… | |
… | |
36 | |
36 | |
37 | =cut |
37 | =cut |
38 | |
38 | |
39 | package AnyEvent::HTTP; |
39 | package AnyEvent::HTTP; |
40 | |
40 | |
41 | use strict; |
41 | use common::sense; |
42 | no warnings; |
|
|
43 | |
42 | |
44 | use Errno (); |
43 | use Errno (); |
45 | |
44 | |
46 | use AnyEvent 5.0 (); |
45 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
46 | use AnyEvent::Util (); |
… | |
… | |
196 | =item cookie_jar => $hash_ref |
195 | =item cookie_jar => $hash_ref |
197 | |
196 | |
198 | Passing this parameter enables (simplified) cookie-processing, loosely |
197 | Passing this parameter enables (simplified) cookie-processing, loosely |
199 | based on the original netscape specification. |
198 | based on the original netscape specification. |
200 | |
199 | |
201 | The C<$hash_ref> must be an (initially empty) hash reference which will |
200 | The C<$hash_ref> must be an (initially empty) hash reference which |
202 | get updated automatically. It is possible to save the cookie jar to |
201 | will get updated automatically. It is possible to save the cookie jar |
203 | persistent storage with something like JSON or Storable, but this is not |
202 | to persistent storage with something like JSON or Storable - see the |
204 | recommended, as session-only cookies might survive longer than expected. |
203 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
204 | expired or session-only cookies, and also for documentation on the format |
|
|
205 | of the cookie jar. |
205 | |
206 | |
206 | Note that this cookie implementation is not meant to be complete. If |
207 | Note that this cookie implementation is not meant to be complete. If |
207 | you want complete cookie management you have to do that on your |
208 | you want complete cookie management you have to do that on your |
208 | own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites |
209 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
209 | working. Cookies are a privacy disaster, do not use them unless required |
210 | working. Cookies are a privacy disaster, do not use them unless required |
210 | to. |
211 | to. |
211 | |
212 | |
212 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
213 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
213 | headers will be set and handled by this module, otherwise they will be |
214 | headers will be set and handled by this module, otherwise they will be |
… | |
… | |
378 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
379 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
379 | |
380 | |
380 | _slot_schedule $_[0]; |
381 | _slot_schedule $_[0]; |
381 | } |
382 | } |
382 | |
383 | |
|
|
384 | ############################################################################# |
|
|
385 | |
|
|
386 | # expire cookies |
|
|
387 | sub cookie_jar_expire($;$) { |
|
|
388 | my ($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 | |
383 | # extract cookies from jar |
416 | # extract cookies from jar |
384 | sub cookie_jar_extract($$$$) { |
417 | sub cookie_jar_extract($$$$) { |
385 | my ($jar, $uscheme, $uhost, $upath) = @_; |
418 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
419 | |
|
|
420 | $uhost = lc $uhost; |
386 | |
421 | |
387 | %$jar = () if $jar->{version} != 1; |
422 | %$jar = () if $jar->{version} != 1; |
388 | |
423 | |
389 | my @cookies; |
424 | my @cookies; |
390 | |
425 | |
… | |
… | |
403 | next unless $cpath eq substr $upath, 0, length $cpath; |
438 | next unless $cpath eq substr $upath, 0, length $cpath; |
404 | |
439 | |
405 | while (my ($cookie, $kv) = each %$cookies) { |
440 | while (my ($cookie, $kv) = each %$cookies) { |
406 | next if $uscheme ne "https" && exists $kv->{secure}; |
441 | next if $uscheme ne "https" && exists $kv->{secure}; |
