|
Is the result of the sizeof operator determined by the compiler or filled in by the linker?
Consider the following:
My C++ project links with a commercial static library. The provider of the static library has supplied header files for the classes contained therein.
These header files describe the public interfaces of the classes, but do not reveal the private members.
Therefore, how does the build system know the size of a certain class if all I have is a header file with only the public interface?
The difficult we do right away...
...the impossible takes slightly longer.
|
|
|
|
|
You cannot use incomplete types with the sizeof operator.
«_Superman_»
I love work. It gives me something to do between weekends.
Microsoft MVP (Visual C++) (October 2009 - September 2013) Polymorphism in C
|
|
|
|
|
Thank you.
The difficult we do right away...
...the impossible takes slightly longer.
|
|
|
|
|
Richard Andrew x64 wrote: These header files describe the public interfaces of the classes, but do not
reveal the private members.
The class must be declared in the header file else you would have a load of 'undefined type' errors and the class must have its provate members too.
|
|
|
|
|
Thank you.
The difficult we do right away...
...the impossible takes slightly longer.
|
|
|
|
|
If there are no private members in these headers then there are none! In C++ you cannot hide the members of a class. However, the class supplied in the header may just be an interface, and the actual implementation may come from a derived class which you don't know (and don't need to know) the definition of! If the class in question has no public constructor, this is a sign that it is in fact an interface. Instead it may provide some sort of "create" function.
Here as an example for the public interface of such a library:
class ILog {
public:
static ILog* createInstance(const std::string& name); virtual ~ILog() {}
virtual void Info(const std::string& context, const std::string& message)=0;
virtual void Warning(const std::string& context, const std::string& message)=0;
virtual void Error(const std::string& context, const std::string& message)=0;
};
And hidden in your library, this may be the implementation class:
class CLog : public ILog {
std::string name_;
public:
CLog(std::string& name) : name_(name) {} virtual ~CLog() {}
virtual void Info(const std::string& context, const std::string& message);
virtual void Warning(const std::string& context, const std::string& message);
virtual void Error(const std::string& context, const std::string& message);
};
ILog* ILog::createInstance(const std::string& name) {
return new CLog(name);
}
GOTOs are a bit like wire coat hangers: they tend to breed in the darkness, such that where there once were few, eventually there are many, and the program's architecture collapses beneath them. (Fran Poretto)
|
|
|
|
|
Stefan_Lang wrote: However, the class supplied in the header may just be an interface, and the actual implementation may come from a derived class which you don't know
OH, I see. That's quite clever.
The difficult we do right away...
...the impossible takes slightly longer.
|
|
|
|
|
Stefan_Lang wrote: and the actual implementation may come from a derived class which you don't know
(and don't need to know) the definition of
But wil still have to be declared in a header file included in the file the derived class' is declared in otherwise it still wont compile.
|
|
|
|
|
Only the distributor of the library will need to compile the derived class, not the person using the API!
GOTOs are a bit like wire coat hangers: they tend to breed in the darkness, such that where there once were few, eventually there are many, and the program's architecture collapses beneath them. (Fran Poretto)
|
|
|
|
|
I meant his code, not the library. If the class definition is in a header and is being used, then all its base classes will also have to be declared.
|
|
|
|
|
Erudite_Eric wrote: If the class definition is in a header and is being used, then all its base classes will also have to be declared.
In the example and per the answer given it is child classes, not base classes, that are being hidden.
|
|
|
|
|
The OP didnt mention base or derived classes.
|
|
|
|
|
Erudite_Eric wrote:
The OP didnt mention base or derived
classes.
You didn't respond to the OP. You responded to the second posters example and a comment that poster made about the that example.
|
|
|
|
|
Please reread my example: the CLog definition and declaration only goes into the library code! Only the ILog definition goes into the public API: since that one is a base class it is self-sufficient: there is no other definition or header file required!
On a sidenote, we've been using that very technique for years: the APIs don't have any data members, and in many cases we don't have the slightest idea how the actual implementatuion looks like.
GOTOs are a bit like wire coat hangers: they tend to breed in the darkness, such that where there once were few, eventually there are many, and the program's architecture collapses beneath them. (Fran Poretto)
|
|
|
|
|
I didnt say you werent using your tecnique but the OP asked about the class definition in the header. If it isnt defined it wont compile. Period.
modified 29-Nov-13 8:06am.
|
|
|
|
|
That is not the point at all. The OP wondered about class definitions that don't contain data members. I explained how an API can work without data members by just defining interface classes without data. The API only provides the interface headers. The ILog definition and any call to it will compile just fine without ever seeing the CLog implementation. That's what we did, and apparently that's what the library mentioned in the OP does, too.
GOTOs are a bit like wire coat hangers: they tend to breed in the darkness, such that where there once were few, eventually there are many, and the program's architecture collapses beneath them. (Fran Poretto)
|
|
|
|
|
Stefan_Lang wrote: That is not the point at all.
Just noting that I agree with you that the other response was off base.
|
|
|
|
|
hi all,
how to know the process(self and others) is run as admin privileges or not,
I read the process information using PROCESSENTRY32 ,here no option to get information about the process running state.
thanks.
|
|
|
|
|
|
it just get the process by its name not the information about process running state (its run from admin or not)
|
|
|
|
|
You have to open the process token, then check to see which group the user is a member of.
I don't recall the functions involved, but if you google, you'll find it.
The difficult we do right away...
...the impossible takes slightly longer.
|
|
|
|
|
Run this piece of code -
HANDLE hProcess = ::GetCurrentProcess();
HANDLE hToken;
::OpenProcessToken(hProcess, TOKEN_QUERY, &hToken);
PTOKEN_ELEVATION_TYPE ele = 0;
DWORD dwLen;
::GetTokenInformation(hToken, TokenElevationType, (LPVOID)ele, 0, &dwLen);
ele = (PTOKEN_ELEVATION_TYPE)::HeapAlloc(GetProcessHeap(), HEAP_ZERO_MEMORY, dwLen);
::GetTokenInformation(hToken, TokenElevationType, (LPVOID)ele, dwLen, &dwLen);
ele will be TokenElevationTypeFull if run with admin privileges and TokenElevationTypeLimited if not.
The above code will check the current process.
To check for other processes, as others have said, you need to open the process to get its handle.
«_Superman_»
I love work. It gives me something to do between weekends.
Microsoft MVP (Visual C++) (October 2009 - September 2013) Polymorphism in C
|
|
|
|
|
thanks to all of you for valuable suggestion and help.
thanks alot.
but i have one another problem this works on vista and 7 but on XP, GetTokenInformation fail with invalid parameter.
please help me for this.
thanks.
modified 27-Nov-13 8:03am.
|
|
|
|
|
I am trying to get users name using traversing c:\users but I am getting 3 user name extra which does not in that folder i.e. All Users, Default User, Public.
How can I get exact users name?
|
|
|
|
|
john5632 wrote: How can I get exact users name?
Which one? The one logged in to the PC? The one running your program? Be specific. Have you looked into GetUserName()?
"One man's wage rise is another man's price increase." - Harold Wilson
"Fireproof doesn't mean the fire will never come. It means when the fire comes that you will be able to withstand it." - Michael Simmons
"Show me a community that obeys the Ten Commandments and I'll show you a less crowded prison system." - Anonymous
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
