3fbde9c195
Spirit were assuming that wchar_t is 32-bit and the content is UCS-4. It is wrong, the actual representation is implementation defined [lex.ccon]/6. However, on most Unix platforms this assumption is valid and gives the expected outcome, but on Windows wchar_t is 16-bit and the content is UTF-16.
29 lines
1.0 KiB
C++
29 lines
1.0 KiB
C++
/*=============================================================================
|
|
Copyright (c) 2018 Nikita Kniazev
|
|
|
|
Distributed under the Boost Software License, Version 1.0. (See accompanying
|
|
file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
|
|
=============================================================================*/
|
|
#include <boost/core/lightweight_test.hpp>
|
|
#include <boost/spirit/home/x3/support/utility/utf8.hpp>
|
|
|
|
int main()
|
|
{
|
|
using boost::spirit::x3::to_utf8;
|
|
|
|
// Assume wchar_t is 16-bit on Windows and 32-bit on Unix
|
|
#if defined(_WIN32) || defined(__CYGWIN__)
|
|
BOOST_TEST_CSTR_EQ("\xEF\xBF\xA1", to_utf8(L'\uFFE1').c_str());
|
|
#else
|
|
BOOST_TEST_CSTR_EQ("\xF0\x9F\xA7\x90", to_utf8(L'\U0001F9D0').c_str());
|
|
#endif
|
|
|
|
BOOST_TEST_CSTR_EQ("\xF0\x9F\xA7\x90\xF0\x9F\xA7\xA0",
|
|
to_utf8(L"\U0001F9D0\U0001F9E0").c_str());
|
|
|
|
BOOST_TEST_CSTR_EQ("\xF0\x9F\xA7\x90\xF0\x9F\xA7\xA0",
|
|
to_utf8(std::wstring(L"\U0001F9D0\U0001F9E0")).c_str());
|
|
|
|
return boost::report_errors();
|
|
}
|