|
Sorry, I mistyped it in the post. Of course I declared it as a pointer and it created the mentioned error.
|
|
|
|
|
|
class *Parent;
is in CMyOwnCtl.h. If it was not there, I would not have any problem: in the function itself CMyOwnDlg can be used. because both headers are known there (and then John M. Drescher's suggestion works).
|
|
|
|
|
When you use forward declaration. The forward declared variable cannot be accessed in the declaration file, since compiler only knows the pointer and allocates the size of pointer when you access it, compiler won't have enough information to do this.
ctl_MyControl.Parent = this;
Is this statement is in declaration file, if so, use this in a function definition is cpp file.
Since the dialog is immediate parent, you know the level of the parent class, you can use john's method (dynamic cast the parent window).
Best Regards
Raj
|
|
|
|
|
One thing you could do is to make *Parent a class member of CMyOwnCtl and pass it in a constructor or a SetParent member.
Actually you do not need to store the pointer though as you can always do a GetParent() in the control and DYNAMIC_CAST or (dynamic_cast) the CWnd pointer to CMyOwnDlg. I do this 90% of the time and use dynamic_cast syntax over DYNAMIC_CAST as my programs are compiled with RTTI and I avoid the MFC macros as much as I can.
John
|
|
|
|
|
This appeared to be all right, at least syntactically.
However,
CMyOwnDlg *Parent = dynamic_cast <CMyOwnDlg *> (GetParent());
in the function of the control caused an error: RTDynamicCast threw an exception.
|
|
|
|
|
Did you set the compiler option to enable RTTI (Run time type info)? If not use DYNAMIC_CAST as this will work without the compiler option.
John
|
|
|
|
|
What is the implication of using virtaul constructors?how to acchieve the model of the same even thogh C++ does not have them?
|
|
|
|
|
tom groezer wrote: virtaul constructors
such a thing doesn't exist... so I don't know where you're taking your questions from, but they're erroneous
|
|
|
|
|
It depends on what you mean. It's true that C++ doesn't support virtual constructors per se, but there is a design pattern called the virtual constructor idiom[^] which may be what the OP is after. Many programmers and designers use the term "virtual constructor" to refer to this idiom and are not talking about literally making constructors virtual.
Steve
|
|
|
|
|
What is your requirement, If you want to hide the details of Object creation,
Refer Factory, builder, .. patterns(Design Patterns)
Contructors are required to identify the class whose object is created. Making it virtual is meaning less.
Best Regards
Raj
|
|
|
|
|
It depends on what you mean. It's true that C++ doesn't support virtual constructors per se, but there is a design pattern called the virtual constructor idiom[^] which may be what the you're after. Many programmers and designers use the term "virtual constructor" to refer to this idiom and are not talking about literally making constructors virtual.
Steve
|
|
|
|
|
|
A constant variable is one that can't be changed (at least the compiler won't let you do it
directly).
In-class means it is a member of a class.
For usage, the section "How do I define an in-class constant?" in Bjarne Stroustrup's
C++ Style and Technique FAQ[^] may help 
Mark
"Posting a VB.NET question in the C++ forum will end in tears." Chris Maunder
|
|
|
|
|
why is v[i] = i++; and f(v[i],i++); deemed inappropiate in C++
|
|
|
|
|
A bit cryptic, maybe confusing, that's all (I dont' deem the above inappropiate).
If the Lord God Almighty had consulted me before embarking upon the Creation, I would have recommended something simpler.
-- Alfonso the Wise, 13th Century King of Castile.
|
|
|
|
|
It's something which has been proposed by Stroustup. Basically it is involvind some kind of two reads in a single operation. Any furtehr light. How to identidy such situation. will a[j] = i++ be appropriate?
|
|
|
|
|
tom groezer wrote: will a[j] = i++ be appropriate?
yes, because the variable you use as an index, is not being modified on the same line of code. i++ means, return i, then increment it. a[j] will definately contain the old value of i. The thing is that when i is incremented is not clear. Does a[i] = i++ set the a at the index equal to the old i, or the new i ? It may be defined ( I don't think it is, I think it's compiler specific ), but it's at least hard to read.
