1 /* GENERATED SOURCE. DO NOT MODIFY. */ 2 // 2016 and later: Unicode, Inc. and others. 3 // License & terms of use: http://www.unicode.org/copyright.html#License 4 /** 5 ******************************************************************************* 6 * Copyright (C) 2001-2016 International Business Machines Corporation and 7 * others. All Rights Reserved. 8 ******************************************************************************* 9 */ 10 11 package android.icu.lang; 12 13 import java.util.BitSet; 14 import java.util.Locale; 15 16 import android.icu.impl.UCharacterProperty; 17 import android.icu.util.ULocale; 18 19 /** 20 * Constants for ISO 15924 script codes, and related functions. 21 * 22 * <p>The current set of script code constants supports at least all scripts 23 * that are encoded in the version of Unicode which ICU currently supports. 24 * The names of the constants are usually derived from the 25 * Unicode script property value aliases. 26 * See UAX #24 Unicode Script Property (http://www.unicode.org/reports/tr24/) 27 * and http://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt . 28 * 29 * <p>In addition, constants for many ISO 15924 script codes 30 * are included, for use with language tags, CLDR data, and similar. 31 * Some of those codes are not used in the Unicode Character Database (UCD). 32 * For example, there are no characters that have a UCD script property value of 33 * Hans or Hant. All Han ideographs have the Hani script property value in Unicode. 34 * 35 * <p>Private-use codes Qaaa..Qabx are not included, except as used in the UCD or in CLDR. 36 * 37 * <p>Starting with ICU 55, script codes are only added when their scripts 38 * have been or will certainly be encoded in Unicode, 39 * and have been assigned Unicode script property value aliases, 40 * to ensure that their script names are stable and match the names of the constants. 41 * Script codes like Latf and Aran that are not subject to separate encoding 42 * may be added at any time. 43 */ 44 public final class UScript { 45 /** 46 * Invalid code 47 */ 48 public static final int INVALID_CODE = -1; 49 /** 50 * Common 51 */ 52 public static final int COMMON = 0; /* Zyyy */ 53 /** 54 * Inherited 55 */ 56 public static final int INHERITED = 1; /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */ 57 /** 58 * Arabic 59 */ 60 public static final int ARABIC = 2; /* Arab */ 61 /** 62 * Armenian 63 */ 64 public static final int ARMENIAN = 3; /* Armn */ 65 /** 66 * Bengali 67 */ 68 public static final int BENGALI = 4; /* Beng */ 69 /** 70 * Bopomofo 71 */ 72 public static final int BOPOMOFO = 5; /* Bopo */ 73 /** 74 * Cherokee 75 */ 76 public static final int CHEROKEE = 6; /* Cher */ 77 /** 78 * Coptic 79 */ 80 public static final int COPTIC = 7; /* Qaac */ 81 /** 82 * Cyrillic 83 */ 84 public static final int CYRILLIC = 8; /* Cyrl (Cyrs) */ 85 /** 86 * Deseret 87 */ 88 public static final int DESERET = 9; /* Dsrt */ 89 /** 90 * Devanagari 91 */ 92 public static final int DEVANAGARI = 10; /* Deva */ 93 /** 94 * Ethiopic 95 */ 96 public static final int ETHIOPIC = 11; /* Ethi */ 97 /** 98 * Georgian 99 */ 100 public static final int GEORGIAN = 12; /* Geor (Geon; Geoa) */ 101 /** 102 * Gothic 103 */ 104 public static final int GOTHIC = 13; /* Goth */ 105 /** 106 * Greek 107 */ 108 public static final int GREEK = 14; /* Grek */ 109 /** 110 * Gujarati 111 */ 112 public static final int GUJARATI = 15; /* Gujr */ 113 /** 114 * Gurmukhi 115 */ 116 public static final int GURMUKHI = 16; /* Guru */ 117 /** 118 * Han 119 */ 120 public static final int HAN = 17; /* Hani */ 121 /** 122 * Hangul 123 */ 124 public static final int HANGUL = 18; /* Hang */ 125 /** 126 * Hebrew 127 */ 128 public static final int HEBREW = 19; /* Hebr */ 129 /** 130 * Hiragana 131 */ 132 public static final int HIRAGANA = 20; /* Hira */ 133 /** 134 * Kannada 135 */ 136 public static final int KANNADA = 21; /* Knda */ 137 /** 138 * Katakana 139 */ 140 public static final int KATAKANA = 22; /* Kana */ 141 /** 142 * Khmer 143 */ 144 public static final int KHMER = 23; /* Khmr */ 145 /** 146 * Lao 147 */ 148 public static final int LAO = 24; /* Laoo */ 149 /** 150 * Latin 151 */ 152 public static final int LATIN = 25; /* Latn (Latf; Latg) */ 153 /** 154 * Malayalam 155 */ 156 public static final int MALAYALAM = 26; /* Mlym */ 157 /** 158 * Mangolian 159 */ 160 public static final int MONGOLIAN = 27; /* Mong */ 161 /** 162 * Myammar 163 */ 164 public static final int MYANMAR = 28; /* Mymr */ 165 /** 166 * Ogham 167 */ 168 public static final int OGHAM = 29; /* Ogam */ 169 /** 170 * Old Itallic 171 */ 172 public static final int OLD_ITALIC = 30; /* Ital */ 173 /** 174 * Oriya 175 */ 176 public static final int ORIYA = 31; /* Orya */ 177 /** 178 * Runic 179 */ 180 public static final int RUNIC = 32; /* Runr */ 181 /** 182 * Sinhala 183 */ 184 public static final int SINHALA = 33; /* Sinh */ 