|
Very Strange, the OnEraseBkgnd should always be called before OnDraw. Anyway, one possible solution would be to call ExcludeClipRect or ExcludeUpdateRgn in the OnDraw function so that any future drawing will not draw over what has already drawn.
Note: The above may lead to unusual drawing, if OnDraw is realy called before OnEraseBkgnd.
What I recommend is to see if you can reproduce the problem in a simple test program (the smaller the better). This will allow one of us to see how OnEraseBkgnd is being called first (or you to see how that is happening).
I have found that if you override the OnEraseBkgnd to return TRUE and override the OnDraw function, so that it calls ExcludeClipRect or ExcludeUpdateRgn to validate anything you have drawn, is a great way to elimenate any flicker.
If you find a solution please post it (or write and article [prefered]).
If what you describe is actualy happening, I feel for you. It's one of those things that makes us want to pound are head against the wall (very depressing).
Good Luck, and keep progamming!
INTP
"The more help VB provides VB programmers, the more miserable your life as a C++ programmer becomes."
Andrew W. Troelsen
|
|
|
|
|
Thanks for the reply! View class contains an array of CButtons, so the CButton’s Erase is being called after the View’s OnDraw() method which moves the CButtons (MoveWindow()). Please see my other reply to this thread for a more complete description (I don’t want to double-post).
Thanks!
JennyP
|
|
|
|
|
what's mean "with a CButton array",which class does th OnDraw() method belong to?
your friend:bobi
|
|
|
|
|
Thanks for the reply. The View class contains an array of CButtons that it creates upon init-dialog. Then, in the View’s OnDraw() method, these buttons are repositioned (MoveWindow()) based on the user’s resizing the overall view. After calling MoveWindow(), I draw a bunch of lines (dc->LineTo()).
When the app is running and the user resizes the view, the lines all have blank squares imprinted over them where the CButton(s) used to be (i.e., before they were moved with MoveWindow()).
When I insert debug TRACE()s, I see that the CButton’s OnEraseBackground method is temporally executed AFTER the View’s OnDraw() is completed. I suspect that the MoveWindow() simply puts a message in the queue for the CButtons to erase themselves. However, I want this operation to complete immediately before the lines are drawn.
Any suggestions?
Thanks!
JennyP
|
|
|
|
|
just to be sure I do this the right way ...
I have a vector of something and I want to sort it according to a criteria; so I define a class as the criteria, and I want to pass some context to it ( some additional global thingies )
typedef std::vector < something > vectorOfSomething_t;
vectorOfSomething_t myVector;
...
vectorOfSomething_t::iterator start = myVector.start();
vectorOfSomething_t::iterator end = myVector.end();
std::sort( start, end, myCriteriaFunctor );
...
class myCriteriaFunctor
{
public:
myCriteriaFunctor ( bool b, int i ): m_vp(vp), m_bSortOrder( b ), m_iSomeContext(i) {};
private:
bool m_bSortOrder;
int m_iSomeContext;
public:
bool operator() ( something& something1 , something& something2 ) const
{
bool bSmaller;
...
return bSmaller;
};
the question, is it kosher to pass data like that to a sort functor ?
It's working right now, and I just want to be sure ...
Thanks.
Maximilien Lincourt
Your Head A Splode - Strong Bad
|
|
|
|
|
I do not see any problem with your code.
Looks good.
My site - Body Jewelry
|
|
|
|
|
That's perfectly fine, the usual way of doing it is to create a temp object in the sort() call and pass the appropriate data to its ctor:
std::sort ( start, end, <font color=red>myCriteriaFunctor(true, 42)</font> ); If you need the object lifetime to be longer than just that one line, you can create it on the stack like any other C++ object. (A "functor" is a C++ object, after all, it just also has an overloaded operator() for STL to call.)
--Mike--
LINKS~! Ericahist updated! | 1ClickPicGrabber | CP SearchBar v2.0.2 | C++ Forum FAQ
Strange things are afoot at the U+004B U+20DD
|
|
|
|
|
Hi,
I'm a bit confused with the copy constructor business. A book I found says that given a variable 'a' of type MyClass, if you have:
<br />
a = SomeFunction();
then the copy constructor of MyClass would be invoked. None of the examples I've seen on the net ever try to delete memory inside a copy constructor. They only allocate new memory and copy the stuff. However in this case 'a', would already exist with some memory being used and would result in a memory leak? If the book is wrong and the operator=() is called then that makes more sense. Or possibly most of the examples I've seen are wrong and you should always call delete on your memory in the copy constructor.
Thanks for cleaning this up. If you know of a good resource on the net on this topic let me know.
|
|
|
|
|
Hi friend,
I don't know what kind of book you read, but i think that you might missunderdstood the issue.
