2004-04-30 16:26:14 -04:00
|
|
|
|
///////////////////////////////////////////////////////////////////////////////
|
|
|
|
|
// Name: tests/strings/unicode.cpp
|
|
|
|
|
// Purpose: Unicode unit test
|
|
|
|
|
// Author: Vadim Zeitlin, Wlodzimierz ABX Skiba
|
|
|
|
|
// Created: 2004-04-28
|
|
|
|
|
// RCS-ID: $Id$
|
|
|
|
|
// Copyright: (c) 2004 Vadim Zeitlin, Wlodzimierz Skiba
|
|
|
|
|
///////////////////////////////////////////////////////////////////////////////
|
|
|
|
|
|
|
|
|
|
// ----------------------------------------------------------------------------
|
|
|
|
|
// headers
|
|
|
|
|
// ----------------------------------------------------------------------------
|
|
|
|
|
|
2004-11-22 00:00:19 -05:00
|
|
|
|
#include "testprec.h"
|
2004-04-30 16:26:14 -04:00
|
|
|
|
|
|
|
|
|
#ifdef __BORLANDC__
|
|
|
|
|
#pragma hdrstop
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef WX_PRECOMP
|
|
|
|
|
#endif // WX_PRECOMP
|
|
|
|
|
|
2006-03-31 12:42:26 -05:00
|
|
|
|
// ----------------------------------------------------------------------------
|
|
|
|
|
// local functions
|
|
|
|
|
// ----------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
#if wxUSE_WCHAR_T && !wxUSE_UNICODE
|
|
|
|
|
|
|
|
|
|
// in case wcscmp is missing
|
|
|
|
|
static int wx_wcscmp(const wchar_t *s1, const wchar_t *s2)
|
|
|
|
|
{
|
|
|
|
|
while (*s1 == *s2 && *s1 != 0)
|
|
|
|
|
{
|
|
|
|
|
s1++;
|
|
|
|
|
s2++;
|
|
|
|
|
}
|
|
|
|
|
return *s1 - *s2;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif // wxUSE_WCHAR_T && !wxUSE_UNICODE
|
|
|
|
|
|
2004-04-30 16:26:14 -04:00
|
|
|
|
// ----------------------------------------------------------------------------
|
|
|
|
|
// test class
|
|
|
|
|
// ----------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
class UnicodeTestCase : public CppUnit::TestCase
|
|
|
|
|
{
|
|
|
|
|
public:
|
|
|
|
|
UnicodeTestCase();
|
|
|
|
|
|
|
|
|
|
private:
|
|
|
|
|
CPPUNIT_TEST_SUITE( UnicodeTestCase );
|
|
|
|
|
CPPUNIT_TEST( ToFromAscii );
|
2006-03-31 12:10:07 -05:00
|
|
|
|
#if wxUSE_WCHAR_T
|
|
|
|
|
CPPUNIT_TEST( ConstructorsWithConversion );
|
|
|
|
|
CPPUNIT_TEST( Conversion );
|
|
|
|
|
CPPUNIT_TEST( ConversionUTF7 );
|
|
|
|
|
CPPUNIT_TEST( ConversionUTF8 );
|
|
|
|
|
#endif // wxUSE_WCHAR_T
|
2004-04-30 16:26:14 -04:00
|
|
|
|
CPPUNIT_TEST_SUITE_END();
|
|
|
|
|
|
|
|
|
|
void ToFromAscii();
|
2006-03-31 12:10:07 -05:00
|
|
|
|
#if wxUSE_WCHAR_T
|
|
|
|
|
void ConstructorsWithConversion();
|
|
|
|
|
void Conversion();
|
|
|
|
|
void ConversionUTF7();
|
|
|
|
|
void ConversionUTF8();
|
|
|
|
|
|
|
|
|
|
// test if converting s using the given encoding gives ws and vice versa
|
|
|
|
|
//
|
|
|
|
|
// if either of the first 2 arguments is NULL, the conversion is supposed
|
|
|
|
|
// to fail
|
|
|
|
|
void DoTestConversion(const char *s, const wchar_t *w, wxCSConv& conv);
|
|
|
|
|
#endif // wxUSE_WCHAR_T
|
|
|
|
|
|
2004-04-30 16:26:14 -04:00
|
|
|
|
|
|
|
|
|
DECLARE_NO_COPY_CLASS(UnicodeTestCase)
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
