1 /******************************************************************** 2 * Copyright (c) 1997-2009, 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", "Batk", "Blis", "Brah", "Cham", "Cirt", "Cyrs", "Egyd", "Egyh", "Egyp", 308 "Geok", "Hans", "Hant", "Hmng", "Hung", "Inds", "Java", "Kayah_Li", "Latf", "Latg", 309 "Lepcha", "Lina", "Mand", "Maya", "Mero", "Nko", "Orkh", "Perm", "Phags_Pa", "Phoenician", 310 "Plrd", "Roro", "Sara", "Syre", "Syrj", "Syrn", "Teng", "Vai", "Visp", "Cuneiform", 311 "Zxxx", "Unknown", 312 "Carian", "Jpan", "Lana", "Lycian", "Lydian", "Ol_Chiki", "Rejang", "Saurashtra", "Sgnw", "Sundanese", 313 "Moon", "Mtei", 314 /* new in ICU 4.0 */ 315 "Armi", "Avst", "Cakm", "Kore", 316 "Kthi", "Mani", "Phli", "Phlp", "Phlv", "Prti", "Samr", "Tavt", 317 "Zmth", "Zsym", 318 }; 319 static const char* expectedShort[] = { 320 "Bali", "Batk", "Blis", "Brah", "Cham", "Cirt", "Cyrs", "Egyd", "Egyh", "Egyp", 321 "Geok", "Hans", "Hant", "Hmng", "Hung", "Inds", "Java", "Kali", "Latf", "Latg", 322 "Lepc", "Lina", "Mand", "Maya", "Mero", "Nkoo", "Orkh", "Perm", "Phag", "Phnx", 323 "Plrd", "Roro", "Sara", "Syre", "Syrj", "Syrn", "Teng", "Vaii", "Visp", "Xsux", 324 "Zxxx", "Zzzz", 325 "Cari", "Jpan", "Lana", "Lyci", "Lydi", "Olck", "Rjng", "Saur", "Sgnw", "Sund", 326 "Moon", "Mtei", 327 /* new in ICU 4.0 */ 328 "Armi", "Avst", "Cakm", "Kore", 329 "Kthi", "Mani", "Phli", "Phlp", "Phlv", "Prti", "Samr", "Tavt", 330 "Zmth", "Zsym", 331 }; 332 int32_t j = 0; 333 for(i=USCRIPT_BALINESE; (UScriptCode)i<USCRIPT_CODE_LIMIT; i++, j++){ 334 const char* name = uscript_getName((UScriptCode)i); 335 if(name==NULL || strcmp(name,expectedLong[j])!=0){ 336 log_err("uscript_getName failed for code %i: %s!=%s\n", i, name, expectedLong[j]); 337 } 338 name = uscript_getShortName((UScriptCode)i); 339 if(name==NULL || strcmp(name,expectedShort[j])!=0){ 340 log_err("uscript_getShortName failed for code %i: %s!=%s\n", i, name, expectedShort[j]); 341 } 342 } 343 for(i=0; i<LENGTHOF(expectedLong); i++){ 344 UScriptCode fillIn[5] = {USCRIPT_INVALID_CODE}; 345 UErrorCode status = U_ZERO_ERROR; 346 int32_t len = 0; 347 len = uscript_getCode(expectedShort[i], fillIn, LENGTHOF(fillIn), &status); 348 if(U_FAILURE(status)){ 349 log_err("uscript_getCode failed for script name %s. Error: %s\n",expectedShort[i], u_errorName(status)); 350 } 351 if(len>1){ 352 log_err("uscript_getCode did not return expected number of codes for script %s. EXPECTED: 1 GOT: %i\n", expectedShort[i], len); 353 } 354 if(fillIn[0]!= (UScriptCode)(USCRIPT_BALINESE+i)){ 355 log_err("uscript_getCode did not return expected code for script %s. EXPECTED: %i GOT: %i\n", expectedShort[i], (USCRIPT_BALINESE+i), fillIn[0] ); 356 } 357 } 358 } 359 } 360 361 void TestBinaryValues() { 362 /* 363 * Unicode 5.1 explicitly defines binary property value aliases. 364 * Verify that they are all recognized. 365 */ 366 static const char *const falseValues[]={ "N", "No", "F", "False" }; 367 static const char *const trueValues[]={ "Y", "Yes", "T", "True" }; 368 int32_t i; 369 for(i=0; i<LENGTHOF(falseValues); ++i) { 370 if(FALSE!=u_getPropertyValueEnum(UCHAR_ALPHABETIC, falseValues[i])) { 371 log_data_err("u_getPropertyValueEnum(UCHAR_ALPHABETIC, \"%s\")!=FALSE (Are you missing data?)\n", falseValues[i]); 372 } 373 } 374 for(i=0; i<LENGTHOF(trueValues); ++i) { 375 if(TRUE!=u_getPropertyValueEnum(UCHAR_ALPHABETIC, trueValues[i])) { 376 log_data_err("u_getPropertyValueEnum(UCHAR_ALPHABETIC, \"%s\")!=TRUE (Are you missing data?)\n", trueValues[i]); 377 } 378 } 379 } 380