In the example you wrote:
a = SomeFunction(); //returns MyClass object
You are right, the operator= is called, but have you read the implementation of operator=...?
if you are using a default version of operator=, then you will get a call of the copy construcor because its implemntation goes like this:
<br />
M operator=(const M &m)<br />
{<br />
return m;
}
because a copy of object m is returned BY VALUE, not the actual object will be returned, but a copy of object m. No memory leak will occur because this temporary object is created on the stack!
Furthermore, if you create an object with the operator=, the copy constructor will be called instaed of operator=
MyClass new=old; //copy constructor is called.
A good resource is the book Thinking in C++ version 2, it is available on many sites for FREE. use a search engine to find it.
Good luck,
Mohammad Gdeisat
|
|
|
|
|
Well, the default assignment operator generated by the compiler will *NOT* result in a copy constructor call. It does a bitwise copy and that's the source of the dangling pointer problem.
And if you define your own operator =, you're supposed to return a *reference*, otherwise chaining the operator like a = b = c won't work. A typical operator = overload will look like this
M & operator = (const M& val)
{
// do the job
return *this;
}
Regards
Senthil
My Blog
|
|
|
|
|
Hi,
yes you are right about the implementation.
But you can write a program and a class, with Copy contructor and operator= implemented , and write cout statements to trace program flow.
Its really a tricky behaviour,
Regards,
Mohammad
|
|
|
|
|
Well, you're right. And so is the book's author, if SomeFunction returns a value and not a reference.. Both the copy constructor and operator = will get called. How? SomeFunction returns a value and the compiler invokes the copy constructor to create a temporary object. It then calls operator = on a, passing the temporary object.
And yeah, you are right, inside the overloaded assignment operator, you need to check if you have a valid pointer and if you do, delete it before copying the contents. This is not needed in a copy constructor because it can be invoked only once, when the object is created.
You need to watch out for something called return value optimization though. If you write code like this,
<br />
Class a = SomeFunction();<br />
then the compiler is free to optimize away the call to the copy constructor and instead construct a directly in place. So the above code will result in only copy constructor call, instead of the two you expect (one for the returned temporary object, one for a).
Regards
Senthil
My Blog
|
|
|
|
|
If 'a' already exists and you wish to replace it with data from anouther object then you must free any memory that your object allocated before copying the data. But to be safe, you must first determine it you can make a copy of the data. Which means if an allocation is needed, then allocate the required memory. If the allocation fails then throw an exception (or return an error condition). If the allocation is successfull, then free the previous memory pointers and set them equal to the newly allocated memory pointers. The idea here is to leave the object ('a') in the same state that it was in before the copy was attempted.
There is a differnce between the following:
MyClass a = b; // 1st - object being initialised
a = c; // 2nd object data being replaced
In the 1st case the code calls the copy constructor MyClass::MyClass(const MyClass& argumentMyClass).
In the 2nd case it calls the operater MyClass::operater=(const MyClass argumentMyClass).
The 1st case is easy, but it must(/should) throw an exception if a memory allocation fails (because constuctors do not return a failed/success value).
The 2nd case is a little different, because 'a' alrady exist. We have to free any memory associated with it, before reassigning the data pointers.
Now here is the flaw in the sytstem, if you don't delete your current objects data pointers before allocating space for the new data then there may not be enough memory to make a copy (highly unlikely - but possible). If that is the case then you are running so low on memory that it does not matter (just throw an exception or return a major error value).
General Rule: Any time a function/routine fails, the state of the object/data should remain in the state that is was in before the failure.
 Sorry, I tend to get a little carried away. This is a fraction of what you may have to deal with, when it comes to copy constructors.
INTP
"The more help VB provides VB programmers, the more miserable your life as a C++ programmer becomes."
Andrew W. Troelsen
|
|
|
|
|
That clears it up for me.
|
|
|
|
|
Hi there
I´m working in a project that mixes managed and unmanaged code. While debuggin my unmanaged code that makes a call to a class that uses managed code I get a dialog box with this message: "There is no source code for the current location".
All the projects contained in the solution are seted to use managed extensions and the debug mode is seted to "mixed".
Any hint ou there to solve this problem?
Thanks in advance.
|
|
|
|
|
|
Thanks for the tip, but reading the msdn article
http://msdn.microsoft.com/library/default.asp?url=/library/en-us/vsdebug/html/vxtskLaunchingDebuggerAutomatically.asp[^] pointed in the greggm's blog, it makes reference to "desenv.exe" and I could not find desenv.exe in my system. I already installed "Debugging Tools for Windows" and still missing this file.
Like I told before, the project I'm working on is a C++ (native code) that call a dll that uses managed code and when I try to step into a function in this dll, the debugger stops and show me a message "There is no source code for the current location" along with a checkbox "Show disassembly automatically" and three buttons, OK, SHow Disassembly and help.
