OLD | NEW |
(Empty) | |
| 1 /* |
| 2 ******************************************************************************* |
| 3 * |
| 4 * Copyright (C) 2002-2009, International Business Machines |
| 5 * Corporation and others. All Rights Reserved. |
| 6 * |
| 7 ******************************************************************************* |
| 8 * file name: strcase.cpp |
| 9 * encoding: US-ASCII |
| 10 * tab size: 8 (not used) |
| 11 * indentation:4 |
| 12 * |
| 13 * created on: 2002mar12 |
| 14 * created by: Markus W. Scherer |
| 15 * |
| 16 * Test file for string casing C++ API functions. |
| 17 */ |
| 18 |
| 19 #include "unicode/uchar.h" |
| 20 #include "unicode/ures.h" |
| 21 #include "unicode/uloc.h" |
| 22 #include "unicode/locid.h" |
| 23 #include "unicode/ubrk.h" |
| 24 #include "unicode/unistr.h" |
| 25 #include "unicode/ucasemap.h" |
| 26 #include "ustrtest.h" |
| 27 #include "unicode/tstdtmod.h" |
| 28 |
| 29 #define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0])) |
| 30 |
| 31 StringCaseTest::~StringCaseTest() {} |
| 32 |
| 33 void |
| 34 StringCaseTest::runIndexedTest(int32_t index, UBool exec, const char *&name, cha
r * /*par*/) { |
| 35 if (exec) logln("TestSuite StringCaseTest: "); |
| 36 switch (index) { |
| 37 case 0: name = "TestCaseConversion"; if (exec) TestCaseConversion(); bre
ak; |
| 38 case 1: |
| 39 #if !UCONFIG_NO_BREAK_ITERATION && !UCONFIG_NO_FILE_IO && !UCONFIG_NO_LEGACY_CON
VERSION |
| 40 name = "TestCasing"; |
| 41 if(exec) TestCasing(); |
| 42 #else |
| 43 name = "skip"; |
| 44 #endif |
| 45 break; |
| 46 |
| 47 default: name = ""; break; //needed to end loop |
| 48 } |
| 49 } |
| 50 |
| 51 void |
| 52 StringCaseTest::TestCaseConversion() |
| 53 { |
| 54 static const UChar uppercaseGreek[] = |
| 55 { 0x399, 0x395, 0x3a3, 0x3a5, 0x3a3, 0x20, 0x03a7, 0x3a1, 0x399, 0x3a3,
0x3a4, |
| 56 0x39f, 0x3a3, 0 }; |
| 57 // "IESUS CHRISTOS" |
| 58 |
| 59 static const UChar lowercaseGreek[] = |
| 60 { 0x3b9, 0x3b5, 0x3c3, 0x3c5, 0x3c2, 0x20, 0x03c7, 0x3c1, 0x3b9, 0x3c3,
0x3c4, |
| 61 0x3bf, 0x3c2, 0 }; |
| 62 // "iesus christos" |
| 63 |
| 64 static const UChar lowercaseTurkish[] = |
| 65 { 0x69, 0x73, 0x74, 0x61, 0x6e, 0x62, 0x75, 0x6c, 0x2c, 0x20, 0x6e, 0x6f
, 0x74, 0x20, 0x63, 0x6f, |
| 66 0x6e, 0x73, 0x74, 0x61, 0x6e, 0x74, 0x0131, 0x6e, 0x6f, 0x70, 0x6c, 0x65
, 0x21, 0 }; |
| 67 |
| 68 static const UChar uppercaseTurkish[] = |
| 69 { 0x54, 0x4f, 0x50, 0x4b, 0x41, 0x50, 0x49, 0x20, 0x50, 0x41, 0x4c, 0x41
, 0x43, 0x45, 0x2c, 0x20, |
| 70 0x0130, 0x53, 0x54, 0x41, 0x4e, 0x42, 0x55, 0x4c, 0 }; |
| 71 |
| 72 UnicodeString expectedResult; |
| 73 UnicodeString test3; |
| 74 |
| 75 test3 += (UChar32)0x0130; |
| 76 test3 += "STANBUL, NOT CONSTANTINOPLE!"; |
| 77 |
