1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/********************************************************************
* COPYRIGHT:
* Copyright (c) 1997-2016, International Business Machines Corporation and
* others. All Rights Reserved.
********************************************************************/
#include "unicode/utypes.h"
#if !UCONFIG_NO_COLLATION
#include "unicode/coll.h"
#include "unicode/localpointer.h"
#include "unicode/tblcoll.h"
#include "unicode/unistr.h"
#include "unicode/sortkey.h"
#include "regcoll.h"
#include "sfwdchit.h"
#include "testutil.h"
#include "cmemory.h"
CollationRegressionTest::CollationRegressionTest()
{
UErrorCode status = U_ZERO_ERROR;
en_us = dynamic_cast<RuleBasedCollator*>(Collator::createInstance(Locale::getUS(), status));
if(U_FAILURE(status)) {
delete en_us;
en_us = nullptr;
errcheckln(status, "Collator creation failed with %s", u_errorName(status));
return;
}
}
CollationRegressionTest::~CollationRegressionTest()
{
delete en_us;
}
// @bug 4048446
//
// CollationElementIterator.reset() doesn't work
//
void CollationRegressionTest::Test4048446(/* char* par */)
{
const UnicodeString test1 = "XFILE What subset of all possible test cases has the highest probability of detecting the most errors?";
const UnicodeString test2 = "Xf_ile What subset of all possible test cases has the lowest probability of detecting the least errors?";
CollationElementIterator *i1 = en_us->createCollationElementIterator(test1);
CollationElementIterator *i2 = en_us->createCollationElementIterator(test1);
UErrorCode status = U_ZERO_ERROR;
if (i1 == nullptr|| i2 == nullptr)
{
errln("Could not create CollationElementIterator's");
delete i1;
delete i2;
return;
}
while (i1->next(status) != CollationElementIterator::NULLORDER)
{
if (U_FAILURE(status))
{
errln("error calling next()");
delete i1;
delete i2;
return;
}
}
i1->reset();
assertEqual(*i1, *i2);
delete i1;
delete i2;
}
// @bug 4051866
//
// Collator -> rules -> Collator round-trip broken for expanding characters
//
void CollationRegressionTest::Test4051866(/* char* par */)
{
UnicodeString rules;
UErrorCode status = U_ZERO_ERROR;
rules += "&n < o ";
rules += "& oe ,o";
rules += static_cast<char16_t>(0x3080);
rules += "& oe ,";
rules += static_cast<char16_t>(0x1530);
rules += " ,O";
rules += "& OE ,O";
rules += static_cast<char16_t>(0x3080);
rules += "& OE ,";
rules += static_cast<char16_t>(0x1520);
rules += "< p ,P";
// Build a collator containing expanding characters
LocalPointer<RuleBasedCollator> c1(new RuleBasedCollator(rules, status), status);
if (U_FAILURE(status)) {
errln("RuleBasedCollator(rule string) failed - %s", u_errorName(status));
return;
}
// Build another using the rules from the first
LocalPointer<RuleBasedCollator> c2(new RuleBasedCollator(c1->getRules(), status), status);
if (U_FAILURE(status)) {
errln("RuleBasedCollator(rule string from other RBC) failed - %s", u_errorName(status));
return;
}
// Make sure they're the same
if (!(c1->getRules() == c2->getRules()))
{
errln("Rules are not equal");
}
}
// @bug 4053636
//
// Collator thinks "black-bird" == "black"
//
void CollationRegressionTest::Test4053636(/* char* par */)
{
if (en_us->equals("black_bird", "black"))
{
errln("black-bird == black");
}
}
// @bug 4054238
//
// CollationElementIterator will not work correctly if the associated
// Collator object's mode is changed
//
void CollationRegressionTest::Test4054238(/* char* par */)
{
const char16_t chars3[] = {0x61, 0x00FC, 0x62, 0x65, 0x63, 0x6b, 0x20, 0x47, 0x72, 0x00F6, 0x00DF, 0x65, 0x20, 0x4c, 0x00FC, 0x62, 0x63, 0x6b, 0};
const UnicodeString test3(chars3);
RuleBasedCollator *c = en_us->clone();
// NOTE: The Java code uses en_us to create the CollationElementIterators
// but I'm pretty sure that's wrong, so I've changed this to use c.
