i18nutil/source/utility/unicode.cxx

   1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
   2 /*
   3  * This file is part of the LibreOffice project.
   4  *
   5  * This Source Code Form is subject to the terms of the Mozilla Public
   6  * License, v. 2.0. If a copy of the MPL was not distributed with this
   7  * file, You can obtain one at http://mozilla.org/MPL/2.0/.
   8  *
   9  * This file incorporates work covered by the following license notice:
  10  *
  11  *   Licensed to the Apache Software Foundation (ASF) under one or more
  12  *   contributor license agreements. See the NOTICE file distributed
  13  *   with this work for additional information regarding copyright
  14  *   ownership. The ASF licenses this file to you under the Apache
  15  *   License, Version 2.0 (the "License"); you may not use this file
  16  *   except in compliance with the License. You may obtain a copy of
  17  *   the License at http://www.apache.org/licenses/LICENSE-2.0 .
  18  */
  19
  20 #include <com/sun/star/i18n/UnicodeType.hpp>
  21 #include <com/sun/star/i18n/KCharacterType.hpp>
  22 #include <com/sun/star/i18n/ScriptType.hpp>
  23 #include <i18nutil/unicode.hxx>
  24 #include "unicode_data.h"
  25
  26 // Workaround for glibc braindamage:
  27 // glibc 2.4's langinfo.h does "#define CURRENCY_SYMBOL __CURRENCY_SYMBOL"
  28 // which (obviously) breaks UnicodeType::CURRENCY_SYMBOL
  29 #undef CURRENCY_SYMBOL
  30
  31 using namespace ::com::sun::star::i18n;
  32
  33 static ScriptTypeList defaultTypeList[] = {
  34     { UnicodeScript_kBasicLatin,
  35       UnicodeScript_kBasicLatin,
  36       UnicodeScript_kBasicLatin },      // 0,
  37     { UnicodeScript_kLatin1Supplement,
  38       UnicodeScript_kLatin1Supplement,
  39       UnicodeScript_kLatin1Supplement },// 1,
  40     { UnicodeScript_kLatinExtendedA,
  41       UnicodeScript_kLatinExtendedA,
  42       UnicodeScript_kLatinExtendedA }, // 2,
  43     { UnicodeScript_kLatinExtendedB,
  44       UnicodeScript_kLatinExtendedB,
  45       UnicodeScript_kLatinExtendedB }, // 3,
  46     { UnicodeScript_kIPAExtension,
  47       UnicodeScript_kIPAExtension,
  48       UnicodeScript_kIPAExtension }, // 4,
  49     { UnicodeScript_kSpacingModifier,
  50       UnicodeScript_kSpacingModifier,
  51       UnicodeScript_kSpacingModifier }, // 5,
  52     { UnicodeScript_kCombiningDiacritical,
  53       UnicodeScript_kCombiningDiacritical,
  54       UnicodeScript_kCombiningDiacritical }, // 6,
  55     { UnicodeScript_kGreek,
  56       UnicodeScript_kGreek,
  57       UnicodeScript_kGreek }, // 7,
  58     { UnicodeScript_kCyrillic,
  59       UnicodeScript_kCyrillic,
  60       UnicodeScript_kCyrillic }, // 8,
  61     { UnicodeScript_kArmenian,
  62       UnicodeScript_kArmenian,
  63       UnicodeScript_kArmenian }, // 9,
  64     { UnicodeScript_kHebrew,
  65       UnicodeScript_kHebrew,
  66       UnicodeScript_kHebrew }, // 10,
  67     { UnicodeScript_kArabic,
  68       UnicodeScript_kArabic,
  69       UnicodeScript_kArabic }, // 11,
  70     { UnicodeScript_kSyriac,
  71       UnicodeScript_kSyriac,
  72       UnicodeScript_kSyriac }, // 12,
  73     { UnicodeScript_kThaana,
  74       UnicodeScript_kThaana,
  75       UnicodeScript_kThaana }, // 13,
  76     { UnicodeScript_kDevanagari,
  77       UnicodeScript_kDevanagari,
  78       UnicodeScript_kDevanagari }, // 14,
  79     { UnicodeScript_kBengali,
  80       UnicodeScript_kBengali,
  81       UnicodeScript_kBengali }, // 15,
  82     { UnicodeScript_kGurmukhi,
  83       UnicodeScript_kGurmukhi,
  84       UnicodeScript_kGurmukhi }, // 16,
  85     { UnicodeScript_kGujarati,
  86       UnicodeScript_kGujarati,
  87       UnicodeScript_kGujarati }, // 17,
  88     { UnicodeScript_kOriya,
  89       UnicodeScript_kOriya,
  90       UnicodeScript_kOriya }, // 18,
  91     { UnicodeScript_kTamil,
  92       UnicodeScript_kTamil,
  93       UnicodeScript_kTamil }, // 19,
  94     { UnicodeScript_kTelugu,
  95       UnicodeScript_kTelugu,
  96       UnicodeScript_kTelugu }, // 20,
  97     { UnicodeScript_kKannada,
  98       UnicodeScript_kKannada,
  99       UnicodeScript_kKannada }, // 21,
 100     { UnicodeScript_kMalayalam,
 101       UnicodeScript_kMalayalam,
 102       UnicodeScript_kMalayalam }, // 22,
 103     { UnicodeScript_kSinhala,
 104       UnicodeScript_kSinhala,
 105       UnicodeScript_kSinhala }, // 23,