| 78 UnicodeString test4(test3); |
| 79 test4.toLower(Locale("")); |
| 80 expectedResult = UnicodeString("i\\u0307stanbul, not constantinople!", "").u
nescape(); |
| 81 if (test4 != expectedResult) |
| 82 errln("1. toLower failed: expected \"" + expectedResult + "\", got \"" +
test4 + "\"."); |
| 83 |
| 84 test4 = test3; |
| 85 test4.toLower(Locale("tr", "TR")); |
| 86 expectedResult = lowercaseTurkish; |
| 87 if (test4 != expectedResult) |
| 88 errln("2. toLower failed: expected \"" + expectedResult + "\", got \"" +
test4 + "\"."); |
| 89 |
| 90 test3 = "topkap"; |
| 91 test3 += (UChar32)0x0131; |
| 92 test3 += " palace, istanbul"; |
| 93 test4 = test3; |
| 94 |
| 95 test4.toUpper(Locale("")); |
| 96 expectedResult = "TOPKAPI PALACE, ISTANBUL"; |
| 97 if (test4 != expectedResult) |
| 98 errln("toUpper failed: expected \"" + expectedResult + "\", got \"" + te
st4 + "\"."); |
| 99 |
| 100 test4 = test3; |
| 101 test4.toUpper(Locale("tr", "TR")); |
| 102 expectedResult = uppercaseTurkish; |
| 103 if (test4 != expectedResult) |
| 104 errln("toUpper failed: expected \"" + expectedResult + "\", got \"" + te
st4 + "\"."); |
| 105 |
| 106 test3 = CharsToUnicodeString("S\\u00FC\\u00DFmayrstra\\u00DFe"); |
| 107 |
| 108 test3.toUpper(Locale("de", "DE")); |
| 109 expectedResult = CharsToUnicodeString("S\\u00DCSSMAYRSTRASSE"); |
| 110 if (test3 != expectedResult) |
| 111 errln("toUpper failed: expected \"" + expectedResult + "\", got \"" + te
st3 + "\"."); |
| 112 |
| 113 test4.replace(0, test4.length(), uppercaseGreek); |
| 114 |
| 115 test4.toLower(Locale("el", "GR")); |
| 116 expectedResult = lowercaseGreek; |
| 117 if (test4 != expectedResult) |
| 118 errln("toLower failed: expected \"" + expectedResult + "\", got \"" + te
st4 + "\"."); |
| 119 |
| 120 test4.replace(0, test4.length(), lowercaseGreek); |
| 121 |
| 122 test4.toUpper(); |
| 123 expectedResult = uppercaseGreek; |
| 124 if (test4 != expectedResult) |
| 125 errln("toUpper failed: expected \"" + expectedResult + "\", got \"" + te
st4 + "\"."); |
| 126 |
| 127 // more string case mapping tests with the new implementation |
| 128 { |
| 129 static const UChar |
| 130 |
| 131 beforeLower[]= { 0x61, 0x42, 0x49, 0x3a3, 0xdf, 0x3a3, 0x2f, 0xd93f, 0x
dfff }, |
| 132 lowerRoot[]= { 0x61, 0x62, 0x69, 0x3c3, 0xdf, 0x3c2, 0x2f, 0xd93f, 0x
dfff }, |
| 133 lowerTurkish[]={ 0x61, 0x62, 0x131, 0x3c3, 0xdf, 0x3c2, 0x2f, 0xd93f, 0x
dfff }, |
| 134 |
| 135 beforeUpper[]= { 0x61, 0x42, 0x69, 0x3c2, 0xdf, 0x3c3, 0x2f, 0xfb
03, 0xfb03, 0xfb03, 0xd93f, 0xdfff }, |
| 136 upperRoot[]= { 0x41, 0x42, 0x49, 0x3a3, 0x53, 0x53, 0x3a3, 0x2f, 0x46
, 0x46, 0x49, 0x46, 0x46, 0x49, 0x46, 0x46, 0x49, 0xd93f, 0xdfff }, |
| 137 upperTurkish[]={ 0x41, 0x42, 0x130, 0x3a3, 0x53, 0x53, 0x3a3, 0x2f, 0x46
