--- AnyEvent-HTTP/HTTP.pm 2008/06/04 12:05:45 1.6 +++ AnyEvent-HTTP/HTTP.pm 2009/07/05 23:50:59 1.41 @@ -6,11 +6,30 @@ use AnyEvent::HTTP; + http_get "http://www.nethype.de/", sub { print $_[1] }; + + # ... do something else here + =head1 DESCRIPTION This module is an L user, you need to make sure that you use and run a supported event loop. +This module implements a simple, stateless and non-blocking HTTP +client. It supports GET, POST and other request methods, cookies and more, +all on a very low level. It can follow redirects supports proxies and +automatically limits the number of connections to the values specified in +the RFC. + +It should generally be a "good client" that is enough for most HTTP +tasks. Simple tasks should be simple, but complex tasks should still be +possible as the user retains control over request and response headers. + +The caller is responsible for authentication management, cookies (if +the simplistic implementation in this module doesn't suffice), referer +and other high-level protocol details for which this module offers only +limited support. + =head2 METHODS =over 4 @@ -22,20 +41,20 @@ use strict; no warnings; -use Carp; +use Errno (); -use AnyEvent (); +use AnyEvent 4.452 (); use AnyEvent::Util (); use AnyEvent::Socket (); use AnyEvent::Handle (); use base Exporter::; -our $VERSION = '1.0'; +our $VERSION = '1.12'; -our @EXPORT = qw(http_get http_request); +our @EXPORT = qw(http_get http_post http_head http_request); -our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; +our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; our $MAX_RECURSE = 10; our $MAX_PERSISTENT = 8; our $PERSISTENT_TIMEOUT = 2; @@ -43,44 +62,57 @@ # changing these is evil our $MAX_PERSISTENT_PER_HOST = 2; -our $MAX_PER_HOST = 4; # not respected yet :( +our $MAX_PER_HOST = 4; our $PROXY; +our $ACTIVE = 0; my %KA_COUNT; # number of open keep-alive connections per host +my %CO_SLOT; # number of open connections, and wait queue, per host =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, $headers) -Executes an HTTP-POST request with a requets body of C<$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, C). The URL must be an absolute http or https URL. +When called in void context, nothing is returned. In other contexts, +C 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 if it wasn't available due to errors), and a hash-ref with response headers as second argument. -All the headers in that has 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. +All the headers in that hash are lowercased. In addition to the response +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 times, then their contents will be +joined together with a comma (C<,>), as per the HTTP spec. If an internal error occurs, such as not being able to resolve a hostname, -then C<$data> will be C, C<< $headers->{Status} >> will be C<599> -and the C pseudo-header will contain an error message. +then C<$data> will be C, C<< $headers->{Status} >> will be C<59x> +(usually C<599>) and the C pseudo-header will contain an error +message. A typical callback might look like this: @@ -106,7 +138,9 @@ =item headers => hashref -The request headers to use. +The request headers to use. Currently, C may provide its +own C, C, C and C headers +and will provide defaults for C and C. =item timeout => $seconds @@ -126,189 +160,555 @@ The request body, usually empty. Will be-sent as-is (future versions of this module might offer more options). -=back +=item cookie_jar => $hash_ref + +Passing this parameter enables (simplified) cookie-processing, loosely +based on the original netscape specification. + +The C<$hash_ref> must be an (initially empty) hash reference which will +get updated automatically. It is possible to save the cookie_jar to +persistent storage with something like JSON or Storable, but this is not +recommended, as expiry times are currently being ignored. + +Note that this cookie implementation is not of very high quality, nor +meant to be complete. If you want complete cookie management you have to +do that on your own. C is meant as a quick fix to get some +cookie-using sites working. Cookies are a privacy disaster, do not use +them unless required to. + +=item tls_ctx => $scheme | $tls_ctx + +Specifies the AnyEvent::TLS context to be used for https connections. This +parameter follows the same rules