std::u32string conversion to/from std::string and std::u16string
If you read the documentation at CppReference.com for wstring_convert
, codecvt_utf8
, codecvt_utf16
, and codecvt_utf8_utf16
, the pages include a table that tells you exactly what you can use for the various UTF conversions.
And yes, you would use std::wstring_convert
to facilitate the conversion between the various UTFs. Despite its name, it is not limited to just std::wstring
, it actually operates with any std::basic_string
type (which std::string
, std::wstring
, and std::uXXstring
are all based on).
Class template std::wstring_convert performs conversions between byte string
std::string
and wide stringstd::basic_string<Elem>
, using an individual code conversion facet Codecvt. std::wstring_convert assumes ownership of the conversion facet, and cannot use a facet managed by a locale. The standard facets suitable for use with std::wstring_convert are std::codecvt_utf8 for UTF-8/UCS2 and UTF-8/UCS4 conversions and std::codecvt_utf8_utf16 for UTF-8/UTF-16 conversions.
For example:
typedef std::string u8string;u8string To_UTF8(const std::u16string &s){ std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> conv; return conv.to_bytes(s);}u8string To_UTF8(const std::u32string &s){ std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> conv; return conv.to_bytes(s);}std::u16string To_UTF16(const u8string &s){ std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> conv; return conv.from_bytes(s);}std::u16string To_UTF16(const std::u32string &s){ std::wstring_convert<std::codecvt_utf16<char32_t>, char32_t> conv; std::string bytes = conv.to_bytes(s); return std::u16string(reinterpret_cast<const char16_t*>(bytes.c_str()), bytes.length()/sizeof(char16_t));}std::u32string To_UTF32(const u8string &s){ std::wstring_convert<codecvt_utf8<char32_t>, char32_t> conv; return conv.from_bytes(s);}std::u32string To_UTF32(const std::u16string &s){ const char16_t *pData = s.c_str(); std::wstring_convert<std::codecvt_utf16<char32_t>, char32_t> conv; return conv.from_bytes(reinterpret_cast<const char*>(pData), reinterpret_cast<const char*>(pData+s.length()));}