Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 1 | // © 2016 and later: Unicode, Inc. and others. |
| 2 | // License & terms of use: http://www.unicode.org/copyright.html |
| 3 | /* |
| 4 | ***************************************************************************** |
| 5 | * Copyright (C) 2001-2016, International Business Machines orporation |
| 6 | * and others. All Rights Reserved. |
| 7 | ****************************************************************************/ |
| 8 | |
| 9 | #include "unicode/utypes.h" |
| 10 | |
| 11 | #if !UCONFIG_NO_COLLATION |
| 12 | |
| 13 | #include "srchtest.h" |
| 14 | #if !UCONFIG_NO_BREAK_ITERATION |
| 15 | #include "../cintltst/usrchdat.c" |
| 16 | #endif |
| 17 | #include "unicode/stsearch.h" |
| 18 | #include "unicode/ustring.h" |
| 19 | #include "unicode/schriter.h" |
| 20 | #include "cmemory.h" |
| 21 | #include <string.h> |
| 22 | #include <stdio.h> |
| 23 | |
| 24 | // private definitions ----------------------------------------------------- |
| 25 | |
| 26 | #define CASE(id,test) \ |
| 27 | case id: \ |
| 28 | name = #test; \ |
| 29 | if (exec) { \ |
| 30 | logln(#test "---"); \ |
| 31 | logln((UnicodeString)""); \ |
| 32 | if(areBroken) { \ |
| 33 | dataerrln(__FILE__ " cannot test - failed to create collator."); \ |
| 34 | } else { \ |
| 35 | test(); \ |
| 36 | } \ |
| 37 | } \ |
| 38 | break; |
| 39 | |
| 40 | // public constructors and destructors -------------------------------------- |
| 41 | |
| 42 | StringSearchTest::StringSearchTest() |
| 43 | #if !UCONFIG_NO_BREAK_ITERATION |
| 44 | : |
| 45 | m_en_wordbreaker_(NULL), m_en_characterbreaker_(NULL) |
| 46 | #endif |
| 47 | { |
| 48 | #if !UCONFIG_NO_BREAK_ITERATION |
| 49 | UErrorCode status = U_ZERO_ERROR; |
| 50 | |
| 51 | m_en_us_ = (RuleBasedCollator *)Collator::createInstance("en_US", status); |
| 52 | m_fr_fr_ = (RuleBasedCollator *)Collator::createInstance("fr_FR", status); |
| 53 | m_de_ = (RuleBasedCollator *)Collator::createInstance("de_DE", status); |
| 54 | m_es_ = (RuleBasedCollator *)Collator::createInstance("es_ES", status); |
| 55 | if(U_FAILURE(status)) { |
| 56 | delete m_en_us_; |
| 57 | delete m_fr_fr_; |
| 58 | delete m_de_; |
| 59 | delete m_es_; |
| 60 | m_en_us_ = 0; |
| 61 | m_fr_fr_ = 0; |
| 62 | m_de_ = 0; |
| 63 | m_es_ = 0; |
| 64 | errln("Collator creation failed with %s", u_errorName(status)); |
| 65 | return; |
| 66 | } |
| 67 | |
| 68 | |
| 69 | UnicodeString rules; |
| 70 | rules.setTo(((RuleBasedCollator *)m_de_)->getRules()); |
| 71 | UChar extrarules[128]; |
| 72 | u_unescape(EXTRACOLLATIONRULE, extrarules, 128); |
| 73 | rules.append(extrarules, u_strlen(extrarules)); |
| 74 | delete m_de_; |
| 75 | |
| 76 | m_de_ = new RuleBasedCollator(rules, status); |
| 77 | |
| 78 | rules.setTo(((RuleBasedCollator *)m_es_)->getRules()); |
| 79 | rules.append(extrarules, u_strlen(extrarules)); |
| 80 | |
| 81 | delete m_es_; |
| 82 | |
| 83 | m_es_ = new RuleBasedCollator(rules, status); |
| 84 | |
| 85 | #if !UCONFIG_NO_BREAK_ITERATION |
| 86 | m_en_wordbreaker_ = BreakIterator::createWordInstance( |
| 87 | Locale::getEnglish(), status); |
| 88 | m_en_characterbreaker_ = BreakIterator::createCharacterInstance( |
| 89 | Locale::getEnglish(), status); |
| 90 | #endif |
| 91 | #endif |
| 92 | } |
| 93 | |
| 94 | StringSearchTest::~StringSearchTest() |
| 95 | { |
| 96 | #if !UCONFIG_NO_BREAK_ITERATION |
| 97 | delete m_en_us_; |
| 98 | delete m_fr_fr_; |
| 99 | delete m_de_; |
| 100 | delete m_es_; |
| 101 | #if !UCONFIG_NO_BREAK_ITERATION |
| 102 | delete m_en_wordbreaker_; |
| 103 | delete m_en_characterbreaker_; |
| 104 | #endif |
| 105 | #endif |
| 106 | } |
| 107 | |
| 108 | // public methods ---------------------------------------------------------- |
| 109 | |
| 110 | void StringSearchTest::runIndexedTest(int32_t index, UBool exec, |
| 111 | const char* &name, char* ) |
| 112 | { |
| 113 | #if !UCONFIG_NO_BREAK_ITERATION |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 114 | UBool areBroken = false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 115 | if (m_en_us_ == NULL && m_fr_fr_ == NULL && m_de_ == NULL && |
| 116 | m_es_ == NULL && m_en_wordbreaker_ == NULL && |
| 117 | m_en_characterbreaker_ == NULL && exec) { |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 118 | areBroken = true; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 119 | } |
| 120 | |
| 121 | switch (index) { |
| 122 | #if !UCONFIG_NO_FILE_IO |
| 123 | CASE(0, TestOpenClose) |
| 124 | #endif |
| 125 | CASE(1, TestInitialization) |
| 126 | CASE(2, TestBasic) |
| 127 | CASE(3, TestNormExact) |
| 128 | CASE(4, TestStrength) |
| 129 | #if UCONFIG_NO_BREAK_ITERATION |
| 130 | case 5: |
| 131 | name = "TestBreakIterator"; |
| 132 | break; |
| 133 | #else |
| 134 | CASE(5, TestBreakIterator) |
| 135 | #endif |
| 136 | CASE(6, TestVariable) |
| 137 | CASE(7, TestOverlap) |
| 138 | CASE(8, TestCollator) |
| 139 | CASE(9, TestPattern) |
| 140 | CASE(10, TestText) |
| 141 | CASE(11, TestCompositeBoundaries) |
| 142 | CASE(12, TestGetSetOffset) |
| 143 | CASE(13, TestGetSetAttribute) |
| 144 | CASE(14, TestGetMatch) |
| 145 | CASE(15, TestSetMatch) |
| 146 | CASE(16, TestReset) |
| 147 | CASE(17, TestSupplementary) |
| 148 | CASE(18, TestContraction) |
| 149 | CASE(19, TestIgnorable) |
| 150 | CASE(20, TestCanonical) |
| 151 | CASE(21, TestNormCanonical) |
| 152 | CASE(22, TestStrengthCanonical) |
| 153 | #if UCONFIG_NO_BREAK_ITERATION |
| 154 | case 23: |
| 155 | name = "TestBreakIteratorCanonical"; |
| 156 | break; |
| 157 | #else |
| 158 | CASE(23, TestBreakIteratorCanonical) |
| 159 | #endif |
| 160 | CASE(24, TestVariableCanonical) |
| 161 | CASE(25, TestOverlapCanonical) |
| 162 | CASE(26, TestCollatorCanonical) |
| 163 | CASE(27, TestPatternCanonical) |
| 164 | CASE(28, TestTextCanonical) |
| 165 | CASE(29, TestCompositeBoundariesCanonical) |
| 166 | CASE(30, TestGetSetOffsetCanonical) |
| 167 | CASE(31, TestSupplementaryCanonical) |
| 168 | CASE(32, TestContractionCanonical) |
| 169 | CASE(33, TestUClassID) |
| 170 | CASE(34, TestSubclass) |
| 171 | CASE(35, TestCoverage) |
| 172 | CASE(36, TestDiacriticMatch) |
| 173 | default: name = ""; break; |
| 174 | } |
| 175 | #else |
| 176 | name=""; |
| 177 | #endif |
| 178 | } |
| 179 | |
| 180 | #if !UCONFIG_NO_BREAK_ITERATION |
| 181 | // private methods ------------------------------------------------------ |
| 182 | |
| 183 | RuleBasedCollator * StringSearchTest::getCollator(const char *collator) |
| 184 | { |
| 185 | if (collator == NULL) { |
| 186 | return m_en_us_; |
| 187 | } |
| 188 | if (strcmp(collator, "fr") == 0) { |
| 189 | return m_fr_fr_; |
| 190 | } |
| 191 | else if (strcmp(collator, "de") == 0) { |
| 192 | return m_de_; |
| 193 | } |
| 194 | else if (strcmp(collator, "es") == 0) { |
| 195 | return m_es_; |
| 196 | } |
| 197 | else { |
| 198 | return m_en_us_; |
| 199 | } |
| 200 | } |
| 201 | |
| 202 | BreakIterator * StringSearchTest::getBreakIterator(const char *breaker) |
| 203 | { |
| 204 | #if UCONFIG_NO_BREAK_ITERATION |
| 205 | return NULL; |
| 206 | #else |
| 207 | if (breaker == NULL) { |
| 208 | return NULL; |
| 209 | } |
| 210 | if (strcmp(breaker, "wordbreaker") == 0) { |
| 211 | return m_en_wordbreaker_; |
| 212 | } |
| 213 | else { |
| 214 | return m_en_characterbreaker_; |
| 215 | } |
| 216 | #endif |
| 217 | } |
| 218 | |
| 219 | char * StringSearchTest::toCharString(const UnicodeString &text) |
| 220 | { |
| 221 | static char result[1024]; |
| 222 | int index = 0; |
| 223 | int count = 0; |
| 224 | int length = text.length(); |
| 225 | |
| 226 | for (; count < length; count ++) { |
| 227 | UChar ch = text[count]; |
| 228 | if (ch >= 0x20 && ch <= 0x7e) { |
| 229 | result[index ++] = (char)ch; |
| 230 | } |
| 231 | else { |
| 232 | sprintf(result+index, "\\u%04x", ch); |
| 233 | index += 6; /* \uxxxx */ |
| 234 | } |
| 235 | } |
| 236 | result[index] = 0; |
| 237 | |
| 238 | return result; |
| 239 | } |
| 240 | |
| 241 | Collator::ECollationStrength StringSearchTest::getECollationStrength( |
| 242 | const UCollationStrength &strength) const |
| 243 | { |
| 244 | switch (strength) |
| 245 | { |
| 246 | case UCOL_PRIMARY : |
| 247 | return Collator::PRIMARY; |
| 248 | case UCOL_SECONDARY : |
| 249 | return Collator::SECONDARY; |
| 250 | case UCOL_TERTIARY : |
| 251 | return Collator::TERTIARY; |
| 252 | default : |
| 253 | return Collator::IDENTICAL; |
| 254 | } |
| 255 | } |
| 256 | |
| 257 | UBool StringSearchTest::assertEqualWithStringSearch(StringSearch *strsrch, |
| 258 | const SearchData *search) |
| 259 | { |
| 260 | int32_t count = 0; |
| 261 | UErrorCode status = U_ZERO_ERROR; |
| 262 | int32_t matchindex = search->offset[count]; |
| 263 | UnicodeString matchtext; |
| 264 | int32_t matchlength; |
| 265 | |
| 266 | strsrch->setAttribute(USEARCH_ELEMENT_COMPARISON, search->elemCompare, status); |
| 267 | if (U_FAILURE(status)) { |
| 268 | errln("Error setting USEARCH_ELEMENT_COMPARISON attribute %s", u_errorName(status)); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 269 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 270 | } |
| 271 | |
| 272 | if (strsrch->getMatchedStart() != USEARCH_DONE || |
| 273 | strsrch->getMatchedLength() != 0) { |
| 274 | errln("Error with the initialization of match start and length"); |
| 275 | } |
| 276 | |
| 277 | // start of next matches |
| 278 | while (U_SUCCESS(status) && matchindex >= 0) { |
| 279 | matchlength = search->size[count]; |
| 280 | strsrch->next(status); |
| 281 | if (matchindex != strsrch->getMatchedStart() || |
| 282 | matchlength != strsrch->getMatchedLength()) { |
| 283 | char *str = toCharString(strsrch->getText()); |
| 284 | errln("Text: %s", str); |
| 285 | str = toCharString(strsrch->getPattern()); |
| 286 | errln("Pattern: %s", str); |
| 287 | errln("Error next match found at %d (len:%d); expected %d (len:%d)", |
| 288 | strsrch->getMatchedStart(), strsrch->getMatchedLength(), |
| 289 | matchindex, matchlength); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 290 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 291 | } |
| 292 | count ++; |
| 293 | |
| 294 | strsrch->getMatchedText(matchtext); |
| 295 | |
| 296 | if (U_FAILURE(status) || |
| 297 | strsrch->getText().compareBetween(matchindex, |
| 298 | matchindex + matchlength, |
| 299 | matchtext, 0, |
| 300 | matchtext.length())) { |
| 301 | errln("Error getting next matched text"); |
| 302 | } |
| 303 | |
| 304 | matchindex = search->offset[count]; |
| 305 | } |
| 306 | strsrch->next(status); |
| 307 | if (strsrch->getMatchedStart() != USEARCH_DONE || |
| 308 | strsrch->getMatchedLength() != 0) { |
| 309 | char *str = toCharString(strsrch->getText()); |
| 310 | errln("Text: %s", str); |
| 311 | str = toCharString(strsrch->getPattern()); |
| 312 | errln("Pattern: %s", str); |
| 313 | errln("Error next match found at %d (len:%d); expected <NO MATCH>", |
| 314 | strsrch->getMatchedStart(), strsrch->getMatchedLength()); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 315 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 316 | } |
| 317 | |
| 318 | // start of previous matches |
| 319 | count = count == 0 ? 0 : count - 1; |
| 320 | matchindex = search->offset[count]; |
| 321 | while (U_SUCCESS(status) && matchindex >= 0) { |
| 322 | matchlength = search->size[count]; |
| 323 | strsrch->previous(status); |
| 324 | if (matchindex != strsrch->getMatchedStart() || |
| 325 | matchlength != strsrch->getMatchedLength()) { |
| 326 | char *str = toCharString(strsrch->getText()); |
| 327 | errln("Text: %s", str); |
