1 // © 2016 and later: Unicode, Inc. and others. 2 // License & terms of use: http://www.unicode.org/copyright.html 3 /************************************************************************* 4 * Copyright (c) 1999-2016, International Business Machines 5 * Corporation and others. All Rights Reserved. 6 ************************************************************************* 7 * Date Name Description 8 * 12/15/99 Madhu Creation. 9 * 01/12/2000 Madhu Updated for changed API and added new tests 10 ************************************************************************/ 11 12 13 #ifndef RBBITEST_H 14 #define RBBITEST_H 15 16 #include "unicode/utypes.h" 17 18 #if !UCONFIG_NO_BREAK_ITERATION 19 20 #include <memory> 21 22 #include "intltest.h" 23 #include "unicode/brkiter.h" 24 #include "unicode/rbbi.h" 25 #include "unicode/uscript.h" 26 27 class Enumeration; 28 class BITestData; 29 struct TestParams; 30 class RBBIMonkeyKind; 31 32 U_NAMESPACE_BEGIN 33 class UVector32; 34 U_NAMESPACE_END 35 36 /** 37 * Test the RuleBasedBreakIterator class giving different rules 38 */ 39 class RBBITest: public IntlTest { 40 public: 41 42 RBBITest(); 43 virtual ~RBBITest(); 44 45 void runIndexedTest( int32_t index, UBool exec, const char* &name, char* par = NULL ) override; 46 47 void TestGetAvailableLocales(); 48 void TestGetDisplayName(); 49 void TestEndBehaviour(); 50 void TestBug4153072(); 51 void TestJapaneseLineBreak(); 52 void TestThaiLineBreak(); 53 void TestMixedThaiLineBreak(); 54 void TestMaiyamok(); 55 void TestMonkey(); 56 57 void TestExtended(); 58 void executeTest(TestParams *, UErrorCode &status); 59 60 void TestWordBreaks(); 61 void TestWordBoundary(); 62 void TestLineBreaks(); 63 void TestSentBreaks(); 64 void TestBug3818(); 65 void TestJapaneseWordBreak(); 66 void TestTrieDict(); 67 void TestUnicodeFiles(); 68 void TestBug5775(); 69 void TestTailoredBreaks(); 70 void TestDictRules(); 71 void TestBug5532(); 72 void TestBug9983(); 73 void TestBug7547(); 74 void TestBug12797(); 75 void TestBug12918(); 76 void TestBug12932(); 77 void TestEmoji(); 78 void TestBug12519(); 79 void TestBug12677(); 80 void TestTableRedundancies(); 81 void TestBug13447(); 82 void TestReverse(); 83 void TestReverse(std::unique_ptr<RuleBasedBreakIterator>bi); 84 void TestBug13692(); 85 void TestDebugRules(); 86 void TestUnpairedSurrogate(); 87 88 void TestDebug(); 89 void TestProperties(); 90 void Test8BitsTrieWith8BitStateTable(); 91 void Test8BitsTrieWith16BitStateTable(); 92 void Test16BitsTrieWith8BitStateTable(); 93 void Test16BitsTrieWith16BitStateTable(); 94 void TestTable_8_16_Bits(); 95 void TestBug13590(); 96 void TestLSTMThai(); 97 void TestLSTMBurmese(); 98 99 #if U_ENABLE_TRACING 100 void TestTraceCreateCharacter(); 101 void TestTraceCreateWord(); 102 void TestTraceCreateSentence(); 103 void TestTraceCreateTitle(); 104 void TestTraceCreateLine(); 105 void TestTraceCreateLineNormal(); 106 void TestTraceCreateLineStrict(); 107 void TestTraceCreateLineLoose(); 108 void TestTraceCreateLineNormalPhrase(); 109 void TestTraceCreateLineLoosePhrase(); 110 void TestTraceCreateLineStrictPhrase(); 111 void TestTraceCreateLinePhrase(); 112 void TestTraceCreateBreakEngine(); 113 #endif 114 115 /***********************/ 116 private: 117 /** 118 * internal methods to prepare test data 119 **/ 120 121 void RunMonkey(BreakIterator *bi, RBBIMonkeyKind &mk, const char *name, uint32_t seed, 122 int32_t loopCount, UBool useUText); 123 124 // Run one of the Unicode Consortium boundary test data files. 125 void runUnicodeTestData(const char *fileName, RuleBasedBreakIterator *bi); 126 127 // Run tests from one of the LSTM test files. 128 void runLSTMTestFromFile(const char* filename, UScriptCode script); 129 130 // Run a single test case from one of the Unicode Consortium test files. 131 void checkUnicodeTestCase(const char *testFileName, int lineNumber, 132 const UnicodeString &testString, 133 UVector32 *breakPositions, 134 RuleBasedBreakIterator *bi); 135 136 // Run the actual tests for TestTailoredBreaks() 137 void TBTest(BreakIterator* brkitr, int type, const char *locale, const char* escapedText, 138 const int32_t *expectOffsets, int32_t expectOffsetsCount); 139 140 /** Filter for test cases from the Unicode test data files. 141 * Some need to be skipped because ICU is unable to fully implement the 142 * Unicode boundary specifications. 143 * @param testCase the test data string. 144 * @param fileName the Unicode test data file name. 145 * @return FALSE if the test case should be run, TRUE if it should be skipped. 146 */ 147 UBool testCaseIsKnownIssue(const UnicodeString &testCase, const char *fileName); 148 149 // Test parameters, from the test framework and test invocation. 150 const char* fTestParams; 151 152 // Helper functions to test different trie bit sizes and state table bit sizes. 153 void testTrieStateTable(int32_t numChar, bool expectedTrieWidthIn8Bits, bool expectedStateRowIn8Bits); 154 155 #if U_ENABLE_TRACING 156 void assertTestTraceResult(int32_t fnNumber, const char* expectedData); 157 #endif 158 159 }; 160 161 #endif /* #if !UCONFIG_NO_BREAK_ITERATION */ 162 163 #endif 164