Christian Graus - Microsoft MVP - C++
Metal Musings - Rex and my new metal blog
"I am working on a project that will convert a FORTRAN code to corresponding C++ code.I am not aware of FORTRAN syntax" ( spotted in the C++/CLI forum )
|
|
|
|
|
Christian Graus wrote: I don't think it is, I think it's compiler specific
AFAIK the postfix increment operator acts the following way:
use the current value of the variable in the statement and then increment it.
Christian Graus wrote: but it's at least hard to read.
I completely agree on the above.
If the Lord God Almighty had consulted me before embarking upon the Creation, I would have recommended something simpler.
-- Alfonso the Wise, 13th Century King of Castile.
|
|
|
|
|
CPallini wrote: Christian Graus wrote: I don't think it is, I think it's compiler specific
AFAIK the postfix increment operator acts the following way:
use the current value of the variable in the statement and then increment it.
This is absolutely correct and of course considered C/C++ basics. 
I think Christian meant that the statement
a[i] = i++; is an undefined behavior and the resulting operation is compiler specific.
It's undefined what index of a will be operated on.
If i equals 1 before the statement above, will a[1] be assigned 1 or will a[2] be assigned 1?
"It's supposed to be hard, otherwise anybody could do it!" - selfquote
"High speed never compensates for wrong direction!" - unknown
|
|
|
|
|
IMHO should be always
a[1] = 1;
because a[i] = i++; is one statement.
What do you think about?
If the Lord God Almighty had consulted me before embarking upon the Creation, I would have recommended something simpler.
-- Alfonso the Wise, 13th Century King of Castile.
|
|
|
|
|
CPallini wrote: IMHO should be always
a[1] = 1; because a[i] = i++; is one statement.
What do you think about?
Well, I can agree on that in this context.
However, this can get very complex for the compiler. i++ is a statement that is parsed by the compiler and would generate almost the same instructions if the statement isn't too complex. Consider the following "complier complex" code:
a[i] = foo( i++ ); I would be surprised if the compiler assigned the array index matching i before the incrementation. It will usually put the variable on the stack prior to the function call and then increment it using the incremented i as array index when assigning. This is also how the VC6 compiler resolves the statement.
But...
the VC6 compiler will assign 1 to a[1] with the following statements:
i = 1;
a[i] = i++; This is a simpler statement and then the compiler gets smart, but it doesn't work the same way as in the example above, i.e. if the function call is replaced by simply incrementing the variable it won't assign the same array index. And this is for the same compiler. 
"It's supposed to be hard, otherwise anybody could do it!" - selfquote
"High speed never compensates for wrong direction!" - unknown
|
|
|
|
|
Roger Stoltz wrote: a[i] = foo( i++ );
Actually the VC6 compiler is honestly doing its job, because
foo( i++ ); is by itself a statement.
Anyway I agree on the overall point of view and I will never encourage somebody to write code like that.
If the Lord God Almighty had consulted me before embarking upon the Creation, I would have recommended something simpler.
-- Alfonso the Wise, 13th Century King of Castile.
|
|
|
|
|
I am a new learner of VC++ and usually get good support from code project.
I am facing problem with Streams. I need some kind guidance of some senior programmer.
Problem is that I receive some data in a ISpStreamFormat object. I want to read this data into byte pointers but when I call IStream->Read() functions with a non-zero argument as desired no of bytes to read, read method fails returning STG_E_INVALIDPOINTER message. Only fixing a zero "0" as the desired number of byted does not result in Failure message but it reads nothing.
So please if anybody guids me how to read binary data from ISpStreamFormat stream.
Regrads
Zia
|
|
|
|
|
smzhaq wrote: ISpStreamFormat
Never heard of it. What sort of data are you reading ? Why are the standard C++ streams not sufficient to the task ?
It sounds to me like your stream does not have a proper input source.
Christian Graus - Microsoft MVP - C++
Metal Musings - Rex and my new metal blog
"I am working on a project that will convert a FORTRAN code to corresponding C++ code.I am not aware of FORTRAN syntax" ( spotted in the C++/CLI forum )
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