There is another utility that I coukd use to debug the managed code in the dll?
Thanks in advance
|
|
|
|
|
We have a CFormView based application. Within this application, some have created CDialog classes and so we have a mixture of window types. Some of our modal windows are CFormView based and some are CDialog based. The CDialog windows always have priority over the CFormView based windows. Even when I click on a window that is a CFormView, the title bar activates and the window is selected, but it cannot be brought to the front to display over the CDialog windows. Does anyone know what properties I have to enable or disable to change this behavior?
I need CFormView windows to display overtop of the other independent CDialog windows.
Best Regards,
Shawn D. Fox
|
|
|
|
|
I have a named pipe server, created using CreateNamedPipe(). Has anyone any idea how can I make it disallow remote clients (so only pipe clients on the same system as the server are allowed to connect to it) ?
Many thanks for any help.
Thanks,
Neil Humphreys.
|
|
|
|
|
I have an MFC application in which I need to perform a join operation of two tables Emp and Assets, with the EmpID field being the primary key. I did not use any AppWizard options to implement database connectivity functionality. Instead, I added two classes derived from CRecordset and two forms derived from CRecordview class to implement DBMS. I need to select all asets for a given EmpID in the Emp table and show the on a form. Is there a way to do this without using the m_strFilter variable/parameter stuff?
log live the dEvIL
|
|
|
|
|
I think you need to derive a class from CRecordset that has as its member variables all columns returned from the query. For example. given the following two tables:
Table1
=======
CustID
Name
Address
Phone
Table2
=======
OrderID
CustID
Total
the CRecordset-derived class would have a query that looked like:
SELECT Table1.Name, Table1.Address, Table1.Phone, Table2.Total
FROM Table1 INNER JOIN Table2 ON Table1.CustID = Table2.CustID
The class would need four member variables. Does this get you close?
"Opinions are neither right nor wrong. I cannot change your opinion. I can, however, change what influences your opinion." - David Crow
|
|
|
|
|
Na, I am way too far. I did derive a class from CREcordset and linked it up to a table, I just need to set the filter. How do I do that?
long live the dEvIL
|
|
|
|
|
If you already have a CRecordset-derived class, and the subject of this thread indicates you want to implement a join, why not just change the value returned from the GetDefaultSQL() method? Using the m_strFilter member variable does not do the same thing as a join operation.
"Opinions are neither right nor wrong. I cannot change your opinion. I can, however, change what influences your opinion." - David Crow
|
|
|
|
|
Hello
Can anybody explain to me why the following four bold lines of code yield different results to their counterparts on the line below? By my reckoning the results should be the same with the only difference being one set are printed to the console window and the other to a text file. The purple lines are definitely creating correct results because they are a product of help code for Microsoft Visual Studio .NET and the results look good. The red lines of code (my code) are definitely producing incorrect results and all four of the outputs are often identical. Am I doing some memory management incorrectly???
#include "stdafx.h"
#using
#include
#include
#include
using namespace System;
// This is the entry point for this application
int _tmain(void)
{
_int64 ctr1 = 0, ctr2 = 0, freq = 0;
int acc = 0, i = 0;
FILE *storage;
//Start timing the code
if(QueryPerformanceCounter((LARGE_INTEGER *)&ctr1) != 0)
{
storage = fopen("C:\\TestTimer.txt", "a"); //Open a file for data output
//Code segment is being timed
for(i=0; i<100; i++) acc++;
//Finish timing the code
QueryPerformanceCounter((LARGE_INTEGER *)&ctr2);
fprintf(storage, "Start Value %s\n", ctr1.ToString());Console::WriteLine("Start Value: {0}",ctr1.ToString());
fprintf(storage, "End Value %s\n", ctr2.ToString());
Console::WriteLine("End Value: {0}",ctr2.ToString());
QueryPerformanceFrequency((LARGE_INTEGER *)&freq);
fprintf(storage, "Frequency %s\n", freq.ToString());Console::WriteLine(S"QueryPerformanceCounter minimum resolution: 1/{0} seconds.",freq.ToString());
fprintf(storage, "Time %s\n", ((ctr2-ctr1) * 1.0 / freq).ToString()); Console::WriteLine("100 Increment time: {0} seconds.",((ctr2-ctr1) * 1.0 / freq).ToString());
fclose(storage);
}
return 0;
}
|
|
|
|
|
You're mixing CLR strings with C-style strings. fprintf() expects a const char* on the stack, to be inserted where the %s is, however what you're putting on the stack is a whole System::String object, which is totally not the same thing. You need to convert that object to a C-style string (with PtrToStringChars, for example).
--Mike--
LINKS~! Ericahist updated! | 1ClickPicGrabber | CP SearchBar v2.0.2 | C++ Forum FAQ
Strange things are afoot at the U+004B U+20DD
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
