737..1073F
7137 LINEAR_A, // 10740..10755
7138 UNKNOWN, // 10756..1075F
7139 LINEAR_A, // 10760..10767
7140 UNKNOWN, // 10768..107FF
7141 CYPRIOT, // 10800..10805
7142 UNKNOWN, // 10806..10807
7143 CYPRIOT, // 10808
7144 UNKNOWN, // 10809
7145 CYPRIOT, // 1080A..10835
7146 UNKNOWN, // 10836
7147 CYPRIOT, // 10837..10838
7148 UNKNOWN, // 10839..1083B
7149 CYPRIOT, // 1083C
7150 UNKNOWN, // 1083D..1083E
7151 CYPRIOT, // 1083F
7152 IMPERIAL_ARAMAIC, // 10840..10855
7153 UNKNOWN, // 10856
7154 IMPERIAL_ARAMAIC, // 10857..1085F
7155 PALMYRENE, // 10860..1087F
7156 NABATAEAN, // 10880..1089E
7157 UNKNOWN, // 1089F..108A6
7158 NABATAEAN, // 108A7..108AF
7159 UNKNOWN, // 108B0..108DF
7160 HATRAN, // 108E0..108F2
7161 UNKNOWN, // 108F3
7162 HATRAN, // 108F4..108F5
7163 UNKNOWN, // 108F6..108FA
7164 HATRAN, // 108FB..108FF
7165 PHOENICIAN, // 10900..1091B
7166 UNKNOWN, // 1091C..1091E
7167 PHOENICIAN, // 1091F
7168 LYDIAN, // 10920..10939
7169 UNKNOWN, // 1093A..1093E
7170 LYDIAN, // 1093F
7171 UNKNOWN, // 10940..1097F
7172 MEROITIC_HIEROGLYPHS, // 10980..1099F
7173 MEROITIC_CURSIVE, // 109A0..109B7
7174 UNKNOWN, // 109B8..109BB
7175 MEROITIC_CURSIVE, // 109BC..109CF
7176 UNKNOWN, // 109D0..109D1
7177 MEROITIC_CURSIVE, // 109D2..109FF
7178 KHAROSHTHI, // 10A00..10A03
7179 UNKNOWN, // 10A04
7180 KHAROSHTHI, // 10A05..10A06
7181 UNKNOWN, // 10A07..10A0B
7182 KHAROSHTHI, // 10A0C..10A13
7183 UNKNOWN, // 10A14
7184 KHAROSHTHI, // 10A15..10A17
7185 UNKNOWN, // 10A18
7186 KHAROSHTHI, // 10A19..10A33
7187 UNKNOWN, // 10A34..10A37
7188 KHAROSHTHI, // 10A38..10A3A
7189 UNKNOWN, // 10A3B..10A3E
7190 KHAROSHTHI, // 10A3F..10A47
7191 UNKNOWN, // 10A48..10A4F
7192 KHAROSHTHI, // 10A50..10A58
7193 UNKNOWN, // 10A59..10A5F
7194 OLD_SOUTH_ARABIAN, // 10A60..10A7F
7195 OLD_NORTH_ARABIAN, // 10A80..10A9F
7196 UNKNOWN, // 10AA0..10ABF
7197 MANICHAEAN, // 10AC0..10AE6
7198 UNKNOWN, // 10AE7..10AEA
7199 MANICHAEAN, // 10AEB..10AF6
7200 UNKNOWN, // 10AF7..10AFF
7201 AVESTAN, // 10B00..10B35
7202 UNKNOWN, // 10B36..10B38
7203 AVESTAN, // 10B39..10B3F
7204 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
7205 UNKNOWN, // 10B56..10B57
7206 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
7207 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
7208 UNKNOWN, // 10B73..10B77
7209 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
7210 PSALTER_PAHLAVI, // 10B80..10B91
7211 UNKNOWN, // 10B92..10B98
7212 PSALTER_PAHLAVI, // 10B99..10B9C
7213 UNKNOWN, // 10B9D..10BA8
7214 PSALTER_PAHLAVI, // 10BA9..10BAF
7215 UNKNOWN, // 10BB0..10BFF
7216 OLD_TURKIC, // 10C00..10C48
7217 UNKNOWN, // 10C49..10C7F
7218 OLD_HUNGARIAN, // 10C80..10CB2
7219 UNKNOWN, // 10CB3..10CBF
7220 OLD_HUNGARIAN, // 10CC0..10CF2
7221 UNKNOWN, // 10CF3..10CF9
7222 OLD_HUNGARIAN, // 10CFA..10CFF
7223 UNKNOWN, // 10D00..10E5F
7224 ARABIC, // 10E60..10E7E
7225 UNKNOWN, // 10E7F..10FFF
7226 BRAHMI, // 11000..1104D
7227 UNKNOWN, // 1104E..11051
7228 BRAHMI, // 11052..1106F
7229 UNKNOWN, // 11070..1107E
7230 BRAHMI, // 1107F
7231 KAITHI, // 11080..110C1
7232 UNKNOWN, // 110C2..110CF
7233 SORA_SOMPENG, // 110D0..110E8
7234 UNKNOWN, // 110E9..110EF
7235 SORA_SOMPENG, // 110F0..110F9
7236 UNKNOWN, // 110FA..110FF
7237 CHAKMA, // 11100..11134
7238 UNKNOWN, // 11135
7239 CHAKMA, // 11136..11143
7240 UNKNOWN, // 11144..1114F
7241 MAHAJANI, // 11150..11176
7242 UNKNOWN, // 11177..1117F
7243 SHARADA, // 11180..111CD
7244 UNKNOWN, // 111CE..111CF
7245 SHARADA, // 111D0..111DF
7246 UNKNOWN, // 111E0
7247 SINHALA, // 111E1..111F4
7248 UNKNOWN, // 111F5..111FF
7249 KHOJKI, // 11200..11211
7250 UNKNOWN, // 11212
7251 KHOJKI, // 11213..1123E
7252 UNKNOWN, // 1123F..1127F
7253 MULTANI, // 11280..11286
7254 UNKNOWN, // 11287
7255 MULTANI, // 11288
7256 UNKNOWN, // 11289
7257 MULTANI, // 1128A..1128D
7258 UNKNOWN, // 1128E
7259 MULTANI, // 1128F..1129D
7260 UNKNOWN, // 1129E
7261 MULTANI, // 1129F..112A9
7262 UNKNOWN, // 112AA..112AF
7263 KHUDAWADI, // 112B0..112EA
7264 UNKNOWN, // 112EB..112EF
7265 KHUDAWADI, // 112F0..112F9
7266 UNKNOWN, // 112FA..112FF
7267 GRANTHA, // 11300..11303
7268 UNKNOWN, // 11304
7269 GRANTHA, // 11305..1130C
7270 UNKNOWN, // 1130D..1130E
7271 GRANTHA, // 1130F..11310
7272 UNKNOWN, // 11311..11312
7273 GRANTHA, // 11313..11328
7274 UNKNOWN, // 11329
7275 GRANTHA, // 1132A..11330
7276 UNKNOWN, // 11331
7277 GRANTHA, // 11332..11333
7278 UNKNOWN, // 11334
7279 GRANTHA, // 11335..11339
7280 UNKNOWN, // 1133A..1133B
7281 GRANTHA, // 1133C..11344
7282 UNKNOWN, // 11345..11346
7283 GRANTHA, // 11347..11348
7284 UNKNOWN, // 11349..1134A
7285 GRANTHA, // 1134B..1134D
7286 UNKNOWN, // 1134E..1134F
7287 GRANTHA, // 11350
7288 UNKNOWN, // 11351..11356
7289 GRANTHA, // 11357
7290 UNKNOWN, // 11358..1135C
7291 GRANTHA, // 1135D..11363
7292 UNKNOWN, // 11364..11365
7293 GRANTHA, // 11366..1136C
7294 UNKNOWN, // 1136D..1136F
7295 GRANTHA, // 11370..11374
7296 UNKNOWN, // 11375..113FF
7297 NEWA, // 11400..11459
7298 UNKNOWN, // 1145A
7299 NEWA, // 1145B
7300 UNKNOWN, // 1145C
7301 NEWA, // 1145D
7302 UNKNOWN, // 1145E..1147F
7303 TIRHUTA, // 11480..114C7
7304 UNKNOWN, // 114C8..114CF
7305 TIRHUTA, // 114D0..114D9
7306 UNKNOWN, // 114DA..1157F
7307 SIDDHAM, // 11580..115B5
7308 UNKNOWN, // 115B6..115B7
7309 SIDDHAM, // 115B8..115DD
7310 UNKNOWN, // 115DE..115FF
7311 MODI, // 11600..11644
7312 UNKNOWN, // 11645..1164F
7313 MODI, // 11650..11659
7314 UNKNOWN, // 1165A..1165F
7315 MONGOLIAN, // 11660..1166C
7316 UNKNOWN, // 1166D..1167F
7317 TAKRI, // 11680..116B7
7318 UNKNOWN, // 116B8..116BF
7319 TAKRI, // 116C0..116C9
7320 UNKNOWN, // 116CA..116FF
7321 AHOM, // 11700..11719
7322 UNKNOWN, // 1171A..1171C
7323 AHOM, // 1171D..1172B
7324 UNKNOWN, // 1172C..1172F
7325 AHOM, // 11730..1173F
7326 UNKNOWN, // 11740..1189F
7327 WARANG_CITI, // 118A0..118F2
7328 UNKNOWN, // 118F3..118FE
7329 WARANG_CITI, // 118FF
7330 UNKNOWN, // 11900..119FF
7331 ZANABAZAR_SQUARE, // 11A00..11A47
7332 UNKNOWN, // 11A48..11A4F
7333 SOYOMBO, // 11A50..11A83
7334 UNKNOWN, // 11A84..11A85
7335 SOYOMBO, // 11A86..11A9C
7336 UNKNOWN, // 11A9D
7337 SOYOMBO, // 11A9E..11AA2
7338 UNKNOWN, // 11AA3..11ABF
7339 PAU_CIN_HAU, // 11AC0..11AF8
7340 UNKNOWN, // 11AF9..11BFF
7341 BHAIKSUKI, // 11C00..11C08
7342 UNKNOWN, // 11C09
7343 BHAIKSUKI, // 11C0A..11C36
7344 UNKNOWN, // 11C37
7345 BHAIKSUKI, // 11C38..11C45
7346 UNKNOWN, // 11C46..11C49
7347 BHAIKSUKI, // 11C50..11C6C
7348 UNKNOWN, // 11C6D..11C6F
7349 MARCHEN, // 11C70..11C8F
7350 UNKNOWN, // 11C90..11C91
7351 MARCHEN, // 11C92..11CA7
7352 UNKNOWN, // 11CA8
7353 MARCHEN, // 11CA9..11CB6
7354 UNKNOWN, // 11CB7..11CFF
7355 MASARAM_GONDI, // 11D00..11D06
7356 UNKNOWN, // 11D07
7357 MASARAM_GONDI, // 11D08..11D09
7358 UNKNOWN, // 11D0A
7359 MASARAM_GONDI, // 11D0B..11D36
7360 UNKNOWN, // 11D37..11D39
7361 MASARAM_GONDI, // 11D3A
7362 UNKNOWN, // 11D3B
7363 MASARAM_GONDI, // 11D3C..11D3D
7364 UNKNOWN, // 11D3E
7365 MASARAM_GONDI, // 11D3F..11D47
7366 UNKNOWN, // 11D48..11D49
7367 MASARAM_GONDI, // 11D50..11D59
7368 UNKNOWN, // 11D5A..1AFFF;
7369 CUNEIFORM, // 12000..12399
7370 UNKNOWN, // 1239A..123FF
7371 CUNEIFORM, // 12400..1246E
7372 UNKNOWN, // 1246F
7373 CUNEIFORM, // 12470..12474
7374 UNKNOWN, // 12475..1247F
7375 CUNEIFORM, // 12480..12543
7376 UNKNOWN, // 12544..12FFF
7377 EGYPTIAN_HIEROGLYPHS, // 13000..1342E
7378 UNKNOWN, // 1342F..143FF
7379 ANATOLIAN_HIEROGLYPHS, // 14400..14646
7380 UNKNOWN, // 14647..167FF
7381 BAMUM, // 16800..16A38
7382 UNKNOWN, // 16A39..16A3F
7383 MRO, // 16A40..16A5E
7384 UNKNOWN, // 16A5F
7385 MRO, // 16A60..16A69
7386 UNKNOWN, // 16A6A..16A6D
7387 MRO, // 16A6E..16A6F
7388 UNKNOWN, // 16A70..16ACF
7389 BASSA_VAH, // 16AD0..16AED
7390 UNKNOWN, // 16AEE..16AEF
7391 BASSA_VAH, // 16AF0..16AF5
7392 UNKNOWN, // 16AF6..16AFF
7393 PAHAWH_HMONG, // 16B00..16B45
7394 UNKNOWN, // 16B46..16B4F
7395 PAHAWH_HMONG, // 16B50..16B59
7396 UNKNOWN, // 16B5A
7397 PAHAWH_HMONG, // 16B5B..16B61
7398 UNKNOWN, // 16B62
7399 PAHAWH_HMONG, // 16B63..16B77
7400 UNKNOWN, // 16B78..16B7C
7401 PAHAWH_HMONG, // 16B7D..16B8F
7402 UNKNOWN, // 16B90..16EFF
7403 MIAO, // 16F00..16F44
7404 UNKNOWN, // 16F45..16F4F
7405 MIAO, // 16F50..16F7E
7406 UNKNOWN, // 16F7F..16F8E
7407 MIAO, // 16F8F..16F9F
7408 UNKNOWN, // 16FA0..16FDF
7409 TANGUT, // 16FE0
7410 NUSHU, // 16FE1
7411 UNKNOWN, // 16FE2..16FFF
7412 TANGUT, // 17000..187EC
7413 UNKNOWN, // 187ED..187FF
7414 TANGUT, // 18800..18AF2
7415 UNKNOWN, // 18AF3..1AFFF
7416 KATAKANA, // 1B000
7417 HIRAGANA, // 1B001..1B11E
7418 UNKNOWN, // 1B11F..1B16F
7419 NUSHU, // 1B170..1B2FB
7420 UNKNOWN, // 1B2FC..1BBFF
7421 DUPLOYAN, // 1BC00..1BC6A
7422 UNKNOWN, // 1BC6B..1BC6F
7423 DUPLOYAN, // 1BC70..1BC7C
7424 UNKNOWN, // 1BC7D..1BC7F
7425 DUPLOYAN, // 1BC80..1BC88
7426 UNKNOWN, // 1BC89..1BC8F
7427 DUPLOYAN, // 1BC90..1BC99
7428 UNKNOWN, // 1BC9A..1BC9B
7429 DUPLOYAN, // 1BC9C..1BC9F
7430 COMMON, // 1BCA0..1BCA3
7431 UNKNOWN, // 1BCA4..1CFFF
7432 COMMON, // 1D000..1D0F5
7433 UNKNOWN, // 1D0F6..1D0FF
7434 COMMON, // 1D100..1D126
7435 UNKNOWN, // 1D127..1D128
7436 COMMON, // 1D129..1D166
7437 INHERITED, // 1D167..1D169
7438 COMMON, // 1D16A..1D17A
7439 INHERITED, // 1D17B..1D182
7440 COMMON, // 1D183..1D184
7441 INHERITED, // 1D185..1D18B
7442 COMMON, // 1D18C..1D1A9
7443 INHERITED, // 1D1AA..1D1AD
7444 COMMON, // 1D1AE..1D1E8
7445 UNKNOWN, // 1D1E9..1D1FF
7446 GREEK, // 1D200..1D245
7447 UNKNOWN, // 1D246..1D2FF
7448 COMMON, // 1D300..1D356
7449 UNKNOWN, // 1D357..1D35F
7450 COMMON, // 1D360..1D371
7451 UNKNOWN, // 1D372..1D3FF
7452 COMMON, // 1D400..1D454
7453 UNKNOWN, // 1D455
7454 COMMON, // 1D456..1D49C
7455 UNKNOWN, // 1D49D
7456 COMMON, // 1D49E..1D49F
7457 UNKNOWN, // 1D4A0..1D4A1
7458 COMMON, // 1D4A2
7459 UNKNOWN, // 1D4A3..1D4A4
7460 COMMON, // 1D4A5..1D4A6
7461 UNKNOWN, // 1D4A7..1D4A8
7462 COMMON, // 1D4A9..1D4AC
7463 UNKNOWN, // 1D4AD
7464 COMMON, // 1D4AE..1D4B9
7465 UNKNOWN, // 1D4BA
7466 COMMON, // 1D4BB
7467 UNKNOWN, // 1D4BC
7468 COMMON, // 1D4BD..1D4C3
7469 UNKNOWN, // 1D4C4
7470 COMMON, // 1D4C5..1D505
7471 UNKNOWN, // 1D506
7472 COMMON, // 1D507..1D50A
7473 UNKNOWN, // 1D50B..1D50C
7474 COMMON, // 1D50D..1D514
7475 UNKNOWN, // 1D515
7476 COMMON, // 1D516..1D51C
7477 UNKNOWN, // 1D51D
7478 COMMON, // 1D51E..1D539
7479 UNKNOWN, // 1D53A
7480 COMMON, // 1D53B..1D53E
7481 UNKNOWN, // 1D53F
7482 COMMON, // 1D540..1D544
7483 UNKNOWN, // 1D545
7484 COMMON, // 1D546
7485 UNKNOWN, // 1D547..1D549
7486 COMMON, // 1D54A..1D550
7487 UNKNOWN, // 1D551
7488 COMMON, // 1D552..1D6A5
7489 UNKNOWN, // 1D6A6..1D6A7
7490 COMMON, // 1D6A8..1D7CB
7491 UNKNOWN, // 1D7CC..1D7CD
7492 COMMON, // 1D7CE..1D7FF
7493 SIGNWRITING, // 1D800..1DA8B
7494 UNKNOWN, // 1DA8C..1DA9A
7495 SIGNWRITING, // 1DA9B..1DA9F
