1 /******************************************************************** 2 * Copyright (c) 1997-2013, International Business Machines 3 * Corporation and others. All Rights Reserved. 4 ********************************************************************/ 5 6 #include <string.h> 7 #include "unicode/utypes.h" 8 #include "unicode/uscript.h" 9 #include "unicode/uchar.h" 10 #include "cintltst.h" 11 #include "cucdapi.h" 12 13 #define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof(array[0])) 14 15 void TestUScriptCodeAPI(){ 16 int i =0; 17 int numErrors =0; 18 { 19 const char* testNames[]={ 20 /* test locale */ 21 "en", "en_US", "sr", "ta" , "te_IN", 22 "hi", "he", "ar", 23 /* test abbr */ 24 "Hani", "Hang","Hebr","Hira", 25 "Knda","Kana","Khmr","Lao", 26 "Latn",/*"Latf","Latg",*/ 27 "Mlym", "Mong", 28 29 /* test names */ 30 "CYRILLIC","DESERET","DEVANAGARI","ETHIOPIC","GEORGIAN", 31 "GOTHIC", "GREEK", "GUJARATI", "COMMON", "INHERITED", 32 /* test lower case names */ 33 "malayalam", "mongolian", "myanmar", "ogham", "old-italic", 34 "oriya", "runic", "sinhala", "syriac","tamil", 35 "telugu", "thaana", "thai", "tibetan", 36 /* test the bounds*/ 37 "tagb", "arabic", 38 /* test bogus */ 39 "asfdasd", "5464", "12235", 40 /* test the last index */ 41 "zyyy", "YI", 42 '\0' 43 }; 44 UScriptCode expected[] ={ 45 /* locales should return */ 46 USCRIPT_LATIN, USCRIPT_LATIN, USCRIPT_CYRILLIC, USCRIPT_TAMIL, USCRIPT_TELUGU, 47 USCRIPT_DEVANAGARI, USCRIPT_HEBREW, USCRIPT_ARABIC, 48 /* abbr should return */ 49 USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA, 50 USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO, 51 USCRIPT_LATIN,/* USCRIPT_LATIN, USCRIPT_LATIN,*/ 52 USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN, 53 /* names should return */ 54 USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN, 55 USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI, USCRIPT_COMMON, USCRIPT_INHERITED, 56 /* lower case names should return */ 57 USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN, USCRIPT_MYANMAR, USCRIPT_OGHAM, USCRIPT_OLD_ITALIC, 58 USCRIPT_ORIYA, USCRIPT_RUNIC, USCRIPT_SINHALA, USCRIPT_SYRIAC, USCRIPT_TAMIL, 59 USCRIPT_TELUGU, USCRIPT_THAANA, USCRIPT_THAI, USCRIPT_TIBETAN, 60 /* bounds */ 61 USCRIPT_TAGBANWA, USCRIPT_ARABIC, 62 /* bogus names should return invalid code */ 63 USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE, USCRIPT_INVALID_CODE, 64 USCRIPT_COMMON, USCRIPT_YI, 65 }; 66 67 UErrorCode err = U_ZERO_ERROR; 68 69 const int32_t capacity = 10; 70 71 for( ; testNames[i]!='\0'; i++){ 72 UScriptCode script[10]={USCRIPT_INVALID_CODE}; 73 uscript_getCode(testNames[i],script,capacity, &err); 74 if( script[0] != expected[i]){ 75 log_data_err("Error getting script code Got: %i Expected: %i for name %s (Error code does not propagate if data is not present. Are you missing data?)