, 0x46, 0x49, 0x46, 0x46, 0x49, 0x46, 0x46, 0x49, 0xd93f, 0xdfff }, |
| 138 |
| 139 beforeMiniUpper[]= { 0xdf, 0x61 }, |
| 140 miniUpper[]= { 0x53, 0x53, 0x41 }; |
| 141 |
| 142 UnicodeString s; |
| 143 |
| 144 /* lowercase with root locale */ |
| 145 s=UnicodeString(FALSE, beforeLower, (int32_t)(sizeof(beforeLower)/U_SIZE
OF_UCHAR)); |
| 146 s.toLower(""); |
| 147 if( s.length()!=(sizeof(lowerRoot)/U_SIZEOF_UCHAR) || |
| 148 s!=UnicodeString(FALSE, lowerRoot, s.length()) |
| 149 ) { |
| 150 errln("error in toLower(root locale)=\"" + s + "\" expected \"" + Un
icodeString(FALSE, lowerRoot, (int32_t)(sizeof(lowerRoot)/U_SIZEOF_UCHAR)) + "\"
"); |
| 151 } |
| 152 |
| 153 /* lowercase with turkish locale */ |
| 154 s=UnicodeString(FALSE, beforeLower, (int32_t)(sizeof(beforeLower)/U_SIZE
OF_UCHAR)); |
| 155 s.setCharAt(0, beforeLower[0]).toLower(Locale("tr")); |
| 156 if( s.length()!=(sizeof(lowerTurkish)/U_SIZEOF_UCHAR) || |
| 157 s!=UnicodeString(FALSE, lowerTurkish, s.length()) |
| 158 ) { |
| 159 errln("error in toLower(turkish locale)=\"" + s + "\" expected \"" +
UnicodeString(FALSE, lowerTurkish, (int32_t)(sizeof(lowerTurkish)/U_SIZEOF_UCHA
R)) + "\""); |
| 160 } |
| 161 |
| 162 /* uppercase with root locale */ |
| 163 s=UnicodeString(FALSE, beforeUpper, (int32_t)(sizeof(beforeUpper)/U_SIZE
OF_UCHAR)); |
| 164 s.setCharAt(0, beforeUpper[0]).toUpper(Locale("")); |
| 165 if( s.length()!=(sizeof(upperRoot)/U_SIZEOF_UCHAR) || |
| 166 s!=UnicodeString(FALSE, upperRoot, s.length()) |
| 167 ) { |
| 168 errln("error in toUpper(root locale)=\"" + s + "\" expected \"" + Un
icodeString(FALSE, upperRoot, (int32_t)(sizeof(upperRoot)/U_SIZEOF_UCHAR)) + "\"
"); |
| 169 } |
| 170 |
| 171 /* uppercase with turkish locale */ |
| 172 s=UnicodeString(FALSE, beforeUpper, (int32_t)(sizeof(beforeUpper)/U_SIZE
OF_UCHAR)); |
| 173 s.toUpper(Locale("tr")); |
| 174 if( s.length()!=(sizeof(upperTurkish)/U_SIZEOF_UCHAR) || |
| 175 s!=UnicodeString(FALSE, upperTurkish, s.length()) |
| 176 ) { |
| 177 errln("error in toUpper(turkish locale)=\"" + s + "\" expected \"" +
UnicodeString(FALSE, upperTurkish, (int32_t)(sizeof(upperTurkish)/U_SIZEOF_UCHA
R)) + "\""); |
| 178 } |
| 179 |
| 180 /* uppercase a short string with root locale */ |
| 181 s=UnicodeString(FALSE, beforeMiniUpper, (int32_t)(sizeof(beforeMiniUpper
)/U_SIZEOF_UCHAR)); |
| 182 s.setCharAt(0, beforeMiniUpper[0]).toUpper(""); |
| 183 if( s.length()!=(sizeof(miniUpper)/U_SIZEOF_UCHAR) || |
| 184 s!=UnicodeString(FALSE, miniUpper, s.length()) |
| 185 ) { |
| 186 errln("error in toUpper(root locale)=\"" + s + "\" expected \"" + Un
icodeString(FALSE, miniUpper, (int32_t)(sizeof(miniUpper)/U_SIZEOF_UCHAR)) + "\"
"); |
| 187 } |