407 | |
442 | |
408 | if (exists $kv->{expires}) { |
443 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
409 | if (AE::now > parse_date ($kv->{expires})) { |
|
|
410 | delete $cookies->{$cookie}; |
444 | delete $cookies->{$cookie}; |
411 | next; |
445 | next; |
412 | } |
|
|
413 | } |
446 | } |
414 | |
447 | |
415 | my $value = $kv->{value}; |
448 | my $value = $kv->{value}; |
416 | |
449 | |
417 | if ($value =~ /[=;,[:space:]]/) { |
450 | if ($value =~ /[=;,[:space:]]/) { |
… | |
… | |
426 | |
459 | |
427 | \@cookies |
460 | \@cookies |
428 | } |
461 | } |
429 | |
462 | |
430 | # parse set_cookie header into jar |
463 | # parse set_cookie header into jar |
431 | sub cookie_jar_set_cookie($$$) { |
464 | sub cookie_jar_set_cookie($$$$) { |
432 | my ($jar, $set_cookie, $uhost) = @_; |
465 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
466 | |
|
|
467 | my $anow = int AE::now; |
|
|
468 | my $snow; # server-now |
433 | |
469 | |
434 | for ($set_cookie) { |
470 | for ($set_cookie) { |
435 | # parse NAME=VALUE |
471 | # parse NAME=VALUE |
436 | my @kv; |
472 | my @kv; |
437 | |
473 | |
|
|
474 | # expires is not http-compliant in the original cookie-spec, |
|
|
475 | # we support the official date format and some extensions |
438 | while ( |
476 | while ( |
439 | m{ |
477 | m{ |
440 | \G\s* |
478 | \G\s* |
441 | (?: |
479 | (?: |
442 | expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) |
480 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
443 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
481 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
444 | ) |
482 | ) |
445 | }gcxsi |
483 | }gcxsi |
446 | ) { |
484 | ) { |
447 | my $name = $2; |
485 | my $name = $2; |
448 | my $value = $4; |
486 | my $value = $4; |
449 | |
487 | |
450 | unless (defined $name) { |
488 | if (defined $1) { |
451 | # expires |
489 | # expires |
452 | $name = "expires"; |
490 | $name = "expires"; |
453 | $value = $1; |
491 | $value = $1; |
454 | } elsif (!defined $value) { |
492 | } elsif (defined $3) { |
455 | # quoted |
493 | # quoted |
456 | $value = $3; |
494 | $value = $3; |
457 | $value =~ s/\\(.)/$1/gs; |
495 | $value =~ s/\\(.)/$1/gs; |
458 | } |
496 | } |
459 | |
497 | |
… | |
… | |
465 | last unless @kv; |
503 | last unless @kv; |
466 | |
504 | |
467 | my $name = shift @kv; |
505 | my $name = shift @kv; |
468 | my %kv = (value => shift @kv, @kv); |
506 | my %kv = (value => shift @kv, @kv); |
469 | |
507 | |
470 | $kv{expires} ||= format_date (AE::now + $kv{"max-age"}) |
|
|
471 | if exists $kv{"max-age"}; |
508 | if (exists $kv{"max-age"}) { |
|
|
509 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
510 | } elsif (exists $kv{expires}) { |
|
|
511 | $snow ||= parse_date ($date) || $anow; |
|
|
512 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
513 | } else { |
|
|
514 | delete $kv{_expires}; |
|
|
515 | } |
472 | |
516 | |
473 | my $cdom; |
517 | my $cdom; |
474 | my $cpath = (delete $kv{path}) || "/"; |
518 | my $cpath = (delete $kv{path}) || "/"; |
475 | |
519 | |
476 | if (exists $kv{domain}) { |
520 | if (exists $kv{domain}) { |
… | |
… | |
487 | $cdom = $uhost; |
531 | $cdom = $uhost; |
488 | } |
532 | } |
489 | |
533 | |
490 | # store it |
534 | # store it |
491 | $jar->{version} = 1; |
535 | $jar->{version} = 1; |
492 | $jar->{$cdom}{$cpath}{$name} = \%kv; |
536 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
493 | |
537 | |
494 | redo if /\G\s*,/gc; |
538 | redo if /\G\s*,/gc; |
495 | } |
539 | } |
496 | } |
540 | } |
497 | |
541 | |
… | |
… | |
615 | $state{slot_guard} = shift; |
659 | $state{slot_guard} = shift; |
616 | |
660 | |
617 | return unless $state{connect_guard}; |
661 | return unless $state{connect_guard}; |