 106     { UnicodeScript_kThai,
 107       UnicodeScript_kThai,
 108       UnicodeScript_kThai }, // 24,
 109     { UnicodeScript_kLao,
 110       UnicodeScript_kLao,
 111       UnicodeScript_kLao }, // 25,
 112     { UnicodeScript_kTibetan,
 113       UnicodeScript_kTibetan,
 114       UnicodeScript_kTibetan }, // 26,
 115     { UnicodeScript_kMyanmar,
 116       UnicodeScript_kMyanmar,
 117       UnicodeScript_kMyanmar }, // 27,
 118     { UnicodeScript_kGeorgian,
 119       UnicodeScript_kGeorgian,
 120       UnicodeScript_kGeorgian }, // 28,
 121     { UnicodeScript_kHangulJamo,
 122       UnicodeScript_kHangulJamo,
 123       UnicodeScript_kHangulJamo }, // 29,
 124     { UnicodeScript_kEthiopic,
 125       UnicodeScript_kEthiopic,
 126       UnicodeScript_kEthiopic }, // 30,
 127     { UnicodeScript_kCherokee,
 128       UnicodeScript_kCherokee,
 129       UnicodeScript_kCherokee }, // 31,
 130     { UnicodeScript_kUnifiedCanadianAboriginalSyllabics,
 131       UnicodeScript_kUnifiedCanadianAboriginalSyllabics,
 132       UnicodeScript_kUnifiedCanadianAboriginalSyllabics }, // 32,
 133     { UnicodeScript_kOgham,
 134       UnicodeScript_kOgham,
 135       UnicodeScript_kOgham }, // 33,
 136     { UnicodeScript_kRunic,
 137       UnicodeScript_kRunic,
 138       UnicodeScript_kRunic }, // 34,
 139     { UnicodeScript_kKhmer,
 140       UnicodeScript_kKhmer,
 141       UnicodeScript_kKhmer }, // 35,
 142     { UnicodeScript_kMongolian,
 143       UnicodeScript_kMongolian,
 144       UnicodeScript_kMongolian }, // 36,
 145     { UnicodeScript_kLatinExtendedAdditional,
 146       UnicodeScript_kLatinExtendedAdditional,
 147       UnicodeScript_kLatinExtendedAdditional }, // 37,
 148     { UnicodeScript_kGreekExtended,
 149       UnicodeScript_kGreekExtended,
 150       UnicodeScript_kGreekExtended }, // 38,
 151     { UnicodeScript_kGeneralPunctuation,
 152       UnicodeScript_kGeneralPunctuation,
 153       UnicodeScript_kGeneralPunctuation }, // 39,
 154     { UnicodeScript_kSuperSubScript,
 155       UnicodeScript_kSuperSubScript,
 156       UnicodeScript_kSuperSubScript }, // 40,
 157     { UnicodeScript_kCurrencySymbolScript,
 158       UnicodeScript_kCurrencySymbolScript,
 159       UnicodeScript_kCurrencySymbolScript }, // 41,
 160     { UnicodeScript_kSymbolCombiningMark,
 161       UnicodeScript_kSymbolCombiningMark,
 162       UnicodeScript_kSymbolCombiningMark }, // 42,
 163     { UnicodeScript_kLetterlikeSymbol,
 164       UnicodeScript_kLetterlikeSymbol,
 165       UnicodeScript_kLetterlikeSymbol }, // 43,
 166     { UnicodeScript_kNumberForm,
 167       UnicodeScript_kNumberForm,
 168       UnicodeScript_kNumberForm }, // 44,
 169     { UnicodeScript_kArrow,
 170       UnicodeScript_kArrow,
 171       UnicodeScript_kArrow }, // 45,
 172     { UnicodeScript_kMathOperator,
 173       UnicodeScript_kMathOperator,
 174       UnicodeScript_kMathOperator }, // 46,
 175     { UnicodeScript_kMiscTechnical,
 176       UnicodeScript_kMiscTechnical,
 177       UnicodeScript_kMiscTechnical }, // 47,
 178     { UnicodeScript_kControlPicture,
 179       UnicodeScript_kControlPicture,
 180       UnicodeScript_kControlPicture }, // 48,
 181     { UnicodeScript_kOpticalCharacter,
 182       UnicodeScript_kOpticalCharacter,
 183       UnicodeScript_kOpticalCharacter }, // 49,
 184     { UnicodeScript_kEnclosedAlphanumeric,
 185       UnicodeScript_kEnclosedAlphanumeric,
 186       UnicodeScript_kEnclosedAlphanumeric }, // 50,
 187     { UnicodeScript_kBoxDrawing,
 188       UnicodeScript_kBoxDrawing,
 189       UnicodeScript_kBoxDrawing }, // 51,
 190     { UnicodeScript_kBlockElement,
 191       UnicodeScript_kBlockElement,
 192       UnicodeScript_kBlockElement }, // 52,
 193     { UnicodeScript_kGeometricShape,
 194       UnicodeScript_kGeometricShape,
 195       UnicodeScript_kGeometricShape }, // 53,
 196     { UnicodeScript_kMiscSymbol,
 197       UnicodeScript_kMiscSymbol,
 198       UnicodeScript_kMiscSymbol }, // 54,
 199     { UnicodeScript_kDingbat,
 200       UnicodeScript_kDingbat,
 201       UnicodeScript_kDingbat }, // 55,
 202     { UnicodeScript_kBraillePatterns,
 203       UnicodeScript_kBraillePatterns,
 204       UnicodeScript_kBraillePatterns }, // 56,
 205     { UnicodeScript_kCJKRadicalsSupplement,
 206       UnicodeScript_kCJKRadicalsSupplement,
 207       UnicodeScript_kCJKRadicalsSupplement }, // 57,
 208     { UnicodeScript_kKangxiRadicals,
