1 /*
2 * Copyright (c) 2002, 2010, 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 /**
34 * The <code>Character</code> class wraps a value of the primitive
35 * type <code>char</code> in an object. An object of type
36 * <code>Character</code> contains a single field whose type is
37 * <code>char</code>.
38 * <p>
39 * In addition, this class provides several methods for determining
40 * a character's category (lowercase letter, digit, etc.) and for converting
41 * characters from uppercase to lowercase and vice versa.
42 * <p>
43 * Character information is based on the Unicode Standard, version 6.0.0.
44 * <p>
45 * The methods and data of class <code>Character</code> are defined by
46 * the information in the <i>UnicodeData</i> file that is part of the
47 * Unicode Character Database maintained by the Unicode
48 * Consortium. This file specifies various properties including name
49 * and general category for every defined Unicode code point or
50 * character range.
51 * <p>
52 * The file and its description are available from the Unicode Consortium at:
53 * <ul>
54 * <li><a href="http://www.unicode.org">http://www.unicode.org</a>
55 * </ul>
56 *
57 * <h4><a name="unicode">Unicode Character Representations</a></h4>
58 *
59 * <p>The <code>char</code> data type (and therefore the value that a
60 * <code>Character</code> object encapsulates) are based on the
61 * original Unicode specification, which defined characters as
62 * fixed-width 16-bit entities. The Unicode standard has since been
63 * changed to allow for characters whose representation requires more
64 * than 16 bits. The range of legal <em>code point</em>s is now
65 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
66 * (Refer to the <a
67 * href="http://www.unicode.org/reports/tr27/#notation"><i>
68 * definition</i></a> of the U+<i>n</i> notation in the Unicode
69 * standard.)
70 *
71 * <p><a name="BMP">The set of characters from U+0000 to U+FFFF is
72 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
73 * <a name="supplementary">Characters</a> whose code points are greater
74 * than U+FFFF are called <em>supplementary character</em>s. The Java
75 * platform uses the UTF-16 representation in <code>char</code> arrays and
76 * in the <code>String</code> and <code>StringBuffer</code> classes. In
77 * this representation, supplementary characters are represented as a pair
78 * of <code>char</code> values, the first from the <em>high-surrogates</em>
79 * range, (\uD800-\uDBFF), the second from the
80 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
81 *
82 * <p>A <code>char</code> value, therefore, represents Basic
83 * Multilingual Plane (BMP) code points, including the surrogate
84 * code points, or code units of the UTF-16 encoding. An
85 * <code>int</code> value represents all Unicode code points,
86 * including supplementary code points. The lower (least significant)
87 * 21 bits of <code>int</code> are used to represent Unicode code
88 * points and the upper (most significant) 11 bits must be zero.
89 * Unless otherwise specified, the behavior with respect to
90 * supplementary characters and surrogate <code>char</code> values is
91 * as follows:
92 *
93 * <ul>
94 * <li>The methods that only accept a <code>char</code> value cannot support
95 * supplementary characters. They treat <code>char</code> values from the
96 * surrogate ranges as undefined characters. For example,
97 * <code>Character.isLetter('\uD840')</code> returns <code>false</code>, even though
98 * this specific value if followed by any low-surrogate value in a string
99 * would represent a letter.
100 *
101 * <li>The methods that accept an <code>int</code> value support all
102 * Unicode characters, including supplementary characters. For
103 * example, <code>Character.isLetter(0x2F81A)</code> returns
104 * <code>true</code> because the code point value represents a letter
105 * (a CJK ideograph).
106 * </ul>
107 *
108 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
109 * used for character values in the range between U+0000 and U+10FFFF,
110 * and <em>Unicode code unit</em> is used for 16-bit
111 * <code>char</code> values that are code units of the <em>UTF-16</em>
112 * encoding. For more information on Unicode terminology, refer to the
113 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
114 *
115 * @author Lee Boynton
116 * @author Guy Steele
117 * @author Akira Tanaka
118 * @author Martin Buchholz
119 * @author Ulf Zibis
120 * @since 1.0
121 */
122 public final
123 class Character implements java.io.Serializable, Comparable<Character> {
124 /**
125 * The minimum radix available for conversion to and from strings.
126 * The constant value of this field is the smallest value permitted
127 * for the radix argument in radix-conversion methods such as the
128 * <code>digit</code> method, the <code>forDigit</code>
129 * method, and the <code>toString</code> method of class
130 * <code>Integer</code>.
131 *
132 * @see Character#digit(char, int)
133 * @see Character#forDigit(int, int)
134 * @see Integer#toString(int, int)
135 * @see Integer#valueOf(String)
136 */
137 public static final int MIN_RADIX = 2;
138
139 /**
140 * The maximum radix available for conversion to and from strings.
141 * The constant value of this field is the largest value permitted
142 * for the radix argument in radix-conversion methods such as the
143 * <code>digit</code> method, the <code>forDigit</code>
144 * method, and the <code>toString</code> method of class
145 * <code>Integer</code>.
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>, <code>'\u0000'</code>.
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>, <code>'\uFFFF'</code>.
165 *
166 * @since 1.0.2
167 */
168 public static final char MAX_VALUE = '\uFFFF';
169
170 /**
171 * The <code>Class</code> instance representing the primitive type
172 * <code>char</code>.
173 *
174 * @since 1.1
175 */
176 @SuppressWarnings("unchecked")
177 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
178
179 /*
180 * Normative general types
181 */
182
183 /*
184 * General character types
185 */
186
187 /**
188 * General category "Cn" in the Unicode specification.
189 * @since 1.1
190 */
191 public static final byte UNASSIGNED = 0;
192
193 /**
194 * General category "Lu" in the Unicode specification.
195 * @since 1.1
196 */
197 public static final byte UPPERCASE_LETTER = 1;
198
199 /**
200 * General category "Ll" in the Unicode specification.
201 * @since 1.1
202 */
203 public static final byte LOWERCASE_LETTER = 2;
204
205 /**
206 * General category "Lt" in the Unicode specification.
207 * @since 1.1
208 */
209 public static final byte TITLECASE_LETTER = 3;
210
211 /**
212 * General category "Lm" in the Unicode specification.
213 * @since 1.1
214 */
215 public static final byte MODIFIER_LETTER = 4;
216
217 /**
218 * General category "Lo" in the Unicode specification.
219 * @since 1.1
220 */
221 public static final byte OTHER_LETTER = 5;
222
223 /**
224 * General category "Mn" in the Unicode specification.
225 * @since 1.1
226 */
227 public static final byte NON_SPACING_MARK = 6;
228
229 /**
230 * General category "Me" in the Unicode specification.
231 * @since 1.1
232 */
233 public static final byte ENCLOSING_MARK = 7;
234
235 /**
236 * General category "Mc" in the Unicode specification.
237 * @since 1.1
238 */
239 public static final byte COMBINING_SPACING_MARK = 8;
240
241 /**
242 * General category "Nd" in the Unicode specification.
243 * @since 1.1
244 */
245 public static final byte DECIMAL_DIGIT_NUMBER = 9;
246
247 /**
248 * General category "Nl" in the Unicode specification.
249 * @since 1.1
250 */
251 public static final byte LETTER_NUMBER = 10;
252
253 /**
254 * General category "No" in the Unicode specification.
255 * @since 1.1
256 */
257 public static final byte OTHER_NUMBER = 11;
258
259 /**
260 * General category "Zs" in the Unicode specification.
261 * @since 1.1
262 */
263 public static final byte SPACE_SEPARATOR = 12;
264
265 /**
266 * General category "Zl" in the Unicode specification.
267 * @since 1.1
268 */
269 public static final byte LINE_SEPARATOR = 13;
270
271 /**
272 * General category "Zp" in the Unicode specification.
273 * @since 1.1
274 */
275 public static final byte PARAGRAPH_SEPARATOR = 14;
276
277 /**
278 * General category "Cc" in the Unicode specification.
279 * @since 1.1
280 */
281 public static final byte CONTROL = 15;
282
283 /**
284 * General category "Cf" in the Unicode specification.
285 * @since 1.1
286 */
287 public static final byte FORMAT = 16;
288
289 /**
290 * General category "Co" in the Unicode specification.
291 * @since 1.1
292 */
293 public static final byte PRIVATE_USE = 18;
294
295 /**
296 * General category "Cs" in the Unicode specification.
297 * @since 1.1
298 */
299 public static final byte SURROGATE = 19;
300
301 /**
302 * General category "Pd" in the Unicode specification.
303 * @since 1.1
304 */
305 public static final byte DASH_PUNCTUATION = 20;
306
307 /**
308 * General category "Ps" in the Unicode specification.
309 * @since 1.1
310 */
311 public static final byte START_PUNCTUATION = 21;
312
313 /**
314 * General category "Pe" in the Unicode specification.
315 * @since 1.1
316 */
317 public static final byte END_PUNCTUATION = 22;
318
319 /**
320 * General category "Pc" in the Unicode specification.
321 * @since 1.1
322 */
323 public static final byte CONNECTOR_PUNCTUATION = 23;
324
325 /**
326 * General category "Po" in the Unicode specification.
327 * @since 1.1
328 */
329 public static final byte OTHER_PUNCTUATION = 24;
330
331 /**
332 * General category "Sm" in the Unicode specification.
333 * @since 1.1
334 */
335 public static final byte MATH_SYMBOL = 25;
336
337 /**
338 * General category "Sc" in the Unicode specification.
339 * @since 1.1
340 */
341 public static final byte CURRENCY_SYMBOL = 26;
342
343 /**
344 * General category "Sk" in the Unicode specification.
345 * @since 1.1
346 */
347 public static final byte MODIFIER_SYMBOL = 27;
348
349 /**
350 * General category "So" in the Unicode specification.
351 * @since 1.1
352 */
353 public static final byte OTHER_SYMBOL = 28;
354
355 /**
356 * General category "Pi" in the Unicode specification.
357 * @since 1.4
358 */
359 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
360
361 /**
362 * General category "Pf" in the Unicode specification.
363 * @since 1.4
364 */
365 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
366
367 /**
368 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
369 */
370 static final int ERROR = 0xFFFFFFFF;
371
372
373 /**
374 * Undefined bidirectional character type. Undefined <code>char</code>
375 * values have undefined directionality in the Unicode specification.
376 * @since 1.4
377 */
378 public static final byte DIRECTIONALITY_UNDEFINED = -1;
379
380 /**
381 * Strong bidirectional character type "L" in the Unicode specification.
382 * @since 1.4
383 */
384 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
385
386 /**
387 * Strong bidirectional character type "R" in the Unicode specification.
388 * @since 1.4
389 */
390 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
391
392 /**
393 * Strong bidirectional character type "AL" in the Unicode specification.
394 * @since 1.4
395 */
396 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
397
398 /**
399 * Weak bidirectional character type "EN" in the Unicode specification.
400 * @since 1.4
401 */
402 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
403
404 /**
405 * Weak bidirectional character type "ES" in the Unicode specification.
406 * @since 1.4
407 */
408 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
409
410 /**
411 * Weak bidirectional character type "ET" in the Unicode specification.
412 * @since 1.4
413 */
414 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
415
416 /**
417 * Weak bidirectional character type "AN" in the Unicode specification.
418 * @since 1.4
419 */
420 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
421
422 /**
423 * Weak bidirectional character type "CS" in the Unicode specification.
424 * @since 1.4
425 */
426 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
427
428 /**
429 * Weak bidirectional character type "NSM" in the Unicode specification.
430 * @since 1.4
431 */
432 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
433
434 /**
435 * Weak bidirectional character type "BN" in the Unicode specification.
436 * @since 1.4
437 */
438 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
439
440 /**
441 * Neutral bidirectional character type "B" in the Unicode specification.
442 * @since 1.4
443 */
444 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
445
446 /**
447 * Neutral bidirectional character type "S" in the Unicode specification.
448 * @since 1.4
449 */
450 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
451
452 /**
453 * Neutral bidirectional character type "WS" in the Unicode specification.
454 * @since 1.4
455 */
456 public static final byte DIRECTIONALITY_WHITESPACE = 12;
457
458 /**
459 * Neutral bidirectional character type "ON" in the Unicode specification.
460 * @since 1.4
461 */
462 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
463
464 /**
465 * Strong bidirectional character type "LRE" in the Unicode specification.
466 * @since 1.4
467 */
468 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
469
470 /**
471 * Strong bidirectional character type "LRO" in the Unicode specification.
472 * @since 1.4
473 */
474 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
475
476 /**
477 * Strong bidirectional character type "RLE" in the Unicode specification.
478 * @since 1.4
479 */
480 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
481
482 /**
483 * Strong bidirectional character type "RLO" in the Unicode specification.
484 * @since 1.4
485 */
486 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
487
488 /**
489 * Weak bidirectional character type "PDF" in the Unicode specification.
490 * @since 1.4
491 */
492 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
493
494 /**
495 * The minimum value of a
496 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
497 * Unicode high-surrogate code unit</a>
498 * in the UTF-16 encoding, constant <code>'\uD800'</code>.
499 * A high-surrogate is also known as a <i>leading-surrogate</i>.
500 *
501 * @since 1.5
502 */
503 public static final char MIN_HIGH_SURROGATE = '\uD800';
504
505 /**
506 * The maximum value of a
507 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
508 * Unicode high-surrogate code unit</a>
509 * in the UTF-16 encoding, constant <code>'\uDBFF'</code>.
510 * A high-surrogate is also known as a <i>leading-surrogate</i>.
511 *
512 * @since 1.5
513 */
514 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
515
516 /**
517 * The minimum value of a
518 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
519 * Unicode low-surrogate code unit</a>
520 * in the UTF-16 encoding, constant <code>'\uDC00'</code>.
521 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
522 *
523 * @since 1.5
524 */
525 public static final char MIN_LOW_SURROGATE = '\uDC00';
526
527 /**
528 * The maximum value of a
529 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
530 * Unicode low-surrogate code unit</a>
531 * in the UTF-16 encoding, constant <code>'\uDFFF'</code>.
532 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
533 *
534 * @since 1.5
535 */
536 public static final char MAX_LOW_SURROGATE = '\uDFFF';
537
538 /**
539 * The minimum value of a Unicode surrogate code unit in the
540 * UTF-16 encoding, constant <code>'\uD800'</code>.
541 *
542 * @since 1.5
543 */
544 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
545
546 /**
547 * The maximum value of a Unicode surrogate code unit in the
548 * UTF-16 encoding, constant <code>'\uDFFF'</code>.
549 *
550 * @since 1.5
551 */
552 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
553
554 /**
555 * The minimum value of a
556 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
557 * Unicode supplementary code point</a>, constant {@code U+10000}.
558 *
559 * @since 1.5
560 */
561 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
562
563 /**
564 * The minimum value of a
565 * <a href="http://www.unicode.org/glossary/#code_point">
566 * Unicode code point</a>, constant {@code U+0000}.
567 *
568 * @since 1.5
569 */
570 public static final int MIN_CODE_POINT = 0x000000;
571
572 /**
573 * The maximum value of a
574 * <a href="http://www.unicode.org/glossary/#code_point">
575 * Unicode code point</a>, constant {@code U+10FFFF}.
576 *
577 * @since 1.5
578 */
579 public static final int MAX_CODE_POINT = 0X10FFFF;
580
581
582 /**
583 * Instances of this class represent particular subsets of the Unicode
584 * character set. The only family of subsets defined in the
585 * <code>Character</code> class is {@link Character.UnicodeBlock}.
586 * Other portions of the Java API may define other subsets for their
587 * own purposes.
588 *
589 * @since 1.2
590 */
591 public static class Subset {
592
593 private String name;
594
595 /**
596 * Constructs a new <code>Subset</code> instance.
597 *
598 * @param name The name of this subset
599 * @exception NullPointerException if name is <code>null</code>
600 */
601 protected Subset(String name) {
602 if (name == null) {
603 throw new NullPointerException("name");
604 }
605 this.name = name;
606 }
607
608 /**
609 * Compares two <code>Subset</code> objects for equality.
610 * This method returns <code>true</code> if and only if
611 * <code>this</code> and the argument refer to the same
612 * object; since this method is <code>final</code>, this
613 * guarantee holds for all subclasses.
614 */
615 public final boolean equals(Object obj) {
616 return (this == obj);
617 }
618
619 /**
620 * Returns the standard hash code as defined by the
621 * <code>{@link Object#hashCode}</code> method. This method
622 * is <code>final</code> in order to ensure that the
623 * <code>equals</code> and <code>hashCode</code> methods will
624 * be consistent in all subclasses.
625 */
626 public final int hashCode() {
627 return super.hashCode();
628 }
629
630 /**
631 * Returns the name of this subset.
632 */
633 public final String toString() {
634 return name;
635 }
636 }
637
638 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
639 // for the latest specification of Unicode Blocks.
640
641 /**
642 * A family of character subsets representing the character blocks in the
643 * Unicode specification. Character blocks generally define characters
644 * used for a specific script or purpose. A character is contained by
645 * at most one Unicode block.
646 *
647 * @since 1.2
648 */
649 public static final class UnicodeBlock extends Subset {
650
651 private static Map<String, UnicodeBlock> map
652 = new HashMap<>(256);
653
654 /**
655 * Creates a UnicodeBlock with the given identifier name.
656 * This name must be the same as the block identifier.
657 */
658 private UnicodeBlock(String idName) {
659 super(idName);
660 map.put(idName, this);
661 }
662
663 /**
664 * Creates a UnicodeBlock with the given identifier name and
665 * alias name.
666 */
667 private UnicodeBlock(String idName, String alias) {
668 this(idName);
669 map.put(alias, this);
670 }
671
672 /**
673 * Creates a UnicodeBlock with the given identifier name and
674 * alias names.
675 */
676 private UnicodeBlock(String idName, String... aliases) {
677 this(idName);
678 for (String alias : aliases)
679 map.put(alias, this);
680 }
681
682 /**
683 * Constant for the "Basic Latin" Unicode character block.
684 * @since 1.2
685 */
686 public static final UnicodeBlock BASIC_LATIN =
687 new UnicodeBlock("BASIC_LATIN",
688 "BASIC LATIN",
689 "BASICLATIN");
690
691 /**
692 * Constant for the "Latin-1 Supplement" Unicode character block.
693 * @since 1.2
694 */
695 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
696 new UnicodeBlock("LATIN_1_SUPPLEMENT",
697 "LATIN-1 SUPPLEMENT",
698 "LATIN-1SUPPLEMENT");
699
700 /**
701 * Constant for the "Latin Extended-A" Unicode character block.
702 * @since 1.2
703 */
704 public static final UnicodeBlock LATIN_EXTENDED_A =
705 new UnicodeBlock("LATIN_EXTENDED_A",
706 "LATIN EXTENDED-A",
707 "LATINEXTENDED-A");
708
709 /**
710 * Constant for the "Latin Extended-B" Unicode character block.
711 * @since 1.2
712 */
713 public static final UnicodeBlock LATIN_EXTENDED_B =
714 new UnicodeBlock("LATIN_EXTENDED_B",
715 "LATIN EXTENDED-B",
716 "LATINEXTENDED-B");
717
718 /**
719 * Constant for the "IPA Extensions" Unicode character block.
720 * @since 1.2
721 */
722 public static final UnicodeBlock IPA_EXTENSIONS =
723 new UnicodeBlock("IPA_EXTENSIONS",
724 "IPA EXTENSIONS",
725 "IPAEXTENSIONS");
726
727 /**
728 * Constant for the "Spacing Modifier Letters" Unicode character block.
729 * @since 1.2
730 */
731 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
732 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
733 "SPACING MODIFIER LETTERS",
734 "SPACINGMODIFIERLETTERS");
735
736 /**
737 * Constant for the "Combining Diacritical Marks" Unicode character block.
738 * @since 1.2
739 */
740 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
741 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
742 "COMBINING DIACRITICAL MARKS",
743 "COMBININGDIACRITICALMARKS");
744
745 /**
746 * Constant for the "Greek and Coptic" Unicode character block.
747 * <p>
748 * This block was previously known as the "Greek" block.
749 *
750 * @since 1.2
751 */
752 public static final UnicodeBlock GREEK =
753 new UnicodeBlock("GREEK",
754 "GREEK AND COPTIC",
755 "GREEKANDCOPTIC");
756
757 /**
758 * Constant for the "Cyrillic" Unicode character block.
759 * @since 1.2
760 */
761 public static final UnicodeBlock CYRILLIC =
762 new UnicodeBlock("CYRILLIC");
763
764 /**
765 * Constant for the "Armenian" Unicode character block.
766 * @since 1.2
767 */
768 public static final UnicodeBlock ARMENIAN =
769 new UnicodeBlock("ARMENIAN");
770
771 /**
772 * Constant for the "Hebrew" Unicode character block.
773 * @since 1.2
774 */
775 public static final UnicodeBlock HEBREW =
776 new UnicodeBlock("HEBREW");
777
778 /**
779 * Constant for the "Arabic" Unicode character block.
780 * @since 1.2
781 */
782 public static final UnicodeBlock ARABIC =
783 new UnicodeBlock("ARABIC");
784
785 /**
786 * Constant for the "Devanagari" Unicode character block.
787 * @since 1.2
788 */
789 public static final UnicodeBlock DEVANAGARI =
790 new UnicodeBlock("DEVANAGARI");
791
792 /**
793 * Constant for the "Bengali" Unicode character block.
794 * @since 1.2
795 */
796 public static final UnicodeBlock BENGALI =
797 new UnicodeBlock("BENGALI");
798
799 /**
800 * Constant for the "Gurmukhi" Unicode character block.
801 * @since 1.2
802 */
803 public static final UnicodeBlock GURMUKHI =
804 new UnicodeBlock("GURMUKHI");
805
806 /**
807 * Constant for the "Gujarati" Unicode character block.
808 * @since 1.2
809 */
810 public static final UnicodeBlock GUJARATI =
811 new UnicodeBlock("GUJARATI");
812
813 /**
814 * Constant for the "Oriya" Unicode character block.
815 * @since 1.2
816 */
817 public static final UnicodeBlock ORIYA =
818 new UnicodeBlock("ORIYA");
819
820 /**
821 * Constant for the "Tamil" Unicode character block.
822 * @since 1.2
823 */
824 public static final UnicodeBlock TAMIL =
825 new UnicodeBlock("TAMIL");
826
827 /**
828 * Constant for the "Telugu" Unicode character block.
829 * @since 1.2
830 */
831 public static final UnicodeBlock TELUGU =
832 new UnicodeBlock("TELUGU");
833
834 /**
835 * Constant for the "Kannada" Unicode character block.
836 * @since 1.2
837 */
838 public static final UnicodeBlock KANNADA =
839 new UnicodeBlock("KANNADA");
840
841 /**
842 * Constant for the "Malayalam" Unicode character block.
843 * @since 1.2
844 */
845 public static final UnicodeBlock MALAYALAM =
846 new UnicodeBlock("MALAYALAM");
847
848 /**
849 * Constant for the "Thai" Unicode character block.
850 * @since 1.2
851 */
852 public static final UnicodeBlock THAI =
853 new UnicodeBlock("THAI");
854
855 /**
856 * Constant for the "Lao" Unicode character block.
857 * @since 1.2
858 */
859 public static final UnicodeBlock LAO =
860 new UnicodeBlock("LAO");
861
862 /**
863 * Constant for the "Tibetan" Unicode character block.
864 * @since 1.2
865 */
866 public static final UnicodeBlock TIBETAN =
867 new UnicodeBlock("TIBETAN");
868
869 /**
870 * Constant for the "Georgian" Unicode character block.
871 * @since 1.2
872 */
873 public static final UnicodeBlock GEORGIAN =
874 new UnicodeBlock("GEORGIAN");
875
876 /**
877 * Constant for the "Hangul Jamo" Unicode character block.
878 * @since 1.2
879 */
880 public static final UnicodeBlock HANGUL_JAMO =
881 new UnicodeBlock("HANGUL_JAMO",
882 "HANGUL JAMO",
883 "HANGULJAMO");
884
885 /**
886 * Constant for the "Latin Extended Additional" Unicode character block.
887 * @since 1.2
888 */
889 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
890 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
891 "LATIN EXTENDED ADDITIONAL",
892 "LATINEXTENDEDADDITIONAL");
893
894 /**
895 * Constant for the "Greek Extended" Unicode character block.
896 * @since 1.2
897 */
898 public static final UnicodeBlock GREEK_EXTENDED =
899 new UnicodeBlock("GREEK_EXTENDED",
900 "GREEK EXTENDED",
901 "GREEKEXTENDED");
902
903 /**
904 * Constant for the "General Punctuation" Unicode character block.
905 * @since 1.2
906 */
907 public static final UnicodeBlock GENERAL_PUNCTUATION =
908 new UnicodeBlock("GENERAL_PUNCTUATION",
909 "GENERAL PUNCTUATION",
910 "GENERALPUNCTUATION");
911
912 /**
913 * Constant for the "Superscripts and Subscripts" Unicode character
914 * block.
915 * @since 1.2
916 */
917 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
918 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
919 "SUPERSCRIPTS AND SUBSCRIPTS",
920 "SUPERSCRIPTSANDSUBSCRIPTS");
921
922 /**
923 * Constant for the "Currency Symbols" Unicode character block.
924 * @since 1.2
925 */
926 public static final UnicodeBlock CURRENCY_SYMBOLS =
927 new UnicodeBlock("CURRENCY_SYMBOLS",
928 "CURRENCY SYMBOLS",
929 "CURRENCYSYMBOLS");
930
931 /**
932 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
933 * character block.
934 * <p>
935 * This block was previously known as "Combining Marks for Symbols".
936 * @since 1.2
937 */
938 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
939 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
940 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
941 "COMBININGDIACRITICALMARKSFORSYMBOLS",
942 "COMBINING MARKS FOR SYMBOLS",
943 "COMBININGMARKSFORSYMBOLS");
944
945 /**
946 * Constant for the "Letterlike Symbols" Unicode character block.
947 * @since 1.2
948 */
949 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
950 new UnicodeBlock("LETTERLIKE_SYMBOLS",
951 "LETTERLIKE SYMBOLS",
952 "LETTERLIKESYMBOLS");
953
954 /**
955 * Constant for the "Number Forms" Unicode character block.
956 * @since 1.2
957 */
958 public static final UnicodeBlock NUMBER_FORMS =
959 new UnicodeBlock("NUMBER_FORMS",
960 "NUMBER FORMS",
961 "NUMBERFORMS");
962
963 /**
964 * Constant for the "Arrows" Unicode character block.
965 * @since 1.2
966 */
967 public static final UnicodeBlock ARROWS =
968 new UnicodeBlock("ARROWS");
969
970 /**
971 * Constant for the "Mathematical Operators" Unicode character block.
972 * @since 1.2
973 */
974 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
975 new UnicodeBlock("MATHEMATICAL_OPERATORS",
976 "MATHEMATICAL OPERATORS",
977 "MATHEMATICALOPERATORS");
978
979 /**
980 * Constant for the "Miscellaneous Technical" Unicode character block.
981 * @since 1.2
982 */
983 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
984 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
985 "MISCELLANEOUS TECHNICAL",
986 "MISCELLANEOUSTECHNICAL");
987
988 /**
989 * Constant for the "Control Pictures" Unicode character block.
990 * @since 1.2
991 */
992 public static final UnicodeBlock CONTROL_PICTURES =
993 new UnicodeBlock("CONTROL_PICTURES",
994 "CONTROL PICTURES",
995 "CONTROLPICTURES");
996
997 /**
998 * Constant for the "Optical Character Recognition" Unicode character block.
999 * @since 1.2
1000 */
1001 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1002 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1003 "OPTICAL CHARACTER RECOGNITION",
1004 "OPTICALCHARACTERRECOGNITION");
1005
1006 /**
1007 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1008 * @since 1.2
1009 */
1010 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1011 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1012 "ENCLOSED ALPHANUMERICS",
1013 "ENCLOSEDALPHANUMERICS");
1014
1015 /**
1016 * Constant for the "Box Drawing" Unicode character block.
1017 * @since 1.2
1018 */
1019 public static final UnicodeBlock BOX_DRAWING =
1020 new UnicodeBlock("BOX_DRAWING",
1021 "BOX DRAWING",
1022 "BOXDRAWING");
1023
1024 /**
1025 * Constant for the "Block Elements" Unicode character block.
1026 * @since 1.2
1027 */
1028 public static final UnicodeBlock BLOCK_ELEMENTS =
1029 new UnicodeBlock("BLOCK_ELEMENTS",
1030 "BLOCK ELEMENTS",
1031 "BLOCKELEMENTS");
1032
1033 /**
1034 * Constant for the "Geometric Shapes" Unicode character block.
1035 * @since 1.2
1036 */
1037 public static final UnicodeBlock GEOMETRIC_SHAPES =
1038 new UnicodeBlock("GEOMETRIC_SHAPES",
1039 "GEOMETRIC SHAPES",
1040 "GEOMETRICSHAPES");
1041
1042 /**
1043 * Constant for the "Miscellaneous Symbols" Unicode character block.
1044 * @since 1.2
1045 */
1046 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1047 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1048 "MISCELLANEOUS SYMBOLS",
1049 "MISCELLANEOUSSYMBOLS");
1050
1051 /**
1052 * Constant for the "Dingbats" Unicode character block.
1053 * @since 1.2
1054 */
1055 public static final UnicodeBlock DINGBATS =
1056 new UnicodeBlock("DINGBATS");
1057
1058 /**
1059 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1060 * @since 1.2
1061 */
1062 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1063 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1064 "CJK SYMBOLS AND PUNCTUATION",
1065 "CJKSYMBOLSANDPUNCTUATION");
1066
1067 /**
1068 * Constant for the "Hiragana" Unicode character block.
1069 * @since 1.2
1070 */
1071 public static final UnicodeBlock HIRAGANA =
1072 new UnicodeBlock("HIRAGANA");
1073
1074 /**
1075 * Constant for the "Katakana" Unicode character block.
1076 * @since 1.2
1077 */
1078 public static final UnicodeBlock KATAKANA =
1079 new UnicodeBlock("KATAKANA");
1080
1081 /**
1082 * Constant for the "Bopomofo" Unicode character block.
1083 * @since 1.2
1084 */
1085 public static final UnicodeBlock BOPOMOFO =
1086 new UnicodeBlock("BOPOMOFO");
1087
1088 /**
1089 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1090 * @since 1.2
1091 */
1092 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1093 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1094 "HANGUL COMPATIBILITY JAMO",
1095 "HANGULCOMPATIBILITYJAMO");
1096
1097 /**
1098 * Constant for the "Kanbun" Unicode character block.
