codecvt本地化库学习

此标头是本地化库的一部分。该头文件包括3个类，codecvt_utf8,codecvt_utf16, codecvt_utf8_utf16三个类，本篇介绍这三个类的一些用法。

成员函数

out	调用 do_out (std::codecvt<InternT,ExternT,StateT> 的公开成员函数)
in	调用 do_in (std::codecvt<InternT,ExternT,StateT> 的公开成员函数)
unshift	调用 do_unshift (std::codecvt<InternT,ExternT,StateT> 的公开成员函数)
encoding	调用 do_encoding (std::codecvt<InternT,ExternT,StateT> 的公开成员函数)
always_noconv	调用 do_always_noconv (std::codecvt<InternT,ExternT,StateT> 的公开成员函数)
length	调用 do_length (std::codecvt<InternT,ExternT,StateT> 的公开成员函数)
max_length	调用 do_max_length (std::codecvt<InternT,ExternT,StateT> 的公开成员函数)

示例代码：

#include <iostream>       // std::wcout, std::wcout 
#include <codecvt>
#include <fstream>

#include <locale>         // std::locale, std::codecvt, std::use_facet
#include <string>         // std::wstring
#include <cwchar>         // std::mbstate_t

int main()
{
	// codecvt::in example
	typedef std::codecvt<wchar_t, char, std::mbstate_t> facet_type;
	std::locale mylocale;
	const facet_type& myfacet = std::use_facet<facet_type>(mylocale);
	const char mystr[] = "Test string";
	// prepare objects to be filled by codecvt::in :
	wchar_t pwstr[sizeof(mystr)];              // the destination buffer (might be too short)
	std::mbstate_t mystate = std::mbstate_t(); // the shift state object
	const char* pc;                            // from_next
	wchar_t* pwc;                              // to_next

	// translate characters:
	facet_type::result myresult = myfacet.in(mystate,
		mystr, mystr + sizeof(mystr), pc,
		pwstr, pwstr + sizeof(mystr), pwc);

	if (myresult == facet_type::ok)
	{
		std::wcout << L"Translation successful: ";
		std::wcout << pwstr << std::endl;
	}

	// codecvt::out example
	typedef std::codecvt<wchar_t, char, std::mbstate_t> facet_type2;

	std::locale mylocale2;

	const facet_type2& myfacet2 = std::use_facet<facet_type2>(mylocale2);

	std::wstring mywstring2;
	std::cout << "Enter sentence: ";
	std::getline(std::wcin, mywstring2);

	std::wstring::size_type length2 = mywstring2.length();

	// prepare objects to be filled by codecvt::out :
	char* pstr2 = new char[length2 + 1];           // the destination buffer (might be too short)
	std::mbstate_t mystate2 = std::mbstate_t(); // the shift state object
	const wchar_t* pwc2;                        // from_next
	char* pc2;                                  // to_next

	// call codecvt::out (translate characters):
	facet_type::result myresult2 = myfacet2.out(mystate2,
		mywstring2.c_str(), mywstring2.c_str() + length2 + 1, pwc2,
		pstr2, pstr2 + length2 + 1, pc2);

	if (myresult2 == facet_type2::ok)
		std::cout << "Translation successful: " << pstr2 << '\n';

	delete[] pstr2;

	// codecvt::always_noconv example
	std::locale loc3;
	std::cout << std::boolalpha;
	std::cout << "always_noconv for codecvt<char,char,mbstate_t>: ";
	std::cout << std::use_facet<std::codecvt<char, char, mbstate_t> >(loc3).always_noconv();
	std::cout << '\n';
	std::cout << "always_noconv for codecvt<wchar_t,char,mbstate_t>: ";
	std::cout << std::use_facet<std::codecvt<wchar_t, char, mbstate_t> >(loc3).always_noconv();
	std::cout << '\n';

	// codecvt::encoding example
	std::locale loc4;
	const std::codecvt<wchar_t, char, mbstate_t>& myfacet4 = std::use_facet<std::codecvt<wchar_t, char, mbstate_t> >(loc4);
	std::cout << "Characteristics of codecvt<wchar_t,char,mbstate_t>:\n";
	std::cout << "Encoding: " << myfacet4.encoding() << '\n';
	std::cout << "Always noconv: " << myfacet4.always_noconv() << '\n';
	std::cout << "Max length: " << myfacet4.max_length() << '\n';

	// codecvt::length example
	typedef std::codecvt<wchar_t, char, std::mbstate_t> facet_type5;
	std::locale loc5;
	const facet_type& myfacet5 = std::use_facet<facet_type5>(loc5);
	const char source[] = "abcdefghijklmnopqrstuvwxyz";
	// prepare objects for codecvt::length:
	std::mbstate_t mystate5;
	const char *pc5;
	wchar_t *pwc5;
	// calculate length of dest (max 30):
	std::size_t length5 = myfacet5.length(mystate5, source, source + sizeof(source), 30);
	wchar_t* dest = new wchar_t[length5];
	myfacet5.in(mystate5, source, source + sizeof(source), pc5, dest, dest + length5, pwc5);
	std::wcout << dest << std::endl;

	delete[] dest;

	// codecvt::max_length example
	std::locale loc6;
	std::cout << "max_length for codecvt<char,char,mbstate_t>: ";
	std::cout << std::use_facet<std::codecvt<char, char, mbstate_t> >(loc6).max_length();
	std::cout << '\n';
	std::cout << "max_length for codecvt<wchar_t,char,mbstate_t>: ";
	std::cout << std::use_facet<std::codecvt<wchar_t, char, mbstate_t> >(loc6).max_length();
	std::cout << '\n';

    return 0;
}

运行结果：

参考：

https://cplusplus.com/reference/codecvt/codecvt_utf8/

https://cplusplus.com/reference/codecvt/codecvt_utf16/

https://cplusplus.com/reference/codecvt/codecvt_utf8_utf16/

https://zh.cppreference.com/w/cpp/header/codecvt