|
Yeah I got tired of waiting for an actual answer on here so I just did some tests and found the answer. It is just a pointer. And I get ref, I am well aware of what happens when you pass by reference and by value. And I am well aware of the central points of C#, just do C++ at my studio for our engine. 9 Hours a day of C++ and then going home to do C# is a kind of rough transition. I just equate things to C++ which is my naitive language. I did a GC memory check at the begining and end of creation of the class in question and just watched how many bytes were used with two different versions of the class. I applaud you though, your the first one to actually get the question right. Wait, correction, I think the first response got the question right too.
modified on Sunday, September 12, 2010 4:44 PM
|
|
|
|
|
Actually, you got the correct answer from all three. You should reread what Luc had to say on the subject as well, as you've not read it through properly; he's one smart cookie and he provided the info from the other side.
|
|
|
|
|
I guess I got kind of confused when Luc said that it depends on the size of the class. I took it to mean that he was saying that when declaired as an interface and passed as an interface type it still got passed as a class. So I dont think I got the right answer from all three, because two of the answers were the same and one said the opposite. But you guys have all been very helpful and I appreciate it. Especially paul_71, your answer was very precise and had the information I was looking for to begin with. But like I said, did some research on my own and found my answer like I should have in the first place.
|
|
|
|
|
As a side note, I would like to thank you all for your help. I hope I did not come of as mean.The transition from C++ to C# is a frustrating one to say the least. The managed environment is exciting and taxing at the same time. I appreciate you all for taking the time to answer my question.
|
|
|
|
|
You are welcome... I saw that Luc's answer already contained the required information, but I decided to give a more 'explicit' version for a specific reason: I saw that you're coming from C++. It is really interesting that the way experienced C++ devs are approaching the CLI (esp. C#) world is the same all over the world 
|
|
|
|
|
I just want pointers! I looked into using them with the unsafe environement, but it is way to unstable! Just give me pointers!
|
|
|
|
|
Assuming I have a string of numbers beginning with "6" (i.e., "612345"). I wish to check if the numbers 6, 2, and 4 appear in that order. Thus, I can check for "6[0-9]*2[0-9]*4" using regular expressions. However, knowing that the numbers I'm checking have to begin with a 6, does it actually save me time to only search for "2[0-9]*4"? The reason I ask is because logically, using the first search, "6" would be found in the first character and "2" would start from the second character. However, using the second search, "2" would start from the first character which I already know to be a "6". In the first case, I get code readability, while in the second, I'm only searching for what the minimum is needed. I'm wondering if there is any optimization technique that could possibly make the first method run faster than the second?
Thanks!
|
|
|
|
|
some comments, not an answer:
1.
we have a regular expressions forum
2.
you're worried about readability and yet you use regular expressions?
3.
what do you want to happen with numbers having multiple two's and four's?
is 612423 two matches? a match and a fail?
|
|
|
|
|
Luc Pattyn wrote: 1.
we have a regular expressions forum
I knew I should have checked all the forums. However, I am using C#. Maybe someone will move this to the right forum.
Luc Pattyn wrote: 2.
you're worried about readability and yet you use regular expressions?
It's a simple numeric search. I could easily add a comment that I'm actually searching for 6-2-4, but only 2-4 is needed since the numbers begin with 6.
Luc Pattyn wrote: 3.
what do you want to happen with numbers having multiple two's and four's?
is 612423 two matches? a match and a fail?
As long as there's a 2 before a 4, it passes. The string 612345 was just an example. It could be 64444444444444422222222222123678901236789012345678903456789034567890 and it would still pass.
|
|
|
|
|
Bassam Abdul-Baki wrote: as there's a 2 before a 4, it passes
Check for the 6
Compare String.IndexOf ( 2 ) < String.LastIndexOf ( 4 ) (Check for -1 too)
Done
|
|
|
|
|
Nice! I like this, but my example only had two numbers for simplicity. I actually have three numbers. Missed it by this much.
|
|
|
|
|
Well, why didn't you say so?
http://msdn.microsoft.com/en-us/library/5xkyx09y.aspx[^]
if ( s [ 0 ] == firstdigit )
and int x = s.IndexOf ( secondsdigit ) > 0
and int y = s.IndexOf ( thirddigit , x ) > 0
and int z = s.IndexOf ( fourthdigit , y ) > 0
etc.
Perhaps in a loop.
|
|
|
|
|
D'oh! That would work. Haven't used IndexOf in quite a while.  Thanks!
|
|
|
|
|
If you really want to optimize this, just step through the characters with a state machine.
This is faster than using a regular expression, which has overhead because it's designed to handle the much more complex general case.
|
|
|
|
|
Alan Balkany wrote: If you really want to optimize this, just step through the characters with a state machine.
Not familiar with it. However, I have an obscene amount of strings that I'm parsing and it's coded in C#.
|
|
|
|
|
Are you always looking for these three digits, or was that just an example?
|
|
|
|
|
The three digits were an example, but the same digits all the time. So yes and no.
|
|
|
|
|
A state machine uses a single int to mark where you are in your search. E.g.:
int state = 0;
foreach (char c in nextString)
switch (state)
{
case (0): if (c == '6') state = 1;
break;
case (1): if (c == '2') state = 2;
break;
case (2): if (c == '4') state = 3;
break;
}
if (state == 3)
return (FOUND);
else
return (NOT_FOUND);
This is way faster than using regular expressions, which must handle much more complex cases.
|
|
|
|
|
Groovy (not the language)! I'll try it out. Thanks!
|
|
|
|
|
I'm afraid the switch will turn out to be expensive, and it really is unnecessary. How about:
int len=s.Length;
int i=0;
while(i<len) {
char c=s[i++];
if (c=='6') {
while(i<len) {
c=s[i++];
if (c=='2') {
while(i<len) {
c=s[i++];
if (c=='4') return true;
}
}
}
}
}
return false;
or the more structured:
string search="624x";
int iSearch=0;
char cSearch=search[iSearch];
foreach(char c in s) {
if(c==cSearch) {
cSearch=search[++iSearch];
if (cSearch=='x') return true;
}
}
return false;
BTW: none if these fulfill the requirement, as they would accept 6424 whereas the OP wants to reject that; so the state machine needs to be a tiny bit more complex.
|
|
|
|
|
Yes, your first example is a more efficient implementation of the state machine, but I was trying to illustrate the concept with the most clarity.
My example also could be optimized by immediately returning when the third digit was found, but I wanted to show a pure example of a state machine.
|
|
|
|
|
|
Luc Pattyn wrote: BTW: none if these fulfill the requirement, as they would accept 6424 whereas the OP wants to reject that; so the state machine needs to be a tiny bit more complex.
No, I wouldn't. When I said as long as 6-2-4 appear in that order, I meant 6[0-9]*2[0-9]*4.
|
|
|
|
|
The first example you provided is quite clear, although you had a len missing in the third while loop. I'm not so sure about the second one(since I don't have a compiler at work - not my thing anymore). Never mind. I got it. Except the 'x' confused the hell out of me.
I think I like the second one better, but I need to use the one that's faster.
Thanks!
|
|
|
|
|
sorry. I fixed both mistakes now.
I don't expect you would notice a significant performance difference between both approaches.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
