Canonical way to parse the command line into arguments in plain C Windows API

Question

In a Windows program, what is the canonical way to parse the command line obtained from GetCommandLine into multiple arguments, similar to the argv array in Unix? It seems that CommandLineToArgvW does this for a Unicode command line, but I can't find a non-Unicode equivalent. Should I be using Unicode or not? If not, how do I parse the command line?

Answer 1

This article claims to provide an ANSI version of CommandLineToArgvW.

Answer 2

CommandLineToArgvW() is in shell32.dll. I'd guessthat the Shell developers created the function for their own use, and it was made public either because someone decided that 3rd party devs would find it useful or because some court action made them do it.

Since the Shell developers only ever needed a Unicode version that's all they ever wrote. It would be fairly simple to write an ANSI wrapper for the function that converts the ANSI to Unicode, calls the function and converts the Unicode results to ANSI (and if Shell32.dll ever provided an ANSI variant of this API, that's probably exactly what would do).

Answer 3

See what portion of MSDN?

Answer 4

Apparently you can use __argv outside main() to access the pre-parsed argument vector...

Answer 5

Here is an implementation of CommandLineToArgvA that delegate the work to CommandLineToArgvW, MultiByteToWideChar and WideCharToMultiByte.

LPSTR* CommandLineToArgvA(LPSTR lpCmdLine, INT *pNumArgs)
{
    int retval;
    retval = MultiByteToWideChar(CP_ACP, MB_ERR_INVALID_CHARS, lpCmdLine, -1, NULL, 0);
    if (!SUCCEEDED(retval))
        return NULL;

    LPWSTR lpWideCharStr = (LPWSTR)malloc(retval * sizeof(WCHAR));
    if (lpWideCharStr == NULL)
        return NULL;

    retval = MultiByteToWideChar(CP_ACP, MB_ERR_INVALID_CHARS, lpCmdLine, -1, lpWideCharStr, retval);
    if (!SUCCEEDED(retval))
    {
        free(lpWideCharStr);
        return NULL;
    }

    int numArgs;
    LPWSTR* args;
    args = CommandLineToArgvW(lpWideCharStr, &numArgs);
    free(lpWideCharStr);
    if (args == NULL)
        return NULL;

    int storage = numArgs * sizeof(LPSTR);
    for (int i = 0; i < numArgs; ++ i)
    {
        BOOL lpUsedDefaultChar = FALSE;
        retval = WideCharToMultiByte(CP_ACP, 0, args[i], -1, NULL, 0, NULL, &lpUsedDefaultChar);
        if (!SUCCEEDED(retval))
        {
            LocalFree(args);
            return NULL;
        }

        storage += retval;
    }

    LPSTR* result = (LPSTR*)LocalAlloc(LMEM_FIXED, storage);
    if (result == NULL)
    {
        LocalFree(args);
        return NULL;
    }

    int bufLen = storage - numArgs * sizeof(LPSTR);
    LPSTR buffer = ((LPSTR)result) + numArgs * sizeof(LPSTR);
    for (int i = 0; i < numArgs; ++ i)
    {
        assert(bufLen > 0);
        BOOL lpUsedDefaultChar = FALSE;
        retval = WideCharToMultiByte(CP_ACP, 0, args[i], -1, buffer, bufLen, NULL, &lpUsedDefaultChar);
        if (!SUCCEEDED(retval))
        {
            LocalFree(result);
            LocalFree(args);
            return NULL;
        }

        result[i] = buffer;
        bufLen -= retval;
    }

    LocalFree(args);

    *pNumArgs = numArgs;
    return result;
}