Henrik Nordstrom wrote:
>
> Jordan Mendelson wrote:
> >
> > For some reason squid 1.2b22 stopped spitting out that error for 0
> > sized answers and started sending back to the client 0 sized answers.
>
> RFC 2068 (HTTP 1.1) section "14.14 Content-Length"
> Any Content-Length greater than or equal to zero is a valid value.
>
> > This happens all the time on http://slashdot.org for one reason or
> > another... but until I upgraded to 1.2b22 has the browser ever shown
> > the error instead of the standard squid error.
>
> Showing an error on a valid reply is a bug.
>
> Try to capture what the server returns (using client). If the
> object-headers are returned and there is a Content-Length: 0 then it is
> a valid reply, and hence Squid should not translate it into an error.
>
> It can be argued wether a zero bytes reply without Content-Length is
> valid or not. I could not find anything in RFC2068 on stating that it
> isn't (only the contraty, that a object may be zero bytes), but most
> times this is seen is on a malperforming cgi-bin program. On the other
> hand Squid is only a relay agent and as such it should not transform
> correct replies into errors.
I figure that as long as you got a blank-line after the response
headers, it's not an error for there to be no data in the response body.
If the connection closed without the empty line after the response
headers, I'd say that's bad.
That's all assuming that the content length is 0 or unspecified. If it's
a positive integer and we don't match...well...we shrug our shoulders,
pass on the object, and discard it.
D
-- -----BEGIN GEEK CODE BLOCK----- Version: 3.1 GAT d- s++: a C++++$ UL++++B+++S+++C++H++U++V+++$ P+++$ L+++ E- W+++(--)$ N++ w++$>--- t+ 5++ X+() R+ tv b++++ DI+++ e- h-@ ------END GEEK CODE BLOCK------Received on Mon Jul 27 1998 - 20:44:05 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:41:16 MST