--- AnyEvent-HTTP/HTTP.pm 2008/06/04 11:59:22 1.4 +++ AnyEvent-HTTP/HTTP.pm 2008/07/02 01:30:33 1.24 @@ -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 @@ -31,9 +50,9 @@ use base Exporter::; -our $VERSION = '1.0'; +our $VERSION = '1.03'; -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 $MAX_RECURSE = 10; @@ -43,20 +62,27 @@ # 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. -=item http_get $url, $body, key => value..., $cb->($data, $headers) +=item http_head $url, key => value..., $cb->($data, $headers) + +Executes an HTTP-HEAD request. See the http_request function for details on +additional parameters. + +=item http_post $url, $body, key => value..., $cb->($data, $headers) -Executes an HTTP-POST request with a requets body of C<$bod>. See the +Executes an HTTP-POST request with a request body of C<$bod>. See the http_request function for details on additional parameters. =item http_request $method => $url, key => value..., $cb->($data, $headers) @@ -68,15 +94,31 @@ (or C if it wasn't available due to errors), and a hash-ref with response headers as second argument. -All the headers in that has are lowercased. In addition to the response -headers, the three "pseudo-headers" C, C and -C contain the three parts of the HTTP Status-Line of the same -name. +All the headers in that hash are lowercased. In addition to the response +headers, the "pseudo-headers" C, C and C +contain the three parts of the HTTP Status-Line of the same name. The +pseudo-header C contains the original URL (which can differ from the +requested URL when following redirects). + +If the server sends a header multiple lines, then their contents will be +joined together with C<\x00>. If an internal error occurs, such as not being able to resolve a hostname, then C<$data> will be C, C<< $headers->{Status} >> will be C<599> and the C pseudo-header will contain an error message. +A typical callback might look like this: + + sub { + my ($body, $hdr) = @_; + + if ($hdr->{Status} =~ /^2/) { + ... everything should be ok + } else { + print "error, $hdr->{Status} $hdr->{Reason}\n"; + } + } + Additional parameters are key-value pairs, and are fully optional. They include: @@ -89,7 +131,9 @@ =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 @@ -109,13 +153,77 @@ 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 expire 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. =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; + } + ; + =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]; +} + +sub http_request($$@) { my $cb = pop; my ($method, $url, %arg) = @_; @@ -123,175 +231,259 @@ $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 $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; + + return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) + if $recurse < 0; + my $proxy = $arg{proxy} || $PROXY; my $timeout = $arg{timeout} || $TIMEOUT; - my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; $hdr{"user-agent"} ||= $USERAGENT; - my ($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"; + my ($scheme, $authority, $upath, $query, $fragment) = + $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; - $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x - or croak "$authority: unparsable URL"; - - $host = $1; - $port = $2 if defined $2; + $scheme = lc $scheme; - $host =~ s/^\[(.*)\]$/$1/; - $path .= "?$query" if length $query; + my $uport = $scheme eq "http" ? 80 + : $scheme eq "https" ? 443 + : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); + + $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic + + $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/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) { + next unless $chost eq substr $uhost, -length $chost; + next unless $chost =~ /^\./; + + while (my ($cpath, $v) = each %$v) { + next unless $cpath eq substr $upath, 0, length $cpath; + + while (my ($k, $v) = each %$v) { + next if $scheme ne "https" && exists $v->{secure}; + push @cookie, "$k=$v->{value}"; + } + } + } + + $hdr{cookie} = join "; ", @cookie + if @cookie; + } - $path = "/" unless $path; + my ($rhost, $rport, $rpath); # request host, port, path - $hdr{host} = $host = lc $host; + if ($proxy) { + ($rhost, $rport, $scheme) = @$proxy; + $rpath = $url; + } else { + ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); + $hdr{host} = $uhost; } - $scheme = lc $scheme; + $hdr{"content-length"} = length $arg{body}; - my %state; + my %state = (connect_guard => 1); - $state{body} = delete $arg{body}; + _get_slot $uhost, sub { + $state{slot_guard} = shift; - $hdr{"content-length"} = length $state{body}; + return unless $state{connect_guard}; - $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { - $state{fh} = shift - or return $cb->(undef, { Status => 599, Reason => "$!" }); + $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { + $state{fh} = shift + or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); + + delete $state{connect_guard}; # reduce memory usage, save a tree + + # get handle + $state{handle} = new AnyEvent::Handle + fh => $state{fh}, + ($scheme eq "https" ? (tls => "connect") : ()); + + # 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}; + } + + # (re-)configure handle + $state{handle}->timeout ($timeout); + $state{handle}->on_error (sub { + my $errno = "$!"; + %state = (); + $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); + }); + $state{handle}->on_eof (sub { + %state = (); + $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); + }); - delete $state{connect_guard}; # reduce memory usage, save a tree + # send request + $state{handle}->push_write ( + "$method $rpath HTTP/1.0\015\012" + . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) + . "\015\012" + . (delete $arg{body}) + ); - # get handle - $state{handle} = new AnyEvent::Handle - fh => $state{fh}, - ($scheme eq "https" ? (tls => "connect") : ()); + %hdr = (); # reduce memory usage, save a kitten - # 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}; - } + # 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])", URL => $url })); + + my %hdr = ( # response headers + HTTPVersion => "\x00$1", + Status => "\x00$2", + Reason => "\x00$3", + URL => "\x00$url" + ); + + # 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} .= "\x00$2" + while /\G + ([^:\000-\037]+): + [\011\040]* + ((?: [^\015\012]+ | \015?\012[\011\040] )*) + \015?\012 + /gxc; - # (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 => ",$3", - ); + /\G$/ + or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); + } - # 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; + substr $_, 0, 1, "" + for values %hdr; - /\G$/ - or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); - } + my $finish = sub { + %state = (); - substr $_, 0, 1, "" - for values %hdr; + # set-cookie processing + if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { + for (split /\x00/, $hdr{"set-cookie"}) { + my ($cookie, @arg) = split /;\s*/; + my ($name, $value) = split /=/, $cookie, 2; + my %kv = (value => $value, map { split /=/, $_, 2 } @arg); + + my $cdom = (delete $kv{domain}) || $uhost; + my $cpath = (delete $kv{path}) || "/"; + + $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); + + # store it + $arg{cookie_jar}{version} = 1; + $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; + } + } + + # 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/% + if exists $_[1]{location}; + + if ($_[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], $_[1]); + } + }; - if ($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 - }; - - %state = (); - $cb->($_[1], \%hdr); - }); + if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { + $finish->(undef, \%hdr); } 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 { }); + 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 + }; + + $finish->($_[1], \%hdr); + }); + } else { + # too bad, need to read until we get an error or EOF, + # no way to detect winged data. + $_[0]->on_error (sub { + $finish->($_[0]{rbuf}, \%hdr); + }); + $_[0]->on_eof (undef); + $_[0]->on_read (sub { }); + } } - } + }); }); - }); - }, sub { - $timeout + }, 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 @@ -322,6 +514,12 @@ 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 @@ -339,8 +537,8 @@ =head1 AUTHOR - Marc Lehmann - http://home.schmorp.de/ + Marc Lehmann + http://home.schmorp.de/ =cut