1 /*
2 * Copyright (c) 2002, 2015, 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 8.0.0.
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 name="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 name="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 name="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 * Zero {@code Character} constant.
172 */
173 private static final Character ZERO = new Character((char)0);
174
175 /**
176 * The {@code Class} instance representing the primitive type
177 * {@code char}.
178 *
179 * @since 1.1
180 */
181 @SuppressWarnings("unchecked")
182 public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char");
183
184 /*
185 * Normative general types
186 */
187
188 /*
189 * General character types
190 */
191
192 /**
193 * General category "Cn" in the Unicode specification.
194 * @since 1.1
195 */
196 public static final byte UNASSIGNED = 0;
197
198 /**
199 * General category "Lu" in the Unicode specification.
200 * @since 1.1
201 */
202 public static final byte UPPERCASE_LETTER = 1;
203
204 /**
205 * General category "Ll" in the Unicode specification.
206 * @since 1.1
207 */
208 public static final byte LOWERCASE_LETTER = 2;
209
210 /**
211 * General category "Lt" in the Unicode specification.
212 * @since 1.1
213 */
214 public static final byte TITLECASE_LETTER = 3;
215
216 /**
217 * General category "Lm" in the Unicode specification.
218 * @since 1.1
219 */
220 public static final byte MODIFIER_LETTER = 4;
221
222 /**
223 * General category "Lo" in the Unicode specification.
224 * @since 1.1
225 */
226 public static final byte OTHER_LETTER = 5;
227
228 /**
229 * General category "Mn" in the Unicode specification.
230 * @since 1.1
231 */
232 public static final byte NON_SPACING_MARK = 6;
233
234 /**
235 * General category "Me" in the Unicode specification.
236 * @since 1.1
237 */
238 public static final byte ENCLOSING_MARK = 7;
239
240 /**
241 * General category "Mc" in the Unicode specification.
242 * @since 1.1
243 */
244 public static final byte COMBINING_SPACING_MARK = 8;
245
246 /**
247 * General category "Nd" in the Unicode specification.
248 * @since 1.1
249 */
250 public static final byte DECIMAL_DIGIT_NUMBER = 9;
251
252 /**
253 * General category "Nl" in the Unicode specification.
254 * @since 1.1
255 */
256 public static final byte LETTER_NUMBER = 10;
257
258 /**
259 * General category "No" in the Unicode specification.
260 * @since 1.1
261 */
262 public static final byte OTHER_NUMBER = 11;
263
264 /**
265 * General category "Zs" in the Unicode specification.
266 * @since 1.1
267 */
268 public static final byte SPACE_SEPARATOR = 12;
269
270 /**
271 * General category "Zl" in the Unicode specification.
272 * @since 1.1
273 */
274 public static final byte LINE_SEPARATOR = 13;
275
276 /**
277 * General category "Zp" in the Unicode specification.
278 * @since 1.1
279 */
280 public static final byte PARAGRAPH_SEPARATOR = 14;
281
282 /**
283 * General category "Cc" in the Unicode specification.
284 * @since 1.1
285 */
286 public static final byte CONTROL = 15;
287
288 /**
289 * General category "Cf" in the Unicode specification.
290 * @since 1.1
291 */
292 public static final byte FORMAT = 16;
293
294 /**
295 * General category "Co" in the Unicode specification.
296 * @since 1.1
297 */
298 public static final byte PRIVATE_USE = 18;
299
300 /**
301 * General category "Cs" in the Unicode specification.
302 * @since 1.1
303 */
304 public static final byte SURROGATE = 19;
305
306 /**
307 * General category "Pd" in the Unicode specification.
308 * @since 1.1
309 */
310 public static final byte DASH_PUNCTUATION = 20;
311
312 /**
313 * General category "Ps" in the Unicode specification.
314 * @since 1.1
315 */
316 public static final byte START_PUNCTUATION = 21;
317
318 /**
319 * General category "Pe" in the Unicode specification.
320 * @since 1.1
321 */
322 public static final byte END_PUNCTUATION = 22;
323
324 /**
325 * General category "Pc" in the Unicode specification.
326 * @since 1.1
327 */
328 public static final byte CONNECTOR_PUNCTUATION = 23;
329
330 /**
331 * General category "Po" in the Unicode specification.
332 * @since 1.1
333 */
334 public static final byte OTHER_PUNCTUATION = 24;
335
336 /**
337 * General category "Sm" in the Unicode specification.
338 * @since 1.1
339 */
340 public static final byte MATH_SYMBOL = 25;
341
342 /**
343 * General category "Sc" in the Unicode specification.
344 * @since 1.1
345 */
346 public static final byte CURRENCY_SYMBOL = 26;
347
348 /**
349 * General category "Sk" in the Unicode specification.
350 * @since 1.1
351 */
352 public static final byte MODIFIER_SYMBOL = 27;
353
354 /**
355 * General category "So" in the Unicode specification.
356 * @since 1.1
357 */
358 public static final byte OTHER_SYMBOL = 28;
359
360 /**
361 * General category "Pi" in the Unicode specification.
362 * @since 1.4
363 */
364 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
365
366 /**
367 * General category "Pf" in the Unicode specification.
368 * @since 1.4
369 */
370 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
371
372 /**
373 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
374 */
375 static final int ERROR = 0xFFFFFFFF;
376
377
378 /**
379 * Undefined bidirectional character type. Undefined {@code char}
380 * values have undefined directionality in the Unicode specification.
381 * @since 1.4
382 */
383 public static final byte DIRECTIONALITY_UNDEFINED = -1;
384
385 /**
386 * Strong bidirectional character type "L" in the Unicode specification.
387 * @since 1.4
388 */
389 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
390
391 /**
392 * Strong bidirectional character type "R" in the Unicode specification.
393 * @since 1.4
394 */
395 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
396
397 /**
398 * Strong bidirectional character type "AL" in the Unicode specification.
399 * @since 1.4
400 */
401 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
402
403 /**
404 * Weak bidirectional character type "EN" in the Unicode specification.
405 * @since 1.4
406 */
407 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
408
409 /**
410 * Weak bidirectional character type "ES" in the Unicode specification.
411 * @since 1.4
412 */
413 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
414
415 /**
416 * Weak bidirectional character type "ET" in the Unicode specification.
417 * @since 1.4
418 */
419 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
420
421 /**
422 * Weak bidirectional character type "AN" in the Unicode specification.
423 * @since 1.4
424 */
425 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
426
427 /**
428 * Weak bidirectional character type "CS" in the Unicode specification.
429 * @since 1.4
430 */
431 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
432
433 /**
434 * Weak bidirectional character type "NSM" in the Unicode specification.
435 * @since 1.4
436 */
437 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
438
439 /**
440 * Weak bidirectional character type "BN" in the Unicode specification.
441 * @since 1.4
442 */
443 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
444
445 /**
446 * Neutral bidirectional character type "B" in the Unicode specification.
447 * @since 1.4
448 */
449 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
450
451 /**
452 * Neutral bidirectional character type "S" in the Unicode specification.
453 * @since 1.4
454 */
455 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
456
457 /**
458 * Neutral bidirectional character type "WS" in the Unicode specification.
459 * @since 1.4
460 */
461 public static final byte DIRECTIONALITY_WHITESPACE = 12;
462
463 /**
464 * Neutral bidirectional character type "ON" in the Unicode specification.
465 * @since 1.4
466 */
467 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
468
469 /**
470 * Strong bidirectional character type "LRE" in the Unicode specification.
471 * @since 1.4
472 */
473 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
474
475 /**
476 * Strong bidirectional character type "LRO" in the Unicode specification.
477 * @since 1.4
478 */
479 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
480
481 /**
482 * Strong bidirectional character type "RLE" in the Unicode specification.
483 * @since 1.4
484 */
485 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
486
487 /**
488 * Strong bidirectional character type "RLO" in the Unicode specification.
489 * @since 1.4
490 */
491 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
492
493 /**
494 * Weak bidirectional character type "PDF" in the Unicode specification.
495 * @since 1.4
496 */
497 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
498
499 /**
500 * Weak bidirectional character type "LRI" in the Unicode specification.
501 * @since 1.9
502 */
503 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
504
505 /**
506 * Weak bidirectional character type "RLI" in the Unicode specification.
507 * @since 1.9
508 */
509 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
510
511 /**
512 * Weak bidirectional character type "FSI" in the Unicode specification.
513 * @since 1.9
514 */
515 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
516
517 /**
518 * Weak bidirectional character type "PDI" in the Unicode specification.
519 * @since 1.9
520 */
521 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
522
523 /**
524 * The minimum value of a
525 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
526 * Unicode high-surrogate code unit</a>
527 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
528 * A high-surrogate is also known as a <i>leading-surrogate</i>.
529 *
530 * @since 1.5
531 */
532 public static final char MIN_HIGH_SURROGATE = '\uD800';
533
534 /**
535 * The maximum value of a
536 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
537 * Unicode high-surrogate code unit</a>
538 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
539 * A high-surrogate is also known as a <i>leading-surrogate</i>.
540 *
541 * @since 1.5
542 */
543 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
544
545 /**
546 * The minimum value of a
547 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
548 * Unicode low-surrogate code unit</a>
549 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
550 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
551 *
552 * @since 1.5
553 */
554 public static final char MIN_LOW_SURROGATE = '\uDC00';
555
556 /**
557 * The maximum value of a
558 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
559 * Unicode low-surrogate code unit</a>
560 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
561 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
562 *
563 * @since 1.5
564 */
565 public static final char MAX_LOW_SURROGATE = '\uDFFF';
566
567 /**
568 * The minimum value of a Unicode surrogate code unit in the
569 * UTF-16 encoding, constant {@code '\u005CuD800'}.
570 *
571 * @since 1.5
572 */
573 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
574
575 /**
576 * The maximum value of a Unicode surrogate code unit in the
577 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
578 *
579 * @since 1.5
580 */
581 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
582
583 /**
584 * The minimum value of a
585 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
586 * Unicode supplementary code point</a>, constant {@code U+10000}.
587 *
588 * @since 1.5
589 */
590 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
591
592 /**
593 * The minimum value of a
594 * <a href="http://www.unicode.org/glossary/#code_point">
595 * Unicode code point</a>, constant {@code U+0000}.
596 *
597 * @since 1.5
598 */
599 public static final int MIN_CODE_POINT = 0x000000;
600
601 /**
602 * The maximum value of a
603 * <a href="http://www.unicode.org/glossary/#code_point">
604 * Unicode code point</a>, constant {@code U+10FFFF}.
605 *
606 * @since 1.5
607 */
608 public static final int MAX_CODE_POINT = 0X10FFFF;
609
610
611 /**
612 * Instances of this class represent particular subsets of the Unicode
613 * character set. The only family of subsets defined in the
614 * {@code Character} class is {@link Character.UnicodeBlock}.
615 * Other portions of the Java API may define other subsets for their
616 * own purposes.
617 *
618 * @since 1.2
619 */
620 public static class Subset {
621
622 private String name;
623
624 /**
625 * Constructs a new {@code Subset} instance.
626 *
627 * @param name The name of this subset
628 * @exception NullPointerException if name is {@code null}
629 */
630 protected Subset(String name) {
631 if (name == null) {
632 throw new NullPointerException("name");
633 }
634 this.name = name;
635 }
636
637 /**
638 * Compares two {@code Subset} objects for equality.
639 * This method returns {@code true} if and only if
640 * {@code this} and the argument refer to the same
641 * object; since this method is {@code final}, this
642 * guarantee holds for all subclasses.
643 */
644 public final boolean equals(Object obj) {
645 return (this == obj);
646 }
647
648 /**
649 * Returns the standard hash code as defined by the
650 * {@link Object#hashCode} method. This method
651 * is {@code final} in order to ensure that the
652 * {@code equals} and {@code hashCode} methods will
653 * be consistent in all subclasses.
654 */
655 public final int hashCode() {
656 return super.hashCode();
657 }
658
659 /**
660 * Returns the name of this subset.
661 */
662 public final String toString() {
663 return name;
664 }
665 }
666
667 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
668 // for the latest specification of Unicode Blocks.
669
670 /**
671 * A family of character subsets representing the character blocks in the
672 * Unicode specification. Character blocks generally define characters
673 * used for a specific script or purpose. A character is contained by
674 * at most one Unicode block.
675 *
676 * @since 1.2
677 */
678 public static final class UnicodeBlock extends Subset {
679 /**
680 * 510 - the expected number of entities
681 * 0.75 - the default load factor of HashMap
682 */
683 private static Map<String, UnicodeBlock> map =
684 new HashMap<>((int)(510 / 0.75f + 1.0f));
685
686 /**
687 * Creates a UnicodeBlock with the given identifier name.
688 * This name must be the same as the block identifier.
689 */
690 private UnicodeBlock(String idName) {
691 super(idName);
692 map.put(idName, this);
693 }
694
695 /**
696 * Creates a UnicodeBlock with the given identifier name and
697 * alias name.
698 */
699 private UnicodeBlock(String idName, String alias) {
700 this(idName);
701 map.put(alias, this);
702 }
703
704 /**
705 * Creates a UnicodeBlock with the given identifier name and
706 * alias names.
707 */
708 private UnicodeBlock(String idName, String... aliases) {
709 this(idName);
710 for (String alias : aliases)
711 map.put(alias, this);
712 }
713
714 /**
715 * Constant for the "Basic Latin" Unicode character block.
716 * @since 1.2
717 */
718 public static final UnicodeBlock BASIC_LATIN =
719 new UnicodeBlock("BASIC_LATIN",
720 "BASIC LATIN",
721 "BASICLATIN");
722
723 /**
724 * Constant for the "Latin-1 Supplement" Unicode character block.
725 * @since 1.2
726 */
727 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
728 new UnicodeBlock("LATIN_1_SUPPLEMENT",
729 "LATIN-1 SUPPLEMENT",
730 "LATIN-1SUPPLEMENT");
731
732 /**
733 * Constant for the "Latin Extended-A" Unicode character block.
734 * @since 1.2
735 */
736 public static final UnicodeBlock LATIN_EXTENDED_A =
737 new UnicodeBlock("LATIN_EXTENDED_A",
738 "LATIN EXTENDED-A",
739 "LATINEXTENDED-A");
740
741 /**
742 * Constant for the "Latin Extended-B" Unicode character block.
743 * @since 1.2
744 */
745 public static final UnicodeBlock LATIN_EXTENDED_B =
746 new UnicodeBlock("LATIN_EXTENDED_B",
747 "LATIN EXTENDED-B",
748 "LATINEXTENDED-B");
749
750 /**
751 * Constant for the "IPA Extensions" Unicode character block.
752 * @since 1.2
753 */
754 public static final UnicodeBlock IPA_EXTENSIONS =
755 new UnicodeBlock("IPA_EXTENSIONS",
756 "IPA EXTENSIONS",
757 "IPAEXTENSIONS");
758
759 /**
760 * Constant for the "Spacing Modifier Letters" Unicode character block.
761 * @since 1.2
762 */
763 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
764 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
765 "SPACING MODIFIER LETTERS",
766 "SPACINGMODIFIERLETTERS");
767
768 /**
769 * Constant for the "Combining Diacritical Marks" Unicode character block.
770 * @since 1.2
771 */
772 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
773 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
774 "COMBINING DIACRITICAL MARKS",
775 "COMBININGDIACRITICALMARKS");
776
777 /**
778 * Constant for the "Greek and Coptic" Unicode character block.
779 * <p>
780 * This block was previously known as the "Greek" block.
781 *
782 * @since 1.2
783 */
784 public static final UnicodeBlock GREEK =
785 new UnicodeBlock("GREEK",
786 "GREEK AND COPTIC",
787 "GREEKANDCOPTIC");
788
789 /**
790 * Constant for the "Cyrillic" Unicode character block.
791 * @since 1.2
792 */
793 public static final UnicodeBlock CYRILLIC =
794 new UnicodeBlock("CYRILLIC");
795
796 /**
797 * Constant for the "Armenian" Unicode character block.
798 * @since 1.2
799 */
800 public static final UnicodeBlock ARMENIAN =
801 new UnicodeBlock("ARMENIAN");
802
803 /**
804 * Constant for the "Hebrew" Unicode character block.
805 * @since 1.2
806 */
807 public static final UnicodeBlock HEBREW =
808 new UnicodeBlock("HEBREW");
809
810 /**
811 * Constant for the "Arabic" Unicode character block.
812 * @since 1.2
813 */
814 public static final UnicodeBlock ARABIC =
815 new UnicodeBlock("ARABIC");
816
817 /**
818 * Constant for the "Devanagari" Unicode character block.
819 * @since 1.2
820 */
821 public static final UnicodeBlock DEVANAGARI =
822 new UnicodeBlock("DEVANAGARI");
823
824 /**
825 * Constant for the "Bengali" Unicode character block.
826 * @since 1.2
827 */
828 public static final UnicodeBlock BENGALI =
829 new UnicodeBlock("BENGALI");
830
831 /**
832 * Constant for the "Gurmukhi" Unicode character block.
833 * @since 1.2
834 */
835 public static final UnicodeBlock GURMUKHI =
836 new UnicodeBlock("GURMUKHI");
837
838 /**
839 * Constant for the "Gujarati" Unicode character block.
840 * @since 1.2
841 */
842 public static final UnicodeBlock GUJARATI =
843 new UnicodeBlock("GUJARATI");
844
845 /**
846 * Constant for the "Oriya" Unicode character block.
847 * @since 1.2
848 */
849 public static final UnicodeBlock ORIYA =
850 new UnicodeBlock("ORIYA");
851
852 /**
853 * Constant for the "Tamil" Unicode character block.
854 * @since 1.2
855 */
856 public static final UnicodeBlock TAMIL =
857 new UnicodeBlock("TAMIL");
858
859 /**
860 * Constant for the "Telugu" Unicode character block.
861 * @since 1.2
862 */
863 public static final UnicodeBlock TELUGU =
864 new UnicodeBlock("TELUGU");
865
866 /**
867 * Constant for the "Kannada" Unicode character block.
868 * @since 1.2
869 */
870 public static final UnicodeBlock KANNADA =
871 new UnicodeBlock("KANNADA");
872
873 /**
874 * Constant for the "Malayalam" Unicode character block.
875 * @since 1.2
876 */
877 public static final UnicodeBlock MALAYALAM =
878 new UnicodeBlock("MALAYALAM");
879
880 /**
881 * Constant for the "Thai" Unicode character block.
882 * @since 1.2
883 */
884 public static final UnicodeBlock THAI =
885 new UnicodeBlock("THAI");
886
887 /**
888 * Constant for the "Lao" Unicode character block.
889 * @since 1.2
890 */
891 public static final UnicodeBlock LAO =
892 new UnicodeBlock("LAO");
893
894 /**
895 * Constant for the "Tibetan" Unicode character block.
896 * @since 1.2
897 */
898 public static final UnicodeBlock TIBETAN =
899 new UnicodeBlock("TIBETAN");
900
901 /**
902 * Constant for the "Georgian" Unicode character block.
903 * @since 1.2
904 */
905 public static final UnicodeBlock GEORGIAN =
906 new UnicodeBlock("GEORGIAN");
907
908 /**
909 * Constant for the "Hangul Jamo" Unicode character block.
910 * @since 1.2
911 */
912 public static final UnicodeBlock HANGUL_JAMO =
913 new UnicodeBlock("HANGUL_JAMO",
914 "HANGUL JAMO",
915 "HANGULJAMO");
916
917 /**
918 * Constant for the "Latin Extended Additional" Unicode character block.
919 * @since 1.2
920 */
921 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
922 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
923 "LATIN EXTENDED ADDITIONAL",
924 "LATINEXTENDEDADDITIONAL");
925
926 /**
927 * Constant for the "Greek Extended" Unicode character block.
928 * @since 1.2
929 */
930 public static final UnicodeBlock GREEK_EXTENDED =
931 new UnicodeBlock("GREEK_EXTENDED",
932 "GREEK EXTENDED",
933 "GREEKEXTENDED");
934
935 /**
936 * Constant for the "General Punctuation" Unicode character block.
937 * @since 1.2
938 */
939 public static final UnicodeBlock GENERAL_PUNCTUATION =
940 new UnicodeBlock("GENERAL_PUNCTUATION",
941 "GENERAL PUNCTUATION",
942 "GENERALPUNCTUATION");
943
944 /**
945 * Constant for the "Superscripts and Subscripts" Unicode character
946 * block.
947 * @since 1.2
948 */
949 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
950 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
951 "SUPERSCRIPTS AND SUBSCRIPTS",
952 "SUPERSCRIPTSANDSUBSCRIPTS");
953
954 /**
955 * Constant for the "Currency Symbols" Unicode character block.
956 * @since 1.2
957 */
958 public static final UnicodeBlock CURRENCY_SYMBOLS =
959 new UnicodeBlock("CURRENCY_SYMBOLS",
960 "CURRENCY SYMBOLS",
961 "CURRENCYSYMBOLS");
962
963 /**
964 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
965 * character block.
966 * <p>
967 * This block was previously known as "Combining Marks for Symbols".
968 * @since 1.2
969 */
970 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
971 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
972 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
973 "COMBININGDIACRITICALMARKSFORSYMBOLS",
974 "COMBINING MARKS FOR SYMBOLS",
975 "COMBININGMARKSFORSYMBOLS");
976
977 /**
978 * Constant for the "Letterlike Symbols" Unicode character block.
979 * @since 1.2
980 */
981 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
982 new UnicodeBlock("LETTERLIKE_SYMBOLS",
983 "LETTERLIKE SYMBOLS",
984 "LETTERLIKESYMBOLS");
985
986 /**
987 * Constant for the "Number Forms" Unicode character block.
988 * @since 1.2
989 */
990 public static final UnicodeBlock NUMBER_FORMS =
991 new UnicodeBlock("NUMBER_FORMS",
992 "NUMBER FORMS",
993 "NUMBERFORMS");
994
995 /**
996 * Constant for the "Arrows" Unicode character block.
997 * @since 1.2
998 */
999 public static final UnicodeBlock ARROWS =
1000 new UnicodeBlock("ARROWS");
1001
1002 /**
1003 * Constant for the "Mathematical Operators" Unicode character block.
1004 * @since 1.2
1005 */
1006 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1007 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1008 "MATHEMATICAL OPERATORS",
1009 "MATHEMATICALOPERATORS");
1010
1011 /**
1012 * Constant for the "Miscellaneous Technical" Unicode character block.
1013 * @since 1.2
1014 */
1015 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1016 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1017 "MISCELLANEOUS TECHNICAL",
1018 "MISCELLANEOUSTECHNICAL");
1019
1020 /**
1021 * Constant for the "Control Pictures" Unicode character block.
1022 * @since 1.2
1023 */
1024 public static final UnicodeBlock CONTROL_PICTURES =
1025 new UnicodeBlock("CONTROL_PICTURES",
1026 "CONTROL PICTURES",
1027 "CONTROLPICTURES");
1028
1029 /**
1030 * Constant for the "Optical Character Recognition" Unicode character block.
1031 * @since 1.2
1032 */
1033 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1034 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1035 "OPTICAL CHARACTER RECOGNITION",
1036 "OPTICALCHARACTERRECOGNITION");
1037
1038 /**
1039 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1040 * @since 1.2
1041 */
1042 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1043 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1044 "ENCLOSED ALPHANUMERICS",
1045 "ENCLOSEDALPHANUMERICS");
1046
1047 /**
1048 * Constant for the "Box Drawing" Unicode character block.
1049 * @since 1.2
1050 */
1051 public static final UnicodeBlock BOX_DRAWING =
1052 new UnicodeBlock("BOX_DRAWING",
1053 "BOX DRAWING",
1054 "BOXDRAWING");
1055
1056 /**
1057 * Constant for the "Block Elements" Unicode character block.
1058 * @since 1.2
1059 */
1060 public static final UnicodeBlock BLOCK_ELEMENTS =
1061 new UnicodeBlock("BLOCK_ELEMENTS",
1062 "BLOCK ELEMENTS",
1063 "BLOCKELEMENTS");
1064
1065 /**
1066 * Constant for the "Geometric Shapes" Unicode character block.
1067 * @since 1.2
1068 */
1069 public static final UnicodeBlock GEOMETRIC_SHAPES =
1070 new UnicodeBlock("GEOMETRIC_SHAPES",
1071 "GEOMETRIC SHAPES",
1072 "GEOMETRICSHAPES");
1073
1074 /**
1075 * Constant for the "Miscellaneous Symbols" Unicode character block.
1076 * @since 1.2
1077 */
1078 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1079 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1080 "MISCELLANEOUS SYMBOLS",
1081 "MISCELLANEOUSSYMBOLS");
1082
1083 /**
1084 * Constant for the "Dingbats" Unicode character block.
1085 * @since 1.2
1086 */
1087 public static final UnicodeBlock DINGBATS =
1088 new UnicodeBlock("DINGBATS");
1089
1090 /**
1091 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1092 * @since 1.2
1093 */
1094 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1095 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1096 "CJK SYMBOLS AND PUNCTUATION",
1097 "CJKSYMBOLSANDPUNCTUATION");
1098
1099 /**
1100 * Constant for the "Hiragana" Unicode character block.
1101 * @since 1.2
1102 */
1103 public static final UnicodeBlock HIRAGANA =
1104 new UnicodeBlock("HIRAGANA");
1105
1106 /**
1107 * Constant for the "Katakana" Unicode character block.
1108 * @since 1.2
1109 */
1110 public static final UnicodeBlock KATAKANA =
1111 new UnicodeBlock("KATAKANA");
1112
1113 /**
1114 * Constant for the "Bopomofo" Unicode character block.
1115 * @since 1.2
1116 */
1117 public static final UnicodeBlock BOPOMOFO =
1118 new UnicodeBlock("BOPOMOFO");
1119
1120 /**
1121 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1122 * @since 1.2
1123 */
1124 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1125 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1126 "HANGUL COMPATIBILITY JAMO",
1127 "HANGULCOMPATIBILITYJAMO");
1128
1129 /**
1130 * Constant for the "Kanbun" Unicode character block.
1131 * @since 1.2
1132 */
1133 public static final UnicodeBlock KANBUN =
1134 new UnicodeBlock("KANBUN");
1135
1136 /**
1137 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1138 * @since 1.2
1139 */
1140 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1141 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1142 "ENCLOSED CJK LETTERS AND MONTHS",
1143 "ENCLOSEDCJKLETTERSANDMONTHS");
1144
1145 /**
1146 * Constant for the "CJK Compatibility" Unicode character block.
1147 * @since 1.2
1148 */
1149 public static final UnicodeBlock CJK_COMPATIBILITY =
1150 new UnicodeBlock("CJK_COMPATIBILITY",
1151 "CJK COMPATIBILITY",
1152 "CJKCOMPATIBILITY");
1153
1154 /**
1155 * Constant for the "CJK Unified Ideographs" Unicode character block.
1156 * @since 1.2
1157 */
1158 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1159 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1160 "CJK UNIFIED IDEOGRAPHS",
1161 "CJKUNIFIEDIDEOGRAPHS");
1162
1163 /**
1164 * Constant for the "Hangul Syllables" Unicode character block.
1165 * @since 1.2
1166 */
1167 public static final UnicodeBlock HANGUL_SYLLABLES =
1168 new UnicodeBlock("HANGUL_SYLLABLES",
1169 "HANGUL SYLLABLES",
1170 "HANGULSYLLABLES");
1171
1172 /**
1173 * Constant for the "Private Use Area" Unicode character block.
1174 * @since 1.2
1175 */
1176 public static final UnicodeBlock PRIVATE_USE_AREA =
1177 new UnicodeBlock("PRIVATE_USE_AREA",
1178 "PRIVATE USE AREA",
1179 "PRIVATEUSEAREA");
1180
1181 /**
1182 * Constant for the "CJK Compatibility Ideographs" Unicode character
1183 * block.
1184 * @since 1.2
1185 */
1186 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1187 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1188 "CJK COMPATIBILITY IDEOGRAPHS",
1189 "CJKCOMPATIBILITYIDEOGRAPHS");
1190
1191 /**
1192 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1193 * @since 1.2
1194 */
1195 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1196 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1197 "ALPHABETIC PRESENTATION FORMS",
1198 "ALPHABETICPRESENTATIONFORMS");
1199
1200 /**
1201 * Constant for the "Arabic Presentation Forms-A" Unicode character
1202 * block.
1203 * @since 1.2
1204 */
1205 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1206 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1207 "ARABIC PRESENTATION FORMS-A",
1208 "ARABICPRESENTATIONFORMS-A");
1209
1210 /**
1211 * Constant for the "Combining Half Marks" Unicode character block.
1212 * @since 1.2
1213 */
1214 public static final UnicodeBlock COMBINING_HALF_MARKS =
1215 new UnicodeBlock("COMBINING_HALF_MARKS",
1216 "COMBINING HALF MARKS",
1217 "COMBININGHALFMARKS");
1218
1219 /**
1220 * Constant for the "CJK Compatibility Forms" Unicode character block.
1221 * @since 1.2
1222 */
1223 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1224 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1225 "CJK COMPATIBILITY FORMS",
1226 "CJKCOMPATIBILITYFORMS");
1227
1228 /**
1229 * Constant for the "Small Form Variants" Unicode character block.
1230 * @since 1.2
1231 */
1232 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1233 new UnicodeBlock("SMALL_FORM_VARIANTS",
1234 "SMALL FORM VARIANTS",
1235 "SMALLFORMVARIANTS");
1236
1237 /**
1238 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1239 * @since 1.2
1240 */
1241 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1242 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1243 "ARABIC PRESENTATION FORMS-B",
1244 "ARABICPRESENTATIONFORMS-B");
1245
1246 /**
1247 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1248 * block.
1249 * @since 1.2
1250 */
1251 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1252 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1253 "HALFWIDTH AND FULLWIDTH FORMS",
1254 "HALFWIDTHANDFULLWIDTHFORMS");
1255
1256 /**
1257 * Constant for the "Specials" Unicode character block.
1258 * @since 1.2
1259 */
1260 public static final UnicodeBlock SPECIALS =
1261 new UnicodeBlock("SPECIALS");
1262
1263 /**
1264 * @deprecated As of J2SE 5, use {@link #HIGH_SURROGATES},
1265 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and
1266 * {@link #LOW_SURROGATES}. These new constants match
1267 * the block definitions of the Unicode Standard.
1268 * The {@link #of(char)} and {@link #of(int)} methods
1269 * return the new constants, not SURROGATES_AREA.
1270 */
1271 @Deprecated
1272 public static final UnicodeBlock SURROGATES_AREA =
1273 new UnicodeBlock("SURROGATES_AREA");
1274
1275 /**
1276 * Constant for the "Syriac" Unicode character block.
1277 * @since 1.4
1278 */
1279 public static final UnicodeBlock SYRIAC =
1280 new UnicodeBlock("SYRIAC");
1281
1282 /**
1283 * Constant for the "Thaana" Unicode character block.
1284 * @since 1.4
1285 */
1286 public static final UnicodeBlock THAANA =
1287 new UnicodeBlock("THAANA");
1288
1289 /**
1290 * Constant for the "Sinhala" Unicode character block.
1291 * @since 1.4
1292 */
1293 public static final UnicodeBlock SINHALA =
1294 new UnicodeBlock("SINHALA");
1295
1296 /**
1297 * Constant for the "Myanmar" Unicode character block.
1298 * @since 1.4
1299 */
1300 public static final UnicodeBlock MYANMAR =
1301 new UnicodeBlock("MYANMAR");
1302
1303 /**
1304 * Constant for the "Ethiopic" Unicode character block.
1305 * @since 1.4
1306 */
1307 public static final UnicodeBlock ETHIOPIC =
1308 new UnicodeBlock("ETHIOPIC");
1309
1310 /**
1311 * Constant for the "Cherokee" Unicode character block.
1312 * @since 1.4
1313 */
1314 public static final UnicodeBlock CHEROKEE =
1315 new UnicodeBlock("CHEROKEE");
1316
1317 /**
1318 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1319 * @since 1.4
1320 */
1321 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1322 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1323 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1324 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1325
1326 /**
1327 * Constant for the "Ogham" Unicode character block.
1328 * @since 1.4
1329 */
1330 public static final UnicodeBlock OGHAM =
1331 new UnicodeBlock("OGHAM");
1332
1333 /**
1334 * Constant for the "Runic" Unicode character block.
1335 * @since 1.4
1336 */
1337 public static final UnicodeBlock RUNIC =
1338 new UnicodeBlock("RUNIC");
1339
1340 /**
1341 * Constant for the "Khmer" Unicode character block.
1342 * @since 1.4
1343 */
1344 public static final UnicodeBlock KHMER =
1345 new UnicodeBlock("KHMER");
1346
1347 /**
1348 * Constant for the "Mongolian" Unicode character block.
1349 * @since 1.4
1350 */
1351 public static final UnicodeBlock MONGOLIAN =
1352 new UnicodeBlock("MONGOLIAN");
1353
1354 /**
1355 * Constant for the "Braille Patterns" Unicode character block.
1356 * @since 1.4
1357 */
1358 public static final UnicodeBlock BRAILLE_PATTERNS =
1359 new UnicodeBlock("BRAILLE_PATTERNS",
1360 "BRAILLE PATTERNS",
1361 "BRAILLEPATTERNS");
1362
1363 /**
1364 * Constant for the "CJK Radicals Supplement" Unicode character block.
1365 * @since 1.4
1366 */
1367 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1368 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1369 "CJK RADICALS SUPPLEMENT",
1370 "CJKRADICALSSUPPLEMENT");
1371
1372 /**
1373 * Constant for the "Kangxi Radicals" Unicode character block.
1374 * @since 1.4
1375 */
1376 public static final UnicodeBlock KANGXI_RADICALS =
1377 new UnicodeBlock("KANGXI_RADICALS",
1378 "KANGXI RADICALS",
1379 "KANGXIRADICALS");
1380
1381 /**
1382 * Constant for the "Ideographic Description Characters" Unicode character block.
1383 * @since 1.4
1384 */
1385 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1386 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1387 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1388 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1389
1390 /**
1391 * Constant for the "Bopomofo Extended" Unicode character block.
1392 * @since 1.4
1393 */
1394 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1395 new UnicodeBlock("BOPOMOFO_EXTENDED",
1396 "BOPOMOFO EXTENDED",
1397 "BOPOMOFOEXTENDED");
1398
1399 /**
1400 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1401 * @since 1.4
1402 */
1403 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1404 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1405 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1406 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1407
1408 /**
1409 * Constant for the "Yi Syllables" Unicode character block.
1410 * @since 1.4
1411 */
1412 public static final UnicodeBlock YI_SYLLABLES =
1413 new UnicodeBlock("YI_SYLLABLES",
1414 "YI SYLLABLES",
1415 "YISYLLABLES");
1416
1417 /**
1418 * Constant for the "Yi Radicals" Unicode character block.
1419 * @since 1.4
1420 */
1421 public static final UnicodeBlock YI_RADICALS =
1422 new UnicodeBlock("YI_RADICALS",
1423 "YI RADICALS",
1424 "YIRADICALS");
1425
1426 /**
1427 * Constant for the "Cyrillic Supplementary" Unicode character block.
1428 * @since 1.5
1429 */
1430 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1431 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1432 "CYRILLIC SUPPLEMENTARY",
1433 "CYRILLICSUPPLEMENTARY",
1434 "CYRILLIC SUPPLEMENT",
1435 "CYRILLICSUPPLEMENT");
1436
1437 /**
1438 * Constant for the "Tagalog" Unicode character block.
1439 * @since 1.5
1440 */
1441 public static final UnicodeBlock TAGALOG =
1442 new UnicodeBlock("TAGALOG");
1443
1444 /**
1445 * Constant for the "Hanunoo" Unicode character block.
1446 * @since 1.5
1447 */
1448 public static final UnicodeBlock HANUNOO =
1449 new UnicodeBlock("HANUNOO");
1450
1451 /**
1452 * Constant for the "Buhid" Unicode character block.
1453 * @since 1.5
1454 */
1455 public static final UnicodeBlock BUHID =
1456 new UnicodeBlock("BUHID");
1457
1458 /**
1459 * Constant for the "Tagbanwa" Unicode character block.
1460 * @since 1.5
1461 */
1462 public static final UnicodeBlock TAGBANWA =
1463 new UnicodeBlock("TAGBANWA");
1464
1465 /**
1466 * Constant for the "Limbu" Unicode character block.
1467 * @since 1.5
1468 */
1469 public static final UnicodeBlock LIMBU =
1470 new UnicodeBlock("LIMBU");
1471
1472 /**
1473 * Constant for the "Tai Le" Unicode character block.
1474 * @since 1.5
1475 */
1476 public static final UnicodeBlock TAI_LE =
1477 new UnicodeBlock("TAI_LE",
1478 "TAI LE",
1479 "TAILE");
1480
1481 /**
1482 * Constant for the "Khmer Symbols" Unicode character block.
1483 * @since 1.5
1484 */
1485 public static final UnicodeBlock KHMER_SYMBOLS =
1486 new UnicodeBlock("KHMER_SYMBOLS",
1487 "KHMER SYMBOLS",
1488 "KHMERSYMBOLS");
1489
1490 /**
1491 * Constant for the "Phonetic Extensions" Unicode character block.
1492 * @since 1.5
1493 */
1494 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1495 new UnicodeBlock("PHONETIC_EXTENSIONS",
1496 "PHONETIC EXTENSIONS",
1497 "PHONETICEXTENSIONS");
1498
1499 /**
1500 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1501 * @since 1.5
1502 */
1503 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1504 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1505 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1506 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1507
1508 /**
1509 * Constant for the "Supplemental Arrows-A" Unicode character block.
1510 * @since 1.5
1511 */
1512 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1513 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1514 "SUPPLEMENTAL ARROWS-A",
1515 "SUPPLEMENTALARROWS-A");
1516
1517 /**
1518 * Constant for the "Supplemental Arrows-B" Unicode character block.
1519 * @since 1.5
1520 */
1521 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1522 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1523 "SUPPLEMENTAL ARROWS-B",
1524 "SUPPLEMENTALARROWS-B");
1525
1526 /**
1527 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1528 * character block.
1529 * @since 1.5
1530 */
1531 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1532 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1533 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1534 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1535
1536 /**
1537 * Constant for the "Supplemental Mathematical Operators" Unicode
1538 * character block.
1539 * @since 1.5
1540 */
1541 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1542 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1543 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1544 "SUPPLEMENTALMATHEMATICALOPERATORS");
1545
1546 /**
1547 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1548 * block.
1549 * @since 1.5
1550 */
1551 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1552 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1553 "MISCELLANEOUS SYMBOLS AND ARROWS",
1554 "MISCELLANEOUSSYMBOLSANDARROWS");
1555
1556 /**
1557 * Constant for the "Katakana Phonetic Extensions" Unicode character
1558 * block.
1559 * @since 1.5
1560 */
1561 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1562 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1563 "KATAKANA PHONETIC EXTENSIONS",
1564 "KATAKANAPHONETICEXTENSIONS");
1565
1566 /**
1567 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1568 * @since 1.5
1569 */
1570 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1571 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1572 "YIJING HEXAGRAM SYMBOLS",
1573 "YIJINGHEXAGRAMSYMBOLS");
1574
1575 /**
1576 * Constant for the "Variation Selectors" Unicode character block.
1577 * @since 1.5
1578 */
1579 public static final UnicodeBlock VARIATION_SELECTORS =
1580 new UnicodeBlock("VARIATION_SELECTORS",
1581 "VARIATION SELECTORS",
1582 "VARIATIONSELECTORS");
1583
1584 /**
1585 * Constant for the "Linear B Syllabary" Unicode character block.
1586 * @since 1.5
1587 */
1588 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1589 new UnicodeBlock("LINEAR_B_SYLLABARY",
1590 "LINEAR B SYLLABARY",
1591 "LINEARBSYLLABARY");
1592
1593 /**
1594 * Constant for the "Linear B Ideograms" Unicode character block.
1595 * @since 1.5
1596 */
1597 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1598 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1599 "LINEAR B IDEOGRAMS",
1600 "LINEARBIDEOGRAMS");
1601
1602 /**
1603 * Constant for the "Aegean Numbers" Unicode character block.
1604 * @since 1.5
1605 */
1606 public static final UnicodeBlock AEGEAN_NUMBERS =
1607 new UnicodeBlock("AEGEAN_NUMBERS",
1608 "AEGEAN NUMBERS",
1609 "AEGEANNUMBERS");
1610
1611 /**
1612 * Constant for the "Old Italic" Unicode character block.
1613 * @since 1.5
1614 */
1615 public static final UnicodeBlock OLD_ITALIC =
1616 new UnicodeBlock("OLD_ITALIC",
1617 "OLD ITALIC",
1618 "OLDITALIC");
1619
1620 /**
1621 * Constant for the "Gothic" Unicode character block.
1622 * @since 1.5
1623 */
1624 public static final UnicodeBlock GOTHIC =
1625 new UnicodeBlock("GOTHIC");
1626
1627 /**
1628 * Constant for the "Ugaritic" Unicode character block.
1629 * @since 1.5
1630 */
1631 public static final UnicodeBlock UGARITIC =
1632 new UnicodeBlock("UGARITIC");
1633
1634 /**
1635 * Constant for the "Deseret" Unicode character block.
1636 * @since 1.5
1637 */
1638 public static final UnicodeBlock DESERET =
1639 new UnicodeBlock("DESERET");
1640
1641 /**
1642 * Constant for the "Shavian" Unicode character block.
1643 * @since 1.5
1644 */
1645 public static final UnicodeBlock SHAVIAN =
1646 new UnicodeBlock("SHAVIAN");
1647
1648 /**
1649 * Constant for the "Osmanya" Unicode character block.
1650 * @since 1.5
1651 */
1652 public static final UnicodeBlock OSMANYA =
1653 new UnicodeBlock("OSMANYA");
1654
1655 /**
1656 * Constant for the "Cypriot Syllabary" Unicode character block.
1657 * @since 1.5
1658 */
1659 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1660 new UnicodeBlock("CYPRIOT_SYLLABARY",
1661 "CYPRIOT SYLLABARY",
1662 "CYPRIOTSYLLABARY");
1663
1664 /**
1665 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1666 * @since 1.5
1667 */
1668 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1669 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1670 "BYZANTINE MUSICAL SYMBOLS",
1671 "BYZANTINEMUSICALSYMBOLS");
1672
1673 /**
1674 * Constant for the "Musical Symbols" Unicode character block.
1675 * @since 1.5
1676 */
1677 public static final UnicodeBlock MUSICAL_SYMBOLS =
1678 new UnicodeBlock("MUSICAL_SYMBOLS",
1679 "MUSICAL SYMBOLS",
1680 "MUSICALSYMBOLS");
1681
1682 /**
1683 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1684 * @since 1.5
1685 */
1686 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1687 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1688 "TAI XUAN JING SYMBOLS",
1689 "TAIXUANJINGSYMBOLS");
1690
1691 /**
1692 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1693 * character block.
1694 * @since 1.5
1695 */
1696 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1697 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1698 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1699 "MATHEMATICALALPHANUMERICSYMBOLS");
1700
1701 /**
1702 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1703 * character block.
1704 * @since 1.5
1705 */
1706 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1707 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1708 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1709 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1710
1711 /**
1712 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1713 * @since 1.5
1714 */
1715 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1716 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1717 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1718 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1719
1720 /**
1721 * Constant for the "Tags" Unicode character block.
1722 * @since 1.5
1723 */
1724 public static final UnicodeBlock TAGS =
1725 new UnicodeBlock("TAGS");
1726
1727 /**
1728 * Constant for the "Variation Selectors Supplement" Unicode character
1729 * block.
1730 * @since 1.5
1731 */
1732 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1733 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1734 "VARIATION SELECTORS SUPPLEMENT",
1735 "VARIATIONSELECTORSSUPPLEMENT");
1736
1737 /**
1738 * Constant for the "Supplementary Private Use Area-A" Unicode character
1739 * block.
1740 * @since 1.5
1741 */
1742 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1743 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1744 "SUPPLEMENTARY PRIVATE USE AREA-A",
1745 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1746
1747 /**
1748 * Constant for the "Supplementary Private Use Area-B" Unicode character
1749 * block.
1750 * @since 1.5
1751 */
1752 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1753 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1754 "SUPPLEMENTARY PRIVATE USE AREA-B",
1755 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1756
1757 /**
1758 * Constant for the "High Surrogates" Unicode character block.
1759 * This block represents codepoint values in the high surrogate
1760 * range: U+D800 through U+DB7F
1761 *
1762 * @since 1.5
1763 */
1764 public static final UnicodeBlock HIGH_SURROGATES =
1765 new UnicodeBlock("HIGH_SURROGATES",
1766 "HIGH SURROGATES",
1767 "HIGHSURROGATES");
1768
1769 /**
1770 * Constant for the "High Private Use Surrogates" Unicode character
1771 * block.
1772 * This block represents codepoint values in the private use high
1773 * surrogate range: U+DB80 through U+DBFF
1774 *
1775 * @since 1.5
1776 */
1777 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1778 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1779 "HIGH PRIVATE USE SURROGATES",
1780 "HIGHPRIVATEUSESURROGATES");
1781
1782 /**
1783 * Constant for the "Low Surrogates" Unicode character block.
1784 * This block represents codepoint values in the low surrogate
1785 * range: U+DC00 through U+DFFF
1786 *
1787 * @since 1.5
1788 */
1789 public static final UnicodeBlock LOW_SURROGATES =
1790 new UnicodeBlock("LOW_SURROGATES",
1791 "LOW SURROGATES",
1792 "LOWSURROGATES");
1793
1794 /**
1795 * Constant for the "Arabic Supplement" Unicode character block.
1796 * @since 1.7
1797 */
1798 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1799 new UnicodeBlock("ARABIC_SUPPLEMENT",
1800 "ARABIC SUPPLEMENT",
1801 "ARABICSUPPLEMENT");
1802
1803 /**
1804 * Constant for the "NKo" Unicode character block.
1805 * @since 1.7
1806 */
1807 public static final UnicodeBlock NKO =
1808 new UnicodeBlock("NKO");
1809
1810 /**
1811 * Constant for the "Samaritan" Unicode character block.
1812 * @since 1.7
1813 */
1814 public static final UnicodeBlock SAMARITAN =
1815 new UnicodeBlock("SAMARITAN");
1816
1817 /**
1818 * Constant for the "Mandaic" Unicode character block.
1819 * @since 1.7
1820 */
1821 public static final UnicodeBlock MANDAIC =
1822 new UnicodeBlock("MANDAIC");
1823
1824 /**
1825 * Constant for the "Ethiopic Supplement" Unicode character block.
1826 * @since 1.7
1827 */
1828 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1829 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1830 "ETHIOPIC SUPPLEMENT",
1831 "ETHIOPICSUPPLEMENT");
1832
1833 /**
1834 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1835 * Unicode character block.
1836 * @since 1.7
1837 */
1838 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1839 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1840 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1841 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1842
1843 /**
1844 * Constant for the "New Tai Lue" Unicode character block.
1845 * @since 1.7
1846 */
1847 public static final UnicodeBlock NEW_TAI_LUE =
1848 new UnicodeBlock("NEW_TAI_LUE",
1849 "NEW TAI LUE",
1850 "NEWTAILUE");
1851
1852 /**
1853 * Constant for the "Buginese" Unicode character block.
1854 * @since 1.7
1855 */
1856 public static final UnicodeBlock BUGINESE =
1857 new UnicodeBlock("BUGINESE");
1858
1859 /**
1860 * Constant for the "Tai Tham" Unicode character block.
1861 * @since 1.7
1862 */
1863 public static final UnicodeBlock TAI_THAM =
1864 new UnicodeBlock("TAI_THAM",
1865 "TAI THAM",
1866 "TAITHAM");
1867
1868 /**
1869 * Constant for the "Balinese" Unicode character block.
1870 * @since 1.7
1871 */
1872 public static final UnicodeBlock BALINESE =
1873 new UnicodeBlock("BALINESE");
1874
1875 /**
1876 * Constant for the "Sundanese" Unicode character block.
1877 * @since 1.7
1878 */
1879 public static final UnicodeBlock SUNDANESE =
1880 new UnicodeBlock("SUNDANESE");
1881
1882 /**
1883 * Constant for the "Batak" Unicode character block.
1884 * @since 1.7
1885 */
1886 public static final UnicodeBlock BATAK =
1887 new UnicodeBlock("BATAK");
1888
1889 /**
1890 * Constant for the "Lepcha" Unicode character block.
1891 * @since 1.7
1892 */
1893 public static final UnicodeBlock LEPCHA =
1894 new UnicodeBlock("LEPCHA");
1895
1896 /**
1897 * Constant for the "Ol Chiki" Unicode character block.