1099 * @since 1.2
1100 */
1101 public static final UnicodeBlock KANBUN =
1102 new UnicodeBlock("KANBUN");
1103
1104 /**
1105 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1106 * @since 1.2
1107 */
1108 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1109 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1110 "ENCLOSED CJK LETTERS AND MONTHS",
1111 "ENCLOSEDCJKLETTERSANDMONTHS");
1112
1113 /**
1114 * Constant for the "CJK Compatibility" Unicode character block.
1115 * @since 1.2
1116 */
1117 public static final UnicodeBlock CJK_COMPATIBILITY =
1118 new UnicodeBlock("CJK_COMPATIBILITY",
1119 "CJK COMPATIBILITY",
1120 "CJKCOMPATIBILITY");
1121
1122 /**
1123 * Constant for the "CJK Unified Ideographs" Unicode character block.
1124 * @since 1.2
1125 */
1126 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1127 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1128 "CJK UNIFIED IDEOGRAPHS",
1129 "CJKUNIFIEDIDEOGRAPHS");
1130
1131 /**
1132 * Constant for the "Hangul Syllables" Unicode character block.
1133 * @since 1.2
1134 */
1135 public static final UnicodeBlock HANGUL_SYLLABLES =
1136 new UnicodeBlock("HANGUL_SYLLABLES",
1137 "HANGUL SYLLABLES",
1138 "HANGULSYLLABLES");
1139
1140 /**
1141 * Constant for the "Private Use Area" Unicode character block.
1142 * @since 1.2
1143 */
1144 public static final UnicodeBlock PRIVATE_USE_AREA =
1145 new UnicodeBlock("PRIVATE_USE_AREA",
1146 "PRIVATE USE AREA",
1147 "PRIVATEUSEAREA");
1148
1149 /**
1150 * Constant for the "CJK Compatibility Ideographs" Unicode character
1151 * block.
1152 * @since 1.2
1153 */
1154 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1155 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1156 "CJK COMPATIBILITY IDEOGRAPHS",
1157 "CJKCOMPATIBILITYIDEOGRAPHS");
1158
1159 /**
1160 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1161 * @since 1.2
1162 */
1163 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1164 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1165 "ALPHABETIC PRESENTATION FORMS",
1166 "ALPHABETICPRESENTATIONFORMS");
1167
1168 /**
1169 * Constant for the "Arabic Presentation Forms-A" Unicode character
1170 * block.
1171 * @since 1.2
1172 */
1173 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1174 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1175 "ARABIC PRESENTATION FORMS-A",
1176 "ARABICPRESENTATIONFORMS-A");
1177
1178 /**
1179 * Constant for the "Combining Half Marks" Unicode character block.
1180 * @since 1.2
1181 */
1182 public static final UnicodeBlock COMBINING_HALF_MARKS =
1183 new UnicodeBlock("COMBINING_HALF_MARKS",
1184 "COMBINING HALF MARKS",
1185 "COMBININGHALFMARKS");
1186
1187 /**
1188 * Constant for the "CJK Compatibility Forms" Unicode character block.
1189 * @since 1.2
1190 */
1191 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1192 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1193 "CJK COMPATIBILITY FORMS",
1194 "CJKCOMPATIBILITYFORMS");
1195
1196 /**
1197 * Constant for the "Small Form Variants" Unicode character block.
1198 * @since 1.2
1199 */
1200 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1201 new UnicodeBlock("SMALL_FORM_VARIANTS",
1202 "SMALL FORM VARIANTS",
1203 "SMALLFORMVARIANTS");
1204
1205 /**
1206 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1207 * @since 1.2
1208 */
1209 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1210 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1211 "ARABIC PRESENTATION FORMS-B",
1212 "ARABICPRESENTATIONFORMS-B");
1213
1214 /**
1215 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1216 * block.
1217 * @since 1.2
1218 */
1219 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1220 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1221 "HALFWIDTH AND FULLWIDTH FORMS",
1222 "HALFWIDTHANDFULLWIDTHFORMS");
1223
1224 /**
1225 * Constant for the "Specials" Unicode character block.
1226 * @since 1.2
1227 */
1228 public static final UnicodeBlock SPECIALS =
1229 new UnicodeBlock("SPECIALS");
1230
1231 /**
1232 * @deprecated As of J2SE 5, use {@link #HIGH_SURROGATES},
1233 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and
1234 * {@link #LOW_SURROGATES}. These new constants match
1235 * the block definitions of the Unicode Standard.
1236 * The {@link #of(char)} and {@link #of(int)} methods
1237 * return the new constants, not SURROGATES_AREA.
1238 */
1239 @Deprecated
1240 public static final UnicodeBlock SURROGATES_AREA =
1241 new UnicodeBlock("SURROGATES_AREA");
1242
1243 /**
1244 * Constant for the "Syriac" Unicode character block.
1245 * @since 1.4
1246 */
1247 public static final UnicodeBlock SYRIAC =
1248 new UnicodeBlock("SYRIAC");
1249
1250 /**
1251 * Constant for the "Thaana" Unicode character block.
1252 * @since 1.4
1253 */
1254 public static final UnicodeBlock THAANA =
1255 new UnicodeBlock("THAANA");
1256
1257 /**
1258 * Constant for the "Sinhala" Unicode character block.
1259 * @since 1.4
1260 */
1261 public static final UnicodeBlock SINHALA =
1262 new UnicodeBlock("SINHALA");
1263
1264 /**
1265 * Constant for the "Myanmar" Unicode character block.
1266 * @since 1.4
1267 */
1268 public static final UnicodeBlock MYANMAR =
1269 new UnicodeBlock("MYANMAR");
1270
1271 /**
1272 * Constant for the "Ethiopic" Unicode character block.
1273 * @since 1.4
1274 */
1275 public static final UnicodeBlock ETHIOPIC =
1276 new UnicodeBlock("ETHIOPIC");
1277
1278 /**
1279 * Constant for the "Cherokee" Unicode character block.
1280 * @since 1.4
1281 */
1282 public static final UnicodeBlock CHEROKEE =
1283 new UnicodeBlock("CHEROKEE");
1284
1285 /**
1286 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1287 * @since 1.4
1288 */
1289 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1290 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1291 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1292 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1293
1294 /**
1295 * Constant for the "Ogham" Unicode character block.
1296 * @since 1.4
1297 */
1298 public static final UnicodeBlock OGHAM =
1299 new UnicodeBlock("OGHAM");
1300
1301 /**
1302 * Constant for the "Runic" Unicode character block.
1303 * @since 1.4
1304 */
1305 public static final UnicodeBlock RUNIC =
1306 new UnicodeBlock("RUNIC");
1307
1308 /**
1309 * Constant for the "Khmer" Unicode character block.
1310 * @since 1.4
1311 */
1312 public static final UnicodeBlock KHMER =
1313 new UnicodeBlock("KHMER");
1314
1315 /**
1316 * Constant for the "Mongolian" Unicode character block.
1317 * @since 1.4
1318 */
1319 public static final UnicodeBlock MONGOLIAN =
1320 new UnicodeBlock("MONGOLIAN");
1321
1322 /**
1323 * Constant for the "Braille Patterns" Unicode character block.
1324 * @since 1.4
1325 */
1326 public static final UnicodeBlock BRAILLE_PATTERNS =
1327 new UnicodeBlock("BRAILLE_PATTERNS",
1328 "BRAILLE PATTERNS",
1329 "BRAILLEPATTERNS");
1330
1331 /**
1332 * Constant for the "CJK Radicals Supplement" Unicode character block.
1333 * @since 1.4
1334 */
1335 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1336 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1337 "CJK RADICALS SUPPLEMENT",
1338 "CJKRADICALSSUPPLEMENT");
1339
1340 /**
1341 * Constant for the "Kangxi Radicals" Unicode character block.
1342 * @since 1.4
1343 */
1344 public static final UnicodeBlock KANGXI_RADICALS =
1345 new UnicodeBlock("KANGXI_RADICALS",
1346 "KANGXI RADICALS",
1347 "KANGXIRADICALS");
1348
1349 /**
1350 * Constant for the "Ideographic Description Characters" Unicode character block.
1351 * @since 1.4
1352 */
1353 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1354 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1355 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1356 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1357
1358 /**
1359 * Constant for the "Bopomofo Extended" Unicode character block.
1360 * @since 1.4
1361 */
1362 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1363 new UnicodeBlock("BOPOMOFO_EXTENDED",
1364 "BOPOMOFO EXTENDED",
1365 "BOPOMOFOEXTENDED");
1366
1367 /**
1368 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1369 * @since 1.4
1370 */
1371 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1372 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1373 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1374 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1375
1376 /**
1377 * Constant for the "Yi Syllables" Unicode character block.
1378 * @since 1.4
1379 */
1380 public static final UnicodeBlock YI_SYLLABLES =
1381 new UnicodeBlock("YI_SYLLABLES",
1382 "YI SYLLABLES",
1383 "YISYLLABLES");
1384
1385 /**
1386 * Constant for the "Yi Radicals" Unicode character block.
1387 * @since 1.4
1388 */
1389 public static final UnicodeBlock YI_RADICALS =
1390 new UnicodeBlock("YI_RADICALS",
1391 "YI RADICALS",
1392 "YIRADICALS");
1393
1394 /**
1395 * Constant for the "Cyrillic Supplementary" Unicode character block.
1396 * @since 1.5
1397 */
1398 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1399 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1400 "CYRILLIC SUPPLEMENTARY",
1401 "CYRILLICSUPPLEMENTARY",
1402 "CYRILLIC SUPPLEMENT",
1403 "CYRILLICSUPPLEMENT");
1404
1405 /**
1406 * Constant for the "Tagalog" Unicode character block.
1407 * @since 1.5
1408 */
1409 public static final UnicodeBlock TAGALOG =
1410 new UnicodeBlock("TAGALOG");
1411
1412 /**
1413 * Constant for the "Hanunoo" Unicode character block.
1414 * @since 1.5
1415 */
1416 public static final UnicodeBlock HANUNOO =
1417 new UnicodeBlock("HANUNOO");
1418
1419 /**
1420 * Constant for the "Buhid" Unicode character block.
1421 * @since 1.5
1422 */
1423 public static final UnicodeBlock BUHID =
1424 new UnicodeBlock("BUHID");
1425
1426 /**
1427 * Constant for the "Tagbanwa" Unicode character block.
1428 * @since 1.5
1429 */
1430 public static final UnicodeBlock TAGBANWA =
1431 new UnicodeBlock("TAGBANWA");
1432
1433 /**
1434 * Constant for the "Limbu" Unicode character block.
1435 * @since 1.5
1436 */
1437 public static final UnicodeBlock LIMBU =
1438 new UnicodeBlock("LIMBU");
1439
1440 /**
1441 * Constant for the "Tai Le" Unicode character block.
1442 * @since 1.5
1443 */
1444 public static final UnicodeBlock TAI_LE =
1445 new UnicodeBlock("TAI_LE",
1446 "TAI LE",
1447 "TAILE");
1448
1449 /**
1450 * Constant for the "Khmer Symbols" Unicode character block.
1451 * @since 1.5
1452 */
1453 public static final UnicodeBlock KHMER_SYMBOLS =
1454 new UnicodeBlock("KHMER_SYMBOLS",
1455 "KHMER SYMBOLS",
1456 "KHMERSYMBOLS");
1457
1458 /**
1459 * Constant for the "Phonetic Extensions" Unicode character block.
1460 * @since 1.5
1461 */
1462 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1463 new UnicodeBlock("PHONETIC_EXTENSIONS",
1464 "PHONETIC EXTENSIONS",
1465 "PHONETICEXTENSIONS");
1466
1467 /**
1468 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1469 * @since 1.5
1470 */
1471 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1472 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1473 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1474 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1475
1476 /**
1477 * Constant for the "Supplemental Arrows-A" Unicode character block.
1478 * @since 1.5
1479 */
1480 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1481 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1482 "SUPPLEMENTAL ARROWS-A",
1483 "SUPPLEMENTALARROWS-A");
1484
1485 /**
1486 * Constant for the "Supplemental Arrows-B" Unicode character block.
1487 * @since 1.5
1488 */
1489 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1490 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1491 "SUPPLEMENTAL ARROWS-B",
1492 "SUPPLEMENTALARROWS-B");
1493
1494 /**
1495 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1496 * character block.
1497 * @since 1.5
1498 */
1499 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1500 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1501 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1502 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1503
1504 /**
1505 * Constant for the "Supplemental Mathematical Operators" Unicode
1506 * character block.
1507 * @since 1.5
1508 */
1509 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1510 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1511 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1512 "SUPPLEMENTALMATHEMATICALOPERATORS");
1513
1514 /**
1515 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1516 * block.
1517 * @since 1.5
1518 */
1519 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1520 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1521 "MISCELLANEOUS SYMBOLS AND ARROWS",
1522 "MISCELLANEOUSSYMBOLSANDARROWS");
1523
1524 /**
1525 * Constant for the "Katakana Phonetic Extensions" Unicode character
1526 * block.
1527 * @since 1.5
1528 */
1529 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1530 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1531 "KATAKANA PHONETIC EXTENSIONS",
1532 "KATAKANAPHONETICEXTENSIONS");
1533
1534 /**
1535 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1536 * @since 1.5
1537 */
1538 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1539 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1540 "YIJING HEXAGRAM SYMBOLS",
1541 "YIJINGHEXAGRAMSYMBOLS");
1542
1543 /**
1544 * Constant for the "Variation Selectors" Unicode character block.
1545 * @since 1.5
1546 */
1547 public static final UnicodeBlock VARIATION_SELECTORS =
1548 new UnicodeBlock("VARIATION_SELECTORS",
1549 "VARIATION SELECTORS",
1550 "VARIATIONSELECTORS");
1551
1552 /**
1553 * Constant for the "Linear B Syllabary" Unicode character block.
1554 * @since 1.5
1555 */
1556 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1557 new UnicodeBlock("LINEAR_B_SYLLABARY",
1558 "LINEAR B SYLLABARY",
1559 "LINEARBSYLLABARY");
1560
1561 /**
1562 * Constant for the "Linear B Ideograms" Unicode character block.
1563 * @since 1.5
1564 */
1565 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1566 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1567 "LINEAR B IDEOGRAMS",
1568 "LINEARBIDEOGRAMS");
1569
1570 /**
1571 * Constant for the "Aegean Numbers" Unicode character block.
1572 * @since 1.5
1573 */
1574 public static final UnicodeBlock AEGEAN_NUMBERS =
1575 new UnicodeBlock("AEGEAN_NUMBERS",
1576 "AEGEAN NUMBERS",
1577 "AEGEANNUMBERS");
1578
1579 /**
1580 * Constant for the "Old Italic" Unicode character block.
1581 * @since 1.5
1582 */
1583 public static final UnicodeBlock OLD_ITALIC =
1584 new UnicodeBlock("OLD_ITALIC",
1585 "OLD ITALIC",
1586 "OLDITALIC");
1587
1588 /**
1589 * Constant for the "Gothic" Unicode character block.
1590 * @since 1.5
1591 */
1592 public static final UnicodeBlock GOTHIC =
1593 new UnicodeBlock("GOTHIC");
1594
1595 /**
1596 * Constant for the "Ugaritic" Unicode character block.
1597 * @since 1.5
1598 */
1599 public static final UnicodeBlock UGARITIC =
1600 new UnicodeBlock("UGARITIC");
1601
1602 /**
1603 * Constant for the "Deseret" Unicode character block.
1604 * @since 1.5
1605 */
1606 public static final UnicodeBlock DESERET =
1607 new UnicodeBlock("DESERET");
1608
1609 /**
1610 * Constant for the "Shavian" Unicode character block.
1611 * @since 1.5
1612 */
1613 public static final UnicodeBlock SHAVIAN =
1614 new UnicodeBlock("SHAVIAN");
1615
1616 /**
1617 * Constant for the "Osmanya" Unicode character block.
1618 * @since 1.5
1619 */
1620 public static final UnicodeBlock OSMANYA =
1621 new UnicodeBlock("OSMANYA");
1622
1623 /**
1624 * Constant for the "Cypriot Syllabary" Unicode character block.
1625 * @since 1.5
1626 */
1627 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1628 new UnicodeBlock("CYPRIOT_SYLLABARY",
1629 "CYPRIOT SYLLABARY",
1630 "CYPRIOTSYLLABARY");
1631
1632 /**
1633 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1634 * @since 1.5
1635 */
1636 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1637 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1638 "BYZANTINE MUSICAL SYMBOLS",
1639 "BYZANTINEMUSICALSYMBOLS");
1640
1641 /**
1642 * Constant for the "Musical Symbols" Unicode character block.
1643 * @since 1.5
1644 */
1645 public static final UnicodeBlock MUSICAL_SYMBOLS =
1646 new UnicodeBlock("MUSICAL_SYMBOLS",
1647 "MUSICAL SYMBOLS",
1648 "MUSICALSYMBOLS");
1649
1650 /**
1651 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1652 * @since 1.5
1653 */
1654 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1655 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1656 "TAI XUAN JING SYMBOLS",
1657 "TAIXUANJINGSYMBOLS");
1658
1659 /**
1660 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1661 * character block.
1662 * @since 1.5
1663 */
1664 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1665 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1666 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1667 "MATHEMATICALALPHANUMERICSYMBOLS");
1668
1669 /**
1670 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1671 * character block.
1672 * @since 1.5
1673 */
1674 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1675 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1676 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1677 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1678
1679 /**
1680 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1681 * @since 1.5
1682 */
1683 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1684 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1685 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1686 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1687
1688 /**
1689 * Constant for the "Tags" Unicode character block.
1690 * @since 1.5
1691 */
1692 public static final UnicodeBlock TAGS =
1693 new UnicodeBlock("TAGS");
1694
1695 /**
1696 * Constant for the "Variation Selectors Supplement" Unicode character
1697 * block.
1698 * @since 1.5
1699 */
1700 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1701 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1702 "VARIATION SELECTORS SUPPLEMENT",
1703 "VARIATIONSELECTORSSUPPLEMENT");
1704
1705 /**
1706 * Constant for the "Supplementary Private Use Area-A" Unicode character
1707 * block.
1708 * @since 1.5
1709 */
1710 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1711 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1712 "SUPPLEMENTARY PRIVATE USE AREA-A",
1713 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1714
1715 /**
1716 * Constant for the "Supplementary Private Use Area-B" Unicode character
1717 * block.
1718 * @since 1.5
1719 */
1720 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1721 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1722 "SUPPLEMENTARY PRIVATE USE AREA-B",
1723 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1724
1725 /**
1726 * Constant for the "High Surrogates" Unicode character block.
1727 * This block represents codepoint values in the high surrogate
1728 * range: U+D800 through U+DB7F
1729 *
1730 * @since 1.5
1731 */
1732 public static final UnicodeBlock HIGH_SURROGATES =
1733 new UnicodeBlock("HIGH_SURROGATES",
1734 "HIGH SURROGATES",
1735 "HIGHSURROGATES");
1736
1737 /**
1738 * Constant for the "High Private Use Surrogates" Unicode character
1739 * block.
1740 * This block represents codepoint values in the private use high
1741 * surrogate range: U+DB80 through U+DBFF
1742 *
1743 * @since 1.5
1744 */
1745 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1746 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1747 "HIGH PRIVATE USE SURROGATES",
1748 "HIGHPRIVATEUSESURROGATES");
1749
1750 /**
1751 * Constant for the "Low Surrogates" Unicode character block.
1752 * This block represents codepoint values in the low surrogate
1753 * range: U+DC00 through U+DFFF
1754 *
1755 * @since 1.5
1756 */
1757 public static final UnicodeBlock LOW_SURROGATES =
1758 new UnicodeBlock("LOW_SURROGATES",
1759 "LOW SURROGATES",
1760 "LOWSURROGATES");
1761
1762 /**
1763 * Constant for the "Arabic Supplement" Unicode character block.
1764 * @since 1.7
1765 */
1766 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1767 new UnicodeBlock("ARABIC_SUPPLEMENT",
1768 "ARABIC SUPPLEMENT",
1769 "ARABICSUPPLEMENT");
1770
1771 /**
1772 * Constant for the "NKo" Unicode character block.
1773 * @since 1.7
1774 */
1775 public static final UnicodeBlock NKO =
1776 new UnicodeBlock("NKO");
1777
1778 /**
1779 * Constant for the "Samaritan" Unicode character block.
1780 * @since 1.7
1781 */
1782 public static final UnicodeBlock SAMARITAN =
1783 new UnicodeBlock("SAMARITAN");
1784
1785 /**
1786 * Constant for the "Mandaic" Unicode character block.
1787 * @since 1.7
1788 */
1789 public static final UnicodeBlock MANDAIC =
1790 new UnicodeBlock("MANDAIC");
1791
1792 /**
1793 * Constant for the "Ethiopic Supplement" Unicode character block.
1794 * @since 1.7
1795 */
1796 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1797 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1798 "ETHIOPIC SUPPLEMENT",
1799 "ETHIOPICSUPPLEMENT");
1800
1801 /**
1802 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1803 * Unicode character block.
1804 * @since 1.7
1805 */
1806 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1807 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1808 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1809 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1810
1811 /**
1812 * Constant for the "New Tai Lue" Unicode character block.
1813 * @since 1.7
1814 */
1815 public static final UnicodeBlock NEW_TAI_LUE =
1816 new UnicodeBlock("NEW_TAI_LUE",
1817 "NEW TAI LUE",
1818 "NEWTAILUE");
1819
1820 /**
1821 * Constant for the "Buginese" Unicode character block.
1822 * @since 1.7
1823 */
1824 public static final UnicodeBlock BUGINESE =
1825 new UnicodeBlock("BUGINESE");
1826
1827 /**
1828 * Constant for the "Tai Tham" Unicode character block.
1829 * @since 1.7
1830 */
1831 public static final UnicodeBlock TAI_THAM =
1832 new UnicodeBlock("TAI_THAM",
1833 "TAI THAM",
1834 "TAITHAM");
1835
1836 /**
1837 * Constant for the "Balinese" Unicode character block.
1838 * @since 1.7
1839 */
1840 public static final UnicodeBlock BALINESE =
1841 new UnicodeBlock("BALINESE");
1842
1843 /**
1844 * Constant for the "Sundanese" Unicode character block.
1845 * @since 1.7
1846 */
1847 public static final UnicodeBlock SUNDANESE =
1848 new UnicodeBlock("SUNDANESE");
1849
1850 /**
1851 * Constant for the "Batak" Unicode character block.
1852 * @since 1.7
1853 */
1854 public static final UnicodeBlock BATAK =
1855 new UnicodeBlock("BATAK");
1856
1857 /**
1858 * Constant for the "Lepcha" Unicode character block.
1859 * @since 1.7
1860 */
1861 public static final UnicodeBlock LEPCHA =
1862 new UnicodeBlock("LEPCHA");
1863
1864 /**
1865 * Constant for the "Ol Chiki" Unicode character block.
1866 * @since 1.7
1867 */
1868 public static final UnicodeBlock OL_CHIKI =
1869 new UnicodeBlock("OL_CHIKI",
1870 "OL CHIKI",
1871 "OLCHIKI");
1872
1873 /**
1874 * Constant for the "Vedic Extensions" Unicode character block.
1875 * @since 1.7
1876 */
1877 public static final UnicodeBlock VEDIC_EXTENSIONS =
1878 new UnicodeBlock("VEDIC_EXTENSIONS",
1879 "VEDIC EXTENSIONS",
1880 "VEDICEXTENSIONS");
1881
1882 /**
1883 * Constant for the "Phonetic Extensions Supplement" Unicode character
1884 * block.
1885 * @since 1.7
1886 */
1887 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1888 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1889 "PHONETIC EXTENSIONS SUPPLEMENT",
1890 "PHONETICEXTENSIONSSUPPLEMENT");
1891
1892 /**
1893 * Constant for the "Combining Diacritical Marks Supplement" Unicode
1894 * character block.
1895 * @since 1.7
1896 */
1897 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1898 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1899 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1900 "COMBININGDIACRITICALMARKSSUPPLEMENT");
1901
1902 /**
1903 * Constant for the "Glagolitic" Unicode character block.
1904 * @since 1.7
1905 */
1906 public static final UnicodeBlock GLAGOLITIC =
1907 new UnicodeBlock("GLAGOLITIC");
1908
1909 /**
1910 * Constant for the "Latin Extended-C" Unicode character block.
1911 * @since 1.7
1912 */
1913 public static final UnicodeBlock LATIN_EXTENDED_C =
1914 new UnicodeBlock("LATIN_EXTENDED_C",
1915 "LATIN EXTENDED-C",
1916 "LATINEXTENDED-C");
1917
1918 /**
1919 * Constant for the "Coptic" Unicode character block.
1920 * @since 1.7
1921 */
1922 public static final UnicodeBlock COPTIC =
1923 new UnicodeBlock("COPTIC");
1924
1925 /**
1926 * Constant for the "Georgian Supplement" Unicode character block.
1927 * @since 1.7
1928 */
1929 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
1930 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
1931 "GEORGIAN SUPPLEMENT",
1932 "GEORGIANSUPPLEMENT");
1933
1934 /**
1935 * Constant for the "Tifinagh" Unicode character block.
1936 * @since 1.7
1937 */
1938 public static final UnicodeBlock TIFINAGH =
1939 new UnicodeBlock("TIFINAGH");
1940
1941 /**
1942 * Constant for the "Ethiopic Extended" Unicode character block.
1943 * @since 1.7
1944 */
1945 public static final UnicodeBlock ETHIOPIC_EXTENDED =
1946 new UnicodeBlock("ETHIOPIC_EXTENDED",
1947 "ETHIOPIC EXTENDED",
1948 "ETHIOPICEXTENDED");
1949
1950 /**
1951 * Constant for the "Cyrillic Extended-A" Unicode character block.
1952 * @since 1.7
1953 */
1954 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
1955 new UnicodeBlock("CYRILLIC_EXTENDED_A",
1956 "CYRILLIC EXTENDED-A",
1957 "CYRILLICEXTENDED-A");
1958
1959 /**
1960 * Constant for the "Supplemental Punctuation" Unicode character block.
1961 * @since 1.7
1962 */
1963 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
1964 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
1965 "SUPPLEMENTAL PUNCTUATION",
1966 "SUPPLEMENTALPUNCTUATION");
1967
1968 /**
1969 * Constant for the "CJK Strokes" Unicode character block.
1970 * @since 1.7
1971 */
1972 public static final UnicodeBlock CJK_STROKES =
1973 new UnicodeBlock("CJK_STROKES",
1974 "CJK STROKES",
1975 "CJKSTROKES");
1976
1977 /**
1978 * Constant for the "Lisu" Unicode character block.
1979 * @since 1.7
1980 */
1981 public static final UnicodeBlock LISU =
1982 new UnicodeBlock("LISU");
1983
1984 /**
1985 * Constant for the "Vai" Unicode character block.
1986 * @since 1.7
1987 */
1988 public static final UnicodeBlock VAI =
1989 new UnicodeBlock("VAI");
1990
1991 /**
1992 * Constant for the "Cyrillic Extended-B" Unicode character block.
1993 * @since 1.7
1994 */
1995 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
1996 new UnicodeBlock("CYRILLIC_EXTENDED_B",
1997 "CYRILLIC EXTENDED-B",
1998 "CYRILLICEXTENDED-B");
1999
2000 /**
2001 * Constant for the "Bamum" Unicode character block.
2002 * @since 1.7
2003 */
2004 public static final UnicodeBlock BAMUM =
2005 new UnicodeBlock("BAMUM");
2006
2007 /**
2008 * Constant for the "Modifier Tone Letters" Unicode character block.
2009 * @since 1.7
2010 */
2011 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2012 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2013 "MODIFIER TONE LETTERS",
2014 "MODIFIERTONELETTERS");
2015
2016 /**
2017 * Constant for the "Latin Extended-D" Unicode character block.
2018 * @since 1.7
2019 */
2020 public static final UnicodeBlock LATIN_EXTENDED_D =
2021 new UnicodeBlock("LATIN_EXTENDED_D",
2022 "LATIN EXTENDED-D",
2023 "LATINEXTENDED-D");
2024
2025 /**
2026 * Constant for the "Syloti Nagri" Unicode character block.
2027 * @since 1.7
2028 */
2029 public static final UnicodeBlock SYLOTI_NAGRI =
2030 new UnicodeBlock("SYLOTI_NAGRI",
2031 "SYLOTI NAGRI",
2032 "SYLOTINAGRI");
2033
2034 /**
2035 * Constant for the "Common Indic Number Forms" Unicode character block.
2036 * @since 1.7
2037 */
2038 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2039 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2040 "COMMON INDIC NUMBER FORMS",
2041 "COMMONINDICNUMBERFORMS");
2042
2043 /**
2044 * Constant for the "Phags-pa" Unicode character block.
2045 * @since 1.7
2046 */
2047 public static final UnicodeBlock PHAGS_PA =
2048 new UnicodeBlock("PHAGS_PA",
2049 "PHAGS-PA");
2050
2051 /**
2052 * Constant for the "Saurashtra" Unicode character block.
2053 * @since 1.7
2054 */
2055 public static final UnicodeBlock SAURASHTRA =
2056 new UnicodeBlock("SAURASHTRA");
2057
2058 /**
2059 * Constant for the "Devanagari Extended" Unicode character block.
2060 * @since 1.7
2061 */
2062 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2063 new UnicodeBlock("DEVANAGARI_EXTENDED",
2064 "DEVANAGARI EXTENDED",
2065 "DEVANAGARIEXTENDED");
2066
2067 /**
2068 * Constant for the "Kayah Li" Unicode character block.
2069 * @since 1.7
2070 */
2071 public static final UnicodeBlock KAYAH_LI =
2072 new UnicodeBlock("KAYAH_LI",
2073 "KAYAH LI",
2074 "KAYAHLI");
2075
2076 /**
2077 * Constant for the "Rejang" Unicode character block.
2078 * @since 1.7
2079 */
2080 public static final UnicodeBlock REJANG =
2081 new UnicodeBlock("REJANG");
2082
2083 /**
2084 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2085 * @since 1.7
2086 */
2087 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2088 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2089 "HANGUL JAMO EXTENDED-A",
2090 "HANGULJAMOEXTENDED-A");
2091
2092 /**
2093 * Constant for the "Javanese" Unicode character block.
2094 * @since 1.7
2095 */
2096 public static final UnicodeBlock JAVANESE =
2097 new UnicodeBlock("JAVANESE");
2098
2099 /**
2100 * Constant for the "Cham" Unicode character block.
