X-Git-Url: https://git.saurik.com/wxWidgets.git/blobdiff_plain/3af0741ccc1eaaf3c115a92ccedf8c864101a4e3..4f2511d706e5274a34e1521e11c1b95fed735b42:/tests/mbconv/mbconvtest.cpp diff --git a/tests/mbconv/mbconvtest.cpp b/tests/mbconv/mbconvtest.cpp index 6d385495ef..b5d0185467 100644 --- a/tests/mbconv/mbconvtest.cpp +++ b/tests/mbconv/mbconvtest.cpp @@ -78,6 +78,7 @@ private: CPPUNIT_TEST( CP1252Tests ); // depends on UTF8 Decoder functioning correctly CPPUNIT_TEST( LibcTests ); CPPUNIT_TEST( IconvTests ); + CPPUNIT_TEST( Latin1Tests ); CPPUNIT_TEST( FontmapTests ); #ifdef HAVE_WCHAR_H CPPUNIT_TEST( UTF8_41 ); @@ -113,6 +114,7 @@ private: void LibcTests(); void FontmapTests(); void IconvTests(); + void Latin1Tests(); // verifies that the specified multibyte sequence decodes to the specified wchar_t sequence void TestDecoder( @@ -269,11 +271,11 @@ wxString CByteArrayFormat( const void* data, size_t len, const wxChar* name ) return result; } -// The following bytes represent the same string, containing Japanese and English +// The following bytes represent the same string, containing Japanese and English // characters, encoded in several different formats. // encoded by iconv -const static unsigned char welcome_utf7_iconv[84] = +const static unsigned char welcome_utf7_iconv[84] = { 0x57,0x65,0x6c,0x63,0x6f,0x6d,0x65,0x20,0x74,0x6f,0x20,0x6f,0x75,0x72,0x20,0x63, 0x79,0x62,0x65,0x72,0x20,0x73,0x70,0x61,0x63,0x65,0x20,0x66,0x6f,0x72,0x63,0x65, @@ -283,7 +285,7 @@ const static unsigned char welcome_utf7_iconv[84] = 0x57,0x54,0x41,0x43 }; // encoded by wxWindows (iconv can decode this successfully) -const static unsigned char welcome_utf7_wx[109] = +const static unsigned char welcome_utf7_wx[109] = { 0x57,0x65,0x6c,0x63,0x6f,0x6d,0x65,0x2b,0x41,0x43,0x41,0x2d,0x74,0x6f,0x2b,0x41, 0x43,0x41,0x2d,0x6f,0x75,0x72,0x2b,0x41,0x43,0x41,0x2d,0x63,0x79,0x62,0x65,0x72, @@ -294,7 +296,7 @@ const static unsigned char welcome_utf7_wx[109] = 0x51,0x77,0x52,0x44,0x42,0x6e,0x4d,0x46,0x6b,0x77,0x41,0x67,0x2d }; // encoded by iconv -const static unsigned char welcome_utf8[89] = +const static unsigned char welcome_utf8[89] = { 0x57,0x65,0x6c,0x63,0x6f,0x6d,0x65,0x20,0x74,0x6f,0x20,0x6f,0x75,0x72,0x20,0x63, 0x79,0x62,0x65,0x72,0x20,0x73,0x70,0x61,0x63,0x65,0x20,0x66,0x6f,0x72,0x63,0x65, @@ -304,7 +306,7 @@ const static unsigned char welcome_utf8[89] = 0xe3,0x81,0xa7,0xe3,0x81,0x99,0xe3,0x80,0x82 }; // encoded by iconv -const static unsigned char welcome_utf16le[106] = +const static unsigned char welcome_utf16le[106] = { 0x57,0x00,0x65,0x00,0x6c,0x00,0x63,0x00,0x6f,0x00,0x6d,0x00,0x65,0x00,0x20,0x00, 0x74,0x00,0x6f,0x00,0x20,0x00,0x6f,0x00,0x75,0x00,0x72,0x00,0x20,0x00,0x63,0x00, @@ -315,7 +317,7 @@ const static unsigned char welcome_utf16le[106] = 0x44,0x30,0x44,0x30,0x67,0x30,0x59,0x30,0x02,0x30 }; // encoded by iconv -const static unsigned char welcome_utf16be[106] = +const static unsigned char welcome_utf16be[106] = { 0x00,0x57,0x00,0x65,0x00,0x6c,0x00,0x63,0x00,0x6f,0x00,0x6d,0x00,0x65,0x00,0x20, 0x00,0x74,0x00,0x6f,0x00,0x20,0x00,0x6f,0x00,0x75,0x00,0x72,0x00,0x20,0x00,0x63, @@ -326,7 +328,7 @@ const static unsigned char welcome_utf16be[106] = 0x30,0x44,0x30,0x44,0x30,0x67,0x30,0x59,0x30,0x02 }; // encoded by iconv -const static unsigned char welcome_utf32le[212] = +const static unsigned char welcome_utf32le[212] = { 0x57,0x00,0x00,0x00,0x65,0x00,0x00,0x00,0x6c,0x00,0x00,0x00,0x63,0x00,0x00,0x00, 0x6f,0x00,0x00,0x00,0x6d,0x00,0x00,0x00,0x65,0x00,0x00,0x00,0x20,0x00,0x00,0x00, @@ -344,7 +346,7 @@ const static unsigned char welcome_utf32le[212] = 0x02,0x30,0x00,0x00 }; // encoded by iconv -const static unsigned char welcome_utf32be[212] = +const static unsigned char welcome_utf32be[212] = { 0x00,0x00,0x00,0x57,0x00,0x00,0x00,0x65,0x00,0x00,0x00,0x6c,0x00,0x00,0x00,0x63, 0x00,0x00,0x00,0x6f,0x00,0x00,0x00,0x6d,0x00,0x00,0x00,0x65,0x00,0x00,0x00,0x20, @@ -362,7 +364,7 @@ const static unsigned char welcome_utf32be[212] = 0x00,0x00,0x30,0x02 }; // encoded by iconv -const static unsigned char welcome_cp932[71] = +const static unsigned char welcome_cp932[71] = { 0x57,0x65,0x6c,0x63,0x6f,0x6d,0x65,0x20,0x74,0x6f,0x20,0x6f,0x75,0x72,0x20,0x63, 0x79,0x62,0x65,0x72,0x20,0x73,0x70,0x61,0x63,0x65,0x20,0x66,0x6f,0x72,0x63,0x65, @@ -387,45 +389,51 @@ const static unsigned char welcome_cp932[71] = void MBConvTestCase::UTF7Tests() { +#if 0 + wxCSConv convUTF7(wxFONTENCODING_UTF7); +#else + wxMBConvUTF7 convUTF7; +#endif + TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf7_iconv, - sizeof(welcome_utf7_iconv), - wxConvUTF7, + (const char*)welcome_utf7_iconv, + sizeof(welcome_utf7_iconv), + convUTF7, 1 ); TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf7_wx, - sizeof(welcome_utf7_wx), - wxConvUTF7, + (const char*)welcome_utf7_wx, + sizeof(welcome_utf7_wx), + convUTF7, 1 ); -#if 0 - // wxWidget's UTF-7 encoder generates different byte sequences than iconv's. +#if 0 + // wxWidget's UTF-7 encoder generates different byte sequences than iconv's. // but both seem to be equally legal. // This test won't work and that's okay. TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf7_iconv, - sizeof(welcome_utf7_iconv), - wxConvUTF7, + (const char*)welcome_utf7_iconv, + sizeof(welcome_utf7_iconv), + convUTF7, 1 ); #endif TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf7_wx, - sizeof(welcome_utf7_wx), - wxConvUTF7, + (const char*)welcome_utf7_wx, + sizeof(welcome_utf7_wx), + convUTF7, 1 ); } @@ -433,20 +441,20 @@ void MBConvTestCase::UTF7Tests() void MBConvTestCase::UTF8Tests() { TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf8, - sizeof(welcome_utf8), + (const char*)welcome_utf8, + sizeof(welcome_utf8), wxConvUTF8, 1 ); TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf8, - sizeof(welcome_utf8), + (const char*)welcome_utf8, + sizeof(welcome_utf8), wxConvUTF8, 1 ); @@ -456,20 +464,20 @@ void MBConvTestCase::UTF16LETests() { wxMBConvUTF16LE convUTF16LE; TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf16le, - sizeof(welcome_utf16le), + (const char*)welcome_utf16le, + sizeof(welcome_utf16le), convUTF16LE, 2 ); TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf16le, - sizeof(welcome_utf16le), + (const