ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/AnyEvent-HTTP/HTTP.pm
(Generate patch)

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.74 by root, Fri Dec 31 22:40:54 2010 UTC vs.
Revision 1.89 by root, Mon Jan 3 00:23:25 2011 UTC

… …
36 36
37=cut 37=cut
38 38
39package AnyEvent::HTTP; 39package AnyEvent::HTTP;
40 40
41use strict; 41use common::sense;
42no warnings;
43 42
44use Errno (); 43use Errno ();
45 44
46use AnyEvent 5.0 (); 45use AnyEvent 5.0 ();
47use AnyEvent::Util (); 46use AnyEvent::Util ();
… …
58our $MAX_PERSISTENT = 8; 57our $MAX_PERSISTENT = 8;
59our $PERSISTENT_TIMEOUT = 2; 58our $PERSISTENT_TIMEOUT = 2;
60our $TIMEOUT = 300; 59our $TIMEOUT = 300;
61 60
62# changing these is evil 61# changing these is evil
63our $MAX_PERSISTENT_PER_HOST = 0; 62our $MAX_PERSISTENT_PER_HOST = 2;
64our $MAX_PER_HOST = 4; 63our $MAX_PER_HOST = 4;
65 64
66our $PROXY; 65our $PROXY;
67our $ACTIVE = 0; 66our $ACTIVE = 0;
68 67
… …
122 121
123If the server sends a header multiple times, then their contents will be 122If the server sends a header multiple times, then their contents will be
124joined together with a comma (C<,>), as per the HTTP spec. 123joined together with a comma (C<,>), as per the HTTP spec.
125 124
126If an internal error occurs, such as not being able to resolve a hostname, 125If an internal error occurs, such as not being able to resolve a hostname,
127then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> 126then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
128(usually C<599>) and the C<Reason> pseudo-header will contain an error 127C<590>-C<599> and the C<Reason> pseudo-header will contain an error
129message. 128message. Currently the following status codes are used:
129
130=over 4
131
132=item 595 - errors during connection etsbalishment, proxy handshake.
133
134=item 596 - errors during TLS negotiation, request sending and header processing.
135
136=item 597 - errors during body receiving or processing.
137
138=item 598 - user aborted request via C<on_header> or C<on_body>.
139
140=item 599 - other, usually nonretryable, errors (garbled URL etc.).
141
142=back
130 143
131A typical callback might look like this: 144A typical callback might look like this:
132 145
133 sub { 146 sub {
134 my ($body, $hdr) = @_; 147 my ($body, $hdr) = @_;
… …
182=item cookie_jar => $hash_ref 195=item cookie_jar => $hash_ref
183 196
184Passing this parameter enables (simplified) cookie-processing, loosely 197Passing this parameter enables (simplified) cookie-processing, loosely
185based on the original netscape specification. 198based on the original netscape specification.
186 199
187The C<$hash_ref> must be an (initially empty) hash reference which will 200The C<$hash_ref> must be an (initially empty) hash reference which
188get updated automatically. It is possible to save the cookie jar to 201will get updated automatically. It is possible to save the cookie jar
189persistent storage with something like JSON or Storable, but this is not 202to persistent storage with something like JSON or Storable - see the
190recommended, as session-only cookies might survive longer than expected. 203C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
204expired or session-only cookies, and also for documentation on the format
205of the cookie jar.
191 206
192Note that this cookie implementation is not meant to be complete. If 207Note that this cookie implementation is not meant to be complete. If
193you want complete cookie management you have to do that on your 208you want complete cookie management you have to do that on your
194own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites 209own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
195working. Cookies are a privacy disaster, do not use them unless required 210working. Cookies are a privacy disaster, do not use them unless required
196to. 211to.