| 188 } |
| 189 |
| 190 // test some supplementary characters (>= Unicode 3.1) |
| 191 { |
| 192 UnicodeString t; |
| 193 |
| 194 UnicodeString |
| 195 deseretInput=UnicodeString("\\U0001043C\\U00010414", "").unescape(), |
| 196 deseretLower=UnicodeString("\\U0001043C\\U0001043C", "").unescape(), |
| 197 deseretUpper=UnicodeString("\\U00010414\\U00010414", "").unescape(); |
| 198 (t=deseretInput).toLower(); |
| 199 if(t!=deseretLower) { |
| 200 errln("error lowercasing Deseret (plane 1) characters"); |
| 201 } |
| 202 (t=deseretInput).toUpper(); |
| 203 if(t!=deseretUpper) { |
| 204 errln("error uppercasing Deseret (plane 1) characters"); |
| 205 } |
| 206 } |
| 207 |
| 208 // test some more cases that looked like problems |
| 209 { |
| 210 UnicodeString t; |
| 211 |
| 212 UnicodeString |
| 213 ljInput=UnicodeString("ab'cD \\uFB00i\\u0131I\\u0130 \\u01C7\\u01C8\
\u01C9 \\U0001043C\\U00010414", "").unescape(), |
| 214 ljLower=UnicodeString("ab'cd \\uFB00i\\u0131ii\\u0307 \\u01C9\\u01C9
\\u01C9 \\U0001043C\\U0001043C", "").unescape(), |
| 215 ljUpper=UnicodeString("AB'CD FFIII\\u0130 \\u01C7\\u01C7\\u01C7 \\U0
0010414\\U00010414", "").unescape(); |
| 216 (t=ljInput).toLower("en"); |
| 217 if(t!=ljLower) { |
| 218 errln("error lowercasing LJ characters"); |
| 219 } |
| 220 (t=ljInput).toUpper("en"); |
| 221 if(t!=ljUpper) { |
| 222 errln("error uppercasing LJ characters"); |
| 223 } |
| 224 } |
| 225 |
| 226 #if !UCONFIG_NO_NORMALIZATION |
| 227 // some context-sensitive casing depends on normalization data being present |
| 228 |
| 229 // Unicode 3.1.1 SpecialCasing tests |
| 230 { |
| 231 UnicodeString t; |
| 232 |
| 233 // sigmas preceded and/or followed by cased letters |
| 234 UnicodeString |
| 235 sigmas=UnicodeString("i\\u0307\\u03a3\\u0308j \\u0307\\u03a3\\u0308j
i\\u00ad\\u03a3\\u0308 \\u0307\\u03a3\\u0308 ", "").unescape(), |
| 236 sigmasLower=UnicodeString("i\\u0307\\u03c3\\u0308j \\u0307\\u03c3\\u
0308j i\\u00ad\\u03c2\\u0308 \\u0307\\u03c3\\u0308 ", "").unescape(), |
| 237 sigmasUpper=UnicodeString("I\\u0307\\u03a3\\u0308J \\u0307\\u03a3\\u
0308J I\\u00ad\\u03a3\\u0308 \\u0307\\u03a3\\u0308 ", "").unescape(); |
| 238 |
| 239 (t=sigmas).toLower(); |
| 240 if(t!=sigmasLower) { |
| 241 errln("error in sigmas.toLower()=\"" + t + "\" expected \"" + sigmas
Lower + "\""); |
| 242 } |
| 243 |
| 244 (t=sigmas).toUpper(Locale("")); |
| 245 if(t!=sigmasUpper) { |
| 246 errln("error in sigmas.toUpper()=\"" + t + "\" expected \"" + sigmas
Upper + "\""); |
| 247 } |
| 248 |
| 249 // turkish & azerbaijani dotless i & dotted I |
| 250 // remove dot above if there was a capital I before and there are no mor
e accents above |
| 251 UnicodeString |
| 252 dots=UnicodeString("I \\u0130 I\\u0307 I\\u0327\\u0307 I\\u0301\\u03