 209       UnicodeScript_kKangxiRadicals,
 210       UnicodeScript_kKangxiRadicals }, // 58,
 211     { UnicodeScript_kIdeographicDescriptionCharacters,
 212       UnicodeScript_kIdeographicDescriptionCharacters,
 213       UnicodeScript_kIdeographicDescriptionCharacters }, // 59,
 214     { UnicodeScript_kCJKSymbolPunctuation,
 215       UnicodeScript_kCJKSymbolPunctuation,
 216       UnicodeScript_kCJKSymbolPunctuation }, // 60,
 217     { UnicodeScript_kHiragana,
 218       UnicodeScript_kHiragana,
 219       UnicodeScript_kHiragana }, // 61,
 220     { UnicodeScript_kKatakana,
 221       UnicodeScript_kKatakana,
 222       UnicodeScript_kKatakana }, // 62,
 223     { UnicodeScript_kBopomofo,
 224       UnicodeScript_kBopomofo,
 225       UnicodeScript_kBopomofo }, // 63,
 226     { UnicodeScript_kHangulCompatibilityJamo,
 227       UnicodeScript_kHangulCompatibilityJamo,
 228       UnicodeScript_kHangulCompatibilityJamo }, // 64,
 229     { UnicodeScript_kKanbun,
 230       UnicodeScript_kKanbun,
 231       UnicodeScript_kKanbun }, // 65,
 232     { UnicodeScript_kBopomofoExtended,
 233       UnicodeScript_kBopomofoExtended,
 234       UnicodeScript_kBopomofoExtended }, // 66,
 235     { UnicodeScript_kEnclosedCJKLetterMonth,
 236       UnicodeScript_kEnclosedCJKLetterMonth,
 237       UnicodeScript_kEnclosedCJKLetterMonth }, // 67,
 238     { UnicodeScript_kCJKCompatibility,
 239       UnicodeScript_kCJKCompatibility,
 240       UnicodeScript_kCJKCompatibility }, // 68,
 241     { UnicodeScript_k_CJKUnifiedIdeographsExtensionA,
 242       UnicodeScript_k_CJKUnifiedIdeographsExtensionA,
 243       UnicodeScript_k_CJKUnifiedIdeographsExtensionA }, // 69,
 244     { UnicodeScript_kCJKUnifiedIdeograph,
 245       UnicodeScript_kCJKUnifiedIdeograph,
 246       UnicodeScript_kCJKUnifiedIdeograph }, // 70,
 247     { UnicodeScript_kYiSyllables,
 248       UnicodeScript_kYiSyllables,
 249       UnicodeScript_kYiSyllables }, // 71,
 250     { UnicodeScript_kYiRadicals,
 251       UnicodeScript_kYiRadicals,
 252       UnicodeScript_kYiRadicals }, // 72,
 253     { UnicodeScript_kHangulSyllable,
 254       UnicodeScript_kHangulSyllable,
 255       UnicodeScript_kHangulSyllable }, // 73,
 256     { UnicodeScript_kHighSurrogate,
 257       UnicodeScript_kHighSurrogate,
 258       UnicodeScript_kHighSurrogate }, // 74,
 259     { UnicodeScript_kHighPrivateUseSurrogate,
 260       UnicodeScript_kHighPrivateUseSurrogate,
 261       UnicodeScript_kHighPrivateUseSurrogate }, // 75,
 262     { UnicodeScript_kLowSurrogate,
 263       UnicodeScript_kLowSurrogate,
 264       UnicodeScript_kLowSurrogate }, // 76,
 265     { UnicodeScript_kPrivateUse,
 266       UnicodeScript_kPrivateUse,
 267       UnicodeScript_kPrivateUse }, // 77,
 268     { UnicodeScript_kCJKCompatibilityIdeograph,
 269       UnicodeScript_kCJKCompatibilityIdeograph,
 270       UnicodeScript_kCJKCompatibilityIdeograph }, // 78,
 271     { UnicodeScript_kAlphabeticPresentation,
 272       UnicodeScript_kAlphabeticPresentation,
 273       UnicodeScript_kAlphabeticPresentation }, // 79,
 274     { UnicodeScript_kArabicPresentationA,
 275       UnicodeScript_kArabicPresentationA,
 276       UnicodeScript_kArabicPresentationA }, // 80,
 277     { UnicodeScript_kCombiningHalfMark,
 278       UnicodeScript_kCombiningHalfMark,
 279       UnicodeScript_kCombiningHalfMark }, // 81,
 280     { UnicodeScript_kCJKCompatibilityForm,
 281       UnicodeScript_kCJKCompatibilityForm,
 282       UnicodeScript_kCJKCompatibilityForm }, // 82,
 283     { UnicodeScript_kSmallFormVariant,
 284       UnicodeScript_kSmallFormVariant,
 285       UnicodeScript_kSmallFormVariant }, // 83,
 286     { UnicodeScript_kArabicPresentationB,
 287       UnicodeScript_kArabicPresentationB,
 288       UnicodeScript_kArabicPresentationB }, // 84,
 289     { UnicodeScript_kNoScript,
 290       UnicodeScript_kNoScript,
 291       UnicodeScript_kNoScript }, // 85,
 292     { UnicodeScript_kHalfwidthFullwidthForm,
 293       UnicodeScript_kHalfwidthFullwidthForm,
 294       UnicodeScript_kHalfwidthFullwidthForm }, // 86,
 295     { UnicodeScript_kScriptCount,
 296       UnicodeScript_kScriptCount,
 297       UnicodeScript_kNoScript } // 87,
 298 };
 299
 300 sal_Int16 SAL_CALL
 301 unicode::getUnicodeScriptType( const sal_Unicode ch, ScriptTypeList* typeList, sal_Int16 unknownType ) {
 302
 303     if (!typeList) {
 304         typeList = defaultTypeList;
