[wxWidgets.git] / tests / strings / tokenizer.cpp

///////////////////////////////////////////////////////////////////////////////
// Name:        tests/strings/strings.cpp
// Purpose:     wxStringTokenizer unit test
// Author:      Vadim Zeitlin
// Created:     2005-12-20 (extacted from strings.cpp)
// RCS-ID:      $Id$
// Copyright:   (c) 2004-2005 Vadim Zeitlin
///////////////////////////////////////////////////////////////////////////////

// ----------------------------------------------------------------------------
// headers
// ----------------------------------------------------------------------------

#include "testprec.h"

#ifdef __BORLANDC__
    #pragma hdrstop
#endif

#ifndef WX_PRECOMP
    #include "wx/wx.h"
#endif // WX_PRECOMP

#include "wx/tokenzr.h"

// ----------------------------------------------------------------------------
// test class
// ----------------------------------------------------------------------------

class TokenizerTestCase : public CppUnit::TestCase
{
public:
    TokenizerTestCase() { }

private:
    CPPUNIT_TEST_SUITE( TokenizerTestCase );
        CPPUNIT_TEST( GetCount );
        CPPUNIT_TEST( GetPosition );
        CPPUNIT_TEST( GetString );
        CPPUNIT_TEST( LastDelimiter );
        CPPUNIT_TEST( StrtokCompat );
    CPPUNIT_TEST_SUITE_END();

    void GetCount();
    void GetPosition();
    void GetString();
    void LastDelimiter();
    void StrtokCompat();

    DECLARE_NO_COPY_CLASS(TokenizerTestCase)
};

// register in the unnamed registry so that these tests are run by default
CPPUNIT_TEST_SUITE_REGISTRATION( TokenizerTestCase );

// also include in its own registry so that these tests can be run alone
CPPUNIT_TEST_SUITE_NAMED_REGISTRATION( TokenizerTestCase, "TokenizerTestCase" );

// ----------------------------------------------------------------------------
// test data
// ----------------------------------------------------------------------------

static const struct TokenizerTestData
{
    // the string to tokenize
    const wxChar *str;

    // the delimiters to use
    const wxChar *delims;

    // the tokenizer mode
    wxStringTokenizerMode mode;

    // expected number of tokens
    size_t count;
}
gs_testData[] =
{
    { wxT(""),                   wxT(" "),              wxTOKEN_DEFAULT,       0 },
    { wxT(""),                   wxT(" "),              wxTOKEN_RET_EMPTY,     0 },
    { wxT(""),                   wxT(" "),              wxTOKEN_RET_EMPTY_ALL, 0 },
    { wxT(""),                   wxT(" "),              wxTOKEN_RET_DELIMS,    0 },
    { wxT(":"),                  wxT(":"),              wxTOKEN_RET_EMPTY,     1 },
    { wxT(":"),                  wxT(":"),              wxTOKEN_RET_DELIMS,    1 },
    { wxT(":"),                  wxT(":"),              wxTOKEN_RET_EMPTY_ALL, 2 },
    { wxT("::"),                 wxT(":"),              wxTOKEN_RET_EMPTY,     1 },
    { wxT("::"),                 wxT(":"),              wxTOKEN_RET_DELIMS,    1 },
    { wxT("::"),                 wxT(":"),              wxTOKEN_RET_EMPTY_ALL, 3 },

    { wxT("Hello, world"),       wxT(" "),              wxTOKEN_DEFAULT,       2 },
    { wxT("Hello,   world  "),   wxT(" "),              wxTOKEN_DEFAULT,       2 },
    { wxT("Hello, world"),       wxT(","),              wxTOKEN_DEFAULT,       2 },
    { wxT("Hello, world!"),      wxT(",!"),             wxTOKEN_DEFAULT,       2 },
    { wxT("Hello,, world!"),     wxT(",!"),             wxTOKEN_DEFAULT,       3 },
    { wxT("Hello,, world!"),     wxT(",!"),             wxTOKEN_STRTOK,        2 },
    { wxT("Hello, world!"),      wxT(",!"),             wxTOKEN_RET_EMPTY_ALL, 3 },