2101 * @since 1.7
2102 */
2103 public static final UnicodeBlock CHAM =
2104 new UnicodeBlock("CHAM");
2105
2106 /**
2107 * Constant for the "Myanmar Extended-A" Unicode character block.
2108 * @since 1.7
2109 */
2110 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2111 new UnicodeBlock("MYANMAR_EXTENDED_A",
2112 "MYANMAR EXTENDED-A",
2113 "MYANMAREXTENDED-A");
2114
2115 /**
2116 * Constant for the "Tai Viet" Unicode character block.
2117 * @since 1.7
2118 */
2119 public static final UnicodeBlock TAI_VIET =
2120 new UnicodeBlock("TAI_VIET",
2121 "TAI VIET",
2122 "TAIVIET");
2123
2124 /**
2125 * Constant for the "Ethiopic Extended-A" Unicode character block.
2126 * @since 1.7
2127 */
2128 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2129 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2130 "ETHIOPIC EXTENDED-A",
2131 "ETHIOPICEXTENDED-A");
2132
2133 /**
2134 * Constant for the "Meetei Mayek" Unicode character block.
2135 * @since 1.7
2136 */
2137 public static final UnicodeBlock MEETEI_MAYEK =
2138 new UnicodeBlock("MEETEI_MAYEK",
2139 "MEETEI MAYEK",
2140 "MEETEIMAYEK");
2141
2142 /**
2143 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2144 * @since 1.7
2145 */
2146 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2147 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2148 "HANGUL JAMO EXTENDED-B",
2149 "HANGULJAMOEXTENDED-B");
2150
2151 /**
2152 * Constant for the "Vertical Forms" Unicode character block.
2153 * @since 1.7
2154 */
2155 public static final UnicodeBlock VERTICAL_FORMS =
2156 new UnicodeBlock("VERTICAL_FORMS",
2157 "VERTICAL FORMS",
2158 "VERTICALFORMS");
2159
2160 /**
2161 * Constant for the "Ancient Greek Numbers" Unicode character block.
2162 * @since 1.7
2163 */
2164 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2165 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2166 "ANCIENT GREEK NUMBERS",
2167 "ANCIENTGREEKNUMBERS");
2168
2169 /**
2170 * Constant for the "Ancient Symbols" Unicode character block.
2171 * @since 1.7
2172 */
2173 public static final UnicodeBlock ANCIENT_SYMBOLS =
2174 new UnicodeBlock("ANCIENT_SYMBOLS",
2175 "ANCIENT SYMBOLS",
2176 "ANCIENTSYMBOLS");
2177
2178 /**
2179 * Constant for the "Phaistos Disc" Unicode character block.
2180 * @since 1.7
2181 */
2182 public static final UnicodeBlock PHAISTOS_DISC =
2183 new UnicodeBlock("PHAISTOS_DISC",
2184 "PHAISTOS DISC",
2185 "PHAISTOSDISC");
2186
2187 /**
2188 * Constant for the "Lycian" Unicode character block.
2189 * @since 1.7
2190 */
2191 public static final UnicodeBlock LYCIAN =
2192 new UnicodeBlock("LYCIAN");
2193
2194 /**
2195 * Constant for the "Carian" Unicode character block.
2196 * @since 1.7
2197 */
2198 public static final UnicodeBlock CARIAN =
2199 new UnicodeBlock("CARIAN");
2200
2201 /**
2202 * Constant for the "Old Persian" Unicode character block.
2203 * @since 1.7
2204 */
2205 public static final UnicodeBlock OLD_PERSIAN =
2206 new UnicodeBlock("OLD_PERSIAN",
2207 "OLD PERSIAN",
2208 "OLDPERSIAN");
2209
2210 /**
2211 * Constant for the "Imperial Aramaic" Unicode character block.
2212 * @since 1.7
2213 */
2214 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2215 new UnicodeBlock("IMPERIAL_ARAMAIC",
2216 "IMPERIAL ARAMAIC",
2217 "IMPERIALARAMAIC");
2218
2219 /**
2220 * Constant for the "Phoenician" Unicode character block.
2221 * @since 1.7
2222 */
2223 public static final UnicodeBlock PHOENICIAN =
2224 new UnicodeBlock("PHOENICIAN");
2225
2226 /**
2227 * Constant for the "Lydian" Unicode character block.
2228 * @since 1.7
2229 */
2230 public static final UnicodeBlock LYDIAN =
2231 new UnicodeBlock("LYDIAN");
2232
2233 /**
2234 * Constant for the "Kharoshthi" Unicode character block.
2235 * @since 1.7
2236 */
2237 public static final UnicodeBlock KHAROSHTHI =
2238 new UnicodeBlock("KHAROSHTHI");
2239
2240 /**
2241 * Constant for the "Old South Arabian" Unicode character block.
2242 * @since 1.7
2243 */
2244 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2245 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2246 "OLD SOUTH ARABIAN",
2247 "OLDSOUTHARABIAN");
2248
2249 /**
2250 * Constant for the "Avestan" Unicode character block.
2251 * @since 1.7
2252 */
2253 public static final UnicodeBlock AVESTAN =
2254 new UnicodeBlock("AVESTAN");
2255
2256 /**
2257 * Constant for the "Inscriptional Parthian" Unicode character block.
2258 * @since 1.7
2259 */
2260 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2261 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2262 "INSCRIPTIONAL PARTHIAN",
2263 "INSCRIPTIONALPARTHIAN");
2264
2265 /**
2266 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2267 * @since 1.7
2268 */
2269 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2270 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2271 "INSCRIPTIONAL PAHLAVI",
2272 "INSCRIPTIONALPAHLAVI");
2273
2274 /**
2275 * Constant for the "Old Turkic" Unicode character block.
2276 * @since 1.7
2277 */
2278 public static final UnicodeBlock OLD_TURKIC =
2279 new UnicodeBlock("OLD_TURKIC",
2280 "OLD TURKIC",
2281 "OLDTURKIC");
2282
2283 /**
2284 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2285 * @since 1.7
2286 */
2287 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2288 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2289 "RUMI NUMERAL SYMBOLS",
2290 "RUMINUMERALSYMBOLS");
2291
2292 /**
2293 * Constant for the "Brahmi" Unicode character block.
2294 * @since 1.7
2295 */
2296 public static final UnicodeBlock BRAHMI =
2297 new UnicodeBlock("BRAHMI");
2298
2299 /**
2300 * Constant for the "Kaithi" Unicode character block.
2301 * @since 1.7
2302 */
2303 public static final UnicodeBlock KAITHI =
2304 new UnicodeBlock("KAITHI");
2305
2306 /**
2307 * Constant for the "Cuneiform" Unicode character block.
2308 * @since 1.7
2309 */
2310 public static final UnicodeBlock CUNEIFORM =
2311 new UnicodeBlock("CUNEIFORM");
2312
2313 /**
2314 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2315 * character block.
2316 * @since 1.7
2317 */
2318 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2319 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2320 "CUNEIFORM NUMBERS AND PUNCTUATION",
2321 "CUNEIFORMNUMBERSANDPUNCTUATION");
2322
2323 /**
2324 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2325 * @since 1.7
2326 */
2327 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2328 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2329 "EGYPTIAN HIEROGLYPHS",
2330 "EGYPTIANHIEROGLYPHS");
2331
2332 /**
2333 * Constant for the "Bamum Supplement" Unicode character block.
2334 * @since 1.7
2335 */
2336 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2337 new UnicodeBlock("BAMUM_SUPPLEMENT",
2338 "BAMUM SUPPLEMENT",
2339 "BAMUMSUPPLEMENT");
2340
2341 /**
2342 * Constant for the "Kana Supplement" Unicode character block.
2343 * @since 1.7
2344 */
2345 public static final UnicodeBlock KANA_SUPPLEMENT =
2346 new UnicodeBlock("KANA_SUPPLEMENT",
2347 "KANA SUPPLEMENT",
2348 "KANASUPPLEMENT");
2349
2350 /**
2351 * Constant for the "Ancient Greek Musical Notation" Unicode character
2352 * block.
2353 * @since 1.7
2354 */
2355 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2356 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2357 "ANCIENT GREEK MUSICAL NOTATION",
2358 "ANCIENTGREEKMUSICALNOTATION");
2359
2360 /**
2361 * Constant for the "Counting Rod Numerals" Unicode character block.
2362 * @since 1.7
2363 */
2364 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2365 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2366 "COUNTING ROD NUMERALS",
2367 "COUNTINGRODNUMERALS");
2368
2369 /**
2370 * Constant for the "Mahjong Tiles" Unicode character block.
2371 * @since 1.7
2372 */
2373 public static final UnicodeBlock MAHJONG_TILES =
2374 new UnicodeBlock("MAHJONG_TILES",
2375 "MAHJONG TILES",
2376 "MAHJONGTILES");
2377
2378 /**
2379 * Constant for the "Domino Tiles" Unicode character block.
2380 * @since 1.7
2381 */
2382 public static final UnicodeBlock DOMINO_TILES =
2383 new UnicodeBlock("DOMINO_TILES",
2384 "DOMINO TILES",
2385 "DOMINOTILES");
2386
2387 /**
2388 * Constant for the "Playing Cards" Unicode character block.
2389 * @since 1.7
2390 */
2391 public static final UnicodeBlock PLAYING_CARDS =
2392 new UnicodeBlock("PLAYING_CARDS",
2393 "PLAYING CARDS",
2394 "PLAYINGCARDS");
2395
2396 /**
2397 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2398 * block.
2399 * @since 1.7
2400 */
2401 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2402 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2403 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2404 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2405
2406 /**
2407 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2408 * block.
2409 * @since 1.7
2410 */
2411 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2412 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2413 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2414 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2415
2416 /**
2417 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2418 * character block.
2419 * @since 1.7
2420 */
2421 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2422 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2423 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2424 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2425
2426 /**
2427 * Constant for the "Emoticons" Unicode character block.
2428 * @since 1.7
2429 */
2430 public static final UnicodeBlock EMOTICONS =
2431 new UnicodeBlock("EMOTICONS");
2432
2433 /**
2434 * Constant for the "Transport And Map Symbols" Unicode character block.
2435 * @since 1.7
2436 */
2437 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2438 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2439 "TRANSPORT AND MAP SYMBOLS",
2440 "TRANSPORTANDMAPSYMBOLS");
2441
2442 /**
2443 * Constant for the "Alchemical Symbols" Unicode character block.
2444 * @since 1.7
2445 */
2446 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2447 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2448 "ALCHEMICAL SYMBOLS",
2449 "ALCHEMICALSYMBOLS");
2450
2451 /**
2452 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2453 * character block.
2454 * @since 1.7
2455 */
2456 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2457 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2458 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2459 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2460
2461 /**
2462 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2463 * character block.
2464 * @since 1.7
2465 */
2466 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2467 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2468 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2469 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2470
2471 private static final int blockStarts[] = {
2472 0x0000, // 0000..007F; Basic Latin
2473 0x0080, // 0080..00FF; Latin-1 Supplement
2474 0x0100, // 0100..017F; Latin Extended-A
2475 0x0180, // 0180..024F; Latin Extended-B
2476 0x0250, // 0250..02AF; IPA Extensions
2477 0x02B0, // 02B0..02FF; Spacing Modifier Letters
2478 0x0300, // 0300..036F; Combining Diacritical Marks
2479 0x0370, // 0370..03FF; Greek and Coptic
2480 0x0400, // 0400..04FF; Cyrillic
2481 0x0500, // 0500..052F; Cyrillic Supplement
2482 0x0530, // 0530..058F; Armenian
2483 0x0590, // 0590..05FF; Hebrew
2484 0x0600, // 0600..06FF; Arabic
2485 0x0700, // 0700..074F; Syriac
2486 0x0750, // 0750..077F; Arabic Supplement
2487 0x0780, // 0780..07BF; Thaana
2488 0x07C0, // 07C0..07FF; NKo
2489 0x0800, // 0800..083F; Samaritan
2490 0x0840, // 0840..085F; Mandaic
2491 0x0860, // unassigned
2492 0x0900, // 0900..097F; Devanagari
2493 0x0980, // 0980..09FF; Bengali
2494 0x0A00, // 0A00..0A7F; Gurmukhi
2495 0x0A80, // 0A80..0AFF; Gujarati
2496 0x0B00, // 0B00..0B7F; Oriya
2497 0x0B80, // 0B80..0BFF; Tamil
2498 0x0C00, // 0C00..0C7F; Telugu
2499 0x0C80, // 0C80..0CFF; Kannada
2500 0x0D00, // 0D00..0D7F; Malayalam
2501 0x0D80, // 0D80..0DFF; Sinhala
2502 0x0E00, // 0E00..0E7F; Thai
2503 0x0E80, // 0E80..0EFF; Lao
2504 0x0F00, // 0F00..0FFF; Tibetan
2505 0x1000, // 1000..109F; Myanmar
2506 0x10A0, // 10A0..10FF; Georgian
2507 0x1100, // 1100..11FF; Hangul Jamo
2508 0x1200, // 1200..137F; Ethiopic
2509 0x1380, // 1380..139F; Ethiopic Supplement
2510 0x13A0, // 13A0..13FF; Cherokee
2511 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
2512 0x1680, // 1680..169F; Ogham
2513 0x16A0, // 16A0..16FF; Runic
2514 0x1700, // 1700..171F; Tagalog
2515 0x1720, // 1720..173F; Hanunoo
2516 0x1740, // 1740..175F; Buhid
2517 0x1760, // 1760..177F; Tagbanwa
2518 0x1780, // 1780..17FF; Khmer
2519 0x1800, // 1800..18AF; Mongolian
2520 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
2521 0x1900, // 1900..194F; Limbu
2522 0x1950, // 1950..197F; Tai Le
2523 0x1980, // 1980..19DF; New Tai Lue
2524 0x19E0, // 19E0..19FF; Khmer Symbols
2525 0x1A00, // 1A00..1A1F; Buginese
2526 0x1A20, // 1A20..1AAF; Tai Tham
2527 0x1AB0, // unassigned
2528 0x1B00, // 1B00..1B7F; Balinese
2529 0x1B80, // 1B80..1BBF; Sundanese
2530 0x1BC0, // 1BC0..1BFF; Batak
2531 0x1C00, // 1C00..1C4F; Lepcha
2532 0x1C50, // 1C50..1C7F; Ol Chiki
2533 0x1C80, // unassigned
2534 0x1CD0, // 1CD0..1CFF; Vedic Extensions
2535 0x1D00, // 1D00..1D7F; Phonetic Extensions
2536 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
2537 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
2538 0x1E00, // 1E00..1EFF; Latin Extended Additional
2539 0x1F00, // 1F00..1FFF; Greek Extended
2540 0x2000, // 2000..206F; General Punctuation
2541 0x2070, // 2070..209F; Superscripts and Subscripts
2542 0x20A0, // 20A0..20CF; Currency Symbols
2543 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
2544 0x2100, // 2100..214F; Letterlike Symbols
2545 0x2150, // 2150..218F; Number Forms
2546 0x2190, // 2190..21FF; Arrows
2547 0x2200, // 2200..22FF; Mathematical Operators
2548 0x2300, // 2300..23FF; Miscellaneous Technical
2549 0x2400, // 2400..243F; Control Pictures
2550 0x2440, // 2440..245F; Optical Character Recognition
2551 0x2460, // 2460..24FF; Enclosed Alphanumerics
2552 0x2500, // 2500..257F; Box Drawing
2553 0x2580, // 2580..259F; Block Elements
2554 0x25A0, // 25A0..25FF; Geometric Shapes
2555 0x2600, // 2600..26FF; Miscellaneous Symbols
2556 0x2700, // 2700..27BF; Dingbats
2557 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
2558 0x27F0, // 27F0..27FF; Supplemental Arrows-A
2559 0x2800, // 2800..28FF; Braille Patterns
2560 0x2900, // 2900..297F; Supplemental Arrows-B
2561 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
2562 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
2563 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
2564 0x2C00, // 2C00..2C5F; Glagolitic
2565 0x2C60, // 2C60..2C7F; Latin Extended-C
2566 0x2C80, // 2C80..2CFF; Coptic
2567 0x2D00, // 2D00..2D2F; Georgian Supplement
2568 0x2D30, // 2D30..2D7F; Tifinagh
2569 0x2D80, // 2D80..2DDF; Ethiopic Extended
2570 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
2571 0x2E00, // 2E00..2E7F; Supplemental Punctuation
2572 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
2573 0x2F00, // 2F00..2FDF; Kangxi Radicals
2574 0x2FE0, // unassigned
2575 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
2576 0x3000, // 3000..303F; CJK Symbols and Punctuation
2577 0x3040, // 3040..309F; Hiragana
2578 0x30A0, // 30A0..30FF; Katakana
2579 0x3100, // 3100..312F; Bopomofo
2580 0x3130, // 3130..318F; Hangul Compatibility Jamo
2581 0x3190, // 3190..319F; Kanbun
2582 0x31A0, // 31A0..31BF; Bopomofo Extended
2583 0x31C0, // 31C0..31EF; CJK Strokes
2584 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
2585 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
2586 0x3300, // 3300..33FF; CJK Compatibility
2587 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
2588 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
2589 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
2590 0xA000, // A000..A48F; Yi Syllables
2591 0xA490, // A490..A4CF; Yi Radicals
2592 0xA4D0, // A4D0..A4FF; Lisu
2593 0xA500, // A500..A63F; Vai
2594 0xA640, // A640..A69F; Cyrillic Extended-B
2595 0xA6A0, // A6A0..A6FF; Bamum
2596 0xA700, // A700..A71F; Modifier Tone Letters
2597 0xA720, // A720..A7FF; Latin Extended-D
2598 0xA800, // A800..A82F; Syloti Nagri
2599 0xA830, // A830..A83F; Common Indic Number Forms
2600 0xA840, // A840..A87F; Phags-pa
2601 0xA880, // A880..A8DF; Saurashtra
2602 0xA8E0, // A8E0..A8FF; Devanagari Extended
2603 0xA900, // A900..A92F; Kayah Li
2604 0xA930, // A930..A95F; Rejang
2605 0xA960, // A960..A97F; Hangul Jamo Extended-A
2606 0xA980, // A980..A9DF; Javanese
2607 0xA9E0, // unassigned
2608 0xAA00, // AA00..AA5F; Cham
2609 0xAA60, // AA60..AA7F; Myanmar Extended-A
2610 0xAA80, // AA80..AADF; Tai Viet
2611 0xAAE0, // unassigned
2612 0xAB00, // AB00..AB2F; Ethiopic Extended-A
2613 0xAB30, // unassigned
2614 0xABC0, // ABC0..ABFF; Meetei Mayek
2615 0xAC00, // AC00..D7AF; Hangul Syllables
2616 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
2617 0xD800, // D800..DB7F; High Surrogates
2618 0xDB80, // DB80..DBFF; High Private Use Surrogates
2619 0xDC00, // DC00..DFFF; Low Surrogates
2620 0xE000, // E000..F8FF; Private Use Area
2621 0xF900, // F900..FAFF; CJK Compatibility Ideographs
2622 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
2623 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
2624 0xFE00, // FE00..FE0F; Variation Selectors
2625 0xFE10, // FE10..FE1F; Vertical Forms
2626 0xFE20, // FE20..FE2F; Combining Half Marks
2627 0xFE30, // FE30..FE4F; CJK Compatibility Forms
2628 0xFE50, // FE50..FE6F; Small Form Variants
2629 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
2630 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
2631 0xFFF0, // FFF0..FFFF; Specials
2632 0x10000, // 10000..1007F; Linear B Syllabary
2633 0x10080, // 10080..100FF; Linear B Ideograms
2634 0x10100, // 10100..1013F; Aegean Numbers
2635 0x10140, // 10140..1018F; Ancient Greek Numbers
2636 0x10190, // 10190..101CF; Ancient Symbols
2637 0x101D0, // 101D0..101FF; Phaistos Disc
2638 0x10200, // unassigned
2639 0x10280, // 10280..1029F; Lycian
2640 0x102A0, // 102A0..102DF; Carian
2641 0x102E0, // unassigned
2642 0x10300, // 10300..1032F; Old Italic
2643 0x10330, // 10330..1034F; Gothic
2644 0x10350, // unassigned
2645 0x10380, // 10380..1039F; Ugaritic
2646 0x103A0, // 103A0..103DF; Old Persian
2647 0x103E0, // unassigned
2648 0x10400, // 10400..1044F; Deseret
2649 0x10450, // 10450..1047F; Shavian
2650 0x10480, // 10480..104AF; Osmanya
2651 0x104B0, // unassigned
2652 0x10800, // 10800..1083F; Cypriot Syllabary
2653 0x10840, // 10840..1085F; Imperial Aramaic
2654 0x10860, // unassigned
2655 0x10900, // 10900..1091F; Phoenician
2656 0x10920, // 10920..1093F; Lydian
2657 0x10940, // unassigned
2658 0x10A00, // 10A00..10A5F; Kharoshthi
2659 0x10A60, // 10A60..10A7F; Old South Arabian
2660 0x10A80, // unassigned
2661 0x10B00, // 10B00..10B3F; Avestan
2662 0x10B40, // 10B40..10B5F; Inscriptional Parthian
2663 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
2664 0x10B80, // unassigned
2665 0x10C00, // 10C00..10C4F; Old Turkic
2666 0x10C50, // unassigned
2667 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
2668 0x10E80, // unassigned
2669 0x11000, // 11000..1107F; Brahmi
2670 0x11080, // 11080..110CF; Kaithi
2671 0x110D0, // unassigned
2672 0x12000, // 12000..123FF; Cuneiform
2673 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
2674 0x12480, // unassigned
2675 0x13000, // 13000..1342F; Egyptian Hieroglyphs
2676 0x13430, // unassigned
2677 0x16800, // 16800..16A3F; Bamum Supplement
2678 0x16A40, // unassigned
2679 0x1B000, // 1B000..1B0FF; Kana Supplement
2680 0x1B100, // unassigned
2681 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
2682 0x1D100, // 1D100..1D1FF; Musical Symbols
2683 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
2684 0x1D250, // unassigned
2685 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
2686 0x1D360, // 1D360..1D37F; Counting Rod Numerals
2687 0x1D380, // unassigned
2688 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
2689 0x1D800, // unassigned
2690 0x1F000, // 1F000..1F02F; Mahjong Tiles
2691 0x1F030, // 1F030..1F09F; Domino Tiles
2692 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
2693 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
2694 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
2695 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols And Pictographs
2696 0x1F600, // 1F600..1F64F; Emoticons
2697 0x1F650, // unassigned
2698 0x1F680, // 1F680..1F6FF; Transport And Map Symbols
2699 0x1F700, // 1F700..1F77F; Alchemical Symbols
2700 0x1F780, // unassigned
2701 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
2702 0x2A6E0, // unassigned
2703 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
2704 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
2705 0x2B820, // unassigned
2706 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
2707 0x2FA20, // unassigned
2708 0xE0000, // E0000..E007F; Tags
2709 0xE0080, // unassigned
2710 0xE0100, // E0100..E01EF; Variation Selectors Supplement
2711 0xE01F0, // unassigned
2712 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
2713 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B
2714 };
2715
2716 private static final UnicodeBlock[] blocks = {
2717 BASIC_LATIN,
2718 LATIN_1_SUPPLEMENT,
2719 LATIN_EXTENDED_A,
2720 LATIN_EXTENDED_B,
2721 IPA_EXTENSIONS,
2722 SPACING_MODIFIER_LETTERS,
2723 COMBINING_DIACRITICAL_MARKS,
2724 GREEK,
2725 CYRILLIC,
2726 CYRILLIC_SUPPLEMENTARY,
2727 ARMENIAN,
2728 HEBREW,
2729 ARABIC,
2730 SYRIAC,
2731 ARABIC_SUPPLEMENT,
2732 THAANA,
2733 NKO,
2734 SAMARITAN,
2735 MANDAIC,
2736 null,
2737 DEVANAGARI,
2738 BENGALI,
2739 GURMUKHI,
2740 GUJARATI,
2741 ORIYA,
2742 TAMIL,
2743 TELUGU,
2744 KANNADA,
2745 MALAYALAM,
2746 SINHALA,
2747 THAI,
2748 LAO,
2749 TIBETAN,
2750 MYANMAR,
2751 GEORGIAN,
2752 HANGUL_JAMO,
2753 ETHIOPIC,
2754 ETHIOPIC_SUPPLEMENT,
2755 CHEROKEE,
2756 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
2757 OGHAM,
2758 RUNIC,
2759 TAGALOG,
2760 HANUNOO,
2761 BUHID,
2762 TAGBANWA,
2763 KHMER,
2764 MONGOLIAN,
2765 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
2766 LIMBU,
2767 TAI_LE,
2768 NEW_TAI_LUE,
2769 KHMER_SYMBOLS,
2770 BUGINESE,
2771 TAI_THAM,
2772 null,
2773 BALINESE,
2774 SUNDANESE,
2775 BATAK,
2776 LEPCHA,
2777 OL_CHIKI,
2778 null,
2779 VEDIC_EXTENSIONS,
2780 PHONETIC_EXTENSIONS,
2781 PHONETIC_EXTENSIONS_SUPPLEMENT,
2782 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
2783 LATIN_EXTENDED_ADDITIONAL,
2784 GREEK_EXTENDED,
2785 GENERAL_PUNCTUATION,
2786 SUPERSCRIPTS_AND_SUBSCRIPTS,
2787 CURRENCY_SYMBOLS,
2788 COMBINING_MARKS_FOR_SYMBOLS,
2789 LETTERLIKE_SYMBOLS,
2790 NUMBER_FORMS,
2791 ARROWS,
2792 MATHEMATICAL_OPERATORS,
2793 MISCELLANEOUS_TECHNICAL,
2794 CONTROL_PICTURES,
2795 OPTICAL_CHARACTER_RECOGNITION,
2796 ENCLOSED_ALPHANUMERICS,
2797 BOX_DRAWING,
2798 BLOCK_ELEMENTS,
2799 GEOMETRIC_SHAPES,
2800 MISCELLANEOUS_SYMBOLS,
2801 DINGBATS,
2802 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
2803 SUPPLEMENTAL_ARROWS_A,
2804 BRAILLE_PATTERNS,
2805 SUPPLEMENTAL_ARROWS_B,
2806 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
2807 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
2808 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
2809 GLAGOLITIC,
2810 LATIN_EXTENDED_C,
2811 COPTIC,
2812 GEORGIAN_SUPPLEMENT,
2813 TIFINAGH,
2814 ETHIOPIC_EXTENDED,
2815 CYRILLIC_EXTENDED_A,
2816 SUPPLEMENTAL_PUNCTUATION,
2817 CJK_RADICALS_SUPPLEMENT,
2818 KANGXI_RADICALS,
2819 null,
2820 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
2821 CJK_SYMBOLS_AND_PUNCTUATION,
2822 HIRAGANA,
2823 KATAKANA,
2824 BOPOMOFO,
2825 HANGUL_COMPATIBILITY_JAMO,
2826 KANBUN,
2827 BOPOMOFO_EXTENDED,
2828 CJK_STROKES,
2829 KATAKANA_PHONETIC_EXTENSIONS,
2830 ENCLOSED_CJK_LETTERS_AND_MONTHS,
2831 CJK_COMPATIBILITY,
2832 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
2833 YIJING_HEXAGRAM_SYMBOLS,
2834 CJK_UNIFIED_IDEOGRAPHS,
2835 YI_SYLLABLES,
2836 YI_RADICALS,
2837 LISU,
2838 VAI,
2839 CYRILLIC_EXTENDED_B,
2840 BAMUM,
2841 MODIFIER_TONE_LETTERS,
2842 LATIN_EXTENDED_D,
2843 SYLOTI_NAGRI,
2844 COMMON_INDIC_NUMBER_FORMS,
2845 PHAGS_PA,
2846 SAURASHTRA,
2847 DEVANAGARI_EXTENDED,
2848 KAYAH_LI,
2849 REJANG,
2850 HANGUL_JAMO_EXTENDED_A,
2851 JAVANESE,
2852 null,
2853 CHAM,
2854 MYANMAR_EXTENDED_A,
2855 TAI_VIET,
2856 null,
2857 ETHIOPIC_EXTENDED_A,
2858 null,
2859 MEETEI_MAYEK,
2860 HANGUL_SYLLABLES,
2861 HANGUL_JAMO_EXTENDED_B,
2862 HIGH_SURROGATES,
2863 HIGH_PRIVATE_USE_SURROGATES,
2864 LOW_SURROGATES,
2865 PRIVATE_USE_AREA,
2866 CJK_COMPATIBILITY_IDEOGRAPHS,
2867 ALPHABETIC_PRESENTATION_FORMS,
2868 ARABIC_PRESENTATION_FORMS_A,
2869 VARIATION_SELECTORS,
2870 VERTICAL_FORMS,
2871 COMBINING_HALF_MARKS,
2872 CJK_COMPATIBILITY_FORMS,
2873 SMALL_FORM_VARIANTS,
2874 ARABIC_PRESENTATION_FORMS_B,
2875 HALFWIDTH_AND_FULLWIDTH_FORMS,
2876 SPECIALS,
2877 LINEAR_B_SYLLABARY,
2878 LINEAR_B_IDEOGRAMS,
2879 AEGEAN_NUMBERS,
2880 ANCIENT_GREEK_NUMBERS,
2881 ANCIENT_SYMBOLS,
2882 PHAISTOS_DISC,
2883 null,
2884 LYCIAN,
2885 CARIAN,
2886 null,
2887 OLD_ITALIC,
2888 GOTHIC,
2889 null,
2890 UGARITIC,
2891 OLD_PERSIAN,
2892 null,
2893 DESERET,
2894 SHAVIAN,
2895 OSMANYA,
2896 null,
2897 CYPRIOT_SYLLABARY,
2898 IMPERIAL_ARAMAIC,
2899 null,
2900 PHOENICIAN,
2901 LYDIAN,
2902 null,
2903 KHAROSHTHI,
2904 OLD_SOUTH_ARABIAN,
2905 null,
2906 AVESTAN,
2907 INSCRIPTIONAL_PARTHIAN,
2908 INSCRIPTIONAL_PAHLAVI,
2909 null,
2910 OLD_TURKIC,
2911 null,
2912 RUMI_NUMERAL_SYMBOLS,
2913 null,
2914 BRAHMI,
2915 KAITHI,
2916 null,
2917 CUNEIFORM,
2918 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
2919 null,
2920 EGYPTIAN_HIEROGLYPHS,
2921 null,
2922 BAMUM_SUPPLEMENT,
2923 null,
2924 KANA_SUPPLEMENT,
2925 null,
2926 BYZANTINE_MUSICAL_SYMBOLS,
2927 MUSICAL_SYMBOLS,
2928 ANCIENT_GREEK_MUSICAL_NOTATION,
2929 null,
2930 TAI_XUAN_JING_SYMBOLS,
2931 COUNTING_ROD_NUMERALS,
2932 null,
2933 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
2934 null,
2935 MAHJONG_TILES,
2936 DOMINO_TILES,
2937 PLAYING_CARDS,
2938 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
2939 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
2940 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
2941 EMOTICONS,
2942 null,
2943 TRANSPORT_AND_MAP_SYMBOLS,
2944 ALCHEMICAL_SYMBOLS,
2945 null,
2946 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
2947 null,
2948 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
2949 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
2950 null,
2951 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
2952 null,
2953 TAGS,
2954 null,
2955 VARIATION_SELECTORS_SUPPLEMENT,
2956 null,
2957 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
2958 SUPPLEMENTARY_PRIVATE_USE_AREA_B
2959 };
2960
2961
2962 /**
2963 * Returns the object representing the Unicode block containing the
2964 * given character, or <code>null</code> if the character is not a
2965 * member of a defined block.
