Re: [squid-users] Squid 3.0rc1 and ICAP: squid quits using ICAP

On fre, 2007-10-12 at 10:32 -0600, Alex Rousskov wrote:

> > Unless the request method was HEAD, the entity of the
> > response SHOULD contain a short hypertext note with a hyperlink to
> > the new URI(s).
>
> but that violation alone is not a good enough excuse for Squid to fail.

Certainly not. A zero-length body is technically fine from a protocol
perspective. and is used by quite many web sites.

> Your ICAP response is kind of violating RFC 2616 rules about message
> bodies (Section 4.4), but that is debatable.

It's violating a SHOULD level requirement (not MUST) on what a 302
message should include, but not the HTTP message format as such. This
SHOULD requirement is there to make HTTP friendly and MAY be ignored by
implementations not wanting to be friendly.

> In HTTP context, the length
> of your HTTP message body would be determined by the HTTP server closing
> the connection. In ICAP context, there is no HTTP server. Your ICAP
> headers tell Squid there is no body but your HTTP headers tell Squid
> there should be one...

True. There is a slight difference between no body and an empty body.

What happens if you respond with a 0 length body?

Regards
Henrik