197 212
198When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> 213When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
199headers will be set and handled by this module, otherwise they will be 214headers will be set and handled by this module, otherwise they will be
… …
364 push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; 379 push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
365 380
366 _slot_schedule $_[0]; 381 _slot_schedule $_[0];
367} 382}
368 383
384#############################################################################
385
386# expire cookies
387sub cookie_jar_expire($;$) {
388 my ($jar, $session_end) = @_;
389
390 %$jar = () if $jar->{version} != 1;
391
392 my $anow = AE::now;
393
394 while (my ($chost, $paths) = each %$jar) {
395 next unless ref $paths;
396
397 while (my ($cpath, $cookies) = each %$paths) {
398 while (my ($cookie, $kv) = each %$cookies) {
399 if (exists $kv->{_expires}) {
400 delete $cookies->{$cookie}
401 if $anow > $kv->{_expires};
402 } elsif ($session_end) {
403 delete $cookies->{$cookie};
404 }
405 }
406
407 delete $paths->{$cpath}
408 unless %$cookies;
409 }
410
411 delete $jar->{$chost}
412 unless %$paths;
413 }
414}
415
369# extract cookies from jar 416# extract cookies from jar
370sub cookie_jar_extract($$$$) { 417sub cookie_jar_extract($$$$) {
371 my ($jar, $uscheme, $uhost, $upath) = @_; 418 my ($jar, $uscheme, $uhost, $upath) = @_;
372 419
373 %$jar = () if $jar->{version} != 1; 420 %$jar = () if $jar->{version} != 1;
… …
389 next unless $cpath eq substr $upath, 0, length $cpath; 436 next unless $cpath eq substr $upath, 0, length $cpath;
390 437
391 while (my ($cookie, $kv) = each %$cookies) { 438 while (my ($cookie, $kv) = each %$cookies) {
392 next if $uscheme ne "https" && exists $kv->{secure}; 439 next if $uscheme ne "https" && exists $kv->{secure};
393 440
394 if (exists $kv->{expires}) { 441 if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
395 if (AE::now > parse_date ($kv->{expires})) {
396 delete $cookies->{$cookie}; 442 delete $cookies->{$cookie};
397 next; 443 next;
398 }
399 } 444 }
400 445
401 my $value = $kv->{value}; 446 my $value = $kv->{value};
402 447
403 if ($value =~ /[=;,[:space:]]/) { 448 if ($value =~ /[=;,[:space:]]/) {
… …
412 457
413 \@cookies 458 \@cookies
414} 459}
415 460
416# parse set_cookie header into jar 461# parse set_cookie header into jar
417sub cookie_jar_set_cookie($$$) { 462sub cookie_jar_set_cookie($$$$) {
418 my ($jar, $set_cookie, $uhost) = @_; 463 my ($jar, $set_cookie, $uhost, $date) = @_;
464
465 my $anow = int AE::now;
466 my $snow; # server-now
419 467
420 for ($set_cookie) { 468 for ($set_cookie) {
421 # parse NAME=VALUE 469 # parse NAME=VALUE
422 my @kv; 470 my @kv;
423 471
472 # expires is not http-compliant in the original cookie-spec,
473 # we support the official date format and some extensions
424 while ( 474 while (
425 m{ 475 m{
426 \G\s* 476 \G\s*
427 (?: 477 (?:
428 expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) 478 expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
429 | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) 479 | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )?