185 /** 186 * Syriac 187 */ 188 public static final int SYRIAC = 34; /* Syrc (Syrj; Syrn; Syre) */ 189 /** 190 * Tamil 191 */ 192 public static final int TAMIL = 35; /* Taml */ 193 /** 194 * Telugu 195 */ 196 public static final int TELUGU = 36; /* Telu */ 197 /** 198 * Thana 199 */ 200 public static final int THAANA = 37; /* Thaa */ 201 /** 202 * Thai 203 */ 204 public static final int THAI = 38; /* Thai */ 205 /** 206 * Tibetan 207 */ 208 public static final int TIBETAN = 39; /* Tibt */ 209 /** 210 * Unified Canadian Aboriginal Symbols 211 */ 212 public static final int CANADIAN_ABORIGINAL = 40; /* Cans */ 213 /** 214 * Unified Canadian Aboriginal Symbols (alias) 215 */ 216 public static final int UCAS = CANADIAN_ABORIGINAL; /* Cans */ 217 /** 218 * Yi syllables 219 */ 220 public static final int YI = 41; /* Yiii */ 221 /** 222 * Tagalog 223 */ 224 public static final int TAGALOG = 42; /* Tglg */ 225 /** 226 * Hanunooo 227 */ 228 public static final int HANUNOO = 43; /* Hano */ 229 /** 230 * Buhid 231 */ 232 public static final int BUHID = 44; /* Buhd */ 233 /** 234 * Tagbanwa 235 */ 236 public static final int TAGBANWA = 45; /* Tagb */ 237 /** 238 * Braille 239 * Script in Unicode 4 240 * 241 */ 242 public static final int BRAILLE = 46; /* Brai */ 243 /** 244 * Cypriot 245 * Script in Unicode 4 246 * 247 */ 248 public static final int CYPRIOT = 47; /* Cprt */ 249 /** 250 * Limbu 251 * Script in Unicode 4 252 * 253 */ 254 public static final int LIMBU = 48; /* Limb */ 255 /** 256 * Linear B 257 * Script in Unicode 4 258 * 259 */ 260 public static final int LINEAR_B = 49; /* Linb */ 261 /** 262 * Osmanya 263 * Script in Unicode 4 264 * 265 */ 266 public static final int OSMANYA = 50; /* Osma */ 267 /** 268 * Shavian 269 * Script in Unicode 4 270 * 271 */ 272 public static final int SHAVIAN = 51; /* Shaw */ 273 /** 274 * Tai Le 275 * Script in Unicode 4 276 * 277 */ 278 public static final int TAI_LE = 52; /* Tale */ 279 /** 280 * Ugaritic 281 * Script in Unicode 4 282 * 283 */ 284 public static final int UGARITIC = 53; /* Ugar */ 285 /** 286 * Script in Unicode 4.0.1 287 */ 288 public static final int KATAKANA_OR_HIRAGANA = 54; /*Hrkt */ 289 290 /** 291 * Script in Unicode 4.1 292 */ 293 public static final int BUGINESE = 55; /* Bugi */ 294 /** 295 * Script in Unicode 4.1 296 */ 297 public static final int GLAGOLITIC = 56; /* Glag */ 298 /** 299 * Script in Unicode 4.1 300 */ 301 public static final int KHAROSHTHI = 57; /* Khar */ 302 /** 303 * Script in Unicode 4.1 304 */ 305 public static final int SYLOTI_NAGRI = 58; /* Sylo */ 306 /** 307 * Script in Unicode 4.1 308 */ 309 public static final int NEW_TAI_LUE = 59; /* Talu */ 310 /** 311 * Script in Unicode 4.1 312 */ 313 public static final int TIFINAGH = 60; /* Tfng */ 314 /** 315 * Script in Unicode 4.1 316 */ 317 public static final int OLD_PERSIAN = 61; /* Xpeo */ 318 319 320 /** 321 * ISO 15924 script code 322 */ 323 public static final int BALINESE = 62; /* Bali */ 324 /** 325 * ISO 15924 script code 326 */ 327 public static final int BATAK = 63; /* Batk */ 328 /** 329 * ISO 15924 script code 330 */ 331 public static final int BLISSYMBOLS = 64; /* Blis */ 332 /** 333 * ISO 15924 script code 334 */ 335 public static final int BRAHMI = 65; /* Brah */ 336 /** 337 * ISO 15924 script code 338 */ 339 public static final int CHAM = 66; /* Cham */ 340 /** 341 * ISO 15924 script code 342 */ 343 public static final int CIRTH = 67; /* Cirt */ 344 /** 345 * ISO 15924 script code 346 */ 347 public static final int OLD_CHURCH_SLAVONIC_CYRILLIC = 68; /* Cyrs */ 348 /** 349 * ISO 15924 script code 350 */ 351 public static final int DEMOTIC_EGYPTIAN = 69; /* Egyd */ 352 /** 353 * ISO 15924 script code 354 */ 355 public static final int HIERATIC_EGYPTIAN = 70; /* Egyh */ 356 /** 357 * ISO 15924 script code 358 */ 359 public static final int EGYPTIAN_HIEROGLYPHS = 71; /* Egyp */ 360 /** 361 * ISO 15924 script code 362 */ 363 public static final int KHUTSURI = 72; /* Geok */ 364 /** 365 * ISO 15924 script code 366 */ 367 public static final int SIMPLIFIED_HAN = 73; /* Hans */ 368 /** 369 * ISO 15924 script code 370 */ 371 public static final int TRADITIONAL_HAN = 74; /* Hant */ 372 /** 373 * ISO 15924 script code 374 */ 375 public static final int PAHAWH_HMONG = 75; /* Hmng */ 376 /** 377 * ISO 15924 script code 378 */ 379 public static final int OLD_HUNGARIAN = 76; /* Hung */ 380 /** 381 * ISO 15924 script code 382 */ 383 public static final int HARAPPAN_INDUS = 77; /* Inds */ 384 /** 385 * ISO 15924 script code 386 */ 387 public static final int JAVANESE = 78; /* Java */ 388 /** 389 * ISO 15924 script code 390 */ 391 public static final int KAYAH_LI = 79; /* Kali */ 392 /** 393 * ISO 15924 script code 394 */ 395 public static final int LATIN_FRAKTUR = 80; /* Latf */ 396 /** 397 * ISO 15924 script code 398 */ 399 public static final int LATIN_GAELIC = 81; /* Latg */ 400 /** 401 * ISO 15924 