tests/strings/strings.cpp

   1 ///////////////////////////////////////////////////////////////////////////////
   2 // Name:        tests/strings/strings.cpp
   3 // Purpose:     wxString unit test
   4 // Author:      Vadim Zeitlin, Wlodzimierz ABX Skiba
   5 // Created:     2004-04-19
   6 // RCS-ID:      $Id$
   7 // Copyright:   (c) 2004 Vadim Zeitlin, Wlodzimierz Skiba
   8 ///////////////////////////////////////////////////////////////////////////////
   9
  10 // ----------------------------------------------------------------------------
  11 // headers
  12 // ----------------------------------------------------------------------------
  13
  14 #include "wx/wxprec.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 #include "wx/cppunit.h"
  27
  28 // ----------------------------------------------------------------------------
  29 // test class
  30 // ----------------------------------------------------------------------------
  31
  32 class StringTestCase : public CppUnit::TestCase
  33 {
  34 public:
  35     StringTestCase();
  36
  37 private:
  38     CPPUNIT_TEST_SUITE( StringTestCase );
  39         CPPUNIT_TEST( String );
  40         CPPUNIT_TEST( PChar );
  41         CPPUNIT_TEST( Format );
  42         CPPUNIT_TEST( Constructors );
  43 #if wxUSE_WCHAR_T
  44         CPPUNIT_TEST( ConstructorsWithConversion );
  45         CPPUNIT_TEST( Conversion );
  46 #endif
  47 #if wxUSE_UNICODE
  48         CPPUNIT_TEST( ConversionUTF7 );
  49 #endif
  50         CPPUNIT_TEST( Extraction );
  51         CPPUNIT_TEST( Find );
  52         CPPUNIT_TEST( Tokenizer );
  53         CPPUNIT_TEST( TokenizerGetPosition );
  54         CPPUNIT_TEST( Replace );
  55         CPPUNIT_TEST( Match );
  56         CPPUNIT_TEST( CaseChanges );
  57         CPPUNIT_TEST( Compare );
  58         CPPUNIT_TEST( CompareNoCase );
  59     CPPUNIT_TEST_SUITE_END();
  60
  61     void String();
  62     void PChar();
  63     void Format();
  64     void Constructors();
  65 #if wxUSE_WCHAR_T
  66     void ConstructorsWithConversion();
  67     void Conversion();
  68 #endif
  69 #if wxUSE_UNICODE
  70     void ConversionUTF7();
  71 #endif
  72     void Extraction();
  73     void Find();
  74     void SingleTokenizerTest( wxChar *str, wxChar *delims, size_t count , wxStringTokenizerMode mode );
  75     void Tokenizer();
  76     void TokenizerGetPosition();
  77     void Replace();
  78     void Match();
  79     void CaseChanges();
  80     void Compare();
  81     void CompareNoCase();
  82
  83     DECLARE_NO_COPY_CLASS(StringTestCase)
  84 };
  85
  86 // register in the unnamed registry so that these tests are run by default
  87 CPPUNIT_TEST_SUITE_REGISTRATION( StringTestCase );
  88
  89 // also include in it's own registry so that these tests can be run alone
  90 CPPUNIT_TEST_SUITE_NAMED_REGISTRATION( StringTestCase, "StringTestCase" );
  91
  92 StringTestCase::StringTestCase()
  93 {
  94 }
  95
  96 void StringTestCase::String()
  97 {
  98     wxString a, b, c;
  99
 100     a.reserve (128);
 101     b.reserve (128);
 102     c.reserve (128);
 103
 104     for (int i = 0; i < 2; ++i)