1898 * @since 1.7
1899 */
1900 public static final UnicodeBlock OL_CHIKI =
1901 new UnicodeBlock("OL_CHIKI",
1902 "OL CHIKI",
1903 "OLCHIKI");
1904
1905 /**
1906 * Constant for the "Vedic Extensions" Unicode character block.
1907 * @since 1.7
1908 */
1909 public static final UnicodeBlock VEDIC_EXTENSIONS =
1910 new UnicodeBlock("VEDIC_EXTENSIONS",
1911 "VEDIC EXTENSIONS",
1912 "VEDICEXTENSIONS");
1913
1914 /**
1915 * Constant for the "Phonetic Extensions Supplement" Unicode character
1916 * block.
1917 * @since 1.7
1918 */
1919 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1920 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1921 "PHONETIC EXTENSIONS SUPPLEMENT",
1922 "PHONETICEXTENSIONSSUPPLEMENT");
1923
1924 /**
1925 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1926 * character block.
1927 * @since 1.7
1928 */
1929 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1930 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1931 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1932 "COMBININGDIACRITICALMARKSSUPPLEMENT");
1933
1934 /**
1935 * Constant for the "Glagolitic" Unicode character block.
1936 * @since 1.7
1937 */
1938 public static final UnicodeBlock GLAGOLITIC =
1939 new UnicodeBlock("GLAGOLITIC");
1940
1941 /**
1942 * Constant for the "Latin Extended-C" Unicode character block.
1943 * @since 1.7
1944 */
1945 public static final UnicodeBlock LATIN_EXTENDED_C =
1946 new UnicodeBlock("LATIN_EXTENDED_C",
1947 "LATIN EXTENDED-C",
1948 "LATINEXTENDED-C");
1949
1950 /**
1951 * Constant for the "Coptic" Unicode character block.
1952 * @since 1.7
1953 */
1954 public static final UnicodeBlock COPTIC =
1955 new UnicodeBlock("COPTIC");
1956
1957 /**
1958 * Constant for the "Georgian Supplement" Unicode character block.
1959 * @since 1.7
1960 */
1961 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
1962 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
1963 "GEORGIAN SUPPLEMENT",
1964 "GEORGIANSUPPLEMENT");
1965
1966 /**
1967 * Constant for the "Tifinagh" Unicode character block.
1968 * @since 1.7
1969 */
1970 public static final UnicodeBlock TIFINAGH =
1971 new UnicodeBlock("TIFINAGH");
1972
1973 /**
1974 * Constant for the "Ethiopic Extended" Unicode character block.
1975 * @since 1.7
1976 */
1977 public static final UnicodeBlock ETHIOPIC_EXTENDED =
1978 new UnicodeBlock("ETHIOPIC_EXTENDED",
1979 "ETHIOPIC EXTENDED",
1980 "ETHIOPICEXTENDED");
1981
1982 /**
1983 * Constant for the "Cyrillic Extended-A" Unicode character block.
1984 * @since 1.7
1985 */
1986 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
1987 new UnicodeBlock("CYRILLIC_EXTENDED_A",
1988 "CYRILLIC EXTENDED-A",
1989 "CYRILLICEXTENDED-A");
1990
1991 /**
1992 * Constant for the "Supplemental Punctuation" Unicode character block.
1993 * @since 1.7
1994 */
1995 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
1996 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
1997 "SUPPLEMENTAL PUNCTUATION",
1998 "SUPPLEMENTALPUNCTUATION");
1999
2000 /**
2001 * Constant for the "CJK Strokes" Unicode character block.
2002 * @since 1.7
2003 */
2004 public static final UnicodeBlock CJK_STROKES =
2005 new UnicodeBlock("CJK_STROKES",
2006 "CJK STROKES",
2007 "CJKSTROKES");
2008
2009 /**
2010 * Constant for the "Lisu" Unicode character block.
2011 * @since 1.7
2012 */
2013 public static final UnicodeBlock LISU =
2014 new UnicodeBlock("LISU");
2015
2016 /**
2017 * Constant for the "Vai" Unicode character block.
2018 * @since 1.7
2019 */
2020 public static final UnicodeBlock VAI =
2021 new UnicodeBlock("VAI");
2022
2023 /**
2024 * Constant for the "Cyrillic Extended-B" Unicode character block.
2025 * @since 1.7
2026 */
2027 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2028 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2029 "CYRILLIC EXTENDED-B",
2030 "CYRILLICEXTENDED-B");
2031
2032 /**
2033 * Constant for the "Bamum" Unicode character block.
2034 * @since 1.7
2035 */
2036 public static final UnicodeBlock BAMUM =
2037 new UnicodeBlock("BAMUM");
2038
2039 /**
2040 * Constant for the "Modifier Tone Letters" Unicode character block.
2041 * @since 1.7
2042 */
2043 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2044 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2045 "MODIFIER TONE LETTERS",
2046 "MODIFIERTONELETTERS");
2047
2048 /**
2049 * Constant for the "Latin Extended-D" Unicode character block.
2050 * @since 1.7
2051 */
2052 public static final UnicodeBlock LATIN_EXTENDED_D =
2053 new UnicodeBlock("LATIN_EXTENDED_D",
2054 "LATIN EXTENDED-D",
2055 "LATINEXTENDED-D");
2056
2057 /**
2058 * Constant for the "Syloti Nagri" Unicode character block.
2059 * @since 1.7
2060 */
2061 public static final UnicodeBlock SYLOTI_NAGRI =
2062 new UnicodeBlock("SYLOTI_NAGRI",
2063 "SYLOTI NAGRI",
2064 "SYLOTINAGRI");
2065
2066 /**
2067 * Constant for the "Common Indic Number Forms" Unicode character block.
2068 * @since 1.7
2069 */
2070 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2071 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2072 "COMMON INDIC NUMBER FORMS",
2073 "COMMONINDICNUMBERFORMS");
2074
2075 /**
2076 * Constant for the "Phags-pa" Unicode character block.
2077 * @since 1.7
2078 */
2079 public static final UnicodeBlock PHAGS_PA =
2080 new UnicodeBlock("PHAGS_PA",
2081 "PHAGS-PA");
2082
2083 /**
2084 * Constant for the "Saurashtra" Unicode character block.
2085 * @since 1.7
2086 */
2087 public static final UnicodeBlock SAURASHTRA =
2088 new UnicodeBlock("SAURASHTRA");
2089
2090 /**
2091 * Constant for the "Devanagari Extended" Unicode character block.
2092 * @since 1.7
2093 */
2094 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2095 new UnicodeBlock("DEVANAGARI_EXTENDED",
2096 "DEVANAGARI EXTENDED",
2097 "DEVANAGARIEXTENDED");
2098
2099 /**
2100 * Constant for the "Kayah Li" Unicode character block.
2101 * @since 1.7
2102 */
2103 public static final UnicodeBlock KAYAH_LI =
2104 new UnicodeBlock("KAYAH_LI",
2105 "KAYAH LI",
2106 "KAYAHLI");
2107
2108 /**
2109 * Constant for the "Rejang" Unicode character block.
2110 * @since 1.7
2111 */
2112 public static final UnicodeBlock REJANG =
2113 new UnicodeBlock("REJANG");
2114
2115 /**
2116 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2117 * @since 1.7
2118 */
2119 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2120 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2121 "HANGUL JAMO EXTENDED-A",
2122 "HANGULJAMOEXTENDED-A");
2123
2124 /**
2125 * Constant for the "Javanese" Unicode character block.
2126 * @since 1.7
2127 */
2128 public static final UnicodeBlock JAVANESE =
2129 new UnicodeBlock("JAVANESE");
2130
2131 /**
2132 * Constant for the "Cham" Unicode character block.
2133 * @since 1.7
2134 */
2135 public static final UnicodeBlock CHAM =
2136 new UnicodeBlock("CHAM");
2137
2138 /**
2139 * Constant for the "Myanmar Extended-A" Unicode character block.
2140 * @since 1.7
2141 */
2142 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2143 new UnicodeBlock("MYANMAR_EXTENDED_A",
2144 "MYANMAR EXTENDED-A",
2145 "MYANMAREXTENDED-A");
2146
2147 /**
2148 * Constant for the "Tai Viet" Unicode character block.
2149 * @since 1.7
2150 */
2151 public static final UnicodeBlock TAI_VIET =
2152 new UnicodeBlock("TAI_VIET",
2153 "TAI VIET",
2154 "TAIVIET");
2155
2156 /**
2157 * Constant for the "Ethiopic Extended-A" Unicode character block.
2158 * @since 1.7
2159 */
2160 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2161 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2162 "ETHIOPIC EXTENDED-A",
2163 "ETHIOPICEXTENDED-A");
2164
2165 /**
2166 * Constant for the "Meetei Mayek" Unicode character block.
2167 * @since 1.7
2168 */
2169 public static final UnicodeBlock MEETEI_MAYEK =
2170 new UnicodeBlock("MEETEI_MAYEK",
2171 "MEETEI MAYEK",
2172 "MEETEIMAYEK");
2173
2174 /**
2175 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2176 * @since 1.7
2177 */
2178 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2179 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2180 "HANGUL JAMO EXTENDED-B",
2181 "HANGULJAMOEXTENDED-B");
2182
2183 /**
2184 * Constant for the "Vertical Forms" Unicode character block.
2185 * @since 1.7
2186 */
2187 public static final UnicodeBlock VERTICAL_FORMS =
2188 new UnicodeBlock("VERTICAL_FORMS",
2189 "VERTICAL FORMS",
2190 "VERTICALFORMS");
2191
2192 /**
2193 * Constant for the "Ancient Greek Numbers" Unicode character block.
2194 * @since 1.7
2195 */
2196 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2197 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2198 "ANCIENT GREEK NUMBERS",
2199 "ANCIENTGREEKNUMBERS");
2200
2201 /**
2202 * Constant for the "Ancient Symbols" Unicode character block.
2203 * @since 1.7
2204 */
2205 public static final UnicodeBlock ANCIENT_SYMBOLS =
2206 new UnicodeBlock("ANCIENT_SYMBOLS",
2207 "ANCIENT SYMBOLS",
2208 "ANCIENTSYMBOLS");
2209
2210 /**
2211 * Constant for the "Phaistos Disc" Unicode character block.
2212 * @since 1.7
2213 */
2214 public static final UnicodeBlock PHAISTOS_DISC =
2215 new UnicodeBlock("PHAISTOS_DISC",
2216 "PHAISTOS DISC",
2217 "PHAISTOSDISC");
2218
2219 /**
2220 * Constant for the "Lycian" Unicode character block.
2221 * @since 1.7
2222 */
2223 public static final UnicodeBlock LYCIAN =
2224 new UnicodeBlock("LYCIAN");
2225
2226 /**
2227 * Constant for the "Carian" Unicode character block.
2228 * @since 1.7
2229 */
2230 public static final UnicodeBlock CARIAN =
2231 new UnicodeBlock("CARIAN");
2232
2233 /**
2234 * Constant for the "Old Persian" Unicode character block.
2235 * @since 1.7
2236 */
2237 public static final UnicodeBlock OLD_PERSIAN =
2238 new UnicodeBlock("OLD_PERSIAN",
2239 "OLD PERSIAN",
2240 "OLDPERSIAN");
2241
2242 /**
2243 * Constant for the "Imperial Aramaic" Unicode character block.
2244 * @since 1.7
2245 */
2246 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2247 new UnicodeBlock("IMPERIAL_ARAMAIC",
2248 "IMPERIAL ARAMAIC",
2249 "IMPERIALARAMAIC");
2250
2251 /**
2252 * Constant for the "Phoenician" Unicode character block.
2253 * @since 1.7
2254 */
2255 public static final UnicodeBlock PHOENICIAN =
2256 new UnicodeBlock("PHOENICIAN");
2257
2258 /**
2259 * Constant for the "Lydian" Unicode character block.
2260 * @since 1.7
2261 */
2262 public static final UnicodeBlock LYDIAN =
2263 new UnicodeBlock("LYDIAN");
2264
2265 /**
2266 * Constant for the "Kharoshthi" Unicode character block.
2267 * @since 1.7
2268 */
2269 public static final UnicodeBlock KHAROSHTHI =
2270 new UnicodeBlock("KHAROSHTHI");
2271
2272 /**
2273 * Constant for the "Old South Arabian" Unicode character block.
2274 * @since 1.7
2275 */
2276 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2277 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2278 "OLD SOUTH ARABIAN",
2279 "OLDSOUTHARABIAN");
2280
2281 /**
2282 * Constant for the "Avestan" Unicode character block.
2283 * @since 1.7
2284 */
2285 public static final UnicodeBlock AVESTAN =
2286 new UnicodeBlock("AVESTAN");
2287
2288 /**
2289 * Constant for the "Inscriptional Parthian" Unicode character block.
2290 * @since 1.7
2291 */
2292 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2293 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2294 "INSCRIPTIONAL PARTHIAN",
2295 "INSCRIPTIONALPARTHIAN");
2296
2297 /**
2298 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2299 * @since 1.7
2300 */
2301 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2302 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2303 "INSCRIPTIONAL PAHLAVI",
2304 "INSCRIPTIONALPAHLAVI");
2305
2306 /**
2307 * Constant for the "Old Turkic" Unicode character block.
2308 * @since 1.7
2309 */
2310 public static final UnicodeBlock OLD_TURKIC =
2311 new UnicodeBlock("OLD_TURKIC",
2312 "OLD TURKIC",
2313 "OLDTURKIC");
2314
2315 /**
2316 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2317 * @since 1.7
2318 */
2319 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2320 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2321 "RUMI NUMERAL SYMBOLS",
2322 "RUMINUMERALSYMBOLS");
2323
2324 /**
2325 * Constant for the "Brahmi" Unicode character block.
2326 * @since 1.7
2327 */
2328 public static final UnicodeBlock BRAHMI =
2329 new UnicodeBlock("BRAHMI");
2330
2331 /**
2332 * Constant for the "Kaithi" Unicode character block.
2333 * @since 1.7
2334 */
2335 public static final UnicodeBlock KAITHI =
2336 new UnicodeBlock("KAITHI");
2337
2338 /**
2339 * Constant for the "Cuneiform" Unicode character block.
2340 * @since 1.7
2341 */
2342 public static final UnicodeBlock CUNEIFORM =
2343 new UnicodeBlock("CUNEIFORM");
2344
2345 /**
2346 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2347 * character block.
2348 * @since 1.7
2349 */
2350 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2351 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2352 "CUNEIFORM NUMBERS AND PUNCTUATION",
2353 "CUNEIFORMNUMBERSANDPUNCTUATION");
2354
2355 /**
2356 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2357 * @since 1.7
2358 */
2359 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2360 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2361 "EGYPTIAN HIEROGLYPHS",
2362 "EGYPTIANHIEROGLYPHS");
2363
2364 /**
2365 * Constant for the "Bamum Supplement" Unicode character block.
2366 * @since 1.7
2367 */
2368 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2369 new UnicodeBlock("BAMUM_SUPPLEMENT",
2370 "BAMUM SUPPLEMENT",
2371 "BAMUMSUPPLEMENT");
2372
2373 /**
2374 * Constant for the "Kana Supplement" Unicode character block.
2375 * @since 1.7
2376 */
2377 public static final UnicodeBlock KANA_SUPPLEMENT =
2378 new UnicodeBlock("KANA_SUPPLEMENT",
2379 "KANA SUPPLEMENT",
2380 "KANASUPPLEMENT");
2381
2382 /**
2383 * Constant for the "Ancient Greek Musical Notation" Unicode character
2384 * block.
2385 * @since 1.7
2386 */
2387 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2388 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2389 "ANCIENT GREEK MUSICAL NOTATION",
2390 "ANCIENTGREEKMUSICALNOTATION");
2391
2392 /**
2393 * Constant for the "Counting Rod Numerals" Unicode character block.
2394 * @since 1.7
2395 */
2396 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2397 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2398 "COUNTING ROD NUMERALS",
2399 "COUNTINGRODNUMERALS");
2400
2401 /**
2402 * Constant for the "Mahjong Tiles" Unicode character block.
2403 * @since 1.7
2404 */
2405 public static final UnicodeBlock MAHJONG_TILES =
2406 new UnicodeBlock("MAHJONG_TILES",
2407 "MAHJONG TILES",
2408 "MAHJONGTILES");
2409
2410 /**
2411 * Constant for the "Domino Tiles" Unicode character block.
2412 * @since 1.7
2413 */
2414 public static final UnicodeBlock DOMINO_TILES =
2415 new UnicodeBlock("DOMINO_TILES",
2416 "DOMINO TILES",
2417 "DOMINOTILES");
2418
2419 /**
2420 * Constant for the "Playing Cards" Unicode character block.
2421 * @since 1.7
2422 */
2423 public static final UnicodeBlock PLAYING_CARDS =
2424 new UnicodeBlock("PLAYING_CARDS",
2425 "PLAYING CARDS",
2426 "PLAYINGCARDS");
2427
2428 /**
2429 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2430 * block.
2431 * @since 1.7
2432 */
2433 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2434 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2435 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2436 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2437
2438 /**
2439 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2440 * block.
2441 * @since 1.7
2442 */
2443 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2444 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2445 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2446 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2447
2448 /**
2449 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2450 * character block.
2451 * @since 1.7
2452 */
2453 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2454 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2455 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2456 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2457
2458 /**
2459 * Constant for the "Emoticons" Unicode character block.
2460 * @since 1.7
2461 */
2462 public static final UnicodeBlock EMOTICONS =
2463 new UnicodeBlock("EMOTICONS");
2464
2465 /**
2466 * Constant for the "Transport And Map Symbols" Unicode character block.
2467 * @since 1.7
2468 */
2469 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2470 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2471 "TRANSPORT AND MAP SYMBOLS",
2472 "TRANSPORTANDMAPSYMBOLS");
2473
2474 /**
2475 * Constant for the "Alchemical Symbols" Unicode character block.
2476 * @since 1.7
2477 */
2478 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2479 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2480 "ALCHEMICAL SYMBOLS",
2481 "ALCHEMICALSYMBOLS");
2482
2483 /**
2484 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2485 * character block.
2486 * @since 1.7
2487 */
2488 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2489 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2490 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2491 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2492
2493 /**
2494 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2495 * character block.
2496 * @since 1.7
2497 */
2498 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2499 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2500 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2501 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2502
2503 /**
2504 * Constant for the "Arabic Extended-A" Unicode character block.
2505 * @since 1.8
2506 */
2507 public static final UnicodeBlock ARABIC_EXTENDED_A =
2508 new UnicodeBlock("ARABIC_EXTENDED_A",
2509 "ARABIC EXTENDED-A",
2510 "ARABICEXTENDED-A");
2511
2512 /**
2513 * Constant for the "Sundanese Supplement" Unicode character block.
2514 * @since 1.8
2515 */
2516 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2517 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2518 "SUNDANESE SUPPLEMENT",
2519 "SUNDANESESUPPLEMENT");
2520
2521 /**
2522 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2523 * @since 1.8
2524 */
2525 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2526 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2527 "MEETEI MAYEK EXTENSIONS",
2528 "MEETEIMAYEKEXTENSIONS");
2529
2530 /**
2531 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2532 * @since 1.8
2533 */
2534 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2535 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2536 "MEROITIC HIEROGLYPHS",
2537 "MEROITICHIEROGLYPHS");
2538
2539 /**
2540 * Constant for the "Meroitic Cursive" Unicode character block.
2541 * @since 1.8
2542 */
2543 public static final UnicodeBlock MEROITIC_CURSIVE =
2544 new UnicodeBlock("MEROITIC_CURSIVE",
2545 "MEROITIC CURSIVE",
2546 "MEROITICCURSIVE");
2547
2548 /**
2549 * Constant for the "Sora Sompeng" Unicode character block.
2550 * @since 1.8
2551 */
2552 public static final UnicodeBlock SORA_SOMPENG =
2553 new UnicodeBlock("SORA_SOMPENG",
2554 "SORA SOMPENG",
2555 "SORASOMPENG");
2556
2557 /**
2558 * Constant for the "Chakma" Unicode character block.
2559 * @since 1.8
2560 */
2561 public static final UnicodeBlock CHAKMA =
2562 new UnicodeBlock("CHAKMA");
2563
2564 /**
2565 * Constant for the "Sharada" Unicode character block.
2566 * @since 1.8
2567 */
2568 public static final UnicodeBlock SHARADA =
2569 new UnicodeBlock("SHARADA");
2570
2571 /**
2572 * Constant for the "Takri" Unicode character block.
2573 * @since 1.8
2574 */
2575 public static final UnicodeBlock TAKRI =
2576 new UnicodeBlock("TAKRI");
2577
2578 /**
2579 * Constant for the "Miao" Unicode character block.
2580 * @since 1.8
2581 */
2582 public static final UnicodeBlock MIAO =
2583 new UnicodeBlock("MIAO");
2584
2585 /**
2586 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2587 * character block.
2588 * @since 1.8
2589 */
2590 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2591 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2592 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2593 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2594
2595 /**
2596 * Constant for the "Combining Diacritical Marks Extended" Unicode
2597 * character block.
2598 * @since 1.9
2599 */
2600 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2601 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2602 "COMBINING DIACRITICAL MARKS EXTENDED",
2603 "COMBININGDIACRITICALMARKSEXTENDED");
2604
2605 /**
2606 * Constant for the "Myanmar Extended-B" Unicode character block.
2607 * @since 1.9
2608 */
2609 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2610 new UnicodeBlock("MYANMAR_EXTENDED_B",
2611 "MYANMAR EXTENDED-B",
2612 "MYANMAREXTENDED-B");
2613
2614 /**
2615 * Constant for the "Latin Extended-E" Unicode character block.
2616 * @since 1.9
2617 */
2618 public static final UnicodeBlock LATIN_EXTENDED_E =
2619 new UnicodeBlock("LATIN_EXTENDED_E",
2620 "LATIN EXTENDED-E",
2621 "LATINEXTENDED-E");
2622
2623 /**
2624 * Constant for the "Coptic Epact Numbers" Unicode character block.
2625 * @since 1.9
2626 */
2627 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2628 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2629 "COPTIC EPACT NUMBERS",
2630 "COPTICEPACTNUMBERS");
2631
2632 /**
2633 * Constant for the "Old Permic" Unicode character block.
2634 * @since 1.9
2635 */
2636 public static final UnicodeBlock OLD_PERMIC =
2637 new UnicodeBlock("OLD_PERMIC",
2638 "OLD PERMIC",
2639 "OLDPERMIC");
2640
2641 /**
2642 * Constant for the "Elbasan" Unicode character block.
2643 * @since 1.9
2644 */
2645 public static final UnicodeBlock ELBASAN =
2646 new UnicodeBlock("ELBASAN");
2647
2648 /**
2649 * Constant for the "Caucasian Albanian" Unicode character block.
2650 * @since 1.9
2651 */
2652 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2653 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2654 "CAUCASIAN ALBANIAN",
2655 "CAUCASIANALBANIAN");
2656
2657 /**
2658 * Constant for the "Linear A" Unicode character block.
2659 * @since 1.9
2660 */
2661 public static final UnicodeBlock LINEAR_A =
2662 new UnicodeBlock("LINEAR_A",
2663 "LINEAR A",
2664 "LINEARA");
2665
2666 /**
2667 * Constant for the "Palmyrene" Unicode character block.
2668 * @since 1.9
2669 */
2670 public static final UnicodeBlock PALMYRENE =
2671 new UnicodeBlock("PALMYRENE");
2672
2673 /**
2674 * Constant for the "Nabataean" Unicode character block.
2675 * @since 1.9
2676 */
2677 public static final UnicodeBlock NABATAEAN =
2678 new UnicodeBlock("NABATAEAN");
2679
2680 /**
2681 * Constant for the "Old North Arabian" Unicode character block.
2682 * @since 1.9
2683 */
2684 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2685 new UnicodeBlock("OLD_NORTH_ARABIAN",
2686 "OLD NORTH ARABIAN",
2687 "OLDNORTHARABIAN");
2688
2689 /**
2690 * Constant for the "Manichaean" Unicode character block.
2691 * @since 1.9
2692 */
2693 public static final UnicodeBlock MANICHAEAN =
2694 new UnicodeBlock("MANICHAEAN");
2695
2696 /**
2697 * Constant for the "Psalter Pahlavi" Unicode character block.
2698 * @since 1.9
2699 */
2700 public static final UnicodeBlock PSALTER_PAHLAVI =
2701 new UnicodeBlock("PSALTER_PAHLAVI",
2702 "PSALTER PAHLAVI",
2703 "PSALTERPAHLAVI");
2704
2705 /**
2706 * Constant for the "Mahajani" Unicode character block.
2707 * @since 1.9
2708 */
2709 public static final UnicodeBlock MAHAJANI =
2710 new UnicodeBlock("MAHAJANI");
2711
2712 /**
2713 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2714 * @since 1.9
2715 */
2716 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2717 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2718 "SINHALA ARCHAIC NUMBERS",
2719 "SINHALAARCHAICNUMBERS");
2720
2721 /**
2722 * Constant for the "Khojki" Unicode character block.
2723 * @since 1.9
2724 */
2725 public static final UnicodeBlock KHOJKI =
2726 new UnicodeBlock("KHOJKI");
2727
2728 /**
2729 * Constant for the "Khudawadi" Unicode character block.
2730 * @since 1.9
2731 */
2732 public static final UnicodeBlock KHUDAWADI =
2733 new UnicodeBlock("KHUDAWADI");
2734
2735 /**
2736 * Constant for the "Grantha" Unicode character block.
2737 * @since 1.9
2738 */
2739 public static final UnicodeBlock GRANTHA =
2740 new UnicodeBlock("GRANTHA");
2741
2742 /**
2743 * Constant for the "Tirhuta" Unicode character block.
2744 * @since 1.9
2745 */
2746 public static final UnicodeBlock TIRHUTA =
2747 new UnicodeBlock("TIRHUTA");
2748
2749 /**
2750 * Constant for the "Siddham" Unicode character block.
2751 * @since 1.9
2752 */
2753 public static final UnicodeBlock SIDDHAM =
2754 new UnicodeBlock("SIDDHAM");
2755
2756 /**
2757 * Constant for the "Modi" Unicode character block.
2758 * @since 1.9
2759 */
2760 public static final UnicodeBlock MODI =
2761 new UnicodeBlock("MODI");
2762
2763 /**
2764 * Constant for the "Warang Citi" Unicode character block.
2765 * @since 1.9
2766 */
2767 public static final UnicodeBlock WARANG_CITI =
2768 new UnicodeBlock("WARANG_CITI",
2769 "WARANG CITI",
2770 "WARANGCITI");
2771
2772 /**
2773 * Constant for the "Pau Cin Hau" Unicode character block.
2774 * @since 1.9
2775 */
2776 public static final UnicodeBlock PAU_CIN_HAU =
2777 new UnicodeBlock("PAU_CIN_HAU",
2778 "PAU CIN HAU",
2779 "PAUCINHAU");
2780
2781 /**
2782 * Constant for the "Mro" Unicode character block.
2783 * @since 1.9
2784 */
2785 public static final UnicodeBlock MRO =
2786 new UnicodeBlock("MRO");
2787
2788 /**
2789 * Constant for the "Bassa Vah" Unicode character block.
2790 * @since 1.9
2791 */
2792 public static final UnicodeBlock BASSA_VAH =
2793 new UnicodeBlock("BASSA_VAH",
2794 "BASSA VAH",
2795 "BASSAVAH");
2796
2797 /**
2798 * Constant for the "Pahawh Hmong" Unicode character block.
2799 * @since 1.9
2800 */
2801 public static final UnicodeBlock PAHAWH_HMONG =
2802 new UnicodeBlock("PAHAWH_HMONG",
2803 "PAHAWH HMONG",
2804 "PAHAWHHMONG");
2805
2806 /**
2807 * Constant for the "Duployan" Unicode character block.
2808 * @since 1.9
2809 */
2810 public static final UnicodeBlock DUPLOYAN =
2811 new UnicodeBlock("DUPLOYAN");
2812
2813 /**
2814 * Constant for the "Shorthand Format Controls" Unicode character block.
2815 * @since 1.9
2816 */
2817 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2818 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2819 "SHORTHAND FORMAT CONTROLS",
2820 "SHORTHANDFORMATCONTROLS");
2821
2822 /**
2823 * Constant for the "Mende Kikakui" Unicode character block.
2824 * @since 1.9
2825 */
2826 public static final UnicodeBlock MENDE_KIKAKUI =
2827 new UnicodeBlock("MENDE_KIKAKUI",
2828 "MENDE KIKAKUI",
2829 "MENDEKIKAKUI");
2830
2831 /**
2832 * Constant for the "Ornamental Dingbats" Unicode character block.
2833 * @since 1.9
2834 */
2835 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2836 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2837 "ORNAMENTAL DINGBATS",
2838 "ORNAMENTALDINGBATS");
2839
2840 /**
2841 * Constant for the "Geometric Shapes Extended" Unicode character block.
2842 * @since 1.9
2843 */
2844 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2845 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2846 "GEOMETRIC SHAPES EXTENDED",
2847 "GEOMETRICSHAPESEXTENDED");
2848
2849 /**
2850 * Constant for the "Supplemental Arrows-C" Unicode character block.
2851 * @since 1.9
2852 */
2853 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2854 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2855 "SUPPLEMENTAL ARROWS-C",
2856 "SUPPLEMENTALARROWS-C");
2857
2858 /**
2859 * Constant for the "Cherokee Supplement" Unicode character block.
2860 * @since 1.9
2861 */
2862 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2863 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2864 "CHEROKEE SUPPLEMENT",
2865 "CHEROKEESUPPLEMENT");
2866
2867 /**
2868 * Constant for the "Hatran" Unicode character block.
2869 * @since 1.9
2870 */
2871 public static final UnicodeBlock HATRAN =
2872 new UnicodeBlock("HATRAN");
2873
2874 /**
2875 * Constant for the "Old Hungarian" Unicode character block.
2876 * @since 1.9
2877 */
2878 public static final UnicodeBlock OLD_HUNGARIAN =
2879 new UnicodeBlock("OLD_HUNGARIAN",
2880 "OLD HUNGARIAN",
2881 "OLDHUNGARIAN");
2882
2883 /**
2884 * Constant for the "Multani" Unicode character block.
2885 * @since 1.9
2886 */
2887 public static final UnicodeBlock MULTANI =
2888 new UnicodeBlock("MULTANI");
2889
2890 /**
2891 * Constant for the "Ahom" Unicode character block.
2892 * @since 1.9
2893 */
2894 public static final UnicodeBlock AHOM =
2895 new UnicodeBlock("AHOM");
2896
2897 /**
2898 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2899 * @since 1.9
2900 */
2901 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2902 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2903 "EARLY DYNASTIC CUNEIFORM",
2904 "EARLYDYNASTICCUNEIFORM");
2905
2906 /**
2907 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2908 * @since 1.9
2909 */
2910 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2911 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2912 "ANATOLIAN HIEROGLYPHS",
2913 "ANATOLIANHIEROGLYPHS");
2914
2915 /**
2916 * Constant for the "Sutton SignWriting" Unicode character block.
2917 * @since 1.9
2918 */
2919 public static final UnicodeBlock SUTTON_SIGNWRITING =
2920 new UnicodeBlock("SUTTON_SIGNWRITING",
2921 "SUTTON SIGNWRITING",
2922 "SUTTONSIGNWRITING");
2923
2924 /**
2925 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2926 * character block.
2927 * @since 1.9
2928 */
2929 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2930 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2931 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2932 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2933
2934 /**
2935 * Constant for the "CJK Unified Ideographs Extension E" Unicode
2936 * character block.
2937 * @since 1.9
2938 */
2939 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
2940 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
2941 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
2942 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
2943
2944
2945 private static final int blockStarts[] = {
2946 0x0000, // 0000..007F; Basic Latin
2947 0x0080, // 0080..00FF; Latin-1 Supplement
2948 0x0100, // 0100..017F; Latin Extended-A
2949 0x0180, // 0180..024F; Latin Extended-B
2950 0x0250, // 0250..02AF; IPA Extensions
2951 0x02B0, // 02B0..02FF; Spacing Modifier Letters
2952 0x0300, // 0300..036F; Combining Diacritical Marks
2953 0x0370, // 0370..03FF; Greek and Coptic
2954 0x0400, // 0400..04FF; Cyrillic
2955 0x0500, // 0500..052F; Cyrillic Supplement
2956 0x0530, // 0530..058F; Armenian
2957 0x0590, // 0590..05FF; Hebrew
2958 0x0600, // 0600..06FF; Arabic
2959 0x0700, // 0700..074F; Syriac
2960 0x0750, // 0750..077F; Arabic Supplement
2961 0x0780, // 0780..07BF; Thaana
2962 0x07C0, // 07C0..07FF; NKo
2963 0x0800, // 0800..083F; Samaritan
2964 0x0840, // 0840..085F; Mandaic
2965 0x0860, // unassigned
2966 0x08A0, // 08A0..08FF; Arabic Extended-A
2967 0x0900, // 0900..097F; Devanagari
2968 0x0980, // 0980..09FF; Bengali
2969 0x0A00, // 0A00..0A7F; Gurmukhi
2970 0x0A80, // 0A80..0AFF; Gujarati
2971 0x0B00, // 0B00..0B7F; Oriya
2972 0x0B80, // 0B80..0BFF; Tamil
2973 0x0C00, // 0C00..0C7F; Telugu
2974 0x0C80, // 0C80..0CFF; Kannada
2975 0x0D00, // 0D00..0D7F; Malayalam
2976 0x0D80, // 0D80..0DFF; Sinhala
2977 0x0E00, // 0E00..0E7F; Thai
2978 0x0E80, // 0E80..0EFF; Lao
2979 0x0F00, // 0F00..0FFF; Tibetan
2980 0x1000, // 1000..109F; Myanmar
2981 0x10A0, // 10A0..10FF; Georgian
2982 0x1100, // 1100..11FF; Hangul Jamo
2983 0x1200, // 1200..137F; Ethiopic
2984 0x1380, // 1380..139F; Ethiopic Supplement
2985 0x13A0, // 13A0..13FF; Cherokee
2986 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
2987 0x1680, // 1680..169F; Ogham
2988 0x16A0, // 16A0..16FF; Runic
2989 0x1700, // 1700..171F; Tagalog
2990 0x1720, // 1720..173F; Hanunoo
2991 0x1740, // 1740..175F; Buhid
2992 0x1760, // 1760..177F; Tagbanwa
2993 0x1780, // 1780..17FF; Khmer
2994 0x1800, // 1800..18AF; Mongolian
2995 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
2996 0x1900, // 1900..194F; Limbu
2997 0x1950, // 1950..197F; Tai Le
2998 0x1980, // 1980..19DF; New Tai Lue
2999 0x19E0, // 19E0..19FF; Khmer Symbols
3000 0x1A00, // 1A00..1A1F; Buginese
3001 0x1A20, // 1A20..1AAF; Tai Tham
3002 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3003 0x1B00, // 1B00..1B7F; Balinese
3004 0x1B80, // 1B80..1BBF; Sundanese
3005 0x1BC0, // 1BC0..1BFF; Batak
3006 0x1C00, // 1C00..1C4F; Lepcha
3007 0x1C50, // 1C50..1C7F; Ol Chiki
3008 0x1C80, // unassigned
3009 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3010 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3011 0x1D00, // 1D00..1D7F; Phonetic Extensions
3012 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3013 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3014 0x1E00, // 1E00..1EFF; Latin Extended Additional
3015 0x1F00, // 1F00..1FFF; Greek Extended
3016 0x2000, // 2000..206F; General Punctuation
3017 0x2070, // 2070..209F; Superscripts and Subscripts
3018 0x20A0, // 20A0..20CF; Currency Symbols
3019 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3020 0x2100, // 2100..214F; Letterlike Symbols
3021 0x2150, // 2150..218F; Number Forms
3022 0x2190, // 2190..21FF; Arrows
3023 0x2200, // 2200..22FF; Mathematical Operators
3024 0x2300, // 2300..23FF; Miscellaneous Technical
3025 0x2400, // 2400..243F; Control Pictures
3026 0x2440, // 2440..245F; Optical Character Recognition
3027 0x2460, // 2460..24FF; Enclosed Alphanumerics
3028 0x2500, // 2500..257F; Box Drawing
3029 0x2580, // 2580..259F; Block Elements
3030 0x25A0, // 25A0..25FF; Geometric Shapes
3031 0x2600, // 2600..26FF; Miscellaneous Symbols
3032 0x2700, // 2700..27BF; Dingbats
3033 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3034 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3035 0x2800, // 2800..28FF; Braille Patterns
3036 0x2900, // 2900..297F; Supplemental Arrows-B
3037 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3038 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3039 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3040 0x2C00, // 2C00..2C5F; Glagolitic
3041 0x2C60, // 2C60..2C7F; Latin Extended-C
3042 0x2C80, // 2C80..2CFF; Coptic
3043 0x2D00, // 2D00..2D2F; Georgian Supplement
3044 0x2D30, // 2D30..2D7F; Tifinagh
3045 0x2D80, // 2D80..2DDF; Ethiopic Extended
3046 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3047 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3048 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3049 0x2F00, // 2F00..2FDF; Kangxi Radicals
3050 0x2FE0, // unassigned
3051 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3052 0x3000, // 3000..303F; CJK Symbols and Punctuation
3053 0x3040, // 3040..309F; Hiragana
3054 0x30A0, // 30A0..30FF; Katakana
3055 0x3100, // 3100..312F; Bopomofo
3056 0x3130, // 3130..318F; Hangul Compatibility Jamo
3057 0x3190, // 3190..319F; Kanbun
3058 0x31A0, // 31A0..31BF; Bopomofo Extended
3059 0x31C0, // 31C0..31EF; CJK Strokes
3060 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3061 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3062 0x3300, // 3300..33FF; CJK Compatibility
3063 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3064 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3065 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3066 0xA000, // A000..A48F; Yi Syllables
3067 0xA490, // A490..A4CF; Yi Radicals
3068 0xA4D0, // A4D0..A4FF; Lisu
3069 0xA500, // A500..A63F; Vai
3070 0xA640, // A640..A69F; Cyrillic Extended-B
3071 0xA6A0, // A6A0..A6FF; Bamum
3072 0xA700, // A700..A71F; Modifier Tone Letters
3073 0xA720, // A720..A7FF; Latin Extended-D
3074 0xA800, // A800..A82F; Syloti Nagri
3075 0xA830, // A830..A83F; Common Indic Number Forms
3076 0xA840, // A840..A87F; Phags-pa
3077 0xA880, // A880..A8DF; Saurashtra
3078 0xA8E0, // A8E0..A8FF; Devanagari Extended
3079 0xA900, // A900..A92F; Kayah Li
3080 0xA930, // A930..A95F; Rejang
3081 0xA960, // A960..A97F; Hangul Jamo Extended-A
3082 0xA980, // A980..A9DF; Javanese
3083 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3084 0xAA00, // AA00..AA5F; Cham
3085 0xAA60, // AA60..AA7F; Myanmar Extended-A
3086 0xAA80, // AA80..AADF; Tai Viet
3087 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3088 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3089 0xAB30, // AB30..AB6F; Latin Extended-E
3090 0xAB70, // AB70..ABBF; Cherokee Supplement
3091 0xABC0, // ABC0..ABFF; Meetei Mayek
3092 0xAC00, // AC00..D7AF; Hangul Syllables
3093 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3094 0xD800, // D800..DB7F; High Surrogates
3095 0xDB80, // DB80..DBFF; High Private Use Surrogates
3096 0xDC00, // DC00..DFFF; Low Surrogates
3097 0xE000, // E000..F8FF; Private Use Area
3098 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3099 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3100 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3101 0xFE00, // FE00..FE0F; Variation Selectors
3102 0xFE10, // FE10..FE1F; Vertical Forms
3103 0xFE20, // FE20..FE2F; Combining Half Marks
3104 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3105 0xFE50, // FE50..FE6F; Small Form Variants
3106 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3107 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3108 0xFFF0, // FFF0..FFFF; Specials
3109 0x10000, // 10000..1007F; Linear B Syllabary
3110 0x10080, // 10080..100FF; Linear B Ideograms
3111 0x10100, // 10100..1013F; Aegean Numbers
3112 0x10140, // 10140..1018F; Ancient Greek Numbers
3113 0x10190, // 10190..101CF; Ancient Symbols
3114 0x101D0, // 101D0..101FF; Phaistos Disc
3115 0x10200, // unassigned
3116 0x10280, // 10280..1029F; Lycian
3117 0x102A0, // 102A0..102DF; Carian
3118 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3119 0x10300, // 10300..1032F; Old Italic
3120 0x10330, // 10330..1034F; Gothic
3121 0x10350, // 10350..1037F; Old Permic
3122 0x10380, // 10380..1039F; Ugaritic
3123 0x103A0, // 103A0..103DF; Old Persian
3124 0x103E0, // unassigned
3125 0x10400, // 10400..1044F; Deseret
3126 0x10450, // 10450..1047F; Shavian
3127 0x10480, // 10480..104AF; Osmanya
3128 0x104B0, // unassigned
3129 0x10500, // 10500..1052F; Elbasan
3130 0x10530, // 10530..1056F; Caucasian Albanian
3131 0x10570, // unassigned
3132 0x10600, // 10600..1077F; Linear A
3133 0x10780, // unassigned
3134 0x10800, // 10800..1083F; Cypriot Syllabary
3135 0x10840, // 10840..1085F; Imperial Aramaic
3136 0x10860, // 10860..1087F; Palmyrene
3137 0x10880, // 10880..108AF; Nabataean
3138 0x108B0, // unassigned
3139 0x108E0, // 108E0..108FF; Hatran
3140 0x10900, // 10900..1091F; Phoenician
3141 0x10920, // 10920..1093F; Lydian
3142 0x10940, // unassigned
3143 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3144 0x109A0, // 109A0..109FF; Meroitic Cursive
3145 0x10A00, // 10A00..10A5F; Kharoshthi
3146 0x10A60, // 10A60..10A7F; Old South Arabian
3147 0x10A80, // 10A80..10A9F; Old North Arabian
3148 0x10AA0, // unassigned
3149 0x10AC0, // 10AC0..10AFF; Manichaean
3150 0x10B00, // 10B00..10B3F; Avestan
3151 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3152 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3153 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3154 0x10BB0, // unassigned
3155 0x10C00, // 10C00..10C4F; Old Turkic
3156 0x10C50, // unassigned
3157 0x10C80, // 10C80..10CFF; Old Hungarian
3158 0x10D00, // unassigned
3159 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3160 0x10E80, // unassigned
3161 0x11000, // 11000..1107F; Brahmi
3162 0x11080, // 11080..110CF; Kaithi
3163 0x110D0, // 110D0..110FF; Sora Sompeng
3164 0x11100, // 11100..1114F; Chakma
3165 0x11150, // 11150..1117F; Mahajani
3166 0x11180, // 11180..111DF; Sharada
3167 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3168 0x11200, // 11200..1124F; Khojki
3169 0x11250, // unassigned
3170 0x11280, // 11280..112AF; Multani
3171 0x112B0, // 112B0..112FF; Khudawadi
3172 0x11300, // 11300..1137F; Grantha
3173 0x11380, // unassigned
3174 0x11480, // 11480..114DF; Tirhuta
3175 0x114E0, // unassigned
3176 0x11580, // 11580..115FF; Siddham
3177 0x11600, // 11600..1165F; Modi
3178 0x11660, // unassigned
3179 0x11680, // 11680..116CF; Takri
3180 0x116D0, // unassigned
3181 0x11700, // 11700..1173F; Ahom
3182 0x11740, // unassigned
3183 0x118A0, // 118A0..118FF; Warang Citi
3184 0x11900, // unassigned
3185 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3186 0x11B00, // unassigned
3187 0x12000, // 12000..123FF; Cuneiform
3188 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3189 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3190 0x12550, // unassigned
3191 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3192 0x13430, // unassigned
3193 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3194 0x14680, // unassigned
3195 0x16800, // 16800..16A3F; Bamum Supplement
3196 0x16A40, // 16A40..16A6F; Mro
3197 0x16A70, // unassigned
3198 0x16AD0, // 16AD0..16AFF; Bassa Vah
3199 0x16B00, // 16B00..16B8F; Pahawh Hmong
3200 0x16B90, // unassigned
3201 0x16F00, // 16F00..16F9F; Miao
3202 0x16FA0, // unassigned
3203 0x1B000, // 1B000..1B0FF; Kana Supplement
3204 0x1B100, // unassigned
3205 0x1BC00, // 1BC00..1BC9F; Duployan
3206 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3207 0x1BCB0, // unassigned
3208 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3209 0x1D100, // 1D100..1D1FF; Musical Symbols
3210 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3211 0x1D250, // unassigned
3212 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3213 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3214 0x1D380, // unassigned
3215 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3216 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3217 0x1DAB0, // unassigned
3218 0x1E800, // 1E800..1E8DF; Mende Kikakui
3219 0x1E8E0, // unassigned
3220 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3221 0x1EF00, // unassigned
3222 0x1F000, // 1F000..1F02F; Mahjong Tiles
3223 0x1F030, // 1F030..1F09F; Domino Tiles
3224 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3225 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3226 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3227 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3228 0x1F600, // 1F600..1F64F; Emoticons
3229 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3230 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3231 0x1F700, // 1F700..1F77F; Alchemical Symbols
3232 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3233 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3234 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3235 0x1FA00, // unassigned
3236 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3237 0x2A6E0, // unassigned
3238 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3239 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3240 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
3241 0x2CEB0, // unassigned
3242 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
3243 0x2FA20, // unassigned
3244 0xE0000, // E0000..E007F; Tags
3245 0xE0080, // unassigned
3246 0xE0100, // E0100..E01EF; Variation Selectors Supplement
3247 0xE01F0, // unassigned
3248 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
3249 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B
3250 };
3251
3252 private static final UnicodeBlock[] blocks = {
3253 BASIC_LATIN,
3254 LATIN_1_SUPPLEMENT,
3255 LATIN_EXTENDED_A,
3256 LATIN_EXTENDED_B,
3257 IPA_EXTENSIONS,
3258 SPACING_MODIFIER_LETTERS,
3259 COMBINING_DIACRITICAL_MARKS,
3260 GREEK,
3261 CYRILLIC,
3262 CYRILLIC_SUPPLEMENTARY,
3263 ARMENIAN,
3264 HEBREW,
3265 ARABIC,
3266 SYRIAC,
3267 ARABIC_SUPPLEMENT,
3268 THAANA,
3269 NKO,
3270 SAMARITAN,
3271 MANDAIC,
3272 null,
3273 ARABIC_EXTENDED_A,
3274 DEVANAGARI,
3275 BENGALI,
3276 GURMUKHI,
3277 GUJARATI,
3278 ORIYA,
3279 TAMIL,
3280 TELUGU,
3281 KANNADA,
3282 MALAYALAM,
3283 SINHALA,
3284 THAI,
3285 LAO,
3286 TIBETAN,
3287 MYANMAR,
3288 GEORGIAN,
3289 HANGUL_JAMO,
3290 ETHIOPIC,
3291 ETHIOPIC_SUPPLEMENT,
3292 CHEROKEE,
3293 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
3294 OGHAM,
3295 RUNIC,
3296 TAGALOG,
3297 HANUNOO,
3298 BUHID,
3299 TAGBANWA,
3300 KHMER,
3301 MONGOLIAN,
3302 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
3303 LIMBU,
3304 TAI_LE,
3305 NEW_TAI_LUE,
3306 KHMER_SYMBOLS,
3307 BUGINESE,
3308 TAI_THAM,
3309 COMBINING_DIACRITICAL_MARKS_EXTENDED,
3310 BALINESE,
3311 SUNDANESE,
3312 BATAK,
3313 LEPCHA,
3314 OL_CHIKI,
3315 null,
3316 SUNDANESE_SUPPLEMENT,
3317 VEDIC_EXTENSIONS,
3318 PHONETIC_EXTENSIONS,
3319 PHONETIC_EXTENSIONS_SUPPLEMENT,
3320 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
3321 LATIN_EXTENDED_ADDITIONAL,
3322 GREEK_EXTENDED,
3323 GENERAL_PUNCTUATION,
3324 SUPERSCRIPTS_AND_SUBSCRIPTS,
3325 CURRENCY_SYMBOLS,
3326 COMBINING_MARKS_FOR_SYMBOLS,
3327 LETTERLIKE_SYMBOLS,
3328 NUMBER_FORMS,
3329 ARROWS,
3330 MATHEMATICAL_OPERATORS,
3331 MISCELLANEOUS_TECHNICAL,
3332 CONTROL_PICTURES,
3333 OPTICAL_CHARACTER_RECOGNITION,
3334 ENCLOSED_ALPHANUMERICS,
3335 BOX_DRAWING,
3336 BLOCK_ELEMENTS,
3337 GEOMETRIC_SHAPES,
3338 MISCELLANEOUS_SYMBOLS,
3339 DINGBATS,
3340 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
3341 SUPPLEMENTAL_ARROWS_A,
3342 BRAILLE_PATTERNS,
3343 SUPPLEMENTAL_ARROWS_B,
3344 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
3345 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
3346 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
3347 GLAGOLITIC,
3348 LATIN_EXTENDED_C,
3349 COPTIC,
3350 GEORGIAN_SUPPLEMENT,
3351 TIFINAGH,
3352 ETHIOPIC_EXTENDED,
3353 CYRILLIC_EXTENDED_A,
3354 SUPPLEMENTAL_PUNCTUATION,
3355 CJK_RADICALS_SUPPLEMENT,
3356 KANGXI_RADICALS,
3357 null,
3358 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
3359 CJK_SYMBOLS_AND_PUNCTUATION,
3360 HIRAGANA,
3361 KATAKANA,
3362 BOPOMOFO,
3363 HANGUL_COMPATIBILITY_JAMO,
3364 KANBUN,
3365 BOPOMOFO_EXTENDED,
3366 CJK_STROKES,
3367 KATAKANA_PHONETIC_EXTENSIONS,
3368 ENCLOSED_CJK_LETTERS_AND_MONTHS,
3369 CJK_COMPATIBILITY,
3370 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
3371 YIJING_HEXAGRAM_SYMBOLS,
3372 CJK_UNIFIED_IDEOGRAPHS,
3373 YI_SYLLABLES,
3374 YI_RADICALS,
3375 LISU,
3376 VAI,
3377 CYRILLIC_EXTENDED_B,
3378 BAMUM,
3379 MODIFIER_TONE_LETTERS,
3380 LATIN_EXTENDED_D,
3381 SYLOTI_NAGRI,
3382 COMMON_INDIC_NUMBER_FORMS,
3383 PHAGS_PA,
3384 SAURASHTRA,
3385 DEVANAGARI_EXTENDED,
3386 KAYAH_LI,
3387 REJANG,
3388 HANGUL_JAMO_EXTENDED_A,
3389 JAVANESE,
3390 MYANMAR_EXTENDED_B,
3391 CHAM,
3392 MYANMAR_EXTENDED_A,
3393 TAI_VIET,
3394 MEETEI_MAYEK_EXTENSIONS,
3395 ETHIOPIC_EXTENDED_A,
3396 LATIN_EXTENDED_E,
3397 CHEROKEE_SUPPLEMENT,
3398 MEETEI_MAYEK,
3399 HANGUL_SYLLABLES,
3400 HANGUL_JAMO_EXTENDED_B,
3401 HIGH_SURROGATES,
3402 HIGH_PRIVATE_USE_SURROGATES,
3403 LOW_SURROGATES,
3404 PRIVATE_USE_AREA,
3405 CJK_COMPATIBILITY_IDEOGRAPHS,
3406 ALPHABETIC_PRESENTATION_FORMS,
3407 ARABIC_PRESENTATION_FORMS_A,
3408 VARIATION_SELECTORS,
3409 VERTICAL_FORMS,
3410 COMBINING_HALF_MARKS,
3411 CJK_COMPATIBILITY_FORMS,
3412 SMALL_FORM_VARIANTS,
3413 ARABIC_PRESENTATION_FORMS_B,
3414 HALFWIDTH_AND_FULLWIDTH_FORMS,
3415 SPECIALS,
3416 LINEAR_B_SYLLABARY,
3417 LINEAR_B_IDEOGRAMS,
3418 AEGEAN_NUMBERS,
3419 ANCIENT_GREEK_NUMBERS,
3420 ANCIENT_SYMBOLS,
3421 PHAISTOS_DISC,
3422 null,
3423 LYCIAN,
3424 CARIAN,
3425 COPTIC_EPACT_NUMBERS,
3426 OLD_ITALIC,
3427 GOTHIC,
3428 OLD_PERMIC,
3429 UGARITIC,
3430 OLD_PERSIAN,
3431 null,
3432 DESERET,
3433 SHAVIAN,
3434 OSMANYA,
3435 null,
3436 ELBASAN,
3437 CAUCASIAN_ALBANIAN,
3438 null,
3439 LINEAR_A,
3440 null,
3441 CYPRIOT_SYLLABARY,
3442 IMPERIAL_ARAMAIC,
3443 PALMYRENE,
3444 NABATAEAN,
3445 null,
3446 HATRAN,
3447 PHOENICIAN,
3448 LYDIAN,
3449 null,
3450 MEROITIC_HIEROGLYPHS,
3451 MEROITIC_CURSIVE,
3452 KHAROSHTHI,
3453 OLD_SOUTH_ARABIAN,
3454 OLD_NORTH_ARABIAN,
3455 null,
3456 MANICHAEAN,
3457 AVESTAN,
3458 INSCRIPTIONAL_PARTHIAN,
3459 INSCRIPTIONAL_PAHLAVI,
3460 PSALTER_PAHLAVI,
3461 null,
3462 OLD_TURKIC,
3463 null,
3464 OLD_HUNGARIAN,
3465 null,
3466 RUMI_NUMERAL_SYMBOLS,
3467 null,
3468 BRAHMI,
3469 KAITHI,
3470 SORA_SOMPENG,
3471 CHAKMA,
3472 MAHAJANI,
3473 SHARADA,
3474 SINHALA_ARCHAIC_NUMBERS,
3475 KHOJKI,
3476 null,
3477 MULTANI,
3478 KHUDAWADI,
3479 GRANTHA,
3480 null,
3481 TIRHUTA,
3482 null,
3483 SIDDHAM,
3484 MODI,
3485 null,
3486 TAKRI,
3487 null,
3488 AHOM,
3489 null,
3490 WARANG_CITI,
3491 null,
3492 PAU_CIN_HAU,
3493 null,
3494 CUNEIFORM,
3495 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
3496 EARLY_DYNASTIC_CUNEIFORM,
3497 null,
3498 EGYPTIAN_HIEROGLYPHS,
3499 null,
3500 ANATOLIAN_HIEROGLYPHS,
3501 null,
3502 BAMUM_SUPPLEMENT,
3503 MRO,
3504 null,
3505 BASSA_VAH,
3506 PAHAWH_HMONG,
3507 null,
3508 MIAO,
3509 null,
3510 KANA_SUPPLEMENT,
3511 null,
3512 DUPLOYAN,
3513 SHORTHAND_FORMAT_CONTROLS,
3514 null,
3515 BYZANTINE_MUSICAL_SYMBOLS,
3516 MUSICAL_SYMBOLS,
3517 ANCIENT_GREEK_MUSICAL_NOTATION,
3518 null,
3519 TAI_XUAN_JING_SYMBOLS,
3520 COUNTING_ROD_NUMERALS,
3521 null,
3522 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
3523 SUTTON_SIGNWRITING,
3524 null,
3525 MENDE_KIKAKUI,
3526 null,
3527 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
3528 null,
3529 MAHJONG_TILES,
3530 DOMINO_TILES,
3531 PLAYING_CARDS,
3532 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
3533 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
3534 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
3535 EMOTICONS,
3536 ORNAMENTAL_DINGBATS,
3537 TRANSPORT_AND_MAP_SYMBOLS,
3538 ALCHEMICAL_SYMBOLS,
3539 GEOMETRIC_SHAPES_EXTENDED,
3540 SUPPLEMENTAL_ARROWS_C,
3541 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
3542 null,
3543 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
3544 null,
3545 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
3546 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
3547 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
3548 null,
3549 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
3550 null,
3551 TAGS,
3552 null,
3553 VARIATION_SELECTORS_SUPPLEMENT,
3554 null,
3555 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
3556 SUPPLEMENTARY_PRIVATE_USE_AREA_B
3557 };
3558
3559
3560 /**
3561 * Returns the object representing the Unicode block containing the
3562 * given character, or {@code null} if the character is not a
3563 * member of a defined block.
