|
For future reference, if someone have the problem:
What I needed to do to solve it was:
(the order HAS to be this: )
1. uninstall the .MSI
2. uninstall the .NET framework
3. reinstall the .NET framework
4. apply .NET framework SP2 (don't know if it's required, but I did this way just to be safe)
5. reinstall the .MSI
The tricky part was (1) to uninstall the .MSI, since it was giving the same message when uninstalling. So, the solution was to use a .MSI without the custom actions which install the COM+ components, mantaining the MSI version number and product code. Use this MSI to remove the faulty application. The rest seems necessary to rebuild the GAC again.
I see dumb people
|
|
|
|
|
After install .Net framework, the programme also can't run right( mfc70.dll is not include in framework ). is that other components need install?
|
|
|
|
|
I hope you don't believe MFC has anything to do with the .NET run-time.
|
|
|
|
|
I'm trying to get my hands on the beta2 version of the .NET Compact Framework. Unfourtunatly, it is only available with VS.NET 2003 (VS.NET 2002 will not support smart device extentions).
You'd think after spending about $1000 for MSDN Subscription Professional edition, I could at least get a copy of VS.NET 2003 beta. For some reason, MS chose to only make it available to Universal subscribers, not fair! When I signed up for MSDN Pro, I was told I would get access to all beta versions of operating systems, sdks and visual studio.net.
If anyone can comprehend MS's thought process, please help me out.
|
|
|
|
|
$$$$$ is all that matters to M$. And Bill needs some more since he keeps givig BIG$ away to organizations and nations that don't want it....
R
|
|
|
|
|
And giving away BIG$ is a fantastic tax write-off.
|
|
|
|
|
|
Hi!
There is a need to create a custom run-time form designer under .NET. It
should be pretty similar to the Visual Studio's own designer. Is there any
control providing such functionality? (I tried to pull out smth from Visual
Studio -- no luck).
Could somebody help me?
Thanks!
Regards,
John Wood
|
|
|
|
|
Let's say I have 3 classes.
Class 1 needs to create an instance of Class 2 or Class 3 depending on some evaluation. All three classes reside within the same assembly.
When Activator.CreateInstance() is called does the loaded type get re-jitted even though the caller is in fact the same assembly and has already been jitted?
Just wondering 
Any thoughts on this would be appreciated!!!
Jarrod
|
|
|
|
|
JarrodM wrote:
When Activator.CreateInstance() is called does the loaded type get re-jitted even though the caller is in fact the same assembly and has already been jitted?
Unless you run the ngen utility on your assembly, JITting takes place on a method by method basis. So the JIT should only occur once per method.
James
- out of order -
|
|
|
|
|
So each time I call a method for the first time on one of these classes newly instantiated by reflection it will JIT?
Jarrod
|
|
|
|
|
Sorry, I meant to add that bit in but forgot 
This part is tricky for me to word so please accept my apologies before hand.
JITting occurs when one of a few things happen: A method is being run for the first time, the underlying IL of an already JITted method has changed, or in certain circumstances the native code produced by ngen will be ignored (ASP.NET is one case). There are also some Debug/Profiling methods that will perfrom a re-JIT.
Unless you are causing the JIT by running ngen, the native code generated will be tossed out after the Assembly has been unloaded. The native code generated is also AppDomain specific, so if you have two AppDomains each loading the same assembly then each method will be JITted once for each AppDomain.
Now in your case, the JIT will only occur the first time each method is used, regardless of whether the object using that method is created by Reflection or regular code.
James
- out of order -
|
|
|
|
|
I have a strange problem with a custom control (derives from System.Windows.Control). I've added code to the protected OnKeyDown and OnKeyUp methods of my control to handle up/down/left/right keypresses.
The keys work great most of the time. The one case where they do not work is when my control is used with the System.Windows.Forms.ListBox control. The listbox kills the focus on my control, preventing any keypress events from fireing. Sometimes the listbox takes the focus itself, sometimes not.
Any ideas on what the deal is?  Thanks.
|
|
|
|
|
Jon Rista wrote:
The one case where they do not work is when my control is used with the System.Windows.Forms.ListBox control.
What exactly is the relationship between your custom control and the listbox? Is on embedded within the other, are you superclassing, are they siblings on a form...?
|
|
|
|
|
They are siblings on a form.
After more testing, this seems to be a .NET issue. By default, .NET seems to shift focus when the arrow keys are pressed down. Focus is automatically taken from one control and moved to the next until it hits a control that can keep the focus. For example, if you put a button, a checkbox, a textbox, and a radio button on a form, in top-down order, you can try this:
Click the button. Press down arrow three times. You will see the focus shift from the button, to the checkbox, and stop at the textbox, never reaching the radio button. Somehow the textbox is keeping the focus, although how I do not know.
I need to figure out what .NET does that prevents a custom control derived from the Control class from keeping focus once it has it. Well, rather, keeping focus when the arrow keys are pressed, it keeps focus for all other key events.
|
|
|
|
|
is there any facility available in VISUAL STUDIO .NET editor
to get the class diagram of a given project
|
|
|
|
|
No, you'd have to use Visio 2002 as well in order to get the class modeling features you want.
I don't know whether it's just the light but I swear the database server gives me dirty looks everytime I wander past.
-Chris Maunder
Microsoft has reinvented the wheel, this time they made it round.
-Peterchen on VS.NET
|
|
|
|
|
I've been playing around with the graphics object's transform functions (scale,rotate,translate). While they are useful functions for doing static drawing, they seem to be inefficient when used in a more dynamic drawing environment.