 305         unknownType = UnicodeScript_kNoScript;
 306     }
 307
 308     sal_Int16 i = 0, type = typeList[0].to;
 309     while (type < UnicodeScript_kScriptCount && ch > UnicodeScriptType[type][UnicodeScriptTypeTo]) {
 310         type = typeList[++i].to;
 311     }
 312
 313     return (type < UnicodeScript_kScriptCount &&
 314             ch >= UnicodeScriptType[typeList[i].from][UnicodeScriptTypeFrom]) ?
 315             typeList[i].value : unknownType;
 316 }
 317
 318 sal_Unicode SAL_CALL
 319 unicode::getUnicodeScriptStart( UnicodeScript type) {
 320     return UnicodeScriptType[type][UnicodeScriptTypeFrom];
 321 }
 322
 323 sal_Unicode SAL_CALL
 324 unicode::getUnicodeScriptEnd( UnicodeScript type) {
 325     return UnicodeScriptType[type][UnicodeScriptTypeTo];
 326 }
 327
 328 sal_Int16 SAL_CALL
 329 unicode::getUnicodeType( const sal_Unicode ch ) {
 330     static sal_Unicode c = 0x00;
 331     static sal_Int16 r = 0x00;
 332
 333     if (ch == c) return r;
 334     else c = ch;
 335
 336     sal_Int16 address = UnicodeTypeIndex[ch >> 8];
 337     return r = (sal_Int16)((address < UnicodeTypeNumberBlock) ? UnicodeTypeBlockValue[address] :
 338         UnicodeTypeValue[((address - UnicodeTypeNumberBlock) << 8) + (ch & 0xff)]);
 339 }
 340
 341 sal_uInt8 SAL_CALL
 342 unicode::getUnicodeDirection( const sal_Unicode ch ) {
 343     static sal_Unicode c = 0x00;
 344     static sal_uInt8 r = 0x00;
 345
 346     if (ch == c) return r;
 347     else c = ch;
 348
 349     sal_Int16 address = UnicodeDirectionIndex[ch >> 8];
 350     return r = ((address < UnicodeDirectionNumberBlock) ? UnicodeDirectionBlockValue[address] :
 351         UnicodeDirectionValue[((address - UnicodeDirectionNumberBlock) << 8) + (ch & 0xff)]);
 352
 353 }
 354
 355 #define bit(name)   (1 << name)
 356
 357 #define UPPERMASK   bit(UnicodeType::UPPERCASE_LETTER)
 358
 359 #define LOWERMASK   bit(UnicodeType::LOWERCASE_LETTER)
 360
 361 #define TITLEMASK   bit(UnicodeType::TITLECASE_LETTER)
 362
 363 #define DIGITMASK   bit(UnicodeType::DECIMAL_DIGIT_NUMBER)|\
 364             bit(UnicodeType::LETTER_NUMBER)|\
 365             bit(UnicodeType::OTHER_NUMBER)
 366
 367 #define ALPHAMASK   UPPERMASK|LOWERMASK|TITLEMASK|\
 368             bit(UnicodeType::MODIFIER_LETTER)|\
 369             bit(UnicodeType::OTHER_LETTER)
 370
 371 #define BASEMASK    DIGITMASK|ALPHAMASK|\
 372             bit(UnicodeType::NON_SPACING_MARK)|\
 373             bit(UnicodeType::ENCLOSING_MARK)|\
 374             bit(UnicodeType::COMBINING_SPACING_MARK)
 375
 376 #define SPACEMASK   bit(UnicodeType::SPACE_SEPARATOR)|\
 377             bit(UnicodeType::LINE_SEPARATOR)|\
 378             bit(UnicodeType::PARAGRAPH_SEPARATOR)
 379
 380 #define PUNCTUATIONMASK bit(UnicodeType::DASH_PUNCTUATION)|\
 381             bit(UnicodeType::INITIAL_PUNCTUATION)|\
 382             bit(UnicodeType::FINAL_PUNCTUATION)|\
 383             bit(UnicodeType::CONNECTOR_PUNCTUATION)|\
 384             bit(UnicodeType::OTHER_PUNCTUATION)
 385
 386 #define SYMBOLMASK  bit(UnicodeType::MATH_SYMBOL)|\
 387             bit(UnicodeType::CURRENCY_SYMBOL)|\
 388             bit(UnicodeType::MODIFIER_SYMBOL)|\
 389             bit(UnicodeType::OTHER_SYMBOL)
 390
 391 #define PRINTMASK   BASEMASK|SPACEMASK|PUNCTUATIONMASK|SYMBOLMASK
 392
 393 #define CONTROLMASK bit(UnicodeType::CONTROL)|\
 394             bit(UnicodeType::FORMAT)|\
 395             bit(UnicodeType::LINE_SEPARATOR)|\
 396             bit(UnicodeType::PARAGRAPH_SEPARATOR)
 397
 398 #define IsType(func, mask)  \
 399 sal_Bool SAL_CALL func( const sal_Unicode ch) {\
 400     return (bit(getUnicodeType(ch)) & (mask)) != 0;\
 401 }
 402
 403 IsType(unicode::isUpper, UPPERMASK)
 404 IsType(unicode::isLower, LOWERMASK)
 405 IsType(unicode::isControl, CONTROLMASK)
 406 IsType(unicode::isPrint, PRINTMASK)
 407 IsType(unicode::isAlpha, ALPHAMASK)
 408 IsType(unicode::isDigit, DIGITMASK)
 409 IsType(unicode::isAlphaDigit, ALPHAMASK|DIGITMASK)
 410 IsType(unicode::isSpace, SPACEMASK)
 411
 412 #define CONTROLSPACE    bit(0x09)|bit(0x0a)|bit(0x0b)|bit(0x0c)|bit(0x0d)|\
 413             bit(0x1c)|bit(0x1d)|bit(0x1e)|bit(0x1f)
 414
 415 sal_Bool SAL_CALL unicode::isWhiteSpace( const sal_Unicode ch) {
 416     return (ch != 0xa0 && isSpace(ch)) || (ch <= 0x1F && (bit(ch) & (CONTROLSPACE)));
 417 }
 418
 419 sal_Int16 SAL_CALL unicode::getScriptClassFromUScriptCode(UScriptCode eScript)