3564 *
3565 * <p><b>Note:</b> This method cannot handle
3566 * <a href="Character.html#supplementary"> supplementary
3567 * characters</a>. To support all Unicode characters, including
3568 * supplementary characters, use the {@link #of(int)} method.
3569 *
3570 * @param c The character in question
3571 * @return The {@code UnicodeBlock} instance representing the
3572 * Unicode block of which this character is a member, or
3573 * {@code null} if the character is not a member of any
3574 * Unicode block
3575 */
3576 public static UnicodeBlock of(char c) {
3577 return of((int)c);
3578 }
3579
3580 /**
3581 * Returns the object representing the Unicode block
3582 * containing the given character (Unicode code point), or
3583 * {@code null} if the character is not a member of a
3584 * defined block.
3585 *
3586 * @param codePoint the character (Unicode code point) in question.
3587 * @return The {@code UnicodeBlock} instance representing the
3588 * Unicode block of which this character is a member, or
3589 * {@code null} if the character is not a member of any
3590 * Unicode block
3591 * @exception IllegalArgumentException if the specified
3592 * {@code codePoint} is an invalid Unicode code point.
3593 * @see Character#isValidCodePoint(int)
3594 * @since 1.5
3595 */
3596 public static UnicodeBlock of(int codePoint) {
3597 if (!isValidCodePoint(codePoint)) {
3598 throw new IllegalArgumentException();
3599 }
3600
3601 int top, bottom, current;
3602 bottom = 0;
3603 top = blockStarts.length;
3604 current = top/2;
3605
3606 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
3607 while (top - bottom > 1) {
3608 if (codePoint >= blockStarts[current]) {
3609 bottom = current;
3610 } else {
3611 top = current;
3612 }
3613 current = (top + bottom) / 2;
3614 }
3615 return blocks[current];
3616 }
3617
3618 /**
3619 * Returns the UnicodeBlock with the given name. Block
3620 * names are determined by The Unicode Standard. The file
3621 * {@code Blocks-<version>.txt} defines blocks for a particular
3622 * version of the standard. The {@link Character} class specifies
3623 * the version of the standard that it supports.
3624 * <p>
3625 * This method accepts block names in the following forms:
3626 * <ol>
3627 * <li> Canonical block names as defined by the Unicode Standard.
3628 * For example, the standard defines a "Basic Latin" block. Therefore, this
3629 * method accepts "Basic Latin" as a valid block name. The documentation of
3630 * each UnicodeBlock provides the canonical name.
3631 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
3632 * is a valid block name for the "Basic Latin" block.
3633 * <li>The text representation of each constant UnicodeBlock identifier.
3634 * For example, this method will return the {@link #BASIC_LATIN} block if
3635 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
3636 * hyphens in the canonical name with underscores.
3637 * </ol>
3638 * Finally, character case is ignored for all of the valid block name forms.
3639 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
3640 * The en_US locale's case mapping rules are used to provide case-insensitive
3641 * string comparisons for block name validation.
3642 * <p>
3643 * If the Unicode Standard changes block names, both the previous and
3644 * current names will be accepted.
3645 *
3646 * @param blockName A {@code UnicodeBlock} name.
3647 * @return The {@code UnicodeBlock} instance identified
3648 * by {@code blockName}
3649 * @throws IllegalArgumentException if {@code blockName} is an
3650 * invalid name
3651 * @throws NullPointerException if {@code blockName} is null
3652 * @since 1.5
3653 */
3654 public static final UnicodeBlock forName(String blockName) {
3655 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
3656 if (block == null) {
3657 throw new IllegalArgumentException();
3658 }
3659 return block;
3660 }
3661 }
3662
3663
3664 /**
3665 * A family of character subsets representing the character scripts
3666 * defined in the <a href="http://www.unicode.org/reports/tr24/">
3667 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
3668 * character is assigned to a single Unicode script, either a specific
3669 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
3670 * one of the following three special values,
3671 * {@link Character.UnicodeScript#INHERITED Inherited},
3672 * {@link Character.UnicodeScript#COMMON Common} or
3673 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
3674 *
3675 * @since 1.7
3676 */
3677 public static enum UnicodeScript {
3678 /**
3679 * Unicode script "Common".
3680 */
3681 COMMON,
3682
3683 /**
3684 * Unicode script "Latin".
3685 */
3686 LATIN,
3687
3688 /**
3689 * Unicode script "Greek".
3690 */
3691 GREEK,
3692
3693 /**
3694 * Unicode script "Cyrillic".
3695 */
3696 CYRILLIC,
3697
3698 /**
3699 * Unicode script "Armenian".
3700 */
3701 ARMENIAN,
3702
3703 /**
3704 * Unicode script "Hebrew".
3705 */
3706 HEBREW,
3707
3708 /**
3709 * Unicode script "Arabic".
3710 */
3711 ARABIC,
3712
3713 /**
3714 * Unicode script "Syriac".
3715 */
3716 SYRIAC,
3717
3718 /**
3719 * Unicode script "Thaana".
3720 */
3721 THAANA,
3722
3723 /**
3724 * Unicode script "Devanagari".
3725 */
3726 DEVANAGARI,
3727
3728 /**
3729 * Unicode script "Bengali".
3730 */
3731 BENGALI,
3732
3733 /**
3734 * Unicode script "Gurmukhi".
3735 */
3736 GURMUKHI,
3737
3738 /**
3739 * Unicode script "Gujarati".
3740 */
3741 GUJARATI,
3742
3743 /**
3744 * Unicode script "Oriya".
3745 */
3746 ORIYA,
3747
3748 /**
3749 * Unicode script "Tamil".
3750 */
3751 TAMIL,
3752
3753 /**
3754 * Unicode script "Telugu".
3755 */
3756 TELUGU,
3757
3758 /**
3759 * Unicode script "Kannada".
3760 */
3761 KANNADA,
3762
3763 /**
3764 * Unicode script "Malayalam".
3765 */
3766 MALAYALAM,
3767
3768 /**
3769 * Unicode script "Sinhala".
3770 */
3771 SINHALA,
3772
3773 /**
3774 * Unicode script "Thai".
3775 */
3776 THAI,
3777
3778 /**
3779 * Unicode script "Lao".
3780 */
3781 LAO,
3782
3783 /**
3784 * Unicode script "Tibetan".
3785 */
3786 TIBETAN,
3787
3788 /**
3789 * Unicode script "Myanmar".
3790 */
3791 MYANMAR,
3792
3793 /**
3794 * Unicode script "Georgian".
3795 */
3796 GEORGIAN,
3797
3798 /**
3799 * Unicode script "Hangul".
3800 */
3801 HANGUL,
3802
3803 /**
3804 * Unicode script "Ethiopic".
3805 */
3806 ETHIOPIC,
3807
3808 /**
3809 * Unicode script "Cherokee".
3810 */
3811 CHEROKEE,
3812
3813 /**
3814 * Unicode script "Canadian_Aboriginal".
3815 */
3816 CANADIAN_ABORIGINAL,
3817
3818 /**
3819 * Unicode script "Ogham".
3820 */
3821 OGHAM,
3822
3823 /**
3824 * Unicode script "Runic".
3825 */
3826 RUNIC,
3827
3828 /**
3829 * Unicode script "Khmer".
3830 */
3831 KHMER,
3832
3833 /**
3834 * Unicode script "Mongolian".
3835 */
3836 MONGOLIAN,
3837
3838 /**
3839 * Unicode script "Hiragana".
3840 */
3841 HIRAGANA,
3842
3843 /**
3844 * Unicode script "Katakana".
3845 */
3846 KATAKANA,
3847
3848 /**
3849 * Unicode script "Bopomofo".
3850 */
3851 BOPOMOFO,
3852
3853 /**
3854 * Unicode script "Han".
3855 */
3856 HAN,
3857
3858 /**
3859 * Unicode script "Yi".
3860 */
3861 YI,
3862
3863 /**
3864 * Unicode script "Old_Italic".
3865 */
3866 OLD_ITALIC,
3867
3868 /**
3869 * Unicode script "Gothic".
3870 */
3871 GOTHIC,
3872
3873 /**
3874 * Unicode script "Deseret".
3875 */
3876 DESERET,
3877
3878 /**
3879 * Unicode script "Inherited".
3880 */
3881 INHERITED,
3882
3883 /**
3884 * Unicode script "Tagalog".
3885 */
3886 TAGALOG,
3887
3888 /**
3889 * Unicode script "Hanunoo".
3890 */
3891 HANUNOO,
3892
3893 /**
3894 * Unicode script "Buhid".
3895 */
3896 BUHID,
3897
3898 /**
3899 * Unicode script "Tagbanwa".
3900 */
3901 TAGBANWA,
3902
3903 /**
3904 * Unicode script "Limbu".
3905 */
3906 LIMBU,
3907
3908 /**
3909 * Unicode script "Tai_Le".
3910 */
3911 TAI_LE,
3912
3913 /**
3914 * Unicode script "Linear_B".
3915 */
3916 LINEAR_B,
3917
3918 /**
3919 * Unicode script "Ugaritic".
3920 */
3921 UGARITIC,
3922
3923 /**
3924 * Unicode script "Shavian".
3925 */
3926 SHAVIAN,
3927
3928 /**
3929 * Unicode script "Osmanya".
3930 */
3931 OSMANYA,
3932
3933 /**
3934 * Unicode script "Cypriot".
3935 */
3936 CYPRIOT,
3937
3938 /**
3939 * Unicode script "Braille".
3940 */
3941 BRAILLE,
3942
3943 /**
3944 * Unicode script "Buginese".
3945 */
3946 BUGINESE,
3947
3948 /**
3949 * Unicode script "Coptic".
3950 */
3951 COPTIC,
3952
3953 /**
3954 * Unicode script "New_Tai_Lue".
3955 */
3956 NEW_TAI_LUE,
3957
3958 /**
3959 * Unicode script "Glagolitic".
3960 */
3961 GLAGOLITIC,
3962
3963 /**
3964 * Unicode script "Tifinagh".
3965 */
3966 TIFINAGH,
3967
3968 /**
3969 * Unicode script "Syloti_Nagri".
3970 */
3971 SYLOTI_NAGRI,
3972
3973 /**
3974 * Unicode script "Old_Persian".
3975 */
3976 OLD_PERSIAN,
3977
3978 /**
3979 * Unicode script "Kharoshthi".
3980 */
3981 KHAROSHTHI,
3982
3983 /**
3984 * Unicode script "Balinese".
3985 */
3986 BALINESE,
3987
3988 /**
3989 * Unicode script "Cuneiform".
3990 */
3991 CUNEIFORM,
3992
3993 /**
3994 * Unicode script "Phoenician".
3995 */
3996 PHOENICIAN,
3997
3998 /**
3999 * Unicode script "Phags_Pa".
4000 */
4001 PHAGS_PA,
4002
4003 /**
4004 * Unicode script "Nko".
4005 */
4006 NKO,
4007
4008 /**
4009 * Unicode script "Sundanese".
4010 */
4011 SUNDANESE,
4012
4013 /**
4014 * Unicode script "Batak".
4015 */
4016 BATAK,
4017
4018 /**
4019 * Unicode script "Lepcha".
4020 */
4021 LEPCHA,
4022
4023 /**
4024 * Unicode script "Ol_Chiki".
4025 */
4026 OL_CHIKI,
4027
4028 /**
4029 * Unicode script "Vai".
4030 */
4031 VAI,
4032
4033 /**
4034 * Unicode script "Saurashtra".
4035 */
4036 SAURASHTRA,
4037
4038 /**
4039 * Unicode script "Kayah_Li".
4040 */
4041 KAYAH_LI,
4042
4043 /**
4044 * Unicode script "Rejang".
4045 */
4046 REJANG,
4047
4048 /**
4049 * Unicode script "Lycian".
4050 */
4051 LYCIAN,
4052
4053 /**
4054 * Unicode script "Carian".
4055 */
4056 CARIAN,
4057
4058 /**
4059 * Unicode script "Lydian".
4060 */
4061 LYDIAN,
4062
4063 /**
4064 * Unicode script "Cham".
4065 */
4066 CHAM,
4067
4068 /**
4069 * Unicode script "Tai_Tham".
4070 */
4071 TAI_THAM,
4072
4073 /**
4074 * Unicode script "Tai_Viet".
4075 */
4076 TAI_VIET,
4077
4078 /**
4079 * Unicode script "Avestan".
4080 */
4081 AVESTAN,
4082
4083 /**
4084 * Unicode script "Egyptian_Hieroglyphs".
4085 */
4086 EGYPTIAN_HIEROGLYPHS,
4087
4088 /**
4089 * Unicode script "Samaritan".
4090 */
4091 SAMARITAN,
4092
4093 /**
4094 * Unicode script "Mandaic".
4095 */
4096 MANDAIC,
4097
4098 /**
4099 * Unicode script "Lisu".
4100 */
4101 LISU,
4102
4103 /**
4104 * Unicode script "Bamum".
4105 */
4106 BAMUM,
4107
4108 /**
4109 * Unicode script "Javanese".
4110 */
4111 JAVANESE,
4112
4113 /**
4114 * Unicode script "Meetei_Mayek".
4115 */
4116 MEETEI_MAYEK,
4117
4118 /**
4119 * Unicode script "Imperial_Aramaic".
4120 */
4121 IMPERIAL_ARAMAIC,
4122
4123 /**
4124 * Unicode script "Old_South_Arabian".
4125 */
4126 OLD_SOUTH_ARABIAN,
4127
4128 /**
4129 * Unicode script "Inscriptional_Parthian".
4130 */
4131 INSCRIPTIONAL_PARTHIAN,
4132
4133 /**
4134 * Unicode script "Inscriptional_Pahlavi".
4135 */
4136 INSCRIPTIONAL_PAHLAVI,
4137
4138 /**
4139 * Unicode script "Old_Turkic".
4140 */
4141 OLD_TURKIC,
4142
4143 /**
4144 * Unicode script "Brahmi".
4145 */
4146 BRAHMI,
4147
4148 /**
4149 * Unicode script "Kaithi".
4150 */
4151 KAITHI,
4152
4153 /**
4154 * Unicode script "Meroitic Hieroglyphs".
4155 * @since 1.8
4156 */
4157 MEROITIC_HIEROGLYPHS,
4158
4159 /**
4160 * Unicode script "Meroitic Cursive".
4161 * @since 1.8
4162 */
4163 MEROITIC_CURSIVE,
4164
4165 /**
4166 * Unicode script "Sora Sompeng".
4167 * @since 1.8
4168 */
4169 SORA_SOMPENG,
4170
4171 /**
4172 * Unicode script "Chakma".
4173 * @since 1.8
4174 */
4175 CHAKMA,
4176
4177 /**
4178 * Unicode script "Sharada".
4179 * @since 1.8
4180 */
4181 SHARADA,
4182
4183 /**
4184 * Unicode script "Takri".
4185 * @since 1.8
4186 */
4187 TAKRI,
4188
4189 /**
4190 * Unicode script "Miao".
4191 * @since 1.8
4192 */
4193 MIAO,
4194
4195 /**
4196 * Unicode script "Caucasian Albanian".
4197 * @since 1.9
4198 */
4199 CAUCASIAN_ALBANIAN,
4200
4201 /**
4202 * Unicode script "Bassa Vah".
4203 * @since 1.9
4204 */
4205 BASSA_VAH,
4206
4207 /**
4208 * Unicode script "Duployan".
4209 * @since 1.9
4210 */
4211 DUPLOYAN,
4212
4213 /**
4214 * Unicode script "Elbasan".
4215 * @since 1.9
4216 */
4217 ELBASAN,
4218
4219 /**
4220 * Unicode script "Grantha".
4221 * @since 1.9
4222 */
4223 GRANTHA,
4224
4225 /**
4226 * Unicode script "Pahawh Hmong".
4227 * @since 1.9
4228 */
4229 PAHAWH_HMONG,
4230
4231 /**
4232 * Unicode script "Khojki".
4233 * @since 1.9
4234 */
4235 KHOJKI,
4236
4237 /**
4238 * Unicode script "Linear A".
4239 * @since 1.9
4240 */
4241 LINEAR_A,
4242
4243 /**
4244 * Unicode script "Mahajani".
4245 * @since 1.9
4246 */
4247 MAHAJANI,
4248
4249 /**
4250 * Unicode script "Manichaean".
4251 * @since 1.9
4252 */
4253 MANICHAEAN,
4254
4255 /**
4256 * Unicode script "Mende Kikakui".
4257 * @since 1.9
4258 */
4259 MENDE_KIKAKUI,
4260
4261 /**
4262 * Unicode script "Modi".
4263 * @since 1.9
4264 */
4265 MODI,
4266
4267 /**
4268 * Unicode script "Mro".
4269 * @since 1.9
4270 */
4271 MRO,
4272
4273 /**
4274 * Unicode script "Old North Arabian".
4275 * @since 1.9
4276 */
4277 OLD_NORTH_ARABIAN,
4278
4279 /**
4280 * Unicode script "Nabataean".
4281 * @since 1.9
4282 */
4283 NABATAEAN,
4284
4285 /**
4286 * Unicode script "Palmyrene".
4287 * @since 1.9
4288 */
4289 PALMYRENE,
4290
4291 /**
4292 * Unicode script "Pau Cin Hau".
4293 * @since 1.9
4294 */
4295 PAU_CIN_HAU,
4296
4297 /**
4298 * Unicode script "Old Permic".
4299 * @since 1.9
4300 */
4301 OLD_PERMIC,
4302
4303 /**
4304 * Unicode script "Psalter Pahlavi".
4305 * @since 1.9
4306 */
4307 PSALTER_PAHLAVI,
4308
4309 /**
4310 * Unicode script "Siddham".
4311 * @since 1.9
4312 */
4313 SIDDHAM,
4314
4315 /**
4316 * Unicode script "Khudawadi".
4317 * @since 1.9
4318 */
4319 KHUDAWADI,
4320
4321 /**
4322 * Unicode script "Tirhuta".
4323 * @since 1.9
4324 */
4325 TIRHUTA,
4326
4327 /**
4328 * Unicode script "Warang Citi".
4329 * @since 1.9
4330 */
4331 WARANG_CITI,
4332
4333 /**
4334 * Unicode script "Ahom".
4335 * @since 1.9
4336 */
4337 AHOM,
4338
4339 /**
4340 * Unicode script "Anatolian Hieroglyphs".
4341 * @since 1.9
4342 */
4343 ANATOLIAN_HIEROGLYPHS,
4344
4345 /**
4346 * Unicode script "Hatran".
4347 * @since 1.9
4348 */
4349 HATRAN,
4350
4351 /**
4352 * Unicode script "Multani".
4353 * @since 1.9
4354 */
4355 MULTANI,
4356
4357 /**
4358 * Unicode script "Old Hungarian".
4359 * @since 1.9
4360 */
4361 OLD_HUNGARIAN,
4362
4363 /**
4364 * Unicode script "SignWriting".
4365 * @since 1.9
4366 */
4367 SIGNWRITING,
4368
4369 /**
4370 * Unicode script "Unknown".
4371 */
4372 UNKNOWN;
4373
4374 private static final int[] scriptStarts = {
4375 0x0000, // 0000..0040; COMMON
4376 0x0041, // 0041..005A; LATIN
4377 0x005B, // 005B..0060; COMMON
4378 0x0061, // 0061..007A; LATIN
4379 0x007B, // 007B..00A9; COMMON
4380 0x00AA, // 00AA ; LATIN
4381 0x00AB, // 00AB..00B9; COMMON
4382 0x00BA, // 00BA ; LATIN
4383 0x00BB, // 00BB..00BF; COMMON
4384 0x00C0, // 00C0..00D6; LATIN
4385 0x00D7, // 00D7 ; COMMON
4386 0x00D8, // 00D8..00F6; LATIN
4387 0x00F7, // 00F7 ; COMMON
4388 0x00F8, // 00F8..02B8; LATIN
4389 0x02B9, // 02B9..02DF; COMMON
4390 0x02E0, // 02E0..02E4; LATIN
4391 0x02E5, // 02E5..02E9; COMMON
4392 0x02EA, // 02EA..02EB; BOPOMOFO
4393 0x02EC, // 02EC..02FF; COMMON
4394 0x0300, // 0300..036F; INHERITED
4395 0x0370, // 0370..0373; GREEK
4396 0x0374, // 0374 ; COMMON
4397 0x0375, // 0375..0377; GREEK
4398 0x0378, // 0378..0379; UNKNOWN
4399 0x037A, // 037A..037D; GREEK
4400 0x037E, // 037E ; COMMON
4401 0x037F, // 037F ; GREEK
4402 0x0380, // 0380..0383; UNKNOWN
4403 0x0384, // 0384 ; GREEK
4404 0x0385, // 0385 ; COMMON
4405 0x0386, // 0386 ; GREEK
4406 0x0387, // 0387 ; COMMON
4407 0x0388, // 0388..038A; GREEK
4408 0x038B, // 038B ; UNKNOWN
4409 0x038C, // 038C ; GREEK
4410 0x038D, // 038D ; UNKNOWN
4411 0x038E, // 038E..03A1; GREEK
4412 0x03A2, // 03A2 ; UNKNOWN
4413 0x03A3, // 03A3..03E1; GREEK
4414 0x03E2, // 03E2..03EF; COPTIC
4415 0x03F0, // 03F0..03FF; GREEK
4416 0x0400, // 0400..0484; CYRILLIC
4417 0x0485, // 0485..0486; INHERITED
4418 0x0487, // 0487..052F; CYRILLIC
4419 0x0530, // 0530 ; UNKNOWN
4420 0x0531, // 0531..0556; ARMENIAN
4421 0x0557, // 0557..0558; UNKNOWN
4422 0x0559, // 0559..055F; ARMENIAN
4423 0x0560, // 0560 ; UNKNOWN
4424 0x0561, // 0561..0587; ARMENIAN
4425 0x0588, // 0588 ; UNKNOWN
4426 0x0589, // 0589 ; COMMON
4427 0x058A, // 058A ; ARMENIAN
4428 0x058B, // 058B..058C; UNKNOWN
4429 0x058D, // 058D..058F; ARMENIAN
4430 0x0590, // 0590 ; UNKNOWN
4431 0x0591, // 0591..05C7; HEBREW
4432 0x05C8, // 05C8..05CF; UNKNOWN
4433 0x05D0, // 05D0..05EA; HEBREW
4434 0x05EB, // 05EB..05EF; UNKNOWN
4435 0x05F0, // 05F0..05F4; HEBREW
4436 0x05F5, // 05F5..05FF; UNKNOWN
4437 0x0600, // 0600..0604; ARABIC
4438 0x0605, // 0605 ; COMMON
4439 0x0606, // 0606..060B; ARABIC
4440 0x060C, // 060C ; COMMON
4441 0x060D, // 060D..061A; ARABIC
4442 0x061B, // 061B..061C; COMMON
4443 0x061D, // 061D ; UNKNOWN
4444 0x061E, // 061E ; ARABIC
4445 0x061F, // 061F ; COMMON
4446 0x0620, // 0620..063F; ARABIC
4447 0x0640, // 0640 ; COMMON
4448 0x0641, // 0641..064A; ARABIC
4449 0x064B, // 064B..0655; INHERITED
4450 0x0656, // 0656..066F; ARABIC
4451 0x0670, // 0670 ; INHERITED
4452 0x0671, // 0671..06DC; ARABIC
4453 0x06DD, // 06DD ; COMMON
4454 0x06DE, // 06DE..06FF; ARABIC
4455 0x0700, // 0700..070D; SYRIAC
4456 0x070E, // 070E ; UNKNOWN
4457 0x070F, // 070F..074A; SYRIAC
4458 0x074B, // 074B..074C; UNKNOWN
4459 0x074D, // 074D..074F; SYRIAC
4460 0x0750, // 0750..077F; ARABIC
4461 0x0780, // 0780..07B1; THAANA
4462 0x07B2, // 07B2..07BF; UNKNOWN
4463 0x07C0, // 07C0..07FA; NKO
4464 0x07FB, // 07FB..07FF; UNKNOWN
4465 0x0800, // 0800..082D; SAMARITAN
4466 0x082E, // 082E..082F; UNKNOWN
4467 0x0830, // 0830..083E; SAMARITAN
4468 0x083F, // 083F ; UNKNOWN
4469 0x0840, // 0840..085B; MANDAIC
4470 0x085C, // 085C..085D; UNKNOWN
4471 0x085E, // 085E ; MANDAIC
4472 0x085F, // 085F..089F; UNKNOWN
4473 0x08A0, // 08A0..08B4; ARABIC
4474 0x08B5, // 08B5..08E2; UNKNOWN
4475 0x08E3, // 08E3..08FF; ARABIC
4476 0x0900, // 0900..0950; DEVANAGARI
4477 0x0951, // 0951..0952; INHERITED
4478 0x0953, // 0953..0963; DEVANAGARI
4479 0x0964, // 0964..0965; COMMON
4480 0x0966, // 0966..097F; DEVANAGARI
4481 0x0980, // 0980..0983; BENGALI
4482 0x0984, // 0984 ; UNKNOWN
4483 0x0985, // 0985..098C; BENGALI
4484 0x098D, // 098D..098E; UNKNOWN
4485 0x098F, // 098F..0990; BENGALI
4486 0x0991, // 0991..0992; UNKNOWN
4487 0x0993, // 0993..09A8; BENGALI
4488 0x09A9, // 09A9 ; UNKNOWN
4489 0x09AA, // 09AA..09B0; BENGALI
4490 0x09B1, // 09B1 ; UNKNOWN
4491 0x09B2, // 09B2 ; BENGALI
4492 0x09B3, // 09B3..09B5; UNKNOWN
4493 0x09B6, // 09B6..09B9; BENGALI
4494 0x09BA, // 09BA..09BB; UNKNOWN
4495 0x09BC, // 09BC..09C4; BENGALI
4496 0x09C5, // 09C5..09C6; UNKNOWN
4497 0x09C7, // 09C7..09C8; BENGALI
4498 0x09C9, // 09C9..09CA; UNKNOWN
4499 0x09CB, // 09CB..09CE; BENGALI
4500 0x09CF, // 09CF..09D6; UNKNOWN
4501 0x09D7, // 09D7 ; BENGALI
4502 0x09D8, // 09D8..09DB; UNKNOWN
4503 0x09DC, // 09DC..09DD; BENGALI
4504 0x09DE, // 09DE ; UNKNOWN
4505 0x09DF, // 09DF..09E3; BENGALI
4506 0x09E4, // 09E4..09E5; UNKNOWN
4507 0x09E6, // 09E6..09FB; BENGALI
4508 0x09FC, // 09FC..0A00; UNKNOWN
4509 0x0A01, // 0A01..0A03; GURMUKHI
4510 0x0A04, // 0A04 ; UNKNOWN
4511 0x0A05, // 0A05..0A0A; GURMUKHI
4512 0x0A0B, // 0A0B..0A0E; UNKNOWN
4513 0x0A0F, // 0A0F..0A10; GURMUKHI
4514 0x0A11, // 0A11..0A12; UNKNOWN
4515 0x0A13, // 0A13..0A28; GURMUKHI
4516 0x0A29, // 0A29 ; UNKNOWN
4517 0x0A2A, // 0A2A..0A30; GURMUKHI
4518 0x0A31, // 0A31 ; UNKNOWN
4519 0x0A32, // 0A32..0A33; GURMUKHI
4520 0x0A34, // 0A34 ; UNKNOWN
4521 0x0A35, // 0A35..0A36; GURMUKHI
4522 0x0A37, // 0A37 ; UNKNOWN
4523 0x0A38, // 0A38..0A39; GURMUKHI
4524 0x0A3A, // 0A3A..0A3B; UNKNOWN
4525 0x0A3C, // 0A3C ; GURMUKHI
4526 0x0A3D, // 0A3D ; UNKNOWN
4527 0x0A3E, // 0A3E..0A42; GURMUKHI
4528 0x0A43, // 0A43..0A46; UNKNOWN
4529 0x0A47, // 0A47..0A48; GURMUKHI
4530 0x0A49, // 0A49..0A4A; UNKNOWN
4531 0x0A4B, // 0A4B..0A4D; GURMUKHI
4532 0x0A4E, // 0A4E..0A50; UNKNOWN
4533 0x0A51, // 0A51 ; GURMUKHI
4534 0x0A52, // 0A52..0A58; UNKNOWN
4535 0x0A59, // 0A59..0A5C; GURMUKHI
4536 0x0A5D, // 0A5D ; UNKNOWN
4537 0x0A5E, // 0A5E ; GURMUKHI
4538 0x0A5F, // 0A5F..0A65; UNKNOWN
4539 0x0A66, // 0A66..0A75; GURMUKHI
4540 0x0A76, // 0A76..0A80; UNKNOWN
4541 0x0A81, // 0A81..0A83; GUJARATI
4542 0x0A84, // 0A84 ; UNKNOWN
4543 0x0A85, // 0A85..0A8D; GUJARATI
4544 0x0A8E, // 0A8E ; UNKNOWN
4545 0x0A8F, // 0A8F..0A91; GUJARATI
4546 0x0A92, // 0A92 ; UNKNOWN
4547 0x0A93, // 0A93..0AA8; GUJARATI
4548 0x0AA9, // 0AA9 ; UNKNOWN
4549 0x0AAA, // 0AAA..0AB0; GUJARATI
4550 0x0AB1, // 0AB1 ; UNKNOWN
4551 0x0AB2, // 0AB2..0AB3; GUJARATI
4552 0x0AB4, // 0AB4 ; UNKNOWN
4553 0x0AB5, // 0AB5..0AB9; GUJARATI
4554 0x0ABA, // 0ABA..0ABB; UNKNOWN
4555 0x0ABC, // 0ABC..0AC5; GUJARATI
4556 0x0AC6, // 0AC6 ; UNKNOWN
4557 0x0AC7, // 0AC7..0AC9; GUJARATI
4558 0x0ACA, // 0ACA ; UNKNOWN
4559 0x0ACB, // 0ACB..0ACD; GUJARATI
4560 0x0ACE, // 0ACE..0ACF; UNKNOWN
4561 0x0AD0, // 0AD0 ; GUJARATI
4562 0x0AD1, // 0AD1..0ADF; UNKNOWN
4563 0x0AE0, // 0AE0..0AE3; GUJARATI
4564 0x0AE4, // 0AE4..0AE5; UNKNOWN
4565 0x0AE6, // 0AE6..0AF1; GUJARATI
4566 0x0AF2, // 0AF2..0AF8; UNKNOWN
4567 0x0AF9, // 0AF9 ; GUJARATI
4568 0x0AFA, // 0AFA..0B00; UNKNOWN
4569 0x0B01, // 0B01..0B03; ORIYA
4570 0x0B04, // 0B04 ; UNKNOWN
4571 0x0B05, // 0B05..0B0C; ORIYA
4572 0x0B0D, // 0B0D..0B0E; UNKNOWN
4573 0x0B0F, // 0B0F..0B10; ORIYA
4574 0x0B11, // 0B11..0B12; UNKNOWN
4575 0x0B13, // 0B13..0B28; ORIYA
4576 0x0B29, // 0B29 ; UNKNOWN
4577 0x0B2A, // 0B2A..0B30; ORIYA
4578 0x0B31, // 0B31 ; UNKNOWN
4579 0x0B32, // 0B32..0B33; ORIYA
4580 0x0B34, // 0B34 ; UNKNOWN
4581 0x0B35, // 0B35..0B39; ORIYA
4582 0x0B3A, // 0B3A..0B3B; UNKNOWN
4583 0x0B3C, // 0B3C..0B44; ORIYA
4584 0x0B45, // 0B45..0B46; UNKNOWN
4585 0x0B47, // 0B47..0B48; ORIYA
4586 0x0B49, // 0B49..0B4A; UNKNOWN
4587 0x0B4B, // 0B4B..0B4D; ORIYA
4588 0x0B4E, // 0B4E..0B55; UNKNOWN
4589 0x0B56, // 0B56..0B57; ORIYA
4590 0x0B58, // 0B58..0B5B; UNKNOWN
4591 0x0B5C, // 0B5C..0B5D; ORIYA
4592 0x0B5E, // 0B5E ; UNKNOWN
4593 0x0B5F, // 0B5F..0B63; ORIYA
4594 0x0B64, // 0B64..0B65; UNKNOWN
4595 0x0B66, // 0B66..0B77; ORIYA
4596 0x0B78, // 0B78..0B81; UNKNOWN
4597 0x0B82, // 0B82..0B83; TAMIL
4598 0x0B84, // 0B84 ; UNKNOWN
4599 0x0B85, // 0B85..0B8A; TAMIL
4600 0x0B8B, // 0B8B..0B8D; UNKNOWN
4601 0x0B8E, // 0B8E..0B90; TAMIL
4602 0x0B91, // 0B91 ; UNKNOWN
4603 0x0B92, // 0B92..0B95; TAMIL
4604 0x0B96, // 0B96..0B98; UNKNOWN
4605 0x0B99, // 0B99..0B9A; TAMIL
4606 0x0B9B, // 0B9B ; UNKNOWN
4607 0x0B9C, // 0B9C ; TAMIL
4608 0x0B9D, // 0B9D ; UNKNOWN
4609 0x0B9E, // 0B9E..0B9F; TAMIL
4610 0x0BA0, // 0BA0..0BA2; UNKNOWN
4611 0x0BA3, // 0BA3..0BA4; TAMIL
4612 0x0BA5, // 0BA5..0BA7; UNKNOWN
4613 0x0BA8, // 0BA8..0BAA; TAMIL
4614 0x0BAB, // 0BAB..0BAD; UNKNOWN
4615 0x0BAE, // 0BAE..0BB9; TAMIL
4616 0x0BBA, // 0BBA..0BBD; UNKNOWN
4617 0x0BBE, // 0BBE..0BC2; TAMIL
4618 0x0BC3, // 0BC3..0BC5; UNKNOWN
4619 0x0BC6, // 0BC6..0BC8; TAMIL
4620 0x0BC9, // 0BC9 ; UNKNOWN
4621 0x0BCA, // 0BCA..0BCD; TAMIL
4622 0x0BCE, // 0BCE..0BCF; UNKNOWN
4623 0x0BD0, // 0BD0 ; TAMIL
4624 0x0BD1, // 0BD1..0BD6; UNKNOWN
4625 0x0BD7, // 0BD7 ; TAMIL
4626 0x0BD8, // 0BD8..0BE5; UNKNOWN
4627 0x0BE6, // 0BE6..0BFA; TAMIL
4628 0x0BFB, // 0BFB..0BFF; UNKNOWN
4629 0x0C00, // 0C00..0C03; TELUGU
4630 0x0C04, // 0C04 ; UNKNOWN
4631 0x0C05, // 0C05..0C0C; TELUGU
4632 0x0C0D, // 0C0D ; UNKNOWN
4633 0x0C0E, // 0C0E..0C10; TELUGU
4634 0x0C11, // 0C11 ; UNKNOWN
4635 0x0C12, // 0C12..0C28; TELUGU
4636 0x0C29, // 0C29 ; UNKNOWN
4637 0x0C2A, // 0C2A..0C39; TELUGU
4638 0x0C3A, // 0C3A..0C3C; UNKNOWN
4639 0x0C3D, // 0C3D..0C44; TELUGU
4640 0x0C45, // 0C45 ; UNKNOWN
4641 0x0C46, // 0C46..0C48; TELUGU
4642 0x0C49, // 0C49 ; UNKNOWN
4643 0x0C4A, // 0C4A..0C4D; TELUGU
4644 0x0C4E, // 0C4E..0C54; UNKNOWN
4645 0x0C55, // 0C55..0C56; TELUGU
4646 0x0C57, // 0C57 ; UNKNOWN
4647 0x0C58, // 0C58..0C5A; TELUGU
4648 0x0C5B, // 0C5B..0C5F; UNKNOWN
4649 0x0C60, // 0C60..0C63; TELUGU
4650 0x0C64, // 0C64..0C65; UNKNOWN
4651 0x0C66, // 0C66..0C6F; TELUGU
4652 0x0C70, // 0C70..0C77; UNKNOWN
4653 0x0C78, // 0C78..0C7F; TELUGU
4654 0x0C80, // 0C80 ; UNKNOWN
4655 0x0C81, // 0C81..0C83; KANNADA
4656 0x0C84, // 0C84 ; UNKNOWN
4657 0x0C85, // 0C85..0C8C; KANNADA
4658 0x0C8D, // 0C8D ; UNKNOWN
4659 0x0C8E, // 0C8E..0C90; KANNADA
4660 0x0C91, // 0C91 ; UNKNOWN
4661 0x0C92, // 0C92..0CA8; KANNADA
4662 0x0CA9, // 0CA9 ; UNKNOWN
4663 0x0CAA, // 0CAA..0CB3; KANNADA
4664 0x0CB4, // 0CB4 ; UNKNOWN
4665 0x0CB5, // 0CB5..0CB9; KANNADA
4666 0x0CBA, // 0CBA..0CBB; UNKNOWN
4667 0x0CBC, // 0CBC..0CC4; KANNADA
4668 0x0CC5, // 0CC5 ; UNKNOWN
4669 0x0CC6, // 0CC6..0CC8; KANNADA
4670 0x0CC9, // 0CC9 ; UNKNOWN
4671 0x0CCA, // 0CCA..0CCD; KANNADA
4672 0x0CCE, // 0CCE..0CD4; UNKNOWN
4673 0x0CD5, // 0CD5..0CD6; KANNADA
4674 0x0CD7, // 0CD7..0CDD; UNKNOWN
4675 0x0CDE, // 0CDE ; KANNADA
4676 0x0CDF, // 0CDF ; UNKNOWN
4677 0x0CE0, // 0CE0..0CE3; KANNADA
4678 0x0CE4, // 0CE4..0CE5; UNKNOWN
4679 0x0CE6, // 0CE6..0CEF; KANNADA
4680 0x0CF0, // 0CF0 ; UNKNOWN
4681 0x0CF1, // 0CF1..0CF2; KANNADA
4682 0x0CF3, // 0CF3..0D00; UNKNOWN
4683 0x0D01, // 0D01..0D03; MALAYALAM
4684 0x0D04, // 0D04 ; UNKNOWN
4685 0x0D05, // 0D05..0D0C; MALAYALAM
4686 0x0D0D, // 0D0D ; UNKNOWN
4687 0x0D0E, // 0D0E..0D10; MALAYALAM
4688 0x0D11, // 0D11 ; UNKNOWN
4689 0x0D12, // 0D12..0D3A; MALAYALAM
4690 0x0D3B, // 0D3B..0D3C; UNKNOWN
4691 0x0D3D, // 0D3D..0D44; MALAYALAM
4692 0x0D45, // 0D45 ; UNKNOWN
4693 0x0D46, // 0D46..0D48; MALAYALAM
4694 0x0D49, // 0D49 ; UNKNOWN
4695 0x0D4A, // 0D4A..0D4E; MALAYALAM
4696 0x0D4F, // 0D4F..0D56; UNKNOWN
4697 0x0D57, // 0D57 ; MALAYALAM
4698 0x0D58, // 0D58..0D5E; UNKNOWN
4699 0x0D5F, // 0D5F..0D63; MALAYALAM
4700 0x0D64, // 0D64..0D65; UNKNOWN
4701 0x0D66, // 0D66..0D75; MALAYALAM
4702 0x0D76, // 0D76..0D78; UNKNOWN
4703 0x0D79, // 0D79..0D7F; MALAYALAM
4704 0x0D80, // 0D80..0D81; UNKNOWN
4705 0x0D82, // 0D82..0D83; SINHALA
4706 0x0D84, // 0D84 ; UNKNOWN
4707 0x0D85, // 0D85..0D96; SINHALA
4708 0x0D97, // 0D97..0D99; UNKNOWN
4709 0x0D9A, // 0D9A..0DB1; SINHALA
4710 0x0DB2, // 0DB2 ; UNKNOWN
4711 0x0DB3, // 0DB3..0DBB; SINHALA
4712 0x0DBC, // 0DBC ; UNKNOWN
4713 0x0DBD, // 0DBD ; SINHALA
4714 0x0DBE, // 0DBE..0DBF; UNKNOWN
4715 0x0DC0, // 0DC0..0DC6; SINHALA
4716 0x0DC7, // 0DC7..0DC9; UNKNOWN
4717 0x0DCA, // 0DCA ; SINHALA
4718 0x0DCB, // 0DCB..0DCE; UNKNOWN
4719 0x0DCF, // 0DCF..0DD4; SINHALA
4720 0x0DD5, // 0DD5 ; UNKNOWN
4721 0x0DD6, // 0DD6 ; SINHALA
4722 0x0DD7, // 0DD7 ; UNKNOWN
4723 0x0DD8, // 0DD8..0DDF; SINHALA
4724 0x0DE0, // 0DE0..0DE5; UNKNOWN
4725 0x0DE6, // 0DE6..0DEF; SINHALA
4726 0x0DF0, // 0DF0..0DF1; UNKNOWN
4727 0x0DF2, // 0DF2..0DF4; SINHALA
4728 0x0DF5, // 0DF5..0E00; UNKNOWN
4729 0x0E01, // 0E01..0E3A; THAI
4730 0x0E3B, // 0E3B..0E3E; UNKNOWN
4731 0x0E3F, // 0E3F ; COMMON
4732 0x0E40, // 0E40..0E5B; THAI
4733 0x0E5C, // 0E5C..0E80; UNKNOWN
4734 0x0E81, // 0E81..0E82; LAO
4735 0x0E83, // 0E83 ; UNKNOWN
4736 0x0E84, // 0E84 ; LAO
4737 0x0E85, // 0E85..0E86; UNKNOWN
4738 0x0E87, // 0E87..0E88; LAO
4739 0x0E89, // 0E89 ; UNKNOWN
4740 0x0E8A, // 0E8A ; LAO
4741 0x0E8B, // 0E8B..0E8C; UNKNOWN
4742 0x0E8D, // 0E8D ; LAO
4743 0x0E8E, // 0E8E..0E93; UNKNOWN
4744 0x0E94, // 0E94..0E97; LAO
4745 0x0E98, // 0E98 ; UNKNOWN
4746 0x0E99, // 0E99..0E9F; LAO
4747 0x0EA0, // 0EA0 ; UNKNOWN
4748 0x0EA1, // 0EA1..0EA3; LAO
4749 0x0EA4, // 0EA4 ; UNKNOWN
4750 0x0EA5, // 0EA5 ; LAO
4751 0x0EA6, // 0EA6 ; UNKNOWN
4752 0x0EA7, // 0EA7 ; LAO
4753 0x0EA8, // 0EA8..0EA9; UNKNOWN
4754 0x0EAA, // 0EAA..0EAB; LAO
4755 0x0EAC, // 0EAC ; UNKNOWN
4756 0x0EAD, // 0EAD..0EB9; LAO
4757 0x0EBA, // 0EBA ; UNKNOWN
4758 0x0EBB, // 0EBB..0EBD; LAO
4759 0x0EBE, // 0EBE..0EBF; UNKNOWN
4760 0x0EC0, // 0EC0..0EC4; LAO
4761 0x0EC5, // 0EC5 ; UNKNOWN
4762 0x0EC6, // 0EC6 ; LAO
4763 0x0EC7, // 0EC7 ; UNKNOWN
4764 0x0EC8, // 0EC8..0ECD; LAO
4765 0x0ECE, // 0ECE..0ECF; UNKNOWN
4766 0x0ED0, // 0ED0..0ED9; LAO
4767 0x0EDA, // 0EDA..0EDB; UNKNOWN
4768 0x0EDC, // 0EDC..0EDF; LAO
4769 0x0EE0, // 0EE0..0EFF; UNKNOWN
4770 0x0F00, // 0F00..0F47; TIBETAN
4771 0x0F48, // 0F48 ; UNKNOWN
4772 0x0F49, // 0F49..0F6C; TIBETAN
4773 0x0F6D, // 0F6D..0F70; UNKNOWN
4774 0x0F71, // 0F71..0F97; TIBETAN
4775 0x0F98, // 0F98 ; UNKNOWN
4776 0x0F99, // 0F99..0FBC; TIBETAN
4777 0x0FBD, // 0FBD ; UNKNOWN
4778 0x0FBE, // 0FBE..0FCC; TIBETAN
4779 0x0FCD, // 0FCD ; UNKNOWN
4780 0x0FCE, // 0FCE..0FD4; TIBETAN
4781 0x0FD5, // 0FD5..0FD8; COMMON
4782 0x0FD9, // 0FD9..0FDA; TIBETAN
4783 0x0FDB, // 0FDB..FFF; UNKNOWN
4784 0x1000, // 1000..109F; MYANMAR
4785 0x10A0, // 10A0..10C5; GEORGIAN
4786 0x10C6, // 10C6 ; UNKNOWN
4787 0x10C7, // 10C7 ; GEORGIAN
4788 0x10C8, // 10C8..10CC; UNKNOWN
4789 0x10CD, // 10CD ; GEORGIAN
4790 0x10CE, // 10CE..10CF; UNKNOWN
4791 0x10D0, // 10D0..10FA; GEORGIAN
4792 0x10FB, // 10FB ; COMMON
4793 0x10FC, // 10FC..10FF; GEORGIAN
4794 0x1100, // 1100..11FF; HANGUL