\n", 76 script[0],expected[i],testNames[i]); 77 numErrors++; 78 } 79 } 80 if(numErrors >0 ){ 81 log_data_err("Errors uchar_getScriptCode() : %i \n",numErrors); 82 } 83 } 84 85 { 86 UErrorCode err = U_ZERO_ERROR; 87 int32_t capacity=0; 88 int32_t j; 89 UScriptCode jaCode[]={USCRIPT_KATAKANA, USCRIPT_HIRAGANA, USCRIPT_HAN }; 90 UScriptCode script[10]={USCRIPT_INVALID_CODE}; 91 int32_t num = uscript_getCode("ja",script,capacity, &err); 92 /* preflight */ 93 if(err==U_BUFFER_OVERFLOW_ERROR){ 94 err = U_ZERO_ERROR; 95 capacity = 10; 96 num = uscript_getCode("ja",script,capacity, &err); 97 if(num!=(sizeof(jaCode)/sizeof(UScriptCode))){ 98 log_err("Errors uscript_getScriptCode() for Japanese locale: num=%d, expected %d \n", 99 num, (sizeof(jaCode)/sizeof(UScriptCode))); 100 } 101 for(j=0;j<sizeof(jaCode)/sizeof(UScriptCode);j++) { 102 if(script[j]!=jaCode[j]) { 103 log_err("Japanese locale: code #%d was %d (%s) but expected %d (%s)\n", j, 104 script[j], uscript_getName(script[j]), 105 jaCode[j], uscript_getName(jaCode[j])); 106 107 } 108 } 109 }else{ 110 log_data_err("Errors in uscript_getScriptCode() expected error : %s got: %s \n", 111 "U_BUFFER_OVERFLOW_ERROR", 112 u_errorName(err)); 113 } 114 115 } 116 117 { 118 UScriptCode testAbbr[]={ 119 /* names should return */ 120 USCRIPT_CYRILLIC, USCRIPT_DESERET, USCRIPT_DEVANAGARI, USCRIPT_ETHIOPIC, USCRIPT_GEORGIAN, 121 USCRIPT_GOTHIC, USCRIPT_GREEK, USCRIPT_GUJARATI, 122 }; 123 124 const char* expectedNames[]={ 125 126 /* test names */ 127 "Cyrillic","Deseret","Devanagari","Ethiopic","Georgian", 128 "Gothic", "Greek", "Gujarati", 129 '\0' 130 }; 131 i=0; 132 while(i<sizeof(testAbbr)/sizeof(UScriptCode)){ 133 const char* name = uscript_getName(testAbbr[i]); 134 if(name == NULL) { 135 log_data_err("Couldn't get script name\n"); 136 return; 137 } 138 numErrors=0; 139 if(strcmp(expectedNames[i],name)!=0){ 140 log_err("Error getting abbreviations Got: %s Expected: %s\n",name,expectedNames[i]); 141 numErrors++; 142 } 143 if(numErrors > 0){ 144 if(numErrors >0 ){ 145 log_err("Errors uchar_getScriptAbbr() : %i \n",numErrors); 146 } 147 } 148 i++; 149 } 150 151 } 152 153 { 154 UScriptCode testAbbr[]={ 155 /* abbr should return */ 156 USCRIPT_HAN, USCRIPT_HANGUL, USCRIPT_HEBREW, USCRIPT_HIRAGANA, 157 USCRIPT_KANNADA, USCRIPT_KATAKANA, USCRIPT_KHMER, USCRIPT_LAO, 158 USCRIPT_LATIN, 159 USCRIPT_MALAYALAM, USCRIPT_MONGOLIAN, 160 }; 161 162 const char* expectedAbbr[]={ 163 /* test abbr */ 164 "Hani", "Hang","Hebr","Hira", 165 "Knda","Kana","Khmr","Laoo", 166 "Latn", 167 "Mlym", "Mong", 168 '\0' 169 }; 170 i=0; 171 while(i<sizeof(testAbbr)/sizeof(UScriptCode)){ 172 const char* name = uscript_getShortName(testAbbr[i]); 173 numErrors=0; 174 if(strcmp(expectedAbbr[i],name)!