C / C++ / MFC

DavidCrow wrote:

The problem is that a month does not have a constant value.

DavidCrow wrote:

Also, suppose you wanted to add three months to the date. Since February does not have 31 days, do you stop at February 28, or go 3 days into March? If the latter, it looks odd since March would then be four months away.

Cedric Moonen wrote:

But CPallini's answer is the way to go I suppose (didn't implement it yet).

COleDateTime AddMonths( const COleDateTime dt, const int nMonthsToAdd )
{
    COleDateTime    dateTemp;
    int             nMonth = (dt.GetMonth() - 1) + nMonthsToAdd,
                    nYear  = dt.GetYear(),                    
                    x = 0;
 
    dateTemp.SetStatus(COleDateTime::invalid);
 
    while (dateTemp.GetStatus() == COleDateTime::invalid && x < 4)
    {
        dateTemp.SetDateTime(nYear + (nMonth / 12), 
                             (nMonth % 12) + 1, 
                             dt.GetDay() - x, 
                             dt.GetHour(),
                             dt.GetMinute(),
                             dt.GetSecond());
 
        x++;
    }
 
    return dateTemp;
}

George_George wrote:

1. To get the wide character binary value, I use L"MÍST" and use debug mode to watch its internal buffer in Visual Studio.

George_George wrote:

To get the multibyte (UTF-8) binary value, I use WideCharacterToMultibyte API to convert L"MÍST" to multibyte value;

CPallini wrote:

Fine. Since wide chars are unsigned shorts, I'm sure you're also able to figure out how programmatically find the encoded values.

CPallini wrote:

but I think CP_UTF8 gives you have unmapped chars than Czech codepage (1250?))

George_George wrote:

How do you find the magic value numebr 1250, in some Windows header (.h) file?

CPallini wrote:

hence no need for you.

George_George wrote:

Why no need for me? If I need to change language settings to get the correct value, I have to and should change.

George_George wrote:

For the page you recommended before, there are two terms, SBCS and DBCS. When we map our term multibyte and wide character to them, is multibyte the same as SBCS and wide character the same as DBCS?

CPallini wrote:

When you use WideCharacterToMultibyte you must be aware that (of course) not all wide string characters can be mapped to the codepage you're specifying (I'm not an expert, but I think CP_UTF8 gives you have unmapped chars than Czech codepage (1250?)

George_George wrote:

For the same wide character string in Czech, I am not sure whether converting to Czech codepage (1250) or CP_UTF8 will making information lose ... i.e. resulting in ?? (0x3F) character.

Nemanja Trifunovic wrote:

If you don't know for sure the wide string contains only Central Europian characters, you can still safely convert to UTF-8, but not to CP1250.

George_George wrote:

But why not safe with CP1250?

Nemanja Trifunovic wrote:

here is 1-1 mapping between UTF-16 (wide chars on Windows) and UTF-8 (both are simply different encoding forms for Unicode character set).

Nemanja Trifunovic wrote:

On the other hand, there is no 1-1 mapping between Unicode and CP1250.

CPallini wrote:

There is 1-1 mapping for the subset representing Czech characters, I suppose.