|
 You will burn on a stake for that!
While we were at strong opinions... 
Personally, I have no problem with multiple returns. But an amazing number of styleguides strongly forbid it - contrary to intuition and code readability, as I think.
Let's think the unthinkable, let's do the undoable, let's prepare to grapple with the ineffable itself, and see if we may not eff it after all.
Douglas Adams, "Dirk Gently's Holistic Detective Agency"
|
|
|
|
|
It made sense in C / procedural style, where "one exit point" made sense for avoiding ressource management errors.
However in any modern language we have exceptions thwarting the effort anyway, and deterministic destructors/finalizers to deal with the problem.
|
|
|
|
|
I like this style as well. Not only for the readability but also because it better reflects what the code is doing - it's making several tests whether it can safely go ahead with whatever action it's going to perform or if something's wrong and it should fail.
I hate it when if ... else ... if ... else ...... is used instead because it can confuse you by suggesting branching where there is none.
There is sufficient light for those who desire to see, and there is sufficient darkness for those of a contrary disposition.
Blaise Pascal
|
|
|
|
|
Agreed.
---- You're right.
These facts that you've laid out totally contradict the wild ramblings that I pulled off the back of cornflakes packets .
|
|
|
|
|
It depends on the relative lengths of the then and else clauses. If both are short then I'm more likely to put the true clause first. If one if short (often because its an error case) and the other is long then the shorter one comes first. This makes it easier to determine which if statement a code block belongs to.
For instance
if(statement is false)
return ERROR_CODE;
else
{
}
in preference to
if(statement is true)
{
}
else
{
return ERROR_CODE;
}
Of course, if both are long (or even if just one of them is long) I'd refactor the long code into functions, i.e.
if(statement is false)
DoLongComplicatedStuff();
else
DoOtherLongComplicatedStuff();
Graham
Librarians rule, Ook!
|
|
|
|
|
For me it depends on the frequency of each of the outcomes. Which ever is likely to happen most often is the "if", and the less frequently encountered condition is the "else".
If they are equally likely, or nearly so, I tend to use the true case as the if, 'cause I don't usually like reading negative logic.
/bs
|
|
|
|
|
Yours is my preferred method. Though sometimes there are cases that either the false or true statement just makes it easier to understand what is happening. In some cases where I have if..then..else but no case statements I'll handle the only definitive answer first and handle the opposite and "maybe" answers elsewhere.
|
|
|
|
|
Graham Shanks wrote:
For instance
if(statement is false)
return ERROR_CODE;
else
{
}
in preference to
if(statement is true)
{
}
else
{
return ERROR_CODE;
}
This should be rewritten as follows for clarity and reduced code size.
if(statement is false)
{
return ERROR_CODE;
}
There is NO ELSE.
Gary
|
|
|
|
|
And THAT makes it even easier to read! Good catch!
Meddle not in the affairs of dragons,
For you are crunchy, and good with mustard.
|
|
|
|
|
if(areUsingTDD)
thisQuestionDoesntReallyMakeSense
|
|
|
|
|
How does TDD fit in here?
You don't use coditions in TDD?
|
|
|
|
|
because where boolean types are supported only by integers then FALSE is always zero but TRUE can be 1, -1, 42 or anything that is not zero thus relying on TRUE to be one, and I have seen lots of old code that does, can lead to a world of pain and despair.
|
|
|
|
|
But in those cases it is better to test for non-zero instead of TRUE.
BOOL bAnswer = ReturnOfSomeFunction();
if( bAnswer != 0 ) {
do something;
}
|
|
|
|
|
That was exactly the point I tried to make. Tests on TRUE can be unreliable, Tests on FALSE that might well be stated as !FALSE or NOT FALSE can usually be relied upon. Hence my response to the survey test FALSE first.
|
|
|
|
|
But of course that only pertains to the Microsoft BOOL variable and not bool in C++. C did not actually have a bool value defined until C99. BOOL is actually an INT (sizeof(BOOL) = 4 or 8 on x64) whereas bool is a byte (sizeof(bool) = 1). Most languages use a built in type of bool that is one byte and only capable of being true or false (1 or 0). The proper use of BOOL is to test if it is non-zero for TRUE with most functions that return BOOL. Some functions that return BOOL will actually return more than just 2 possible answers (ie: 0 for success or a value representing a return or error code).
|
|
|
|
|
Then it depends on the language?
|
|
|
|
|
|
if(statement is true)
{
return "Yes";
}
else if(statement is false)
{
return "No";
}
else
{
return "The meaning of life";
}
In what school this philosophy lies?
Ittay Ophir
ittay.ophir@gmail.com
|
|
|
|
|
Don't know, but I can tell you that if you ever find your function returning "the meaning of life" then something has gone horribly horribly wrong. :-/
|
|
|
|
|
A decent compiler would issue a diagnostic for that final else clause.
Software Zen: delete this;
|
|
|
|
|
return 42; 
This would be it I think.
Cheers
You have the thought that modern physics just relay on assumptions, that somehow depends on a smile of a cat, which isn’t there.( Albert Einstein)
|
|
|
|
|
|
There are two elses and at least one if to nuke.
|
|
|
|
|
That's fuzzy logic and would mean that "statement" could not be a boolean variable having only two states. An example would be if you were testing to see if a string was equal to something. An exact match would be true and a partial match would be not false or true and a complete miss would be false.
Statement = "My dog has fleas"
if( Statement = "dog" )
else if( Statement contains "dog" case insensitively)
else
|
|
|
|
|
Behind every seemingly trivial task there are many schools of philosophy
Marcello Turnbull
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