=0){ 175 log_err("Error getting abbreviations Got: %s Expected: %s\n",name,expectedAbbr[i]); 176 numErrors++; 177 } 178 if(numErrors > 0){ 179 if(numErrors >0 ){ 180 log_err("Errors uchar_getScriptAbbr() : %i \n",numErrors); 181 } 182 } 183 i++; 184 } 185 186 } 187 /* now test uscript_getScript() API */ 188 { 189 uint32_t codepoints[] = { 190 0x0000FF9D, /* USCRIPT_KATAKANA*/ 191 0x0000FFBE, /* USCRIPT_HANGUL*/ 192 0x0000FFC7, /* USCRIPT_HANGUL*/ 193 0x0000FFCF, /* USCRIPT_HANGUL*/ 194 0x0000FFD7, /* USCRIPT_HANGUL*/ 195 0x0000FFDC, /* USCRIPT_HANGUL*/ 196 0x00010300, /* USCRIPT_OLD_ITALIC*/ 197 0x00010330, /* USCRIPT_GOTHIC*/ 198 0x0001034A, /* USCRIPT_GOTHIC*/ 199 0x00010400, /* USCRIPT_DESERET*/ 200 0x00010428, /* USCRIPT_DESERET*/ 201 0x0001D167, /* USCRIPT_INHERITED*/ 202 0x0001D17B, /* USCRIPT_INHERITED*/ 203 0x0001D185, /* USCRIPT_INHERITED*/ 204 0x0001D1AA, /* USCRIPT_INHERITED*/ 205 0x00020000, /* USCRIPT_HAN*/ 206 0x00000D02, /* USCRIPT_MALAYALAM*/ 207 0x00000D00, /* USCRIPT_UNKNOWN (new Zzzz value in Unicode 5.0) */ 208 0x00000000, /* USCRIPT_COMMON*/ 209 0x0001D169, /* USCRIPT_INHERITED*/ 210 0x0001D182, /* USCRIPT_INHERITED*/ 211 0x0001D18B, /* USCRIPT_INHERITED*/ 212 0x0001D1AD, /* USCRIPT_INHERITED*/ 213 }; 214 215 UScriptCode expected[] = { 216 USCRIPT_KATAKANA , 217 USCRIPT_HANGUL , 218 USCRIPT_HANGUL , 219 USCRIPT_HANGUL , 220 USCRIPT_HANGUL , 221 USCRIPT_HANGUL , 222 USCRIPT_OLD_ITALIC, 223 USCRIPT_GOTHIC , 224 USCRIPT_GOTHIC , 225 USCRIPT_DESERET , 226 USCRIPT_DESERET , 227 USCRIPT_INHERITED, 228 USCRIPT_INHERITED, 229 USCRIPT_INHERITED, 230 USCRIPT_INHERITED, 231 USCRIPT_HAN , 232 USCRIPT_MALAYALAM, 233 USCRIPT_UNKNOWN, 234 USCRIPT_COMMON, 235 USCRIPT_INHERITED , 236 USCRIPT_INHERITED , 237 USCRIPT_INHERITED , 238 USCRIPT_INHERITED , 239 }; 240 UScriptCode code = USCRIPT_INVALID_CODE; 241 UErrorCode status = U_ZERO_ERROR; 242 UBool passed = TRUE; 243 244 for(i=0; i<LENGTHOF(codepoints); ++i){ 245 code = uscript_getScript(codepoints[i],&status); 246 if(U_SUCCESS(status)){ 247 if( code != expected[i] || 248 code != (UScriptCode)u_getIntPropertyValue(codepoints[i], UCHAR_SCRIPT) 249 ) { 250 log_err("uscript_getScript for codepoint \\U%08X failed\n",codepoints[i]); 251 passed = FALSE; 252 } 253 }else{ 254 log_err("uscript_getScript for codepoint \\U%08X failed. Error: %s\n", 255 codepoints[i],u_errorName(status)); 256 break; 257 } 258 } 259 260 if(passed==FALSE){ 261 log_err("uscript_getScript failed.\n"); 262 } 263 } 264 { 265 UScriptCode code= USCRIPT_INVALID_CODE; 266 UErrorCode status = U_ZERO_ERROR; 267 code = uscript_getScript(0x001D169,&status); 268 if(code != USCRIPT_INHERITED){ 269 log_err("\\U001D169 is not contained in USCRIPT_INHERITED"); 270 } 271 } 272 { 273 UScriptCode code= USCRIPT_INVALID_CODE; 274 UErrorCode status = U_ZERO_ERROR; 275 int32_t err = 0; 276 277 for(i = 0; i<=0x10ffff; i++){ 278 code = uscript_getScript(i,&status); 279 if(code == USCRIPT_INVALID_CODE){ 280 err++; 281 log_err("uscript_getScript for codepoint \\U%08X failed.