618 | |
662 | |
619 | my $ae_error = 595; # connecting |
663 | my $ae_error = 595; # connecting |
|
|
664 | |
|
|
665 | # handle actual, non-tunneled, request |
|
|
666 | my $handle_actual_request = sub { |
|
|
667 | $ae_error = 596; # request phase |
|
|
668 | |
|
|
669 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
670 | |
|
|
671 | # send request |
|
|
672 | $state{handle}->push_write ( |
|
|
673 | "$method $rpath HTTP/1.1\015\012" |
|
|
674 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
675 | . "\015\012" |
|
|
676 | . (delete $arg{body}) |
|
|
677 | ); |
|
|
678 | |
|
|
679 | # return if error occured during push_write() |
|
|
680 | return unless %state; |
|
|
681 | |
|
|
682 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
683 | |
|
|
684 | # status line and headers |
|
|
685 | $state{read_response} = sub { |
|
|
686 | for ("$_[1]") { |
|
|
687 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
688 | |
|
|
689 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
690 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
691 | |
|
|
692 | # 100 Continue handling |
|
|
693 | # should not happen as we don't send expect: 100-continue, |
|
|
694 | # but we handle it just in case. |
|
|
695 | # since we send the request body regardless, if we get an error |
|
|
696 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
697 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
698 | if $2 eq 100; |
|
|
699 | |
|
|
700 | push @pseudo, |
|
|
701 | HTTPVersion => $1, |
|
|
702 | Status => $2, |
|
|
703 | Reason => $3, |
|
|
704 | ; |
|
|
705 | |
|
|
706 | my $hdr = parse_hdr |
|
|
707 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
708 | |
|
|
709 | %hdr = (%$hdr, @pseudo); |
|
|
710 | } |
|
|
711 | |
|
|
712 | # redirect handling |
|
|
713 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
714 | # try to support some common forms of broken Location headers. |
|
|
715 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
716 | $hdr{location} =~ s/^\.\/+//; |
|
|
717 | |
|
|
718 | my $url = "$rscheme://$uhost:$uport"; |
|
|
719 | |
|
|
720 | unless ($hdr{location} =~ s/^\///) { |
|
|
721 | $url .= $upath; |
|
|
722 | $url =~ s/\/[^\/]*$//; |
|
|
723 | } |
|
|
724 | |
|
|
725 | $hdr{location} = "$url/$hdr{location}"; |
|
|
726 | } |
|
|
727 | |
|
|
728 | my $redirect; |
|
|
729 | |
|
|
730 | if ($recurse) { |
|
|
731 | my $status = $hdr{Status}; |
|
|
732 | |
|
|
733 | # industry standard is to redirect POST as GET for |
|
|
734 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
735 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
736 | # industry standard seems to be to simply follow. |
|
|
737 | # we go with the industry standard. |
|
|
738 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
739 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
740 | $method = "GET" unless $method eq "HEAD"; |
|
|
741 | $redirect = 1; |
|
|
742 | } elsif ($status == 307) { |
|
|
743 | $redirect = 1; |
|
|
744 | } |
|
|
745 | } |
|
|
746 | |
|
|
747 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
748 | my $may_keep_alive = $_[3]; |
|
|
749 | |
|
|
750 | $state{handle}->destroy if $state{handle}; |
|
|
751 | %state = (); |
|
|
752 | |
|
|
753 | if (defined $_[1]) { |
|
|
754 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
755 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
756 | } |
|
|
757 | |
|
|
758 | # set-cookie processing |
|
|
759 | if ($arg{cookie_jar}) { |
|
|
760 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
|
|
761 | } |
|
|
762 | |
|
|
763 | if ($redirect && exists $hdr{location}) { |
|
|
764 | # we ignore any errors, as it is very common to receive |
|
|
765 | # Content-Length != 0 but no actual body |