 105     {
 106         a = _T("Hello");
 107         b = _T(" world");
 108         c = _T("! How'ya doin'?");
 109         a += b;
 110         a += c;
 111         c = _T("Hello world! What's up?");
 112         CPPUNIT_ASSERT( c != a );
 113     }
 114 }
 115
 116 void StringTestCase::PChar()
 117 {
 118     wxChar a [128];
 119     wxChar b [128];
 120     wxChar c [128];
 121
 122     for (int i = 0; i < 2; ++i)
 123     {
 124         wxStrcpy (a, _T("Hello"));
 125         wxStrcpy (b, _T(" world"));
 126         wxStrcpy (c, _T("! How'ya doin'?"));
 127         wxStrcat (a, b);
 128         wxStrcat (a, c);
 129         wxStrcpy (c, _T("Hello world! What's up?"));
 130         CPPUNIT_ASSERT( wxStrcmp (c, a) != 0 );
 131     }
 132 }
 133
 134 void StringTestCase::Format()
 135 {
 136     wxString s1,s2;
 137     s1.Printf(_T("%03d"), 18);
 138     CPPUNIT_ASSERT( s1 == wxString::Format(_T("%03d"), 18) );
 139     s2.Printf(_T("Number 18: %s\n"), s1.c_str());
 140     CPPUNIT_ASSERT( s2 == wxString::Format(_T("Number 18: %s\n"), s1.c_str()) );
 141 }
 142
 143 void StringTestCase::Constructors()
 144 {
 145     #define TEST_CTOR(args, res)                                               \
 146         {                                                                      \
 147             wxString s args ;                                                  \
 148             CPPUNIT_ASSERT( s == res );                                        \
 149         }
 150
 151     TEST_CTOR((_T('Z'), 4), _T("ZZZZ"));
 152     TEST_CTOR((_T("Hello"), 4), _T("Hell"));
 153     TEST_CTOR((_T("Hello"), 5), _T("Hello"));
 154
 155     static const wxChar *s = _T("?really!");
 156     const wxChar *start = wxStrchr(s, _T('r'));
 157     const wxChar *end = wxStrchr(s, _T('!'));
 158     TEST_CTOR((start, end), _T("really"));
 159 }
 160
 161 #if wxUSE_WCHAR_T
 162 void StringTestCase::ConstructorsWithConversion()
 163 {
 164     // the string "Déjà" in UTF-8 and wchar_t:
 165     const unsigned char utf8Buf[] = {0x44,0xC3,0xA9,0x6A,0xC3,0xA0,0};
 166     const wchar_t wchar[] = {0x44,0xE9,0x6A,0xE0,0};
 167     const unsigned char utf8subBuf[] = {0x44,0xC3,0xA9,0x6A,0}; // just "Déj"
 168     const char *utf8 = (char *)utf8Buf;
 169     const char *utf8sub = (char *)utf8subBuf;
 170
 171     wxString s1(utf8, wxConvUTF8);
 172     wxString s2(wchar, wxConvUTF8);
 173
 174 #if wxUSE_UNICODE
 175     CPPUNIT_ASSERT( s1 == wchar );
 176     CPPUNIT_ASSERT( s2 == wchar );
 177 #else
 178     CPPUNIT_ASSERT( s1 == utf8 );
 179     CPPUNIT_ASSERT( s2 == utf8 );
 180 #endif
 181
 182     wxString sub(utf8sub, wxConvUTF8); // "Dej" substring
 183     wxString s3(utf8, wxConvUTF8, 4);
 184     wxString s4(wchar, wxConvUTF8, 3);
 185
 186     CPPUNIT_ASSERT( s3 == sub );
 187     CPPUNIT_ASSERT( s4 == sub );
 188
 189 #if wxUSE_UNICODE
 190     CPPUNIT_ASSERT ( wxString("\t[pl]open.format.Sformatuj dyskietkê=gfloppy %f",
 191                                wxConvUTF8) == wxT("") ); //Pos 35 (funky e) is invalid UTF8
 192 #else
 193     CPPUNIT_ASSERT ( wxString(L"\t[pl]open.format.Sformatuj dyskietkê=gfloppy %f",