7496 UNKNOWN, // 1DAA0
7497 SIGNWRITING, // 1DAA1..1DAAF
7498 UNKNOWN, // 1DAB0..1DFFF
7499 GLAGOLITIC, // 1E000..1E006
7500 UNKNOWN, // 1E007
7501 GLAGOLITIC, // 1E008..1E018
7502 UNKNOWN, // 1E019..1E01A
7503 GLAGOLITIC, // 1E01B..1E021
7504 UNKNOWN, // 1E022
7505 GLAGOLITIC, // 1E023..1E024
7506 UNKNOWN, // 1E025
7507 GLAGOLITIC, // 1E026..1E02A
7508 UNKNOWN, // 1E02B..1E7FF
7509 MENDE_KIKAKUI, // 1E800..1E8C4
7510 UNKNOWN, // 1E8C5..1E8C6
7511 MENDE_KIKAKUI, // 1E8C7..1E8D6
7512 UNKNOWN, // 1E8D7..1E8FF
7513 ADLAM, // 1E900..1E94A
7514 UNKNOWN, // 1E94B..1E94F
7515 ADLAM, // 1E950..1E959
7516 UNKNOWN, // 1E95A..1E95D
7517 ADLAM, // 1E95E..1E95F
7518 UNKNOWN, // 1E960..1EDFF
7519 ARABIC, // 1EE00..1EE03
7520 UNKNOWN, // 1EE04
7521 ARABIC, // 1EE05..1EE1F
7522 UNKNOWN, // 1EE20
7523 ARABIC, // 1EE21..1EE22
7524 UNKNOWN, // 1EE23
7525 ARABIC, // 1EE24
7526 UNKNOWN, // 1EE25..1EE26
7527 ARABIC, // 1EE27
7528 UNKNOWN, // 1EE28
7529 ARABIC, // 1EE29..1EE32
7530 UNKNOWN, // 1EE33
7531 ARABIC, // 1EE34..1EE37
7532 UNKNOWN, // 1EE38
7533 ARABIC, // 1EE39
7534 UNKNOWN, // 1EE3A
7535 ARABIC, // 1EE3B
7536 UNKNOWN, // 1EE3C..1EE41
7537 ARABIC, // 1EE42
7538 UNKNOWN, // 1EE43..1EE46
7539 ARABIC, // 1EE47
7540 UNKNOWN, // 1EE48
7541 ARABIC, // 1EE49
7542 UNKNOWN, // 1EE4A
7543 ARABIC, // 1EE4B
7544 UNKNOWN, // 1EE4C
7545 ARABIC, // 1EE4D..1EE4F
7546 UNKNOWN, // 1EE50
7547 ARABIC, // 1EE51..1EE52
7548 UNKNOWN, // 1EE53
7549 ARABIC, // 1EE54
7550 UNKNOWN, // 1EE55..1EE56
7551 ARABIC, // 1EE57
7552 UNKNOWN, // 1EE58
7553 ARABIC, // 1EE59
7554 UNKNOWN, // 1EE5A
7555 ARABIC, // 1EE5B
7556 UNKNOWN, // 1EE5C
7557 ARABIC, // 1EE5D
7558 UNKNOWN, // 1EE5E
7559 ARABIC, // 1EE5F
7560 UNKNOWN, // 1EE60
7561 ARABIC, // 1EE61..1EE62
7562 UNKNOWN, // 1EE63
7563 ARABIC, // 1EE64
7564 UNKNOWN, // 1EE65..1EE66
7565 ARABIC, // 1EE67..1EE6A
7566 UNKNOWN, // 1EE6B
7567 ARABIC, // 1EE6C..1EE72
7568 UNKNOWN, // 1EE73
7569 ARABIC, // 1EE74..1EE77
7570 UNKNOWN, // 1EE78
7571 ARABIC, // 1EE79..1EE7C
7572 UNKNOWN, // 1EE7D
7573 ARABIC, // 1EE7E
7574 UNKNOWN, // 1EE7F
7575 ARABIC, // 1EE80..1EE89
7576 UNKNOWN, // 1EE8A
7577 ARABIC, // 1EE8B..1EE9B
7578 UNKNOWN, // 1EE9C..1EEA0
7579 ARABIC, // 1EEA1..1EEA3
7580 UNKNOWN, // 1EEA4
7581 ARABIC, // 1EEA5..1EEA9
7582 UNKNOWN, // 1EEAA
7583 ARABIC, // 1EEAB..1EEBB
7584 UNKNOWN, // 1EEBC..1EEEF
7585 ARABIC, // 1EEF0..1EEF1
7586 UNKNOWN, // 1EEF2..1EFFF
7587 COMMON, // 1F000..1F02B
7588 UNKNOWN, // 1F02C..1F02F
7589 COMMON, // 1F030..1F093
7590 UNKNOWN, // 1F094..1F09F
7591 COMMON, // 1F0A0..1F0AE
7592 UNKNOWN, // 1F0AF..1F0B0
7593 COMMON, // 1F0B1..1F0BF
7594 UNKNOWN, // 1F0C0
7595 COMMON, // 1F0C1..1F0CF
7596 UNKNOWN, // 1F0D0
7597 COMMON, // 1F0D1..1F0F5
7598 UNKNOWN, // 1F0F6..1F0FF
7599 COMMON, // 1F100..1F10C
7600 UNKNOWN, // 1F10D..1F10F
7601 COMMON, // 1F110..1F12E
7602 UNKNOWN, // 1F12F
7603 COMMON, // 1F130..1F16B
7604 UNKNOWN, // 1F16C..1F16F
7605 COMMON, // 1F170..1F1AC
7606 UNKNOWN, // 1F1AD..1F1E5
7607 COMMON, // 1F1E6..1F1FF
7608 HIRAGANA, // 1F200
7609 COMMON, // 1F201..1F202
7610 UNKNOWN, // 1F203..1F20F
7611 COMMON, // 1F210..1F23B
7612 UNKNOWN, // 1F23C..1F23F
7613 COMMON, // 1F240..1F248
7614 UNKNOWN, // 1F249..1F24F
7615 COMMON, // 1F250..1F251
7616 UNKNOWN, // 1F252..1F25F
7617 COMMON, // 1F260..1F265
7618 UNKNOWN, // 1F266..1F2FF
7619 COMMON, // 1F300..1F6D4
7620 UNKNOWN, // 1F6D5..1F6DF
7621 COMMON, // 1F6E0..1F6EC
7622 UNKNOWN, // 1F6ED..1F6EF
7623 COMMON, // 1F6F0..1F6F8
7624 UNKNOWN, // 1F6F9..1F6FF
7625 COMMON, // 1F700..1F773
7626 UNKNOWN, // 1F774..1F77F
7627 COMMON, // 1F780..1F7D4
7628 UNKNOWN, // 1F7D5..1F7FF
7629 COMMON, // 1F800..1F80B
7630 UNKNOWN, // 1F80C..1F80F
7631 COMMON, // 1F810..1F847
7632 UNKNOWN, // 1F848..1F84F
7633 COMMON, // 1F850..1F859
7634 UNKNOWN, // 1F85A..1F85F
7635 COMMON, // 1F860..1F887
7636 UNKNOWN, // 1F888..1F88F
7637 COMMON, // 1F890..1F8AD
7638 UNKNOWN, // 1F8AE..1F8FF
7639 COMMON, // 1F900..1F90B
7640 UNKNOWN, // 1F90C..1F90F
7641 COMMON, // 1F910..1F93E
7642 UNKNOWN, // 1F93F
7643 COMMON, // 1F940..1F94C
7644 UNKNOWN, // 1F94D..1F94F
7645 COMMON, // 1F950..1F96B
7646 UNKNOWN, // 1F96C..1F97F
7647 COMMON, // 1F980..1F997
7648 UNKNOWN, // 1F998..1F9BF
7649 COMMON, // 1F9C0
7650 UNKNOWN, // 1F9C1..1F9CF
7651 COMMON, // 1F9D0..1F9E6
7652 UNKNOWN, // 1F9E7..1FFFF
7653 HAN, // 20000..2A6D6
7654 UNKNOWN, // 2A6D7..2A6FF
7655 HAN, // 2A700..2B734
7656 UNKNOWN, // 2B735..2B73F
7657 HAN, // 2B740..2B81D
7658 UNKNOWN, // 2B81E..2B81F
7659 HAN, // 2B820..2CEA1
7660 UNKNOWN, // 2CEA2..2CEAF
7661 HAN, // 2CEB0..2EBE0
7662 UNKNOWN, // 2EBE1..2F7FF
7663 HAN, // 2F800..2FA1D
7664 UNKNOWN, // 2FA1E..E0000
7665 COMMON, // E0001
7666 UNKNOWN, // E0002..E001F
7667 COMMON, // E0020..E007F
7668 UNKNOWN, // E0080..E00FF
7669 INHERITED, // E0100..E01EF
7670 UNKNOWN // E01F0..10FFFF
7671 };
7672
7673 private static HashMap<String, Character.UnicodeScript> aliases;
7674 static {
7675 aliases = new HashMap<>((int)(142 / 0.75f + 1.0f));
7676 aliases.put("ADLM", ADLAM);
7677 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
7678 aliases.put("AHOM", AHOM);
7679 aliases.put("ARAB", ARABIC);
7680 aliases.put("ARMI", IMPERIAL_ARAMAIC);
7681 aliases.put("ARMN", ARMENIAN);
7682 aliases.put("AVST", AVESTAN);
7683 aliases.put("BALI", BALINESE);
7684 aliases.put("BAMU", BAMUM);
7685 aliases.put("BASS", BASSA_VAH);
7686 aliases.put("BATK", BATAK);
7687 aliases.put("BENG", BENGALI);
7688 aliases.put("BHKS", BHAIKSUKI);
7689 aliases.put("BOPO", BOPOMOFO);
7690 aliases.put("BRAH", BRAHMI);
7691 aliases.put("BRAI", BRAILLE);
7692 aliases.put("BUGI", BUGINESE);
7693 aliases.put("BUHD", BUHID);
7694 aliases.put("CAKM", CHAKMA);
7695 aliases.put("CANS", CANADIAN_ABORIGINAL);
7696 aliases.put("CARI", CARIAN);
7697 aliases.put("CHAM", CHAM);
7698 aliases.put("CHER", CHEROKEE);
7699 aliases.put("COPT", COPTIC);
7700 aliases.put("CPRT", CYPRIOT);
7701 aliases.put("CYRL", CYRILLIC);
7702 aliases.put("DEVA", DEVANAGARI);
7703 aliases.put("DSRT", DESERET);
7704 aliases.put("DUPL", DUPLOYAN);
7705 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
7706 aliases.put("ELBA", ELBASAN);
7707 aliases.put("ETHI", ETHIOPIC);
7708 aliases.put("GEOR", GEORGIAN);
7709 aliases.put("GLAG", GLAGOLITIC);
7710 aliases.put("GONM", MASARAM_GONDI);
7711 aliases.put("GOTH", GOTHIC);
7712 aliases.put("GRAN", GRANTHA);
7713 aliases.put("GREK", GREEK);
7714 aliases.put("GUJR", GUJARATI);
7715 aliases.put("GURU", GURMUKHI);
7716 aliases.put("HANG", HANGUL);
7717 aliases.put("HANI", HAN);
7718 aliases.put("HANO", HANUNOO);
7719 aliases.put("HATR", HATRAN);
7720 aliases.put("HEBR", HEBREW);
7721 aliases.put("HIRA", HIRAGANA);
7722 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
7723 aliases.put("HMNG", PAHAWH_HMONG);
7724 // it appears we don't have the KATAKANA_OR_HIRAGANA
7725 //aliases.put("HRKT", KATAKANA_OR_HIRAGANA);
7726 aliases.put("HUNG", OLD_HUNGARIAN);
7727 aliases.put("ITAL", OLD_ITALIC);
7728 aliases.put("JAVA", JAVANESE);
7729 aliases.put("KALI", KAYAH_LI);
7730 aliases.put("KANA", KATAKANA);
7731 aliases.put("KHAR", KHAROSHTHI);
7732 aliases.put("KHMR", KHMER);
7733 aliases.put("KHOJ", KHOJKI);
7734 aliases.put("KNDA", KANNADA);
7735 aliases.put("KTHI", KAITHI);
7736 aliases.put("LANA", TAI_THAM);
7737 aliases.put("LAOO", LAO);
7738 aliases.put("LATN", LATIN);
7739 aliases.put("LEPC", LEPCHA);
7740 aliases.put("LIMB", LIMBU);
7741 aliases.put("LINA", LINEAR_A);
7742 aliases.put("LINB", LINEAR_B);
7743 aliases.put("LISU", LISU);
7744 aliases.put("LYCI", LYCIAN);
7745 aliases.put("LYDI", LYDIAN);
7746 aliases.put("MAHJ", MAHAJANI);
7747 aliases.put("MARC", MARCHEN);
7748 aliases.put("MAND", MANDAIC);
7749 aliases.put("MANI", MANICHAEAN);
7750 aliases.put("MEND", MENDE_KIKAKUI);
7751 aliases.put("MERC", MEROITIC_CURSIVE);
7752 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
7753 aliases.put("MLYM", MALAYALAM);
7754 aliases.put("MODI", MODI);
7755 aliases.put("MONG", MONGOLIAN);
7756 aliases.put("MROO", MRO);
7757 aliases.put("MTEI", MEETEI_MAYEK);
7758 aliases.put("MULT", MULTANI);
7759 aliases.put("MYMR", MYANMAR);
7760 aliases.put("NARB", OLD_NORTH_ARABIAN);
7761 aliases.put("NBAT", NABATAEAN);
7762 aliases.put("NEWA", NEWA);
7763 aliases.put("NKOO", NKO);
7764 aliases.put("NSHU", NUSHU);
7765 aliases.put("OGAM", OGHAM);
7766 aliases.put("OLCK", OL_CHIKI);
7767 aliases.put("ORKH", OLD_TURKIC);
7768 aliases.put("ORYA", ORIYA);
7769 aliases.put("OSGE", OSAGE);
7770 aliases.put("OSMA", OSMANYA);
7771 aliases.put("PALM", PALMYRENE);
7772 aliases.put("PAUC", PAU_CIN_HAU);
7773 aliases.put("PERM", OLD_PERMIC);
7774 aliases.put("PHAG", PHAGS_PA);
7775 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
7776 aliases.put("PHLP", PSALTER_PAHLAVI);
7777 aliases.put("PHNX", PHOENICIAN);
7778 aliases.put("PLRD", MIAO);
7779 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
7780 aliases.put("RJNG", REJANG);
7781 aliases.put("RUNR", RUNIC);
7782 aliases.put("SAMR", SAMARITAN);
7783 aliases.put("SARB", OLD_SOUTH_ARABIAN);
7784 aliases.put("SAUR", SAURASHTRA);
7785 aliases.put("SGNW", SIGNWRITING);
7786 aliases.put("SHAW", SHAVIAN);
7787 aliases.put("SHRD", SHARADA);
7788 aliases.put("SIDD", SIDDHAM);
7789 aliases.put("SIND", KHUDAWADI);
7790 aliases.put("SINH", SINHALA);
7791 aliases.put("SORA", SORA_SOMPENG);
7792 aliases.put("SOYO", SOYOMBO);
7793 aliases.put("SUND", SUNDANESE);
7794 aliases.put("SYLO", SYLOTI_NAGRI);
7795 aliases.put("SYRC", SYRIAC);
7796 aliases.put("TAGB", TAGBANWA);
7797 aliases.put("TAKR", TAKRI);
7798 aliases.put("TALE", TAI_LE);
7799 aliases.put("TALU", NEW_TAI_LUE);
7800 aliases.put("TAML", TAMIL);
7801 aliases.put("TANG", TANGUT);
7802 aliases.put("TAVT", TAI_VIET);
7803 aliases.put("TELU", TELUGU);
7804 aliases.put("TFNG", TIFINAGH);
7805 aliases.put("TGLG", TAGALOG);
7806 aliases.put("THAA", THAANA);
7807 aliases.put("THAI", THAI);
7808 aliases.put("TIBT", TIBETAN);
7809 aliases.put("TIRH", TIRHUTA);
7810 aliases.put("UGAR", UGARITIC);
7811 aliases.put("VAII", VAI);
7812 aliases.put("WARA", WARANG_CITI);
7813 aliases.put("XPEO", OLD_PERSIAN);
7814 aliases.put("XSUX", CUNEIFORM);
7815 aliases.put("YIII", YI);
7816 aliases.put("ZANB", ZANABAZAR_SQUARE);
7817 aliases.put("ZINH", INHERITED);
7818 aliases.put("ZYYY", COMMON);
7819 aliases.put("ZZZZ", UNKNOWN);
7820 }
7821
7822 /**
7823 * Returns the enum constant representing the Unicode script of which
7824 * the given character (Unicode code point) is assigned to.
7825 *
7826 * @param codePoint the character (Unicode code point) in question.
7827 * @return The {@code UnicodeScript} constant representing the
7828 * Unicode script of which this character is assigned to.