| 328 | str = toCharString(strsrch->getPattern()); |
| 329 | errln("Pattern: %s", str); |
| 330 | errln("Error previous match found at %d (len:%d); expected %d (len:%d)", |
| 331 | strsrch->getMatchedStart(), strsrch->getMatchedLength(), |
| 332 | matchindex, matchlength); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 333 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 334 | } |
| 335 | |
| 336 | strsrch->getMatchedText(matchtext); |
| 337 | |
| 338 | if (U_FAILURE(status) || |
| 339 | strsrch->getText().compareBetween(matchindex, |
| 340 | matchindex + matchlength, |
| 341 | matchtext, 0, |
| 342 | matchtext.length())) { |
| 343 | errln("Error getting previous matched text"); |
| 344 | } |
| 345 | |
| 346 | matchindex = count > 0 ? search->offset[count - 1] : -1; |
| 347 | count --; |
| 348 | } |
| 349 | strsrch->previous(status); |
| 350 | if (strsrch->getMatchedStart() != USEARCH_DONE || |
| 351 | strsrch->getMatchedLength() != 0) { |
| 352 | char *str = toCharString(strsrch->getText()); |
| 353 | errln("Text: %s", str); |
| 354 | str = toCharString(strsrch->getPattern()); |
| 355 | errln("Pattern: %s", str); |
| 356 | errln("Error previous match found at %d (len:%d); expected <NO MATCH>", |
| 357 | strsrch->getMatchedStart(), strsrch->getMatchedLength()); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 358 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 359 | } |
| 360 | |
| 361 | int32_t nextStart; |
| 362 | UBool isOverlap = (strsrch->getAttribute(USEARCH_OVERLAP) == USEARCH_ON); |
| 363 | |
| 364 | // start of following matches |
| 365 | count = 0; |
| 366 | matchindex = search->offset[count]; |
| 367 | nextStart = 0; |
| 368 | |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 369 | while (true) { |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 370 | strsrch->following(nextStart, status); |
| 371 | |
| 372 | if (matchindex < 0) { |
| 373 | if (strsrch->getMatchedStart() != USEARCH_DONE || |
| 374 | strsrch->getMatchedLength() != 0) { |
| 375 | char *str = toCharString(strsrch->getText()); |
| 376 | errln("Text: %s", str); |
| 377 | str = toCharString(strsrch->getPattern()); |
| 378 | errln("Pattern: %s", str); |
| 379 | errln("Error following match starting at %d (overlap:%d) found at %d (len:%d); expected <NO MATCH>", |
| 380 | nextStart, isOverlap, |
| 381 | strsrch->getMatchedStart(), strsrch->getMatchedLength()); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 382 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 383 | } |
| 384 | // no more matches |
| 385 | break; |
| 386 | } |
| 387 | |
| 388 | matchlength = search->size[count]; |
| 389 | if (strsrch->getMatchedStart() != matchindex |
| 390 | || strsrch->getMatchedLength() != matchlength |
| 391 | || U_FAILURE(status)) { |
| 392 | char *str = toCharString(strsrch->getText()); |
| 393 | errln("Text: %s\n", str); |
| 394 | str = toCharString(strsrch->getPattern()); |
| 395 | errln("Pattern: %s\n", str); |
| 396 | errln("Error following match starting at %d (overlap: %d) found at %d (len:%d); expected %d (len:%d)\n", |
| 397 | nextStart, isOverlap, |
| 398 | strsrch->getMatchedStart(), strsrch->getMatchedLength(), |
| 399 | matchindex, matchlength); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 400 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 401 | } |
| 402 | |
| 403 | if (isOverlap || strsrch->getMatchedLength() == 0) { |
| 404 | nextStart = strsrch->getMatchedStart() + 1; |
| 405 | } else { |
| 406 | nextStart = strsrch->getMatchedStart() + strsrch->getMatchedLength(); |
| 407 | } |
| 408 | |
| 409 | count++; |
| 410 | matchindex = search->offset[count]; |
| 411 | } |
| 412 | |
| 413 | // start preceding matches |
| 414 | count = -1; // last non-negative offset index, could be -1 if no match |
| 415 | while (search->offset[count + 1] >= 0) { |
| 416 | count++; |
| 417 | } |
| 418 | nextStart = strsrch->getText().length(); |
| 419 | |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 420 | while (true) { |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 421 | strsrch->preceding(nextStart, status); |
| 422 | |
| 423 | if (count < 0) { |
| 424 | if (strsrch->getMatchedStart() != USEARCH_DONE || strsrch->getMatchedLength() != 0) { |
| 425 | char *str = toCharString(strsrch->getText()); |
| 426 | errln("Text: %s\n", str); |
| 427 | str = toCharString(strsrch->getPattern()); |
| 428 | errln("Pattern: %s\n", str); |
| 429 | errln("Error preceding match starting at %d (overlap: %d) found at %d (len:%d); expected <NO MATCH>\n", |
| 430 | nextStart, isOverlap, |
| 431 | strsrch->getMatchedStart(), |
| 432 | strsrch->getMatchedLength()); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 433 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 434 | } |
| 435 | // no more matches |
| 436 | break; |
| 437 | } |
| 438 | |
| 439 | matchindex = search->offset[count]; |
| 440 | matchlength = search->size[count]; |
| 441 | if (strsrch->getMatchedStart() != matchindex |
| 442 | || strsrch->getMatchedLength() != matchlength |
| 443 | || U_FAILURE(status)) { |
| 444 | char *str = toCharString(strsrch->getText()); |
| 445 | errln("Text: %s\n", str); |
| 446 | str = toCharString(strsrch->getPattern()); |
| 447 | errln("Pattern: %s\n", str); |
| 448 | errln("Error preceding match starting at %d (overlap: %d) found at %d (len:%d); expected %d (len:%d)\n", |
| 449 | nextStart, isOverlap, |
| 450 | strsrch->getMatchedStart(), strsrch->getMatchedLength(), |
| 451 | matchindex, matchlength); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 452 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 453 | } |
| 454 | |
| 455 | nextStart = matchindex; |
| 456 | count--; |
| 457 | } |
| 458 | |
| 459 | strsrch->setAttribute(USEARCH_ELEMENT_COMPARISON, USEARCH_STANDARD_ELEMENT_COMPARISON, status); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 460 | return true; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 461 | } |
| 462 | |
| 463 | UBool StringSearchTest::assertEqual(const SearchData *search) |
| 464 | { |
| 465 | UErrorCode status = U_ZERO_ERROR; |
| 466 | |
| 467 | Collator *collator = getCollator(search->collator); |
| 468 | BreakIterator *breaker = getBreakIterator(search->breaker); |
| 469 | StringSearch *strsrch, *strsrch2; |
| 470 | UChar temp[128]; |
| 471 | |
| 472 | #if UCONFIG_NO_BREAK_ITERATION |
| 473 | if(search->breaker) { |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 474 | return true; /* skip test */ |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 475 | } |
| 476 | #endif |
| 477 | u_unescape(search->text, temp, 128); |
| 478 | UnicodeString text; |
| 479 | text.setTo(temp); |
| 480 | u_unescape(search->pattern, temp, 128); |
| 481 | UnicodeString pattern; |
| 482 | pattern.setTo(temp); |
| 483 | |
| 484 | #if !UCONFIG_NO_BREAK_ITERATION |
| 485 | if (breaker != NULL) { |
| 486 | breaker->setText(text); |
| 487 | } |
| 488 | #endif |
| 489 | collator->setStrength(getECollationStrength(search->strength)); |
| 490 | strsrch = new StringSearch(pattern, text, (RuleBasedCollator *)collator, |
| 491 | breaker, status); |
| 492 | if (U_FAILURE(status)) { |
| 493 | errln("Error opening string search %s", u_errorName(status)); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 494 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 495 | } |
| 496 | |
| 497 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 498 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 499 | delete strsrch; |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 500 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 501 | } |
| 502 | |
| 503 | |
| 504 | strsrch2 = strsrch->clone(); |
| 505 | if( strsrch2 == strsrch || *strsrch2 != *strsrch || |
| 506 | !assertEqualWithStringSearch(strsrch2, search) |
| 507 | ) { |
| 508 | infoln("failure with StringSearch.clone()"); |
| 509 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 510 | delete strsrch; |
| 511 | delete strsrch2; |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 512 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 513 | } |
| 514 | delete strsrch2; |
| 515 | |
| 516 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 517 | delete strsrch; |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 518 | return true; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 519 | } |
| 520 | |
| 521 | UBool StringSearchTest::assertCanonicalEqual(const SearchData *search) |
| 522 | { |
| 523 | UErrorCode status = U_ZERO_ERROR; |
| 524 | Collator *collator = getCollator(search->collator); |
| 525 | BreakIterator *breaker = getBreakIterator(search->breaker); |
| 526 | StringSearch *strsrch; |
| 527 | UChar temp[128]; |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 528 | UBool result = true; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 529 | |
| 530 | #if UCONFIG_NO_BREAK_ITERATION |
| 531 | if(search->breaker) { |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 532 | return true; /* skip test */ |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 533 | } |
| 534 | #endif |
| 535 | |
| 536 | u_unescape(search->text, temp, 128); |
| 537 | UnicodeString text; |
| 538 | text.setTo(temp); |
| 539 | u_unescape(search->pattern, temp, 128); |
| 540 | UnicodeString pattern; |
| 541 | pattern.setTo(temp); |
| 542 | |
| 543 | #if !UCONFIG_NO_BREAK_ITERATION |
| 544 | if (breaker != NULL) { |
| 545 | breaker->setText(text); |
| 546 | } |
| 547 | #endif |
| 548 | collator->setStrength(getECollationStrength(search->strength)); |
| 549 | collator->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status); |
| 550 | strsrch = new StringSearch(pattern, text, (RuleBasedCollator *)collator, |
| 551 | breaker, status); |
| 552 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 553 | if (U_FAILURE(status)) { |
| 554 | errln("Error opening string search %s", u_errorName(status)); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 555 | result = false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 556 | goto bail; |
| 557 | } |
| 558 | |
| 559 | if (!assertEqualWithStringSearch(strsrch, search)) { |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 560 | result = false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 561 | goto bail; |
| 562 | } |
| 563 | |
| 564 | bail: |
| 565 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 566 | collator->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_OFF, status); |
| 567 | delete strsrch; |
| 568 | |
| 569 | return result; |
| 570 | } |
| 571 | |
| 572 | UBool StringSearchTest::assertEqualWithAttribute(const SearchData *search, |
| 573 | USearchAttributeValue canonical, |
| 574 | USearchAttributeValue overlap) |
| 575 | { |
| 576 | UErrorCode status = U_ZERO_ERROR; |
| 577 | Collator *collator = getCollator(search->collator); |
| 578 | BreakIterator *breaker = getBreakIterator(search->breaker); |
| 579 | StringSearch *strsrch; |
| 580 | UChar temp[128]; |
| 581 | |
| 582 | |
| 583 | #if UCONFIG_NO_BREAK_ITERATION |
| 584 | if(search->breaker) { |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 585 | return true; /* skip test */ |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 586 | } |
| 587 | #endif |
| 588 | |
| 589 | u_unescape(search->text, temp, 128); |
| 590 | UnicodeString text; |
| 591 | text.setTo(temp); |
| 592 | u_unescape(search->pattern, temp, 128); |
| 593 | UnicodeString pattern; |
| 594 | pattern.setTo(temp); |
| 595 | |
| 596 | #if !UCONFIG_NO_BREAK_ITERATION |
| 597 | if (breaker != NULL) { |
| 598 | breaker->setText(text); |
| 599 | } |
| 600 | #endif |
