|
I know you know. There was just great confusion. 
|
|
|
|
|
code like this:
class Your
{
public:
My my[3];
};
class My has no default constructor, as:
class My
{
public:
My(int iv)
{
}
};
how do you init class array my[3]?
is it impossible?
|
|
|
|
|
I'm not near a compiler, but it *might* work...
If Your::My was not an array, then you could do this:
Your::Your ()
: My (42)
{
}
I'm wondering if:
Your::Your ()
: My [0](42), My [1](420), My [2](3)
{
}
would work.
Iain.
I am one of "those foreigners coming over here and stealing our jobs". Yay me!
|
|
|
|
|
A class is responsible for its data members. An external user thus shouldn't care what the class does with the data members. And the class itself should add a default ctor if there is a need.
And the initial value will be zero so is that not sufficient?
If you are trying to circumvent the class itself without altering the code, then you can manipulate it via a pointer. That of course requires a bit of spelunking as to the exact data in the class, but with your example it should be just a zero offset.
|
|
|
|
|
The particular condition "array of objects without default constructor" makes, as far as I know, your code not viable. The easiest workaround is, in my opinion, adding the default contructor to your My class.
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.
This is going on my arrogant assumptions. You may have a superb reason why I'm completely wrong.
-- Iain Clarke
[My articles]
|
|
|
|
|
The only way to initialize standard arrays is aggregate initialization:
My my[] = {3,5,11};
My my3[3] = {3,5,11};
My my4[4] = {3,5,11};
The easiest way to solve your problem thus would be to add a default constructor to class My.
If that isn't an option, you can work around this issue by separating the allocation of the required memory and its initialization like this:
class My {
int val;
public:
My(int i) : val(i) {}
int get() const {return val;}
};
class Your {
char myPlaceHolder[3][sizeof(My)];
My* my;
public:
Your()
{
my = (My*)(myPlaceHolder);
new (&my[0]) My(3);
new (&my[1]) My(5);
new (&my[2]) My(11);
}
int operator[](int i) const { return my[i].get(); }
};
void testYour() {
Your your;
std::cout << "my[0]="<<your[0] << " ; my[1]="<<your[1] << " ; my[2]=" <<your[2] << std::endl;
}
The function testYour() will print "my[0]=3 ; my[1]=5 ; my[2]=11"
|
|
|
|
|
Hi everyone
I'm interested in coding programs that work with the web.
Most of the times, I need to host some web-browser in my application and use CHtmlView for it.
I would like to try to host Firefox in my applications too. Since it is opensource, is not it possible to use it in the mfc application?
Thank you in advance.
|
|
|
|
|
May be it doesn't suppsoed.
|
|
|
|
|
There is an article at https://developer.mozilla.org/en/Gecko_Embedding_Basics[^] which covers the basics on embedding the gecko engine into a program.
The fact that you are using MFC is meaningless, you may need to make a wrapper class, but it will work.
You may also want to look at the SpiderMonkey[^] article too, as that may help if you are wanting to use JavaScript.
|
|
|
|
|
You could possibly take the source code of Firefox and extract the parts that make up the actual browser control and include that in your application, but I do not think it would be an easy task.
I must get a clever new signature for 2011.
|
|
|
|
|
msn92 wrote: Since it (firefox) is opensource, is not it possible to use it in the mfc application?
is your program open source ?
Watched code never compiles.
|
|
|
|
|
LPBYTE bReadFile(DWORD sizeToRead)
{
LPBYTE _b = new BYTE[sizeToRead];
ReadFile(_handle,_b,sizeToRead,&dwReadSize,NULL);
return _b;
}
int main()
LPBYTE reader;
reader = bReadFile(512);
how to free the variable LPBYTE reader;
as it is not initialized using new/malloc, so i cannot use delete[]/free.
LPBYTE reader
Need Help
Some Day I Will Prove MySelf :: GOLD
|
|
|
|
|
simply delete it
delete reader
goldenrose9 wrote: as it is not initialized using new/malloc, so i cannot use delete[]/free.
You are returning the new'ed _b, which in turn gives you back the ref of _b. So, even though you did not do new on reader, it still points to the same mem as _b and is ok to call delete on it.
|
|
|
|
|
Yusuf wrote: delete reader
when i call delete reader then
Debug Assertion Failed error occurs.
Some Day I Will Prove MySelf :: GOLD
|
|
|
|
|
Which form of delete are you calling? As you've allocated the block of memory using the array form of new you have to delete it the same way (e.g. use delete [] reader; NOT delete reader;).
Cheers,
Ash
|
|
|
|
|
i had tried both
delete reader and
delete []reader
Some Day I Will Prove MySelf :: GOLD
|
|
|
|
|
In that case it sounds like you're mangling the heap somehow - some other pointer related operation is destroying a heap data structure so it can't work out what to do with the pointer you're giving it. The best thing to do in this case (which isn't practical in every case) is to go on a pointer purge and convert them to slightly less dangerous objects. In the short term check that the memory around your buffer isn't scribbled on by something else during it's lifetime.
Cheers,
Ash
|
|
|
|
|
It looks like you're getting confused by what a pointer is. A pointer is just a variable that can be set to the addresses of arbitrary chunks of system memory. You don't need to "free" reader but you have to release whatever it points to back to the compiler's runtime. In the case you've presented all you have to do is:
delete [] reader;
when you've finished with the block of memory the pointer points to.
