tests/strings/tokenizer.cpp

   1 ///////////////////////////////////////////////////////////////////////////////
   2 // Name:        tests/strings/strings.cpp
   3 // Purpose:     wxStringTokenizer unit test
   4 // Author:      Vadim Zeitlin
   5 // Created:     2005-12-20 (extacted from strings.cpp)
   6 // RCS-ID:      $Id$
   7 // Copyright:   (c) 2004-2005 Vadim Zeitlin
   8 ///////////////////////////////////////////////////////////////////////////////
   9
  10 // ----------------------------------------------------------------------------
  11 // headers
  12 // ----------------------------------------------------------------------------
  13
  14 #include "testprec.h"
  15
  16 #ifdef __BORLANDC__
  17     #pragma hdrstop
  18 #endif
  19
  20 #ifndef WX_PRECOMP
  21     #include "wx/wx.h"
  22 #endif // WX_PRECOMP
  23
  24 #include "wx/tokenzr.h"
  25
  26 // ----------------------------------------------------------------------------
  27 // test class
  28 // ----------------------------------------------------------------------------
  29
  30 class TokenizerTestCase : public CppUnit::TestCase
  31 {
  32 public:
  33     TokenizerTestCase() { }
  34
  35 private:
  36     CPPUNIT_TEST_SUITE( TokenizerTestCase );
  37         CPPUNIT_TEST( GetCount );
  38         CPPUNIT_TEST( GetPosition );
  39         CPPUNIT_TEST( LastDelimiter );
  40         CPPUNIT_TEST( StrtokCompat );
  41     CPPUNIT_TEST_SUITE_END();
  42
  43     void GetCount();
  44     void GetPosition();
  45     void LastDelimiter();
  46     void StrtokCompat();
  47
  48     DECLARE_NO_COPY_CLASS(TokenizerTestCase)
  49 };
  50
  51 // register in the unnamed registry so that these tests are run by default
  52 CPPUNIT_TEST_SUITE_REGISTRATION( TokenizerTestCase );
  53
  54 // also include in it's own registry so that these tests can be run alone
  55 CPPUNIT_TEST_SUITE_NAMED_REGISTRATION( TokenizerTestCase, "TokenizerTestCase" );
  56
  57 // ----------------------------------------------------------------------------
  58 // test data
  59 // ----------------------------------------------------------------------------
  60
  61 static const struct TokenizerTestData
  62 {
  63     // the string to tokenize
  64     const wxChar *str;
  65
  66     // the delimiters to use
  67     const wxChar *delims;
  68
  69     // the tokenizer mode
  70     wxStringTokenizerMode mode;
  71
  72     // expected number of tokens
  73     size_t count;
  74 }
  75 gs_testData[] =
  76 {
  77     { _T(""),                   _T(" "),              wxTOKEN_DEFAULT,       0 },
  78     { _T(""),                   _T(" "),              wxTOKEN_RET_EMPTY,     0 },
  79     { _T(""),                   _T(" "),              wxTOKEN_RET_EMPTY_ALL, 0 },
  80     { _T(""),                   _T(" "),              wxTOKEN_RET_DELIMS,    0 },
  81     { _T(":"),                  _T(":"),              wxTOKEN_RET_EMPTY,     1 },
  82     { _T(":"),                  _T(":"),              wxTOKEN_RET_DELIMS,    1 },
  83     { _T(":"),                  _T(":"),              wxTOKEN_RET_EMPTY_ALL, 2 },
  84     { _T("::"),                 _T(":"),              wxTOKEN_RET_EMPTY,     1 },
  85     { _T("::"),                 _T(":"),              wxTOKEN_RET_DELIMS,    1 },
  86     { _T("::"),                 _T(":"),              wxTOKEN_RET_EMPTY_ALL, 3 },
  87
  88     { _T("Hello, world"),       _T(" "),              wxTOKEN_DEFAULT,       2 },
  89     { _T("Hello,   world  "),   _T(" "),              wxTOKEN_DEFAULT,       2 },
  90     { _T("Hello, world"),       _T(","),              wxTOKEN_DEFAULT,       2 },
  91     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_DEFAULT,       2 },
  92     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_DEFAULT,       3 },
  93     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_STRTOK,        2 },
  94     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_RET_EMPTY_ALL, 3 },
  95
  96     { _T("username:password:uid:gid:gecos:home:shell"),
  97                                 _T(":"),              wxTOKEN_DEFAULT,       7 },
  98
  99     { _T("1:2::3:"),            _T(":"),              wxTOKEN_DEFAULT,       4 },
 100     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY,     4 },
 101     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY_ALL, 5 },
 102     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_DELIMS,    4 },
