476 /**
477 * Strong bidirectional character type "RLE" in the Unicode specification.
478 * @since 1.4
479 */
480 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
481
482 /**
483 * Strong bidirectional character type "RLO" in the Unicode specification.
484 * @since 1.4
485 */
486 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
487
488 /**
489 * Weak bidirectional character type "PDF" in the Unicode specification.
490 * @since 1.4
491 */
492 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
493
494 /**
495 * Weak bidirectional character type "LRI" in the Unicode specification.
496 * @since 1.9
497 */
498 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
499
500 /**
501 * Weak bidirectional character type "RLI" in the Unicode specification.
502 * @since 1.9
503 */
504 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
505
506 /**
507 * Weak bidirectional character type "FSI" in the Unicode specification.
508 * @since 1.9
509 */
510 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
511
512 /**
513 * Weak bidirectional character type "PDI" in the Unicode specification.
514 * @since 1.9
515 */
516 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
517
518 /**
519 * The minimum value of a
520 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
521 * Unicode high-surrogate code unit</a>
522 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
523 * A high-surrogate is also known as a <i>leading-surrogate</i>.
524 *
525 * @since 1.5
526 */
527 public static final char MIN_HIGH_SURROGATE = '\uD800';
528
529 /**
530 * The maximum value of a
531 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
532 * Unicode high-surrogate code unit</a>
533 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
534 * A high-surrogate is also known as a <i>leading-surrogate</i>.
2573 /**
2574 * Constant for the "Miao" Unicode character block.
2575 * @since 1.8
2576 */
2577 public static final UnicodeBlock MIAO =
2578 new UnicodeBlock("MIAO");
2579
2580 /**
2581 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2582 * character block.
2583 * @since 1.8
2584 */
2585 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2586 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2587 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2588 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2589
2590 /**
2591 * Constant for the "Combining Diacritical Marks Extended" Unicode
2592 * character block.
2593 * @since 1.9
2594 */
2595 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2596 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2597 "COMBINING DIACRITICAL MARKS EXTENDED",
2598 "COMBININGDIACRITICALMARKSEXTENDED");
2599
2600 /**
2601 * Constant for the "Myanmar Extended-B" Unicode character block.
2602 * @since 1.9
2603 */
2604 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2605 new UnicodeBlock("MYANMAR_EXTENDED_B",
2606 "MYANMAR EXTENDED-B",
2607 "MYANMAREXTENDED-B");
2608
2609 /**
2610 * Constant for the "Latin Extended-E" Unicode character block.
2611 * @since 1.9
2612 */
2613 public static final UnicodeBlock LATIN_EXTENDED_E =
2614 new UnicodeBlock("LATIN_EXTENDED_E",
2615 "LATIN EXTENDED-E",
2616 "LATINEXTENDED-E");
2617
2618 /**
2619 * Constant for the "Coptic Epact Numbers" Unicode character block.
2620 * @since 1.9
2621 */
2622 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2623 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2624 "COPTIC EPACT NUMBERS",
2625 "COPTICEPACTNUMBERS");
2626
2627 /**
2628 * Constant for the "Old Permic" Unicode character block.
2629 * @since 1.9
2630 */
2631 public static final UnicodeBlock OLD_PERMIC =
2632 new UnicodeBlock("OLD_PERMIC",
2633 "OLD PERMIC",
2634 "OLDPERMIC");
2635
2636 /**
2637 * Constant for the "Elbasan" Unicode character block.
2638 * @since 1.9
2639 */
2640 public static final UnicodeBlock ELBASAN =
2641 new UnicodeBlock("ELBASAN");
2642
2643 /**
2644 * Constant for the "Caucasian Albanian" Unicode character block.
2645 * @since 1.9
2646 */
2647 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2648 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2649 "CAUCASIAN ALBANIAN",
2650 "CAUCASIANALBANIAN");
2651
2652 /**
2653 * Constant for the "Linear A" Unicode character block.
2654 * @since 1.9
2655 */
2656 public static final UnicodeBlock LINEAR_A =
2657 new UnicodeBlock("LINEAR_A",
2658 "LINEAR A",
2659 "LINEARA");
2660
2661 /**
2662 * Constant for the "Palmyrene" Unicode character block.
2663 * @since 1.9
2664 */
2665 public static final UnicodeBlock PALMYRENE =
2666 new UnicodeBlock("PALMYRENE");
2667
2668 /**
2669 * Constant for the "Nabataean" Unicode character block.
2670 * @since 1.9
2671 */
2672 public static final UnicodeBlock NABATAEAN =
2673 new UnicodeBlock("NABATAEAN");
2674
2675 /**
2676 * Constant for the "Old North Arabian" Unicode character block.
