X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/4388f060552cc537e71e957d32f35e9d75a61233..2be6500137966bba13903b24204a44804f9e133a:/icuSources/test/intltest/alphaindextst.cpp diff --git a/icuSources/test/intltest/alphaindextst.cpp b/icuSources/test/intltest/alphaindextst.cpp index bc928600..9e025496 100644 --- a/icuSources/test/intltest/alphaindextst.cpp +++ b/icuSources/test/intltest/alphaindextst.cpp @@ -1,17 +1,20 @@ /******************************************************************** * COPYRIGHT: - * Copyright (c) 2012, International Business Machines Corporation and - * others. All Rights Reserved. + * Copyright (c) 2012-2013, International Business Machines Corporation + * and others. All Rights Reserved. ********************************************************************/ // // file: alphaindex.cpp // Alphabetic Index Tests. // +#include // for sprintf + #include "intltest.h" #include "alphaindextst.h" #include "unicode/alphaindex.h" #include "unicode/coll.h" +#include "unicode/localpointer.h" #include "unicode/tblcoll.h" #include "unicode/uniset.h" @@ -20,6 +23,24 @@ // #include // #include +#define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0])) + +namespace { + +UnicodeString joinLabelsAndAppend(AlphabeticIndex::ImmutableIndex &index, UnicodeString &dest) { + int32_t oldLength = dest.length(); + const AlphabeticIndex::Bucket *bucket; + for (int32_t i = 0; (bucket = index.getBucket(i)) != NULL; ++i) { + if (dest.length() > oldLength) { + dest.append((UChar)0x3A); // ':' + } + dest.append(bucket->getLabel()); + } + return dest; +} + +} // namespace + AlphabeticIndexTest::AlphabeticIndexTest() { } @@ -29,27 +50,18 @@ AlphabeticIndexTest::~AlphabeticIndexTest() { void AlphabeticIndexTest::runIndexedTest( int32_t index, UBool exec, const char* &name, char* /*par*/ ) { if (exec) logln("TestSuite AlphabeticIndex: "); - switch (index) { - - case 0: name = "APITest"; - if (exec) APITest(); - break; - - case 1: name = "ManyLocales"; - if (exec) ManyLocalesTest(); - break; - - case 2: name = "HackPinyinTest"; - if (exec) HackPinyinTest(); - break; - - case 3: name = "TestBug9009"; - if (exec) TestBug9009(); - break; - - default: name = ""; - break; //needed to end loop - } + TESTCASE_AUTO_BEGIN; + TESTCASE_AUTO(APITest); + TESTCASE_AUTO(ManyLocalesTest); + TESTCASE_AUTO(HackPinyinTest); + TESTCASE_AUTO(TestBug9009); + TESTCASE_AUTO(TestIndexCharactersList); + TESTCASE_AUTO(TestHaniFirst); + TESTCASE_AUTO(TestPinyinFirst); + TESTCASE_AUTO(TestSchSt); + TESTCASE_AUTO(TestNoLabels); + TESTCASE_AUTO(TestChineseZhuyin); + TESTCASE_AUTO_END; } #define TEST_CHECK_STATUS {if (U_FAILURE(status)) {dataerrln("%s:%d: Test failure. status=%s", \ @@ -76,6 +88,21 @@ void AlphabeticIndexTest::APITest() { //printf("getBucketCount() == %d\n", lc); delete index; + // Constructor from a Collator + // + status = U_ZERO_ERROR; + RuleBasedCollator *coll = dynamic_cast(Collator::createInstance(Locale::getChinese(), status)); + TEST_CHECK_STATUS; + TEST_ASSERT(coll != NULL); + index = new AlphabeticIndex(coll, status); + TEST_CHECK_STATUS; + TEST_ASSERT(coll == &index->getCollator()); + assertEquals("only the underflow label in an index built from a collator", + 1, index->getBucketCount(status)); + TEST_CHECK_STATUS; + delete