How do you properly use WideCharToMultiByte

Solution 1:

Here's a couple of functions (based on Brian Bondy's example) that use WideCharToMultiByte and MultiByteToWideChar to convert between std::wstring and std::string using utf8 to not lose any data.

// Convert a wide Unicode string to an UTF8 string
std::string utf8_encode(const std::wstring &wstr)
{
    if( wstr.empty() ) return std::string();
    int size_needed = WideCharToMultiByte(CP_UTF8, 0, &wstr[0], (int)wstr.size(), NULL, 0, NULL, NULL);
    std::string strTo( size_needed, 0 );
    WideCharToMultiByte                  (CP_UTF8, 0, &wstr[0], (int)wstr.size(), &strTo[0], size_needed, NULL, NULL);
    return strTo;
}

// Convert an UTF8 string to a wide Unicode String
std::wstring utf8_decode(const std::string &str)
{
    if( str.empty() ) return std::wstring();
    int size_needed = MultiByteToWideChar(CP_UTF8, 0, &str[0], (int)str.size(), NULL, 0);
    std::wstring wstrTo( size_needed, 0 );
    MultiByteToWideChar                  (CP_UTF8, 0, &str[0], (int)str.size(), &wstrTo[0], size_needed);
    return wstrTo;
}

Solution 2:

Elaborating on the answer provided by Brian R. Bondy: Here's an example that shows why you can't simply size the output buffer to the number of wide characters in the source string:

#include <windows.h>
#include <stdio.h>
#include <wchar.h>
#include <string.h>

/* string consisting of several Asian characters */
wchar_t wcsString[] = L"\u9580\u961c\u9640\u963f\u963b\u9644";

int main() 
{

    size_t wcsChars = wcslen( wcsString);

    size_t sizeRequired = WideCharToMultiByte( 950, 0, wcsString, -1, 
                                               NULL, 0,  NULL, NULL);

    printf( "Wide chars in wcsString: %u\n", wcsChars);
    printf( "Bytes required for CP950 encoding (excluding NUL terminator): %u\n",
             sizeRequired-1);

    sizeRequired = WideCharToMultiByte( CP_UTF8, 0, wcsString, -1,
                                        NULL, 0,  NULL, NULL);
    printf( "Bytes required for UTF8 encoding (excluding NUL terminator): %u\n",
             sizeRequired-1);
}

And the output:

Wide chars in wcsString: 6
Bytes required for CP950 encoding (excluding NUL terminator): 12
Bytes required for UTF8 encoding (excluding NUL terminator): 18

Solution 3:

You use the lpMultiByteStr [out] parameter by creating a new char array. You then pass this char array in to get it filled. You only need to initialize the length of the string + 1 so that you can have a null terminated string after the conversion.

Here are a couple of useful helper functions for you, they show the usage of all parameters.

#include <string>

std::string wstrtostr(const std::wstring &wstr)
{
    // Convert a Unicode string to an ASCII string
    std::string strTo;
    char *szTo = new char[wstr.length() + 1];
    szTo[wstr.size()] = '\0';
    WideCharToMultiByte(CP_ACP, 0, wstr.c_str(), -1, szTo, (int)wstr.length(), NULL, NULL);
    strTo = szTo;
    delete[] szTo;
    return strTo;
}

std::wstring strtowstr(const std::string &str)
{
    // Convert an ASCII string to a Unicode String
    std::wstring wstrTo;
    wchar_t *wszTo = new wchar_t[str.length() + 1];
    wszTo[str.size()] = L'\0';
    MultiByteToWideChar(CP_ACP, 0, str.c_str(), -1, wszTo, (int)str.length());
    wstrTo = wszTo;
    delete[] wszTo;
    return wstrTo;
}

--

Anytime in documentation when you see that it has a parameter which is a pointer to a type, and they tell you it is an out variable, you will want to create that type, and then pass in a pointer to it. The function will use that pointer to fill your variable.

So you can understand this better:

//pX is an out parameter, it fills your variable with 10.
void fillXWith10(int *pX)
{
  *pX = 10;
}

int main(int argc, char ** argv)
{
  int X;
  fillXWith10(&X);
  return 0;
}