script code 402 */ 403 public static final int LEPCHA = 82; /* Lepc */ 404 /** 405 * ISO 15924 script code 406 */ 407 public static final int LINEAR_A = 83; /* Lina */ 408 /** 409 * ISO 15924 script code 410 */ 411 public static final int MANDAIC = 84; /* Mand */ 412 /** 413 * ISO 15924 script code 414 */ 415 public static final int MANDAEAN = MANDAIC; 416 /** 417 * ISO 15924 script code 418 */ 419 public static final int MAYAN_HIEROGLYPHS = 85; /* Maya */ 420 /** 421 * ISO 15924 script code 422 */ 423 public static final int MEROITIC_HIEROGLYPHS = 86; /* Mero */ 424 /** 425 * ISO 15924 script code 426 */ 427 public static final int MEROITIC = MEROITIC_HIEROGLYPHS; 428 /** 429 * ISO 15924 script code 430 */ 431 public static final int NKO = 87; /* Nkoo */ 432 /** 433 * ISO 15924 script code 434 */ 435 public static final int ORKHON = 88; /* Orkh */ 436 /** 437 * ISO 15924 script code 438 */ 439 public static final int OLD_PERMIC = 89; /* Perm */ 440 /** 441 * ISO 15924 script code 442 */ 443 public static final int PHAGS_PA = 90; /* Phag */ 444 /** 445 * ISO 15924 script code 446 */ 447 public static final int PHOENICIAN = 91; /* Phnx */ 448 /** 449 * ISO 15924 script code 450 */ 451 public static final int MIAO = 92; /* Plrd */ 452 /** 453 * ISO 15924 script code 454 */ 455 public static final int PHONETIC_POLLARD = MIAO; 456 /** 457 * ISO 15924 script code 458 */ 459 public static final int RONGORONGO = 93; /* Roro */ 460 /** 461 * ISO 15924 script code 462 */ 463 public static final int SARATI = 94; /* Sara */ 464 /** 465 * ISO 15924 script code 466 */ 467 public static final int ESTRANGELO_SYRIAC = 95; /* Syre */ 468 /** 469 * ISO 15924 script code 470 */ 471 public static final int WESTERN_SYRIAC = 96; /* Syrj */ 472 /** 473 * ISO 15924 script code 474 */ 475 public static final int EASTERN_SYRIAC = 97; /* Syrn */ 476 /** 477 * ISO 15924 script code 478 */ 479 public static final int TENGWAR = 98; /* Teng */ 480 /** 481 * ISO 15924 script code 482 */ 483 public static final int VAI = 99; /* Vaii */ 484 /** 485 * ISO 15924 script code 486 */ 487 public static final int VISIBLE_SPEECH = 100;/* Visp */ 488 /** 489 * ISO 15924 script code 490 */ 491 public static final int CUNEIFORM = 101;/* Xsux */ 492 /** 493 * ISO 15924 script code 494 */ 495 public static final int UNWRITTEN_LANGUAGES = 102;/* Zxxx */ 496 /** 497 * ISO 15924 script code 498 */ 499 public static final int UNKNOWN = 103;/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */ 500 501 /** 502 * ISO 15924 script code 503 */ 504 public static final int CARIAN = 104;/* Cari */ 505 /** 506 * ISO 15924 script code 507 */ 508 public static final int JAPANESE = 105;/* Jpan */ 509 /** 510 * ISO 15924 script code 511 */ 512 public static final int LANNA = 106;/* Lana */ 513 /** 514 * ISO 15924 script code 515 */ 516 public static final int LYCIAN = 107;/* Lyci */ 517 /** 518 * ISO 15924 script code 519 */ 520 public static final int LYDIAN = 108;/* Lydi */ 521 /** 522 * ISO 15924 script code 523 */ 524 public static final int OL_CHIKI = 109;/* Olck */ 525 /** 526 * ISO 15924 script code 527 */ 528 public static final int REJANG = 110;/* Rjng */ 529 /** 530 * ISO 15924 script code 531 */ 532 public static final int SAURASHTRA = 111;/* Saur */ 533 /** 534 * ISO 15924 script code for Sutton SignWriting 535 */ 536 public static final int SIGN_WRITING = 112;/* Sgnw */ 537 /** 538 * ISO 15924 script code 539 */ 540 public static final int SUNDANESE = 113;/* Sund */ 541 /** 542 * ISO 15924 script code 543 */ 544 public static final int MOON = 114;/* Moon */ 545 /** 546 * ISO 15924 script code 547 */ 548 public static final int MEITEI_MAYEK = 115;/* Mtei */ 549 550 /** 551 * ISO 15924 script code 552 */ 553 public static final int IMPERIAL_ARAMAIC = 116;/* Armi */ 554 555 /** 556 * ISO 15924 script code 557 */ 558 public static final int AVESTAN = 117;/* Avst */ 559 560 /** 561 * ISO 15924 script code 562 */ 563 public static final int CHAKMA = 118;/* Cakm */ 564 565 /** 566 * ISO 15924 script code 567 */ 568 public static final int KOREAN = 119;/* Kore */ 569 570 /** 571 * ISO 15924 script code 572 */ 573 public static final int KAITHI = 120;/* Kthi */ 574 575 /** 576 * ISO 15924 script code 577 */ 578 public static final int MANICHAEAN = 121;/* Mani */ 579 580 /** 581 * ISO 15924 script code 582 */ 583 public static final int INSCRIPTIONAL_PAHLAVI = 122;/* Phli */ 584 585 /** 586 * ISO 15924 script code 587 */ 588 public static final int PSALTER_PAHLAVI = 123;/* Phlp */ 589 590 /** 591 * ISO 15924 script code 592 */ 593 public static final int BOOK_PAHLAVI = 124;/* Phlv */ 594 595 /** 596 * ISO 15924 script code 597 */ 598 public static final int INSCRIPTIONAL_PARTHIAN = 125;/* Prti */ 599 600 /** 601 * ISO 15924 script code 602 */ 603 public static final int SAMARITAN = 126;/* Samr */ 604 605 /** 606 * ISO 15924 script code 607 */ 608 public static final int TAI_VIET = 127;/* Tavt */ 609 610 /** 611 * ISO 15924 script code 612 */ 613 public static final int MATHEMATICAL_NOTATION = 128;/* Zmth */ 614 615 /** 616 * ISO 15924 script code 617 */ 618 public static final int SYMBOLS = 129;/* Zsym */ 619 620 /** 621 * ISO 15924 script code 622 */ 623 public static final int BAMUM = 130;/* Bamu */ 624 /** 625 * ISO 15924 script code 626 */ 627 public static final int LISU = 131;/* Lisu */ 628 /** 629 * ISO 15924 script code 630 */ 631 public static final int NAKHI_GEBA = 132;/* Nkgb */ 632 /** 633 * ISO 15924 script code 634 */ 635 public static final int OLD_SOUTH_ARABIAN = 133;/* Sarb */ 636 637 /** 638 * ISO 15924 script code 639 */ 640 public static final int BASSA_VAH = 134;/* Bass */ 641 /** 642 * ISO 15924 script code 643 */ 644 public static final int DUPLOYAN = 135;/* Dupl */ 645 /** 646 * Typo, use DUPLOYAN 647 * @deprecated ICU 54 648 * @hide original deprecated declaration 649 */ 650 @Deprecated 651 public static final int DUPLOYAN_SHORTAND = DUPLOYAN; 652 /** 653 * ISO 15924 script code 654 */ 655 public static final int ELBASAN = 136;/* Elba */ 656 /** 657 * ISO 15924 script code 658 */ 659 public static final int GRANTHA = 137;/* Gran */ 660 /** 661 * ISO 15924 script code 662 */ 663 public static final int KPELLE = 138;/* Kpel */ 664 /** 665 * ISO 15924 script code 666 */ 667 public static final int LOMA = 139;/* Loma */ 668 /** 669 * Mende Kikakui 670 * ISO 15924 script code 671 */ 672 public static final int MENDE = 140;/* Mend */ 673 /** 674 * ISO 15924 script code 675 */ 676 public static final int MEROITIC_CURSIVE = 141;/* Merc */ 677 /** 678 * ISO 15924 script code 679 */ 680 public static final int OLD_NORTH_ARABIAN = 142;/* Narb */ 681 /** 682 * ISO 15924 script code 683 */ 684 public static final int NABATAEAN = 143;/* Nbat */ 685 /** 686 * ISO 15924 script code 687 */ 688 public static final int PALMYRENE = 144;/* Palm */ 689 /** 690 * ISO 15924 script code 691 */ 692 public static final int KHUDAWADI = 145;/* Sind */ 693 /** 694 * ISO 15924 script code 695 */ 696 public static final int SINDHI = KHUDAWADI; 697 /** 698 * ISO 15924 script code 699 */ 700 public static final int WARANG_CITI = 146;/* Wara */ 701 702 /** 703 * ISO 15924 script code 704 */ 705 public static final int AFAKA = 147;/* Afak */ 706 /** 707 * ISO 15924 script code 708 */ 709 public static final int JURCHEN = 148;/* Jurc */ 710 /** 711 * ISO 15924 script code 712 */ 713 public static final int MRO = 149;/* Mroo */ 714 /** 715 * ISO 15924 script code 716 */ 717 public static final int NUSHU = 150;/* Nshu */ 718 /** 719 * ISO 15924 script code 720 */ 721 public static final int SHARADA = 151;/* Shrd */ 722 /** 723 * ISO 15924 script code 724 */ 725 public static final int SORA_SOMPENG = 152;/* Sora */ 726 /** 727 * ISO 15924 script code 728 */ 729 public static final int TAKRI = 153;/* Takr */ 730 /** 731 * ISO 15924 script code 732 */ 733 public static final int TANGUT = 154;/* Tang */ 734 /** 735 * ISO 15924 script code 736 */ 737 public static final int WOLEAI = 155;/* Wole */ 738 739 /** 740 * ISO 15924 script code 741 */ 742 public static final int ANATOLIAN_HIEROGLYPHS = 156;/* Hluw */ 743 /** 744 * ISO 15924 script code 745 */ 746 public static final int KHOJKI = 157;/* Khoj */ 747 /** 748 * ISO 15924 script code 749 */ 750 public static final int TIRHUTA = 158;/* Tirh */ 751 /** 752 * ISO 15924 script code 753 */ 754 public static final int CAUCASIAN_ALBANIAN = 159; /* Aghb */ 755 /** 756 * ISO 15924 script code 757 */ 758 public static final int MAHAJANI = 160; /* Mahj */ 759 760 /** 761 * ISO 15924 script code 762 */ 763 public static final int AHOM = 161; /* Ahom */ 764 /** 765 * ISO 15924 script code 766 */ 767 public static final int HATRAN = 162; /* Hatr */ 768 /** 769 * ISO 15924 script code 770 */ 771 public static final int MODI = 163; /* Modi */ 772 /** 773 * ISO 15924 script code 774 */ 775 public static final int MULTANI = 164; /* Mult */ 776 /** 777 * ISO 15924 script code 778 */ 779 public static final int PAU_CIN_HAU = 165; /* Pauc */ 780 /** 781 * ISO 15924 script code 782 */ 783 public static final int SIDDHAM = 166; /* Sidd */ 784 785 /** 786 * ISO 15924 script code 787 */ 788 public static final int ADLAM = 167; /* Adlm */ 789 /** 790 * ISO 15924 script code 791 */ 792 public static final int BHAIKSUKI = 168; /* Bhks */ 793 /** 794 * ISO 15924 script code 795 */ 796 public static final int MARCHEN = 169; /* Marc */ 797 /** 798 * ISO 15924 script code 799 */ 800 public static final int NEWA = 170; /* Newa */ 801 /** 802 * ISO 15924 script code 803 */ 804 public static final int OSAGE = 171; /* Osge */ 805 806 /** 807 * ISO 15924 script code 808 */ 809 public static final int HAN_WITH_BOPOMOFO = 172; /* Hanb */ 810 /** 811 * ISO 15924 script code 812 */ 813 public static final int JAMO = 173; /* Jamo */ 814 /** 815 * ISO 15924 script code 816 */ 817 public static final int SYMBOLS_EMOJI = 174; /* Zsye */ 818 819 /** 820 * One more than the highest normal UScript code. 821 * The highest value is available via UCharacter.getIntPropertyMaxValue(UProperty.SCRIPT). 