index; + + // addLabels() status = U_ZERO_ERROR; @@ -87,12 +114,8 @@ void AlphabeticIndexTest::APITest() { TEST_CHECK_STATUS; lc = index->getBucketCount(status); TEST_CHECK_STATUS; - // TODO: should get 31. Java also gives 30. Needs fixing - TEST_ASSERT(30 == lc); // 26 Latin letters plus - // TEST_ASSERT(31 == lc); // 26 Latin letters plus - // 2 Cyrillic letters plus - // 1 inflow label plus - // two under/overflow labels. + assertEquals("underflow, A-Z, inflow, 2 Cyrillic, overflow", + 31, index->getBucketCount(status)); // std::cout << lc << std::endl; delete index; @@ -281,17 +304,26 @@ void AlphabeticIndexTest::APITest() { delete index; index = new AlphabeticIndex(Locale::createFromName("ru"), status); - //Locale loc = Locale::createFromName(localeName); TEST_CHECK_STATUS; + assertEquals("Russian index.getBucketCount()", 32, index->getBucketCount(status)); + // Latin-script names should go into the underflow label (0) + // if the Russian collation does not use script reordering, + // but into the overflow label (getBucketCount()-1) + // if Russian sorts Cyrillic first. + int32_t reorderCodes[20]; + int32_t expectedLatinIndex = 0; + if (index->getCollator().getReorderCodes(reorderCodes, LENGTHOF(reorderCodes), status) > 0) { + expectedLatinIndex = index->getBucketCount(status) - 1; + } n = index->getBucketIndex(adam, status); TEST_CHECK_STATUS; - TEST_ASSERT(n == 0); // Label #0 is underflow + assertEquals("Russian index.getBucketIndex(adam)", expectedLatinIndex, n); n = index->getBucketIndex(baker, status); - TEST_ASSERT(n == 0); + assertEquals("Russian index.getBucketIndex(baker)", expectedLatinIndex, n); n = index->getBucketIndex(Cyrillic, status); - TEST_ASSERT(n == 1); // Overflow label + assertEquals("Russian index.getBucketIndex(Cyrillic)", 1, n); n = index->getBucketIndex(zed, status); - TEST_ASSERT(n == 0); + assertEquals("Russian index.getBucketIndex(zed)", expectedLatinIndex, n); delete index; @@ -310,7 +342,6 @@ static const char * KEY_LOCALES[] = { void AlphabeticIndexTest::ManyLocalesTest() { UErrorCode status = U_ZERO_ERROR; int32_t lc = 0; - AlphabeticIndex *index = NULL; for (int i=0; ; ++i) { status = U_ZERO_ERROR; @@ -320,23 +351,40 @@ void AlphabeticIndexTest::ManyLocalesTest() { } // std::cout << localeName << " "; Locale loc = Locale::createFromName(localeName); - index = new AlphabeticIndex(loc, status); + AlphabeticIndex index(loc, status); TEST_CHECK_STATUS; - lc = index->getBucketCount(status); + lc = index.getBucketCount(status); TEST_CHECK_STATUS; // std::cout << "getBucketCount() == " << lc << std::endl; - while (index->nextBucket(status)) { + LocalPointer immIndex(index.buildImmutableIndex(status)); + TEST_CHECK_STATUS; + TEST_ASSERT(lc == immIndex->getBucketCount()); + + assertEquals("initial bucket index", -1, index.getBucketIndex()); + int32_t bucketIndex = 0; + while (index.nextBucket(status)) { TEST_CHECK_STATUS; - const UnicodeString &label = index->getBucketLabel(); + assertEquals("bucket index", bucketIndex, index.getBucketIndex()); + const UnicodeString &label = index.getBucketLabel(); TEST_ASSERT(label.length()>0); // std::string ss; // std::cout << ":" << label.toUTF8String(ss); + const AlphabeticIndex::Bucket *bucket = immIndex->getBucket(bucketIndex); + TEST_ASSERT(bucket != NULL); + assertEquals("bucket label vs. immutable: locale=" + UnicodeString(localeName) + + " index=" + bucketIndex, + label, bucket->getLabel()); + TEST_ASSERT(&label != &bucket->getLabel()); // not the same pointers + UAlphabeticIndexLabelType labelType = index.getBucketLabelType(); + TEST_ASSERT(labelType == bucket->getLabelType()); + ++bucketIndex; } // std::cout << ":" << std::endl; - - delete index; + TEST_ASSERT(immIndex->getBucketCount() == bucketIndex); + TEST_ASSERT(immIndex->getBucket(-1) == NULL); + TEST_ASSERT(immIndex->getBucket(bucketIndex) == NULL); } } @@ -430,6 +478,200 @@ void AlphabeticIndexTest::TestBug9009() { aindex.nextBucket(status); // Crash here before bug was fixed. TEST_CHECK_STATUS; } - + +static const char *localeAndIndexCharactersLists[][2] = { + /* Arabic*/ {"ar", "\\u0627:\\u0628:\\u062A:\\u062B:\\u062C:\\u062D:\\u062E:\\u062F:\\u0630:\\u0631:\\u0632:\\u0633:\\u0634:\\u0635:\\u0636:\\u0637:\\u0638:\\u0639:\\u063A:\\u0641:\\u0642:\\u0643:\\u0644:\\u0645:\\u0646:\\u0647:\\u0648:\\u064A"}, + /* Bulgarian*/ {"bg", "\\u0410:\\u0411:\\u0412:\\u0413:\\u0414:\\u0415:\\u0416:\\u0417:\\u0418:\\u0419:\\u041A:\\u041B:\\u041C:\\u041D:\\u041E:\\u041F:\\u0420:\\u0421:\\u0422:\\u0423:\\u0424:\\u0425:\\u0426:\\u0427:\\u0428:\\u0429:\\u042E:\\u042F"}, + /* Catalan*/ {"ca", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Czech*/ {"cs", "A:B:C:\\u010C:D:E:F:G:H:CH:I:J:K:L:M:N:O:P:Q:R:\\u0158:S:\\u0160:T:U:V:W:X:Y:Z:\\u017D"}, + /* Danish*/ {"da", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\\u00C6:\\u00D8:\\u00C5"}, + /* German*/ {"de", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:Sch:St:T:U:V:W:X:Y:Z"}, + /* Greek*/ {"el", "\\u0391:\\u0392:\\u0393:\\u0394:\\u0395:\\u0396:\\u0397:\\u0398:\\u0399:\\u039A:\\u039B:\\u039C:\\u039D:\\u039E:\\u039F:\\u03A0:\\u03A1:\\u03A3:\\u03A4:\\u03A5:\\u03A6:\\u03A7:\\u03A8:\\u03A9"}, + /* English*/ {"en", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Spanish*/ {"es", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:\\u00D1:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Estonian*/ {"et", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:\\u0160:Z:\\u017D:T:U:V:\\u00D5:\\u00C4:\\u00D6:\\u00DC:X:Y"}, + /* Basque*/ {"eu", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Finnish*/ {"fi", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\\u00C5:\\u00C4:\\u00D6"}, + /* Filipino*/ {"fil", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* French*/ {"fr", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Hebrew*/ {"he", "\\u05D0:\\u05D1:\\u05D2:\\u05D3:\\u05D4:\\u05D5:\\u05D6:\\u05D7:\\u05D8:\\u05D9:\\u05DB:\\u05DC:\\u05DE:\\u05E0:\\u05E1:\\u05E2:\\u05E4:\\u05E6:\\u05E7:\\u05E8:\\u05E9:\\u05EA"}, + /* Icelandic*/ {"is", "A:\\u00C1:B:C:D:\\u00D0:E:\\u00C9:F:G:H:I:\\u00CD:J:K:L:M:N:O:\\u00D3:P:Q:R:S:T:U:\\u00DA:V:W:X:Y:\\u00DD:Z:\\u00DE:\\u00C6:\\u00D6"}, + /* Italian*/ {"it", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Japanese*/ {"ja", "\\u3042:\\u304B:\\u3055:\\u305F:\\u306A:\\u306F:\\u307E:\\u3084:\\u3089:\\u308F"}, + /* Korean*/ {"ko", "\\u3131:\\u3134:\\u3137:\\u3139:\\u3141:\\u3142:\\u3145:\\u3147:\\u3148:\\u314A:\\u314B:\\u314C:\\u314D:\\u314E"}, + /* Lithuanian*/ {"lt", "A:B:C:\\u010C:D:E:F:G:H:I:J:K:L:M:N:O:P:R:S:\\u0160:T:U:V:Z:\\u017D"}, + // This