-
-void RBBITest::TestJapaneseWordBreak() {
- UErrorCode status = U_ZERO_ERROR;
- BITestData japaneseWordSelection(status);
-
- ADD_DATACHUNK(japaneseWordSelection, NULL, 0, status); // Break at start of data
- ADD_DATACHUNK(japaneseWordSelection, "\\u4ECA\\u65E5", 400, status); //2
- ADD_DATACHUNK(japaneseWordSelection, "\\u306F\\u3044\\u3044", 300, status); //5
- ADD_DATACHUNK(japaneseWordSelection, "\\u5929\\u6C17", 400, status); //7
- ADD_DATACHUNK(japaneseWordSelection, "\\u3067\\u3059\\u306D", 300, status); //10
- ADD_DATACHUNK(japaneseWordSelection, "\\u3002", 0, status); //11
- ADD_DATACHUNK(japaneseWordSelection, "\\u000D\\u000A", 0, status); //12
-
- RuleBasedBreakIterator* e = (RuleBasedBreakIterator *)BreakIterator::createWordInstance(
- Locale("ja"), status);
- if (U_FAILURE(status))
- {
- errln("Failed to create the BreakIterator for Japanese locale in TestJapaneseWordBreak.\n");
- return;
- }
-
- generalIteratorTest(*e, japaneseWordSelection);
- delete e;
-}
-
-void RBBITest::TestTrieDict() {
- UErrorCode status = U_ZERO_ERROR;
-
- //
- // Open and read the test data file.
- //
- const char *testDataDirectory = IntlTest::getSourceTestData(status);
- char testFileName[1000];
- if (testDataDirectory == NULL || strlen(testDataDirectory) + strlen("riwords.txt") + 10 >= sizeof(testFileName)) {
- errln("Can't open test data. Path too long.");
- return;
- }
- strcpy(testFileName, testDataDirectory);
- strcat(testFileName, "riwords.txt");
-
- // Items needing deleting at the end
- MutableTrieDictionary *mutableDict = NULL;
- CompactTrieDictionary *compactDict = NULL;
- UnicodeSet *breaks = NULL;
- UChar *testFile = NULL;
- StringEnumeration *enumer = NULL;
- MutableTrieDictionary *mutable2 = NULL;
- StringEnumeration *cloneEnum = NULL;
- CompactTrieDictionary *compact2 = NULL;
-
-
- const UnicodeString *originalWord = NULL;
- const UnicodeString *cloneWord = NULL;
- UChar *current;
- UChar *word;
- UChar uc;
- int32_t wordLen;
- int32_t wordCount;
- int32_t testCount;
-
- int len;
- testFile = ReadAndConvertFile(testFileName, len, status);
- if (U_FAILURE(status)) {
- goto cleanup; /* something went wrong, error already output */
- }
-
- mutableDict = new MutableTrieDictionary(0x0E1C, status);
- if (U_FAILURE(status)) {
- errln("Error creating MutableTrieDictionary: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- breaks = new UnicodeSet;
- breaks->add(0x000A); // Line Feed
- breaks->add(0x000D); // Carriage Return
- breaks->add(0x2028); // Line Separator
- breaks->add(0x2029); // Paragraph Separator
-
- // Now add each non-comment line of the file as a word.
- current = testFile;
- word = current;
- uc = *current++;
- wordLen = 0;
- wordCount = 0;
-
- while (uc) {
- if (uc == 0x0023) { // #comment line, skip
- while (uc && !breaks->contains(uc)) {
- uc = *current++;
- }
- }
- else while (uc && !breaks->contains(uc)) {
- ++wordLen;
- uc = *current++;
- }
- if (wordLen > 0) {
- mutableDict->addWord(word, wordLen, status);
- if (U_FAILURE(status)) {
- errln("Could not add word to mutable dictionary; status %s\n", u_errorName(status));
- goto cleanup;
- }
- wordCount += 1;
- }
-
- // Find beginning of next line
- while (uc && breaks->contains(uc)) {
- uc = *current++;
- }
- word = current-1;
- wordLen = 0;
- }
-
- if (wordCount < 50) {
- errln("Word count (%d) unreasonably small\n", wordCount);
- goto cleanup;
- }
-
- enumer = mutableDict->openWords(status);
- if (U_FAILURE(status)) {
- errln("Could not open mutable dictionary enumerator: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- testCount = 0;
- if (wordCount != (testCount = enumer->count(status))) {
- errln("MutableTrieDictionary word count (%d) differs from file word count (%d), with status %s\n",
- testCount, wordCount, u_errorName(status));
- goto cleanup;
- }
-
- delete enumer;
- enumer = NULL;
-
- // Now compact it
- compactDict = new CompactTrieDictionary(*mutableDict, status);
- if (U_FAILURE(status)) {
- errln("Failed to create CompactTrieDictionary: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- enumer = compactDict->openWords(status);
- if (U_FAILURE(status)) {
- errln("Could not open compact trie dictionary enumerator: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- if (wordCount != (testCount = enumer->count(status))) {
- errln("CompactTrieDictionary word count (%d) differs from file word count (%d), with status %s\n",
- testCount, wordCount, u_errorName(status));
- goto cleanup;
- }
-
- delete enumer;
- enumer = NULL;
-
- // Now un-compact it
- mutable2 = compactDict->cloneMutable(status);
- if (U_FAILURE(status)) {
- errln("Could not clone CompactTrieDictionary to MutableTrieDictionary: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- cloneEnum = mutable2->openWords(status);
- if (U_FAILURE(status)) {
- errln("Could not create cloned mutable enumerator: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- if (wordCount != (testCount = cloneEnum->count(status))) {
- errln("Cloned MutableTrieDictionary word count (%d) differs from file word count (%d), with status %s\n",
- testCount, wordCount, u_errorName(status));
- goto cleanup;
- }
-
- // Compact original dictionary to clone. Note that we can only compare the same kind of
- // dictionary as the order of the enumerators is not guaranteed to be the same between
- // different kinds
- enumer = mutableDict->openWords(status);
- if (U_FAILURE(status)) {
- errln("Could not re-open mutable dictionary enumerator: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- originalWord = enumer->snext(status);
- cloneWord = cloneEnum->snext(status);
- while (U_SUCCESS(status) && originalWord != NULL && cloneWord != NULL) {
- if (*originalWord != *cloneWord) {
- errln("Original and cloned MutableTrieDictionary word mismatch\n");
- goto cleanup;
- }
- originalWord = enumer->snext(status);
- cloneWord = cloneEnum->snext(status);
- }
-
- if (U_FAILURE(status)) {
- errln("Enumeration failed: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- if (originalWord != cloneWord) {
- errln("Original and cloned MutableTrieDictionary ended enumeration at different points\n");
- goto cleanup;
- }
-
- // Test the data copying constructor for CompactTrieDict, and the data access APIs.