2966 *
2967 * <p><b>Note:</b> This method cannot handle
2968 * <a href="Character.html#supplementary"> supplementary
2969 * characters</a>. To support all Unicode characters, including
2970 * supplementary characters, use the {@link #of(int)} method.
2971 *
2972 * @param c The character in question
2973 * @return The <code>UnicodeBlock</code> instance representing the
2974 * Unicode block of which this character is a member, or
2975 * <code>null</code> if the character is not a member of any
2976 * Unicode block
2977 */
2978 public static UnicodeBlock of(char c) {
2979 return of((int)c);
2980 }
2981
2982 /**
2983 * Returns the object representing the Unicode block
2984 * containing the given character (Unicode code point), or
2985 * <code>null</code> if the character is not a member of a
2986 * defined block.
2987 *
2988 * @param codePoint the character (Unicode code point) in question.
2989 * @return The <code>UnicodeBlock</code> instance representing the
2990 * Unicode block of which this character is a member, or
2991 * <code>null</code> if the character is not a member of any
2992 * Unicode block
2993 * @exception IllegalArgumentException if the specified
2994 * <code>codePoint</code> is an invalid Unicode code point.
2995 * @see Character#isValidCodePoint(int)
2996 * @since 1.5
2997 */
2998 public static UnicodeBlock of(int codePoint) {
2999 if (!isValidCodePoint(codePoint)) {
3000 throw new IllegalArgumentException();
3001 }
3002
3003 int top, bottom, current;
3004 bottom = 0;
3005 top = blockStarts.length;
3006 current = top/2;
3007
3008 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
3009 while (top - bottom > 1) {
3010 if (codePoint >= blockStarts[current]) {
3011 bottom = current;
3012 } else {
3013 top = current;
3014 }
3015 current = (top + bottom) / 2;
3016 }
3017 return blocks[current];
3018 }
3019
3020 /**
3021 * Returns the UnicodeBlock with the given name. Block
3022 * names are determined by The Unicode Standard. The file
3023 * Blocks-<version>.txt defines blocks for a particular
3024 * version of the standard. The {@link Character} class specifies
3025 * the version of the standard that it supports.
3026 * <p>
3027 * This method accepts block names in the following forms:
3028 * <ol>
3029 * <li> Canonical block names as defined by the Unicode Standard.
3030 * For example, the standard defines a "Basic Latin" block. Therefore, this
3031 * method accepts "Basic Latin" as a valid block name. The documentation of
3032 * each UnicodeBlock provides the canonical name.
3033 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
3034 * is a valid block name for the "Basic Latin" block.
3035 * <li>The text representation of each constant UnicodeBlock identifier.
3036 * For example, this method will return the {@link #BASIC_LATIN} block if
3037 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
3038 * hyphens in the canonical name with underscores.
3039 * </ol>
3040 * Finally, character case is ignored for all of the valid block name forms.
3041 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
3042 * The en_US locale's case mapping rules are used to provide case-insensitive
3043 * string comparisons for block name validation.
3044 * <p>
3045 * If the Unicode Standard changes block names, both the previous and
3046 * current names will be accepted.
3047 *
3048 * @param blockName A <code>UnicodeBlock</code> name.
3049 * @return The <code>UnicodeBlock</code> instance identified
3050 * by <code>blockName</code>
3051 * @throws IllegalArgumentException if <code>blockName</code> is an
3052 * invalid name
3053 * @throws NullPointerException if <code>blockName</code> is null
3054 * @since 1.5
3055 */
3056 public static final UnicodeBlock forName(String blockName) {
3057 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
3058 if (block == null) {
3059 throw new IllegalArgumentException();
3060 }
3061 return block;
3062 }
3063 }
3064
3065
3066 /**
3067 * A family of character subsets representing the character scripts
3068 * defined in the <a href="http://www.unicode.org/reports/tr24/">
3069 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
3070 * character is assigned to a single Unicode script, either a specific
3071 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
3072 * one of the following three special values,
3073 * {@link Character.UnicodeScript#INHERITED Inherited},
3074 * {@link Character.UnicodeScript#COMMON Common} or
3075 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
3076 *
3077 * @since 1.7
3078 */
3079 public static enum UnicodeScript {
3080 /**
3081 * Unicode script "Common".
3082 */
3083 COMMON,
3084
3085 /**
3086 * Unicode script "Latin".
3087 */
3088 LATIN,
3089
3090 /**
3091 * Unicode script "Greek".
3092 */
3093 GREEK,
3094
3095 /**
3096 * Unicode script "Cyrillic".
3097 */
3098 CYRILLIC,
3099
3100 /**
3101 * Unicode script "Armenian".
3102 */
3103 ARMENIAN,
3104
3105 /**
3106 * Unicode script "Hebrew".
3107 */
3108 HEBREW,
3109
3110 /**
3111 * Unicode script "Arabic".
3112 */
3113 ARABIC,
3114
3115 /**
3116 * Unicode script "Syriac".
3117 */
3118 SYRIAC,
3119
3120 /**
3121 * Unicode script "Thaana".
3122 */
3123 THAANA,
3124
3125 /**
3126 * Unicode script "Devanagari".
3127 */
3128 DEVANAGARI,
3129
3130 /**
3131 * Unicode script "Bengali".
3132 */
3133 BENGALI,
3134
3135 /**
3136 * Unicode script "Gurmukhi".
3137 */
3138 GURMUKHI,
3139
3140 /**
3141 * Unicode script "Gujarati".
3142 */
3143 GUJARATI,
3144
3145 /**
3146 * Unicode script "Oriya".
3147 */
3148 ORIYA,
3149
3150 /**
3151 * Unicode script "Tamil".
3152 */
3153 TAMIL,
3154
3155 /**
3156 * Unicode script "Telugu".
3157 */
3158 TELUGU,
3159
3160 /**
3161 * Unicode script "Kannada".
3162 */
3163 KANNADA,
3164
3165 /**
3166 * Unicode script "Malayalam".
3167 */
3168 MALAYALAM,
3169
3170 /**
3171 * Unicode script "Sinhala".
3172 */
3173 SINHALA,
3174
3175 /**
3176 * Unicode script "Thai".
3177 */
3178 THAI,
3179
3180 /**
3181 * Unicode script "Lao".
3182 */
3183 LAO,
3184
3185 /**
3186 * Unicode script "Tibetan".
3187 */
3188 TIBETAN,
3189
3190 /**
3191 * Unicode script "Myanmar".
3192 */
3193 MYANMAR,
3194
3195 /**
3196 * Unicode script "Georgian".
3197 */
3198 GEORGIAN,
3199
3200 /**
3201 * Unicode script "Hangul".
3202 */
3203 HANGUL,
3204
3205 /**
3206 * Unicode script "Ethiopic".
3207 */
3208 ETHIOPIC,
3209
3210 /**
3211 * Unicode script "Cherokee".
3212 */
3213 CHEROKEE,
3214
3215 /**
3216 * Unicode script "Canadian_Aboriginal".
3217 */
3218 CANADIAN_ABORIGINAL,
3219
3220 /**
3221 * Unicode script "Ogham".
3222 */
3223 OGHAM,
3224
3225 /**
3226 * Unicode script "Runic".
3227 */
3228 RUNIC,
3229
3230 /**
3231 * Unicode script "Khmer".
3232 */
3233 KHMER,
3234
3235 /**
3236 * Unicode script "Mongolian".
3237 */
3238 MONGOLIAN,
3239
3240 /**
3241 * Unicode script "Hiragana".
3242 */
3243 HIRAGANA,
3244
3245 /**
3246 * Unicode script "Katakana".
3247 */
3248 KATAKANA,
3249
3250 /**
3251 * Unicode script "Bopomofo".
3252 */
3253 BOPOMOFO,
3254
3255 /**
3256 * Unicode script "Han".
3257 */
3258 HAN,
3259
3260 /**
3261 * Unicode script "Yi".
3262 */
3263 YI,
3264
3265 /**
3266 * Unicode script "Old_Italic".
3267 */
3268 OLD_ITALIC,
3269
3270 /**
3271 * Unicode script "Gothic".
3272 */
3273 GOTHIC,
3274
3275 /**
3276 * Unicode script "Deseret".
3277 */
3278 DESERET,
3279
3280 /**
3281 * Unicode script "Inherited".
3282 */
3283 INHERITED,
3284
3285 /**
3286 * Unicode script "Tagalog".
3287 */
3288 TAGALOG,
3289
3290 /**
3291 * Unicode script "Hanunoo".
3292 */
3293 HANUNOO,
3294
3295 /**
3296 * Unicode script "Buhid".
3297 */
3298 BUHID,
3299
3300 /**
3301 * Unicode script "Tagbanwa".
3302 */
3303 TAGBANWA,
3304
3305 /**
3306 * Unicode script "Limbu".
3307 */
3308 LIMBU,
3309
3310 /**
3311 * Unicode script "Tai_Le".
3312 */
3313 TAI_LE,
3314
3315 /**
3316 * Unicode script "Linear_B".
3317 */
3318 LINEAR_B,
3319
3320 /**
3321 * Unicode script "Ugaritic".
3322 */
3323 UGARITIC,
3324
3325 /**
3326 * Unicode script "Shavian".
3327 */
3328 SHAVIAN,
3329
3330 /**
3331 * Unicode script "Osmanya".
3332 */
3333 OSMANYA,
3334
3335 /**
3336 * Unicode script "Cypriot".
3337 */
3338 CYPRIOT,
3339
3340 /**
3341 * Unicode script "Braille".
3342 */
3343 BRAILLE,
3344
3345 /**
3346 * Unicode script "Buginese".
3347 */
3348 BUGINESE,
3349
3350 /**
3351 * Unicode script "Coptic".
3352 */
3353 COPTIC,
3354
3355 /**
3356 * Unicode script "New_Tai_Lue".
3357 */
3358 NEW_TAI_LUE,
3359
3360 /**
3361 * Unicode script "Glagolitic".
3362 */
3363 GLAGOLITIC,
3364
3365 /**
3366 * Unicode script "Tifinagh".
3367 */
3368 TIFINAGH,
3369
3370 /**
3371 * Unicode script "Syloti_Nagri".
3372 */
3373 SYLOTI_NAGRI,
3374
3375 /**
3376 * Unicode script "Old_Persian".
3377 */
3378 OLD_PERSIAN,
3379
3380 /**
3381 * Unicode script "Kharoshthi".
3382 */
3383 KHAROSHTHI,
3384
3385 /**
3386 * Unicode script "Balinese".
3387 */
3388 BALINESE,
3389
3390 /**
3391 * Unicode script "Cuneiform".
3392 */
3393 CUNEIFORM,
3394
3395 /**
3396 * Unicode script "Phoenician".
3397 */
3398 PHOENICIAN,
3399
3400 /**
3401 * Unicode script "Phags_Pa".
3402 */
3403 PHAGS_PA,
3404
3405 /**
3406 * Unicode script "Nko".
3407 */
3408 NKO,
3409
3410 /**
3411 * Unicode script "Sundanese".
3412 */
3413 SUNDANESE,
3414
3415 /**
3416 * Unicode script "Batak".
3417 */
3418 BATAK,
3419
3420 /**
3421 * Unicode script "Lepcha".
3422 */
3423 LEPCHA,
3424
3425 /**
3426 * Unicode script "Ol_Chiki".
3427 */
3428 OL_CHIKI,
3429
3430 /**
3431 * Unicode script "Vai".
3432 */
3433 VAI,
3434
3435 /**
3436 * Unicode script "Saurashtra".
3437 */
3438 SAURASHTRA,
3439
3440 /**
3441 * Unicode script "Kayah_Li".
3442 */
3443 KAYAH_LI,
3444
3445 /**
3446 * Unicode script "Rejang".
3447 */
3448 REJANG,
3449
3450 /**
3451 * Unicode script "Lycian".
3452 */
3453 LYCIAN,
3454
3455 /**
3456 * Unicode script "Carian".
3457 */
3458 CARIAN,
3459
3460 /**
3461 * Unicode script "Lydian".
3462 */
3463 LYDIAN,
3464
3465 /**
3466 * Unicode script "Cham".
3467 */
3468 CHAM,
3469
3470 /**
3471 * Unicode script "Tai_Tham".
3472 */
3473 TAI_THAM,
3474
3475 /**
3476 * Unicode script "Tai_Viet".
3477 */
3478 TAI_VIET,
3479
3480 /**
3481 * Unicode script "Avestan".
3482 */
3483 AVESTAN,
3484
3485 /**
3486 * Unicode script "Egyptian_Hieroglyphs".
3487 */
3488 EGYPTIAN_HIEROGLYPHS,
3489
3490 /**
3491 * Unicode script "Samaritan".
3492 */
3493 SAMARITAN,
3494
3495 /**
3496 * Unicode script "Mandaic".
3497 */
3498 MANDAIC,
3499
3500 /**
3501 * Unicode script "Lisu".
3502 */
3503 LISU,
3504
3505 /**
3506 * Unicode script "Bamum".
3507 */
3508 BAMUM,
3509
3510 /**
3511 * Unicode script "Javanese".
3512 */
3513 JAVANESE,
3514
3515 /**
3516 * Unicode script "Meetei_Mayek".
3517 */
3518 MEETEI_MAYEK,
3519
3520 /**
3521 * Unicode script "Imperial_Aramaic".
3522 */
3523 IMPERIAL_ARAMAIC,
3524
3525 /**
3526 * Unicode script "Old_South_Arabian".
3527 */
3528 OLD_SOUTH_ARABIAN,
3529
3530 /**
3531 * Unicode script "Inscriptional_Parthian".
3532 */
3533 INSCRIPTIONAL_PARTHIAN,
3534
3535 /**
3536 * Unicode script "Inscriptional_Pahlavi".
3537 */
3538 INSCRIPTIONAL_PAHLAVI,
3539
3540 /**
3541 * Unicode script "Old_Turkic".
3542 */
3543 OLD_TURKIC,
3544
3545 /**
3546 * Unicode script "Brahmi".
3547 */
3548 BRAHMI,
3549
3550 /**
3551 * Unicode script "Kaithi".
3552 */
3553 KAITHI,
3554
3555 /**
3556 * Unicode script "Unknown".
3557 */
3558 UNKNOWN;
3559
3560 private static final int[] scriptStarts = {
3561 0x0000, // 0000..0040; COMMON
3562 0x0041, // 0041..005A; LATIN
3563 0x005B, // 005B..0060; COMMON
3564 0x0061, // 0061..007A; LATIN
3565 0x007B, // 007B..00A9; COMMON
3566 0x00AA, // 00AA..00AA; LATIN
3567 0x00AB, // 00AB..00B9; COMMON
3568 0x00BA, // 00BA..00BA; LATIN
3569 0x00BB, // 00BB..00BF; COMMON
3570 0x00C0, // 00C0..00D6; LATIN
3571 0x00D7, // 00D7..00D7; COMMON
3572 0x00D8, // 00D8..00F6; LATIN
3573 0x00F7, // 00F7..00F7; COMMON
3574 0x00F8, // 00F8..02B8; LATIN
3575 0x02B9, // 02B9..02DF; COMMON
3576 0x02E0, // 02E0..02E4; LATIN
3577 0x02E5, // 02E5..02E9; COMMON
3578 0x02EA, // 02EA..02EB; BOPOMOFO
3579 0x02EC, // 02EC..02FF; COMMON
3580 0x0300, // 0300..036F; INHERITED
3581 0x0370, // 0370..0373; GREEK
3582 0x0374, // 0374..0374; COMMON
3583 0x0375, // 0375..037D; GREEK
3584 0x037E, // 037E..0383; COMMON
3585 0x0384, // 0384..0384; GREEK
3586 0x0385, // 0385..0385; COMMON
3587 0x0386, // 0386..0386; GREEK
3588 0x0387, // 0387..0387; COMMON
3589 0x0388, // 0388..03E1; GREEK
3590 0x03E2, // 03E2..03EF; COPTIC
3591 0x03F0, // 03F0..03FF; GREEK
3592 0x0400, // 0400..0484; CYRILLIC
3593 0x0485, // 0485..0486; INHERITED
3594 0x0487, // 0487..0530; CYRILLIC
3595 0x0531, // 0531..0588; ARMENIAN
3596 0x0589, // 0589..0589; COMMON
3597 0x058A, // 058A..0590; ARMENIAN
3598 0x0591, // 0591..05FF; HEBREW
3599 0x0600, // 0600..060B; ARABIC
3600 0x060C, // 060C..060C; COMMON
3601 0x060D, // 060D..061A; ARABIC
3602 0x061B, // 061B..061D; COMMON
3603 0x061E, // 061E..061E; ARABIC
3604 0x061F, // 061F..061F; COMMON
3605 0x0620, // 0620..063F; ARABIC
3606 0x0640, // 0640..0640; COMMON
3607 0x0641, // 0641..064A; ARABIC
3608 0x064B, // 064B..0655; INHERITED
3609 0x0656, // 0656..065E; ARABIC
3610 0x065F, // 065F..065F; INHERITED
3611 0x0660, // 0660..0669; COMMON
3612 0x066A, // 066A..066F; ARABIC
3613 0x0670, // 0670..0670; INHERITED
3614 0x0671, // 0671..06DC; ARABIC
3615 0x06DD, // 06DD..06DD; COMMON
3616 0x06DE, // 06DE..06FF; ARABIC
3617 0x0700, // 0700..074F; SYRIAC
3618 0x0750, // 0750..077F; ARABIC
3619 0x0780, // 0780..07BF; THAANA
3620 0x07C0, // 07C0..07FF; NKO
3621 0x0800, // 0800..083F; SAMARITAN
3622 0x0840, // 0840..08FF; MANDAIC
3623 0x0900, // 0900..0950; DEVANAGARI
3624 0x0951, // 0951..0952; INHERITED
3625 0x0953, // 0953..0963; DEVANAGARI
3626 0x0964, // 0964..0965; COMMON
3627 0x0966, // 0966..096F; DEVANAGARI
3628 0x0970, // 0970..0970; COMMON
3629 0x0971, // 0971..0980; DEVANAGARI
3630 0x0981, // 0981..0A00; BENGALI
3631 0x0A01, // 0A01..0A80; GURMUKHI
3632 0x0A81, // 0A81..0B00; GUJARATI
3633 0x0B01, // 0B01..0B81; ORIYA
3634 0x0B82, // 0B82..0C00; TAMIL
3635 0x0C01, // 0C01..0C81; TELUGU
3636 0x0C82, // 0C82..0CF0; KANNADA
3637 0x0D02, // 0D02..0D81; MALAYALAM
3638 0x0D82, // 0D82..0E00; SINHALA
3639 0x0E01, // 0E01..0E3E; THAI
3640 0x0E3F, // 0E3F..0E3F; COMMON
3641 0x0E40, // 0E40..0E80; THAI
3642 0x0E81, // 0E81..0EFF; LAO
3643 0x0F00, // 0F00..0FD4; TIBETAN
3644 0x0FD5, // 0FD5..0FD8; COMMON
3645 0x0FD9, // 0FD9..0FFF; TIBETAN
3646 0x1000, // 1000..109F; MYANMAR
3647 0x10A0, // 10A0..10FA; GEORGIAN
3648 0x10FB, // 10FB..10FB; COMMON
3649 0x10FC, // 10FC..10FF; GEORGIAN
3650 0x1100, // 1100..11FF; HANGUL
3651 0x1200, // 1200..139F; ETHIOPIC
3652 0x13A0, // 13A0..13FF; CHEROKEE
3653 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
3654 0x1680, // 1680..169F; OGHAM
3655 0x16A0, // 16A0..16EA; RUNIC
3656 0x16EB, // 16EB..16ED; COMMON
3657 0x16EE, // 16EE..16FF; RUNIC
3658 0x1700, // 1700..171F; TAGALOG
3659 0x1720, // 1720..1734; HANUNOO
3660 0x1735, // 1735..173F; COMMON
3661 0x1740, // 1740..175F; BUHID
3662 0x1760, // 1760..177F; TAGBANWA
3663 0x1780, // 1780..17FF; KHMER
3664 0x1800, // 1800..1801; MONGOLIAN
3665 0x1802, // 1802..1803; COMMON
3666 0x1804, // 1804..1804; MONGOLIAN
3667 0x1805, // 1805..1805; COMMON
3668 0x1806, // 1806..18AF; MONGOLIAN
3669 0x18B0, // 18B0..18FF; CANADIAN_ABORIGINAL
3670 0x1900, // 1900..194F; LIMBU
3671 0x1950, // 1950..197F; TAI_LE
3672 0x1980, // 1980..19DF; NEW_TAI_LUE
3673 0x19E0, // 19E0..19FF; KHMER
3674 0x1A00, // 1A00..1A1F; BUGINESE
3675 0x1A20, // 1A20..1AFF; TAI_THAM
3676 0x1B00, // 1B00..1B7F; BALINESE
3677 0x1B80, // 1B80..1BBF; SUNDANESE
3678 0x1BC0, // 1BC0..1BFF; BATAK
3679 0x1C00, // 1C00..1C4F; LEPCHA
3680 0x1C50, // 1C50..1CCF; OL_CHIKI
3681 0x1CD0, // 1CD0..1CD2; INHERITED
3682 0x1CD3, // 1CD3..1CD3; COMMON
3683 0x1CD4, // 1CD4..1CE0; INHERITED
3684 0x1CE1, // 1CE1..1CE1; COMMON
3685 0x1CE2, // 1CE2..1CE8; INHERITED
3686 0x1CE9, // 1CE9..1CEC; COMMON
3687 0x1CED, // 1CED..1CED; INHERITED
3688 0x1CEE, // 1CEE..1CFF; COMMON
3689 0x1D00, // 1D00..1D25; LATIN
3690 0x1D26, // 1D26..1D2A; GREEK
3691 0x1D2B, // 1D2B..1D2B; CYRILLIC
3692 0x1D2C, // 1D2C..1D5C; LATIN
3693 0x1D5D, // 1D5D..1D61; GREEK
3694 0x1D62, // 1D62..1D65; LATIN
3695 0x1D66, // 1D66..1D6A; GREEK
3696 0x1D6B, // 1D6B..1D77; LATIN
3697 0x1D78, // 1D78..1D78; CYRILLIC
3698 0x1D79, // 1D79..1DBE; LATIN
3699 0x1DBF, // 1DBF..1DBF; GREEK
3700 0x1DC0, // 1DC0..1DFF; INHERITED
3701 0x1E00, // 1E00..1EFF; LATIN
3702 0x1F00, // 1F00..1FFF; GREEK
3703 0x2000, // 2000..200B; COMMON
3704 0x200C, // 200C..200D; INHERITED
3705 0x200E, // 200E..2070; COMMON
3706 0x2071, // 2071..2073; LATIN
3707 0x2074, // 2074..207E; COMMON
3708 0x207F, // 207F..207F; LATIN
3709 0x2080, // 2080..208F; COMMON
3710 0x2090, // 2090..209F; LATIN
3711 0x20A0, // 20A0..20CF; COMMON
3712 0x20D0, // 20D0..20FF; INHERITED
3713 0x2100, // 2100..2125; COMMON
3714 0x2126, // 2126..2126; GREEK
3715 0x2127, // 2127..2129; COMMON
3716 0x212A, // 212A..212B; LATIN
3717 0x212C, // 212C..2131; COMMON
3718 0x2132, // 2132..2132; LATIN
3719 0x2133, // 2133..214D; COMMON
3720 0x214E, // 214E..214E; LATIN
3721 0x214F, // 214F..215F; COMMON
3722 0x2160, // 2160..2188; LATIN
3723 0x2189, // 2189..27FF; COMMON
3724 0x2800, // 2800..28FF; BRAILLE
3725 0x2900, // 2900..2BFF; COMMON
3726 0x2C00, // 2C00..2C5F; GLAGOLITIC
3727 0x2C60, // 2C60..2C7F; LATIN
3728 0x2C80, // 2C80..2CFF; COPTIC
3729 0x2D00, // 2D00..2D2F; GEORGIAN
3730 0x2D30, // 2D30..2D7F; TIFINAGH
3731 0x2D80, // 2D80..2DDF; ETHIOPIC
3732 0x2DE0, // 2DE0..2DFF; CYRILLIC
3733 0x2E00, // 2E00..2E7F; COMMON
3734 0x2E80, // 2E80..2FEF; HAN
3735 0x2FF0, // 2FF0..3004; COMMON
3736 0x3005, // 3005..3005; HAN
3737 0x3006, // 3006..3006; COMMON
3738 0x3007, // 3007..3007; HAN
3739 0x3008, // 3008..3020; COMMON
3740 0x3021, // 3021..3029; HAN
3741 0x302A, // 302A..302D; INHERITED
3742 0x302E, // 302E..302F; HANGUL
3743 0x3030, // 3030..3037; COMMON
3744 0x3038, // 3038..303B; HAN
3745 0x303C, // 303C..3040; COMMON
3746 0x3041, // 3041..3098; HIRAGANA
3747 0x3099, // 3099..309A; INHERITED
3748 0x309B, // 309B..309C; COMMON
3749 0x309D, // 309D..309F; HIRAGANA
3750 0x30A0, // 30A0..30A0; COMMON
3751 0x30A1, // 30A1..30FA; KATAKANA
3752 0x30FB, // 30FB..30FC; COMMON
3753 0x30FD, // 30FD..3104; KATAKANA
3754 0x3105, // 3105..3130; BOPOMOFO
3755 0x3131, // 3131..318F; HANGUL
3756 0x3190, // 3190..319F; COMMON
3757 0x31A0, // 31A0..31BF; BOPOMOFO
3758 0x31C0, // 31C0..31EF; COMMON
3759 0x31F0, // 31F0..31FF; KATAKANA
3760 0x3200, // 3200..321F; HANGUL
3761 0x3220, // 3220..325F; COMMON
3762 0x3260, // 3260..327E; HANGUL
3763 0x327F, // 327F..32CF; COMMON
3764 0x32D0, // 32D0..3357; KATAKANA
3765 0x3358, // 3358..33FF; COMMON
3766 0x3400, // 3400..4DBF; HAN
3767 0x4DC0, // 4DC0..4DFF; COMMON
3768 0x4E00, // 4E00..9FFF; HAN
3769 0xA000, // A000..A4CF; YI
3770 0xA4D0, // A4D0..A4FF; LISU
3771 0xA500, // A500..A63F; VAI
3772 0xA640, // A640..A69F; CYRILLIC
3773 0xA6A0, // A6A0..A6FF; BAMUM
3774 0xA700, // A700..A721; COMMON
3775 0xA722, // A722..A787; LATIN
3776 0xA788, // A788..A78A; COMMON
3777 0xA78B, // A78B..A7FF; LATIN
3778 0xA800, // A800..A82F; SYLOTI_NAGRI
3779 0xA830, // A830..A83F; COMMON
3780 0xA840, // A840..A87F; PHAGS_PA
3781 0xA880, // A880..A8DF; SAURASHTRA
3782 0xA8E0, // A8E0..A8FF; DEVANAGARI
3783 0xA900, // A900..A92F; KAYAH_LI
3784 0xA930, // A930..A95F; REJANG
3785 0xA960, // A960..A97F; HANGUL
3786 0xA980, // A980..A9FF; JAVANESE
3787 0xAA00, // AA00..AA5F; CHAM
3788 0xAA60, // AA60..AA7F; MYANMAR
3789 0xAA80, // AA80..AB00; TAI_VIET
3790 0xAB01, // AB01..ABBF; ETHIOPIC
3791 0xABC0, // ABC0..ABFF; MEETEI_MAYEK
3792 0xAC00, // AC00..D7FB; HANGUL
3793 0xD7FC, // D7FC..F8FF; UNKNOWN
3794 0xF900, // F900..FAFF; HAN
3795 0xFB00, // FB00..FB12; LATIN
3796 0xFB13, // FB13..FB1C; ARMENIAN
3797 0xFB1D, // FB1D..FB4F; HEBREW
3798 0xFB50, // FB50..FD3D; ARABIC
3799 0xFD3E, // FD3E..FD4F; COMMON
3800 0xFD50, // FD50..FDFC; ARABIC
3801 0xFDFD, // FDFD..FDFF; COMMON
3802 0xFE00, // FE00..FE0F; INHERITED
3803 0xFE10, // FE10..FE1F; COMMON
3804 0xFE20, // FE20..FE2F; INHERITED
3805 0xFE30, // FE30..FE6F; COMMON
3806 0xFE70, // FE70..FEFE; ARABIC
3807 0xFEFF, // FEFF..FF20; COMMON
3808 0xFF21, // FF21..FF3A; LATIN
3809 0xFF3B, // FF3B..FF40; COMMON
3810 0xFF41, // FF41..FF5A; LATIN
3811 0xFF5B, // FF5B..FF65; COMMON
3812 0xFF66, // FF66..FF6F; KATAKANA
3813 0xFF70, // FF70..FF70; COMMON
3814 0xFF71, // FF71..FF9D; KATAKANA
3815 0xFF9E, // FF9E..FF9F; COMMON
3816 0xFFA0, // FFA0..FFDF; HANGUL
3817 0xFFE0, // FFE0..FFFF; COMMON
3818 0x10000, // 10000..100FF; LINEAR_B
3819 0x10100, // 10100..1013F; COMMON
3820 0x10140, // 10140..1018F; GREEK
3821 0x10190, // 10190..101FC; COMMON
3822 0x101FD, // 101FD..1027F; INHERITED
3823 0x10280, // 10280..1029F; LYCIAN
3824 0x102A0, // 102A0..102FF; CARIAN
3825 0x10300, // 10300..1032F; OLD_ITALIC
3826 0x10330, // 10330..1037F; GOTHIC
3827 0x10380, // 10380..1039F; UGARITIC
3828 0x103A0, // 103A0..103FF; OLD_PERSIAN
3829 0x10400, // 10400..1044F; DESERET
3830 0x10450, // 10450..1047F; SHAVIAN
3831 0x10480, // 10480..107FF; OSMANYA
3832 0x10800, // 10800..1083F; CYPRIOT
3833 0x10840, // 10840..108FF; IMPERIAL_ARAMAIC
3834 0x10900, // 10900..1091F; PHOENICIAN
3835 0x10920, // 10920..109FF; LYDIAN
3836 0x10A00, // 10A00..10A5F; KHAROSHTHI
3837 0x10A60, // 10A60..10AFF; OLD_SOUTH_ARABIAN
3838 0x10B00, // 10B00..10B3F; AVESTAN
3839 0x10B40, // 10B40..10B5F; INSCRIPTIONAL_PARTHIAN
3840 0x10B60, // 10B60..10BFF; INSCRIPTIONAL_PAHLAVI
3841 0x10C00, // 10C00..10E5F; OLD_TURKIC
3842 0x10E60, // 10E60..10FFF; ARABIC
3843 0x11000, // 11000..1107F; BRAHMI
3844 0x11080, // 11080..11FFF; KAITHI
3845 0x12000, // 12000..12FFF; CUNEIFORM
3846 0x13000, // 13000..167FF; EGYPTIAN_HIEROGLYPHS
3847 0x16800, // 16800..16A38; BAMUM
3848 0x1B000, // 1B000..1B000; KATAKANA
3849 0x1B001, // 1B001..1CFFF; HIRAGANA
3850 0x1D000, // 1D000..1D166; COMMON
3851 0x1D167, // 1D167..1D169; INHERITED
3852 0x1D16A, // 1D16A..1D17A; COMMON
3853 0x1D17B, // 1D17B..1D182; INHERITED
3854 0x1D183, // 1D183..1D184; COMMON
3855 0x1D185, // 1D185..1D18B; INHERITED
3856 0x1D18C, // 1D18C..1D1A9; COMMON
3857 0x1D1AA, // 1D1AA..1D1AD; INHERITED
3858 0x1D1AE, // 1D1AE..1D1FF; COMMON
3859 0x1D200, // 1D200..1D2FF; GREEK
3860 0x1D300, // 1D300..1F1FF; COMMON
3861 0x1F200, // 1F200..1F200; HIRAGANA
3862 0x1F201, // 1F210..1FFFF; COMMON
3863 0x20000, // 20000..E0000; HAN
3864 0xE0001, // E0001..E00FF; COMMON
3865 0xE0100, // E0100..E01EF; INHERITED
3866 0xE01F0 // E01F0..10FFFF; UNKNOWN
3867
3868 };
3869
3870 private static final UnicodeScript[] scripts = {
3871 COMMON,
3872 LATIN,
3873 COMMON,
3874 LATIN,
3875 COMMON,
3876 LATIN,
3877 COMMON,
3878 LATIN,
3879 COMMON,
3880 LATIN,
3881 COMMON,
3882 LATIN,
3883 COMMON,
3884 LATIN,
3885 COMMON,
3886 LATIN,
3887 COMMON,
3888 BOPOMOFO,
3889 COMMON,
3890 INHERITED,
3891 GREEK,
3892 COMMON,
3893 GREEK,
3894 COMMON,
3895 GREEK,
3896 COMMON,
3897 GREEK,