as the C parameter to +L, but additionally, the two strings C or +C can be specified, which give you a predefined low-security (no +verification, highest compatibility) and high-security (CA and common-name +verification) TLS context. + +The default for this option is C, which could be interpreted as "give +me the page, no matter what". + +=item on_header => $callback->($hdr) + +When specified, this callback will be called with the header hash as soon +as headers have been successfully received from the remote server (not on +locally-generated errors). + +It has to return either true (in which case AnyEvent::HTTP will continue), +or false, in which case AnyEvent::HTTP will cancel the download (and call +the finish callback with an error code of C<598>). + +This callback is useful, among other things, to quickly reject unwanted +content, which, if it is supposed to be rare, can be faster than first +doing a C request. + +=item on_body => $callback->($data, $hdr) + +When specified, all body data will be "filtered" through this callback. + +The callback will incrementally receive body data, and is supposed to +return it or a modified version of it (empty strings are valid returns). + +If the callback returns C, then the request will be cancelled. + +This callback is useful when you want to do some processing on the data, +or the data is too large to be held in memory (so the callback writes it +to a file and returns the empty string) and so on. + +It is usually preferred over doing your own body handling via +C. + +=item want_body_handle => $enable + +When enabled (default is disabled), the behaviour of AnyEvent::HTTP +changes considerably: after parsing the headers, and instead of +downloading the body (if any), the completion callback will be +called. Instead of the C<$body> argument containing the body data, the +callback will receive the L object associated with the +connection. In error cases, C will be passed. When there is no body +(e.g. status C<304>), the empty string will be passed. + +The handle object might or might not be in TLS mode, might be connected to +a proxy, be a persistent connection etc., and configured in unspecified +ways. The user is responsible for this handle (it will not be used by this +module anymore). + +This is useful with some push-type services, where, after the initial +headers, an interactive protocol is used (typical example would be the +push-style twitter API which starts a JSON/XML stream). + +If you think you need this, first have a look at C, to see if +that doesn'T solve your problem in a better way. =back +Example: make a simple HTTP GET request for http://www.nethype.de/ + + http_request GET => "http://www.nethype.de/", sub { + my ($body, $hdr) = @_; + print "$body\n"; + }; + +Example: make a HTTP HEAD request on https://www.google.com/, use a +timeout of 30 seconds. + + http_request + GET => "https://www.google.com", + timeout => 30, + sub { + my ($body, $hdr) = @_; + use Data::Dumper; + print Dumper $hdr; + } + ; + +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 http_request($$$;@) { +sub _slot_schedule; +sub _slot_schedule($) { + my $host = shift; + + while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { + if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { + # somebody wants that slot + ++$CO_SLOT{$host}[0]; + ++$ACTIVE; + + $cb->(AnyEvent::Util::guard { + --$ACTIVE; + --$CO_SLOT{$host}[0]; + _slot_schedule $host; + }); + } else { + # nobody wants the slot, maybe we can forget about it + delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0]; + last; + } + } +} + +# wait for a free slot on host, call callback +sub _get_slot($$) { + push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; + + _slot_schedule $_[0]; +} + +our $qr_nl = qr<\015?\012>; +our $qr_nlnl = qr<\015?\012\015?\012>; + +our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; +our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; + +sub http_request($$@) { my $cb = pop; my ($method, $url, %arg) = @_; my %hdr; + $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; + $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; + $method = uc $method; - if (my $hdr = delete $arg{headers}) { + if (my $hdr = $arg{headers}) { while (my ($k, $v) = each %$hdr) { $hdr{lc $k} = $v; } } - my $proxy = $arg{proxy} || $PROXY; - my $timeout = $arg{timeout} || $TIMEOUT; - my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; + my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; - $hdr{"user-agent"} ||= $USERAGENT; + return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) + if $recurse < 0; - my ($host, $port, $path, $scheme); - - if ($proxy) { - ($host, $port, $scheme) = @$proxy; - $path = $url; - } else { - ($scheme, my $authority, $path, my $query, my $fragment) = - $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; - - $port = $scheme eq "http" ? 