7829 *
7830 * @throws IllegalArgumentException if the specified
7831 * {@code codePoint} is an invalid Unicode code point.
7832 * @see Character#isValidCodePoint(int)
7833 *
7834 */
7835 public static UnicodeScript of(int codePoint) {
7836 if (!isValidCodePoint(codePoint))
7837 throw new IllegalArgumentException(
7838 String.format("Not a valid Unicode code point: 0x%X", codePoint));
7839 int type = getType(codePoint);
7840 // leave SURROGATE and PRIVATE_USE for table lookup
7841 if (type == UNASSIGNED)
7842 return UNKNOWN;
7843 int index = Arrays.binarySearch(scriptStarts, codePoint);
7844 if (index < 0)
7845 index = -index - 2;
7846 return scripts[index];
7847 }
7848
7849 /**
7850 * Returns the UnicodeScript constant with the given Unicode script
7851 * name or the script name alias. Script names and their aliases are
7852 * determined by The Unicode Standard. The files {@code Scripts<version>.txt}
7853 * and {@code PropertyValueAliases<version>.txt} define script names
7854 * and the script name aliases for a particular version of the
7855 * standard. The {@link Character} class specifies the version of
7856 * the standard that it supports.
7857 * <p>
7858 * Character case is ignored for all of the valid script names.
7859 * The en_US locale's case mapping rules are used to provide
7860 * case-insensitive string comparisons for script name validation.
7861 *
7862 * @param scriptName A {@code UnicodeScript} name.
7863 * @return The {@code UnicodeScript} constant identified
7864 * by {@code scriptName}
7865 * @throws IllegalArgumentException if {@code scriptName} is an
7866 * invalid name
7867 * @throws NullPointerException if {@code scriptName} is null
7868 */
7869 public static final UnicodeScript forName(String scriptName) {
7870 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
7871 //.replace(' ', '_'));
7872 UnicodeScript sc = aliases.get(scriptName);
7873 if (sc != null)
7874 return sc;
7875 return valueOf(scriptName);
7876 }
7877 }
7878
7879 /**
7880 * The value of the {@code Character}.
7881 *
7882 * @serial
7883 */
7884 private final char value;
7885
7886 /** use serialVersionUID from JDK 1.0.2 for interoperability */
7887 private static final long serialVersionUID = 3786198910865385080L;
7888
7889 /**
7890 * Constructs a newly allocated {@code Character} object that
7891 * represents the specified {@code char} value.
7892 *
7893 * @param value the value to be represented by the
7894 * {@code Character} object.
7895 *
7896 * @deprecated
7897 * It is rarely appropriate to use this constructor. The static factory
7898 * {@link #valueOf(char)} is generally a better choice, as it is
7899 * likely to yield significantly better space and time performance.
7900 */
7901 @Deprecated(since="9")
7902 public Character(char value) {
7903 this.value = value;
7904 }
7905
7906 private static class CharacterCache {
7907 private CharacterCache(){}
7908
7909 static final Character cache[] = new Character[127 + 1];
7910
7911 static {
7912 for (int i = 0; i < cache.length; i++)
7913 cache[i] = new Character((char)i);
7914 }
7915 }
7916
7917 /**
7918 * Returns a {@code Character} instance representing the specified
7919 * {@code char} value.
7920 * If a new {@code Character} instance is not required, this method
7921 * should generally be used in preference to the constructor
7922 * {@link #Character(char)}, as this method is likely to yield
7923 * significantly better space and time performance by caching
7924 * frequently requested values.
7925 *
7926 * This method will always cache values in the range {@code
7927 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
7928 * cache other values outside of this range.
7929 *
7930 * @param c a char value.
7931 * @return a {@code Character} instance representing {@code c}.
7932 * @since 1.5
7933 */
7934 @HotSpotIntrinsicCandidate
7935 public static Character valueOf(char c) {
7936 if (c <= 127) { // must cache
7937 return CharacterCache.cache[(int)c];
7938 }
7939 return new Character(c);
7940 }
7941
7942 /**
7943 * Returns the value of this {@code Character} object.
7944 * @return the primitive {@code char} value represented by
7945 * this object.
7946 */
7947 @HotSpotIntrinsicCandidate
7948 public char charValue() {
7949 return value;
7950 }
7951
7952 /**
7953 * Returns a hash code for this {@code Character}; equal to the result
7954 * of invoking {@code charValue()}.
7955 *
7956 * @return a hash code value for this {@code Character}
7957 */
7958 @Override
7959 public int hashCode() {
7960 return Character.hashCode(value);
7961 }
7962
7963 /**
7964 * Returns a hash code for a {@code char} value; compatible with
7965 * {@code Character.hashCode()}.
7966 *
7967 * @since 1.8
7968 *
7969 * @param value The {@code char} for which to return a hash code.
7970 * @return a hash code value for a {@code char} value.
7971 */
7972 public static int hashCode(char value) {
7973 return (int)value;
7974 }
7975
7976 /**
7977 * Compares this object against the specified object.
7978 * The result is {@code true} if and only if the argument is not
7979 * {@code null} and is a {@code Character} object that
7980 * represents the same {@code char} value as this object.
7981 *
7982 * @param obj the object to compare with.
7983 * @return {@code true} if the objects are the same;
7984 * {@code false} otherwise.
7985 */
7986 public boolean equals(Object obj) {
7987 if (obj instanceof Character) {
7988 return value == ((Character)obj).charValue();
7989 }
7990 return false;
7991 }
7992
7993 /**
7994 * Returns a {@code String} object representing this
7995 * {@code Character}'s value. The result is a string of
7996 * length 1 whose sole component is the primitive
7997 * {@code char} value represented by this
7998 * {@code Character} object.
7999 *
8000 * @return a string representation of this object.
8001 */
8002 public String toString() {
8003 char buf[] = {value};
8004 return String.valueOf(buf);
8005 }
8006
8007 /**
8008 * Returns a {@code String} object representing the
8009 * specified {@code char}. The result is a string of length
8010 * 1 consisting solely of the specified {@code char}.
8011 *
8012 * @apiNote This method cannot handle <a
8013 * href="#supplementary"> supplementary characters</a>. To support
8014 * all Unicode characters, including supplementary characters, use
8015 * the {@link #toString(int)} method.
8016 *
8017 * @param c the {@code char} to be converted
8018 * @return the string representation of the specified {@code char}
8019 * @since 1.4
8020 */
8021 public static String toString(char c) {
8022 return String.valueOf(c);
8023 }
8024
8025 /**
8026 * Returns a {@code String} object representing the
8027 * specified character (Unicode code point). The result is a string of
8028 * length 1 or 2, consisting solely of the specified {@code codePoint}.
8029 *
8030 * @param codePoint the {@code codePoint} to be converted
8031 * @return the string representation of the specified {@code codePoint}
8032 * @throws IllegalArgumentException if the specified
8033 * {@code codePoint} is not a {@linkplain #isValidCodePoint
8034 * valid Unicode code point}.
8035 * @since 11
8036 */
8037 public static String toString(int codePoint) {
8038 return String.valueOfCodePoint(codePoint);
8039 }
8040
8041 /**
8042 * Determines whether the specified code point is a valid
8043 * <a href="http://www.unicode.org/glossary/#code_point">
8044 * Unicode code point value</a>.
8045 *
8046 * @param codePoint the Unicode code point to be tested
8047 * @return {@code true} if the specified code point value is between
8048 * {@link #MIN_CODE_POINT} and
8049 * {@link #MAX_CODE_POINT} inclusive;
8050 * {@code false} otherwise.
8051 * @since 1.5
8052 */
8053 public static boolean isValidCodePoint(int codePoint) {
8054 // Optimized form of:
8055 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
8056 int plane = codePoint >>> 16;
8057 return plane < ((MAX_CODE_POINT + 1) >>> 16);
8058 }
8059
8060 /**
8061 * Determines whether the specified character (Unicode code point)
8062 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
8063 * Such code points can be represented using a single {@code char}.
8064 *
8065 * @param codePoint the character (Unicode code point) to be tested
8066 * @return {@code true} if the specified code point is between
8067 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
8068 * {@code false} otherwise.
8069 * @since 1.7
8070 */
8071 public static boolean isBmpCodePoint(int codePoint) {
8072 return codePoint >>> 16 == 0;
8073 // Optimized form of:
8074 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
8075 // We consistently use logical shift (>>>) to facilitate
8076 // additional runtime optimizations.
8077 }
8078
8079 /**
8080 * Determines whether the specified character (Unicode code point)
8081 * is in the <a href="#supplementary">supplementary character</a> range.
8082 *
8083 * @param codePoint the character (Unicode code point) to be tested
8084 * @return {@code true} if the specified code point is between
8085 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
8086 * {@link #MAX_CODE_POINT} inclusive;
8087 * {@code false} otherwise.
8088 * @since 1.5
8089 */
8090 public static boolean isSupplementaryCodePoint(int codePoint) {
8091 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
8092 && codePoint < MAX_CODE_POINT + 1;
8093 }
8094
8095 /**
8096 * Determines if the given {@code char} value is a
8097 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
8098 * Unicode high-surrogate code unit</a>
8099 * (also known as <i>leading-surrogate code unit</i>).
8100 *
8101 * <p>Such values do not represent characters by themselves,
8102 * but are used in the representation of
8103 * <a href="#supplementary">supplementary characters</a>
8104 * in the UTF-16 encoding.
8105 *
8106 * @param ch the {@code char} value to be tested.
8107 * @return {@code true} if the {@code char} value is between
8108 * {@link #MIN_HIGH_SURROGATE} and
8109 * {@link #MAX_HIGH_SURROGATE} inclusive;
8110 * {@code false} otherwise.
8111 * @see Character#isLowSurrogate(char)
8112 * @see Character.UnicodeBlock#of(int)
8113 * @since 1.5
8114 */
8115 public static boolean isHighSurrogate(char ch) {
8116 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
8117 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
8118 }
8119
8120 /**
8121 * Determines if the given {@code char} value is a
8122 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
8123 * Unicode low-surrogate code unit</a>
8124 * (also known as <i>trailing-surrogate code unit</i>).
8125 *
8126 * <p>Such values do not represent characters by themselves,
8127 * but are used in the representation of
8128 * <a href="#supplementary">supplementary characters</a>
8129 * in the UTF-16 encoding.
8130 *
8131 * @param ch the {@code char} value to be tested.
8132 * @return {@code true} if the {@code char} value is between
8133 * {@link #MIN_LOW_SURROGATE} and
8134 * {@link #MAX_LOW_SURROGATE} inclusive;
8135 * {@code false} otherwise.
8136 * @see Character#isHighSurrogate(char)
8137 * @since 1.5
8138 */
8139 public static boolean isLowSurrogate(char ch) {
8140 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
8141 }
8142
8143 /**
8144 * Determines if the given {@code char} value is a Unicode
8145 * <i>surrogate code unit</i>.
8146 *
8147 * <p>Such values do not represent characters by themselves,
8148 * but are used in the representation of
8149 * <a href="#supplementary">supplementary characters</a>
8150 * in the UTF-16 encoding.
8151 *
8152 * <p>A char value is a surrogate code unit if and only if it is either
8153 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
8154 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
8155 *
8156 * @param ch the {@code char} value to be tested.
8157 * @return {@code true} if the {@code char} value is between
8158 * {@link #MIN_SURROGATE} and
8159 * {@link #MAX_SURROGATE} inclusive;
8160 * {@code false} otherwise.
8161 * @since 1.7
8162 */
8163 public static boolean isSurrogate(char ch) {
8164 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
8165 }
8166
8167 /**
8168 * Determines whether the specified pair of {@code char}
8169 * values is a valid
8170 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8171 * Unicode surrogate pair</a>.
8172
8173 * <p>This method is equivalent to the expression:
8174 * <blockquote><pre>{@code
8175 * isHighSurrogate(high) && isLowSurrogate(low)
8176 * }</pre></blockquote>
8177 *
8178 * @param high the high-surrogate code value to be tested
8179 * @param low the low-surrogate code value to be tested
8180 * @return {@code true} if the specified high and
8181 * low-surrogate code values represent a valid surrogate pair;
8182 * {@code false} otherwise.
8183 * @since 1.5
8184 */
8185 public static boolean isSurrogatePair(char high, char low) {
8186 return isHighSurrogate(high) && isLowSurrogate(low);
8187 }
8188
8189 /**
8190 * Determines the number of {@code char} values needed to
8191 * represent the specified character (Unicode code point). If the
8192 * specified character is equal to or greater than 0x10000, then
8193 * the method returns 2. Otherwise, the method returns 1.
8194 *
8195 * <p>This method doesn't validate the specified character to be a
8196 * valid Unicode code point. The caller must validate the
8197 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
8198 * if necessary.
8199 *
8200 * @param codePoint the character (Unicode code point) to be tested.
8201 * @return 2 if the character is a valid supplementary character; 1 otherwise.
8202 * @see Character#isSupplementaryCodePoint(int)
8203 * @since 1.5
8204 */
8205 public static int charCount(int codePoint) {
8206 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
8207 }
8208
8209 /**
8210 * Converts the specified surrogate pair to its supplementary code
8211 * point value. This method does not validate the specified
8212 * surrogate pair. The caller must validate it using {@link
8213 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
8214 *
8215 * @param high the high-surrogate code unit
8216 * @param low the low-surrogate code unit
8217 * @return the supplementary code point composed from the
8218 * specified surrogate pair.
8219 * @since 1.5
8220 */
8221 public static int toCodePoint(char high, char low) {
8222 // Optimized form of:
8223 // return ((high - MIN_HIGH_SURROGATE) << 10)
8224 // + (low - MIN_LOW_SURROGATE)
8225 // + MIN_SUPPLEMENTARY_CODE_POINT;
8226 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
8227 - (MIN_HIGH_SURROGATE << 10)
8228 - MIN_LOW_SURROGATE);
8229 }
8230
8231 /**
8232 * Returns the code point at the given index of the
8233 * {@code CharSequence}. If the {@code char} value at
8234 * the given index in the {@code CharSequence} is in the
8235 * high-surrogate range, the following index is less than the
8236 * length of the {@code CharSequence}, and the
8237 * {@code char} value at the following index is in the
8238 * low-surrogate range, then the supplementary code point
8239 * corresponding to this surrogate pair is returned. Otherwise,
8240 * the {@code char} value at the given index is returned.
8241 *
8242 * @param seq a sequence of {@code char} values (Unicode code
8243 * units)
8244 * @param index the index to the {@code char} values (Unicode
8245 * code units) in {@code seq} to be converted
8246 * @return the Unicode code point at the given index
8247 * @throws NullPointerException if {@code seq} is null.
8248 * @throws IndexOutOfBoundsException if the value
8249 * {@code index} is negative or not less than
8250 * {@link CharSequence#length() seq.length()}.
8251 * @since 1.5
8252 */
8253 public static int codePointAt(CharSequence seq, int index) {
8254 char c1 = seq.charAt(index);
8255 if (isHighSurrogate(c1) && ++index < seq.length()) {
8256 char c2 = seq.charAt(index);
8257 if (isLowSurrogate(c2)) {
8258 return toCodePoint(c1, c2);
8259 }
8260 }
8261 return c1;
8262 }
8263
8264 /**
8265 * Returns the code point at the given index of the
8266 * {@code char} array. If the {@code char} value at
8267 * the given index in the {@code char} array is in the
8268 * high-surrogate range, the following index is less than the
8269 * length of the {@code char} array, and the
8270 * {@code char} value at the following index is in the
8271 * low-surrogate range, then the supplementary code point
8272 * corresponding to this surrogate pair is returned. Otherwise,
8273 * the {@code char} value at the given index is returned.
8274 *
8275 * @param a the {@code char} array
8276 * @param index the index to the {@code char} values (Unicode
8277 * code units) in the {@code char} array to be converted
8278 * @return the Unicode code point at the given index
8279 * @throws NullPointerException if {@code a} is null.
8280 * @throws IndexOutOfBoundsException if the value
8281 * {@code index} is negative or not less than
8282 * the length of the {@code char} array.
8283 * @since 1.5
8284 */
8285 public static int codePointAt(char[] a, int index) {
8286 return codePointAtImpl(a, index, a.length);
8287 }
8288
8289 /**
8290 * Returns the code point at the given index of the
8291 * {@code char} array, where only array elements with
8292 * {@code index} less than {@code limit} can be used. If
8293 * the {@code char} value at the given index in the
8294 * {@code char} array is in the high-surrogate range, the
8295 * following index is less than the {@code limit}, and the
8296 * {@code char} value at the following index is in the
8297 * low-surrogate range, then the supplementary code point
8298 * corresponding to this surrogate pair is returned. Otherwise,
8299 * the {@code char} value at the given index is returned.
8300 *
8301 * @param a the {@code char} array
8302 * @param index the index to the {@code char} values (Unicode
8303 * code units) in the {@code char} array to be converted
8304 * @param limit the index after the last array element that
8305 * can be used in the {@code char} array
8306 * @return the Unicode code point at the given index
8307 * @throws NullPointerException if {@code a} is null.
8308 * @throws IndexOutOfBoundsException if the {@code index}
8309 * argument is negative or not less than the {@code limit}
8310 * argument, or if the {@code limit} argument is negative or
8311 * greater than the length of the {@code char} array.
