Re: segfault in clientSocketRecipient

On Thu, 2007-07-26 at 22:26 -0600, Alex Rousskov wrote:

> > revision 1.593
> > date: 2002/09/24 10:46:43; author: robertc; state: Exp; lines: +783 -659
> > Client side refactoring - no functionality changes
>
> Does anybody know whether we should resurrect support for the NULL rep
> case in clientSocketRecipient? Or, at least, what does it mean that rep
> is NULL there?

If I remember correctly, the refactoring in question was to break out
the different cases in to different callback handlers. So you would only
be called in clientSocketRecipient once a reply does in fact exist,
rather than it being a if/then on every callback.

So it should never be NULL today, unless something is setting it as the
callback routine in appropriately.

This is from memory, I hope it helps.
-Rob

-- 
GPG key available at: <http://www.robertcollins.net/keys.txt>.