UErrorCode status = U_ZERO_ERROR;
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
CollationElementIterator *i1 = c->createCollationElementIterator(test3);
delete i1;
delete c;
}
// @bug 4054734
//
// Collator::IDENTICAL documented but not implemented
//
void CollationRegressionTest::Test4054734(/* char* par */)
{
/*
Here's the original Java:
String[] decomp = {
"\u0001", "<", "\u0002",
"\u0001", "=", "\u0001",
"A\u0001", ">", "~\u0002", // Ensure A and ~ are not compared bitwise
"\u00C0", "=", "A\u0300" // Decomp should make these equal
};
String[] nodecomp = {
"\u00C0", ">", "A\u0300" // A-grave vs. A combining-grave
};
*/
static const char16_t decomp[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x0001, 0}, {0x3c, 0}, {0x0002, 0},
{0x0001, 0}, {0x3d, 0}, {0x0001, 0},
{0x41, 0x0001, 0}, {0x3e, 0}, {0x7e, 0x0002, 0},
{0x00c0, 0}, {0x3d, 0}, {0x41, 0x0300, 0}
};
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::IDENTICAL);
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
compareArray(*c, decomp, UPRV_LENGTHOF(decomp));
delete c;
}
// @bug 4054736
//
// Full Decomposition mode not implemented
//
void CollationRegressionTest::Test4054736(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::SECONDARY);
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0xFB4F, 0}, {0x3d, 0}, {0x05D0, 0x05DC} // Alef-Lamed vs. Alef, Lamed
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4058613
//
// Collator::createInstance() causes an ArrayIndexOutofBoundsException for Korean
//
void CollationRegressionTest::Test4058613(/* char* par */)
{
// Creating a default collator doesn't work when Korean is the default
// locale
Locale oldDefault = Locale::getDefault();
UErrorCode status = U_ZERO_ERROR;
Locale::setDefault(Locale::getKorean(), status);
if (U_FAILURE(status))
{
errln("Could not set default locale to Locale::KOREAN");
return;
}
Collator *c = nullptr;
c = Collator::createInstance("en_US", status);
if (c == nullptr || U_FAILURE(status))
{
errln("Could not create a Korean collator");
Locale::setDefault(oldDefault, status);
delete c;
return;
}
// Since the fix to this bug was to turn off decomposition for Korean collators,
// ensure that's what we got
if (c->getAttribute(UCOL_NORMALIZATION_MODE, status) != UCOL_OFF)
{
errln("Decomposition is not set to NO_DECOMPOSITION for Korean collator");
}
delete c;
Locale::setDefault(oldDefault, status);
}
// @bug 4059820
//
// RuleBasedCollator.getRules does not return the exact pattern as input
// for expanding character sequences
//
void CollationRegressionTest::Test4059820(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = nullptr;
UnicodeString rules = "&9 < a < b , c/a < d < z";
c = new RuleBasedCollator(rules, status);
if (c == nullptr || U_FAILURE(status))
{
errln("Failure building a collator.");
delete c;
return;
}
if ( c->getRules().indexOf("c/a") == -1)
{
errln("returned rules do not contain 'c/a'");
}
delete c;
}
// @bug 4060154
//
// MergeCollation::fixEntry broken for "& H < \u0131, \u0130, i, I"
//
void CollationRegressionTest::Test4060154(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
UnicodeString rules;
rules += "&f < g, G < h, H < i, I < j, J";
rules += " & H < ";
rules += static_cast<char16_t>(0x0131);
rules += ", ";
rules += static_cast<char16_t>(0x0130);
rules += ", i, I";
RuleBasedCollator *c = nullptr;
c = new RuleBasedCollator(rules, status);
if (c == nullptr || U_FAILURE(status))
{
errln("failure building collator.");
delete c;
return;
}
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
/*
String[] tertiary = {
"A", "<", "B",
"H", "<", "\u0131",
"H", "<", "I",
"\u0131", "<", "\u0130",
"\u0130", "<", "i",
"\u0130", ">", "H",
};
*/
static const char16_t tertiary[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x41, 0}, {0x3c, 0}, {0x42, 0},
{0x48, 0}, {0x3c, 0}, {0x0131, 0},
{0x48, 0}, {0x3c, 0}, {0x49, 0},
{0x0131, 0}, {0x3c, 0}, {0x0130, 0},
{0x0130, 0}, {0x3c, 0}, {0x69, 0},
{0x0130, 0}, {0x3e, 0}, {0x48, 0}
};
c->setStrength(Collator::TERTIARY);
compareArray(*c, tertiary, UPRV_LENGTHOF(tertiary));
/*
String[] secondary = {
"H", "<", "I",
"\u0131", "=", "\u0130",
};
*/
static const char16_t secondary[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x48, 0}, {0x3c, 0}, {0x49, 0},
{0x0131, 0}, {0x3d, 0}, {0x0130, 0}
};
c->setStrength(Collator::PRIMARY);
compareArray(*c, secondary, UPRV_LENGTHOF(secondary));
delete c;
}
// @bug 4062418
//
// Secondary/Tertiary comparison incorrect in French Secondary
//
void CollationRegressionTest::Test4062418(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = nullptr;
c = dynamic_cast<RuleBasedCollator*>(Collator::createInstance(Locale::getCanadaFrench(), status));
if (c == nullptr || U_FAILURE(status))
{
errln("Failed to create collator for Locale::getCanadaFrench()");
delete c;
return;
}
c->setStrength(Collator::SECONDARY);
/*
String[] tests = {
"p\u00eache", "<", "p\u00e9ch\u00e9", // Comparing accents from end, p\u00e9ch\u00e9 is greater
};
*/
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x70, 0x00EA, 0x63, 0x68, 0x65, 0}, {0x3c, 0}, {0x70, 0x00E9, 0x63, 0x68, 0x00E9, 0}
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4065540
//
// Collator::compare() method broken if either string contains spaces
//
void CollationRegressionTest::Test4065540(/* char* par */)
{
if (en_us->compare("abcd e", "abcd f") == 0)
{
errln("'abcd e' == 'abcd f'");
}
}
// @bug 4066189
//
// Unicode characters need to be recursively decomposed to get the
// correct result. For example,
// u1EB1 -> \u0103 + \u0300 -> a + \u0306 + \u0300.