4795 0x1200, // 1200..1248; ETHIOPIC
4796 0x1249, // 1249 ; UNKNOWN
4797 0x124A, // 124A..124D; ETHIOPIC
4798 0x124E, // 124E..124F; UNKNOWN
4799 0x1250, // 1250..1256; ETHIOPIC
4800 0x1257, // 1257 ; UNKNOWN
4801 0x1258, // 1258 ; ETHIOPIC
4802 0x1259, // 1259 ; UNKNOWN
4803 0x125A, // 125A..125D; ETHIOPIC
4804 0x125E, // 125E..125F; UNKNOWN
4805 0x1260, // 1260..1288; ETHIOPIC
4806 0x1289, // 1289 ; UNKNOWN
4807 0x128A, // 128A..128D; ETHIOPIC
4808 0x128E, // 128E..128F; UNKNOWN
4809 0x1290, // 1290..12B0; ETHIOPIC
4810 0x12B1, // 12B1 ; UNKNOWN
4811 0x12B2, // 12B2..12B5; ETHIOPIC
4812 0x12B6, // 12B6..12B7; UNKNOWN
4813 0x12B8, // 12B8..12BE; ETHIOPIC
4814 0x12BF, // 12BF ; UNKNOWN
4815 0x12C0, // 12C0 ; ETHIOPIC
4816 0x12C1, // 12C1 ; UNKNOWN
4817 0x12C2, // 12C2..12C5; ETHIOPIC
4818 0x12C6, // 12C6..12C7; UNKNOWN
4819 0x12C8, // 12C8..12D6; ETHIOPIC
4820 0x12D7, // 12D7 ; UNKNOWN
4821 0x12D8, // 12D8..1310; ETHIOPIC
4822 0x1311, // 1311 ; UNKNOWN
4823 0x1312, // 1312..1315; ETHIOPIC
4824 0x1316, // 1316..1317; UNKNOWN
4825 0x1318, // 1318..135A; ETHIOPIC
4826 0x135B, // 135B..135C; UNKNOWN
4827 0x135D, // 135D..137C; ETHIOPIC
4828 0x137D, // 137D..137F; UNKNOWN
4829 0x1380, // 1380..1399; ETHIOPIC
4830 0x139A, // 139A..139F; UNKNOWN
4831 0x13A0, // 13A0..13F5; CHEROKEE
4832 0x13F6, // 13F6..13F7; UNKNOWN
4833 0x13F8, // 13F8..13FD; CHEROKEE
4834 0x13FE, // 13FE..13FF; UNKNOWN
4835 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
4836 0x1680, // 1680..169C; OGHAM
4837 0x169D, // 169D..169F; UNKNOWN
4838 0x16A0, // 16A0..16EA; RUNIC
4839 0x16EB, // 16EB..16ED; COMMON
4840 0x16EE, // 16EE..16F8; RUNIC
4841 0x16F9, // 16F9..16FF; UNKNOWN
4842 0x1700, // 1700..170C; TAGALOG
4843 0x170D, // 170D ; UNKNOWN
4844 0x170E, // 170E..1714; TAGALOG
4845 0x1715, // 1715..171F; UNKNOWN
4846 0x1720, // 1720..1734; HANUNOO
4847 0x1735, // 1735..1736; COMMON
4848 0x1737, // 1737..173F; UNKNOWN
4849 0x1740, // 1740..1753; BUHID
4850 0x1754, // 1754..175F; UNKNOWN
4851 0x1760, // 1760..176C; TAGBANWA
4852 0x176D, // 176D ; UNKNOWN
4853 0x176E, // 176E..1770; TAGBANWA
4854 0x1771, // 1771 ; UNKNOWN
4855 0x1772, // 1772..1773; TAGBANWA
4856 0x1774, // 1774..177F; UNKNOWN
4857 0x1780, // 1780..17DD; KHMER
4858 0x17DE, // 17DE..17DF; UNKNOWN
4859 0x17E0, // 17E0..17E9; KHMER
4860 0x17EA, // 17EA..17EF; UNKNOWN
4861 0x17F0, // 17F0..17F9; KHMER
4862 0x17FA, // 17FA..17FF; UNKNOWN
4863 0x1800, // 1800..1801; MONGOLIAN
4864 0x1802, // 1802..1803; COMMON
4865 0x1804, // 1804 ; MONGOLIAN
4866 0x1805, // 1805 ; COMMON
4867 0x1806, // 1806..180E; MONGOLIAN
4868 0x180F, // 180F ; UNKNOWN
4869 0x1810, // 1810..1819; MONGOLIAN
4870 0x181A, // 181A..181F; UNKNOWN
4871 0x1820, // 1820..1877; MONGOLIAN
4872 0x1878, // 1878..187F; UNKNOWN
4873 0x1880, // 1880..18AA; MONGOLIAN
4874 0x18AB, // 18AB..18AF; UNKNOWN
4875 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
4876 0x18F6, // 18F6..18FF; UNKNOWN
4877 0x1900, // 1900..191E; LIMBU
4878 0x191F, // 191F ; UNKNOWN
4879 0x1920, // 1920..192B; LIMBU
4880 0x192C, // 192C..192F; UNKNOWN
4881 0x1930, // 1930..193B; LIMBU
4882 0x193C, // 193C..193F; UNKNOWN
4883 0x1940, // 1940 ; LIMBU
4884 0x1941, // 1941..1943; UNKNOWN
4885 0x1944, // 1944..194F; LIMBU
4886 0x1950, // 1950..196D; TAI_LE
4887 0x196E, // 196E..196F; UNKNOWN
4888 0x1970, // 1970..1974; TAI_LE
4889 0x1975, // 1975..197F; UNKNOWN
4890 0x1980, // 1980..19AB; NEW_TAI_LUE
4891 0x19AC, // 19AC..19AF; UNKNOWN
4892 0x19B0, // 19B0..19C9; NEW_TAI_LUE
4893 0x19CA, // 19CA..19CF; UNKNOWN
4894 0x19D0, // 19D0..19DA; NEW_TAI_LUE
4895 0x19DB, // 19DB..19DD; UNKNOWN
4896 0x19DE, // 19DE..19DF; NEW_TAI_LUE
4897 0x19E0, // 19E0..19FF; KHMER
4898 0x1A00, // 1A00..1A1B; BUGINESE
4899 0x1A1C, // 1A1C..1A1D; UNKNOWN
4900 0x1A1E, // 1A1E..1A1F; BUGINESE
4901 0x1A20, // 1A20..1A5E; TAI_THAM
4902 0x1A5F, // 1A5F ; UNKNOWN
4903 0x1A60, // 1A60..1A7C; TAI_THAM
4904 0x1A7D, // 1A7D..1A7E; UNKNOWN
4905 0x1A7F, // 1A7F..1A89; TAI_THAM
4906 0x1A8A, // 1A8A..1A8F; UNKNOWN
4907 0x1A90, // 1A90..1A99; TAI_THAM
4908 0x1A9A, // 1A9A..1A9F; UNKNOWN
4909 0x1AA0, // 1AA0..1AAD; TAI_THAM
4910 0x1AAE, // 1AAE..1AAF; UNKNOWN
4911 0x1AB0, // 1AB0..1ABE; INHERITED
4912 0x1ABF, // 1ABF..1AFF; UNKNOWN
4913 0x1B00, // 1B00..1B4B; BALINESE
4914 0x1B4C, // 1B4C..1B4F; UNKNOWN
4915 0x1B50, // 1B50..1B7C; BALINESE
4916 0x1B7D, // 1B7D..1B7F; UNKNOWN
4917 0x1B80, // 1B80..1BBF; SUNDANESE
4918 0x1BC0, // 1BC0..1BF3; BATAK
4919 0x1BF4, // 1BF4..1BFB; UNKNOWN
4920 0x1BFC, // 1BFC..1BFF; BATAK
4921 0x1C00, // 1C00..1C37; LEPCHA
4922 0x1C38, // 1C38..1C3A; UNKNOWN
4923 0x1C3B, // 1C3B..1C49; LEPCHA
4924 0x1C4A, // 1C4A..1C4C; UNKNOWN
4925 0x1C4D, // 1C4D..1C4F; LEPCHA
4926 0x1C50, // 1C50..1C7F; OL_CHIKI
4927 0x1C80, // 1C80..1CBF; UNKNOWN
4928 0x1CC0, // 1CC0..1CC7; SUNDANESE
4929 0x1CC8, // 1CC8..1CCF; UNKNOWN
4930 0x1CD0, // 1CD0..1CD2; INHERITED
4931 0x1CD3, // 1CD3 ; COMMON
4932 0x1CD4, // 1CD4..1CE0; INHERITED
4933 0x1CE1, // 1CE1 ; COMMON
4934 0x1CE2, // 1CE2..1CE8; INHERITED
4935 0x1CE9, // 1CE9..1CEC; COMMON
4936 0x1CED, // 1CED ; INHERITED
4937 0x1CEE, // 1CEE..1CF3; COMMON
4938 0x1CF4, // 1CF4 ; INHERITED
4939 0x1CF5, // 1CF5..1CF6; COMMON
4940 0x1CF7, // 1CF7 ; UNKNOWN
4941 0x1CF8, // 1CF8..1CF9; INHERITED
4942 0x1CFA, // 1CFA..1CFF; UNKNOWN
4943 0x1D00, // 1D00..1D25; LATIN
4944 0x1D26, // 1D26..1D2A; GREEK
4945 0x1D2B, // 1D2B ; CYRILLIC
4946 0x1D2C, // 1D2C..1D5C; LATIN
4947 0x1D5D, // 1D5D..1D61; GREEK
4948 0x1D62, // 1D62..1D65; LATIN
4949 0x1D66, // 1D66..1D6A; GREEK
4950 0x1D6B, // 1D6B..1D77; LATIN
4951 0x1D78, // 1D78 ; CYRILLIC
4952 0x1D79, // 1D79..1DBE; LATIN
4953 0x1DBF, // 1DBF ; GREEK
4954 0x1DC0, // 1DC0..1DF5; INHERITED
4955 0x1DF6, // 1DF6..1DFB; UNKNOWN
4956 0x1DFC, // 1DFC..1DFF; INHERITED
4957 0x1E00, // 1E00..1EFF; LATIN
4958 0x1F00, // 1F00..1F15; GREEK
4959 0x1F16, // 1F16..1F17; UNKNOWN
4960 0x1F18, // 1F18..1F1D; GREEK
4961 0x1F1E, // 1F1E..1F1F; UNKNOWN
4962 0x1F20, // 1F20..1F45; GREEK
4963 0x1F46, // 1F46..1F47; UNKNOWN
4964 0x1F48, // 1F48..1F4D; GREEK
4965 0x1F4E, // 1F4E..1F4F; UNKNOWN
4966 0x1F50, // 1F50..1F57; GREEK
4967 0x1F58, // 1F58 ; UNKNOWN
4968 0x1F59, // 1F59 ; GREEK
4969 0x1F5A, // 1F5A ; UNKNOWN
4970 0x1F5B, // 1F5B ; GREEK
4971 0x1F5C, // 1F5C ; UNKNOWN
4972 0x1F5D, // 1F5D ; GREEK
4973 0x1F5E, // 1F5E ; UNKNOWN
4974 0x1F5F, // 1F5F..1F7D; GREEK
4975 0x1F7E, // 1F7E..1F7F; UNKNOWN
4976 0x1F80, // 1F80..1FB4; GREEK
4977 0x1FB5, // 1FB5 ; UNKNOWN
4978 0x1FB6, // 1FB6..1FC4; GREEK
4979 0x1FC5, // 1FC5 ; UNKNOWN
4980 0x1FC6, // 1FC6..1FD3; GREEK
4981 0x1FD4, // 1FD4..1FD5; UNKNOWN
4982 0x1FD6, // 1FD6..1FDB; GREEK
4983 0x1FDC, // 1FDC ; UNKNOWN
4984 0x1FDD, // 1FDD..1FEF; GREEK
4985 0x1FF0, // 1FF0..1FF1; UNKNOWN
4986 0x1FF2, // 1FF2..1FF4; GREEK
4987 0x1FF5, // 1FF5 ; UNKNOWN
4988 0x1FF6, // 1FF6..1FFE; GREEK
4989 0x1FFF, // 1FFF ; UNKNOWN
4990 0x2000, // 2000..200B; COMMON
4991 0x200C, // 200C..200D; INHERITED
4992 0x200E, // 200E..2064; COMMON
4993 0x2065, // 2065 ; UNKNOWN
4994 0x2066, // 2066..2070; COMMON
4995 0x2071, // 2071 ; LATIN
4996 0x2072, // 2072..2073; UNKNOWN
4997 0x2074, // 2074..207E; COMMON
4998 0x207F, // 207F ; LATIN
4999 0x2080, // 2080..208E; COMMON
5000 0x208F, // 208F ; UNKNOWN
5001 0x2090, // 2090..209C; LATIN
5002 0x209D, // 209D..209F; UNKNOWN
5003 0x20A0, // 20A0..20BE; COMMON
5004 0x20BF, // 20BF..20CF; UNKNOWN
5005 0x20D0, // 20D0..20F0; INHERITED
5006 0x20F1, // 20F1..20FF; UNKNOWN
5007 0x2100, // 2100..2125; COMMON
5008 0x2126, // 2126 ; GREEK
5009 0x2127, // 2127..2129; COMMON
5010 0x212A, // 212A..212B; LATIN
5011 0x212C, // 212C..2131; COMMON
5012 0x2132, // 2132 ; LATIN
5013 0x2133, // 2133..214D; COMMON
5014 0x214E, // 214E ; LATIN
5015 0x214F, // 214F..215F; COMMON
5016 0x2160, // 2160..2188; LATIN
5017 0x2189, // 2189..218B; COMMON
5018 0x218C, // 218C..218F; UNKNOWN
5019 0x2190, // 2190..23FA; COMMON
5020 0x23FB, // 23FB..23FF; UNKNOWN
5021 0x2400, // 2400..2426; COMMON
5022 0x2427, // 2427..243F; UNKNOWN
5023 0x2440, // 2440..244A; COMMON
5024 0x244B, // 244B..245F; UNKNOWN
5025 0x2460, // 2460..27FF; COMMON
5026 0x2800, // 2800..28FF; BRAILLE
5027 0x2900, // 2900..2B73; COMMON
5028 0x2B74, // 2B74..2B75; UNKNOWN
5029 0x2B76, // 2B76..2B95; COMMON
5030 0x2B96, // 2B96..2B97; UNKNOWN
5031 0x2B98, // 2B98..2BB9; COMMON
5032 0x2BBA, // 2BBA..2BBC; UNKNOWN
5033 0x2BBD, // 2BBD..2BC8; COMMON
5034 0x2BC9, // 2BC9 ; UNKNOWN
5035 0x2BCA, // 2BCA..2BD1; COMMON
5036 0x2BD2, // 2BD2..2BEB; UNKNOWN
5037 0x2BEC, // 2BEC..2BEF; COMMON
5038 0x2BF0, // 2BF0..2BFF; UNKNOWN
5039 0x2C00, // 2C00..2C2E; GLAGOLITIC
5040 0x2C2F, // 2C2F ; UNKNOWN
5041 0x2C30, // 2C30..2C5E; GLAGOLITIC
5042 0x2C5F, // 2C5F ; UNKNOWN
5043 0x2C60, // 2C60..2C7F; LATIN
5044 0x2C80, // 2C80..2CF3; COPTIC
5045 0x2CF4, // 2CF4..2CF8; UNKNOWN
5046 0x2CF9, // 2CF9..2CFF; COPTIC
5047 0x2D00, // 2D00..2D25; GEORGIAN
5048 0x2D26, // 2D26 ; UNKNOWN
5049 0x2D27, // 2D27 ; GEORGIAN
5050 0x2D28, // 2D28..2D2C; UNKNOWN
5051 0x2D2D, // 2D2D ; GEORGIAN
5052 0x2D2E, // 2D2E..2D2F; UNKNOWN
5053 0x2D30, // 2D30..2D67; TIFINAGH
5054 0x2D68, // 2D68..2D6E; UNKNOWN
5055 0x2D6F, // 2D6F..2D70; TIFINAGH
5056 0x2D71, // 2D71..2D7E; UNKNOWN
5057 0x2D7F, // 2D7F ; TIFINAGH
5058 0x2D80, // 2D80..2D96; ETHIOPIC
5059 0x2D97, // 2D97..2D9F; UNKNOWN
5060 0x2DA0, // 2DA0..2DA6; ETHIOPIC
5061 0x2DA7, // 2DA7 ; UNKNOWN
5062 0x2DA8, // 2DA8..2DAE; ETHIOPIC
5063 0x2DAF, // 2DAF ; UNKNOWN
5064 0x2DB0, // 2DB0..2DB6; ETHIOPIC
5065 0x2DB7, // 2DB7 ; UNKNOWN
5066 0x2DB8, // 2DB8..2DBE; ETHIOPIC
5067 0x2DBF, // 2DBF ; UNKNOWN
5068 0x2DC0, // 2DC0..2DC6; ETHIOPIC
5069 0x2DC7, // 2DC7 ; UNKNOWN
5070 0x2DC8, // 2DC8..2DCE; ETHIOPIC
5071 0x2DCF, // 2DCF ; UNKNOWN
5072 0x2DD0, // 2DD0..2DD6; ETHIOPIC
5073 0x2DD7, // 2DD7 ; UNKNOWN
5074 0x2DD8, // 2DD8..2DDE; ETHIOPIC
5075 0x2DDF, // 2DDF ; UNKNOWN
5076 0x2DE0, // 2DE0..2DFF; CYRILLIC
5077 0x2E00, // 2E00..2E42; COMMON
5078 0x2E43, // 2E43..2E7F; UNKNOWN
5079 0x2E80, // 2E80..2E99; HAN
5080 0x2E9A, // 2E9A ; UNKNOWN
5081 0x2E9B, // 2E9B..2EF3; HAN
5082 0x2EF4, // 2EF4..2EFF; UNKNOWN
5083 0x2F00, // 2F00..2FD5; HAN
5084 0x2FD6, // 2FD6..2FEF; UNKNOWN
5085 0x2FF0, // 2FF0..2FFB; COMMON
5086 0x2FFC, // 2FFC..2FFF; UNKNOWN
5087 0x3000, // 3000..3004; COMMON
5088 0x3005, // 3005 ; HAN
5089 0x3006, // 3006 ; COMMON
5090 0x3007, // 3007 ; HAN
5091 0x3008, // 3008..3020; COMMON
5092 0x3021, // 3021..3029; HAN
5093 0x302A, // 302A..302D; INHERITED
5094 0x302E, // 302E..302F; HANGUL
5095 0x3030, // 3030..3037; COMMON
5096 0x3038, // 3038..303B; HAN
5097 0x303C, // 303C..303F; COMMON
5098 0x3040, // 3040 ; UNKNOWN
5099 0x3041, // 3041..3096; HIRAGANA
5100 0x3097, // 3097..3098; UNKNOWN
5101 0x3099, // 3099..309A; INHERITED
5102 0x309B, // 309B..309C; COMMON
5103 0x309D, // 309D..309F; HIRAGANA
5104 0x30A0, // 30A0 ; COMMON
5105 0x30A1, // 30A1..30FA; KATAKANA
5106 0x30FB, // 30FB..30FC; COMMON
5107 0x30FD, // 30FD..30FF; KATAKANA
5108 0x3100, // 3100..3104; UNKNOWN
5109 0x3105, // 3105..312D; BOPOMOFO
5110 0x312E, // 312E..3130; UNKNOWN
5111 0x3131, // 3131..318E; HANGUL
5112 0x318F, // 318F ; UNKNOWN
5113 0x3190, // 3190..319F; COMMON
5114 0x31A0, // 31A0..31BA; BOPOMOFO
5115 0x31BB, // 31BB..31BF; UNKNOWN
5116 0x31C0, // 31C0..31E3; COMMON
5117 0x31E4, // 31E4..31EF; UNKNOWN
5118 0x31F0, // 31F0..31FF; KATAKANA
5119 0x3200, // 3200..321E; HANGUL
5120 0x321F, // 321F ; UNKNOWN
5121 0x3220, // 3220..325F; COMMON
5122 0x3260, // 3260..327E; HANGUL
5123 0x327F, // 327F..32CF; COMMON
5124 0x32D0, // 32D0..32FE; KATAKANA
5125 0x32FF, // 32FF ; UNKNOWN
5126 0x3300, // 3300..3357; KATAKANA
5127 0x3358, // 3358..33FF; COMMON
5128 0x3400, // 3400..4DB5; HAN
5129 0x4DB6, // 4DB6..4DBF; UNKNOWN
5130 0x4DC0, // 4DC0..4DFF; COMMON
5131 0x4E00, // 4E00..9FD5; HAN
5132 0x9FD6, // 9FD6..9FFF; UNKNOWN
5133 0xA000, // A000..A48C; YI
5134 0xA48D, // A48D..A48F; UNKNOWN
5135 0xA490, // A490..A4C6; YI
5136 0xA4C7, // A4C7..A4CF; UNKNOWN
5137 0xA4D0, // A4D0..A4FF; LISU
5138 0xA500, // A500..A62B; VAI
5139 0xA62C, // A62C..A63F; UNKNOWN
5140 0xA640, // A640..A69F; CYRILLIC
5141 0xA6A0, // A6A0..A6F7; BAMUM
5142 0xA6F8, // A6F8..A6FF; UNKNOWN
5143 0xA700, // A700..A721; COMMON
5144 0xA722, // A722..A787; LATIN
5145 0xA788, // A788..A78A; COMMON
5146 0xA78B, // A78B..A7AD; LATIN
5147 0xA7AE, // A7AE..A7AF; UNKNOWN
5148 0xA7B0, // A7B0..A7B7; LATIN
5149 0xA7B8, // A7B8..A7F6; UNKNOWN
5150 0xA7F7, // A7F7..A7FF; LATIN
5151 0xA800, // A800..A82B; SYLOTI_NAGRI
5152 0xA82C, // A82C..A82F; UNKNOWN
5153 0xA830, // A830..A839; COMMON
5154 0xA83A, // A83A..A83F; UNKNOWN
5155 0xA840, // A840..A877; PHAGS_PA
5156 0xA878, // A878..A87F; UNKNOWN
5157 0xA880, // A880..A8C4; SAURASHTRA
5158 0xA8C5, // A8C5..A8CD; UNKNOWN
5159 0xA8CE, // A8CE..A8D9; SAURASHTRA
5160 0xA8DA, // A8DA..A8DF; UNKNOWN
5161 0xA8E0, // A8E0..A8FD; DEVANAGARI
5162 0xA8FE, // A8FE..A8FF; UNKNOWN
5163 0xA900, // A900..A92D; KAYAH_LI
5164 0xA92E, // A92E ; COMMON
5165 0xA92F, // A92F ; KAYAH_LI
5166 0xA930, // A930..A953; REJANG
5167 0xA954, // A954..A95E; UNKNOWN
5168 0xA95F, // A95F ; REJANG
5169 0xA960, // A960..A97C; HANGUL
5170 0xA97D, // A97D..A97F; UNKNOWN
5171 0xA980, // A980..A9CD; JAVANESE
5172 0xA9CE, // A9CE ; UNKNOWN
5173 0xA9CF, // A9CF ; COMMON
5174 0xA9D0, // A9D0..A9D9; JAVANESE
5175 0xA9DA, // A9DA..A9DD; UNKNOWN
5176 0xA9DE, // A9DE..A9DF; JAVANESE
5177 0xA9E0, // A9E0..A9FE; MYANMAR
5178 0xA9FF, // A9FF ; UNKNOWN
5179 0xAA00, // AA00..AA36; CHAM
5180 0xAA37, // AA37..AA3F; UNKNOWN
5181 0xAA40, // AA40..AA4D; CHAM
5182 0xAA4E, // AA4E..AA4F; UNKNOWN
5183 0xAA50, // AA50..AA59; CHAM
5184 0xAA5A, // AA5A..AA5B; UNKNOWN
5185 0xAA5C, // AA5C..AA5F; CHAM
5186 0xAA60, // AA60..AA7F; MYANMAR
5187 0xAA80, // AA80..AAC2; TAI_VIET
5188 0xAAC3, // AAC3..AADA; UNKNOWN
5189 0xAADB, // AADB..AADF; TAI_VIET
5190 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
5191 0xAAF7, // AAF7..AB00; UNKNOWN
5192 0xAB01, // AB01..AB06; ETHIOPIC
5193 0xAB07, // AB07..AB08; UNKNOWN
5194 0xAB09, // AB09..AB0E; ETHIOPIC
5195 0xAB0F, // AB0F..AB10; UNKNOWN
5196 0xAB11, // AB11..AB16; ETHIOPIC
5197 0xAB17, // AB17..AB1F; UNKNOWN
5198 0xAB20, // AB20..AB26; ETHIOPIC
5199 0xAB27, // AB27 ; UNKNOWN
5200 0xAB28, // AB28..AB2E; ETHIOPIC
5201 0xAB2F, // AB2F ; UNKNOWN
5202 0xAB30, // AB30..AB5A; LATIN
5203 0xAB5B, // AB5B ; COMMON
5204 0xAB5C, // AB5C..AB64; LATIN
5205 0xAB65, // AB65 ; GREEK
5206 0xAB66, // AB66..AB6F; UNKNOWN
5207 0xAB70, // AB70..ABBF; CHEROKEE
5208 0xABC0, // ABC0..ABED; MEETEI_MAYEK
5209 0xABEE, // ABEE..ABEF; UNKNOWN
5210 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
5211 0xABFA, // ABFA..ABFF; UNKNOWN
5212 0xAC00, // AC00..D7A3; HANGUL
5213 0xD7A4, // D7A4..D7AF; UNKNOWN
5214 0xD7B0, // D7B0..D7C6; HANGUL
5215 0xD7C7, // D7C7..D7CA; UNKNOWN
5216 0xD7CB, // D7CB..D7FB; HANGUL
5217 0xD7FC, // D7FC..F8FF; UNKNOWN
5218 0xF900, // F900..FA6D; HAN
5219 0xFA6E, // FA6E..FA6F; UNKNOWN
5220 0xFA70, // FA70..FAD9; HAN
5221 0xFADA, // FADA..FAFF; UNKNOWN
5222 0xFB00, // FB00..FB06; LATIN
5223 0xFB07, // FB07..FB12; UNKNOWN
5224 0xFB13, // FB13..FB17; ARMENIAN
5225 0xFB18, // FB18..FB1C; UNKNOWN
5226 0xFB1D, // FB1D..FB36; HEBREW
5227 0xFB37, // FB37 ; UNKNOWN
5228 0xFB38, // FB38..FB3C; HEBREW
5229 0xFB3D, // FB3D ; UNKNOWN
5230 0xFB3E, // FB3E ; HEBREW
5231 0xFB3F, // FB3F ; UNKNOWN
5232 0xFB40, // FB40..FB41; HEBREW
5233 0xFB42, // FB42 ; UNKNOWN
5234 0xFB43, // FB43..FB44; HEBREW
5235 0xFB45, // FB45 ; UNKNOWN
5236 0xFB46, // FB46..FB4F; HEBREW
5237 0xFB50, // FB50..FBC1; ARABIC
5238 0xFBC2, // FBC2..FBD2; UNKNOWN
5239 0xFBD3, // FBD3..FD3D; ARABIC
5240 0xFD3E, // FD3E..FD3F; COMMON
5241 0xFD40, // FD40..FD4F; UNKNOWN
5242 0xFD50, // FD50..FD8F; ARABIC
5243 0xFD90, // FD90..FD91; UNKNOWN
5244 0xFD92, // FD92..FDC7; ARABIC
5245 0xFDC8, // FDC8..FDEF; UNKNOWN
5246 0xFDF0, // FDF0..FDFD; ARABIC
5247 0xFDFE, // FDFE..FDFF; UNKNOWN
5248 0xFE00, // FE00..FE0F; INHERITED
5249 0xFE10, // FE10..FE19; COMMON
5250 0xFE1A, // FE1A..FE1F; UNKNOWN
5251 0xFE20, // FE20..FE2D; INHERITED
5252 0xFE2E, // FE2E..FE2F; CYRILLIC
5253 0xFE30, // FE30..FE52; COMMON
5254 0xFE53, // FE53 ; UNKNOWN
5255 0xFE54, // FE54..FE66; COMMON
5256 0xFE67, // FE67 ; UNKNOWN
5257 0xFE68, // FE68..FE6B; COMMON
5258 0xFE6C, // FE6C..FE6F; UNKNOWN
5259 0xFE70, // FE70..FE74; ARABIC
5260 0xFE75, // FE75 ; UNKNOWN
5261 0xFE76, // FE76..FEFC; ARABIC
5262 0xFEFD, // FEFD..FEFE; UNKNOWN
5263 0xFEFF, // FEFF ; COMMON
5264 0xFF00, // FF00 ; UNKNOWN
5265 0xFF01, // FF01..FF20; COMMON
5266 0xFF21, // FF21..FF3A; LATIN
5267 0xFF3B, // FF3B..FF40; COMMON
5268 0xFF41, // FF41..FF5A; LATIN
5269 0xFF5B, // FF5B..FF65; COMMON
5270 0xFF66, // FF66..FF6F; KATAKANA
5271 0xFF70, // FF70 ; COMMON
5272 0xFF71, // FF71..FF9D; KATAKANA
5273 0xFF9E, // FF9E..FF9F; COMMON
5274 0xFFA0, // FFA0..FFBE; HANGUL
5275 0xFFBF, // FFBF..FFC1; UNKNOWN
5276 0xFFC2, // FFC2..FFC7; HANGUL
5277 0xFFC8, // FFC8..FFC9; UNKNOWN
5278 0xFFCA, // FFCA..FFCF; HANGUL
5279 0xFFD0, // FFD0..FFD1; UNKNOWN
5280 0xFFD2, // FFD2..FFD7; HANGUL
5281 0xFFD8, // FFD8..FFD9; UNKNOWN
5282 0xFFDA, // FFDA..FFDC; HANGUL
5283 0xFFDD, // FFDD..FFDF; UNKNOWN
5284 0xFFE0, // FFE0..FFE6; COMMON
5285 0xFFE7, // FFE7 ; UNKNOWN
5286 0xFFE8, // FFE8..FFEE; COMMON
5287 0xFFEF, // FFEF..FFF8; UNKNOWN
5288 0xFFF9, // FFF9..FFFD; COMMON
5289 0xFFFE, // FFFE..FFFF; UNKNOWN
5290 0x10000, // 10000..1000B; LINEAR_B
5291 0x1000C, // 1000C ; UNKNOWN
5292 0x1000D, // 1000D..10026; LINEAR_B
5293 0x10027, // 10027 ; UNKNOWN
5294 0x10028, // 10028..1003A; LINEAR_B
5295 0x1003B, // 1003B ; UNKNOWN
5296 0x1003C, // 1003C..1003D; LINEAR_B
5297 0x1003E, // 1003E ; UNKNOWN
5298 0x1003F, // 1003F..1004D; LINEAR_B
5299 0x1004E, // 1004E..1004F; UNKNOWN
5300 0x10050, // 10050..1005D; LINEAR_B
5301 0x1005E, // 1005E..1007F; UNKNOWN
5302 0x10080, // 10080..100FA; LINEAR_B
5303 0x100FB, // 100FB..100FF; UNKNOWN
5304 0x10100, // 10100..10102; COMMON
5305 0x10103, // 10103..10106; UNKNOWN
5306 0x10107, // 10107..10133; COMMON
5307 0x10134, // 10134..10136; UNKNOWN
5308 0x10137, // 10137..1013F; COMMON
5309 0x10140, // 10140..1018C; GREEK
5310 0x1018D, // 1018D..1018F; UNKNOWN
5311 0x10190, // 10190..1019B; COMMON
5312 0x1019C, // 1019C..1019F; UNKNOWN
5313 0x101A0, // 101A0 ; GREEK
5314 0x101A1, // 101A1..101CF; UNKNOWN
5315 0x101D0, // 101D0..101FC; COMMON
5316 0x101FD, // 101FD ; INHERITED
5317 0x101FE, // 101FE..1027F; UNKNOWN
5318 0x10280, // 10280..1029C; LYCIAN
5319 0x1029D, // 1029D..1029F; UNKNOWN
5320 0x102A0, // 102A0..102D0; CARIAN
5321 0x102D1, // 102D1..102DF; UNKNOWN
5322 0x102E0, // 102E0 ; INHERITED
5323 0x102E1, // 102E1..102FB; COMMON
5324 0x102FC, // 102FC..102FF; UNKNOWN
5325 0x10300, // 10300..10323; OLD_ITALIC
5326 0x10324, // 10324..1032F; UNKNOWN
5327 0x10330, // 10330..1034A; GOTHIC
5328 0x1034B, // 1034B..1034F; UNKNOWN
5329 0x10350, // 10350..1037A; OLD_PERMIC
5330 0x1037B, // 1037B..1037F; UNKNOWN
5331 0x10380, // 10380..1039D; UGARITIC
5332 0x1039E, // 1039E ; UNKNOWN
5333 0x1039F, // 1039F ; UGARITIC
5334 0x103A0, // 103A0..103C3; OLD_PERSIAN
5335 0x103C4, // 103C4..103C7; UNKNOWN
5336 0x103C8, // 103C8..103D5; OLD_PERSIAN
5337 0x103D6, // 103D6..103FF; UNKNOWN
5338 0x10400, // 10400..1044F; DESERET
5339 0x10450, // 10450..1047F; SHAVIAN
5340 0x10480, // 10480..1049D; OSMANYA
5341 0x1049E, // 1049E..1049F; UNKNOWN
5342 0x104A0, // 104A0..104A9; OSMANYA
5343 0x104AA, // 104AA..104FF; UNKNOWN
5344 0x10500, // 10500..10527; ELBASAN
5345 0x10528, // 10528..1052F; UNKNOWN
5346 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
5347 0x10564, // 10564..1056E; UNKNOWN
5348 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
5349 0x10570, // 10570..105FF; UNKNOWN
5350 0x10600, // 10600..10736; LINEAR_A
5351 0x10737, // 10737..1073F; UNKNOWN
5352 0x10740, // 10740..10755; LINEAR_A
5353 0x10756, // 10756..1075F; UNKNOWN
5354 0x10760, // 10760..10767; LINEAR_A
5355 0x10768, // 10768..107FF; UNKNOWN
5356 0x10800, // 10800..10805; CYPRIOT
5357 0x10806, // 10806..10807; UNKNOWN
5358 0x10808, // 10808 ; CYPRIOT
5359 0x10809, // 10809 ; UNKNOWN
5360 0x1080A, // 1080A..10835; CYPRIOT
5361 0x10836, // 10836 ; UNKNOWN
5362 0x10837, // 10837..10838; CYPRIOT
5363 0x10839, // 10839..1083B; UNKNOWN
5364 0x1083C, // 1083C ; CYPRIOT
5365 0x1083D, // 1083D..1083E; UNKNOWN
5366 0x1083F, // 1083F ; CYPRIOT
5367 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
5368 0x10856, // 10856 ; UNKNOWN
5369 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
5370 0x10860, // 10860..1087F; PALMYRENE
5371 0x10880, // 10880..1089E; NABATAEAN
5372 0x1089F, // 1089F..108A6; UNKNOWN
5373 0x108A7, // 108A7..108AF; NABATAEAN
5374 0x108B0, // 108B0..108DF; UNKNOWN
5375 0x108E0, // 108E0..108F2; HATRAN
5376 0x108F3, // 108F3 ; UNKNOWN
5377 0x108F4, // 108F4..108F5; HATRAN
5378 0x108F6, // 108F6..108FA; UNKNOWN
5379 0x108FB, // 108FB..108FF; HATRAN
5380 0x10900, // 10900..1091B; PHOENICIAN
5381 0x1091C, // 1091C..1091E; UNKNOWN
5382 0x1091F, // 1091F ; PHOENICIAN
5383 0x10920, // 10920..10939; LYDIAN
5384 0x1093A, // 1093A..1093E; UNKNOWN
5385 0x1093F, // 1093F ; LYDIAN
5386 0x10940, // 10940..1097F; UNKNOWN
5387 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
5388 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
5389 0x109B8, // 109B8..109BB; UNKNOWN
5390 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
5391 0x109D0, // 109D0..109D1; UNKNOWN
5392 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
5393 0x10A00, // 10A00..10A03; KHAROSHTHI
5394 0x10A04, // 10A04 ; UNKNOWN
5395 0x10A05, // 10A05..10A06; KHAROSHTHI
5396 0x10A07, // 10A07..10A0B; UNKNOWN
5397 0x10A0C, // 10A0C..10A13; KHAROSHTHI
5398 0x10A14, // 10A14 ; UNKNOWN
5399 0x10A15, // 10A15..10A17; KHAROSHTHI
5400 0x10A18, // 10A18 ; UNKNOWN
5401 0x10A19, // 10A19..10A33; KHAROSHTHI
5402 0x10A34, // 10A34..10A37; UNKNOWN
5403 0x10A38, // 10A38..10A3A; KHAROSHTHI
5404 0x10A3B, // 10A3B..10A3E; UNKNOWN
5405 0x10A3F, // 10A3F..10A47; KHAROSHTHI
5406 0x10A48, // 10A48..10A4F; UNKNOWN
5407 0x10A50, // 10A50..10A58; KHAROSHTHI
5408 0x10A59, // 10A59..10A5F; UNKNOWN
5409 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
5410 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
5411 0x10AA0, // 10AA0..10ABF; UNKNOWN
5412 0x10AC0, // 10AC0..10AE6; MANICHAEAN
5413 0x10AE7, // 10AE7..10AEA; UNKNOWN
5414 0x10AEB, // 10AEB..10AF6; MANICHAEAN
5415 0x10AF7, // 10AF7..10AFF; UNKNOWN
5416 0x10B00, // 10B00..10B35; AVESTAN
5417 0x10B36, // 10B36..10B38; UNKNOWN
5418 0x10B39, // 10B39..10B3F; AVESTAN
5419 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
5420 0x10B56, // 10B56..10B57; UNKNOWN
5421 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
5422 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
5423 0x10B73, // 10B73..10B77; UNKNOWN
5424 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
5425 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
5426 0x10B92, // 10B92..10B98; UNKNOWN
5427 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
5428 0x10B9D, // 10B9D..10BA8; UNKNOWN
5429 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
5430 0x10BB0, // 10BB0..10BFF; UNKNOWN
5431 0x10C00, // 10C00..10C48; OLD_TURKIC
5432 0x10C49, // 10C49..10C7F; UNKNOWN
5433 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
5434 0x10CB3, // 10CB3..10CBF; UNKNOWN
5435 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
5436 0x10CF3, // 10CF3..10CF9; UNKNOWN
5437 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
5438 0x10D00, // 10D00..10E5F; UNKNOWN
5439 0x10E60, // 10E60..10E7E; ARABIC
5440 0x10E7F, // 10E7F..10FFF; UNKNOWN
5441 0x11000, // 11000..1104D; BRAHMI
5442 0x1104E, // 1104E..11051; UNKNOWN
5443 0x11052, // 11052..1106F; BRAHMI
5444 0x11070, // 11070..1107E; UNKNOWN
5445 0x1107F, // 1107F ; BRAHMI
5446 0x11080, // 11080..110C1; KAITHI
5447 0x110C2, // 110C2..110CF; UNKNOWN
5448 0x110D0, // 110D0..110E8; SORA_SOMPENG
5449 0x110E9, // 110E9..110EF; UNKNOWN
5450 0x110F0, // 110F0..110F9; SORA_SOMPENG
5451 0x110FA, // 110FA..110FF; UNKNOWN
5452 0x11100, // 11100..11134; CHAKMA
5453 0x11135, // 11135 ; UNKNOWN
5454 0x11136, // 11136..11143; CHAKMA
5455 0x11144, // 11144..1114F; UNKNOWN
5456 0x11150, // 11150..11176; MAHAJANI
5457 0x11177, // 11177..1117F; UNKNOWN
5458 0x11180, // 11180..111CD; SHARADA
5459 0x111CE, // 111CE..111CF; UNKNOWN
5460 0x111D0, // 111D0..111DF; SHARADA
5461 0x111E0, // 111E0 ; UNKNOWN
5462 0x111E1, // 111E1..111F4; SINHALA
5463 0x111F5, // 111F5..111FF; UNKNOWN
5464 0x11200, // 11200..11211; KHOJKI
5465 0x11212, // 11212 ; UNKNOWN
5466 0x11213, // 11213..1123D; KHOJKI
5467 0x1123E, // 1123E..1127F; UNKNOWN
5468 0x11280, // 11280..11286; MULTANI
5469 0x11287, // 11287 ; UNKNOWN
5470 0x11288, // 11288 ; MULTANI
5471 0x11289, // 11289 ; UNKNOWN
5472 0x1128A, // 1128A..1128D; MULTANI
5473 0x1128E, // 1128E ; UNKNOWN
5474 0x1128F, // 1128F..1129D; MULTANI
5475 0x1129E, // 1129E ; UNKNOWN
5476 0x1129F, // 1129F..112A9; MULTANI
5477 0x112AA, // 112AA..112AF; UNKNOWN
5478 0x112B0, // 112B0..112EA; KHUDAWADI
5479 0x112EB, // 112EB..112EF; UNKNOWN
5480 0x112F0, // 112F0..112F9; KHUDAWADI
5481 0x112FA, // 112FA..112FF; UNKNOWN
5482 0x11300, // 11300..11303; GRANTHA
5483 0x11304, // 11304 ; UNKNOWN
5484 0x11305, // 11305..1130C; GRANTHA
5485 0x1130D, // 1130D..1130E; UNKNOWN
5486 0x1130F, // 1130F..11310; GRANTHA
5487 0x11311, // 11311..11312; UNKNOWN
5488 0x11313, // 11313..11328; GRANTHA
5489 0x11329, // 11329 ; UNKNOWN
5490 0x1132A, // 1132A..11330; GRANTHA
5491 0x11331, // 11331 ; UNKNOWN
5492 0x11332, // 11332..11333; GRANTHA
5493 0x11334, // 11334 ; UNKNOWN
5494 0x11335, // 11335..11339; GRANTHA
5495 0x1133A, // 1133A..1133B; UNKNOWN
5496 0x1133C, // 1133C..11344; GRANTHA
5497 0x11345, // 11345..11346; UNKNOWN
5498 0x11347, // 11347..11348; GRANTHA
5499 0x11349, // 11349..1134A; UNKNOWN
5500 0x1134B, // 1134B..1134D; GRANTHA
5501 0x1134E, // 1134E..1134F; UNKNOWN
5502 0x11350, // 11350 ; GRANTHA
5503 0x11351, // 11351..11356; UNKNOWN
5504 0x11357, // 11357 ; GRANTHA
5505 0x11358, // 11358..1135C; UNKNOWN
5506 0x1135D, // 1135D..11363; GRANTHA
5507 0x11364, // 11364..11365; UNKNOWN
5508 0x11366, // 11366..1136C; GRANTHA
5509 0x1136D, // 1136D..1136F; UNKNOWN
5510 0x11370, // 11370..11374; GRANTHA
5511 0x11375, // 11375..1147F; UNKNOWN
5512 0x11480, // 11480..114C7; TIRHUTA
5513 0x114C8, // 114C8..114CF; UNKNOWN
5514 0x114D0, // 114D0..114D9; TIRHUTA
5515 0x114DA, // 114DA..1157F; UNKNOWN
5516 0x11580, // 11580..115B5; SIDDHAM
5517 0x115B6, // 115B6..115B7; UNKNOWN
5518 0x115B8, // 115B8..115DD; SIDDHAM
5519 0x115DE, // 115DE..115FF; UNKNOWN
5520 0x11600, // 11600..11644; MODI
5521 0x11645, // 11645..1164F; UNKNOWN
5522 0x11650, // 11650..11659; MODI
5523 0x1165A, // 1165A..1167F; UNKNOWN
5524 0x11680, // 11680..116B7; TAKRI
5525 0x116B8, // 116B8..116BF; UNKNOWN
5526 0x116C0, // 116C0..116C9; TAKRI
5527 0x116CA, // 116CA..116FF; UNKNOWN
5528 0x11700, // 11700..11719; AHOM
5529 0x1171A, // 1171A..1171C; UNKNOWN
5530 0x1171D, // 1171D..1172B; AHOM
5531 0x1172C, // 1172C..1172F; UNKNOWN
5532 0x11730, // 11730..1173F; AHOM
5533 0x11740, // 11740..1189F; UNKNOWN
5534 0x118A0, // 118A0..118F2; WARANG_CITI
5535 0x118F3, // 118F3..118FE; UNKNOWN
5536 0x118FF, // 118FF ; WARANG_CITI
5537 0x11900, // 11900..11ABF; UNKNOWN
5538 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
5539 0x11AF9, // 11AF9..11FFF; UNKNOWN
5540 0x12000, // 12000..12399; CUNEIFORM
5541 0x1239A, // 1239A..123FF; UNKNOWN
5542 0x12400, // 12400..1246E; CUNEIFORM
5543 0x1246F, // 1246F ; UNKNOWN
5544 0x12470, // 12470..12474; CUNEIFORM
5545 0x12475, // 12475..1247F; UNKNOWN
5546 0x12480, // 12480..12543; CUNEIFORM
5547 0x12544, // 12544..12FFF; UNKNOWN
5548 0x13000, // 13000..1342E; EGYPTIAN_HIEROGLYPHS
5549 0x1342F, // 1342F..143FF; UNKNOWN
5550 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
5551 0x14647, // 14647..167FF; UNKNOWN
5552 0x16800, // 16800..16A38; BAMUM
5553 0x16A39, // 16A39..16A3F; UNKNOWN
5554 0x16A40, // 16A40..16A5E; MRO
5555 0x16A5F, // 16A5F ; UNKNOWN
5556 0x16A60, // 16A60..16A69; MRO
5557 0x16A6A, // 16A6A..16A6D; UNKNOWN
5558 0x16A6E, // 16A6E..16A6F; MRO
5559 0x16A70, // 16A70..16ACF; UNKNOWN
5560 0x16AD0, // 16AD0..16AED; BASSA_VAH
5561 0x16AEE, // 16AEE..16AEF; UNKNOWN
5562 0x16AF0, // 16AF0..16AF5; BASSA_VAH
5563 0x16AF6, // 16AF6..16AFF; UNKNOWN
5564 0x16B00, // 16B00..16B45; PAHAWH_HMONG
5565 0x16B46, // 16B46..16B4F; UNKNOWN
5566 0x16B50, // 16B50..16B59; PAHAWH_HMONG
5567 0x16B5A, // 16B5A ; UNKNOWN
5568 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
5569 0x16B62, // 16B62 ; UNKNOWN
5570 0x16B63, // 16B63..16B77; PAHAWH_HMONG
5571 0x16B78, // 16B78..16B7C; UNKNOWN
5572 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
5573 0x16B90, // 16B90..16EFF; UNKNOWN
5574 0x16F00, // 16F00..16F44; MIAO
5575 0x16F45, // 16F45..16F4F; UNKNOWN
5576 0x16F50, // 16F50..16F7E; MIAO
5577 0x16F7F, // 16F7F..16F8E; UNKNOWN
5578 0x16F8F, // 16F8F..16F9F; MIAO
5579 0x16FA0, // 16FA0..1AFFF; UNKNOWN
5580 0x1B000, // 1B000 ; KATAKANA
5581 0x1B001, // 1B001 ; HIRAGANA
