|
I totally agree with you, but that´s not the point 
The studio can create references to any registered component on the system. So I´m sure there is a way to do the same !?
|
|
|
|
|
What do you mean, "The studio can create references to any registered component on the system."? Your project needs to reference the assemblies required by your project, period. When you add components, the assemblies in which that component and its dependencies are defined are added automatically if they aren't added already, but only when you use the designer. If you manually type the code, it does not do this automatically. It's all because of the designer.
If you're talking about the assemblies that show up in the Add Reference dialog, you can add additional directories in which to search in the HKEY_LOCAL_MACHINE\Software\Microsoft\.NETFramework\Assembly folders key.
If you don't want to worry about where assemblies are located (even though VS.NET will copy assemblies to the application directory that aren't installed in the GAC), you can use gacutil.exe to add assemblies to the Global Assembly Cache (GAC), or drag-n-drop the assemblies into the %WINDIR%\assembly directory.
This is no different than any other language or platform, as I said before. In Java, the classes or JAR files have to be in the CLASSPATH when compiling or running the application (you can override the CLASSPATH on the command line, though). In Win32, libs must be linked in when compiling and the DLLs must either be in the application directory or in a directory in the PATH environment variable. In linux, the shared objects must be in a lib directory configured in the SO cache. With COM, a CLSID is used but that CLSID must be registered on the system, in which case the path to the file is specified in the registry, or a file can be referenced that is already in a PATH directory (though not recommended).
That's just how everything works. The only assembly that doesn't show up in the references is mscorlib.dll, which is implied by the compiler unless overridden (possible in the VS.NET 2003 C# project properties, or using the command-line compiler since .NET 1.0 (v1.0.3705)).
-----BEGIN GEEK CODE BLOCK-----
Version: 3.21
GCS/G/MU d- s: a- C++++ UL@ P++(+++) L+(--) E--- W+++ N++ o+ K? w++++ O- M(+) V? PS-- PE Y++ PGP++ t++@ 5 X+++ R+@ tv+ b(-)>b++ DI++++ D+ G e++>+++ h---* r+++ y+++
-----END GEEK CODE BLOCK-----
|
|
|
|
|
Ok, thank you for your detailed describtion !!
In my case it´s a com dll I want to load by manually typeing the code (that´s why I was talking about registered components). The reason is that I don´t want that people, using my code in their own projects, have to care about the references I need. I want to enable my code to collect everything it needs on it´s own.
|
|
|
|
|
Sure you can redefine the COM interfaces you require in your source, but you have to worry about instantiating, casting, marshaling, and more. Using tlbimp.exe or aximp.exe to create a Runtime Callable Wrapper (RCW), or interop assembly, is much easier. Besides, whether or not other developers use that interop assembly is moot - they can just as easily create their own! Remember, an RCW isn't the COM object - thus containing the code - itself, but just a wrapper. So long as that COM object is installed on the target machine, anyone can create an interop assembly from it. And there's will be no different from yours except, perhaps, differing only by the public key token if you sign the interop assembly when you create it.
Depending on the complexities of your COM object, manually defining all this stuff can be tedious, if not a waste of time.
-----BEGIN GEEK CODE BLOCK-----
Version: 3.21
GCS/G/MU d- s: a- C++++ UL@ P++(+++) L+(--) E--- W+++ N++ o+ K? w++++ O- M(+) V? PS-- PE Y++ PGP++ t++@ 5 X+++ R+@ tv+ b(-)>b++ DI++++ D+ G e++>+++ h---* r+++ y+++
-----END GEEK CODE BLOCK-----
|
|
|
|
|
Finally it works by invoking the methods on the object, created through the assembly, but I guess you are right. Compared with the two short mouse clicks you need to add a reference it´s really a waste of time.
And using the rcw wrapper class is simply much more comfortable.
Hmm.. so everything will remain unaffected, just explored a little more of the .new world 
Thanks to all of you for your help...
|
|
|
|
|
You can use reflection to load an assembly.