|
|
766 | # we also access %hdr, as $_[1] might be an erro |
|
|
767 | http_request ( |
|
|
768 | $method => $hdr{location}, |
|
|
769 | %arg, |
|
|
770 | recurse => $recurse - 1, |
|
|
771 | Redirect => [$_[0], \%hdr], |
|
|
772 | $cb); |
|
|
773 | } else { |
|
|
774 | $cb->($_[0], \%hdr); |
|
|
775 | } |
|
|
776 | }; |
|
|
777 | |
|
|
778 | $ae_error = 597; # body phase |
|
|
779 | |
|
|
780 | my $len = $hdr{"content-length"}; |
|
|
781 | |
|
|
782 | # body handling, many different code paths |
|
|
783 | # - no body expected |
|
|
784 | # - want_body_handle |
|
|
785 | # - te chunked |
|
|
786 | # - 2x length known (with or without on_body) |
|
|
787 | # - 2x length not known (with or without on_body) |
|
|
788 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
789 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
790 | } elsif ( |
|
|
791 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
792 | or $method eq "HEAD" |
|
|
793 | or (defined $len && $len == 0) # == 0, not !, because "0 " is true |
|
|
794 | ) { |
|
|
795 | # no body |
|
|
796 | $finish->("", undef, undef, 1); |
|
|
797 | |
|
|
798 | } elsif (!$redirect && $arg{want_body_handle}) { |
|
|
799 | $_[0]->on_eof (undef); |
|
|
800 | $_[0]->on_error (undef); |
|
|
801 | $_[0]->on_read (undef); |
|
|
802 | |
|
|
803 | $finish->(delete $state{handle}); |
|
|
804 | |
|
|
805 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
806 | my $cl = 0; |
|
|
807 | my $body = undef; |
|
|
808 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
809 | |
|
|
810 | $state{read_chunk} = sub { |
|
|
811 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
812 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
813 | |
|
|
814 | my $len = hex $1; |
|
|
815 | |
|
|
816 | if ($len) { |
|
|
817 | $cl += $len; |
|
|
818 | |
|
|
819 | $_[0]->push_read (chunk => $len, sub { |
|
|
820 | $on_body->($_[1], \%hdr) |
|
|
821 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
822 | |
|
|
823 | $_[0]->push_read (line => sub { |
|
|
824 | length $_[1] |
|
|
825 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
826 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
827 | }); |
|
|
828 | }); |
|
|
829 | } else { |
|
|
830 | $hdr{"content-length"} ||= $cl; |
|
|
831 | |
|
|
832 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
833 | if (length $_[1]) { |
|
|
834 | for ("$_[1]") { |
|
|
835 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
836 | |
|
|
837 | my $hdr = parse_hdr |
|
|
838 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
839 | |
|
|
840 | %hdr = (%hdr, %$hdr); |
|
|
841 | } |
|
|
842 | } |
|
|
843 | |
|
|
844 | $finish->($body, undef, undef, 1); |
|
|
845 | }); |
|
|
846 | } |
|
|
847 | }; |
|
|
848 | |
|
|
849 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
850 | |
|
|
851 | } elsif ($arg{on_body}) { |
|
|
852 | if (defined $len) { |
|
|
853 | $_[0]->on_read (sub { |
|
|
854 | $len -= length $_[0]{rbuf}; |
|
|
855 | |
|
|
856 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
857 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
858 | |
|
|
859 | $len > 0 |
|
|
860 | or $finish->("", undef, undef, 1); |
|
|
861 | }); |
|
|
862 | } else { |
|
|
863 | $_[0]->on_eof (sub { |
|
|
864 | $finish->(""); |
|
|
865 | }); |
|
|
866 | $_[0]->on_read (sub { |
|
|
867 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
868 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
869 | }); |
|
|
870 | } |
|
|
871 | } else { |
|
|
872 | $_[0]->on_eof (undef); |
|
|
873 | |
|
|
874 | if (defined $len) { |
|
|
875 | $_[0]->on_read (sub { |
|
|
876 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
877 | if $len <= length $_[0]{rbuf}; |
|
|
878 | }); |
|
|
879 | } else { |
|
|