//
void CollationRegressionTest::Test4066189(/* char* par */)
{
static const char16_t chars1[] = {0x1EB1, 0};
static const char16_t chars2[] = {0x61, 0x0306, 0x0300, 0};
const UnicodeString test1(chars1);
const UnicodeString test2(chars2);
UErrorCode status = U_ZERO_ERROR;
// NOTE: The java code used en_us to create the
// CollationElementIterator's. I'm pretty sure that
// was wrong, so I've change the code to use c1 and c2
RuleBasedCollator *c1 = en_us->clone();
c1->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
CollationElementIterator *i1 = c1->createCollationElementIterator(test1);
RuleBasedCollator *c2 = en_us->clone();
c2->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_OFF, status);
CollationElementIterator *i2 = c2->createCollationElementIterator(test2);
assertEqual(*i1, *i2);
delete i2;
delete c2;
delete i1;
delete c1;
}
// @bug 4066696
//
// French secondary collation checking at the end of compare iteration fails
//
void CollationRegressionTest::Test4066696(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = nullptr;
c = dynamic_cast<RuleBasedCollator*>(Collator::createInstance(Locale::getCanadaFrench(), status));
if (c == nullptr || U_FAILURE(status))
{
errln("Failure creating collator for Locale::getCanadaFrench()");
delete c;
return;
}
c->setStrength(Collator::SECONDARY);
/*
String[] tests = {
"\u00e0", "<", "\u01fa", // a-grave < A-ring-acute
};
should be:
String[] tests = {
"\u00e0", ">", "\u01fa", // a-grave < A-ring-acute
};
*/
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x00E0, 0}, {0x3e, 0}, {0x01FA, 0}
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4076676
//
// Bad canonicalization of same-class combining characters
//
void CollationRegressionTest::Test4076676(/* char* par */)
{
// These combining characters are all in the same class, so they should not
// be reordered, and they should compare as unequal.
static const char16_t s1[] = {0x41, 0x0301, 0x0302, 0x0300, 0};
static const char16_t s2[] = {0x41, 0x0302, 0x0300, 0x0301, 0};
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::TERTIARY);
if (c->compare(s1,s2) == 0)
{
errln("Same-class combining chars were reordered");
}
delete c;
}
// @bug 4079231
//
// RuleBasedCollator::operator==(nullptr) throws NullPointerException
//
void CollationRegressionTest::Test4079231(/* char* par */)
{
// I don't think there's any way to write this test
// in C++. The following is equivalent to the Java,
// but doesn't compile 'cause nullptr can't be converted
// to Collator&
//
// if (en_us->operator==(nullptr))
// {
// errln("en_us->operator==(nullptr) returned true");
// }
/*
try {
if (en_us->equals(null)) {
errln("en_us->equals(null) returned true");
}
}
catch (Exception e) {
errln("en_us->equals(null) threw " + e.toString());
}
*/
}
// @bug 4078588
//
// RuleBasedCollator breaks on "< a < bb" rule
//
void CollationRegressionTest::Test4078588(/* char *par */)
{
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *rbc = new RuleBasedCollator("&9 < a < bb", status);
if (rbc == nullptr || U_FAILURE(status))
{
errln("Failed to create RuleBasedCollator.");
delete rbc;
return;
}
Collator::EComparisonResult result = rbc->compare("a","bb");
if (result != Collator::LESS)
{
errln(UnicodeString("Compare(a,bb) returned ") + static_cast<int>(result)
+ UnicodeString("; expected -1"));
}
delete rbc;
}
// @bug 4081866
//
// Combining characters in different classes not reordered properly.
//
void CollationRegressionTest::Test4081866(/* char* par */)
{
// These combining characters are all in different classes,
// so they should be reordered and the strings should compare as equal.
static const char16_t s1[] = {0x41, 0x0300, 0x0316, 0x0327, 0x0315, 0};
static const char16_t s2[] = {0x41, 0x0327, 0x0316, 0x0315, 0x0300, 0};
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::TERTIARY);
// Now that the default collators are set to NO_DECOMPOSITION
// (as a result of fixing bug 4114077), we must set it explicitly
// when we're testing reordering behavior. -- lwerner, 5/5/98
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
if (c->compare(s1,s2) != 0)
{
errln("Combining chars were not reordered");
}
delete c;
}
// @bug 4087241
//
// string comparison errors in Scandinavian collators
//
void CollationRegressionTest::Test4087241(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
Locale da_DK("da", "DK");
RuleBasedCollator *c = nullptr;
c = dynamic_cast<RuleBasedCollator*>(Collator::createInstance(da_DK, status));
if (c == nullptr || U_FAILURE(status))
{
errln("Failed to create collator for da_DK locale");
delete c;
return;
}
c->setStrength(Collator::SECONDARY);
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x7a, 0}, {0x3c, 0}, {0x00E6, 0}, // z < ae
{0x61, 0x0308, 0}, {0x3c, 0}, {0x61, 0x030A, 0}, // a-umlaut < a-ring
{0x59, 0}, {0x3c, 0}, {0x75, 0x0308, 0}, // Y < u-umlaut
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4087243
//
// CollationKey takes ignorable strings into account when it shouldn't
//
void CollationRegressionTest::Test4087243(/* char* par */)
{
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::TERTIARY);
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x31, 0x32, 0x33, 0}, {0x3d, 0}, {0x31, 0x32, 0x33, 0x0001, 0} // 1 2 3 = 1 2 3 ctrl-A
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4092260
//
// Mu/micro conflict
// Micro symbol and greek lowercase letter Mu should sort identically
//
void CollationRegressionTest::Test4092260(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
Locale el("el", "");
Collator *c = nullptr;
c = Collator::createInstance(el, status);
if (c == nullptr || U_FAILURE(status))
{
errln("Failed to create collator for el locale.");