5582 0x1B002, // 1B002..1BBFF; UNKNOWN
5583 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
5584 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
5585 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
5586 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
5587 0x1BC80, // 1BC80..1BC88; DUPLOYAN
5588 0x1BC89, // 1BC89..1BC8F; UNKNOWN
5589 0x1BC90, // 1BC90..1BC99; DUPLOYAN
5590 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
5591 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
5592 0x1BCA0, // 1BCA0..1BCA3; COMMON
5593 0x1BCA4, // 1BCA4..1CFFF; UNKNOWN
5594 0x1D000, // 1D000..1D0F5; COMMON
5595 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
5596 0x1D100, // 1D100..1D126; COMMON
5597 0x1D127, // 1D127..1D128; UNKNOWN
5598 0x1D129, // 1D129..1D166; COMMON
5599 0x1D167, // 1D167..1D169; INHERITED
5600 0x1D16A, // 1D16A..1D17A; COMMON
5601 0x1D17B, // 1D17B..1D182; INHERITED
5602 0x1D183, // 1D183..1D184; COMMON
5603 0x1D185, // 1D185..1D18B; INHERITED
5604 0x1D18C, // 1D18C..1D1A9; COMMON
5605 0x1D1AA, // 1D1AA..1D1AD; INHERITED
5606 0x1D1AE, // 1D1AE..1D1E8; COMMON
5607 0x1D1E9, // 1D1E9..1D1FF; UNKNOWN
5608 0x1D200, // 1D200..1D245; GREEK
5609 0x1D246, // 1D246..1D2FF; UNKNOWN
5610 0x1D300, // 1D300..1D356; COMMON
5611 0x1D357, // 1D357..1D35F; UNKNOWN
5612 0x1D360, // 1D360..1D371; COMMON
5613 0x1D372, // 1D372..1D3FF; UNKNOWN
5614 0x1D400, // 1D400..1D454; COMMON
5615 0x1D455, // 1D455 ; UNKNOWN
5616 0x1D456, // 1D456..1D49C; COMMON
5617 0x1D49D, // 1D49D ; UNKNOWN
5618 0x1D49E, // 1D49E..1D49F; COMMON
5619 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
5620 0x1D4A2, // 1D4A2 ; COMMON
5621 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
5622 0x1D4A5, // 1D4A5..1D4A6; COMMON
5623 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
5624 0x1D4A9, // 1D4A9..1D4AC; COMMON
5625 0x1D4AD, // 1D4AD ; UNKNOWN
5626 0x1D4AE, // 1D4AE..1D4B9; COMMON
5627 0x1D4BA, // 1D4BA ; UNKNOWN
5628 0x1D4BB, // 1D4BB ; COMMON
5629 0x1D4BC, // 1D4BC ; UNKNOWN
5630 0x1D4BD, // 1D4BD..1D4C3; COMMON
5631 0x1D4C4, // 1D4C4 ; UNKNOWN
5632 0x1D4C5, // 1D4C5..1D505; COMMON
5633 0x1D506, // 1D506 ; UNKNOWN
5634 0x1D507, // 1D507..1D50A; COMMON
5635 0x1D50B, // 1D50B..1D50C; UNKNOWN
5636 0x1D50D, // 1D50D..1D514; COMMON
5637 0x1D515, // 1D515 ; UNKNOWN
5638 0x1D516, // 1D516..1D51C; COMMON
5639 0x1D51D, // 1D51D ; UNKNOWN
5640 0x1D51E, // 1D51E..1D539; COMMON
5641 0x1D53A, // 1D53A ; UNKNOWN
5642 0x1D53B, // 1D53B..1D53E; COMMON
5643 0x1D53F, // 1D53F ; UNKNOWN
5644 0x1D540, // 1D540..1D544; COMMON
5645 0x1D545, // 1D545 ; UNKNOWN
5646 0x1D546, // 1D546 ; COMMON
5647 0x1D547, // 1D547..1D549; UNKNOWN
5648 0x1D54A, // 1D54A..1D550; COMMON
5649 0x1D551, // 1D551 ; UNKNOWN
5650 0x1D552, // 1D552..1D6A5; COMMON
5651 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
5652 0x1D6A8, // 1D6A8..1D7CB; COMMON
5653 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
5654 0x1D7CE, // 1D7CE..1D7FF; COMMON
5655 0x1D800, // 1D800..1DA8B; SIGNWRITING
5656 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
5657 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
5658 0x1DAA0, // 1DAA0 ; UNKNOWN
5659 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
5660 0x1DAB0, // 1DAB0..1E7FF; UNKNOWN
5661 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
5662 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
5663 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
5664 0x1E8D7, // 1E8D7..1EDFF; UNKNOWN
5665 0x1EE00, // 1EE00..1EE03; ARABIC
5666 0x1EE04, // 1EE04 ; UNKNOWN
5667 0x1EE05, // 1EE05..1EE1F; ARABIC
5668 0x1EE20, // 1EE20 ; UNKNOWN
5669 0x1EE21, // 1EE21..1EE22; ARABIC
5670 0x1EE23, // 1EE23 ; UNKNOWN
5671 0x1EE24, // 1EE24 ; ARABIC
5672 0x1EE25, // 1EE25..1EE26; UNKNOWN
5673 0x1EE27, // 1EE27 ; ARABIC
5674 0x1EE28, // 1EE28 ; UNKNOWN
5675 0x1EE29, // 1EE29..1EE32; ARABIC
5676 0x1EE33, // 1EE33 ; UNKNOWN
5677 0x1EE34, // 1EE34..1EE37; ARABIC
5678 0x1EE38, // 1EE38 ; UNKNOWN
5679 0x1EE39, // 1EE39 ; ARABIC
5680 0x1EE3A, // 1EE3A ; UNKNOWN
5681 0x1EE3B, // 1EE3B ; ARABIC
5682 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
5683 0x1EE42, // 1EE42 ; ARABIC
5684 0x1EE43, // 1EE43..1EE46; UNKNOWN
5685 0x1EE47, // 1EE47 ; ARABIC
5686 0x1EE48, // 1EE48 ; UNKNOWN
5687 0x1EE49, // 1EE49 ; ARABIC
5688 0x1EE4A, // 1EE4A ; UNKNOWN
5689 0x1EE4B, // 1EE4B ; ARABIC
5690 0x1EE4C, // 1EE4C ; UNKNOWN
5691 0x1EE4D, // 1EE4D..1EE4F; ARABIC
5692 0x1EE50, // 1EE50 ; UNKNOWN
5693 0x1EE51, // 1EE51..1EE52; ARABIC
5694 0x1EE53, // 1EE53 ; UNKNOWN
5695 0x1EE54, // 1EE54 ; ARABIC
5696 0x1EE55, // 1EE55..1EE56; UNKNOWN
5697 0x1EE57, // 1EE57 ; ARABIC
5698 0x1EE58, // 1EE58 ; UNKNOWN
5699 0x1EE59, // 1EE59 ; ARABIC
5700 0x1EE5A, // 1EE5A ; UNKNOWN
5701 0x1EE5B, // 1EE5B ; ARABIC
5702 0x1EE5C, // 1EE5C ; UNKNOWN
5703 0x1EE5D, // 1EE5D ; ARABIC
5704 0x1EE5E, // 1EE5E ; UNKNOWN
5705 0x1EE5F, // 1EE5F ; ARABIC
5706 0x1EE60, // 1EE60 ; UNKNOWN
5707 0x1EE61, // 1EE61..1EE62; ARABIC
5708 0x1EE63, // 1EE63 ; UNKNOWN
5709 0x1EE64, // 1EE64 ; ARABIC
5710 0x1EE65, // 1EE65..1EE66; UNKNOWN
5711 0x1EE67, // 1EE67..1EE6A; ARABIC
5712 0x1EE6B, // 1EE6B ; UNKNOWN
5713 0x1EE6C, // 1EE6C..1EE72; ARABIC
5714 0x1EE73, // 1EE73 ; UNKNOWN
5715 0x1EE74, // 1EE74..1EE77; ARABIC
5716 0x1EE78, // 1EE78 ; UNKNOWN
5717 0x1EE79, // 1EE79..1EE7C; ARABIC
5718 0x1EE7D, // 1EE7D ; UNKNOWN
5719 0x1EE7E, // 1EE7E ; ARABIC
5720 0x1EE7F, // 1EE7F ; UNKNOWN
5721 0x1EE80, // 1EE80..1EE89; ARABIC
5722 0x1EE8A, // 1EE8A ; UNKNOWN
5723 0x1EE8B, // 1EE8B..1EE9B; ARABIC
5724 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
5725 0x1EEA1, // 1EEA1..1EEA3; ARABIC
5726 0x1EEA4, // 1EEA4 ; UNKNOWN
5727 0x1EEA5, // 1EEA5..1EEA9; ARABIC
5728 0x1EEAA, // 1EEAA ; UNKNOWN
5729 0x1EEAB, // 1EEAB..1EEBB; ARABIC
5730 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
5731 0x1EEF0, // 1EEF0..1EEF1; ARABIC
5732 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
5733 0x1F000, // 1F000..1F02B; COMMON
5734 0x1F02C, // 1F02C..1F02F; UNKNOWN
5735 0x1F030, // 1F030..1F093; COMMON
5736 0x1F094, // 1F094..1F09F; UNKNOWN
5737 0x1F0A0, // 1F0A0..1F0AE; COMMON
5738 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
5739 0x1F0B1, // 1F0B1..1F0BF; COMMON
5740 0x1F0C0, // 1F0C0 ; UNKNOWN
5741 0x1F0C1, // 1F0C1..1F0CF; COMMON
5742 0x1F0D0, // 1F0D0 ; UNKNOWN
5743 0x1F0D1, // 1F0D1..1F0F5; COMMON
5744 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
5745 0x1F100, // 1F100..1F10C; COMMON
5746 0x1F10D, // 1F10D..1F10F; UNKNOWN
5747 0x1F110, // 1F110..1F12E; COMMON
5748 0x1F12F, // 1F12F ; UNKNOWN
5749 0x1F130, // 1F130..1F16B; COMMON
5750 0x1F16C, // 1F16C..1F16F; UNKNOWN
5751 0x1F170, // 1F170..1F19A; COMMON
5752 0x1F19B, // 1F19B..1F1E5; UNKNOWN
5753 0x1F1E6, // 1F1E6..1F1FF; COMMON
5754 0x1F200, // 1F200 ; HIRAGANA
5755 0x1F201, // 1F201..1F202; COMMON
5756 0x1F203, // 1F203..1F20F; UNKNOWN
5757 0x1F210, // 1F210..1F23A; COMMON
5758 0x1F23B, // 1F23B..1F23F; UNKNOWN
5759 0x1F240, // 1F240..1F248; COMMON
5760 0x1F249, // 1F249..1F24F; UNKNOWN
5761 0x1F250, // 1F250..1F251; COMMON
5762 0x1F252, // 1F252..1F2FF; UNKNOWN
5763 0x1F300, // 1F300..1F579; COMMON
5764 0x1F57A, // 1F57A ; UNKNOWN
5765 0x1F57B, // 1F57B..1F5A3; COMMON
5766 0x1F5A4, // 1F5A4 ; UNKNOWN
5767 0x1F5A5, // 1F5A5..1F6D0; COMMON
5768 0x1F6D1, // 1F6D1..1F6DF; UNKNOWN
5769 0x1F6E0, // 1F6E0..1F6EC; COMMON
5770 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
5771 0x1F6F0, // 1F6F0..1F6F3; COMMON
5772 0x1F6F4, // 1F6F4..1F6FF; UNKNOWN
5773 0x1F700, // 1F700..1F773; COMMON
5774 0x1F774, // 1F774..1F77F; UNKNOWN
5775 0x1F780, // 1F780..1F7D4; COMMON
5776 0x1F7D5, // 1F7D5..1F7FF; UNKNOWN
5777 0x1F800, // 1F800..1F80B; COMMON
5778 0x1F80C, // 1F80C..1F80F; UNKNOWN
5779 0x1F810, // 1F810..1F847; COMMON
5780 0x1F848, // 1F848..1F84F; UNKNOWN
5781 0x1F850, // 1F850..1F859; COMMON
5782 0x1F85A, // 1F85A..1F85F; UNKNOWN
5783 0x1F860, // 1F860..1F887; COMMON
5784 0x1F888, // 1F888..1F88F; UNKNOWN
5785 0x1F890, // 1F890..1F8AD; COMMON
5786 0x1F8AE, // 1F8AE..1F90F; UNKNOWN
5787 0x1F910, // 1F910..1F918; COMMON
5788 0x1F919, // 1F919..1F97F; UNKNOWN
5789 0x1F980, // 1F980..1F984; COMMON
5790 0x1F985, // 1F985..1F9BF; UNKNOWN
5791 0x1F9C0, // 1F9C0 ; COMMON
5792 0x1F9C1, // 1F9C1..1FFFF; UNKNOWN
5793 0x20000, // 20000..2A6D6; HAN
5794 0x2A6D7, // 2A6D7..2A6FF; UNKNOWN
5795 0x2A700, // 2A700..2B734; HAN
5796 0x2B735, // 2B735..2B73F; UNKNOWN
5797 0x2B740, // 2B740..2B81D; HAN
5798 0x2B81E, // 2B81E..2B81F; UNKNOWN
5799 0x2B820, // 2B820..2CEA1; HAN
5800 0x2CEA2, // 2CEA2..2F7FF; UNKNOWN
5801 0x2F800, // 2F800..2FA1D; HAN
5802 0x2FA1E, // 2FA1E..E0000; UNKNOWN
5803 0xE0001, // E0001 ; COMMON
5804 0xE0002, // E0002..E001F; UNKNOWN
5805 0xE0020, // E0020..E007F; COMMON
5806 0xE0080, // E0080..E00FF; UNKNOWN
5807 0xE0100, // E0100..E01EF; INHERITED
5808 0xE01F0 // E01F0..10FFFF; UNKNOWN
5809 };
5810
5811 private static final UnicodeScript[] scripts = {
5812 COMMON, // 0000..0040
5813 LATIN, // 0041..005A
5814 COMMON, // 005B..0060
5815 LATIN, // 0061..007A
5816 COMMON, // 007B..00A9
5817 LATIN, // 00AA
5818 COMMON, // 00AB..00B9
5819 LATIN, // 00BA
5820 COMMON, // 00BB..00BF
5821 LATIN, // 00C0..00D6
5822 COMMON, // 00D7
5823 LATIN, // 00D8..00F6
5824 COMMON, // 00F7
5825 LATIN, // 00F8..02B8
5826 COMMON, // 02B9..02DF
5827 LATIN, // 02E0..02E4
5828 COMMON, // 02E5..02E9
5829 BOPOMOFO, // 02EA..02EB
5830 COMMON, // 02EC..02FF
5831 INHERITED, // 0300..036F
5832 GREEK, // 0370..0373
5833 COMMON, // 0374
5834 GREEK, // 0375..0377
5835 UNKNOWN, // 0378..0379
5836 GREEK, // 037A..037D
5837 COMMON, // 037E
5838 GREEK, // 037F
5839 UNKNOWN, // 0380..0383
5840 GREEK, // 0384
5841 COMMON, // 0385
5842 GREEK, // 0386
5843 COMMON, // 0387
5844 GREEK, // 0388..038A
5845 UNKNOWN, // 038B
5846 GREEK, // 038C
5847 UNKNOWN, // 038D
5848 GREEK, // 038E..03A1
5849 UNKNOWN, // 03A2
5850 GREEK, // 03A3..03E1
5851 COPTIC, // 03E2..03EF
5852 GREEK, // 03F0..03FF
5853 CYRILLIC, // 0400..0484
5854 INHERITED, // 0485..0486
5855 CYRILLIC, // 0487..052F
5856 UNKNOWN, // 0530
5857 ARMENIAN, // 0531..0556
5858 UNKNOWN, // 0557..0558
5859 ARMENIAN, // 0559..055F
5860 UNKNOWN, // 0560
5861 ARMENIAN, // 0561..0587
5862 UNKNOWN, // 0588
5863 COMMON, // 0589
5864 ARMENIAN, // 058A
5865 UNKNOWN, // 058B..058C
5866 ARMENIAN, // 058D..058F
5867 UNKNOWN, // 0590
5868 HEBREW, // 0591..05C7
5869 UNKNOWN, // 05C8..05CF
5870 HEBREW, // 05D0..05EA
5871 UNKNOWN, // 05EB..05EF
5872 HEBREW, // 05F0..05F4
5873 UNKNOWN, // 05F5..05FF
5874 ARABIC, // 0600..0604
5875 COMMON, // 0605
5876 ARABIC, // 0606..060B
5877 COMMON, // 060C
5878 ARABIC, // 060D..061A
5879 COMMON, // 061B..061C
5880 UNKNOWN, // 061D
5881 ARABIC, // 061E
5882 COMMON, // 061F
5883 ARABIC, // 0620..063F
5884 COMMON, // 0640
5885 ARABIC, // 0641..064A
5886 INHERITED, // 064B..0655
5887 ARABIC, // 0656..066F
5888 INHERITED, // 0670
5889 ARABIC, // 0671..06DC
5890 COMMON, // 06DD
5891 ARABIC, // 06DE..06FF
5892 SYRIAC, // 0700..070D
5893 UNKNOWN, // 070E
5894 SYRIAC, // 070F..074A
5895 UNKNOWN, // 074B..074C
5896 SYRIAC, // 074D..074F
5897 ARABIC, // 0750..077F
5898 THAANA, // 0780..07B1
5899 UNKNOWN, // 07B2..07BF
5900 NKO, // 07C0..07FA
5901 UNKNOWN, // 07FB..07FF
5902 SAMARITAN, // 0800..082D
5903 UNKNOWN, // 082E..082F
5904 SAMARITAN, // 0830..083E
5905 UNKNOWN, // 083F
5906 MANDAIC, // 0840..085B
5907 UNKNOWN, // 085C..085D
5908 MANDAIC, // 085E
5909 UNKNOWN, // 085F..089F
5910 ARABIC, // 08A0..08B4
5911 UNKNOWN, // 08B5..08E2
5912 ARABIC, // 08E3..08FF
5913 DEVANAGARI, // 0900..0950
5914 INHERITED, // 0951..0952
5915 DEVANAGARI, // 0953..0963
5916 COMMON, // 0964..0965
5917 DEVANAGARI, // 0966..097F
5918 BENGALI, // 0980..0983
5919 UNKNOWN, // 0984
5920 BENGALI, // 0985..098C
5921 UNKNOWN, // 098D..098E
5922 BENGALI, // 098F..0990
5923 UNKNOWN, // 0991..0992
5924 BENGALI, // 0993..09A8
5925 UNKNOWN, // 09A9
5926 BENGALI, // 09AA..09B0
5927 UNKNOWN, // 09B1
5928 BENGALI, // 09B2
5929 UNKNOWN, // 09B3..09B5
5930 BENGALI, // 09B6..09B9
5931 UNKNOWN, // 09BA..09BB
5932 BENGALI, // 09BC..09C4
5933 UNKNOWN, // 09C5..09C6
5934 BENGALI, // 09C7..09C8
5935 UNKNOWN, // 09C9..09CA
5936 BENGALI, // 09CB..09CE
5937 UNKNOWN, // 09CF..09D6
5938 BENGALI, // 09D7
5939 UNKNOWN, // 09D8..09DB
5940 BENGALI, // 09DC..09DD
5941 UNKNOWN, // 09DE
5942 BENGALI, // 09DF..09E3
5943 UNKNOWN, // 09E4..09E5
5944 BENGALI, // 09E6..09FB
5945 UNKNOWN, // 09FC..0A00
5946 GURMUKHI, // 0A01..0A03
5947 UNKNOWN, // 0A04
5948 GURMUKHI, // 0A05..0A0A
5949 UNKNOWN, // 0A0B..0A0E
5950 GURMUKHI, // 0A0F..0A10
5951 UNKNOWN, // 0A11..0A12
5952 GURMUKHI, // 0A13..0A28
5953 UNKNOWN, // 0A29
5954 GURMUKHI, // 0A2A..0A30
5955 UNKNOWN, // 0A31
5956 GURMUKHI, // 0A32..0A33
5957 UNKNOWN, // 0A34
5958 GURMUKHI, // 0A35..0A36
5959 UNKNOWN, // 0A37
5960 GURMUKHI, // 0A38..0A39
5961 UNKNOWN, // 0A3A..0A3B
5962 GURMUKHI, // 0A3C
5963 UNKNOWN, // 0A3D
5964 GURMUKHI, // 0A3E..0A42
5965 UNKNOWN, // 0A43..0A46
5966 GURMUKHI, // 0A47..0A48
5967 UNKNOWN, // 0A49..0A4A
5968 GURMUKHI, // 0A4B..0A4D
5969 UNKNOWN, // 0A4E..0A50
5970 GURMUKHI, // 0A51
5971 UNKNOWN, // 0A52..0A58
5972 GURMUKHI, // 0A59..0A5C
5973 UNKNOWN, // 0A5D
5974 GURMUKHI, // 0A5E
5975 UNKNOWN, // 0A5F..0A65
5976 GURMUKHI, // 0A66..0A75
5977 UNKNOWN, // 0A76..0A80
5978 GUJARATI, // 0A81..0A83
5979 UNKNOWN, // 0A84
5980 GUJARATI, // 0A85..0A8D
5981 UNKNOWN, // 0A8E
5982 GUJARATI, // 0A8F..0A91
5983 UNKNOWN, // 0A92
5984 GUJARATI, // 0A93..0AA8
5985 UNKNOWN, // 0AA9
5986 GUJARATI, // 0AAA..0AB0
5987 UNKNOWN, // 0AB1
5988 GUJARATI, // 0AB2..0AB3
5989 UNKNOWN, // 0AB4
5990 GUJARATI, // 0AB5..0AB9
5991 UNKNOWN, // 0ABA..0ABB
5992 GUJARATI, // 0ABC..0AC5
5993 UNKNOWN, // 0AC6
5994 GUJARATI, // 0AC7..0AC9
5995 UNKNOWN, // 0ACA
5996 GUJARATI, // 0ACB..0ACD
5997 UNKNOWN, // 0ACE..0ACF
5998 GUJARATI, // 0AD0
5999 UNKNOWN, // 0AD1..0ADF
6000 GUJARATI, // 0AE0..0AE3
6001 UNKNOWN, // 0AE4..0AE5
6002 GUJARATI, // 0AE6..0AF1
6003 UNKNOWN, // 0AF2..0AF8
6004 GUJARATI, // 0AF9
6005 UNKNOWN, // 0AFA..0B00
6006 ORIYA, // 0B01..0B03
6007 UNKNOWN, // 0B04
6008 ORIYA, // 0B05..0B0C
6009 UNKNOWN, // 0B0D..0B0E
6010 ORIYA, // 0B0F..0B10
6011 UNKNOWN, // 0B11..0B12
6012 ORIYA, // 0B13..0B28
6013 UNKNOWN, // 0B29
6014 ORIYA, // 0B2A..0B30
6015 UNKNOWN, // 0B31
6016 ORIYA, // 0B32..0B33
6017 UNKNOWN, // 0B34
6018 ORIYA, // 0B35..0B39
6019 UNKNOWN, // 0B3A..0B3B
6020 ORIYA, // 0B3C..0B44
6021 UNKNOWN, // 0B45..0B46
6022 ORIYA, // 0B47..0B48
6023 UNKNOWN, // 0B49..0B4A
6024 ORIYA, // 0B4B..0B4D
6025 UNKNOWN, // 0B4E..0B55
6026 ORIYA, // 0B56..0B57
6027 UNKNOWN, // 0B58..0B5B
6028 ORIYA, // 0B5C..0B5D
6029 UNKNOWN, // 0B5E
6030 ORIYA, // 0B5F..0B63
6031 UNKNOWN, // 0B64..0B65
6032 ORIYA, // 0B66..0B77
6033 UNKNOWN, // 0B78..0B81
6034 TAMIL, // 0B82..0B83
6035 UNKNOWN, // 0B84
6036 TAMIL, // 0B85..0B8A
6037 UNKNOWN, // 0B8B..0B8D
6038 TAMIL, // 0B8E..0B90
6039 UNKNOWN, // 0B91
6040 TAMIL, // 0B92..0B95
6041 UNKNOWN, // 0B96..0B98
6042 TAMIL, // 0B99..0B9A
6043 UNKNOWN, // 0B9B
6044 TAMIL, // 0B9C
6045 UNKNOWN, // 0B9D
6046 TAMIL, // 0B9E..0B9F
6047 UNKNOWN, // 0BA0..0BA2
6048 TAMIL, // 0BA3..0BA4
6049 UNKNOWN, // 0BA5..0BA7
6050 TAMIL, // 0BA8..0BAA
6051 UNKNOWN, // 0BAB..0BAD
6052 TAMIL, // 0BAE..0BB9
6053 UNKNOWN, // 0BBA..0BBD
6054 TAMIL, // 0BBE..0BC2
6055 UNKNOWN, // 0BC3..0BC5
6056 TAMIL, // 0BC6..0BC8
6057 UNKNOWN, // 0BC9
6058 TAMIL, // 0BCA..0BCD
6059 UNKNOWN, // 0BCE..0BCF
6060 TAMIL, // 0BD0
6061 UNKNOWN, // 0BD1..0BD6
6062 TAMIL, // 0BD7
6063 UNKNOWN, // 0BD8..0BE5
6064 TAMIL, // 0BE6..0BFA
6065 UNKNOWN, // 0BFB..0BFF
6066 TELUGU, // 0C00..0C03
6067 UNKNOWN, // 0C04
6068 TELUGU, // 0C05..0C0C
6069 UNKNOWN, // 0C0D
6070 TELUGU, // 0C0E..0C10
6071 UNKNOWN, // 0C11
6072 TELUGU, // 0C12..0C28
6073 UNKNOWN, // 0C29
6074 TELUGU, // 0C2A..0C39
6075 UNKNOWN, // 0C3A..0C3C
6076 TELUGU, // 0C3D..0C44
6077 UNKNOWN, // 0C45
6078 TELUGU, // 0C46..0C48
6079 UNKNOWN, // 0C49
6080 TELUGU, // 0C4A..0C4D
6081 UNKNOWN, // 0C4E..0C54
6082 TELUGU, // 0C55..0C56
6083 UNKNOWN, // 0C57
6084 TELUGU, // 0C58..0C5A
6085 UNKNOWN, // 0C5B..0C5F
6086 TELUGU, // 0C60..0C63
6087 UNKNOWN, // 0C64..0C65
6088 TELUGU, // 0C66..0C6F
6089 UNKNOWN, // 0C70..0C77
6090 TELUGU, // 0C78..0C7F
6091 UNKNOWN, // 0C80
6092 KANNADA, // 0C81..0C83
6093 UNKNOWN, // 0C84
6094 KANNADA, // 0C85..0C8C
6095 UNKNOWN, // 0C8D
6096 KANNADA, // 0C8E..0C90
6097 UNKNOWN, // 0C91
6098 KANNADA, // 0C92..0CA8
6099 UNKNOWN, // 0CA9
6100 KANNADA, // 0CAA..0CB3
6101 UNKNOWN, // 0CB4
6102 KANNADA, // 0CB5..0CB9
6103 UNKNOWN, // 0CBA..0CBB
6104 KANNADA, // 0CBC..0CC4
6105 UNKNOWN, // 0CC5
6106 KANNADA, // 0CC6..0CC8
6107 UNKNOWN, // 0CC9
6108 KANNADA, // 0CCA..0CCD
6109 UNKNOWN, // 0CCE..0CD4
6110 KANNADA, // 0CD5..0CD6
6111 UNKNOWN, // 0CD7..0CDD
6112 KANNADA, // 0CDE
6113 UNKNOWN, // 0CDF
6114 KANNADA, // 0CE0..0CE3
6115 UNKNOWN, // 0CE4..0CE5
6116 KANNADA, // 0CE6..0CEF
6117 UNKNOWN, // 0CF0
6118 KANNADA, // 0CF1..0CF2
6119 UNKNOWN, // 0CF3..0D00
6120 MALAYALAM, // 0D01..0D03
6121 UNKNOWN, // 0D04
6122 MALAYALAM, // 0D05..0D0C
6123 UNKNOWN, // 0D0D
6124 MALAYALAM, // 0D0E..0D10
6125 UNKNOWN, // 0D11
6126 MALAYALAM, // 0D12..0D3A
6127 UNKNOWN, // 0D3B..0D3C
6128 MALAYALAM, // 0D3D..0D44
6129 UNKNOWN, // 0D45
6130 MALAYALAM, // 0D46..0D48
6131 UNKNOWN, // 0D49
6132 MALAYALAM, // 0D4A..0D4E
6133 UNKNOWN, // 0D4F..0D56
6134 MALAYALAM, // 0D57
6135 UNKNOWN, // 0D58..0D5E
6136 MALAYALAM, // 0D5F..0D63
6137 UNKNOWN, // 0D64..0D65
6138 MALAYALAM, // 0D66..0D75
6139 UNKNOWN, // 0D76..0D78
6140 MALAYALAM, // 0D79..0D7F
6141 UNKNOWN, // 0D80..0D81
6142 SINHALA, // 0D82..0D83
6143 UNKNOWN, // 0D84
6144 SINHALA, // 0D85..0D96
6145 UNKNOWN, // 0D97..0D99
6146 SINHALA, // 0D9A..0DB1
6147 UNKNOWN, // 0DB2
6148 SINHALA, // 0DB3..0DBB
6149 UNKNOWN, // 0DBC
6150 SINHALA, // 0DBD
6151 UNKNOWN, // 0DBE..0DBF
6152 SINHALA, // 0DC0..0DC6
6153 UNKNOWN, // 0DC7..0DC9
6154 SINHALA, // 0DCA
6155 UNKNOWN, // 0DCB..0DCE
6156 SINHALA, // 0DCF..0DD4
6157 UNKNOWN, // 0DD5
6158 SINHALA, // 0DD6
6159 UNKNOWN, // 0DD7
6160 SINHALA, // 0DD8..0DDF
6161 UNKNOWN, // 0DE0..0DE5
6162 SINHALA, // 0DE6..0DEF
6163 UNKNOWN, // 0DF0..0DF1
6164 SINHALA, // 0DF2..0DF4
6165 UNKNOWN, // 0DF5..0E00
6166 THAI, // 0E01..0E3A
6167 UNKNOWN, // 0E3B..0E3E
6168 COMMON, // 0E3F
6169 THAI, // 0E40..0E5B
6170 UNKNOWN, // 0E5C..0E80
6171 LAO, // 0E81..0E82
6172 UNKNOWN, // 0E83
6173 LAO, // 0E84
6174 UNKNOWN, // 0E85..0E86
6175 LAO, // 0E87..0E88
6176 UNKNOWN, // 0E89
6177 LAO, // 0E8A
6178 UNKNOWN, // 0E8B..0E8C
6179 LAO, // 0E8D
6180 UNKNOWN, // 0E8E..0E93
6181 LAO, // 0E94..0E97
6182 UNKNOWN, // 0E98
6183 LAO, // 0E99..0E9F
6184 UNKNOWN, // 0EA0
6185 LAO, // 0EA1..0EA3
6186 UNKNOWN, // 0EA4
6187 LAO, // 0EA5
6188 UNKNOWN, // 0EA6
6189 LAO, // 0EA7
6190 UNKNOWN, // 0EA8..0EA9
6191 LAO, // 0EAA..0EAB
6192 UNKNOWN, // 0EAC
6193 LAO, // 0EAD..0EB9
6194 UNKNOWN, // 0EBA
6195 LAO, // 0EBB..0EBD
6196 UNKNOWN, // 0EBE..0EBF
6197 LAO, // 0EC0..0EC4
6198 UNKNOWN, // 0EC5
6199 LAO, // 0EC6
6200 UNKNOWN, // 0EC7
6201 LAO, // 0EC8..0ECD
6202 UNKNOWN, // 0ECE..0ECF
6203 LAO, // 0ED0..0ED9
6204 UNKNOWN, // 0EDA..0EDB
6205 LAO, // 0EDC..0EDF
6206 UNKNOWN, // 0EE0..0EFF
6207 TIBETAN, // 0F00..0F47
6208 UNKNOWN, // 0F48
6209 TIBETAN, // 0F49..0F6C
6210 UNKNOWN, // 0F6D..0F70
6211 TIBETAN, // 0F71..0F97
6212 UNKNOWN, // 0F98
6213 TIBETAN, // 0F99..0FBC
6214 UNKNOWN, // 0FBD
6215 TIBETAN, // 0FBE..0FCC
6216 UNKNOWN, // 0FCD
6217 TIBETAN, // 0FCE..0FD4
6218 COMMON, // 0FD5..0FD8
6219 TIBETAN, // 0FD9..0FDA
6220 UNKNOWN, // 0FDB..FFF
6221 MYANMAR, // 1000..109F
6222 GEORGIAN, // 10A0..10C5
6223 UNKNOWN, // 10C6
6224 GEORGIAN, // 10C7
6225 UNKNOWN, // 10C8..10CC
6226 GEORGIAN, // 10CD
6227 UNKNOWN, // 10CE..10CF
6228 GEORGIAN, // 10D0..10FA
6229 COMMON, // 10FB
6230 GEORGIAN, // 10FC..10FF
6231 HANGUL, // 1100..11FF
6232 ETHIOPIC, // 1200..1248
6233 UNKNOWN, // 1249
6234 ETHIOPIC, // 124A..124D
6235 UNKNOWN, // 124E..124F
6236 ETHIOPIC, // 1250..1256
6237 UNKNOWN, // 1257
6238 ETHIOPIC, // 1258
6239 UNKNOWN, // 1259
6240 ETHIOPIC, // 125A..125D
6241 UNKNOWN, // 125E..125F
6242 ETHIOPIC, // 1260..1288
6243 UNKNOWN, // 1289
6244 ETHIOPIC, // 128A..128D
6245 UNKNOWN, // 128E..128F
6246 ETHIOPIC, // 1290..12B0
6247 UNKNOWN, // 12B1
6248 ETHIOPIC, // 12B2..12B5
6249 UNKNOWN, // 12B6..12B7
6250 ETHIOPIC, // 12B8..12BE
6251 UNKNOWN, // 12BF
6252 ETHIOPIC, // 12C0
6253 UNKNOWN, // 12C1
6254 ETHIOPIC, // 12C2..12C5
6255 UNKNOWN, // 12C6..12C7
6256 ETHIOPIC, // 12C8..12D6
6257 UNKNOWN, // 12D7
6258 ETHIOPIC, // 12D8..1310
6259 UNKNOWN, // 1311
6260 ETHIOPIC, // 1312..1315
6261 UNKNOWN, // 1316..1317
6262 ETHIOPIC, // 1318..135A
6263 UNKNOWN, // 135B..135C
6264 ETHIOPIC, // 135D..137C
6265 UNKNOWN, // 137D..137F
6266 ETHIOPIC, // 1380..1399
6267 UNKNOWN, // 139A..139F
6268 CHEROKEE, // 13A0..13F5
6269 UNKNOWN, // 13F6..13F7
6270 CHEROKEE, // 13F8..13FD
6271 UNKNOWN, // 13FE..13FF
6272 CANADIAN_ABORIGINAL, // 1400..167F
6273 OGHAM, // 1680..169C
6274 UNKNOWN, // 169D..169F
6275 RUNIC, // 16A0..16EA
6276 COMMON, // 16EB..16ED
6277 RUNIC, // 16EE..16F8
6278 UNKNOWN, // 16F9..16FF
6279 TAGALOG, // 1700..170C
6280 UNKNOWN, // 170D
6281 TAGALOG, // 170E..1714
6282 UNKNOWN, // 1715..171F
6283 HANUNOO, // 1720..1734
6284 COMMON, // 1735..1736
6285 UNKNOWN, // 1737..173F
6286 BUHID, // 1740..1753
6287 UNKNOWN, // 1754..175F
6288 TAGBANWA, // 1760..176C
6289 UNKNOWN, // 176D
6290 TAGBANWA, // 176E..1770
6291 UNKNOWN, // 1771
6292 TAGBANWA, // 1772..1773
6293 UNKNOWN, // 1774..177F
6294 KHMER, // 1780..17DD
6295 UNKNOWN, // 17DE..17DF
6296 KHMER, // 17E0..17E9
6297 UNKNOWN, // 17EA..17EF
6298 KHMER, // 17F0..17F9
6299 UNKNOWN, // 17FA..17FF
6300 MONGOLIAN, // 1800..1801
6301 COMMON, // 1802..1803
6302 MONGOLIAN, // 1804
6303 COMMON, // 1805
6304 MONGOLIAN, // 1806..180E
6305 UNKNOWN, // 180F
6306 MONGOLIAN, // 1810..1819
6307 UNKNOWN, // 181A..181F
6308 MONGOLIAN, // 1820..1877
6309 UNKNOWN, // 1878..187F
6310 MONGOLIAN, // 1880..18AA
6311 UNKNOWN, // 18AB..18AF
6312 CANADIAN_ABORIGINAL, // 18B0..18F5
6313 UNKNOWN, // 18F6..18FF
6314 LIMBU, // 1900..191E
6315 UNKNOWN, // 191F
6316 LIMBU, // 1920..192B
6317 UNKNOWN, // 192C..192F
6318 LIMBU, // 1930..193B
6319 UNKNOWN, // 193C..193F
6320 LIMBU, // 1940
6321 UNKNOWN, // 1941..1943
6322 LIMBU, // 1944..194F
6323 TAI_LE, // 1950..196D
6324 UNKNOWN, // 196E..196F
6325 TAI_LE, // 1970..1974
6326 UNKNOWN, // 1975..197F
6327 NEW_TAI_LUE, // 1980..19AB
6328 UNKNOWN, // 19AC..19AF
6329 NEW_TAI_LUE, // 19B0..19C9
6330 UNKNOWN, // 19CA..19CF
6331 NEW_TAI_LUE, // 19D0..19DA
6332 UNKNOWN, // 19DB..19DD
6333 NEW_TAI_LUE, // 19DE..19DF
6334 KHMER, // 19E0..19FF
6335 BUGINESE, // 1A00..1A1B
6336 UNKNOWN, // 1A1C..1A1D
6337 BUGINESE, // 1A1E..1A1F
6338 TAI_THAM, // 1A20..1A5E
6339 UNKNOWN, // 1A5F
6340 TAI_THAM, // 1A60..1A7C
6341 UNKNOWN, // 1A7D..1A7E
6342 TAI_THAM, // 1A7F..1A89
6343 UNKNOWN, // 1A8A..1A8F
6344 TAI_THAM, // 1A90..1A99
6345 UNKNOWN, // 1A9A..1A9F
6346 TAI_THAM, // 1AA0..1AAD
6347 UNKNOWN, // 1AAE..1AAF
6348 INHERITED, // 1AB0..1ABE
6349 UNKNOWN, // 1ABF..1AFF
6350 BALINESE, // 1B00..1B4B
6351 UNKNOWN, // 1B4C..1B4F
6352 BALINESE, // 1B50..1B7C
6353 UNKNOWN, // 1B7D..1B7F
6354 SUNDANESE, // 1B80..1BBF
6355 BATAK, // 1BC0..1BF3
6356 UNKNOWN, // 1BF4..1BFB
6357 BATAK, // 1BFC..1BFF
6358 LEPCHA, // 1C00..1C37
6359 UNKNOWN, // 1C38..1C3A
6360 LEPCHA, // 1C3B..1C49
6361 UNKNOWN, // 1C4A..1C4C
6362 LEPCHA, // 1C4D..1C4F
6363 OL_CHIKI, // 1C50..1C7F
6364 UNKNOWN, // 1C80..1CBF
6365 SUNDANESE, // 1CC0..1CC7
6366 UNKNOWN, // 1CC8..1CCF
6367 INHERITED, // 1CD0..1CD2
6368 COMMON, // 1CD3
6369 INHERITED, // 1CD4..1CE0
6370 COMMON, // 1CE1
6371 INHERITED, // 1CE2..1CE8
6372 COMMON, // 1CE9..1CEC
6373 INHERITED, // 1CED
6374 COMMON, // 1CEE..1CF3
6375 INHERITED, // 1CF4
6376 COMMON, // 1CF5..1CF6
6377 UNKNOWN, // 1CF7
6378 INHERITED, // 1CF8..1CF9
6379 UNKNOWN, // 1CFA..1CFF
6380 LATIN, // 1D00..1D25
6381 GREEK, // 1D26..1D2A
6382 CYRILLIC, // 1D2B
6383 LATIN, // 1D2C..1D5C
6384 GREEK, // 1D5D..1D61
6385 LATIN, // 1D62..1D65
6386 GREEK, // 1D66..1D6A
6387 LATIN, // 1D6B..1D77
6388 CYRILLIC, // 1D78
6389 LATIN, // 1D79..1DBE
6390 GREEK, // 1DBF
6391 INHERITED, // 1DC0..1DF5
6392 UNKNOWN, // 1DF6..1DFB
6393 INHERITED, // 1DFC..1DFF
6394 LATIN, // 1E00..1EFF
6395 GREEK, // 1F00..1F15
6396 UNKNOWN, // 1F16..1F17
6397 GREEK, // 1F18..1F1D
6398 UNKNOWN, // 1F1E..1F1F
6399 GREEK, // 1F20..1F45
6400 UNKNOWN, // 1F46..1F47
6401 GREEK, // 1F48..1F4D
6402 UNKNOWN, // 1F4E..1F4F
6403 GREEK, // 1F50..1F57
6404 UNKNOWN, // 1F58
6405 GREEK, // 1F59
6406 UNKNOWN, // 1F5A
6407 GREEK, // 1F5B
6408 UNKNOWN, // 1F5C
6409 GREEK, // 1F5D
6410 UNKNOWN, // 1F5E
6411 GREEK, // 1F5F..1F7D
6412 UNKNOWN, // 1F7E..1F7F
6413 GREEK, // 1F80..1FB4
6414 UNKNOWN, // 1FB5
6415 GREEK, // 1FB6..1FC4
6416 UNKNOWN, // 1FC5
6417 GREEK, // 1FC6..1FD3
6418 UNKNOWN, // 1FD4..1FD5
6419 GREEK, // 1FD6..1FDB
6420 UNKNOWN, // 1FDC
6421 GREEK, // 1FDD..1FEF
6422 UNKNOWN, // 1FF0..1FF1
6423 GREEK, // 1FF2..1FF4
6424 UNKNOWN, // 1FF5
6425 GREEK, // 1FF6..1FFE
6426 UNKNOWN, // 1FFF
6427 COMMON, // 2000..200B
6428 INHERITED, // 200C..200D
6429 COMMON, // 200E..2064
6430 UNKNOWN, // 2065
6431 COMMON, // 2066..2070
6432 LATIN, // 2071
6433 UNKNOWN, // 2072..2073
6434 COMMON, // 2074..207E
6435 LATIN, // 207F
6436 COMMON, // 2080..208E
6437 UNKNOWN, // 208F
6438 LATIN, // 2090..209C
6439 UNKNOWN, // 209D..209F
6440 COMMON, // 20A0..20BE
6441 UNKNOWN, // 20BF..20CF
6442 INHERITED, // 20D0..20F0
6443 UNKNOWN, // 20F1..20FF
6444 COMMON, // 2100..2125
6445 GREEK, // 2126
6446 COMMON, // 2127..2129
6447 LATIN, // 212A..212B
6448 COMMON, // 212C..2131
6449 LATIN, // 2132
6450 COMMON, // 2133..214D
6451 LATIN, // 214E
6452 COMMON, // 214F..215F
6453 LATIN, // 2160..2188
6454 COMMON, // 2189..218B
6455 UNKNOWN, // 218C..218F
6456 COMMON, // 2190..23FA
6457 UNKNOWN, // 23FB..23FF
6458 COMMON, // 2400..2426
6459 UNKNOWN, // 2427..243F
6460 COMMON, // 2440..244A
6461 UNKNOWN, // 244B..245F
6462 COMMON, // 2460..27FF
6463 BRAILLE, // 2800..28FF
6464 COMMON, // 2900..2B73
6465 UNKNOWN, // 2B74..2B75
6466 COMMON, // 2B76..2B95
6467 UNKNOWN, // 2B96..2B97
6468 COMMON, // 2B98..2BB9
6469 UNKNOWN, // 2BBA..2BBC
6470 COMMON, // 2BBD..2BC8
6471 UNKNOWN, // 2BC9
6472 COMMON, // 2BCA..2BD1
6473 UNKNOWN, // 2BD2..2BEB
6474 COMMON, // 2BEC..2BEF
6475 UNKNOWN, // 2BF0..2BFF
6476 GLAGOLITIC, // 2C00..2C2E
6477 UNKNOWN, // 2C2F
6478 GLAGOLITIC, // 2C30..2C5E
6479 UNKNOWN, // 2C5F
6480 LATIN, // 2C60..2C7F
6481 COPTIC, // 2C80..2CF3
6482 UNKNOWN, // 2CF4..2CF8
6483 COPTIC, // 2CF9..2CFF
6484 GEORGIAN, // 2D00..2D25
6485 UNKNOWN, // 2D26
6486 GEORGIAN, // 2D27
6487 UNKNOWN, // 2D28..2D2C
6488 GEORGIAN, // 2D2D
6489 UNKNOWN, // 2D2E..2D2F
6490 TIFINAGH, // 2D30..2D67
6491 UNKNOWN, // 2D68..2D6E
6492 TIFINAGH, // 2D6F..2D70
6493 UNKNOWN, // 2D71..2D7E
6494 TIFINAGH, // 2D7F
6495 ETHIOPIC, // 2D80..2D96
6496 UNKNOWN, // 2D97..2D9F
6497 ETHIOPIC, // 2DA0..2DA6
6498 UNKNOWN, // 2DA7
6499 ETHIOPIC, // 2DA8..2DAE
6500 UNKNOWN, // 2DAF
6501 ETHIOPIC, // 2DB0..2DB6
6502 UNKNOWN, // 2DB7
6503 ETHIOPIC, // 2DB8..2DBE
6504 UNKNOWN, // 2DBF
6505 ETHIOPIC, // 2DC0..2DC6
6506 UNKNOWN, // 2DC7
6507 ETHIOPIC, // 2DC8..2DCE
6508 UNKNOWN, // 2DCF
6509 ETHIOPIC, // 2DD0..2DD6
6510 UNKNOWN, // 2DD7
6511 ETHIOPIC, // 2DD8..2DDE
6512 UNKNOWN, // 2DDF
6513 CYRILLIC, // 2DE0..2DFF
6514 COMMON, // 2E00..2E42
6515 UNKNOWN, // 2E43..2E7F
6516 HAN, // 2E80..2E99
6517 UNKNOWN, // 2E9A
6518 HAN, // 2E9B..2EF3
6519 UNKNOWN, // 2EF4..2EFF
6520 HAN, // 2F00..2FD5
6521 UNKNOWN, // 2FD6..2FEF
6522 COMMON, // 2FF0..2FFB
6523 UNKNOWN, // 2FFC..2FFF
6524 COMMON, // 3000..3004
6525 HAN, // 3005
6526 COMMON, // 3006
6527 HAN, // 3007
6528 COMMON, // 3008..3020
6529 HAN, // 3021..3029
6530 INHERITED, // 302A..302D
6531 HANGUL, // 302E..302F
6532 COMMON, // 3030..3037
6533 HAN, // 3038..303B
6534 COMMON, // 303C..303F
6535 UNKNOWN, // 3040
6536 HIRAGANA, // 3041..3096
6537 UNKNOWN, // 3097..3098
6538 INHERITED, // 3099..309A
6539 COMMON, // 309B..309C
6540 HIRAGANA, // 309D..309F
6541 COMMON, // 30A0
6542 KATAKANA, // 30A1..30FA
6543 COMMON, // 30FB..30FC
6544 KATAKANA, // 30FD..30FF
6545 UNKNOWN, // 3100..3104
6546 BOPOMOFO, // 3105..312D
6547 UNKNOWN, // 312E..3130
6548 HANGUL, // 3131..318E
6549 UNKNOWN, // 318F
6550 COMMON, // 3190..319F
6551 BOPOMOFO, // 31A0..31BA
6552 UNKNOWN, // 31BB..31BF
6553 COMMON, // 31C0..31E3
6554 UNKNOWN, // 31E4..31EF
6555 KATAKANA, // 31F0..31FF
6556 HANGUL, // 3200..321E
6557 UNKNOWN, // 321F
6558 COMMON, // 3220..325F
6559 HANGUL, // 3260..327E
6560 COMMON, // 327F..32CF
6561 KATAKANA, // 32D0..32FE
6562 UNKNOWN, // 32FF
6563 KATAKANA, // 3300..3357
6564 COMMON, // 3358..33FF
6565 HAN, // 3400..4DB5
6566 UNKNOWN, // 4DB6..4DBF
6567 COMMON, // 4DC0..4DFF
6568 HAN, // 4E00..9FD5
6569 UNKNOWN, // 9FD6..9FFF
6570 YI, // A000..A48C
6571 UNKNOWN, // A48D..A48F
6572 YI, // A490..A4C6
6573 UNKNOWN, // A4C7..A4CF
6574 LISU, // A4D0..A4FF
6575 VAI, // A500..A62B
6576 UNKNOWN, // A62C..A63F
6577 CYRILLIC, // A640..A69F
6578 BAMUM, // A6A0..A6F7
6579 UNKNOWN, // A6F8..A6FF