430 ) 480 )
431 }gcxsi 481 }gcxsi
432 ) { 482 ) {
433 my $name = $2; 483 my $name = $2;
434 my $value = $4; 484 my $value = $4;
435 485
436 unless (defined $name) { 486 if (defined $1) {
437 # expires 487 # expires
438 $name = "expires"; 488 $name = "expires";
439 $value = $1; 489 $value = $1;
440 } elsif (!defined $value) { 490 } elsif (defined $3) {
441 # quoted 491 # quoted
442 $value = $3; 492 $value = $3;
443 $value =~ s/\\(.)/$1/gs; 493 $value =~ s/\\(.)/$1/gs;
444 } 494 }
445 495
… …
451 last unless @kv; 501 last unless @kv;
452 502
453 my $name = shift @kv; 503 my $name = shift @kv;
454 my %kv = (value => shift @kv, @kv); 504 my %kv = (value => shift @kv, @kv);
455 505
456 $kv{expires} ||= format_date (AE::now + $kv{"max-age"})
457 if exists $kv{"max-age"}; 506 if (exists $kv{"max-age"}) {
507 $kv{_expires} = $anow + delete $kv{"max-age"};
508 } elsif (exists $kv{expires}) {
509 $snow ||= parse_date ($date) || $anow;
510 $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
511 } else {
512 delete $kv{_expires};
513 }
458 514
459 my $cdom; 515 my $cdom;
460 my $cpath = (delete $kv{path}) || "/"; 516 my $cpath = (delete $kv{path}) || "/";
461 517
462 if (exists $kv{domain}) { 518 if (exists $kv{domain}) {
… …
473 $cdom = $uhost; 529 $cdom = $uhost;
474 } 530 }
475 531
476 # store it 532 # store it
477 $jar->{version} = 1; 533 $jar->{version} = 1;
478 $jar->{$cdom}{$cpath}{$name} = \%kv; 534 $jar->{lc $cdom}{$cpath}{$name} = \%kv;
479 535
480 redo if /\G\s*,/gc; 536 redo if /\G\s*,/gc;
481 } 537 }
482} 538}
483 539
… …
550 : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); 606 : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
551 607
552 $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 608 $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
553 or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); 609 or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
554 610
555 my $uhost = $1; 611 my $uhost = lc $1;
556 $uport = $2 if defined $2; 612 $uport = $2 if defined $2;
557 613
558 $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" 614 $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
559 unless exists $hdr{host}; 615 unless exists $hdr{host};
560 616
… …
579 $rscheme = "http" unless defined $rscheme; 635 $rscheme = "http" unless defined $rscheme;
580 636
581 # don't support https requests over https-proxy transport, 637 # don't support https requests over https-proxy transport,
582 # can't be done with tls as spec'ed, unless you double-encrypt. 638 # can't be done with tls as spec'ed, unless you double-encrypt.
583 $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; 639 $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
640
641 $rhost = lc $rhost;
642 $rscheme = lc $rscheme;
584 } else { 643 } else {
585 ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); 644 ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
586 } 645 }
587 646
588 # leave out fragment and query string, just a heuristic 647 # leave out fragment and query string, just a heuristic
… …
590 $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; 649 $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
591 650
592 $hdr{"content-length"} = length $arg{body} 651 $hdr{"content-length"} = length $arg{body}
593 if length $arg{body} || $method ne "GET"; 652 if length $arg{body} || $method ne "GET";
594 653
595 $hdr{connection} = "close TE"; #1.1 654 my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/;
655
656 # default value for keepalive is true iff the request is for an idempotent method
657 my $keepalive = exists $arg{keepalive}
658 ? $arg{keepalive}*1
659 : $idempotent ? $PERSISTENT_TIMEOUT : 0;
660
661 $hdr{connection} = ($keepalive ? "" : "close ") . "Te"; #1.1
596 $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 662 $hdr{te} = "trailers" unless exists $hdr{te}; #1.1
597 663
598 my %state = (connect_guard => 1); 664 my %state = (connect_guard => 1);
599 665
600 _get_slot $uhost, sub { 666 my $ae_error = 595; # connecting
601 $state{slot_guard} = shift;
602 667
668 # handle actual, non-tunneled, request
669 my $handle_actual_request = sub {
670 $ae_error = 596; # request phase
671
672 $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
673
674 # send request
675 $state{handle}->push_write (
676 "$method $rpath HTTP/1.1\015\012"
677 . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
678 . "\015\012"
679 . (delete $arg{body})
680 );
681
682 # return if error occured during push_write()
603 return unless $state{connect_guard}; 683 return unless %state;
604 684
605 my $connect_cb = sub { 685 # reduce memory usage, save a kitten, also re-use it for the response headers.