2677 * @since 1.9
2678 */
2679 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2680 new UnicodeBlock("OLD_NORTH_ARABIAN",
2681 "OLD NORTH ARABIAN",
2682 "OLDNORTHARABIAN");
2683
2684 /**
2685 * Constant for the "Manichaean" Unicode character block.
2686 * @since 1.9
2687 */
2688 public static final UnicodeBlock MANICHAEAN =
2689 new UnicodeBlock("MANICHAEAN");
2690
2691 /**
2692 * Constant for the "Psalter Pahlavi" Unicode character block.
2693 * @since 1.9
2694 */
2695 public static final UnicodeBlock PSALTER_PAHLAVI =
2696 new UnicodeBlock("PSALTER_PAHLAVI",
2697 "PSALTER PAHLAVI",
2698 "PSALTERPAHLAVI");
2699
2700 /**
2701 * Constant for the "Mahajani" Unicode character block.
2702 * @since 1.9
2703 */
2704 public static final UnicodeBlock MAHAJANI =
2705 new UnicodeBlock("MAHAJANI");
2706
2707 /**
2708 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2709 * @since 1.9
2710 */
2711 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2712 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2713 "SINHALA ARCHAIC NUMBERS",
2714 "SINHALAARCHAICNUMBERS");
2715
2716 /**
2717 * Constant for the "Khojki" Unicode character block.
2718 * @since 1.9
2719 */
2720 public static final UnicodeBlock KHOJKI =
2721 new UnicodeBlock("KHOJKI");
2722
2723 /**
2724 * Constant for the "Khudawadi" Unicode character block.
2725 * @since 1.9
2726 */
2727 public static final UnicodeBlock KHUDAWADI =
2728 new UnicodeBlock("KHUDAWADI");
2729
2730 /**
2731 * Constant for the "Grantha" Unicode character block.
2732 * @since 1.9
2733 */
2734 public static final UnicodeBlock GRANTHA =
2735 new UnicodeBlock("GRANTHA");
2736
2737 /**
2738 * Constant for the "Tirhuta" Unicode character block.
2739 * @since 1.9
2740 */
2741 public static final UnicodeBlock TIRHUTA =
2742 new UnicodeBlock("TIRHUTA");
2743
2744 /**
2745 * Constant for the "Siddham" Unicode character block.
2746 * @since 1.9
2747 */
2748 public static final UnicodeBlock SIDDHAM =
2749 new UnicodeBlock("SIDDHAM");
2750
2751 /**
2752 * Constant for the "Modi" Unicode character block.
2753 * @since 1.9
2754 */
2755 public static final UnicodeBlock MODI =
2756 new UnicodeBlock("MODI");
2757
2758 /**
2759 * Constant for the "Warang Citi" Unicode character block.
2760 * @since 1.9
2761 */
2762 public static final UnicodeBlock WARANG_CITI =
2763 new UnicodeBlock("WARANG_CITI",
2764 "WARANG CITI",
2765 "WARANGCITI");
2766
2767 /**
2768 * Constant for the "Pau Cin Hau" Unicode character block.
2769 * @since 1.9
2770 */
2771 public static final UnicodeBlock PAU_CIN_HAU =
2772 new UnicodeBlock("PAU_CIN_HAU",
2773 "PAU CIN HAU",
2774 "PAUCINHAU");
2775
2776 /**
2777 * Constant for the "Mro" Unicode character block.
2778 * @since 1.9
2779 */
2780 public static final UnicodeBlock MRO =
2781 new UnicodeBlock("MRO");
2782
2783 /**
2784 * Constant for the "Bassa Vah" Unicode character block.
2785 * @since 1.9
2786 */
2787 public static final UnicodeBlock BASSA_VAH =
2788 new UnicodeBlock("BASSA_VAH",
2789 "BASSA VAH",
2790 "BASSAVAH");
2791
2792 /**
2793 * Constant for the "Pahawh Hmong" Unicode character block.
2794 * @since 1.9
2795 */
2796 public static final UnicodeBlock PAHAWH_HMONG =
2797 new UnicodeBlock("PAHAWH_HMONG",
2798 "PAHAWH HMONG",
2799 "PAHAWHHMONG");
2800
2801 /**
2802 * Constant for the "Duployan" Unicode character block.
2803 * @since 1.9
2804 */
2805 public static final UnicodeBlock DUPLOYAN =
2806 new UnicodeBlock("DUPLOYAN");
2807
2808 /**
2809 * Constant for the "Shorthand Format Controls" Unicode character block.
2810 * @since 1.9
2811 */
2812 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2813 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2814 "SHORTHAND FORMAT CONTROLS",
2815 "SHORTHANDFORMATCONTROLS");
2816
2817 /**
2818 * Constant for the "Mende Kikakui" Unicode character block.