\n", i); 282 } 283 } 284 if(err>0){ 285 log_err("uscript_getScript failed for %d codepoints\n", err); 286 } 287 } 288 { 289 for(i=0; (UScriptCode)i< USCRIPT_CODE_LIMIT; i++){ 290 const char* name = uscript_getName((UScriptCode)i); 291 if(name==NULL || strcmp(name,"")==0){ 292 log_err("uscript_getName failed for code %i: name is NULL or \"\"\n",i); 293 } 294 } 295 } 296 297 { 298 /* 299 * These script codes were originally added to ICU pre-3.6, so that ICU would 300 * have all ISO 15924 script codes. ICU was then based on Unicode 4.1. 301 * These script codes were added with only short names because we don't 302 * want to invent long names ourselves. 303 * Unicode 5 and later encode some of these scripts and give them long names. 304 * Whenever this happens, the long script names here need to be updated. 305 */ 306 static const char* expectedLong[] = { 307 "Balinese", "Batak", "Blis", "Brahmi", "Cham", "Cirt", "Cyrs", "Egyd", "Egyh", "Egyptian_Hieroglyphs", 308 "Geok", "Hans", "Hant", "Hmng", "Hung", "Inds", "Javanese", "Kayah_Li", "Latf", "Latg", 309 "Lepcha", "Lina", "Mandaic", "Maya", "Meroitic_Hieroglyphs", "Nko", "Old_Turkic", "Perm", "Phags_Pa", "Phoenician", 310 "Miao", "Roro", "Sara", "Syre", "Syrj", "Syrn", "Teng", "Vai", "Visp", "Cuneiform", 311 "Zxxx", "Unknown", 312 "Carian", "Jpan", "Tai_Tham", "Lycian", "Lydian", "Ol_Chiki", "Rejang", "Saurashtra", "Sgnw", "Sundanese", 313 "Moon", "Meetei_Mayek", 314 /* new in ICU 4.0 */ 315 "Imperial_Aramaic", "Avestan", "Chakma", "Kore", 316 "Kaithi", "Mani", "Inscriptional_Pahlavi", "Phlp", "Phlv", "Inscriptional_Parthian", "Samaritan", "Tai_Viet", 317 "Zmth", "Zsym", 318 /* new in ICU 4.4 */ 319 "Bamum", "Lisu", "Nkgb", "Old_South_Arabian", 320 /* new in ICU 4.6 */ 321 "Bass", "Dupl", "Elba", "Gran", "Kpel", "Loma", "Mend", "Meroitic_Cursive", 322 "Narb", "Nbat", "Palm", "Sind", "Wara", 323 /* new in ICU 4.8 */ 324 "Afak", "Jurc", "Mroo", "Nshu", "Sharada", "Sora_Sompeng", "Takri", "Tang", "Wole", 325 /* new in ICU 49 */ 326 "Hluw", "Khoj", "Tirh", 327 }; 328 static const char* expectedShort[] = { 329 "Bali", "Batk", "Blis", "Brah", "Cham", "Cirt", "Cyrs", "Egyd", "Egyh", "Egyp", 330 "Geok", "Hans", "Hant", "Hmng", "Hung", "Inds", "Java", "Kali", "Latf", "Latg", 331 "Lepc", "Lina", "Mand", "Maya", "Mero", "Nkoo", "Orkh", "Perm", "Phag", "Phnx", 332 "Plrd", "Roro", "Sara", "Syre", "Syrj", "Syrn", "Teng", "Vaii", "Visp", "Xsux", 333 "Zxxx", "Zzzz", 334 "Cari", "Jpan", "Lana", "Lyci", "Lydi", "Olck", "Rjng", "Saur", "Sgnw", "Sund", 335 "Moon", "Mtei", 336 /* new in ICU 4.0 */ 337 "Armi", "Avst", "Cakm", "Kore", 338 "Kthi", "Mani", "Phli", "Phlp", "Phlv", "Prti", "Samr", "Tavt", 339 "Zmth", "Zsym", 340 /* new in ICU 4.4 */ 341 "Bamu", "Lisu", "Nkgb", "Sarb", 342 /* new in ICU 4.6 */ 343 "Bass", "Dupl", "Elba", "Gran", "Kpel", "Loma", "Mend", "Merc", 344 "Narb", "Nbat", "Palm", "Sind", "Wara", 345 /* new in ICU 4.8 */ 346 "Afak", "Jurc", "Mroo", "Nshu", "Shrd", "Sora", "Takr", "Tang", "Wole", 347 /* new in ICU 49 */ 348 "Hluw", "Khoj", "Tirh", 349 }; 350 int32_t j = 0; 351 if(LENGTHOF(expectedLong)!