delete c;
return;
}
// These now have tertiary differences in UCA
c->setAttribute(UCOL_STRENGTH, UCOL_SECONDARY, status);
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x00B5, 0}, {0x3d, 0}, {0x03BC, 0}
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4095316
//
void CollationRegressionTest::Test4095316(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
Locale el_GR("el", "GR");
Collator *c = Collator::createInstance(el_GR, status);
if (c == nullptr || U_FAILURE(status))
{
errln("Failed to create collator for el_GR locale");
delete c;
return;
}
// These now have tertiary differences in UCA
//c->setStrength(Collator::TERTIARY);
c->setAttribute(UCOL_STRENGTH, UCOL_SECONDARY, status);
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x03D4, 0}, {0x3d, 0}, {0x03AB, 0}
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4101940
//
void CollationRegressionTest::Test4101940(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = nullptr;
UnicodeString rules = "&9 < a < b";
UnicodeString nothing = "";
c = new RuleBasedCollator(rules, status);
if (c == nullptr || U_FAILURE(status))
{
errln("Failed to create RuleBasedCollator");
delete c;
return;
}
CollationElementIterator *i = c->createCollationElementIterator(nothing);
i->reset();
if (i->next(status) != CollationElementIterator::NULLORDER)
{
errln("next did not return NULLORDER");
}
delete i;
delete c;
}
// @bug 4103436
//
// Collator::compare not handling spaces properly
//
void CollationRegressionTest::Test4103436(/* char* par */)
{
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::TERTIARY);
static const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x66, 0x69, 0x6c, 0x65, 0}, {0x3c, 0}, {0x66, 0x69, 0x6c, 0x65, 0x20, 0x61, 0x63, 0x63, 0x65, 0x73, 0x73, 0},
{0x66, 0x69, 0x6c, 0x65, 0}, {0x3c, 0}, {0x66, 0x69, 0x6c, 0x65, 0x61, 0x63, 0x63, 0x65, 0x73, 0x73, 0}
};
compareArray(*c, tests, UPRV_LENGTHOF(tests));
delete c;
}
// @bug 4114076
//
// Collation not Unicode conformant with Hangul syllables
//
void CollationRegressionTest::Test4114076(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::TERTIARY);
//
// With Canonical decomposition, Hangul syllables should get decomposed
// into Jamo, but Jamo characters should not be decomposed into
// conjoining Jamo
//
static const char16_t test1[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0xd4db, 0}, {0x3d, 0}, {0x1111, 0x1171, 0x11b6, 0}
};
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
compareArray(*c, test1, UPRV_LENGTHOF(test1));
// From UTR #15:
// *In earlier versions of Unicode, jamo characters like ksf
// had compatibility mappings to kf + sf. These mappings were
// removed in Unicode 2.1.9 to ensure that Hangul syllables are maintained.)
// That is, the following test is obsolete as of 2.1.9
//obsolete- // With Full decomposition, it should go all the way down to
//obsolete- // conjoining Jamo characters.
//obsolete- //
//obsolete- static const char16_t test2[][CollationRegressionTest::MAX_TOKEN_LEN] =
//obsolete- {
//obsolete- {0xd4db, 0}, {0x3d, 0}, {0x1111, 0x116e, 0x1175, 0x11af, 0x11c2, 0}
//obsolete- };
//obsolete-
//obsolete- c->setDecomposition(Normalizer::DECOMP_COMPAT);
//obsolete- compareArray(*c, test2, UPRV_LENGTHOF(test2));
delete c;
}
// @bug 4124632
//
// Collator::getCollationKey was hanging on certain character sequences
//
void CollationRegressionTest::Test4124632(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
Collator *coll = nullptr;
coll = Collator::createInstance(Locale::getJapan(), status);
if (coll == nullptr || U_FAILURE(status))
{
errln("Failed to create collator for Locale::JAPAN");
delete coll;
return;
}
static const char16_t test[] = {0x41, 0x0308, 0x62, 0x63, 0};
CollationKey key;
coll->getCollationKey(test, key, status);
if (key.isBogus() || U_FAILURE(status))
{
errln("CollationKey creation failed.");
}
delete coll;
}
// @bug 4132736
//
// sort order of french words with multiple accents has errors
//
void CollationRegressionTest::Test4132736(/* char* par */)
{
UErrorCode status = U_ZERO_ERROR;
Collator *c = nullptr;
c = Collator::createInstance(Locale::getCanadaFrench(), status);
c->setStrength(Collator::TERTIARY);
if (c == nullptr || U_FAILURE(status))
{
errln("Failed to create a collator for Locale::getCanadaFrench()");
delete c;
return;
}
static const char16_t test1[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x65, 0x0300, 0x65, 0x0301, 0}, {0x3c, 0}, {0x65, 0x0301, 0x65, 0x0300, 0},
{0x65, 0x0300, 0x0301, 0}, {0x3c, 0}, {0x65, 0x0301, 0x0300, 0}
};
compareArray(*c, test1, UPRV_LENGTHOF(test1));
delete c;
}
// @bug 4133509
//
// The sorting using java.text.CollationKey is not in the exact order
//
void CollationRegressionTest::Test4133509(/* char* par */)
{
static const char16_t test1[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x45, 0x78, 0x63, 0x65, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0}, {0x3c, 0}, {0x45, 0x78, 0x63, 0x65, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x49, 0x6e, 0x49, 0x6e, 0x69, 0x74, 0x69, 0x61, 0x6c, 0x69, 0x7a, 0x65, 0x72, 0x45, 0x72, 0x72, 0x6f, 0x72, 0},
{0x47, 0x72, 0x61, 0x70, 0x68, 0x69, 0x63, 0x73, 0}, {0x3c, 0}, {0x47, 0x72, 0x61, 0x70, 0x68, 0x69, 0x63, 0x73, 0x45, 0x6e, 0x76, 0x69, 0x72, 0x6f, 0x6e, 0x6d, 0x65, 0x6e, 0x74, 0},
{0x53, 0x74, 0x72, 0x69, 0x6e, 0x67, 0}, {0x3c, 0}, {0x53, 0x74, 0x72, 0x69, 0x6e, 0x67, 0x42, 0x75, 0x66, 0x66, 0x65, 0x72, 0}
};
compareArray(*en_us, test1, UPRV_LENGTHOF(test1));
}
// @bug 4114077
//
// Collation with decomposition off doesn't work for Europe
//
void CollationRegressionTest::Test4114077(/* char* par */)
{
// Ensure that we get the same results with decomposition off
// as we do with it on....
