How to convert wstring into string?

Question

The question is how to convert wstring to string?

I have next example :

#include 
#include 

int main()
{
    std::wstr         


        

Answer 1

This solution is inspired in dk123's solution, but uses a locale dependent codecvt facet. The result is in locale encoded string instead of UTF-8 (if it is not set as locale):

std::string w2s(const std::wstring &var)
{
   static std::locale loc("");
   auto &facet = std::use_facet<std::codecvt<wchar_t, char, std::mbstate_t>>(loc);
   return std::wstring_convert<std::remove_reference<decltype(facet)>::type, wchar_t>(&facet).to_bytes(var);
}

std::wstring s2w(const std::string &var)
{
   static std::locale loc("");
   auto &facet = std::use_facet<std::codecvt<wchar_t, char, std::mbstate_t>>(loc);
   return std::wstring_convert<std::remove_reference<decltype(facet)>::type, wchar_t>(&facet).from_bytes(var);
}

I was searching for it, but I can't find it. Finally I found that I can get the right facet from std::locale using the std::use_facet() function with the right typename. Hope this helps.

Answer 2

Here is a worked-out solution based on the other suggestions:

#include <string>
#include <iostream>
#include <clocale>
#include <locale>
#include <vector>

int main() {
  std::setlocale(LC_ALL, "");
  const std::wstring ws = L"ħëłlö";
  const std::locale locale("");
  typedef std::codecvt<wchar_t, char, std::mbstate_t> converter_type;
  const converter_type& converter = std::use_facet<converter_type>(locale);
  std::vector<char> to(ws.length() * converter.max_length());
  std::mbstate_t state;
  const wchar_t* from_next;
  char* to_next;
  const converter_type::result result = converter.out(state, ws.data(), ws.data() + ws.length(), from_next, &to[0], &to[0] + to.size(), to_next);
  if (result == converter_type::ok or result == converter_type::noconv) {
    const std::string s(&to[0], to_next);
    std::cout <<"std::string =     "<<s<<std::endl;
  }
}

This will usually work for Linux, but will create problems on Windows.

Answer 3

In case anyone else is interested: I needed a class that could be used interchangeably wherever either a string or wstring was expected. The following class convertible_string, based on dk123's solution, can be initialized with either a string, char const*, wstring or wchar_t const* and can be assigned to by or implicitly converted to either a string or wstring (so can be passed into a functions that take either).

class convertible_string
{
public:
    // default ctor
    convertible_string()
    {}

    /* conversion ctors */
    convertible_string(std::string const& value) : value_(value)
    {}
    convertible_string(char const* val_array) : value_(val_array)
    {}
    convertible_string(std::wstring const& wvalue) : value_(ws2s(wvalue))
    {}
    convertible_string(wchar_t const* wval_array) : value_(ws2s(std::wstring(wval_array)))
    {}

    /* assignment operators */
    convertible_string& operator=(std::string const& value)
    {
        value_ = value;
        return *this;
    }
    convertible_string& operator=(std::wstring const& wvalue)
    {
        value_ = ws2s(wvalue);
        return *this;
    }

    /* implicit conversion operators */
    operator std::string() const { return value_; }
    operator std::wstring() const { return s2ws(value_); }
private:
    std::string value_;
};

Answer 4

Default encoding on:

• Windows UTF-16.
• Linux UTF-8.
• MacOS UTF-8.

This code have two forms to convert std::string to std::wstring and std::wstring to std::string. If you negate #if defined WIN32, you get the same result.

1. std::string to std::wstring

• MultiByteToWideChar WinAPI

• _mbstowcs_s_l

#if defined WIN32
#include <windows.h>
#endif

std::wstring StringToWideString(std::string str)
{
    if (str.empty())
    {
        return std::wstring();
    }
    size_t len = str.length() + 1;
    std::wstring ret = std::wstring(len, 0);
#if defined WIN32
    int size = MultiByteToWideChar(CP_UTF8, MB_ERR_INVALID_CHARS, &str[0], str.size(), &ret[0], len);
    ret.resize(size);
#else
    size_t size = 0;
    _locale_t lc = _create_locale(LC_ALL, "en_US.UTF-8");
    errno_t retval = _mbstowcs_s_l(&size, &ret[0], len, &str[0], _TRUNCATE, lc);
    _free_locale(lc);
    ret.resize(size - 1);
#endif
    return ret;
}

2. std::wstring to std::string

• WideCharToMultiByte WinAPI

• _wcstombs_s_l

std::string WidestringToString(std::wstring wstr)
{
    if (wstr.empty())
    {
        return std::string();
    }
#if defined WIN32
    int size = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS, &wstr[0], wstr.size(), NULL, 0, NULL, NULL);
    std::string ret = std::string(size, 0);
    WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS, &wstr[0], wstr.size(), &ret[0], size, NULL, NULL);
#else
    size_t size = 0;
    _locale_t lc = _create_locale(LC_ALL, "en_US.UTF-8");
    errno_t err = _wcstombs_s_l(&size, NULL, 0, &wstr[0], _TRUNCATE, lc);
    std::string ret = std::string(size, 0);
    err = _wcstombs_s_l(&size, &ret[0], size, &wstr[0], _TRUNCATE, lc);
    _free_locale(lc);
    ret.resize(size - 1);
#endif
    return ret;
}

3. On windows you need to print unicode, using WinAPI.

• WriteConsole

#if defined _WIN32
    void WriteLineUnicode(std::string s)
    {
        std::wstring unicode = StringToWideString(s);
        WriteConsole(GetStdHandle(STD_OUTPUT_HANDLE), unicode.c_str(), unicode.length(), NULL, NULL);
        std::cout << std::endl;
    }

    void WriteUnicode(std::string s)
    {
        std::wstring unicode = StringToWideString(s);
        WriteConsole(GetStdHandle(STD_OUTPUT_HANDLE), unicode.c_str(), unicode.length(), NULL, NULL);
    }

    void WriteLineUnicode(std::wstring ws)
    {
        WriteConsole(GetStdHandle(STD_OUTPUT_HANDLE), ws.c_str(), ws.length(), NULL, NULL);
        std::cout << std::endl;
    }

    void WriteUnicode(std::wstring ws)
    {
        WriteConsole(GetStdHandle(STD_OUTPUT_HANDLE), ws.c_str(), ws.length(), NULL, NULL);
    }

4. On main program.

#if defined _WIN32
int wmain(int argc, WCHAR ** args)
#else
int main(int argc, CHAR ** args)
#endif
{
    std::string source = u8"ÜüΩωЙ你月曜日\na                                                                    

                                                        
            

Answer 5

// Embarcadero C++ Builder 

// convertion string to wstring
string str1 = "hello";
String str2 = str1;         // typedef UnicodeString String;   -> str2 contains now u"hello";

// convertion wstring to string
String str2 = u"hello";
string str1 = UTF8string(str2).c_str();   // -> str1 contains now "hello"