=(USCRIPT_CODE_LIMIT-USCRIPT_BALINESE)) { 352 log_err("need to add new script codes in cucdapi.c!\n"); 353 return; 354 } 355 for(i=USCRIPT_BALINESE; (UScriptCode)i<USCRIPT_CODE_LIMIT; i++, j++){ 356 const char* name = uscript_getName((UScriptCode)i); 357 if(name==NULL || strcmp(name,expectedLong[j])!=0){ 358 log_err("uscript_getName failed for code %i: %s!=%s\n", i, name, expectedLong[j]); 359 } 360 name = uscript_getShortName((UScriptCode)i); 361 if(name==NULL || strcmp(name,expectedShort[j])!=0){ 362 log_err("uscript_getShortName failed for code %i: %s!=%s\n", i, name, expectedShort[j]); 363 } 364 } 365 for(i=0; i<LENGTHOF(expectedLong); i++){ 366 UScriptCode fillIn[5] = {USCRIPT_INVALID_CODE}; 367 UErrorCode status = U_ZERO_ERROR; 368 int32_t len = 0; 369 len = uscript_getCode(expectedShort[i], fillIn, LENGTHOF(fillIn), &status); 370 if(U_FAILURE(status)){ 371 log_err("uscript_getCode failed for script name %s. Error: %s\n",expectedShort[i], u_errorName(status)); 372 } 373 if(len>1){ 374 log_err("uscript_getCode did not return expected number of codes for script %s. EXPECTED: 1 GOT: %i\n", expectedShort[i], len); 375 } 376 if(fillIn[0]!= (UScriptCode)(USCRIPT_BALINESE+i)){ 377 log_err("uscript_getCode did not return expected code for script %s. EXPECTED: %i GOT: %i\n", expectedShort[i], (USCRIPT_BALINESE+i), fillIn[0] ); 378 } 379 } 380 } 381 382 { 383 /* test characters which have Script_Extensions */ 384 UErrorCode errorCode=U_ZERO_ERROR; 385 if(!( 386 USCRIPT_COMMON==uscript_getScript(0x0640, &errorCode) && 387 USCRIPT_INHERITED==uscript_getScript(0x0650, &errorCode) && 388 USCRIPT_ARABIC==uscript_getScript(0xfdf2, &errorCode)) || 389 U_FAILURE(errorCode) 390 ) { 391 log_err("uscript_getScript(character with Script_Extensions) failed\n"); 392 } 393 } 394 } 395 396 void TestHasScript() { 397 if(!( 398 !uscript_hasScript(0x063f, USCRIPT_COMMON) && 399 uscript_hasScript(0x063f, USCRIPT_ARABIC) && /* main Script value */ 400 !uscript_hasScript(0x063f, USCRIPT_SYRIAC) && 401 !uscript_hasScript(0x063f, USCRIPT_THAANA)) 402 ) { 403 log_err("uscript_hasScript(U+063F, ...) is wrong\n"); 404 } 405 if(!( 406 !uscript_hasScript(0x0640, USCRIPT_COMMON) && /* main Script value */ 407 uscript_hasScript(0x0640, USCRIPT_ARABIC) && 408 uscript_hasScript(0x0640, USCRIPT_SYRIAC) && 409 !uscript_hasScript(0x0640, USCRIPT_THAANA)) 410 ) { 411 log_err("uscript_hasScript(U+0640, ...) is wrong\n"); 412 } 413 if(!