C / C++ / MFC

Benoy Bose31-May-06 21:40

Benoy Bose

31-May-06 21:40

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 );
}

Benoy Bose31-May-06 21:42

Benoy Bose

31-May-06 21:42

Answer to the second question:

For putting you application in System Tray you can use the APIs
Shell_NotifyIcon() along with the structure NOTIFYICONDATA

Hamid_RT31-May-06 21:47

Hamid_RT

31-May-06 21:47

Minimize your app to systray in 8 easy steps[^]

whitesky

how to compute set intersection efficiently?

bosfan1-Jun-06 3:08

bosfan

1-Jun-06 3:08

Hello whitesky and other,
i solve my problem, thanx a lot Smile | :)

i use systray in i easy steps Smile | :)

regards
break;

George_George31-May-06 21:18

Re: how to compute set intersection efficiently?

31-May-06 21:18

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

David Crow1-Jun-06 4:58

David Crow

1-Jun-06 4:58

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

Re: how to compute set intersection efficiently?

George_George1-Jun-06 18:41

Re: how to compute set intersection efficiently?

1-Jun-06 18:41

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

David Crow2-Jun-06 2:51

David Crow

2-Jun-06 2:51

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

Re: how to compute set intersection efficiently? [modified]

Stephen Hewitt1-Jun-06 14:20

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 14:20

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

George_George1-Jun-06 18:45

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 18:45

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

Stephen Hewitt1-Jun-06 18:54

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 18:54

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

George_George1-Jun-06 19:06

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 19:06

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

Stephen Hewitt1-Jun-06 19:21

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 19:21

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

George_George1-Jun-06 20:13

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 20:13

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

Stephen Hewitt1-Jun-06 20:17

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 20:17

George_George wrote:
But in order to use sort or set_intersection, I have to use C++ runtime library. Correct?

This is not the case. Both sort and set_intersection are both just short inline functions with no dependencies on any runtime libraries. Have a look at the algorithm header file. In fact most or STL is like this. These are exceptions such as the stream and locale classes.

Steve

Stephen Hewitt1-Jun-06 18:57

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 18:57

He's a version which sorts the array in-place without using a vector:

#include "stdafx.h"
#include <iostream>
#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[])
{
sort(g_Names1Begin, g_Names1End, CharLess());
sort(g_Names2Begin, g_Names2End, CharLess());
set_intersection(
g_Names1Begin, g_Names1End,
g_Names2Begin, g_Names2End,
ostream_iterator<const char*>(cout, "\n"),
CharLess()
);

return 0;
}

Steve

George_George1-Jun-06 19:09

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 19:09

Hi Steve,

To me, it is the same -- since I am trying to remove STL/C++ and implement it by myself. I am looking for an efficient implementation -- there are a couple of sets and each contains a lot of data. Any comments or ideas?

regards,
George

Stephen Hewitt1-Jun-06 19:22

Re: how to compute set intersection efficiently? [modified]

1-Jun-06 19:22

If you really want to re-invent the wheel copy STL's code - all the source is there. After looking at the code in question you'll realise you should have just used it as is. You'll have a hard time matching STL's efficiency.

Steve

George_George1-Jun-06 20:16