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 1.85 by root, Sun Jan 2 05:31:56 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 ();
… …
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($$$$) { 417sub cookie_jar_extract($$$$) {
371 my ($jar, $uscheme, $uhost, $upath) = @_; 418 my ($jar, $uscheme, $uhost, $upath) = @_;
419
420 $uhost = lc $uhost;
372 421
373 %$jar = () if $jar->{version} != 1; 422 %$jar = () if $jar->{version} != 1;
374 423
375 my @cookies; 424 my @cookies;
376 425
… …
389 next unless $cpath eq substr $upath, 0, length $cpath; 438 next unless $cpath eq substr $upath, 0, length $cpath;
390 439
391 while (my ($cookie, $kv) = each %$cookies) { 440 while (my ($cookie, $kv) = each %$cookies) {
392 next if $uscheme ne "https" && exists $kv->{secure}; 441 next if $uscheme ne "https" && exists $kv->{secure};
393 442
394 if (exists $kv->{expires}) { 443 if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
395 if (AE::now > parse_date ($kv->{expires})) {
396 delete $cookies->{$cookie}; 444 delete $cookies->{$cookie};
397 next; 445 next;
398 }
399 } 446 }
400 447
401 my $value = $kv->{value}; 448 my $value = $kv->{value};
402 449
403 if ($value =~ /[=;,[:space:]]/) { 450 if ($value =~ /[=;,[:space:]]/) {
… …
412 459
413 \@cookies 460 \@cookies
414} 461}
415 462
416# parse set_cookie header into jar 463# parse set_cookie header into jar
417sub cookie_jar_set_cookie($$$) { 464sub cookie_jar_set_cookie($$$$) {
418 my ($jar, $set_cookie, $uhost) = @_; 465 my ($jar, $set_cookie, $uhost, $date) = @_;
466
467 my $anow = int AE::now;
468 my $snow; # server-now
419 469
420 for ($set_cookie) { 470 for ($set_cookie) {
421 # parse NAME=VALUE 471 # parse NAME=VALUE
422 my @kv; 472 my @kv;
423 473
474 # expires is not http-compliant in the original cookie-spec,
475 # we support the official date format and some extensions
424 while ( 476 while (
425 m{ 477 m{
426 \G\s* 478 \G\s*
427 (?: 479 (?:
428 expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) 480 expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
429 | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) 481 | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )?
430 ) 482 )
431 }gcxsi 483 }gcxsi
432 ) { 484 ) {
433 my $name = $2; 485 my $name = $2;
434 my $value = $4; 486 my $value = $4;
435 487
436 unless (defined $name) { 488 if (defined $1) {
437 # expires 489 # expires
438 $name = "expires"; 490 $name = "expires";
439 $value = $1; 491 $value = $1;
440 } elsif (!defined $value) { 492 } elsif (defined $3) {
441 # quoted 493 # quoted
442 $value = $3; 494 $value = $3;
443 $value =~ s/\\(.)/$1/gs; 495 $value =~ s/\\(.)/$1/gs;
444 } 496 }
445 497
… …
451 last unless @kv; 503 last unless @kv;
452 504
453 my $name = shift @kv; 505 my $name = shift @kv;
454 my %kv = (value => shift @kv, @kv); 506 my %kv = (value => shift @kv, @kv);
455 507
456 $kv{expires} ||= format_date (AE::now + $kv{"max-age"})
457 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 }
458 516
459 my $cdom; 517 my $cdom;
460 my $cpath = (delete $kv{path}) || "/"; 518 my $cpath = (delete $kv{path}) || "/";
461 519
462 if (exists $kv{domain}) { 520 if (exists $kv{domain}) {
… …
473 $cdom = $uhost; 531 $cdom = $uhost;
474 } 532 }
475 533
476 # store it 534 # store it
477 $jar->{version} = 1; 535 $jar->{version} = 1;
478 $jar->{$cdom}{$cpath}{$name} = \%kv; 536 $jar->{lc $cdom}{$cpath}{$name} = \%kv;
479 537
480 redo if /\G\s*,/gc; 538 redo if /\G\s*,/gc;
481 } 539 }
482} 540}
483 541
… …
600 _get_slot $uhost, sub { 658 _get_slot $uhost, sub {
601 $state{slot_guard} = shift; 659 $state{slot_guard} = shift;
602 660
603 return unless $state{connect_guard}; 661 return unless $state{connect_guard};
604 662
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 };
892
605 my $connect_cb = sub { 893 my $connect_cb = sub {
606 $state{fh} = shift 894 $state{fh} = shift
607 or do { 895 or do {
608 my $err = "$!"; 896 my $err = "$!";
609 %state = (); 897 %state = ();
610 return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); 898 return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
611 }; 899 };
612
613 pop; # free memory, save a tree
614 900
615 return unless delete $state{connect_guard}; 901 return unless delete $state{connect_guard};
616 902
617 # get handle 903 # get handle
618 $state{handle} = new AnyEvent::Handle 904 $state{handle} = new AnyEvent::Handle
… …
621 tls_ctx => $arg{tls_ctx}, 907 tls_ctx => $arg{tls_ctx},
622 # these need to be reconfigured on keepalive handles 908 # these need to be reconfigured on keepalive handles
623 timeout => $timeout, 909 timeout => $timeout,
624 on_error => sub { 910 on_error => sub {
625 %state = (); 911 %state = ();
626 $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); 912 $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
627 }, 913 },
628 on_eof => sub { 914 on_eof => sub {
629 %state = (); 915 %state = ();
630 $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); 916 $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
631 }, 917 },
632 ; 918 ;
633 919
634 # limit the number of persistent connections 920 # limit the number of persistent connections
635 # keepalive not yet supported 921 # keepalive not yet supported
… …
641# $hdr{connection} = "keep-alive"; 927# $hdr{connection} = "keep-alive";
642# } 928# }
643 929
644 $state{handle}->starttls ("connect") if $rscheme eq "https"; 930 $state{handle}->starttls ("connect") if $rscheme eq "https";
645 931
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, $state{read_response});
874 };
875
876 # now handle proxy-CONNECT method 932 # now handle proxy-CONNECT method
877 if ($proxy && $uscheme eq "https") { 933 if ($proxy && $uscheme eq "https") {
878 # oh dear, we have to wrap it into a connect request 934 # oh dear, we have to wrap it into a connect request
879 935
880 # maybe re-use $uauthority with patched port? 936 # maybe re-use $uauthority with patched port?