3898 COMMON,
3899 GREEK,
3900 COPTIC,
3901 GREEK,
3902 CYRILLIC,
3903 INHERITED,
3904 CYRILLIC,
3905 ARMENIAN,
3906 COMMON,
3907 ARMENIAN,
3908 HEBREW,
3909 ARABIC,
3910 COMMON,
3911 ARABIC,
3912 COMMON,
3913 ARABIC,
3914 COMMON,
3915 ARABIC,
3916 COMMON,
3917 ARABIC,
3918 INHERITED,
3919 ARABIC,
3920 INHERITED,
3921 COMMON,
3922 ARABIC,
3923 INHERITED,
3924 ARABIC,
3925 COMMON,
3926 ARABIC,
3927 SYRIAC,
3928 ARABIC,
3929 THAANA,
3930 NKO,
3931 SAMARITAN,
3932 MANDAIC,
3933 DEVANAGARI,
3934 INHERITED,
3935 DEVANAGARI,
3936 COMMON,
3937 DEVANAGARI,
3938 COMMON,
3939 DEVANAGARI,
3940 BENGALI,
3941 GURMUKHI,
3942 GUJARATI,
3943 ORIYA,
3944 TAMIL,
3945 TELUGU,
3946 KANNADA,
3947 MALAYALAM,
3948 SINHALA,
3949 THAI,
3950 COMMON,
3951 THAI,
3952 LAO,
3953 TIBETAN,
3954 COMMON,
3955 TIBETAN,
3956 MYANMAR,
3957 GEORGIAN,
3958 COMMON,
3959 GEORGIAN,
3960 HANGUL,
3961 ETHIOPIC,
3962 CHEROKEE,
3963 CANADIAN_ABORIGINAL,
3964 OGHAM,
3965 RUNIC,
3966 COMMON,
3967 RUNIC,
3968 TAGALOG,
3969 HANUNOO,
3970 COMMON,
3971 BUHID,
3972 TAGBANWA,
3973 KHMER,
3974 MONGOLIAN,
3975 COMMON,
3976 MONGOLIAN,
3977 COMMON,
3978 MONGOLIAN,
3979 CANADIAN_ABORIGINAL,
3980 LIMBU,
3981 TAI_LE,
3982 NEW_TAI_LUE,
3983 KHMER,
3984 BUGINESE,
3985 TAI_THAM,
3986 BALINESE,
3987 SUNDANESE,
3988 BATAK,
3989 LEPCHA,
3990 OL_CHIKI,
3991 INHERITED,
3992 COMMON,
3993 INHERITED,
3994 COMMON,
3995 INHERITED,
3996 COMMON,
3997 INHERITED,
3998 COMMON,
3999 LATIN,
4000 GREEK,
4001 CYRILLIC,
4002 LATIN,
4003 GREEK,
4004 LATIN,
4005 GREEK,
4006 LATIN,
4007 CYRILLIC,
4008 LATIN,
4009 GREEK,
4010 INHERITED,
4011 LATIN,
4012 GREEK,
4013 COMMON,
4014 INHERITED,
4015 COMMON,
4016 LATIN,
4017 COMMON,
4018 LATIN,
4019 COMMON,
4020 LATIN,
4021 COMMON,
4022 INHERITED,
4023 COMMON,
4024 GREEK,
4025 COMMON,
4026 LATIN,
4027 COMMON,
4028 LATIN,
4029 COMMON,
4030 LATIN,
4031 COMMON,
4032 LATIN,
4033 COMMON,
4034 BRAILLE,
4035 COMMON,
4036 GLAGOLITIC,
4037 LATIN,
4038 COPTIC,
4039 GEORGIAN,
4040 TIFINAGH,
4041 ETHIOPIC,
4042 CYRILLIC,
4043 COMMON,
4044 HAN,
4045 COMMON,
4046 HAN,
4047 COMMON,
4048 HAN,
4049 COMMON,
4050 HAN,
4051 INHERITED,
4052 HANGUL,
4053 COMMON,
4054 HAN,
4055 COMMON,
4056 HIRAGANA,
4057 INHERITED,
4058 COMMON,
4059 HIRAGANA,
4060 COMMON,
4061 KATAKANA,
4062 COMMON,
4063 KATAKANA,
4064 BOPOMOFO,
4065 HANGUL,
4066 COMMON,
4067 BOPOMOFO,
4068 COMMON,
4069 KATAKANA,
4070 HANGUL,
4071 COMMON,
4072 HANGUL,
4073 COMMON,
4074 KATAKANA,
4075 COMMON,
4076 HAN,
4077 COMMON,
4078 HAN,
4079 YI,
4080 LISU,
4081 VAI,
4082 CYRILLIC,
4083 BAMUM,
4084 COMMON,
4085 LATIN,
4086 COMMON,
4087 LATIN,
4088 SYLOTI_NAGRI,
4089 COMMON,
4090 PHAGS_PA,
4091 SAURASHTRA,
4092 DEVANAGARI,
4093 KAYAH_LI,
4094 REJANG,
4095 HANGUL,
4096 JAVANESE,
4097 CHAM,
4098 MYANMAR,
4099 TAI_VIET,
4100 ETHIOPIC,
4101 MEETEI_MAYEK,
4102 HANGUL,
4103 UNKNOWN,
4104 HAN,
4105 LATIN,
4106 ARMENIAN,
4107 HEBREW,
4108 ARABIC,
4109 COMMON,
4110 ARABIC,
4111 COMMON,
4112 INHERITED,
4113 COMMON,
4114 INHERITED,
4115 COMMON,
4116 ARABIC,
4117 COMMON,
4118 LATIN,
4119 COMMON,
4120 LATIN,
4121 COMMON,
4122 KATAKANA,
4123 COMMON,
4124 KATAKANA,
4125 COMMON,
4126 HANGUL,
4127 COMMON,
4128 LINEAR_B,
4129 COMMON,
4130 GREEK,
4131 COMMON,
4132 INHERITED,
4133 LYCIAN,
4134 CARIAN,
4135 OLD_ITALIC,
4136 GOTHIC,
4137 UGARITIC,
4138 OLD_PERSIAN,
4139 DESERET,
4140 SHAVIAN,
4141 OSMANYA,
4142 CYPRIOT,
4143 IMPERIAL_ARAMAIC,
4144 PHOENICIAN,
4145 LYDIAN,
4146 KHAROSHTHI,
4147 OLD_SOUTH_ARABIAN,
4148 AVESTAN,
4149 INSCRIPTIONAL_PARTHIAN,
4150 INSCRIPTIONAL_PAHLAVI,
4151 OLD_TURKIC,
4152 ARABIC,
4153 BRAHMI,
4154 KAITHI,
4155 CUNEIFORM,
4156 EGYPTIAN_HIEROGLYPHS,
4157 BAMUM,
4158 KATAKANA,
4159 HIRAGANA,
4160 COMMON,
4161 INHERITED,
4162 COMMON,
4163 INHERITED,
4164 COMMON,
4165 INHERITED,
4166 COMMON,
4167 INHERITED,
4168 COMMON,
4169 GREEK,
4170 COMMON,
4171 HIRAGANA,
4172 COMMON,
4173 HAN,
4174 COMMON,
4175 INHERITED,
4176 UNKNOWN
4177 };
4178
4179 private static HashMap<String, Character.UnicodeScript> aliases;
4180 static {
4181 aliases = new HashMap<>(128);
4182 aliases.put("ARAB", ARABIC);
4183 aliases.put("ARMI", IMPERIAL_ARAMAIC);
4184 aliases.put("ARMN", ARMENIAN);
4185 aliases.put("AVST", AVESTAN);
4186 aliases.put("BALI", BALINESE);
4187 aliases.put("BAMU", BAMUM);
4188 aliases.put("BENG", BENGALI);
4189 aliases.put("BOPO", BOPOMOFO);
4190 aliases.put("BRAI", BRAILLE);
4191 aliases.put("BUGI", BUGINESE);
4192 aliases.put("BUHD", BUHID);
4193 aliases.put("CANS", CANADIAN_ABORIGINAL);
4194 aliases.put("CARI", CARIAN);
4195 aliases.put("CHAM", CHAM);
4196 aliases.put("CHER", CHEROKEE);
4197 aliases.put("COPT", COPTIC);
4198 aliases.put("CPRT", CYPRIOT);
4199 aliases.put("CYRL", CYRILLIC);
4200 aliases.put("DEVA", DEVANAGARI);
4201 aliases.put("DSRT", DESERET);
4202 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
4203 aliases.put("ETHI", ETHIOPIC);
4204 aliases.put("GEOR", GEORGIAN);
4205 aliases.put("GLAG", GLAGOLITIC);
4206 aliases.put("GOTH", GOTHIC);
4207 aliases.put("GREK", GREEK);
4208 aliases.put("GUJR", GUJARATI);
4209 aliases.put("GURU", GURMUKHI);
4210 aliases.put("HANG", HANGUL);
4211 aliases.put("HANI", HAN);
4212 aliases.put("HANO", HANUNOO);
4213 aliases.put("HEBR", HEBREW);
4214 aliases.put("HIRA", HIRAGANA);
4215 // it appears we don't have the KATAKANA_OR_HIRAGANA
4216 //aliases.put("HRKT", KATAKANA_OR_HIRAGANA);
4217 aliases.put("ITAL", OLD_ITALIC);
4218 aliases.put("JAVA", JAVANESE);
4219 aliases.put("KALI", KAYAH_LI);
4220 aliases.put("KANA", KATAKANA);
4221 aliases.put("KHAR", KHAROSHTHI);
4222 aliases.put("KHMR", KHMER);
4223 aliases.put("KNDA", KANNADA);
4224 aliases.put("KTHI", KAITHI);
4225 aliases.put("LANA", TAI_THAM);
4226 aliases.put("LAOO", LAO);
4227 aliases.put("LATN", LATIN);
4228 aliases.put("LEPC", LEPCHA);
4229 aliases.put("LIMB", LIMBU);
4230 aliases.put("LINB", LINEAR_B);
4231 aliases.put("LISU", LISU);
4232 aliases.put("LYCI", LYCIAN);
4233 aliases.put("LYDI", LYDIAN);
4234 aliases.put("MLYM", MALAYALAM);
4235 aliases.put("MONG", MONGOLIAN);
4236 aliases.put("MTEI", MEETEI_MAYEK);
4237 aliases.put("MYMR", MYANMAR);
4238 aliases.put("NKOO", NKO);
4239 aliases.put("OGAM", OGHAM);
4240 aliases.put("OLCK", OL_CHIKI);
4241 aliases.put("ORKH", OLD_TURKIC);
4242 aliases.put("ORYA", ORIYA);
4243 aliases.put("OSMA", OSMANYA);
4244 aliases.put("PHAG", PHAGS_PA);
4245 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
4246 aliases.put("PHNX", PHOENICIAN);
4247 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
4248 aliases.put("RJNG", REJANG);
4249 aliases.put("RUNR", RUNIC);
4250 aliases.put("SAMR", SAMARITAN);
4251 aliases.put("SARB", OLD_SOUTH_ARABIAN);
4252 aliases.put("SAUR", SAURASHTRA);
4253 aliases.put("SHAW", SHAVIAN);
4254 aliases.put("SINH", SINHALA);
4255 aliases.put("SUND", SUNDANESE);
4256 aliases.put("SYLO", SYLOTI_NAGRI);
4257 aliases.put("SYRC", SYRIAC);
4258 aliases.put("TAGB", TAGBANWA);
4259 aliases.put("TALE", TAI_LE);
4260 aliases.put("TALU", NEW_TAI_LUE);
4261 aliases.put("TAML", TAMIL);
4262 aliases.put("TAVT", TAI_VIET);
4263 aliases.put("TELU", TELUGU);
4264 aliases.put("TFNG", TIFINAGH);
4265 aliases.put("TGLG", TAGALOG);
4266 aliases.put("THAA", THAANA);
4267 aliases.put("THAI", THAI);
4268 aliases.put("TIBT", TIBETAN);
4269 aliases.put("UGAR", UGARITIC);
4270 aliases.put("VAII", VAI);
4271 aliases.put("XPEO", OLD_PERSIAN);
4272 aliases.put("XSUX", CUNEIFORM);
4273 aliases.put("YIII", YI);
4274 aliases.put("ZINH", INHERITED);
4275 aliases.put("ZYYY", COMMON);
4276 aliases.put("ZZZZ", UNKNOWN);
4277 }
4278
4279 /**
4280 * Returns the enum constant representing the Unicode script of which
4281 * the given character (Unicode code point) is assigned to.
4282 *
4283 * @param codePoint the character (Unicode code point) in question.
4284 * @return The <code>UnicodeScript</code> constant representing the
4285 * Unicode script of which this character is assigned to.
4286 *
4287 * @exception IllegalArgumentException if the specified
4288 * <code>codePoint</code> is an invalid Unicode code point.
4289 * @see Character#isValidCodePoint(int)
4290 *
4291 */
4292 public static UnicodeScript of(int codePoint) {
4293 if (!isValidCodePoint(codePoint))
4294 throw new IllegalArgumentException();
4295 int type = getType(codePoint);
4296 // leave SURROGATE and PRIVATE_USE for table lookup
4297 if (type == UNASSIGNED)
4298 return UNKNOWN;
4299 int index = Arrays.binarySearch(scriptStarts, codePoint);
4300 if (index < 0)
4301 index = -index - 2;
4302 return scripts[index];
4303 }
4304
4305 /**
4306 * Returns the UnicodeScript constant with the given Unicode script
4307 * name or the script name alias. Script names and their aliases are
4308 * determined by The Unicode Standard. The files Scripts<version>.txt
4309 * and PropertyValueAliases<version>.txt define script names
4310 * and the script name aliases for a particular version of the
4311 * standard. The {@link Character} class specifies the version of
4312 * the standard that it supports.
4313 * <p>
4314 * Character case is ignored for all of the valid script names.
4315 * The en_US locale's case mapping rules are used to provide
4316 * case-insensitive string comparisons for script name validation.
4317 * <p>
4318 *
4319 * @param scriptName A <code>UnicodeScript</code> name.
4320 * @return The <code>UnicodeScript</code> constant identified
4321 * by <code>scriptName</code>
4322 * @throws IllegalArgumentException if <code>scriptName</code> is an
4323 * invalid name
4324 * @throws NullPointerException if <code>scriptName</code> is null
4325 */
4326 public static final UnicodeScript forName(String scriptName) {
4327 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
4328 //.replace(' ', '_'));
4329 UnicodeScript sc = aliases.get(scriptName);
4330 if (sc != null)
4331 return sc;
4332 return valueOf(scriptName);
4333 }
4334 }
4335
4336 /**
4337 * The value of the <code>Character</code>.
4338 *
4339 * @serial
4340 */
4341 private final char value;
4342
4343 /** use serialVersionUID from JDK 1.0.2 for interoperability */
4344 private static final long serialVersionUID = 3786198910865385080L;
4345
4346 /**
4347 * Constructs a newly allocated <code>Character</code> object that
4348 * represents the specified <code>char</code> value.
4349 *
4350 * @param value the value to be represented by the
4351 * <code>Character</code> object.
4352 */
4353 public Character(char value) {
4354 this.value = value;
4355 }
4356
4357 private static class CharacterCache {
4358 private CharacterCache(){}
4359
4360 static final Character cache[] = new Character[127 + 1];
4361
4362 static {
4363 for (int i = 0; i < cache.length; i++)
4364 cache[i] = new Character((char)i);
4365 }
4366 }
4367
4368 /**
4369 * Returns a <tt>Character</tt> instance representing the specified
4370 * <tt>char</tt> value.
4371 * If a new <tt>Character</tt> instance is not required, this method
4372 * should generally be used in preference to the constructor
4373 * {@link #Character(char)}, as this method is likely to yield
4374 * significantly better space and time performance by caching
4375 * frequently requested values.
4376 *
4377 * This method will always cache values in the range {@code
4378 * '\u005Cu0000'} to {@code '\u005Cu007f'}, inclusive, and may
4379 * cache other values outside of this range.
4380 *
4381 * @param c a char value.
4382 * @return a <tt>Character</tt> instance representing <tt>c</tt>.
4383 * @since 1.5
4384 */
4385 public static Character valueOf(char c) {
4386 if (c <= 127) { // must cache
4387 return CharacterCache.cache[(int)c];
4388 }
4389 return new Character(c);
4390 }
4391
4392 /**
4393 * Returns the value of this <code>Character</code> object.
4394 * @return the primitive <code>char</code> value represented by
4395 * this object.
4396 */
4397 public char charValue() {
4398 return value;
4399 }
4400
4401 /**
4402 * Returns a hash code for this {@code Character}; equal to the result
4403 * of invoking {@code charValue()}.
4404 *
4405 * @return a hash code value for this {@code Character}
4406 */
4407 public int hashCode() {
4408 return (int)value;
4409 }
4410
4411 /**
4412 * Compares this object against the specified object.
4413 * The result is <code>true</code> if and only if the argument is not
4414 * <code>null</code> and is a <code>Character</code> object that
4415 * represents the same <code>char</code> value as this object.
4416 *
4417 * @param obj the object to compare with.
4418 * @return <code>true</code> if the objects are the same;
4419 * <code>false</code> otherwise.
4420 */
4421 public boolean equals(Object obj) {
4422 if (obj instanceof Character) {
4423 return value == ((Character)obj).charValue();
4424 }
4425 return false;
4426 }
4427
4428 /**
4429 * Returns a <code>String</code> object representing this
4430 * <code>Character</code>'s value. The result is a string of
4431 * length 1 whose sole component is the primitive
4432 * <code>char</code> value represented by this
4433 * <code>Character</code> object.
4434 *
4435 * @return a string representation of this object.
4436 */
4437 public String toString() {
4438 char buf[] = {value};
4439 return String.valueOf(buf);
4440 }
4441
4442 /**
4443 * Returns a <code>String</code> object representing the
4444 * specified <code>char</code>. The result is a string of length
4445 * 1 consisting solely of the specified <code>char</code>.
4446 *
4447 * @param c the <code>char</code> to be converted
4448 * @return the string representation of the specified <code>char</code>
4449 * @since 1.4
4450 */
4451 public static String toString(char c) {
4452 return String.valueOf(c);
4453 }
4454
4455 /**
4456 * Determines whether the specified code point is a valid
4457 * <a href="http://www.unicode.org/glossary/#code_point">
4458 * Unicode code point value</a>.
4459 *
4460 * @param codePoint the Unicode code point to be tested
4461 * @return {@code true} if the specified code point value is between
4462 * {@link #MIN_CODE_POINT} and
4463 * {@link #MAX_CODE_POINT} inclusive;
4464 * {@code false} otherwise.
4465 * @since 1.5
4466 */
4467 public static boolean isValidCodePoint(int codePoint) {
4468 // Optimized form of:
4469 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
4470 int plane = codePoint >>> 16;
4471 return plane < ((MAX_CODE_POINT + 1) >>> 16);
4472 }
4473
4474 /**
4475 * Determines whether the specified character (Unicode code point)
4476 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
4477 * Such code points can be represented using a single {@code char}.
4478 *
4479 * @param codePoint the character (Unicode code point) to be tested
4480 * @return {@code true} if the specified code point is between
4481 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
4482 * {@code false} otherwise.
4483 * @since 1.7
4484 */
4485 public static boolean isBmpCodePoint(int codePoint) {
4486 return codePoint >>> 16 == 0;
4487 // Optimized form of:
4488 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
4489 // We consistently use logical shift (>>>) to facilitate
4490 // additional runtime optimizations.
4491 }
4492
4493 /**
4494 * Determines whether the specified character (Unicode code point)
4495 * is in the <a href="#supplementary">supplementary character</a> range.
4496 *
4497 * @param codePoint the character (Unicode code point) to be tested
4498 * @return {@code true} if the specified code point is between
4499 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
4500 * {@link #MAX_CODE_POINT} inclusive;
4501 * {@code false} otherwise.
4502 * @since 1.5
4503 */
4504 public static boolean isSupplementaryCodePoint(int codePoint) {
4505 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
4506 && codePoint < MAX_CODE_POINT + 1;
4507 }
4508
4509 /**
4510 * Determines if the given {@code char} value is a
4511 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
4512 * Unicode high-surrogate code unit</a>
4513 * (also known as <i>leading-surrogate code unit</i>).
4514 *
4515 * <p>Such values do not represent characters by themselves,
4516 * but are used in the representation of
4517 * <a href="#supplementary">supplementary characters</a>
4518 * in the UTF-16 encoding.
4519 *
4520 * @param ch the {@code char} value to be tested.
4521 * @return {@code true} if the {@code char} value is between
4522 * {@link #MIN_HIGH_SURROGATE} and
4523 * {@link #MAX_HIGH_SURROGATE} inclusive;
4524 * {@code false} otherwise.
4525 * @see Character#isLowSurrogate(char)
4526 * @see Character.UnicodeBlock#of(int)
4527 * @since 1.5
4528 */
4529 public static boolean isHighSurrogate(char ch) {
4530 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
4531 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
4532 }
4533
4534 /**
4535 * Determines if the given {@code char} value is a
4536 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
4537 * Unicode low-surrogate code unit</a>
4538 * (also known as <i>trailing-surrogate code unit</i>).
4539 *
4540 * <p>Such values do not represent characters by themselves,
4541 * but are used in the representation of
4542 * <a href="#supplementary">supplementary characters</a>
4543 * in the UTF-16 encoding.
4544 *
4545 * @param ch the {@code char} value to be tested.
4546 * @return {@code true} if the {@code char} value is between
4547 * {@link #MIN_LOW_SURROGATE} and
4548 * {@link #MAX_LOW_SURROGATE} inclusive;
4549 * {@code false} otherwise.
4550 * @see Character#isHighSurrogate(char)
4551 * @since 1.5
4552 */
4553 public static boolean isLowSurrogate(char ch) {
4554 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
4555 }
4556
4557 /**
4558 * Determines if the given {@code char} value is a Unicode
4559 * <i>surrogate code unit</i>.
4560 *
4561 * <p>Such values do not represent characters by themselves,
4562 * but are used in the representation of
4563 * <a href="#supplementary">supplementary characters</a>
4564 * in the UTF-16 encoding.
4565 *
4566 * <p>A char value is a surrogate code unit if and only if it is either
4567 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
4568 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
4569 *
4570 * @param ch the {@code char} value to be tested.
4571 * @return {@code true} if the {@code char} value is between
4572 * {@link #MIN_SURROGATE} and
4573 * {@link #MAX_SURROGATE} inclusive;
4574 * {@code false} otherwise.
4575 * @since 1.7
4576 */
4577 public static boolean isSurrogate(char ch) {
4578 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
4579 }
4580
4581 /**
4582 * Determines whether the specified pair of <code>char</code>
4583 * values is a valid
4584 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
4585 * Unicode surrogate pair</a>.
4586
4587 * <p>This method is equivalent to the expression:
4588 * <blockquote><pre>
4589 * isHighSurrogate(high) && isLowSurrogate(low)
4590 * </pre></blockquote>
4591 *
4592 * @param high the high-surrogate code value to be tested
4593 * @param low the low-surrogate code value to be tested
4594 * @return <code>true</code> if the specified high and
4595 * low-surrogate code values represent a valid surrogate pair;
4596 * <code>false</code> otherwise.
4597 * @since 1.5
4598 */
4599 public static boolean isSurrogatePair(char high, char low) {
4600 return isHighSurrogate(high) && isLowSurrogate(low);
4601 }
4602
4603 /**
4604 * Determines the number of <code>char</code> values needed to
4605 * represent the specified character (Unicode code point). If the
4606 * specified character is equal to or greater than 0x10000, then
4607 * the method returns 2. Otherwise, the method returns 1.
4608 *
4609 * <p>This method doesn't validate the specified character to be a
4610 * valid Unicode code point. The caller must validate the
4611 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
4612 * if necessary.
4613 *
4614 * @param codePoint the character (Unicode code point) to be tested.
4615 * @return 2 if the character is a valid supplementary character; 1 otherwise.
4616 * @see Character#isSupplementaryCodePoint(int)
4617 * @since 1.5
4618 */
4619 public static int charCount(int codePoint) {
4620 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
4621 }
4622
4623 /**
4624 * Converts the specified surrogate pair to its supplementary code
4625 * point value. This method does not validate the specified
4626 * surrogate pair. The caller must validate it using {@link
4627 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
4628 *
4629 * @param high the high-surrogate code unit
4630 * @param low the low-surrogate code unit
4631 * @return the supplementary code point composed from the
4632 * specified surrogate pair.
4633 * @since 1.5
4634 */
4635 public static int toCodePoint(char high, char low) {
4636 // Optimized form of:
4637 // return ((high - MIN_HIGH_SURROGATE) << 10)
4638 // + (low - MIN_LOW_SURROGATE)
4639 // + MIN_SUPPLEMENTARY_CODE_POINT;
4640 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
4641 - (MIN_HIGH_SURROGATE << 10)
4642 - MIN_LOW_SURROGATE);
4643 }
4644
4645 /**
4646 * Returns the code point at the given index of the
4647 * <code>CharSequence</code>. If the <code>char</code> value at
4648 * the given index in the <code>CharSequence</code> is in the
4649 * high-surrogate range, the following index is less than the
4650 * length of the <code>CharSequence</code>, and the
4651 * <code>char</code> value at the following index is in the
4652 * low-surrogate range, then the supplementary code point
4653 * corresponding to this surrogate pair is returned. Otherwise,
4654 * the <code>char</code> value at the given index is returned.
4655 *
4656 * @param seq a sequence of <code>char</code> values (Unicode code
4657 * units)
4658 * @param index the index to the <code>char</code> values (Unicode
4659 * code units) in <code>seq</code> to be converted
4660 * @return the Unicode code point at the given index
4661 * @exception NullPointerException if <code>seq</code> is null.
4662 * @exception IndexOutOfBoundsException if the value
4663 * <code>index</code> is negative or not less than
4664 * {@link CharSequence#length() seq.length()}.
4665 * @since 1.5
4666 */
4667 public static int codePointAt(CharSequence seq, int index) {
4668 char c1 = seq.charAt(index++);
4669 if (isHighSurrogate(c1)) {
4670 if (index < seq.length()) {
4671 char c2 = seq.charAt(index);
4672 if (isLowSurrogate(c2)) {
4673 return toCodePoint(c1, c2);
4674 }
4675 }
4676 }
4677 return c1;
4678 }
4679
4680 /**
4681 * Returns the code point at the given index of the
4682 * <code>char</code> array. If the <code>char</code> value at
4683 * the given index in the <code>char</code> array is in the
4684 * high-surrogate range, the following index is less than the
4685 * length of the <code>char</code> array, and the
4686 * <code>char</code> value at the following index is in the
4687 * low-surrogate range, then the supplementary code point
4688 * corresponding to this surrogate pair is returned. Otherwise,
4689 * the <code>char</code> value at the given index is returned.
