Re: Feedback about the content processing framework]

Update your CVS... I fixed a bug last night(early this morning :-]) where client_side.c was short circuiting the filter list on EOF.

If you are up to date, let me know :-[

Rob
----- Original Message -----
From: "Moez Mahfoudh" <moez.mahfoudh@imag.fr>
To: "Squid Dev" <squid-dev@squid-cache.org>
Sent: Wednesday, January 31, 2001 9:12 PM
Subject: [Fwd: Feedback about the content processing framework]

> Moez Mahfoudh wrote:
>
> > Robert Collins wrote:
> >
> > > ----- Original Message -----
> > > From: "Moez Mahfoudh" <moez.mahfoudh@imag.fr>
> > > To: "Robert Collins" <robert.collins@itdomain.com.au>
> > > Sent: Wednesday, January 31, 2001 9:05 PM
> > > Subject: Re: Feedback about the content processing framework
> > >
> > > > >
> > > > > Currently: The last chunk has len==0, buf==NULL. The flag is defined, but not used all over yet.
> > > > > store a state variable for headers seen, and test for EOF/LASTCHUNK by buf==NULL || flags & FILTER_EOF. That'll cover both
bases
> > > > > until I've finished the tidyup.
> > > >
> > > > Sorry for insisting, but in my tests, I cannot see such a behavior. There is no call for my filter function with buf=NULL or
> > > len=0.
> > >
> > > How are you inserting the filter into the chain? (Can you mail me your module.c & Makefile.in ?) I need to see where in the
chain
> > > you sit to give you a sensible answer.
> >
> > I just replaced the textreplace filter function with the one I gave you. I didn't more...
> >
> > >
> > > Are you using a http/1.1 client or 1.0 (ie is chunked encoding on or off?)
> >
> > I use netscape 4.72... I think it is not fully 1.1 client...
> >
> > >
> > >
> > > And of course.. it might be a bug :-]
> >
> > May be...
> >
> > --Moez
>
Received on Wed Jan 31 2001 - 03:16:21 MST