880 | $_[0]->on_error (sub { |
|
|
881 | ($! == Errno::EPIPE || !$!) |
|
|
882 | ? $finish->(delete $_[0]{rbuf}) |
|
|
883 | : $finish->(undef, $ae_error => $_[2]); |
|
|
884 | }); |
|
|
885 | $_[0]->on_read (sub { }); |
|
|
886 | } |
|
|
887 | } |
|
|
888 | }; |
|
|
889 | |
|
|
890 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
891 | }; |
620 | |
892 | |
621 | my $connect_cb = sub { |
893 | my $connect_cb = sub { |
622 | $state{fh} = shift |
894 | $state{fh} = shift |
623 | or do { |
895 | or do { |
624 | my $err = "$!"; |
896 | my $err = "$!"; |
… | |
… | |
655 | # $hdr{connection} = "keep-alive"; |
927 | # $hdr{connection} = "keep-alive"; |
656 | # } |
928 | # } |
657 | |
929 | |
658 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
930 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
659 | |
931 | |
660 | # handle actual, non-tunneled, request |
|
|
661 | my $handle_actual_request = sub { |
|
|
662 | $ae_error = 596; # request phase |
|
|
663 | |
|
|
664 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
665 | |
|
|
666 | # send request |
|
|
667 | $state{handle}->push_write ( |
|
|
668 | "$method $rpath HTTP/1.1\015\012" |
|
|
669 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
670 | . "\015\012" |
|
|
671 | . (delete $arg{body}) |
|
|
672 | ); |
|
|
673 | |
|
|
674 | # return if error occured during push_write() |
|
|
675 | return unless %state; |
|
|
676 | |
|
|
677 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
678 | |
|
|
679 | # status line and headers |
|
|
680 | $state{read_response} = sub { |
|
|
681 | for ("$_[1]") { |
|
|
682 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
683 | |
|
|
684 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
685 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
686 | |
|
|
687 | # 100 Continue handling |
|
|
688 | # should not happen as we don't send expect: 100-continue, |
|
|
689 | # but we handle it just in case. |
|
|
690 | # since we send the request body regardless, if we get an error |
|
|
691 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
692 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
693 | if $2 eq 100; |
|
|
694 | |
|
|
695 | push @pseudo, |
|
|
696 | HTTPVersion => $1, |
|
|
697 | Status => $2, |
|
|
698 | Reason => $3, |
|
|
699 | ; |
|
|
700 | |
|
|
701 | my $hdr = parse_hdr |
|
|
702 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
703 | |
|
|
704 | %hdr = (%$hdr, @pseudo); |
|
|
705 | } |
|
|
706 | |
|
|
707 | # redirect handling |
|
|
708 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
709 | # try to support some common forms of broken Location headers. |
|
|
710 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
711 | $hdr{location} =~ s/^\.\/+//; |
|
|
712 | |
|
|
713 | my $url = "$rscheme://$uhost:$uport"; |
|
|
714 | |
|
|
715 | unless ($hdr{location} =~ s/^\///) { |
|
|
716 | $url .= $upath; |
|
|
717 | $url =~ s/\/[^\/]*$//; |
|
|
718 | } |
|
|
719 | |
|
|
720 | $hdr{location} = "$url/$hdr{location}"; |
|
|
721 | } |
|
|
722 | |
|
|
723 | my $redirect; |
|
|
724 | |
|
|
725 | if ($recurse) { |
|
|
726 | my $status = $hdr{Status}; |
|
|
727 | |
|
|
728 | # industry standard is to redirect POST as GET for |
|
|
729 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
730 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
731 | # industry standard seems to be to simply follow. |
|
|
732 | # we go with the industry standard. |
|
|
733 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
734 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
735 | $method = "GET" unless $method eq "HEAD"; |
|
|
736 | $redirect = 1; |
|
|
737 | } elsif ($status == 307) { |
|
|
738 | $redirect = 1; |
|
|
739 | } |
|
|
740 | } |
|
|
741 | |