4690 *
4691 * @param a the <code>char</code> array
4692 * @param index the index to the <code>char</code> values (Unicode
4693 * code units) in the <code>char</code> array to be converted
4694 * @return the Unicode code point at the given index
4695 * @exception NullPointerException if <code>a</code> is null.
4696 * @exception IndexOutOfBoundsException if the value
4697 * <code>index</code> is negative or not less than
4698 * the length of the <code>char</code> array.
4699 * @since 1.5
4700 */
4701 public static int codePointAt(char[] a, int index) {
4702 return codePointAtImpl(a, index, a.length);
4703 }
4704
4705 /**
4706 * Returns the code point at the given index of the
4707 * <code>char</code> array, where only array elements with
4708 * <code>index</code> less than <code>limit</code> can be used. If
4709 * the <code>char</code> value at the given index in the
4710 * <code>char</code> array is in the high-surrogate range, the
4711 * following index is less than the <code>limit</code>, and the
4712 * <code>char</code> value at the following index is in the
4713 * low-surrogate range, then the supplementary code point
4714 * corresponding to this surrogate pair is returned. Otherwise,
4715 * the <code>char</code> value at the given index is returned.
4716 *
4717 * @param a the <code>char</code> array
4718 * @param index the index to the <code>char</code> values (Unicode
4719 * code units) in the <code>char</code> array to be converted
4720 * @param limit the index after the last array element that can be used in the
4721 * <code>char</code> array
4722 * @return the Unicode code point at the given index
4723 * @exception NullPointerException if <code>a</code> is null.
4724 * @exception IndexOutOfBoundsException if the <code>index</code>
4725 * argument is negative or not less than the <code>limit</code>
4726 * argument, or if the <code>limit</code> argument is negative or
4727 * greater than the length of the <code>char</code> array.
4728 * @since 1.5
4729 */
4730 public static int codePointAt(char[] a, int index, int limit) {
4731 if (index >= limit || limit < 0 || limit > a.length) {
4732 throw new IndexOutOfBoundsException();
4733 }
4734 return codePointAtImpl(a, index, limit);
4735 }
4736
4737 // throws ArrayIndexOutofBoundsException if index out of bounds
4738 static int codePointAtImpl(char[] a, int index, int limit) {
4739 char c1 = a[index++];
4740 if (isHighSurrogate(c1)) {
4741 if (index < limit) {
4742 char c2 = a[index];
4743 if (isLowSurrogate(c2)) {
4744 return toCodePoint(c1, c2);
4745 }
4746 }
4747 }
4748 return c1;
4749 }
4750
4751 /**
4752 * Returns the code point preceding the given index of the
4753 * <code>CharSequence</code>. If the <code>char</code> value at
4754 * <code>(index - 1)</code> in the <code>CharSequence</code> is in
4755 * the low-surrogate range, <code>(index - 2)</code> is not
4756 * negative, and the <code>char</code> value at <code>(index -
4757 * 2)</code> in the <code>CharSequence</code> is in the
4758 * high-surrogate range, then the supplementary code point
4759 * corresponding to this surrogate pair is returned. Otherwise,
4760 * the <code>char</code> value at <code>(index - 1)</code> is
4761 * returned.
4762 *
4763 * @param seq the <code>CharSequence</code> instance
4764 * @param index the index following the code point that should be returned
4765 * @return the Unicode code point value before the given index.
4766 * @exception NullPointerException if <code>seq</code> is null.
4767 * @exception IndexOutOfBoundsException if the <code>index</code>
4768 * argument is less than 1 or greater than {@link
4769 * CharSequence#length() seq.length()}.
4770 * @since 1.5
4771 */
4772 public static int codePointBefore(CharSequence seq, int index) {
4773 char c2 = seq.charAt(--index);
4774 if (isLowSurrogate(c2)) {
4775 if (index > 0) {
4776 char c1 = seq.charAt(--index);
4777 if (isHighSurrogate(c1)) {
4778 return toCodePoint(c1, c2);
4779 }
4780 }
4781 }
4782 return c2;
4783 }
4784
4785 /**
4786 * Returns the code point preceding the given index of the
4787 * <code>char</code> array. If the <code>char</code> value at
4788 * <code>(index - 1)</code> in the <code>char</code> array is in
4789 * the low-surrogate range, <code>(index - 2)</code> is not
4790 * negative, and the <code>char</code> value at <code>(index -
4791 * 2)</code> in the <code>char</code> array is in the
4792 * high-surrogate range, then the supplementary code point
4793 * corresponding to this surrogate pair is returned. Otherwise,
4794 * the <code>char</code> value at <code>(index - 1)</code> is
4795 * returned.
4796 *
4797 * @param a the <code>char</code> array
4798 * @param index the index following the code point that should be returned
4799 * @return the Unicode code point value before the given index.
4800 * @exception NullPointerException if <code>a</code> is null.
4801 * @exception IndexOutOfBoundsException if the <code>index</code>
4802 * argument is less than 1 or greater than the length of the
4803 * <code>char</code> array
4804 * @since 1.5
4805 */
4806 public static int codePointBefore(char[] a, int index) {
4807 return codePointBeforeImpl(a, index, 0);
4808 }
4809
4810 /**
4811 * Returns the code point preceding the given index of the
4812 * <code>char</code> array, where only array elements with
4813 * <code>index</code> greater than or equal to <code>start</code>
4814 * can be used. If the <code>char</code> value at <code>(index -
4815 * 1)</code> in the <code>char</code> array is in the
4816 * low-surrogate range, <code>(index - 2)</code> is not less than
4817 * <code>start</code>, and the <code>char</code> value at
4818 * <code>(index - 2)</code> in the <code>char</code> array is in
4819 * the high-surrogate range, then the supplementary code point
4820 * corresponding to this surrogate pair is returned. Otherwise,
4821 * the <code>char</code> value at <code>(index - 1)</code> is
4822 * returned.
4823 *
4824 * @param a the <code>char</code> array
4825 * @param index the index following the code point that should be returned
4826 * @param start the index of the first array element in the
4827 * <code>char</code> array
4828 * @return the Unicode code point value before the given index.
4829 * @exception NullPointerException if <code>a</code> is null.
4830 * @exception IndexOutOfBoundsException if the <code>index</code>
4831 * argument is not greater than the <code>start</code> argument or
4832 * is greater than the length of the <code>char</code> array, or
4833 * if the <code>start</code> argument is negative or not less than
4834 * the length of the <code>char</code> array.
4835 * @since 1.5
4836 */
4837 public static int codePointBefore(char[] a, int index, int start) {
4838 if (index <= start || start < 0 || start >= a.length) {
4839 throw new IndexOutOfBoundsException();
4840 }
4841 return codePointBeforeImpl(a, index, start);
4842 }
4843
4844 // throws ArrayIndexOutofBoundsException if index-1 out of bounds
4845 static int codePointBeforeImpl(char[] a, int index, int start) {
4846 char c2 = a[--index];
4847 if (isLowSurrogate(c2)) {
4848 if (index > start) {
4849 char c1 = a[--index];
4850 if (isHighSurrogate(c1)) {
4851 return toCodePoint(c1, c2);
4852 }
4853 }
4854 }
4855 return c2;
4856 }
4857
4858 /**
4859 * Returns the leading surrogate (a
4860 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
4861 * high surrogate code unit</a>) of the
4862 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
4863 * surrogate pair</a>
4864 * representing the specified supplementary character (Unicode
4865 * code point) in the UTF-16 encoding. If the specified character
4866 * is not a
4867 * <a href="Character.html#supplementary">supplementary character</a>,
4868 * an unspecified {@code char} is returned.
4869 *
4870 * <p>If
4871 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
4872 * is {@code true}, then
4873 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
4874 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
4875 * are also always {@code true}.
4876 *
4877 * @param codePoint a supplementary character (Unicode code point)
4878 * @return the leading surrogate code unit used to represent the
4879 * character in the UTF-16 encoding
4880 * @since 1.7
4881 */
4882 public static char highSurrogate(int codePoint) {
4883 return (char) ((codePoint >>> 10)
4884 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
4885 }
4886
4887 /**
4888 * Returns the trailing surrogate (a
4889 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
4890 * low surrogate code unit</a>) of the
4891 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
4892 * surrogate pair</a>
4893 * representing the specified supplementary character (Unicode
4894 * code point) in the UTF-16 encoding. If the specified character
4895 * is not a
4896 * <a href="Character.html#supplementary">supplementary character</a>,
4897 * an unspecified {@code char} is returned.
4898 *
4899 * <p>If
4900 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
4901 * is {@code true}, then
4902 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
4903 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
4904 * are also always {@code true}.
4905 *
4906 * @param codePoint a supplementary character (Unicode code point)
4907 * @return the trailing surrogate code unit used to represent the
4908 * character in the UTF-16 encoding
4909 * @since 1.7
4910 */
4911 public static char lowSurrogate(int codePoint) {
4912 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
4913 }
4914
4915 /**
4916 * Converts the specified character (Unicode code point) to its
4917 * UTF-16 representation. If the specified code point is a BMP
4918 * (Basic Multilingual Plane or Plane 0) value, the same value is
4919 * stored in <code>dst[dstIndex]</code>, and 1 is returned. If the
4920 * specified code point is a supplementary character, its
4921 * surrogate values are stored in <code>dst[dstIndex]</code>
4922 * (high-surrogate) and <code>dst[dstIndex+1]</code>
4923 * (low-surrogate), and 2 is returned.
4924 *
4925 * @param codePoint the character (Unicode code point) to be converted.
4926 * @param dst an array of <code>char</code> in which the
4927 * <code>codePoint</code>'s UTF-16 value is stored.
4928 * @param dstIndex the start index into the <code>dst</code>
4929 * array where the converted value is stored.
4930 * @return 1 if the code point is a BMP code point, 2 if the
4931 * code point is a supplementary code point.
4932 * @exception IllegalArgumentException if the specified
4933 * <code>codePoint</code> is not a valid Unicode code point.
4934 * @exception NullPointerException if the specified <code>dst</code> is null.
4935 * @exception IndexOutOfBoundsException if <code>dstIndex</code>
4936 * is negative or not less than <code>dst.length</code>, or if
4937 * <code>dst</code> at <code>dstIndex</code> doesn't have enough
4938 * array element(s) to store the resulting <code>char</code>
4939 * value(s). (If <code>dstIndex</code> is equal to
4940 * <code>dst.length-1</code> and the specified
4941 * <code>codePoint</code> is a supplementary character, the
4942 * high-surrogate value is not stored in
4943 * <code>dst[dstIndex]</code>.)
4944 * @since 1.5
4945 */
4946 public static int toChars(int codePoint, char[] dst, int dstIndex) {
4947 if (isBmpCodePoint(codePoint)) {
4948 dst[dstIndex] = (char) codePoint;
4949 return 1;
4950 } else if (isValidCodePoint(codePoint)) {
4951 toSurrogates(codePoint, dst, dstIndex);
4952 return 2;
4953 } else {
4954 throw new IllegalArgumentException();
4955 }
4956 }
4957
4958 /**
4959 * Converts the specified character (Unicode code point) to its
4960 * UTF-16 representation stored in a <code>char</code> array. If
4961 * the specified code point is a BMP (Basic Multilingual Plane or
4962 * Plane 0) value, the resulting <code>char</code> array has
4963 * the same value as <code>codePoint</code>. If the specified code
4964 * point is a supplementary code point, the resulting
4965 * <code>char</code> array has the corresponding surrogate pair.
4966 *
4967 * @param codePoint a Unicode code point
4968 * @return a <code>char</code> array having
4969 * <code>codePoint</code>'s UTF-16 representation.
4970 * @exception IllegalArgumentException if the specified
4971 * <code>codePoint</code> is not a valid Unicode code point.
4972 * @since 1.5
4973 */
4974 public static char[] toChars(int codePoint) {
4975 if (isBmpCodePoint(codePoint)) {
4976 return new char[] { (char) codePoint };
4977 } else if (isValidCodePoint(codePoint)) {
4978 char[] result = new char[2];
4979 toSurrogates(codePoint, result, 0);
4980 return result;
4981 } else {
4982 throw new IllegalArgumentException();
4983 }
4984 }
4985
4986 static void toSurrogates(int codePoint, char[] dst, int index) {
4987 // We write elements "backwards" to guarantee all-or-nothing
4988 dst[index+1] = lowSurrogate(codePoint);
4989 dst[index] = highSurrogate(codePoint);
4990 }
4991
4992 /**
4993 * Returns the number of Unicode code points in the text range of
4994 * the specified char sequence. The text range begins at the
4995 * specified <code>beginIndex</code> and extends to the
4996 * <code>char</code> at index <code>endIndex - 1</code>. Thus the
4997 * length (in <code>char</code>s) of the text range is
4998 * <code>endIndex-beginIndex</code>. Unpaired surrogates within
4999 * the text range count as one code point each.
5000 *
5001 * @param seq the char sequence
5002 * @param beginIndex the index to the first <code>char</code> of
5003 * the text range.
5004 * @param endIndex the index after the last <code>char</code> of
5005 * the text range.
5006 * @return the number of Unicode code points in the specified text
5007 * range
5008 * @exception NullPointerException if <code>seq</code> is null.
5009 * @exception IndexOutOfBoundsException if the
5010 * <code>beginIndex</code> is negative, or <code>endIndex</code>
5011 * is larger than the length of the given sequence, or
5012 * <code>beginIndex</code> is larger than <code>endIndex</code>.
5013 * @since 1.5
5014 */
5015 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
5016 int length = seq.length();
5017 if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) {
5018 throw new IndexOutOfBoundsException();
5019 }
5020 int n = endIndex - beginIndex;
5021 for (int i = beginIndex; i < endIndex; ) {
5022 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
5023 isLowSurrogate(seq.charAt(i))) {
5024 n--;
5025 i++;
5026 }
5027 }
5028 return n;
5029 }
5030
5031 /**
5032 * Returns the number of Unicode code points in a subarray of the
5033 * <code>char</code> array argument. The <code>offset</code>
5034 * argument is the index of the first <code>char</code> of the
5035 * subarray and the <code>count</code> argument specifies the
5036 * length of the subarray in <code>char</code>s. Unpaired
5037 * surrogates within the subarray count as one code point each.
5038 *
5039 * @param a the <code>char</code> array
5040 * @param offset the index of the first <code>char</code> in the
5041 * given <code>char</code> array
5042 * @param count the length of the subarray in <code>char</code>s
5043 * @return the number of Unicode code points in the specified subarray
5044 * @exception NullPointerException if <code>a</code> is null.
5045 * @exception IndexOutOfBoundsException if <code>offset</code> or
5046 * <code>count</code> is negative, or if <code>offset +
5047 * count</code> is larger than the length of the given array.
5048 * @since 1.5
5049 */
5050 public static int codePointCount(char[] a, int offset, int count) {
5051 if (count > a.length - offset || offset < 0 || count < 0) {
5052 throw new IndexOutOfBoundsException();
5053 }
5054 return codePointCountImpl(a, offset, count);
5055 }
5056
5057 static int codePointCountImpl(char[] a, int offset, int count) {
5058 int endIndex = offset + count;
5059 int n = count;
5060 for (int i = offset; i < endIndex; ) {
5061 if (isHighSurrogate(a[i++]) && i < endIndex &&
5062 isLowSurrogate(a[i])) {
5063 n--;
5064 i++;
5065 }
5066 }
5067 return n;
5068 }
5069
5070 /**
5071 * Returns the index within the given char sequence that is offset
5072 * from the given <code>index</code> by <code>codePointOffset</code>
5073 * code points. Unpaired surrogates within the text range given by
5074 * <code>index</code> and <code>codePointOffset</code> count as
5075 * one code point each.
5076 *
5077 * @param seq the char sequence
5078 * @param index the index to be offset
5079 * @param codePointOffset the offset in code points
5080 * @return the index within the char sequence
5081 * @exception NullPointerException if <code>seq</code> is null.
5082 * @exception IndexOutOfBoundsException if <code>index</code>
5083 * is negative or larger then the length of the char sequence,
5084 * or if <code>codePointOffset</code> is positive and the
5085 * subsequence starting with <code>index</code> has fewer than
5086 * <code>codePointOffset</code> code points, or if
5087 * <code>codePointOffset</code> is negative and the subsequence
5088 * before <code>index</code> has fewer than the absolute value
5089 * of <code>codePointOffset</code> code points.
5090 * @since 1.5
5091 */
5092 public static int offsetByCodePoints(CharSequence seq, int index,
5093 int codePointOffset) {
5094 int length = seq.length();
5095 if (index < 0 || index > length) {
5096 throw new IndexOutOfBoundsException();
5097 }
5098
5099 int x = index;
5100 if (codePointOffset >= 0) {
5101 int i;
5102 for (i = 0; x < length && i < codePointOffset; i++) {
5103 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
5104 isLowSurrogate(seq.charAt(x))) {
5105 x++;
5106 }
5107 }
5108 if (i < codePointOffset) {
5109 throw new IndexOutOfBoundsException();
5110 }
5111 } else {
5112 int i;
5113 for (i = codePointOffset; x > 0 && i < 0; i++) {
5114 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
5115 isHighSurrogate(seq.charAt(x-1))) {
5116 x--;
5117 }
5118 }
5119 if (i < 0) {
5120 throw new IndexOutOfBoundsException();
5121 }
5122 }
5123 return x;
5124 }
5125
5126 /**
5127 * Returns the index within the given <code>char</code> subarray
5128 * that is offset from the given <code>index</code> by
5129 * <code>codePointOffset</code> code points. The
5130 * <code>start</code> and <code>count</code> arguments specify a
5131 * subarray of the <code>char</code> array. Unpaired surrogates
5132 * within the text range given by <code>index</code> and
5133 * <code>codePointOffset</code> count as one code point each.
5134 *
5135 * @param a the <code>char</code> array
5136 * @param start the index of the first <code>char</code> of the
5137 * subarray
5138 * @param count the length of the subarray in <code>char</code>s
5139 * @param index the index to be offset
5140 * @param codePointOffset the offset in code points
5141 * @return the index within the subarray
5142 * @exception NullPointerException if <code>a</code> is null.
5143 * @exception IndexOutOfBoundsException
5144 * if <code>start</code> or <code>count</code> is negative,
5145 * or if <code>start + count</code> is larger than the length of
5146 * the given array,
5147 * or if <code>index</code> is less than <code>start</code> or
5148 * larger then <code>start + count</code>,
5149 * or if <code>codePointOffset</code> is positive and the text range
5150 * starting with <code>index</code> and ending with <code>start
5151 * + count - 1</code> has fewer than <code>codePointOffset</code> code
5152 * points,
5153 * or if <code>codePointOffset</code> is negative and the text range
5154 * starting with <code>start</code> and ending with <code>index
5155 * - 1</code> has fewer than the absolute value of
5156 * <code>codePointOffset</code> code points.
5157 * @since 1.5
5158 */
5159 public static int offsetByCodePoints(char[] a, int start, int count,
5160 int index, int codePointOffset) {
5161 if (count > a.length-start || start < 0 || count < 0
5162 || index < start || index > start+count) {
5163 throw new IndexOutOfBoundsException();
5164 }
5165 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
5166 }
5167
5168 static int offsetByCodePointsImpl(char[]a, int start, int count,
5169 int index, int codePointOffset) {
5170 int x = index;
5171 if (codePointOffset >= 0) {
5172 int limit = start + count;
5173 int i;
5174 for (i = 0; x < limit && i < codePointOffset; i++) {
5175 if (isHighSurrogate(a[x++]) && x < limit &&
5176 isLowSurrogate(a[x])) {
5177 x++;
5178 }
5179 }
5180 if (i < codePointOffset) {
5181 throw new IndexOutOfBoundsException();
5182 }
5183 } else {
5184 int i;
5185 for (i = codePointOffset; x > start && i < 0; i++) {
5186 if (isLowSurrogate(a[--x]) && x > start &&
5187 isHighSurrogate(a[x-1])) {
5188 x--;
5189 }
5190 }
5191 if (i < 0) {
5192 throw new IndexOutOfBoundsException();
5193 }
5194 }
5195 return x;
5196 }
5197
5198 /**
5199 * Determines if the specified character is a lowercase character.
5200 * <p>
5201 * A character is lowercase if its general category type, provided
5202 * by <code>Character.getType(ch)</code>, is
5203 * <code>LOWERCASE_LETTER</code>.
5204 * <p>
5205 * The following are examples of lowercase characters:
5206 * <p><blockquote><pre>
5207 * 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
5208 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
5209 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
5210 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
5211 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
5212 * </pre></blockquote>
5213 * <p> Many other Unicode characters are lowercase too.
5214 *
5215 * <p><b>Note:</b> This method cannot handle <a
5216 * href="#supplementary"> supplementary characters</a>. To support
5217 * all Unicode characters, including supplementary characters, use
5218 * the {@link #isLowerCase(int)} method.
5219 *
5220 * @param ch the character to be tested.
5221 * @return <code>true</code> if the character is lowercase;
5222 * <code>false</code> otherwise.
5223 * @see Character#isLowerCase(char)
5224 * @see Character#isTitleCase(char)
5225 * @see Character#toLowerCase(char)
5226 * @see Character#getType(char)
5227 */
5228 public static boolean isLowerCase(char ch) {
5229 return isLowerCase((int)ch);
5230 }
5231
5232 /**
5233 * Determines if the specified character (Unicode code point) is a
5234 * lowercase character.
5235 * <p>
5236 * A character is lowercase if its general category type, provided
5237 * by {@link Character#getType getType(codePoint)}, is
5238 * <code>LOWERCASE_LETTER</code>.
5239 * <p>
5240 * The following are examples of lowercase characters:
5241 * <p><blockquote><pre>
5242 * 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
5243 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
5244 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
5245 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
5246 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
5247 * </pre></blockquote>
5248 * <p> Many other Unicode characters are lowercase too.
5249 *
5250 * @param codePoint the character (Unicode code point) to be tested.
5251 * @return <code>true</code> if the character is lowercase;
5252 * <code>false</code> otherwise.
5253 * @see Character#isLowerCase(int)
5254 * @see Character#isTitleCase(int)
5255 * @see Character#toLowerCase(int)
5256 * @see Character#getType(int)
5257 * @since 1.5
5258 */
5259 public static boolean isLowerCase(int codePoint) {
5260 return getType(codePoint) == Character.LOWERCASE_LETTER;
5261 }
5262
5263 /**
5264 * Determines if the specified character is an uppercase character.
5265 * <p>
5266 * A character is uppercase if its general category type, provided by
5267 * <code>Character.getType(ch)</code>, is <code>UPPERCASE_LETTER</code>.
5268 * <p>
5269 * The following are examples of uppercase characters:
5270 * <p><blockquote><pre>
5271 * 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
5272 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
5273 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
5274 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
5275 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
5276 * </pre></blockquote>
5277 * <p> Many other Unicode characters are uppercase too.<p>
5278 *
5279 * <p><b>Note:</b> This method cannot handle <a
5280 * href="#supplementary"> supplementary characters</a>. To support
5281 * all Unicode characters, including supplementary characters, use
5282 * the {@link #isUpperCase(int)} method.
5283 *
5284 * @param ch the character to be tested.
5285 * @return <code>true</code> if the character is uppercase;
5286 * <code>false</code> otherwise.
5287 * @see Character#isLowerCase(char)
5288 * @see Character#isTitleCase(char)
5289 * @see Character#toUpperCase(char)
5290 * @see Character#getType(char)
5291 * @since 1.0
5292 */
5293 public static boolean isUpperCase(char ch) {
5294 return isUpperCase((int)ch);
5295 }
5296
5297 /**
5298 * Determines if the specified character (Unicode code point) is an uppercase character.
5299 * <p>
5300 * A character is uppercase if its general category type, provided by
5301 * {@link Character#getType(int) getType(codePoint)}, is <code>UPPERCASE_LETTER</code>.
5302 * <p>
5303 * The following are examples of uppercase characters:
5304 * <p><blockquote><pre>
5305 * 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
5306 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
5307 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
5308 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
5309 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
5310 * </pre></blockquote>
5311 * <p> Many other Unicode characters are uppercase too.<p>
5312 *
5313 * @param codePoint the character (Unicode code point) to be tested.
5314 * @return <code>true</code> if the character is uppercase;
5315 * <code>false</code> otherwise.
5316 * @see Character#isLowerCase(int)
5317 * @see Character#isTitleCase(int)
5318 * @see Character#toUpperCase(int)
5319 * @see Character#getType(int)
5320 * @since 1.5
5321 */
5322 public static boolean isUpperCase(int codePoint) {
5323 return getType(codePoint) == Character.UPPERCASE_LETTER;
5324 }
5325
5326 /**
5327 * Determines if the specified character is a titlecase character.
5328 * <p>
5329 * A character is a titlecase character if its general
5330 * category type, provided by <code>Character.getType(ch)</code>,
5331 * is <code>TITLECASE_LETTER</code>.
5332 * <p>
5333 * Some characters look like pairs of Latin letters. For example, there
5334 * is an uppercase letter that looks like "LJ" and has a corresponding
5335 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
5336 * is the appropriate form to use when rendering a word in lowercase
5337 * with initial capitals, as for a book title.
5338 * <p>
5339 * These are some of the Unicode characters for which this method returns
5340 * <code>true</code>:
5341 * <ul>
5342 * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON</code>
5343 * <li><code>LATIN CAPITAL LETTER L WITH SMALL LETTER J</code>
5344 * <li><code>LATIN CAPITAL LETTER N WITH SMALL LETTER J</code>
5345 * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z</code>
5346 * </ul>
5347 * <p> Many other Unicode characters are titlecase too.<p>
5348 *
5349 * <p><b>Note:</b> This method cannot handle <a
5350 * href="#supplementary"> supplementary characters</a>. To support
5351 * all Unicode characters, including supplementary characters, use
5352 * the {@link #isTitleCase(int)} method.
5353 *
5354 * @param ch the character to be tested.
5355 * @return <code>true</code> if the character is titlecase;
5356 * <code>false</code> otherwise.
5357 * @see Character#isLowerCase(char)
5358 * @see Character#isUpperCase(char)
5359 * @see Character#toTitleCase(char)
5360 * @see Character#getType(char)
5361 * @since 1.0.2
5362 */
5363 public static boolean isTitleCase(char ch) {
5364 return isTitleCase((int)ch);
5365 }
5366
5367 /**
5368 * Determines if the specified character (Unicode code point) is a titlecase character.
5369 * <p>
5370 * A character is a titlecase character if its general
5371 * category type, provided by {@link Character#getType(int) getType(codePoint)},
5372 * is <code>TITLECASE_LETTER</code>.
5373 * <p>
5374 * Some characters look like pairs of Latin letters. For example, there
5375 * is an uppercase letter that looks like "LJ" and has a corresponding
5376 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
5377 * is the appropriate form to use when rendering a word in lowercase
5378 * with initial capitals, as for a book title.
5379 * <p>
5380 * These are some of the Unicode characters for which this method returns
5381 * <code>true</code>:
5382 * <ul>
5383 * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON</code>
5384 * <li><code>LATIN CAPITAL LETTER L WITH SMALL LETTER J</code>
5385 * <li><code>LATIN CAPITAL LETTER N WITH SMALL LETTER J</code>
5386 * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z</code>
5387 * </ul>
5388 * <p> Many other Unicode characters are titlecase too.<p>
5389 *
5390 * @param codePoint the character (Unicode code point) to be tested.
5391 * @return <code>true</code> if the character is titlecase;
5392 * <code>false</code> otherwise.
5393 * @see Character#isLowerCase(int)
5394 * @see Character#isUpperCase(int)
5395 * @see Character#toTitleCase(int)
5396 * @see Character#getType(int)
5397 * @since 1.5
5398 */
5399 public static boolean isTitleCase(int codePoint) {
5400 return getType(codePoint) == Character.TITLECASE_LETTER;
5401 }
5402
5403 /**
5404 * Determines if the specified character is a digit.
5405 * <p>
5406 * A character is a digit if its general category type, provided
5407 * by <code>Character.getType(ch)</code>, is
5408 * <code>DECIMAL_DIGIT_NUMBER</code>.
5409 * <p>
5410 * Some Unicode character ranges that contain digits:
5411 * <ul>
5412 * <li><code>'\u0030'</code> through <code>'\u0039'</code>,
5413 * ISO-LATIN-1 digits (<code>'0'</code> through <code>'9'</code>)
5414 * <li><code>'\u0660'</code> through <code>'\u0669'</code>,
5415 * Arabic-Indic digits
5416 * <li><code>'\u06F0'</code> through <code>'\u06F9'</code>,
5417 * Extended Arabic-Indic digits
5418 * <li><code>'\u0966'</code> through <code>'\u096F'</code>,
5419 * Devanagari digits
5420 * <li><code>'\uFF10'</code> through <code>'\uFF19'</code>,
5421 * Fullwidth digits
5422 * </ul>
5423 *
5424 * Many other character ranges contain digits as well.
5425 *
5426 * <p><b>Note:</b> This method cannot handle <a
5427 * href="#supplementary"> supplementary characters</a>. To support
5428 * all Unicode characters, including supplementary characters, use
5429 * the {@link #isDigit(int)} method.
5430 *
5431 * @param ch the character to be tested.
5432 * @return <code>true</code> if the character is a digit;
5433 * <code>false</code> otherwise.
5434 * @see Character#digit(char, int)
5435 * @see Character#forDigit(int, int)
5436 * @see Character#getType(char)
5437 */
5438 public static boolean isDigit(char ch) {
5439 return isDigit((int)ch);
5440 }
5441
5442 /**
5443 * Determines if the specified character (Unicode code point) is a digit.
5444 * <p>
5445 * A character is a digit if its general category type, provided
5446 * by {@link Character#getType(int) getType(codePoint)}, is
5447 * <code>DECIMAL_DIGIT_NUMBER</code>.
5448 * <p>
5449 * Some Unicode character ranges that contain digits:
5450 * <ul>
5451 * <li><code>'\u0030'</code> through <code>'\u0039'</code>,
5452 * ISO-LATIN-1 digits (<code>'0'</code> through <code>'9'</code>)
5453 * <li><code>'\u0660'</code> through <code>'\u0669'</code>,
5454 * Arabic-Indic digits
5455 * <li><code>'\u06F0'</code> through <code>'\u06F9'</code>,
5456 * Extended Arabic-Indic digits
5457 * <li><code>'\u0966'</code> through <code>'\u096F'</code>,
5458 * Devanagari digits
5459 * <li><code>'\uFF10'</code> through <code>'\uFF19'</code>,
5460 * Fullwidth digits
5461 * </ul>
5462 *
5463 * Many other character ranges contain digits as well.