80 - : $scheme eq "https" ? 443 - : croak "$url: only http and https URLs supported"; - - $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x - or croak "$authority: unparsable URL"; - - $host = $1; - $port = $2 if defined $2; + my $proxy = $arg{proxy} || $PROXY; + my $timeout = $arg{timeout} || $TIMEOUT; - $host =~ s/^\[(.*)\]$/$1/; - $path .= "?$query" if length $query; + my ($uscheme, $uauthority, $upath, $query, $fragment) = + $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; - $path = "/" unless $path; + $uscheme = lc $uscheme; - $hdr{host} = $host = lc $host; + my $uport = $uscheme eq "http" ? 80 + : $uscheme eq "https" ? 443 + : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url }); + + $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x + or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); + + my $uhost = $1; + $uport = $2 if defined $2; + + $uhost =~ s/^\[(.*)\]$/$1/; + $upath .= "?$query" if length $query; + + $upath =~ s%^/?%/%; + + # cookie processing + if (my $jar = $arg{cookie_jar}) { + %$jar = () if $jar->{version} != 1; + + my @cookie; + + while (my ($chost, $v) = each %$jar) { + if ($chost =~ /^\./) { + next unless $chost eq substr $uhost, -length $chost; + } elsif ($chost =~ /\./) { + next unless $chost eq $uhost; + } else { + next; + } + + while (my ($cpath, $v) = each %$v) { + next unless $cpath eq substr $upath, 0, length $cpath; + + while (my ($k, $v) = each %$v) { + next if $uscheme ne "https" && exists $v->{secure}; + my $value = $v->{value}; + $value =~ s/([\\"])/\\$1/g; + push @cookie, "$k=\"$value\""; + } + } + } + + $hdr{cookie} = join "; ", @cookie + if @cookie; } - $scheme = lc $scheme; + my ($rhost, $rport, $rscheme, $rpath); # request host, port, path - my %state; - - $state{body} = delete $arg{body}; - - $hdr{"content-length"} = length $state{body}; - - $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { - $state{fh} = shift - or return $cb->(undef, { Status => 599, Reason => "$!" }); + if ($proxy) { + ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); - delete $state{connect_guard}; # reduce memory usage, save a tree + # 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" && $rscheme eq "https"; + } else { + ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); + } - # get handle - $state{handle} = new AnyEvent::Handle - fh => $state{fh}, - ($scheme eq "https" ? (tls => "connect") : ()); + $hdr{"user-agent"} ||= $USERAGENT; + $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic - # limit the number of persistent connections - if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { - ++$KA_COUNT{$_[1]}; - $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; - $hdr{connection} = "keep-alive"; - delete $hdr{connection}; # keep-alive not yet supported - } else { - delete $hdr{connection}; - } + $hdr{host} = "$uhost:$uport"; + $hdr{"content-length"} = length $arg{body}; - # (re-)configure handle - $state{handle}->timeout ($timeout); - $state{handle}->on_error (sub { - %state = (); - $cb->(undef, { Status => 599, Reason => "$!" }); - }); - $state{handle}->on_eof (sub { - %state = (); - $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); - }); - - # send request - $state{handle}->push_write ( - "$method $path HTTP/1.0\015\012" - . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) - . "\015\012" - . (delete $state{body}) - ); - - %hdr = (); # reduce memory usage, save a kitten - - # status line - $state{handle}->push_read (line => qr/\015?\012/, sub { - $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix - or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); - - my %hdr = ( # response headers - HTTPVersion => ",$1", - Status => ",$2", - Reason => ",$3", - ); - - # headers, could be optimized a bit - $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { - for ("$_[1]\012") { - # we support spaces in field names, as lotus domino - # creates them. - $hdr{lc $1} .