07 I\\u0327\\u0307\\u0301", "").unescape(), |
| 253 dotsTurkish=UnicodeString("\\u0131 i i i\\u0327 \\u0131\\u0301\\u030
7 i\\u0327\\u0301", "").unescape(), |
| 254 dotsDefault=UnicodeString("i i\\u0307 i\\u0307 i\\u0327\\u0307 i\\u0
301\\u0307 i\\u0327\\u0307\\u0301", "").unescape(); |
| 255 |
| 256 (t=dots).toLower("tr"); |
| 257 if(t!=dotsTurkish) { |
| 258 errln("error in dots.toLower(tr)=\"" + t + "\" expected \"" + dotsTu
rkish + "\""); |
| 259 } |
| 260 |
| 261 (t=dots).toLower("de"); |
| 262 if(t!=dotsDefault) { |
| 263 errln("error in dots.toLower(de)=\"" + t + "\" expected \"" + dotsDe
fault + "\""); |
| 264 } |
| 265 } |
| 266 |
| 267 // more Unicode 3.1.1 tests |
| 268 { |
| 269 UnicodeString t; |
| 270 |
| 271 // lithuanian dot above in uppercasing |
| 272 UnicodeString |
| 273 dots=UnicodeString("a\\u0307 \\u0307 i\\u0307 j\\u0327\\u0307 j\\u03
01\\u0307", "").unescape(), |
| 274 dotsLithuanian=UnicodeString("A\\u0307 \\u0307 I J\\u0327 J\\u0301\\
u0307", "").unescape(), |
| 275 dotsDefault=UnicodeString("A\\u0307 \\u0307 I\\u0307 J\\u0327\\u0307
J\\u0301\\u0307", "").unescape(); |
| 276 |
| 277 (t=dots).toUpper("lt"); |
| 278 if(t!=dotsLithuanian) { |
| 279 errln("error in dots.toUpper(lt)=\"" + t + "\" expected \"" + dotsLi
thuanian + "\""); |
| 280 } |
| 281 |
| 282 (t=dots).toUpper("de"); |
| 283 if(t!=dotsDefault) { |
| 284 errln("error in dots.toUpper(de)=\"" + t + "\" expected \"" + dotsDe
fault + "\""); |
| 285 } |
| 286 |
| 287 // lithuanian adds dot above to i in lowercasing if there are more above
accents |
| 288 UnicodeString |
| 289 i=UnicodeString("I I\\u0301 J J\\u0301 \\u012e \\u012e\\u0301 \\u00c
c\\u00cd\\u0128", "").unescape(), |
| 290 iLithuanian=UnicodeString("i i\\u0307\\u0301 j j\\u0307\\u0301 \\u01
2f \\u012f\\u0307\\u0301 i\\u0307\\u0300i\\u0307\\u0301i\\u0307\\u0303", "").une
scape(), |
| 291 iDefault=UnicodeString("i i\\u0301 j j\\u0301 \\u012f \\u012f\\u0301
\\u00ec\\u00ed\\u0129", "").unescape(); |
| 292 |
| 293 (t=i).toLower("lt"); |
| 294 if(t!=iLithuanian) { |
| 295 errln("error in i.toLower(lt)=\"" + t + "\" expected \"" + iLithuani
an + "\""); |
| 296 } |
| 297 |
| 298 (t=i).toLower("de"); |
| 299 if(t!=iDefault) { |
| 300 errln("error in i.toLower(de)=\"" + t + "\" expected \"" + iDefault
+ "\""); |
| 301 } |
| 302 } |
| 303 |
| 304 #endif |
| 305 |
| 306 // test case folding |
| 307 { |
| 308 UnicodeString |
| 309 s=UnicodeString("A\\u00df\\u00b5\\ufb03\\U0001040c\\u0130\\u0131", "
").unescape(), |
| 310 f=UnicodeString("ass\\u03bcffi\\U00010434i\\u0307\\u0131", "").unesc
ape(), |
| 311 g=UnicodeString("ass\\u03bcffi\\U00010434i\\u0131", "").unescape(), |
| 312 t; |
| 313 |
| 314 (t=s).foldCase(); |
| 315 if(f!=t) { |
