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 1.71 by root, Fri Dec 31 20:50:58 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
416# extract cookies from jar
369sub cookie_jar_extract($$$$) { 417sub cookie_jar_extract($$$$) {
370 my ($jar, $uscheme, $uhost, $upath) = @_; 418 my ($jar, $uscheme, $uhost, $upath) = @_;
419
420 $uhost = lc $uhost;
371 421
372 %$jar = () if $jar->{version} != 1; 422 %$jar = () if $jar->{version} != 1;
373 423
374 my @cookies; 424 my @cookies;
375 425
… …
388 next unless $cpath eq substr $upath, 0, length $cpath; 438 next unless $cpath eq substr $upath, 0, length $cpath;
389 439
390 while (my ($cookie, $kv) = each %$cookies) { 440 while (my ($cookie, $kv) = each %$cookies) {
391 next if $uscheme ne "https" && exists $kv->{secure}; 441 next if $uscheme ne "https" && exists $kv->{secure};
392 442
393 if (exists $kv->{expires}) { 443 if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
394 if (AE::now > parse_date ($kv->{expires})) {
395 delete $cookies->{$cookie}; 444 delete $cookies->{$cookie};
396 next; 445 next;
397 }
398 } 446 }
399 447
400 my $value = $kv->{value}; 448 my $value = $kv->{value};
401 449
402 if ($value =~ /[=;,[:space:]]/) { 450 if ($value =~ /[=;,[:space:]]/) {
… …
410 } 458 }
411 459
412 \@cookies 460 \@cookies
413} 461}
414 462
463# parse set_cookie header into jar
464sub cookie_jar_set_cookie($$$$) {
465 my ($jar, $set_cookie, $uhost, $date) = @_;
466
467 my $anow = int AE::now;
468 my $snow; # server-now
469
470 for ($set_cookie) {
471 # parse NAME=VALUE
472 my @kv;
473
474 # expires is not http-compliant in the original cookie-spec,
475 # we support the official date format and some extensions
476 while (
477 m{
478 \G\s*
479 (?:
480 expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
481 | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )?
482 )
483 }gcxsi
484 ) {
485 my $name = $2;
486 my $value = $4;
487
488 if (defined $1) {
489 # expires
490 $name = "expires";
491 $value = $1;
492 } elsif (defined $3) {
493 # quoted
494 $value = $3;
495 $value =~ s/\\(.)/$1/gs;
496 }
497
498 push @kv, lc $name, $value;
499
500 last unless /\G\s*;/gc;
501 }
502
503 last unless @kv;
504
505 my $name = shift @kv;
506 my %kv = (value => shift @kv, @kv);
507
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 }
516
517 my $cdom;
518 my $cpath = (delete $kv{path}) || "/";
519
520 if (exists $kv{domain}) {
521 $cdom = delete $kv{domain};
522
523 $cdom =~ s/^\.?/./; # make sure it starts with a "."
524
525 next if $cdom =~ /\.$/;
526
527 # this is not rfc-like and not netscape-like. go figure.