822 * 823 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 824 * @hide unsupported on Android 825 */ 826 @Deprecated 827 public static final int CODE_LIMIT = 175; 828 829 private static int[] getCodesFromLocale(ULocale locale) { 830 // Multi-script languages, equivalent to the LocaleScript data 831 // that we used to load from locale resource bundles. 832 String lang = locale.getLanguage(); 833 if(lang.equals("ja")) { 834 return new int[] { UScript.KATAKANA, UScript.HIRAGANA, UScript.HAN }; 835 } 836 if(lang.equals("ko")) { 837 return new int[] { UScript.HANGUL, UScript.HAN }; 838 } 839 String script = locale.getScript(); 840 if(lang.equals("zh") && script.equals("Hant")) { 841 return new int[] { UScript.HAN, UScript.BOPOMOFO }; 842 } 843 // Explicit script code. 844 if(script.length() != 0) { 845 int scriptCode = UScript.getCodeFromName(script); 846 if(scriptCode != UScript.INVALID_CODE) { 847 if(scriptCode == UScript.SIMPLIFIED_HAN || scriptCode == UScript.TRADITIONAL_HAN) { 848 scriptCode = UScript.HAN; 849 } 850 return new int[] { scriptCode }; 851 } 852 } 853 return null; 854 } 855 856 /** 857 * Helper function to find the code from locale. 858 * @param locale The locale. 859 */ 860 private static int[] findCodeFromLocale(ULocale locale) { 861 int[] result = getCodesFromLocale(locale); 862 if(result != null) { 863 return result; 864 } 865 ULocale likely = ULocale.addLikelySubtags(locale); 866 return getCodesFromLocale(likely); 867 } 868 869 /** 870 * Gets a script codes associated with the given locale or ISO 15924 abbreviation or name. 871 * Returns MALAYAM given "Malayam" OR "Mlym". 872 * Returns LATIN given "en" OR "en_US" 873 * @param locale Locale 874 * @return The script codes array. null if the the code cannot be found. 875 */ 876 public static final int[] getCode(Locale locale){ 877 return findCodeFromLocale(ULocale.forLocale(locale)); 878 } 879 /** 880 * Gets a script codes associated with the given locale or ISO 15924 abbreviation or name. 881 * Returns MALAYAM given "Malayam" OR "Mlym". 882 * Returns LATIN given "en" OR "en_US" 883 * @param locale ULocale 884 * @return The script codes array. null if the the code cannot be found. 885 */ 886 public static final int[] getCode(ULocale locale){ 887 return findCodeFromLocale(locale); 888 } 889 /** 890 * Gets the script codes associated with the given locale or ISO 15924 abbreviation or name. 891 * Returns MALAYAM given "Malayam" OR "Mlym". 892 * Returns LATIN given "en" OR "en_US" 893 * 894 * <p>Note: To search by short or long script alias only, use 895 * {@link #getCodeFromName(String)} instead. 896 * That does a fast lookup with no access of the locale data. 897 * 898 * @param nameOrAbbrOrLocale name of the script or ISO 15924 code or locale 899 * @return The script codes array. null if the the code cannot be found. 900 */ 901 public static final int[] getCode(String nameOrAbbrOrLocale) { 902 boolean triedCode = false; 903 if (nameOrAbbrOrLocale.indexOf('_') < 0 && nameOrAbbrOrLocale.indexOf('-') < 0) { 904 int propNum = UCharacter.getPropertyValueEnumNoThrow(UProperty.SCRIPT, nameOrAbbrOrLocale); 905 if (propNum != UProperty.UNDEFINED) { 906 return new int[] {propNum}; 907 } 908 triedCode = true; 909 } 910 int[] scripts = findCodeFromLocale(new ULocale(nameOrAbbrOrLocale)); 911 if (scripts != null) { 912 return scripts; 913 } 914 if (!triedCode) { 915 int propNum = UCharacter.getPropertyValueEnumNoThrow(UProperty.SCRIPT, nameOrAbbrOrLocale); 916 if (propNum != UProperty.UNDEFINED) { 917 return new int[] {propNum}; 918 } 919 } 920 return null; 921 } 922 923 /** 924 * Returns the script code associated with the given Unicode script property alias 925 * (name or abbreviation). 926 * Short aliases are ISO 15924 script codes. 927 * Returns MALAYAM given "Malayam" OR "Mlym". 928 * 929 * @param nameOrAbbr name of the script or ISO 15924 code 930 * @return The script code value, or INVALID_CODE if the code cannot be found. 931 */ 932 public static final int getCodeFromName(String nameOrAbbr) { 933 int propNum = UCharacter.getPropertyValueEnumNoThrow(UProperty.SCRIPT, nameOrAbbr); 934 return propNum == UProperty.UNDEFINED ? INVALID_CODE : propNum; 935 } 936 937 /** 938 * Gets the script code associated with the given codepoint. 