For example, when I need to move images across the surface of a large, background image, and I use ScaleTransform to properly scale all the various components being drawn, the drawing is much more sluggish than when I simple handle the scaling the old-fashioned way (pre-calculate the values and draw all the bitmaps to a scaled rectangle as when BitBlting or strechtblt ).
I am placing the ScaleTransform in my paint function. I see no way to use the Transform functions in the same way that the old Win32/gdi MapMode functions were used (set them once and they are applied on every paint).
Is there something I am missing about how to use the Transforms, or am I just expecting more from them than was intended?
"Any clod can have the facts, but having opinions is an art."
Charles McCabe, San Francisco Chronicle
|
|
|
|
|
Hi,
I don't know if this is the correct forum, but let's try...
I have some componente written in VB.Net that is called by ASP pages.
All of them works fine except for one that gives me the "class doesn't support automation" error message. The only help that I've got was "try to contact the application vendor"...
Running it interactively, I have another error message that I'm trying to work around ("The root transaction wanted to commit, but transaction aborted"), but this is a ContextUtil problem.
All the components have the same imports and inherits clauses and same properties in the packages. Any clue?
Thanks in advance,
Molina.
|
|
|
|
|
If you do, what do you end up with?
I assume that you end up with nothing, and the GC eventualy will take care of anything that gets created in the constructor up until the exception gets thrown.
Am I mistakin'?
Paul Watson wrote:
"At the end of the day it is what you produce that counts, not how many doctorates you have on the wall."
Unknown wrote:
"Don't sweat the petty things, and don't pet the sweaty things."
|
|
|
|
|
I have to keep fighting the urge to assume everthing's like C++, but that seems to be right.
I tried creating an object as described, caught the exception in the function where the object was created, and nothing was returned. That is, since the constructor never finishes, a pointer to the object (ahem, I mean a reference to the "reference type") never gets assigned. I would imagine the object actually gets created on the gc heap before the constructor is called, or else nothing could be assigned in the ctor, but that only the gc knows about it if the ctor fails (interrupted by an exception).
The destructor (finalize method in framework paralance) does eventually get called, when the gc gets around to it. I forced it by calling GC.Collect(), and all was fine.
Cheers
|
|
|
|
|
That's basically right.
The one exception to watch for is if any non-managed memory gets allocated as part of your constructor sequence, you need to put cleanup code in a handler for that case.
Generally you'll know if you're doing this directly, but if you create any objects that implement IDisposable, you should try to call their Dispose method. For example, Windows Forms Controls allocate a window handle. Its better to call Dispose on them before they become unreachable rather than wait for the GC to do it.
Burt Harris
|
|
|
|
|
I'm trying to expose my custom WMI class:
/////////////////////////////////////////////////////
[assembly:Instrumented("Root/Default")]
[System.ComponentModel.RunInstaller(true)]
public class MyInstaller : DefaultManagementProjectInstaller {}
[InstrumentationClass(InstrumentationType.Instance)]
public class InstanceClass : Instance
{
public string SampleName;
public int SampleNumber;
public void DoSomething()
{
//Doing something...
}
}
....
InstanceClass instClass = new InstanceClass();
instClass.SampleName = "Hello";
instClass.SampleNumber = 111;
instClass.Published = true;
/////////////////////////////////////////////////////
But when I try to invoke DoSomething method:
/////////////////////////////////////////////////////
ManagementObjectSearcher s = new ManagementObjectSearcher(new ManagementScope("Root/Default"),new SelectQuery("InstanceClass"));
foreach (ManagementObject ob in s.Get())
{
ob.InvokeMethod("DoSomething",null);
}
/////////////////////////////////////////////////////
I get System.Management.ManagementException stating that this method is not implemented
at System.Management.ManagementException.ThrowWithExtendedInfo(ManagementStatus errorCode)
at System.Management.ManagementObject.GetMethodParameters(String methodName, ManagementBaseObject& inParameters, IWbemClassObjectFreeThreaded& inParametersClass, IWbemClassObjectFreeThreaded& outParametersClass)
at System.Management.ManagementObject.InvokeMethod(String methodName, Object[] args)
at WMIClient.Form1.button1_Click(Object sender, EventArgs e) in e:\_projects_\dotnet_projects\_tests_\wmiclient\form1.cs:line 126
However, I can successfully set and get values of data members:
/////////////////////////////////////////////////////
lb1.Items.Add((string)ob.GetPropertyValue("SampleName"));
/////////////////////////////////////////////////////
Do I need some additional actions to be taken before I call InvokeMethod, or maybe
I have something wrong with the method definition?
Is it possible at all to expose methods in WMI custom classes?
Best regards,
Eugene
|
|
|
|
|
I have a process where I am taking a schema, running a transform against it, and saving the resulting xml file. Today we do this manually with XMLSpy without problems. I would like to change this to be a programmatic function.
When I build my transform wihtin the framework, however, it requires me to feed it only an XML file. If I feed it an XSD file, it runs it through an XML validator and kicks out the file.
Is there a way of running a transform on a schema? Is there some way of turning off the xml validator? (and if so, how?)
Thanks for any input!!!
_____________________________________________
The world is a dangerous place.
Not because of those that do evil,
but because of those who look on and do nothing.
|
|
|
|
|
Is it possible to impersonate the caller of a method that is remoted? I have a remote component (which currently I'm planning to always run on the same machine as the client) that is hosted by a Windows Service. I want to run the service as LocalSystem yet impersonate the client user for some sections of code. Is this possible? Does it require COM+ and does that affect remoting?
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