528 my $ndots = $cdom =~ y/.//;
529 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
530 } else {
531 $cdom = $uhost;
532 }
533
534 # store it
535 $jar->{version} = 1;
536 $jar->{lc $cdom}{$cpath}{$name} = \%kv;
537
538 redo if /\G\s*,/gc;
539 }
540}
541
415# continue to parse $_ for headers and place them into the arg 542# continue to parse $_ for headers and place them into the arg
416sub parse_hdr() { 543sub parse_hdr() {
417 my %hdr; 544 my %hdr;
418 545
419 # things seen, not parsed: 546 # things seen, not parsed:
… …
531 _get_slot $uhost, sub { 658 _get_slot $uhost, sub {
532 $state{slot_guard} = shift; 659 $state{slot_guard} = shift;
533 660
534 return unless $state{connect_guard}; 661 return unless $state{connect_guard};
535 662
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
536 my $connect_cb = sub { 893 my $connect_cb = sub {
537 $state{fh} = shift 894 $state{fh} = shift
538 or do { 895 or do {
539 my $err = "$!"; 896 my $err = "$!";
540 %state = (); 897 %state = ();
541 return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); 898 return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
542 }; 899 };
543
544 pop; # free memory, save a tree
545 900
546 return unless delete $state{connect_guard}; 901 return unless delete $state{connect_guard};
547 902
548 # get handle 903 # get handle
549 $state{handle} = new AnyEvent::Handle 904 $state{handle} = new AnyEvent::Handle
… …
552 tls_ctx => $arg{tls_ctx}, 907 tls_ctx => $arg{tls_ctx},
553 # these need to be reconfigured on keepalive handles 908 # these need to be reconfigured on keepalive handles
554 timeout => $timeout, 909 timeout => $timeout,
555 on_error => sub { 910 on_error => sub {
556 %state = (); 911 %state = ();
557 $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); 912 $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
558 }, 913 },
559 on_eof => sub { 914 on_eof => sub {
560 %state = (); 915 %state = ();
561 $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); 916 $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
562 }, 917 },
563 ; 918 ;
564 919
565 # limit the number of persistent connections 920 # limit the number of persistent connections
566 # keepalive not yet supported 921 # keepalive not yet supported
… …
572# $hdr{connection} = "keep-alive"; 927# $hdr{connection} = "keep-alive";
573# } 928# }
574 929
575 $state{handle}->starttls ("connect") if $rscheme eq "https"; 930 $state{handle}->starttls ("connect") if $rscheme eq "https";
576 931
577 # handle actual, non-tunneled, request
578 my $handle_actual_request = sub {
579 $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
580
581 # send request
582 $state{handle}->push_write (
583 "$method $rpath HTTP/1.1\015\012"
584 . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
585 . "\015\012"
586 . (delete $arg{body})
587 );
588
589 # return if error occured during push_write()
590 return unless %state;
591
592 %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
593
594 # status line and headers
595 $state{read_response} = sub {
596 for ("$_[1]") {
597 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
598
599 /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
600 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
601
602 # 100 Continue handling
603 # should not happen as we don't send expect: 100-continue,
604 # but we handle it just in case.
605 # since we send the request body regardless, if we get an error
606 # we are out of-sync, which we currently do NOT handle correctly.
607 return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
608 if $2 eq 100;
609
610 push @pseudo,
611 HTTPVersion => $1,
612 Status => $2,
613 Reason => $3,
614 ;
615
616 my $hdr = parse_hdr
617 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
618
619 %hdr = (%$hdr, @pseudo);
620 }
621
622 # redirect handling
623 # microsoft and other shitheads don't give a shit for following standards,
624 # try to support some common forms of broken Location headers.
625 if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
626 $hdr{location} =~ s/^\.\/+//;
627
628 my $url = "$rscheme://$uhost:$uport";
629
630 unless ($hdr{location} =~ s/^\///) {
631 $url .= $upath;
632 $url =~ s/\/[^\/]*$//;
633 }
634
635 $hdr{location} = "$url/$hdr{location}";
636 }
637
638 my $redirect;
639
640 if ($recurse) {
641 my $status = $hdr{Status};
642
643 # industry standard is to redirect POST as GET for
644 # 301, 302 and 303, in contrast to http/1.0 and 1.1.
645 # also, the UA should ask the user for 301 and 307 and POST,
646 # industry standard seems to be to simply follow.
647 # we go with the industry standard.
648 if ($status == 301 or $status == 302 or $status == 303) {
649 # HTTP/1.1 is unclear on how to mutate the method
650 $method = "GET" unless $method eq "HEAD";
651 $redirect = 1;
652 } elsif ($status == 307) {
653 $redirect = 1;
654 }
655 }
656
657 my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
658 my $keepalive = pop;
659
660 $state{handle}->destroy if $state{handle};
661 %state = ();
662
663 if (defined $_[1]) {
664 $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
665 $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
666 }
667
668 # set-cookie processing
669 if ($arg{cookie_jar}) {
670 for ($hdr{"set-cookie"}) {
671 # parse NAME=VALUE
672 my @kv;
673
674 while (
675 m{
676 \G\s*
677 (?:
678 expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+)
679 | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )
680 )
681 }gcxsi
682 ) {
683 my $name = $2;
684 my $value = $4;
685
686 unless (defined $name) {
687 # expires
688 $name = "expires";
689 $value = $1;
690 } elsif (!defined $value) {
691 # quoted
692 $value = $3;
693 $value =~ s/\\(.)/$1/gs;
694 }
695
696 push @kv, lc $name, $value;
697
698 last unless /\G\s*;/gc;
699 }
700
701 last unless @kv;
702
703 my $name = shift @kv;
704 my %kv = (value => shift @kv, @kv);
705
706 $kv{expires} ||= format_date (AE::now + $kv{"max-age"})
707 if exists $kv{"max-age"};
708
709 my $cdom;
710 my $cpath = (delete $kv{path}) || "/";
711
712 if (exists $kv{domain}) {
713 $cdom = delete $kv{domain};
714
715 $cdom =~ s/^\.?/./; # make sure it starts with a "."