606 $state{fh} = shift 686 %hdr = ();
687
688 # status line and headers
689 $state{read_response} = sub {
690 for ("$_[1]") {
691 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
692
693 /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
694 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
695
696 # 100 Continue handling
697 # should not happen as we don't send expect: 100-continue,
698 # but we handle it just in case.
699 # since we send the request body regardless, if we get an error
700 # we are out of-sync, which we currently do NOT handle correctly.
701 return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
702 if $2 eq 100;
703
704 push @pseudo,
705 HTTPVersion => $1,
706 Status => $2,
707 Reason => $3,
607 or do { 708 ;
608 my $err = "$!"; 709
710 my $hdr = parse_hdr
711 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
712
713 %hdr = (%$hdr, @pseudo);
714 }
715
716 # redirect handling
717 # microsoft and other shitheads don't give a shit for following standards,
718 # try to support some common forms of broken Location headers.
719 if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
720 $hdr{location} =~ s/^\.\/+//;
721
722 my $url = "$rscheme://$uhost:$uport";
723
724 unless ($hdr{location} =~ s/^\///) {
725 $url .= $upath;
726 $url =~ s/\/[^\/]*$//;
727 }
728
729 $hdr{location} = "$url/$hdr{location}";
730 }
731
732 my $redirect;
733
734 if ($recurse) {
735 my $status = $hdr{Status};
736
737 # industry standard is to redirect POST as GET for
738 # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
739 # also, the UA should ask the user for 301 and 307 and POST,
740 # industry standard seems to be to simply follow.
741 # we go with the industry standard.
742 if ($status == 301 or $status == 302 or $status == 303) {
743 # HTTP/1.1 is unclear on how to mutate the method
744 $method = "GET" unless $method eq "HEAD";
745 $redirect = 1;
746 } elsif ($status == 307) {
747 $redirect = 1;
748 }
749 }
750
751 my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
752 my $may_keep_alive = $_[3];
753
754 $state{handle}->destroy if $state{handle};
609 %state = (); 755 %state = ();
610 return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); 756
757 if (defined $_[1]) {
758 $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
759 $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
760 }
761
762 # set-cookie processing
763 if ($arg{cookie_jar}) {
764 cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
765 }
766
767 if ($redirect && exists $hdr{location}) {
768 # we ignore any errors, as it is very common to receive
769 # Content-Length != 0 but no actual body
770 # we also access %hdr, as $_[1] might be an erro
771 http_request (
772 $method => $hdr{location},
773 %arg,
774 recurse => $recurse - 1,
775 Redirect => [$_[0], \%hdr],
776 $cb);
777 } else {
778 $cb->($_[0], \%hdr);
779 }
780 };
781
782 $ae_error = 597; # body phase
783
784 my $len = $hdr{"content-length"};
785
786 # body handling, many different code paths
787 # - no body expected
788 # - want_body_handle
789 # - te chunked
790 # - 2x length known (with or without on_body)
791 # - 2x length not known (with or without on_body)
792 if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
793 $finish->(undef, 598 => "Request cancelled by on_header");
794 } elsif (
795 $hdr{Status} =~ /^(?:1..|204|205|304)$/
796 or $method eq "HEAD"
797 or (defined $len && $len == 0) # == 0, not !, because "0 " is true
798 ) {
799 # no body
800 $finish->("", undef, undef, 1);
801
802 } elsif (!$redirect && $arg{want_body_handle}) {
803 $_[0]->on_eof (undef);
804 $_[0]->on_error (undef);
805 $_[0]->on_read (undef);
806
807 $finish->(delete $state{handle});
808
809 } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
810 my $cl = 0;
811 my $body = undef;
812 my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
813
814 $state{read_chunk} = sub {
815 $_[1] =~ /^([0-9a-fA-F]+)/
816 or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
817
818 my $len = hex $1;
819
820 if ($len) {
821 $cl += $len;
822
823 $_[0]->push_read (chunk => $len, sub {
824 $on_body->($_[1], \%hdr)
825 or return $finish->(undef, 598 => "Request cancelled by on_body");
826
827 $_[0]->push_read (line => sub {
828 length $_[1]
829 and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
830 $_[0]->push_read (line => $state{read_chunk});
