… | |
… | |
122 | |
122 | |
123 | If the server sends a header multiple times, then their contents will be |
123 | If the server sends a header multiple times, then their contents will be |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
125 | |
125 | |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be |
128 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
128 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
129 | message. |
129 | message. Currently the following status codes are used: |
|
|
130 | |
|
|
131 | =over 4 |
|
|
132 | |
|
|
133 | =item 595 - errors during connection etsbalishment, proxy handshake. |
|
|
134 | |
|
|
135 | =item 596 - errors during TLS negotiation, request sending and header processing. |
|
|
136 | |
|
|
137 | =item 597 - errors during body receiving or processing. |
|
|
138 | |
|
|
139 | =item 598 - user aborted request via C<on_header> or C<on_body>. |
|
|
140 | |
|
|
141 | =item 599 - other, usually nonretryable, errors (garbled URL etc.). |
|
|
142 | |
|
|
143 | =back |
130 | |
144 | |
131 | A typical callback might look like this: |
145 | A typical callback might look like this: |
132 | |
146 | |
133 | sub { |
147 | sub { |
134 | my ($body, $hdr) = @_; |
148 | my ($body, $hdr) = @_; |
… | |
… | |
182 | =item cookie_jar => $hash_ref |
196 | =item cookie_jar => $hash_ref |
183 | |
197 | |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
198 | Passing this parameter enables (simplified) cookie-processing, loosely |
185 | based on the original netscape specification. |
199 | based on the original netscape specification. |
186 | |
200 | |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
201 | The C<$hash_ref> must be an (initially empty) hash reference which |
188 | get updated automatically. It is possible to save the cookie jar to |
202 | will get updated automatically. It is possible to save the cookie jar |
189 | persistent storage with something like JSON or Storable, but this is not |
203 | to persistent storage with something like JSON or Storable - see the |
190 | recommended, as session-only cookies might survive longer than expected. |
204 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
205 | expired or session-only cookies, and also for documentation on the format |
|
|
206 | of the cookie jar. |
191 | |
207 | |
192 | Note that this cookie implementation is not meant to be complete. If |
208 | Note that this cookie implementation is not meant to be complete. If |
193 | you want complete cookie management you have to do that on your |
209 | you want complete cookie management you have to do that on your |
194 | own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites |
210 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
195 | working. Cookies are a privacy disaster, do not use them unless required |
211 | working. Cookies are a privacy disaster, do not use them unless required |
196 | to. |
212 | to. |
197 | |
213 | |
198 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
214 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
199 | headers will be set and handled by this module, otherwise they will be |
215 | headers will be set and handled by this module, otherwise they will be |
… | |
… | |
364 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
380 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
365 | |
381 | |
366 | _slot_schedule $_[0]; |
382 | _slot_schedule $_[0]; |
367 | } |
383 | } |
368 | |
384 | |
|
|
385 | ############################################################################# |
|
|
386 | |
|
|
387 | # expire cookies |
|
|
388 | sub cookie_jar_expire($;$) { |
|
|
389 | my ($jar, $session_end) = @_; |
|
|
390 | |
|
|
391 | %$jar = () if $jar->{version} != 1; |
|
|
392 | |
|
|
393 | my $anow = AE::now; |
|
|
394 | |
|
|
395 | while (my ($chost, $paths) = each %$jar) { |
|
|
396 | next unless ref $paths; |
|
|
397 | |
|
|
398 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
399 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
400 | if (exists $kv->{_expires}) { |
|
|
401 | delete $cookies->{$cookie} |
|
|
402 | if $anow > $kv->{_expires}; |
|
|
403 | } elsif ($session_end) { |
|
|