716
717 next if $cdom =~ /\.$/;
718
719 # this is not rfc-like and not netscape-like. go figure.
720 my $ndots = $cdom =~ y/.//;
721 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
722 } else {
723 $cdom = $uhost;
724 }
725
726 # store it
727 $arg{cookie_jar}{version} = 1;
728 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
729
730 redo if /\G\s*,/gc;
731 }
732 }
733
734 if ($redirect && exists $hdr{location}) {
735 # we ignore any errors, as it is very common to receive
736 # Content-Length != 0 but no actual body
737 # we also access %hdr, as $_[1] might be an erro
738 http_request (
739 $method => $hdr{location},
740 %arg,
741 recurse => $recurse - 1,
742 Redirect => [$_[0], \%hdr],
743 $cb);
744 } else {
745 $cb->($_[0], \%hdr);
746 }
747 };
748
749 my $len = $hdr{"content-length"};
750
751 if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
752 $finish->(undef, 598 => "Request cancelled by on_header");
753 } elsif (
754 $hdr{Status} =~ /^(?:1..|204|205|304)$/
755 or $method eq "HEAD"
756 or (defined $len && !$len)
757 ) {
758 # no body
759 $finish->("", undef, undef, 1);
760 } else {
761 # body handling, many different code paths
762 # - no body expected
763 # - want_body_handle
764 # - te chunked
765 # - 2x length known (with or without on_body)
766 # - 2x length not known (with or without on_body)
767 if (!$redirect && $arg{want_body_handle}) {
768 $_[0]->on_eof (undef);
769 $_[0]->on_error (undef);
770 $_[0]->on_read (undef);
771
772 $finish->(delete $state{handle});
773
774 } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
775 my $cl = 0;
776 my $body = undef;
777 my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
778
779 $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
780
781 my $read_chunk; $read_chunk = sub {
782 $_[1] =~ /^([0-9a-fA-F]+)/
783 or $finish->(undef, 599 => "Garbled chunked transfer encoding");
784
785 my $len = hex $1;
786
787 if ($len) {
788 $cl += $len;
789
790 $_[0]->push_read (chunk => $len, sub {
791 $on_body->($_[1], \%hdr)
792 or return $finish->(undef, 598 => "Request cancelled by on_body");
793
794 $_[0]->push_read (line => sub {
795 length $_[1]
796 and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
797 $_[0]->push_read (line => $read_chunk);
798 });
799 });
800 } else {
801 $hdr{"content-length"} ||= $cl;
802
803 $_[0]->push_read (line => $qr_nlnl, sub {
804 if (length $_[1]) {
805 for ("$_[1]") {
806 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
807
808 my $hdr = parse_hdr
809 or return $finish->(undef, 599 => "Garbled response trailers");
810
811 %hdr = (%hdr, %$hdr);
812 }
813 }
814
815 $finish->($body, undef, undef, 1);
816 });
817 }
818 };
819
820 $_[0]->push_read (line => $read_chunk);
821
822 } elsif ($arg{on_body}) {
823 $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
824
825 if ($len) {
826 $_[0]->on_read (sub {
827 $len -= length $_[0]{rbuf};
828
829 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
830 or return $finish->(undef, 598 => "Request cancelled by on_body");
831
832 $len > 0
833 or $finish->("", undef, undef, 1);
834 });
835 } else {
836 $_[0]->on_eof (sub {
837 $finish->("");
838 });
839 $_[0]->on_read (sub {
840 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
841 or $finish->(undef, 598 => "Request cancelled by on_body");
842 });
843 }
844 } else {
845 $_[0]->on_eof (undef);
846
847 if ($len) {
848 $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
849 $_[0]->on_read (sub {
850 $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
851 if $len <= length $_[0]{rbuf};
852 });
853 } else {
854 $_[0]->on_error (sub {
855 ($! == Errno::EPIPE || !$!)