UErrorCode status = U_ZERO_ERROR;
RuleBasedCollator *c = en_us->clone();
c->setStrength(Collator::TERTIARY);
static const char16_t test1[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x00C0, 0}, {0x3d, 0}, {0x41, 0x0300, 0}, // Should be equivalent
{0x70, 0x00ea, 0x63, 0x68, 0x65, 0}, {0x3e, 0}, {0x70, 0x00e9, 0x63, 0x68, 0x00e9, 0},
{0x0204, 0}, {0x3d, 0}, {0x45, 0x030F, 0},
{0x01fa, 0}, {0x3d, 0}, {0x41, 0x030a, 0x0301, 0}, // a-ring-acute -> a-ring, acute
// -> a, ring, acute
{0x41, 0x0300, 0x0316, 0}, {0x3c, 0}, {0x41, 0x0316, 0x0300, 0} // No reordering --> unequal
};
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_OFF, status);
compareArray(*c, test1, UPRV_LENGTHOF(test1));
static const char16_t test2[][CollationRegressionTest::MAX_TOKEN_LEN] =
{
{0x41, 0x0300, 0x0316, 0}, {0x3d, 0}, {0x41, 0x0316, 0x0300, 0} // Reordering --> equal
};
c->setAttribute(UCOL_NORMALIZATION_MODE, UCOL_ON, status);
compareArray(*c, test2, UPRV_LENGTHOF(test2));
delete c;
}
// @bug 4141640
//
// Support for Swedish gone in 1.1.6 (Can't create Swedish collator)
//
void CollationRegressionTest::Test4141640(/* char* par */)
{
//
// Rather than just creating a Swedish collator, we might as well
// try to instantiate one for every locale available on the system
// in order to prevent this sort of bug from cropping up in the future
//
UErrorCode status = U_ZERO_ERROR;
int32_t i, localeCount;
const Locale *locales = Locale::getAvailableLocales(localeCount);
for (i = 0; i < localeCount; i += 1)
{
Collator *c = nullptr;
status = U_ZERO_ERROR;
c = Collator::createInstance(locales[i], status);
if (c == nullptr || U_FAILURE(status))
{
UnicodeString msg, localeName;
msg += "Could not create collator for locale ";
msg += locales[i].getName();
errln(msg);
}
delete c;
}
}
// @bug 4139572
//
// getCollationKey throws exception for spanish text
// Cannot reproduce this bug on 1.2, however it DOES fail on 1.1.6
//
void CollationRegressionTest::Test4139572(/* char* par */)
{
//
// Code pasted straight from the bug report
// (and then translated to C++ ;-)
//
// create spanish locale and collator
UErrorCode status = U_ZERO_ERROR;
Locale l("es", "es");
Collator *col = nullptr;
col = Collator::createInstance(l, status);
if (col == nullptr || U_FAILURE(status))
{
errln("Failed to create a collator for es_es locale.");
delete col;
return;
}
CollationKey key;
// this spanish phrase kills it!
col->getCollationKey("Nombre De Objeto", key, status);
if (key.isBogus() || U_FAILURE(status))
{
errln("Error creating CollationKey for \"Nombre De Ojbeto\"");
}
delete col;
}
void CollationRegressionTest::Test4179216() {
// you can position a CollationElementIterator in the middle of
// a contracting character sequence, yielding a bogus collation
// element
IcuTestErrorCode errorCode(*this, "Test4179216");
RuleBasedCollator coll(en_us->getRules() + " & C < ch , cH , Ch , CH < cat < crunchy", errorCode);
UnicodeString testText = "church church catcatcher runcrunchynchy";
CollationElementIterator *iter = coll.createCollationElementIterator(testText);
// test that the "ch" combination works properly
iter->setOffset(4, errorCode);
int32_t elt4 = CollationElementIterator::primaryOrder(iter->next(errorCode));
iter->reset();
int32_t elt0 = CollationElementIterator::primaryOrder(iter->next(errorCode));
iter->setOffset(5, errorCode);
int32_t elt5 = CollationElementIterator::primaryOrder(iter->next(errorCode));
// Compares and prints only 16-bit primary weights.
if (elt4 != elt0 || elt5 != elt0) {
errln("The collation elements at positions 0 (0x%04x), "
"4 (0x%04x), and 5 (0x%04x) don't match.",
elt0, elt4, elt5);
}
// test that the "cat" combination works properly
iter->setOffset(14, errorCode);
int32_t elt14 = CollationElementIterator::primaryOrder(iter->next(errorCode));
iter->setOffset(15, errorCode);
int32_t elt15 = CollationElementIterator::primaryOrder(iter->next(errorCode));
iter->setOffset(16, errorCode);
int32_t elt16 = CollationElementIterator::primaryOrder(iter->next(errorCode));
iter->setOffset(17, errorCode);
int32_t elt17 = CollationElementIterator::primaryOrder(iter->next(errorCode));
iter->setOffset(18, errorCode);
int32_t elt18 = CollationElementIterator::primaryOrder(iter->next(errorCode));
iter->setOffset(19, errorCode);
int32_t elt19 = CollationElementIterator::primaryOrder(iter->next(errorCode));
// Compares and prints only 16-bit primary weights.