5464 *
5465 * @param codePoint the character (Unicode code point) to be tested.
5466 * @return <code>true</code> if the character is a digit;
5467 * <code>false</code> otherwise.
5468 * @see Character#forDigit(int, int)
5469 * @see Character#getType(int)
5470 * @since 1.5
5471 */
5472 public static boolean isDigit(int codePoint) {
5473 return getType(codePoint) == Character.DECIMAL_DIGIT_NUMBER;
5474 }
5475
5476 /**
5477 * Determines if a character is defined in Unicode.
5478 * <p>
5479 * A character is defined if at least one of the following is true:
5480 * <ul>
5481 * <li>It has an entry in the UnicodeData file.
5482 * <li>It has a value in a range defined by the UnicodeData file.
5483 * </ul>
5484 *
5485 * <p><b>Note:</b> This method cannot handle <a
5486 * href="#supplementary"> supplementary characters</a>. To support
5487 * all Unicode characters, including supplementary characters, use
5488 * the {@link #isDefined(int)} method.
5489 *
5490 * @param ch the character to be tested
5491 * @return <code>true</code> if the character has a defined meaning
5492 * in Unicode; <code>false</code> otherwise.
5493 * @see Character#isDigit(char)
5494 * @see Character#isLetter(char)
5495 * @see Character#isLetterOrDigit(char)
5496 * @see Character#isLowerCase(char)
5497 * @see Character#isTitleCase(char)
5498 * @see Character#isUpperCase(char)
5499 * @since 1.0.2
5500 */
5501 public static boolean isDefined(char ch) {
5502 return isDefined((int)ch);
5503 }
5504
5505 /**
5506 * Determines if a character (Unicode code point) is defined in Unicode.
5507 * <p>
5508 * A character is defined if at least one of the following is true:
5509 * <ul>
5510 * <li>It has an entry in the UnicodeData file.
5511 * <li>It has a value in a range defined by the UnicodeData file.
5512 * </ul>
5513 *
5514 * @param codePoint the character (Unicode code point) to be tested.
5515 * @return <code>true</code> if the character has a defined meaning
5516 * in Unicode; <code>false</code> otherwise.
5517 * @see Character#isDigit(int)
5518 * @see Character#isLetter(int)
5519 * @see Character#isLetterOrDigit(int)
5520 * @see Character#isLowerCase(int)
5521 * @see Character#isTitleCase(int)
5522 * @see Character#isUpperCase(int)
5523 * @since 1.5
5524 */
5525 public static boolean isDefined(int codePoint) {
5526 return getType(codePoint) != Character.UNASSIGNED;
5527 }
5528
5529 /**
5530 * Determines if the specified character is a letter.
5531 * <p>
5532 * A character is considered to be a letter if its general
5533 * category type, provided by <code>Character.getType(ch)</code>,
5534 * is any of the following:
5535 * <ul>
5536 * <li> <code>UPPERCASE_LETTER</code>
5537 * <li> <code>LOWERCASE_LETTER</code>
5538 * <li> <code>TITLECASE_LETTER</code>
5539 * <li> <code>MODIFIER_LETTER</code>
5540 * <li> <code>OTHER_LETTER</code>
5541 * </ul>
5542 *
5543 * Not all letters have case. Many characters are
5544 * letters but are neither uppercase nor lowercase nor titlecase.
5545 *
5546 * <p><b>Note:</b> This method cannot handle <a
5547 * href="#supplementary"> supplementary characters</a>. To support
5548 * all Unicode characters, including supplementary characters, use
5549 * the {@link #isLetter(int)} method.
5550 *
5551 * @param ch the character to be tested.
5552 * @return <code>true</code> if the character is a letter;
5553 * <code>false</code> otherwise.
5554 * @see Character#isDigit(char)
5555 * @see Character#isJavaIdentifierStart(char)
5556 * @see Character#isJavaLetter(char)
5557 * @see Character#isJavaLetterOrDigit(char)
5558 * @see Character#isLetterOrDigit(char)
5559 * @see Character#isLowerCase(char)
5560 * @see Character#isTitleCase(char)
5561 * @see Character#isUnicodeIdentifierStart(char)
5562 * @see Character#isUpperCase(char)
5563 */
5564 public static boolean isLetter(char ch) {
5565 return isLetter((int)ch);
5566 }
5567
5568 /**
5569 * Determines if the specified character (Unicode code point) is a letter.
5570 * <p>
5571 * A character is considered to be a letter if its general
5572 * category type, provided by {@link Character#getType(int) getType(codePoint)},
5573 * is any of the following:
5574 * <ul>
5575 * <li> <code>UPPERCASE_LETTER</code>
5576 * <li> <code>LOWERCASE_LETTER</code>
5577 * <li> <code>TITLECASE_LETTER</code>
5578 * <li> <code>MODIFIER_LETTER</code>
5579 * <li> <code>OTHER_LETTER</code>
5580 * </ul>
5581 *
5582 * Not all letters have case. Many characters are
5583 * letters but are neither uppercase nor lowercase nor titlecase.
5584 *
5585 * @param codePoint the character (Unicode code point) to be tested.
5586 * @return <code>true</code> if the character is a letter;
5587 * <code>false</code> otherwise.
5588 * @see Character#isDigit(int)
5589 * @see Character#isJavaIdentifierStart(int)
5590 * @see Character#isLetterOrDigit(int)
5591 * @see Character#isLowerCase(int)
5592 * @see Character#isTitleCase(int)
5593 * @see Character#isUnicodeIdentifierStart(int)
5594 * @see Character#isUpperCase(int)
5595 * @since 1.5
5596 */
5597 public static boolean isLetter(int codePoint) {
5598 return ((((1 << Character.UPPERCASE_LETTER) |
5599 (1 << Character.LOWERCASE_LETTER) |
5600 (1 << Character.TITLECASE_LETTER) |
5601 (1 << Character.MODIFIER_LETTER) |
5602 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
5603 != 0;
5604 }
5605
5606 /**
5607 * Determines if the specified character is a letter or digit.
5608 * <p>
5609 * A character is considered to be a letter or digit if either
5610 * <code>Character.isLetter(char ch)</code> or
5611 * <code>Character.isDigit(char ch)</code> returns
5612 * <code>true</code> for the character.
5613 *
5614 * <p><b>Note:</b> This method cannot handle <a
5615 * href="#supplementary"> supplementary characters</a>. To support
5616 * all Unicode characters, including supplementary characters, use
5617 * the {@link #isLetterOrDigit(int)} method.
5618 *
5619 * @param ch the character to be tested.
5620 * @return <code>true</code> if the character is a letter or digit;
5621 * <code>false</code> otherwise.
5622 * @see Character#isDigit(char)
5623 * @see Character#isJavaIdentifierPart(char)
5624 * @see Character#isJavaLetter(char)
5625 * @see Character#isJavaLetterOrDigit(char)
5626 * @see Character#isLetter(char)
5627 * @see Character#isUnicodeIdentifierPart(char)
5628 * @since 1.0.2
5629 */
5630 public static boolean isLetterOrDigit(char ch) {
5631 return isLetterOrDigit((int)ch);
5632 }
5633
5634 /**
5635 * Determines if the specified character (Unicode code point) is a letter or digit.
5636 * <p>
5637 * A character is considered to be a letter or digit if either
5638 * {@link #isLetter(int) isLetter(codePoint)} or
5639 * {@link #isDigit(int) isDigit(codePoint)} returns
5640 * <code>true</code> for the character.
5641 *
5642 * @param codePoint the character (Unicode code point) to be tested.
5643 * @return <code>true</code> if the character is a letter or digit;
5644 * <code>false</code> otherwise.
5645 * @see Character#isDigit(int)
5646 * @see Character#isJavaIdentifierPart(int)
5647 * @see Character#isLetter(int)
5648 * @see Character#isUnicodeIdentifierPart(int)
5649 * @since 1.5
5650 */
5651 public static boolean isLetterOrDigit(int codePoint) {
5652 return ((((1 << Character.UPPERCASE_LETTER) |
5653 (1 << Character.LOWERCASE_LETTER) |
5654 (1 << Character.TITLECASE_LETTER) |
5655 (1 << Character.MODIFIER_LETTER) |
5656 (1 << Character.OTHER_LETTER) |
5657 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
5658 != 0;
5659 }
5660
5661 /**
5662 * Determines if the specified character is permissible as the first
5663 * character in a Java identifier.
5664 * <p>
5665 * A character may start a Java identifier if and only if
5666 * one of the following is true:
5667 * <ul>
5668 * <li> {@link #isLetter(char) isLetter(ch)} returns <code>true</code>
5669 * <li> {@link #getType(char) getType(ch)} returns <code>LETTER_NUMBER</code>
5670 * <li> ch is a currency symbol (such as "$")
5671 * <li> ch is a connecting punctuation character (such as "_").
5672 * </ul>
5673 *
5674 * @param ch the character to be tested.
5675 * @return <code>true</code> if the character may start a Java
5676 * identifier; <code>false</code> otherwise.
5677 * @see Character#isJavaLetterOrDigit(char)
5678 * @see Character#isJavaIdentifierStart(char)
5679 * @see Character#isJavaIdentifierPart(char)
5680 * @see Character#isLetter(char)
5681 * @see Character#isLetterOrDigit(char)
5682 * @see Character#isUnicodeIdentifierStart(char)
5683 * @since 1.02
5684 * @deprecated Replaced by isJavaIdentifierStart(char).
5685 */
5686 @Deprecated
5687 public static boolean isJavaLetter(char ch) {
5688 return isJavaIdentifierStart(ch);
5689 }
5690
5691 /**
5692 * Determines if the specified character may be part of a Java
5693 * identifier as other than the first character.
5694 * <p>
5695 * A character may be part of a Java identifier if and only if any
5696 * of the following are true:
5697 * <ul>
5698 * <li> it is a letter
5699 * <li> it is a currency symbol (such as <code>'$'</code>)
5700 * <li> it is a connecting punctuation character (such as <code>'_'</code>)
5701 * <li> it is a digit
5702 * <li> it is a numeric letter (such as a Roman numeral character)
5703 * <li> it is a combining mark
5704 * <li> it is a non-spacing mark
5705 * <li> <code>isIdentifierIgnorable</code> returns
5706 * <code>true</code> for the character.
5707 * </ul>
5708 *
5709 * @param ch the character to be tested.
5710 * @return <code>true</code> if the character may be part of a
5711 * Java identifier; <code>false</code> otherwise.
5712 * @see Character#isJavaLetter(char)
5713 * @see Character#isJavaIdentifierStart(char)
5714 * @see Character#isJavaIdentifierPart(char)
5715 * @see Character#isLetter(char)
5716 * @see Character#isLetterOrDigit(char)
5717 * @see Character#isUnicodeIdentifierPart(char)
5718 * @see Character#isIdentifierIgnorable(char)
5719 * @since 1.02
5720 * @deprecated Replaced by isJavaIdentifierPart(char).
5721 */
5722 @Deprecated
5723 public static boolean isJavaLetterOrDigit(char ch) {
5724 return isJavaIdentifierPart(ch);
5725 }
5726
5727 /**
5728 * Determines if the specified character is
5729 * permissible as the first character in a Java identifier.
5730 * <p>
5731 * A character may start a Java identifier if and only if
5732 * one of the following conditions is true:
5733 * <ul>
5734 * <li> {@link #isLetter(char) isLetter(ch)} returns <code>true</code>
5735 * <li> {@link #getType(char) getType(ch)} returns <code>LETTER_NUMBER</code>
5736 * <li> ch is a currency symbol (such as "$")
5737 * <li> ch is a connecting punctuation character (such as "_").
5738 * </ul>
5739 *
5740 * <p><b>Note:</b> This method cannot handle <a
5741 * href="#supplementary"> supplementary characters</a>. To support
5742 * all Unicode characters, including supplementary characters, use
5743 * the {@link #isJavaIdentifierStart(int)} method.
5744 *
5745 * @param ch the character to be tested.
5746 * @return <code>true</code> if the character may start a Java identifier;
5747 * <code>false</code> otherwise.
5748 * @see Character#isJavaIdentifierPart(char)
5749 * @see Character#isLetter(char)
5750 * @see Character#isUnicodeIdentifierStart(char)
5751 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
5752 * @since 1.1
5753 */
5754 public static boolean isJavaIdentifierStart(char ch) {
5755 return isJavaIdentifierStart((int)ch);
5756 }
5757
5758 /**
5759 * Determines if the character (Unicode code point) is
5760 * permissible as the first character in a Java identifier.
5761 * <p>
5762 * A character may start a Java identifier if and only if
5763 * one of the following conditions is true:
5764 * <ul>
5765 * <li> {@link #isLetter(int) isLetter(codePoint)}
5766 * returns <code>true</code>
5767 * <li> {@link #getType(int) getType(codePoint)}
5768 * returns <code>LETTER_NUMBER</code>
5769 * <li> the referenced character is a currency symbol (such as "$")
5770 * <li> the referenced character is a connecting punctuation character
5771 * (such as "_").
5772 * </ul>
5773 *
5774 * @param codePoint the character (Unicode code point) to be tested.
5775 * @return <code>true</code> if the character may start a Java identifier;
5776 * <code>false</code> otherwise.
5777 * @see Character#isJavaIdentifierPart(int)
5778 * @see Character#isLetter(int)
5779 * @see Character#isUnicodeIdentifierStart(int)
5780 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
5781 * @since 1.5
5782 */
5783 public static boolean isJavaIdentifierStart(int codePoint) {
5784 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
5785 }
5786
5787 /**
5788 * Determines if the specified character may be part of a Java
5789 * identifier as other than the first character.
5790 * <p>
5791 * A character may be part of a Java identifier if any of the following
5792 * are true:
5793 * <ul>
5794 * <li> it is a letter
5795 * <li> it is a currency symbol (such as <code>'$'</code>)
5796 * <li> it is a connecting punctuation character (such as <code>'_'</code>)
5797 * <li> it is a digit
5798 * <li> it is a numeric letter (such as a Roman numeral character)
5799 * <li> it is a combining mark
5800 * <li> it is a non-spacing mark
5801 * <li> <code>isIdentifierIgnorable</code> returns
5802 * <code>true</code> for the character
5803 * </ul>
5804 *
5805 * <p><b>Note:</b> This method cannot handle <a
5806 * href="#supplementary"> supplementary characters</a>. To support
5807 * all Unicode characters, including supplementary characters, use
5808 * the {@link #isJavaIdentifierPart(int)} method.
5809 *
5810 * @param ch the character to be tested.
5811 * @return <code>true</code> if the character may be part of a
5812 * Java identifier; <code>false</code> otherwise.
5813 * @see Character#isIdentifierIgnorable(char)
5814 * @see Character#isJavaIdentifierStart(char)
5815 * @see Character#isLetterOrDigit(char)
5816 * @see Character#isUnicodeIdentifierPart(char)
5817 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
5818 * @since 1.1
5819 */
5820 public static boolean isJavaIdentifierPart(char ch) {
5821 return isJavaIdentifierPart((int)ch);
5822 }
5823
5824 /**
5825 * Determines if the character (Unicode code point) may be part of a Java
5826 * identifier as other than the first character.
5827 * <p>
5828 * A character may be part of a Java identifier if any of the following
5829 * are true:
5830 * <ul>
5831 * <li> it is a letter
5832 * <li> it is a currency symbol (such as <code>'$'</code>)
5833 * <li> it is a connecting punctuation character (such as <code>'_'</code>)
5834 * <li> it is a digit
5835 * <li> it is a numeric letter (such as a Roman numeral character)
5836 * <li> it is a combining mark
5837 * <li> it is a non-spacing mark
5838 * <li> {@link #isIdentifierIgnorable(int)
5839 * isIdentifierIgnorable(codePoint)} returns <code>true</code> for
5840 * the character
5841 * </ul>
5842 *
5843 * @param codePoint the character (Unicode code point) to be tested.
5844 * @return <code>true</code> if the character may be part of a
5845 * Java identifier; <code>false</code> otherwise.
5846 * @see Character#isIdentifierIgnorable(int)
5847 * @see Character#isJavaIdentifierStart(int)
5848 * @see Character#isLetterOrDigit(int)
5849 * @see Character#isUnicodeIdentifierPart(int)
5850 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
5851 * @since 1.5
5852 */
5853 public static boolean isJavaIdentifierPart(int codePoint) {
5854 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
5855 }
5856
5857 /**
5858 * Determines if the specified character is permissible as the
5859 * first character in a Unicode identifier.
5860 * <p>
5861 * A character may start a Unicode identifier if and only if
5862 * one of the following conditions is true:
5863 * <ul>
5864 * <li> {@link #isLetter(char) isLetter(ch)} returns <code>true</code>
5865 * <li> {@link #getType(char) getType(ch)} returns
5866 * <code>LETTER_NUMBER</code>.
5867 * </ul>
5868 *
5869 * <p><b>Note:</b> This method cannot handle <a
5870 * href="#supplementary"> supplementary characters</a>. To support
5871 * all Unicode characters, including supplementary characters, use
5872 * the {@link #isUnicodeIdentifierStart(int)} method.
5873 *
5874 * @param ch the character to be tested.
5875 * @return <code>true</code> if the character may start a Unicode
5876 * identifier; <code>false</code> otherwise.
5877 * @see Character#isJavaIdentifierStart(char)
5878 * @see Character#isLetter(char)
5879 * @see Character#isUnicodeIdentifierPart(char)
5880 * @since 1.1
5881 */
5882 public static boolean isUnicodeIdentifierStart(char ch) {
5883 return isUnicodeIdentifierStart((int)ch);
5884 }
5885
5886 /**
5887 * Determines if the specified character (Unicode code point) is permissible as the
5888 * first character in a Unicode identifier.
5889 * <p>
5890 * A character may start a Unicode identifier if and only if
5891 * one of the following conditions is true:
5892 * <ul>
5893 * <li> {@link #isLetter(int) isLetter(codePoint)}
5894 * returns <code>true</code>
5895 * <li> {@link #getType(int) getType(codePoint)}
5896 * returns <code>LETTER_NUMBER</code>.
5897 * </ul>
5898 * @param codePoint the character (Unicode code point) to be tested.
5899 * @return <code>true</code> if the character may start a Unicode
5900 * identifier; <code>false</code> otherwise.
5901 * @see Character#isJavaIdentifierStart(int)
5902 * @see Character#isLetter(int)
5903 * @see Character#isUnicodeIdentifierPart(int)
5904 * @since 1.5
5905 */
5906 public static boolean isUnicodeIdentifierStart(int codePoint) {
5907 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
5908 }
5909
5910 /**
5911 * Determines if the specified character may be part of a Unicode
5912 * identifier as other than the first character.
5913 * <p>
5914 * A character may be part of a Unicode identifier if and only if
5915 * one of the following statements is true:
5916 * <ul>
5917 * <li> it is a letter
5918 * <li> it is a connecting punctuation character (such as <code>'_'</code>)
5919 * <li> it is a digit
5920 * <li> it is a numeric letter (such as a Roman numeral character)
5921 * <li> it is a combining mark
5922 * <li> it is a non-spacing mark
5923 * <li> <code>isIdentifierIgnorable</code> returns
5924 * <code>true</code> for this character.
5925 * </ul>
5926 *
5927 * <p><b>Note:</b> This method cannot handle <a
5928 * href="#supplementary"> supplementary characters</a>. To support
5929 * all Unicode characters, including supplementary characters, use
5930 * the {@link #isUnicodeIdentifierPart(int)} method.
5931 *
5932 * @param ch the character to be tested.
5933 * @return <code>true</code> if the character may be part of a
5934 * Unicode identifier; <code>false</code> otherwise.
5935 * @see Character#isIdentifierIgnorable(char)
5936 * @see Character#isJavaIdentifierPart(char)
5937 * @see Character#isLetterOrDigit(char)
5938 * @see Character#isUnicodeIdentifierStart(char)
5939 * @since 1.1
5940 */
5941 public static boolean isUnicodeIdentifierPart(char ch) {
5942 return isUnicodeIdentifierPart((int)ch);
5943 }
5944
5945 /**
5946 * Determines if the specified character (Unicode code point) may be part of a Unicode
5947 * identifier as other than the first character.
5948 * <p>
5949 * A character may be part of a Unicode identifier if and only if
5950 * one of the following statements is true:
5951 * <ul>
5952 * <li> it is a letter
5953 * <li> it is a connecting punctuation character (such as <code>'_'</code>)
5954 * <li> it is a digit
5955 * <li> it is a numeric letter (such as a Roman numeral character)
5956 * <li> it is a combining mark
5957 * <li> it is a non-spacing mark
5958 * <li> <code>isIdentifierIgnorable</code> returns
5959 * <code>true</code> for this character.
5960 * </ul>
5961 * @param codePoint the character (Unicode code point) to be tested.
5962 * @return <code>true</code> if the character may be part of a
5963 * Unicode identifier; <code>false</code> otherwise.
5964 * @see Character#isIdentifierIgnorable(int)
5965 * @see Character#isJavaIdentifierPart(int)
5966 * @see Character#isLetterOrDigit(int)
5967 * @see Character#isUnicodeIdentifierStart(int)
5968 * @since 1.5
5969 */
5970 public static boolean isUnicodeIdentifierPart(int codePoint) {
5971 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
5972 }
5973
5974 /**
5975 * Determines if the specified character should be regarded as
5976 * an ignorable character in a Java identifier or a Unicode identifier.
5977 * <p>
5978 * The following Unicode characters are ignorable in a Java identifier
5979 * or a Unicode identifier:
5980 * <ul>
5981 * <li>ISO control characters that are not whitespace
5982 * <ul>
5983 * <li><code>'\u0000'</code> through <code>'\u0008'</code>
5984 * <li><code>'\u000E'</code> through <code>'\u001B'</code>
5985 * <li><code>'\u007F'</code> through <code>'\u009F'</code>
5986 * </ul>
5987 *
5988 * <li>all characters that have the <code>FORMAT</code> general
5989 * category value
5990 * </ul>
5991 *
5992 * <p><b>Note:</b> This method cannot handle <a
5993 * href="#supplementary"> supplementary characters</a>. To support
5994 * all Unicode characters, including supplementary characters, use
5995 * the {@link #isIdentifierIgnorable(int)} method.
5996 *
5997 * @param ch the character to be tested.
5998 * @return <code>true</code> if the character is an ignorable control
5999 * character that may be part of a Java or Unicode identifier;
6000 * <code>false</code> otherwise.
6001 * @see Character#isJavaIdentifierPart(char)
6002 * @see Character#isUnicodeIdentifierPart(char)
6003 * @since 1.1
6004 */
6005 public static boolean isIdentifierIgnorable(char ch) {
6006 return isIdentifierIgnorable((int)ch);
6007 }
6008
6009 /**
6010 * Determines if the specified character (Unicode code point) should be regarded as
6011 * an ignorable character in a Java identifier or a Unicode identifier.
6012 * <p>
6013 * The following Unicode characters are ignorable in a Java identifier
6014 * or a Unicode identifier:
6015 * <ul>
6016 * <li>ISO control characters that are not whitespace
6017 * <ul>
6018 * <li><code>'\u0000'</code> through <code>'\u0008'</code>
6019 * <li><code>'\u000E'</code> through <code>'\u001B'</code>
6020 * <li><code>'\u007F'</code> through <code>'\u009F'</code>
6021 * </ul>
6022 *
6023 * <li>all characters that have the <code>FORMAT</code> general
6024 * category value
6025 * </ul>
6026 *
6027 * @param codePoint the character (Unicode code point) to be tested.
6028 * @return <code>true</code> if the character is an ignorable control
6029 * character that may be part of a Java or Unicode identifier;
6030 * <code>false</code> otherwise.
6031 * @see Character#isJavaIdentifierPart(int)
6032 * @see Character#isUnicodeIdentifierPart(int)
6033 * @since 1.5
6034 */
6035 public static boolean isIdentifierIgnorable(int codePoint) {
6036 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
6037 }
6038
6039 /**
6040 * Converts the character argument to lowercase using case
6041 * mapping information from the UnicodeData file.
6042 * <p>
6043 * Note that
6044 * <code>Character.isLowerCase(Character.toLowerCase(ch))</code>
6045 * does not always return <code>true</code> for some ranges of
6046 * characters, particularly those that are symbols or ideographs.
6047 *
6048 * <p>In general, {@link String#toLowerCase()} should be used to map
6049 * characters to lowercase. <code>String</code> case mapping methods
6050 * have several benefits over <code>Character</code> case mapping methods.
6051 * <code>String</code> case mapping methods can perform locale-sensitive
6052 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
6053 * the <code>Character</code> case mapping methods cannot.
6054 *
6055 * <p><b>Note:</b> This method cannot handle <a
6056 * href="#supplementary"> supplementary characters</a>. To support
6057 * all Unicode characters, including supplementary characters, use
6058 * the {@link #toLowerCase(int)} method.
6059 *
6060 * @param ch the character to be converted.
6061 * @return the lowercase equivalent of the character, if any;
6062 * otherwise, the character itself.
6063 * @see Character#isLowerCase(char)
6064 * @see String#toLowerCase()
6065 */
6066 public static char toLowerCase(char ch) {
6067 return (char)toLowerCase((int)ch);
6068 }
6069
6070 /**
6071 * Converts the character (Unicode code point) argument to
6072 * lowercase using case mapping information from the UnicodeData
6073 * file.
6074 *
6075 * <p> Note that
6076 * <code>Character.isLowerCase(Character.toLowerCase(codePoint))</code>
6077 * does not always return <code>true</code> for some ranges of
6078 * characters, particularly those that are symbols or ideographs.
6079 *
6080 * <p>In general, {@link String#toLowerCase()} should be used to map
6081 * characters to lowercase. <code>String</code> case mapping methods
6082 * have several benefits over <code>Character</code> case mapping methods.
6083 * <code>String</code> case mapping methods can perform locale-sensitive
6084 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
6085 * the <code>Character</code> case mapping methods cannot.
6086 *
6087 * @param codePoint the character (Unicode code point) to be converted.
6088 * @return the lowercase equivalent of the character (Unicode code
6089 * point), if any; otherwise, the character itself.
6090 * @see Character#isLowerCase(int)
6091 * @see String#toLowerCase()
6092 *
6093 * @since 1.5
6094 */
6095 public static int toLowerCase(int codePoint) {
6096 return CharacterData.of(codePoint).toLowerCase(codePoint);
6097 }
6098
6099 /**
6100 * Converts the character argument to uppercase using case mapping
6101 * information from the UnicodeData file.
6102 * <p>
6103 * Note that
6104 * <code>Character.isUpperCase(Character.toUpperCase(ch))</code>
6105 * does not always return <code>true</code> for some ranges of
6106 * characters, particularly those that are symbols or ideographs.
6107 *
6108 * <p>In general, {@link String#toUpperCase()} should be used to map
6109 * characters to uppercase. <code>String</code> case mapping methods
6110 * have several benefits over <code>Character</code> case mapping methods.
6111 * <code>String</code> case mapping methods can perform locale-sensitive
6112 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
6113 * the <code>Character</code> case mapping methods cannot.
6114 *
6115 * <p><b>Note:</b> This method cannot handle <a
6116 * href="#supplementary"> supplementary characters</a>. To support
6117 * all Unicode characters, including supplementary characters, use
6118 * the {@link #toUpperCase(int)} method.
6119 *
6120 * @param ch the character to be converted.
6121 * @return the uppercase equivalent of the character, if any;
6122 * otherwise, the character itself.
6123 * @see Character#isUpperCase(char)
6124 * @see String#toUpperCase()
6125 */
6126 public static char toUpperCase(char ch) {
6127 return (char)toUpperCase((int)ch);
6128 }
6129
6130 /**
6131 * Converts the character (Unicode code point) argument to
6132 * uppercase using case mapping information from the UnicodeData
6133 * file.
6134 *
6135 * <p>Note that
6136 * <code>Character.isUpperCase(Character.toUpperCase(codePoint))</code>
6137 * does not always return <code>true</code> for some ranges of
6138 * characters, particularly those that are symbols or ideographs.
6139 *
6140 * <p>In general, {@link String#toUpperCase()} should be used to map
6141 * characters to uppercase. <code>String</code> case mapping methods
6142 * have several benefits over <code>Character</code> case mapping methods.
6143 * <code>String</code> case mapping methods can perform locale-sensitive
6144 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
6145 * the <code>Character</code> case mapping methods cannot.
6146 *
6147 * @param codePoint the character (Unicode code point) to be converted.
6148 * @return the uppercase equivalent of the character, if any;
6149 * otherwise, the character itself.
6150 * @see Character#isUpperCase(int)
6151 * @see String#toUpperCase()
6152 *
6153 * @since 1.5
6154 */
6155 public static int toUpperCase(int codePoint) {
6156 return CharacterData.of(codePoint).toUpperCase(codePoint);
6157 }
6158
6159 /**
6160 * Converts the character argument to titlecase using case mapping
6161 * information from the UnicodeData file. If a character has no
6162 * explicit titlecase mapping and is not itself a titlecase char
6163 * according to UnicodeData, then the uppercase mapping is
6164 * returned as an equivalent titlecase mapping. If the
6165 * <code>char</code> argument is already a titlecase
6166 * <code>char</code>, the same <code>char</code> value will be
6167 * returned.
6168 * <p>
6169 * Note that
6170 * <code>Character.isTitleCase(Character.toTitleCase(ch))</code>
6171 * does not always return <code>true</code> for some ranges of
6172 * characters.
6173 *
6174 * <p><b>Note:</b> This method cannot handle <a
6175 * href="#supplementary"> supplementary characters</a>. To support
6176 * all Unicode characters, including supplementary characters, use
6177 * the {@link #toTitleCase(int)} method.
6178 *
6179 * @param ch the character to be converted.
6180 * @return the titlecase equivalent of the character, if any;
6181 * otherwise, the character itself.
6182 * @see Character#isTitleCase(char)
6183 * @see Character#toLowerCase(char)
6184 * @see Character#toUpperCase(char)
6185 * @since 1.0.2
6186 */
6187 public static char toTitleCase(char ch) {
6188 return (char)toTitleCase((int)ch);
6189 }
6190
6191 /**
6192 * Converts the character (Unicode code point) argument to titlecase using case mapping
6193 * information from the UnicodeData file. If a character has no
6194 * explicit titlecase mapping and is not itself a titlecase char
6195 * according to UnicodeData, then the uppercase mapping is
6196 * returned as an equivalent titlecase mapping. If the
6197 * character argument is already a titlecase
6198 * character, the same character value will be
6199 * returned.