char*)welcome_utf16le, + sizeof(welcome_utf16le), convUTF16LE, 2 ); @@ -479,20 +487,20 @@ void MBConvTestCase::UTF16BETests() { wxMBConvUTF16BE convUTF16BE; TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf16be, - sizeof(welcome_utf16be), + (const char*)welcome_utf16be, + sizeof(welcome_utf16be), convUTF16BE, 2 ); TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf16be, - sizeof(welcome_utf16be), + (const char*)welcome_utf16be, + sizeof(welcome_utf16be), convUTF16BE, 2 ); @@ -502,20 +510,20 @@ void MBConvTestCase::UTF32LETests() { wxMBConvUTF32LE convUTF32LE; TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf32le, - sizeof(welcome_utf32le), + (const char*)welcome_utf32le, + sizeof(welcome_utf32le), convUTF32LE, 4 ); TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf32le, - sizeof(welcome_utf32le), + (const char*)welcome_utf32le, + sizeof(welcome_utf32le), convUTF32LE, 4 ); @@ -525,20 +533,20 @@ void MBConvTestCase::UTF32BETests() { wxMBConvUTF32BE convUTF32BE; TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf32be, - sizeof(welcome_utf32be), + (const char*)welcome_utf32be, + sizeof(welcome_utf32be), convUTF32BE, 4 ); TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_utf32be, - sizeof(welcome_utf32be), + (const char*)welcome_utf32be, + sizeof(welcome_utf32be), convUTF32BE, 4 ); @@ -548,27 +556,27 @@ void MBConvTestCase::CP932Tests() { wxCSConv convCP932( wxFONTENCODING_CP932 ); TestDecoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_cp932, - sizeof(welcome_cp932), + (const char*)welcome_cp932, + sizeof(welcome_cp932), convCP932, 1 ); TestEncoder - ( - (const wchar_t*)welcome_wchar_t, + ( + (const wchar_t*)welcome_wchar_t, sizeof(welcome_wchar_t)/sizeof(wchar_t), - (const char*)welcome_cp932, - sizeof(welcome_cp932), + (const char*)welcome_cp932, + sizeof(welcome_cp932), convCP932, 1 ); } // a character sequence encoded as iso8859-1 (iconv) -static const unsigned char iso8859_1[251] = +static const unsigned char iso8859_1[251] = { 0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0x10,0x11,0x12,0x13,0x14, 0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,0x20,0x21,0x22,0x23,0x24, @@ -588,7 +596,7 @@ static const unsigned char iso8859_1[251] = 0xf5,0xf6,0xf7,0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff }; // the above character sequence encoded as UTF-8 (iconv) -static const unsigned char iso8859_1_utf8[379] = +static const unsigned char iso8859_1_utf8[379] = { 0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0x10,0x11,0x12,0x13,0x14, 0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,0x20,0x21,0x22,0x23,0x24, @@ -617,7 +625,7 @@ static const unsigned char iso8859_1_utf8[379] = }; // a character sequence encoded as CP1252 (iconv) -static const unsigned char CP1252[246] = +static const unsigned char CP1252[246] = { 0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0x10,0x11,0x12,0x13,0x14, 0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,0x20,0x21,0x22,0x23,0x24, @@ -637,7 +645,7 @@ static const unsigned char CP1252[246] = 0x85,0x89,0x8b,0x9b,0x80,0x99 }; // the