| 316 errln("error in foldCase(\"" + s + "\", default)=\"" + t + "\" but e
xpected \"" + f + "\""); |
| 317 } |
| 318 |
| 319 // alternate handling for dotted I/dotless i (U+0130, U+0131) |
| 320 (t=s).foldCase(U_FOLD_CASE_EXCLUDE_SPECIAL_I); |
| 321 if(g!=t) { |
| 322 errln("error in foldCase(\"" + s + "\", U_FOLD_CASE_EXCLUDE_SPECIAL_
I)=\"" + t + "\" but expected \"" + g + "\""); |
| 323 } |
| 324 } |
| 325 } |
| 326 |
| 327 // data-driven case mapping tests ------------------------------------------ *** |
| 328 |
| 329 enum { |
| 330 TEST_LOWER, |
| 331 TEST_UPPER, |
| 332 TEST_TITLE, |
| 333 TEST_FOLD, |
| 334 TEST_COUNT |
| 335 }; |
| 336 |
| 337 // names of TestData children in casing.txt |
| 338 static const char *const dataNames[TEST_COUNT+1]={ |
| 339 "lowercasing", |
| 340 "uppercasing", |
| 341 "titlecasing", |
| 342 "casefolding", |
| 343 "" |
| 344 }; |
| 345 |
| 346 void |
| 347 StringCaseTest::TestCasingImpl(const UnicodeString &input, |
| 348 const UnicodeString &output, |
| 349 int32_t whichCase, |
| 350 void *iter, const char *localeID, uint32_t option
s) { |
| 351 // UnicodeString |
| 352 UnicodeString result; |
| 353 const char *name; |
| 354 Locale locale(localeID); |
| 355 |
| 356 result=input; |
| 357 switch(whichCase) { |
| 358 case TEST_LOWER: |
| 359 name="toLower"; |
| 360 result.toLower(locale); |
| 361 break; |
| 362 case TEST_UPPER: |
| 363 name="toUpper"; |
| 364 result.toUpper(locale); |
| 365 break; |
| 366 #if !UCONFIG_NO_BREAK_ITERATION |
| 367 case TEST_TITLE: |
| 368 name="toTitle"; |
| 369 result.toTitle((BreakIterator *)iter, locale, options); |
| 370 break; |
| 371 #endif |
| 372 case TEST_FOLD: |
| 373 name="foldCase"; |
| 374 result.foldCase(options); |
| 375 break; |
| 376 default: |
| 377 name=""; |
| 378 break; // won't happen |
| 379 } |
| 380 if(result!=output) { |
| 381 dataerrln("error: UnicodeString.%s() got a wrong result for a test case
from casing.res", name); |
| 382 } |
| 383 #if !UCONFIG_NO_BREAK_ITERATION |
| 384 if(whichCase==TEST_TITLE && options==0) { |
| 385 result=input; |
| 386 result.toTitle((BreakIterator *)iter, locale); |
| 387 if(result!=output) { |
| 388 dataerrln("error: UnicodeString.toTitle(options=0) got a wrong resul
t for a test case from casing.res"); |
| 389 } |
| 390 } |
| 391 #endif |
| 392 |
| 393 // UTF-8 |
| 394 char utf8In[100], utf8Out[100]; |
| 395 int32_t utf8InLength, utf8OutLength, resultLength; |
| 396 UChar *buffer; |
| 397 |
| 398 IcuTestErrorCode errorCode(*this, "TestCasingImpl"); |
| 399 LocalUCaseMapPointer csm(ucasemap_open(localeID, options, errorCode)); |
| 400 #if !UCONFIG_NO_BREAK_ITERATION |
| 401 if(iter!=NULL) { |
| 402 // Clone the break iterator so that the UCaseMap can safely adopt it. |