8312 * @since 1.5
8313 */
8314 public static int codePointAt(char[] a, int index, int limit) {
8315 if (index >= limit || limit < 0 || limit > a.length) {
8316 throw new IndexOutOfBoundsException();
8317 }
8318 return codePointAtImpl(a, index, limit);
8319 }
8320
8321 // throws ArrayIndexOutOfBoundsException if index out of bounds
8322 static int codePointAtImpl(char[] a, int index, int limit) {
8323 char c1 = a[index];
8324 if (isHighSurrogate(c1) && ++index < limit) {
8325 char c2 = a[index];
8326 if (isLowSurrogate(c2)) {
8327 return toCodePoint(c1, c2);
8328 }
8329 }
8330 return c1;
8331 }
8332
8333 /**
8334 * Returns the code point preceding the given index of the
8335 * {@code CharSequence}. If the {@code char} value at
8336 * {@code (index - 1)} in the {@code CharSequence} is in
8337 * the low-surrogate range, {@code (index - 2)} is not
8338 * negative, and the {@code char} value at {@code (index - 2)}
8339 * in the {@code CharSequence} is in the
8340 * high-surrogate range, then the supplementary code point
8341 * corresponding to this surrogate pair is returned. Otherwise,
8342 * the {@code char} value at {@code (index - 1)} is
8343 * returned.
8344 *
8345 * @param seq the {@code CharSequence} instance
8346 * @param index the index following the code point that should be returned
8347 * @return the Unicode code point value before the given index.
8348 * @throws NullPointerException if {@code seq} is null.
8349 * @throws IndexOutOfBoundsException if the {@code index}
8350 * argument is less than 1 or greater than {@link
8351 * CharSequence#length() seq.length()}.
8352 * @since 1.5
8353 */
8354 public static int codePointBefore(CharSequence seq, int index) {
8355 char c2 = seq.charAt(--index);
8356 if (isLowSurrogate(c2) && index > 0) {
8357 char c1 = seq.charAt(--index);
8358 if (isHighSurrogate(c1)) {
8359 return toCodePoint(c1, c2);
8360 }
8361 }
8362 return c2;
8363 }
8364
8365 /**
8366 * Returns the code point preceding the given index of the
8367 * {@code char} array. If the {@code char} value at
8368 * {@code (index - 1)} in the {@code char} array is in
8369 * the low-surrogate range, {@code (index - 2)} is not
8370 * negative, and the {@code char} value at {@code (index - 2)}
8371 * in the {@code char} array is in the
8372 * high-surrogate range, then the supplementary code point
8373 * corresponding to this surrogate pair is returned. Otherwise,
8374 * the {@code char} value at {@code (index - 1)} is
8375 * returned.
8376 *
8377 * @param a the {@code char} array
8378 * @param index the index following the code point that should be returned
8379 * @return the Unicode code point value before the given index.
8380 * @throws NullPointerException if {@code a} is null.
8381 * @throws IndexOutOfBoundsException if the {@code index}
8382 * argument is less than 1 or greater than the length of the
8383 * {@code char} array
8384 * @since 1.5
8385 */
8386 public static int codePointBefore(char[] a, int index) {
8387 return codePointBeforeImpl(a, index, 0);
8388 }
8389
8390 /**
8391 * Returns the code point preceding the given index of the
8392 * {@code char} array, where only array elements with
8393 * {@code index} greater than or equal to {@code start}
8394 * can be used. If the {@code char} value at {@code (index - 1)}
8395 * in the {@code char} array is in the
8396 * low-surrogate range, {@code (index - 2)} is not less than
8397 * {@code start}, and the {@code char} value at
8398 * {@code (index - 2)} in the {@code char} array is in
8399 * the high-surrogate range, then the supplementary code point
8400 * corresponding to this surrogate pair is returned. Otherwise,
8401 * the {@code char} value at {@code (index - 1)} is
8402 * returned.
8403 *
8404 * @param a the {@code char} array
8405 * @param index the index following the code point that should be returned
8406 * @param start the index of the first array element in the
8407 * {@code char} array
8408 * @return the Unicode code point value before the given index.
8409 * @throws NullPointerException if {@code a} is null.
8410 * @throws IndexOutOfBoundsException if the {@code index}
8411 * argument is not greater than the {@code start} argument or
8412 * is greater than the length of the {@code char} array, or
8413 * if the {@code start} argument is negative or not less than
8414 * the length of the {@code char} array.
8415 * @since 1.5
8416 */
8417 public static int codePointBefore(char[] a, int index, int start) {
8418 if (index <= start || start < 0 || start >= a.length) {
8419 throw new IndexOutOfBoundsException();
8420 }
8421 return codePointBeforeImpl(a, index, start);
8422 }
8423
8424 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
8425 static int codePointBeforeImpl(char[] a, int index, int start) {
8426 char c2 = a[--index];
8427 if (isLowSurrogate(c2) && index > start) {
8428 char c1 = a[--index];
8429 if (isHighSurrogate(c1)) {
8430 return toCodePoint(c1, c2);
8431 }
8432 }
8433 return c2;
8434 }
8435
8436 /**
8437 * Returns the leading surrogate (a
8438 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
8439 * high surrogate code unit</a>) of the
8440 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8441 * surrogate pair</a>
8442 * representing the specified supplementary character (Unicode
8443 * code point) in the UTF-16 encoding. If the specified character
8444 * is not a
8445 * <a href="Character.html#supplementary">supplementary character</a>,
8446 * an unspecified {@code char} is returned.
8447 *
8448 * <p>If
8449 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
8450 * is {@code true}, then
8451 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
8452 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
8453 * are also always {@code true}.
8454 *
8455 * @param codePoint a supplementary character (Unicode code point)
8456 * @return the leading surrogate code unit used to represent the
8457 * character in the UTF-16 encoding
8458 * @since 1.7
8459 */
8460 public static char highSurrogate(int codePoint) {
8461 return (char) ((codePoint >>> 10)
8462 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
8463 }
8464
8465 /**
8466 * Returns the trailing surrogate (a
8467 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
8468 * low surrogate code unit</a>) of the
8469 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8470 * surrogate pair</a>
8471 * representing the specified supplementary character (Unicode
8472 * code point) in the UTF-16 encoding. If the specified character
8473 * is not a
8474 * <a href="Character.html#supplementary">supplementary character</a>,
8475 * an unspecified {@code char} is returned.
8476 *
8477 * <p>If
8478 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
8479 * is {@code true}, then
8480 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
8481 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
8482 * are also always {@code true}.
8483 *
8484 * @param codePoint a supplementary character (Unicode code point)
8485 * @return the trailing surrogate code unit used to represent the
8486 * character in the UTF-16 encoding
8487 * @since 1.7
8488 */
8489 public static char lowSurrogate(int codePoint) {
8490 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
8491 }
8492
8493 /**
8494 * Converts the specified character (Unicode code point) to its
8495 * UTF-16 representation. If the specified code point is a BMP
8496 * (Basic Multilingual Plane or Plane 0) value, the same value is
8497 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
8498 * specified code point is a supplementary character, its
8499 * surrogate values are stored in {@code dst[dstIndex]}
8500 * (high-surrogate) and {@code dst[dstIndex+1]}
8501 * (low-surrogate), and 2 is returned.
8502 *
8503 * @param codePoint the character (Unicode code point) to be converted.
8504 * @param dst an array of {@code char} in which the
8505 * {@code codePoint}'s UTF-16 value is stored.
8506 * @param dstIndex the start index into the {@code dst}
8507 * array where the converted value is stored.
8508 * @return 1 if the code point is a BMP code point, 2 if the
8509 * code point is a supplementary code point.
8510 * @throws IllegalArgumentException if the specified
8511 * {@code codePoint} is not a valid Unicode code point.
8512 * @throws NullPointerException if the specified {@code dst} is null.
8513 * @throws IndexOutOfBoundsException if {@code dstIndex}
8514 * is negative or not less than {@code dst.length}, or if
8515 * {@code dst} at {@code dstIndex} doesn't have enough
8516 * array element(s) to store the resulting {@code char}
8517 * value(s). (If {@code dstIndex} is equal to
8518 * {@code dst.length-1} and the specified
8519 * {@code codePoint} is a supplementary character, the
8520 * high-surrogate value is not stored in
8521 * {@code dst[dstIndex]}.)
8522 * @since 1.5
8523 */
8524 public static int toChars(int codePoint, char[] dst, int dstIndex) {
8525 if (isBmpCodePoint(codePoint)) {
8526 dst[dstIndex] = (char) codePoint;
8527 return 1;
8528 } else if (isValidCodePoint(codePoint)) {
8529 toSurrogates(codePoint, dst, dstIndex);
8530 return 2;
8531 } else {
8532 throw new IllegalArgumentException(
8533 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8534 }
8535 }
8536
8537 /**
8538 * Converts the specified character (Unicode code point) to its
8539 * UTF-16 representation stored in a {@code char} array. If
8540 * the specified code point is a BMP (Basic Multilingual Plane or
8541 * Plane 0) value, the resulting {@code char} array has
8542 * the same value as {@code codePoint}. If the specified code
8543 * point is a supplementary code point, the resulting
8544 * {@code char} array has the corresponding surrogate pair.
8545 *
8546 * @param codePoint a Unicode code point
8547 * @return a {@code char} array having
8548 * {@code codePoint}'s UTF-16 representation.
8549 * @throws IllegalArgumentException if the specified
8550 * {@code codePoint} is not a valid Unicode code point.
8551 * @since 1.5
8552 */
8553 public static char[] toChars(int codePoint) {
8554 if (isBmpCodePoint(codePoint)) {
8555 return new char[] { (char) codePoint };
8556 } else if (isValidCodePoint(codePoint)) {
8557 char[] result = new char[2];
8558 toSurrogates(codePoint, result, 0);
8559 return result;
8560 } else {
8561 throw new IllegalArgumentException(
8562 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8563 }
8564 }
8565
8566 static void toSurrogates(int codePoint, char[] dst, int index) {
8567 // We write elements "backwards" to guarantee all-or-nothing
8568 dst[index+1] = lowSurrogate(codePoint);
8569 dst[index] = highSurrogate(codePoint);
8570 }
8571
8572 /**
8573 * Returns the number of Unicode code points in the text range of
8574 * the specified char sequence. The text range begins at the
8575 * specified {@code beginIndex} and extends to the
8576 * {@code char} at index {@code endIndex - 1}. Thus the
8577 * length (in {@code char}s) of the text range is
8578 * {@code endIndex-beginIndex}. Unpaired surrogates within
8579 * the text range count as one code point each.
8580 *
8581 * @param seq the char sequence
8582 * @param beginIndex the index to the first {@code char} of
8583 * the text range.
8584 * @param endIndex the index after the last {@code char} of
8585 * the text range.
8586 * @return the number of Unicode code points in the specified text
8587 * range
8588 * @throws NullPointerException if {@code seq} is null.
8589 * @throws IndexOutOfBoundsException if the
8590 * {@code beginIndex} is negative, or {@code endIndex}
8591 * is larger than the length of the given sequence, or
8592 * {@code beginIndex} is larger than {@code endIndex}.
8593 * @since 1.5
8594 */
8595 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
8596 int length = seq.length();
8597 if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) {
8598 throw new IndexOutOfBoundsException();
8599 }
8600 int n = endIndex - beginIndex;
8601 for (int i = beginIndex; i < endIndex; ) {
8602 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
8603 isLowSurrogate(seq.charAt(i))) {
8604 n--;
8605 i++;
8606 }
8607 }
8608 return n;
8609 }
8610
8611 /**
8612 * Returns the number of Unicode code points in a subarray of the
8613 * {@code char} array argument. The {@code offset}
8614 * argument is the index of the first {@code char} of the
8615 * subarray and the {@code count} argument specifies the
8616 * length of the subarray in {@code char}s. Unpaired
8617 * surrogates within the subarray count as one code point each.
8618 *
8619 * @param a the {@code char} array
8620 * @param offset the index of the first {@code char} in the
8621 * given {@code char} array
8622 * @param count the length of the subarray in {@code char}s
8623 * @return the number of Unicode code points in the specified subarray
8624 * @throws NullPointerException if {@code a} is null.
8625 * @throws IndexOutOfBoundsException if {@code offset} or
8626 * {@code count} is negative, or if {@code offset +
8627 * count} is larger than the length of the given array.
8628 * @since 1.5
8629 */
8630 public static int codePointCount(char[] a, int offset, int count) {
8631 if (count > a.length - offset || offset < 0 || count < 0) {
8632 throw new IndexOutOfBoundsException();
8633 }
8634 return codePointCountImpl(a, offset, count);
8635 }
8636
8637 static int codePointCountImpl(char[] a, int offset, int count) {
8638 int endIndex = offset + count;
8639 int n = count;
8640 for (int i = offset; i < endIndex; ) {
8641 if (isHighSurrogate(a[i++]) && i < endIndex &&
8642 isLowSurrogate(a[i])) {
8643 n--;
8644 i++;
8645 }
8646 }
8647 return n;
8648 }
8649
8650 /**
8651 * Returns the index within the given char sequence that is offset
8652 * from the given {@code index} by {@code codePointOffset}
8653 * code points. Unpaired surrogates within the text range given by
8654 * {@code index} and {@code codePointOffset} count as
8655 * one code point each.
8656 *
8657 * @param seq the char sequence
8658 * @param index the index to be offset
8659 * @param codePointOffset the offset in code points
8660 * @return the index within the char sequence
8661 * @throws NullPointerException if {@code seq} is null.
8662 * @throws IndexOutOfBoundsException if {@code index}
8663 * is negative or larger then the length of the char sequence,
8664 * or if {@code codePointOffset} is positive and the
8665 * subsequence starting with {@code index} has fewer than
8666 * {@code codePointOffset} code points, or if
8667 * {@code codePointOffset} is negative and the subsequence
8668 * before {@code index} has fewer than the absolute value
8669 * of {@code codePointOffset} code points.
8670 * @since 1.5
8671 */
8672 public static int offsetByCodePoints(CharSequence seq, int index,
8673 int codePointOffset) {
8674 int length = seq.length();
8675 if (index < 0 || index > length) {
8676 throw new IndexOutOfBoundsException();
8677 }
8678
8679 int x = index;
8680 if (codePointOffset >= 0) {
8681 int i;
8682 for (i = 0; x < length && i < codePointOffset; i++) {
8683 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
8684 isLowSurrogate(seq.charAt(x))) {
8685 x++;
8686 }
8687 }
8688 if (i < codePointOffset) {
8689 throw new IndexOutOfBoundsException();
8690 }
8691 } else {
8692 int i;
8693 for (i = codePointOffset; x > 0 && i < 0; i++) {
8694 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
8695 isHighSurrogate(seq.charAt(x-1))) {
8696 x--;
8697 }
8698 }
8699 if (i < 0) {
8700 throw new IndexOutOfBoundsException();
8701 }
8702 }
8703 return x;
8704 }
8705
8706 /**
8707 * Returns the index within the given {@code char} subarray
8708 * that is offset from the given {@code index} by
8709 * {@code codePointOffset} code points. The
8710 * {@code start} and {@code count} arguments specify a
8711 * subarray of the {@code char} array. Unpaired surrogates
8712 * within the text range given by {@code index} and
8713 * {@code codePointOffset} count as one code point each.
8714 *
8715 * @param a the {@code char} array
8716 * @param start the index of the first {@code char} of the
8717 * subarray
8718 * @param count the length of the subarray in {@code char}s
8719 * @param index the index to be offset
8720 * @param codePointOffset the offset in code points
8721 * @return the index within the subarray
8722 * @throws NullPointerException if {@code a} is null.
8723 * @throws IndexOutOfBoundsException
8724 * if {@code start} or {@code count} is negative,
8725 * or if {@code start + count} is larger than the length of
8726 * the given array,
8727 * or if {@code index} is less than {@code start} or
8728 * larger then {@code start + count},
8729 * or if {@code codePointOffset} is positive and the text range
8730 * starting with {@code index} and ending with {@code start + count - 1}
8731 * has fewer than {@code codePointOffset} code
8732 * points,
8733 * or if {@code codePointOffset} is negative and the text range
8734 * starting with {@code start} and ending with {@code index - 1}
8735 * has fewer than the absolute value of
8736 * {@code codePointOffset} code points.
8737 * @since 1.5
8738 */
8739 public static int offsetByCodePoints(char[] a, int start, int count,
8740 int index, int codePointOffset) {
8741 if (count > a.length-start || start < 0 || count < 0
8742 || index < start || index > start+count) {
8743 throw new IndexOutOfBoundsException();
8744 }
8745 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
8746 }
8747
8748 static int offsetByCodePointsImpl(char[]a, int start, int count,
8749 int index, int codePointOffset) {
8750 int x = index;
8751 if (codePointOffset >= 0) {
8752 int limit = start + count;
8753 int i;
8754 for (i = 0; x < limit && i < codePointOffset; i++) {
8755 if (isHighSurrogate(a[x++]) && x < limit &&
8756 isLowSurrogate(a[x])) {
8757 x++;
8758 }
8759 }
8760 if (i < codePointOffset) {
8761 throw new IndexOutOfBoundsException();
8762 }
8763 } else {
8764 int i;
8765 for (i = codePointOffset; x > start && i < 0; i++) {
8766 if (isLowSurrogate(a[--x]) && x > start &&
8767 isHighSurrogate(a[x-1])) {
8768 x--;
8769 }
8770 }
8771 if (i < 0) {
8772 throw new IndexOutOfBoundsException();
8773 }
8774 }
8775 return x;
8776 }
8777
8778 /**
8779 * Determines if the specified character is a lowercase character.
8780 * <p>
8781 * A character is lowercase if its general category type, provided
8782 * by {@code Character.getType(ch)}, is
8783 * {@code LOWERCASE_LETTER}, or it has contributory property
8784 * Other_Lowercase as defined by the Unicode Standard.