2819 * @since 1.9
2820 */
2821 public static final UnicodeBlock MENDE_KIKAKUI =
2822 new UnicodeBlock("MENDE_KIKAKUI",
2823 "MENDE KIKAKUI",
2824 "MENDEKIKAKUI");
2825
2826 /**
2827 * Constant for the "Ornamental Dingbats" Unicode character block.
2828 * @since 1.9
2829 */
2830 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2831 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2832 "ORNAMENTAL DINGBATS",
2833 "ORNAMENTALDINGBATS");
2834
2835 /**
2836 * Constant for the "Geometric Shapes Extended" Unicode character block.
2837 * @since 1.9
2838 */
2839 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2840 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2841 "GEOMETRIC SHAPES EXTENDED",
2842 "GEOMETRICSHAPESEXTENDED");
2843
2844 /**
2845 * Constant for the "Supplemental Arrows-C" Unicode character block.
2846 * @since 1.9
2847 */
2848 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2849 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2850 "SUPPLEMENTAL ARROWS-C",
2851 "SUPPLEMENTALARROWS-C");
2852
2853 /**
2854 * Constant for the "Cherokee Supplement" Unicode character block.
2855 * @since 1.9
2856 */
2857 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2858 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2859 "CHEROKEE SUPPLEMENT",
2860 "CHEROKEESUPPLEMENT");
2861
2862 /**
2863 * Constant for the "Hatran" Unicode character block.
2864 * @since 1.9
2865 */
2866 public static final UnicodeBlock HATRAN =
2867 new UnicodeBlock("HATRAN");
2868
2869 /**
2870 * Constant for the "Old Hungarian" Unicode character block.
2871 * @since 1.9
2872 */
2873 public static final UnicodeBlock OLD_HUNGARIAN =
2874 new UnicodeBlock("OLD_HUNGARIAN",
2875 "OLD HUNGARIAN",
2876 "OLDHUNGARIAN");
2877
2878 /**
2879 * Constant for the "Multani" Unicode character block.
2880 * @since 1.9
2881 */
2882 public static final UnicodeBlock MULTANI =
2883 new UnicodeBlock("MULTANI");
2884
2885 /**
2886 * Constant for the "Ahom" Unicode character block.
2887 * @since 1.9
2888 */
2889 public static final UnicodeBlock AHOM =
2890 new UnicodeBlock("AHOM");
2891
2892 /**
2893 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2894 * @since 1.9
2895 */
2896 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2897 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2898 "EARLY DYNASTIC CUNEIFORM",
2899 "EARLYDYNASTICCUNEIFORM");
2900
2901 /**
2902 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2903 * @since 1.9
2904 */
2905 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2906 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2907 "ANATOLIAN HIEROGLYPHS",
2908 "ANATOLIANHIEROGLYPHS");
2909
2910 /**
2911 * Constant for the "Sutton SignWriting" Unicode character block.
2912 * @since 1.9
2913 */
2914 public static final UnicodeBlock SUTTON_SIGNWRITING =
2915 new UnicodeBlock("SUTTON_SIGNWRITING",
2916 "SUTTON SIGNWRITING",
2917 "SUTTONSIGNWRITING");
2918
2919 /**
2920 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2921 * character block.
2922 * @since 1.9
2923 */
2924 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2925 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2926 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2927 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2928
2929 /**
2930 * Constant for the "CJK Unified Ideographs Extension E" Unicode
2931 * character block.
2932 * @since 1.9
2933 */
2934 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
2935 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
2936 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
2937 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
2938
2939
2940 private static final int blockStarts[] = {
2941 0x0000, // 0000..007F; Basic Latin
2942 0x0080, // 0080..00FF; Latin-1 Supplement
2943 0x0100, // 0100..017F; Latin Extended-A
2944 0x0180, // 0180..024F; Latin Extended-B
2945 0x0250, // 0250..02AF; IPA Extensions
2946 0x02B0, // 02B0..02FF; Spacing Modifier Letters
2947 0x0300, // 0300..036F; Combining Diacritical Marks
2948 0x0370, // 0370..03FF; Greek and Coptic
2949 0x0400, // 0400..04FF; Cyrillic
2950 0x0500, // 0500..052F; Cyrillic Supplement
2951 0x0530, // 0530..058F; Armenian
2952 0x0590, // 0590..05FF; Hebrew
4172 /**
4173 * Unicode script "Sharada".
4174 * @since 1.8
4175 */
4176 SHARADA,
4177
4178 /**
4179 * Unicode script "Takri".
4180 * @since 1.8
4181 */
4182 TAKRI,
4183
4184 /**
4185 * Unicode script "Miao".
