|
Hi,
I have a class which encapsulates a window. This class has all the Message handlers and stuff. Lets say this class is CMainFrame.
Now, I am creating CMainFrame from another class....
CMainFrame* cMainFrame = new CMainFrame() ;<br />
cMainFrame->CreateWindow() ;
Now when I destory the window does the object tha cMainFrame is pointing to also get deleted from memory or do we have to do it explicitly? What I did was
cMainFrame->DestroyWindow() ;<br />
delete cMainFrame ;<br />
cMainFrame = NULL ;
Is this destruction of the Window and object the correct way to do it?
---
With best regards,
A Manchester United Fan
The Genius of a true fool is that he can mess up a foolproof plan!
|
|
|
|
|
TechyMaila wrote: Now when I destory the window does the object tha cMainFrame is pointing to also get deleted from memory or do we have to do it explicitly? What I did was
cMainFrame->DestroyWindow() ;
delete cMainFrame ;
cMainFrame = NULL ;
Is this destruction of the Window and object the correct way to do it?
From MSDN:
About DestroyWindow:
Destroys the Windows window attached to the CWnd object. The DestroyWindow member function sends appropriate messages to the window to deactivate it and remove the input focus. It also destroys the window’s menu, flushes the application queue, destroys outstanding timers, removes Clipboard ownership, and breaks the Clipboard-viewer chain if CWnd is at the top of the viewer chain. It sends WM_DESTROY and WM_NCDESTROY messages to the window. It does not destroy the CWnd object.
Nibu thomas
A Developer
Programming tips[^] My site[^]
|
|
|
|
|
Thanks Nibu.
So whatever I am doing is correct. I have one question though. As you can see from my example above, I have created a cMainFrame Pointer to the CMainFrame class. Now, lets say that cMainFrame is a private data member of class A. So, it is a who is creating cMainFrame and calling cMainFrame->CreateWindow().
Now my question is, if a user closes the window from the close button on the Window Title bar, I would have to notify class A so that it may do the required cleaning up like delete cMainFrame and stuff. So, when do I notify A then the window is destroyed? Lets say, that I am notifying A during WM_DESTROY. The implementation in A would be as follows:
void A::OnFrameDestroy()<br />
{<br />
delete cMainFrame ;<br />
cMainFrame = NULL ;<br />
}
But the fact is, when I do this, the teh control passes back to the window's WM_DESTROY message handler after notifying A which results in an error. Any suggestions....???? 
---
With best regards,
A Manchester United Fan
The Genius of a true fool is that he can mess up a foolproof plan!
|
|
|
|
|
|
Nibu thomas wrote: Delete the pointer in CWnd::PostNcDestroy.
I am using the Win32API. No MFC. Could you tell me which Windows message is equivalent to CWnd::PostNcDestroy?
---
With best regards,
A Manchester United Fan
The Genius of a true fool is that he can mess up a foolproof plan!
|
|
|
|
|
TechyMaila wrote: I am using the Win32API. No MFC. Could you tell me which Windows message is equivalent to CWnd::PostNcDestroy?
WM_NCDESTROY is the last message for a window.
The MFC implementation goes like this. MFC does some clean up in OnNcDestroy and then calls PostNcDestroy. The default implementation does nothing. So you will have to implement something like this.
From MSDN about PostNcDestroy:
The default implementation of CWnd::PostNcDestroy does nothing which is appropriate for window objects allocated on the stack frame or embedded in other objects. This is not appropriate for window objects that are designed to be allocated by themselves on the heap (not embedded in other C++ object).
Those classes that are designed to be allocated by themselves on the heap override the PostNcDestroy member function to perform a "delete this". This statement will free any C++ memory associated with the C++ object. Even though the default CWnd destructor calls DestroyWindow if m_hWnd is non-NULL, this does not lead to infinite recursion since the handle will be detached and NULL during the cleanup phase.
Nibu thomas
A Developer
Programming tips[^] My site[^]
|
|
|
|
|
TechyMaila wrote: cMainFrame->DestroyWindow() ;
delete cMainFrame ;
I think it is ok.
if some OnClose operations mapped in the class, it is better to Send WM_CLOSE command using "SendMessage" function
cMainFrame->SendMessage(WM_CLOSE) ;<br />
delete cMainFrame ;<br />
cMainFrame = NULL ;
SaRath
"D on't blindly follow rules you read somewhere without verifying that it makes sense for your situation!"
|
|
|
|
|
Hello Comunity,
i have two questions about Programs, first is:
How to change the Text in the Titlebar when the program is minimized SW_MINIMIZE!
and second is:
How to make an TrayIcon, i want to show my application as TryIcon on the right side from the taskbar,
for example right from the clock in the task bar!?  confused:
thanx for any help!
break;
|
|
|
|
|
For placing icon in System tray :
http://www.codeproject.com/shell/trayicons.asp
For changing text in Titlebar:
void CMainFrame::OnSysCommand(UINT nID, LPARAM lParam)
{
// TODO: Add your message handler code here and/or call default
if(nID == SC_MINIMIZE)
{
SetWindowText(_T("Minize"));
}
else
{
SetWindowText(_T("Maximize"));// Original
}
CFrameWnd::OnSysCommand(nID, lParam);
}
 Amar
|
|
|
|
|
|
Hello Amar,
i use this OnSysCommand(UINT nID, LPARAM lParam) function to do this!