8785 * <p>
8786 * The following are examples of lowercase characters:
8787 * <blockquote><pre>
8788 * 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
8789 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
8790 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
8791 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
8792 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
8793 * </pre></blockquote>
8794 * <p> Many other Unicode characters are lowercase too.
8795 *
8796 * <p><b>Note:</b> This method cannot handle <a
8797 * href="#supplementary"> supplementary characters</a>. To support
8798 * all Unicode characters, including supplementary characters, use
8799 * the {@link #isLowerCase(int)} method.
8800 *
8801 * @param ch the character to be tested.
8802 * @return {@code true} if the character is lowercase;
8803 * {@code false} otherwise.
8804 * @see Character#isLowerCase(char)
8805 * @see Character#isTitleCase(char)
8806 * @see Character#toLowerCase(char)
8807 * @see Character#getType(char)
8808 */
8809 public static boolean isLowerCase(char ch) {
8810 return isLowerCase((int)ch);
8811 }
8812
8813 /**
8814 * Determines if the specified character (Unicode code point) is a
8815 * lowercase character.
8816 * <p>
8817 * A character is lowercase if its general category type, provided
8818 * by {@link Character#getType getType(codePoint)}, is
8819 * {@code LOWERCASE_LETTER}, or it has contributory property
8820 * Other_Lowercase as defined by the Unicode Standard.
8821 * <p>
8822 * The following are examples of lowercase characters:
8823 * <blockquote><pre>
8824 * 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
8825 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
8826 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
8827 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
8828 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
8829 * </pre></blockquote>
8830 * <p> Many other Unicode characters are lowercase too.
8831 *
8832 * @param codePoint the character (Unicode code point) to be tested.
8833 * @return {@code true} if the character is lowercase;
8834 * {@code false} otherwise.
8835 * @see Character#isLowerCase(int)
8836 * @see Character#isTitleCase(int)
8837 * @see Character#toLowerCase(int)
8838 * @see Character#getType(int)
8839 * @since 1.5
8840 */
8841 public static boolean isLowerCase(int codePoint) {
8842 return getType(codePoint) == Character.LOWERCASE_LETTER ||
8843 CharacterData.of(codePoint).isOtherLowercase(codePoint);
8844 }
8845
8846 /**
8847 * Determines if the specified character is an uppercase character.
8848 * <p>
8849 * A character is uppercase if its general category type, provided by
8850 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
8851 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
8852 * <p>
8853 * The following are examples of uppercase characters:
8854 * <blockquote><pre>
8855 * 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
8856 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
8857 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
8858 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
8859 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
8860 * </pre></blockquote>
8861 * <p> Many other Unicode characters are uppercase too.
8862 *
8863 * <p><b>Note:</b> This method cannot handle <a
8864 * href="#supplementary"> supplementary characters</a>. To support
8865 * all Unicode characters, including supplementary characters, use
8866 * the {@link #isUpperCase(int)} method.
8867 *
8868 * @param ch the character to be tested.
8869 * @return {@code true} if the character is uppercase;
8870 * {@code false} otherwise.
8871 * @see Character#isLowerCase(char)
8872 * @see Character#isTitleCase(char)
8873 * @see Character#toUpperCase(char)
8874 * @see Character#getType(char)
8875 * @since 1.0
8876 */
8877 public static boolean isUpperCase(char ch) {
8878 return isUpperCase((int)ch);
8879 }
8880
8881 /**
8882 * Determines if the specified character (Unicode code point) is an uppercase character.
8883 * <p>
8884 * A character is uppercase if its general category type, provided by
8885 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
8886 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
8887 * <p>
8888 * The following are examples of uppercase characters:
8889 * <blockquote><pre>
8890 * 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
8891 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
8892 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
8893 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
8894 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
8895 * </pre></blockquote>
8896 * <p> Many other Unicode characters are uppercase too.
8897 *
8898 * @param codePoint the character (Unicode code point) to be tested.
8899 * @return {@code true} if the character is uppercase;
8900 * {@code false} otherwise.
8901 * @see Character#isLowerCase(int)
8902 * @see Character#isTitleCase(int)
8903 * @see Character#toUpperCase(int)
8904 * @see Character#getType(int)
8905 * @since 1.5
8906 */
8907 public static boolean isUpperCase(int codePoint) {
8908 return getType(codePoint) == Character.UPPERCASE_LETTER ||
8909 CharacterData.of(codePoint).isOtherUppercase(codePoint);
8910 }
8911
8912 /**
8913 * Determines if the specified character is a titlecase character.
8914 * <p>
8915 * A character is a titlecase character if its general
8916 * category type, provided by {@code Character.getType(ch)},
8917 * is {@code TITLECASE_LETTER}.
8918 * <p>
8919 * Some characters look like pairs of Latin letters. For example, there
8920 * is an uppercase letter that looks like "LJ" and has a corresponding
8921 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
8922 * is the appropriate form to use when rendering a word in lowercase
8923 * with initial capitals, as for a book title.
8924 * <p>
8925 * These are some of the Unicode characters for which this method returns
8926 * {@code true}:
8927 * <ul>
8928 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
8929 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
8930 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
8931 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
8932 * </ul>
8933 * <p> Many other Unicode characters are titlecase too.
8934 *
8935 * <p><b>Note:</b> This method cannot handle <a
8936 * href="#supplementary"> supplementary characters</a>. To support
8937 * all Unicode characters, including supplementary characters, use
8938 * the {@link #isTitleCase(int)} method.
8939 *
8940 * @param ch the character to be tested.
8941 * @return {@code true} if the character is titlecase;
8942 * {@code false} otherwise.
8943 * @see Character#isLowerCase(char)
8944 * @see Character#isUpperCase(char)
8945 * @see Character#toTitleCase(char)
8946 * @see Character#getType(char)
8947 * @since 1.0.2
8948 */
8949 public static boolean isTitleCase(char ch) {
8950 return isTitleCase((int)ch);
8951 }
8952
8953 /**
8954 * Determines if the specified character (Unicode code point) is a titlecase character.
8955 * <p>
8956 * A character is a titlecase character if its general
8957 * category type, provided by {@link Character#getType(int) getType(codePoint)},
8958 * is {@code TITLECASE_LETTER}.
8959 * <p>
8960 * Some characters look like pairs of Latin letters. For example, there
8961 * is an uppercase letter that looks like "LJ" and has a corresponding
8962 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
8963 * is the appropriate form to use when rendering a word in lowercase
8964 * with initial capitals, as for a book title.
8965 * <p>
8966 * These are some of the Unicode characters for which this method returns
8967 * {@code true}:
8968 * <ul>
8969 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
8970 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
8971 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
8972 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
8973 * </ul>
8974 * <p> Many other Unicode characters are titlecase too.
8975 *
8976 * @param codePoint the character (Unicode code point) to be tested.
8977 * @return {@code true} if the character is titlecase;
8978 * {@code false} otherwise.
8979 * @see Character#isLowerCase(int)
8980 * @see Character#isUpperCase(int)
8981 * @see Character#toTitleCase(int)
8982 * @see Character#getType(int)
8983 * @since 1.5
8984 */
8985 public static boolean isTitleCase(int codePoint) {
8986 return getType(codePoint) == Character.TITLECASE_LETTER;
8987 }
8988
8989 /**
8990 * Determines if the specified character is a digit.
8991 * <p>
8992 * A character is a digit if its general category type, provided
8993 * by {@code Character.getType(ch)}, is
8994 * {@code DECIMAL_DIGIT_NUMBER}.
8995 * <p>
8996 * Some Unicode character ranges that contain digits:
8997 * <ul>
8998 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
8999 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
9000 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
9001 * Arabic-Indic digits
9002 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
9003 * Extended Arabic-Indic digits
9004 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
9005 * Devanagari digits
9006 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
9007 * Fullwidth digits
9008 * </ul>
9009 *
9010 * Many other character ranges contain digits as well.
9011 *
9012 * <p><b>Note:</b> This method cannot handle <a
9013 * href="#supplementary"> supplementary characters</a>. To support
9014 * all Unicode characters, including supplementary characters, use
9015 * the {@link #isDigit(int)} method.
9016 *
9017 * @param ch the character to be tested.
9018 * @return {@code true} if the character is a digit;
9019 * {@code false} otherwise.
9020 * @see Character#digit(char, int)
9021 * @see Character#forDigit(int, int)
9022 * @see Character#getType(char)
9023 */
9024 public static boolean isDigit(char ch) {
9025 return isDigit((int)ch);
9026 }
9027
9028 /**
9029 * Determines if the specified character (Unicode code point) is a digit.
9030 * <p>
9031 * A character is a digit if its general category type, provided
9032 * by {@link Character#getType(int) getType(codePoint)}, is
9033 * {@code DECIMAL_DIGIT_NUMBER}.
9034 * <p>
9035 * Some Unicode character ranges that contain digits:
9036 * <ul>
9037 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
9038 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
9039 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
9040 * Arabic-Indic digits
9041 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
9042 * Extended Arabic-Indic digits
9043 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
9044 * Devanagari digits
9045 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
9046 * Fullwidth digits
9047 * </ul>
9048 *
9049 * Many other character ranges contain digits as well.
9050 *
9051 * @param codePoint the character (Unicode code point) to be tested.
9052 * @return {@code true} if the character is a digit;
9053 * {@code false} otherwise.
9054 * @see Character#forDigit(int, int)
9055 * @see Character#getType(int)
9056 * @since 1.5
9057 */
9058 public static boolean isDigit(int codePoint) {
9059 return getType(codePoint) == Character.DECIMAL_DIGIT_NUMBER;
9060 }
9061
9062 /**
9063 * Determines if a character is defined in Unicode.
9064 * <p>
9065 * A character is defined if at least one of the following is true:
9066 * <ul>
9067 * <li>It has an entry in the UnicodeData file.
9068 * <li>It has a value in a range defined by the UnicodeData file.
9069 * </ul>
9070 *
9071 * <p><b>Note:</b> This method cannot handle <a
9072 * href="#supplementary"> supplementary characters</a>. To support
9073 * all Unicode characters, including supplementary characters, use
9074 * the {@link #isDefined(int)} method.
9075 *
9076 * @param ch the character to be tested
9077 * @return {@code true} if the character has a defined meaning
9078 * in Unicode; {@code false} otherwise.
9079 * @see Character#isDigit(char)
9080 * @see Character#isLetter(char)
9081 * @see Character#isLetterOrDigit(char)
9082 * @see Character#isLowerCase(char)
9083 * @see Character#isTitleCase(char)
9084 * @see Character#isUpperCase(char)
9085 * @since 1.0.2
9086 */
9087 public static boolean isDefined(char ch) {
9088 return isDefined((int)ch);
9089 }
9090
9091 /**
9092 * Determines if a character (Unicode code point) is defined in Unicode.
9093 * <p>
9094 * A character is defined if at least one of the following is true:
9095 * <ul>
9096 * <li>It has an entry in the UnicodeData file.
9097 * <li>It has a value in a range defined by the UnicodeData file.
9098 * </ul>
9099 *
9100 * @param codePoint the character (Unicode code point) to be tested.
9101 * @return {@code true} if the character has a defined meaning
9102 * in Unicode; {@code false} otherwise.
9103 * @see Character#isDigit(int)
9104 * @see Character#isLetter(int)
9105 * @see Character#isLetterOrDigit(int)
9106 * @see Character#isLowerCase(int)
9107 * @see Character#isTitleCase(int)
9108 * @see Character#isUpperCase(int)
9109 * @since 1.5
9110 */
9111 public static boolean isDefined(int codePoint) {
9112 return getType(codePoint) != Character.UNASSIGNED;
9113 }
9114
9115 /**
9116 * Determines if the specified character is a letter.
9117 * <p>
9118 * A character is considered to be a letter if its general
9119 * category type, provided by {@code Character.getType(ch)},
9120 * is any of the following:
9121 * <ul>
9122 * <li> {@code UPPERCASE_LETTER}
9123 * <li> {@code LOWERCASE_LETTER}
9124 * <li> {@code TITLECASE_LETTER}
9125 * <li> {@code MODIFIER_LETTER}
9126 * <li> {@code OTHER_LETTER}
9127 * </ul>
9128 *
9129 * Not all letters have case. Many characters are
9130 * letters but are neither uppercase nor lowercase nor titlecase.
9131 *
9132 * <p><b>Note:</b> This method cannot handle <a
9133 * href="#supplementary"> supplementary characters</a>. To support
9134 * all Unicode characters, including supplementary characters, use
9135 * the {@link #isLetter(int)} method.
9136 *
9137 * @param ch the character to be tested.
9138 * @return {@code true} if the character is a letter;
9139 * {@code false} otherwise.
9140 * @see Character#isDigit(char)
9141 * @see Character#isJavaIdentifierStart(char)
9142 * @see Character#isJavaLetter(char)
9143 * @see Character#isJavaLetterOrDigit(char)
9144 * @see Character#isLetterOrDigit(char)
9145 * @see Character#isLowerCase(char)
9146 * @see Character#isTitleCase(char)
9147 * @see Character#isUnicodeIdentifierStart(char)
9148 * @see Character#isUpperCase(char)
9149 */
9150 public static boolean isLetter(char ch) {
9151 return isLetter((int)ch);
9152 }
9153
9154 /**
9155 * Determines if the specified character (Unicode code point) is a letter.
9156 * <p>
9157 * A character is considered to be a letter if its general
9158 * category type, provided by {@link Character#getType(int) getType(codePoint)},
9159 * is any of the following:
9160 * <ul>
9161 * <li> {@code UPPERCASE_LETTER}
9162 * <li> {@code LOWERCASE_LETTER}
9163 * <li> {@code TITLECASE_LETTER}
9164 * <li> {@code MODIFIER_LETTER}
9165 * <li> {@code OTHER_LETTER}
9166 * </ul>
9167 *
9168 * Not all letters have case. Many characters are
9169 * letters but are neither uppercase nor lowercase nor titlecase.
9170 *
9171 * @param codePoint the character (Unicode code point) to be tested.
9172 * @return {@code true} if the character is a letter;
9173 * {@code false} otherwise.
9174 * @see Character#isDigit(int)
9175 * @see Character#isJavaIdentifierStart(int)
9176 * @see Character#isLetterOrDigit(int)
9177 * @see Character#isLowerCase(int)
9178 * @see Character#isTitleCase(int)
9179 * @see Character#isUnicodeIdentifierStart(int)
9180 * @see Character#isUpperCase(int)
9181 * @since 1.5
9182 */
9183 public static boolean isLetter(int codePoint) {
9184 return ((((1 << Character.UPPERCASE_LETTER) |
9185 (1 << Character.LOWERCASE_LETTER) |
9186 (1 << Character.TITLECASE_LETTER) |
9187 (1 << Character.MODIFIER_LETTER) |
9188 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
9189 != 0;
9190 }
9191
9192 /**
9193 * Determines if the specified character is a letter or digit.
9194 * <p>
9195 * A character is considered to be a letter or digit if either
9196 * {@code Character.isLetter(char ch)} or
9197 * {@code Character.isDigit(char ch)} returns
9198 * {@code true} for the character.
9199 *
9200 * <p><b>Note:</b> This method cannot handle <a
9201 * href="#supplementary"> supplementary characters</a>. To support
9202 * all Unicode characters, including supplementary characters, use
9203 * the {@link #isLetterOrDigit(int)} method.
9204 *
9205 * @param ch the character to be tested.
9206 * @return {@code true} if the character is a letter or digit;
9207 * {@code false} otherwise.
9208 * @see Character#isDigit(char)
9209 * @see Character#isJavaIdentifierPart(char)
9210 * @see Character#isJavaLetter(char)
9211 * @see Character#isJavaLetterOrDigit(char)
9212 * @see Character#isLetter(char)
9213 * @see Character#isUnicodeIdentifierPart(char)
9214 * @since 1.0.2
9215 */
9216 public static boolean isLetterOrDigit(char ch) {
9217 return isLetterOrDigit((int)ch);
9218 }
9219
9220 /**
9221 * Determines if the specified character (Unicode code point) is a letter or digit.
9222 * <p>
9223 * A character is considered to be a letter or digit if either
9224 * {@link #isLetter(int) isLetter(codePoint)} or
9225 * {@link #isDigit(int) isDigit(codePoint)} returns
9226 * {@code true} for the character.
9227 *
9228 * @param codePoint the character (Unicode code point) to be tested.
9229 * @return {@code true} if the character is a letter or digit;
9230 * {@code false} otherwise.
9231 * @see Character#isDigit(int)
9232 * @see Character#isJavaIdentifierPart(int)
9233 * @see Character#isLetter(int)
9234 * @see Character#isUnicodeIdentifierPart(int)
9235 * @since 1.5
9236 */
9237 public static boolean isLetterOrDigit(int codePoint) {
9238 return ((((1 << Character.UPPERCASE_LETTER) |
9239 (1 << Character.LOWERCASE_LETTER) |
9240 (1 << Character.TITLECASE_LETTER) |
9241 (1 << Character.MODIFIER_LETTER) |
9242 (1 << Character.OTHER_LETTER) |
9243 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
9244 != 0;
9245 }
9246
9247 /**
9248 * Determines if the specified character is permissible as the first
9249 * character in a Java identifier.
9250 * <p>
9251 * A character may start a Java identifier if and only if
9252 * one of the following is true:
9253 * <ul>
9254 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9255 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
9256 * <li> {@code ch} is a currency symbol (such as {@code '$'})
9257 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
9258 * </ul>
9259 *
9260 * @param ch the character to be tested.