4186 * @since 1.8
4187 */
4188 MIAO,
4189
4190 /**
4191 * Unicode script "Caucasian Albanian".
4192 * @since 1.9
4193 */
4194 CAUCASIAN_ALBANIAN,
4195
4196 /**
4197 * Unicode script "Bassa Vah".
4198 * @since 1.9
4199 */
4200 BASSA_VAH,
4201
4202 /**
4203 * Unicode script "Duployan".
4204 * @since 1.9
4205 */
4206 DUPLOYAN,
4207
4208 /**
4209 * Unicode script "Elbasan".
4210 * @since 1.9
4211 */
4212 ELBASAN,
4213
4214 /**
4215 * Unicode script "Grantha".
4216 * @since 1.9
4217 */
4218 GRANTHA,
4219
4220 /**
4221 * Unicode script "Pahawh Hmong".
4222 * @since 1.9
4223 */
4224 PAHAWH_HMONG,
4225
4226 /**
4227 * Unicode script "Khojki".
4228 * @since 1.9
4229 */
4230 KHOJKI,
4231
4232 /**
4233 * Unicode script "Linear A".
4234 * @since 1.9
4235 */
4236 LINEAR_A,
4237
4238 /**
4239 * Unicode script "Mahajani".
4240 * @since 1.9
4241 */
4242 MAHAJANI,
4243
4244 /**
4245 * Unicode script "Manichaean".
4246 * @since 1.9
4247 */
4248 MANICHAEAN,
4249
4250 /**
4251 * Unicode script "Mende Kikakui".
4252 * @since 1.9
4253 */
4254 MENDE_KIKAKUI,
4255
4256 /**
4257 * Unicode script "Modi".
4258 * @since 1.9
4259 */
4260 MODI,
4261
4262 /**
4263 * Unicode script "Mro".
4264 * @since 1.9
4265 */
4266 MRO,
4267
4268 /**
4269 * Unicode script "Old North Arabian".
4270 * @since 1.9
4271 */
4272 OLD_NORTH_ARABIAN,
4273
4274 /**
4275 * Unicode script "Nabataean".
4276 * @since 1.9
4277 */
4278 NABATAEAN,
4279
4280 /**
4281 * Unicode script "Palmyrene".
4282 * @since 1.9
4283 */
4284 PALMYRENE,
4285
4286 /**
4287 * Unicode script "Pau Cin Hau".
4288 * @since 1.9
4289 */
4290 PAU_CIN_HAU,
4291
4292 /**
4293 * Unicode script "Old Permic".
4294 * @since 1.9
4295 */
4296 OLD_PERMIC,
4297
4298 /**
4299 * Unicode script "Psalter Pahlavi".
4300 * @since 1.9
4301 */
4302 PSALTER_PAHLAVI,
4303
4304 /**
4305 * Unicode script "Siddham".
4306 * @since 1.9
4307 */
4308 SIDDHAM,
4309
4310 /**
4311 * Unicode script "Khudawadi".
4312 * @since 1.9
4313 */
4314 KHUDAWADI,
4315
4316 /**
4317 * Unicode script "Tirhuta".
4318 * @since 1.9
4319 */
4320 TIRHUTA,
4321
4322 /**
4323 * Unicode script "Warang Citi".
4324 * @since 1.9
4325 */
4326 WARANG_CITI,
4327
4328 /**
4329 * Unicode script "Ahom".
4330 * @since 1.9
4331 */
4332 AHOM,
4333
4334 /**
4335 * Unicode script "Anatolian Hieroglyphs".
4336 * @since 1.9
4337 */
4338 ANATOLIAN_HIEROGLYPHS,
4339
4340 /**
4341 * Unicode script "Hatran".
4342 * @since 1.9
4343 */
4344 HATRAN,
4345
4346 /**
4347 * Unicode script "Multani".
4348 * @since 1.9
4349 */
4350 MULTANI,
4351
4352 /**
4353 * Unicode script "Old Hungarian".
4354 * @since 1.9
4355 */
4356 OLD_HUNGARIAN,
4357
4358 /**
4359 * Unicode script "SignWriting".
4360 * @since 1.9
4361 */
4362 SIGNWRITING,
4363
4364 /**
4365 * Unicode script "Unknown".
4366 */
4367 UNKNOWN;
4368
4369 private static final int[] scriptStarts = {
4370 0x0000, // 0000..0040; COMMON
4371 0x0041, // 0041..005A; LATIN
4372 0x005B, // 005B..0060; COMMON
4373 0x0061, // 0061..007A; LATIN
4374 0x007B, // 007B..00A9; COMMON
4375 0x00AA, // 00AA ; LATIN
4376 0x00AB, // 00AB..00B9; COMMON
4377 0x00BA, // 00BA ; LATIN
4378 0x00BB, // 00BB..00BF; COMMON
4379 0x00C0, // 00C0..00D6; LATIN
4380 0x00D7, // 00D7 ; COMMON
|
476 /**
477 * Strong bidirectional character type "RLE" in the Unicode specification.