| 403 int32_t size=1; // Not 0 because that only gives preflighting. |
| 404 UBreakIterator *clone=ubrk_safeClone((UBreakIterator *)iter, NULL, &size
, errorCode); |
| 405 ucasemap_setBreakIterator(csm.getAlias(), clone, errorCode); |
| 406 } |
| 407 #endif |
| 408 |
| 409 u_strToUTF8(utf8In, (int32_t)sizeof(utf8In), &utf8InLength, input.getBuffer(
), input.length(), errorCode); |
| 410 switch(whichCase) { |
| 411 case TEST_LOWER: |
| 412 name="ucasemap_utf8ToLower"; |
| 413 utf8OutLength=ucasemap_utf8ToLower(csm.getAlias(), |
| 414 utf8Out, (int32_t)sizeof(utf8Out), |
| 415 utf8In, utf8InLength, errorCode); |
| 416 break; |
| 417 case TEST_UPPER: |
| 418 name="ucasemap_utf8ToUpper"; |
| 419 utf8OutLength=ucasemap_utf8ToUpper(csm.getAlias(), |
| 420 utf8Out, (int32_t)sizeof(utf8Out), |
| 421 utf8In, utf8InLength, errorCode); |
| 422 break; |
| 423 #if !UCONFIG_NO_BREAK_ITERATION |
| 424 case TEST_TITLE: |
| 425 name="ucasemap_utf8ToTitle"; |
| 426 utf8OutLength=ucasemap_utf8ToTitle(csm.getAlias(), |
| 427 utf8Out, (int32_t)sizeof(utf8Out), |
| 428 utf8In, utf8InLength, errorCode); |
| 429 break; |
| 430 #endif |
| 431 case TEST_FOLD: |
| 432 name="ucasemap_utf8FoldCase"; |
| 433 utf8OutLength=ucasemap_utf8FoldCase(csm.getAlias(), |
| 434 utf8Out, (int32_t)sizeof(utf8Out), |
| 435 utf8In, utf8InLength, errorCode); |
| 436 break; |
| 437 default: |
| 438 name=""; |
| 439 utf8OutLength=0; |
| 440 break; // won't happen |
| 441 } |
| 442 buffer=result.getBuffer(utf8OutLength); |
| 443 u_strFromUTF8(buffer, result.getCapacity(), &resultLength, utf8Out, utf8OutL
ength, errorCode); |
| 444 result.releaseBuffer(errorCode.isSuccess() ? resultLength : 0); |
| 445 |
| 446 if(errorCode.isFailure()) { |
| 447 errcheckln(errorCode, "error: %s() got an error for a test case from cas
ing.res - %s", name, u_errorName(errorCode)); |
| 448 errorCode.reset(); |
| 449 } else if(result!=output) { |
| 450 errln("error: %s() got a wrong result for a test case from casing.res",
name); |
| 451 errln("expected \"" + output + "\" got \"" + result + "\"" ); |
| 452 } |
| 453 } |
| 454 |
| 455 void |
| 456 StringCaseTest::TestCasing() { |
| 457 UErrorCode status = U_ZERO_ERROR; |
| 458 #if !UCONFIG_NO_BREAK_ITERATION |
| 459 LocalUBreakIteratorPointer iter; |
| 460 #endif |
| 461 char cLocaleID[100]; |
| 462 UnicodeString locale, input, output, optionsString, result; |
| 463 uint32_t options; |
| 464 int32_t whichCase, type; |
| 465 LocalPointer<TestDataModule> driver(TestDataModule::getTestDataModule("casin
g", *this, status)); |
| 466 if(U_SUCCESS(status)) { |
| 467 for(whichCase=0; whichCase<TEST_COUNT; ++whichCase) { |
| 468 #if UCONFIG_NO_BREAK_ITERATION |
| 469 if(whichCase==TEST_TITLE) { |