| 601 | collator->setStrength(getECollationStrength(search->strength)); |
| 602 | strsrch = new StringSearch(pattern, text, (RuleBasedCollator *)collator, |
| 603 | breaker, status); |
| 604 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, canonical, status); |
| 605 | strsrch->setAttribute(USEARCH_OVERLAP, overlap, status); |
| 606 | |
| 607 | if (U_FAILURE(status)) { |
| 608 | errln("Error opening string search %s", u_errorName(status)); |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 609 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 610 | } |
| 611 | |
| 612 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 613 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 614 | delete strsrch; |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 615 | return false; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 616 | } |
| 617 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 618 | delete strsrch; |
Frank Tang | 1f164ee | 2022-11-08 12:31:27 -0800 | [diff] [blame^] | 619 | return true; |
Frank Tang | 3e05d9d | 2021-11-08 14:04:04 -0800 | [diff] [blame] | 620 | } |
| 621 | |
| 622 | void StringSearchTest::TestOpenClose() |
| 623 | { |
| 624 | UErrorCode status = U_ZERO_ERROR; |
| 625 | StringSearch *result; |
| 626 | BreakIterator *breakiter = m_en_wordbreaker_; |
| 627 | UnicodeString pattern; |
| 628 | UnicodeString text; |
| 629 | UnicodeString temp("a"); |
| 630 | StringCharacterIterator chariter(text); |
| 631 | |
| 632 | /* testing null arguments */ |
| 633 | result = new StringSearch(pattern, text, NULL, NULL, status); |
| 634 | if (U_SUCCESS(status)) { |
| 635 | errln("Error: NULL arguments should produce an error"); |
| 636 | } |
| 637 | delete result; |
| 638 | |
| 639 | chariter.setText(text); |
| 640 | status = U_ZERO_ERROR; |
| 641 | result = new StringSearch(pattern, chariter, NULL, NULL, status); |
| 642 | if (U_SUCCESS(status)) { |
| 643 | errln("Error: NULL arguments should produce an error"); |
| 644 | } |
| 645 | delete result; |
| 646 | |
| 647 | // No-op: text.append(0, 0x1); -- what was intended here? |
| 648 | status = U_ZERO_ERROR; |
| 649 | result = new StringSearch(pattern, text, NULL, NULL, status); |
| 650 | if (U_SUCCESS(status)) { |
| 651 | errln("Error: Empty pattern should produce an error"); |
| 652 | } |
| 653 | delete result; |
| 654 | |
| 655 | chariter.setText(text); |
| 656 | status = U_ZERO_ERROR; |
| 657 | result = new StringSearch(pattern, chariter, NULL, NULL, status); |
| 658 | if (U_SUCCESS(status)) { |
| 659 | errln("Error: Empty pattern should produce an error"); |
| 660 | } |
| 661 | delete result; |
| 662 | |
| 663 | text.remove(); |
| 664 | pattern.append(temp); |
| 665 | status = U_ZERO_ERROR; |
| 666 | result = new StringSearch(pattern, text, NULL, NULL, status); |
| 667 | if (U_SUCCESS(status)) { |
| 668 | errln("Error: Empty text should produce an error"); |
| 669 | } |
| 670 | delete result; |
| 671 | |
| 672 | chariter.setText(text); |
| 673 | status = U_ZERO_ERROR; |
| 674 | result = new StringSearch(pattern, chariter, NULL, NULL, status); |
| 675 | if (U_SUCCESS(status)) { |
| 676 | errln("Error: Empty text should produce an error"); |
| 677 | } |
| 678 | delete result; |
| 679 | |
| 680 | text.append(temp); |
| 681 | status = U_ZERO_ERROR; |
| 682 | result = new StringSearch(pattern, text, NULL, NULL, status); |
| 683 | if (U_SUCCESS(status)) { |
| 684 | errln("Error: NULL arguments should produce an error"); |
| 685 | } |
| 686 | delete result; |
| 687 | |
| 688 | chariter.setText(text); |
| 689 | status = U_ZERO_ERROR; |
| 690 | result = new StringSearch(pattern, chariter, NULL, NULL, status); |
| 691 | if (U_SUCCESS(status)) { |
| 692 | errln("Error: NULL arguments should produce an error"); |
| 693 | } |
| 694 | delete result; |
| 695 | |
| 696 | status = U_ZERO_ERROR; |
| 697 | result = new StringSearch(pattern, text, m_en_us_, NULL, status); |
| 698 | if (U_FAILURE(status)) { |
| 699 | errln("Error: NULL break iterator is valid for opening search"); |
| 700 | } |
| 701 | delete result; |
| 702 | |
| 703 | status = U_ZERO_ERROR; |
| 704 | result = new StringSearch(pattern, chariter, m_en_us_, NULL, status); |
| 705 | if (U_FAILURE(status)) { |
| 706 | errln("Error: NULL break iterator is valid for opening search"); |
| 707 | } |
| 708 | delete result; |
| 709 | |
| 710 | status = U_ZERO_ERROR; |
| 711 | result = new StringSearch(pattern, text, Locale::getEnglish(), NULL, status); |
| 712 | if (U_FAILURE(status) || result == NULL) { |
| 713 | errln("Error: NULL break iterator is valid for opening search"); |
| 714 | } |
| 715 | delete result; |
| 716 | |
| 717 | status = U_ZERO_ERROR; |
| 718 | result = new StringSearch(pattern, chariter, Locale::getEnglish(), NULL, status); |
| 719 | if (U_FAILURE(status)) { |
| 720 | errln("Error: NULL break iterator is valid for opening search"); |
| 721 | } |
| 722 | delete result; |
| 723 | |
| 724 | status = U_ZERO_ERROR; |
| 725 | result = new StringSearch(pattern, text, m_en_us_, breakiter, status); |
| 726 | if (U_FAILURE(status)) { |
| 727 | errln("Error: Break iterator is valid for opening search"); |
| 728 | } |
| 729 | delete result; |
| 730 | |
| 731 | status = U_ZERO_ERROR; |
| 732 | result = new StringSearch(pattern, chariter, m_en_us_, NULL, status); |
| 733 | if (U_FAILURE(status)) { |
| 734 | errln("Error: Break iterator is valid for opening search"); |
| 735 | } |
| 736 | delete result; |
| 737 | } |
| 738 | |
| 739 | void StringSearchTest::TestInitialization() |
| 740 | { |
| 741 | UErrorCode status = U_ZERO_ERROR; |
| 742 | UnicodeString pattern; |
| 743 | UnicodeString text; |
| 744 | UnicodeString temp("a"); |
| 745 | StringSearch *result; |
| 746 | int count; |
| 747 | |
| 748 | /* simple test on the pattern ce construction */ |
| 749 | pattern.append(temp); |
| 750 | pattern.append(temp); |
| 751 | text.append(temp); |
| 752 | text.append(temp); |
| 753 | text.append(temp); |
| 754 | result = new StringSearch(pattern, text, m_en_us_, NULL, status); |
| 755 | if (U_FAILURE(status)) { |
| 756 | errln("Error opening search %s", u_errorName(status)); |
| 757 | } |
| 758 | StringSearch *copy = new StringSearch(*result); |
| 759 | if (*(copy->getCollator()) != *(result->getCollator()) || |
| 760 | copy->getBreakIterator() != result->getBreakIterator() || |
| 761 | copy->getMatchedLength() != result->getMatchedLength() || |
| 762 | copy->getMatchedStart() != result->getMatchedStart() || |
| 763 | copy->getOffset() != result->getOffset() || |
| 764 | copy->getPattern() != result->getPattern() || |
| 765 | copy->getText() != result->getText() || |
| 766 | *(copy) != *(result)) |
| 767 | { |
| 768 | errln("Error copying StringSearch"); |
| 769 | } |
| 770 | delete copy; |
| 771 | |
| 772 | copy = result->safeClone(); |
| 773 | if (*(copy->getCollator()) != *(result->getCollator()) || |
| 774 | copy->getBreakIterator() != result->getBreakIterator() || |
| 775 | copy->getMatchedLength() != result->getMatchedLength() || |
| 776 | copy->getMatchedStart() != result->getMatchedStart() || |
| 777 | copy->getOffset() != result->getOffset() || |
| 778 | copy->getPattern() != result->getPattern() || |
| 779 | copy->getText() != result->getText() || |
| 780 | *(copy) != *(result)) { |
| 781 | errln("Error copying StringSearch"); |
| 782 | } |
| 783 | delete result; |
| 784 | |
| 785 | /* testing if an extremely large pattern will fail the initialization */ |
| 786 | for (count = 0; count < 512; count ++) { |
| 787 | pattern.append(temp); |
| 788 | } |
| 789 | result = new StringSearch(pattern, text, m_en_us_, NULL, status); |
| 790 | if (*result != *result) { |
| 791 | errln("Error: string search object expected to match itself"); |
| 792 | } |
| 793 | if (*result == *copy) { |
| 794 | errln("Error: string search objects are not expected to match"); |
| 795 | } |
| 796 | *copy = *result; |
| 797 | if (*(copy->getCollator()) != *(result->getCollator()) || |
| 798 | copy->getBreakIterator() != result->getBreakIterator() || |
| 799 | copy->getMatchedLength() != result->getMatchedLength() || |
| 800 | copy->getMatchedStart() != result->getMatchedStart() || |
| 801 | copy->getOffset() != result->getOffset() || |
| 802 | copy->getPattern() != result->getPattern() || |
| 803 | copy->getText() != result->getText() || |
| 804 | *(copy) != *(result)) { |
| 805 | errln("Error copying StringSearch"); |
| 806 | } |
| 807 | if (U_FAILURE(status)) { |
| 808 | errln("Error opening search %s", u_errorName(status)); |
| 809 | } |
| 810 | delete result; |
| 811 | delete copy; |
| 812 | } |
| 813 | |
| 814 | void StringSearchTest::TestBasic() |
| 815 | { |
| 816 | int count = 0; |
| 817 | while (BASIC[count].text != NULL) { |
| 818 | //printf("count %d", count); |
| 819 | if (!assertEqual(&BASIC[count])) { |
| 820 | infoln("Error at test number %d", count); |
| 821 | } |
| 822 | count ++; |
| 823 | } |
| 824 | } |
| 825 | |
| 826 | void StringSearchTest::TestNormExact() |
| 827 | { |
| 828 | int count = 0; |
| 829 | UErrorCode status = U_ZERO_ERROR; |
| 830 | m_en_us_->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status); |
| 831 | if (U_FAILURE(status)) { |
| 832 | errln("Error setting collation normalization %s", |
| 833 | u_errorName(status)); |
| 834 | } |
| 835 | while (BASIC[count].text != NULL) { |
| 836 | if (!assertEqual(&BASIC[count])) { |
| 837 | infoln("Error at test number %d", count); |
| 838 | } |
| 839 | count ++; |
| 840 | } |
| 841 | count = 0; |
| 842 | while (NORMEXACT[count].text != NULL) { |
| 843 | if (!assertEqual(&NORMEXACT[count])) { |
| 844 | infoln("Error at test number %d", count); |
| 845 | } |
| 846 | count ++; |
| 847 | } |
| 848 | m_en_us_->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_OFF, status); |
| 849 | count = 0; |
| 850 | while (NONNORMEXACT[count].text != NULL) { |
| 851 | if (!assertEqual(&NONNORMEXACT[count])) { |
| 852 | infoln("Error at test number %d", count); |
| 853 | } |
| 854 | count ++; |
| 855 | } |
| 856 | } |
| 857 | |
| 858 | void StringSearchTest::TestStrength() |
| 859 | { |
| 860 | int count = 0; |
| 861 | while (STRENGTH[count].text != NULL) { |
| 862 | if (!assertEqual(&STRENGTH[count])) { |
| 863 | infoln("Error at test number %d", count); |
| 864 | } |
| 865 | count ++; |
| 866 | } |
| 867 | } |
| 868 | |
| 869 | #if !UCONFIG_NO_BREAK_ITERATION |
| 870 | |
| 871 | void StringSearchTest::TestBreakIterator() |
| 872 | { |
| 873 | UChar temp[128]; |
| 874 | u_unescape(BREAKITERATOREXACT[0].text, temp, 128); |
| 875 | UnicodeString text; |
| 876 | text.setTo(temp, u_strlen(temp)); |
| 877 | u_unescape(BREAKITERATOREXACT[0].pattern, temp, 128); |
| 878 | UnicodeString pattern; |
| 879 | pattern.setTo(temp, u_strlen(temp)); |
| 880 | |
| 881 | UErrorCode status = U_ZERO_ERROR; |
| 882 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 883 | status); |
| 884 | if (U_FAILURE(status)) { |
| 885 | errln("Error opening string search %s", u_errorName(status)); |
| 886 | } |
| 887 | |
| 888 | strsrch->setBreakIterator(NULL, status); |
| 889 | if (U_FAILURE(status) || strsrch->getBreakIterator() != NULL) { |
| 890 | errln("Error usearch_getBreakIterator returned wrong object"); |
| 891 | } |
| 892 | |
| 893 | strsrch->setBreakIterator(m_en_characterbreaker_, status); |
| 894 | if (U_FAILURE(status) || |
| 895 | strsrch->getBreakIterator() != m_en_characterbreaker_) { |
| 896 | errln("Error usearch_getBreakIterator returned wrong object"); |
| 897 | } |
| 898 | |
| 899 | strsrch->setBreakIterator(m_en_wordbreaker_, status); |
| 900 | if (U_FAILURE(status) || |