6580 COMMON, // A700..A721
6581 LATIN, // A722..A787
6582 COMMON, // A788..A78A
6583 LATIN, // A78B..A7AD
6584 UNKNOWN, // A7AE..A7AF
6585 LATIN, // A7B0..A7B7
6586 UNKNOWN, // A7B8..A7F6
6587 LATIN, // A7F7..A7FF
6588 SYLOTI_NAGRI, // A800..A82B
6589 UNKNOWN, // A82C..A82F
6590 COMMON, // A830..A839
6591 UNKNOWN, // A83A..A83F
6592 PHAGS_PA, // A840..A877
6593 UNKNOWN, // A878..A87F
6594 SAURASHTRA, // A880..A8C4
6595 UNKNOWN, // A8C5..A8CD
6596 SAURASHTRA, // A8CE..A8D9
6597 UNKNOWN, // A8DA..A8DF
6598 DEVANAGARI, // A8E0..A8FD
6599 UNKNOWN, // A8FE..A8FF
6600 KAYAH_LI, // A900..A92D
6601 COMMON, // A92E
6602 KAYAH_LI, // A92F
6603 REJANG, // A930..A953
6604 UNKNOWN, // A954..A95E
6605 REJANG, // A95F
6606 HANGUL, // A960..A97C
6607 UNKNOWN, // A97D..A97F
6608 JAVANESE, // A980..A9CD
6609 UNKNOWN, // A9CE
6610 COMMON, // A9CF
6611 JAVANESE, // A9D0..A9D9
6612 UNKNOWN, // A9DA..A9DD
6613 JAVANESE, // A9DE..A9DF
6614 MYANMAR, // A9E0..A9FE
6615 UNKNOWN, // A9FF
6616 CHAM, // AA00..AA36
6617 UNKNOWN, // AA37..AA3F
6618 CHAM, // AA40..AA4D
6619 UNKNOWN, // AA4E..AA4F
6620 CHAM, // AA50..AA59
6621 UNKNOWN, // AA5A..AA5B
6622 CHAM, // AA5C..AA5F
6623 MYANMAR, // AA60..AA7F
6624 TAI_VIET, // AA80..AAC2
6625 UNKNOWN, // AAC3..AADA
6626 TAI_VIET, // AADB..AADF
6627 MEETEI_MAYEK, // AAE0..AAF6
6628 UNKNOWN, // AAF7..AB00
6629 ETHIOPIC, // AB01..AB06
6630 UNKNOWN, // AB07..AB08
6631 ETHIOPIC, // AB09..AB0E
6632 UNKNOWN, // AB0F..AB10
6633 ETHIOPIC, // AB11..AB16
6634 UNKNOWN, // AB17..AB1F
6635 ETHIOPIC, // AB20..AB26
6636 UNKNOWN, // AB27
6637 ETHIOPIC, // AB28..AB2E
6638 UNKNOWN, // AB2F
6639 LATIN, // AB30..AB5A
6640 COMMON, // AB5B
6641 LATIN, // AB5C..AB64
6642 GREEK, // AB65
6643 UNKNOWN, // AB66..AB6F
6644 CHEROKEE, // AB70..ABBF
6645 MEETEI_MAYEK, // ABC0..ABED
6646 UNKNOWN, // ABEE..ABEF
6647 MEETEI_MAYEK, // ABF0..ABF9
6648 UNKNOWN, // ABFA..ABFF
6649 HANGUL, // AC00..D7A3
6650 UNKNOWN, // D7A4..D7AF
6651 HANGUL, // D7B0..D7C6
6652 UNKNOWN, // D7C7..D7CA
6653 HANGUL, // D7CB..D7FB
6654 UNKNOWN, // D7FC..F8FF
6655 HAN, // F900..FA6D
6656 UNKNOWN, // FA6E..FA6F
6657 HAN, // FA70..FAD9
6658 UNKNOWN, // FADA..FAFF
6659 LATIN, // FB00..FB06
6660 UNKNOWN, // FB07..FB12
6661 ARMENIAN, // FB13..FB17
6662 UNKNOWN, // FB18..FB1C
6663 HEBREW, // FB1D..FB36
6664 UNKNOWN, // FB37
6665 HEBREW, // FB38..FB3C
6666 UNKNOWN, // FB3D
6667 HEBREW, // FB3E
6668 UNKNOWN, // FB3F
6669 HEBREW, // FB40..FB41
6670 UNKNOWN, // FB42
6671 HEBREW, // FB43..FB44
6672 UNKNOWN, // FB45
6673 HEBREW, // FB46..FB4F
6674 ARABIC, // FB50..FBC1
6675 UNKNOWN, // FBC2..FBD2
6676 ARABIC, // FBD3..FD3D
6677 COMMON, // FD3E..FD3F
6678 UNKNOWN, // FD40..FD4F
6679 ARABIC, // FD50..FD8F
6680 UNKNOWN, // FD90..FD91
6681 ARABIC, // FD92..FDC7
6682 UNKNOWN, // FDC8..FDEF
6683 ARABIC, // FDF0..FDFD
6684 UNKNOWN, // FDFE..FDFF
6685 INHERITED, // FE00..FE0F
6686 COMMON, // FE10..FE19
6687 UNKNOWN, // FE1A..FE1F
6688 INHERITED, // FE20..FE2D
6689 CYRILLIC, // FE2E..FE2F
6690 COMMON, // FE30..FE52
6691 UNKNOWN, // FE53
6692 COMMON, // FE54..FE66
6693 UNKNOWN, // FE67
6694 COMMON, // FE68..FE6B
6695 UNKNOWN, // FE6C..FE6F
6696 ARABIC, // FE70..FE74
6697 UNKNOWN, // FE75
6698 ARABIC, // FE76..FEFC
6699 UNKNOWN, // FEFD..FEFE
6700 COMMON, // FEFF
6701 UNKNOWN, // FF00
6702 COMMON, // FF01..FF20
6703 LATIN, // FF21..FF3A
6704 COMMON, // FF3B..FF40
6705 LATIN, // FF41..FF5A
6706 COMMON, // FF5B..FF65
6707 KATAKANA, // FF66..FF6F
6708 COMMON, // FF70
6709 KATAKANA, // FF71..FF9D
6710 COMMON, // FF9E..FF9F
6711 HANGUL, // FFA0..FFBE
6712 UNKNOWN, // FFBF..FFC1
6713 HANGUL, // FFC2..FFC7
6714 UNKNOWN, // FFC8..FFC9
6715 HANGUL, // FFCA..FFCF
6716 UNKNOWN, // FFD0..FFD1
6717 HANGUL, // FFD2..FFD7
6718 UNKNOWN, // FFD8..FFD9
6719 HANGUL, // FFDA..FFDC
6720 UNKNOWN, // FFDD..FFDF
6721 COMMON, // FFE0..FFE6
6722 UNKNOWN, // FFE7
6723 COMMON, // FFE8..FFEE
6724 UNKNOWN, // FFEF..FFF8
6725 COMMON, // FFF9..FFFD
6726 UNKNOWN, // FFFE..FFFF
6727 LINEAR_B, // 10000..1000B
6728 UNKNOWN, // 1000C
6729 LINEAR_B, // 1000D..10026
6730 UNKNOWN, // 10027
6731 LINEAR_B, // 10028..1003A
6732 UNKNOWN, // 1003B
6733 LINEAR_B, // 1003C..1003D
6734 UNKNOWN, // 1003E
6735 LINEAR_B, // 1003F..1004D
6736 UNKNOWN, // 1004E..1004F
6737 LINEAR_B, // 10050..1005D
6738 UNKNOWN, // 1005E..1007F
6739 LINEAR_B, // 10080..100FA
6740 UNKNOWN, // 100FB..100FF
6741 COMMON, // 10100..10102
6742 UNKNOWN, // 10103..10106
6743 COMMON, // 10107..10133
6744 UNKNOWN, // 10134..10136
6745 COMMON, // 10137..1013F
6746 GREEK, // 10140..1018C
6747 UNKNOWN, // 1018D..1018F
6748 COMMON, // 10190..1019B
6749 UNKNOWN, // 1019C..1019F
6750 GREEK, // 101A0
6751 UNKNOWN, // 101A1..101CF
6752 COMMON, // 101D0..101FC
6753 INHERITED, // 101FD
6754 UNKNOWN, // 101FE..1027F
6755 LYCIAN, // 10280..1029C
6756 UNKNOWN, // 1029D..1029F
6757 CARIAN, // 102A0..102D0
6758 UNKNOWN, // 102D1..102DF
6759 INHERITED, // 102E0
6760 COMMON, // 102E1..102FB
6761 UNKNOWN, // 102FC..102FF
6762 OLD_ITALIC, // 10300..10323
6763 UNKNOWN, // 10324..1032F
6764 GOTHIC, // 10330..1034A
6765 UNKNOWN, // 1034B..1034F
6766 OLD_PERMIC, // 10350..1037A
6767 UNKNOWN, // 1037B..1037F
6768 UGARITIC, // 10380..1039D
6769 UNKNOWN, // 1039E
6770 UGARITIC, // 1039F
6771 OLD_PERSIAN, // 103A0..103C3
6772 UNKNOWN, // 103C4..103C7
6773 OLD_PERSIAN, // 103C8..103D5
6774 UNKNOWN, // 103D6..103FF
6775 DESERET, // 10400..1044F
6776 SHAVIAN, // 10450..1047F
6777 OSMANYA, // 10480..1049D
6778 UNKNOWN, // 1049E..1049F
6779 OSMANYA, // 104A0..104A9
6780 UNKNOWN, // 104AA..104FF
6781 ELBASAN, // 10500..10527
6782 UNKNOWN, // 10528..1052F
6783 CAUCASIAN_ALBANIAN, // 10530..10563
6784 UNKNOWN, // 10564..1056E
6785 CAUCASIAN_ALBANIAN, // 1056F
6786 UNKNOWN, // 10570..105FF
6787 LINEAR_A, // 10600..10736
6788 UNKNOWN, // 10737..1073F
6789 LINEAR_A, // 10740..10755
6790 UNKNOWN, // 10756..1075F
6791 LINEAR_A, // 10760..10767
6792 UNKNOWN, // 10768..107FF
6793 CYPRIOT, // 10800..10805
6794 UNKNOWN, // 10806..10807
6795 CYPRIOT, // 10808
6796 UNKNOWN, // 10809
6797 CYPRIOT, // 1080A..10835
6798 UNKNOWN, // 10836
6799 CYPRIOT, // 10837..10838
6800 UNKNOWN, // 10839..1083B
6801 CYPRIOT, // 1083C
6802 UNKNOWN, // 1083D..1083E
6803 CYPRIOT, // 1083F
6804 IMPERIAL_ARAMAIC, // 10840..10855
6805 UNKNOWN, // 10856
6806 IMPERIAL_ARAMAIC, // 10857..1085F
6807 PALMYRENE, // 10860..1087F
6808 NABATAEAN, // 10880..1089E
6809 UNKNOWN, // 1089F..108A6
6810 NABATAEAN, // 108A7..108AF
6811 UNKNOWN, // 108B0..108DF
6812 HATRAN, // 108E0..108F2
6813 UNKNOWN, // 108F3
6814 HATRAN, // 108F4..108F5
6815 UNKNOWN, // 108F6..108FA
6816 HATRAN, // 108FB..108FF
6817 PHOENICIAN, // 10900..1091B
6818 UNKNOWN, // 1091C..1091E
6819 PHOENICIAN, // 1091F
6820 LYDIAN, // 10920..10939
6821 UNKNOWN, // 1093A..1093E
6822 LYDIAN, // 1093F
6823 UNKNOWN, // 10940..1097F
6824 MEROITIC_HIEROGLYPHS, // 10980..1099F
6825 MEROITIC_CURSIVE, // 109A0..109B7
6826 UNKNOWN, // 109B8..109BB
6827 MEROITIC_CURSIVE, // 109BC..109CF
6828 UNKNOWN, // 109D0..109D1
6829 MEROITIC_CURSIVE, // 109D2..109FF
6830 KHAROSHTHI, // 10A00..10A03
6831 UNKNOWN, // 10A04
6832 KHAROSHTHI, // 10A05..10A06
6833 UNKNOWN, // 10A07..10A0B
6834 KHAROSHTHI, // 10A0C..10A13
6835 UNKNOWN, // 10A14
6836 KHAROSHTHI, // 10A15..10A17
6837 UNKNOWN, // 10A18
6838 KHAROSHTHI, // 10A19..10A33
6839 UNKNOWN, // 10A34..10A37
6840 KHAROSHTHI, // 10A38..10A3A
6841 UNKNOWN, // 10A3B..10A3E
6842 KHAROSHTHI, // 10A3F..10A47
6843 UNKNOWN, // 10A48..10A4F
6844 KHAROSHTHI, // 10A50..10A58
6845 UNKNOWN, // 10A59..10A5F
6846 OLD_SOUTH_ARABIAN, // 10A60..10A7F
6847 OLD_NORTH_ARABIAN, // 10A80..10A9F
6848 UNKNOWN, // 10AA0..10ABF
6849 MANICHAEAN, // 10AC0..10AE6
6850 UNKNOWN, // 10AE7..10AEA
6851 MANICHAEAN, // 10AEB..10AF6
6852 UNKNOWN, // 10AF7..10AFF
6853 AVESTAN, // 10B00..10B35
6854 UNKNOWN, // 10B36..10B38
6855 AVESTAN, // 10B39..10B3F
6856 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
6857 UNKNOWN, // 10B56..10B57
6858 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
6859 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
6860 UNKNOWN, // 10B73..10B77
6861 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
6862 PSALTER_PAHLAVI, // 10B80..10B91
6863 UNKNOWN, // 10B92..10B98
6864 PSALTER_PAHLAVI, // 10B99..10B9C
6865 UNKNOWN, // 10B9D..10BA8
6866 PSALTER_PAHLAVI, // 10BA9..10BAF
6867 UNKNOWN, // 10BB0..10BFF
6868 OLD_TURKIC, // 10C00..10C48
6869 UNKNOWN, // 10C49..10C7F
6870 OLD_HUNGARIAN, // 10C80..10CB2
6871 UNKNOWN, // 10CB3..10CBF
6872 OLD_HUNGARIAN, // 10CC0..10CF2
6873 UNKNOWN, // 10CF3..10CF9
6874 OLD_HUNGARIAN, // 10CFA..10CFF
6875 UNKNOWN, // 10D00..10E5F
6876 ARABIC, // 10E60..10E7E
6877 UNKNOWN, // 10E7F..10FFF
6878 BRAHMI, // 11000..1104D
6879 UNKNOWN, // 1104E..11051
6880 BRAHMI, // 11052..1106F
6881 UNKNOWN, // 11070..1107E
6882 BRAHMI, // 1107F
6883 KAITHI, // 11080..110C1
6884 UNKNOWN, // 110C2..110CF
6885 SORA_SOMPENG, // 110D0..110E8
6886 UNKNOWN, // 110E9..110EF
6887 SORA_SOMPENG, // 110F0..110F9
6888 UNKNOWN, // 110FA..110FF
6889 CHAKMA, // 11100..11134
6890 UNKNOWN, // 11135
6891 CHAKMA, // 11136..11143
6892 UNKNOWN, // 11144..1114F
6893 MAHAJANI, // 11150..11176
6894 UNKNOWN, // 11177..1117F
6895 SHARADA, // 11180..111CD
6896 UNKNOWN, // 111CE..111CF
6897 SHARADA, // 111D0..111DF
6898 UNKNOWN, // 111E0
6899 SINHALA, // 111E1..111F4
6900 UNKNOWN, // 111F5..111FF
6901 KHOJKI, // 11200..11211
6902 UNKNOWN, // 11212
6903 KHOJKI, // 11213..1123D
6904 UNKNOWN, // 1123E..1127F
6905 MULTANI, // 11280..11286
6906 UNKNOWN, // 11287
6907 MULTANI, // 11288
6908 UNKNOWN, // 11289
6909 MULTANI, // 1128A..1128D
6910 UNKNOWN, // 1128E
6911 MULTANI, // 1128F..1129D
6912 UNKNOWN, // 1129E
6913 MULTANI, // 1129F..112A9
6914 UNKNOWN, // 112AA..112AF
6915 KHUDAWADI, // 112B0..112EA
6916 UNKNOWN, // 112EB..112EF
6917 KHUDAWADI, // 112F0..112F9
6918 UNKNOWN, // 112FA..112FF
6919 GRANTHA, // 11300..11303
6920 UNKNOWN, // 11304
6921 GRANTHA, // 11305..1130C
6922 UNKNOWN, // 1130D..1130E
6923 GRANTHA, // 1130F..11310
6924 UNKNOWN, // 11311..11312
6925 GRANTHA, // 11313..11328
6926 UNKNOWN, // 11329
6927 GRANTHA, // 1132A..11330
6928 UNKNOWN, // 11331
6929 GRANTHA, // 11332..11333
6930 UNKNOWN, // 11334
6931 GRANTHA, // 11335..11339
6932 UNKNOWN, // 1133A..1133B
6933 GRANTHA, // 1133C..11344
6934 UNKNOWN, // 11345..11346
6935 GRANTHA, // 11347..11348
6936 UNKNOWN, // 11349..1134A
6937 GRANTHA, // 1134B..1134D
6938 UNKNOWN, // 1134E..1134F
6939 GRANTHA, // 11350
6940 UNKNOWN, // 11351..11356
6941 GRANTHA, // 11357
6942 UNKNOWN, // 11358..1135C
6943 GRANTHA, // 1135D..11363
6944 UNKNOWN, // 11364..11365
6945 GRANTHA, // 11366..1136C
6946 UNKNOWN, // 1136D..1136F
6947 GRANTHA, // 11370..11374
6948 UNKNOWN, // 11375..1147F
6949 TIRHUTA, // 11480..114C7
6950 UNKNOWN, // 114C8..114CF
6951 TIRHUTA, // 114D0..114D9
6952 UNKNOWN, // 114DA..1157F
6953 SIDDHAM, // 11580..115B5
6954 UNKNOWN, // 115B6..115B7
6955 SIDDHAM, // 115B8..115DD
6956 UNKNOWN, // 115DE..115FF
6957 MODI, // 11600..11644
6958 UNKNOWN, // 11645..1164F
6959 MODI, // 11650..11659
6960 UNKNOWN, // 1165A..1167F
6961 TAKRI, // 11680..116B7
6962 UNKNOWN, // 116B8..116BF
6963 TAKRI, // 116C0..116C9
6964 UNKNOWN, // 116CA..116FF
6965 AHOM, // 11700..11719
6966 UNKNOWN, // 1171A..1171C
6967 AHOM, // 1171D..1172B
6968 UNKNOWN, // 1172C..1172F
6969 AHOM, // 11730..1173F
6970 UNKNOWN, // 11740..1189F
6971 WARANG_CITI, // 118A0..118F2
6972 UNKNOWN, // 118F3..118FE
6973 WARANG_CITI, // 118FF
6974 UNKNOWN, // 11900..11ABF
6975 PAU_CIN_HAU, // 11AC0..11AF8
6976 UNKNOWN, // 11AF9..11FFF
6977 CUNEIFORM, // 12000..12399
6978 UNKNOWN, // 1239A..123FF
6979 CUNEIFORM, // 12400..1246E
6980 UNKNOWN, // 1246F
6981 CUNEIFORM, // 12470..12474
6982 UNKNOWN, // 12475..1247F
6983 CUNEIFORM, // 12480..12543
6984 UNKNOWN, // 12544..12FFF
6985 EGYPTIAN_HIEROGLYPHS, // 13000..1342E
6986 UNKNOWN, // 1342F..143FF
6987 ANATOLIAN_HIEROGLYPHS, // 14400..14646
6988 UNKNOWN, // 14647..167FF
6989 BAMUM, // 16800..16A38
6990 UNKNOWN, // 16A39..16A3F
6991 MRO, // 16A40..16A5E
6992 UNKNOWN, // 16A5F
6993 MRO, // 16A60..16A69
6994 UNKNOWN, // 16A6A..16A6D
6995 MRO, // 16A6E..16A6F
6996 UNKNOWN, // 16A70..16ACF
6997 BASSA_VAH, // 16AD0..16AED
6998 UNKNOWN, // 16AEE..16AEF
6999 BASSA_VAH, // 16AF0..16AF5
7000 UNKNOWN, // 16AF6..16AFF
7001 PAHAWH_HMONG, // 16B00..16B45
7002 UNKNOWN, // 16B46..16B4F
7003 PAHAWH_HMONG, // 16B50..16B59
7004 UNKNOWN, // 16B5A
7005 PAHAWH_HMONG, // 16B5B..16B61
7006 UNKNOWN, // 16B62
7007 PAHAWH_HMONG, // 16B63..16B77
7008 UNKNOWN, // 16B78..16B7C
7009 PAHAWH_HMONG, // 16B7D..16B8F
7010 UNKNOWN, // 16B90..16EFF
7011 MIAO, // 16F00..16F44
7012 UNKNOWN, // 16F45..16F4F
7013 MIAO, // 16F50..16F7E
7014 UNKNOWN, // 16F7F..16F8E
7015 MIAO, // 16F8F..16F9F
7016 UNKNOWN, // 16FA0..1AFFF
7017 KATAKANA, // 1B000
7018 HIRAGANA, // 1B001
7019 UNKNOWN, // 1B002..1BBFF
7020 DUPLOYAN, // 1BC00..1BC6A
7021 UNKNOWN, // 1BC6B..1BC6F
7022 DUPLOYAN, // 1BC70..1BC7C
7023 UNKNOWN, // 1BC7D..1BC7F
7024 DUPLOYAN, // 1BC80..1BC88
7025 UNKNOWN, // 1BC89..1BC8F
7026 DUPLOYAN, // 1BC90..1BC99
7027 UNKNOWN, // 1BC9A..1BC9B
7028 DUPLOYAN, // 1BC9C..1BC9F
7029 COMMON, // 1BCA0..1BCA3
7030 UNKNOWN, // 1BCA4..1CFFF
7031 COMMON, // 1D000..1D0F5
7032 UNKNOWN, // 1D0F6..1D0FF
7033 COMMON, // 1D100..1D126
7034 UNKNOWN, // 1D127..1D128
7035 COMMON, // 1D129..1D166
7036 INHERITED, // 1D167..1D169
7037 COMMON, // 1D16A..1D17A
7038 INHERITED, // 1D17B..1D182
7039 COMMON, // 1D183..1D184
7040 INHERITED, // 1D185..1D18B
7041 COMMON, // 1D18C..1D1A9
7042 INHERITED, // 1D1AA..1D1AD
7043 COMMON, // 1D1AE..1D1E8
7044 UNKNOWN, // 1D1E9..1D1FF
7045 GREEK, // 1D200..1D245
7046 UNKNOWN, // 1D246..1D2FF
7047 COMMON, // 1D300..1D356
7048 UNKNOWN, // 1D357..1D35F
7049 COMMON, // 1D360..1D371
7050 UNKNOWN, // 1D372..1D3FF
7051 COMMON, // 1D400..1D454
7052 UNKNOWN, // 1D455
7053 COMMON, // 1D456..1D49C
7054 UNKNOWN, // 1D49D
7055 COMMON, // 1D49E..1D49F
7056 UNKNOWN, // 1D4A0..1D4A1
7057 COMMON, // 1D4A2
7058 UNKNOWN, // 1D4A3..1D4A4
7059 COMMON, // 1D4A5..1D4A6
7060 UNKNOWN, // 1D4A7..1D4A8
7061 COMMON, // 1D4A9..1D4AC
7062 UNKNOWN, // 1D4AD
7063 COMMON, // 1D4AE..1D4B9
7064 UNKNOWN, // 1D4BA
7065 COMMON, // 1D4BB
7066 UNKNOWN, // 1D4BC
7067 COMMON, // 1D4BD..1D4C3
7068 UNKNOWN, // 1D4C4
7069 COMMON, // 1D4C5..1D505
7070 UNKNOWN, // 1D506
7071 COMMON, // 1D507..1D50A
7072 UNKNOWN, // 1D50B..1D50C
7073 COMMON, // 1D50D..1D514
7074 UNKNOWN, // 1D515
7075 COMMON, // 1D516..1D51C
7076 UNKNOWN, // 1D51D
7077 COMMON, // 1D51E..1D539
7078 UNKNOWN, // 1D53A
7079 COMMON, // 1D53B..1D53E
7080 UNKNOWN, // 1D53F
7081 COMMON, // 1D540..1D544
7082 UNKNOWN, // 1D545
7083 COMMON, // 1D546
7084 UNKNOWN, // 1D547..1D549
7085 COMMON, // 1D54A..1D550
7086 UNKNOWN, // 1D551
7087 COMMON, // 1D552..1D6A5
7088 UNKNOWN, // 1D6A6..1D6A7
7089 COMMON, // 1D6A8..1D7CB
7090 UNKNOWN, // 1D7CC..1D7CD
7091 COMMON, // 1D7CE..1D7FF
7092 SIGNWRITING, // 1D800..1DA8B
7093 UNKNOWN, // 1DA8C..1DA9A
7094 SIGNWRITING, // 1DA9B..1DA9F
7095 UNKNOWN, // 1DAA0
7096 SIGNWRITING, // 1DAA1..1DAAF
7097 UNKNOWN, // 1DAB0..1E7FF
7098 MENDE_KIKAKUI, // 1E800..1E8C4
7099 UNKNOWN, // 1E8C5..1E8C6
7100 MENDE_KIKAKUI, // 1E8C7..1E8D6
7101 UNKNOWN, // 1E8D7..1EDFF
7102 ARABIC, // 1EE00..1EE03
7103 UNKNOWN, // 1EE04
7104 ARABIC, // 1EE05..1EE1F
7105 UNKNOWN, // 1EE20
7106 ARABIC, // 1EE21..1EE22
7107 UNKNOWN, // 1EE23
7108 ARABIC, // 1EE24
7109 UNKNOWN, // 1EE25..1EE26
7110 ARABIC, // 1EE27
7111 UNKNOWN, // 1EE28
7112 ARABIC, // 1EE29..1EE32
7113 UNKNOWN, // 1EE33
7114 ARABIC, // 1EE34..1EE37
7115 UNKNOWN, // 1EE38
7116 ARABIC, // 1EE39
7117 UNKNOWN, // 1EE3A
7118 ARABIC, // 1EE3B
7119 UNKNOWN, // 1EE3C..1EE41
7120 ARABIC, // 1EE42
7121 UNKNOWN, // 1EE43..1EE46
7122 ARABIC, // 1EE47
7123 UNKNOWN, // 1EE48
7124 ARABIC, // 1EE49
7125 UNKNOWN, // 1EE4A
7126 ARABIC, // 1EE4B
7127 UNKNOWN, // 1EE4C
7128 ARABIC, // 1EE4D..1EE4F
7129 UNKNOWN, // 1EE50
7130 ARABIC, // 1EE51..1EE52
7131 UNKNOWN, // 1EE53
7132 ARABIC, // 1EE54
7133 UNKNOWN, // 1EE55..1EE56
7134 ARABIC, // 1EE57
7135 UNKNOWN, // 1EE58
7136 ARABIC, // 1EE59
7137 UNKNOWN, // 1EE5A
7138 ARABIC, // 1EE5B
7139 UNKNOWN, // 1EE5C
7140 ARABIC, // 1EE5D
7141 UNKNOWN, // 1EE5E
7142 ARABIC, // 1EE5F
7143 UNKNOWN, // 1EE60
7144 ARABIC, // 1EE61..1EE62
7145 UNKNOWN, // 1EE63
7146 ARABIC, // 1EE64
7147 UNKNOWN, // 1EE65..1EE66
7148 ARABIC, // 1EE67..1EE6A
7149 UNKNOWN, // 1EE6B
7150 ARABIC, // 1EE6C..1EE72
7151 UNKNOWN, // 1EE73
7152 ARABIC, // 1EE74..1EE77
7153 UNKNOWN, // 1EE78
7154 ARABIC, // 1EE79..1EE7C
7155 UNKNOWN, // 1EE7D
7156 ARABIC, // 1EE7E
7157 UNKNOWN, // 1EE7F
7158 ARABIC, // 1EE80..1EE89
7159 UNKNOWN, // 1EE8A
7160 ARABIC, // 1EE8B..1EE9B
7161 UNKNOWN, // 1EE9C..1EEA0
7162 ARABIC, // 1EEA1..1EEA3
7163 UNKNOWN, // 1EEA4
7164 ARABIC, // 1EEA5..1EEA9
7165 UNKNOWN, // 1EEAA
7166 ARABIC, // 1EEAB..1EEBB
7167 UNKNOWN, // 1EEBC..1EEEF
7168 ARABIC, // 1EEF0..1EEF1
7169 UNKNOWN, // 1EEF2..1EFFF
7170 COMMON, // 1F000..1F02B
7171 UNKNOWN, // 1F02C..1F02F
7172 COMMON, // 1F030..1F093
7173 UNKNOWN, // 1F094..1F09F
7174 COMMON, // 1F0A0..1F0AE
7175 UNKNOWN, // 1F0AF..1F0B0
7176 COMMON, // 1F0B1..1F0BF
7177 UNKNOWN, // 1F0C0
7178 COMMON, // 1F0C1..1F0CF
7179 UNKNOWN, // 1F0D0
7180 COMMON, // 1F0D1..1F0F5
7181 UNKNOWN, // 1F0F6..1F0FF
7182 COMMON, // 1F100..1F10C
7183 UNKNOWN, // 1F10D..1F10F
7184 COMMON, // 1F110..1F12E
7185 UNKNOWN, // 1F12F
7186 COMMON, // 1F130..1F16B
7187 UNKNOWN, // 1F16C..1F16F
7188 COMMON, // 1F170..1F19A
7189 UNKNOWN, // 1F19B..1F1E5
7190 COMMON, // 1F1E6..1F1FF
7191 HIRAGANA, // 1F200
7192 COMMON, // 1F201..1F202
7193 UNKNOWN, // 1F203..1F20F
7194 COMMON, // 1F210..1F23A
7195 UNKNOWN, // 1F23B..1F23F
7196 COMMON, // 1F240..1F248
7197 UNKNOWN, // 1F249..1F24F
7198 COMMON, // 1F250..1F251
7199 UNKNOWN, // 1F252..1F2FF
7200 COMMON, // 1F300..1F579
7201 UNKNOWN, // 1F57A
7202 COMMON, // 1F57B..1F5A3
7203 UNKNOWN, // 1F5A4
7204 COMMON, // 1F5A5..1F6D0
7205 UNKNOWN, // 1F6D1..1F6DF
7206 COMMON, // 1F6E0..1F6EC
7207 UNKNOWN, // 1F6ED..1F6EF
7208 COMMON, // 1F6F0..1F6F3
7209 UNKNOWN, // 1F6F4..1F6FF
7210 COMMON, // 1F700..1F773
7211 UNKNOWN, // 1F774..1F77F
7212 COMMON, // 1F780..1F7D4
7213 UNKNOWN, // 1F7D5..1F7FF
7214 COMMON, // 1F800..1F80B
7215 UNKNOWN, // 1F80C..1F80F
7216 COMMON, // 1F810..1F847
7217 UNKNOWN, // 1F848..1F84F
7218 COMMON, // 1F850..1F859
7219 UNKNOWN, // 1F85A..1F85F
7220 COMMON, // 1F860..1F887
7221 UNKNOWN, // 1F888..1F88F
7222 COMMON, // 1F890..1F8AD
7223 UNKNOWN, // 1F8AE..1F90F
7224 COMMON, // 1F910..1F918
7225 UNKNOWN, // 1F919..1F97F
7226 COMMON, // 1F980..1F984
7227 UNKNOWN, // 1F985..1F9BF
7228 COMMON, // 1F9C0
7229 UNKNOWN, // 1F9C1..1FFFF
7230 HAN, // 20000..2A6D6
7231 UNKNOWN, // 2A6D7..2A6FF
7232 HAN, // 2A700..2B734
7233 UNKNOWN, // 2B735..2B73F
7234 HAN, // 2B740..2B81D
7235 UNKNOWN, // 2B81E..2B81F
7236 HAN, // 2B820..2CEA1
7237 UNKNOWN, // 2CEA2..2F7FF
7238 HAN, // 2F800..2FA1D
7239 UNKNOWN, // 2FA1E..E0000
7240 COMMON, // E0001
7241 UNKNOWN, // E0002..E001F
7242 COMMON, // E0020..E007F
7243 UNKNOWN, // E0080..E00FF
7244 INHERITED, // E0100..E01EF
7245 UNKNOWN // E01F0..10FFFF
7246 };
7247
7248 private static HashMap<String, Character.UnicodeScript> aliases;
7249 static {
7250 aliases = new HashMap<>(134);
7251 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
7252 aliases.put("AHOM", AHOM);
7253 aliases.put("ARAB", ARABIC);
7254 aliases.put("ARMI", IMPERIAL_ARAMAIC);
7255 aliases.put("ARMN", ARMENIAN);
7256 aliases.put("AVST", AVESTAN);
7257 aliases.put("BALI", BALINESE);
7258 aliases.put("BAMU", BAMUM);
7259 aliases.put("BASS", BASSA_VAH);
7260 aliases.put("BATK", BATAK);
7261 aliases.put("BENG", BENGALI);
7262 aliases.put("BOPO", BOPOMOFO);
7263 aliases.put("BRAH", BRAHMI);
7264 aliases.put("BRAI", BRAILLE);
7265 aliases.put("BUGI", BUGINESE);
7266 aliases.put("BUHD", BUHID);
7267 aliases.put("CAKM", CHAKMA);
7268 aliases.put("CANS", CANADIAN_ABORIGINAL);
7269 aliases.put("CARI", CARIAN);
7270 aliases.put("CHAM", CHAM);
7271 aliases.put("CHER", CHEROKEE);
7272 aliases.put("COPT", COPTIC);
7273 aliases.put("CPRT", CYPRIOT);
7274 aliases.put("CYRL", CYRILLIC);
7275 aliases.put("DEVA", DEVANAGARI);
7276 aliases.put("DSRT", DESERET);
7277 aliases.put("DUPL", DUPLOYAN);
7278 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
7279 aliases.put("ELBA", ELBASAN);
7280 aliases.put("ETHI", ETHIOPIC);
7281 aliases.put("GEOR", GEORGIAN);
7282 aliases.put("GLAG", GLAGOLITIC);
7283 aliases.put("GOTH", GOTHIC);
7284 aliases.put("GRAN", GRANTHA);
7285 aliases.put("GREK", GREEK);
7286 aliases.put("GUJR", GUJARATI);
7287 aliases.put("GURU", GURMUKHI);
7288 aliases.put("HANG", HANGUL);
7289 aliases.put("HANI", HAN);
7290 aliases.put("HANO", HANUNOO);
7291 aliases.put("HATR", HATRAN);
7292 aliases.put("HEBR", HEBREW);
7293 aliases.put("HIRA", HIRAGANA);
7294 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
7295 aliases.put("HMNG", PAHAWH_HMONG);
7296 // it appears we don't have the KATAKANA_OR_HIRAGANA
7297 //aliases.put("HRKT", KATAKANA_OR_HIRAGANA);
7298 aliases.put("HUNG", OLD_HUNGARIAN);
7299 aliases.put("ITAL", OLD_ITALIC);
7300 aliases.put("JAVA", JAVANESE);
7301 aliases.put("KALI", KAYAH_LI);
7302 aliases.put("KANA", KATAKANA);
7303 aliases.put("KHAR", KHAROSHTHI);
7304 aliases.put("KHMR", KHMER);
7305 aliases.put("KHOJ", KHOJKI);
7306 aliases.put("KNDA", KANNADA);
7307 aliases.put("KTHI", KAITHI);
7308 aliases.put("LANA", TAI_THAM);
7309 aliases.put("LAOO", LAO);
7310 aliases.put("LATN", LATIN);
7311 aliases.put("LEPC", LEPCHA);
7312 aliases.put("LIMB", LIMBU);
7313 aliases.put("LINA", LINEAR_A);
7314 aliases.put("LINB", LINEAR_B);
7315 aliases.put("LISU", LISU);
7316 aliases.put("LYCI", LYCIAN);
7317 aliases.put("LYDI", LYDIAN);
7318 aliases.put("MAHJ", MAHAJANI);
7319 aliases.put("MAND", MANDAIC);
7320 aliases.put("MANI", MANICHAEAN);
7321 aliases.put("MEND", MENDE_KIKAKUI);
7322 aliases.put("MERC", MEROITIC_CURSIVE);
7323 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
7324 aliases.put("MLYM", MALAYALAM);
7325 aliases.put("MODI", MODI);
7326 aliases.put("MONG", MONGOLIAN);
7327 aliases.put("MROO", MRO);
7328 aliases.put("MTEI", MEETEI_MAYEK);
7329 aliases.put("MULT", MULTANI);
7330 aliases.put("MYMR", MYANMAR);
7331 aliases.put("NARB", OLD_NORTH_ARABIAN);
7332 aliases.put("NBAT", NABATAEAN);
7333 aliases.put("NKOO", NKO);
7334 aliases.put("OGAM", OGHAM);
7335 aliases.put("OLCK", OL_CHIKI);
7336 aliases.put("ORKH", OLD_TURKIC);
7337 aliases.put("ORYA", ORIYA);
7338 aliases.put("OSMA", OSMANYA);
7339 aliases.put("PALM", PALMYRENE);
7340 aliases.put("PAUC", PAU_CIN_HAU);
7341 aliases.put("PERM", OLD_PERMIC);
7342 aliases.put("PHAG", PHAGS_PA);
7343 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
7344 aliases.put("PHLP", PSALTER_PAHLAVI);
7345 aliases.put("PHNX", PHOENICIAN);
7346 aliases.put("PLRD", MIAO);
7347 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
7348 aliases.put("RJNG", REJANG);
7349 aliases.put("RUNR", RUNIC);
7350 aliases.put("SAMR", SAMARITAN);
7351 aliases.put("SARB", OLD_SOUTH_ARABIAN);
7352 aliases.put("SAUR", SAURASHTRA);
7353 aliases.put("SGNW", SIGNWRITING);
7354 aliases.put("SHAW", SHAVIAN);
7355 aliases.put("SHRD", SHARADA);
7356 aliases.put("SIDD", SIDDHAM);
7357 aliases.put("SIND", KHUDAWADI);
7358 aliases.put("SINH", SINHALA);
7359 aliases.put("SORA", SORA_SOMPENG);
7360 aliases.put("SUND", SUNDANESE);
7361 aliases.put("SYLO", SYLOTI_NAGRI);
7362 aliases.put("SYRC", SYRIAC);
7363 aliases.put("TAGB", TAGBANWA);
7364 aliases.put("TAKR", TAKRI);
7365 aliases.put("TALE", TAI_LE);
7366 aliases.put("TALU", NEW_TAI_LUE);
7367 aliases.put("TAML", TAMIL);
7368 aliases.put("TAVT", TAI_VIET);
7369 aliases.put("TELU", TELUGU);
7370 aliases.put("TFNG", TIFINAGH);
7371 aliases.put("TGLG", TAGALOG);
7372 aliases.put("THAA", THAANA);
7373 aliases.put("THAI", THAI);
7374 aliases.put("TIBT", TIBETAN);
7375 aliases.put("TIRH", TIRHUTA);
7376 aliases.put("UGAR", UGARITIC);
7377 aliases.put("VAII", VAI);
7378 aliases.put("WARA", WARANG_CITI);
7379 aliases.put("XPEO", OLD_PERSIAN);
7380 aliases.put("XSUX", CUNEIFORM);
7381 aliases.put("YIII", YI);
7382 aliases.put("ZINH", INHERITED);
7383 aliases.put("ZYYY", COMMON);
7384 aliases.put("ZZZZ", UNKNOWN);
7385 }
7386
7387 /**
7388 * Returns the enum constant representing the Unicode script of which
7389 * the given character (Unicode code point) is assigned to.
7390 *
7391 * @param codePoint the character (Unicode code point) in question.
7392 * @return The {@code UnicodeScript} constant representing the
7393 * Unicode script of which this character is assigned to.
7394 *
7395 * @exception IllegalArgumentException if the specified
7396 * {@code codePoint} is an invalid Unicode code point.
7397 * @see Character#isValidCodePoint(int)
7398 *
7399 */
7400 public static UnicodeScript of(int codePoint) {
7401 if (!isValidCodePoint(codePoint))
7402 throw new IllegalArgumentException();
7403 int type = getType(codePoint);
7404 // leave SURROGATE and PRIVATE_USE for table lookup
7405 if (type == UNASSIGNED)
7406 return UNKNOWN;
7407 int index = Arrays.binarySearch(scriptStarts, codePoint);
7408 if (index < 0)
7409 index = -index - 2;
7410 return scripts[index];
7411 }
7412
7413 /**
7414 * Returns the UnicodeScript constant with the given Unicode script
7415 * name or the script name alias. Script names and their aliases are
7416 * determined by The Unicode Standard. The files {@code Scripts<version>.txt}
7417 * and {@code PropertyValueAliases<version>.txt} define script names
7418 * and the script name aliases for a particular version of the
7419 * standard. The {@link Character} class specifies the version of
7420 * the standard that it supports.
7421 * <p>
7422 * Character case is ignored for all of the valid script names.
7423 * The en_US locale's case mapping rules are used to provide
7424 * case-insensitive string comparisons for script name validation.
7425 *
7426 * @param scriptName A {@code UnicodeScript} name.
7427 * @return The {@code UnicodeScript} constant identified
7428 * by {@code scriptName}
7429 * @throws IllegalArgumentException if {@code scriptName} is an
7430 * invalid name
7431 * @throws NullPointerException if {@code scriptName} is null
7432 */
7433 public static final UnicodeScript forName(String scriptName) {
7434 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
7435 //.replace(' ', '_'));
7436 UnicodeScript sc = aliases.get(scriptName);
7437 if (sc != null)
7438 return sc;
7439 return valueOf(scriptName);
7440 }
7441 }
7442
7443 /**
7444 * The value of the {@code Character}.
7445 *
7446 * @serial
7447 */
7448 private final char value;
7449
7450 /** use serialVersionUID from JDK 1.0.2 for interoperability */
7451 private static final long serialVersionUID = 3786198910865385080L;
7452
7453 /**
7454 * Constructs a newly allocated {@code Character} object that
7455 * represents the specified {@code char} value.
7456 *
7457 * @param value the value to be represented by the
7458 * {@code Character} object.
7459 */
7460 public Character(char value) {
7461 this.value = value;
7462 }
7463
7464 private static class CharacterCache {
7465 private CharacterCache(){}
7466
7467 static final Character cache[] = new Character[127 + 1];
7468
7469 static {
7470 cache[0] = ZERO;
7471 for (int i = 1; i < cache.length; i++)
7472 cache[i] = new Character((char)i);
7473 }
7474 }
7475
7476 /**
7477 * Returns a {@code Character} instance representing the specified
7478 * {@code char} value.
7479 * If a new {@code Character} instance is not required, this method
7480 * should generally be used in preference to the constructor
7481 * {@link #Character(char)}, as this method is likely to yield
7482 * significantly better space and time performance by caching
7483 * frequently requested values.
7484 *
7485 * This method will always cache values in the range {@code
7486 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
7487 * cache other values outside of this range.
7488 *
7489 * @param c a char value.
7490 * @return a {@code Character} instance representing {@code c}.
7491 * @since 1.5
7492 */
7493 @HotSpotIntrinsicCandidate
7494 public static Character valueOf(char c) {
7495 if (c <= 127) { // must cache
7496 return CharacterCache.cache[(int)c];
7497 }
7498 return new Character(c);
7499 }
7500
7501 /**
7502 * Returns the value of this {@code Character} object.
7503 * @return the primitive {@code char} value represented by
7504 * this object.
7505 */
7506 @HotSpotIntrinsicCandidate
7507 public char charValue() {
7508 return value;
7509 }
7510
7511 /**
7512 * Returns a hash code for this {@code Character}; equal to the result
7513 * of invoking {@code charValue()}.
7514 *
7515 * @return a hash code value for this {@code Character}
7516 */
7517 @Override
7518 public int hashCode() {
7519 return Character.hashCode(value);
7520 }
7521
7522 /**
7523 * Returns a hash code for a {@code char} value; compatible with
7524 * {@code Character.hashCode()}.
7525 *
7526 * @since 1.8
7527 *
7528 * @param value The {@code char} for which to return a hash code.
7529 * @return a hash code value for a {@code char} value.