should be the correct data. Commented till it is fixed in CLDR collation data. + // {"lv", "A:B:C:\\u010C:D:E:F:G:\\u0122:H:I:Y:J:K:\\u0136:L:\\u013B:M:N:\\u0145:O:P:Q:R:S:\\u0160:T:U:V:W:X:Z:\\u017D"}, + /* Latvian*/ {"lv", "A:B:C:\\u010C:D:E:F:G:\\u0122:H:I:J:K:\\u0136:L:\\u013B:M:N:\\u0145:O:P:Q:R:S:\\u0160:T:U:V:W:X:Y:Z:\\u017D"}, + /* Norwegian Bokm\\u00E5l*/ {"nb", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\\u00C6:\\u00D8:\\u00C5"}, + /* Dutch*/ {"nl", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Polish*/ {"pl", "A:\\u0104:B:C:\\u0106:D:E:\\u0118:F:G:H:I:J:K:L:\\u0141:M:N:\\u0143:O:\\u00D3:P:Q:R:S:\\u015A:T:U:V:W:X:Y:Z:\\u0179:\\u017B"}, + /* Portuguese*/ {"pt", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Romanian*/ {"ro", "A:\\u0102:\\u00C2:B:C:D:E:F:G:H:I:\\u00CE:J:K:L:M:N:O:P:Q:R:S:\\u0218:T:\\u021A:U:V:W:X:Y:Z"}, + /* Russian*/ {"ru", "\\u0410:\\u0411:\\u0412:\\u0413:\\u0414:\\u0415:\\u0416:\\u0417:\\u0418:\\u0419:\\u041A:\\u041B:\\u041C:\\u041D:\\u041E:\\u041F:\\u0420:\\u0421:\\u0422:\\u0423:\\u0424:\\u0425:\\u0426:\\u0427:\\u0428:\\u0429:\\u042B:\\u042D:\\u042E:\\u042F"}, + /* Slovak*/ {"sk", "A:\\u00C4:B:C:\\u010C:D:E:F:G:H:CH:I:J:K:L:M:N:O:\\u00D4:P:Q:R:S:\\u0160:T:U:V:W:X:Y:Z:\\u017D"}, + /* Slovenian*/ {"sl", "A:B:C:\\u010C:\\u0106:D:\\u0110:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:\\u0160:T:U:V:W:X:Y:Z:\\u017D"}, + /* Serbian*/ {"sr", "\\u0410:\\u0411:\\u0412:\\u0413:\\u0414:\\u0402:\\u0415:\\u0416:\\u0417:\\u0418:\\u0408:\\u041A:\\u041B:\\u0409:\\u041C:\\u041D:\\u040A:\\u041E:\\u041F:\\u0420:\\u0421:\\u0422:\\u040B:\\u0423:\\u0424:\\u0425:\\u0426:\\u0427:\\u040F:\\u0428"}, + /* Swedish*/ {"sv", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z:\\u00C5:\\u00C4:\\u00D6"}, + /* Turkish*/ {"tr", "A:B:C:\\u00C7:D:E:F:G:H:I:\\u0130:J:K:L:M:N:O:\\u00D6:P:Q:R:S:\\u015E:T:U:\\u00DC:V:W:X:Y:Z"}, + /* Ukrainian*/ {"uk", "\\u0410:\\u0411:\\u0412:\\u0413:\\u0490:\\u0414:\\u0415:\\u0404:\\u0416:\\u0417:\\u0418:\\u0406:\\u0407:\\u0419:\\u041A:\\u041B:\\u041C:\\u041D:\\u041E:\\u041F:\\u0420:\\u0421:\\u0422:\\u0423:\\u0424:\\u0425:\\u0426:\\u0427:\\u0428:\\u0429:\\u042E:\\u042F"}, + /* Vietnamese*/ {"vi", "A:\\u0102:\\u00C2:B:C:D:\\u0110:E:\\u00CA:F:G:H:I:J:K:L:M:N:O:\\u00D4:\\u01A0:P:Q:R:S:T:U:\\u01AF:V:W:X:Y:Z"}, + /* Chinese*/ {"zh", "A:B:C:D:E:F:G:H:I:J:K:L:M:N:O:P:Q:R:S:T:U:V:W:X:Y:Z"}, + /* Chinese (Traditional Han)*/ {"zh_Hant", "1\\u5283:2\\u5283:3\\u5283:4\\u5283:5\\u5283:6\\u5283:7\\u5283:8\\u5283:9\\u5283:10\\u5283:11\\u5283:12\\u5283:13\\u5283:14\\u5283:15\\u5283:16\\u5283:17\\u5283:18\\u5283:19\\u5283:20\\u5283:21\\u5283:22\\u5283:23\\u5283:24\\u5283:25\\u5283:26\\u5283:27\\u5283:28\\u5283:29\\u5283:30\\u5283:31\\u5283:32\\u5283:33\\u5283:35\\u5283:36\\u5283:39\\u5283:48\\u5283"}, +}; + +void AlphabeticIndexTest::TestIndexCharactersList() { + UErrorCode status = U_ZERO_ERROR; + for (int32_t i = 0; i < LENGTHOF(localeAndIndexCharactersLists); ++i) { + const char *(&localeAndIndexCharacters)[2] = localeAndIndexCharactersLists[i]; + const char *locale = localeAndIndexCharacters[0]; + UnicodeString expectedIndexCharacters + = (UnicodeString("\\u2026:") + localeAndIndexCharacters[1] + ":\\u2026").unescape(); + AlphabeticIndex