… …
883 $_[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
884 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])" }));
885 941
886 if ($2 == 200) { 942 if ($2 == 200) {
887 $rpath = $upath; 943 $rpath = $upath;
888 &$handle_actual_request; 944 $handle_actual_request->();
889 } else { 945 } else {
890 %state = (); 946 %state = ();
891 $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); 947 $cb->(undef, { @pseudo, Status => $2, Reason => $3 });
892 } 948 }
893 }); 949 });
894 } else { 950 } else {
895 &$handle_actual_request; 951 $handle_actual_request->();
896 } 952 }
897 }; 953 };
898 954
899 my $tcp_connect = $arg{tcp_connect} 955 my $tcp_connect = $arg{tcp_connect}
900 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; 956 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
901 957
902 $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 });
903
904 }; 959 };
905 960
906 defined wantarray && AnyEvent::Util::guard { %state = () } 961 defined wantarray && AnyEvent::Util::guard { %state = () }
907} 962}
908 963
… …
943string of the form C<http://host:port> (optionally C<https:...>), croaks 998string of the form C<http://host:port> (optionally C<https:...>), croaks
944otherwise. 999otherwise.
945 1000
946To clear an already-set proxy, use C<undef>. 1001To clear an already-set proxy, use C<undef>.
947 1002
1003=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
1004
1005Remove all cookies from the cookie jar that have been expired. If
1006C<$session_end> is given and true, then additionally remove all session
1007cookies.
1008
1009You should call this function (with a true C<$session_end>) before you
1010save cookies to disk, and you should call this function after loading them
1011again. If you have a long-running program you can additonally call this
1012function from time to time.
1013
1014A cookie jar is initially an empty hash-reference that is managed by this
1015module. It's format is subject to change, but currently it is like this:
1016
1017The key C<version> has to contain C<1>, otherwise the hash gets
1018emptied. All other keys are hostnames or IP addresses pointing to
1019hash-references. The key for these inner hash references is the
1020server path for which this cookie is meant, and the values are again
1021hash-references. The keys of those hash-references is the cookie name, and
1022the value, you guessed it, is another hash-reference, this time with the
1023key-value pairs from the cookie, except for C<expires> and C<max-age>,
1024which have been replaced by a C<_expires> key that contains the cookie
1025expiry timestamp.
1026
1027Here is an example of a cookie jar with a single cookie, so you have a
1028chance 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
948=item $date = AnyEvent::HTTP::format_date $timestamp 1042=item $date = AnyEvent::HTTP::format_date $timestamp
949 1043
950Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP 1044Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
951Date (RFC 2616). 1045Date (RFC 2616).
952 1046
953=item $timestamp = AnyEvent::HTTP::parse_date $date 1047=item $timestamp = AnyEvent::HTTP::parse_date $date
954 1048
955Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and 1049Takes 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 1050bunch of minor variations of those, and returns the corresponding POSIX
957be parsed. 1051timestamp, or C<undef> if the date cannot be parsed.
958 1052
959=item $AnyEvent::HTTP::MAX_RECURSE 1053=item $AnyEvent::HTTP::MAX_RECURSE
960 1054
961The default value for the C<recurse> request parameter (default: C<10>). 1055The default value for the C<recurse> request parameter (default: C<10>).
962 1056
… …
1001sub parse_date($) { 1095sub parse_date($) {
1002 my ($date) = @_; 1096 my ($date) = @_;
1003 1097
1004 my ($d, $m, $y, $H, $M, $S); 1098 my ($d, $m, $y, $H, $M, $S);
1005 1099
1006 if ($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$/) { 1100 if ($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$/) {
1007 # RFC 822/1123, required by RFC 2616 (with " ") 1101 # RFC 822/1123, required by RFC 2616 (with " ")
1008 # cookie dates (with "-") 1102 # cookie dates (with "-")
1009 1103
1010 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); 1104 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
1011 1105
1012 } elsif ($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$/) { 1106 } elsif ($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$/) {
1013 # RFC 850 1107 # RFC 850
1014 ($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, $6);
1015 1109
1016 } elsif ($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])$/) { 1110 } elsif ($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])$/) {
1017 # ISO C's asctime 1111 # ISO C's asctime
1018 ($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);
1019 } 1113 }
1020 # other formats fail in the loop below 1114 # other formats fail in the loop below
1021 1115

Diff Legend

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