|
I know it's probably more complicated than I understand, but to me a dll is just a library of functions that you add to your class with a using statement. In C# I believe you create it as a class library, then use the class member methods in your form or console app to accomplish useful things. Keep in mind, of course, that as a programmer I'm a complete idiot, barely functional, but I do manage to make things I need to have work somehow. I could be giving you bad advice, but it seems to me that you might want to create a class library to hold all the useful functions you use in multiple places, a Windows Form for the user interface, and a "something else" that actually controls all the interactions. The GUI part should really only handle display and input, then pass inputs to something else for handling, and respond to events for things that need to be displayed. Your class library would contain the functions that do all the heavy lifting.
In website development, there's a model called MVC - I don't know if it's applied to desktop apps, but I see no reason not to. I once reviewed a book on the subject, and got a free copy of the book when it was finally published, and I was much impressed by the logic of this approach. Your Model (M) would include the class library with all of the workhorse bits, the View (V) would just accept input and display results, and your Controller (C) would contain the state machine and event handlers that make everything happen. To my thinking, this would save you some work, as the command line version of your app could actually be the Controller, using a constructor that accepts the initial inputs on the command line, instead of being provided by your GUI interface. C# allows multiple constructors, so long as the signature is different for each, IIRC.
Of course, I could be leading you astray, being just a hobbyist who will never be an expert, as the majority of our members are. But that's the way I'd tackle it, then if I was completely wrong I'd come back here and beg for help. If it makes sense to you, give it a try... Good luck, and you might have the beginnings of a good article here. Keep that in mind... 
Will Rogers never met me.
|
|
|
|
|
using statements just allow you to elide the namespace name when you're typing a class name. To add a library to the available classes, you need to reference it: Add Reference to the project in an IDE, or use /r with csc.
|
|
|
|
|
Roger Wright wrote: In C# I believe you create it as a class library,
Just to note that that is in fact exactly what it is called at least in Visual Studio.
|
|
|
|
|
You can create a dll by choosing Class Library in the project menu. Think of it as a group of namespaces or something, a whole set of functionality put together and that is reusable for other applications or other assemblies in your application.
However, a dll itself will not do something, you'll need an exe file which will be created if you choose the console or winforms/wpf projects, and then add a reference to use the dll. If you're totally new, start with a winforms and later move on the wpf.
For a first time I wouldn't search too far to hook up an application with an assembly, but basically there are three ways.
1. select one from your current solution
2. select one from the hard drive somewhere (optionally with a local copy or not)
3. If the assembly is added to the GAC, select it from there.
Just start out with 1.
You can also download VS2010 Express which is free (you'll need to register, but it's free) and SQL Server Express as well if you need it. (also free)
You can use MSDN[^] to find information on the objects and its members and this site [^] for more advanced help 
Hope this helps somewhat, come back if you have specific questions.
good luck.
V.
|
|
|
|
|
I think you are looking at this from the wrong perspective. You have decided that you need a DLL without really understanding what a DLL is or how it would help to solve your problem. You say that you are converting a C++ console program to C#, so presumably the basics will be exactly the same, unless you are going for a completely new design. Look at your inputs, outputs and user interfaces first and decide how they should fit together. It may well be that a single executable written in C# will satisfy all the requirements.
One of these days I'm going to think of a really clever signature.
|
|
|
|
|
PapaGeek wrote: Does this sound like a reasonable approach?
Yes.
You should do the following
1. Design the API. That is what the dll exposed.
2. Code the dll, implementing the API.
3. Create the console, it does console output and uses the API.
4. Create the form.
PapaGeek wrote: and how to create bi-directional communicate with it?
You just write classes/methods that you will use. If you want to get fancy then you can play with the 'internal'. Those go in the library as the API.
Then you use those in console/form.
|
|
|
|
|
PapaGeek wrote: Thanks in advance for any feedback and pointers you can offer.
This is C#, you don't have to worry about pointers.
|
|
|
|
|
Your C# program can use the same DLL as the C++ program.
Using a DLL from C# is even easier than using it from C++: Just use the DllImport directive:
http://msdn.microsoft.com/en-us/library/aa984739%28v=vs.71%29.aspx[^]
The above example doesn't show the mangled C++ name you need in a DllImport directive, so here's a working example from my code:
[DllImport("vdrdll.dll", CallingConvention = CallingConvention.Cdecl, EntryPoint = @"?setNumObjects@@YAXH@Z")]
static extern void setNumObjects(int num);
You get the mangled name from the *.exp file that's created when you compile the C++ DLL. The mangled name always starts with '?' and ends with 'Z'.
The second line is just the standard function signature.
Your C# program needs:
using System.Runtime.InteropServices;
at the top so it recognizes the DllImport keyword.
"Microsoft -- Adding unnecessary complexity to your work since 1987!"
|
|
|
|
|
Another tip: Read "Effective C#" by Bill Wagner, 2nd edition.
It gives you more information about coding in C# than just an introductory C# language book. The 2nd edition covers .NET 4.
"Microsoft -- Adding unnecessary complexity to your work since 1987!"
|
|
|
|
|
I need to create time slots using start time and end time as 8 to 5 with 20 minutes intervals, getting the start and end time from a table in a database dynamically and once the slots are created I need to save them in another table. Any suggestions.