 420 {
 421     //See unicode/uscript.h
 422     static sal_Int16 scriptTypes[] =
 423     {
 424         ScriptType::WEAK, ScriptType::WEAK, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX,
 425         ScriptType::ASIAN, ScriptType::LATIN, ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX,
 426         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::LATIN, ScriptType::LATIN,
 427     // 15
 428         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::ASIAN, ScriptType::ASIAN, ScriptType::COMPLEX,
 429         ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::COMPLEX,
 430         ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN,
 431     // 30
 432         ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX,
 433         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 434         ScriptType::LATIN, ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 435     // 45
 436         ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX,
 437         ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN,
 438         ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 439     // 60
 440         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 441         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX,
 442         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::ASIAN, ScriptType::ASIAN,
 443     // 75
 444         ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 445         ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 446         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 447     // 90
 448         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 449         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 450         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::WEAK, ScriptType::WEAK, ScriptType::COMPLEX,
 451     // 105
 452         ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 453         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 454         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::ASIAN,
 455     // 120
 456         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 457         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::WEAK, ScriptType::WEAK,
 458         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 459     // 135
 460         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 461         ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX,
 462         ScriptType::COMPLEX,
 463         ScriptType::WEAK
 464     };
 465
 466     sal_Int16 nRet;
 467     if (eScript < USCRIPT_COMMON)
 468         nRet = ScriptType::WEAK;
 469     else if (static_cast<size_t>(eScript) >= SAL_N_ELEMENTS(scriptTypes))
 470         nRet = ScriptType::COMPLEX;         // anything new is going to be pretty wild
 471     else
 472         nRet = scriptTypes[eScript];
 473     return nRet;
 474 }
 475
 476 OString SAL_CALL unicode::getExemplerLanguageForUScriptCode(UScriptCode eScript)
 477 {
 478     OString sRet;
 479     switch (eScript)
 480     {
 481         case USCRIPT_CODE_LIMIT:
 482         case USCRIPT_INVALID_CODE:
 483             sRet = "zxx";
 484             break;
 485         case USCRIPT_COMMON:
 486         case USCRIPT_INHERITED:
 487             sRet = "und";
 488             break;
 489         case USCRIPT_MATHEMATICAL_NOTATION:
 490         case USCRIPT_SYMBOLS:
 491             sRet = "zxx";
 492             break;
 493         case USCRIPT_UNWRITTEN_LANGUAGES:
 494         case USCRIPT_UNKNOWN:
 495             sRet = "und";
 496             break;
 497         case USCRIPT_NABATAEAN: //no language with an assigned code yet
 498             sRet = "mis";
 499             break;
 500         case USCRIPT_PALMYRENE: //no language with an assigned code yet
 501             sRet = "mis";
 502             break;
 503         case USCRIPT_ARABIC:
 504             sRet = "ar";
 505             break;
 506         case USCRIPT_ARMENIAN:
 507             sRet = "hy";
 508             break;
 509         case USCRIPT_BENGALI:
 510             sRet = "bn";
 511             break;
 512         case USCRIPT_BOPOMOFO:
 513             sRet = "zh";
 514             break;
 515         case USCRIPT_CHEROKEE:
 516             sRet = "chr";
 517             break;
 518         case USCRIPT_COPTIC:
 519             sRet = "cop";
 520             break;
 521         case USCRIPT_CYRILLIC:
 522             sRet = "ru";
 523             break;
 524         case USCRIPT_DESERET:
 525             sRet = "en";
 526             break;
 527         case USCRIPT_DEVANAGARI:
 528             sRet = "hi";
 529             break;
 530         case USCRIPT_ETHIOPIC:
 531             sRet = "am";
 532             break;
 533         case USCRIPT_GEORGIAN:
 534             sRet = "ka";
 535             break;
 536         case USCRIPT_GOTHIC:
 537             sRet = "got";
 538             break;
 539         case USCRIPT_GREEK:
 540             sRet = "el";
 541             break;
 542         case USCRIPT_GUJARATI:
 543             sRet = "gu";
 544             break;
 545         case USCRIPT_GURMUKHI:
 546             sRet = "pa";
 547             break;
 548         case USCRIPT_HAN:
 549             sRet = "zh";
 550             break;
 551         case USCRIPT_HANGUL:
 552             sRet = "ko";
 553             break;
 554         case USCRIPT_HEBREW:
 555             sRet = "hr";
 556             break;
 557         case USCRIPT_HIRAGANA:
 558             sRet = "ja";
 559             break;
 560         case USCRIPT_KANNADA:
 561             sRet = "kn";
 562             break;
 563         case USCRIPT_KATAKANA:
 564             sRet = "ja";
 565             break;
 566         case USCRIPT_KHMER:
 567             sRet = "km";
 568             break;
 569         case USCRIPT_LAO:
 570             sRet = "lo";
 571             break;
 572         case USCRIPT_LATIN:
 573             sRet = "en";
 574             break;
 575         case USCRIPT_MALAYALAM:
 576             sRet = "ml";
 577             break;
 578         case USCRIPT_MONGOLIAN:
 579             sRet = "mn";
 580             break;
 581         case USCRIPT_MYANMAR:
 582             sRet = "my";
 583             break;
 584         case USCRIPT_OGHAM:
 585             sRet = "pgl";
 586             break;
 587         case USCRIPT_OLD_ITALIC:
 588             sRet = "osc";
 589             break;
 590         case USCRIPT_ORIYA:
 591             sRet = "or";
 592             break;
 593         case USCRIPT_RUNIC:
 594             sRet = "ang";
 595             break;
 596         case USCRIPT_SINHALA:
 597             sRet = "si";
 598             break;
 599         case USCRIPT_SYRIAC:
 600             sRet = "syr";
 601             break;
 602         case USCRIPT_TAMIL:
 603             sRet = "ta";
 604             break;
 605         case USCRIPT_TELUGU:
 606             sRet = "te";
 607             break;
 608         case USCRIPT_THAANA:
 609             sRet = "dv";
 610             break;
 611         case USCRIPT_THAI:
 612             sRet = "th";
 613             break;
 614         case USCRIPT_TIBETAN:
 615             sRet = "bo";
 616             break;
 617         case USCRIPT_CANADIAN_ABORIGINAL:
 618             sRet = "iu";
 619             break;
 620         case USCRIPT_YI:
 621             sRet = "ii";
 622             break;
 623         case USCRIPT_TAGALOG:
 624             sRet = "tl";
 625             break;
 626         case USCRIPT_HANUNOO:
 627             sRet = "hnn";
 628             break;
 629         case USCRIPT_BUHID:
 630             sRet = "bku";
 631             break;
 632         case USCRIPT_TAGBANWA:
 633             sRet = "tbw";
 634             break;
 635         case USCRIPT_BRAILLE:
 636             sRet = "en";
 637             break;
 638         case USCRIPT_CYPRIOT:
 639             sRet = "ecy";
 640             break;
 641         case USCRIPT_LIMBU:
 642             sRet = "lif";
 643             break;
 644         case USCRIPT_LINEAR_B:
 645             sRet = "gmy";
 646             break;
 647         case USCRIPT_OSMANYA:
 648             sRet = "so";
 649             break;
 650         case USCRIPT_SHAVIAN:
 651             sRet = "en";
 652             break;
 653         case USCRIPT_TAI_LE:
 654             sRet = "tdd";
 655             break;
 656         case USCRIPT_UGARITIC:
 657             sRet = "uga";
 658             break;
 659         case USCRIPT_KATAKANA_OR_HIRAGANA:
 660             sRet = "ja";
 661             break;
 662         case USCRIPT_BUGINESE:
 663             sRet = "bug";
 664             break;
 665         case USCRIPT_GLAGOLITIC:
 666             sRet = "ch";
 667             break;
 668         case USCRIPT_KHAROSHTHI:
 669             sRet = "pra";