 194                                wxConvUTF8) == wxT("") ); //Pos 35 (funky e) is invalid UTF8
 195 #endif
 196 }
 197
 198 void StringTestCase::Conversion()
 199 {
 200 #if wxUSE_UNICODE
 201         wxString szTheString(L"The\0String", wxConvLibc, 10);
 202         wxCharBuffer theBuffer = szTheString.mb_str();
 203
 204         CPPUNIT_ASSERT( memcmp(theBuffer.data(), "The\0String", 11) == 0 );
 205
 206         wxString szTheString2("The\0String", wxConvLocal, 10);
 207         CPPUNIT_ASSERT( wxMemcmp(szTheString2.c_str(), L"The\0String", 11) == 0 );
 208 #else
 209         wxString szTheString(wxT("TheString"));
 210         szTheString.insert(3, 1, '\0');
 211         wxWCharBuffer theBuffer = szTheString.wc_str(wxConvLibc);
 212
 213         CPPUNIT_ASSERT( memcmp(theBuffer.data(), L"The\0String", 11 * sizeof(wchar_t)) == 0 );
 214
 215         wxString szLocalTheString(wxT("TheString"));
 216         szLocalTheString.insert(3, 1, '\0');
 217         wxWCharBuffer theLocalBuffer = szLocalTheString.wc_str(wxConvLocal);
 218
 219         CPPUNIT_ASSERT( memcmp(theLocalBuffer.data(), L"The\0String", 11 * sizeof(wchar_t)) == 0 );
 220 #endif
 221 }
 222 #endif // wxUSE_WCHAR_T
 223
 224 #if wxUSE_UNICODE
 225 void StringTestCase::ConversionUTF7()
 226 {
 227     const wxChar wdata[] = { 0x00A3, 0x00A3, 0x00A3, 0x00A3, 0 }; // pound signs
 228     const char *utf7 = "+AKM-+AKM-+AKM-+AKM-";
 229     wxString str(wdata);
 230
 231     wxCSConv conv(_T("utf-7"));
 232     CPPUNIT_ASSERT( strcmp(str.mb_str(conv), utf7) == 0 );
 233 }
 234 #endif // wxUSE_UNICODE
 235
 236 void StringTestCase::Extraction()
 237 {
 238     wxString s(_T("Hello, world!"));
 239
 240     CPPUNIT_ASSERT( wxStrcmp( s.c_str() , _T("Hello, world!") ) == 0 );
 241     CPPUNIT_ASSERT( wxStrcmp( s.Left(5).c_str() , _T("Hello") ) == 0 );
 242     CPPUNIT_ASSERT( wxStrcmp( s.Right(6).c_str() , _T("world!") ) == 0 );
 243     CPPUNIT_ASSERT( wxStrcmp( s(3, 5).c_str() , _T("lo, w") ) == 0 );
 244     CPPUNIT_ASSERT( wxStrcmp( s.Mid(3).c_str() , _T("lo, world!") ) == 0 );
 245     CPPUNIT_ASSERT( wxStrcmp( s.substr(3, 5).c_str() , _T("lo, w") ) == 0 );
 246     CPPUNIT_ASSERT( wxStrcmp( s.substr(3).c_str() , _T("lo, world!") ) == 0 );
 247
 248     wxString rest;
 249
 250     #define TEST_STARTS_WITH( prefix , correct_rest, result ) \
 251         CPPUNIT_ASSERT( \
 252             ( s.StartsWith( prefix, &rest ) == result ) && \
 253             ( ( result == false ) || ( wxStrcmp( correct_rest , rest ) == 0 ) ) \
 254         )
 255
 256     TEST_STARTS_WITH( _T("Hello"),           _T(", world!"),      true  );
 257     TEST_STARTS_WITH( _T("Hello, "),         _T("world!"),        true  );
 258     TEST_STARTS_WITH( _T("Hello, world!"),   _T(""),              true  );
 259     TEST_STARTS_WITH( _T("Hello, world!!!"), _T(""),              false );
 260     TEST_STARTS_WITH( _T(""),                _T("Hello, world!"), true  );
 261     TEST_STARTS_WITH( _T("Goodbye"),         _T(""),              false );
 262     TEST_STARTS_WITH( _T("Hi"),              _T(""),              false );
 263
 264     #undef TEST_STARTS_WITH
 265 }
 266