831 });
832 });
833 } else {
834 $hdr{"content-length"} ||= $cl;
835
836 $_[0]->push_read (line => $qr_nlnl, sub {
837 if (length $_[1]) {
838 for ("$_[1]") {
839 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
840
841 my $hdr = parse_hdr
842 or return $finish->(undef, $ae_error => "Garbled response trailers");
843
844 %hdr = (%hdr, %$hdr);
845 }
846 }
847
848 $finish->($body, undef, undef, 1);
849 });
850 }
611 }; 851 };
612 852
613 pop; # free memory, save a tree 853 $_[0]->push_read (line => $state{read_chunk});
614 854
855 } elsif ($arg{on_body}) {
856 if (defined $len) {
857 $_[0]->on_read (sub {
858 $len -= length $_[0]{rbuf};
859
860 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
861 or return $finish->(undef, 598 => "Request cancelled by on_body");
862
863 $len > 0
864 or $finish->("", undef, undef, 1);
865 });
866 } else {
867 $_[0]->on_eof (sub {
868 $finish->("");
869 });
870 $_[0]->on_read (sub {
871 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
872 or $finish->(undef, 598 => "Request cancelled by on_body");
873 });
874 }
875 } else {
876 $_[0]->on_eof (undef);
877
878 if (defined $len) {
879 $_[0]->on_read (sub {
880 $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
881 if $len <= length $_[0]{rbuf};
882 });
883 } else {
884 $_[0]->on_error (sub {
885 ($! == Errno::EPIPE || !$!)
886 ? $finish->(delete $_[0]{rbuf})
887 : $finish->(undef, $ae_error => $_[2]);
888 });
889 $_[0]->on_read (sub { });
890 }
891 }
892 };
893
894 $state{handle}->push_read (line => $qr_nlnl, $state{read_response});
895 };
896
897 my $connect_cb = sub {
898 $state{fh} = shift
899 or do {
900 my $err = "$!";
901 %state = ();
902 return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
903 };
904
615 return unless delete $state{connect_guard}; 905 return unless delete $state{connect_guard};
616 906
617 # get handle 907 # get handle
618 $state{handle} = new AnyEvent::Handle 908 $state{handle} = new AnyEvent::Handle
619 fh => $state{fh}, 909 fh => $state{fh},
620 peername => $rhost, 910 peername => $rhost,
621 tls_ctx => $arg{tls_ctx}, 911 tls_ctx => $arg{tls_ctx},
622 # these need to be reconfigured on keepalive handles 912 # these need to be reconfigured on keepalive handles
623 timeout => $timeout, 913 timeout => $timeout,
624 on_error => sub { 914 on_error => sub {
625 %state = (); 915 %state = ();
626 $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); 916 $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
627 }, 917 },
628 on_eof => sub { 918 on_eof => sub {
629 %state = (); 919 %state = ();
630 $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); 920 $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
631 }, 921 },
632 ; 922 ;
633 923
634 # limit the number of persistent connections 924 # limit the number of persistent connections
635 # keepalive not yet supported 925 # keepalive not yet supported
636# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { 926# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
637# ++$KA_COUNT{$_[1]}; 927# ++$KA_COUNT{$_[1]};
638# $state{handle}{ka_count_guard} = AnyEvent::Util::guard { 928# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
639# --$KA_COUNT{$_[1]} 929# --$KA_COUNT{$_[1]}
640# }; 930# };
641# $hdr{connection} = "keep-alive"; 931# $hdr{connection} = "keep-alive";
642# } 932# }
643 933
644 $state{handle}->starttls ("connect") if $rscheme eq "https"; 934 $state{handle}->starttls ("connect") if $rscheme eq "https";
645 935
646 # handle actual, non-tunneled, request
647 my $handle_actual_request = sub {
648 $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
649
650 # send request
651 $state{handle}->push_write (
652 "$method $rpath HTTP/1.1\015\012"
653 . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
654 . "\015\012"
655 . (delete $arg{body})
656 );
657
658 # return if error occured during push_write()
659 return unless %state;
660
661 %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
662
663 # status line and headers
664 $state{read_response} = sub {
665 for ("$_[1]") {
666 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
667
668 /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
669 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
670
671 # 100 Continue handling
672 # should not happen as we don't send expect: 100-continue,
673 # but we handle it just in case.