<br />
Assembly a = Assembly.LoadFrom("your.dll");<br />
Type t = a.GetType("namespace.classname");<br />
MethodInfo m = t.GetMethod("method");<br />
object o = Activator.CreateInstance(t);<br />
object result = m.Invoke(o,new object[]{parameters});<br />
If you want to avoid call methods in this way, you can also create an interface with all the necessary information about the dll and when you call CreateInstance just cast to it. For instance:
<br />
public interface IAnInterface<br />
{<br />
void Method();<br />
}<br />
.......<br />
<br />
IAnInterface anInterface = (IAnInterface)o.CreateInstance(atype);<br />
IAnInterface.Method();<br />
|
|
|
|
|
I type mismatched the last line
should be "anInterface.Method();" instead of "IAnInterface.Method();"
it was evident but .....
|
|
|
|
|
In fact I´ve already tried it the first way, but didn´t know how to call methods on my created object. Simply connecting an interface pointer to my object never worked...
The second way seems to be pretty smart, so I will try something like that.
Thanks for your inspiration !!!
|
|
|
|
|
You cast the object that you get from Activator.CreateInstance to whatever class or interface it is. The assembly still has to be resolvable by either being in the application directory, a private path, the Global Assembly Cache, or by an implementation in your handler for the AppDomain.AssemblyResolve event. If the assembly can't be found that contains the Type, you'll get a TypeLoadException. Note that there is a significant performance issue using this over direct instantiation.
-----BEGIN GEEK CODE BLOCK-----
Version: 3.21
GCS/G/MU d- s: a- C++++ UL@ P++(+++) L+(--) E--- W+++ N++ o+ K? w++++ O- M(+) V? PS-- PE Y++ PGP++ t++@ 5 X+++ R+@ tv+ b(-)>b++ DI++++ D+ G e++>+++ h---* r+++ y+++
-----END GEEK CODE BLOCK-----
|
|
|
|
|
I see you've told others they kind of missed the point, maybe you were looking for this?
Perhaps what you are looking for is a dynamically loaded dll, as in a plug-in type senario.
The author of the excellent DotNetMagic library has written this article that may turn a lightbulb on in your head:
http://www.divil.co.uk/net/articles/plugins/plugins.asp
/**********************************
Paul Evans, Dorset, UK.
Personal Homepage "EnjoySoftware" @
http://www.enjoysoftware.co.uk/
**********************************/
|
|
|
|
|
HOW TO CHECK IN A TEXT BOX WHETHER THE INPUT VALUE IS STRING OR NUMERIC VALUE
|
|
|
|
|
A down and dirty way is to convert the text to a number in a try-catch block. If an exception is thrown, then ....
I'm trapping on the KeyPressed event and checking each key pressed. If it isn't the key I want, I disregard it.
If anyone has a better way of doing this, I would like to see it.
Larry J. Siddens
|
|
|
|
|
As the previous reply mentioned, you can do something like this:
public bool IsNumeric(TextBox tb)
{
try
{
Int32.Parse(tb.Parse);
}
catch
{
return false;
}
}If you need to check larger values or decimal values, you could replace Int32 with Int64 (long) or Double (double), respectively. If you want to allow other characters like a group separator ("." or ",", depending on the current culture), currenty symbols, etc., use the Int32.Parse(string, NumberStyles) overload and see the documentation for the NumberStyles enum for more information.
Also, in the future please do not use all caps. Most times, it's considered flaming (yelling at someone) - which most likely you didn't intend - but it still makes it hard to read.
-----BEGIN GEEK CODE BLOCK-----
Version: 3.21
GCS/G/MU d- s: a- C++++ UL@ P++(+++) L+(--) E--- W+++ N++ o+ K? w++++ O- M(+) V? PS-- PE Y++ PGP++ t++@ 5 X+++ R+@ tv+ b(-)>b++ DI++++ D+ G e++>+++ h---* r+++ y+++
-----END GEEK CODE BLOCK-----
|
|
|
|
|
Heath,
How you doing? Have you used the method "TryParse"? I see that as a method in the System.Double class.