above character sequence encoded as UTF-8 (iconv) -static const unsigned char CP1252_utf8[386] = +static const unsigned char CP1252_utf8[386] = { 0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0x10,0x11,0x12,0x13,0x14, 0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,0x20,0x21,0x22,0x23,0x24, @@ -667,7 +675,7 @@ static const unsigned char CP1252_utf8[386] = }; // a character sequence encoded as iso8859-5 (iconv) -static const unsigned char iso8859_5[251] = +static const unsigned char iso8859_5[251] = { 0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0x10,0x11,0x12,0x13,0x14, 0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,0x20,0x21,0x22,0x23,0x24, @@ -687,7 +695,7 @@ static const unsigned char iso8859_5[251] = 0xf5,0xf6,0xf7,0xf8,0xf9,0xfa,0xfb,0xfc,0xfe,0xff,0xf0 }; // the above character sequence encoded as UTF-8 (iconv) -static const unsigned char iso8859_5_utf8[380] = +static const unsigned char iso8859_5_utf8[380] = { 0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0x10,0x11,0x12,0x13,0x14, 0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,0x20,0x21,0x22,0x23,0x24, @@ -757,19 +765,19 @@ void MBConvTestCase::TestCoder( size_t wideChars = wxWcslen( wideBuffer.data() ); TestDecoder - ( - wideBuffer.data(), + ( + wideBuffer.data(), wideChars, - (const char*)multiBuffer, + (const char*)multiBuffer, multiBytes, converter, sizeofNull ); TestEncoder - ( - wideBuffer.data(), + ( + wideBuffer.data(), wideChars, - (const char*)multiBuffer, + (const char*)multiBuffer, multiBytes, converter, sizeofNull @@ -822,6 +830,24 @@ void MBConvTestCase::IconvTests() #endif } +void MBConvTestCase::Latin1Tests() +{ + TestCoder( + (const char*)iso8859_1, + sizeof(iso8859_1), + (const char*)iso8859_1_utf8, + sizeof(iso8859_1_utf8), + wxConvISO8859_1, + 1 + ); + + static const char nulstr[] = "foo\0bar\0"; + static const size_t mbLen = WXSIZEOF(nulstr) - 1; + size_t wcLen; + wxWCharBuffer wbuf(wxConvISO8859_1.cMB2WC(nulstr, mbLen, &wcLen)); + CPPUNIT_ASSERT_EQUAL( mbLen, wcLen ); +} + void MBConvTestCase::CP1252Tests() { wxCSConv convCP1252( wxFONTENCODING_CP1252 ); @@ -857,9 +883,9 @@ void MBConvTestCase::LibcTests() #endif wxMBConvLibc convLibc; TestCoder( - (const char*)systemMB, + (const char*)systemMB, systemMB_size, - (const char*)systemMB_utf8, + (const char*)systemMB_utf8, systemMB_utf8_size, convLibc, 1 @@ -887,13 +913,13 @@ void MBConvTestCase::TestDecoder( // calculate the output size size_t outputWritten = converter.MB2WC - ( - 0, - (const char*)inputCopy.data(), + ( + 0, + (const char*)inputCopy.data(), 0 ); // make sure the correct output length was calculated - CPPUNIT_ASSERT( outputWritten == wideChars ); + CPPUNIT_ASSERT_EQUAL( wideChars, outputWritten ); // convert the string size_t guardChars = 8; // to make sure we're not overrunning the output buffer @@ -903,13 +929,13 @@ void MBConvTestCase::TestDecoder( memset( outputBuffer.data(), UNINITIALIZED, outputBufferChars*sizeof(wchar_t) ); outputWritten = converter.MB2WC - ( - outputBuffer.data(), - (const char*)inputCopy.data(), + ( + outputBuffer.data(), + (const