 267 void StringTestCase::Find()
 268 {
 269     #define TEST_FIND( str , start , result )  \
 270         CPPUNIT_ASSERT( wxString(str).find(_T("ell"), start) == result );
 271
 272     TEST_FIND( _T("Well, hello world"),  0, 1              );
 273     TEST_FIND( _T("Well, hello world"),  6, 7              );
 274     TEST_FIND( _T("Well, hello world"),  9, wxString::npos );
 275
 276     #undef TEST_FIND
 277 }
 278
 279 void StringTestCase::SingleTokenizerTest( wxChar *str, wxChar *delims, size_t count , wxStringTokenizerMode mode )
 280 {
 281     wxStringTokenizer tkz( str, delims, mode);
 282     CPPUNIT_ASSERT( tkz.CountTokens() == count );
 283
 284     wxChar *buf, *s = NULL, *last;
 285
 286     if ( tkz.GetMode() == wxTOKEN_STRTOK )
 287     {
 288         buf = new wxChar[wxStrlen(str) + 1];
 289         wxStrcpy(buf, str);
 290         s = wxStrtok(buf, delims, &last);
 291     }
 292     else
 293     {
 294         buf = NULL;
 295     }
 296
 297     size_t count2 = 0;
 298     while ( tkz.HasMoreTokens() )
 299     {
 300         wxString token = tkz.GetNextToken();
 301         if ( buf )
 302         {
 303             CPPUNIT_ASSERT( token == s );
 304             s = wxStrtok(NULL, delims, &last);
 305         }
 306         count2++;
 307     }
 308
 309     CPPUNIT_ASSERT( count2 == count );
 310     if ( buf )
 311     {
 312         delete [] buf;
 313     }
 314 }
 315
 316 void StringTestCase::Tokenizer()
 317 {
 318     SingleTokenizerTest( _T(""),                                           _T(" "),              0, wxTOKEN_DEFAULT       );
 319     SingleTokenizerTest( _T("Hello, world"),                               _T(" "),              2, wxTOKEN_DEFAULT       );
 320     SingleTokenizerTest( _T("Hello,   world  "),                           _T(" "),              2, wxTOKEN_DEFAULT       );
 321     SingleTokenizerTest( _T("Hello, world"),                               _T(","),              2, wxTOKEN_DEFAULT       );
 322     SingleTokenizerTest( _T("Hello, world!"),                              _T(",!"),             2, wxTOKEN_DEFAULT       );
 323     SingleTokenizerTest( _T("Hello,, world!"),                             _T(",!"),             3, wxTOKEN_DEFAULT       );
 324     SingleTokenizerTest( _T("Hello, world!"),                              _T(",!"),             3, wxTOKEN_RET_EMPTY_ALL );
 325     SingleTokenizerTest( _T("username:password:uid:gid:gecos:home:shell"), _T(":"),              7, wxTOKEN_DEFAULT       );
 326     SingleTokenizerTest( _T("1 \t3\t4  6   "),                             wxDEFAULT_DELIMITERS, 4, wxTOKEN_DEFAULT       );
 327     SingleTokenizerTest( _T("1 \t3\t4  6   "),                             wxDEFAULT_DELIMITERS, 6, wxTOKEN_RET_EMPTY     );
 328     SingleTokenizerTest( _T("1 \t3\t4  6   "),                             wxDEFAULT_DELIMITERS, 9, wxTOKEN_RET_EMPTY_ALL );
 329     SingleTokenizerTest( _T("01/02/99"),                                   _T("/-"),             3, wxTOKEN_DEFAULT       );
 330     SingleTokenizerTest( _T("01-02/99"),                                   _T("/-"),             3, wxTOKEN_RET_DELIMS    );