// register in the unnamed registry so that these tests are run by default
|
|
|
|
|
CPPUNIT_TEST_SUITE_REGISTRATION( UnicodeTestCase );
|
|
|
|
|
|
|
|
|
|
// also include in it's own registry so that these tests can be run alone
|
|
|
|
|
CPPUNIT_TEST_SUITE_NAMED_REGISTRATION( UnicodeTestCase, "UnicodeTestCase" );
|
|
|
|
|
|
|
|
|
|
UnicodeTestCase::UnicodeTestCase()
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void UnicodeTestCase::ToFromAscii()
|
|
|
|
|
{
|
|
|
|
|
|
|
|
|
|
#define TEST_TO_FROM_ASCII(txt) \
|
|
|
|
|
{ \
|
|
|
|
|
static const char *msg = txt; \
|
|
|
|
|
wxString s = wxString::FromAscii(msg); \
|
|
|
|
|
CPPUNIT_ASSERT( strcmp( s.ToAscii() , msg ) == 0 ); \
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
TEST_TO_FROM_ASCII( "Hello, world!" );
|
|
|
|
|
TEST_TO_FROM_ASCII( "additional \" special \t test \\ component \n :-)" );
|
|
|
|
|
}
|
|
|
|
|
|
2006-03-31 12:10:07 -05:00
|
|
|
|
#if wxUSE_WCHAR_T
|
|
|
|
|
void UnicodeTestCase::ConstructorsWithConversion()
|
|
|
|
|
{
|
|
|
|
|
// the string "D<>j<EFBFBD>" in UTF-8 and wchar_t:
|
|
|
|
|
const unsigned char utf8Buf[] = {0x44,0xC3,0xA9,0x6A,0xC3,0xA0,0};
|
|
|
|
|
const wchar_t wchar[] = {0x44,0xE9,0x6A,0xE0,0};
|
|
|
|
|
const unsigned char utf8subBuf[] = {0x44,0xC3,0xA9,0x6A,0}; // just "D<>j"
|
|
|
|
|
const char *utf8 = (char *)utf8Buf;
|
|
|
|
|
const char *utf8sub = (char *)utf8subBuf;
|
|
|
|
|
|
|
|
|
|
wxString s1(utf8, wxConvUTF8);
|
|
|
|
|
wxString s2(wchar, wxConvUTF8);
|
|
|
|
|
|
|
|
|
|
#if wxUSE_UNICODE
|
|
|
|
|
CPPUNIT_ASSERT( s1 == wchar );
|
|
|
|
|
CPPUNIT_ASSERT( s2 == wchar );
|
|
|
|
|
#else
|
|
|
|
|
CPPUNIT_ASSERT( s1 == utf8 );
|
|
|
|
|
CPPUNIT_ASSERT( s2 == utf8 );
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
wxString sub(utf8sub, wxConvUTF8); // "Dej" substring
|
|
|
|
|
wxString s3(utf8, wxConvUTF8, 4);
|
|
|
|
|
wxString s4(wchar, wxConvUTF8, 3);
|
|
|
|
|
|
|
|
|
|
CPPUNIT_ASSERT( s3 == sub );
|
|
|
|
|
CPPUNIT_ASSERT( s4 == sub );
|
|
|
|
|
|
|
|
|
|
#if wxUSE_UNICODE
|
|
|
|
|
CPPUNIT_ASSERT ( wxString("\t[pl]open.format.Sformatuj dyskietk<74>=gfloppy %f",
|
|
|
|
|
wxConvUTF8) == wxT("") ); //should stop at pos 35
|
|
|
|
|
#endif
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void UnicodeTestCase::Conversion()
|
|
|
|
|
{
|
|
|
|
|
#if wxUSE_UNICODE
|
2006-03-31 14:24:23 -05:00
|
|
|
|
static const size_t lenNulString = 10;
|
|
|
|
|
|
|
|
|
|
wxString szTheString(L"The\0String", wxConvLibc, lenNulString);
|
2006-03-31 12:10:07 -05:00
|
|
|
|
wxCharBuffer theBuffer = szTheString.mb_str();
|
|
|
|
|
|
2006-03-31 14:24:23 -05:00
|
|
|
|
CPPUNIT_ASSERT( memcmp(theBuffer.data(), "The\0String",
|
|
|
|
|
lenNulString + 1) == 0 );
|
2006-03-31 12:10:07 -05:00
|
|
|
|
|
2006-03-31 14:24:23 -05:00
|
|
|
|
wxString szTheString2("The\0String", wxConvLocal, lenNulString);
|
|
|
|
|
CPPUNIT_ASSERT_EQUAL( lenNulString, szTheString2.length() );
|
|
|
|
|
CPPUNIT_ASSERT( wxTmemcmp(szTheString2.c_str(), L"The\0String",
|
|
|
|
|
lenNulString + 1) == 0 );
|
2006-03-31 12:10:07 -05:00
|
|
|
|
#else