index(locale, status); + TEST_CHECK_STATUS; + LocalPointer immIndex(index.buildImmutableIndex(status)); + TEST_CHECK_STATUS; + + // Join the elements of the list to a string with delimiter ":" + UnicodeString actualIndexCharacters; + assertEquals(locale, + expectedIndexCharacters, + joinLabelsAndAppend(*immIndex, actualIndexCharacters)); + logln(locale + UnicodeString(": ") + actualIndexCharacters); + } +} + +void AlphabeticIndexTest::TestHaniFirst() { + UErrorCode status = U_ZERO_ERROR; + LocalPointer coll( + static_cast(Collator::createInstance(Locale::getRoot(), status))); + + if (U_FAILURE(status)) { + dataerrln("Failed Collator::createInstance call - %s", u_errorName(status)); + return; + } + int32_t reorderCodes[] = { USCRIPT_HAN }; + coll->setReorderCodes(reorderCodes, LENGTHOF(reorderCodes), status); + TEST_CHECK_STATUS; + AlphabeticIndex index(coll.orphan(), status); + TEST_CHECK_STATUS; + assertEquals("getBucketCount()", 1, index.getBucketCount(status)); // ... (underflow only) + index.addLabels(Locale::getEnglish(), status); + assertEquals("getBucketCount()", 28, index.getBucketCount(status)); // ... A-Z ... + int32_t bucketIndex = index.getBucketIndex(UnicodeString((UChar)0x897f), status); + assertEquals("getBucketIndex(U+897F)", 0, bucketIndex); // underflow bucket + bucketIndex = index.getBucketIndex("i", status); + assertEquals("getBucketIndex(i)", 9, bucketIndex); + bucketIndex = index.getBucketIndex(UnicodeString((UChar)0x03B1), status); + assertEquals("getBucketIndex(Greek alpha)", 27, bucketIndex); + // TODO: Test with an unassigned code point (not just U+FFFF) + // when unassigned code points are not in the Hani reordering group any more. + // String unassigned = UTF16.valueOf(0x50005); + bucketIndex = index.getBucketIndex(UnicodeString((UChar)0xFFFF), status); + assertEquals("getBucketIndex(U+FFFF)", 27, bucketIndex); +} + +void AlphabeticIndexTest::TestPinyinFirst() { + UErrorCode status = U_ZERO_ERROR; + LocalPointer coll( + static_cast(Collator::createInstance(Locale::getChinese(), status))); + if (U_FAILURE(status)) { + dataerrln("Failed Collator::createInstance call - %s", u_errorName(status)); + return; + } + int32_t reorderCodes[] = { USCRIPT_HAN }; + coll->setReorderCodes(reorderCodes, LENGTHOF(reorderCodes), status); + TEST_CHECK_STATUS; + AlphabeticIndex index(coll.orphan(), status); + TEST_CHECK_STATUS; + assertEquals("getBucketCount()", 1, index.getBucketCount(status)); // ... (underflow only) + index.addLabels(Locale::getChinese(), status); + assertEquals("getBucketCount()", 28, index.getBucketCount(status)); // ... A-Z ... + int bucketIndex = index.getBucketIndex(UnicodeString((UChar)0x897f), status); + assertEquals("getBucketIndex(U+897F)", 'X' - 'A' + 1, bucketIndex); + bucketIndex = index.getBucketIndex("i", status); + assertEquals("getBucketIndex(i)", 9, bucketIndex); + bucketIndex = index.getBucketIndex(UnicodeString((UChar)0x03B1), status); + assertEquals("getBucketIndex(Greek alpha)", 27, bucketIndex); + // TODO: Test with an unassigned code point (not just U+FFFF) + // when unassigned code points are not in the Hani reordering group any more. + // String unassigned = UTF16.valueOf(0x50005); + bucketIndex = index.getBucketIndex(UnicodeString((UChar)0xFFFF), status); + assertEquals("getBucketIndex(U+FFFF)", 