9261 * @return {@code true} if the character may start a Java
9262 * identifier; {@code false} otherwise.
9263 * @see Character#isJavaLetterOrDigit(char)
9264 * @see Character#isJavaIdentifierStart(char)
9265 * @see Character#isJavaIdentifierPart(char)
9266 * @see Character#isLetter(char)
9267 * @see Character#isLetterOrDigit(char)
9268 * @see Character#isUnicodeIdentifierStart(char)
9269 * @since 1.0.2
9270 * @deprecated Replaced by isJavaIdentifierStart(char).
9271 */
9272 @Deprecated(since="1.1")
9273 public static boolean isJavaLetter(char ch) {
9274 return isJavaIdentifierStart(ch);
9275 }
9276
9277 /**
9278 * Determines if the specified character may be part of a Java
9279 * identifier as other than the first character.
9280 * <p>
9281 * A character may be part of a Java identifier if and only if any
9282 * of the following are true:
9283 * <ul>
9284 * <li> it is a letter
9285 * <li> it is a currency symbol (such as {@code '$'})
9286 * <li> it is a connecting punctuation character (such as {@code '_'})
9287 * <li> it is a digit
9288 * <li> it is a numeric letter (such as a Roman numeral character)
9289 * <li> it is a combining mark
9290 * <li> it is a non-spacing mark
9291 * <li> {@code isIdentifierIgnorable} returns
9292 * {@code true} for the character.
9293 * </ul>
9294 *
9295 * @param ch the character to be tested.
9296 * @return {@code true} if the character may be part of a
9297 * Java identifier; {@code false} otherwise.
9298 * @see Character#isJavaLetter(char)
9299 * @see Character#isJavaIdentifierStart(char)
9300 * @see Character#isJavaIdentifierPart(char)
9301 * @see Character#isLetter(char)
9302 * @see Character#isLetterOrDigit(char)
9303 * @see Character#isUnicodeIdentifierPart(char)
9304 * @see Character#isIdentifierIgnorable(char)
9305 * @since 1.0.2
9306 * @deprecated Replaced by isJavaIdentifierPart(char).
9307 */
9308 @Deprecated(since="1.1")
9309 public static boolean isJavaLetterOrDigit(char ch) {
9310 return isJavaIdentifierPart(ch);
9311 }
9312
9313 /**
9314 * Determines if the specified character (Unicode code point) is an alphabet.
9315 * <p>
9316 * A character is considered to be alphabetic if its general category type,
9317 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
9318 * the following:
9319 * <ul>
9320 * <li> {@code UPPERCASE_LETTER}
9321 * <li> {@code LOWERCASE_LETTER}
9322 * <li> {@code TITLECASE_LETTER}
9323 * <li> {@code MODIFIER_LETTER}
9324 * <li> {@code OTHER_LETTER}
9325 * <li> {@code LETTER_NUMBER}
9326 * </ul>
9327 * or it has contributory property Other_Alphabetic as defined by the
9328 * Unicode Standard.
9329 *
9330 * @param codePoint the character (Unicode code point) to be tested.
9331 * @return {@code true} if the character is a Unicode alphabet
9332 * character, {@code false} otherwise.
9333 * @since 1.7
9334 */
9335 public static boolean isAlphabetic(int codePoint) {
9336 return (((((1 << Character.UPPERCASE_LETTER) |
9337 (1 << Character.LOWERCASE_LETTER) |
9338 (1 << Character.TITLECASE_LETTER) |
9339 (1 << Character.MODIFIER_LETTER) |
9340 (1 << Character.OTHER_LETTER) |
9341 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
9342 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
9343 }
9344
9345 /**
9346 * Determines if the specified character (Unicode code point) is a CJKV
9347 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
9348 * the Unicode Standard.
9349 *
9350 * @param codePoint the character (Unicode code point) to be tested.
9351 * @return {@code true} if the character is a Unicode ideograph
9352 * character, {@code false} otherwise.
9353 * @since 1.7
9354 */
9355 public static boolean isIdeographic(int codePoint) {
9356 return CharacterData.of(codePoint).isIdeographic(codePoint);
9357 }
9358
9359 /**
9360 * Determines if the specified character is
9361 * permissible as the first character in a Java identifier.
9362 * <p>
9363 * A character may start a Java identifier if and only if
9364 * one of the following conditions is true:
9365 * <ul>
9366 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9367 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
9368 * <li> {@code ch} is a currency symbol (such as {@code '$'})
9369 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
9370 * </ul>
9371 *
9372 * <p><b>Note:</b> This method cannot handle <a
9373 * href="#supplementary"> supplementary characters</a>. To support
9374 * all Unicode characters, including supplementary characters, use
9375 * the {@link #isJavaIdentifierStart(int)} method.
9376 *
9377 * @param ch the character to be tested.
9378 * @return {@code true} if the character may start a Java identifier;
9379 * {@code false} otherwise.
9380 * @see Character#isJavaIdentifierPart(char)
9381 * @see Character#isLetter(char)
9382 * @see Character#isUnicodeIdentifierStart(char)
9383 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9384 * @since 1.1
9385 */
9386 public static boolean isJavaIdentifierStart(char ch) {
9387 return isJavaIdentifierStart((int)ch);
9388 }
9389
9390 /**
9391 * Determines if the character (Unicode code point) is
9392 * permissible as the first character in a Java identifier.
9393 * <p>
9394 * A character may start a Java identifier if and only if
9395 * one of the following conditions is true:
9396 * <ul>
9397 * <li> {@link #isLetter(int) isLetter(codePoint)}
9398 * returns {@code true}
9399 * <li> {@link #getType(int) getType(codePoint)}
9400 * returns {@code LETTER_NUMBER}
9401 * <li> the referenced character is a currency symbol (such as {@code '$'})
9402 * <li> the referenced character is a connecting punctuation character
9403 * (such as {@code '_'}).
9404 * </ul>
9405 *
9406 * @param codePoint the character (Unicode code point) to be tested.
9407 * @return {@code true} if the character may start a Java identifier;
9408 * {@code false} otherwise.
9409 * @see Character#isJavaIdentifierPart(int)
9410 * @see Character#isLetter(int)
9411 * @see Character#isUnicodeIdentifierStart(int)
9412 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9413 * @since 1.5
9414 */
9415 public static boolean isJavaIdentifierStart(int codePoint) {
9416 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
9417 }
9418
9419 /**
9420 * Determines if the specified character may be part of a Java
9421 * identifier as other than the first character.
9422 * <p>
9423 * A character may be part of a Java identifier if any of the following
9424 * are true:
9425 * <ul>
9426 * <li> it is a letter
9427 * <li> it is a currency symbol (such as {@code '$'})
9428 * <li> it is a connecting punctuation character (such as {@code '_'})
9429 * <li> it is a digit
9430 * <li> it is a numeric letter (such as a Roman numeral character)
9431 * <li> it is a combining mark
9432 * <li> it is a non-spacing mark
9433 * <li> {@code isIdentifierIgnorable} returns
9434 * {@code true} for the character
9435 * </ul>
9436 *
9437 * <p><b>Note:</b> This method cannot handle <a
9438 * href="#supplementary"> supplementary characters</a>. To support
9439 * all Unicode characters, including supplementary characters, use
9440 * the {@link #isJavaIdentifierPart(int)} method.
9441 *
9442 * @param ch the character to be tested.
9443 * @return {@code true} if the character may be part of a
9444 * Java identifier; {@code false} otherwise.
9445 * @see Character#isIdentifierIgnorable(char)
9446 * @see Character#isJavaIdentifierStart(char)
9447 * @see Character#isLetterOrDigit(char)
9448 * @see Character#isUnicodeIdentifierPart(char)
9449 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9450 * @since 1.1
9451 */
9452 public static boolean isJavaIdentifierPart(char ch) {
9453 return isJavaIdentifierPart((int)ch);
9454 }
9455
9456 /**
9457 * Determines if the character (Unicode code point) may be part of a Java
9458 * identifier as other than the first character.
9459 * <p>
9460 * A character may be part of a Java identifier if any of the following
9461 * are true:
9462 * <ul>
9463 * <li> it is a letter
9464 * <li> it is a currency symbol (such as {@code '$'})
9465 * <li> it is a connecting punctuation character (such as {@code '_'})
9466 * <li> it is a digit
9467 * <li> it is a numeric letter (such as a Roman numeral character)
9468 * <li> it is a combining mark
9469 * <li> it is a non-spacing mark
9470 * <li> {@link #isIdentifierIgnorable(int)
9471 * isIdentifierIgnorable(codePoint)} returns {@code true} for
9472 * the character
9473 * </ul>
9474 *
9475 * @param codePoint the character (Unicode code point) to be tested.
9476 * @return {@code true} if the character may be part of a
9477 * Java identifier; {@code false} otherwise.
9478 * @see Character#isIdentifierIgnorable(int)
9479 * @see Character#isJavaIdentifierStart(int)
9480 * @see Character#isLetterOrDigit(int)
9481 * @see Character#isUnicodeIdentifierPart(int)
9482 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9483 * @since 1.5
9484 */
9485 public static boolean isJavaIdentifierPart(int codePoint) {
9486 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
9487 }
9488
9489 /**
9490 * Determines if the specified character is permissible as the
9491 * first character in a Unicode identifier.
9492 * <p>
9493 * A character may start a Unicode identifier if and only if
9494 * one of the following conditions is true:
9495 * <ul>
9496 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9497 * <li> {@link #getType(char) getType(ch)} returns
9498 * {@code LETTER_NUMBER}.
9499 * </ul>
9500 *
9501 * <p><b>Note:</b> This method cannot handle <a
9502 * href="#supplementary"> supplementary characters</a>. To support
9503 * all Unicode characters, including supplementary characters, use
9504 * the {@link #isUnicodeIdentifierStart(int)} method.
9505 *
9506 * @param ch the character to be tested.
9507 * @return {@code true} if the character may start a Unicode
9508 * identifier; {@code false} otherwise.
9509 * @see Character#isJavaIdentifierStart(char)
9510 * @see Character#isLetter(char)
9511 * @see Character#isUnicodeIdentifierPart(char)
9512 * @since 1.1
9513 */
9514 public static boolean isUnicodeIdentifierStart(char ch) {
9515 return isUnicodeIdentifierStart((int)ch);
9516 }
9517
9518 /**
9519 * Determines if the specified character (Unicode code point) is permissible as the
9520 * first character in a Unicode identifier.
9521 * <p>
9522 * A character may start a Unicode identifier if and only if
9523 * one of the following conditions is true:
9524 * <ul>
9525 * <li> {@link #isLetter(int) isLetter(codePoint)}
9526 * returns {@code true}
9527 * <li> {@link #getType(int) getType(codePoint)}
9528 * returns {@code LETTER_NUMBER}.
9529 * </ul>
9530 * @param codePoint the character (Unicode code point) to be tested.
9531 * @return {@code true} if the character may start a Unicode
9532 * identifier; {@code false} otherwise.
9533 * @see Character#isJavaIdentifierStart(int)
9534 * @see Character#isLetter(int)
9535 * @see Character#isUnicodeIdentifierPart(int)
9536 * @since 1.5
9537 */
9538 public static boolean isUnicodeIdentifierStart(int codePoint) {
9539 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
9540 }
9541
9542 /**
9543 * Determines if the specified character may be part of a Unicode
9544 * identifier as other than the first character.
9545 * <p>
9546 * A character may be part of a Unicode identifier if and only if
9547 * one of the following statements is true:
9548 * <ul>
9549 * <li> it is a letter
9550 * <li> it is a connecting punctuation character (such as {@code '_'})
9551 * <li> it is a digit
9552 * <li> it is a numeric letter (such as a Roman numeral character)
9553 * <li> it is a combining mark
9554 * <li> it is a non-spacing mark
9555 * <li> {@code isIdentifierIgnorable} returns
9556 * {@code true} for this character.
9557 * </ul>
9558 *
9559 * <p><b>Note:</b> This method cannot handle <a
9560 * href="#supplementary"> supplementary characters</a>. To support
9561 * all Unicode characters, including supplementary characters, use
9562 * the {@link #isUnicodeIdentifierPart(int)} method.
9563 *
9564 * @param ch the character to be tested.
9565 * @return {@code true} if the character may be part of a
9566 * Unicode identifier; {@code false} otherwise.
9567 * @see Character#isIdentifierIgnorable(char)
9568 * @see Character#isJavaIdentifierPart(char)
9569 * @see Character#isLetterOrDigit(char)
9570 * @see Character#isUnicodeIdentifierStart(char)
9571 * @since 1.1
9572 */
9573 public static boolean isUnicodeIdentifierPart(char ch) {
9574 return isUnicodeIdentifierPart((int)ch);
9575 }
9576
9577 /**
9578 * Determines if the specified character (Unicode code point) may be part of a Unicode
9579 * identifier as other than the first character.
9580 * <p>
9581 * A character may be part of a Unicode identifier if and only if
9582 * one of the following statements is true:
9583 * <ul>
9584 * <li> it is a letter
9585 * <li> it is a connecting punctuation character (such as {@code '_'})
9586 * <li> it is a digit
9587 * <li> it is a numeric letter (such as a Roman numeral character)
9588 * <li> it is a combining mark
9589 * <li> it is a non-spacing mark
9590 * <li> {@code isIdentifierIgnorable} returns
9591 * {@code true} for this character.
9592 * </ul>
9593 * @param codePoint the character (Unicode code point) to be tested.
9594 * @return {@code true} if the character may be part of a
9595 * Unicode identifier; {@code false} otherwise.
9596 * @see Character#isIdentifierIgnorable(int)
9597 * @see Character#isJavaIdentifierPart(int)
9598 * @see Character#isLetterOrDigit(int)
9599 * @see Character#isUnicodeIdentifierStart(int)
9600 * @since 1.5
9601 */
9602 public static boolean isUnicodeIdentifierPart(int codePoint) {
9603 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
9604 }
9605
9606 /**
9607 * Determines if the specified character should be regarded as
9608 * an ignorable character in a Java identifier or a Unicode identifier.
9609 * <p>
9610 * The following Unicode characters are ignorable in a Java identifier
9611 * or a Unicode identifier:
9612 * <ul>
9613 * <li>ISO control characters that are not whitespace
9614 * <ul>
9615 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9616 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9617 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9618 * </ul>
9619 *
9620 * <li>all characters that have the {@code FORMAT} general
9621 * category value
9622 * </ul>
9623 *
9624 * <p><b>Note:</b> This method cannot handle <a
9625 * href="#supplementary"> supplementary characters</a>. To support
9626 * all Unicode characters, including supplementary characters, use
9627 * the {@link #isIdentifierIgnorable(int)} method.
9628 *
9629 * @param ch the character to be tested.
9630 * @return {@code true} if the character is an ignorable control
9631 * character that may be part of a Java or Unicode identifier;
9632 * {@code false} otherwise.
9633 * @see Character#isJavaIdentifierPart(char)
9634 * @see Character#isUnicodeIdentifierPart(char)
9635 * @since 1.1
9636 */
9637 public static boolean isIdentifierIgnorable(char ch) {
9638 return isIdentifierIgnorable((int)ch);
9639 }
9640
9641 /**
9642 * Determines if the specified character (Unicode code point) should be regarded as
9643 * an ignorable character in a Java identifier or a Unicode identifier.
9644 * <p>
9645 * The following Unicode characters are ignorable in a Java identifier
9646 * or a Unicode identifier:
9647 * <ul>
9648 * <li>ISO control characters that are not whitespace
9649 * <ul>
9650 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9651 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9652 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9653 * </ul>
9654 *
9655 * <li>all characters that have the {@code FORMAT} general
9656 * category value
9657 * </ul>
9658 *
9659 * @param codePoint the character (Unicode code point) to be tested.
9660 * @return {@code true} if the character is an ignorable control
9661 * character that may be part of a Java or Unicode identifier;
9662 * {@code false} otherwise.
9663 * @see Character#isJavaIdentifierPart(int)
9664 * @see Character#isUnicodeIdentifierPart(int)
9665 * @since 1.5
9666 */
9667 public static boolean isIdentifierIgnorable(int codePoint) {
9668 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
9669 }
9670
9671 /**
9672 * Converts the character argument to lowercase using case
9673 * mapping information from the UnicodeData file.
9674 * <p>
9675 * Note that
9676 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
9677 * does not always return {@code true} for some ranges of
9678 * characters, particularly those that are symbols or ideographs.
9679 *
9680 * <p>In general, {@link String#toLowerCase()} should be used to map
9681 * characters to lowercase. {@code String} case mapping methods
9682 * have several benefits over {@code Character} case mapping methods.
9683 * {@code String} case mapping methods can perform locale-sensitive
9684 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9685 * the {@code Character} case mapping methods cannot.
9686 *
9687 * <p><b>Note:</b> This method cannot handle <a
9688 * href="#supplementary"> supplementary characters</a>. To support
9689 * all Unicode characters, including supplementary characters, use
9690 * the {@link #toLowerCase(int)} method.
9691 *
9692 * @param ch the character to be converted.
9693 * @return the lowercase equivalent of the character, if any;
9694 * otherwise, the character itself.
9695 * @see Character#isLowerCase(char)
9696 * @see String#toLowerCase()
9697 */
9698 public static char toLowerCase(char ch) {
9699 return (char)toLowerCase((int)ch);
9700 }
9701
9702 /**
9703 * Converts the character (Unicode code point) argument to
9704 * lowercase using case mapping information from the UnicodeData
9705 * file.