| 470 continue; |
| 471 } |
| 472 #endif |
| 473 LocalPointer<TestData> casingTest(driver->createTestData(dataNames[w
hichCase], status)); |
| 474 if(U_FAILURE(status)) { |
| 475 errln("TestCasing failed to createTestData(%s) - %s", dataNames[
whichCase], u_errorName(status)); |
| 476 break; |
| 477 } |
| 478 const DataMap *myCase = NULL; |
| 479 while(casingTest->nextCase(myCase, status)) { |
| 480 input = myCase->getString("Input", status); |
| 481 output = myCase->getString("Output", status); |
| 482 |
| 483 if(whichCase!=TEST_FOLD) { |
| 484 locale = myCase->getString("Locale", status); |
| 485 } |
| 486 locale.extract(0, 0x7fffffff, cLocaleID, sizeof(cLocaleID), ""); |
| 487 |
| 488 #if !UCONFIG_NO_BREAK_ITERATION |
| 489 if(whichCase==TEST_TITLE) { |
| 490 type = myCase->getInt("Type", status); |
| 491 if(type>=0) { |
| 492 iter.adoptInstead(ubrk_open((UBreakIteratorType)type, cL
ocaleID, NULL, 0, &status)); |
| 493 } else if(type==-2) { |
| 494 // Open a trivial break iterator that only delivers { 0,
length } |
| 495 // or even just { 0 } as boundaries. |
| 496 static const UChar rules[] = { 0x2e, 0x2a, 0x3b }; // "
.*;" |
| 497 UParseError parseError; |
| 498 iter.adoptInstead(ubrk_openRules(rules, LENGTHOF(rules),
NULL, 0, &parseError, &status)); |
| 499 } |
| 500 } |
| 501 #endif |
| 502 options = 0; |
| 503 if(whichCase==TEST_TITLE || whichCase==TEST_FOLD) { |
| 504 optionsString = myCase->getString("Options", status); |
| 505 if(optionsString.indexOf((UChar)0x54)>=0) { // T |
| 506 options|=U_FOLD_CASE_EXCLUDE_SPECIAL_I; |
| 507 } |
| 508 if(optionsString.indexOf((UChar)0x4c)>=0) { // L |
| 509 options|=U_TITLECASE_NO_LOWERCASE; |
| 510 } |
| 511 if(optionsString.indexOf((UChar)0x41)>=0) { // A |
| 512 options|=U_TITLECASE_NO_BREAK_ADJUSTMENT; |
| 513 } |
| 514 } |
| 515 |
| 516 if(U_FAILURE(status)) { |
| 517 dataerrln("error: TestCasing() setup failed for %s test case
from casing.res: %s", dataNames[whichCase], u_errorName(status)); |
| 518 status = U_ZERO_ERROR; |
| 519 } else { |
| 520 #if UCONFIG_NO_BREAK_ITERATION |
| 521 LocalPointer<UMemory> iter; |
| 522 #endif |
| 523 TestCasingImpl(input, output, whichCase, iter.getAlias(), cL
ocaleID, options); |
| 524 } |
| 525 |
| 526 #if !UCONFIG_NO_BREAK_ITERATION |
| 527 iter.adoptInstead(NULL); |
| 528 #endif |
| 529 } |
| 530 } |
| 531 } |
| 532 |
| 533 #if !UCONFIG_NO_BREAK_ITERATION |
| 534 // more tests for API coverage |
| 535 status=U_ZERO_ERROR; |
| 536 input=UNICODE_STRING_SIMPLE("sTrA\\u00dfE").unescape(); |
| 537 (result=input).toTitle(NULL); |
| 538 if(result!=UNICODE_STRING_SIMPLE("Stra\\u00dfe").unescape()) { |
| 539 dataerrln("UnicodeString::toTitle(NULL) failed."); |
| 540 } |
| 541 #endif |
| 542 } |
OLD | NEW |