27, bucketIndex); +} + +void AlphabeticIndexTest::TestSchSt() { + UErrorCode status = U_ZERO_ERROR; + AlphabeticIndex index(Locale::getGerman(), status); + index.addLabels(UnicodeSet("[\\u00C6{Sch*}{St*}]", status), status); + TEST_CHECK_STATUS; + // ... A AE-ligature B-R S Sch St T-Z ... + LocalPointer immIndex(index.buildImmutableIndex(status)); + TEST_CHECK_STATUS; + assertEquals("getBucketCount()", 31, index.getBucketCount(status)); + assertEquals("immutable getBucketCount()", 31, immIndex->getBucketCount()); + static const struct TestCase { + const char *name; + int32_t bucketIndex; + const char *bucketLabel; + } testCases[] = { + // name, bucket index, bucket label + { "Adelbert", 1, "A" }, + { "Afrika", 1, "A" }, + { "\\u00C6sculap", 2, "\\u00C6" }, + { "Aesthet", 2, "\\u00C6" }, + { "Berlin", 3, "B" }, + { "Rilke", 19, "R" }, + { "Sacher", 20, "S" }, + { "Seiler", 20, "S" }, + { "Sultan", 20, "S" }, + { "Schiller", 21, "Sch" }, + { "Steiff", 22, "St" }, + { "Thomas", 23, "T" } + }; + for (int32_t i = 0; i < LENGTHOF(testCases); ++i) { + const TestCase &testCase = testCases[i]; + UnicodeString name = UnicodeString(testCase.name).unescape(); + UnicodeString label = UnicodeString(testCase.bucketLabel).unescape(); + char msg[100]; + sprintf(msg, "getBucketIndex(%s)", testCase.name); + assertEquals(msg, testCase.bucketIndex, index.getBucketIndex(name, status)); + sprintf(msg, "immutable getBucketIndex(%s)", testCase.name); + assertEquals(msg, testCase.bucketIndex, immIndex->getBucketIndex(name, status)); + sprintf(msg, "immutable bucket label (%s)", testCase.name); + assertEquals(msg, label, immIndex->getBucket(testCase.bucketIndex)->getLabel()); + } +} + +void AlphabeticIndexTest::TestNoLabels() { + UErrorCode status = U_ZERO_ERROR; + LocalPointer coll( + static_cast(Collator::createInstance(Locale::getRoot(), status))); + TEST_CHECK_STATUS; + AlphabeticIndex index(coll.orphan(), status); + TEST_CHECK_STATUS; + index.addRecord(UnicodeString((UChar)0x897f), NULL, status); + index.addRecord("i", NULL, status); + index.addRecord(UnicodeString((UChar)0x03B1), NULL, status); + assertEquals("getBucketCount()", 1, index.getBucketCount(status)); // ... + TEST_ASSERT(index.nextBucket(status)); + assertEquals("underflow label type", U_ALPHAINDEX_UNDERFLOW, index.getBucketLabelType()); + assertEquals("all records in the underflow bucket", 3, index.getBucketRecordCount()); +} + +void AlphabeticIndexTest::TestChineseZhuyin() { + UErrorCode status = U_ZERO_ERROR; + char loc[100]; + uloc_forLanguageTag("zh-u-co-zhuyin", loc, LENGTHOF(loc), NULL, &status); + AlphabeticIndex index(loc, status); + LocalPointer immIndex(index.buildImmutableIndex(status)); + TEST_CHECK_STATUS; + assertEquals("getBucketCount()", 38, immIndex->getBucketCount()); + assertEquals("label 1", UnicodeString((UChar)0x3105), immIndex->getBucket(1)->getLabel()); + assertEquals("label 2", UnicodeString((UChar)0x3106), immIndex->getBucket(2)->getLabel()); + assertEquals("label 3", UnicodeString((UChar)0x3107), immIndex->getBucket(3)->getLabel()); + assertEquals("label 4", UnicodeString((UChar)0x3108), immIndex->getBucket(4)->getLabel()); + assertEquals("label 5", UnicodeString((UChar)0x3109), immIndex->getBucket(5)->getLabel()); +} #endif