| 901 | strsrch->getBreakIterator() != m_en_wordbreaker_) { |
| 902 | errln("Error usearch_getBreakIterator returned wrong object"); |
| 903 | } |
| 904 | |
| 905 | delete strsrch; |
| 906 | |
| 907 | int count = 0; |
| 908 | while (count < 4) { |
| 909 | // special purposes for tests numbers 0-3 |
| 910 | const SearchData *search = &(BREAKITERATOREXACT[count]); |
| 911 | RuleBasedCollator *collator = getCollator(search->collator); |
| 912 | BreakIterator *breaker = getBreakIterator(search->breaker); |
| 913 | StringSearch *strsrch; |
| 914 | |
| 915 | u_unescape(search->text, temp, 128); |
| 916 | text.setTo(temp, u_strlen(temp)); |
| 917 | u_unescape(search->pattern, temp, 128); |
| 918 | pattern.setTo(temp, u_strlen(temp)); |
| 919 | if (breaker != NULL) { |
| 920 | breaker->setText(text); |
| 921 | } |
| 922 | collator->setStrength(getECollationStrength(search->strength)); |
| 923 | |
| 924 | strsrch = new StringSearch(pattern, text, collator, breaker, status); |
| 925 | if (U_FAILURE(status) || |
| 926 | strsrch->getBreakIterator() != breaker) { |
| 927 | errln("Error setting break iterator"); |
| 928 | if (strsrch != NULL) { |
| 929 | delete strsrch; |
| 930 | } |
| 931 | } |
| 932 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 933 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 934 | delete strsrch; |
| 935 | } |
| 936 | search = &(BREAKITERATOREXACT[count + 1]); |
| 937 | breaker = getBreakIterator(search->breaker); |
| 938 | if (breaker != NULL) { |
| 939 | breaker->setText(text); |
| 940 | } |
| 941 | strsrch->setBreakIterator(breaker, status); |
| 942 | if (U_FAILURE(status) || |
| 943 | strsrch->getBreakIterator() != breaker) { |
| 944 | errln("Error setting break iterator"); |
| 945 | delete strsrch; |
| 946 | } |
| 947 | strsrch->reset(); |
| 948 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 949 | infoln("Error at test number %d", count); |
| 950 | } |
| 951 | delete strsrch; |
| 952 | count += 2; |
| 953 | } |
| 954 | count = 0; |
| 955 | while (BREAKITERATOREXACT[count].text != NULL) { |
| 956 | if (!assertEqual(&BREAKITERATOREXACT[count])) { |
| 957 | infoln("Error at test number %d", count); |
| 958 | } |
| 959 | count ++; |
| 960 | } |
| 961 | } |
| 962 | |
| 963 | #endif |
| 964 | |
| 965 | void StringSearchTest::TestVariable() |
| 966 | { |
| 967 | int count = 0; |
| 968 | UErrorCode status = U_ZERO_ERROR; |
| 969 | m_en_us_->setAttribute(UCOL_ALTERNATE_HANDLING, UCOL_SHIFTED, status); |
| 970 | if (U_FAILURE(status)) { |
| 971 | errln("Error setting collation alternate attribute %s", |
| 972 | u_errorName(status)); |
| 973 | } |
| 974 | while (VARIABLE[count].text != NULL) { |
| 975 | logln("variable %d", count); |
| 976 | if (!assertEqual(&VARIABLE[count])) { |
| 977 | infoln("Error at test number %d", count); |
| 978 | } |
| 979 | count ++; |
| 980 | } |
| 981 | m_en_us_->setAttribute(UCOL_ALTERNATE_HANDLING, UCOL_NON_IGNORABLE, |
| 982 | status); |
| 983 | } |
| 984 | |
| 985 | void StringSearchTest::TestOverlap() |
| 986 | { |
| 987 | int count = 0; |
| 988 | while (OVERLAP[count].text != NULL) { |
| 989 | if (!assertEqualWithAttribute(&OVERLAP[count], USEARCH_OFF, |
| 990 | USEARCH_ON)) { |
| 991 | errln("Error at overlap test number %d", count); |
| 992 | } |
| 993 | count ++; |
| 994 | } |
| 995 | count = 0; |
| 996 | while (NONOVERLAP[count].text != NULL) { |
| 997 | if (!assertEqual(&NONOVERLAP[count])) { |
| 998 | errln("Error at non overlap test number %d", count); |
| 999 | } |
| 1000 | count ++; |
| 1001 | } |
| 1002 | |
| 1003 | count = 0; |
| 1004 | while (count < 1) { |
| 1005 | const SearchData *search = &(OVERLAP[count]); |
| 1006 | UChar temp[128]; |
| 1007 | u_unescape(search->text, temp, 128); |
| 1008 | UnicodeString text; |
| 1009 | text.setTo(temp, u_strlen(temp)); |
| 1010 | u_unescape(search->pattern, temp, 128); |
| 1011 | UnicodeString pattern; |
| 1012 | pattern.setTo(temp, u_strlen(temp)); |
| 1013 | |
| 1014 | RuleBasedCollator *collator = getCollator(search->collator); |
| 1015 | UErrorCode status = U_ZERO_ERROR; |
| 1016 | StringSearch *strsrch = new StringSearch(pattern, text, |
| 1017 | collator, NULL, |
| 1018 | status); |
| 1019 | |
| 1020 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_ON, status); |
| 1021 | if (U_FAILURE(status) || |
| 1022 | strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_ON) { |
| 1023 | errln("Error setting overlap option"); |
| 1024 | } |
| 1025 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 1026 | delete strsrch; |
| 1027 | return; |
| 1028 | } |
| 1029 | |
| 1030 | search = &(NONOVERLAP[count]); |
| 1031 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_OFF, status); |
| 1032 | if (U_FAILURE(status) || |
| 1033 | strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_OFF) { |
| 1034 | errln("Error setting overlap option"); |
| 1035 | } |
| 1036 | strsrch->reset(); |
| 1037 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 1038 | delete strsrch; |
| 1039 | errln("Error at test number %d", count); |
| 1040 | } |
| 1041 | |
| 1042 | count ++; |
| 1043 | delete strsrch; |
| 1044 | } |
| 1045 | } |
| 1046 | |
| 1047 | void StringSearchTest::TestCollator() |
| 1048 | { |
| 1049 | // test collator that thinks "o" and "p" are the same thing |
| 1050 | UChar temp[128]; |
| 1051 | u_unescape(COLLATOR[0].text, temp, 128); |
| 1052 | UnicodeString text; |
| 1053 | text.setTo(temp, u_strlen(temp)); |
| 1054 | u_unescape(COLLATOR[0].pattern, temp, 128); |
| 1055 | UnicodeString pattern; |
| 1056 | pattern.setTo(temp, u_strlen(temp)); |
| 1057 | |
| 1058 | UErrorCode status = U_ZERO_ERROR; |
| 1059 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 1060 | status); |
| 1061 | if (U_FAILURE(status)) { |
| 1062 | errln("Error opening string search %s", u_errorName(status)); |
| 1063 | delete strsrch; |
| 1064 | return; |
| 1065 | } |
| 1066 | if (!assertEqualWithStringSearch(strsrch, &COLLATOR[0])) { |
| 1067 | delete strsrch; |
| 1068 | return; |
| 1069 | } |
| 1070 | |
| 1071 | u_unescape(TESTCOLLATORRULE, temp, 128); |
| 1072 | UnicodeString rules; |
| 1073 | rules.setTo(temp, u_strlen(temp)); |
| 1074 | RuleBasedCollator *tailored = new RuleBasedCollator(rules, status); |
| 1075 | tailored->setStrength(getECollationStrength(COLLATOR[1].strength)); |
| 1076 | |
| 1077 | if (U_FAILURE(status)) { |
| 1078 | errln("Error opening rule based collator %s", u_errorName(status)); |
| 1079 | delete strsrch; |
| 1080 | delete tailored; |
| 1081 | return; |
| 1082 | } |
| 1083 | |
| 1084 | strsrch->setCollator(tailored, status); |
| 1085 | if (U_FAILURE(status) || (*strsrch->getCollator()) != (*tailored)) { |
| 1086 | errln("Error setting rule based collator"); |
| 1087 | delete strsrch; |
| 1088 | delete tailored; |
| 1089 | } |
| 1090 | strsrch->reset(); |
| 1091 | if (!assertEqualWithStringSearch(strsrch, &COLLATOR[1])) { |
| 1092 | delete strsrch; |
| 1093 | delete tailored; |
| 1094 | return; |
| 1095 | } |
| 1096 | |
| 1097 | strsrch->setCollator(m_en_us_, status); |
| 1098 | strsrch->reset(); |
| 1099 | if (U_FAILURE(status) || (*strsrch->getCollator()) != (*m_en_us_)) { |
| 1100 | errln("Error setting rule based collator"); |
| 1101 | delete strsrch; |
| 1102 | delete tailored; |
| 1103 | } |
| 1104 | if (!assertEqualWithStringSearch(strsrch, &COLLATOR[0])) { |
| 1105 | errln("Error searching collator test"); |
| 1106 | } |
| 1107 | delete strsrch; |
| 1108 | delete tailored; |
| 1109 | } |
| 1110 | |
| 1111 | void StringSearchTest::TestPattern() |
| 1112 | { |
| 1113 | |
| 1114 | UChar temp[512]; |
| 1115 | int templength; |
| 1116 | u_unescape(PATTERN[0].text, temp, 512); |
| 1117 | UnicodeString text; |
| 1118 | text.setTo(temp, u_strlen(temp)); |
| 1119 | u_unescape(PATTERN[0].pattern, temp, 512); |
| 1120 | UnicodeString pattern; |
| 1121 | pattern.setTo(temp, u_strlen(temp)); |
| 1122 | |
| 1123 | m_en_us_->setStrength(getECollationStrength(PATTERN[0].strength)); |
| 1124 | UErrorCode status = U_ZERO_ERROR; |
| 1125 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 1126 | status); |
| 1127 | |
| 1128 | if (U_FAILURE(status)) { |
| 1129 | errln("Error opening string search %s", u_errorName(status)); |
| 1130 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1131 | if (strsrch != NULL) { |
| 1132 | delete strsrch; |
| 1133 | } |
| 1134 | return; |
| 1135 | } |
| 1136 | if (strsrch->getPattern() != pattern) { |
| 1137 | errln("Error setting pattern"); |
| 1138 | } |
| 1139 | if (!assertEqualWithStringSearch(strsrch, &PATTERN[0])) { |
| 1140 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1141 | if (strsrch != NULL) { |
| 1142 | delete strsrch; |
| 1143 | } |
| 1144 | return; |
| 1145 | } |
| 1146 | |
| 1147 | u_unescape(PATTERN[1].pattern, temp, 512); |
| 1148 | pattern.setTo(temp, u_strlen(temp)); |
| 1149 | strsrch->setPattern(pattern, status); |
| 1150 | if (pattern != strsrch->getPattern()) { |
| 1151 | errln("Error setting pattern"); |
| 1152 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1153 | if (strsrch != NULL) { |
| 1154 | delete strsrch; |
| 1155 | } |
| 1156 | return; |
| 1157 | } |
| 1158 | strsrch->reset(); |
| 1159 | if (U_FAILURE(status)) { |
| 1160 | errln("Error setting pattern %s", u_errorName(status)); |
| 1161 | } |
| 1162 | if (!assertEqualWithStringSearch(strsrch, &PATTERN[1])) { |
| 1163 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1164 | if (strsrch != NULL) { |
| 1165 | delete strsrch; |
| 1166 | } |
| 1167 | return; |
| 1168 | } |
| 1169 | |
| 1170 | u_unescape(PATTERN[0].pattern, temp, 512); |
| 1171 | pattern.setTo(temp, u_strlen(temp)); |
| 1172 | strsrch->setPattern(pattern, status); |
| 1173 | if (pattern != strsrch->getPattern()) { |
| 1174 | errln("Error setting pattern"); |
| 1175 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1176 | if (strsrch != NULL) { |
| 1177 | delete strsrch; |
| 1178 | } |
| 1179 | return; |
| 1180 | } |
| 1181 | strsrch->reset(); |
| 1182 | if (U_FAILURE(status)) { |
| 1183 | errln("Error setting pattern %s", u_errorName(status)); |
| 1184 | } |
| 1185 | if (!assertEqualWithStringSearch(strsrch, &PATTERN[0])) { |
| 1186 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1187 | if (strsrch != NULL) { |
| 1188 | delete strsrch; |
| 1189 | } |
| 1190 | return; |
| 1191 | } |
| 1192 | /* enormous pattern size to see if this crashes */ |
| 1193 | for (templength = 0; templength != 512; templength ++) { |
| 1194 | temp[templength] = 0x61; |
| 1195 | } |
| 1196 | temp[511] = 0; |
| 1197 | pattern.setTo(temp, 511); |
| 1198 | strsrch->setPattern(pattern, status); |
| 1199 | if (U_FAILURE(status)) { |
| 1200 | errln("Error setting pattern with size 512, %s", u_errorName(status)); |
| 1201 | } |
| 1202 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1203 | if (strsrch != NULL) { |
| 1204 | delete strsrch; |
| 1205 | } |
| 1206 | } |
| 1207 | |
| 1208 | void StringSearchTest::TestText() |
| 1209 | { |
| 1210 | UChar temp[128]; |
| 1211 | u_unescape(TEXT[0].text, temp, 128); |
| 1212 | UnicodeString text; |
| 1213 | text.setTo(temp, u_strlen(temp)); |
| 1214 | u_unescape(TEXT[0].pattern, temp, 128); |
| 1215 | UnicodeString pattern; |
| 1216 | pattern.setTo(temp, u_strlen(temp)); |
| 1217 | |
| 1218 | UErrorCode status = U_ZERO_ERROR; |
| 1219 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 1220 | status); |
| 1221 | if (U_FAILURE(status)) { |
| 1222 | errln("Error opening string search %s", u_errorName(status)); |
| 1223 | return; |
| 1224 | } |
| 1225 | if (text != strsrch->getText()) { |
| 1226 | errln("Error setting text"); |
| 1227 | } |