if (elt14 != elt15 || elt14 != elt16 || elt14 != elt17
|| elt14 != elt18 || elt14 != elt19) {
errln("\"cat\" elements don't match: elt14 = 0x%04x, "
"elt15 = 0x%04x, elt16 = 0x%04x, elt17 = 0x%04x, "
"elt18 = 0x%04x, elt19 = 0x%04x",
elt14, elt15, elt16, elt17, elt18, elt19);
}
// now generate a complete list of the collation elements,
// first using next() and then using setOffset(), and
// make sure both interfaces return the same set of elements
iter->reset();
int32_t elt = iter->next(errorCode);
int32_t count = 0;
while (elt != CollationElementIterator::NULLORDER) {
++count;
elt = iter->next(errorCode);
}
LocalArray<UnicodeString> nextElements(new UnicodeString[count]);
LocalArray<UnicodeString> setOffsetElements(new UnicodeString[count]);
int32_t lastPos = 0;
iter->reset();
elt = iter->next(errorCode);
count = 0;
while (elt != CollationElementIterator::NULLORDER) {
nextElements[count++] = testText.tempSubStringBetween(lastPos, iter->getOffset());
lastPos = iter->getOffset();
elt = iter->next(errorCode);
}
int32_t nextElementsLength = count;
count = 0;
for (int32_t i = 0; i < testText.length(); ) {
iter->setOffset(i, errorCode);
lastPos = iter->getOffset();
elt = iter->next(errorCode);
setOffsetElements[count++] = testText.tempSubStringBetween(lastPos, iter->getOffset());
i = iter->getOffset();
}
for (int32_t i = 0; i < nextElementsLength; i++) {
if (nextElements[i] == setOffsetElements[i]) {
logln(nextElements[i]);
} else {
errln(UnicodeString("Error: next() yielded ") + nextElements[i] +
", but setOffset() yielded " + setOffsetElements[i]);
}
}
delete iter;
}
// Ticket 7189
//
// nextSortKeyPart incorrect for EO_S1 collation
static int32_t calcKeyIncremental(UCollator *coll, const char16_t* text, int32_t len, uint8_t *keyBuf, int32_t /*keyBufLen*/, UErrorCode& status) {
UCharIterator uiter;
uint32_t state[2] = { 0, 0 };
int32_t keyLen;
int32_t count = 8;
uiter_setString(&uiter, text, len);
keyLen = 0;
while (true) {
int32_t keyPartLen = ucol_nextSortKeyPart(coll, &uiter, state, &keyBuf[keyLen], count, &status);
if (U_FAILURE(status)) {
return -1;
}
if (keyPartLen == 0) {
break;
}
keyLen += keyPartLen;
}
return keyLen;
}
void CollationRegressionTest::TestT7189() {
UErrorCode status = U_ZERO_ERROR;
UCollator *coll;
uint32_t i;
static const char16_t text1[][CollationRegressionTest::MAX_TOKEN_LEN] = {
// "Achter De Hoven"
{ 0x41, 0x63, 0x68, 0x74, 0x65, 0x72, 0x20, 0x44, 0x65, 0x20, 0x48, 0x6F, 0x76, 0x65, 0x6E, 0x00 },
// "ABC"
{ 0x41, 0x42, 0x43, 0x00 },
// "HELLO world!"
{ 0x48, 0x45, 0x4C, 0x4C, 0x4F, 0x20, 0x77, 0x6F, 0x72, 0x6C, 0x64, 0x21, 0x00 }
};
static const char16_t text2[][CollationRegressionTest::MAX_TOKEN_LEN] = {
// "Achter de Hoven"
{ 0x41, 0x63, 0x68, 0x74, 0x65, 0x72, 0x20, 0x64, 0x65, 0x20, 0x48, 0x6F, 0x76, 0x65, 0x6E, 0x00 },
// "abc"
{ 0x61, 0x62, 0x63, 0x00 },
// "hello world!"