7530 */
7531 public static int hashCode(char value) {
7532 return (int)value;
7533 }
7534
7535 /**
7536 * Compares this object against the specified object.
7537 * The result is {@code true} if and only if the argument is not
7538 * {@code null} and is a {@code Character} object that
7539 * represents the same {@code char} value as this object.
7540 *
7541 * @param obj the object to compare with.
7542 * @return {@code true} if the objects are the same;
7543 * {@code false} otherwise.
7544 */
7545 public boolean equals(Object obj) {
7546 if (obj instanceof Character) {
7547 return value == ((Character)obj).charValue();
7548 }
7549 return false;
7550 }
7551
7552 /**
7553 * Returns a {@code String} object representing this
7554 * {@code Character}'s value. The result is a string of
7555 * length 1 whose sole component is the primitive
7556 * {@code char} value represented by this
7557 * {@code Character} object.
7558 *
7559 * @return a string representation of this object.
7560 */
7561 public String toString() {
7562 char buf[] = {value};
7563 return String.valueOf(buf);
7564 }
7565
7566 /**
7567 * Returns a {@code String} object representing the
7568 * specified {@code char}. The result is a string of length
7569 * 1 consisting solely of the specified {@code char}.
7570 *
7571 * @param c the {@code char} to be converted
7572 * @return the string representation of the specified {@code char}
7573 * @since 1.4
7574 */
7575 public static String toString(char c) {
7576 return String.valueOf(c);
7577 }
7578
7579 /**
7580 * Determines whether the specified code point is a valid
7581 * <a href="http://www.unicode.org/glossary/#code_point">
7582 * Unicode code point value</a>.
7583 *
7584 * @param codePoint the Unicode code point to be tested
7585 * @return {@code true} if the specified code point value is between
7586 * {@link #MIN_CODE_POINT} and
7587 * {@link #MAX_CODE_POINT} inclusive;
7588 * {@code false} otherwise.
7589 * @since 1.5
7590 */
7591 public static boolean isValidCodePoint(int codePoint) {
7592 // Optimized form of:
7593 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
7594 int plane = codePoint >>> 16;
7595 return plane < ((MAX_CODE_POINT + 1) >>> 16);
7596 }
7597
7598 /**
7599 * Determines whether the specified character (Unicode code point)
7600 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
7601 * Such code points can be represented using a single {@code char}.
7602 *
7603 * @param codePoint the character (Unicode code point) to be tested
7604 * @return {@code true} if the specified code point is between
7605 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
7606 * {@code false} otherwise.
7607 * @since 1.7
7608 */
7609 public static boolean isBmpCodePoint(int codePoint) {
7610 return codePoint >>> 16 == 0;
7611 // Optimized form of:
7612 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
7613 // We consistently use logical shift (>>>) to facilitate
7614 // additional runtime optimizations.
7615 }
7616
7617 /**
7618 * Determines whether the specified character (Unicode code point)
7619 * is in the <a href="#supplementary">supplementary character</a> range.
7620 *
7621 * @param codePoint the character (Unicode code point) to be tested
7622 * @return {@code true} if the specified code point is between
7623 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
7624 * {@link #MAX_CODE_POINT} inclusive;
7625 * {@code false} otherwise.
7626 * @since 1.5
7627 */
7628 public static boolean isSupplementaryCodePoint(int codePoint) {
7629 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
7630 && codePoint < MAX_CODE_POINT + 1;
7631 }
7632
7633 /**
7634 * Determines if the given {@code char} value is a
7635 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
7636 * Unicode high-surrogate code unit</a>
7637 * (also known as <i>leading-surrogate code unit</i>).
7638 *
7639 * <p>Such values do not represent characters by themselves,
7640 * but are used in the representation of
7641 * <a href="#supplementary">supplementary characters</a>
7642 * in the UTF-16 encoding.
7643 *
7644 * @param ch the {@code char} value to be tested.
7645 * @return {@code true} if the {@code char} value is between
7646 * {@link #MIN_HIGH_SURROGATE} and
7647 * {@link #MAX_HIGH_SURROGATE} inclusive;
7648 * {@code false} otherwise.
7649 * @see Character#isLowSurrogate(char)
7650 * @see Character.UnicodeBlock#of(int)
7651 * @since 1.5
7652 */
7653 public static boolean isHighSurrogate(char ch) {
7654 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
7655 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
7656 }
7657
7658 /**
7659 * Determines if the given {@code char} value is a
7660 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
7661 * Unicode low-surrogate code unit</a>
7662 * (also known as <i>trailing-surrogate code unit</i>).
7663 *
7664 * <p>Such values do not represent characters by themselves,
7665 * but are used in the representation of
7666 * <a href="#supplementary">supplementary characters</a>
7667 * in the UTF-16 encoding.
7668 *
7669 * @param ch the {@code char} value to be tested.
7670 * @return {@code true} if the {@code char} value is between
7671 * {@link #MIN_LOW_SURROGATE} and
7672 * {@link #MAX_LOW_SURROGATE} inclusive;
7673 * {@code false} otherwise.
7674 * @see Character#isHighSurrogate(char)
7675 * @since 1.5
7676 */
7677 public static boolean isLowSurrogate(char ch) {
7678 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
7679 }
7680
7681 /**
7682 * Determines if the given {@code char} value is a Unicode
7683 * <i>surrogate code unit</i>.
7684 *
7685 * <p>Such values do not represent characters by themselves,
7686 * but are used in the representation of
7687 * <a href="#supplementary">supplementary characters</a>
7688 * in the UTF-16 encoding.
7689 *
7690 * <p>A char value is a surrogate code unit if and only if it is either
7691 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
7692 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
7693 *
7694 * @param ch the {@code char} value to be tested.
7695 * @return {@code true} if the {@code char} value is between
7696 * {@link #MIN_SURROGATE} and
7697 * {@link #MAX_SURROGATE} inclusive;
7698 * {@code false} otherwise.
7699 * @since 1.7
7700 */
7701 public static boolean isSurrogate(char ch) {
7702 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
7703 }
7704
7705 /**
7706 * Determines whether the specified pair of {@code char}
7707 * values is a valid
7708 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
7709 * Unicode surrogate pair</a>.
7710
7711 * <p>This method is equivalent to the expression:
7712 * <blockquote><pre>{@code
7713 * isHighSurrogate(high) && isLowSurrogate(low)
7714 * }</pre></blockquote>
7715 *
7716 * @param high the high-surrogate code value to be tested
7717 * @param low the low-surrogate code value to be tested
7718 * @return {@code true} if the specified high and
7719 * low-surrogate code values represent a valid surrogate pair;
7720 * {@code false} otherwise.
7721 * @since 1.5
7722 */
7723 public static boolean isSurrogatePair(char high, char low) {
7724 return isHighSurrogate(high) && isLowSurrogate(low);
7725 }
7726
7727 /**
7728 * Determines the number of {@code char} values needed to
7729 * represent the specified character (Unicode code point). If the
7730 * specified character is equal to or greater than 0x10000, then
7731 * the method returns 2. Otherwise, the method returns 1.
7732 *
7733 * <p>This method doesn't validate the specified character to be a
7734 * valid Unicode code point. The caller must validate the
7735 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
7736 * if necessary.
7737 *
7738 * @param codePoint the character (Unicode code point) to be tested.
7739 * @return 2 if the character is a valid supplementary character; 1 otherwise.
7740 * @see Character#isSupplementaryCodePoint(int)
7741 * @since 1.5
7742 */
7743 public static int charCount(int codePoint) {
7744 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
7745 }
7746
7747 /**
7748 * Converts the specified surrogate pair to its supplementary code
7749 * point value. This method does not validate the specified
7750 * surrogate pair. The caller must validate it using {@link
7751 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
7752 *
7753 * @param high the high-surrogate code unit
7754 * @param low the low-surrogate code unit
7755 * @return the supplementary code point composed from the
7756 * specified surrogate pair.
7757 * @since 1.5
7758 */
7759 public static int toCodePoint(char high, char low) {
7760 // Optimized form of:
7761 // return ((high - MIN_HIGH_SURROGATE) << 10)
7762 // + (low - MIN_LOW_SURROGATE)
7763 // + MIN_SUPPLEMENTARY_CODE_POINT;
7764 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
7765 - (MIN_HIGH_SURROGATE << 10)
7766 - MIN_LOW_SURROGATE);
7767 }
7768
7769 /**
7770 * Returns the code point at the given index of the
7771 * {@code CharSequence}. If the {@code char} value at
7772 * the given index in the {@code CharSequence} is in the
7773 * high-surrogate range, the following index is less than the
7774 * length of the {@code CharSequence}, and the
7775 * {@code char} value at the following index is in the
7776 * low-surrogate range, then the supplementary code point
7777 * corresponding to this surrogate pair is returned. Otherwise,
7778 * the {@code char} value at the given index is returned.
7779 *
7780 * @param seq a sequence of {@code char} values (Unicode code
7781 * units)
7782 * @param index the index to the {@code char} values (Unicode
7783 * code units) in {@code seq} to be converted
7784 * @return the Unicode code point at the given index
7785 * @exception NullPointerException if {@code seq} is null.
7786 * @exception IndexOutOfBoundsException if the value
7787 * {@code index} is negative or not less than
7788 * {@link CharSequence#length() seq.length()}.
7789 * @since 1.5
7790 */
7791 public static int codePointAt(CharSequence seq, int index) {
7792 char c1 = seq.charAt(index);
7793 if (isHighSurrogate(c1) && ++index < seq.length()) {
7794 char c2 = seq.charAt(index);
7795 if (isLowSurrogate(c2)) {
7796 return toCodePoint(c1, c2);
7797 }
7798 }
7799 return c1;
7800 }
7801
7802 /**
7803 * Returns the code point at the given index of the
7804 * {@code char} array. If the {@code char} value at
7805 * the given index in the {@code char} array is in the
7806 * high-surrogate range, the following index is less than the
7807 * length of the {@code char} array, and the
7808 * {@code char} value at the following index is in the
7809 * low-surrogate range, then the supplementary code point
7810 * corresponding to this surrogate pair is returned. Otherwise,
7811 * the {@code char} value at the given index is returned.
7812 *
7813 * @param a the {@code char} array
7814 * @param index the index to the {@code char} values (Unicode
7815 * code units) in the {@code char} array to be converted
7816 * @return the Unicode code point at the given index
7817 * @exception NullPointerException if {@code a} is null.
7818 * @exception IndexOutOfBoundsException if the value
7819 * {@code index} is negative or not less than
7820 * the length of the {@code char} array.
7821 * @since 1.5
7822 */
7823 public static int codePointAt(char[] a, int index) {
7824 return codePointAtImpl(a, index, a.length);
7825 }
7826
7827 /**
7828 * Returns the code point at the given index of the
7829 * {@code char} array, where only array elements with
7830 * {@code index} less than {@code limit} can be used. If
7831 * the {@code char} value at the given index in the
7832 * {@code char} array is in the high-surrogate range, the
7833 * following index is less than the {@code limit}, and the
7834 * {@code char} value at the following index is in the
7835 * low-surrogate range, then the supplementary code point
7836 * corresponding to this surrogate pair is returned. Otherwise,
7837 * the {@code char} value at the given index is returned.
7838 *
7839 * @param a the {@code char} array
7840 * @param index the index to the {@code char} values (Unicode
7841 * code units) in the {@code char} array to be converted
7842 * @param limit the index after the last array element that
7843 * can be used in the {@code char} array
7844 * @return the Unicode code point at the given index
7845 * @exception NullPointerException if {@code a} is null.
7846 * @exception IndexOutOfBoundsException if the {@code index}
7847 * argument is negative or not less than the {@code limit}
7848 * argument, or if the {@code limit} argument is negative or
7849 * greater than the length of the {@code char} array.
7850 * @since 1.5
7851 */
7852 public static int codePointAt(char[] a, int index, int limit) {
7853 if (index >= limit || limit < 0 || limit > a.length) {
7854 throw new IndexOutOfBoundsException();
7855 }
7856 return codePointAtImpl(a, index, limit);
7857 }
7858
7859 // throws ArrayIndexOutOfBoundsException if index out of bounds
7860 static int codePointAtImpl(char[] a, int index, int limit) {
7861 char c1 = a[index];
7862 if (isHighSurrogate(c1) && ++index < limit) {
7863 char c2 = a[index];
7864 if (isLowSurrogate(c2)) {
7865 return toCodePoint(c1, c2);
7866 }
7867 }
7868 return c1;
7869 }
7870
7871 /**
7872 * Returns the code point preceding the given index of the
7873 * {@code CharSequence}. If the {@code char} value at
7874 * {@code (index - 1)} in the {@code CharSequence} is in
7875 * the low-surrogate range, {@code (index - 2)} is not
7876 * negative, and the {@code char} value at {@code (index - 2)}
7877 * in the {@code CharSequence} is in the
7878 * high-surrogate range, then the supplementary code point
7879 * corresponding to this surrogate pair is returned. Otherwise,
7880 * the {@code char} value at {@code (index - 1)} is
7881 * returned.
7882 *
7883 * @param seq the {@code CharSequence} instance
7884 * @param index the index following the code point that should be returned
7885 * @return the Unicode code point value before the given index.
7886 * @exception NullPointerException if {@code seq} is null.
7887 * @exception IndexOutOfBoundsException if the {@code index}
7888 * argument is less than 1 or greater than {@link
7889 * CharSequence#length() seq.length()}.
7890 * @since 1.5
7891 */
7892 public static int codePointBefore(CharSequence seq, int index) {
7893 char c2 = seq.charAt(--index);
7894 if (isLowSurrogate(c2) && index > 0) {
7895 char c1 = seq.charAt(--index);
7896 if (isHighSurrogate(c1)) {
7897 return toCodePoint(c1, c2);
7898 }
7899 }
7900 return c2;
7901 }
7902
7903 /**
7904 * Returns the code point preceding the given index of the
7905 * {@code char} array. If the {@code char} value at
7906 * {@code (index - 1)} in the {@code char} array is in
7907 * the low-surrogate range, {@code (index - 2)} is not
7908 * negative, and the {@code char} value at {@code (index - 2)}
7909 * in the {@code char} array is in the
7910 * high-surrogate range, then the supplementary code point
7911 * corresponding to this surrogate pair is returned. Otherwise,
7912 * the {@code char} value at {@code (index - 1)} is
7913 * returned.
7914 *
7915 * @param a the {@code char} array
7916 * @param index the index following the code point that should be returned
7917 * @return the Unicode code point value before the given index.
7918 * @exception NullPointerException if {@code a} is null.
7919 * @exception IndexOutOfBoundsException if the {@code index}
7920 * argument is less than 1 or greater than the length of the
7921 * {@code char} array
7922 * @since 1.5
7923 */
7924 public static int codePointBefore(char[] a, int index) {
7925 return codePointBeforeImpl(a, index, 0);
7926 }
7927
7928 /**
7929 * Returns the code point preceding the given index of the
7930 * {@code char} array, where only array elements with
7931 * {@code index} greater than or equal to {@code start}
7932 * can be used. If the {@code char} value at {@code (index - 1)}
7933 * in the {@code char} array is in the
7934 * low-surrogate range, {@code (index - 2)} is not less than
7935 * {@code start}, and the {@code char} value at
7936 * {@code (index - 2)} in the {@code char} array is in
7937 * the high-surrogate range, then the supplementary code point
7938 * corresponding to this surrogate pair is returned. Otherwise,
7939 * the {@code char} value at {@code (index - 1)} is
7940 * returned.
7941 *
7942 * @param a the {@code char} array
7943 * @param index the index following the code point that should be returned
7944 * @param start the index of the first array element in the
7945 * {@code char} array
7946 * @return the Unicode code point value before the given index.
7947 * @exception NullPointerException if {@code a} is null.
7948 * @exception IndexOutOfBoundsException if the {@code index}
7949 * argument is not greater than the {@code start} argument or
7950 * is greater than the length of the {@code char} array, or
7951 * if the {@code start} argument is negative or not less than
7952 * the length of the {@code char} array.
7953 * @since 1.5
7954 */
7955 public static int codePointBefore(char[] a, int index, int start) {
7956 if (index <= start || start < 0 || start >= a.length) {
7957 throw new IndexOutOfBoundsException();
7958 }
7959 return codePointBeforeImpl(a, index, start);
7960 }
7961
7962 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
7963 static int codePointBeforeImpl(char[] a, int index, int start) {
7964 char c2 = a[--index];
7965 if (isLowSurrogate(c2) && index > start) {
7966 char c1 = a[--index];
7967 if (isHighSurrogate(c1)) {
7968 return toCodePoint(c1, c2);
7969 }
7970 }
7971 return c2;
7972 }
7973
7974 /**
7975 * Returns the leading surrogate (a
7976 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
7977 * high surrogate code unit</a>) of the
7978 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
7979 * surrogate pair</a>
7980 * representing the specified supplementary character (Unicode
7981 * code point) in the UTF-16 encoding. If the specified character
7982 * is not a
7983 * <a href="Character.html#supplementary">supplementary character</a>,
7984 * an unspecified {@code char} is returned.
7985 *
7986 * <p>If
7987 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
7988 * is {@code true}, then
7989 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
7990 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
7991 * are also always {@code true}.
7992 *
7993 * @param codePoint a supplementary character (Unicode code point)
7994 * @return the leading surrogate code unit used to represent the
7995 * character in the UTF-16 encoding
7996 * @since 1.7
7997 */
7998 public static char highSurrogate(int codePoint) {
7999 return (char) ((codePoint >>> 10)
8000 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
8001 }
8002
8003 /**
8004 * Returns the trailing surrogate (a
8005 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
8006 * low surrogate code unit</a>) of the
8007 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
8008 * surrogate pair</a>
8009 * representing the specified supplementary character (Unicode
8010 * code point) in the UTF-16 encoding. If the specified character
8011 * is not a
8012 * <a href="Character.html#supplementary">supplementary character</a>,
8013 * an unspecified {@code char} is returned.
8014 *
8015 * <p>If
8016 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
8017 * is {@code true}, then
8018 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
8019 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
8020 * are also always {@code true}.
8021 *
8022 * @param codePoint a supplementary character (Unicode code point)
8023 * @return the trailing surrogate code unit used to represent the
8024 * character in the UTF-16 encoding
8025 * @since 1.7
8026 */
8027 public static char lowSurrogate(int codePoint) {
8028 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
8029 }
8030
8031 /**
8032 * Converts the specified character (Unicode code point) to its
8033 * UTF-16 representation. If the specified code point is a BMP
8034 * (Basic Multilingual Plane or Plane 0) value, the same value is
8035 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
8036 * specified code point is a supplementary character, its
8037 * surrogate values are stored in {@code dst[dstIndex]}
8038 * (high-surrogate) and {@code dst[dstIndex+1]}
8039 * (low-surrogate), and 2 is returned.
8040 *
8041 * @param codePoint the character (Unicode code point) to be converted.
8042 * @param dst an array of {@code char} in which the
8043 * {@code codePoint}'s UTF-16 value is stored.
8044 * @param dstIndex the start index into the {@code dst}
8045 * array where the converted value is stored.
8046 * @return 1 if the code point is a BMP code point, 2 if the
8047 * code point is a supplementary code point.
8048 * @exception IllegalArgumentException if the specified
8049 * {@code codePoint} is not a valid Unicode code point.
8050 * @exception NullPointerException if the specified {@code dst} is null.
8051 * @exception IndexOutOfBoundsException if {@code dstIndex}
8052 * is negative or not less than {@code dst.length}, or if
8053 * {@code dst} at {@code dstIndex} doesn't have enough
8054 * array element(s) to store the resulting {@code char}
8055 * value(s). (If {@code dstIndex} is equal to
8056 * {@code dst.length-1} and the specified
8057 * {@code codePoint} is a supplementary character, the
8058 * high-surrogate value is not stored in
8059 * {@code dst[dstIndex]}.)
8060 * @since 1.5
8061 */
8062 public static int toChars(int codePoint, char[] dst, int dstIndex) {
8063 if (isBmpCodePoint(codePoint)) {
8064 dst[dstIndex] = (char) codePoint;
8065 return 1;
8066 } else if (isValidCodePoint(codePoint)) {
8067 toSurrogates(codePoint, dst, dstIndex);
8068 return 2;
8069 } else {
8070 throw new IllegalArgumentException();
8071 }
8072 }
8073
8074 /**
8075 * Converts the specified character (Unicode code point) to its
8076 * UTF-16 representation stored in a {@code char} array. If
8077 * the specified code point is a BMP (Basic Multilingual Plane or
8078 * Plane 0) value, the resulting {@code char} array has
8079 * the same value as {@code codePoint}. If the specified code
8080 * point is a supplementary code point, the resulting
8081 * {@code char} array has the corresponding surrogate pair.
8082 *
8083 * @param codePoint a Unicode code point
8084 * @return a {@code char} array having
8085 * {@code codePoint}'s UTF-16 representation.
8086 * @exception IllegalArgumentException if the specified
8087 * {@code codePoint} is not a valid Unicode code point.
8088 * @since 1.5
8089 */
8090 public static char[] toChars(int codePoint) {
8091 if (isBmpCodePoint(codePoint)) {
8092 return new char[] { (char) codePoint };
8093 } else if (isValidCodePoint(codePoint)) {
8094 char[] result = new char[2];
8095 toSurrogates(codePoint, result, 0);
8096 return result;
8097 } else {
8098 throw new IllegalArgumentException();
8099 }
8100 }
8101
8102 static void toSurrogates(int codePoint, char[] dst, int index) {
8103 // We write elements "backwards" to guarantee all-or-nothing
8104 dst[index+1] = lowSurrogate(codePoint);
8105 dst[index] = highSurrogate(codePoint);
8106 }
8107
8108 /**
8109 * Returns the number of Unicode code points in the text range of
8110 * the specified char sequence. The text range begins at the
8111 * specified {@code beginIndex} and extends to the
8112 * {@code char} at index {@code endIndex - 1}. Thus the
8113 * length (in {@code char}s) of the text range is
8114 * {@code endIndex-beginIndex}. Unpaired surrogates within
8115 * the text range count as one code point each.
8116 *
8117 * @param seq the char sequence
8118 * @param beginIndex the index to the first {@code char} of
8119 * the text range.
8120 * @param endIndex the index after the last {@code char} of
8121 * the text range.
8122 * @return the number of Unicode code points in the specified text
8123 * range
8124 * @exception NullPointerException if {@code seq} is null.
8125 * @exception IndexOutOfBoundsException if the
8126 * {@code beginIndex} is negative, or {@code endIndex}
8127 * is larger than the length of the given sequence, or
8128 * {@code beginIndex} is larger than {@code endIndex}.
8129 * @since 1.5
8130 */
8131 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
8132 int length = seq.length();
8133 if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) {
8134 throw new IndexOutOfBoundsException();
8135 }
8136 int n = endIndex - beginIndex;
8137 for (int i = beginIndex; i < endIndex; ) {
8138 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
8139 isLowSurrogate(seq.charAt(i))) {
8140 n--;
8141 i++;
8142 }
8143 }
8144 return n;
8145 }
8146
8147 /**
8148 * Returns the number of Unicode code points in a subarray of the
8149 * {@code char} array argument. The {@code offset}
8150 * argument is the index of the first {@code char} of the
8151 * subarray and the {@code count} argument specifies the
8152 * length of the subarray in {@code char}s. Unpaired
8153 * surrogates within the subarray count as one code point each.
8154 *
8155 * @param a the {@code char} array
8156 * @param offset the index of the first {@code char} in the
8157 * given {@code char} array
8158 * @param count the length of the subarray in {@code char}s
8159 * @return the number of Unicode code points in the specified subarray
8160 * @exception NullPointerException if {@code a} is null.
8161 * @exception IndexOutOfBoundsException if {@code offset} or
8162 * {@code count} is negative, or if {@code offset +
8163 * count} is larger than the length of the given array.
8164 * @since 1.5
8165 */
8166 public static int codePointCount(char[] a, int offset, int count) {
8167 if (count > a.length - offset || offset < 0 || count < 0) {
8168 throw new IndexOutOfBoundsException();
8169 }
8170 return codePointCountImpl(a, offset, count);
8171 }
8172
8173 static int codePointCountImpl(char[] a, int offset, int count) {
8174 int endIndex = offset + count;
8175 int n = count;
8176 for (int i = offset; i < endIndex; ) {
8177 if (isHighSurrogate(a[i++]) && i < endIndex &&
8178 isLowSurrogate(a[i])) {
8179 n--;
8180 i++;
8181 }
8182 }
8183 return n;
8184 }
8185
8186 /**
8187 * Returns the index within the given char sequence that is offset
8188 * from the given {@code index} by {@code codePointOffset}
8189 * code points. Unpaired surrogates within the text range given by
8190 * {@code index} and {@code codePointOffset} count as
8191 * one code point each.
8192 *
8193 * @param seq the char sequence
8194 * @param index the index to be offset
8195 * @param codePointOffset the offset in code points
8196 * @return the index within the char sequence
8197 * @exception NullPointerException if {@code seq} is null.
8198 * @exception IndexOutOfBoundsException if {@code index}
8199 * is negative or larger then the length of the char sequence,
8200 * or if {@code codePointOffset} is positive and the
8201 * subsequence starting with {@code index} has fewer than
8202 * {@code codePointOffset} code points, or if
8203 * {@code codePointOffset} is negative and the subsequence
8204 * before {@code index} has fewer than the absolute value
8205 * of {@code codePointOffset} code points.
8206 * @since 1.5
8207 */
8208 public static int offsetByCodePoints(CharSequence seq, int index,
8209 int codePointOffset) {
8210 int length = seq.length();
8211 if (index < 0 || index > length) {
8212 throw new IndexOutOfBoundsException();
8213 }
8214
8215 int x = index;
8216 if (codePointOffset >= 0) {
8217 int i;
8218 for (i = 0; x < length && i < codePointOffset; i++) {
8219 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
8220 isLowSurrogate(seq.charAt(x))) {
8221 x++;
8222 }
8223 }
8224 if (i < codePointOffset) {
8225 throw new IndexOutOfBoundsException();
8226 }
8227 } else {
8228 int i;
8229 for (i = codePointOffset; x > 0 && i < 0; i++) {
8230 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
8231 isHighSurrogate(seq.charAt(x-1))) {
8232 x--;
8233 }
8234 }
8235 if (i < 0) {
8236 throw new IndexOutOfBoundsException();
8237 }
8238 }
8239 return x;
8240 }
8241
8242 /**
8243 * Returns the index within the given {@code char} subarray
8244 * that is offset from the given {@code index} by
8245 * {@code codePointOffset} code points. The
8246 * {@code start} and {@code count} arguments specify a
8247 * subarray of the {@code char} array. Unpaired surrogates
8248 * within the text range given by {@code index} and
8249 * {@code codePointOffset} count as one code point each.
8250 *
8251 * @param a the {@code char} array
8252 * @param start the index of the first {@code char} of the
8253 * subarray
8254 * @param count the length of the subarray in {@code char}s
8255 * @param index the index to be offset
8256 * @param codePointOffset the offset in code points
8257 * @return the index within the subarray
8258 * @exception NullPointerException if {@code a} is null.
8259 * @exception IndexOutOfBoundsException
8260 * if {@code start} or {@code count} is negative,
8261 * or if {@code start + count} is larger than the length of
8262 * the given array,
8263 * or if {@code index} is less than {@code start} or
8264 * larger then {@code start + count},
8265 * or if {@code codePointOffset} is positive and the text range
8266 * starting with {@code index} and ending with {@code start + count - 1}
8267 * has fewer than {@code codePointOffset} code
8268 * points,
8269 * or if {@code codePointOffset} is negative and the text range
8270 * starting with {@code start} and ending with {@code index - 1}
8271 * has fewer than the absolute value of
8272 * {@code codePointOffset} code points.
8273 * @since 1.5
8274 */
8275 public static int offsetByCodePoints(char[] a, int start, int count,
8276 int index, int codePointOffset) {
8277 if (count > a.length-start || start < 0 || count < 0
8278 || index < start || index > start+count) {
8279 throw new IndexOutOfBoundsException();
8280 }
8281 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
8282 }
8283
8284 static int offsetByCodePointsImpl(char[]a, int start, int count,
8285 int index, int codePointOffset) {
8286 int x = index;
8287 if (codePointOffset >= 0) {
8288 int limit = start + count;
8289 int i;
8290 for (i = 0; x < limit && i < codePointOffset; i++) {
8291 if (isHighSurrogate(a[x++]) && x < limit &&
8292 isLowSurrogate(a[x])) {
8293 x++;
8294 }
8295 }
8296 if (i < codePointOffset) {
8297 throw new IndexOutOfBoundsException();
8298 }
8299 } else {
8300 int i;
8301 for (i = codePointOffset; x > start && i < 0; i++) {
8302 if (isLowSurrogate(a[--x]) && x > start &&
8303 isHighSurrogate(a[x-1])) {
8304 x--;
8305 }
8306 }
8307 if (i < 0) {
8308 throw new IndexOutOfBoundsException();
8309 }
8310 }
8311 return x;
8312 }
8313
8314 /**
8315 * Determines if the specified character is a lowercase character.
8316 * <p>
8317 * A character is lowercase if its general category type, provided
8318 * by {@code Character.getType(ch)}, is
8319 * {@code LOWERCASE_LETTER}, or it has contributory property
8320 * Other_Lowercase as defined by the Unicode Standard.
8321 * <p>
8322 * The following are examples of lowercase characters:
8323 * <blockquote><pre>
8324 * 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
8325 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
8326 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
8327 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
8328 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
8329 * </pre></blockquote>
8330 * <p> Many other Unicode characters are lowercase too.
8331 *
8332 * <p><b>Note:</b> This method cannot handle <a
8333 * href="#supplementary"> supplementary characters</a>. To support
8334 * all Unicode characters, including supplementary characters, use
8335 * the {@link #isLowerCase(int)} method.
8336 *
8337 * @param ch the character to be tested.
8338 * @return {@code true} if the character is lowercase;
8339 * {@code false} otherwise.
8340 * @see Character#isLowerCase(char)
8341 * @see Character#isTitleCase(char)
8342 * @see Character#toLowerCase(char)
8343 * @see Character#getType(char)
8344 */
8345 public static boolean isLowerCase(char ch) {
8346 return isLowerCase((int)ch);
8347 }
8348
8349 /**
8350 * Determines if the specified character (Unicode code point) is a
8351 * lowercase character.
8352 * <p>
8353 * A character is lowercase if its general category type, provided
8354 * by {@link Character#getType getType(codePoint)}, is
8355 * {@code LOWERCASE_LETTER}, or it has contributory property
8356 * Other_Lowercase as defined by the Unicode Standard.
8357 * <p>
8358 * The following are examples of lowercase characters:
8359 * <blockquote><pre>
8360 * 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
8361 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
8362 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
8363 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
8364 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
8365 * </pre></blockquote>
8366 * <p> Many other Unicode characters are lowercase too.
8367 *
8368 * @param codePoint the character (Unicode code point) to be tested.
8369 * @return {@code true} if the character is lowercase;
8370 * {@code false} otherwise.
8371 * @see Character#isLowerCase(int)
8372 * @see Character#isTitleCase(int)
8373 * @see Character#toLowerCase(int)
8374 * @see Character#getType(int)
8375 * @since 1.5
8376 */
8377 public static boolean isLowerCase(int codePoint) {
8378 return getType(codePoint) == Character.LOWERCASE_LETTER ||
8379 CharacterData.of(codePoint).isOtherLowercase(codePoint);
8380 }
8381
8382 /**
8383 * Determines if the specified character is an uppercase character.
8384 * <p>
8385 * A character is uppercase if its general category type, provided by
8386 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
8387 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
8388 * <p>
8389 * The following are examples of uppercase characters:
8390 * <blockquote><pre>
8391 * 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
8392 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
8393 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
8394 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
8395 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
8396 * </pre></blockquote>
8397 * <p> Many other Unicode characters are uppercase too.
8398 *
8399 * <p><b>Note:</b> This method cannot handle <a
8400 * href="#supplementary"> supplementary characters</a>. To support
8401 * all Unicode characters, including supplementary characters, use
8402 * the {@link #isUpperCase(int)} method.
8403 *
8404 * @param ch the character to be tested.
8405 * @return {@code true} if the character is uppercase;
8406 * {@code false} otherwise.
8407 * @see Character#isLowerCase(char)
8408 * @see Character#isTitleCase(char)
8409 * @see Character#toUpperCase(char)
8410 * @see Character#getType(char)
8411 * @since 1.0
8412 */
8413 public static boolean isUpperCase(char ch) {
8414 return isUpperCase((int)ch);
8415 }
8416
8417 /**
8418 * Determines if the specified character (Unicode code point) is an uppercase character.
8419 * <p>
8420 * A character is uppercase if its general category type, provided by
8421 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
8422 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
8423 * <p>
8424 * The following are examples of uppercase characters:
8425 * <blockquote><pre>
8426 * 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
8427 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
8428 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
8429 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
8430 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
8431 * </pre></blockquote>
8432 * <p> Many other Unicode characters are uppercase too.
8433 *
8434 * @param codePoint the character (Unicode code point) to be tested.
8435 * @return {@code true} if the character is uppercase;
8436 * {@code false} otherwise.
8437 * @see Character#isLowerCase(int)
8438 * @see Character#isTitleCase(int)
8439 * @see Character#toUpperCase(int)
8440 * @see Character#getType(int)
8441 * @since 1.5
8442 */
8443 public static boolean isUpperCase(int codePoint) {
8444 return getType(codePoint) == Character.UPPERCASE_LETTER ||
8445 CharacterData.of(codePoint).isOtherUppercase(codePoint);
8446 }
8447
8448 /**
8449 * Determines if the specified character is a titlecase character.
8450 * <p>
8451 * A character is a titlecase character if its general
8452 * category type, provided by {@code Character.getType(ch)},
8453 * is {@code TITLECASE_LETTER}.
8454 * <p>
8455 * Some characters look like pairs of Latin letters. For example, there
8456 * is an uppercase letter that looks like "LJ" and has a corresponding
8457 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
8458 * is the appropriate form to use when rendering a word in lowercase
8459 * with initial capitals, as for a book title.
8460 * <p>
8461 * These are some of the Unicode characters for which this method returns
8462 * {@code true}:
8463 * <ul>
8464 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
8465 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
8466 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
8467 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
8468 * </ul>
8469 * <p> Many other Unicode characters are titlecase too.
8470 *
8471 * <p><b>Note:</b> This method cannot handle <a
8472 * href="#supplementary"> supplementary characters</a>. To support
8473 * all Unicode characters, including supplementary characters, use
8474 * the {@link #isTitleCase(int)} method.
8475 *
8476 * @param ch the character to be tested.
8477 * @return {@code true} if the character is titlecase;
8478 * {@code false} otherwise.
8479 * @see Character#isLowerCase(char)
8480 * @see Character#isUpperCase(char)
8481 * @see Character#toTitleCase(char)
8482 * @see Character#getType(char)
8483 * @since 1.0.2
8484 */
8485 public static boolean isTitleCase(char ch) {
8486 return isTitleCase((int)ch);
8487 }
8488
8489 /**
8490 * Determines if the specified character (Unicode code point) is a titlecase character.
8491 * <p>
8492 * A character is a titlecase character if its general
8493 * category type, provided by {@link Character#getType(int) getType(codePoint)},
8494 * is {@code TITLECASE_LETTER}.
8495 * <p>
8496 * Some characters look like pairs of Latin letters. For example, there
8497 * is an uppercase letter that looks like "LJ" and has a corresponding
8498 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
8499 * is the appropriate form to use when rendering a word in lowercase
8500 * with initial capitals, as for a book title.
8501 * <p>
8502 * These are some of the Unicode characters for which this method returns
8503 * {@code true}:
8504 * <ul>
8505 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
8506 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
8507 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
8508 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
8509 * </ul>
8510 * <p> Many other Unicode characters are titlecase too.
8511 *
8512 * @param codePoint the character (Unicode code point) to be tested.
8513 * @return {@code true} if the character is titlecase;
8514 * {@code false} otherwise.
8515 * @see Character#isLowerCase(int)
8516 * @see Character#isUpperCase(int)
8517 * @see Character#toTitleCase(int)
8518 * @see Character#getType(int)
8519 * @since 1.5
8520 */
8521 public static boolean isTitleCase(int codePoint) {
8522 return getType(codePoint) == Character.TITLECASE_LETTER;
8523 }
8524
8525 /**
8526 * Determines if the specified character is a digit.
8527 * <p>
8528 * A character is a digit if its general category type, provided
8529 * by {@code Character.getType(ch)}, is
8530 * {@code DECIMAL_DIGIT_NUMBER}.
8531 * <p>
8532 * Some Unicode character ranges that contain digits:
8533 * <ul>
8534 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
8535 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
8536 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
8537 * Arabic-Indic digits
8538 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
8539 * Extended Arabic-Indic digits
8540 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
8541 * Devanagari digits
8542 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
8543 * Fullwidth digits
8544 * </ul>
8545 *
8546 * Many other character ranges contain digits as well.
8547 *
8548 * <p><b>Note:</b> This method cannot handle <a
8549 * href="#supplementary"> supplementary characters</a>. To support
8550 * all Unicode characters, including supplementary characters, use
8551 * the {@link #isDigit(int)} method.
8552 *
8553 * @param ch the character to be tested.
8554 * @return {@code true} if the character is a digit;
8555 * {@code false} otherwise.
8556 * @see Character#digit(char, int)
8557 * @see Character#forDigit(int, int)
8558 * @see Character#getType(char)
8559 */
8560 public static boolean isDigit(char ch) {
8561 return isDigit((int)ch);
8562 }
8563
8564 /**
8565 * Determines if the specified character (Unicode code point) is a digit.
8566 * <p>
8567 * A character is a digit if its general category type, provided
8568 * by {@link Character#getType(int) getType(codePoint)}, is
8569 * {@code DECIMAL_DIGIT_NUMBER}.
8570 * <p>
8571 * Some Unicode character ranges that contain digits:
8572 * <ul>
8573 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
8574 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
8575 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
8576 * Arabic-Indic digits
8577 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
8578 * Extended Arabic-Indic digits
8579 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
8580 * Devanagari digits
8581 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
8582 * Fullwidth digits
8583 * </ul>
8584 *
8585 * Many other character ranges contain digits as well.
8586 *
8587 * @param codePoint the character (Unicode code point) to be tested.
8588 * @return {@code true} if the character is a digit;
8589 * {@code false} otherwise.
8590 * @see Character#forDigit(int, int)
8591 * @see Character#getType(int)
8592 * @since 1.5
8593 */
8594 public static boolean isDigit(int codePoint) {
8595 return getType(codePoint) == Character.DECIMAL_DIGIT_NUMBER;
8596 }
8597
8598 /**
8599 * Determines if a character is defined in Unicode.
8600 * <p>
8601 * A character is defined if at least one of the following is true:
8602 * <ul>
8603 * <li>It has an entry in the UnicodeData file.
8604 * <li>It has a value in a range defined by the UnicodeData file.
8605 * </ul>
8606 *
8607 * <p><b>Note:</b> This method cannot handle <a
8608 * href="#supplementary"> supplementary characters</a>. To support
8609 * all Unicode characters, including supplementary characters, use
8610 * the {@link #isDefined(int)} method.
8611 *
8612 * @param ch the character to be tested
8613 * @return {@code true} if the character has a defined meaning
8614 * in Unicode; {@code false} otherwise.
8615 * @see Character#isDigit(char)
8616 * @see Character#isLetter(char)
8617 * @see Character#isLetterOrDigit(char)
8618 * @see Character#isLowerCase(char)
8619 * @see Character#isTitleCase(char)
8620 * @see Character#isUpperCase(char)
8621 * @since 1.0.2
8622 */
8623 public static boolean isDefined(char ch) {
8624 return isDefined((int)ch);
8625 }
8626
8627 /**
8628 * Determines if a character (Unicode code point) is defined in Unicode.
8629 * <p>
8630 * A character is defined if at least one of the following is true:
8631 * <ul>
8632 * <li>It has an entry in the UnicodeData file.
8633 * <li>It has a value in a range defined by the UnicodeData file.
8634 * </ul>
8635 *
8636 * @param codePoint the character (Unicode code point) to be tested.
8637 * @return {@code true} if the character has a defined meaning
8638 * in Unicode; {@code false} otherwise.
8639 * @see Character#isDigit(int)
8640 * @see Character#isLetter(int)
8641 * @see Character#isLetterOrDigit(int)
8642 * @see Character#isLowerCase(int)
8643 * @see Character#isTitleCase(int)
8644 * @see Character#isUpperCase(int)
8645 * @since 1.5
8646 */
8647 public static boolean isDefined(int codePoint) {
8648 return getType(codePoint) != Character.UNASSIGNED;
8649 }
8650
8651 /**
8652 * Determines if the specified character is a letter.
8653 * <p>
8654 * A character is considered to be a letter if its general
8655 * category type, provided by {@code Character.getType(ch)},
8656 * is any of the following:
8657 * <ul>
8658 * <li> {@code UPPERCASE_LETTER}
8659 * <li> {@code LOWERCASE_LETTER}
8660 * <li> {@code TITLECASE_LETTER}
8661 * <li> {@code MODIFIER_LETTER}
8662 * <li> {@code OTHER_LETTER}
8663 * </ul>
8664 *
8665 * Not all letters have case. Many characters are
8666 * letters but are neither uppercase nor lowercase nor titlecase.
8667 *
8668 * <p><b>Note:</b> This method cannot handle <a
8669 * href="#supplementary"> supplementary characters</a>. To support
8670 * all Unicode characters, including supplementary characters, use
8671 * the {@link #isLetter(int)} method.
8672 *
8673 * @param ch the character to be tested.
8674 * @return {@code true} if the character is a letter;
8675 * {@code false} otherwise.
8676 * @see Character#isDigit(char)
8677 * @see Character#isJavaIdentifierStart(char)
8678 * @see Character#isJavaLetter(char)
8679 * @see Character#isJavaLetterOrDigit(char)
8680 * @see Character#isLetterOrDigit(char)
8681 * @see Character#isLowerCase(char)
8682 * @see Character#isTitleCase(char)
8683 * @see Character#isUnicodeIdentifierStart(char)
8684 * @see Character#isUpperCase(char)
8685 */
8686 public static boolean isLetter(char ch) {
8687 return isLetter((int)ch);
8688 }
8689
8690 /**
8691 * Determines if the specified character (Unicode code point) is a letter.
8692 * <p>
8693 * A character is considered to be a letter if its general
8694 * category type, provided by {@link Character#getType(int) getType(codePoint)},
8695 * is any of the following:
8696 * <ul>
8697 * <li> {@code UPPERCASE_LETTER}
8698 * <li> {@code LOWERCASE_LETTER}
8699 * <li> {@code TITLECASE_LETTER}
8700 * <li> {@code MODIFIER_LETTER}
8701 * <li> {@code OTHER_LETTER}
8702 * </ul>
8703 *
8704 * Not all letters have case. Many characters are
8705 * letters but are neither uppercase nor lowercase nor titlecase.
8706 *
8707 * @param codePoint the character (Unicode code point) to be tested.
8708 * @return {@code true} if the character is a letter;
8709 * {@code false} otherwise.
8710 * @see Character#isDigit(int)
8711 * @see Character#isJavaIdentifierStart(int)
8712 * @see Character#isLetterOrDigit(int)
8713 * @see Character#isLowerCase(int)
8714 * @see Character#isTitleCase(int)
8715 * @see Character#isUnicodeIdentifierStart(int)
8716 * @see Character#isUpperCase(int)
8717 * @since 1.5
8718 */
8719 public static boolean isLetter(int codePoint) {
8720 return ((((1 << Character.UPPERCASE_LETTER) |
8721 (1 << Character.LOWERCASE_LETTER) |
8722 (1 << Character.TITLECASE_LETTER) |
8723 (1 << Character.MODIFIER_LETTER) |
8724 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
8725 != 0;
8726 }
8727
8728 /**
8729 * Determines if the specified character is a letter or digit.
8730 * <p>
8731 * A character is considered to be a letter or digit if either
8732 * {@code Character.isLetter(char ch)} or
8733 * {@code Character.isDigit(char ch)} returns
8734 * {@code true} for the character.
8735 *
8736 * <p><b>Note:</b> This method cannot handle <a
8737 * href="#supplementary"> supplementary characters</a>. To support
8738 * all Unicode characters, including supplementary characters, use
8739 * the {@link #isLetterOrDigit(int)} method.
8740 *
8741 * @param ch the character to be tested.
8742 * @return {@code true} if the character is a letter or digit;
8743 * {@code false} otherwise.
8744 * @see Character#isDigit(char)
8745 * @see Character#isJavaIdentifierPart(char)
8746 * @see Character#isJavaLetter(char)
8747 * @see Character#isJavaLetterOrDigit(char)
8748 * @see Character#isLetter(char)
8749 * @see Character#isUnicodeIdentifierPart(char)
8750 * @since 1.0.2
8751 */
8752 public static boolean isLetterOrDigit(char ch) {
8753 return isLetterOrDigit((int)ch);
8754 }
8755
8756 /**
8757 * Determines if the specified character (Unicode code point) is a letter or digit.
8758 * <p>
8759 * A character is considered to be a letter or digit if either
8760 * {@link #isLetter(int) isLetter(codePoint)} or
8761 * {@link #isDigit(int) isDigit(codePoint)} returns
8762 * {@code true} for the character.
8763 *
8764 * @param codePoint the character (Unicode code point) to be tested.
8765 * @return {@code true} if the character is a letter or digit;
8766 * {@code false} otherwise.
8767 * @see Character#isDigit(int)
8768 * @see Character#isJavaIdentifierPart(int)
8769 * @see Character#isLetter(int)
8770 * @see Character#isUnicodeIdentifierPart(int)
8771 * @since 1.5
8772 */
8773 public static boolean isLetterOrDigit(int codePoint) {
8774 return ((((1 << Character.UPPERCASE_LETTER) |
8775 (1 << Character.LOWERCASE_LETTER) |
8776 (1 << Character.TITLECASE_LETTER) |
8777 (1 << Character.MODIFIER_LETTER) |
8778 (1 << Character.OTHER_LETTER) |
8779 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
8780 != 0;
8781 }
8782
8783 /**
8784 * Determines if the specified character is permissible as the first
8785 * character in a Java identifier.
8786 * <p>
8787 * A character may start a Java identifier if and only if
8788 * one of the following is true:
8789 * <ul>
8790 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
8791 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
8792 * <li> {@code ch} is a currency symbol (such as {@code '$'})
8793 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
8794 * </ul>
8795 *
8796 * @param ch the character to be tested.
8797 * @return {@code true} if the character may start a Java
8798 * identifier; {@code false} otherwise.
8799 * @see Character#isJavaLetterOrDigit(char)
8800 * @see Character#isJavaIdentifierStart(char)
8801 * @see Character#isJavaIdentifierPart(char)
8802 * @see Character#isLetter(char)
8803 * @see Character#isLetterOrDigit(char)
8804 * @see Character#isUnicodeIdentifierStart(char)
8805 * @since 1.0.2
8806 * @deprecated Replaced by isJavaIdentifierStart(char).
8807 */
8808 @Deprecated
8809 public static boolean isJavaLetter(char ch) {
8810 return isJavaIdentifierStart(ch);
8811 }
8812
8813 /**
8814 * Determines if the specified character may be part of a Java
8815 * identifier as other than the first character.
8816 * <p>
8817 * A character may be part of a Java identifier if and only if any
8818 * of the following are true:
8819 * <ul>
8820 * <li> it is a letter
8821 * <li> it is a currency symbol (such as {@code '$'})
8822 * <li> it is a connecting punctuation character (such as {@code '_'})
8823 * <li> it is a digit
8824 * <li> it is a numeric letter (such as a Roman numeral character)
8825 * <li> it is a combining mark
8826 * <li> it is a non-spacing mark
8827 * <li> {@code isIdentifierIgnorable} returns
8828 * {@code true} for the character.
8829 * </ul>
8830 *
8831 * @param ch the character to be tested.
8832 * @return {@code true} if the character may be part of a
8833 * Java identifier; {@code false} otherwise.
8834 * @see Character#isJavaLetter(char)
8835 * @see Character#isJavaIdentifierStart(char)
8836 * @see Character#isJavaIdentifierPart(char)
8837 * @see Character#isLetter(char)
8838 * @see Character#isLetterOrDigit(char)
8839 * @see Character#isUnicodeIdentifierPart(char)
8840 * @see Character#isIdentifierIgnorable(char)
8841 * @since 1.0.2
8842 * @deprecated Replaced by isJavaIdentifierPart(char).