Larry J. Siddens
|
|
|
|
|
If you read the documentation, this is just like Parse but it try/catches internally and returns a boolean if the value could be successfully parsed. If it could, the out param contains the value, something similar to this:
public static bool TryParse(string s, NumberStyles style,
IFormatProvider provider, out double result)
{
try
{
result = double.Parse(s, style, provider);
}
catch
{
return false;
}
}It just depends on whichever you want to use. If you don't want to handle exceptions yourself, use Double.TryParse.
-----BEGIN GEEK CODE BLOCK-----
Version: 3.21
GCS/G/MU d- s: a- C++++ UL@ P++(+++) L+(--) E--- W+++ N++ o+ K? w++++ O- M(+) V? PS-- PE Y++ PGP++ t++@ 5 X+++ R+@ tv+ b(-)>b++ DI++++ D+ G e++>+++ h---* r+++ y+++
-----END GEEK CODE BLOCK-----
|
|
|
|
|
Thanks for the reply Heath!
Larry J. Siddens
|
|
|
|
|
What about using regular expressions?
Something like:
public bool IsNaturalNumber(string sValue)
{
return (Regex.IsMatch(sValue, @"0*[1-9][0-9]*") && !Regex.IsMatch(sValue,@"[^0-9]"));
}
|
|
|
|
|
Sure, but keep in mind that regular expressions are inherently slower than simple string parsing. If you will be using this regex several times, you should at least compile it. This will boost performance a bit, but it will still be slower than just parsing a string, especially in such an easy case.
-----BEGIN GEEK CODE BLOCK-----
Version: 3.21
GCS/G/MU d- s: a- C++++ UL@ P++(+++) L+(--) E--- W+++ N++ o+ K? w++++ O- M(+) V? PS-- PE Y++ PGP++ t++@ 5 X+++ R+@ tv+ b(-)>b++ DI++++ D+ G e++>+++ h---* r+++ y+++
-----END GEEK CODE BLOCK-----
|
|
|
|
|
Jose Fco Bonnin wrote:
@"0*[1-9][0-9]*"
WTF? Firstly, why not use @"\d+" ? And what is the purpose of the "prepended" zero's? And lastly, why test it again (not correctly even!) ? Very counter-productive...
leppie::AllocCPArticle("Zee blog");
Seen on my Campus BBS: Linux is free...coz no-one wants to pay for it.
|
|
|
|
|
if you use @"\d+" and your string is "aaaa1" the result will be true.
|
|
|
|
|
Oops, just forgot the line markers, should be @"^\d+$". 
leppie::AllocCPArticle("Zee blog");
Seen on my Campus BBS: Linux is free...coz no-one wants to pay for it.
|
|
|
|
|
Thank you Bonnin, it works fine. can u explain the whole stuff,
ie why we want 0,*.......
all i changed \p{Nd} instead of [0-9] and it works fine since i use unicode.
those who reponded to my query once again, thanks a lot.
|
|
|
|
|
Hi everyone,
I did not know where else to post this.
I am using MS XP Office Web Components in C# to generate an excel file using the spreadsheet component. I do not want to use the Excel COM object for various reasons.
My problem is that I could not find any way to set the header and footer property of a Worksheet object. In Excel you can set the header and footer for every worksheet. I wanted to do the same with the spreadsheet component in OWC10. However, I have had no luck finding an API for this.
If anyone has any idea on how to accomplish this, I would really appreciate it.
Thanks,
Pankaj
Without struggle, there is no progress
|
|
|
|
|
Greetings
I'm trying to create an CaptureBuffer object. When the constructor is called in run-time I get the following error: value does not fall within the expected range.
My code looks like this:
g = DSoundHelper.DefaultCaptureDevice;
Microsoft.DirectX.DirectSound.Capture c = new Microsoft.DirectX.DirectSound.Capture(g);
CaptureBufferDescription cbd = new CaptureBufferDescription();
cbd.Format = soundbuffer.Format;
cbd.BufferBytes = caps.BufferBytes;
cbd.ControlEffects=false;
cbd.WaveMapped=false;
cbd.ControlEffects=false;
cb = new CaptureBuffer(cbd,c); // Here I get the error.
Please help I'm stuck with this error for two days..
Kind Regards
Shimi
|
|
|
|
|
I'm replying for myself but I located the bug.
The caps object wasn't intialized!
Shimi
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