char*)inputCopy.data(), outputBufferChars ); // make sure the correct number of characters were outputs - CPPUNIT_ASSERT( outputWritten == wideChars ); + CPPUNIT_ASSERT_EQUAL( wideChars, outputWritten ); // make sure the characters generated are correct CPPUNIT_ASSERT( 0 == memcmp( outputBuffer, wideBuffer, wideChars*sizeof(wchar_t) ) ); @@ -947,13 +973,13 @@ void MBConvTestCase::TestEncoder( // calculate the output size size_t outputWritten = converter.WC2MB - ( - 0, - (const wchar_t*)inputCopy.data(), + ( + 0, + (const wchar_t*)inputCopy.data(), 0 ); // make sure the correct output length was calculated - CPPUNIT_ASSERT( outputWritten == multiBytes ); + CPPUNIT_ASSERT_EQUAL( multiBytes, outputWritten ); // convert the string size_t guardBytes = 8; // to make sure we're not overrunning the output buffer @@ -962,14 +988,14 @@ void MBConvTestCase::TestEncoder( memset( outputBuffer.data(), UNINITIALIZED, outputBufferSize ); outputWritten = converter.WC2MB - ( - outputBuffer.data(), - (const wchar_t*)inputCopy.data(), - outputBufferSize + ( + outputBuffer.data(), + (const wchar_t*)inputCopy.data(), + outputBufferSize ); // make sure the correct number of characters were output - CPPUNIT_ASSERT( outputWritten == multiBytes ); + CPPUNIT_ASSERT_EQUAL( multiBytes, outputWritten ); // make sure the characters generated are correct CPPUNIT_ASSERT( 0 == memcmp( outputBuffer, multiBuffer, multiBytes ) ); @@ -1012,7 +1038,11 @@ void MBConvTestCase::TestStreamDecoder( for ( size_t i = 0; i < wideChars; i++ ) { wxChar wc = textInputStream.GetChar(); - CPPUNIT_ASSERT( wc == wideBuffer[i] ); + CPPUNIT_ASSERT_EQUAL_MESSAGE( + std::string(wxString::Format("At position %lu", (unsigned long)i)), + wideBuffer[i], + wc + ); } CPPUNIT_ASSERT( 0 == textInputStream.GetChar() ); CPPUNIT_ASSERT( memoryInputStream.Eof() ); @@ -1040,6 +1070,9 @@ void MBConvTestCase::TestStreamEncoder( { textOutputStream.PutChar( wideBuffer[i] ); } + + textOutputStream.Flush(); + CPPUNIT_ASSERT_EQUAL( (wxFileOffset)multiBytes, memoryOutputStream.TellO() ); wxCharBuffer copy( memoryOutputStream.TellO() ); memoryOutputStream.CopyTo( copy.data(), memoryOutputStream.TellO()); @@ -1093,7 +1126,7 @@ void MBConvTestCase::UTF8Octal(const char *charSequence, // static wchar_t *wx_wcscpy(wchar_t *dest, const wchar_t *src) { - wchar_t *d = dest; + wchar_t *d = dest; while ((*d++ = *src++) != 0) ; return dest; @@ -1103,7 +1136,7 @@ static wchar_t *wx_wcscpy(wchar_t *dest, const wchar_t *src) // static wchar_t *wx_wcscat(wchar_t *dest, const wchar_t *src) { - wchar_t *d = dest; + wchar_t *d = dest; while (*d) d++; while ((*d++ = *src++) != 0) @@ -1146,12 +1179,12 @@ void MBConvTestCase::UTF8(const char *charSequence, const size_t BUFSIZE = 128; wxASSERT(strlen(charSequence) * 3 + 10 < BUFSIZE); char bytes[BUFSIZE]; - + // include the option in the error messages so it's possible to see // which test failed sprintf(bytes, " (with option == %d)", option); std::string errmsg(bytes); - + // put the charSequence at the start, middle and end of a string strcpy(bytes, charSequence); strcat(bytes, "ABC");