674 # since we send the request body regardless, if we get an error
675 # we are out of-sync, which we currently do NOT handle correctly.
676 return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
677 if $2 eq 100;
678
679 push @pseudo,
680 HTTPVersion => $1,
681 Status => $2,
682 Reason => $3,
683 ;
684
685 my $hdr = parse_hdr
686 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
687
688 %hdr = (%$hdr, @pseudo);
689 }
690
691 # redirect handling
692 # microsoft and other shitheads don't give a shit for following standards,
693 # try to support some common forms of broken Location headers.
694 if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
695 $hdr{location} =~ s/^\.\/+//;
696
697 my $url = "$rscheme://$uhost:$uport";
698
699 unless ($hdr{location} =~ s/^\///) {
700 $url .= $upath;
701 $url =~ s/\/[^\/]*$//;
702 }
703
704 $hdr{location} = "$url/$hdr{location}";
705 }
706
707 my $redirect;
708
709 if ($recurse) {
710 my $status = $hdr{Status};
711
712 # industry standard is to redirect POST as GET for
713 # 301, 302 and 303, in contrast to http/1.0 and 1.1.
714 # also, the UA should ask the user for 301 and 307 and POST,
715 # industry standard seems to be to simply follow.
716 # we go with the industry standard.
717 if ($status == 301 or $status == 302 or $status == 303) {
718 # HTTP/1.1 is unclear on how to mutate the method
719 $method = "GET" unless $method eq "HEAD";
720 $redirect = 1;
721 } elsif ($status == 307) {
722 $redirect = 1;
723 }
724 }
725
726 my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
727 my $may_keep_alive = $_[3];
728
729 $state{handle}->destroy if $state{handle};
730 %state = ();
731
732 if (defined $_[1]) {
733 $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
734 $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
735 }
736
737 # set-cookie processing
738 if ($arg{cookie_jar}) {
739 cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost;
740 }
741
742 if ($redirect && exists $hdr{location}) {
743 # we ignore any errors, as it is very common to receive
744 # Content-Length != 0 but no actual body
745 # we also access %hdr, as $_[1] might be an erro
746 http_request (
747 $method => $hdr{location},
748 %arg,
749 recurse => $recurse - 1,
750 Redirect => [$_[0], \%hdr],
751 $cb);
752 } else {
753 $cb->($_[0], \%hdr);
754 }
755 };
756
757 my $len = $hdr{"content-length"};
758
759 if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
760 $finish->(undef, 598 => "Request cancelled by on_header");
761 } elsif (
762 $hdr{Status} =~ /^(?:1..|204|205|304)$/
763 or $method eq "HEAD"
764 or (defined $len && !$len)
765 ) {
766 # no body
767 $finish->("", undef, undef, 1);
768 } else {
769 # body handling, many different code paths
770 # - no body expected
771 # - want_body_handle
772 # - te chunked
773 # - 2x length known (with or without on_body)
774 # - 2x length not known (with or without on_body)
775 if (!$redirect && $arg{want_body_handle}) {
776 $_[0]->on_eof (undef);
777 $_[0]->on_error (undef);
778 $_[0]->on_read (undef);
779
780 $finish->(delete $state{handle});
781
782 } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
783 my $cl = 0;
784 my $body = undef;
785 my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
786
787 $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
788
789 my $read_chunk; $read_chunk = sub {
790 $_[1] =~ /^([0-9a-fA-F]+)/
791 or $finish->(undef, 599 => "Garbled chunked transfer encoding");
792
793 my $len = hex $1;
794
795 if ($len) {
796 $cl += $len;
797
798 $_[0]->push_read (chunk => $len, sub {
799 $on_body->($_[1], \%hdr)
800 or return $finish->(undef, 598 => "Request cancelled by on_body");
801
802 $_[0]->push_read (line => sub {
803 length $_[1]
804 and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
805 $_[0]->push_read (line => $read_chunk);
806 });
807 });
808 } else {
809 $hdr{"content-length"} ||= $cl;
810
811 $_[0]->push_read (line => $qr_nlnl, sub {
812 if (length $_[1]) {
813 for ("$_[1]") {
814 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
815
816 my $hdr = parse_hdr
817 or return $finish->(undef, 599 => "Garbled response trailers");
818
819 %hdr = (%hdr, %$hdr);
820 }
821 }
822
823 $finish->($body, undef, undef, 1);
824 });
825 }
826 };
827
828 $_[0]->push_read (line => $read_chunk);
829
830 } elsif ($arg{on_body}) {
831 $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
832
833 if ($len) {
834 $_[0]->on_read (sub {
835 $len -= length $_[0]{rbuf};
836
837 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
838 or return $finish->(undef, 598 => "Request cancelled by on_body");
839
840 $len > 0
841 or $finish->("", undef, undef, 1);
842 });
843 } else {
844 $_[0]->on_eof (sub {
845 $finish->("");
846 });
847 $_[0]->on_read (sub {
848 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
849 or $finish->(undef, 598 => "Request cancelled by on_body");
850 });
851 }
852 } else {
853 $_[0]->on_eof (undef);
854
855 if ($len) {
856 $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
857 $_[0]->on_read (sub {
858 $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
859 if $len <= length $_[0]{rbuf};
860 });
861 } else {
862 $_[0]->on_error (sub {
863 ($! == Errno::EPIPE || !$!)
864 ? $finish->(delete $_[0]{rbuf})
865 : $finish->(undef, 599 => $_[2]);
866 });
867 $_[0]->on_read (sub { });
868 }
869 }
870 }
871 };
872
873 $state{handle}->push_read (line => $qr_nlnl, $state{read_response});
874 };
875
876 # now handle proxy-CONNECT method 936 # now handle proxy-CONNECT method
877 if ($proxy && $uscheme eq "https") { 937 if ($proxy && $uscheme eq "https") {
878 # oh dear, we have to wrap it into a connect request 938 # oh dear, we have to wrap it into a connect request
879 939
880 # maybe re-use $uauthority with patched port? 940 # maybe re-use $uauthority with patched port?
881 $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); 941 $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
882 $state{handle}->push_read (line => $qr_nlnl, sub { 942 $state{handle}->push_read (line => $qr_nlnl, sub {
883 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix 943 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
884 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); 944 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
885 945
886 if ($2 == 200) { 946 if ($2 == 200) {
887 $rpath = $upath; 947 $rpath = $upath;
888 &$handle_actual_request; 948 $handle_actual_request->();
889 } else { 949 } else {
890 %state = (); 950 %state = ();
891 $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); 951 $cb->(undef, { @pseudo, Status => $2, Reason => $3 });
892 }
893 }); 952 }
894 } else {
895 &$handle_actual_request;
896 } 953 });
954 } else {
955 $handle_actual_request->();
897 }; 956 }
957 };
958
959 _get_slot $uhost, sub {
960 $state{slot_guard} = shift;
961
962 return unless $state{connect_guard};
898 963
899 my $tcp_connect = $arg{tcp_connect} 964 my $tcp_connect = $arg{tcp_connect}
900 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; 965 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
901 966
902 $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); 967 $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
903
904 }; 968 };
905 969
906 defined wantarray && AnyEvent::Util::guard { %state = () } 970 defined wantarray && AnyEvent::Util::guard { %state = () }
907} 971}
908 972
… …
943string of the form C<http://host:port> (optionally C<https:...>), croaks 1007string of the form C<http://host:port> (optionally C<https:...>), croaks
944otherwise. 1008otherwise.