|
|
742 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
743 | my $may_keep_alive = $_[3]; |
|
|
744 | |
|
|
745 | $state{handle}->destroy if $state{handle}; |
|
|
746 | %state = (); |
|
|
747 | |
|
|
748 | if (defined $_[1]) { |
|
|
749 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
750 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
751 | } |
|
|
752 | |
|
|
753 | # set-cookie processing |
|
|
754 | if ($arg{cookie_jar}) { |
|
|
755 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost; |
|
|
756 | } |
|
|
757 | |
|
|
758 | if ($redirect && exists $hdr{location}) { |
|
|
759 | # we ignore any errors, as it is very common to receive |
|
|
760 | # Content-Length != 0 but no actual body |
|
|
761 | # we also access %hdr, as $_[1] might be an erro |
|
|
762 | http_request ( |
|
|
763 | $method => $hdr{location}, |
|
|
764 | %arg, |
|
|
765 | recurse => $recurse - 1, |
|
|
766 | Redirect => [$_[0], \%hdr], |
|
|
767 | $cb); |
|
|
768 | } else { |
|
|
769 | $cb->($_[0], \%hdr); |
|
|
770 | } |
|
|
771 | }; |
|
|
772 | |
|
|
773 | $ae_error = 597; # body phase |
|
|
774 | |
|
|
775 | my $len = $hdr{"content-length"}; |
|
|
776 | |
|
|
777 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
778 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
779 | } elsif ( |
|
|
780 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
781 | or $method eq "HEAD" |
|
|
782 | or (defined $len && !$len) |
|
|
783 | ) { |
|
|
784 | # no body |
|
|
785 | $finish->("", undef, undef, 1); |
|
|
786 | } else { |
|
|
787 | # body handling, many different code paths |
|
|
788 | # - no body expected |
|
|
789 | # - want_body_handle |
|
|
790 | # - te chunked |
|
|
791 | # - 2x length known (with or without on_body) |
|
|
792 | # - 2x length not known (with or without on_body) |
|
|
793 | if (!$redirect && $arg{want_body_handle}) { |
|
|
794 | $_[0]->on_eof (undef); |
|
|
795 | $_[0]->on_error (undef); |
|
|
796 | $_[0]->on_read (undef); |
|
|
797 | |
|
|
798 | $finish->(delete $state{handle}); |
|
|
799 | |
|
|
800 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
801 | my $cl = 0; |
|
|
802 | my $body = undef; |
|
|
803 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
804 | |
|
|
805 | my $read_chunk; $read_chunk = sub { |
|
|
806 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
807 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
808 | |
|
|
809 | my $len = hex $1; |
|
|
810 | |
|
|
811 | if ($len) { |
|
|
812 | $cl += $len; |
|
|
813 | |
|
|
814 | $_[0]->push_read (chunk => $len, sub { |
|
|
815 | $on_body->($_[1], \%hdr) |
|
|
816 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
817 | |
|
|
818 | $_[0]->push_read (line => sub { |
|
|
819 | length $_[1] |
|
|
820 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
821 | $_[0]->push_read (line => $read_chunk); |
|
|
822 | }); |
|
|
823 | }); |
|
|
824 | } else { |
|
|
825 | $hdr{"content-length"} ||= $cl; |
|
|
826 | |
|
|
827 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
828 | if (length $_[1]) { |
|
|
829 | for ("$_[1]") { |
|
|
830 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
831 | |
|
|
832 | my $hdr = parse_hdr |
|
|
833 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
834 | |
|
|
835 | %hdr = (%hdr, %$hdr); |
|
|
836 | } |
|
|
837 | } |
|
|
838 | |
|
|
839 | $finish->($body, undef, undef, 1); |
|
|
840 | }); |
|
|
841 | } |
|
|
842 | }; |
|
|
843 | |
|
|
844 | $_[0]->push_read (line => $read_chunk); |
|
|
845 | |
|
|
846 | } elsif ($arg{on_body}) { |
|
|
847 | if ($len) { |
|
|
848 | $_[0]->on_read (sub { |
|
|
849 | $len -= length $_[0]{rbuf}; |
|
|
850 | |
|
|
851 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
852 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