404 | delete $cookies->{$cookie}; |
|
|
405 | } |
|
|
406 | } |
|
|
407 | |
|
|
408 | delete $paths->{$cpath} |
|
|
409 | unless %$cookies; |
|
|
410 | } |
|
|
411 | |
|
|
412 | delete $jar->{$chost} |
|
|
413 | unless %$paths; |
|
|
414 | } |
|
|
415 | } |
|
|
416 | |
369 | # extract cookies from jar |
417 | # extract cookies from jar |
370 | sub cookie_jar_extract($$$$) { |
418 | sub cookie_jar_extract($$$$) { |
371 | my ($jar, $uscheme, $uhost, $upath) = @_; |
419 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
420 | |
|
|
421 | $uhost = lc $uhost; |
372 | |
422 | |
373 | %$jar = () if $jar->{version} != 1; |
423 | %$jar = () if $jar->{version} != 1; |
374 | |
424 | |
375 | my @cookies; |
425 | my @cookies; |
376 | |
426 | |
… | |
… | |
389 | next unless $cpath eq substr $upath, 0, length $cpath; |
439 | next unless $cpath eq substr $upath, 0, length $cpath; |
390 | |
440 | |
391 | while (my ($cookie, $kv) = each %$cookies) { |
441 | while (my ($cookie, $kv) = each %$cookies) { |
392 | next if $uscheme ne "https" && exists $kv->{secure}; |
442 | next if $uscheme ne "https" && exists $kv->{secure}; |
393 | |
443 | |
394 | if (exists $kv->{expires}) { |
444 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
395 | if (AE::now > parse_date ($kv->{expires})) { |
|
|
396 | delete $cookies->{$cookie}; |
445 | delete $cookies->{$cookie}; |
397 | next; |
446 | next; |
398 | } |
|
|
399 | } |
447 | } |
400 | |
448 | |
401 | my $value = $kv->{value}; |
449 | my $value = $kv->{value}; |
402 | |
450 | |
403 | if ($value =~ /[=;,[:space:]]/) { |
451 | if ($value =~ /[=;,[:space:]]/) { |
… | |
… | |
412 | |
460 | |
413 | \@cookies |
461 | \@cookies |
414 | } |
462 | } |
415 | |
463 | |
416 | # parse set_cookie header into jar |
464 | # parse set_cookie header into jar |
417 | sub cookie_jar_set_cookie($$$) { |
465 | sub cookie_jar_set_cookie($$$$) { |
418 | my ($jar, $set_cookie, $uhost) = @_; |
466 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
467 | |
|
|
468 | my $anow = int AE::now; |
|
|
469 | my $snow; # server-now |
419 | |
470 | |
420 | for ($set_cookie) { |
471 | for ($set_cookie) { |
421 | # parse NAME=VALUE |
472 | # parse NAME=VALUE |
422 | my @kv; |
473 | my @kv; |
423 | |
474 | |
|
|
475 | # expires is not http-compliant in the original cookie-spec, |
|
|
476 | # we support the official date format and some extensions |
424 | while ( |
477 | while ( |
425 | m{ |
478 | m{ |
426 | \G\s* |
479 | \G\s* |
427 | (?: |
480 | (?: |
428 | expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) |
481 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
429 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
482 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
430 | ) |
483 | ) |
431 | }gcxsi |
484 | }gcxsi |
432 | ) { |
485 | ) { |
433 | my $name = $2; |
486 | my $name = $2; |
434 | my $value = $4; |
487 | my $value = $4; |
435 | |
488 | |
436 | unless (defined $name) { |
489 | if (defined $1) { |
437 | # expires |
490 | # expires |
438 | $name = "expires"; |
491 | $name = "expires"; |
439 | $value = $1; |
492 | $value = $1; |
440 | } elsif (!defined $value) { |
493 | } elsif (defined $3) { |
441 | # quoted |
494 | # quoted |
442 | $value = $3; |
495 | $value = $3; |
443 | $value =~ s/\\(.)/$1/gs; |
496 | $value =~ s/\\(.)/$1/gs; |
444 | } |
497 | } |
445 | |
498 | |
… | |
… | |
451 | last unless @kv; |
504 | last unless @kv; |
452 | |
505 | |
453 | my $name = shift @kv; |
506 | my $name = shift @kv; |
454 | my %kv = (value => shift @kv, @kv); |
507 | my %kv = (value => shift @kv, @kv); |
455 | |
508 | |
456 | $kv{expires} ||= format_date (AE::now + $kv{"max-age"}) |
|
|
457 | if exists $kv{"max-age"}; |
509 | if (exists $kv{"max-age"}) { |
|
|
510 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
511 | } elsif (exists $kv{expires}) { |
|
|
512 | $snow ||= parse_date ($date) || $anow; |
|
|
513 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
514 | } else { |
|
|
515 | delete $kv{_expires}; |
|
|
516 | } |
458 | |
517 | |
459 | my $cdom; |
518 | my $cdom; |
460 | my $cpath = (delete $kv{path}) || "/"; |
519 | my $cpath = (delete $kv{path}) || "/"; |
461 | |
520 | |
462 | if (exists $kv{domain}) { |
521 | if (exists $kv{domain}) { |
… | |
… | |
473 | $cdom = $uhost; |
532 | $cdom = $uhost; |
474 | } |
533 | } |
475 | |
534 | |
476 | # store it |
535 | # store it |
477 | $jar->{version} = 1; |
536 | $jar->{version} = 1; |
478 | $jar->{$cdom}{$cpath}{$name} = \%kv; |
537 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
479 | |
538 | |
480 | redo if /\G\s*,/gc; |
539 | redo if /\G\s*,/gc; |
481 | } |
540 | } |
482 | } |
541 | } |
483 | |
542 | |
… | |
… | |
600 | _get_slot $uhost, sub { |
659 | _get_slot $uhost, sub { |
601 | $state{slot_guard} = shift; |
660 | $state{slot_guard} = shift; |
602 | |
661 | |
603 | return unless $state{connect_guard}; |
662 | return unless $state{connect_guard}; |
604 | |
663 | |
|
|
664 | my $ae_error = 595; # connecting |
|
|
665 | |
|
|
666 | # handle actual, non-tunneled, request |
|
|
667 | my $handle_actual_request = sub { |
|
|
668 | $ae_error = 596; # request phase |
|
|
669 | |
|
|
670 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
671 | |
|
|
672 | # send request |
|
|
673 | $state{handle}->push_write ( |
|
|
674 | "$method $rpath HTTP/1.1\015\012" |
|
|
675 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
676 | . "\015\012" |
|
|
677 | . (delete $arg{body}) |
|
|
678 | ); |
|
|
679 | |
|
|
680 | # return if error occured during push_write() |
|
|
681 | return unless %state; |
|
|
682 | |
|
|
683 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
684 | |
|
|
685 | # status line and headers |
|
|
686 | $state{read_response} = sub { |
|
|
687 | for ("$_[1]") { |
|
|
688 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
689 | |
|
|
690 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
691 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
692 | |
|
|
693 | # 100 Continue handling |
|
|
694 | # should not happen as we don't send expect: 100-continue, |
|
|
695 | # but we handle it just in case. |
|
|
696 | # since we send the request body regardless, if we get an error |
|
|
697 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
698 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
699 | if $2 eq 100; |
|
|
700 | |
|
|
701 | push @pseudo, |
|
|
702 | HTTPVersion => $1, |
|
|
703 | Status => $2, |
|
|
704 | Reason => $3, |
|
|
705 | ; |
|
|
706 | |
|
|
707 | my $hdr = parse_hdr |
|
|
708 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
709 | |
|
|
710 | %hdr = (%$hdr, @pseudo); |
|
|
711 | } |
|
|
712 | |
|
|
713 | # redirect handling |
|
|
714 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
715 | # try to support some common forms of broken Location headers. |
|
|
716 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
717 | $hdr{location} =~ s/^\.\/+//; |
|
|
718 | |
|
|
719 | my $url = "$rscheme://$uhost:$uport"; |
|
|
720 | |
|
|
721 | unless ($hdr{location} =~ s/^\///) { |
|
|
722 | $url .= $upath; |
|
|
723 | $url =~ s/\/[^\/]*$//; |
|
|
724 | } |
|
|
725 | |
|
|
726 | $hdr{location} = "$url/$hdr{location}"; |
|
|
727 | } |
|
|
728 | |
|
|
729 | my $redirect; |
|
|
730 | |
|
|
731 | if ($recurse) { |
|
|
732 | my $status = $hdr{Status}; |
|
|
733 | |
|
|
734 | # industry standard is to redirect POST as GET for |
|
|
735 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
736 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
737 | # industry standard seems to be to simply follow. |
|
|
738 | # we go with the industry standard. |
|
|
739 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
740 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
741 | $method = "GET" unless $method eq "HEAD"; |
|
|
742 | $redirect = 1; |
|
|
743 | } elsif ($status == 307) { |
|
|
744 | $redirect = 1; |
|
|
745 | } |
|
|
746 | } |
|
|
747 | |
|
|
748 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
749 | my $may_keep_alive = $_[3]; |
|
|
750 | |
|
|
751 | $state{handle}->destroy if $state{handle}; |
|
|
752 | %state = (); |
|
|
753 | |
|
|
754 | if (defined $_[1]) { |
|
|
755 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
756 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
757 | } |
|
|
758 | |
|
|
759 | # set-cookie processing |
|
|
760 | if ($arg{cookie_jar}) { |
|
|