| 1228 | if (!assertEqualWithStringSearch(strsrch, &TEXT[0])) { |
| 1229 | delete strsrch; |
| 1230 | return; |
| 1231 | } |
| 1232 | |
| 1233 | u_unescape(TEXT[1].text, temp, 128); |
| 1234 | text.setTo(temp, u_strlen(temp)); |
| 1235 | strsrch->setText(text, status); |
| 1236 | if (text != strsrch->getText()) { |
| 1237 | errln("Error setting text"); |
| 1238 | delete strsrch; |
| 1239 | return; |
| 1240 | } |
| 1241 | if (U_FAILURE(status)) { |
| 1242 | errln("Error setting text %s", u_errorName(status)); |
| 1243 | } |
| 1244 | if (!assertEqualWithStringSearch(strsrch, &TEXT[1])) { |
| 1245 | delete strsrch; |
| 1246 | return; |
| 1247 | } |
| 1248 | |
| 1249 | u_unescape(TEXT[0].text, temp, 128); |
| 1250 | text.setTo(temp, u_strlen(temp)); |
| 1251 | StringCharacterIterator chariter(text); |
| 1252 | strsrch->setText(chariter, status); |
| 1253 | if (text != strsrch->getText()) { |
| 1254 | errln("Error setting text"); |
| 1255 | delete strsrch; |
| 1256 | return; |
| 1257 | } |
| 1258 | if (U_FAILURE(status)) { |
| 1259 | errln("Error setting pattern %s", u_errorName(status)); |
| 1260 | } |
| 1261 | if (!assertEqualWithStringSearch(strsrch, &TEXT[0])) { |
| 1262 | errln("Error searching within set text"); |
| 1263 | } |
| 1264 | delete strsrch; |
| 1265 | } |
| 1266 | |
| 1267 | void StringSearchTest::TestCompositeBoundaries() |
| 1268 | { |
| 1269 | int count = 0; |
| 1270 | while (COMPOSITEBOUNDARIES[count].text != NULL) { |
| 1271 | logln("composite %d", count); |
| 1272 | if (!assertEqual(&COMPOSITEBOUNDARIES[count])) { |
| 1273 | errln("Error at test number %d", count); |
| 1274 | } |
| 1275 | count ++; |
| 1276 | } |
| 1277 | } |
| 1278 | |
| 1279 | void StringSearchTest::TestGetSetOffset() |
| 1280 | { |
| 1281 | UErrorCode status = U_ZERO_ERROR; |
| 1282 | UnicodeString pattern("1234567890123456"); |
| 1283 | UnicodeString text("12345678901234567890123456789012"); |
| 1284 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, |
| 1285 | NULL, status); |
| 1286 | /* testing out of bounds error */ |
| 1287 | strsrch->setOffset(-1, status); |
| 1288 | if (U_SUCCESS(status)) { |
| 1289 | errln("Error expecting set offset error"); |
| 1290 | } |
| 1291 | strsrch->setOffset(128, status); |
| 1292 | if (U_SUCCESS(status)) { |
| 1293 | errln("Error expecting set offset error"); |
| 1294 | } |
| 1295 | int index = 0; |
| 1296 | while (BASIC[index].text != NULL) { |
| 1297 | UErrorCode status = U_ZERO_ERROR; |
| 1298 | SearchData search = BASIC[index ++]; |
| 1299 | UChar temp[128]; |
| 1300 | |
| 1301 | u_unescape(search.text, temp, 128); |
| 1302 | text.setTo(temp, u_strlen(temp)); |
| 1303 | u_unescape(search.pattern, temp, 128); |
| 1304 | pattern.setTo(temp, u_strlen(temp)); |
| 1305 | strsrch->setText(text, status); |
| 1306 | strsrch->setPattern(pattern, status); |
| 1307 | strsrch->getCollator()->setStrength(getECollationStrength( |
| 1308 | search.strength)); |
| 1309 | strsrch->reset(); |
| 1310 | |
| 1311 | int count = 0; |
| 1312 | int32_t matchindex = search.offset[count]; |
| 1313 | while (U_SUCCESS(status) && matchindex >= 0) { |
| 1314 | int32_t matchlength = search.size[count]; |
| 1315 | strsrch->next(status); |
| 1316 | if (matchindex != strsrch->getMatchedStart() || |
| 1317 | matchlength != strsrch->getMatchedLength()) { |
| 1318 | char *str = toCharString(strsrch->getText()); |
| 1319 | errln("Text: %s", str); |
| 1320 | str = toCharString(strsrch->getPattern()); |
| 1321 | errln("Pattern: %s", str); |
| 1322 | errln("Error match found at %d %d", |
| 1323 | strsrch->getMatchedStart(), |
| 1324 | strsrch->getMatchedLength()); |
| 1325 | return; |
| 1326 | } |
| 1327 | matchindex = search.offset[count + 1] == -1 ? -1 : |
| 1328 | search.offset[count + 2]; |
| 1329 | if (search.offset[count + 1] != -1) { |
| 1330 | strsrch->setOffset(search.offset[count + 1] + 1, status); |
| 1331 | if (strsrch->getOffset() != search.offset[count + 1] + 1) { |
| 1332 | errln("Error setting offset\n"); |
| 1333 | return; |
| 1334 | } |
| 1335 | } |
| 1336 | |
| 1337 | count += 2; |
| 1338 | } |
| 1339 | strsrch->next(status); |
| 1340 | if (strsrch->getMatchedStart() != USEARCH_DONE) { |
| 1341 | char *str = toCharString(strsrch->getText()); |
| 1342 | errln("Text: %s", str); |
| 1343 | str = toCharString(strsrch->getPattern()); |
| 1344 | errln("Pattern: %s", str); |
| 1345 | errln("Error match found at %d %d", |
| 1346 | strsrch->getMatchedStart(), |
| 1347 | strsrch->getMatchedLength()); |
| 1348 | return; |
| 1349 | } |
| 1350 | } |
| 1351 | strsrch->getCollator()->setStrength(getECollationStrength( |
| 1352 | UCOL_TERTIARY)); |
| 1353 | delete strsrch; |
| 1354 | } |
| 1355 | |
| 1356 | void StringSearchTest::TestGetSetAttribute() |
| 1357 | { |
| 1358 | UErrorCode status = U_ZERO_ERROR; |
| 1359 | UnicodeString pattern("pattern"); |
| 1360 | UnicodeString text("text"); |
| 1361 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 1362 | status); |
| 1363 | if (U_FAILURE(status)) { |
| 1364 | errln("Error opening search %s", u_errorName(status)); |
| 1365 | return; |
| 1366 | } |
| 1367 | |
| 1368 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_DEFAULT, status); |
| 1369 | if (U_FAILURE(status) || |
| 1370 | strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_OFF) { |
| 1371 | errln("Error setting overlap to the default"); |
| 1372 | } |
| 1373 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_ON, status); |
| 1374 | if (U_FAILURE(status) || |
| 1375 | strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_ON) { |
| 1376 | errln("Error setting overlap true"); |
| 1377 | } |
| 1378 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_OFF, status); |
| 1379 | if (U_FAILURE(status) || |
| 1380 | strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_OFF) { |
| 1381 | errln("Error setting overlap false"); |
| 1382 | } |
| 1383 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_ATTRIBUTE_VALUE_COUNT, |
| 1384 | status); |
| 1385 | if (U_SUCCESS(status)) { |
| 1386 | errln("Error setting overlap to illegal value"); |
| 1387 | } |
| 1388 | status = U_ZERO_ERROR; |
| 1389 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_DEFAULT, status); |
| 1390 | if (U_FAILURE(status) || |
| 1391 | strsrch->getAttribute(USEARCH_CANONICAL_MATCH) != USEARCH_OFF) { |
| 1392 | errln("Error setting canonical match to the default"); |
| 1393 | } |
| 1394 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1395 | if (U_FAILURE(status) || |
| 1396 | strsrch->getAttribute(USEARCH_CANONICAL_MATCH) != USEARCH_ON) { |
| 1397 | errln("Error setting canonical match true"); |
| 1398 | } |
| 1399 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_OFF, status); |
| 1400 | if (U_FAILURE(status) || |
| 1401 | strsrch->getAttribute(USEARCH_CANONICAL_MATCH) != USEARCH_OFF) { |
| 1402 | errln("Error setting canonical match false"); |
| 1403 | } |
| 1404 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, |
| 1405 | USEARCH_ATTRIBUTE_VALUE_COUNT, status); |
| 1406 | if (U_SUCCESS(status)) { |
| 1407 | errln("Error setting canonical match to illegal value"); |
| 1408 | } |
| 1409 | status = U_ZERO_ERROR; |
| 1410 | strsrch->setAttribute(USEARCH_ATTRIBUTE_COUNT, USEARCH_DEFAULT, status); |
| 1411 | if (U_SUCCESS(status)) { |
| 1412 | errln("Error setting illegal attribute success"); |
| 1413 | } |
| 1414 | |
| 1415 | delete strsrch; |
| 1416 | } |
| 1417 | |
| 1418 | void StringSearchTest::TestGetMatch() |
| 1419 | { |
| 1420 | UChar temp[128]; |
| 1421 | SearchData search = MATCH[0]; |
| 1422 | u_unescape(search.text, temp, 128); |
| 1423 | UnicodeString text; |
| 1424 | text.setTo(temp, u_strlen(temp)); |
| 1425 | u_unescape(search.pattern, temp, 128); |
| 1426 | UnicodeString pattern; |
| 1427 | pattern.setTo(temp, u_strlen(temp)); |
| 1428 | |
| 1429 | UErrorCode status = U_ZERO_ERROR; |
| 1430 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 1431 | status); |
| 1432 | if (U_FAILURE(status)) { |
| 1433 | errln("Error opening string search %s", u_errorName(status)); |
| 1434 | if (strsrch != NULL) { |
| 1435 | delete strsrch; |
| 1436 | } |
| 1437 | return; |
| 1438 | } |
| 1439 | |
| 1440 | int count = 0; |
| 1441 | int32_t matchindex = search.offset[count]; |
| 1442 | UnicodeString matchtext; |
| 1443 | while (U_SUCCESS(status) && matchindex >= 0) { |
| 1444 | int32_t matchlength = search.size[count]; |
| 1445 | strsrch->next(status); |
| 1446 | if (matchindex != strsrch->getMatchedStart() || |
| 1447 | matchlength != strsrch->getMatchedLength()) { |
| 1448 | char *str = toCharString(strsrch->getText()); |
| 1449 | errln("Text: %s", str); |
| 1450 | str = toCharString(strsrch->getPattern()); |
| 1451 | errln("Pattern: %s", str); |
| 1452 | errln("Error match found at %d %d", strsrch->getMatchedStart(), |
| 1453 | strsrch->getMatchedLength()); |
| 1454 | return; |
| 1455 | } |
| 1456 | count ++; |
| 1457 | |
| 1458 | status = U_ZERO_ERROR; |
| 1459 | strsrch->getMatchedText(matchtext); |
| 1460 | if (matchtext.length() != matchlength || U_FAILURE(status)){ |
| 1461 | errln("Error getting match text"); |
| 1462 | } |
| 1463 | matchindex = search.offset[count]; |
| 1464 | } |
| 1465 | status = U_ZERO_ERROR; |
| 1466 | strsrch->next(status); |
| 1467 | if (strsrch->getMatchedStart() != USEARCH_DONE || |
| 1468 | strsrch->getMatchedLength() != 0) { |
| 1469 | errln("Error end of match not found"); |
| 1470 | } |
| 1471 | status = U_ZERO_ERROR; |
| 1472 | strsrch->getMatchedText(matchtext); |
| 1473 | if (matchtext.length() != 0) { |
| 1474 | errln("Error getting null matches"); |
| 1475 | } |
| 1476 | delete strsrch; |
| 1477 | } |
| 1478 | |
| 1479 | void StringSearchTest::TestSetMatch() |
| 1480 | { |
| 1481 | int count = 0; |
| 1482 | while (MATCH[count].text != NULL) { |
| 1483 | SearchData search = MATCH[count]; |
| 1484 | UChar temp[128]; |
| 1485 | UErrorCode status = U_ZERO_ERROR; |
| 1486 | u_unescape(search.text, temp, 128); |
| 1487 | UnicodeString text; |
| 1488 | text.setTo(temp, u_strlen(temp)); |
| 1489 | u_unescape(search.pattern, temp, 128); |
| 1490 | UnicodeString pattern; |
| 1491 | pattern.setTo(temp, u_strlen(temp)); |
| 1492 | |
| 1493 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, |
| 1494 | NULL, status); |
| 1495 | if (U_FAILURE(status)) { |
| 1496 | errln("Error opening string search %s", u_errorName(status)); |
| 1497 | if (strsrch != NULL) { |
| 1498 | delete strsrch; |
| 1499 | } |
| 1500 | return; |
| 1501 | } |
| 1502 | |
| 1503 | int size = 0; |
| 1504 | while (search.offset[size] != -1) { |
| 1505 | size ++; |
| 1506 | } |
| 1507 | |
| 1508 | if (strsrch->first(status) != search.offset[0] || U_FAILURE(status)) { |
| 1509 | errln("Error getting first match"); |
| 1510 | } |
| 1511 | if (strsrch->last(status) != search.offset[size -1] || |
| 1512 | U_FAILURE(status)) { |
| 1513 | errln("Error getting last match"); |
| 1514 | } |
| 1515 | |
| 1516 | int index = 0; |
| 1517 | while (index < size) { |
| 1518 | if (index + 2 < size) { |
| 1519 | if (strsrch->following(search.offset[index + 2] - 1, status) |
| 1520 | != search.offset[index + 2] || U_FAILURE(status)) { |
| 1521 | errln("Error getting following match at index %d", |
| 1522 | search.offset[index + 2] - 1); |
| 1523 | } |
| 1524 | } |
| 1525 | if (index + 1 < size) { |
| 1526 | if (strsrch->preceding(search.offset[index + 1] + |
| 1527 | search.size[index + 1] + 1, |
| 1528 | status) != search.offset[index + 1] || |
| 1529 | U_FAILURE(status)) { |
| 1530 | errln("Error getting preceding match at index %d", |
| 1531 | search.offset[index + 1] + 1); |