|
|
|
|
|
wxString szTheString(wxT("TheString"));
|
|
|
|
|
szTheString.insert(3, 1, '\0');
|
|
|
|
|
wxWCharBuffer theBuffer = szTheString.wc_str(wxConvLibc);
|
|
|
|
|
|
|
|
|
|
CPPUNIT_ASSERT( memcmp(theBuffer.data(), L"The\0String", 11 * sizeof(wchar_t)) == 0 );
|
|
|
|
|
|
|
|
|
|
wxString szLocalTheString(wxT("TheString"));
|
|
|
|
|
szLocalTheString.insert(3, 1, '\0');
|
|
|
|
|
wxWCharBuffer theLocalBuffer = szLocalTheString.wc_str(wxConvLocal);
|
|
|
|
|
|
|
|
|
|
CPPUNIT_ASSERT( memcmp(theLocalBuffer.data(), L"The\0String", 11 * sizeof(wchar_t)) == 0 );
|
|
|
|
|
#endif
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
UnicodeTestCase::DoTestConversion(const char *s,
|
2006-03-31 12:42:26 -05:00
|
|
|
|
const wchar_t *ws,
|
|
|
|
|
wxCSConv& conv)
|
2006-03-31 12:10:07 -05:00
|
|
|
|
{
|
|
|
|
|
#if wxUSE_UNICODE
|
|
|
|
|
if ( ws )
|
|
|
|
|
{
|
|
|
|
|
wxCharBuffer buf(wxString(ws).mb_str(conv));
|
|
|
|
|
|
|
|
|
|
CPPUNIT_ASSERT( strcmp(buf, s) == 0 );
|
|
|
|
|
}
|
|
|
|
|
#else // wxUSE_UNICODE
|
|
|
|
|
if ( s )
|
|
|
|
|
{
|
|
|
|
|
wxWCharBuffer wbuf(wxString(s).wc_str(conv));
|
|
|
|
|
|
|
|
|
|
if ( ws )
|
|
|
|
|
CPPUNIT_ASSERT( wx_wcscmp(wbuf, ws) == 0 );
|
|
|
|
|
else
|
|
|
|
|
CPPUNIT_ASSERT( !*wbuf );
|
|
|
|
|
}
|
|
|
|
|
#endif // wxUSE_UNICODE/!wxUSE_UNICODE
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
struct StringConversionData
|
|
|
|
|
{
|
|
|
|
|
const char *str;
|
|
|
|
|
const wchar_t *wcs;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
void UnicodeTestCase::ConversionUTF7()
|
|
|
|
|
{
|
|
|
|
|
static const StringConversionData utf7data[] =
|
|
|
|
|
{
|
|
|
|
|
{ "+-", L"+" },
|
|
|
|
|
{ "+--", L"+-" },
|
2006-03-31 12:42:26 -05:00
|
|
|
|
|
|
|
|
|
#ifdef wxHAVE_U_ESCAPE
|
2006-03-31 12:10:07 -05:00
|
|
|
|
{ "+AKM-", L"\u00a3" },
|
2006-03-31 12:42:26 -05:00
|
|
|
|
#endif // wxHAVE_U_ESCAPE
|
|
|
|
|
|
|
|
|
|
// the following are invalid UTF-7 sequences
|
2006-03-31 12:10:07 -05:00
|
|
|
|
{ "+", NULL },
|
2006-03-31 12:42:26 -05:00
|
|
|
|
{ "a+", NULL },
|
2006-03-31 12:10:07 -05:00
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
wxCSConv conv(_T("utf-7"));
|
|
|
|
|
for ( size_t n = 0; n < WXSIZEOF(utf7data); n++ )
|
|
|
|
|
{
|
|
|
|
|
const StringConversionData& d = utf7data[n];
|
|
|
|
|
DoTestConversion(d.str, d.wcs, conv);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void UnicodeTestCase::ConversionUTF8()
|
|
|
|
|
{
|
|
|
|
|
static const StringConversionData utf8data[] =
|
|
|
|
|
{
|
|
|
|
|
//\u isn't recognized on MSVC 6
|
2006-03-31 12:42:26 -05:00
|
|
|
|
#ifdef wxHAVE_U_ESCAPE
|
2006-03-31 12:10:07 -05:00
|
|
|
|
{ "\xc2\xa3", L"\u00a3" },
|
|
|
|
|
#endif
|
|
|
|
|
{ "\xc2", NULL },
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
wxCSConv conv(_T("utf-8"));
|
|
|
|
|
for ( size_t n = 0; n < WXSIZEOF(utf8data); n++ )
|
|
|
|
|
{
|
|
|
|
|
const StringConversionData& d = utf8data[n];
|
|
|
|
|
DoTestConversion(d.str, d.wcs, conv);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif // wxUSE_WCHAR_T
|
|
|
|
|
|