根据cppref,operator <<
接受std::basic_ostream<wchar_t>
的{{1}}重载。似乎转换操作只是将每个const char*
扩展为char
。也就是说,转换(插入)的宽字符数等于窄字符数。所以这是一个问题。窄字符串可能使用GB2312编码国际字符,例如中文字符。进一步假设wchar_t
为sizeof(wchar_t)
并使用UTF16编码。那么这种天真的字符转换方法应该如何运作?
答案 0 :(得分:0)
我刚刚在Visual Studio 2015中检查过你是对的。 char
只会在没有任何转化的情况下扩展为wchar_t
秒。在我看来,你必须自己将窄字符串转换为宽字符串。有几种方法可以做到,有些方法已经提出过了。
这里我建议您可以使用纯C ++工具来完成它,假设您的C ++编译器和标准库足够完整(Visual Studio,或Linux上的GCC(仅在那里)):< / p>
void clear_mbstate (std::mbstate_t & mbs);
void
towstring_internal (std::wstring & outstr, const char * src, std::size_t size,
std::locale const & loc)
{
if (size == 0)
{
outstr.clear ();
return;
}
typedef std::codecvt<wchar_t, char, std::mbstate_t> CodeCvt;
const CodeCvt & cdcvt = std::use_facet<CodeCvt>(loc);
std::mbstate_t state;
clear_mbstate (state);
char const * from_first = src;
std::size_t const from_size = size;
char const * const from_last = from_first + from_size;
char const * from_next = from_first;
std::vector<wchar_t> dest (from_size);
wchar_t * to_first = &dest.front ();
std::size_t to_size = dest.size ();
wchar_t * to_last = to_first + to_size;
wchar_t * to_next = to_first;
CodeCvt::result result;
std::size_t converted = 0;
while (true)
{
result = cdcvt.in (
state, from_first, from_last,
from_next, to_first, to_last,
to_next);
// XXX: Even if only half of the input has been converted the
// in() method returns CodeCvt::ok. I think it should return
// CodeCvt::partial.
if ((result == CodeCvt::partial || result == CodeCvt::ok)
&& from_next != from_last)
{
to_size = dest.size () * 2;
dest.resize (to_size);
converted = to_next - to_first;
to_first = &dest.front ();
to_last = to_first + to_size;
to_next = to_first + converted;
continue;
}
else if (result == CodeCvt::ok && from_next == from_last)
break;
else if (result == CodeCvt::error
&& to_next != to_last && from_next != from_last)
{
clear_mbstate (state);
++from_next;
from_first = from_next;
*to_next = L'?';
++to_next;
to_first = to_next;
}
else
break;
}
converted = to_next - &dest[0];
outstr.assign (dest.begin (), dest.begin () + converted);
}
void
clear_mbstate (std::mbstate_t & mbs)
{
// Initialize/clear mbstate_t type.
// XXX: This is just a hack that works. The shape of mbstate_t varies
// from single unsigned to char[128]. Without some sort of initialization
// the codecvt::in/out methods randomly fail because the initial state is
// random/invalid.
std::memset (&mbs, 0, sizeof (std::mbstate_t));
}
此功能是log4cplus库的一部分,它可以工作。它使用codecvt
构面进行转换。您必须正确设置locale
。
Visual Studio可能会出现问题,为您提供适当的GB2312语言环境设置。您可能必须使用_setmbcp()
才能使其正常工作。有关详细信息,请参阅“double byte character sequence conversion issue in Visual Studio 2015”。