icap devel branch feedback

Geetha,
   Some feedback on the iCAP branch follows. If you have any
questions/disagreements I'd love to hear them.

You have multiple occurences of #undef HS_FEAT_ICAP in acconfig.h, and
likewise in client_side.c.

Changing the default access mode for icp and http to allow all is bad -
it will not be acceptable for merging into HEAD like this.

You appear to only support one of reqmod and respmod at a time. This
appears quite limiting - it should be possible to support both request
and respond modification, indeed you should allow *multiple* occurences
of both on a single request->response pair. I.e.: use foo reqmod for
access control/redirection, then virus scan the response before caching,
and finally perform add-stripping on html documents before delivery to
the user.

You can avoid the global registration of the icap CBDATA by using the
CBDATA_TYPE and CBDATA_INIT_TYPE or CBDATA_INIT_TYPE_FREECB macros
within a single translation unit. This can be quite handy where only a
single file needs to create cbdata objects of a given type.

Rather than using private functions from forward.c, http.c and
client_side.c, consider generalising the relevant file to allow it's
current external API to do what you need it to. You can also consider
adding hooks for callbacks to allow you more control over it's
behaviour. (Don't work on client_side - I've done a lot there that
should hit HEAD soon :}).

Cheers,
Rob