Question

all the while, I am using setw for my ANSI text file alignment. Recently, I want to support UTF-8 in my text file. I found out that setw no longer work.

#include <windows.h>
#include <iostream>
// For StringCchLengthW.
#include <Strsafe.h>
#include <fstream>
#include <iomanip>
#include <string>
#include <cassert>

std::string wstring2string(const std::wstring& utf16_unicode) {
    //
    // Special case of NULL or empty input string
    //
    if ( (utf16_unicode.c_str() == NULL) || (*(utf16_unicode.c_str()) == L'\0') )
    {
        // Return empty string
        return "";
    }

    //
    // Consider WCHAR's count corresponding to total input string length,
    // including end-of-string (L'\0') character.
    //
    const size_t cchUTF16Max = INT_MAX - 1;
    size_t cchUTF16;
    HRESULT hr = ::StringCchLengthW( utf16_unicode.c_str(), cchUTF16Max, &cchUTF16 );

    if ( FAILED( hr ) )
    {
        throw std::exception("Error during wstring2string");
    }

    // Consider also terminating \0
    ++cchUTF16;

    //
    // WC_ERR_INVALID_CHARS flag is set to fail if invalid input character
    // is encountered.
    // This flag is supported on Windows Vista and later.
    // Don't use it on Windows XP and previous.
    //

    // CHEOK : Under Windows XP VC 2008, WINVER is 0x0600.
    // If I use dwConversionFlags = WC_ERR_INVALID_CHARS, runtime error will
    // occur with last error code (1004, Invalid flags.)
//#if (WINVER >= 0x0600)
//    DWORD dwConversionFlags = WC_ERR_INVALID_CHARS;
//#else
    DWORD dwConversionFlags = 0;
//#endif

    //
    // Get size of destination UTF-8 buffer, in CHAR's (= bytes)
    //
    int cbUTF8 = ::WideCharToMultiByte(
        CP_UTF8,                // convert to UTF-8
        dwConversionFlags,      // specify conversion behavior
        utf16_unicode.c_str(),  // source UTF-16 string
        static_cast<int>( cchUTF16 ),   // total source string length, in WCHAR's,
                                        // including end-of-string \0
        NULL,                   // unused - no conversion required in this step
        0,                      // request buffer size
        NULL, NULL              // unused
        );

    assert( cbUTF8 != 0 );

    if ( cbUTF8 == 0 )
    {
        throw std::exception("Error during wstring2string");
    }

    //
    // Allocate destination buffer for UTF-8 string
    //
    int cchUTF8 = cbUTF8; // sizeof(CHAR) = 1 byte
    CHAR * pszUTF8 = new CHAR[cchUTF8];

    //
    // Do the conversion from UTF-16 to UTF-8
    //
    int result = ::WideCharToMultiByte(
        CP_UTF8,                // convert to UTF-8
        dwConversionFlags,      // specify conversion behavior
        utf16_unicode.c_str(),  // source UTF-16 string
        static_cast<int>( cchUTF16 ),   // total source string length, in WCHAR's,
                                        // including end-of-string \0
        pszUTF8,                // destination buffer
        cbUTF8,                 // destination buffer size, in bytes
        NULL, NULL              // unused
        ); 

    assert( result != 0 );

    if ( result == 0 )
    {
        throw std::exception("Error during wstring2string");
    }

    std::string strUTF8(pszUTF8);

    delete[] pszUTF8;

    // Return resulting UTF-8 string
    return strUTF8;
}

int main() {
    // Write the file content in UTF-8
    {
        std::ofstream file;
        file.open("c:\\A-UTF8.txt");
        file << std::setw(12) << std::left << wstring2string(L"我爱你") << "????" << std::endl;
        file << std::setw(12) << std::left << "ILU" << "????";
    }

    {
        std::ofstream file;
        file.open("c:\\A-ANSI.txt");
        file << std::setw(12) << std::left << "WTF" << "????" << std::endl;
        file << std::setw(12) << std::left << "ILU" << "????";
    }
    return 0;
}

My output for A-ANSI.txt is

WTF         ????
ILU         ????

My out put for A-UTF8.txt is

我爱你   ????
ILU         ????

How can I make A-UTF8.txt’s text aligned properly?

Answer 1

Even in a “monospaced” font, some East Asian characters are wider than others. You also have to consider combining characters, which have no width of their own.

There’s a wcswidth function that may do what you want.