{ 0x68, 0x65, 0x6C, 0x6C, 0x6F, 0x20, 0x77, 0x6F, 0x72, 0x6C, 0x64, 0x21, 0x00 }
};
// Open the collator
coll = ucol_openFromShortString("EO_S1", false, nullptr, &status);
if (U_FAILURE(status)) {
errln("Failed to create a collator for short string EO_S1");
return;
}
for (i = 0; i < UPRV_LENGTHOF(text1); i++) {
uint8_t key1[100], key2[100];
int32_t len1, len2;
len1 = calcKeyIncremental(coll, text1[i], -1, key1, sizeof(key1), status);
if (U_FAILURE(status)) {
errln(UnicodeString("Failed to get a partial collation key for ") + text1[i]);
break;
}
len2 = calcKeyIncremental(coll, text2[i], -1, key2, sizeof(key2), status);
if (U_FAILURE(status)) {
errln(UnicodeString("Failed to get a partial collation key for ") + text2[i]);
break;
}
if (len1 == len2 && uprv_memcmp(key1, key2, len1) == 0) {
errln(UnicodeString("Failed: Identical key\n") + " text1: " + text1[i] + "\n" + " text2: " + text2[i] + "\n" + " key : " + TestUtility::hex(key1, len1));
} else {
logln(UnicodeString("Keys produced -\n") + " text1: " + text1[i] + "\n" + " key1 : " + TestUtility::hex(key1, len1) + "\n" + " text2: " + text2[i] + "\n" + " key2 : "
+ TestUtility::hex(key2, len2));
}
}
ucol_close(coll);
}
void CollationRegressionTest::TestCaseFirstCompression() {
RuleBasedCollator *col = en_us->clone();
UErrorCode status = U_ZERO_ERROR;
// default
caseFirstCompressionSub(col, "default");
// Upper first
col->setAttribute(UCOL_CASE_FIRST, UCOL_UPPER_FIRST, status);
if (U_FAILURE(status)) {
errln("Failed to set UCOL_UPPER_FIRST");
return;
}
caseFirstCompressionSub(col, "upper first");
// Lower first
col->setAttribute(UCOL_CASE_FIRST, UCOL_LOWER_FIRST, status);
if (U_FAILURE(status)) {
errln("Failed to set UCOL_LOWER_FIRST");
return;
}
caseFirstCompressionSub(col, "lower first");
delete col;
}
void CollationRegressionTest::caseFirstCompressionSub(Collator *col, UnicodeString opt) {
const int32_t maxLength = 50;
char16_t str1[maxLength];
char16_t str2[maxLength];
CollationKey key1, key2;
for (int32_t len = 1; len <= maxLength; len++) {
int32_t i = 0;
for (; i < len - 1; i++) {
str1[i] = str2[i] = static_cast<char16_t>(0x61); // 'a'
}
str1[i] = static_cast<char16_t>(0x41); // 'A'
str2[i] = static_cast<char16_t>(0x61); // 'a'
UErrorCode status = U_ZERO_ERROR;
col->getCollationKey(str1, len, key1, status);
col->getCollationKey(str2, len, key2, status);
UCollationResult cmpKey = key1.compareTo(key2, status);
UCollationResult cmpCol = col->compare(str1, len, str2, len, status);
if (U_FAILURE(status)) {
errln("Error in caseFirstCompressionSub");
} else if (cmpKey != cmpCol) {
errln(UnicodeString("Inconsistent comparison(") + opt
+ "): str1=" + UnicodeString(str1, len) + ", str2=" + UnicodeString(str2, len)
+ ", cmpKey=" + cmpKey + ", cmpCol=" + cmpCol);
}
}
}
void CollationRegressionTest::TestTrailingComment() {
// ICU ticket #8070:
// Check that the rule parser handles a comment without terminating end-of-line.
IcuTestErrorCode errorCode(*this, "TestTrailingComment");
RuleBasedCollator coll(UNICODE_STRING_SIMPLE("&c<b#comment1\n<a#comment2"), errorCode);
UnicodeString a(static_cast<char16_t>(0x61)), b(static_cast<char16_t>(0x62)), c(static_cast<char16_t>(0x63));
assertTrue("c<b", coll.compare(c, b) < 0);
assertTrue("b<a", coll.compare(b, a) < 0);
}
void CollationRegressionTest::TestBeforeWithTooStrongAfter() {
// ICU ticket #9959:
// Forbid rules with a before-reset followed by a stronger relation.
IcuTestErrorCode errorCode(*this, "TestBeforeWithTooStrongAfter");
RuleBasedCollator before2(UNICODE_STRING_SIMPLE("&[before 2]x<<q<p"), errorCode);
if(errorCode.isSuccess()) {
errln("should forbid before-2-reset followed by primary relation");
} else {
errorCode.reset();
}
RuleBasedCollator before3(UNICODE_STRING_SIMPLE("&[before 3]x<<<q<<s<p"), errorCode);
if(errorCode.isSuccess()) {
errln("should forbid before-3-reset followed by primary or secondary relation");
} else {
errorCode.reset();
}
}
void CollationRegressionTest::TestICU22555InfinityLoop() {
char16_t data[] = {
0x0020, 0x0026, 0x4000, 0x002c, 0x6601, 0x0106, 0xff7f, 0xff99,
0x003b, 0x1141, 0x106a, 0x1006, 0x0001, 0x0080, 0x1141, 0x106a,
0x0026, 0x00ff, 0xff6f, 0xff99, 0x013b, 0x1141, 0x1067, 0x1026,
0x0601, 0x0080, 0x5f03, 0x17e3, 0x0000, 0x3e00, 0x3e3e, 0x0055,
0x8080, 0x0000, 0x01e4, 0x0000, 0x0300, 0x003d, 0x4cff, 0x8053,
0x7a65, 0x0000, 0x6400, 0x5f00, 0x0150, 0x9090, 0x9090, 0x2f5f,
0x0053, 0xffe4, 0x002c, 0x0300, 0x1f3d, 0x55f7, 0x8053, 0x1750,
0x3d00, 0xff00, 0x00ff, 0xff6f, 0x0099, 0x03fa, 0x0303, 0x0303,
0x0303, 0x0303, 0x0303, 0x0303, 0x0303, 0x0303, 0x0303, 0x0303,