- compact2 = new CompactTrieDictionary(compactDict->data(), status);
- if (U_FAILURE(status)) {
- errln("CompactTrieDictionary(const void *,...) failed\n");
- goto cleanup;
- }
-
- if (compact2->dataSize() == 0) {
- errln("CompactTrieDictionary->dataSize() == 0\n");
- goto cleanup;
- }
-
- // Now count the words via the second dictionary
- delete enumer;
- enumer = compact2->openWords(status);
- if (U_FAILURE(status)) {
- errln("Could not open compact trie dictionary 2 enumerator: %s\n", u_errorName(status));
- goto cleanup;
- }
-
- if (wordCount != (testCount = enumer->count(status))) {
- errln("CompactTrieDictionary 2 word count (%d) differs from file word count (%d), with status %s\n",
- testCount, wordCount, u_errorName(status));
- goto cleanup;
- }
-
-cleanup:
- delete compactDict;
- delete mutableDict;
- delete breaks;
- delete[] testFile;
- delete enumer;
- delete mutable2;
- delete cloneEnum;
- delete compact2;
-}
-
-//---------------------------------------------
-// runIndexedTest
-//---------------------------------------------
-
-void RBBITest::runIndexedTest( int32_t index, UBool exec, const char* &name, char* params )
-{
- if (exec) logln("TestSuite RuleBasedBreakIterator: ");
-
- switch (index) {
- case 0: name = "TestBug4153072";
- if(exec) TestBug4153072(); break;
- case 1: name = "TestJapaneseLineBreak";
- if(exec) TestJapaneseLineBreak(); break;
- case 2: name = "TestStatusReturn";
- if(exec) TestStatusReturn(); break;
-
- case 3: name = "TestLineBreakData";
- if(exec) TestLineBreakData(); break;
- case 4: name = "TestEmptyString";
- if(exec) TestEmptyString(); break;
-
- case 5: name = "TestGetAvailableLocales";
- if(exec) TestGetAvailableLocales(); break;
-
- case 6: name = "TestGetDisplayName";
- if(exec) TestGetDisplayName(); break;
-
- case 7: name = "TestEndBehaviour";
- if(exec) TestEndBehaviour(); break;
- case 8: name = "TestMixedThaiLineBreak";
- if(exec) TestMixedThaiLineBreak(); break;
- case 9: name = "TestThaiLineBreak";
- if(exec) TestThaiLineBreak(); break;
- case 10: name = "TestMaiyamok";
- if(exec) TestMaiyamok(); break;
- case 11: name = "TestWordBreaks";
- if(exec) TestWordBreaks(); break;
- case 12: name = "TestWordBoundary";
- if(exec) TestWordBoundary(); break;
- case 13: name = "TestLineBreaks";
- if(exec) TestLineBreaks(); break;
- case 14: name = "TestSentBreaks";
- if(exec) TestSentBreaks(); break;
- case 15: name = "TestExtended";
- if(exec) TestExtended(); break;
- case 16: name = "TestMonkey";
- if(exec) {
- #if !UCONFIG_NO_REGULAR_EXPRESSIONS
- TestMonkey(params);
- #else
- logln("skipping TestMonkey (UCONFIG_NO_REGULAR_EXPRESSIONS)");
- #endif
- }
- break;
- case 17: name = "TestBug3818";
- if(exec) TestBug3818(); break;
- case 18: name = "TestJapaneseWordBreak";
- if(exec) TestJapaneseWordBreak(); break;
- case 19: name = "TestDebug";
- if(exec) TestDebug(); break;
- case 20: name = "TestTrieDict";
- if(exec) TestTrieDict(); break;
-
- default: name = ""; break; //needed to end loop
- }
-}
-
-
projects / apple / icu.git / blobdiff