how to compare wide characters "H2Oリテイリング" and "Ｈ2Ｏリテイリング"

Question

I am trying to compare some strings which are similar, for example:

1. The comparison of strings "H2Oリテイリング" and "Ｈ2Ｏリテイリング" should return true

2. The comparison of strings "Ｈ２Ｏリテイリング" and "Ｈ2Ｏリテイリング" should return true

I will get these strings by TCHAR array. Is there any way to compare these type of strings?

I tried by compare using character by character, but it doesn't work.

#define MAX_STRING 256
bool IsStringsEqual(TCHAR* str1, TCHAR* str2)
{
    if (_tcscmp(str1, str2) == 0)
        return true;
    else
        return false;   
}

int _tmain(int argc, _TCHAR* argv[])
{
    TCHAR original [MAX_STRING];
    ZeroMemory(original, sizeof(TCHAR) * MAX_STRING);
    _stprintf_s(original, TEXT("%s"), _T("Ｈ2Ｏリテイリング㈱"));

    TCHAR str1[MAX_STRING];
    ZeroMemory(str1, sizeof(TCHAR) * MAX_STRING);
    _stprintf_s(str1, TEXT("%s"), _T("H2Oリテイリング㈱"));
    if (IsStringsEqual(original,str1))
        wcout << endl << " Equal";

    TCHAR str2[MAX_STRING];
    ZeroMemory(str2, sizeof(TCHAR) * MAX_STRING);
    _stprintf_s(str2, TEXT("%s"), _T("Ｈ2Ｏリテイリング㈱"));
    if (IsStringsEqual(original, str2))
        wcout << endl << " Equal";

    TCHAR str3[MAX_STRING];
    ZeroMemory(str3, sizeof(TCHAR) * MAX_STRING);
    _stprintf_s(str3, TEXT("%s"), _T("Ｈ２Ｏリテイリング㈱"));
    if (IsStringsEqual(original, str3))
        wcout <<endl<< " Equal";

    return 0;
}

I'm expecting it to print Equal for all of the above comparisons.

Answer 1

It looks like what you're looking for is the Unicode Compatibility normalized forms. You can achieve it by using NormalizeString prior to the comparison (the code doesn't handle errors, and strings that don't fit):

bool IsStringsEqual(wchar_t* str1, wchar_t* str2)
{
    wchar_t buf1[MAX_STRING], buf2[MAX_STRING];
    NormalizeString(NormalizationKD, str1, -1, buf1, MAX_STRING);
    NormalizeString(NormalizationKD, str2, -1, buf2, MAX_STRING);
    return wcscmp(buf1, buf2) == 0;
}