8843 */
8844 @Deprecated
8845 public static boolean isJavaLetterOrDigit(char ch) {
8846 return isJavaIdentifierPart(ch);
8847 }
8848
8849 /**
8850 * Determines if the specified character (Unicode code point) is an alphabet.
8851 * <p>
8852 * A character is considered to be alphabetic if its general category type,
8853 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
8854 * the following:
8855 * <ul>
8856 * <li> <code>UPPERCASE_LETTER</code>
8857 * <li> <code>LOWERCASE_LETTER</code>
8858 * <li> <code>TITLECASE_LETTER</code>
8859 * <li> <code>MODIFIER_LETTER</code>
8860 * <li> <code>OTHER_LETTER</code>
8861 * <li> <code>LETTER_NUMBER</code>
8862 * </ul>
8863 * or it has contributory property Other_Alphabetic as defined by the
8864 * Unicode Standard.
8865 *
8866 * @param codePoint the character (Unicode code point) to be tested.
8867 * @return <code>true</code> if the character is a Unicode alphabet
8868 * character, <code>false</code> otherwise.
8869 * @since 1.7
8870 */
8871 public static boolean isAlphabetic(int codePoint) {
8872 return (((((1 << Character.UPPERCASE_LETTER) |
8873 (1 << Character.LOWERCASE_LETTER) |
8874 (1 << Character.TITLECASE_LETTER) |
8875 (1 << Character.MODIFIER_LETTER) |
8876 (1 << Character.OTHER_LETTER) |
8877 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
8878 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
8879 }
8880
8881 /**
8882 * Determines if the specified character (Unicode code point) is a CJKV
8883 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
8884 * the Unicode Standard.
8885 *
8886 * @param codePoint the character (Unicode code point) to be tested.
8887 * @return <code>true</code> if the character is a Unicode ideograph
8888 * character, <code>false</code> otherwise.
8889 * @since 1.7
8890 */
8891 public static boolean isIdeographic(int codePoint) {
8892 return CharacterData.of(codePoint).isIdeographic(codePoint);
8893 }
8894
8895 /**
8896 * Determines if the specified character is
8897 * permissible as the first character in a Java identifier.
8898 * <p>
8899 * A character may start a Java identifier if and only if
8900 * one of the following conditions is true:
8901 * <ul>
8902 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
8903 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
8904 * <li> {@code ch} is a currency symbol (such as {@code '$'})
8905 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
8906 * </ul>
8907 *
8908 * <p><b>Note:</b> This method cannot handle <a
8909 * href="#supplementary"> supplementary characters</a>. To support
8910 * all Unicode characters, including supplementary characters, use
8911 * the {@link #isJavaIdentifierStart(int)} method.
8912 *
8913 * @param ch the character to be tested.
8914 * @return {@code true} if the character may start a Java identifier;
8915 * {@code false} otherwise.
8916 * @see Character#isJavaIdentifierPart(char)
8917 * @see Character#isLetter(char)
8918 * @see Character#isUnicodeIdentifierStart(char)
8919 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
8920 * @since 1.1
8921 */
8922 public static boolean isJavaIdentifierStart(char ch) {
8923 return isJavaIdentifierStart((int)ch);
8924 }
8925
8926 /**
8927 * Determines if the character (Unicode code point) is
8928 * permissible as the first character in a Java identifier.
8929 * <p>
8930 * A character may start a Java identifier if and only if
8931 * one of the following conditions is true:
8932 * <ul>
8933 * <li> {@link #isLetter(int) isLetter(codePoint)}
8934 * returns {@code true}
8935 * <li> {@link #getType(int) getType(codePoint)}
8936 * returns {@code LETTER_NUMBER}
8937 * <li> the referenced character is a currency symbol (such as {@code '$'})
8938 * <li> the referenced character is a connecting punctuation character
8939 * (such as {@code '_'}).
8940 * </ul>
8941 *
8942 * @param codePoint the character (Unicode code point) to be tested.
8943 * @return {@code true} if the character may start a Java identifier;
8944 * {@code false} otherwise.
8945 * @see Character#isJavaIdentifierPart(int)
8946 * @see Character#isLetter(int)
8947 * @see Character#isUnicodeIdentifierStart(int)
8948 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
8949 * @since 1.5
8950 */
8951 public static boolean isJavaIdentifierStart(int codePoint) {
8952 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
8953 }
8954
8955 /**
8956 * Determines if the specified character may be part of a Java
8957 * identifier as other than the first character.
8958 * <p>
8959 * A character may be part of a Java identifier if any of the following
8960 * are true:
8961 * <ul>
8962 * <li> it is a letter
8963 * <li> it is a currency symbol (such as {@code '$'})
8964 * <li> it is a connecting punctuation character (such as {@code '_'})
8965 * <li> it is a digit
8966 * <li> it is a numeric letter (such as a Roman numeral character)
8967 * <li> it is a combining mark
8968 * <li> it is a non-spacing mark
8969 * <li> {@code isIdentifierIgnorable} returns
8970 * {@code true} for the character
8971 * </ul>
8972 *
8973 * <p><b>Note:</b> This method cannot handle <a
8974 * href="#supplementary"> supplementary characters</a>. To support
8975 * all Unicode characters, including supplementary characters, use
8976 * the {@link #isJavaIdentifierPart(int)} method.
8977 *
8978 * @param ch the character to be tested.
8979 * @return {@code true} if the character may be part of a
8980 * Java identifier; {@code false} otherwise.
8981 * @see Character#isIdentifierIgnorable(char)
8982 * @see Character#isJavaIdentifierStart(char)
8983 * @see Character#isLetterOrDigit(char)
8984 * @see Character#isUnicodeIdentifierPart(char)
8985 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
8986 * @since 1.1
8987 */
8988 public static boolean isJavaIdentifierPart(char ch) {
8989 return isJavaIdentifierPart((int)ch);
8990 }
8991
8992 /**
8993 * Determines if the character (Unicode code point) may be part of a Java
8994 * identifier as other than the first character.
8995 * <p>
8996 * A character may be part of a Java identifier if any of the following
8997 * are true:
8998 * <ul>
8999 * <li> it is a letter
9000 * <li> it is a currency symbol (such as {@code '$'})
9001 * <li> it is a connecting punctuation character (such as {@code '_'})
9002 * <li> it is a digit
9003 * <li> it is a numeric letter (such as a Roman numeral character)
9004 * <li> it is a combining mark
9005 * <li> it is a non-spacing mark
9006 * <li> {@link #isIdentifierIgnorable(int)
9007 * isIdentifierIgnorable(codePoint)} returns {@code true} for
9008 * the character
9009 * </ul>
9010 *
9011 * @param codePoint the character (Unicode code point) to be tested.
9012 * @return {@code true} if the character may be part of a
9013 * Java identifier; {@code false} otherwise.
9014 * @see Character#isIdentifierIgnorable(int)
9015 * @see Character#isJavaIdentifierStart(int)
9016 * @see Character#isLetterOrDigit(int)
9017 * @see Character#isUnicodeIdentifierPart(int)
9018 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
9019 * @since 1.5
9020 */
9021 public static boolean isJavaIdentifierPart(int codePoint) {
9022 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
9023 }
9024
9025 /**
9026 * Determines if the specified character is permissible as the
9027 * first character in a Unicode identifier.
9028 * <p>
9029 * A character may start a Unicode identifier if and only if
9030 * one of the following conditions is true:
9031 * <ul>
9032 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
9033 * <li> {@link #getType(char) getType(ch)} returns
9034 * {@code LETTER_NUMBER}.
9035 * </ul>
9036 *
9037 * <p><b>Note:</b> This method cannot handle <a
9038 * href="#supplementary"> supplementary characters</a>. To support
9039 * all Unicode characters, including supplementary characters, use
9040 * the {@link #isUnicodeIdentifierStart(int)} method.
9041 *
9042 * @param ch the character to be tested.
9043 * @return {@code true} if the character may start a Unicode
9044 * identifier; {@code false} otherwise.
9045 * @see Character#isJavaIdentifierStart(char)
9046 * @see Character#isLetter(char)
9047 * @see Character#isUnicodeIdentifierPart(char)
9048 * @since 1.1
9049 */
9050 public static boolean isUnicodeIdentifierStart(char ch) {
9051 return isUnicodeIdentifierStart((int)ch);
9052 }
9053
9054 /**
9055 * Determines if the specified character (Unicode code point) is permissible as the
9056 * first character in a Unicode identifier.
9057 * <p>
9058 * A character may start a Unicode identifier if and only if
9059 * one of the following conditions is true:
9060 * <ul>
9061 * <li> {@link #isLetter(int) isLetter(codePoint)}
9062 * returns {@code true}
9063 * <li> {@link #getType(int) getType(codePoint)}
9064 * returns {@code LETTER_NUMBER}.
9065 * </ul>
9066 * @param codePoint the character (Unicode code point) to be tested.
9067 * @return {@code true} if the character may start a Unicode
9068 * identifier; {@code false} otherwise.
9069 * @see Character#isJavaIdentifierStart(int)
9070 * @see Character#isLetter(int)
9071 * @see Character#isUnicodeIdentifierPart(int)
9072 * @since 1.5
9073 */
9074 public static boolean isUnicodeIdentifierStart(int codePoint) {
9075 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
9076 }
9077
9078 /**
9079 * Determines if the specified character may be part of a Unicode
9080 * identifier as other than the first character.
9081 * <p>
9082 * A character may be part of a Unicode identifier if and only if
9083 * one of the following statements is true:
9084 * <ul>
9085 * <li> it is a letter
9086 * <li> it is a connecting punctuation character (such as {@code '_'})
9087 * <li> it is a digit
9088 * <li> it is a numeric letter (such as a Roman numeral character)
9089 * <li> it is a combining mark
9090 * <li> it is a non-spacing mark
9091 * <li> {@code isIdentifierIgnorable} returns
9092 * {@code true} for this character.
9093 * </ul>
9094 *
9095 * <p><b>Note:</b> This method cannot handle <a
9096 * href="#supplementary"> supplementary characters</a>. To support
9097 * all Unicode characters, including supplementary characters, use
9098 * the {@link #isUnicodeIdentifierPart(int)} method.
9099 *
9100 * @param ch the character to be tested.
9101 * @return {@code true} if the character may be part of a
9102 * Unicode identifier; {@code false} otherwise.
9103 * @see Character#isIdentifierIgnorable(char)
9104 * @see Character#isJavaIdentifierPart(char)
9105 * @see Character#isLetterOrDigit(char)
9106 * @see Character#isUnicodeIdentifierStart(char)
9107 * @since 1.1
9108 */
9109 public static boolean isUnicodeIdentifierPart(char ch) {
9110 return isUnicodeIdentifierPart((int)ch);
9111 }
9112
9113 /**
9114 * Determines if the specified character (Unicode code point) may be part of a Unicode
9115 * identifier as other than the first character.
9116 * <p>
9117 * A character may be part of a Unicode identifier if and only if
9118 * one of the following statements is true:
9119 * <ul>
9120 * <li> it is a letter
9121 * <li> it is a connecting punctuation character (such as {@code '_'})
9122 * <li> it is a digit
9123 * <li> it is a numeric letter (such as a Roman numeral character)
9124 * <li> it is a combining mark
9125 * <li> it is a non-spacing mark
9126 * <li> {@code isIdentifierIgnorable} returns
9127 * {@code true} for this character.
9128 * </ul>
9129 * @param codePoint the character (Unicode code point) to be tested.
9130 * @return {@code true} if the character may be part of a
9131 * Unicode identifier; {@code false} otherwise.
9132 * @see Character#isIdentifierIgnorable(int)
9133 * @see Character#isJavaIdentifierPart(int)
9134 * @see Character#isLetterOrDigit(int)
9135 * @see Character#isUnicodeIdentifierStart(int)
9136 * @since 1.5
9137 */
9138 public static boolean isUnicodeIdentifierPart(int codePoint) {
9139 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
9140 }
9141
9142 /**
9143 * Determines if the specified character should be regarded as
9144 * an ignorable character in a Java identifier or a Unicode identifier.
9145 * <p>
9146 * The following Unicode characters are ignorable in a Java identifier
9147 * or a Unicode identifier:
9148 * <ul>
9149 * <li>ISO control characters that are not whitespace
9150 * <ul>
9151 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9152 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9153 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9154 * </ul>
9155 *
9156 * <li>all characters that have the {@code FORMAT} general
9157 * category value
9158 * </ul>
9159 *
9160 * <p><b>Note:</b> This method cannot handle <a
9161 * href="#supplementary"> supplementary characters</a>. To support
9162 * all Unicode characters, including supplementary characters, use
9163 * the {@link #isIdentifierIgnorable(int)} method.
9164 *
9165 * @param ch the character to be tested.
9166 * @return {@code true} if the character is an ignorable control
9167 * character that may be part of a Java or Unicode identifier;
9168 * {@code false} otherwise.
9169 * @see Character#isJavaIdentifierPart(char)
9170 * @see Character#isUnicodeIdentifierPart(char)
9171 * @since 1.1
9172 */
9173 public static boolean isIdentifierIgnorable(char ch) {
9174 return isIdentifierIgnorable((int)ch);
9175 }
9176
9177 /**
9178 * Determines if the specified character (Unicode code point) should be regarded as
9179 * an ignorable character in a Java identifier or a Unicode identifier.
9180 * <p>
9181 * The following Unicode characters are ignorable in a Java identifier
9182 * or a Unicode identifier:
9183 * <ul>
9184 * <li>ISO control characters that are not whitespace
9185 * <ul>
9186 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
9187 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
9188 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
9189 * </ul>
9190 *
9191 * <li>all characters that have the {@code FORMAT} general
9192 * category value
9193 * </ul>
9194 *
9195 * @param codePoint the character (Unicode code point) to be tested.
9196 * @return {@code true} if the character is an ignorable control
9197 * character that may be part of a Java or Unicode identifier;
9198 * {@code false} otherwise.
9199 * @see Character#isJavaIdentifierPart(int)
9200 * @see Character#isUnicodeIdentifierPart(int)
9201 * @since 1.5
9202 */
9203 public static boolean isIdentifierIgnorable(int codePoint) {
9204 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
9205 }
9206
9207 /**
9208 * Converts the character argument to lowercase using case
9209 * mapping information from the UnicodeData file.
9210 * <p>
9211 * Note that
9212 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
9213 * does not always return {@code true} for some ranges of
9214 * characters, particularly those that are symbols or ideographs.
9215 *
9216 * <p>In general, {@link String#toLowerCase()} should be used to map
9217 * characters to lowercase. {@code String} case mapping methods
9218 * have several benefits over {@code Character} case mapping methods.
9219 * {@code String} case mapping methods can perform locale-sensitive
9220 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9221 * the {@code Character} case mapping methods cannot.
9222 *
9223 * <p><b>Note:</b> This method cannot handle <a
9224 * href="#supplementary"> supplementary characters</a>. To support
9225 * all Unicode characters, including supplementary characters, use
9226 * the {@link #toLowerCase(int)} method.
9227 *
9228 * @param ch the character to be converted.
9229 * @return the lowercase equivalent of the character, if any;
9230 * otherwise, the character itself.
9231 * @see Character#isLowerCase(char)
9232 * @see String#toLowerCase()
9233 */
9234 public static char toLowerCase(char ch) {
9235 return (char)toLowerCase((int)ch);
9236 }
9237
9238 /**
9239 * Converts the character (Unicode code point) argument to
9240 * lowercase using case mapping information from the UnicodeData
9241 * file.
9242 *
9243 * <p> Note that
9244 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
9245 * does not always return {@code true} for some ranges of
9246 * characters, particularly those that are symbols or ideographs.
9247 *
9248 * <p>In general, {@link String#toLowerCase()} should be used to map
9249 * characters to lowercase. {@code String} case mapping methods
9250 * have several benefits over {@code Character} case mapping methods.
9251 * {@code String} case mapping methods can perform locale-sensitive
9252 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9253 * the {@code Character} case mapping methods cannot.
9254 *
9255 * @param codePoint the character (Unicode code point) to be converted.
9256 * @return the lowercase equivalent of the character (Unicode code
9257 * point), if any; otherwise, the character itself.
9258 * @see Character#isLowerCase(int)
9259 * @see String#toLowerCase()
9260 *
9261 * @since 1.5
9262 */
9263 public static int toLowerCase(int codePoint) {
9264 return CharacterData.of(codePoint).toLowerCase(codePoint);
9265 }
9266
9267 /**
9268 * Converts the character argument to uppercase using case mapping
9269 * information from the UnicodeData file.
9270 * <p>
9271 * Note that
9272 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
9273 * does not always return {@code true} for some ranges of
9274 * characters, particularly those that are symbols or ideographs.
9275 *
9276 * <p>In general, {@link String#toUpperCase()} should be used to map
9277 * characters to uppercase. {@code String} case mapping methods
9278 * have several benefits over {@code Character} case mapping methods.
9279 * {@code String} case mapping methods can perform locale-sensitive
9280 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9281 * the {@code Character} case mapping methods cannot.
9282 *
9283 * <p><b>Note:</b> This method cannot handle <a
9284 * href="#supplementary"> supplementary characters</a>. To support
9285 * all Unicode characters, including supplementary characters, use
9286 * the {@link #toUpperCase(int)} method.
9287 *
9288 * @param ch the character to be converted.
9289 * @return the uppercase equivalent of the character, if any;
9290 * otherwise, the character itself.
9291 * @see Character#isUpperCase(char)
9292 * @see String#toUpperCase()
9293 */
9294 public static char toUpperCase(char ch) {
9295 return (char)toUpperCase((int)ch);
9296 }
9297
9298 /**
9299 * Converts the character (Unicode code point) argument to
9300 * uppercase using case mapping information from the UnicodeData
9301 * file.
9302 *
9303 * <p>Note that
9304 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
9305 * does not always return {@code true} for some ranges of
9306 * characters, particularly those that are symbols or ideographs.
9307 *
9308 * <p>In general, {@link String#toUpperCase()} should be used to map
9309 * characters to uppercase. {@code String} case mapping methods
9310 * have several benefits over {@code Character} case mapping methods.
9311 * {@code String} case mapping methods can perform locale-sensitive
9312 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
9313 * the {@code Character} case mapping methods cannot.
9314 *
9315 * @param codePoint the character (Unicode code point) to be converted.
9316 * @return the uppercase equivalent of the character, if any;
9317 * otherwise, the character itself.
9318 * @see Character#isUpperCase(int)
9319 * @see String#toUpperCase()
9320 *
9321 * @since 1.5
9322 */
9323 public static int toUpperCase(int codePoint) {
9324 return CharacterData.of(codePoint).toUpperCase(codePoint);
9325 }
9326
9327 /**
9328 * Converts the character argument to titlecase using case mapping
9329 * information from the UnicodeData file. If a character has no
9330 * explicit titlecase mapping and is not itself a titlecase char
9331 * according to UnicodeData, then the uppercase mapping is
9332 * returned as an equivalent titlecase mapping. If the
9333 * {@code char} argument is already a titlecase
9334 * {@code char}, the same {@code char} value will be
9335 * returned.
9336 * <p>
9337 * Note that
9338 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
9339 * does not always return {@code true} for some ranges of
9340 * characters.
9341 *
9342 * <p><b>Note:</b> This method cannot handle <a
9343 * href="#supplementary"> supplementary characters</a>. To support
9344 * all Unicode characters, including supplementary characters, use
9345 * the {@link #toTitleCase(int)} method.
9346 *
9347 * @param ch the character to be converted.
9348 * @return the titlecase equivalent of the character, if any;
9349 * otherwise, the character itself.
9350 * @see Character#isTitleCase(char)
9351 * @see Character#toLowerCase(char)
9352 * @see Character#toUpperCase(char)
9353 * @since 1.0.2
9354 */
9355 public static char toTitleCase(char ch) {
9356 return (char)toTitleCase((int)ch);
9357 }
9358
9359 /**
9360 * Converts the character (Unicode code point) argument to titlecase using case mapping
9361 * information from the UnicodeData file. If a character has no
9362 * explicit titlecase mapping and is not itself a titlecase char
9363 * according to UnicodeData, then the uppercase mapping is
9364 * returned as an equivalent titlecase mapping. If the
9365 * character argument is already a titlecase
9366 * character, the same character value will be
9367 * returned.
9368 *
9369 * <p>Note that
9370 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
9371 * does not always return {@code true} for some ranges of
9372 * characters.
9373 *
9374 * @param codePoint the character (Unicode code point) to be converted.
9375 * @return the titlecase equivalent of the character, if any;
9376 * otherwise, the character itself.
9377 * @see Character#isTitleCase(int)
9378 * @see Character#toLowerCase(int)
9379 * @see Character#toUpperCase(int)
9380 * @since 1.5
9381 */
9382 public static int toTitleCase(int codePoint) {
9383 return CharacterData.of(codePoint).toTitleCase(codePoint);
9384 }
9385
9386 /**
9387 * Returns the numeric value of the character {@code ch} in the
9388 * specified radix.
9389 * <p>
9390 * If the radix is not in the range {@code MIN_RADIX} ≤
9391 * {@code radix} ≤ {@code MAX_RADIX} or if the
9392 * value of {@code ch} is not a valid digit in the specified
9393 * radix, {@code -1} is returned. A character is a valid digit
9394 * if at least one of the following is true:
9395 * <ul>
9396 * <li>The method {@code isDigit} is {@code true} of the character
9397 * and the Unicode decimal digit value of the character (or its
9398 * single-character decomposition) is less than the specified radix.
9399 * In this case the decimal digit value is returned.
9400 * <li>The character is one of the uppercase Latin letters
9401 * {@code 'A'} through {@code 'Z'} and its code is less than
9402 * {@code radix + 'A' - 10}.
9403 * In this case, {@code ch - 'A' + 10}
9404 * is returned.
9405 * <li>The character is one of the lowercase Latin letters
9406 * {@code 'a'} through {@code 'z'} and its code is less than
9407 * {@code radix + 'a' - 10}.
9408 * In this case, {@code ch - 'a' + 10}
9409 * is returned.
9410 * <li>The character is one of the fullwidth uppercase Latin letters A
9411 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
9412 * and its code is less than
9413 * {@code radix + '\u005CuFF21' - 10}.
9414 * In this case, {@code ch - '\u005CuFF21' + 10}
9415 * is returned.
9416 * <li>The character is one of the fullwidth lowercase Latin letters a
9417 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
9418 * and its code is less than
9419 * {@code radix + '\u005CuFF41' - 10}.
9420 * In this case, {@code ch - '\u005CuFF41' + 10}
9421 * is returned.
9422 * </ul>
9423 *
9424 * <p><b>Note:</b> This method cannot handle <a
9425 * href="#supplementary"> supplementary characters</a>. To support
9426 * all Unicode characters, including supplementary characters, use
9427 * the {@link #digit(int, int)} method.
9428 *
9429 * @param ch the character to be converted.
9430 * @param radix the radix.
9431 * @return the numeric value represented by the character in the
9432 * specified radix.
9433 * @see Character#forDigit(int, int)
9434 * @see Character#isDigit(char)
9435 */
9436 public static int digit(char ch, int radix) {
9437 return digit((int)ch, radix);
9438 }
9439
9440 /**
9441 * Returns the numeric value of the specified character (Unicode
9442 * code point) in the specified radix.
9443 *
9444 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
9445 * {@code radix} ≤ {@code MAX_RADIX} or if the
9446 * character is not a valid digit in the specified
9447 * radix, {@code -1} is returned. A character is a valid digit
9448 * if at least one of the following is true:
9449 * <ul>
9450 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
9451 * and the Unicode decimal digit value of the character (or its
9452 * single-character decomposition) is less than the specified radix.
9453 * In this case the decimal digit value is returned.
9454 * <li>The character is one of the uppercase Latin letters
9455 * {@code 'A'} through {@code 'Z'} and its code is less than
9456 * {@code radix + 'A' - 10}.
9457 * In this case, {@code codePoint - 'A' + 10}
9458 * is returned.
9459 * <li>The character is one of the lowercase Latin letters
9460 * {@code 'a'} through {@code 'z'} and its code is less than
9461 * {@code radix + 'a' - 10}.
9462 * In this case, {@code codePoint - 'a' + 10}
9463 * is returned.
9464 * <li>The character is one of the fullwidth uppercase Latin letters A
9465 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
9466 * and its code is less than
9467 * {@code radix + '\u005CuFF21' - 10}.
9468 * In this case,
9469 * {@code codePoint - '\u005CuFF21' + 10}
9470 * is returned.
9471 * <li>The character is one of the fullwidth lowercase Latin letters a
9472 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
9473 * and its code is less than
9474 * {@code radix + '\u005CuFF41'- 10}.
9475 * In this case,
9476 * {@code codePoint - '\u005CuFF41' + 10}
9477 * is returned.
9478 * </ul>
9479 *
9480 * @param codePoint the character (Unicode code point) to be converted.
9481 * @param radix the radix.
9482 * @return the numeric value represented by the character in the
9483 * specified radix.
9484 * @see Character#forDigit(int, int)
9485 * @see Character#isDigit(int)
9486 * @since 1.5
9487 */
9488 public static int digit(int codePoint, int radix) {
9489 return CharacterData.of(codePoint).digit(codePoint, radix);
9490 }
9491
9492 /**
9493 * Returns the {@code int} value that the specified Unicode
9494 * character represents. For example, the character
9495 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
9496 * an int with a value of 50.
9497 * <p>
9498 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
9499 * {@code '\u005Cu005A'}), lowercase
9500 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
9501 * full width variant ({@code '\u005CuFF21'} through
9502 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
9503 * {@code '\u005CuFF5A'}) forms have numeric values from 10
9504 * through 35. This is independent of the Unicode specification,
9505 * which does not assign numeric values to these {@code char}
9506 * values.
9507 * <p>
9508 * If the character does not have a numeric value, then -1 is returned.
9509 * If the character has a numeric value that cannot be represented as a
9510 * nonnegative integer (for example, a fractional value), then -2
9511 * is returned.
9512 *
9513 * <p><b>Note:</b> This method cannot handle <a
9514 * href="#supplementary"> supplementary characters</a>. To support
9515 * all Unicode characters, including supplementary characters, use
9516 * the {@link #getNumericValue(int)} method.
9517 *
9518 * @param ch the character to be converted.
9519 * @return the numeric value of the character, as a nonnegative {@code int}
9520 * value; -2 if the character has a numeric value but the value
9521 * can not be represented as a nonnegative {@code int} value;
9522 * -1 if the character has no numeric value.
9523 * @see Character#forDigit(int, int)
9524 * @see Character#isDigit(char)
9525 * @since 1.1
9526 */
9527 public static int getNumericValue(char ch) {
9528 return getNumericValue((int)ch);
9529 }
9530
9531 /**
9532 * Returns the {@code int} value that the specified
9533 * character (Unicode code point) represents. For example, the character
9534 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
9535 * an {@code int} with a value of 50.
9536 * <p>
9537 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
9538 * {@code '\u005Cu005A'}), lowercase
9539 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
9540 * full width variant ({@code '\u005CuFF21'} through
9541 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
9542 * {@code '\u005CuFF5A'}) forms have numeric values from 10
9543 * through 35. This is independent of the Unicode specification,
9544 * which does not assign numeric values to these {@code char}
9545 * values.
9546 * <p>
9547 * If the character does not have a numeric value, then -1 is returned.
9548 * If the character has a numeric value that cannot be represented as a
9549 * nonnegative integer (for example, a fractional value), then -2
9550 * is returned.
9551 *
9552 * @param codePoint the character (Unicode code point) to be converted.
9553 * @return the numeric value of the character, as a nonnegative {@code int}
9554 * value; -2 if the character has a numeric value but the value
9555 * can not be represented as a nonnegative {@code int} value;
9556 * -1 if the character has no numeric value.
9557 * @see Character#forDigit(int, int)
9558 * @see Character#isDigit(int)
9559 * @since 1.5
9560 */
9561 public static int getNumericValue(int codePoint) {
9562 return CharacterData.of(codePoint).getNumericValue(codePoint);
9563 }
9564
9565 /**
9566 * Determines if the specified character is ISO-LATIN-1 white space.
9567 * This method returns {@code true} for the following five
9568 * characters only:
9569 * <table summary="truechars">
9570 * <tr><td>{@code '\t'}</td> <td>{@code U+0009}</td>
9571 * <td>{@code HORIZONTAL TABULATION}</td></tr>
9572 * <tr><td>{@code '\n'}</td> <td>{@code U+000A}</td>
9573 * <td>{@code NEW LINE}</td></tr>
9574 * <tr><td>{@code '\f'}</td> <td>{@code U+000C}</td>
9575 * <td>{@code FORM FEED}</td></tr>
9576 * <tr><td>{@code '\r'}</td> <td>{@code U+000D}</td>
9577 * <td>{@code CARRIAGE RETURN}</td></tr>
9578 * <tr><td>{@code ' '}</td> <td>{@code U+0020}</td>
9579 * <td>{@code SPACE}</td></tr>
9580 * </table>
9581 *
9582 * @param ch the character to be tested.
9583 * @return {@code true} if the character is ISO-LATIN-1 white
9584 * space; {@code false} otherwise.
9585 * @see Character#isSpaceChar(char)
9586 * @see Character#isWhitespace(char)
9587 * @deprecated Replaced by isWhitespace(char).
9588 */
9589 @Deprecated
9590 public static boolean isSpace(char ch) {
9591 return (ch <= 0x0020) &&
9592 (((((1L << 0x0009) |
9593 (1L << 0x000A) |
9594 (1L << 0x000C) |
9595 (1L << 0x000D) |
9596 (1L << 0x0020)) >> ch) & 1L) != 0);
9597 }
9598
9599
9600 /**
9601 * Determines if the specified character is a Unicode space character.
9602 * A character is considered to be a space character if and only if
9603 * it is specified to be a space character by the Unicode Standard. This
9604 * method returns true if the character's general category type is any of
9605 * the following:
9606 * <ul>
9607 * <li> {@code SPACE_SEPARATOR}
9608 * <li> {@code LINE_SEPARATOR}
9609 * <li> {@code PARAGRAPH_SEPARATOR}
9610 * </ul>
9611 *
9612 * <p><b>Note:</b> This method cannot handle <a
9613 * href="#supplementary"> supplementary characters</a>. To support
9614 * all Unicode characters, including supplementary characters, use
9615 * the {@link #isSpaceChar(int)} method.
9616 *
9617 * @param ch the character to be tested.
9618 * @return {@code true} if the character is a space character;
9619 * {@code false} otherwise.
9620 * @see Character#isWhitespace(char)
9621 * @since 1.1
9622 */
9623 public static boolean isSpaceChar(char ch) {
9624 return isSpaceChar((int)ch);
9625 }
9626
9627 /**
9628 * Determines if the specified character (Unicode code point) is a
9629 * Unicode space character. A character is considered to be a
9630 * space character if and only if it is specified to be a space
9631 * character by the Unicode Standard. This method returns true if
9632 * the character's general category type is any of the following:
9633 *
9634 * <ul>
9635 * <li> {@link #SPACE_SEPARATOR}
9636 * <li> {@link #LINE_SEPARATOR}
9637 * <li> {@link #PARAGRAPH_SEPARATOR}
9638 * </ul>
9639 *
9640 * @param codePoint the character (Unicode code point) to be tested.
9641 * @return {@code true} if the character is a space character;
9642 * {@code false} otherwise.
9643 * @see Character#isWhitespace(int)
9644 * @since 1.5
9645 */
9646 public static boolean isSpaceChar(int codePoint) {
9647 return ((((1 << Character.SPACE_SEPARATOR) |
9648 (1 << Character.LINE_SEPARATOR) |
9649 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
9650 != 0;
9651 }
9652
9653 /**
9654 * Determines if the specified character is white space according to Java.
9655 * A character is a Java whitespace character if and only if it satisfies
9656 * one of the following criteria:
9657 * <ul>
9658 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
9659 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
9660 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
9661 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
9662 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
9663 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
9664 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
9665 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
9666 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
9667 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
9668 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
9669 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
9670 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
9671 * </ul>
9672 *
9673 * <p><b>Note:</b> This method cannot handle <a
9674 * href="#supplementary"> supplementary characters</a>. To support
9675 * all Unicode characters, including supplementary characters, use
9676 * the {@link #isWhitespace(int)} method.
9677 *
9678 * @param ch the character to be tested.
9679 * @return {@code true} if the character is a Java whitespace
9680 * character; {@code false} otherwise.
9681 * @see Character#isSpaceChar(char)
9682 * @since 1.1
9683 */
9684 public static boolean isWhitespace(char ch) {
9685 return isWhitespace((int)ch);
9686 }
9687
9688 /**
9689 * Determines if the specified character (Unicode code point) is
9690 * white space according to Java. A character is a Java
9691 * whitespace character if and only if it satisfies one of the
9692 * following criteria:
9693 * <ul>
9694 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
9695 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
9696 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
9697 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
9698 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
9699 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
9700 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
9701 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
9702 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
9703 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
9704 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
9705 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
9706 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
9707 * </ul>
9708 *
9709 * @param codePoint the character (Unicode code point) to be tested.
9710 * @return {@code true} if the character is a Java whitespace
9711 * character; {@code false} otherwise.
9712 * @see Character#isSpaceChar(int)
9713 * @since 1.5
9714 */
9715 public static boolean isWhitespace(int codePoint) {
9716 return CharacterData.of(codePoint).isWhitespace(codePoint);
9717 }
9718
9719 /**
9720 * Determines if the specified character is an ISO control
9721 * character. A character is considered to be an ISO control
9722 * character if its code is in the range {@code '\u005Cu0000'}
9723 * through {@code '\u005Cu001F'} or in the range
9724 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
9725 *
9726 * <p><b>Note:</b> This method cannot handle <a
9727 * href="#supplementary"> supplementary characters</a>. To support
9728 * all Unicode characters, including supplementary characters, use
9729 * the {@link #isISOControl(int)} method.
9730 *
9731 * @param ch the character to be tested.
9732 * @return {@code true} if the character is an ISO control character;
9733 * {@code false} otherwise.
9734 *
9735 * @see Character#isSpaceChar(char)
9736 * @see Character#isWhitespace(char)
9737 * @since 1.1
9738 */
9739 public static boolean isISOControl(char ch) {
9740 return isISOControl((int)ch);
9741 }
9742
9743 /**
9744 * Determines if the referenced character (Unicode code point) is an ISO control
9745 * character. A character is considered to be an ISO control
9746 * character if its code is in the range {@code '\u005Cu0000'}
9747 * through {@code '\u005Cu001F'} or in the range
9748 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
9749 *
9750 * @param codePoint the character (Unicode code point) to be tested.
9751 * @return {@code true} if the character is an ISO control character;
9752 * {@code false} otherwise.
9753 * @see Character#isSpaceChar(int)
9754 * @see Character#isWhitespace(int)
9755 * @since 1.5
9756 */
9757 public static boolean isISOControl(int codePoint) {
9758 // Optimized form of:
9759 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
9760 // (codePoint >= 0x7F && codePoint <= 0x9F);
9761 return codePoint <= 0x9F &&
9762 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
9763 }
9764
9765 /**
9766 * Returns a value indicating a character's general category.
9767 *
9768 * <p><b>Note:</b> This method cannot handle <a
9769 * href="#supplementary"> supplementary characters</a>. To support
9770 * all Unicode characters, including supplementary characters, use
9771 * the {@link #getType(int)} method.
9772 *
9773 * @param ch the character to be tested.
9774 * @return a value of type {@code int} representing the
9775 * character's general category.
9776 * @see Character#COMBINING_SPACING_MARK
9777 * @see Character#CONNECTOR_PUNCTUATION
9778 * @see Character#CONTROL
9779 * @see Character#CURRENCY_SYMBOL
9780 * @see Character#DASH_PUNCTUATION
9781 * @see Character#DECIMAL_DIGIT_NUMBER
9782 * @see Character#ENCLOSING_MARK
9783 * @see Character#END_PUNCTUATION
9784 * @see Character#FINAL_QUOTE_PUNCTUATION
9785 * @see Character#FORMAT
9786 * @see Character#INITIAL_QUOTE_PUNCTUATION
9787 * @see Character#LETTER_NUMBER
9788 * @see Character#LINE_SEPARATOR
9789 * @see Character#LOWERCASE_LETTER
9790 * @see Character#MATH_SYMBOL
9791 * @see Character#MODIFIER_LETTER
9792 * @see Character#MODIFIER_SYMBOL
9793 * @see Character#NON_SPACING_MARK
9794 * @see Character#OTHER_LETTER
9795 * @see Character#OTHER_NUMBER
9796 * @see Character#OTHER_PUNCTUATION
9797 * @see Character#OTHER_SYMBOL
9798 * @see Character#PARAGRAPH_SEPARATOR
9799 * @see Character#PRIVATE_USE
9800 * @see Character#SPACE_SEPARATOR
9801 * @see Character#START_PUNCTUATION
9802 * @see Character#SURROGATE
9803 * @see Character#TITLECASE_LETTER
9804 * @see Character#UNASSIGNED
9805 * @see Character#UPPERCASE_LETTER
9806 * @since 1.1
9807 */
9808 public static int getType(char ch) {
9809 return getType((int)ch);
9810 }
9811
9812 /**
9813 * Returns a value indicating a character's general category.
9814 *
9815 * @param codePoint the character (Unicode code point) to be tested.
9816 * @return a value of type {@code int} representing the
9817 * character's general category.
9818 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
9819 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
9820 * @see Character#CONTROL CONTROL
9821 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
9822 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
9823 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
9824 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
9825 * @see Character#END_PUNCTUATION END_PUNCTUATION
9826 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
9827 * @see Character#FORMAT FORMAT
9828 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
9829 * @see Character#LETTER_NUMBER LETTER_NUMBER
9830 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
9831 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
9832 * @see Character#MATH_SYMBOL MATH_SYMBOL
9833 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
9834 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
9835 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
9836 * @see Character#OTHER_LETTER OTHER_LETTER
9837 * @see Character#OTHER_NUMBER OTHER_NUMBER
9838 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
9839 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
9840 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
9841 * @see Character#PRIVATE_USE PRIVATE_USE
9842 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
9843 * @see Character#START_PUNCTUATION START_PUNCTUATION
9844 * @see Character#SURROGATE SURROGATE
9845 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
9846 * @see Character#UNASSIGNED UNASSIGNED
9847 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
9848 * @since 1.5
9849 */
9850 public static int getType(int codePoint) {
9851 return CharacterData.of(codePoint).getType(codePoint);
9852 }
9853
9854 /**
9855 * Determines the character representation for a specific digit in
9856 * the specified radix. If the value of {@code radix} is not a
9857 * valid radix, or the value of {@code digit} is not a valid
9858 * digit in the specified radix, the null character
9859 * ({@code '\u005Cu0000'}) is returned.
9860 * <p>
9861 * The {@code radix} argument is valid if it is greater than or
9862 * equal to {@code MIN_RADIX} and less than or equal to
9863 * {@code MAX_RADIX}. The {@code digit} argument is valid if
9864 * {@code 0 <= digit < radix}.
9865 * <p>
9866 * If the digit is less than 10, then
9867 * {@code '0' + digit} is returned. Otherwise, the value
9868 * {@code 'a' + digit - 10} is returned.
9869 *
9870 * @param digit the number to convert to a character.
9871 * @param radix the radix.
9872 * @return the {@code char} representation of the specified digit
9873 * in the specified radix.
9874 * @see Character#MIN_RADIX
9875 * @see Character#MAX_RADIX
9876 * @see Character#digit(char, int)
9877 */
9878 public static char forDigit(int digit, int radix) {
9879 if ((digit >= radix) || (digit < 0)) {
9880 return '\0';
9881 }
9882 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
9883 return '\0';
9884 }
9885 if (digit < 10) {
9886 return (char)('0' + digit);
9887 }
9888 return (char)('a' - 10 + digit);
9889 }
9890
9891 /**
9892 * Returns the Unicode directionality property for the given
9893 * character. Character directionality is used to calculate the
9894 * visual ordering of text. The directionality value of undefined
9895 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
9896 *
9897 * <p><b>Note:</b> This method cannot handle <a
9898 * href="#supplementary"> supplementary characters</a>. To support
9899 * all Unicode characters, including supplementary characters, use
9900 * the {@link #getDirectionality(int)} method.
9901 *
9902 * @param ch {@code char} for which the directionality property
9903 * is requested.
9904 * @return the directionality property of the {@code char} value.
9905 *
9906 * @see Character#DIRECTIONALITY_UNDEFINED
9907 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
9908 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
9909 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
9910 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
9911 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
9912 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
9913 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
9914 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
9915 * @see Character#DIRECTIONALITY_NONSPACING_MARK
9916 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
9917 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
9918 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
9919 * @see Character#DIRECTIONALITY_WHITESPACE
9920 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
9921 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
9922 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
9923 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
9924 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
9925 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
9926 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
9927 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
9928 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
9929 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
9930 * @since 1.4
9931 */
9932 public static byte getDirectionality(char ch) {
9933 return getDirectionality((int)ch);
9934 }
9935
9936 /**
9937 * Returns the Unicode directionality property for the given
9938 * character (Unicode code point). Character directionality is
9939 * used to calculate the visual ordering of text. The
9940 * directionality value of undefined character is {@link
9941 * #DIRECTIONALITY_UNDEFINED}.
9942 *
9943 * @param codePoint the character (Unicode code point) for which
9944 * the directionality property is requested.
9945 * @return the directionality property of the character.
9946 *
9947 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
9948 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
9949 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
9950 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
9951 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
9952 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
9953 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
9954 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
9955 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
9956 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
9957 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
9958 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
9959 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
9960 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
9961 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
9962 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
9963 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
9964 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
9965 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
9966 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
9967 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
9968 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
9969 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
9970 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
9971 * @since 1.5
9972 */
9973 public static byte getDirectionality(int codePoint) {
9974 return CharacterData.of(codePoint).getDirectionality(codePoint);
9975 }
9976
9977 /**
9978 * Determines whether the character is mirrored according to the
9979 * Unicode specification. Mirrored characters should have their
9980 * glyphs horizontally mirrored when displayed in text that is
9981 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
9982 * PARENTHESIS is semantically defined to be an <i>opening
9983 * parenthesis</i>. This will appear as a "(" in text that is
9984 * left-to-right but as a ")" in text that is right-to-left.
9985 *
9986 * <p><b>Note:</b> This method cannot handle <a
9987 * href="#supplementary"> supplementary characters</a>. To support
9988 * all Unicode characters, including supplementary characters, use
9989 * the {@link #isMirrored(int)} method.
9990 *
9991 * @param ch {@code char} for which the mirrored property is requested
9992 * @return {@code true} if the char is mirrored, {@code false}
9993 * if the {@code char} is not mirrored or is not defined.
9994 * @since 1.4
9995 */
9996 public static boolean isMirrored(char ch) {
9997 return isMirrored((int)ch);
9998 }
9999
10000 /**
10001 * Determines whether the specified character (Unicode code point)
10002 * is mirrored according to the Unicode specification. Mirrored
10003 * characters should have their glyphs horizontally mirrored when
10004 * displayed in text that is right-to-left. For example,
10005 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
10006 * defined to be an <i>opening parenthesis</i>. This will appear
10007 * as a "(" in text that is left-to-right but as a ")" in text
10008 * that is right-to-left.
10009 *
10010 * @param codePoint the character (Unicode code point) to be tested.
10011 * @return {@code true} if the character is mirrored, {@code false}
10012 * if the character is not mirrored or is not defined.
10013 * @since 1.5
10014 */
10015 public static boolean isMirrored(int codePoint) {
10016 return CharacterData.of(codePoint).isMirrored(codePoint);
10017 }
10018
10019 /**
10020 * Compares two {@code Character} objects numerically.
10021 *
10022 * @param anotherCharacter the {@code Character} to be compared.
10023
10024 * @return the value {@code 0} if the argument {@code Character}
10025 * is equal to this {@code Character}; a value less than
10026 * {@code 0} if this {@code Character} is numerically less
10027 * than the {@code Character} argument; and a value greater than
10028 * {@code 0} if this {@code Character} is numerically greater
10029 * than the {@code Character} argument (unsigned comparison).
10030 * Note that this is strictly a numerical comparison; it is not
10031 * locale-dependent.
10032 * @since 1.2
10033 */
10034 public int compareTo(Character anotherCharacter) {
10035 return compare(this.value, anotherCharacter.value);
10036 }
10037
10038 /**
10039 * Compares two {@code char} values numerically.
10040 * The value returned is identical to what would be returned by:
10041 * <pre>
10042 * Character.valueOf(x).compareTo(Character.valueOf(y))
10043 * </pre>
10044 *
10045 * @param x the first {@code char} to compare
10046 * @param y the second {@code char} to compare
10047 * @return the value {@code 0} if {@code x == y};
10048 * a value less than {@code 0} if {@code x < y}; and
10049 * a value greater than {@code 0} if {@code x > y}
10050 * @since 1.7
10051 */
10052 public static int compare(char x, char y) {
10053 return x - y;
10054 }
10055
10056 /**
10057 * Converts the character (Unicode code point) argument to uppercase using
10058 * information from the UnicodeData file.
10059 *
10060 * @param codePoint the character (Unicode code point) to be converted.
10061 * @return either the uppercase equivalent of the character, if
10062 * any, or an error flag ({@code Character.ERROR})
10063 * that indicates that a 1:M {@code char} mapping exists.
10064 * @see Character#isLowerCase(char)
10065 * @see Character#isUpperCase(char)
10066 * @see Character#toLowerCase(char)
10067 * @see Character#toTitleCase(char)
10068 * @since 1.4
10069 */
10070 static int toUpperCaseEx(int codePoint) {
10071 assert isValidCodePoint(codePoint);
10072 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
10073 }
10074
10075 /**
10076 * Converts the character (Unicode code point) argument to uppercase using case
10077 * mapping information from the SpecialCasing file in the Unicode
10078 * specification. If a character has no explicit uppercase
10079 * mapping, then the {@code char} itself is returned in the
10080 * {@code char[]}.
10081 *
10082 * @param codePoint the character (Unicode code point) to be converted.
10083 * @return a {@code char[]} with the uppercased character.
10084 * @since 1.4
10085 */
10086 static char[] toUpperCaseCharArray(int codePoint) {
10087 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
10088 assert isBmpCodePoint(codePoint);
10089 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
10090 }
10091
10092 /**
10093 * The number of bits used to represent a {@code char} value in unsigned
10094 * binary form, constant {@code 16}.
10095 *
10096 * @since 1.5
10097 */
10098 public static final int SIZE = 16;
10099
10100 /**
10101 * The number of bytes used to represent a {@code char} value in unsigned
10102 * binary form.
10103 *
10104 * @since 1.8
10105 */
10106 public static final int BYTES = SIZE / Byte.SIZE;
10107
10108 /**
10109 * Returns the value obtained by reversing the order of the bytes in the
10110 * specified {@code char} value.
10111 *
10112 * @param ch The {@code char} of which to reverse the byte order.
10113 * @return the value obtained by reversing (or, equivalently, swapping)
10114 * the bytes in the specified {@code char} value.
10115 * @since 1.5
10116 */
10117 @HotSpotIntrinsicCandidate
10118 public static char reverseBytes(char ch) {
10119 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
10120 }
10121
10122 /**
10123 * Returns the Unicode name of the specified character
10124 * {@code codePoint}, or null if the code point is
10125 * {@link #UNASSIGNED unassigned}.
10126 * <p>
10127 * Note: if the specified character is not assigned a name by
10128 * the <i>UnicodeData</i> file (part of the Unicode Character
10129 * Database maintained by the Unicode Consortium), the returned
10130 * name is the same as the result of expression.
10131 *
10132 * <blockquote>{@code
10133 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
10134 * + " "
10135 * + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
10136 *
10137 * }</blockquote>
10138 *
10139 * @param codePoint the character (Unicode code point)
10140 *
10141 * @return the Unicode name of the specified character, or null if
10142 * the code point is unassigned.
10143 *
10144 * @exception IllegalArgumentException if the specified
10145 * {@code codePoint} is not a valid Unicode
10146 * code point.
10147 *
10148 * @since 1.7
10149 */
10150 public static String getName(int codePoint) {
10151 if (!isValidCodePoint(codePoint)) {
10152 throw new IllegalArgumentException();
10153 }
10154 String name = CharacterName.get(codePoint);
10155 if (name != null)
10156 return name;
10157 if (getType(codePoint) == UNASSIGNED)
10158 return null;
10159 UnicodeBlock block = UnicodeBlock.of(codePoint);
10160 if (block != null)
10161 return block.toString().replace('_', ' ') + " "
10162 + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
10163 // should never come here
10164 return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
10165 }
10166 }