 670             break;
 671         case USCRIPT_SYLOTI_NAGRI:
 672             sRet = "syl";
 673             break;
 674         case USCRIPT_NEW_TAI_LUE:
 675             sRet = "khb";
 676             break;
 677         case USCRIPT_TIFINAGH:
 678             sRet = "tmh";
 679             break;
 680         case USCRIPT_OLD_PERSIAN:
 681             sRet = "peo";
 682             break;
 683         case USCRIPT_BALINESE:
 684             sRet = "ban";
 685             break;
 686         case USCRIPT_BATAK:
 687             sRet = "btk";
 688             break;
 689         case USCRIPT_BLISSYMBOLS:
 690             sRet = "en";
 691             break;
 692         case USCRIPT_BRAHMI:
 693             sRet = "pra";
 694             break;
 695         case USCRIPT_CHAM:
 696             sRet = "cja";
 697             break;
 698         case USCRIPT_CIRTH:
 699             sRet = "sjn";
 700             break;
 701         case USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC:
 702             sRet = "cu";
 703             break;
 704         case USCRIPT_DEMOTIC_EGYPTIAN:
 705         case USCRIPT_HIERATIC_EGYPTIAN:
 706         case USCRIPT_EGYPTIAN_HIEROGLYPHS:
 707             sRet = "egy";
 708             break;
 709         case USCRIPT_KHUTSURI:
 710             sRet = "ka";
 711             break;
 712         case USCRIPT_SIMPLIFIED_HAN:
 713             sRet = "zh";
 714             break;
 715         case USCRIPT_TRADITIONAL_HAN:
 716             sRet = "zh";
 717             break;
 718         case USCRIPT_PAHAWH_HMONG:
 719             sRet = "blu";
 720             break;
 721         case USCRIPT_OLD_HUNGARIAN:
 722             sRet = "ohu";
 723             break;
 724         case USCRIPT_HARAPPAN_INDUS:
 725             sRet = "xiv";
 726             break;
 727         case USCRIPT_JAVANESE:
 728             sRet = "kaw";
 729             break;
 730         case USCRIPT_KAYAH_LI:
 731             sRet = "eky";
 732             break;
 733         case USCRIPT_LATIN_FRAKTUR:
 734             sRet = "de";
 735             break;
 736         case USCRIPT_LATIN_GAELIC:
 737             sRet = "ga";
 738             break;
 739         case USCRIPT_LEPCHA:
 740             sRet = "lep";
 741             break;
 742         case USCRIPT_LINEAR_A:
 743             sRet = "ecr";
 744             break;
 745         case USCRIPT_MANDAIC:
 746             sRet = "mic";
 747             break;
 748         case USCRIPT_MAYAN_HIEROGLYPHS:
 749             sRet = "myn";
 750             break;
 751         case USCRIPT_MEROITIC:
 752             sRet = "xmr";
 753             break;
 754         case USCRIPT_NKO:
 755             sRet = "nqo";
 756             break;
 757         case USCRIPT_ORKHON:
 758             sRet = "otk";
 759             break;
 760         case USCRIPT_OLD_PERMIC:
 761             sRet = "kv";
 762             break;
 763         case USCRIPT_PHAGS_PA:
 764             sRet = "xng";
 765             break;
 766         case USCRIPT_PHOENICIAN:
 767             sRet = "phn";
 768             break;
 769         case USCRIPT_PHONETIC_POLLARD:
 770             sRet = "hmd";
 771             break;
 772         case USCRIPT_RONGORONGO:
 773             sRet = "rap";
 774             break;
 775         case USCRIPT_SARATI:
 776             sRet = "qya";
 777             break;
 778         case USCRIPT_ESTRANGELO_SYRIAC:
 779             sRet = "syr";
 780             break;
 781         case USCRIPT_WESTERN_SYRIAC:
 782             sRet = "tru";
 783             break;
 784         case USCRIPT_EASTERN_SYRIAC:
 785             sRet = "aii";
 786             break;
 787         case USCRIPT_TENGWAR:
 788             sRet = "sjn";
 789             break;
 790         case USCRIPT_VAI:
 791             sRet = "vai";
 792             break;
 793         case USCRIPT_VISIBLE_SPEECH:
 794             sRet = "en";
 795             break;
 796         case USCRIPT_CUNEIFORM:
 797             sRet = "akk";
 798             break;
 799         case USCRIPT_CARIAN:
 800             sRet = "xcr";
 801             break;
 802         case USCRIPT_JAPANESE:
 803             sRet = "ja";
 804             break;
 805         case USCRIPT_LANNA:
 806             sRet = "nod";
 807             break;
 808         case USCRIPT_LYCIAN:
 809             sRet = "xlc";
 810             break;
 811         case USCRIPT_LYDIAN:
 812             sRet = "xld";
 813             break;
 814         case USCRIPT_OL_CHIKI:
 815             sRet = "sat";
 816             break;
 817         case USCRIPT_REJANG:
 818             sRet = "rej";
 819             break;
 820         case USCRIPT_SAURASHTRA:
 821             sRet = "saz";
 822             break;
 823         case USCRIPT_SIGN_WRITING:
 824             sRet = "en";
 825             break;
 826         case USCRIPT_SUNDANESE:
 827             sRet = "su";
 828             break;
 829         case USCRIPT_MOON:
 830             sRet = "en";
 831             break;
 832         case USCRIPT_MEITEI_MAYEK:
 833             sRet = "mni";
 834             break;
 835         case USCRIPT_IMPERIAL_ARAMAIC:
 836             sRet = "arc";
 837             break;
 838         case USCRIPT_AVESTAN:
 839             sRet = "ae";
 840             break;
 841         case USCRIPT_CHAKMA:
 842             sRet = "ccp";
 843             break;
 844         case USCRIPT_KOREAN:
 845             sRet = "ko";
 846             break;
 847         case USCRIPT_KAITHI:
 848             sRet = "awa";
 849             break;
 850         case USCRIPT_MANICHAEAN:
 851             sRet = "xmn";
 852             break;
 853         case USCRIPT_INSCRIPTIONAL_PAHLAVI:
 854         case USCRIPT_PSALTER_PAHLAVI:
 855         case USCRIPT_BOOK_PAHLAVI:
 856         case USCRIPT_INSCRIPTIONAL_PARTHIAN:
 857             sRet = "xpr";
 858             break;
 859         case USCRIPT_SAMARITAN:
 860             sRet = "heb";
 861             break;
 862         case USCRIPT_TAI_VIET:
 863             sRet = "blt";
 864             break;
 865         case USCRIPT_BAMUM:
 866             sRet = "bax";
 867             break;
 868         case USCRIPT_LISU:
 869             sRet = "lis";
 870             break;
 871         case USCRIPT_NAKHI_GEBA:
 872             sRet = "nxq";
 873             break;
 874         case USCRIPT_OLD_SOUTH_ARABIAN:
 875             sRet = "xsa";
 876             break;
 877         case USCRIPT_BASSA_VAH:
 878             sRet = "bsq";
 879             break;
 880         case USCRIPT_DUPLOYAN_SHORTAND:
 881             sRet = "fr";
 882             break;
 883         case USCRIPT_ELBASAN:
 884             sRet = "sq";
 885             break;
 886         case USCRIPT_GRANTHA:
 887             sRet = "ta";
 888             break;
 889         case USCRIPT_KPELLE:
 890             sRet = "kpe";
 891             break;
 892         case USCRIPT_LOMA:
 893             sRet = "lom";
 894             break;
 895         case USCRIPT_MENDE:
 896             sRet = "men";
 897             break;
 898         case USCRIPT_MEROITIC_CURSIVE:
 899             sRet = "xmr";
 900             break;
 901         case USCRIPT_OLD_NORTH_ARABIAN:
 902             sRet = "xna";
 903             break;
 904         case USCRIPT_SINDHI:
 905             sRet = "sd";
 906             break;
 907         case USCRIPT_WARANG_CITI:
 908             sRet = "hoc";
 909             break;
 910 #if (U_ICU_VERSION_MAJOR_NUM > 4) || (U_ICU_VERSION_MAJOR_NUM == 4 && U_ICU_VERSION_MINOR_NUM >= 8)
 911         case USCRIPT_AFAKA:
 912             sRet = "djk";
 913             break;
 914         case USCRIPT_JURCHEN:
 915             sRet = "juc";
 916             break;
 917         case USCRIPT_MRO:
 918             sRet = "cmr";
 919             break;
 920         case USCRIPT_NUSHU: //no language with an assigned code yet
 921             sRet = "mis";
 922             break;
 923         case USCRIPT_SHARADA:
 924             sRet = "sa";
 925             break;
 926         case USCRIPT_SORA_SOMPENG:
 927             sRet = "srb";
 928             break;
 929         case USCRIPT_TAKRI:
 930             sRet = "doi";
 931             break;
 932         case USCRIPT_TANGUT:
 933             sRet = "txg";
 934             break;
 935         case USCRIPT_WOLEAI:
 936             sRet = "woe";
 937             break;
 938 #endif
 939 #if (U_ICU_VERSION_MAJOR_NUM > 4)
 940         case USCRIPT_ANATOLIAN_HIEROGLYPHS:
 941             sRet = "hlu";
 942             break;
 943         case USCRIPT_KHOJKI:
 944             sRet = "gu";
 945             break;
 946         case USCRIPT_TIRHUTA:
 947             sRet = "mai";
 948             break;
 949 #endif
 950     }
 951     return sRet;
 952 }
 953
 954 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */