--- AnyEvent-HTTP/HTTP.pm 2008/06/09 13:02:13 1.19 +++ AnyEvent-HTTP/HTTP.pm 2008/07/21 05:42:07 1.25 @@ -50,7 +50,7 @@ use base Exporter::; -our $VERSION = '1.01'; +our $VERSION = '1.03'; our @EXPORT = qw(http_get http_post http_head http_request); @@ -95,10 +95,13 @@ response headers as second argument. All the headers in that hash are lowercased. In addition to the response -headers, the three "pseudo-headers" C, C and -C contain the three parts of the HTTP Status-Line of the same -name. If the server sends a header multiple lines, then their contents -will be joined together with C<\x00>. +headers, the "pseudo-headers" C, C and C +contain the three parts of the HTTP Status-Line of the same name. The +pseudo-header C contains the original URL (which can differ from the +requested URL when following redirects). + +If the server sends a header multiple lines, then their contents will be +joined together with C<\x00>. If an internal error occurs, such as not being able to resolve a hostname, then C<$data> will be C, C<< $headers->{Status} >> will be C<599> @@ -234,7 +237,7 @@ } } - my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; + my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) if $recurse < 0; @@ -354,7 +357,7 @@ # status line $state{handle}->push_read (line => qr/\015?\012/, sub { - $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix + $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); my %hdr = ( # response headers @@ -411,12 +414,31 @@ } } - if ($_[1]{Status} =~ /^30[12]$/ && $recurse) { - # microsoft and other assholes don't give a shit for following standards, - # try to support a common form of broken Location header. - $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; + # microsoft and other shitheads don't give a shit for following standards, + # try to support some common forms of broken Location headers. + if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { + $_[1]{location} =~ s/^\.\/+//; + + my $url = "$scheme://$uhost:$uport"; + + unless ($_[1]{location} =~ s/^\///) { + $url .= $upath; + $url =~ s/\/[^\/]*$//; + } + + $_[1]{location} = "$url/$_[1]{location}"; + } + if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { + # apparently, mozilla et al. just change POST to GET here + # more research is needed before we do the same http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); + } elsif ($_[1]{Status} == 303 && $recurse) { + # even http/1.1 is unlear on how to mutate the method + $method = "GET" unless $method eq "HEAD"; + http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); + } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { + http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); } else { $cb->($_[0], $_[1]); } @@ -465,7 +487,8 @@ } sub http_post($$@) { - unshift @_, "POST", "body"; + my $url = shift; + unshift @_, "POST", $url, "body"; &http_request }