[mcmanus@appliedtheory.com: Re: Different web pages for different browser versions]

can someone with a grasp of the HTTP code verify this? I seem to
remember it being raised on squid-dev at some time ..

Adrian

----- Forwarded message from Patrick McManus <mcmanus@appliedtheory.com> -----

Date: Wed, 15 Nov 2000 08:41:57 -0500
From: Patrick McManus <mcmanus@appliedtheory.com>
To: Jacob Palme <jpalme@dsv.su.se>
Cc: wrec@cs.utk.edu, Mikael von Pfaler <mvp@borware.com>
Subject: Re: Different web pages for different browser versions
Reply-To: mcmanus@appliedtheory.com
User-Agent: Mutt/1.2i

this is really http, not whatever the heck wrec is (I just said that
to get the rhyme in.), but the server should add the

Vary: User-Agent

header to the 1.1 response.. A 1.1 cache knows that only future
requests with the same user-agent header (and/or any other header(s)
listed in the vary response header) as the request that generated the
cached response may be satisified by that cached response. (subject to
the other normal freshness rules of course.)

[Jacob Palme: Wed, Nov 15, 2000 at 11:05:00AM +0800]
> I am not a regular participant of wrec. But I have a question
> which maybe you have already solved. I tried to look into
> your archives, but could not find it.
>
> The question is that more and more web sites will chech
> which browser type the user has, and deliver different
> versions of a web page depending on the browser type.
>
> How can proxies handle this, so that you deliver a cached
> version only if it suits the browser capabilities of the
> user?
> --
> Jacob Palme <jpalme@dsv.su.se> (Stockholm University and KTH)
> for more info see URL: http://www.dsv.su.se/jpalme/

----- End forwarded message -----

-- 
Adrian Chadd			"God: Damn! I left pot everywhere!
<adrian@creative.net.au>	  Now I'll have to create Republicans!"
				    - Bill Hicks