6200 *
6201 * <p>Note that
6202 * <code>Character.isTitleCase(Character.toTitleCase(codePoint))</code>
6203 * does not always return <code>true</code> for some ranges of
6204 * characters.
6205 *
6206 * @param codePoint the character (Unicode code point) to be converted.
6207 * @return the titlecase equivalent of the character, if any;
6208 * otherwise, the character itself.
6209 * @see Character#isTitleCase(int)
6210 * @see Character#toLowerCase(int)
6211 * @see Character#toUpperCase(int)
6212 * @since 1.5
6213 */
6214 public static int toTitleCase(int codePoint) {
6215 return CharacterData.of(codePoint).toTitleCase(codePoint);
6216 }
6217
6218 /**
6219 * Returns the numeric value of the character <code>ch</code> in the
6220 * specified radix.
6221 * <p>
6222 * If the radix is not in the range <code>MIN_RADIX</code> <=
6223 * <code>radix</code> <= <code>MAX_RADIX</code> or if the
6224 * value of <code>ch</code> is not a valid digit in the specified
6225 * radix, <code>-1</code> is returned. A character is a valid digit
6226 * if at least one of the following is true:
6227 * <ul>
6228 * <li>The method <code>isDigit</code> is <code>true</code> of the character
6229 * and the Unicode decimal digit value of the character (or its
6230 * single-character decomposition) is less than the specified radix.
6231 * In this case the decimal digit value is returned.
6232 * <li>The character is one of the uppercase Latin letters
6233 * <code>'A'</code> through <code>'Z'</code> and its code is less than
6234 * <code>radix + 'A' - 10</code>.
6235 * In this case, <code>ch - 'A' + 10</code>
6236 * is returned.
6237 * <li>The character is one of the lowercase Latin letters
6238 * <code>'a'</code> through <code>'z'</code> and its code is less than
6239 * <code>radix + 'a' - 10</code>.
6240 * In this case, <code>ch - 'a' + 10</code>
6241 * is returned.
6242 * </ul>
6243 *
6244 * <p><b>Note:</b> This method cannot handle <a
6245 * href="#supplementary"> supplementary characters</a>. To support
6246 * all Unicode characters, including supplementary characters, use
6247 * the {@link #digit(int, int)} method.
6248 *
6249 * @param ch the character to be converted.
6250 * @param radix the radix.
6251 * @return the numeric value represented by the character in the
6252 * specified radix.
6253 * @see Character#forDigit(int, int)
6254 * @see Character#isDigit(char)
6255 */
6256 public static int digit(char ch, int radix) {
6257 return digit((int)ch, radix);
6258 }
6259
6260 /**
6261 * Returns the numeric value of the specified character (Unicode
6262 * code point) in the specified radix.
6263 *
6264 * <p>If the radix is not in the range <code>MIN_RADIX</code> <=
6265 * <code>radix</code> <= <code>MAX_RADIX</code> or if the
6266 * character is not a valid digit in the specified
6267 * radix, <code>-1</code> is returned. A character is a valid digit
6268 * if at least one of the following is true:
6269 * <ul>
6270 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is <code>true</code> of the character
6271 * and the Unicode decimal digit value of the character (or its
6272 * single-character decomposition) is less than the specified radix.
6273 * In this case the decimal digit value is returned.
6274 * <li>The character is one of the uppercase Latin letters
6275 * <code>'A'</code> through <code>'Z'</code> and its code is less than
6276 * <code>radix + 'A' - 10</code>.
6277 * In this case, <code>ch - 'A' + 10</code>
6278 * is returned.
6279 * <li>The character is one of the lowercase Latin letters
6280 * <code>'a'</code> through <code>'z'</code> and its code is less than
6281 * <code>radix + 'a' - 10</code>.
6282 * In this case, <code>ch - 'a' + 10</code>
6283 * is returned.
6284 * </ul>
6285 *
6286 * @param codePoint the character (Unicode code point) to be converted.
6287 * @param radix the radix.
6288 * @return the numeric value represented by the character in the
6289 * specified radix.
6290 * @see Character#forDigit(int, int)
6291 * @see Character#isDigit(int)
6292 * @since 1.5
6293 */
6294 public static int digit(int codePoint, int radix) {
6295 return CharacterData.of(codePoint).digit(codePoint, radix);
6296 }
6297
6298 /**
6299 * Returns the <code>int</code> value that the specified Unicode
6300 * character represents. For example, the character
6301 * <code>'\u216C'</code> (the roman numeral fifty) will return
6302 * an int with a value of 50.
6303 * <p>
6304 * The letters A-Z in their uppercase (<code>'\u0041'</code> through
6305 * <code>'\u005A'</code>), lowercase
6306 * (<code>'\u0061'</code> through <code>'\u007A'</code>), and
6307 * full width variant (<code>'\uFF21'</code> through
6308 * <code>'\uFF3A'</code> and <code>'\uFF41'</code> through
6309 * <code>'\uFF5A'</code>) forms have numeric values from 10
6310 * through 35. This is independent of the Unicode specification,
6311 * which does not assign numeric values to these <code>char</code>
6312 * values.
6313 * <p>
6314 * If the character does not have a numeric value, then -1 is returned.
6315 * If the character has a numeric value that cannot be represented as a
6316 * nonnegative integer (for example, a fractional value), then -2
6317 * is returned.
6318 *
6319 * <p><b>Note:</b> This method cannot handle <a
6320 * href="#supplementary"> supplementary characters</a>. To support
6321 * all Unicode characters, including supplementary characters, use
6322 * the {@link #getNumericValue(int)} method.
6323 *
6324 * @param ch the character to be converted.
6325 * @return the numeric value of the character, as a nonnegative <code>int</code>
6326 * value; -2 if the character has a numeric value that is not a
6327 * nonnegative integer; -1 if the character has no numeric value.
6328 * @see Character#forDigit(int, int)
6329 * @see Character#isDigit(char)
6330 * @since 1.1
6331 */
6332 public static int getNumericValue(char ch) {
6333 return getNumericValue((int)ch);
6334 }
6335
6336 /**
6337 * Returns the <code>int</code> value that the specified
6338 * character (Unicode code point) represents. For example, the character
6339 * <code>'\u216C'</code> (the Roman numeral fifty) will return
6340 * an <code>int</code> with a value of 50.
6341 * <p>
6342 * The letters A-Z in their uppercase (<code>'\u0041'</code> through
6343 * <code>'\u005A'</code>), lowercase
6344 * (<code>'\u0061'</code> through <code>'\u007A'</code>), and
6345 * full width variant (<code>'\uFF21'</code> through
6346 * <code>'\uFF3A'</code> and <code>'\uFF41'</code> through
6347 * <code>'\uFF5A'</code>) forms have numeric values from 10
6348 * through 35. This is independent of the Unicode specification,
6349 * which does not assign numeric values to these <code>char</code>
6350 * values.
6351 * <p>
6352 * If the character does not have a numeric value, then -1 is returned.
6353 * If the character has a numeric value that cannot be represented as a
6354 * nonnegative integer (for example, a fractional value), then -2
6355 * is returned.
6356 *
6357 * @param codePoint the character (Unicode code point) to be converted.
6358 * @return the numeric value of the character, as a nonnegative <code>int</code>
6359 * value; -2 if the character has a numeric value that is not a
6360 * nonnegative integer; -1 if the character has no numeric value.
6361 * @see Character#forDigit(int, int)
6362 * @see Character#isDigit(int)
6363 * @since 1.5
6364 */
6365 public static int getNumericValue(int codePoint) {
6366 return CharacterData.of(codePoint).getNumericValue(codePoint);
6367 }
6368
6369 /**
6370 * Determines if the specified character is ISO-LATIN-1 white space.
6371 * This method returns <code>true</code> for the following five
6372 * characters only:
6373 * <table>
6374 * <tr><td><code>'\t'</code></td> <td><code>'\u0009'</code></td>
6375 * <td><code>HORIZONTAL TABULATION</code></td></tr>
6376 * <tr><td><code>'\n'</code></td> <td><code>'\u000A'</code></td>
6377 * <td><code>NEW LINE</code></td></tr>
6378 * <tr><td><code>'\f'</code></td> <td><code>'\u000C'</code></td>
6379 * <td><code>FORM FEED</code></td></tr>
6380 * <tr><td><code>'\r'</code></td> <td><code>'\u000D'</code></td>
6381 * <td><code>CARRIAGE RETURN</code></td></tr>
6382 * <tr><td><code>' '</code></td> <td><code>'\u0020'</code></td>
6383 * <td><code>SPACE</code></td></tr>
6384 * </table>
6385 *
6386 * @param ch the character to be tested.
6387 * @return <code>true</code> if the character is ISO-LATIN-1 white
6388 * space; <code>false</code> otherwise.
6389 * @see Character#isSpaceChar(char)
6390 * @see Character#isWhitespace(char)
6391 * @deprecated Replaced by isWhitespace(char).
6392 */
6393 @Deprecated
6394 public static boolean isSpace(char ch) {
6395 return (ch <= 0x0020) &&
6396 (((((1L << 0x0009) |
6397 (1L << 0x000A) |
6398 (1L << 0x000C) |
6399 (1L << 0x000D) |
6400 (1L << 0x0020)) >> ch) & 1L) != 0);
6401 }
6402
6403
6404 /**
6405 * Determines if the specified character is a Unicode space character.
6406 * A character is considered to be a space character if and only if
6407 * it is specified to be a space character by the Unicode standard. This
6408 * method returns true if the character's general category type is any of
6409 * the following:
6410 * <ul>
6411 * <li> <code>SPACE_SEPARATOR</code>
6412 * <li> <code>LINE_SEPARATOR</code>
6413 * <li> <code>PARAGRAPH_SEPARATOR</code>
6414 * </ul>
6415 *
6416 * <p><b>Note:</b> This method cannot handle <a
6417 * href="#supplementary"> supplementary characters</a>. To support
6418 * all Unicode characters, including supplementary characters, use
6419 * the {@link #isSpaceChar(int)} method.
6420 *
6421 * @param ch the character to be tested.
6422 * @return <code>true</code> if the character is a space character;
6423 * <code>false</code> otherwise.
6424 * @see Character#isWhitespace(char)
6425 * @since 1.1
6426 */
6427 public static boolean isSpaceChar(char ch) {
6428 return isSpaceChar((int)ch);
6429 }
6430
6431 /**
6432 * Determines if the specified character (Unicode code point) is a
6433 * Unicode space character. A character is considered to be a
6434 * space character if and only if it is specified to be a space
6435 * character by the Unicode standard. This method returns true if
6436 * the character's general category type is any of the following:
6437 *
6438 * <ul>
6439 * <li> {@link #SPACE_SEPARATOR}
6440 * <li> {@link #LINE_SEPARATOR}
6441 * <li> {@link #PARAGRAPH_SEPARATOR}
6442 * </ul>
6443 *
6444 * @param codePoint the character (Unicode code point) to be tested.
6445 * @return <code>true</code> if the character is a space character;
6446 * <code>false</code> otherwise.
6447 * @see Character#isWhitespace(int)
6448 * @since 1.5
6449 */
6450 public static boolean isSpaceChar(int codePoint) {
6451 return ((((1 << Character.SPACE_SEPARATOR) |
6452 (1 << Character.LINE_SEPARATOR) |
6453 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
6454 != 0;
6455 }
6456
6457 /**
6458 * Determines if the specified character is white space according to Java.
6459 * A character is a Java whitespace character if and only if it satisfies
6460 * one of the following criteria:
6461 * <ul>
6462 * <li> It is a Unicode space character (<code>SPACE_SEPARATOR</code>,
6463 * <code>LINE_SEPARATOR</code>, or <code>PARAGRAPH_SEPARATOR</code>)
6464 * but is not also a non-breaking space (<code>'\u00A0'</code>,
6465 * <code>'\u2007'</code>, <code>'\u202F'</code>).
6466 * <li> It is <code>'\u0009'</code>, HORIZONTAL TABULATION.
6467 * <li> It is <code>'\u000A'</code>, LINE FEED.
6468 * <li> It is <code>'\u000B'</code>, VERTICAL TABULATION.
6469 * <li> It is <code>'\u000C'</code>, FORM FEED.
6470 * <li> It is <code>'\u000D'</code>, CARRIAGE RETURN.
6471 * <li> It is <code>'\u001C'</code>, FILE SEPARATOR.
6472 * <li> It is <code>'\u001D'</code>, GROUP SEPARATOR.
6473 * <li> It is <code>'\u001E'</code>, RECORD SEPARATOR.
6474 * <li> It is <code>'\u001F'</code>, UNIT SEPARATOR.
6475 * </ul>
6476 *
6477 * <p><b>Note:</b> This method cannot handle <a
6478 * href="#supplementary"> supplementary characters</a>. To support
6479 * all Unicode characters, including supplementary characters, use
6480 * the {@link #isWhitespace(int)} method.
6481 *
6482 * @param ch the character to be tested.
6483 * @return <code>true</code> if the character is a Java whitespace
6484 * character; <code>false</code> otherwise.
6485 * @see Character#isSpaceChar(char)
6486 * @since 1.1
6487 */
6488 public static boolean isWhitespace(char ch) {
6489 return isWhitespace((int)ch);
6490 }
6491
6492 /**
6493 * Determines if the specified character (Unicode code point) is
6494 * white space according to Java. A character is a Java
6495 * whitespace character if and only if it satisfies one of the
6496 * following criteria:
6497 * <ul>
6498 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
6499 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
6500 * but is not also a non-breaking space (<code>'\u00A0'</code>,
6501 * <code>'\u2007'</code>, <code>'\u202F'</code>).
6502 * <li> It is <code>'\u0009'</code>, HORIZONTAL TABULATION.
6503 * <li> It is <code>'\u000A'</code>, LINE FEED.
6504 * <li> It is <code>'\u000B'</code>, VERTICAL TABULATION.
6505 * <li> It is <code>'\u000C'</code>, FORM FEED.
6506 * <li> It is <code>'\u000D'</code>, CARRIAGE RETURN.
6507 * <li> It is <code>'\u001C'</code>, FILE SEPARATOR.
6508 * <li> It is <code>'\u001D'</code>, GROUP SEPARATOR.
6509 * <li> It is <code>'\u001E'</code>, RECORD SEPARATOR.
6510 * <li> It is <code>'\u001F'</code>, UNIT SEPARATOR.
6511 * </ul>
6512 * <p>
6513 *
6514 * @param codePoint the character (Unicode code point) to be tested.
6515 * @return <code>true</code> if the character is a Java whitespace
6516 * character; <code>false</code> otherwise.
6517 * @see Character#isSpaceChar(int)
6518 * @since 1.5
6519 */
6520 public static boolean isWhitespace(int codePoint) {
6521 return CharacterData.of(codePoint).isWhitespace(codePoint);
6522 }
6523
6524 /**
6525 * Determines if the specified character is an ISO control
6526 * character. A character is considered to be an ISO control
6527 * character if its code is in the range <code>'\u0000'</code>
6528 * through <code>'\u001F'</code> or in the range
6529 * <code>'\u007F'</code> through <code>'\u009F'</code>.
6530 *
6531 * <p><b>Note:</b> This method cannot handle <a
6532 * href="#supplementary"> supplementary characters</a>. To support
6533 * all Unicode characters, including supplementary characters, use
6534 * the {@link #isISOControl(int)} method.
6535 *
6536 * @param ch the character to be tested.
6537 * @return <code>true</code> if the character is an ISO control character;
6538 * <code>false</code> otherwise.
6539 *
6540 * @see Character#isSpaceChar(char)
6541 * @see Character#isWhitespace(char)
6542 * @since 1.1
6543 */
6544 public static boolean isISOControl(char ch) {
6545 return isISOControl((int)ch);
6546 }
6547
6548 /**
6549 * Determines if the referenced character (Unicode code point) is an ISO control
6550 * character. A character is considered to be an ISO control
6551 * character if its code is in the range <code>'\u0000'</code>
6552 * through <code>'\u001F'</code> or in the range
6553 * <code>'\u007F'</code> through <code>'\u009F'</code>.
6554 *
6555 * @param codePoint the character (Unicode code point) to be tested.
6556 * @return <code>true</code> if the character is an ISO control character;
6557 * <code>false</code> otherwise.
6558 * @see Character#isSpaceChar(int)
6559 * @see Character#isWhitespace(int)
6560 * @since 1.5
6561 */
6562 public static boolean isISOControl(int codePoint) {
6563 // Optimized form of:
6564 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
6565 // (codePoint >= 0x7F && codePoint <= 0x9F);
6566 return codePoint <= 0x9F &&
6567 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
6568 }
6569
6570 /**
6571 * Returns a value indicating a character's general category.
6572 *
6573 * <p><b>Note:</b> This method cannot handle <a
6574 * href="#supplementary"> supplementary characters</a>. To support
6575 * all Unicode characters, including supplementary characters, use
6576 * the {@link #getType(int)} method.
6577 *
6578 * @param ch the character to be tested.
6579 * @return a value of type <code>int</code> representing the
6580 * character's general category.
6581 * @see Character#COMBINING_SPACING_MARK
6582 * @see Character#CONNECTOR_PUNCTUATION
6583 * @see Character#CONTROL
6584 * @see Character#CURRENCY_SYMBOL
6585 * @see Character#DASH_PUNCTUATION
6586 * @see Character#DECIMAL_DIGIT_NUMBER
6587 * @see Character#ENCLOSING_MARK
6588 * @see Character#END_PUNCTUATION
6589 * @see Character#FINAL_QUOTE_PUNCTUATION
6590 * @see Character#FORMAT
6591 * @see Character#INITIAL_QUOTE_PUNCTUATION
6592 * @see Character#LETTER_NUMBER
6593 * @see Character#LINE_SEPARATOR
6594 * @see Character#LOWERCASE_LETTER
6595 * @see Character#MATH_SYMBOL
6596 * @see Character#MODIFIER_LETTER
6597 * @see Character#MODIFIER_SYMBOL
6598 * @see Character#NON_SPACING_MARK
6599 * @see Character#OTHER_LETTER
6600 * @see Character#OTHER_NUMBER
6601 * @see Character#OTHER_PUNCTUATION
6602 * @see Character#OTHER_SYMBOL
6603 * @see Character#PARAGRAPH_SEPARATOR
6604 * @see Character#PRIVATE_USE
6605 * @see Character#SPACE_SEPARATOR
6606 * @see Character#START_PUNCTUATION
6607 * @see Character#SURROGATE
6608 * @see Character#TITLECASE_LETTER
6609 * @see Character#UNASSIGNED
6610 * @see Character#UPPERCASE_LETTER
6611 * @since 1.1
6612 */
6613 public static int getType(char ch) {
6614 return getType((int)ch);
6615 }
6616
6617 /**
6618 * Returns a value indicating a character's general category.
6619 *
6620 * @param codePoint the character (Unicode code point) to be tested.
6621 * @return a value of type <code>int</code> representing the
6622 * character's general category.
6623 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
6624 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
6625 * @see Character#CONTROL CONTROL
6626 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
6627 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
6628 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
6629 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
6630 * @see Character#END_PUNCTUATION END_PUNCTUATION
6631 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
6632 * @see Character#FORMAT FORMAT
6633 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
6634 * @see Character#LETTER_NUMBER LETTER_NUMBER
6635 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
6636 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
6637 * @see Character#MATH_SYMBOL MATH_SYMBOL
6638 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
6639 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
6640 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
6641 * @see Character#OTHER_LETTER OTHER_LETTER
6642 * @see Character#OTHER_NUMBER OTHER_NUMBER
6643 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
6644 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
6645 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
6646 * @see Character#PRIVATE_USE PRIVATE_USE
6647 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
6648 * @see Character#START_PUNCTUATION START_PUNCTUATION
6649 * @see Character#SURROGATE SURROGATE
6650 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
6651 * @see Character#UNASSIGNED UNASSIGNED
6652 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
6653 * @since 1.5
6654 */
6655 public static int getType(int codePoint) {
6656 return CharacterData.of(codePoint).getType(codePoint);
6657 }
6658
6659 /**
6660 * Determines the character representation for a specific digit in
6661 * the specified radix. If the value of <code>radix</code> is not a
6662 * valid radix, or the value of <code>digit</code> is not a valid
6663 * digit in the specified radix, the null character
6664 * (<code>'\u0000'</code>) is returned.
6665 * <p>
6666 * The <code>radix</code> argument is valid if it is greater than or
6667 * equal to <code>MIN_RADIX</code> and less than or equal to
6668 * <code>MAX_RADIX</code>. The <code>digit</code> argument is valid if
6669 * <code>0 <=digit < radix</code>.
6670 * <p>
6671 * If the digit is less than 10, then
6672 * <code>'0' + digit</code> is returned. Otherwise, the value
6673 * <code>'a' + digit - 10</code> is returned.
6674 *
6675 * @param digit the number to convert to a character.
6676 * @param radix the radix.
6677 * @return the <code>char</code> representation of the specified digit
6678 * in the specified radix.
6679 * @see Character#MIN_RADIX
6680 * @see Character#MAX_RADIX
6681 * @see Character#digit(char, int)
6682 */
6683 public static char forDigit(int digit, int radix) {
6684 if ((digit >= radix) || (digit < 0)) {
6685 return '\0';
6686 }
6687 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
6688 return '\0';
6689 }
6690 if (digit < 10) {
6691 return (char)('0' + digit);
6692 }
6693 return (char)('a' - 10 + digit);
6694 }
6695
6696 /**
6697 * Returns the Unicode directionality property for the given
6698 * character. Character directionality is used to calculate the
6699 * visual ordering of text. The directionality value of undefined
6700 * <code>char</code> values is <code>DIRECTIONALITY_UNDEFINED</code>.
6701 *
6702 * <p><b>Note:</b> This method cannot handle <a
6703 * href="#supplementary"> supplementary characters</a>. To support
6704 * all Unicode characters, including supplementary characters, use
6705 * the {@link #getDirectionality(int)} method.
6706 *
6707 * @param ch <code>char</code> for which the directionality property
6708 * is requested.
6709 * @return the directionality property of the <code>char</code> value.
6710 *
6711 * @see Character#DIRECTIONALITY_UNDEFINED
6712 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
6713 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
6714 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
6715 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
6716 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
6717 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
6718 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
6719 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
6720 * @see Character#DIRECTIONALITY_NONSPACING_MARK
6721 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
6722 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
6723 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
6724 * @see Character#DIRECTIONALITY_WHITESPACE
6725 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
6726 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
6727 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
6728 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
6729 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
6730 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
6731 * @since 1.4
6732 */
6733 public static byte getDirectionality(char ch) {
6734 return getDirectionality((int)ch);
6735 }
6736
6737 /**
6738 * Returns the Unicode directionality property for the given
6739 * character (Unicode code point). Character directionality is
6740 * used to calculate the visual ordering of text. The
6741 * directionality value of undefined character is {@link
6742 * #DIRECTIONALITY_UNDEFINED}.
6743 *
6744 * @param codePoint the character (Unicode code point) for which
6745 * the directionality property is requested.
6746 * @return the directionality property of the character.
6747 *
6748 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
6749 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
6750 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
6751 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
6752 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
6753 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
6754 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
6755 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
6756 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
6757 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
6758 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
6759 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
6760 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
6761 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
6762 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
6763 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
6764 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
6765 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
6766 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
6767 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
6768 * @since 1.5
6769 */
6770 public static byte getDirectionality(int codePoint) {
6771 return CharacterData.of(codePoint).getDirectionality(codePoint);
6772 }
6773
6774 /**
6775 * Determines whether the character is mirrored according to the
6776 * Unicode specification. Mirrored characters should have their
6777 * glyphs horizontally mirrored when displayed in text that is
6778 * right-to-left. For example, <code>'\u0028'</code> LEFT
6779 * PARENTHESIS is semantically defined to be an <i>opening
6780 * parenthesis</i>. This will appear as a "(" in text that is
6781 * left-to-right but as a ")" in text that is right-to-left.
6782 *
6783 * <p><b>Note:</b> This method cannot handle <a
6784 * href="#supplementary"> supplementary characters</a>. To support
6785 * all Unicode characters, including supplementary characters, use
6786 * the {@link #isMirrored(int)} method.
6787 *
6788 * @param ch <code>char</code> for which the mirrored property is requested
6789 * @return <code>true</code> if the char is mirrored, <code>false</code>
6790 * if the <code>char</code> is not mirrored or is not defined.
6791 * @since 1.4
6792 */
6793 public static boolean isMirrored(char ch) {
6794 return isMirrored((int)ch);
6795 }
6796
6797 /**
6798 * Determines whether the specified character (Unicode code point)
6799 * is mirrored according to the Unicode specification. Mirrored
6800 * characters should have their glyphs horizontally mirrored when
6801 * displayed in text that is right-to-left. For example,
6802 * <code>'\u0028'</code> LEFT PARENTHESIS is semantically
6803 * defined to be an <i>opening parenthesis</i>. This will appear
6804 * as a "(" in text that is left-to-right but as a ")" in text
6805 * that is right-to-left.
6806 *
6807 * @param codePoint the character (Unicode code point) to be tested.
6808 * @return <code>true</code> if the character is mirrored, <code>false</code>
6809 * if the character is not mirrored or is not defined.
6810 * @since 1.5
6811 */
6812 public static boolean isMirrored(int codePoint) {
6813 return CharacterData.of(codePoint).isMirrored(codePoint);
6814 }
6815
6816 /**
6817 * Compares two <code>Character</code> objects numerically.
6818 *
6819 * @param anotherCharacter the <code>Character</code> to be compared.
6820
6821 * @return the value <code>0</code> if the argument <code>Character</code>
6822 * is equal to this <code>Character</code>; a value less than
6823 * <code>0</code> if this <code>Character</code> is numerically less
6824 * than the <code>Character</code> argument; and a value greater than
6825 * <code>0</code> if this <code>Character</code> is numerically greater
6826 * than the <code>Character</code> argument (unsigned comparison).
6827 * Note that this is strictly a numerical comparison; it is not
6828 * locale-dependent.
6829 * @since 1.2
6830 */
6831 public int compareTo(Character anotherCharacter) {
6832 return compare(this.value, anotherCharacter.value);
6833 }
6834
6835 /**
6836 * Compares two {@code char} values numerically.
6837 * The value returned is identical to what would be returned by:
6838 * <pre>
6839 * Character.valueOf(x).compareTo(Character.valueOf(y))
6840 * </pre>
6841 *
6842 * @param x the first {@code char} to compare
6843 * @param y the second {@code char} to compare
6844 * @return the value {@code 0} if {@code x == y};
6845 * a value less than {@code 0} if {@code x < y}; and
6846 * a value greater than {@code 0} if {@code x > y}
6847 * @since 1.7
6848 */
6849 public static int compare(char x, char y) {
6850 return x - y;
6851 }
6852
6853 /**
6854 * Converts the character (Unicode code point) argument to uppercase using
6855 * information from the UnicodeData file.
6856 * <p>
6857 *
6858 * @param codePoint the character (Unicode code point) to be converted.
6859 * @return either the uppercase equivalent of the character, if
6860 * any, or an error flag (<code>Character.ERROR</code>)
6861 * that indicates that a 1:M <code>char</code> mapping exists.
6862 * @see Character#isLowerCase(char)
6863 * @see Character#isUpperCase(char)
6864 * @see Character#toLowerCase(char)
6865 * @see Character#toTitleCase(char)
6866 * @since 1.4
6867 */
6868 static int toUpperCaseEx(int codePoint) {
6869 assert isValidCodePoint(codePoint);
6870 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
6871 }
6872
6873 /**
6874 * Converts the character (Unicode code point) argument to uppercase using case
6875 * mapping information from the SpecialCasing file in the Unicode
6876 * specification. If a character has no explicit uppercase
6877 * mapping, then the <code>char</code> itself is returned in the
6878 * <code>char[]</code>.
6879 *
6880 * @param codePoint the character (Unicode code point) to be converted.
6881 * @return a <code>char[]</code> with the uppercased character.
6882 * @since 1.4
6883 */
6884 static char[] toUpperCaseCharArray(int codePoint) {
6885 // As of Unicode 4.0, 1:M uppercasings only happen in the BMP.
6886 assert isBmpCodePoint(codePoint);
6887 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
6888 }
6889
6890 /**
6891 * The number of bits used to represent a <tt>char</tt> value in unsigned
6892 * binary form, constant {@code 16}.
6893 *
6894 * @since 1.5
6895 */
6896 public static final int SIZE = 16;
6897
6898 /**
6899 * Returns the value obtained by reversing the order of the bytes in the
6900 * specified <tt>char</tt> value.
6901 *
6902 * @return the value obtained by reversing (or, equivalently, swapping)
6903 * the bytes in the specified <tt>char</tt> value.
6904 * @since 1.5
6905 */
6906 public static char reverseBytes(char ch) {
6907 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
6908 }
6909
6910 /**
6911 * Returns the Unicode name of the specified character
6912 * <code>codePoint</code>, or null if the code point is
6913 * {@link #UNASSIGNED unassigned}.
6914 * <p>
6915 * Note: if the specified character is not assigned a name by
6916 * the <i>UnicodeData</i> file (part of the Unicode Character
6917 * Database maintained by the Unicode Consortium), the returned
6918 * name is the same as the result of expression
6919 *
6920 * <blockquote><code>
6921 * Character.UnicodeBlock.of(codePoint)
6922 * .toString()
6923 * .replace('_', ' ')
6924 * + " "
6925 * + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
6926 *
6927 * </code></blockquote>
6928 *
6929 * @param codePoint the character (Unicode code point)
6930 *
6931 * @return the Unicode name of the specified character, or null if
6932 * the code point is unassigned.
6933 *
6934 * @exception IllegalArgumentException if the specified
6935 * <code>codePoint</code> is not a valid Unicode
6936 * code point.
6937 *
6938 * @since 1.7
6939 */
6940 public static String getName(int codePoint) {
6941 if (!isValidCodePoint(codePoint)) {
6942 throw new IllegalArgumentException();
6943 }
6944 String name = CharacterName.get(codePoint);
6945 if (name != null)
6946 return name;
6947 if (getType(codePoint) == UNASSIGNED)
6948 return null;
6949 UnicodeBlock block = UnicodeBlock.of(codePoint);
6950 if (block != null)
6951 return block.toString().replace('_', ' ') + " "
6952 + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
6953 // should never come here
6954 return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
6955 }
6956 }