( 414 !uscript_hasScript(0x0650, USCRIPT_INHERITED) && /* main Script value */ 415 uscript_hasScript(0x0650, USCRIPT_ARABIC) && 416 uscript_hasScript(0x0650, USCRIPT_SYRIAC) && 417 !uscript_hasScript(0x0650, USCRIPT_THAANA)) 418 ) { 419 log_err("uscript_hasScript(U+0650, ...) is wrong\n"); 420 } 421 if(!( 422 !uscript_hasScript(0x0660, USCRIPT_COMMON) && /* main Script value */ 423 uscript_hasScript(0x0660, USCRIPT_ARABIC) && 424 !uscript_hasScript(0x0660, USCRIPT_SYRIAC) && 425 uscript_hasScript(0x0660, USCRIPT_THAANA)) 426 ) { 427 log_err("uscript_hasScript(U+0660, ...) is wrong\n"); 428 } 429 if(!( 430 !uscript_hasScript(0xfdf2, USCRIPT_COMMON) && 431 uscript_hasScript(0xfdf2, USCRIPT_ARABIC) && /* main Script value */ 432 !uscript_hasScript(0xfdf2, USCRIPT_SYRIAC) && 433 uscript_hasScript(0xfdf2, USCRIPT_THAANA)) 434 ) { 435 log_err("uscript_hasScript(U+FDF2, ...) is wrong\n"); 436 } 437 if(uscript_hasScript(0x0640, 0xaffe)) { 438 /* An unguarded implementation might go into an infinite loop. */ 439 log_err("uscript_hasScript(U+0640, bogus 0xaffe) is wrong\n"); 440 } 441 } 442 443 void TestGetScriptExtensions() { 444 UScriptCode scripts[20]; 445 int32_t length; 446 UErrorCode errorCode; 447 448 /* errors and overflows */ 449 errorCode=U_PARSE_ERROR; 450 length=uscript_getScriptExtensions(0x0640, scripts, LENGTHOF(scripts), &errorCode); 451 if(errorCode!=U_PARSE_ERROR) { 452 log_err("uscript_getScriptExtensions(U+0640, U_PARSE_ERROR) did not preserve the UErrorCode - %s\n", 453 u_errorName(errorCode)); 454 } 455 errorCode=U_ZERO_ERROR; 456 length=uscript_getScriptExtensions(0x0640, NULL, LENGTHOF(scripts), &errorCode); 457 if(errorCode!=U_ILLEGAL_ARGUMENT_ERROR) { 458 log_err("uscript_getScriptExtensions(U+0640, NULL) did not set U_ILLEGAL_ARGUMENT_ERROR - %s\n", 459 u_errorName(errorCode)); 460 } 461 errorCode=U_ZERO_ERROR; 462 length=uscript_getScriptExtensions(0x0640, scripts, -1, &errorCode); 463 if(errorCode!=U_ILLEGAL_ARGUMENT_ERROR) { 464 log_err("uscript_getScriptExtensions(U+0640, capacity<0) did not set U_ILLEGAL_ARGUMENT_ERROR - %s\n", 465 u_errorName(errorCode)); 466 } 467 errorCode=U_ZERO_ERROR; 468 length=uscript_getScriptExtensions(0x0640, scripts, 0, &errorCode); 469 if(errorCode!=U_BUFFER_OVERFLOW_ERROR || length!=3) { 470 log_err("uscript_getScriptExtensions(U+0640, capacity=0: pure preflighting)=%d != 3 - %s\n", 471 (int)length, u_errorName(errorCode)); 472 } 473 errorCode=U_ZERO_ERROR; 474 length=uscript_getScriptExtensions(0x0640, scripts, 1, &errorCode); 475 if(errorCode!=U_BUFFER_OVERFLOW_ERROR || length!=3) { 476 log_err("uscript_getScriptExtensions(U+0640, capacity=1: preflighting)=%d != 3 - %s\n", 477 (int)length, u_errorName(errorCode)); 478 } 479 /* U+063F has only a Script code, no Script_Extensions. */ 480 errorCode=U_ZERO_ERROR; 481 length=uscript_getScriptExtensions(0x063f, scripts, 0, &errorCode); 482 if(errorCode!