thanx
|
|
|
|
|
Answer to the first question:
Override the OnSize of the window. Do this using the help of class wizard. Add message handfler for WM_SIZE it will generate overriden function OnSize() it wil look like
YourWindow::OnSize( UINT nType, int cx, int cy )
{
ParentWindow::OnSize( nType, cx, cy )
}
You can change the title of the window by adding the following code snippets
if( SIZE_MINIMIZED == nType )
{
CString csNewTitle = "New Window Title";
SetWindowText( csNewTitle );
}
|
|
|
|
|
Answer to the second question:
For putting you application in System Tray you can use the APIs
Shell_NotifyIcon() along with the structure NOTIFYICONDATA
|
|
|
|
|
|
Hello whitesky and other,
i solve my problem, thanx a lot i use systray in i easy steps
regards
break;
|
|
|
|
|
Hello everyone,
I need to compute the intersection of two (or more) sets. I will use C or C++, but STL algorithms are not enabled to be used. I have Googled, but it seems that there are only union algorithms and no intersection algorithms.
It is not my homework, and it is my interest to improve the application I am working on now. Does anyone have any reference materials or any ideas of how to design the intersection operation of sets efficiently.
thanks in advance,
George
|
|
|
|
|
The first thing to do is sort the sets, like:
int set1[7] = {5, 2, 0, 2, 8, 7, 5};
int set2[7] = {2, 8, 8, 7, 0, 9, 9};
qsort(set1, 7, sizeof(int), compare);
qsort(set2, 7, sizeof(int), compare);
...
int compare( const void *arg1, const void *arg2 )
{
return *(int *) arg1 - *(int *) arg2;
}Now you can compare the items in the first set with the items in the second set, making a note of the matches. If the current item in the first set is less than the current item in the second set, go to the next item in the first set. If the current item in the first set is greater than the current item in the second set, go to the next item in the second set. Otherwise the two numbers match so add the item to the third (output) set, and go to the next item in both the other two sets. Make sense?
"The largest fire starts but with the smallest spark." - David Crow
|
|
|
|
|
Thank you DavidCrow!
Your method is great! I am wondering whether I can do some further improvements. I think we can check the size of each set, then we can use the elements in smaller set to find the matched ones in the bigger set (or vice versa?), which can improve the performnace -- but I am not sure about it. Do you have any comments?
regards,
George
|
|
|
|
|
George_George wrote: I think we can check the size of each set, then we can use the elements in smaller set to find the matched ones in the bigger set (or vice versa?), which can improve the performnace -- but I am not sure about it. Do you have any comments?
Just have your for/while loop check for remaining items in both sets. Something like:
while (there_are_items_in_set1 && there_are_items_in_set2)
...
"The largest fire starts but with the smallest spark." - David Crow
|
|
|
|
|
Use STL. The following calculates a set intersection:
Here's a complete example I had laying around:
----------------------------------------------
#include "stdafx.h"
#include <iostream>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;
const char* g_Names1[] = {"Joe", "Paul", "Simon", "Steve", "Karl"};
const char** g_Names1Begin = &g_Names1[0];
const char** g_Names1End = &g_Names1[sizeof(g_Names1)/sizeof(g_Names1[0])];
const char* g_Names2[] = {"Paul", "Kate", "Oleg"};
const char** g_Names2Begin = &g_Names2[0];
const char** g_Names2End = &g_Names2[sizeof(g_Names2)/sizeof(g_Names2[0])];
struct CharLess
{
bool operator()(const char* p1, const char* p2) const
{
return strcmp(p1, p2)<0;
}
};
int main(int argc, char* argv[])
{
typedef vector<const char*> VEC;
VEC v1(g_Names1Begin, g_Names1End);
VEC v2(g_Names2Begin, g_Names2End);
sort(v1.begin(), v1.end(), CharLess());
sort(v2.begin(), v2.end(), CharLess());
set_intersection(
v1.begin(), v1.end(),
v2.begin(), v2.end(),
ostream_iterator<const char*>(cout, "\n"),
CharLess()
);
return 0;
}
Steve
|
|
|
|
|
Thank you Steve,
I noticed that you are using STL built-in algorithm set_intersection. Do you have any ideas of how to implement it efficient without STL? I need to save footprint on my device. Thank you!
regards,
George
|
|
|
|
|
Your fears that using STL will bloat your program are not well founded. You can check out the source code for set_intersection by looking in the file <algorithm>: it contains a for loop and two if. With STL you only pay for what you use. Note that the algorithm requires the data to be sorted thus you must count the code for the sort algorithm also.
Steve
|
|
|
|
|
Hi Steve,
I am developing on embedded device. So if I need to use C++, I have to port C++ runtime library to this platform, right (actually, I prefer C)? And it will both,
- Increase my working time;
- Increase the footprint to hold C++ runtime library (for example .so files on Linux).
Have I answered your question?
regards,
George
|
|
|
|
|
None of the algorithms I used (sort or set_intersection) use or have any need for the C runtime library. There is no distinct C++ runtime library. The only CRT function used is the one I introduced: strcmp (ignoring the functions I used to write the output to the console). None of what you say need be true. In general using STL will decrease your working time and will have not have a detrimental effect on the footprint of your EXE. Most of your fears are superstition.
Steve
|
|
|
|
|
Sorry Steve,
Maybe I have not make myself understood enough. I mean I prefer C. But in order to use sort or set_intersection, I have to use C++ runtime library. Correct?
regards,
George
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