= ",$2" - while /\G - ([^:\000-\037]+): - [\011\040]* - ((?: [^\015\012]+ | \015?\012[\011\040] )*) - \015?\012 - /gxc; + my %state = (connect_guard => 1); - /\G$/ - or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); - } + _get_slot $uhost, sub { + $state{slot_guard} = shift; + + return unless $state{connect_guard}; + + $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { + $state{fh} = shift + or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url })); + pop; # free memory, save a tree + + return unless delete $state{connect_guard}; + + # get handle + $state{handle} = new AnyEvent::Handle + fh => $state{fh}, + timeout => $timeout, + peername => $rhost, + tls_ctx => $arg{tls_ctx}; + + # limit the number of persistent connections + # keepalive not yet supported + if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { + ++$KA_COUNT{$_[1]}; + $state{handle}{ka_count_guard} = AnyEvent::Util::guard { + --$KA_COUNT{$_[1]} + }; + $hdr{connection} = "keep-alive"; + } else { + delete $hdr{connection}; + } + + # (re-)configure handle + $state{handle}->on_error (sub { + %state = (); + $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); + }); + $state{handle}->on_eof (sub { + %state = (); + $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); + }); - substr $_, 0, 1, "" - for values %hdr; + $state{handle}->starttls ("connect") if $rscheme eq "https"; - if ($method eq "HEAD") { - %state = (); - $cb->(undef, \%hdr); - } else { - if (exists $hdr{"content-length"}) { - $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { - # could cache persistent connection now - if ($hdr{connection} =~ /\bkeep-alive\b/i) { - # but we don't, due to misdesigns, this is annoyingly complex - }; + # handle actual, non-tunneled, request + my $handle_actual_request = sub { + $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; + + # send request + $state{handle}->push_write ( + "$method $rpath HTTP/1.0\015\012" + . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) + . "\015\012" + . (delete $arg{body}) + ); + + %hdr = (); # reduce memory usage, save a kitten + + # status line + $state{handle}->push_read (line => $qr_nl, sub { + $_[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 + HTTPVersion => ",$1", + Status => ",$2", + Reason => ",$3", + URL => ",$url" + ); + + # headers, could be optimized a bit + $state{handle}->unshift_read (line => $qr_nlnl, sub { + for ("$_[1]\012") { + y/\015//d; # weed out any \015, as they show up in the weirdest of places. + + # things seen, not parsed: + # p3pP="NON CUR OTPi OUR NOR UNI" + + $hdr{lc $1} .= ",$2" + while /\G + ([^:\000-\037]+): + [\011\040]* + ((?: [^\012]+ | \012[\011\040] )*) + \012 + /gxc; + + /\G$/ + or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); + } + + substr $_, 0, 1, "" + for values %hdr; + + # redirect handling + # microsoft and other shitheads don't give a shit for following standards, + # try to support some common forms of broken Location headers. + if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { + $hdr{location} =~ s/^\.\/+//; + + my $url = "$rscheme://$uhost:$uport"; + + unless ($hdr{location} =~ s/^\///) { + $url .= $upath; + $url =~ s/\/[^\/]*$//; + } + + $hdr{location} = "$url/$hdr{location}"; + } + + my $redirect; + + if ($recurse) { + if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") { + # apparently, mozilla et al. just change POST to GET here + # more research is needed before we do the same + $redirect = 1; + } elsif ($hdr{Status} == 303) { + # even http/1.1 is unclear on how to mutate the method + $method = "GET" unless $method eq "HEAD"; + $redirect = 1; + } elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) { + $redirect = 1; + } + } + my $finish = sub { + $state{handle}->destroy if $state{handle}; %state = (); - $cb->($_[1], \%hdr); - }); + + # set-cookie processing + if ($arg{cookie_jar}) { + for ($_[1]{"set-cookie"}) { + # parse NAME=VALUE + my @kv; + + while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { + my $name = $1; + my $value = $3; + + unless ($value) { + $value = $2; + $value =~ s/\\(.)/$1/gs; + } + + push @kv, $name => $value; + + last unless /\G\s*;/gc; + } + + last unless @kv; + + my $name = shift @kv; + my %kv = (value => shift @kv, @kv); + + my $cdom; + my $cpath = (delete $kv{path}) || "/"; + + if (exists $kv{domain}) { + $cdom = delete $kv{domain}; + + $cdom =~ s/^\.?