=U_BUFFER_OVERFLOW_ERROR || length!=1) { 483 log_err("uscript_getScriptExtensions(U+063F, capacity=0)=%d != 1 - %s\n", 484 (int)length, u_errorName(errorCode)); 485 } 486 487 /* invalid code points */ 488 errorCode=U_ZERO_ERROR; 489 length=uscript_getScriptExtensions(-1, scripts, LENGTHOF(scripts), &errorCode); 490 if(U_FAILURE(errorCode) || length!=1 || scripts[0]!=USCRIPT_UNKNOWN) { 491 log_err("uscript_getScriptExtensions(-1)=%d does not return {UNKNOWN} - %s\n", 492 (int)length, u_errorName(errorCode)); 493 } 494 errorCode=U_ZERO_ERROR; 495 length=uscript_getScriptExtensions(0x110000, scripts, LENGTHOF(scripts), &errorCode); 496 if(U_FAILURE(errorCode) || length!=1 || scripts[0]!=USCRIPT_UNKNOWN) { 497 log_err("uscript_getScriptExtensions(0x110000)=%d does not return {UNKNOWN} - %s\n", 498 (int)length, u_errorName(errorCode)); 499 } 500 501 /* normal usage */ 502 errorCode=U_ZERO_ERROR; 503 length=uscript_getScriptExtensions(0x063f, scripts, 1, &errorCode); 504 if(U_FAILURE(errorCode) || length!=1 || scripts[0]!=USCRIPT_ARABIC) { 505 log_err("uscript_getScriptExtensions(U+063F, capacity=1)=%d does not return {ARABIC} - %s\n", 506 (int)length, u_errorName(errorCode)); 507 } 508 errorCode=U_ZERO_ERROR; 509 length=uscript_getScriptExtensions(0x0640, scripts, LENGTHOF(scripts), &errorCode); 510 if(U_FAILURE(errorCode) || length!=3 || 511 scripts[0]!=USCRIPT_ARABIC || scripts[1]!=USCRIPT_SYRIAC || scripts[2]!=USCRIPT_MANDAIC 512 ) { 513 log_err("uscript_getScriptExtensions(U+0640)=%d failed - %s\n", 514 (int)length, u_errorName(errorCode)); 515 } 516 errorCode=U_ZERO_ERROR; 517 length=uscript_getScriptExtensions(0xfdf2, scripts, LENGTHOF(scripts), &errorCode); 518 if(U_FAILURE(errorCode) || length!=2 || scripts[0]!=USCRIPT_ARABIC || scripts[1]!=USCRIPT_THAANA) { 519 log_err("uscript_getScriptExtensions(U+FDF2)=%d failed - %s\n", 520 (int)length, u_errorName(errorCode)); 521 } 522 errorCode=U_ZERO_ERROR; 523 length=uscript_getScriptExtensions(0xff65, scripts, LENGTHOF(scripts), &errorCode); 524 if(U_FAILURE(errorCode) || length!=6 || scripts[0]!=USCRIPT_BOPOMOFO || scripts[5]!=USCRIPT_YI) { 525 log_err("uscript_getScriptExtensions(U+FF65)=%d failed - %s\n", 526 (int)length, u_errorName(errorCode)); 527 } 528 } 529 530 void TestScriptMetadataAPI() { 531 /* API & code coverage. More testing in intltest/ucdtest.cpp. */ 532 UErrorCode errorCode=U_ZERO_ERROR; 533 UChar sample[8]; 534 535 if(uscript_getSampleString(USCRIPT_LATIN, sample, LENGTHOF(sample), &errorCode)!=1 || 536 U_FAILURE(errorCode) || 537 uscript_getScript(sample[0], &errorCode)!=USCRIPT_LATIN || 538 sample[1]!=0) { 539 log_err("uscript_getSampleString(Latn) failed - %s\n", u_errorName(errorCode)); 540 } 541 sample[0]=0xfffe; 542 if(uscript_getSampleString(USCRIPT_LATIN, sample, 0, &errorCode)!