478 * @since 1.4
479 */
480 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
481
482 /**
483 * Strong bidirectional character type "RLO" in the Unicode specification.
484 * @since 1.4
485 */
486 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
487
488 /**
489 * Weak bidirectional character type "PDF" in the Unicode specification.
490 * @since 1.4
491 */
492 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
493
494 /**
495 * Weak bidirectional character type "LRI" in the Unicode specification.
496 * @since 9
497 */
498 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
499
500 /**
501 * Weak bidirectional character type "RLI" in the Unicode specification.
502 * @since 9
503 */
504 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
505
506 /**
507 * Weak bidirectional character type "FSI" in the Unicode specification.
508 * @since 9
509 */
510 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
511
512 /**
513 * Weak bidirectional character type "PDI" in the Unicode specification.
514 * @since 9
515 */
516 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
517
518 /**
519 * The minimum value of a
520 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
521 * Unicode high-surrogate code unit</a>
522 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
523 * A high-surrogate is also known as a <i>leading-surrogate</i>.
524 *
525 * @since 1.5
526 */
527 public static final char MIN_HIGH_SURROGATE = '\uD800';
528
529 /**
530 * The maximum value of a
531 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
532 * Unicode high-surrogate code unit</a>
533 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
534 * A high-surrogate is also known as a <i>leading-surrogate</i>.
2573 /**
2574 * Constant for the "Miao" Unicode character block.
2575 * @since 1.8
2576 */
2577 public static final UnicodeBlock MIAO =
2578 new UnicodeBlock("MIAO");
2579
2580 /**
2581 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2582 * character block.
2583 * @since 1.8
2584 */
2585 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2586 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2587 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2588 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2589
2590 /**
2591 * Constant for the "Combining Diacritical Marks Extended" Unicode
2592 * character block.
2593 * @since 9
2594 */
2595 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2596 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2597 "COMBINING DIACRITICAL MARKS EXTENDED",
2598 "COMBININGDIACRITICALMARKSEXTENDED");
2599
2600 /**
2601 * Constant for the "Myanmar Extended-B" Unicode character block.
2602 * @since 9
2603 */
2604 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2605 new UnicodeBlock("MYANMAR_EXTENDED_B",
2606 "MYANMAR EXTENDED-B",
2607 "MYANMAREXTENDED-B");
2608
2609 /**
2610 * Constant for the "Latin Extended-E" Unicode character block.
2611 * @since 9
2612 */
2613 public static final UnicodeBlock LATIN_EXTENDED_E =
2614 new UnicodeBlock("LATIN_EXTENDED_E",
2615 "LATIN EXTENDED-E",
2616 "LATINEXTENDED-E");
2617
2618 /**
2619 * Constant for the "Coptic Epact Numbers" Unicode character block.
2620 * @since 9
2621 */
2622 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2623 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2624 "COPTIC EPACT NUMBERS",
2625 "COPTICEPACTNUMBERS");
2626
2627 /**
2628 * Constant for the "Old Permic" Unicode character block.
2629 * @since 9
2630 */
2631 public static final UnicodeBlock OLD_PERMIC =
2632 new UnicodeBlock("OLD_PERMIC",
2633 "OLD PERMIC",
2634 "OLDPERMIC");
2635
2636 /**
2637 * Constant for the "Elbasan" Unicode character block.
2638 * @since 9
2639 */
2640 public static final UnicodeBlock ELBASAN =
2641 new UnicodeBlock("ELBASAN");
2642
2643 /**
2644 * Constant for the "Caucasian Albanian" Unicode character block.
2645 * @since 9
2646 */
2647 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2648 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2649 "CAUCASIAN ALBANIAN",
2650 "CAUCASIANALBANIAN");
2651
2652 /**
2653 * Constant for the "Linear A" Unicode character block.
2654 * @since 9
2655 */
2656 public static final UnicodeBlock LINEAR_A =
2657 new UnicodeBlock("LINEAR_A",
2658 "LINEAR A",
2659 "LINEARA");
2660
2661 /**
2662 * Constant for the "Palmyrene" Unicode character block.
2663 * @since 9
2664 */
2665 public static final UnicodeBlock PALMYRENE =
2666 new UnicodeBlock("PALMYRENE");
2667
2668 /**
2669 * Constant for the "Nabataean" Unicode character block.
2670 * @since 9
2671 */
2672 public static final UnicodeBlock NABATAEAN =
2673 new UnicodeBlock("NABATAEAN");
2674
2675 /**
2676 * Constant for the "Old North Arabian" Unicode character block.
2677 * @since 9
2678 */
2679 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2680 new UnicodeBlock("OLD_NORTH_ARABIAN",
2681 "OLD NORTH ARABIAN",
2682 "OLDNORTHARABIAN");
2683
2684 /**
2685 * Constant for the "Manichaean" Unicode character block.
2686 * @since 9
2687 */
2688 public static final UnicodeBlock MANICHAEAN =
2689 new UnicodeBlock("MANICHAEAN");
2690
2691 /**
2692 * Constant for the "Psalter Pahlavi" Unicode character block.
2693 * @since 9
2694 */
2695 public static final UnicodeBlock PSALTER_PAHLAVI =
2696 new UnicodeBlock("PSALTER_PAHLAVI",
2697 "PSALTER PAHLAVI",
2698 "PSALTERPAHLAVI");
2699
2700 /**
2701 * Constant for the "Mahajani" Unicode character block.
2702 * @since 9
2703 */
2704 public static final UnicodeBlock MAHAJANI =
2705 new UnicodeBlock("MAHAJANI");
2706
2707 /**
2708 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2709 * @since 9
2710 */
2711 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2712 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2713 "SINHALA ARCHAIC NUMBERS",
2714 "SINHALAARCHAICNUMBERS");
2715
2716 /**
2717 * Constant for the "Khojki" Unicode character block.
2718 * @since 9
2719 */
2720 public static final UnicodeBlock KHOJKI =
2721 new UnicodeBlock("KHOJKI");
2722
2723 /**
2724 * Constant for the "Khudawadi" Unicode character block.
2725 * @since 9
2726 */
2727 public static final UnicodeBlock KHUDAWADI =
2728 new UnicodeBlock("KHUDAWADI");
2729
2730 /**
2731 * Constant for the "Grantha" Unicode character block.
2732 * @since 9
2733 */
2734 public static final UnicodeBlock GRANTHA =
2735 new UnicodeBlock("GRANTHA");
2736
2737 /**
2738 * Constant for the "Tirhuta" Unicode character block.
2739 * @since 9
2740 */
2741 public static final UnicodeBlock TIRHUTA =
2742 new UnicodeBlock("TIRHUTA");
2743
2744 /**
2745 * Constant for the "Siddham" Unicode character block.
2746 * @since 9
2747 */
2748 public static final UnicodeBlock SIDDHAM =
2749 new UnicodeBlock("SIDDHAM");
2750
2751 /**
2752 * Constant for the "Modi" Unicode character block.
2753 * @since 9
2754 */
2755 public static final UnicodeBlock MODI =
2756 new UnicodeBlock("MODI");
2757
2758 /**
2759 * Constant for the "Warang Citi" Unicode character block.
2760 * @since 9
2761 */
2762 public static final UnicodeBlock WARANG_CITI =
2763 new UnicodeBlock("WARANG_CITI",
2764 "WARANG CITI",
2765 "WARANGCITI");
2766
2767 /**
2768 * Constant for the "Pau Cin Hau" Unicode character block.
2769 * @since 9
2770 */
2771 public static final UnicodeBlock PAU_CIN_HAU =
2772 new UnicodeBlock("PAU_CIN_HAU",
2773 "PAU CIN HAU",
2774 "PAUCINHAU");
2775
2776 /**
2777 * Constant for the "Mro" Unicode character block.
2778 * @since 9
2779 */
2780 public static final UnicodeBlock MRO =
2781 new UnicodeBlock("MRO");
2782
2783 /**
2784 * Constant for the "Bassa Vah" Unicode character block.
2785 * @since 9
2786 */
2787 public static final UnicodeBlock BASSA_VAH =
2788 new UnicodeBlock("BASSA_VAH",
2789 "BASSA VAH",
2790 "BASSAVAH");
2791
2792 /**
2793 * Constant for the "Pahawh Hmong" Unicode character block.
2794 * @since 9
2795 */
2796 public static final UnicodeBlock PAHAWH_HMONG =
2797 new UnicodeBlock("PAHAWH_HMONG",
2798 "PAHAWH HMONG",
2799 "PAHAWHHMONG");
2800
2801 /**
2802 * Constant for the "Duployan" Unicode character block.
2803 * @since 9
2804 */
2805 public static final UnicodeBlock DUPLOYAN =
2806 new UnicodeBlock("DUPLOYAN");
2807
2808 /**
2809 * Constant for the "Shorthand Format Controls" Unicode character block.
2810 * @since 9
2811 */
2812 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2813 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2814 "SHORTHAND FORMAT CONTROLS",
2815 "SHORTHANDFORMATCONTROLS");
2816
2817 /**
2818 * Constant for the "Mende Kikakui" Unicode character block.