 331 }
 332
 333 // call this with the string to tokenize, delimeters to use and the expected
 334 // positions (i.e. results of GetPosition()) after each GetNextToken() call,
 335 // terminate positions with 0
 336 static void
 337 DoTokenizerGetPosition(const wxChar *s, const wxChar *delims, int pos, ...)
 338 {
 339     wxStringTokenizer tkz(s, delims);
 340
 341     CPPUNIT_ASSERT( tkz.GetPosition() == 0 );
 342
 343     va_list ap;
 344     va_start(ap, pos);
 345
 346     for ( ;; )
 347     {
 348         if ( !pos )
 349         {
 350             CPPUNIT_ASSERT( !tkz.HasMoreTokens() );
 351             break;
 352         }
 353
 354         tkz.GetNextToken();
 355
 356         CPPUNIT_ASSERT( tkz.GetPosition() == (size_t)pos );
 357
 358         pos = va_arg(ap, int);
 359     }
 360
 361     va_end(ap);
 362 }
 363
 364 void StringTestCase::TokenizerGetPosition()
 365 {
 366     DoTokenizerGetPosition(_T("foo"), _T("_"), 3, 0);
 367     DoTokenizerGetPosition(_T("foo_bar"), _T("_"), 4, 7, 0);
 368     DoTokenizerGetPosition(_T("foo_bar_"), _T("_"), 4, 8, 0);
 369 }
 370
 371 void StringTestCase::Replace()
 372 {
 373     #define TEST_REPLACE( original , pos , len , replacement , result ) \
 374         { \
 375             wxString s = original; \
 376             s.replace( pos , len , replacement ); \
 377             CPPUNIT_ASSERT( s == result ); \
 378         }
 379
 380     TEST_REPLACE( _T("012-AWORD-XYZ"), 4, 5, _T("BWORD"),  _T("012-BWORD-XYZ") );
 381     TEST_REPLACE( _T("increase"),      0, 2, _T("de"),     _T("decrease")      );
 382     TEST_REPLACE( _T("wxWindow"),      8, 0, _T("s"),      _T("wxWindows")     );
 383     TEST_REPLACE( _T("foobar"),        3, 0, _T("-"),      _T("foo-bar")       );
 384     TEST_REPLACE( _T("barfoo"),        0, 6, _T("foobar"), _T("foobar")        );
 385
 386     #undef TEST_REPLACE
 387 }
 388
 389 void StringTestCase::Match()
 390 {
 391     #define TEST_MATCH( s1 , s2 , result ) \
 392         CPPUNIT_ASSERT( wxString(s1).Matches(s2) == result )
 393
 394     TEST_MATCH( _T("foobar"),    _T("foo*"),   true  );
 395     TEST_MATCH( _T("foobar"),    _T("*oo*"),   true  );
 396     TEST_MATCH( _T("foobar"),    _T("*bar"),   true  );
 397     TEST_MATCH( _T("foobar"),    _T("??????"), true  );
 398     TEST_MATCH( _T("foobar"),    _T("f??b*"),  true  );
 399     TEST_MATCH( _T("foobar"),    _T("f?b*"),   false );
 400     TEST_MATCH( _T("foobar"),    _T("*goo*"),  false );
 401     TEST_MATCH( _T("foobar"),    _T("*foo"),   false );
 402     TEST_MATCH( _T("foobarfoo"), _T("*foo"),   true  );
 403     TEST_MATCH( _T(""),          _T("*"),      true  );
 404     TEST_MATCH( _T(""),          _T("?"),      false );
 405
 406     #undef TEST_MATCH
 407 }
 408
 409
 410 void StringTestCase::CaseChanges()
 411 {
 412     wxString s1(_T("Hello!"));
 413     wxString s1u(s1);
 414     wxString s1l(s1);
 415     s1u.MakeUpper();
 416     s1l.MakeLower();
 417     wxString s2u, s2l;
 418     s2u.MakeUpper();
 419     s2l.MakeLower();
 420
 421     CPPUNIT_ASSERT( s1u == _T("HELLO!") );
 422     CPPUNIT_ASSERT( s1l == _T("hello!") );
