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