Squid isn't honoring "Accept" headers when retrieving items from the cache. The
original request might go through with a "gzip" encoding, but then another browser
might not accept that type of encoding when the page is loaded from the cache.
This happens when a modern browser requests a page that gets cached, then an
older browser such as IE 5 asks for the same page. The IE 5 browsers present
a download prompt to the user instead of displaying the page.
I've looked through the squid source code and I didn't see any place where any
"Accept" headers were checked. It looks like the proper place is in client_side.c,
in the clientCacheHit() routine. After reading the appropriate parts of RFC 2616
(sections 14.1 through 14.4) I can see why "Accept" processing was left out.
Are there plans for "Accept" processing in version 2.6? Does anyone have a feel
for which "Accept" header will help the most? Is handling "Accept-Encoding"
sufficient, or do we have to handle all "Accept" headers?
Received on Thu Jun 13 2002 - 16:13:43 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:08:41 MST