853 | |
|
|
854 | $len > 0 |
|
|
855 | or $finish->("", undef, undef, 1); |
|
|
856 | }); |
|
|
857 | } else { |
|
|
858 | $_[0]->on_eof (sub { |
|
|
859 | $finish->(""); |
|
|
860 | }); |
|
|
861 | $_[0]->on_read (sub { |
|
|
862 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
863 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
864 | }); |
|
|
865 | } |
|
|
866 | } else { |
|
|
867 | $_[0]->on_eof (undef); |
|
|
868 | |
|
|
869 | if ($len) { |
|
|
870 | $_[0]->on_read (sub { |
|
|
871 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
872 | if $len <= length $_[0]{rbuf}; |
|
|
873 | }); |
|
|
874 | } else { |
|
|
875 | $_[0]->on_error (sub { |
|
|
876 | ($! == Errno::EPIPE || !$!) |
|
|
877 | ? $finish->(delete $_[0]{rbuf}) |
|
|
878 | : $finish->(undef, $ae_error => $_[2]); |
|
|
879 | }); |
|
|
880 | $_[0]->on_read (sub { }); |
|
|
881 | } |
|
|
882 | } |
|
|
883 | } |
|
|
884 | }; |
|
|
885 | |
|
|
886 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
887 | }; |
|
|
888 | |
|
|
889 | # now handle proxy-CONNECT method |
932 | # now handle proxy-CONNECT method |
890 | if ($proxy && $uscheme eq "https") { |
933 | if ($proxy && $uscheme eq "https") { |
891 | # oh dear, we have to wrap it into a connect request |
934 | # oh dear, we have to wrap it into a connect request |
892 | |
935 | |
893 | # maybe re-use $uauthority with patched port? |
936 | # maybe re-use $uauthority with patched port? |
… | |
… | |
896 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
939 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
897 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
940 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
898 | |
941 | |
899 | if ($2 == 200) { |
942 | if ($2 == 200) { |
900 | $rpath = $upath; |
943 | $rpath = $upath; |
901 | &$handle_actual_request; |
944 | $handle_actual_request->(); |
902 | } else { |
945 | } else { |
903 | %state = (); |
946 | %state = (); |
904 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
947 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
905 | } |
948 | } |
906 | }); |
949 | }); |
907 | } else { |
950 | } else { |
908 | &$handle_actual_request; |
951 | $handle_actual_request->(); |
909 | } |
952 | } |
910 | }; |
953 | }; |
911 | |
954 | |
912 | my $tcp_connect = $arg{tcp_connect} |
955 | my $tcp_connect = $arg{tcp_connect} |
913 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
956 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
914 | |
957 | |
915 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
958 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
916 | |
|
|
917 | }; |
959 | }; |
918 | |
960 | |
919 | defined wantarray && AnyEvent::Util::guard { %state = () } |
961 | defined wantarray && AnyEvent::Util::guard { %state = () } |
920 | } |
962 | } |
921 | |
963 | |
… | |
… | |
956 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
998 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
957 | otherwise. |
999 | otherwise. |
958 | |
1000 | |
959 | To clear an already-set proxy, use C<undef>. |
1001 | To clear an already-set proxy, use C<undef>. |
960 | |
1002 | |
|
|
1003 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1004 | |
|
|
1005 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1006 | C<$session_end> is given and true, then additionally remove all session |
|
|
1007 | cookies. |
|
|
1008 | |
|
|
1009 | You should call this function (with a true C<$session_end>) before you |
|
|
1010 | save cookies to disk, and you should call this function after loading them |
|
|
1011 | again. If you have a long-running program you can additonally call this |
|
|
1012 | function from time to time. |
|
|
1013 | |
|
|