/./; # make sure it starts with a "." + + next if $cdom =~ /\.$/; + + # this is not rfc-like and not netscape-like. go figure. + my $ndots = $cdom =~ y/.//; + next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); + } else { + $cdom = $uhost; + } + + # store it + $arg{cookie_jar}{version} = 1; + $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; + + redo if /\G\s*,/gc; + } + } + + if ($redirect) { + # we ignore any errors, as it is very common to receive + # Content-Length != 0 but no actual body + # we also access %hdr, as $_[1] might be an erro + http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); + } else { + $cb->($_[0], $_[1]); + } + }; + + my $len = $hdr{"content-length"}; + + if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { + $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url }); + } elsif ( + $hdr{Status} =~ /^(?:1..|204|304)$/ + or $method eq "HEAD" + or (defined $len && !$len) + ) { + # no body + $finish->("", \%hdr); + } else { + # body handling, four different code paths + # for want_body_handle, on_body (2x), normal (2x) + # we might read too much here, but it does not matter yet (no pers. connections) + if (!$redirect && $arg{want_body_handle}) { + $_[0]->on_eof (undef); + $_[0]->on_error (undef); + $_[0]->on_read (undef); + + $finish->(delete $state{handle}, \%hdr); + + } elsif ($arg{on_body}) { + $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); + if ($len) { + $_[0]->on_eof (undef); + $_[0]->on_read (sub { + $len -= length $_[0]{rbuf}; + + $arg{on_body}(delete $_[0]{rbuf}, \%hdr) + or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); + + $len > 0 + or $finish->("", \%hdr); + }); + } else { + $_[0]->on_eof (sub { + $finish->("", \%hdr); + }); + $_[0]->on_read (sub { + $arg{on_body}(delete $_[0]{rbuf}, \%hdr) + or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); + }); + } + } else { + $_[0]->on_eof (undef); + + if ($len) { + $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); + $_[0]->on_read (sub { + $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) + if $len <= length $_[0]{rbuf}; + }); + } else { + $_[0]->on_error (sub { + $! == Errno::EPIPE + ? $finish->(delete $_[0]{rbuf}, \%hdr) + : $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }); + }); + $_[0]->on_read (sub { }); + } + } + } + }); + }); + }; + + # now handle proxy-CONNECT method + if ($proxy && $uscheme eq "https") { + # oh dear, we have to wrap it into a connect request + + # maybe re-use $uauthority with patched port? + $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); + $state{handle}->push_read (line => $qr_nlnl, sub { + $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix + or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); + + if ($2 == 200) { + $rpath = $upath; + &$handle_actual_request; } else { - # too bad, need to read until we get an error or EOF, - # no way to detect winged data. - $_[0]->on_error (sub { - %state = (); - $cb->($_[0]{rbuf}, \%hdr); - }); - $_[0]->on_eof (undef); - $_[0]->on_read (sub { }); + %state = (); + $cb->(undef, { Status => $2, Reason => $3, URL => $url }); } - } - }); - }); - }, sub { - $timeout + }); + } else { + &$handle_actual_request; + } + + }, sub { + $timeout + }; }; defined wantarray && AnyEvent::Util::guard { %state = () } } -sub http_get($$;@) { +sub http_get($@) { unshift @_, "GET"; &http_request } -sub http_head($$;@) { +sub http_head($@) { unshift @_, "HEAD"; &http_request } -sub http_post($$$;@) { - unshift @_, "POST", "body"; +sub http_post($$@) { + my $url = shift; + unshift @_, "POST", $url, "body"; &http_request } +=back + =head2 GLOBAL FUNCTIONS AND VARIABLES =over 4 @@ -325,7 +725,7 @@ =item $AnyEvent::HTTP::USERAGENT The default value for the C header (the default is -C). +C). =item $AnyEvent::HTTP::MAX_PERSISTENT @@ -339,6 +739,12 @@ Not implemented currently. +=item $AnyEvent::HTTP::ACTIVE + +The number of active connections. This is not the number of currently +running requests, but the number of currently open and non-idle TCP +connections. This number of can be useful for load-leveling. + =back =cut @@ -356,8 +762,11 @@ =head1 AUTHOR - Marc Lehmann - http://home.schmorp.de/ + Marc Lehmann + http://home.schmorp.de/ + +With many thanks to Дмитрий Шалашов, who provided countless +testcases and bugreports. =cut