939 * Returns UScript.MALAYAM given 0x0D02 940 * @param codepoint UChar32 codepoint 941 * @return The script code 942 */ 943 public static final int getScript(int codepoint){ 944 if (codepoint >= UCharacter.MIN_VALUE & codepoint <= UCharacter.MAX_VALUE) { 945 int scriptX=UCharacterProperty.INSTANCE.getAdditional(codepoint, 0)&UCharacterProperty.SCRIPT_X_MASK; 946 if(scriptX<UCharacterProperty.SCRIPT_X_WITH_COMMON) { 947 return scriptX; 948 } else if(scriptX<UCharacterProperty.SCRIPT_X_WITH_INHERITED) { 949 return UScript.COMMON; 950 } else if(scriptX<UCharacterProperty.SCRIPT_X_WITH_OTHER) { 951 return UScript.INHERITED; 952 } else { 953 return UCharacterProperty.INSTANCE.m_scriptExtensions_[scriptX&UCharacterProperty.SCRIPT_MASK_]; 954 } 955 }else{ 956 throw new IllegalArgumentException(Integer.toString(codepoint)); 957 } 958 } 959 960 /** 961 * Do the Script_Extensions of code point c contain script sc? 962 * If c does not have explicit Script_Extensions, then this tests whether 963 * c has the Script property value sc. 964 * 965 * <p>Some characters are commonly used in multiple scripts. 966 * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 967 * 968 * @param c code point 969 * @param sc script code 970 * @return true if sc is in Script_Extensions(c) 971 */ 972 public static final boolean hasScript(int c, int sc) { 973 int scriptX=UCharacterProperty.INSTANCE.getAdditional(c, 0)&UCharacterProperty.SCRIPT_X_MASK; 974 if(scriptX<UCharacterProperty.SCRIPT_X_WITH_COMMON) { 975 return sc==scriptX; 976 } 977 978 char[] scriptExtensions=UCharacterProperty.INSTANCE.m_scriptExtensions_; 979 int scx=scriptX&UCharacterProperty.SCRIPT_MASK_; // index into scriptExtensions 980 if(scriptX>=UCharacterProperty.SCRIPT_X_WITH_OTHER) { 981 scx=scriptExtensions[scx+1]; 982 } 983 if(sc>0x7fff) { 984 // Guard against bogus input that would 985 // make us go past the Script_Extensions terminator. 986 return false; 987 } 988 while(sc>scriptExtensions[scx]) { 989 ++scx; 990 } 991 return sc==(scriptExtensions[scx]&0x7fff); 992 } 993 994 /** 995 * Sets code point c's Script_Extensions as script code integers into the output BitSet. 996 * <ul> 997 * <li>If c does have Script_Extensions, then the return value is 998 * the negative number of Script_Extensions codes (= -set.cardinality()); 999 * in this case, the Script property value 1000 * (normally Common or Inherited) is not included in the set. 1001 * <li>If c does not have Script_Extensions, then the one Script code is put into the set 1002 * and also returned. 1003 * <li>If c is not a valid code point, then the one {@link #UNKNOWN} code is put into the set 1004 * and also returned. 1005 * </ul> 1006 * In other words, if the return value is non-negative, it is c's single Script code 1007 * and the set contains exactly this Script code. 1008 * If the return value is -n, then the set contains c's n>=2 Script_Extensions script codes. 1009 * 1010 * <p>Some characters are commonly used in multiple scripts. 1011 * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 1012 * 1013 * @param c code point 1014 * @param set set of script code integers; will be cleared, then bits are set 1015 * corresponding to c's Script_Extensions 1016 * @return negative number of script codes in c's Script_Extensions, 1017 * or the non-negative single Script value 1018 */ 1019 public static final int getScriptExtensions(int c, BitSet set) { 1020 set.clear(); 1021 int scriptX=UCharacterProperty.INSTANCE.getAdditional(c, 0)&UCharacterProperty.SCRIPT_X_MASK; 1022 if(scriptX<UCharacterProperty.SCRIPT_X_WITH_COMMON) { 1023 set.set(scriptX); 1024 return scriptX; 1025 } 1026 1027 char[] scriptExtensions=UCharacterProperty.INSTANCE.m_scriptExtensions_; 1028 int scx=scriptX&UCharacterProperty.SCRIPT_MASK_; // index into scriptExtensions 1029 if(scriptX>=UCharacterProperty.SCRIPT_X_WITH_OTHER) { 1030 scx=scriptExtensions[scx+1]; 1031 } 1032 int length=0; 1033 int sx; 1034 do { 1035 sx=scriptExtensions[scx++]; 1036 set.set(sx&0x7fff); 1037 ++length; 1038 } while(sx<0x8000); 1039 // length==set.cardinality() 1040 return -length; 1041 } 1042 1043 /** 1044 * Returns the long Unicode script name, if there is one. 1045 * Otherwise returns the 4-letter ISO 15924 script code. 1046 * Returns "Malayam" given MALAYALAM. 1047 * 1048 * @param scriptCode int script code 1049 * @return long script name as given in PropertyValueAliases.txt, or the 4-letter code 1050 * @throws IllegalArgumentException if the script code is not valid 1051 */ 1052 public static final String getName(int scriptCode){ 1053 return UCharacter.getPropertyValueName(UProperty.SCRIPT, 1054 scriptCode, 1055 UProperty.NameChoice.LONG); 1056 } 1057 1058 /** 1059 * Returns the 4-letter ISO 15924 script code, 1060 * which is the same as the short Unicode script name if Unicode has names for the script. 1061 * Returns "Mlym" given MALAYALAM. 1062 * 1063 * @param scriptCode int script code 1064 * @return short script name (4-letter code) 1065 * @throws IllegalArgumentException if the script code is not valid 1066 */ 1067 public static final String getShortName(int scriptCode){ 1068 return UCharacter.getPropertyValueName(UProperty.SCRIPT, 1069 scriptCode, 1070 UProperty.NameChoice.SHORT); 1071 } 1072 1073 /** 1074 * Script metadata (script properties). 