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( StrtokCompat );
  40     CPPUNIT_TEST_SUITE_END();
  41
  42     void GetCount();
  43     void GetPosition();
  44     void StrtokCompat();
  45
  46     DECLARE_NO_COPY_CLASS(TokenizerTestCase)
  47 };
  48
  49 // register in the unnamed registry so that these tests are run by default
  50 CPPUNIT_TEST_SUITE_REGISTRATION( TokenizerTestCase );
  51
  52 // also include in it's own registry so that these tests can be run alone
  53 CPPUNIT_TEST_SUITE_NAMED_REGISTRATION( TokenizerTestCase, "TokenizerTestCase" );
  54
  55 // ----------------------------------------------------------------------------
  56 // test data
  57 // ----------------------------------------------------------------------------
  58
  59 static const struct TokenizerTestData
  60 {
  61     // the string to tokenize
  62     const wxChar *str;
  63
  64     // the delimiters to use
  65     const wxChar *delims;
  66
  67     // the tokenizer mode
  68     wxStringTokenizerMode mode;
  69
  70     // expected number of tokens
  71     size_t count;
  72 }
  73 gs_testData[] =
  74 {
  75     { _T(""),                   _T(" "),              wxTOKEN_DEFAULT,       0 },
  76     { _T(""),                   _T(" "),              wxTOKEN_RET_EMPTY,     0 },
  77     { _T(""),                   _T(" "),              wxTOKEN_RET_EMPTY_ALL, 0 },
  78
  79     { _T("Hello, world"),       _T(" "),              wxTOKEN_DEFAULT,       2 },
  80     { _T("Hello,   world  "),   _T(" "),              wxTOKEN_DEFAULT,       2 },
  81     { _T("Hello, world"),       _T(","),              wxTOKEN_DEFAULT,       2 },
  82     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_DEFAULT,       2 },
  83     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_DEFAULT,       3 },
  84     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_STRTOK,        2 },
  85     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_RET_EMPTY_ALL, 3 },
  86
  87     { _T("username:password:uid:gid:gecos:home:shell"),
  88                                 _T(":"),              wxTOKEN_DEFAULT,       7 },
  89
  90     { _T("1:2::3:"),            _T(":"),              wxTOKEN_DEFAULT,       4 },
  91     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY,     4 },
  92     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY_ALL, 5 },
  93     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_DELIMS,    4 },
  94     { _T("1:2::3:"),            _T(":"),              wxTOKEN_STRTOK,        3 },
  95
  96     { _T("1:2::3::"),           _T(":"),              wxTOKEN_DEFAULT,       5 },
  97     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY,     4 },
  98     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY_ALL, 6 },
  99     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_DELIMS,    5 },
 100     { _T("1:2::3::"),           _T(":"),              wxTOKEN_STRTOK,        3 },
 101
 102     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_DEFAULT,       4 },
 103     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_STRTOK,        4 },
 104     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY,     6 },
 105     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY_ALL, 9 },
 106
 107     { _T("01/02/99"),           _T("/-"),             wxTOKEN_DEFAULT,       3 },
 108     { _T("01-02/99"),           _T("/-"),             wxTOKEN_RET_DELIMS,    3 },
 109 };
 110
 111 // ----------------------------------------------------------------------------
 112 // the tests
 113 // ----------------------------------------------------------------------------
 114
 115 void TokenizerTestCase::GetCount()
 116 {
 117     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 118     {
 119         const TokenizerTestData& ttd = gs_testData[n];
 120
 121         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 122         CPPUNIT_ASSERT_EQUAL( ttd.count, tkz.CountTokens() );
 123
 124         size_t count = 0;
 125         while ( tkz.HasMoreTokens() )
 126         {
 127             tkz.GetNextToken();
 128             count++;
 129         }
 130
 131         CPPUNIT_ASSERT_EQUAL( ttd.count, count );
 132     }
 133 }
 134
 135 // call this with the string to tokenize, delimeters to use and the expected
 136 // positions (i.e. results of GetPosition()) after each GetNextToken() call,
 137 // terminate positions with 0
 138 static void
 139 DoTestGetPosition(const wxChar *s, const wxChar *delims, int pos, ...)
 140 {
 141     wxStringTokenizer tkz(s, delims);
 142
 143     CPPUNIT_ASSERT_EQUAL( (size_t)0, tkz.GetPosition() );
 144
 145     va_list ap;
 146     va_start(ap, pos);
 147
 148     for ( ;; )
 149     {
 150         if ( !pos )
 151         {
 152             CPPUNIT_ASSERT( !tkz.HasMoreTokens() );
 153             break;
 154         }
 155
 156         tkz.GetNextToken();
 157
 158         CPPUNIT_ASSERT_EQUAL( (size_t)pos, tkz.GetPosition() );
 159
 160         pos = va_arg(ap, int);
 161     }
 162
 163     va_end(ap);
 164 }
 165
 166 void TokenizerTestCase::GetPosition()
 167 {
 168     DoTestGetPosition(_T("foo"), _T("_"), 3, 0);
 169     DoTestGetPosition(_T("foo_bar"), _T("_"), 4, 7, 0);
 170     DoTestGetPosition(_T("foo_bar_"), _T("_"), 4, 8, 0);
 171 }
 172
 173 void TokenizerTestCase::StrtokCompat()
 174 {
 175     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 176     {
 177         const TokenizerTestData& ttd = gs_testData[n];
 178         if ( ttd.mode != wxTOKEN_STRTOK )
 179             continue;
 180
 181 #if wxUSE_UNICODE
 182         wxWCharBuffer
 183 #else
 184         wxCharBuffer
 185 #endif
 186             buf(ttd.str);
 187         wxChar *last;
 188         wxChar *s = wxStrtok(buf.data(), ttd.delims, &last);
 189
 190         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 191         while ( tkz.HasMoreTokens() )
 192         {
 193             CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetNextToken() );
 194             s = wxStrtok(NULL, ttd.delims, &last);
 195         }
 196     }
 197 }
 198
 199