|
you can't. You have to write p/invoke signatures that allow you to call methods on the dll, but you can't import it the way you can a COM or managed dll file.
Christian Graus - Microsoft MVP - C++
"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 )
|
|
|
|
|
thanks,
can you explain please how to write p/invoke signatures .
|
|
|
|
|
You use dllimport, as the other poster said, and then you write a signature that matches the method. www.pinvoke.net[^] has lots of examples, it's probably a great place to start.
Christian Graus - Microsoft MVP - C++
"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 )
|
|
|
|
|
Hello,
I am currently working on an app that needs the ability to inquire about capabilities of scanners.
I am using the definitions of this project. The problem that appears here is the use of unmanaged library twain_32.dll. All methods imported with dllimport work fine except the DSCap(...) method returns failure code when inquiring about capabilities.
The method DSCap should set the TwCapability variable that is passed with. This TwCapability is defined in the original header file of the twain_32.dll as follows:
typedef struct {
TW_UINT16 Cap;
TW_UINT16 ConType;
TW_HANDLE hContainer;
} TW_CAPABILITY, FAR * pTW_CAPABILITY;
where TW_UINT16 is defined as "typedef short TW_INT16, FAR *pTW_INT16;"
and TW_HANDLE is defined as "typedef HANDLE TW_HANDLE;"
"ConType" gives information about the type of the container that holds the capabilities information and "hContainer" is the pointer to the real capabilities information data.
This TW_CAPABILITY struct is defined in the c# code as follows:
[StructLayout(LayoutKind.Sequential, Pack = 2)]
internal class TwCapability
{
public TwCapability(TwCap cap)
{
Cap = (short)cap;
ConType = -1;
}
~TwCapability()
{
if (hContainer != IntPtr.Zero)
Twain.GlobalFree(hContainer);
}
public short Cap;
public short ConType;
public IntPtr hContainer;
}
To make things easier for you this is the "step by step guide" of how to inquire scanner capabilities from the official TWAINSpec.pdf taken from www.twain.org:
Step 1:
Application allocates a TW_CAPABILITY structure and fills its fields as follows:
• Cap = the CAP_ or ICAP_ name for the capability it is interested in
• ConType = TWON_DONTCARE16
• hContainer = NULL
Step 2:
Application uses the TW_CAPABILITY structure in a DG_CONTROL /
DAT_CAPABILITY / MSG_GET operation.
Step 3:
The Source examines the Cap field to see if it supports the capability. If it does, it creates
information for the application. In either case, it sets its Return Code appropriately.
Step 4:
Application examines the Return Code, and maybe the Condition Code, from the
operation.
If TWRC_SUCCESS then the Source does support the capability and
• The ConType field was filled by the Source with a container identifier
(TWON_ARRAY, TWON_ENUMERATION, TWON_ONEVALUE, or
TWON_RANGE)
• The Source allocated a container structure of ConType and referenced the
hContainer field to this structure. It then filled the container with values
describing the capability’s Current Value, Default Value, and Available Values.
Based on the type of container and its contents (whose type is indicated by it ItemType
field), the application can read the values. The application must deallocate the
container.
If TWRC_FAILURE and TWCC_CAPUNSUPPORTED
• Source does not support this capability
This is how I try inquiring about the caps:
public void GetCapabilities()
{
TwRC rc;
TwCapability twCap = new TwCapability(TwCap.XferCount);
rc = DScap(appid, srcds, TwDG.Control, TwDAT.Capability, TwMSG.Get, twCap);
if (rc == TwRC.Success)
{
MessageBox.Show("worked!");
}
else MessageBox.Show("not!");
}
I always get TWRC_FAILURE in return, though XFERCOUNT must be supported by every scanner.
I suspect the hContainer variable to be the problem, but I am new to c# and interops.
This is the dllimport of the method:
[DllImport("twain_32.dll", EntryPoint = "#1")]
private static extern TwRC DScap([In, Out] TwIdentity origin, [In] TwIdentity dest, TwDG dg, TwDAT dat, TwMSG msg, [In, Out] TwCapability capa);
I know this is a lot of information, but I hope someone has already worked with TWAIN under .net and can help me fix this problem.
Thx in advance
Dominik
|
|
|
|
|
Hi,
I have a backgroundworker that executes a method that returns a string[].
In turn, that string[] is returned via e.Result.
How do I convert the object e.Result into a string[]?
eg
string[] = fileList;
...
do backgroundwork
...
fileList = e.Result;
Thanks,
Glen Harvy
|
|
|
|
|
fileList = (string[])e.Result;
|
|
|
|
|
|
Which one will be a good practice
using ( class1 c1 = new class1() )
{
}
or
class1 c1 = new class1()
try
{
}
finally
{
c1.Dispose();
}
If first one is good what will happen to the object if any error happened in between the process ? Will it be disposed ?
|
|
|
|
|
using is always good practice. I'd put my try/catch inside the using block, if I felt an exception was likely to occur. I would never write a try block by default. If I don't foresee a possible exception, I want it to throw, so I find out about it.