2819 * @since 9
2820 */
2821 public static final UnicodeBlock MENDE_KIKAKUI =
2822 new UnicodeBlock("MENDE_KIKAKUI",
2823 "MENDE KIKAKUI",
2824 "MENDEKIKAKUI");
2825
2826 /**
2827 * Constant for the "Ornamental Dingbats" Unicode character block.
2828 * @since 9
2829 */
2830 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2831 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2832 "ORNAMENTAL DINGBATS",
2833 "ORNAMENTALDINGBATS");
2834
2835 /**
2836 * Constant for the "Geometric Shapes Extended" Unicode character block.
2837 * @since 9
2838 */
2839 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2840 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2841 "GEOMETRIC SHAPES EXTENDED",
2842 "GEOMETRICSHAPESEXTENDED");
2843
2844 /**
2845 * Constant for the "Supplemental Arrows-C" Unicode character block.
2846 * @since 9
2847 */
2848 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2849 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2850 "SUPPLEMENTAL ARROWS-C",
2851 "SUPPLEMENTALARROWS-C");
2852
2853 /**
2854 * Constant for the "Cherokee Supplement" Unicode character block.
2855 * @since 9
2856 */
2857 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2858 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2859 "CHEROKEE SUPPLEMENT",
2860 "CHEROKEESUPPLEMENT");
2861
2862 /**
2863 * Constant for the "Hatran" Unicode character block.
2864 * @since 9
2865 */
2866 public static final UnicodeBlock HATRAN =
2867 new UnicodeBlock("HATRAN");
2868
2869 /**
2870 * Constant for the "Old Hungarian" Unicode character block.
2871 * @since 9
2872 */
2873 public static final UnicodeBlock OLD_HUNGARIAN =
2874 new UnicodeBlock("OLD_HUNGARIAN",
2875 "OLD HUNGARIAN",
2876 "OLDHUNGARIAN");
2877
2878 /**
2879 * Constant for the "Multani" Unicode character block.
2880 * @since 9
2881 */
2882 public static final UnicodeBlock MULTANI =
2883 new UnicodeBlock("MULTANI");
2884
2885 /**
2886 * Constant for the "Ahom" Unicode character block.
2887 * @since 9
2888 */
2889 public static final UnicodeBlock AHOM =
2890 new UnicodeBlock("AHOM");
2891
2892 /**
2893 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2894 * @since 9
2895 */
2896 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2897 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2898 "EARLY DYNASTIC CUNEIFORM",
2899 "EARLYDYNASTICCUNEIFORM");
2900
2901 /**
2902 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2903 * @since 9
2904 */
2905 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2906 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2907 "ANATOLIAN HIEROGLYPHS",
2908 "ANATOLIANHIEROGLYPHS");
2909
2910 /**
2911 * Constant for the "Sutton SignWriting" Unicode character block.
2912 * @since 9
2913 */
2914 public static final UnicodeBlock SUTTON_SIGNWRITING =
2915 new UnicodeBlock("SUTTON_SIGNWRITING",
2916 "SUTTON SIGNWRITING",
2917 "SUTTONSIGNWRITING");
2918
2919 /**
2920 * Constant for the "Supplemental Symbols and Pictographs" Unicode
2921 * character block.
2922 * @since 9
2923 */
2924 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
2925 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
2926 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
2927 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
2928
2929 /**
2930 * Constant for the "CJK Unified Ideographs Extension E" Unicode
2931 * character block.
2932 * @since 9
2933 */
2934 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
2935 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
2936 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
2937 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
2938
2939
2940 private static final int blockStarts[] = {
2941 0x0000, // 0000..007F; Basic Latin
2942 0x0080, // 0080..00FF; Latin-1 Supplement
2943 0x0100, // 0100..017F; Latin Extended-A
2944 0x0180, // 0180..024F; Latin Extended-B
2945 0x0250, // 0250..02AF; IPA Extensions
2946 0x02B0, // 02B0..02FF; Spacing Modifier Letters
2947 0x0300, // 0300..036F; Combining Diacritical Marks
2948 0x0370, // 0370..03FF; Greek and Coptic
2949 0x0400, // 0400..04FF; Cyrillic
2950 0x0500, // 0500..052F; Cyrillic Supplement
2951 0x0530, // 0530..058F; Armenian
2952 0x0590, // 0590..05FF; Hebrew
4172 /**
4173 * Unicode script "Sharada".
4174 * @since 1.8
4175 */
4176 SHARADA,
4177
4178 /**
4179 * Unicode script "Takri".
4180 * @since 1.8
4181 */
4182 TAKRI,
4183
4184 /**
4185 * Unicode script "Miao".