However the way you've written the code is a bit crap - if anything throws an exception between calling bReadFile and the delete you're going to leak memory. Instead of using an array consider using something with a bit more behavioural intelligence - e.g. std::vector. Then you'll not have to worry about cleaning up after yourself:
std::vector<char> read_from_file( std::size_t bytes_to_read )
{
std::vector<char> bytes_read( bytes_to_read );
std::size_t number_bytes_read = 0;
ReadFile( handle_of_file, &bytes_read[ 0 ], &number_of_bytes_read, 0 );
return bytes_read;
}
The code there will be within 5% of the performance of what you've written (faster on some compilers as there's no pointer aliasing) AND exception safe.
Cheers,
Ash
PS: Anyone who thinks there's an expensive copy of the vector returned to the caller should upgrade their compiler.
|
|
|
|
|
Since you're bringing performance up, the output parameter alternative might be a lot faster under some conditions. Especially when you're calling read_from_file() several times in a loop, which is most likely.
std::vector<char>& read_from_file( std::size_t bytes_to_read, std::vector<char> &bytes_read )
{
bytes_read.reserve( bytes_to_read );
std::size_t number_bytes_read = 0;
ReadFile( handle_of_file, &bytes_read[ 0 ], &number_of_bytes_read, 0 );
bytes_read.resize(number_of_bytes_read);
return bytes_read;
}
Edit: Forgot to resize the vector.
home
modified on Saturday, February 12, 2011 12:57 PM
|
|
|
|
|
3rd parameter is missing in the ReadFile()
 nice info about output parameter.
here <char>is returned from the function. Can i use BYTE instead of char to read the file, is it ok or not.
Niklas Lindquist wrote: bytes_read.reserve( bytes_to_read );
MODIFIED :
<pre>std::vector<std::string> bytes_read;</pre>
I guess bytes_read is a string type.
I was bit confused. Now its ok.
Some Day I Will Prove MySelf :: GOLD
modified on Sunday, February 13, 2011 2:14 AM
|
|
|
|
|
goldenrose9 wrote: 3rd parameter is missing in the ReadFile()
You're quite right, and there's a misspelled one as well.
goldenrose9 wrote: Can i use BYTE instead of char to read the file
std::vector<BYTE> bytes_read; will do just fine. It really depends on how you would like to use the result.
However
std::vector<std::string> bytes_read; gives me the chills here. What exactly did you mean?
|
|
|
|
|
I'd have said that was true 10 years ago, but these days compilers have made that sort of trick fairly pointless. When compilers see a function of the form:
A some_function()
{
A a;
return a;
}
they're allowed (by the standard) to rewrite it as:
void some_function( memory_block_the_size_of_a &a )
{
new( &a ) A;
}
The compiler then converts the calls to that function from:
A a = some_function();
to something like:
memory_block_the_size_of_a block;
A &a( *reinterpret_cast<A *>( block ) );
some_function( &block );
a->~A();
which removes the copy construction which would normally happen with this sort of construct. The transformation the compiler does is a bit hard to represent in C++ as what it produces is usually exception safe while the representation I've done above isn't. That's the beauty of being a compiler I suppose!
This transformation is called NRVO (named return value optimisation). It's fairly unique in that it's one of the few transformations the compiler may or may not do to some code which change it's visible behaviour. NRVO was implemented in VC++ 2005 and at least gcc 4.0, but it might have been a version or two earlier, can't remember without checking.
Anyway, while you can use a reference parameter it (in my opinion at least) makes your code a lot more stilted as you end up writing two lines where you only needed one which was a direct statement of what you were trying to achieve. If you use the double ended reference type of function then you can actually end up with slower code if someone writes (naively):
A a = some_function( b );
as you still end up triggering the copy constructor. So the moral here is either provide an in/out parameter or return by value - don't fall halfway between.
Lest anyone gets a bit slap happy and starts changing large swathes of code to this style it's worth noting that the compiler can't apply NRVO if:
- The thing being returned isn't named (that's the named bit...)
- There are multiple exits from the function, even if they're all returning the same thing
- It's assignment not copy construction (so A a = some_function() can invoke NRVO while a = some_function() won't).
In addition vendors don't have to implement it but most do - if they didn't they'd just make their compilers seem bad.
While I'm banging on I should mention there's a similar optimisation for functions with a single return of an unamed temporary object called RVO. I'll only bother talking about it if there's any interest though!
Cheers,
Ash
|
|
|
|
|
As far as I know, NRVO would still have to issue a call the constructor of the return value every time the function is called. This constructor will then allocate heap memory for the vectors internal buffer. While NRVO will be reusing the same stack space for the vector object, it would not be able to re-use the memory for the internal buffer over subsequent calls to the function. The following usage of the function would only yield a single memory allocation, vector.reserve() in read_from_file(), no matter how many calls you make.
const size_t wanted_chunk_size = 512;
std::vector<char> buffer;
do
{
read_from_file(wanted_chunk_size, buffer);
write_to_somewhere(buffer);
}
while (buffer.size() == wanted_chunk_size);
I might have to brush up on NRVO though. Please correct me if I'm wrong.
I always find your posts interesting to read, so if you have time for an RVO post, that would be appreciated.
|
|
|
|
|
Aescleal wrote: you can actually end up with slower code if someone writes (naively):
A a = some_function( b );
as you still end up triggering the copy constructor.
Aescleal wrote: - It's assignment not copy construction (so A a = some_function() can invoke NRVO while a = some_function() won't).
Should I go sip another coffee or is there a contradiction? 
Otherwise: great post!  Didn't know about NRVO. You just gave me another weapon to fight multiple returns! 
|
|
|
|
|
I think you can have that coffee. For NRVO to kick in, the returned value has to be created within that function.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
