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
  77     { _T("Hello, world"),       _T(" "),              wxTOKEN_DEFAULT      , 2 },
  78     { _T("Hello,   world  "),   _T(" "),              wxTOKEN_DEFAULT      , 2 },
  79     { _T("Hello, world"),       _T(","),              wxTOKEN_DEFAULT      , 2 },
  80     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_DEFAULT      , 2 },
  81     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_DEFAULT      , 3 },
  82     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_STRTOK       , 2 },
  83     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_RET_EMPTY_ALL, 3 },
  84
  85     { _T("username:password:uid:gid:gecos:home:shell"),
  86                                 _T(":"),              wxTOKEN_DEFAULT      , 7 },
  87
  88     { _T("1:2::3:"),            _T(":"),              wxTOKEN_DEFAULT      , 4 },
  89     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY    , 4 },
  90     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY_ALL, 5 },
  91     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_DELIMS   , 4 },
  92     { _T("1:2::3:"),            _T(":"),              wxTOKEN_STRTOK       , 3 },
  93
  94     { _T("1:2::3::"),           _T(":"),              wxTOKEN_DEFAULT      , 5 },
  95     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY    , 5 },
  96     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY_ALL, 6 },
  97     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_DELIMS   , 5 },
  98     { _T("1:2::3::"),           _T(":"),              wxTOKEN_STRTOK       , 3 },
  99
 100     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_DEFAULT      , 4 },
 101     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_STRTOK       , 4 },
 102     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY    , 6 },
 103     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY_ALL, 9 },
 104
 105     { _T("01/02/99"),           _T("/-"),             wxTOKEN_DEFAULT      , 3 },
 106     { _T("01-02/99"),           _T("/-"),             wxTOKEN_RET_DELIMS   , 3 },
 107 };
 108
 109 // ----------------------------------------------------------------------------
 110 // the tests
 111 // ----------------------------------------------------------------------------
 112
 113 void TokenizerTestCase::GetCount()
 114 {
 115     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 116     {
 117         const TokenizerTestData& ttd = gs_testData[n];
 118
 119         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 120         CPPUNIT_ASSERT( tkz.CountTokens() == ttd.count );
 121
 122         size_t count = 0;
 123         while ( tkz.HasMoreTokens() )
 124         {
 125             tkz.GetNextToken();
 126             count++;
 127         }
 128
 129         CPPUNIT_ASSERT_EQUAL( ttd.count, count );
 130     }
 131 }
 132
 133 // call this with the string to tokenize, delimeters to use and the expected
 134 // positions (i.e. results of GetPosition()) after each GetNextToken() call,
 135 // terminate positions with 0
 136 static void
 137 DoTestGetPosition(const wxChar *s, const wxChar *delims, int pos, ...)
 138 {
 139     wxStringTokenizer tkz(s, delims);
 140
 141     CPPUNIT_ASSERT_EQUAL( (size_t)0, tkz.GetPosition() );
 142
 143     va_list ap;
 144     va_start(ap, pos);
 145
 146     for ( ;; )
 147     {
 148         if ( !pos )
 149         {
 150             CPPUNIT_ASSERT( !tkz.HasMoreTokens() );
 151             break;
 152         }
 153
 154         tkz.GetNextToken();
 155
 156         CPPUNIT_ASSERT_EQUAL( (size_t)pos, tkz.GetPosition() );
 157
 158         pos = va_arg(ap, int);
 159     }
 160
 161     va_end(ap);
 162 }
 163
 164 void TokenizerTestCase::GetPosition()
 165 {
 166     DoTestGetPosition(_T("foo"), _T("_"), 3, 0);
 167     DoTestGetPosition(_T("foo_bar"), _T("_"), 4, 7, 0);
 168     DoTestGetPosition(_T("foo_bar_"), _T("_"), 4, 8, 0);
 169 }
 170
 171 void TokenizerTestCase::StrtokCompat()
 172 {
 173     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 174     {
 175         const TokenizerTestData& ttd = gs_testData[n];
 176         if ( ttd.mode != wxTOKEN_STRTOK )
 177             continue;
 178
 179 #if wxUSE_UNICODE
 180         wxWCharBuffer
 181 #else
 182         wxCharBuffer
 183 #endif
 184             buf(ttd.str);
 185         wxChar *last;
 186         wxChar *s = wxStrtok(buf.data(), ttd.delims, &last);
 187
 188         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 189         while ( tkz.HasMoreTokens() )
 190         {
 191             CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetNextToken() );
 192             s = wxStrtok(NULL, ttd.delims, &last);
 193         }
 194     }
 195 }
 196
 197