4186 * @since 1.8
4187 */
4188 MIAO,
4189
4190 /**
4191 * Unicode script "Caucasian Albanian".
4192 * @since 9
4193 */
4194 CAUCASIAN_ALBANIAN,
4195
4196 /**
4197 * Unicode script "Bassa Vah".
4198 * @since 9
4199 */
4200 BASSA_VAH,
4201
4202 /**
4203 * Unicode script "Duployan".
4204 * @since 9
4205 */
4206 DUPLOYAN,
4207
4208 /**
4209 * Unicode script "Elbasan".
4210 * @since 9
4211 */
4212 ELBASAN,
4213
4214 /**
4215 * Unicode script "Grantha".
4216 * @since 9
4217 */
4218 GRANTHA,
4219
4220 /**
4221 * Unicode script "Pahawh Hmong".
4222 * @since 9
4223 */
4224 PAHAWH_HMONG,
4225
4226 /**
4227 * Unicode script "Khojki".
4228 * @since 9
4229 */
4230 KHOJKI,
4231
4232 /**
4233 * Unicode script "Linear A".
4234 * @since 9
4235 */
4236 LINEAR_A,
4237
4238 /**
4239 * Unicode script "Mahajani".
4240 * @since 9
4241 */
4242 MAHAJANI,
4243
4244 /**
4245 * Unicode script "Manichaean".
4246 * @since 9
4247 */
4248 MANICHAEAN,
4249
4250 /**
4251 * Unicode script "Mende Kikakui".
4252 * @since 9
4253 */
4254 MENDE_KIKAKUI,
4255
4256 /**
4257 * Unicode script "Modi".
4258 * @since 9
4259 */
4260 MODI,
4261
4262 /**
4263 * Unicode script "Mro".
4264 * @since 9
4265 */
4266 MRO,
4267
4268 /**
4269 * Unicode script "Old North Arabian".
4270 * @since 9
4271 */
4272 OLD_NORTH_ARABIAN,
4273
4274 /**
4275 * Unicode script "Nabataean".
4276 * @since 9
4277 */
4278 NABATAEAN,
4279
4280 /**
4281 * Unicode script "Palmyrene".
4282 * @since 9
4283 */
4284 PALMYRENE,
4285
4286 /**
4287 * Unicode script "Pau Cin Hau".
4288 * @since 9
4289 */
4290 PAU_CIN_HAU,
4291
4292 /**
4293 * Unicode script "Old Permic".
4294 * @since 9
4295 */
4296 OLD_PERMIC,
4297
4298 /**
4299 * Unicode script "Psalter Pahlavi".
4300 * @since 9
4301 */
4302 PSALTER_PAHLAVI,
4303
4304 /**
4305 * Unicode script "Siddham".
4306 * @since 9
4307 */
4308 SIDDHAM,
4309
4310 /**
4311 * Unicode script "Khudawadi".
4312 * @since 9
4313 */
4314 KHUDAWADI,
4315
4316 /**
4317 * Unicode script "Tirhuta".
4318 * @since 9
4319 */
4320 TIRHUTA,
4321
4322 /**
4323 * Unicode script "Warang Citi".
4324 * @since 9
4325 */
4326 WARANG_CITI,
4327
4328 /**
4329 * Unicode script "Ahom".
4330 * @since 9
4331 */
4332 AHOM,
4333
4334 /**
4335 * Unicode script "Anatolian Hieroglyphs".
4336 * @since 9
4337 */
4338 ANATOLIAN_HIEROGLYPHS,
4339
4340 /**
4341 * Unicode script "Hatran".
4342 * @since 9
4343 */
4344 HATRAN,
4345
4346 /**
4347 * Unicode script "Multani".
4348 * @since 9
4349 */
4350 MULTANI,
4351
4352 /**
4353 * Unicode script "Old Hungarian".
4354 * @since 9
4355 */
4356 OLD_HUNGARIAN,
4357
4358 /**
4359 * Unicode script "SignWriting".
4360 * @since 9
4361 */
4362 SIGNWRITING,
4363
4364 /**
4365 * Unicode script "Unknown".
4366 */
4367 UNKNOWN;
4368
4369 private static final int[] scriptStarts = {
4370 0x0000, // 0000..0040; COMMON
4371 0x0041, // 0041..005A; LATIN
4372 0x005B, // 005B..0060; COMMON
4373 0x0061, // 0061..007A; LATIN
4374 0x007B, // 007B..00A9; COMMON
4375 0x00AA, // 00AA ; LATIN
4376 0x00AB, // 00AB..00B9; COMMON
4377 0x00BA, // 00BA ; LATIN
4378 0x00BB, // 00BB..00BF; COMMON
4379 0x00C0, // 00C0..00D6; LATIN
4380 0x00D7, // 00D7 ; COMMON
|