856 ? $finish->(delete $_[0]{rbuf})
857 : $finish->(undef, 599 => $_[2]);
858 });
859 $_[0]->on_read (sub { });
860 }
861 }
862 }
863 };
864
865 $state{handle}->push_read (line => $qr_nlnl, $state{read_response});
866 };
867
868 # now handle proxy-CONNECT method 932 # now handle proxy-CONNECT method
869 if ($proxy && $uscheme eq "https") { 933 if ($proxy && $uscheme eq "https") {
870 # oh dear, we have to wrap it into a connect request 934 # oh dear, we have to wrap it into a connect request
871 935
872 # maybe re-use $uauthority with patched port? 936 # maybe re-use $uauthority with patched port?
… …
875 $_[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
876 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])" }));
877 941
878 if ($2 == 200) { 942 if ($2 == 200) {
879 $rpath = $upath; 943 $rpath = $upath;
880 &$handle_actual_request; 944 $handle_actual_request->();
881 } else { 945 } else {
882 %state = (); 946 %state = ();
883 $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); 947 $cb->(undef, { @pseudo, Status => $2, Reason => $3 });
884 } 948 }
885 }); 949 });
886 } else { 950 } else {
887 &$handle_actual_request; 951 $handle_actual_request->();
888 } 952 }
889 }; 953 };
890 954
891 my $tcp_connect = $arg{tcp_connect} 955 my $tcp_connect = $arg{tcp_connect}
892 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; 956 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
893 957
894 $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 });
895
896 }; 959 };
897 960
898 defined wantarray && AnyEvent::Util::guard { %state = () } 961 defined wantarray && AnyEvent::Util::guard { %state = () }
899} 962}
900 963
… …
935string of the form C<http://host:port> (optionally C<https:...>), croaks 998string of the form C<http://host:port> (optionally C<https:...>), croaks
936otherwise. 999otherwise.
937 1000
938To clear an already-set proxy, use C<undef>. 1001To clear an already-set proxy, use C<undef>.
939 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
940=item $date = AnyEvent::HTTP::format_date $timestamp 1042=item $date = AnyEvent::HTTP::format_date $timestamp
941 1043
942Takes 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
943Date (RFC 2616). 1045Date (RFC 2616).
944 1046
945=item $timestamp = AnyEvent::HTTP::parse_date $date 1047=item $timestamp = AnyEvent::HTTP::parse_date $date
946 1048
947Takes 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
948returns the corresponding POSIX timestamp, or C<undef> if the date cannot 1050bunch of minor variations of those, and returns the corresponding POSIX
949be parsed. 1051timestamp, or C<undef> if the date cannot be parsed.
950 1052
951=item $AnyEvent::HTTP::MAX_RECURSE 1053=item $AnyEvent::HTTP::MAX_RECURSE
952 1054
953The default value for the C<recurse> request parameter (default: C<10>). 1055The default value for the C<recurse> request parameter (default: C<10>).
954 1056
… …
993sub parse_date($) { 1095sub parse_date($) {
994 my ($date) = @_; 1096 my ($date) = @_;
995 1097
996 my ($d, $m, $y, $H, $M, $S); 1098 my ($d, $m, $y, $H, $M, $S);
997 1099
998 if ($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$/) {
999 # RFC 822/1123, required by RFC 2616 (with " ") 1101 # RFC 822/1123, required by RFC 2616 (with " ")
1000 # cookie dates (with "-") 1102 # cookie dates (with "-")
1001 1103
1002 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); 1104 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
1003 1105
1004 } elsif ($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$/) {
1005 # RFC 850 1107 # RFC 850
1006 ($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, $6);
1007 1109
1008 } elsif ($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])$/) {
1009 # ISO C's asctime 1111 # ISO C's asctime
1010 ($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);
1011 } 1113 }
1012 # other formats fail in the loop below 1114 # other formats fail in the loop below
1013 1115

Diff Legend

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