    { wxT("username:password:uid:gid:gecos:home:shell"),
                                wxT(":"),              wxTOKEN_DEFAULT,       7 },

    { wxT("1:2::3:"),            wxT(":"),              wxTOKEN_DEFAULT,       4 },
    { wxT("1:2::3:"),            wxT(":"),              wxTOKEN_RET_EMPTY,     4 },
    { wxT("1:2::3:"),            wxT(":"),              wxTOKEN_RET_EMPTY_ALL, 5 },
    { wxT("1:2::3:"),            wxT(":"),              wxTOKEN_RET_DELIMS,    4 },
    { wxT("1:2::3:"),            wxT(":"),              wxTOKEN_STRTOK,        3 },

    { wxT("1:2::3::"),           wxT(":"),              wxTOKEN_DEFAULT,       4 },
    { wxT("1:2::3::"),           wxT(":"),              wxTOKEN_RET_EMPTY,     4 },
    { wxT("1:2::3::"),           wxT(":"),              wxTOKEN_RET_EMPTY_ALL, 6 },
    { wxT("1:2::3::"),           wxT(":"),              wxTOKEN_RET_DELIMS,    4 },
    { wxT("1:2::3::"),           wxT(":"),              wxTOKEN_STRTOK,        3 },

    { wxT("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_DEFAULT,       4 },
    { wxT("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_STRTOK,        4 },
    { wxT("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY,     6 },
    { wxT("1 \t3\t4  6   "),     wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY_ALL, 9 },

    { wxT("01/02/99"),           wxT("/-"),             wxTOKEN_DEFAULT,       3 },
    { wxT("01-02/99"),           wxT("/-"),             wxTOKEN_RET_DELIMS,    3 },
};

// helper function returning the string showing the index for which the test
// fails in the diagnostic message
static std::string Nth(size_t n)
{
    return std::string(wxString::Format(wxT("for loop index %lu"),
                                        (unsigned long)n).mb_str());
}

// ----------------------------------------------------------------------------
// the tests
// ----------------------------------------------------------------------------

void TokenizerTestCase::GetCount()
{
    for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
    {
        const TokenizerTestData& ttd = gs_testData[n];

        wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
        CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, tkz.CountTokens() );

        size_t count = 0;
        while ( tkz.HasMoreTokens() )
        {
            tkz.GetNextToken();
            count++;
        }

        CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, count );
    }
}

// call this with the string to tokenize, delimeters to use and the expected
// positions (i.e. results of GetPosition()) after each GetNextToken() call,
// terminate positions with 0
static void
DoTestGetPosition(const wxChar *s, const wxChar *delims, int pos, ...)
{
    wxStringTokenizer tkz(s, delims);

    CPPUNIT_ASSERT_EQUAL( (size_t)0, tkz.GetPosition() );

    va_list ap;
    va_start(ap, pos);

    for ( ;; )
    {
        if ( !pos )
        {
            CPPUNIT_ASSERT( !tkz.HasMoreTokens() );
            break;
        }

        tkz.GetNextToken();

        CPPUNIT_ASSERT_EQUAL( (size_t)pos, tkz.GetPosition() );

        pos = va_arg(ap, int);
    }

    va_end(ap);
}

void TokenizerTestCase::GetPosition()
{
    DoTestGetPosition(wxT("foo"), wxT("_"), 3, 0);
    DoTestGetPosition(wxT("foo_bar"), wxT("_"), 4, 7, 0);
    DoTestGetPosition(wxT("foo_bar_"), wxT("_"), 4, 8, 0);
}

// helper for GetString(): the parameters are the same as for DoTestGetPosition
// but it checks GetString() return value instead of GetPosition()
static void
DoTestGetString(const wxChar *s, const wxChar *delims, int pos, ...)
{
    wxStringTokenizer tkz(s, delims);

    CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetString() );

    va_list ap;
    va_start(ap, pos);

    for ( ;; )
    {
        if ( !pos )
        {
            CPPUNIT_ASSERT( tkz.GetString().empty() ) ;
            break;
        }

        tkz.GetNextToken();