=1 || 543 errorCode!=U_BUFFER_OVERFLOW_ERROR || 544 sample[0]!=0xfffe) { 545 log_err("uscript_getSampleString(Latn, capacity=0) failed - %s\n", u_errorName(errorCode)); 546 } 547 errorCode=U_ZERO_ERROR; 548 if(uscript_getSampleString(USCRIPT_INVALID_CODE, sample, LENGTHOF(sample), &errorCode)!=0 || 549 U_FAILURE(errorCode) || 550 sample[0]!=0) { 551 log_err("uscript_getSampleString(invalid) failed - %s\n", u_errorName(errorCode)); 552 } 553 sample[0]=0xfffe; 554 if(uscript_getSampleString(USCRIPT_CODE_LIMIT, sample, 0, &errorCode)!=0 || 555 errorCode!=U_STRING_NOT_TERMINATED_WARNING || 556 sample[0]!=0xfffe) { 557 log_err("uscript_getSampleString(limit, capacity=0) failed - %s\n", u_errorName(errorCode)); 558 } 559 560 if(uscript_getUsage(USCRIPT_LATIN)!=USCRIPT_USAGE_RECOMMENDED || 561 uscript_getUsage(USCRIPT_YI)!=USCRIPT_USAGE_ASPIRATIONAL || 562 uscript_getUsage(USCRIPT_CHEROKEE)!=USCRIPT_USAGE_LIMITED_USE || 563 uscript_getUsage(USCRIPT_COPTIC)!=USCRIPT_USAGE_EXCLUDED || 564 uscript_getUsage(USCRIPT_CIRTH)!=USCRIPT_USAGE_NOT_ENCODED || 565 uscript_getUsage(USCRIPT_INVALID_CODE)!=USCRIPT_USAGE_NOT_ENCODED || 566 uscript_getUsage(USCRIPT_CODE_LIMIT)!=USCRIPT_USAGE_NOT_ENCODED) { 567 log_err("uscript_getUsage() failed\n"); 568 } 569 570 if(uscript_isRightToLeft(USCRIPT_LATIN) || 571 uscript_isRightToLeft(USCRIPT_CIRTH) || 572 !uscript_isRightToLeft(USCRIPT_ARABIC) || 573 !uscript_isRightToLeft(USCRIPT_HEBREW)) { 574 log_err("uscript_isRightToLeft() failed\n"); 575 } 576 577 if(uscript_breaksBetweenLetters(USCRIPT_LATIN) || 578 uscript_breaksBetweenLetters(USCRIPT_CIRTH) || 579 !uscript_breaksBetweenLetters(USCRIPT_HAN) || 580 !uscript_breaksBetweenLetters(USCRIPT_THAI)) { 581 log_err("uscript_breaksBetweenLetters() failed\n"); 582 } 583 584 if(uscript_isCased(USCRIPT_CIRTH) || 585 uscript_isCased(USCRIPT_HAN) || 586 !uscript_isCased(USCRIPT_LATIN) || 587 !uscript_isCased(USCRIPT_GREEK)) { 588 log_err("uscript_isCased() failed\n"); 589 } 590 } 591 592 void TestBinaryValues() { 593 /* 594 * Unicode 5.1 explicitly defines binary property value aliases. 595 * Verify that they are all recognized. 596 */ 597 static const char *const falseValues[]={ "N", "No", "F", "False" }; 598 static const char *const trueValues[]={ "Y", "Yes", "T", "True" }; 599 int32_t i; 600 for(i=0; i<LENGTHOF(falseValues); ++i) { 601 if(FALSE!=u_getPropertyValueEnum(UCHAR_ALPHABETIC, falseValues[i])) { 602 log_data_err("u_getPropertyValueEnum(UCHAR_ALPHABETIC, \"%s\")!=FALSE (Are you missing data?)\n", falseValues[i]); 603 } 604 } 605 for(i=0; i<LENGTHOF(trueValues); ++i) { 606 if(TRUE!=u_getPropertyValueEnum(UCHAR_ALPHABETIC, trueValues[i])) { 607 log_data_err("u_getPropertyValueEnum(UCHAR_ALPHABETIC, \"%s\")!=TRUE (Are you missing data?)\n", trueValues[i]); 608 } 609 } 610 } 611