| 1532 | } |
| 1533 | } |
| 1534 | index += 2; |
| 1535 | } |
| 1536 | status = U_ZERO_ERROR; |
| 1537 | if (strsrch->following(text.length(), status) != USEARCH_DONE) { |
| 1538 | errln("Error expecting out of bounds match"); |
| 1539 | } |
| 1540 | if (strsrch->preceding(0, status) != USEARCH_DONE) { |
| 1541 | errln("Error expecting out of bounds match"); |
| 1542 | } |
| 1543 | count ++; |
| 1544 | delete strsrch; |
| 1545 | } |
| 1546 | } |
| 1547 | |
| 1548 | void StringSearchTest::TestReset() |
| 1549 | { |
| 1550 | UErrorCode status = U_ZERO_ERROR; |
| 1551 | UnicodeString text("fish fish"); |
| 1552 | UnicodeString pattern("s"); |
| 1553 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 1554 | status); |
| 1555 | if (U_FAILURE(status)) { |
| 1556 | errln("Error opening string search %s", u_errorName(status)); |
| 1557 | if (strsrch != NULL) { |
| 1558 | delete strsrch; |
| 1559 | } |
| 1560 | return; |
| 1561 | } |
| 1562 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_ON, status); |
| 1563 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1564 | strsrch->setOffset(9, status); |
| 1565 | if (U_FAILURE(status)) { |
| 1566 | errln("Error setting attributes and offsets"); |
| 1567 | } |
| 1568 | else { |
| 1569 | strsrch->reset(); |
| 1570 | if (strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_OFF || |
| 1571 | strsrch->getAttribute(USEARCH_CANONICAL_MATCH) != USEARCH_OFF || |
| 1572 | strsrch->getOffset() != 0 || strsrch->getMatchedLength() != 0 || |
| 1573 | strsrch->getMatchedStart() != USEARCH_DONE) { |
| 1574 | errln("Error resetting string search"); |
| 1575 | } |
| 1576 | strsrch->previous(status); |
| 1577 | if (strsrch->getMatchedStart() != 7 || |
| 1578 | strsrch->getMatchedLength() != 1) { |
| 1579 | errln("Error resetting string search\n"); |
| 1580 | } |
| 1581 | } |
| 1582 | delete strsrch; |
| 1583 | } |
| 1584 | |
| 1585 | void StringSearchTest::TestSupplementary() |
| 1586 | { |
| 1587 | int count = 0; |
| 1588 | while (SUPPLEMENTARY[count].text != NULL) { |
| 1589 | if (!assertEqual(&SUPPLEMENTARY[count])) { |
| 1590 | errln("Error at test number %d", count); |
| 1591 | } |
| 1592 | count ++; |
| 1593 | } |
| 1594 | } |
| 1595 | |
| 1596 | void StringSearchTest::TestContraction() |
| 1597 | { |
| 1598 | UChar temp[128]; |
| 1599 | UErrorCode status = U_ZERO_ERROR; |
| 1600 | |
| 1601 | u_unescape(CONTRACTIONRULE, temp, 128); |
| 1602 | UnicodeString rules; |
| 1603 | rules.setTo(temp, u_strlen(temp)); |
| 1604 | RuleBasedCollator *collator = new RuleBasedCollator(rules, |
| 1605 | getECollationStrength(UCOL_TERTIARY), UCOL_ON, status); |
| 1606 | if (U_FAILURE(status)) { |
| 1607 | errln("Error opening collator %s", u_errorName(status)); |
| 1608 | } |
| 1609 | UnicodeString text("text"); |
| 1610 | UnicodeString pattern("pattern"); |
| 1611 | StringSearch *strsrch = new StringSearch(pattern, text, collator, NULL, |
| 1612 | status); |
| 1613 | if (U_FAILURE(status)) { |
| 1614 | errln("Error opening string search %s", u_errorName(status)); |
| 1615 | } |
| 1616 | |
| 1617 | int count = 0; |
| 1618 | while (CONTRACTION[count].text != NULL) { |
| 1619 | u_unescape(CONTRACTION[count].text, temp, 128); |
| 1620 | text.setTo(temp, u_strlen(temp)); |
| 1621 | u_unescape(CONTRACTION[count].pattern, temp, 128); |
| 1622 | pattern.setTo(temp, u_strlen(temp)); |
| 1623 | strsrch->setText(text, status); |
| 1624 | strsrch->setPattern(pattern, status); |
| 1625 | if (!assertEqualWithStringSearch(strsrch, &CONTRACTION[count])) { |
| 1626 | errln("Error at test number %d", count); |
| 1627 | } |
| 1628 | count ++; |
| 1629 | } |
| 1630 | delete strsrch; |
| 1631 | delete collator; |
| 1632 | } |
| 1633 | |
| 1634 | void StringSearchTest::TestIgnorable() |
| 1635 | { |
| 1636 | UChar temp[128]; |
| 1637 | u_unescape(IGNORABLERULE, temp, 128); |
| 1638 | UnicodeString rules; |
| 1639 | rules.setTo(temp, u_strlen(temp)); |
| 1640 | UErrorCode status = U_ZERO_ERROR; |
| 1641 | int count = 0; |
| 1642 | RuleBasedCollator *collator = new RuleBasedCollator(rules, |
| 1643 | getECollationStrength(IGNORABLE[count].strength), |
| 1644 | UCOL_ON, status); |
| 1645 | if (U_FAILURE(status)) { |
| 1646 | errln("Error opening collator %s", u_errorName(status)); |
| 1647 | return; |
| 1648 | } |
| 1649 | UnicodeString pattern("pattern"); |
| 1650 | UnicodeString text("text"); |
| 1651 | StringSearch *strsrch = new StringSearch(pattern, text, collator, NULL, |
| 1652 | status); |
| 1653 | if (U_FAILURE(status)) { |
| 1654 | errln("Error opening string search %s", u_errorName(status)); |
| 1655 | delete collator; |
| 1656 | return; |
| 1657 | } |
| 1658 | |
| 1659 | while (IGNORABLE[count].text != NULL) { |
| 1660 | u_unescape(IGNORABLE[count].text, temp, 128); |
| 1661 | text.setTo(temp, u_strlen(temp)); |
| 1662 | u_unescape(IGNORABLE[count].pattern, temp, 128); |
| 1663 | pattern.setTo(temp, u_strlen(temp)); |
| 1664 | strsrch->setText(text, status); |
| 1665 | strsrch->setPattern(pattern, status); |
| 1666 | if (!assertEqualWithStringSearch(strsrch, &IGNORABLE[count])) { |
| 1667 | errln("Error at test number %d", count); |
| 1668 | } |
| 1669 | count ++; |
| 1670 | } |
| 1671 | delete strsrch; |
| 1672 | delete collator; |
| 1673 | } |
| 1674 | |
| 1675 | void StringSearchTest::TestDiacriticMatch() |
| 1676 | { |
| 1677 | UChar temp[128]; |
| 1678 | UErrorCode status = U_ZERO_ERROR; |
| 1679 | int count = 0; |
| 1680 | RuleBasedCollator* coll = NULL; |
| 1681 | StringSearch *strsrch = NULL; |
| 1682 | |
| 1683 | UnicodeString pattern("pattern"); |
| 1684 | UnicodeString text("text"); |
| 1685 | |
| 1686 | const SearchData *search; |
| 1687 | |
| 1688 | search = &(DIACRITICMATCH[count]); |
| 1689 | while (search->text != NULL) { |
| 1690 | coll = getCollator(search->collator); |
| 1691 | coll->setStrength(getECollationStrength(search->strength)); |
| 1692 | strsrch = new StringSearch(pattern, text, coll, getBreakIterator(search->breaker), status); |
| 1693 | if (U_FAILURE(status)) { |
| 1694 | errln("Error opening string search %s", u_errorName(status)); |
| 1695 | return; |
| 1696 | } |
| 1697 | u_unescape(search->text, temp, 128); |
| 1698 | text.setTo(temp, u_strlen(temp)); |
| 1699 | u_unescape(search->pattern, temp, 128); |
| 1700 | pattern.setTo(temp, u_strlen(temp)); |
| 1701 | strsrch->setText(text, status); |
| 1702 | strsrch->setPattern(pattern, status); |
| 1703 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 1704 | errln("Error at test number %d", count); |
| 1705 | } |
| 1706 | search = &(DIACRITICMATCH[++count]); |
| 1707 | delete strsrch; |
| 1708 | } |
| 1709 | |
| 1710 | } |
| 1711 | |
| 1712 | void StringSearchTest::TestCanonical() |
| 1713 | { |
| 1714 | int count = 0; |
| 1715 | while (BASICCANONICAL[count].text != NULL) { |
| 1716 | if (!assertCanonicalEqual(&BASICCANONICAL[count])) { |
| 1717 | errln("Error at test number %d", count); |
| 1718 | } |
| 1719 | count ++; |
| 1720 | } |
| 1721 | } |
| 1722 | |
| 1723 | void StringSearchTest::TestNormCanonical() |
| 1724 | { |
| 1725 | UErrorCode status = U_ZERO_ERROR; |
| 1726 | m_en_us_->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status); |
| 1727 | int count = 0; |
| 1728 | while (NORMCANONICAL[count].text != NULL) { |
| 1729 | if (!assertCanonicalEqual(&NORMCANONICAL[count])) { |
| 1730 | errln("Error at test number %d", count); |
| 1731 | } |
| 1732 | count ++; |
| 1733 | } |
| 1734 | m_en_us_->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_OFF, status); |
| 1735 | } |
| 1736 | |
| 1737 | void StringSearchTest::TestStrengthCanonical() |
| 1738 | { |
| 1739 | int count = 0; |
| 1740 | while (STRENGTHCANONICAL[count].text != NULL) { |
| 1741 | if (!assertCanonicalEqual(&STRENGTHCANONICAL[count])) { |
| 1742 | errln("Error at test number %d", count); |
| 1743 | } |
| 1744 | count ++; |
| 1745 | } |
| 1746 | } |
| 1747 | |
| 1748 | #if !UCONFIG_NO_BREAK_ITERATION |
| 1749 | |
| 1750 | void StringSearchTest::TestBreakIteratorCanonical() |
| 1751 | { |
| 1752 | UErrorCode status = U_ZERO_ERROR; |
| 1753 | int count = 0; |
| 1754 | |
| 1755 | while (count < 4) { |
| 1756 | // special purposes for tests numbers 0-3 |
| 1757 | UChar temp[128]; |
| 1758 | const SearchData *search = &(BREAKITERATORCANONICAL[count]); |
| 1759 | |
| 1760 | u_unescape(search->text, temp, 128); |
| 1761 | UnicodeString text; |
| 1762 | text.setTo(temp, u_strlen(temp)); |
| 1763 | u_unescape(search->pattern, temp, 128); |
| 1764 | UnicodeString pattern; |
| 1765 | pattern.setTo(temp, u_strlen(temp)); |
| 1766 | RuleBasedCollator *collator = getCollator(search->collator); |
| 1767 | collator->setStrength(getECollationStrength(search->strength)); |
| 1768 | |
| 1769 | BreakIterator *breaker = getBreakIterator(search->breaker); |
| 1770 | StringSearch *strsrch = new StringSearch(pattern, text, collator, |
| 1771 | breaker, status); |
| 1772 | if (U_FAILURE(status)) { |
| 1773 | errln("Error creating string search data"); |
| 1774 | return; |
| 1775 | } |
| 1776 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1777 | if (U_FAILURE(status) || |
| 1778 | strsrch->getBreakIterator() != breaker) { |
| 1779 | errln("Error setting break iterator"); |
| 1780 | delete strsrch; |
| 1781 | return; |
| 1782 | } |
| 1783 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 1784 | collator->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 1785 | delete strsrch; |
| 1786 | return; |
| 1787 | } |
| 1788 | search = &(BREAKITERATOREXACT[count + 1]); |
| 1789 | breaker = getBreakIterator(search->breaker); |
| 1790 | if (breaker == NULL) { |
| 1791 | errln("Error creating BreakIterator"); |
| 1792 | return; |
| 1793 | } |
| 1794 | breaker->setText(strsrch->getText()); |
| 1795 | strsrch->setBreakIterator(breaker, status); |
| 1796 | if (U_FAILURE(status) || strsrch->getBreakIterator() != breaker) { |
| 1797 | errln("Error setting break iterator"); |
| 1798 | delete strsrch; |
| 1799 | return; |
| 1800 | } |
| 1801 | strsrch->reset(); |
| 1802 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1803 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 1804 | errln("Error at test number %d", count); |
| 1805 | return; |
| 1806 | } |
| 1807 | delete strsrch; |
| 1808 | count += 2; |
| 1809 | } |
| 1810 | count = 0; |
| 1811 | while (BREAKITERATORCANONICAL[count].text != NULL) { |
| 1812 | if (!assertEqual(&BREAKITERATORCANONICAL[count])) { |
| 1813 | errln("Error at test number %d", count); |
| 1814 | return; |
| 1815 | } |
| 1816 | count ++; |
| 1817 | } |
| 1818 | } |
| 1819 | |
| 1820 | #endif |
| 1821 | |
| 1822 | void StringSearchTest::TestVariableCanonical() |
| 1823 | { |
| 1824 | int count = 0; |
| 1825 | UErrorCode status = U_ZERO_ERROR; |
| 1826 | m_en_us_->setAttribute(UCOL_ALTERNATE_HANDLING, UCOL_SHIFTED, status); |
| 1827 | if (U_FAILURE(status)) { |
| 1828 | errln("Error setting collation alternate attribute %s", |
| 1829 | u_errorName(status)); |
| 1830 | } |
| 1831 | while (VARIABLE[count].text != NULL) { |
| 1832 | logln("variable %d", count); |
| 1833 | if (!assertCanonicalEqual(&VARIABLE[count])) { |
| 1834 | errln("Error at test number %d", count); |
| 1835 | } |
| 1836 | count ++; |
| 1837 | } |
| 1838 | m_en_us_->setAttribute(UCOL_ALTERNATE_HANDLING, UCOL_NON_IGNORABLE, |
| 1839 | status); |
| 1840 | } |
| 1841 | |
| 1842 | void StringSearchTest::TestOverlapCanonical() |
| 1843 | { |
| 1844 | int count = 0; |
| 1845 | while (OVERLAPCANONICAL[count].text != NULL) { |
| 1846 | if (!assertEqualWithAttribute(&OVERLAPCANONICAL[count], USEARCH_ON, |