        CPPUNIT_ASSERT_EQUAL( wxString(s + pos), tkz.GetString() );

        pos = va_arg(ap, int);
    }

    va_end(ap);
}

void TokenizerTestCase::GetString()
{
    DoTestGetString(wxT("foo"), wxT("_"), 3, 0);
    DoTestGetString(wxT("foo_bar"), wxT("_"), 4, 7, 0);
    DoTestGetString(wxT("foo_bar_"), wxT("_"), 4, 8, 0);
}

void TokenizerTestCase::LastDelimiter()
{
    wxStringTokenizer tkz(wxT("a+-b=c"), wxT("+-="));

    tkz.GetNextToken();
    CPPUNIT_ASSERT_EQUAL( wxT('+'), tkz.GetLastDelimiter() );

    tkz.GetNextToken();
    CPPUNIT_ASSERT_EQUAL( wxT('-'), tkz.GetLastDelimiter() );

    tkz.GetNextToken();
    CPPUNIT_ASSERT_EQUAL( wxT('='), tkz.GetLastDelimiter() );

    tkz.GetNextToken();
    CPPUNIT_ASSERT_EQUAL( wxT('\0'), tkz.GetLastDelimiter() );
}

void TokenizerTestCase::StrtokCompat()
{
    for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
    {
        const TokenizerTestData& ttd = gs_testData[n];
        if ( ttd.mode != wxTOKEN_STRTOK )
            continue;

#if wxUSE_UNICODE
        wxWCharBuffer
#else
        wxCharBuffer
#endif
            buf(ttd.str);
        wxChar *last;
        wxChar *s = wxStrtok(buf.data(), ttd.delims, &last);

        wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
        while ( tkz.HasMoreTokens() )
        {
            CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetNextToken() );
            s = wxStrtok(NULL, ttd.delims, &last);
        }
    }
}
Commit	Line	Data
a67f601b VZ	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 );
06ef1511	39	CPPUNIT_TEST( GetString );
4626c57c	40	CPPUNIT_TEST( LastDelimiter );
a67f601b VZ	41	CPPUNIT_TEST( StrtokCompat );
	42	CPPUNIT_TEST_SUITE_END();
	43
	44	void GetCount();
	45	void GetPosition();
06ef1511	46	void GetString();
4626c57c	47	void LastDelimiter();
a67f601b VZ	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
e3778b4d	56	// also include in its own registry so that these tests can be run alone
a67f601b VZ	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	{
9a83f860 VZ	79	{ wxT(""), wxT(" "), wxTOKEN_DEFAULT, 0 },
	80	{ wxT(""), wxT(" "), wxTOKEN_RET_EMPTY, 0 },
	81	{ wxT(""), wxT(" "), wxTOKEN_RET_EMPTY_ALL, 0 },
	82	{ wxT(""), wxT(" "), wxTOKEN_RET_DELIMS, 0 },
	83	{ wxT(":"), wxT(":"), wxTOKEN_RET_EMPTY, 1 },
	84	{ wxT(":"), wxT(":"), wxTOKEN_RET_DELIMS, 1 },
	85	{ wxT(":"), wxT(":"), wxTOKEN_RET_EMPTY_ALL, 2 },
	86	{ wxT("::"), wxT(":"), wxTOKEN_RET_EMPTY, 1 },
	87	{ wxT("::"), wxT(":"), wxTOKEN_RET_DELIMS, 1 },
	88	{ wxT("::"), wxT(":"), wxTOKEN_RET_EMPTY_ALL, 3 },
	89
	90	{ wxT("Hello, world"), wxT(" "), wxTOKEN_DEFAULT, 2 },
	91	{ wxT("Hello, world "), wxT(" "), wxTOKEN_DEFAULT, 2 },
	92	{ wxT("Hello, world"), wxT(","), wxTOKEN_DEFAULT, 2 },
	93	{ wxT("Hello, world!"), wxT(",!"), wxTOKEN_DEFAULT, 2 },
	94	{ wxT("Hello,, world!"), wxT(",!"), wxTOKEN_DEFAULT, 3 },
	95	{ wxT("Hello,, world!"), wxT(",!"), wxTOKEN_STRTOK, 2 },
	96	{ wxT("Hello, world!"), wxT(",!"), wxTOKEN_RET_EMPTY_ALL, 3 },
	97
	98	{ wxT("username:password:uid:gid:gecos:home:shell"),
	99	wxT(":"), wxTOKEN_DEFAULT, 7 },
	100
	101	{ wxT("1:2::3:"), wxT(":"), wxTOKEN_DEFAULT, 4 },
	102	{ wxT("1:2::3:"), wxT(":"), wxTOKEN_RET_EMPTY, 4 },
	103	{ wxT("1:2::3:"), wxT(":"), wxTOKEN_RET_EMPTY_ALL, 5 },
	104	{ wxT("1:2::3:"), wxT(":"), wxTOKEN_RET_DELIMS, 4 },
	105	{ wxT("1:2::3:"), wxT(":"), wxTOKEN_STRTOK, 3 },
	106
	107	{ wxT("1:2::3::"), wxT(":"), wxTOKEN_DEFAULT, 4 },
	108	{ wxT("1:2::3::"), wxT(":"), wxTOKEN_RET_EMPTY, 4 },
	109	{ wxT("1:2::3::"), wxT(":"), wxTOKEN_RET_EMPTY_ALL, 6 },
	110	{ wxT("1:2::3::"), wxT(":"), wxTOKEN_RET_DELIMS, 4 },
	111	{ wxT("1:2::3::"), wxT(":"), wxTOKEN_STRTOK, 3 },
	112
	113	{ wxT("1 \t3\t4 6 "), wxDEFAULT_DELIMITERS, wxTOKEN_DEFAULT, 4 },
	114	{ wxT("1 \t3\t4 6 "), wxDEFAULT_DELIMITERS, wxTOKEN_STRTOK, 4 },
	115	{ wxT("1 \t3\t4 6 "), wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY, 6 },
	116	{ wxT("1 \t3\t4 6 "), wxDEFAULT_DELIMITERS, wxTOKEN_RET_EMPTY_ALL, 9 },
	117
	118	{ wxT("01/02/99"), wxT("/-"), wxTOKEN_DEFAULT, 3 },
	119	{ wxT("01-02/99"), wxT("/-"), wxTOKEN_RET_DELIMS, 3 },
a67f601b VZ	120	};
a67f601b VZ	121
822c2b9f VZ	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	{
9a83f860	126	return std::string(wxString::Format(wxT("for loop index %lu"),
5ad1f902	127	(unsigned long)n).mb_str());
822c2b9f VZ	128	}
822c2b9f VZ	129
a67f601b VZ	130	// ----------------------------------------------------------------------------
	131	// the tests
	132	// ----------------------------------------------------------------------------
	133
	134	void TokenizerTestCase::GetCount()
	135	{
	136	for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
	137	{
	138	const TokenizerTestData& ttd = gs_testData[n];
	139
	140	wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
