--- AnyEvent-HTTP/HTTP.pm	2009/07/06 03:03:12	1.43
+++ AnyEvent-HTTP/HTTP.pm	2009/12/05 15:37:07	1.53
@@ -43,14 +43,14 @@
 
 use Errno ();
 
-use AnyEvent 4.452 ();
+use AnyEvent 5.0 ();
 use AnyEvent::Util ();
 use AnyEvent::Socket ();
 use AnyEvent::Handle ();
 
 use base Exporter::;
 
-our $VERSION = '1.12';
+our $VERSION = '1.44';
 
 our @EXPORT = qw(http_get http_post http_head http_request);
 
@@ -140,19 +140,24 @@
 
 The request headers to use. Currently, C<http_request> may provide its
 own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
-and will provide defaults for C<User-Agent:> and C<Referer:>.
+and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
+suppressed by using C<undef> for these headers in which case they won't be
+sent at all).
 
 =item timeout => $seconds
 
 The time-out to use for various stages - each connect attempt will reset
-the timeout, as will read or write activity. Default timeout is 5 minutes.
+the timeout, as will read or write activity, i.e. this is not an overall
+timeout.
+
+Default timeout is 5 minutes.
 
 =item proxy => [$host, $port[, $scheme]] or undef
 
 Use the given http proxy for all requests. If not specified, then the
 default proxy (as specified by C<$ENV{http_proxy}>) is used.
 
-C<$scheme> must be either missing or C<http> for HTTP, or C<https> for
+C<$scheme> must be either missing, C<http> for HTTP or C<https> for
 HTTPS.
 
 =item body => $string
@@ -188,6 +193,15 @@
 The default for this option is C<low>, which could be interpreted as "give
 me the page, no matter what".
 
+=item on_prepare => $callback->($fh)
+
+In rare cases you need to "tune" the socket before it is used to
+connect (for exmaple, to bind it on a given IP address). This parameter
+overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
+and behaves exactly the same way (e.g. it has to provide a
+timeout). See the description for the C<$prepare_cb> argument of
+C<AnyEvent::Socket::tcp_connect> for details.
+
 =item on_header => $callback->($headers)
 
 When specified, this callback will be called with the header hash as soon
@@ -223,7 +237,10 @@
 be extracted, or when the body should be processed incrementally.
 
 It is usually preferred over doing your own body handling via
-C<want_body_handle>.
+C<want_body_handle>, but in case of streaming APIs, where HTTP is
+only used to create a connection, C<want_body_handle> is the better
+alternative, as it allows you to install your own event handler, reducing
+resource usage.
 
 =item want_body_handle => $enable
 
@@ -245,7 +262,7 @@
 push-style twitter API which starts a JSON/XML stream).
 
 If you think you need this, first have a look at C<on_body>, to see if
-that doesn'T solve your problem in a better way.
+that doesn't solve your problem in a better way.
 
 =back
 
@@ -311,8 +328,8 @@
    _slot_schedule $_[0];
 }
 
-our $qr_nl   = qr<\015?\012>;
-our $qr_nlnl = qr<\015?\012\015?\012>;
+our $qr_nl   = qr{\015?\012};
+our $qr_nlnl = qr{(?<![^\012])\015?\012};
 
 our $TLS_CTX_LOW  = { cache => 1, sslv2 => 1 };
 our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
@@ -357,7 +374,8 @@
    my $uhost = $1;
    $uport = $2 if defined $2;
 
-   $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";
+   $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
+      unless exists $hdr{host};
 
    $uhost =~ s/^\[(.*)\]$/$1/;
    $upath .= "?$query" if length $query;
@@ -400,6 +418,8 @@
    if ($proxy) {
       ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
 
+      $rscheme = "http" unless defined $rscheme;
+
       # don't support https requests over https-proxy transport,
       # can't be done with tls as spec'ed, unless you double-encrypt.
       $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
@@ -407,10 +427,12 @@
       ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
    }
 
-   $hdr{"user-agent"} ||= $USERAGENT;
-   $hdr{referer}      ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
+   # leave out fragment and query string, just a heuristic
+   $hdr{referer}      ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
+   $hdr{"user-agent"} ||= $USERAGENT                     unless exists $hdr{"user-agent"};
 
-   $hdr{"content-length"} = length $arg{body};
+   $hdr{"content-length"} = length $arg{body}
+      if length $arg{body} || $method ne "GET";
 
    my %state = (connect_guard => 1);
 
@@ -421,7 +443,12 @@
 
       $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
          $state{fh} = shift
-            or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url }));
+            or do {
+               my $err = "$!";
+               %state = ();
+               return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
+            };
+
          pop; # free memory, save a tree
 
          return unless delete $state{connect_guard};
@@ -464,7 +491,7 @@
             # send request
             $state{handle}->push_write (
                "$method $rpath HTTP/1.0\015\012"
-               . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)
+               . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
                . "\015\012"
                . (delete $arg{body})
             );
@@ -485,7 +512,7 @@
 
                # headers, could be optimized a bit
                $state{handle}->unshift_read (line => $qr_nlnl, sub {
-                  for ("$_[1]\012") {
+                  for ("$_[1]") {
                      y/\015//d; # weed out any \015, as they show up in the weirdest of places.
 
                      # things seen, not parsed:
@@ -592,7 +619,7 @@
                         }
                      }
 
-                     if ($redirect) {
+                     if ($redirect && exists $hdr{location}) {
                         # we ignore any errors, as it is very common to receive
                         # Content-Length != 0 but no actual body
                         # we also access %hdr, as $_[1] might be an erro
@@ -691,9 +718,7 @@
             &$handle_actual_request;
          }
 
-      }, sub {
-         $timeout
-      };
+      }, $arg{on_prepare} || sub { $timeout };
    };
 
    defined wantarray && AnyEvent::Util::guard { %state = () }
@@ -724,7 +749,10 @@
 =item AnyEvent::HTTP::set_proxy "proxy-url"
 
 Sets the default proxy server to use. The proxy-url must begin with a
-string of the form C<http://host:port> (optionally C<https:...>).
+string of the form C<http://host:port> (optionally C<https:...>), croaks
+otherwise.
+
+To clear an already-set proxy, use C<undef>.
 
 =item $AnyEvent::HTTP::MAX_RECURSE
 
@@ -737,7 +765,7 @@
 
 =item $AnyEvent::HTTP::MAX_PER_HOST
 
-The maximum number of concurrent conenctions to the same host (identified
+The maximum number of concurrent connections to the same host (identified
 by the hostname). If the limit is exceeded, then the additional requests
 are queued until previous connections are closed.
 
@@ -755,11 +783,19 @@
 =cut
 
 sub set_proxy($) {
-   $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;
+   if (length $_[0]) {
+      $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
+         or Carp::croak "$_[0]: invalid proxy URL";
+      $PROXY = [$2, $3 || 3128, $1]
+   } else {
+      undef $PROXY;
+   }
 }
 
 # initialise proxy from environment
-set_proxy $ENV{http_proxy};
+eval {
+   set_proxy $ENV{http_proxy};
+};
 
 =head1 SEE ALSO