1014 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1015 | module. It's format is subject to change, but currently it is like this: |
|
|
1016 | |
|
|
1017 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1018 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1019 | hash-references. The key for these inner hash references is the |
|
|
1020 | server path for which this cookie is meant, and the values are again |
|
|
1021 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1022 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1023 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1024 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1025 | expiry timestamp. |
|
|
1026 | |
|
|
1027 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1028 | chance of understanding the above paragraph: |
|
|
1029 | |
|
|
1030 | { |
|
|
1031 | version => 1, |
|
|
1032 | "10.0.0.1" => { |
|
|
1033 | "/" => { |
|
|
1034 | "mythweb_id" => { |
|
|
1035 | _expires => 1293917923, |
|
|
1036 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1037 | }, |
|
|
1038 | }, |
|
|
1039 | }, |
|
|
1040 | } |
|
|
1041 | |
961 | =item $date = AnyEvent::HTTP::format_date $timestamp |
1042 | =item $date = AnyEvent::HTTP::format_date $timestamp |
962 | |
1043 | |
963 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
1044 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
964 | Date (RFC 2616). |
1045 | Date (RFC 2616). |
965 | |
1046 | |
966 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
1047 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
967 | |
1048 | |
968 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and |
1049 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
969 | returns the corresponding POSIX timestamp, or C<undef> if the date cannot |
1050 | bunch of minor variations of those, and returns the corresponding POSIX |
970 | be parsed. |
1051 | timestamp, or C<undef> if the date cannot be parsed. |
971 | |
1052 | |
972 | =item $AnyEvent::HTTP::MAX_RECURSE |
1053 | =item $AnyEvent::HTTP::MAX_RECURSE |
973 | |
1054 | |
974 | The default value for the C<recurse> request parameter (default: C<10>). |
1055 | The default value for the C<recurse> request parameter (default: C<10>). |
975 | |
1056 | |
… | |
… | |
1014 | sub parse_date($) { |
1095 | sub parse_date($) { |
1015 | my ($date) = @_; |
1096 | my ($date) = @_; |
1016 | |
1097 | |
1017 | my ($d, $m, $y, $H, $M, $S); |
1098 | my ($d, $m, $y, $H, $M, $S); |
1018 | |
1099 | |
1019 | if ($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$/) { |
1100 | if ($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$/) { |
1020 | # RFC 822/1123, required by RFC 2616 (with " ") |
1101 | # RFC 822/1123, required by RFC 2616 (with " ") |
1021 | # cookie dates (with "-") |
1102 | # cookie dates (with "-") |
1022 | |
1103 | |
1023 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1104 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1024 | |
1105 | |
1025 | } elsif ($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$/) { |
1106 | } elsif ($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$/) { |
1026 | # RFC 850 |
1107 | # RFC 850 |
1027 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1108 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1028 | |
1109 | |
1029 | } elsif ($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])$/) { |
1110 | } elsif ($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])$/) { |
1030 | # ISO C's asctime |
1111 | # ISO C's asctime |
1031 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1112 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1032 | } |
1113 | } |
1033 | # other formats fail in the loop below |
1114 | # other formats fail in the loop below |
1034 | |
1115 | |