 423     CPPUNIT_ASSERT( s2u == wxEmptyString );
 424     CPPUNIT_ASSERT( s2l == wxEmptyString );
 425
 426 #if !wxUSE_UNICODE
 427     wxLocale locRu(wxLANGUAGE_RUSSIAN, 0 /* flags */);
 428     if ( locRu.IsOk() )
 429     {
 430         // try upper casing 8bit strings
 431         wxString sUpper("\xdf"),
 432                  sLower("\xff");
 433
 434         CPPUNIT_ASSERT( sUpper.Lower() == sLower );
 435         CPPUNIT_ASSERT( sLower.Upper() == sUpper );
 436     }
 437 #endif // !wxUSE_UNICODE
 438 }
 439
 440 void StringTestCase::Compare()
 441 {
 442     wxString s1 = wxT("AHH");
 443     wxString eq = wxT("AHH");
 444     wxString neq1 = wxT("HAH");
 445     wxString neq2 = wxT("AH");
 446     wxString neq3 = wxT("AHHH");
 447     wxString neq4 = wxT("AhH");
 448
 449     CPPUNIT_ASSERT( s1 == eq );
 450     CPPUNIT_ASSERT( s1 != neq1 );
 451     CPPUNIT_ASSERT( s1 != neq2 );
 452     CPPUNIT_ASSERT( s1 != neq3 );
 453     CPPUNIT_ASSERT( s1 != neq4 );
 454
 455 //    wxString _s1 = wxT("A\0HH");
 456 //    wxString _eq = wxT("A\0HH");
 457 //    wxString _neq1 = wxT("H\0AH");
 458 //    wxString _neq2 = wxT("A\0H");
 459 //    wxString _neq3 = wxT("A\0HHH");
 460 //    wxString _neq4 = wxT("A\0hH");
 461     s1.insert(1,1,'\0');
 462     eq.insert(1,1,'\0');
 463     neq1.insert(1,1,'\0');
 464     neq2.insert(1,1,'\0');
 465     neq3.insert(1,1,'\0');
 466     neq4.insert(1,1,'\0');
 467
 468     CPPUNIT_ASSERT( s1 == eq );
 469     CPPUNIT_ASSERT( s1 != neq1 );
 470     CPPUNIT_ASSERT( s1 != neq2 );
 471     CPPUNIT_ASSERT( s1 != neq3 );
 472     CPPUNIT_ASSERT( s1 != neq4 );
 473 }
 474
 475 void StringTestCase::CompareNoCase()
 476 {
 477     wxString s1 = wxT("AHH");
 478     wxString eq = wxT("AHH");
 479     wxString eq2 = wxT("AhH");
 480     wxString eq3 = wxT("ahh");
 481     wxString neq = wxT("HAH");
 482     wxString neq2 = wxT("AH");
 483     wxString neq3 = wxT("AHHH");
 484
 485     #define CPPUNIT_CNCEQ_ASSERT(s1, s2) CPPUNIT_ASSERT( s1.CmpNoCase(s2) == 0)
 486     #define CPPUNIT_CNCNEQ_ASSERT(s1, s2) CPPUNIT_ASSERT( s1.CmpNoCase(s2) != 0)
 487
 488     CPPUNIT_CNCEQ_ASSERT( s1, eq );
 489     CPPUNIT_CNCEQ_ASSERT( s1, eq2 );
 490     CPPUNIT_CNCEQ_ASSERT( s1, eq3 );
 491
 492     CPPUNIT_CNCNEQ_ASSERT( s1, neq );
 493     CPPUNIT_CNCNEQ_ASSERT( s1, neq2 );
 494     CPPUNIT_CNCNEQ_ASSERT( s1, neq3 );
 495
 496
 497 //    wxString _s1 = wxT("A\0HH");
 498 //    wxString _eq = wxT("A\0HH");
 499 //    wxString _eq2 = wxT("A\0hH");
 500 //    wxString _eq3 = wxT("a\0hh");
 501 //    wxString _neq = wxT("H\0AH");
 502 //    wxString _neq2 = wxT("A\0H");
 503 //    wxString _neq3 = wxT("A\0HHH");
 504
 505     s1.insert(1,1,'\0');
 506     eq.insert(1,1,'\0');
 507     eq2.insert(1,1,'\0');
 508     eq3.insert(1,1,'\0');
 509     neq.insert(1,1,'\0');
 510     neq2.insert(1,1,'\0');
 511     neq3.insert(1,1,'\0');
 512
 513     CPPUNIT_CNCEQ_ASSERT( s1, eq );
 514     CPPUNIT_CNCEQ_ASSERT( s1, eq2 );
 515     CPPUNIT_CNCEQ_ASSERT( s1, eq3 );
 516
 517     CPPUNIT_CNCNEQ_ASSERT( s1, neq );
 518     CPPUNIT_CNCNEQ_ASSERT( s1, neq2 );
 519     CPPUNIT_CNCNEQ_ASSERT( s1, neq3 );
 520 }
 521