945 1009
946To clear an already-set proxy, use C<undef>. 1010To clear an already-set proxy, use C<undef>.
947 1011
1012=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
1013
1014Remove all cookies from the cookie jar that have been expired. If
1015C<$session_end> is given and true, then additionally remove all session
1016cookies.
1017
1018You should call this function (with a true C<$session_end>) before you
1019save cookies to disk, and you should call this function after loading them
1020again. If you have a long-running program you can additonally call this
1021function from time to time.
1022
1023A cookie jar is initially an empty hash-reference that is managed by this
1024module. It's format is subject to change, but currently it is like this:
1025
1026The key C<version> has to contain C<1>, otherwise the hash gets
1027emptied. All other keys are hostnames or IP addresses pointing to
1028hash-references. The key for these inner hash references is the
1029server path for which this cookie is meant, and the values are again
1030hash-references. The keys of those hash-references is the cookie name, and
1031the value, you guessed it, is another hash-reference, this time with the
1032key-value pairs from the cookie, except for C<expires> and C<max-age>,
1033which have been replaced by a C<_expires> key that contains the cookie
1034expiry timestamp.
1035
1036Here is an example of a cookie jar with a single cookie, so you have a
1037chance of understanding the above paragraph:
1038
1039 {
1040 version => 1,
1041 "10.0.0.1" => {
1042 "/" => {
1043 "mythweb_id" => {
1044 _expires => 1293917923,
1045 value => "ooRung9dThee3ooyXooM1Ohm",
1046 },
1047 },
1048 },
1049 }
1050
948=item $date = AnyEvent::HTTP::format_date $timestamp 1051=item $date = AnyEvent::HTTP::format_date $timestamp
949 1052
950Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP 1053Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
951Date (RFC 2616). 1054Date (RFC 2616).
952 1055
953=item $timestamp = AnyEvent::HTTP::parse_date $date 1056=item $timestamp = AnyEvent::HTTP::parse_date $date
954 1057
955Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and 1058Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
956returns the corresponding POSIX timestamp, or C<undef> if the date cannot 1059bunch of minor variations of those, and returns the corresponding POSIX
957be parsed. 1060timestamp, or C<undef> if the date cannot be parsed.
958 1061
959=item $AnyEvent::HTTP::MAX_RECURSE 1062=item $AnyEvent::HTTP::MAX_RECURSE
960 1063
961The default value for the C<recurse> request parameter (default: C<10>). 1064The default value for the C<recurse> request parameter (default: C<10>).
962 1065
… …
1001sub parse_date($) { 1104sub parse_date($) {
1002 my ($date) = @_; 1105 my ($date) = @_;
1003 1106
1004 my ($d, $m, $y, $H, $M, $S); 1107 my ($d, $m, $y, $H, $M, $S);
1005 1108
1006 if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9])[\- ]([A-Z][a-z][a-z])[\- ]([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { 1109 if ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)[\- ]([A-Z][a-z][a-z])[\- ]([0-9][0-9][0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) {
1007 # RFC 822/1123, required by RFC 2616 (with " ") 1110 # RFC 822/1123, required by RFC 2616 (with " ")
1008 # cookie dates (with "-") 1111 # cookie dates (with "-")
1009 1112
1010 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); 1113 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
1011 1114
1012 } elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { 1115 } elsif ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) {
1013 # RFC 850 1116 # RFC 850
1014 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); 1117 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
1015 1118
1016 } elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) { 1119 } elsif ($date =~ /^[A-Z][a-z][a-z]+ ([A-Z][a-z][a-z]) ([0-9 ]?[0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) ([0-9][0-9][0-9][0-9])$/) {
1017 # ISO C's asctime 1120 # ISO C's asctime
1018 ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); 1121 ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
1019 } 1122 }
1020 # other formats fail in the loop below 1123 # other formats fail in the loop below
1021 1124

Diff Legend

– Removed lines
+ Added lines
< Changed lines
> Changed lines