822c2b9f	141	CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, tkz.CountTokens() );
a67f601b VZ	142
	143	size_t count = 0;
	144	while ( tkz.HasMoreTokens() )
	145	{
	146	tkz.GetNextToken();
	147	count++;
	148	}
	149
822c2b9f	150	CPPUNIT_ASSERT_EQUAL_MESSAGE( Nth(n), ttd.count, count );
a67f601b VZ	151	}
	152	}
	153
	154	// call this with the string to tokenize, delimeters to use and the expected
	155	// positions (i.e. results of GetPosition()) after each GetNextToken() call,
	156	// terminate positions with 0
	157	static void
	158	DoTestGetPosition(const wxChar s, const wxChar delims, int pos, ...)
	159	{
	160	wxStringTokenizer tkz(s, delims);
	161
	162	CPPUNIT_ASSERT_EQUAL( (size_t)0, tkz.GetPosition() );
	163
	164	va_list ap;
	165	va_start(ap, pos);
	166
	167	for ( ;; )
	168	{
	169	if ( !pos )
	170	{
	171	CPPUNIT_ASSERT( !tkz.HasMoreTokens() );
	172	break;
	173	}
	174
	175	tkz.GetNextToken();
	176
	177	CPPUNIT_ASSERT_EQUAL( (size_t)pos, tkz.GetPosition() );
	178
	179	pos = va_arg(ap, int);
	180	}
	181
	182	va_end(ap);
	183	}
	184
	185	void TokenizerTestCase::GetPosition()
	186	{
9a83f860 VZ	187	DoTestGetPosition(wxT("foo"), wxT("_"), 3, 0);
	188	DoTestGetPosition(wxT("foo_bar"), wxT("_"), 4, 7, 0);
	189	DoTestGetPosition(wxT("foo_bar_"), wxT("_"), 4, 8, 0);
a67f601b VZ	190	}
a67f601b VZ	191
06ef1511 VZ	192	// helper for GetString(): the parameters are the same as for DoTestGetPosition
	193	// but it checks GetString() return value instead of GetPosition()
	194	static void
	195	DoTestGetString(const wxChar s, const wxChar delims, int pos, ...)
	196	{
	197	wxStringTokenizer tkz(s, delims);
	198
	199	CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetString() );
	200
	201	va_list ap;
	202	va_start(ap, pos);
	203
	204	for ( ;; )
	205	{
	206	if ( !pos )
	207	{
f30057df	208	CPPUNIT_ASSERT( tkz.GetString().empty() ) ;
06ef1511 VZ	209	break;
	210	}
	211
	212	tkz.GetNextToken();
	213
	214	CPPUNIT_ASSERT_EQUAL( wxString(s + pos), tkz.GetString() );
	215
	216	pos = va_arg(ap, int);
	217	}
	218
	219	va_end(ap);
	220	}
	221
	222	void TokenizerTestCase::GetString()
	223	{
9a83f860 VZ	224	DoTestGetString(wxT("foo"), wxT("_"), 3, 0);
	225	DoTestGetString(wxT("foo_bar"), wxT("_"), 4, 7, 0);
	226	DoTestGetString(wxT("foo_bar_"), wxT("_"), 4, 8, 0);
06ef1511 VZ	227	}
06ef1511 VZ	228
4626c57c VZ	229	void TokenizerTestCase::LastDelimiter()
4626c57c VZ	230	{
9a83f860	231	wxStringTokenizer tkz(wxT("a+-b=c"), wxT("+-="));
4626c57c VZ	232
4626c57c VZ	233	tkz.GetNextToken();
9a83f860	234	CPPUNIT_ASSERT_EQUAL( wxT('+'), tkz.GetLastDelimiter() );
4626c57c VZ	235
4626c57c VZ	236	tkz.GetNextToken();
9a83f860	237	CPPUNIT_ASSERT_EQUAL( wxT('-'), tkz.GetLastDelimiter() );
4626c57c VZ	238
4626c57c VZ	239	tkz.GetNextToken();
9a83f860	240	CPPUNIT_ASSERT_EQUAL( wxT('='), tkz.GetLastDelimiter() );
4626c57c VZ	241
4626c57c VZ	242	tkz.GetNextToken();
9a83f860	243	CPPUNIT_ASSERT_EQUAL( wxT('\0'), tkz.GetLastDelimiter() );
4626c57c VZ	244	}
4626c57c VZ	245
a67f601b VZ	246	void TokenizerTestCase::StrtokCompat()
	247	{
	248	for ( size_t n = 0; n < WXSIZEOF(gs_testData); n++ )
	249	{
	250	const TokenizerTestData& ttd = gs_testData[n];
	251	if ( ttd.mode != wxTOKEN_STRTOK )
	252	continue;
	253
53599fbb VZ	254	#if wxUSE_UNICODE
	255	wxWCharBuffer
	256	#else
	257	wxCharBuffer
	258	#endif
	259	buf(ttd.str);
a67f601b VZ	260	wxChar *last;
	261	wxChar *s = wxStrtok(buf.data(), ttd.delims, &last);
	262
	263	wxStringTokenizer tkz(ttd.str, ttd.delims, ttd.mode);
	264	while ( tkz.HasMoreTokens() )
	265	{
	266	CPPUNIT_ASSERT_EQUAL( wxString(s), tkz.GetNextToken() );
	267	s = wxStrtok(NULL, ttd.delims, &last);
	268	}
	269	}
	270	}
	271
	272