761 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
|
|
762 | } |
|
|
763 | |
|
|
764 | if ($redirect && exists $hdr{location}) { |
|
|
765 | # we ignore any errors, as it is very common to receive |
|
|
766 | # Content-Length != 0 but no actual body |
|
|
767 | # we also access %hdr, as $_[1] might be an erro |
|
|
768 | http_request ( |
|
|
769 | $method => $hdr{location}, |
|
|
770 | %arg, |
|
|
771 | recurse => $recurse - 1, |
|
|
772 | Redirect => [$_[0], \%hdr], |
|
|
773 | $cb); |
|
|
774 | } else { |
|
|
775 | $cb->($_[0], \%hdr); |
|
|
776 | } |
|
|
777 | }; |
|
|
778 | |
|
|
779 | $ae_error = 597; # body phase |
|
|
780 | |
|
|
781 | my $len = $hdr{"content-length"}; |
|
|
782 | warn "no content $redirect x<$len>$hdr{Status}\n";#d# |
|
|
783 | |
|
|
784 | # body handling, many different code paths |
|
|
785 | # - no body expected |
|
|
786 | # - want_body_handle |
|
|
787 | # - te chunked |
|
|
788 | # - 2x length known (with or without on_body) |
|
|
789 | # - 2x length not known (with or without on_body) |
|
|
790 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
791 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
792 | } elsif ( |
|
|
793 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
794 | or $method eq "HEAD" |
|
|
795 | or (defined $len && $len == 0) # == 0, not !, because "0 " is true |
|
|
796 | ) { |
|
|
797 | # no body |
|
|
798 | $finish->("", undef, undef, 1); |
|
|
799 | |
|
|
800 | } elsif (!$redirect && $arg{want_body_handle}) { |
|
|
801 | $_[0]->on_eof (undef); |
|
|
802 | $_[0]->on_error (undef); |
|
|
803 | $_[0]->on_read (undef); |
|
|
804 | |
|
|
805 | $finish->(delete $state{handle}); |
|
|
806 | |
|
|
807 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
808 | my $cl = 0; |
|
|
809 | my $body = undef; |
|
|
810 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
811 | |
|
|
812 | $state{read_chunk} = sub { |
|
|
813 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
814 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
815 | |
|
|
816 | my $len = hex $1; |
|
|
817 | |
|
|
818 | if ($len) { |
|
|
819 | $cl += $len; |
|
|
820 | |
|
|
821 | $_[0]->push_read (chunk => $len, sub { |
|
|
822 | $on_body->($_[1], \%hdr) |
|
|
823 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
824 | |
|
|
825 | $_[0]->push_read (line => sub { |
|
|
826 | length $_[1] |
|
|
827 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
828 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
829 | }); |
|
|
830 | }); |
|
|
831 | } else { |
|
|
832 | $hdr{"content-length"} ||= $cl; |
|
|
833 | |
|
|
834 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
835 | if (length $_[1]) { |
|
|
836 | for ("$_[1]") { |
|
|
837 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
838 | |
|
|
839 | my $hdr = parse_hdr |
|
|
840 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
841 | |
|
|
842 | %hdr = (%hdr, %$hdr); |
|
|
843 | } |
|
|
844 | } |
|
|
845 | |
|
|
846 | $finish->($body, undef, undef, 1); |
|
|
847 | }); |
|
|
848 | } |
|
|
849 | }; |
|
|
850 | |
|
|
851 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
852 | |
|
|
853 | } elsif ($arg{on_body}) { |
|
|
854 | if (defined $len) { |
|
|
855 | $_[0]->on_read (sub { |
|
|
856 | $len -= length $_[0]{rbuf}; |
|
|
857 | |
|
|
858 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
859 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
860 | |
|
|
861 | $len > 0 |
|
|
862 | or $finish->("", undef, undef, 1); |
|
|
863 | }); |
|
|
864 | } else { |
|
|
865 | $_[0]->on_eof (sub { |
|
|
866 | $finish->(""); |
|
|
867 | }); |
|
|
868 | $_[0]->on_read (sub { |
|
|
869 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
870 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
871 | }); |
|
|
872 | } |
|
|
873 | } else { |
|
|
874 | $_[0]->on_eof (undef); |
|
|
875 | |
|
|
876 | if (defined $len) { |
|
|
877 | $_[0]->on_read (sub { |
|
|
878 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
879 | if $len <= length $_[0]{rbuf}; |
|
|
880 | }); |
|
|
881 | } else { |
|
|
882 | $_[0]->on_error (sub { |
|
|
883 | ($! == Errno::EPIPE || !$!) |
|
|
884 | ? $finish->(delete $_[0]{rbuf}) |
|
|
885 | : $finish->(undef, $ae_error => $_[2]); |
|