0x0303, 0x0303, 0x0303, 0x0303, 0x0303, 0x0303, 0x0303, 0x0303,
};
icu::UnicodeString rule(false, data, sizeof(data)/sizeof(char16_t));
UErrorCode status = U_ZERO_ERROR;
icu::LocalPointer<icu::RuleBasedCollator> col1(
new icu::RuleBasedCollator(rule, status));
}
void CollationRegressionTest::TestICU22517() {
IcuTestErrorCode errorCode(*this, "TestICU22517");
char16_t data[] = u"&a=b쫊쫊쫊쫊쫊쫊쫊쫊";
icu::UnicodeString rule(true, data, -1);
int length = quick ? rule.length()-2 : rule.length();
for (int i = 4; i <= length; i++) {
UErrorCode status = U_ZERO_ERROR;
icu::LocalPointer<icu::RuleBasedCollator> col1(
new icu::RuleBasedCollator(rule.tempSubString(0, i), status));
}
}
void CollationRegressionTest::TestICU22277() {
IcuTestErrorCode errorCode(*this, "TestICU22277");
UErrorCode status = U_ZERO_ERROR;
Collator* c = Collator::createInstance("JA-u-Co-priVatE-KANa", status);
if(c != nullptr || U_SUCCESS(status)) {
errcheckln(status, "Collator should have failed with MemorySanitizer: use-of-uninitialized-value error - %s",
u_errorName(status));
delete c;
return;
}
c = Collator::createInstance("hE-U-cO-pRIVate-UNihan", status);
if(c != nullptr || U_SUCCESS(status)) {
errcheckln(status, "Collator should have failed with MemorySanitizer: use-of-uninitialized-value error - %s",
u_errorName(status));
delete c;
return;
}
}
void CollationRegressionTest::compareArray(Collator &c,
const char16_t tests[][CollationRegressionTest::MAX_TOKEN_LEN],
int32_t testCount)
{
int32_t i;
Collator::EComparisonResult expectedResult = Collator::EQUAL;
for (i = 0; i < testCount; i += 3)
{
UnicodeString source(tests[i]);
UnicodeString comparison(tests[i + 1]);
UnicodeString target(tests[i + 2]);
if (comparison == "<")
{
expectedResult = Collator::LESS;
}
else if (comparison == ">")
{
expectedResult = Collator::GREATER;
}
else if (comparison == "=")
{
expectedResult = Collator::EQUAL;
}
else
{
UnicodeString bogus1("Bogus comparison string \"");
UnicodeString bogus2("\"");
errln(bogus1 + comparison + bogus2);
}
Collator::EComparisonResult compareResult = c.compare(source, target);
CollationKey sourceKey, targetKey;
UErrorCode status = U_ZERO_ERROR;
c.getCollationKey(source, sourceKey, status);
if (U_FAILURE(status))
{
errln("Couldn't get collationKey for source");
continue;
}
c.getCollationKey(target, targetKey, status);
if (U_FAILURE(status))
{
errln("Couldn't get collationKey for target");
continue;
}
Collator::EComparisonResult keyResult = sourceKey.compareTo(targetKey);
reportCResult( source, target, sourceKey, targetKey, compareResult, keyResult, compareResult, expectedResult );
}
}
void CollationRegressionTest::assertEqual(CollationElementIterator &i1, CollationElementIterator &i2)
{
int32_t c1, c2, count = 0;
UErrorCode status = U_ZERO_ERROR;
do
{
c1 = i1.next(status);
c2 = i2.next(status);
if (c1 != c2)
{
UnicodeString msg, msg1(" ");
msg += msg1 + count;
msg += ": strength(0x";
appendHex(c1, 8, msg);
msg += ") != strength(0x";
appendHex(c2, 8, msg);
msg += ")";
errln(msg);
break;
}
count += 1;
}
while (c1 != CollationElementIterator::NULLORDER);
}
void CollationRegressionTest::runIndexedTest(int32_t index, UBool exec, const char* &name, char* /* par */)
{
if (exec)
{
logln("Collation Regression Tests: ");
}
if(en_us == nullptr) {
dataerrln("Class collator not instantiated");
name = "";
return;
}
TESTCASE_AUTO_BEGIN;
TESTCASE_AUTO(Test4048446);
TESTCASE_AUTO(Test4051866);
TESTCASE_AUTO(Test4053636);
TESTCASE_AUTO(Test4054238);
TESTCASE_AUTO(Test4054734);
TESTCASE_AUTO(Test4054736);
TESTCASE_AUTO(Test4058613);
TESTCASE_AUTO(Test4059820);
TESTCASE_AUTO(Test4060154);
TESTCASE_AUTO(Test4062418);
TESTCASE_AUTO(Test4065540);
TESTCASE_AUTO(Test4066189);
TESTCASE_AUTO(Test4066696);
TESTCASE_AUTO(Test4076676);
TESTCASE_AUTO(Test4078588);
TESTCASE_AUTO(Test4079231);
TESTCASE_AUTO(Test4081866);
TESTCASE_AUTO(Test4087241);
TESTCASE_AUTO(Test4087243);
TESTCASE_AUTO(Test4092260);
TESTCASE_AUTO(Test4095316);
TESTCASE_AUTO(Test4101940);
TESTCASE_AUTO(Test4103436);
TESTCASE_AUTO(Test4114076);
TESTCASE_AUTO(Test4114077);
TESTCASE_AUTO(Test4124632);
TESTCASE_AUTO(Test4132736);
TESTCASE_AUTO(Test4133509);
TESTCASE_AUTO(Test4139572);
TESTCASE_AUTO(Test4141640);
TESTCASE_AUTO(Test4179216);
TESTCASE_AUTO(TestT7189);
TESTCASE_AUTO(TestCaseFirstCompression);
TESTCASE_AUTO(TestTrailingComment);
TESTCASE_AUTO(TestBeforeWithTooStrongAfter);
TESTCASE_AUTO(TestICU22277);
TESTCASE_AUTO(TestICU22517);
TESTCASE_AUTO(TestICU22555InfinityLoop);
TESTCASE_AUTO_END;
}
#endif /* #if !UCONFIG_NO_COLLATION */
|