Re: http/1.1 requirements

Robert Collins wrote:

> > 15: Conditionally compliant. Can be violated by the use of redirectors.
>
> conditionally compliant means we follow MUST and MUST NOT's but not all the
> SHOULD and SHOULD NOT's. So we aren't compliant. Can users use redirectors
> but force squid to prevent the hostname-in-fqdn request changing? Or do we
> simply say "squid w/o redirectors is conditionally compliant"

Squid is conditionally compliant with this section. The condition is
that redirectors are not used. Without removing the redirector interface
we have to live with this, and when specifying compliance it must be
noted that Squid is compliant provided no redirectors are used to
rewrite the host component, just as the not implemented SHOULD must be
specified..

The primary use of the redirector interface is just to rewrite the
domain component of the URL, and this is not likely something we will
remove only because of HTTP compliance. However, if
--disable-http-violations is in effect then this should be enforced I
think.

> > 16: Optional. Done when using the append_domain directive.
> >
> > 17: Compliant, except for 18 and 19.

Which is compliant, as these are exceptions in the RFC, not specific to
the Squid implementation.

> > 20: Not applicable to proxies I think. Not done. See note at the end of
> > section 5.1.2.
>
> It's applicable to the extent of comparing entities to determine if they can
> be compared using strong or weak comparison see also Content-Location or
> Location.

I fail to see how you can apply the result of any such comparisation
without violating the note. If you do then I se an apparent risk of
having implicit transformations of the URL.

For a proxy
  http://sourceforge.net/~hno/
and
  http://sourceforge.net/%7Ehno/
is completely different URLs

for all other HTTP agents (clients and servers) they SHOULD be
identical.. but there might be servers not understanding this and is why
proxies are not allowed to assume they are.

/Henrik
Received on Wed Oct 25 2000 - 00:33:24 MDT