1075 * See http://unicode.org/cldr/trac/browser/trunk/common/properties/scriptMetadata.txt 1076 */ 1077 private static final class ScriptMetadata { 1078 // 0 = NOT_ENCODED, no sample character, default false script properties. 1079 // Bits 20.. 0: sample character 1080 1081 // Bits 23..21: usage 1082 private static final int UNKNOWN = 1 << 21; 1083 private static final int EXCLUSION = 2 << 21; 1084 private static final int LIMITED_USE = 3 << 21; 1085 private static final int ASPIRATIONAL = 4 << 21; 1086 private static final int RECOMMENDED = 5 << 21; 1087 1088 // Bits 31..24: Single-bit flags 1089 private static final int RTL = 1 << 24; 1090 private static final int LB_LETTERS = 1 << 25; 1091 private static final int CASED = 1 << 26; 1092 1093 private static final int SCRIPT_PROPS[] = { 1094 // Begin copy-paste output from 1095 // tools/trunk/unicode/py/parsescriptmetadata.py 1096 // or from icu/trunk/source/common/uscript_props.cpp 1097 0x0040 | RECOMMENDED, // Zyyy 1098 0x0308 | RECOMMENDED, // Zinh 1099 0x0628 | RECOMMENDED | RTL, // Arab 1100 0x0531 | RECOMMENDED | CASED, // Armn 1101 0x0995 | RECOMMENDED, // Beng 1102 0x3105 | RECOMMENDED | LB_LETTERS, // Bopo 1103 0x13C4 | LIMITED_USE | CASED, // Cher 1104 0x03E2 | EXCLUSION | CASED, // Copt 1105 0x042F | RECOMMENDED | CASED, // Cyrl 1106 0x10414 | EXCLUSION | CASED, // Dsrt 1107 0x0905 | RECOMMENDED, // Deva 1108 0x12A0 | RECOMMENDED, // Ethi 1109 0x10D3 | RECOMMENDED, // Geor 1110 0x10330 | EXCLUSION, // Goth 1111 0x03A9 | RECOMMENDED | CASED, // Grek 1112 0x0A95 | RECOMMENDED, // Gujr 1113 0x0A15 | RECOMMENDED, // Guru 1114 0x5B57 | RECOMMENDED | LB_LETTERS, // Hani 1115 0xAC00 | RECOMMENDED, // Hang 1116 0x05D0 | RECOMMENDED | RTL, // Hebr 1117 0x304B | RECOMMENDED | LB_LETTERS, // Hira 1118 0x0C95 | RECOMMENDED, // Knda 1119 0x30AB | RECOMMENDED | LB_LETTERS, // Kana 1120 0x1780 | RECOMMENDED | LB_LETTERS, // Khmr 1121 0x0EA5 | RECOMMENDED | LB_LETTERS, // Laoo 1122 0x004C | RECOMMENDED | CASED, // Latn 1123 0x0D15 | RECOMMENDED, // Mlym 1124 0x1826 | ASPIRATIONAL, // Mong 1125 0x1000 | RECOMMENDED | LB_LETTERS, // Mymr 1126 0x168F | EXCLUSION, // Ogam 1127 0x10300 | EXCLUSION, // Ital 1128 0x0B15 | RECOMMENDED, // Orya 1129 0x16A0 | EXCLUSION, // Runr 1130 0x0D85 | RECOMMENDED, // Sinh 1131 0x0710 | LIMITED_USE | RTL, // Syrc 1132 0x0B95 | RECOMMENDED, // Taml 1133 0x0C15 | RECOMMENDED, // Telu 1134 0x078C | RECOMMENDED | RTL, // Thaa 1135 0x0E17 | RECOMMENDED | LB_LETTERS, // Thai 1136 0x0F40 | RECOMMENDED, // Tibt 1137 0x14C0 | ASPIRATIONAL, // Cans 1138 0xA288 | ASPIRATIONAL | LB_LETTERS, // Yiii 1139 0x1703 | EXCLUSION, // Tglg 1140 0x1723 | EXCLUSION, // Hano 1141 0x1743 | EXCLUSION, // Buhd 1142 0x1763 | EXCLUSION, // Tagb 1143 0x280E | UNKNOWN, // Brai 1144 0x10800 | EXCLUSION | RTL, // Cprt 1145 0x1900 | LIMITED_USE, // Limb 1146 0x10000 | EXCLUSION, // Linb 1147 0x10480 | EXCLUSION, // Osma 1148 0x10450 | EXCLUSION, // Shaw 1149 0x1950 | LIMITED_USE | LB_LETTERS, // Tale 1150 0x10380 | EXCLUSION, // Ugar 1151 0, 1152 0x1A00 | EXCLUSION, // Bugi 1153 0x2C00 | EXCLUSION | CASED, // Glag 1154 0x10A00 | EXCLUSION | RTL, // Khar 1155 0xA800 | LIMITED_USE, // Sylo 1156 0x1980 | LIMITED_USE | LB_LETTERS, // Talu 1157 0x2D30 | ASPIRATIONAL, // Tfng 1158 0x103A0 | EXCLUSION, // Xpeo 1159 0x1B05 | LIMITED_USE, // Bali 1160 0x1BC0 | LIMITED_USE, // Batk 1161 0, 1162 0x11005 | EXCLUSION, // Brah 1163 0xAA00 | LIMITED_USE, // Cham 1164 0, 1165 0, 1166 0, 1167 0, 1168 0x13153 | EXCLUSION, // Egyp 1169 0, 1170 0x5B57 | RECOMMENDED | LB_LETTERS, // Hans 1171 0x5B57 | RECOMMENDED | LB_LETTERS, // Hant 1172 0x16B1C | EXCLUSION, // Hmng 1173 0x10CA1 | EXCLUSION | RTL | CASED, // Hung 1174 0, 1175 0xA984 | LIMITED_USE, // Java 1176 0xA90A | LIMITED_USE, // Kali 1177 0, 1178 0, 1179 0x1C00 | LIMITED_USE, // Lepc 1180 0x10647 | EXCLUSION, // Lina 1181 0x0840 | LIMITED_USE | RTL, // Mand 1182 0, 1183 0x10980 | EXCLUSION | RTL, // Mero 1184 0x07CA | LIMITED_USE | RTL, // Nkoo 1185 0x10C00 | EXCLUSION | RTL, // Orkh 1186 0x1036B | EXCLUSION, // Perm 1187 0xA840 | EXCLUSION, // Phag 1188 0x10900 | EXCLUSION | RTL, // Phnx 1189 0x16F00 | ASPIRATIONAL, // Plrd 1190 0, 1191 0, 1192 0, 1193 0, 1194 0, 1195 0, 1196 0xA549 | LIMITED_USE, // Vaii 1197 0, 1198 0x12000 | EXCLUSION, // Xsux 1199 0, 1200 0xFDD0 | UNKNOWN, // Zzzz 1201 0x102A0 | EXCLUSION, // Cari 1202 0x304B | RECOMMENDED | LB_LETTERS, // Jpan 1203 0x1A20 | LIMITED_USE | LB_LETTERS, // Lana 1204 0x10280 | EXCLUSION, // Lyci 1205 0x10920 | EXCLUSION | RTL, // Lydi 1206 0x1C5A | LIMITED_USE, // Olck 1207 0xA930 | EXCLUSION, // Rjng 1208 0xA882 | LIMITED_USE, // Saur 1209 0x1D850 | EXCLUSION, // Sgnw 1210 0x1B83 | LIMITED_USE, // Sund 1211 0, 1212 0xABC0 | LIMITED_USE, // Mtei 1213 0x10840 | EXCLUSION | RTL, // Armi 1214 0x10B00 | EXCLUSION | RTL, // Avst 1215 0x11103 | LIMITED_USE, // Cakm 1216 0xAC00 | RECOMMENDED, // Kore 1217 0x11083 | EXCLUSION, // Kthi 1218 0x10AD8 | EXCLUSION | RTL, // Mani 1219 0x10B60 | EXCLUSION | RTL, // Phli 