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( GetString );
  40         CPPUNIT_TEST( LastDelimiter );
  41         CPPUNIT_TEST( StrtokCompat );
  42     CPPUNIT_TEST_SUITE_END();
  43
  44     void GetCount();
  45     void GetPosition();
  46     void GetString();
  47     void LastDelimiter();
  48     void StrtokCompat();
  49
  50     DECLARE_NO_COPY_CLASS(TokenizerTestCase)
  51 };
  52
  53 // register in the unnamed registry so that these tests are run by default
  54 CPPUNIT_TEST_SUITE_REGISTRATION( TokenizerTestCase );
  55
  56 // also include in it's own registry so that these tests can be run alone
  57 CPPUNIT_TEST_SUITE_NAMED_REGISTRATION( TokenizerTestCase, "TokenizerTestCase" );
  58
  59 // ----------------------------------------------------------------------------
  60 // test data
  61 // ----------------------------------------------------------------------------
  62
  63 static const struct TokenizerTestData
  64 {
  65     // the string to tokenize
  66     const wxChar *str;
  67
  68     // the delimiters to use
  69     const wxChar *delims;
  70
  71     // the tokenizer mode
  72     wxStringTokenizerMode mode;
  73
  74     // expected number of tokens
  75     size_t count;
  76 }
  77 gs_testData[] =
  78 {
  79     { _T(""),                   _T(" "),              wxTOKEN_DEFAULT,       0 },
  80     { _T(""),                   _T(" "),              wxTOKEN_RET_EMPTY,     0 },
  81     { _T(""),                   _T(" "),              wxTOKEN_RET_EMPTY_ALL, 0 },
  82     { _T(""),                   _T(" "),              wxTOKEN_RET_DELIMS,    0 },
  83     { _T(":"),                  _T(":"),              wxTOKEN_RET_EMPTY,     1 },
  84     { _T(":"),                  _T(":"),              wxTOKEN_RET_DELIMS,    1 },
  85     { _T(":"),                  _T(":"),              wxTOKEN_RET_EMPTY_ALL, 2 },
  86     { _T("::"),                 _T(":"),              wxTOKEN_RET_EMPTY,     1 },
  87     { _T("::"),                 _T(":"),              wxTOKEN_RET_DELIMS,    1 },
  88     { _T("::"),                 _T(":"),              wxTOKEN_RET_EMPTY_ALL, 3 },
  89
  90     { _T("Hello, world"),       _T(" "),              wxTOKEN_DEFAULT,       2 },
  91     { _T("Hello,   world  "),   _T(" "),              wxTOKEN_DEFAULT,       2 },
  92     { _T("Hello, world"),       _T(","),              wxTOKEN_DEFAULT,       2 },
  93     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_DEFAULT,       2 },
  94     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_DEFAULT,       3 },
  95     { _T("Hello,, world!"),     _T(",!"),             wxTOKEN_STRTOK,        2 },
  96     { _T("Hello, world!"),      _T(",!"),             wxTOKEN_RET_EMPTY_ALL, 3 },
  97
  98     { _T("username:password:uid:gid:gecos:home:shell"),
  99                                 _T(":"),              wxTOKEN_DEFAULT,       7 },
 100
 101     { _T("1:2::3:"),            _T(":"),              wxTOKEN_DEFAULT,       4 },
 102     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY,     4 },
 103     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_EMPTY_ALL, 5 },
 104     { _T("1:2::3:"),            _T(":"),              wxTOKEN_RET_DELIMS,    4 },
 105     { _T("1:2::3:"),            _T(":"),              wxTOKEN_STRTOK,        3 },
 106
 107     { _T("1:2::3::"),           _T(":"),              wxTOKEN_DEFAULT,       4 },
 108     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY,     4 },
 109     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_EMPTY_ALL, 6 },
 110     { _T("1:2::3::"),           _T(":"),              wxTOKEN_RET_DELIMS,    4 },
 111     { _T("1:2::3::"),           _T(":"),              wxTOKEN_STRTOK,        3 },
 112
 113     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_DEFAULT,       4 },
 114     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_STRTOK,        4 },
 115     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY,     6 },
 116     { _T("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY_ALL, 9 },
 117
 118     { _T("01/02/99"),           _T("/-"),             wxTOKEN_DEFAULT,       3 },
 119     { _T("01-02/99"),           _T("/-"),             wxTOKEN_RET_DELIMS,    3 },
 120 };
 121
 122 // helper function returning the string showing the index for which the test
 123 // fails in the diagnostic message
 124 static std::string Nth(size_t n)
 125 {
 126     return wxString::Format(_T("for loop index %lu"), (unsigned long)n).mb_str();
 127 }
 128
 129 // ----------------------------------------------------------------------------
 130 // the tests
 131 // ----------------------------------------------------------------------------
 132
 133 void TokenizerTestCase::GetCount()
 134 {
 135     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 136     {
 137         const TokenizerTestData& ttd = gs_testData[n];
 138
 139         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 140         CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, tkz.CountTokens() );
 141
 142         size_t count = 0;
 143         while ( tkz.HasMoreTokens() )
 144         {
 145             tkz.GetNextToken();
 146             count++;