Christian Graus - Microsoft MVP - C++
"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: using is always good practice.
Thanks,
Assume I am not calling the dispose method and not using the using keyword. Then how long unmanaged object would be in memory ? Or will it automatically disposed when scope ends ?
|
|
|
|
|
N a v a n e e t h wrote: Then how long unmanaged object would be in memory ?
If you create an object which contains an unmanaged object, it will remain active until garbage collection picks the object up. You should not risk this, regardless of the fact that anythign in a using block probably lives for such a short time that it should, in theory, be collected pretty quickly.
Christian Graus - Microsoft MVP - C++
"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: f you create an object which contains an unmanaged object, it will remain active until garbage collection picks the object up
The garbage collector will not pick up an unmanaged object. That's why it is called unmanaged.
Or am I missing something?? Must be the case then Christian is always right, isn't he?
-^-^-^-^-^-
no risk no funk ................... please vote ------>
|
|
|
|
|
I am assuming that the 'unmanaged object' is something that is being held in a managed object, for example, a HDC in a graphics object. In this instance, when the graphics object is finalised, it should release the HDC. I was wording my reply carefully, I wasn't sure if he realised that an IDisposable is, by definition, a managed object. Of course, if you create an HDC directly via p/invoke, no GC will ever occur, nor is the object going to impliment IDisposable, making the whole discussion moot.
Christian Graus - Microsoft MVP - C++
"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 )
|
|
|
|
|
They both to the same (well using first checks if c1 isn't null) but the first one is easier to understand and use 
|
|
|
|
|
OK, I thought that at first, but I wasn't sure if using generates the try block. I guess it's the logical thing for it to do.
Christian Graus - Microsoft MVP - C++
"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 )
|
|
|
|
|
These are essentially the same thing. The using statement is "syntactic sugar" that provides an easier way to write a try/finally block. That being said, the using is the recommended "best practice" because it guarantees that the pattern is followed properly (even if that pattern changes at some point in a future release of .NET) and is easier to read.
N a v a n e e t h wrote: what will happen to the object if any error happened in between the process ? Will it be disposed ?
Since they are equivalent, the behavior would be the same as you get with the try/finally block.
|
|
|
|
|
Hello, iv recently started to use C#, and now iv found i want to wait for an event. Im writing an application that reacts to diffrent Windows Live Messenger events. For instance, plays a sound when a message is receieved.
Im using the IMessengerAPI by adding a com reference to it in my project. I don't really need to do anything in my applications unless there is an event to react to. So i just want it to Sleep(); while there are no events, and then when an event arrives, handle it, and then go back to sleep.
So i need to create a function, WaitForAnyOfTheMsnAPIEvents(); or something like that. That Sleeps the application while it listens for events. How do i do this?
<br />
static class Program<br />
{<br />
static MessengerAPI.Messenger MSN = new MessengerAPI.Messenger();<br />
<br />
[STAThread]<br />
static void Main()<br />
{<br />
MSN.OnIMWindowDestroyed += new MessengerAPI.DMessengerEvents_OnIMWindowDestroyedEventHandler(MSN_OnIMWindowDestroyed);<br />
<br />
while(true)<br />
{<br />
WaitForAnyOfTheMsnAPIEvents(); }<br />
}<br />
<br />
static void MSN_OnIMWindowDestroyed(object pIMWindow);<br />
}<br />
Sorry if im stupid, im very new to C#, but i think this should be possible, in C++ you could do something similiar for events, WaitForMultipleObjects() etc..
Thanks in advance.
|
|
|
|
|
Just write a windows program which does nothing, this will create a message pump that will then respond to any messages that occur. It's automatic, just like it was in C++. WaitForMultipleObjects was something different, you can do that in C#, also.
Christian Graus - Microsoft MVP - C++
"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 )
|
|
|
|
|
Ahh i see! Thanks, but how do i create a windows program without a window, that still has a messagepump? Could you point me in the right direction? My application dosn't need a window, it uses messagebox popups.
|
|
|
|
|
One simple way would be to create a window that is not visible and does not appear in the taskbar. I'd expect you'd want your app either in the taskbar or the system tray, tho, so users can interact with it, even if only to exit it.
Christian Graus - Microsoft MVP - C++
"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 )
|
|
|
|
|
Hi!
You can achieve this very easily by replacing your while(true) loop with a call to Application.Run().
To shut down the application just call Application.Exit() (in the OnIMWindowDestroyed event handler, for example).
Regards,
mav
--
Black holes are the places where God divided by 0...
|
|
|
|
|
Hai every body,
I have to display a message box from a windows service.
Best Regards,
M. J. Jaya Chitra
|
|
|
|
|
A windows service has no user interface because it can start running before a user has logged into the system and will continue to run when they log off.
|
|
|
|
|
Can you give me a solution to do this.
Can i create a form in the service and show that form with that message by calling it.
Best Regards,
M. J. Jaya Chitra
|
|
|
|
|
If you can get a handle to the desktop window, then you can make that the parent of your message box. I think you need p/invoke for this, but you may not.
Christian Graus - Microsoft MVP - C++
"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