Thanks
|
|
|
|
|
Well, you could use a loop, a list of DateTime items, and a method on the DateTime class to add some minutes. Then you'll need to do some data base work.
|
|
|
|
|
I have implemented the "Sieve of Eratosthenes" algorithm in c# to find prime numbers below 2,000,000. The execution takes very time. How can I improve my implementation?
Here is my code:
public class Number
{
private int _Value;
private bool _IsPrime;
public int Value
{
get { return this._Value; }
set { this._Value = value; }
}
public bool IsPrime
{
get { return this._IsPrime; }
set { this._IsPrime = value; }
}
public Number(int value)
{
this.Value = value;
this.IsPrim = true;
}
}
List<Number> numbers = new List<Number>();
for (int i = 2; i < 20000000; i++)
numbers.Add(new Number(i));
for (int i = 0; i < numbers.Count - 1; i++)
if (numbers[i].IsPrime)
for (int j = i + 1; j < numbers.Count - 1; j++)
if (numbers[j].Value % numbers[i].Value == 0)
numbers[j].IsPrime = false;
Meysam
modified 12-Sep-12 17:18pm.
|
|
|
|
|
You have a typo in the definition of the numbers variable. For your code to even compile that would need to be List<Number> numbers = new List<Number>()..., but I can't help but think that this will be very inefficient.
I wasn't, now I am, then I won't be anymore.
|
|
|
|
|
Your code would not even compile, so how can you say it is slow:
List<Number> numbers = new List<Number>() { 2, 3, 4, 5, 6, ... , 2000000 };
for (int i = 0; i < numbers.Count - 1; i++)
if (numbers[i].IsPrime)
for (int j = i + 1; j < numbers.Count - 1; j++)
if (numbers[j].Value % numbers[i].Value == 0)
numbers[j].IsPrime = false;
Regards,
— Manfred
"With sufficient thrust, pigs fly just fine."
Ross Callon, The Twelve Networking Truths, RFC1925
|
|
|
|
|
if you mean this:
List<Number> numbers = new List<Number>() { 2, 3, 4, 5, 6, ... , 2000000 };
it is not the real. I was going to say that I have an array from 2 to 2,000,000.
I just edited the question.
Meysam
|
|
|
|
|
Which part did you edit. The code still is not valid. If you don't use an array or a list of Number instances your algorithm will not compile since you are accessing IsPrime and Value in that loop.
Your code is still broken. 
"With sufficient thrust, pigs fly just fine."
Ross Callon, The Twelve Networking Truths, RFC1925
modified 13-Sep-12 9:12am.
|
|
|
|
|
What are you talking about?
I have tested my code in some low ranges, and it work great.
It Compiles.
Why you say your opinion when you even didn't try it?
Meysam
|
|
|
|
|
If you post code make sure that the code posted will work.
As your question currently stands the code is invalid for the exact reasons I told you.
In your algorithm you are using the properties IsPrime and Value. For that reason the array or list has to contain these kind of objects. Correct the code you posted!
"With sufficient thrust, pigs fly just fine."
Ross Callon, The Twelve Networking Truths, RFC1925
|
|
|
|
|
Meysam Tolouee wrote: It Compiles.
I have just copied the code from your question (as I expect Manfred also did) and it does not compile. Maybe if you copied and pasted the actual code from your program it would make a bit more sense and you would not need to go petulantly down voting Manfred's responses.
One of these days I'm going to think of a really clever signature.
|
|
|
|
|
According to wiki[^]
"The sieve of Eratosthenes is one of the most efficient ways to find all of the smaller primes (below 10 million or so)." (Citation: The Prime Glossary: "The Sieve of Eratosthenes", http://primes.utm.edu/glossary/page.php?sort=SieveOfEratosthenes, references 16. November 2008.)
That should answer your question; The algo is good for the range of numbes you've chosen.
However (and thats a BIG however), your implementation is wrong.
for i = 2, 3, 4, ..., √n :
if A[i] is true:
for j = i2, i2+i, i2+2i, ..., n:
A[j] := false
You've forgotton to only go to the square root of n (Think about why its only necessary to go to sqrt of n!), which takes a HUGE chunk off of the processing. Also, there should be no second if, in that part of the code, you've already multiplied 2 numbers together, so you know the result cannot be prime.
All in all, youve implemented brute force, which is miles slower than the Sieve of Eratosthenesfor finding primes.
|
|
|
|
|
I'm not surprised you find it takes a long time. The time for this algorithm is 0(n log log n). Also, you haven't actually used the Sieve algorithm. What you've done here is a brute force approach. I suggest you read this[^] to see what the algorithm really is.
|
|
|
|
|
Of course I used the algorithm.
If you trace the code you will understand.
Meysam
|
|
|
|
|
No, no you havent. Read my answer for an explanation of why not!
|
|
|
|
|
I wouldn't waste to much time on OP.
I already told OP that he produced invalid code which OP does somehow not understand or chooses to ignore.
I give up! 
Cheers!
"With sufficient thrust, pigs fly just fine."
Ross Callon, The Twelve Networking Truths, RFC1925
|
|
|
|
|
I think actually it's your failing! Its totally understandable what the OP is asking, even if there are some slight misgivings in his code example.
Your comments on this thread are more annoying than his by an order of magnitude.
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