 147         }
 148
 149         CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, count );
 150     }
 151 }
 152
 153 // call this with the string to tokenize, delimeters to use and the expected
 154 // positions (i.e. results of GetPosition()) after each GetNextToken() call,
 155 // terminate positions with 0
 156 static void
 157 DoTestGetPosition(const wxChar *s, const wxChar *delims, int pos, ...)
 158 {
 159     wxStringTokenizer tkz(s, delims);
 160
 161     CPPUNIT_ASSERT_EQUAL( (size_t)0, tkz.GetPosition() );
 162
 163     va_list ap;
 164     va_start(ap, pos);
 165
 166     for ( ;; )
 167     {
 168         if ( !pos )
 169         {
 170             CPPUNIT_ASSERT( !tkz.HasMoreTokens() );
 171             break;
 172         }
 173
 174         tkz.GetNextToken();
 175
 176         CPPUNIT_ASSERT_EQUAL( (size_t)pos, tkz.GetPosition() );
 177
 178         pos = va_arg(ap, int);
 179     }
 180
 181     va_end(ap);
 182 }
 183
 184 void TokenizerTestCase::GetPosition()
 185 {
 186     DoTestGetPosition(_T("foo"), _T("_"), 3, 0);
 187     DoTestGetPosition(_T("foo_bar"), _T("_"), 4, 7, 0);
 188     DoTestGetPosition(_T("foo_bar_"), _T("_"), 4, 8, 0);
 189 }
 190
 191 // helper for GetString(): the parameters are the same as for DoTestGetPosition
 192 // but it checks GetString() return value instead of GetPosition()
 193 static void
 194 DoTestGetString(const wxChar *s, const wxChar *delims, int pos, ...)
 195 {
 196     wxStringTokenizer tkz(s, delims);
 197
 198     CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetString() );
 199
 200     va_list ap;
 201     va_start(ap, pos);
 202
 203     for ( ;; )
 204     {
 205         if ( !pos )
 206         {
 207             CPPUNIT_ASSERT_EQUAL( wxString(), tkz.GetString() );
 208             break;
 209         }
 210
 211         tkz.GetNextToken();
 212
 213         CPPUNIT_ASSERT_EQUAL( wxString(s + pos), tkz.GetString() );
 214
 215         pos = va_arg(ap, int);
 216     }
 217
 218     va_end(ap);
 219 }
 220
 221 void TokenizerTestCase::GetString()
 222 {
 223     DoTestGetString(_T("foo"), _T("_"), 3, 0);
 224     DoTestGetString(_T("foo_bar"), _T("_"), 4, 7, 0);
 225     DoTestGetString(_T("foo_bar_"), _T("_"), 4, 8, 0);
 226 }
 227
 228 void TokenizerTestCase::LastDelimiter()
 229 {
 230     wxStringTokenizer tkz(_T("a+-b=c"), _T("+-="));
 231
 232     tkz.GetNextToken();
 233     CPPUNIT_ASSERT_EQUAL( _T('+'), tkz.GetLastDelimiter() );
 234
 235     tkz.GetNextToken();
 236     CPPUNIT_ASSERT_EQUAL( _T('-'), tkz.GetLastDelimiter() );
 237
 238     tkz.GetNextToken();
 239     CPPUNIT_ASSERT_EQUAL( _T('='), tkz.GetLastDelimiter() );
 240
 241     tkz.GetNextToken();
 242     CPPUNIT_ASSERT_EQUAL( _T('\0'), tkz.GetLastDelimiter() );
 243 }
 244
 245 void TokenizerTestCase::StrtokCompat()
 246 {
 247     for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
 248     {
 249         const TokenizerTestData& ttd = gs_testData[n];
 250         if ( ttd.mode != wxTOKEN_STRTOK )
 251             continue;
 252
 253 #if wxUSE_UNICODE
 254         wxWCharBuffer
 255 #else
 256         wxCharBuffer
 257 #endif
 258             buf(ttd.str);
 259         wxChar *last;
 260         wxChar *s = wxStrtok(buf.data(), ttd.delims, &last);
 261
 262         wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
 263         while ( tkz.HasMoreTokens() )
 264         {
 265             CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetNextToken() );
 266             s = wxStrtok(NULL, ttd.delims, &last);
 267         }
 268     }
 269 }
 270
 271