1220 0x10B8F | EXCLUSION | RTL, // Phlp 1221 0, 1222 0x10B40 | EXCLUSION | RTL, // Prti 1223 0x0800 | EXCLUSION | RTL, // Samr 1224 0xAA80 | LIMITED_USE | LB_LETTERS, // Tavt 1225 0, 1226 0, 1227 0xA6A0 | LIMITED_USE, // Bamu 1228 0xA4D0 | LIMITED_USE, // Lisu 1229 0, 1230 0x10A60 | EXCLUSION | RTL, // Sarb 1231 0x16AE6 | EXCLUSION, // Bass 1232 0x1BC20 | EXCLUSION, // Dupl 1233 0x10500 | EXCLUSION, // Elba 1234 0x11315 | EXCLUSION, // Gran 1235 0, 1236 0, 1237 0x1E802 | EXCLUSION | RTL, // Mend 1238 0x109A0 | EXCLUSION | RTL, // Merc 1239 0x10A95 | EXCLUSION | RTL, // Narb 1240 0x10896 | EXCLUSION | RTL, // Nbat 1241 0x10873 | EXCLUSION | RTL, // Palm 1242 0x112BE | EXCLUSION, // Sind 1243 0x118B4 | EXCLUSION | CASED, // Wara 1244 0, 1245 0, 1246 0x16A4F | EXCLUSION, // Mroo 1247 0, 1248 0x11183 | EXCLUSION, // Shrd 1249 0x110D0 | EXCLUSION, // Sora 1250 0x11680 | EXCLUSION, // Takr 1251 0x18229 | EXCLUSION | LB_LETTERS, // Tang 1252 0, 1253 0x14400 | EXCLUSION, // Hluw 1254 0x11208 | EXCLUSION, // Khoj 1255 0x11484 | EXCLUSION, // Tirh 1256 0x10537 | EXCLUSION, // Aghb 1257 0x11152 | EXCLUSION, // Mahj 1258 0x11717 | EXCLUSION | LB_LETTERS, // Ahom 1259 0x108F4 | EXCLUSION | RTL, // Hatr 1260 0x1160E | EXCLUSION, // Modi 1261 0x1128F | EXCLUSION, // Mult 1262 0x11AC0 | EXCLUSION, // Pauc 1263 0x1158E | EXCLUSION, // Sidd 1264 0x1E909 | LIMITED_USE | RTL | CASED, // Adlm 1265 0x11C0E | EXCLUSION, // Bhks 1266 0x11C72 | EXCLUSION, // Marc 1267 0x11412 | LIMITED_USE, // Newa 1268 0x104B5 | LIMITED_USE | CASED, // Osge 1269 0x5B57 | RECOMMENDED | LB_LETTERS, // Hanb 1270 0x1112 | RECOMMENDED, // Jamo 1271 0, 1272 // End copy-paste from parsescriptmetadata.py 1273 }; 1274 1275 private static final int getScriptProps(int script) { 1276 if (0 <= script && script < SCRIPT_PROPS.length) { 1277 return SCRIPT_PROPS[script]; 1278 } else { 1279 return 0; 1280 } 1281 } 1282 } 1283 1284 /** 1285 * Script usage constants. 1286 * See UAX #31 Unicode Identifier and Pattern Syntax. 1287 * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers 1288 */ 1289 public enum ScriptUsage { 1290 /** 1291 * Not encoded in Unicode. 1292 */ 1293 NOT_ENCODED, 1294 /** 1295 * Unknown script usage. 1296 */ 1297 UNKNOWN, 1298 /** 1299 * Candidate for Exclusion from Identifiers. 1300 */ 1301 EXCLUDED, 1302 /** 1303 * Limited Use script. 1304 */ 1305 LIMITED_USE, 1306 /** 1307 * Aspirational Use script. 1308 */ 1309 ASPIRATIONAL, 1310 /** 1311 * Recommended script. 1312 */ 1313 RECOMMENDED 1314 } 1315 private static final ScriptUsage[] usageValues = ScriptUsage.values(); 1316 1317 /** 1318 * Returns the script sample character string. 1319 * This string normally consists of one code point but might be longer. 1320 * The string is empty if the script is not encoded. 1321 * 1322 * @param script script code 1323 * @return the sample character string 1324 */ 1325 public static final String getSampleString(int script) { 1326 int sampleChar = ScriptMetadata.getScriptProps(script) & 0x1fffff; 1327 if(sampleChar != 0) { 1328 return new StringBuilder().appendCodePoint(sampleChar).toString(); 1329 } 1330 return ""; 1331 } 1332 1333 /** 1334 * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax. 1335 * Returns {@link ScriptUsage#NOT_ENCODED} if the script is not encoded in Unicode. 1336 * 1337 * @param script script code 1338 * @return script usage 1339 * @see ScriptUsage 1340 */ 1341 public static final ScriptUsage getUsage(int script) { 1342 return usageValues[(ScriptMetadata.getScriptProps(script) >> 21) & 7]; 1343 } 1344 1345 /** 1346 * Returns true if the script is written right-to-left. 1347 * For example, Arab and Hebr. 1348 * 1349 * @param script script code 1350 * @return true if the script is right-to-left 1351 */ 1352 public static final boolean isRightToLeft(int script) { 1353 return (ScriptMetadata.getScriptProps(script) & ScriptMetadata.RTL) != 0; 1354 } 1355 1356 /** 1357 * Returns true if the script allows line breaks between letters (excluding hyphenation). 1358 * Such a script typically requires dictionary-based line breaking. 1359 * For example, Hani and Thai. 1360 * 1361 * @param script script code 1362 * @return true if the script allows line breaks between letters 1363 */ 1364 public static final boolean breaksBetweenLetters(int script) { 1365 return (ScriptMetadata.getScriptProps(script) & ScriptMetadata.LB_LETTERS) != 0; 1366 } 1367 1368 /** 1369 * Returns true if in modern (or most recent) usage of the script case distinctions are customary. 1370 * For example, Latn and Cyrl. 1371 * 1372 * @param script script code 1373 * @return true if the script is cased 1374 */ 1375 public static final boolean isCased(int script) { 1376 return (ScriptMetadata.getScriptProps(script) & ScriptMetadata.CASED) != 0; 1377 } 1378 1379 ///CLOVER:OFF 1380 /** 1381 * Private Constructor. Never default construct 1382 */ 1383 private UScript(){} 1384 ///CLOVER:ON 1385 } 1386