9706 *
9707 * <p> Note that
9708 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
9709 * does not always return {@code true} for some ranges of
9710 * characters, particularly those that are symbols or ideographs.
9711 *
9712 * <p>In general, {@link String#toLowerCase()} should be used to map
9713 * characters to lowercase. {@code String} case mapping methods
9714 * have several benefits over {@code Character} case mapping methods.
9715 * {@code String} case mapping methods can perform locale-sensitive
9716 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9717 * the {@code Character} case mapping methods cannot.
9718 *
9719 * @param codePoint the character (Unicode code point) to be converted.
9720 * @return the lowercase equivalent of the character (Unicode code
9721 * point), if any; otherwise, the character itself.
9722 * @see Character#isLowerCase(int)
9723 * @see String#toLowerCase()
9724 *
9725 * @since 1.5
9726 */
9727 public static int toLowerCase(int codePoint) {
9728 return CharacterData.of(codePoint).toLowerCase(codePoint);
9729 }
9730
9731 /**
9732 * Converts the character argument to uppercase using case mapping
9733 * information from the UnicodeData file.
9734 * <p>
9735 * Note that
9736 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
9737 * does not always return {@code true} for some ranges of
9738 * characters, particularly those that are symbols or ideographs.
9739 *
9740 * <p>In general, {@link String#toUpperCase()} should be used to map
9741 * characters to uppercase. {@code String} case mapping methods
9742 * have several benefits over {@code Character} case mapping methods.
9743 * {@code String} case mapping methods can perform locale-sensitive
9744 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9745 * the {@code Character} case mapping methods cannot.
9746 *
9747 * <p><b>Note:</b> This method cannot handle <a
9748 * href="#supplementary"> supplementary characters</a>. To support
9749 * all Unicode characters, including supplementary characters, use
9750 * the {@link #toUpperCase(int)} method.
9751 *
9752 * @param ch the character to be converted.
9753 * @return the uppercase equivalent of the character, if any;
9754 * otherwise, the character itself.
9755 * @see Character#isUpperCase(char)
9756 * @see String#toUpperCase()
9757 */
9758 public static char toUpperCase(char ch) {
9759 return (char)toUpperCase((int)ch);
9760 }
9761
9762 /**
9763 * Converts the character (Unicode code point) argument to
9764 * uppercase using case mapping information from the UnicodeData
9765 * file.
9766 *
9767 * <p>Note that
9768 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
9769 * does not always return {@code true} for some ranges of
9770 * characters, particularly those that are symbols or ideographs.
9771 *
9772 * <p>In general, {@link String#toUpperCase()} should be used to map
9773 * characters to uppercase. {@code String} case mapping methods
9774 * have several benefits over {@code Character} case mapping methods.
9775 * {@code String} case mapping methods can perform locale-sensitive
9776 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9777 * the {@code Character} case mapping methods cannot.
9778 *
9779 * @param codePoint the character (Unicode code point) to be converted.
9780 * @return the uppercase equivalent of the character, if any;
9781 * otherwise, the character itself.
9782 * @see Character#isUpperCase(int)
9783 * @see String#toUpperCase()
9784 *
9785 * @since 1.5
9786 */
9787 public static int toUpperCase(int codePoint) {
9788 return CharacterData.of(codePoint).toUpperCase(codePoint);
9789 }
9790
9791 /**
9792 * Converts the character argument to titlecase using case mapping
9793 * information from the UnicodeData file. If a character has no
9794 * explicit titlecase mapping and is not itself a titlecase char
9795 * according to UnicodeData, then the uppercase mapping is
9796 * returned as an equivalent titlecase mapping. If the
9797 * {@code char} argument is already a titlecase
9798 * {@code char}, the same {@code char} value will be
9799 * returned.
9800 * <p>
9801 * Note that
9802 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
9803 * does not always return {@code true} for some ranges of
9804 * characters.
9805 *
9806 * <p><b>Note:</b> This method cannot handle <a
9807 * href="#supplementary"> supplementary characters</a>. To support
9808 * all Unicode characters, including supplementary characters, use
9809 * the {@link #toTitleCase(int)} method.
9810 *
9811 * @param ch the character to be converted.
9812 * @return the titlecase equivalent of the character, if any;
9813 * otherwise, the character itself.
9814 * @see Character#isTitleCase(char)
9815 * @see Character#toLowerCase(char)
9816 * @see Character#toUpperCase(char)
9817 * @since 1.0.2
9818 */
9819 public static char toTitleCase(char ch) {
9820 return (char)toTitleCase((int)ch);
9821 }
9822
9823 /**
9824 * Converts the character (Unicode code point) argument to titlecase using case mapping
9825 * information from the UnicodeData file. If a character has no
9826 * explicit titlecase mapping and is not itself a titlecase char
9827 * according to UnicodeData, then the uppercase mapping is
9828 * returned as an equivalent titlecase mapping. If the
9829 * character argument is already a titlecase
9830 * character, the same character value will be
9831 * returned.
9832 *
9833 * <p>Note that
9834 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
9835 * does not always return {@code true} for some ranges of
9836 * characters.
9837 *
9838 * @param codePoint the character (Unicode code point) to be converted.
9839 * @return the titlecase equivalent of the character, if any;
9840 * otherwise, the character itself.
9841 * @see Character#isTitleCase(int)
9842 * @see Character#toLowerCase(int)
9843 * @see Character#toUpperCase(int)
9844 * @since 1.5
9845 */
9846 public static int toTitleCase(int codePoint) {
9847 return CharacterData.of(codePoint).toTitleCase(codePoint);
9848 }
9849
9850 /**
9851 * Returns the numeric value of the character {@code ch} in the
9852 * specified radix.
9853 * <p>
9854 * If the radix is not in the range {@code MIN_RADIX} ≤
9855 * {@code radix} ≤ {@code MAX_RADIX} or if the
9856 * value of {@code ch} is not a valid digit in the specified
9857 * radix, {@code -1} is returned. A character is a valid digit
9858 * if at least one of the following is true:
9859 * <ul>
9860 * <li>The method {@code isDigit} is {@code true} of the character
9861 * and the Unicode decimal digit value of the character (or its
9862 * single-character decomposition) is less than the specified radix.
9863 * In this case the decimal digit value is returned.
9864 * <li>The character is one of the uppercase Latin letters
9865 * {@code 'A'} through {@code 'Z'} and its code is less than
9866 * {@code radix + 'A' - 10}.
9867 * In this case, {@code ch - 'A' + 10}
9868 * is returned.
9869 * <li>The character is one of the lowercase Latin letters
9870 * {@code 'a'} through {@code 'z'} and its code is less than
9871 * {@code radix + 'a' - 10}.
9872 * In this case, {@code ch - 'a' + 10}
9873 * is returned.
9874 * <li>The character is one of the fullwidth uppercase Latin letters A
9875 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
9876 * and its code is less than
9877 * {@code radix + '\u005CuFF21' - 10}.
9878 * In this case, {@code ch - '\u005CuFF21' + 10}
9879 * is returned.
9880 * <li>The character is one of the fullwidth lowercase Latin letters a
9881 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
9882 * and its code is less than
9883 * {@code radix + '\u005CuFF41' - 10}.
9884 * In this case, {@code ch - '\u005CuFF41' + 10}
9885 * is returned.
9886 * </ul>
9887 *
9888 * <p><b>Note:</b> This method cannot handle <a
9889 * href="#supplementary"> supplementary characters</a>. To support
9890 * all Unicode characters, including supplementary characters, use
9891 * the {@link #digit(int, int)} method.
9892 *
9893 * @param ch the character to be converted.
9894 * @param radix the radix.
9895 * @return the numeric value represented by the character in the
9896 * specified radix.
9897 * @see Character#forDigit(int, int)
9898 * @see Character#isDigit(char)
9899 */
9900 public static int digit(char ch, int radix) {
9901 return digit((int)ch, radix);
9902 }
9903
9904 /**
9905 * Returns the numeric value of the specified character (Unicode
9906 * code point) in the specified radix.
9907 *
9908 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
9909 * {@code radix} ≤ {@code MAX_RADIX} or if the
9910 * character is not a valid digit in the specified
9911 * radix, {@code -1} is returned. A character is a valid digit
9912 * if at least one of the following is true:
9913 * <ul>
9914 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
9915 * and the Unicode decimal digit value of the character (or its
9916 * single-character decomposition) is less than the specified radix.
9917 * In this case the decimal digit value is returned.
9918 * <li>The character is one of the uppercase Latin letters
9919 * {@code 'A'} through {@code 'Z'} and its code is less than
9920 * {@code radix + 'A' - 10}.
9921 * In this case, {@code codePoint - 'A' + 10}
9922 * is returned.
9923 * <li>The character is one of the lowercase Latin letters
9924 * {@code 'a'} through {@code 'z'} and its code is less than
9925 * {@code radix + 'a' - 10}.
9926 * In this case, {@code codePoint - 'a' + 10}
9927 * is returned.
9928 * <li>The character is one of the fullwidth uppercase Latin letters A
9929 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
9930 * and its code is less than
9931 * {@code radix + '\u005CuFF21' - 10}.
9932 * In this case,
9933 * {@code codePoint - '\u005CuFF21' + 10}
9934 * is returned.
9935 * <li>The character is one of the fullwidth lowercase Latin letters a
9936 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
9937 * and its code is less than
9938 * {@code radix + '\u005CuFF41'- 10}.
9939 * In this case,
9940 * {@code codePoint - '\u005CuFF41' + 10}
9941 * is returned.
9942 * </ul>
9943 *
9944 * @param codePoint the character (Unicode code point) to be converted.
9945 * @param radix the radix.
9946 * @return the numeric value represented by the character in the
9947 * specified radix.
9948 * @see Character#forDigit(int, int)
9949 * @see Character#isDigit(int)
9950 * @since 1.5
9951 */
9952 public static int digit(int codePoint, int radix) {
9953 return CharacterData.of(codePoint).digit(codePoint, radix);
9954 }
9955
9956 /**
9957 * Returns the {@code int} value that the specified Unicode
9958 * character represents. For example, the character
9959 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
9960 * an int with a value of 50.
9961 * <p>
9962 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
9963 * {@code '\u005Cu005A'}), lowercase
9964 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
9965 * full width variant ({@code '\u005CuFF21'} through
9966 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
9967 * {@code '\u005CuFF5A'}) forms have numeric values from 10
9968 * through 35. This is independent of the Unicode specification,
9969 * which does not assign numeric values to these {@code char}
9970 * values.
9971 * <p>
9972 * If the character does not have a numeric value, then -1 is returned.
9973 * If the character has a numeric value that cannot be represented as a
9974 * nonnegative integer (for example, a fractional value), then -2
9975 * is returned.
9976 *
9977 * <p><b>Note:</b> This method cannot handle <a
9978 * href="#supplementary"> supplementary characters</a>. To support
9979 * all Unicode characters, including supplementary characters, use
9980 * the {@link #getNumericValue(int)} method.
9981 *
9982 * @param ch the character to be converted.
9983 * @return the numeric value of the character, as a nonnegative {@code int}
9984 * value; -2 if the character has a numeric value but the value
9985 * can not be represented as a nonnegative {@code int} value;
9986 * -1 if the character has no numeric value.
9987 * @see Character#forDigit(int, int)
9988 * @see Character#isDigit(char)
9989 * @since 1.1
9990 */
9991 public static int getNumericValue(char ch) {
9992 return getNumericValue((int)ch);
9993 }
9994
9995 /**
9996 * Returns the {@code int} value that the specified
9997 * character (Unicode code point) represents. For example, the character
9998 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
9999 * an {@code int} with a value of 50.
10000 * <p>
10001 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
10002 * {@code '\u005Cu005A'}), lowercase
10003 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
10004 * full width variant ({@code '\u005CuFF21'} through
10005 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
10006 * {@code '\u005CuFF5A'}) forms have numeric values from 10
10007 * through 35. This is independent of the Unicode specification,
10008 * which does not assign numeric values to these {@code char}
10009 * values.
10010 * <p>
10011 * If the character does not have a numeric value, then -1 is returned.
10012 * If the character has a numeric value that cannot be represented as a
10013 * nonnegative integer (for example, a fractional value), then -2
10014 * is returned.
10015 *
10016 * @param codePoint the character (Unicode code point) to be converted.
10017 * @return the numeric value of the character, as a nonnegative {@code int}
10018 * value; -2 if the character has a numeric value but the value
10019 * can not be represented as a nonnegative {@code int} value;
10020 * -1 if the character has no numeric value.
10021 * @see Character#forDigit(int, int)
10022 * @see Character#isDigit(int)
10023 * @since 1.5
10024 */
10025 public static int getNumericValue(int codePoint) {
10026 return CharacterData.of(codePoint).getNumericValue(codePoint);
10027 }
10028
10029 /**
10030 * Determines if the specified character is ISO-LATIN-1 white space.
10031 * This method returns {@code true} for the following five
10032 * characters only:
10033 * <table class="striped">
10034 * <caption style="display:none">truechars</caption>
10035 * <thead>
10036 * <tr><th scope="col">Character
10037 * <th scope="col">Code
10038 * <th scope="col">Name
10039 * </thead>
10040 * <tbody>
10041 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
10042 * <td>{@code HORIZONTAL TABULATION}</td></tr>
10043 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
10044 * <td>{@code NEW LINE}</td></tr>
10045 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
10046 * <td>{@code FORM FEED}</td></tr>
10047 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
10048 * <td>{@code CARRIAGE RETURN}</td></tr>
10049 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
10050 * <td>{@code SPACE}</td></tr>
10051 * </tbody>
10052 * </table>
10053 *
10054 * @param ch the character to be tested.
10055 * @return {@code true} if the character is ISO-LATIN-1 white
10056 * space; {@code false} otherwise.
10057 * @see Character#isSpaceChar(char)
10058 * @see Character#isWhitespace(char)
10059 * @deprecated Replaced by isWhitespace(char).
10060 */
10061 @Deprecated(since="1.1")
10062 public static boolean isSpace(char ch) {
10063 return (ch <= 0x0020) &&
10064 (((((1L << 0x0009) |
10065 (1L << 0x000A) |
10066 (1L << 0x000C) |
10067 (1L << 0x000D) |
10068 (1L << 0x0020)) >> ch) & 1L) != 0);
10069 }
10070
10071
10072 /**
10073 * Determines if the specified character is a Unicode space character.
10074 * A character is considered to be a space character if and only if
10075 * it is specified to be a space character by the Unicode Standard. This
10076 * method returns true if the character's general category type is any of
10077 * the following:
10078 * <ul>
10079 * <li> {@code SPACE_SEPARATOR}
10080 * <li> {@code LINE_SEPARATOR}
10081 * <li> {@code PARAGRAPH_SEPARATOR}
10082 * </ul>
10083 *
10084 * <p><b>Note:</b> This method cannot handle <a
10085 * href="#supplementary"> supplementary characters</a>. To support
10086 * all Unicode characters, including supplementary characters, use
10087 * the {@link #isSpaceChar(int)} method.
10088 *
10089 * @param ch the character to be tested.
10090 * @return {@code true} if the character is a space character;
10091 * {@code false} otherwise.
10092 * @see Character#isWhitespace(char)
10093 * @since 1.1
10094 */
10095 public static boolean isSpaceChar(char ch) {
10096 return isSpaceChar((int)ch);
10097 }
10098
10099 /**
10100 * Determines if the specified character (Unicode code point) is a
10101 * Unicode space character. A character is considered to be a
10102 * space character if and only if it is specified to be a space
10103 * character by the Unicode Standard. This method returns true if
10104 * the character's general category type is any of the following:
10105 *
10106 * <ul>
10107 * <li> {@link #SPACE_SEPARATOR}
10108 * <li> {@link #LINE_SEPARATOR}
10109 * <li> {@link #PARAGRAPH_SEPARATOR}
10110 * </ul>
10111 *
10112 * @param codePoint the character (Unicode code point) to be tested.
10113 * @return {@code true} if the character is a space character;
10114 * {@code false} otherwise.
10115 * @see Character#isWhitespace(int)
10116 * @since 1.5
10117 */
10118 public static boolean isSpaceChar(int codePoint) {
10119 return ((((1 << Character.SPACE_SEPARATOR) |
10120 (1 << Character.LINE_SEPARATOR) |
10121 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
10122 != 0;
10123 }
10124
10125 /**
10126 * Determines if the specified character is white space according to Java.
10127 * A character is a Java whitespace character if and only if it satisfies
10128 * one of the following criteria:
10129 * <ul>
10130 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
10131 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
10132 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
10133 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
10134 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
10135 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
10136 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
10137 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
10138 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
10139 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
10140 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
10141 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
10142 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
10143 * </ul>
10144 *
10145 * <p><b>Note:</b> This method cannot handle <a
10146 * href="#supplementary"> supplementary characters</a>. To support
10147 * all Unicode characters, including supplementary characters, use
10148 * the {@link #isWhitespace(int)} method.
10149 *
10150 * @param ch the character to be tested.
10151 * @return {@code true} if the character is a Java whitespace
10152 * character; {@code false} otherwise.
10153 * @see Character#isSpaceChar(char)
10154 * @since 1.1
10155 */
10156 public static boolean isWhitespace(char ch) {
10157 return isWhitespace((int)ch);
10158 }
10159
10160 /**
10161 * Determines if the specified character (Unicode code point) is
10162 * white space according to Java. A character is a Java
10163 * whitespace character if and only if it satisfies one of the
10164 * following criteria:
10165 * <ul>
10166 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
10167 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
10168 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
10169 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
10170 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
10171 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
10172 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
10173 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
10174 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
10175 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
10176 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
10177 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
10178 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
10179 * </ul>
10180 *
10181 * @param codePoint the character (Unicode code point) to be tested.
