--- AnyEvent-HTTP/HTTP.pm	2008/06/09 13:02:13	1.19
+++ AnyEvent-HTTP/HTTP.pm	2008/10/22 23:28:11	1.29
@@ -50,7 +50,7 @@
 
 use base Exporter::;
 
-our $VERSION = '1.01';
+our $VERSION = '1.05';
 
 our @EXPORT = qw(http_get http_post http_head http_request);
 
@@ -73,32 +73,41 @@
 =item http_get $url, key => value..., $cb->($data, $headers)
 
 Executes an HTTP-GET request. See the http_request function for details on
-additional parameters.
+additional parameters and the return value.
 
 =item http_head $url, key => value..., $cb->($data, $headers)
 
-Executes an HTTP-HEAD request. See the http_request function for details on
-additional parameters.
+Executes an HTTP-HEAD request. See the http_request function for details
+on additional parameters and the return value.
 
 =item http_post $url, $body, key => value..., $cb->($data, $headers)
 
-Executes an HTTP-POST request with a request body of C<$bod>. See the
-http_request function for details on additional parameters.
+Executes an HTTP-POST request with a request body of C<$body>. See the
+http_request function for details on additional parameters and the return
+value.
 
 =item http_request $method => $url, key => value..., $cb->($data, $headers)
 
 Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
 must be an absolute http or https URL.
 
+When called in void context, nothing is returned. In other contexts,
+C<http_request> returns a "cancellation guard" - you have to keep the
+object at least alive until the callback get called. If the object gets
+destroyed before the callbakc is called, the request will be cancelled.
+
 The callback will be called with the response data as first argument
 (or C<undef> if it wasn't available due to errors), and a hash-ref with
 response headers as second argument.
 
 All the headers in that hash are lowercased. In addition to the response
-headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and
-C<Reason> 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<HTTPVersion>, C<Status> and C<Reason>
+contain the three parts of the HTTP Status-Line of the same name. The
+pseudo-header C<URL> 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<undef>, C<< $headers->{Status} >> will be C<599>
@@ -188,6 +197,16 @@
       }
    ;
 
+Example: make another simple HTTP GET request, but immediately try to
+cancel it.
+
+   my $request = http_request GET => "http://www.nethype.de/", sub {
+      my ($body, $hdr) = @_;
+      print "$body\n";
+   };
+
+   undef $request;
+
 =cut
 
 sub _slot_schedule;
@@ -234,7 +253,7 @@
       }
    }
 
-   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 +373,7 @@
 
          # 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
@@ -397,7 +416,7 @@
                         my $cdom  = (delete $kv{domain}) || $uhost;
                         my $cpath = (delete $kv{path})   || "/";
     
-                        $cdom =~ s/^.?/./; # make sure it starts with a "."
+                        $cdom =~ s/^\.?/./; # make sure it starts with a "."
 
                         next if $cdom =~ /\.$/;
     
@@ -411,12 +430,31 @@
                      }
                   }
 
-                  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 +503,8 @@
 }
 
 sub http_post($$@) {
-   unshift @_, "POST", "body";
+   my $url = shift;
+   unshift @_, "POST", $url, "body";
    &http_request
 }