C / C++ / MFC

Re: How to implement variable amount of parameters?

3-Mar-23 21:57

It dpends om what type the extra parameters are. If they are all the same (e.g. all ints, chars etc.) then you are better using an array or a C++ container. But if you are passing a variable number of varying types then you need some way of identifying which type each parameter is. In the C library printf/scanf functions this is done with the format string, where each control item in the string tells the function what type to expect for the corresponding variable.

jschell6-Mar-23 6:20

jschell

6-Mar-23 6:20

Besides the other answers you might want to ask how many of these would be reasonable in the next 5 years of using this method.

So if you start with 2 now and there are 4 in 5 years ok.
But if you start with 2 now and in three months there are 20 then that is a problem. In that case a collection of some sort is better.

Re: How to implement variable amount of parameters?

charlieg19-Mar-23 11:47

charlieg

19-Mar-23 11:47

" in three months there are 20"

Nah, they're on to the next project.... who cares about code maintenance?

Smile | :)

Charlie Gilley

“They who can give up essential liberty to obtain a little temporary safety deserve neither liberty nor safety.” BF, 1759

Has never been more appropriate.

C++ non-null pointers

Mircea Neacsu2-Mar-23 7:47

Re: C++ non-null pointers

2-Mar-23 7:47

Has anyone used a non-null library like Non-nullable pointers for C++[^]? Any opinions on usefulness?

Mircea

jschell6-Mar-23 6:22

jschell

6-Mar-23 6:22

It still requires enforcing correct usage which can only occur via discipline and/or careful code reviews.

And if you are doing that then you shouldn't have a problem in the first place. More careful designs can also reduce the problem.

Re: C++ non-null pointers

Mircea Neacsu6-Mar-23 7:34

6-Mar-23 7:34

My thoughts exactly. Seems more trouble than it's worth.

Mircea

1-Mar-23 7:32

1-Mar-23 7:32

Message Closed

modified 15-May-23 19:06pm.

Mircea Neacsu1-Mar-23 7:37

1-Mar-23 7:37

It's not wrong. Empty statement is a valid C/C++ statement. You can try:

C++

;;;; //this is valid

Also, a very popular beginner mistake is to add a spurious semicolon at the end of a while and wonder why the while "body" is not repeated:

C++

while (i>0); //spurious semi
 {
   //this is not looped
 }

Mircea

modified 1-Mar-23 14:07pm.

CPallini2-Mar-23 20:49

CPallini

2-Mar-23 20:49

Quote:
Also, a very popular beginner mistake

Now, you're calling me 'beginner'. D'Oh! | :doh:

"In testa che avete, Signor di Ceprano?"
-- Rigoletto

Mircea Neacsu3-Mar-23 0:37

3-Mar-23 0:37

Aren’t we all beginners constantly trying to learn new things? Do you think I saw that error in a book? Laugh | :laugh:

Mircea

k50541-Mar-23 7:50

k5054

1-Mar-23 7:50

To add to what Mircea has said, you may even include empty blocks e.g.

C++

int main()
{
  {}
  std::cout << "Hello World!\n";
  {}
}

compiles without complaint.

While that seems rather silly, source code like that might be generated when a pre-processor #define is expanded or perhaps if you have some sort of code generator as part of the build process. e.g. something like Oracle Pro*C, or Postgresql ecpg.

Keep Calm and Carry On

21-Feb-23 8:09

Re: painted myself into a corner - again - need HELP

21-Feb-23 8:09

Message Closed

modified 15-May-23 19:06pm.

Richard MacCutchan21-Feb-23 8:26

Re: painted myself into a corner - again - need HELP

21-Feb-23 8:26

It's because #ifdef is a preprocessor statement and the the preprocessor requires the #ifdef and the #endif to be on separate lines. What you could do is use Find/Replace to convert all qDebug calls to Debug (or some other unique name), and then add something like the following at the top of you source, or in a common header:

C++

#ifdef DEBUG
#define Debug qDebug
#else
#define Debug
#endif

Mircea Neacsu21-Feb-23 8:49

Re: painted myself into a corner - again - need HELP

21-Feb-23 8:49

Copy the following in a file called script.awk

/qDebug/ {
  print "#ifdef DEBUG"
  print $0
  print "#endif"
}
!/qDebug/

Then a command like

awk -f script.awk source.cpp >new_source.cpp

would put a pair of #ifdef/#endif on any line containing qDebug. Obviously replace source.cpp with your source file.

Translated into English, the script says: if line contains the string qDebug, print a line with #ifdef DEBUG, then print the line in question, then print a line with #endif. If line doesn't contain the string qDebug, just print it. The resulting output is put in file new_source.cpp

Good luck!

Mircea

David O'Neil21-Feb-23 15:32

David O'Neil

21-Feb-23 15:32

If you can get Notepad++ working on Linux through Wine, as per this page, you can record a script in it to do the job. Don't know how difficult it will be to do across multiple files, as far as opening them individually goes, but the script can be assigned a keyboard shortcut to make it easier. You can also use extended characters to search and replace every occurrence without having to trigger the macro for each instance in the file.

Our Forgotten Astronomy | Object Oriented Programming with C++ | Wordle solver

19-Feb-23 4:20

19-Feb-23 4:20

Message Closed

modified 15-May-23 19:06pm.

Re: C code challenge...

Richard MacCutchan19-Feb-23 5:19

19-Feb-23 5:19

Create your own Debug class to do it, and change all the qDebug calls to call your class. Then inside your class you can pass the text to qDebug itself, and to your textbox.

Re: C code challenge...

CPallini19-Feb-23 20:47

CPallini

19-Feb-23 20:47

That is C++, not C.
I show you how it could be handled in a similar scenario:

C++

#include <iostream>
#include <sstream>
using namespace std;

#define STD_DEBUG

#ifdef STD_DEBUG
  #define DBG(txt) cerr << txt
#else
  #define DBG(txt)  \
    do { \
      ostringstream os; \
      os << txt; \
      string s = os.str(); \
      cout << "The debug string: " << s; \
    } while (0) 
#endif

int main()
{
  DBG("foobar = " << 42 << "\n");
}

"In testa che avete, Signor di Ceprano?"
-- Rigoletto

14-Feb-23 10:04

Re: How to add #include to makefile ?

14-Feb-23 10:04

Message Closed

modified 15-May-23 19:06pm.

Mircea Neacsu14-Feb-23 10:44

Re: How to add #include to makefile ?

14-Feb-23 10:44

I think you'll have to explain in more detail what you want to accomplish.

Makefiles and include files are not directly related. Makefiles are "recipes" used to compile and link a binary. You write something like:

module1.o : module1.cpp inc1.h inc2.h
  gcc $(CFLAGS) -o module1.o module1.cpp

That would tell make that module1.o object file needs to be recompiled every time any of module1.cpp or inc1.h or inc2.h files changes and what is the command to compile it.

Mircea

Richard MacCutchan14-Feb-23 22:03

Re: How to add #include to makefile ?

14-Feb-23 22:03

You can groupt include statements into a single header file which is then included in every module that requires them. But you should avoid including headers that are not required as that just adds to compilation time. And if you are building for Windows with Visual Studio you can use the "Precompiled Headers" option to make it faster. I do not know whether g++ has a similar option.

As mentioned elsewhere, include statements have nothing to do with make files.

modified 15-Feb-23 5:18am.

k505415-Feb-23 5:39

k5054

15-Feb-23 5:39

g++ will create pre-compiled headers quite simply: g++ foo.hpp creates a foo.hpp.gch, and the compiler will search for a .gch file when processing a #include directive. If necessary, you can include -x c++-header flags to indicate to the compiler that the named sources are to be treated as header files rather than program source code. Also note that some compiler flags need to match for both PCH and source code. More details here: Precompiled Headers (Using the GNU Compiler Collection (GCC))

Keep Calm and Carry On

14-Feb-23 4:39

Re: How to manage application configuration ?

14-Feb-23 4:39

Message Closed

modified 15-May-23 19:06pm.

Mircea Neacsu14-Feb-23 7:57