10182 * @return {@code true} if the character is a Java whitespace
10183 * character; {@code false} otherwise.
10184 * @see Character#isSpaceChar(int)
10185 * @since 1.5
10186 */
10187 public static boolean isWhitespace(int codePoint) {
10188 return CharacterData.of(codePoint).isWhitespace(codePoint);
10189 }
10190
10191 /**
10192 * Determines if the specified character is an ISO control
10193 * character. A character is considered to be an ISO control
10194 * character if its code is in the range {@code '\u005Cu0000'}
10195 * through {@code '\u005Cu001F'} or in the range
10196 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
10197 *
10198 * <p><b>Note:</b> This method cannot handle <a
10199 * href="#supplementary"> supplementary characters</a>. To support
10200 * all Unicode characters, including supplementary characters, use
10201 * the {@link #isISOControl(int)} method.
10202 *
10203 * @param ch the character to be tested.
10204 * @return {@code true} if the character is an ISO control character;
10205 * {@code false} otherwise.
10206 *
10207 * @see Character#isSpaceChar(char)
10208 * @see Character#isWhitespace(char)
10209 * @since 1.1
10210 */
10211 public static boolean isISOControl(char ch) {
10212 return isISOControl((int)ch);
10213 }
10214
10215 /**
10216 * Determines if the referenced character (Unicode code point) is an ISO control
10217 * character. A character is considered to be an ISO control
10218 * character if its code is in the range {@code '\u005Cu0000'}
10219 * through {@code '\u005Cu001F'} or in the range
10220 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
10221 *
10222 * @param codePoint the character (Unicode code point) to be tested.
10223 * @return {@code true} if the character is an ISO control character;
10224 * {@code false} otherwise.
10225 * @see Character#isSpaceChar(int)
10226 * @see Character#isWhitespace(int)
10227 * @since 1.5
10228 */
10229 public static boolean isISOControl(int codePoint) {
10230 // Optimized form of:
10231 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
10232 // (codePoint >= 0x7F && codePoint <= 0x9F);
10233 return codePoint <= 0x9F &&
10234 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
10235 }
10236
10237 /**
10238 * Returns a value indicating a character's general category.
10239 *
10240 * <p><b>Note:</b> This method cannot handle <a
10241 * href="#supplementary"> supplementary characters</a>. To support
10242 * all Unicode characters, including supplementary characters, use
10243 * the {@link #getType(int)} method.
10244 *
10245 * @param ch the character to be tested.
10246 * @return a value of type {@code int} representing the
10247 * character's general category.
10248 * @see Character#COMBINING_SPACING_MARK
10249 * @see Character#CONNECTOR_PUNCTUATION
10250 * @see Character#CONTROL
10251 * @see Character#CURRENCY_SYMBOL
10252 * @see Character#DASH_PUNCTUATION
10253 * @see Character#DECIMAL_DIGIT_NUMBER
10254 * @see Character#ENCLOSING_MARK
10255 * @see Character#END_PUNCTUATION
10256 * @see Character#FINAL_QUOTE_PUNCTUATION
10257 * @see Character#FORMAT
10258 * @see Character#INITIAL_QUOTE_PUNCTUATION
10259 * @see Character#LETTER_NUMBER
10260 * @see Character#LINE_SEPARATOR
10261 * @see Character#LOWERCASE_LETTER
10262 * @see Character#MATH_SYMBOL
10263 * @see Character#MODIFIER_LETTER
10264 * @see Character#MODIFIER_SYMBOL
10265 * @see Character#NON_SPACING_MARK
10266 * @see Character#OTHER_LETTER
10267 * @see Character#OTHER_NUMBER
10268 * @see Character#OTHER_PUNCTUATION
10269 * @see Character#OTHER_SYMBOL
10270 * @see Character#PARAGRAPH_SEPARATOR
10271 * @see Character#PRIVATE_USE
10272 * @see Character#SPACE_SEPARATOR
10273 * @see Character#START_PUNCTUATION
10274 * @see Character#SURROGATE
10275 * @see Character#TITLECASE_LETTER
10276 * @see Character#UNASSIGNED
10277 * @see Character#UPPERCASE_LETTER
10278 * @since 1.1
10279 */
10280 public static int getType(char ch) {
10281 return getType((int)ch);
10282 }
10283
10284 /**
10285 * Returns a value indicating a character's general category.
10286 *
10287 * @param codePoint the character (Unicode code point) to be tested.
10288 * @return a value of type {@code int} representing the
10289 * character's general category.
10290 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
10291 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
10292 * @see Character#CONTROL CONTROL
10293 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
10294 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
10295 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
10296 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
10297 * @see Character#END_PUNCTUATION END_PUNCTUATION
10298 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
10299 * @see Character#FORMAT FORMAT
10300 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
10301 * @see Character#LETTER_NUMBER LETTER_NUMBER
10302 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
10303 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
10304 * @see Character#MATH_SYMBOL MATH_SYMBOL
10305 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
10306 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
10307 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
10308 * @see Character#OTHER_LETTER OTHER_LETTER
10309 * @see Character#OTHER_NUMBER OTHER_NUMBER
10310 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
10311 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
10312 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
10313 * @see Character#PRIVATE_USE PRIVATE_USE
10314 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
10315 * @see Character#START_PUNCTUATION START_PUNCTUATION
10316 * @see Character#SURROGATE SURROGATE
10317 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
10318 * @see Character#UNASSIGNED UNASSIGNED
10319 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
10320 * @since 1.5
10321 */
10322 public static int getType(int codePoint) {
10323 return CharacterData.of(codePoint).getType(codePoint);
10324 }
10325
10326 /**
10327 * Determines the character representation for a specific digit in
10328 * the specified radix. If the value of {@code radix} is not a
10329 * valid radix, or the value of {@code digit} is not a valid
10330 * digit in the specified radix, the null character
10331 * ({@code '\u005Cu0000'}) is returned.
10332 * <p>
10333 * The {@code radix} argument is valid if it is greater than or
10334 * equal to {@code MIN_RADIX} and less than or equal to
10335 * {@code MAX_RADIX}. The {@code digit} argument is valid if
10336 * {@code 0 <= digit < radix}.
10337 * <p>
10338 * If the digit is less than 10, then
10339 * {@code '0' + digit} is returned. Otherwise, the value
10340 * {@code 'a' + digit - 10} is returned.
10341 *
10342 * @param digit the number to convert to a character.
10343 * @param radix the radix.
10344 * @return the {@code char} representation of the specified digit
10345 * in the specified radix.
10346 * @see Character#MIN_RADIX
10347 * @see Character#MAX_RADIX
10348 * @see Character#digit(char, int)
10349 */
10350 public static char forDigit(int digit, int radix) {
10351 if ((digit >= radix) || (digit < 0)) {
10352 return '\0';
10353 }
10354 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
10355 return '\0';
10356 }
10357 if (digit < 10) {
10358 return (char)('0' + digit);
10359 }
10360 return (char)('a' - 10 + digit);
10361 }
10362
10363 /**
10364 * Returns the Unicode directionality property for the given
10365 * character. Character directionality is used to calculate the
10366 * visual ordering of text. The directionality value of undefined
10367 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
10368 *
10369 * <p><b>Note:</b> This method cannot handle <a
10370 * href="#supplementary"> supplementary characters</a>. To support
10371 * all Unicode characters, including supplementary characters, use
10372 * the {@link #getDirectionality(int)} method.
10373 *
10374 * @param ch {@code char} for which the directionality property
10375 * is requested.
10376 * @return the directionality property of the {@code char} value.
10377 *
10378 * @see Character#DIRECTIONALITY_UNDEFINED
10379 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
10380 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
10381 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
10382 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
10383 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
10384 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
10385 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
10386 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
10387 * @see Character#DIRECTIONALITY_NONSPACING_MARK
10388 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
10389 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
10390 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
10391 * @see Character#DIRECTIONALITY_WHITESPACE
10392 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
10393 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
10394 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
10395 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
10396 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
10397 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
10398 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
10399 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
10400 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
10401 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
10402 * @since 1.4
10403 */
10404 public static byte getDirectionality(char ch) {
10405 return getDirectionality((int)ch);
10406 }
10407
10408 /**
10409 * Returns the Unicode directionality property for the given
10410 * character (Unicode code point). Character directionality is
10411 * used to calculate the visual ordering of text. The
10412 * directionality value of undefined character is {@link
10413 * #DIRECTIONALITY_UNDEFINED}.
10414 *
10415 * @param codePoint the character (Unicode code point) for which
10416 * the directionality property is requested.
10417 * @return the directionality property of the character.
10418 *
10419 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
10420 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
10421 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
10422 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
10423 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
10424 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
10425 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
10426 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
10427 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
10428 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
10429 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
10430 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
10431 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
10432 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
10433 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
10434 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
10435 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
10436 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
10437 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
10438 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
10439 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
10440 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
10441 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
10442 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
10443 * @since 1.5
10444 */
10445 public static byte getDirectionality(int codePoint) {
10446 return CharacterData.of(codePoint).getDirectionality(codePoint);
10447 }
10448
10449 /**
10450 * Determines whether the character is mirrored according to the
10451 * Unicode specification. Mirrored characters should have their
10452 * glyphs horizontally mirrored when displayed in text that is
10453 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
10454 * PARENTHESIS is semantically defined to be an <i>opening
10455 * parenthesis</i>. This will appear as a "(" in text that is
10456 * left-to-right but as a ")" in text that is right-to-left.
10457 *
10458 * <p><b>Note:</b> This method cannot handle <a
10459 * href="#supplementary"> supplementary characters</a>. To support
10460 * all Unicode characters, including supplementary characters, use
10461 * the {@link #isMirrored(int)} method.
10462 *
10463 * @param ch {@code char} for which the mirrored property is requested
10464 * @return {@code true} if the char is mirrored, {@code false}
10465 * if the {@code char} is not mirrored or is not defined.
10466 * @since 1.4
10467 */
10468 public static boolean isMirrored(char ch) {
10469 return isMirrored((int)ch);
10470 }
10471
10472 /**
10473 * Determines whether the specified character (Unicode code point)
10474 * is mirrored according to the Unicode specification. Mirrored
10475 * characters should have their glyphs horizontally mirrored when
10476 * displayed in text that is right-to-left. For example,
10477 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
10478 * defined to be an <i>opening parenthesis</i>. This will appear
10479 * as a "(" in text that is left-to-right but as a ")" in text
10480 * that is right-to-left.
10481 *
10482 * @param codePoint the character (Unicode code point) to be tested.
10483 * @return {@code true} if the character is mirrored, {@code false}
10484 * if the character is not mirrored or is not defined.
10485 * @since 1.5
10486 */
10487 public static boolean isMirrored(int codePoint) {
10488 return CharacterData.of(codePoint).isMirrored(codePoint);
10489 }
10490
10491 /**
10492 * Compares two {@code Character} objects numerically.
10493 *
10494 * @param anotherCharacter the {@code Character} to be compared.
10495
10496 * @return the value {@code 0} if the argument {@code Character}
10497 * is equal to this {@code Character}; a value less than
10498 * {@code 0} if this {@code Character} is numerically less
10499 * than the {@code Character} argument; and a value greater than
10500 * {@code 0} if this {@code Character} is numerically greater
10501 * than the {@code Character} argument (unsigned comparison).
10502 * Note that this is strictly a numerical comparison; it is not
10503 * locale-dependent.
10504 * @since 1.2
10505 */
10506 public int compareTo(Character anotherCharacter) {
10507 return compare(this.value, anotherCharacter.value);
10508 }
10509
10510 /**
10511 * Compares two {@code char} values numerically.
10512 * The value returned is identical to what would be returned by:
10513 * <pre>
10514 * Character.valueOf(x).compareTo(Character.valueOf(y))
10515 * </pre>
10516 *
10517 * @param x the first {@code char} to compare
10518 * @param y the second {@code char} to compare
10519 * @return the value {@code 0} if {@code x == y};
10520 * a value less than {@code 0} if {@code x < y}; and
10521 * a value greater than {@code 0} if {@code x > y}
10522 * @since 1.7
10523 */
10524 public static int compare(char x, char y) {
10525 return x - y;
10526 }
10527
10528 /**
10529 * Converts the character (Unicode code point) argument to uppercase using
10530 * information from the UnicodeData file.
10531 *
10532 * @param codePoint the character (Unicode code point) to be converted.
10533 * @return either the uppercase equivalent of the character, if
10534 * any, or an error flag ({@code Character.ERROR})
10535 * that indicates that a 1:M {@code char} mapping exists.
10536 * @see Character#isLowerCase(char)
10537 * @see Character#isUpperCase(char)
10538 * @see Character#toLowerCase(char)
10539 * @see Character#toTitleCase(char)
10540 * @since 1.4
10541 */
10542 static int toUpperCaseEx(int codePoint) {
10543 assert isValidCodePoint(codePoint);
10544 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
10545 }
10546
10547 /**
10548 * Converts the character (Unicode code point) argument to uppercase using case
10549 * mapping information from the SpecialCasing file in the Unicode
10550 * specification. If a character has no explicit uppercase
10551 * mapping, then the {@code char} itself is returned in the
10552 * {@code char[]}.
10553 *
10554 * @param codePoint the character (Unicode code point) to be converted.
10555 * @return a {@code char[]} with the uppercased character.
10556 * @since 1.4
10557 */
10558 static char[] toUpperCaseCharArray(int codePoint) {
10559 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
10560 assert isBmpCodePoint(codePoint);
10561 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
10562 }
10563
10564 /**
10565 * The number of bits used to represent a {@code char} value in unsigned
10566 * binary form, constant {@code 16}.
10567 *
10568 * @since 1.5
10569 */
10570 public static final int SIZE = 16;
10571
10572 /**
10573 * The number of bytes used to represent a {@code char} value in unsigned
10574 * binary form.
10575 *
10576 * @since 1.8
10577 */
10578 public static final int BYTES = SIZE / Byte.SIZE;
10579
10580 /**
10581 * Returns the value obtained by reversing the order of the bytes in the
10582 * specified {@code char} value.
10583 *
10584 * @param ch The {@code char} of which to reverse the byte order.
10585 * @return the value obtained by reversing (or, equivalently, swapping)
10586 * the bytes in the specified {@code char} value.
10587 * @since 1.5
10588 */
10589 @HotSpotIntrinsicCandidate
10590 public static char reverseBytes(char ch) {
10591 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
10592 }
10593
10594 /**
10595 * Returns the Unicode name of the specified character
10596 * {@code codePoint}, or null if the code point is
10597 * {@link #UNASSIGNED unassigned}.
10598 * <p>
10599 * Note: if the specified character is not assigned a name by
10600 * the <i>UnicodeData</i> file (part of the Unicode Character
10601 * Database maintained by the Unicode Consortium), the returned
10602 * name is the same as the result of expression.
10603 *
10604 * <blockquote>{@code
10605 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
10606 * + " "
10607 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10608 *
10609 * }</blockquote>
10610 *
10611 * @param codePoint the character (Unicode code point)
10612 *
10613 * @return the Unicode name of the specified character, or null if
10614 * the code point is unassigned.
10615 *
10616 * @throws IllegalArgumentException if the specified
10617 * {@code codePoint} is not a valid Unicode
10618 * code point.
10619 *
10620 * @since 1.7
10621 */
10622 public static String getName(int codePoint) {
10623 if (!isValidCodePoint(codePoint)) {
10624 throw new IllegalArgumentException(
10625 String.format("Not a valid Unicode code point: 0x%X", codePoint));
10626 }
10627 String name = CharacterName.getInstance().getName(codePoint);
10628 if (name != null)
10629 return name;
10630 if (getType(codePoint) == UNASSIGNED)
10631 return null;
10632 UnicodeBlock block = UnicodeBlock.of(codePoint);
10633 if (block != null)
10634 return block.toString().replace('_', ' ') + " "
10635 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10636 // should never come here
10637 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10638 }
10639
10640 /**
10641 * Returns the code point value of the Unicode character specified by
10642 * the given Unicode character name.
10643 * <p>
10644 * Note: if a character is not assigned a name by the <i>UnicodeData</i>
10645 * file (part of the Unicode Character Database maintained by the Unicode
10646 * Consortium), its name is defined as the result of expression
10647 *
10648 * <blockquote>{@code
10649 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
10650 * + " "
10651 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
10652 *
10653 * }</blockquote>
10654 * <p>
10655 * The {@code name} matching is case insensitive, with any leading and
10656 * trailing whitespace character removed.
10657 *
10658 * @param name the Unicode character name
10659 *
10660 * @return the code point value of the character specified by its name.
10661 *
10662 * @throws IllegalArgumentException if the specified {@code name}
10663 * is not a valid Unicode character name.
10664 * @throws NullPointerException if {@code name} is {@code null}
10665 *
10666 * @since 9
10667 */
10668 public static int codePointOf(String name) {
10669 name = name.trim().toUpperCase(Locale.ROOT);
10670 int cp = CharacterName.getInstance().getCodePoint(name);
10671 if (cp != -1)
10672 return cp;
10673 try {
10674 int off = name.lastIndexOf(' ');
10675 if (off != -1) {
10676 cp = Integer.parseInt(name, off + 1, name.length(), 16);
10677 if (isValidCodePoint(cp) && name.equals(getName(cp)))
10678 return cp;
10679 }
10680 } catch (Exception x) {}
10681 throw new IllegalArgumentException("Unrecognized character name :" + name);
10682 }
10683 }