| 1847 | USEARCH_ON)) { |
| 1848 | errln("Error at overlap test number %d", count); |
| 1849 | } |
| 1850 | count ++; |
| 1851 | } |
| 1852 | count = 0; |
| 1853 | while (NONOVERLAP[count].text != NULL) { |
| 1854 | if (!assertCanonicalEqual(&NONOVERLAPCANONICAL[count])) { |
| 1855 | errln("Error at non overlap test number %d", count); |
| 1856 | } |
| 1857 | count ++; |
| 1858 | } |
| 1859 | |
| 1860 | count = 0; |
| 1861 | while (count < 1) { |
| 1862 | UChar temp[128]; |
| 1863 | const SearchData *search = &(OVERLAPCANONICAL[count]); |
| 1864 | UErrorCode status = U_ZERO_ERROR; |
| 1865 | |
| 1866 | u_unescape(search->text, temp, 128); |
| 1867 | UnicodeString text; |
| 1868 | text.setTo(temp, u_strlen(temp)); |
| 1869 | u_unescape(search->pattern, temp, 128); |
| 1870 | UnicodeString pattern; |
| 1871 | pattern.setTo(temp, u_strlen(temp)); |
| 1872 | RuleBasedCollator *collator = getCollator(search->collator); |
| 1873 | StringSearch *strsrch = new StringSearch(pattern, text, collator, |
| 1874 | NULL, status); |
| 1875 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1876 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_ON, status); |
| 1877 | if (U_FAILURE(status) || |
| 1878 | strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_ON) { |
| 1879 | errln("Error setting overlap option"); |
| 1880 | } |
| 1881 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 1882 | delete strsrch; |
| 1883 | return; |
| 1884 | } |
| 1885 | search = &(NONOVERLAPCANONICAL[count]); |
| 1886 | strsrch->setAttribute(USEARCH_OVERLAP, USEARCH_OFF, status); |
| 1887 | if (U_FAILURE(status) || |
| 1888 | strsrch->getAttribute(USEARCH_OVERLAP) != USEARCH_OFF) { |
| 1889 | errln("Error setting overlap option"); |
| 1890 | } |
| 1891 | strsrch->reset(); |
| 1892 | if (!assertEqualWithStringSearch(strsrch, search)) { |
| 1893 | delete strsrch; |
| 1894 | errln("Error at test number %d", count); |
| 1895 | } |
| 1896 | |
| 1897 | count ++; |
| 1898 | delete strsrch; |
| 1899 | } |
| 1900 | } |
| 1901 | |
| 1902 | void StringSearchTest::TestCollatorCanonical() |
| 1903 | { |
| 1904 | /* test collator that thinks "o" and "p" are the same thing */ |
| 1905 | UChar temp[128]; |
| 1906 | u_unescape(COLLATORCANONICAL[0].text, temp, 128); |
| 1907 | UnicodeString text; |
| 1908 | text.setTo(temp, u_strlen(temp)); |
| 1909 | u_unescape(COLLATORCANONICAL[0].pattern, temp, 128); |
| 1910 | UnicodeString pattern; |
| 1911 | pattern.setTo(temp, u_strlen(temp)); |
| 1912 | |
| 1913 | UErrorCode status = U_ZERO_ERROR; |
| 1914 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, |
| 1915 | NULL, status); |
| 1916 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1917 | if (U_FAILURE(status)) { |
| 1918 | errln("Error opening string search %s", u_errorName(status)); |
| 1919 | } |
| 1920 | if (!assertEqualWithStringSearch(strsrch, &COLLATORCANONICAL[0])) { |
| 1921 | delete strsrch; |
| 1922 | return; |
| 1923 | } |
| 1924 | |
| 1925 | u_unescape(TESTCOLLATORRULE, temp, 128); |
| 1926 | UnicodeString rules; |
| 1927 | rules.setTo(temp, u_strlen(temp)); |
| 1928 | RuleBasedCollator *tailored = new RuleBasedCollator(rules, |
| 1929 | getECollationStrength(COLLATORCANONICAL[1].strength), |
| 1930 | UCOL_ON, status); |
| 1931 | |
| 1932 | if (U_FAILURE(status)) { |
| 1933 | errln("Error opening rule based collator %s", u_errorName(status)); |
| 1934 | } |
| 1935 | |
| 1936 | strsrch->setCollator(tailored, status); |
| 1937 | if (U_FAILURE(status) || *(strsrch->getCollator()) != *tailored) { |
| 1938 | errln("Error setting rule based collator"); |
| 1939 | } |
| 1940 | strsrch->reset(); |
| 1941 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1942 | if (!assertEqualWithStringSearch(strsrch, &COLLATORCANONICAL[1])) { |
| 1943 | delete strsrch; |
| 1944 | if (tailored != NULL) { |
| 1945 | delete tailored; |
| 1946 | } |
| 1947 | |
| 1948 | return; |
| 1949 | } |
| 1950 | |
| 1951 | strsrch->setCollator(m_en_us_, status); |
| 1952 | strsrch->reset(); |
| 1953 | if (U_FAILURE(status) || *(strsrch->getCollator()) != *m_en_us_) { |
| 1954 | errln("Error setting rule based collator"); |
| 1955 | } |
| 1956 | if (!assertEqualWithStringSearch(strsrch, &COLLATORCANONICAL[0])) { |
| 1957 | } |
| 1958 | delete strsrch; |
| 1959 | if (tailored != NULL) { |
| 1960 | delete tailored; |
| 1961 | } |
| 1962 | } |
| 1963 | |
| 1964 | void StringSearchTest::TestPatternCanonical() |
| 1965 | { |
| 1966 | |
| 1967 | UChar temp[128]; |
| 1968 | |
| 1969 | u_unescape(PATTERNCANONICAL[0].text, temp, 128); |
| 1970 | UnicodeString text; |
| 1971 | text.setTo(temp, u_strlen(temp)); |
| 1972 | u_unescape(PATTERNCANONICAL[0].pattern, temp, 128); |
| 1973 | UnicodeString pattern; |
| 1974 | pattern.setTo(temp, u_strlen(temp)); |
| 1975 | |
| 1976 | m_en_us_->setStrength( |
| 1977 | getECollationStrength(PATTERNCANONICAL[0].strength)); |
| 1978 | |
| 1979 | UErrorCode status = U_ZERO_ERROR; |
| 1980 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 1981 | status); |
| 1982 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 1983 | if (U_FAILURE(status)) { |
| 1984 | errln("Error opening string search %s", u_errorName(status)); |
| 1985 | goto ENDTESTPATTERN; |
| 1986 | } |
| 1987 | if (pattern != strsrch->getPattern()) { |
| 1988 | errln("Error setting pattern"); |
| 1989 | } |
| 1990 | if (!assertEqualWithStringSearch(strsrch, &PATTERNCANONICAL[0])) { |
| 1991 | goto ENDTESTPATTERN; |
| 1992 | } |
| 1993 | |
| 1994 | u_unescape(PATTERNCANONICAL[1].pattern, temp, 128); |
| 1995 | pattern.setTo(temp, u_strlen(temp)); |
| 1996 | strsrch->setPattern(pattern, status); |
| 1997 | if (pattern != strsrch->getPattern()) { |
| 1998 | errln("Error setting pattern"); |
| 1999 | goto ENDTESTPATTERN; |
| 2000 | } |
| 2001 | strsrch->reset(); |
| 2002 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 2003 | if (U_FAILURE(status)) { |
| 2004 | errln("Error setting pattern %s", u_errorName(status)); |
| 2005 | } |
| 2006 | if (!assertEqualWithStringSearch(strsrch, &PATTERNCANONICAL[1])) { |
| 2007 | goto ENDTESTPATTERN; |
| 2008 | } |
| 2009 | |
| 2010 | u_unescape(PATTERNCANONICAL[0].pattern, temp, 128); |
| 2011 | pattern.setTo(temp, u_strlen(temp)); |
| 2012 | strsrch->setPattern(pattern, status); |
| 2013 | if (pattern != strsrch->getPattern()) { |
| 2014 | errln("Error setting pattern"); |
| 2015 | goto ENDTESTPATTERN; |
| 2016 | } |
| 2017 | strsrch->reset(); |
| 2018 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 2019 | if (U_FAILURE(status)) { |
| 2020 | errln("Error setting pattern %s", u_errorName(status)); |
| 2021 | } |
| 2022 | if (!assertEqualWithStringSearch(strsrch, &PATTERNCANONICAL[0])) { |
| 2023 | goto ENDTESTPATTERN; |
| 2024 | } |
| 2025 | ENDTESTPATTERN: |
| 2026 | m_en_us_->setStrength(getECollationStrength(UCOL_TERTIARY)); |
| 2027 | if (strsrch != NULL) { |
| 2028 | delete strsrch; |
| 2029 | } |
| 2030 | } |
| 2031 | |
| 2032 | void StringSearchTest::TestTextCanonical() |
| 2033 | { |
| 2034 | UChar temp[128]; |
| 2035 | u_unescape(TEXTCANONICAL[0].text, temp, 128); |
| 2036 | UnicodeString text; |
| 2037 | text.setTo(temp, u_strlen(temp)); |
| 2038 | u_unescape(TEXTCANONICAL[0].pattern, temp, 128); |
| 2039 | UnicodeString pattern; |
| 2040 | pattern.setTo(temp, u_strlen(temp)); |
| 2041 | |
| 2042 | UErrorCode status = U_ZERO_ERROR; |
| 2043 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 2044 | status); |
| 2045 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 2046 | |
| 2047 | if (U_FAILURE(status)) { |
| 2048 | errln("Error opening string search %s", u_errorName(status)); |
| 2049 | goto ENDTESTPATTERN; |
| 2050 | } |
| 2051 | if (text != strsrch->getText()) { |
| 2052 | errln("Error setting text"); |
| 2053 | } |
| 2054 | if (!assertEqualWithStringSearch(strsrch, &TEXTCANONICAL[0])) { |
| 2055 | goto ENDTESTPATTERN; |
| 2056 | } |
| 2057 | |
| 2058 | u_unescape(TEXTCANONICAL[1].text, temp, 128); |
| 2059 | text.setTo(temp, u_strlen(temp)); |
| 2060 | strsrch->setText(text, status); |
| 2061 | if (text != strsrch->getText()) { |
| 2062 | errln("Error setting text"); |
| 2063 | goto ENDTESTPATTERN; |
| 2064 | } |
| 2065 | if (U_FAILURE(status)) { |
| 2066 | errln("Error setting text %s", u_errorName(status)); |
| 2067 | } |
| 2068 | if (!assertEqualWithStringSearch(strsrch, &TEXTCANONICAL[1])) { |
| 2069 | goto ENDTESTPATTERN; |
| 2070 | } |
| 2071 | |
| 2072 | u_unescape(TEXTCANONICAL[0].text, temp, 128); |
| 2073 | text.setTo(temp, u_strlen(temp)); |
| 2074 | strsrch->setText(text, status); |
| 2075 | if (text != strsrch->getText()) { |
| 2076 | errln("Error setting text"); |
| 2077 | goto ENDTESTPATTERN; |
| 2078 | } |
| 2079 | if (U_FAILURE(status)) { |
| 2080 | errln("Error setting pattern %s", u_errorName(status)); |
| 2081 | } |
| 2082 | if (!assertEqualWithStringSearch(strsrch, &TEXTCANONICAL[0])) { |
| 2083 | goto ENDTESTPATTERN; |
| 2084 | } |
| 2085 | ENDTESTPATTERN: |
| 2086 | if (strsrch != NULL) { |
| 2087 | delete strsrch; |
| 2088 | } |
| 2089 | } |
| 2090 | |
| 2091 | void StringSearchTest::TestCompositeBoundariesCanonical() |
| 2092 | { |
| 2093 | int count = 0; |
| 2094 | while (COMPOSITEBOUNDARIESCANONICAL[count].text != NULL) { |
| 2095 | logln("composite %d", count); |
| 2096 | if (!assertCanonicalEqual(&COMPOSITEBOUNDARIESCANONICAL[count])) { |
| 2097 | errln("Error at test number %d", count); |
| 2098 | } |
| 2099 | count ++; |
| 2100 | } |
| 2101 | } |
| 2102 | |
| 2103 | void StringSearchTest::TestGetSetOffsetCanonical() |
| 2104 | { |
| 2105 | |
| 2106 | UErrorCode status = U_ZERO_ERROR; |
| 2107 | UnicodeString text("text"); |
| 2108 | UnicodeString pattern("pattern"); |
| 2109 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 2110 | status); |
| 2111 | Collator *collator = strsrch->getCollator(); |
| 2112 | |
| 2113 | collator->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status); |
| 2114 | |
| 2115 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 2116 | /* testing out of bounds error */ |
| 2117 | strsrch->setOffset(-1, status); |
| 2118 | if (U_SUCCESS(status)) { |
| 2119 | errln("Error expecting set offset error"); |
| 2120 | } |
| 2121 | strsrch->setOffset(128, status); |
| 2122 | if (U_SUCCESS(status)) { |
| 2123 | errln("Error expecting set offset error"); |
| 2124 | } |
| 2125 | int index = 0; |
| 2126 | UChar temp[128]; |
| 2127 | while (BASICCANONICAL[index].text != NULL) { |
| 2128 | SearchData search = BASICCANONICAL[index ++]; |
| 2129 | if (BASICCANONICAL[index].text == NULL) { |
| 2130 | /* skip the last one */ |
| 2131 | break; |
| 2132 | } |
| 2133 | |
| 2134 | u_unescape(search.text, temp, 128); |
| 2135 | text.setTo(temp, u_strlen(temp)); |
| 2136 | u_unescape(search.pattern, temp, 128); |
| 2137 | pattern.setTo(temp, u_strlen(temp)); |
| 2138 | |
| 2139 | UErrorCode status = U_ZERO_ERROR; |
| 2140 | strsrch->setText(text, status); |
| 2141 | |
| 2142 | strsrch->setPattern(pattern, status); |
| 2143 | |
| 2144 | int count = 0; |
| 2145 | int32_t matchindex = search.offset[count]; |
| 2146 | while (U_SUCCESS(status) && matchindex >= 0) { |
| 2147 | int32_t matchlength = search.size[count]; |
| 2148 | strsrch->next(status); |
| 2149 | if (matchindex != strsrch->getMatchedStart() || |
| 2150 | matchlength != strsrch->getMatchedLength()) { |
| 2151 | char *str = toCharString(strsrch->getText()); |
| 2152 | errln("Text: %s", str); |
| 2153 | str = toCharString(strsrch->getPattern()); |
| 2154 | errln("Pattern: %s", str); |
| 2155 | errln("Error match found at %d %d", |
| 2156 | strsrch->getMatchedStart(), |
| 2157 | strsrch->getMatchedLength()); |
| 2158 | goto bail; |
| 2159 | } |
| 2160 | matchindex = search.offset[count + 1] == -1 ? -1 : |
| 2161 | search.offset[count + 2]; |
| 2162 | if (search.offset[count + 1] != -1) { |
| 2163 | strsrch->setOffset(search.offset[count + 1] + 1, status); |
| 2164 | if (strsrch->getOffset() != search.offset[count + 1] + 1) { |
| 2165 | errln("Error setting offset"); |
| 2166 | goto bail; |
| 2167 | } |
| 2168 | } |
| 2169 | |
| 2170 | count += 2; |
| 2171 | } |
| 2172 | strsrch->next(status); |
| 2173 | if (strsrch->getMatchedStart() != USEARCH_DONE) { |
| 2174 | char *str = toCharString(strsrch->getText()); |
| 2175 | errln("Text: %s", str); |
| 2176 | str = toCharString(strsrch->getPattern()); |
| 2177 | errln("Pattern: %s", str); |
| 2178 | errln("Error match found at %d %d", strsrch->getMatchedStart(), |
| 2179 | strsrch->getMatchedLength()); |
| 2180 | goto bail; |
| 2181 | } |
| 2182 | } |
| 2183 | |
| 2184 | bail: |
| 2185 | collator->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_OFF, status); |
| 2186 | delete strsrch; |
| 2187 | } |
| 2188 | |
| 2189 | void StringSearchTest::TestSupplementaryCanonical() |
| 2190 | { |
| 2191 | int count = 0; |
| 2192 | while (SUPPLEMENTARYCANONICAL[count].text != NULL) { |
| 2193 | if (!assertCanonicalEqual(&SUPPLEMENTARYCANONICAL[count])) { |
| 2194 | errln("Error at test number %d", count); |
| 2195 | } |
| 2196 | count ++; |
| 2197 | } |
| 2198 | } |
| 2199 | |
| 2200 | void StringSearchTest::TestContractionCanonical() |
| 2201 | { |
| 2202 | UChar temp[128]; |
| 2203 | |
| 2204 | u_unescape(CONTRACTIONRULE, temp, 128); |
| 2205 | UnicodeString rules; |
| 2206 | rules.setTo(temp, u_strlen(temp)); |
| 2207 | |
| 2208 | UErrorCode status = U_ZERO_ERROR; |
| 2209 | RuleBasedCollator *collator = new RuleBasedCollator(rules, |
| 2210 | getECollationStrength(UCOL_TERTIARY), UCOL_ON, status); |
| 2211 | if (U_FAILURE(status)) { |
| 2212 | errln("Error opening collator %s", u_errorName(status)); |
| 2213 | } |
| 2214 | UnicodeString text("text"); |
| 2215 | UnicodeString pattern("pattern"); |
| 2216 | StringSearch *strsrch = new StringSearch(pattern, text, collator, NULL, |
| 2217 | status); |
| 2218 | strsrch->setAttribute(USEARCH_CANONICAL_MATCH, USEARCH_ON, status); |
| 2219 | if (U_FAILURE(status)) { |
| 2220 | errln("Error opening string search %s", u_errorName(status)); |
| 2221 | } |
| 2222 | |
| 2223 | int count = 0; |
| 2224 | while (CONTRACTIONCANONICAL[count].text != NULL) { |
| 2225 | u_unescape(CONTRACTIONCANONICAL[count].text, temp, 128); |
| 2226 | text.setTo(temp, u_strlen(temp)); |
| 2227 | u_unescape(CONTRACTIONCANONICAL[count].pattern, temp, 128); |
| 2228 | pattern.setTo(temp, u_strlen(temp)); |
| 2229 | strsrch->setText(text, status); |
| 2230 | strsrch->setPattern(pattern, status); |
| 2231 | if (!assertEqualWithStringSearch(strsrch, |
| 2232 | &CONTRACTIONCANONICAL[count])) { |
| 2233 | errln("Error at test number %d", count); |
| 2234 | } |
| 2235 | count ++; |
| 2236 | } |
| 2237 | delete strsrch; |
| 2238 | delete collator; |
| 2239 | } |
| 2240 | |
| 2241 | void StringSearchTest::TestUClassID() |
| 2242 | { |
| 2243 | char id = *((char *)StringSearch::getStaticClassID()); |
| 2244 | if (id != 0) { |
| 2245 | errln("Static class id for StringSearch should be 0"); |
| 2246 | } |
| 2247 | UErrorCode status = U_ZERO_ERROR; |
| 2248 | UnicodeString text("text"); |
| 2249 | UnicodeString pattern("pattern"); |
| 2250 | StringSearch *strsrch = new StringSearch(pattern, text, m_en_us_, NULL, |
| 2251 | status); |
| 2252 | id = *((char *)strsrch->getDynamicClassID()); |
| 2253 | if (id != 0) { |
| 2254 | errln("Dynamic class id for StringSearch should be 0"); |
| 2255 | } |
| 2256 | delete strsrch; |
| 2257 | } |
| 2258 | |
| 2259 | class TestSearch : public SearchIterator |
| 2260 | { |
| 2261 | public: |
| 2262 | TestSearch(const TestSearch &obj); |
| 2263 | TestSearch(const UnicodeString &text, |
| 2264 | BreakIterator *breakiter, |
| 2265 | const UnicodeString &pattern); |
| 2266 | ~TestSearch(); |
| 2267 | |
| 2268 | void setOffset(int32_t position, UErrorCode &status) override; |
| 2269 | int32_t getOffset() const override; |
| 2270 | SearchIterator* safeClone() const override; |
| 2271 | |
| 2272 | |
| 2273 | /** |
| 2274 | * ICU "poor man's RTTI", returns a UClassID for the actual class. |
| 2275 | * |
| 2276 | * @draft ICU 2.2 |
| 2277 | */ |
| 2278 | virtual inline UClassID getDynamicClassID() const override { return getStaticClassID(); } |
| 2279 | |
| 2280 | /** |
| 2281 | * ICU "poor man's RTTI", returns a UClassID for this class. |
| 2282 | * |
| 2283 | * @draft ICU 2.2 |
| 2284 | */ |
| 2285 | static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; } |
| 2286 | |
| 2287 | bool operator!=(const TestSearch &that) const; |
| 2288 | |
| 2289 | UnicodeString m_pattern_; |
| 2290 | |
| 2291 | protected: |
| 2292 | int32_t handleNext(int32_t position, UErrorCode &status) override; |
| 2293 | int32_t handlePrev(int32_t position, UErrorCode &status) override; |
| 2294 | TestSearch & operator=(const TestSearch &that); |
| 2295 | |
| 2296 | private: |
| 2297 | |
| 2298 | /** |
| 2299 | * The address of this static class variable serves as this class's ID |
| 2300 | * for ICU "poor man's RTTI". |
| 2301 | */ |
| 2302 | static const char fgClassID; |
| 2303 | uint32_t m_offset_; |
| 2304 | }; |
| 2305 | |
| 2306 | const char TestSearch::fgClassID=0; |
| 2307 | |
| 2308 | TestSearch::TestSearch(const TestSearch &obj) : SearchIterator(obj) |
| 2309 | { |
| 2310 | m_offset_ = obj.m_offset_; |
| 2311 | m_pattern_ = obj.m_pattern_; |
| 2312 | } |
| 2313 | |
| 2314 | TestSearch::TestSearch(const UnicodeString &text, |
| 2315 | BreakIterator *breakiter, |
| 2316 | const UnicodeString &pattern) : SearchIterator() |
| 2317 | { |
| 2318 | m_breakiterator_ = breakiter; |
| 2319 | m_pattern_ = pattern; |
| 2320 | m_text_ = text; |
| 2321 | m_offset_ = 0; |
| 2322 | m_pattern_ = pattern; |
| 2323 | } |
| 2324 | |
| 2325 | TestSearch::~TestSearch() |
| 2326 | { |
| 2327 | } |
| 2328 | |
| 2329 | |
| 2330 | void TestSearch::setOffset(int32_t position, UErrorCode &status) |
| 2331 | { |
| 2332 | if (position >= 0 && position <= m_text_.length()) { |
| 2333 | m_offset_ = position; |
| 2334 | } |
| 2335 | else { |
| 2336 | status = U_INDEX_OUTOFBOUNDS_ERROR; |
| 2337 | } |
| 2338 | } |
| 2339 | |
| 2340 | int32_t TestSearch::getOffset() const |
| 2341 | { |
| 2342 | return m_offset_; |
| 2343 | } |
| 2344 | |
| 2345 | SearchIterator * TestSearch::safeClone() const |
| 2346 | { |
| 2347 | return new TestSearch(m_text_, m_breakiterator_, m_pattern_); |
| 2348 | } |
| 2349 | |
| 2350 | bool TestSearch::operator!=(const TestSearch &that) const |
| 2351 | { |
| 2352 | if (SearchIterator::operator !=(that)) { |
| 2353 | return false; |
| 2354 | } |
| 2355 | return m_offset_ != that.m_offset_ || m_pattern_ != that.m_pattern_; |
| 2356 | } |
| 2357 | |
| 2358 | int32_t TestSearch::handleNext(int32_t start, UErrorCode &status) |
| 2359 | { |
| 2360 | if(U_SUCCESS(status)) { |
| 2361 | int match = m_text_.indexOf(m_pattern_, start); |
| 2362 | if (match < 0) { |
| 2363 | m_offset_ = m_text_.length(); |
| 2364 | setMatchStart(m_offset_); |
| 2365 | setMatchLength(0); |
| 2366 | return USEARCH_DONE; |
| 2367 | } |
| 2368 | setMatchStart(match); |
| 2369 | m_offset_ = match; |
| 2370 | setMatchLength(m_pattern_.length()); |
| 2371 | return match; |
| 2372 | } else { |
| 2373 | return USEARCH_DONE; |
| 2374 | } |
| 2375 | } |
| 2376 | |
| 2377 | int32_t TestSearch::handlePrev(int32_t start, UErrorCode &status) |
| 2378 | { |
| 2379 | if(U_SUCCESS(status)) { |
| 2380 | int match = m_text_.lastIndexOf(m_pattern_, 0, start); |
| 2381 | if (match < 0) { |
| 2382 | m_offset_ = 0; |
| 2383 | setMatchStart(m_offset_); |
| 2384 | setMatchLength(0); |
| 2385 | return USEARCH_DONE; |
| 2386 | } |
| 2387 | setMatchStart(match); |
| 2388 | m_offset_ = match; |
| 2389 | setMatchLength(m_pattern_.length()); |
| 2390 | return match; |
| 2391 | } else { |
| 2392 | return USEARCH_DONE; |
| 2393 | } |
| 2394 | } |
| 2395 | |
| 2396 | TestSearch & TestSearch::operator=(const TestSearch &that) |
| 2397 | { |
| 2398 | SearchIterator::operator=(that); |
| 2399 | m_offset_ = that.m_offset_; |
| 2400 | m_pattern_ = that.m_pattern_; |
| 2401 | return *this; |
| 2402 | } |
| 2403 | |
| 2404 | void StringSearchTest::TestSubclass() |
| 2405 | { |
| 2406 | UnicodeString text("abc abcd abc"); |
| 2407 | UnicodeString pattern("abc"); |
| 2408 | TestSearch search(text, NULL, pattern); |
| 2409 | TestSearch search2(search); |
| 2410 | int expected[] = {0, 4, 9}; |
| 2411 | UErrorCode status = U_ZERO_ERROR; |
| 2412 | int i; |
| 2413 | StringCharacterIterator chariter(text); |
| 2414 | |
| 2415 | search.setText(text, status); |
| 2416 | if (search.getText() != search2.getText()) { |
| 2417 | errln("Error setting text"); |
| 2418 | } |
| 2419 | |
| 2420 | search.setText(chariter, status); |
| 2421 | if (search.getText() != search2.getText()) { |
| 2422 | errln("Error setting text"); |
| 2423 | } |
| 2424 | |
| 2425 | search.reset(); |
| 2426 | // comparing constructors |
| 2427 | |
| 2428 | for (i = 0; i < UPRV_LENGTHOF(expected); i ++) { |
| 2429 | if (search.next(status) != expected[i]) { |
| 2430 | errln("Error getting next match"); |
| 2431 | } |
| 2432 | if (search.getMatchedLength() != search.m_pattern_.length()) { |
| 2433 | errln("Error getting next match length"); |
| 2434 | } |
| 2435 | } |
| 2436 | if (search.next(status) != USEARCH_DONE) { |
| 2437 | errln("Error should have reached the end of the iteration"); |
| 2438 | } |
| 2439 | for (i = UPRV_LENGTHOF(expected) - 1; i >= 0; i --) { |
| 2440 | if (search.previous(status) != expected[i]) { |
| 2441 | errln("Error getting previous match"); |
| 2442 | } |
| 2443 | if (search.getMatchedLength() != search.m_pattern_.length()) { |
| 2444 | errln("Error getting previous match length"); |
| 2445 | } |
| 2446 | } |
| 2447 | if (search.previous(status) != USEARCH_DONE) { |
| 2448 | errln("Error should have reached the start of the iteration"); |
| 2449 | } |
| 2450 | } |
| 2451 | |
| 2452 | class StubSearchIterator:public SearchIterator{ |
| 2453 | public: |
| 2454 | StubSearchIterator(){} |
| 2455 | virtual void setOffset(int32_t , UErrorCode &) override {} |
| 2456 | virtual int32_t getOffset(void) const override {return 0;} |
| 2457 | virtual SearchIterator* safeClone(void) const override {return NULL;} |
| 2458 | virtual int32_t handleNext(int32_t , UErrorCode &) override {return 0;} |
| 2459 | virtual int32_t handlePrev(int32_t , UErrorCode &) override {return 0;} |
| 2460 | virtual UClassID getDynamicClassID() const override { |
| 2461 | static char classID = 0; |
| 2462 | return (UClassID)&classID; |
| 2463 | } |
| 2464 | }; |
| 2465 | |
| 2466 | void StringSearchTest::TestCoverage(){ |
| 2467 | StubSearchIterator stub1, stub2; |
| 2468 | UErrorCode status = U_ZERO_ERROR; |
| 2469 | |
| 2470 | if (stub1 != stub2){ |
| 2471 | errln("new StubSearchIterator should be equal"); |
| 2472 | } |
| 2473 | |
| 2474 | stub2.setText(UnicodeString("ABC"), status); |
| 2475 | if (U_FAILURE(status)) { |
| 2476 | errln("Error: SearchIterator::SetText"); |
| 2477 | } |
| 2478 | |
| 2479 | stub1 = stub2; |
| 2480 | if (stub1 != stub2){ |
| 2481 | errln("SearchIterator::operator = assigned object should be equal"); |
| 2482 | } |
| 2483 | } |
| 2484 | |
| 2485 | #endif /* !UCONFIG_NO_BREAK_ITERATION */ |
| 2486 | |
| 2487 | #endif /* #if !UCONFIG_NO_COLLATION */ |