 103     { _T("1:2::3:"),            _T(":"),              wxTOKEN_STRTOK,        3 },
 104
 105     { _T("1:2::3::"),           _T(":"),              wxTOKEN_DEFAULT,       4 },
 106     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY,     4 },
 107     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY_ALL, 6 },
 108     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_DELIMS,    4 },
 109     { _T("1:2::3::"),           _T(":"),              wxTOKEN_STRTOK,        3 },
 110
 111     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_DEFAULT,       4 },
 112     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_STRTOK,        4 },
 113     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY,     6 },
 114     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY_ALL, 9 },
 115
 116     { _T("01/02/99"),           _T("/-"),             wxTOKEN_DEFAULT,       3 },
 117     { _T("01-02/99"),           _T("/-"),             wxTOKEN_RET_DELIMS,    3 },
 118 };
 119
 120 // helper function returning the string showing the index for which the test
 121 // fails in the diagnostic message
 122 static std::string Nth(size_t n)
 123 {
 124     return wxString::Format(_T("for loop index %lu"), (unsigned long)n).mb_str();
 125 }
 126
 127 // ----------------------------------------------------------------------------
 128 // the tests
 129 // ----------------------------------------------------------------------------
 130
 131 void TokenizerTestCase::GetCount()
 132 {
 133     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 134     {
 135         const TokenizerTestData& ttd = gs_testData[n];
 136
 137         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 138         CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, tkz.CountTokens() );
 139
 140         size_t count = 0;
 141         while ( tkz.HasMoreTokens() )
 142         {
 143             tkz.GetNextToken();
 144             count++;
 145         }
 146
 147         CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, count );
 148     }
 149 }
 150
 151 // call this with the string to tokenize, delimeters to use and the expected
 152 // positions (i.e. results of GetPosition()) after each GetNextToken() call,
 153 // terminate positions with 0
 154 static void
 155 DoTestGetPosition(const wxChar *s, const wxChar *delims, int pos, ...)
 156 {
 157     wxStringTokenizer tkz(s, delims);
 158
 159     CPPUNIT_ASSERT_EQUAL( (size_t)0, tkz.GetPosition() );
 160
 161     va_list ap;
 162     va_start(ap, pos);
 163
 164     for ( ;; )
 165     {
 166         if ( !pos )
 167         {
 168             CPPUNIT_ASSERT( !tkz.HasMoreTokens() );
 169             break;
 170         }
 171
 172         tkz.GetNextToken();
 173
 174         CPPUNIT_ASSERT_EQUAL( (size_t)pos, tkz.GetPosition() );
 175
 176         pos = va_arg(ap, int);
 177     }
 178
 179     va_end(ap);
 180 }
 181
 182 void TokenizerTestCase::GetPosition()
 183 {
 184     DoTestGetPosition(_T("foo"), _T("_"), 3, 0);
 185     DoTestGetPosition(_T("foo_bar"), _T("_"), 4, 7, 0);
 186     DoTestGetPosition(_T("foo_bar_"), _T("_"), 4, 8, 0);
 187 }
 188
 189 void TokenizerTestCase::LastDelimiter()
 190 {
 191     wxStringTokenizer tkz(_T("a+-b=c"), _T("+-="));
 192
 193     tkz.GetNextToken();
 194     CPPUNIT_ASSERT_EQUAL( _T('+'), tkz.GetLastDelimiter() );
 195
 196     tkz.GetNextToken();
 197     CPPUNIT_ASSERT_EQUAL( _T('-'), tkz.GetLastDelimiter() );
 198
 199     tkz.GetNextToken();
 200     CPPUNIT_ASSERT_EQUAL( _T('='), tkz.GetLastDelimiter() );
 201
 202     tkz.GetNextToken();
 203     CPPUNIT_ASSERT_EQUAL( _T('\0'), tkz.GetLastDelimiter() );
 204 }
 205
 206 void TokenizerTestCase::StrtokCompat()
 207 {
 208     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 209     {
 210         const TokenizerTestData& ttd = gs_testData[n];
 211         if ( ttd.mode != wxTOKEN_STRTOK )
 212             continue;
 213
 214 #if wxUSE_UNICODE
 215         wxWCharBuffer
 216 #else
 217         wxCharBuffer
 218 #endif
 219             buf(ttd.str);
 220         wxChar *last;
 221         wxChar *s = wxStrtok(buf.data(), ttd.delims, &last);
 222
 223         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 224         while ( tkz.HasMoreTokens() )
 225         {
 226             CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetNextToken() );
 227             s = wxStrtok(NULL, ttd.delims, &last);
 228         }
 229     }
 230 }
 231
 232