|
886 | }); |
|
|
887 | $_[0]->on_read (sub { }); |
|
|
888 | } |
|
|
889 | } |
|
|
890 | }; |
|
|
891 | |
|
|
892 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
893 | }; |
|
|
894 | |
605 | my $connect_cb = sub { |
895 | my $connect_cb = sub { |
606 | $state{fh} = shift |
896 | $state{fh} = shift |
607 | or do { |
897 | or do { |
608 | my $err = "$!"; |
898 | my $err = "$!"; |
609 | %state = (); |
899 | %state = (); |
610 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
900 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
611 | }; |
901 | }; |
612 | |
|
|
613 | pop; # free memory, save a tree |
|
|
614 | |
902 | |
615 | return unless delete $state{connect_guard}; |
903 | return unless delete $state{connect_guard}; |
616 | |
904 | |
617 | # get handle |
905 | # get handle |
618 | $state{handle} = new AnyEvent::Handle |
906 | $state{handle} = new AnyEvent::Handle |
… | |
… | |
621 | tls_ctx => $arg{tls_ctx}, |
909 | tls_ctx => $arg{tls_ctx}, |
622 | # these need to be reconfigured on keepalive handles |
910 | # these need to be reconfigured on keepalive handles |
623 | timeout => $timeout, |
911 | timeout => $timeout, |
624 | on_error => sub { |
912 | on_error => sub { |
625 | %state = (); |
913 | %state = (); |
626 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
914 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
627 | }, |
915 | }, |
628 | on_eof => sub { |
916 | on_eof => sub { |
629 | %state = (); |
917 | %state = (); |
630 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
918 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
631 | }, |
919 | }, |
632 | ; |
920 | ; |
633 | |
921 | |
634 | # limit the number of persistent connections |
922 | # limit the number of persistent connections |
635 | # keepalive not yet supported |
923 | # keepalive not yet supported |
… | |
… | |
641 | # $hdr{connection} = "keep-alive"; |
929 | # $hdr{connection} = "keep-alive"; |
642 | # } |
930 | # } |
643 | |
931 | |
644 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
932 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
645 | |
933 | |
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, $state{read_response}); |
|
|
874 | }; |
|
|
875 | |
|
|
876 | # now handle proxy-CONNECT method |
934 | # now handle proxy-CONNECT method |
877 | if ($proxy && $uscheme eq "https") { |
935 | if ($proxy && $uscheme eq "https") { |
878 | # oh dear, we have to wrap it into a connect request |
936 | # oh dear, we have to wrap it into a connect request |
879 | |
937 | |
880 | # maybe re-use $uauthority with patched port? |
938 | # maybe re-use $uauthority with patched port? |
… | |
… | |
883 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
941 | $_[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])" })); |
942 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
885 | |
943 | |
886 | if ($2 == 200) { |
944 | if ($2 == 200) { |
887 | $rpath = $upath; |
945 | $rpath = $upath; |
888 | &$handle_actual_request; |
946 | $handle_actual_request->(); |
889 | } else { |
947 | } else { |
890 | %state = (); |
948 | %state = (); |
891 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
949 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
892 | } |
950 | } |
893 | }); |
951 | }); |
894 | } else { |
952 | } else { |
895 | &$handle_actual_request; |
953 | $handle_actual_request->(); |
896 | } |
954 | } |
897 | }; |
955 | }; |
898 | |
956 | |
899 | my $tcp_connect = $arg{tcp_connect} |
957 | my $tcp_connect = $arg{tcp_connect} |
900 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
958 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
901 | |
959 | |
902 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
960 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
903 | |
|
|
904 | }; |
961 | }; |
905 | |
962 | |
906 | defined wantarray && AnyEvent::Util::guard { %state = () } |
963 | defined wantarray && AnyEvent::Util::guard { %state = () } |
907 | } |
964 | } |
908 | |
965 | |
… | |
… | |
943 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
1000 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
944 | otherwise. |
1001 | otherwise. |
945 | |
1002 | |
946 | To clear an already-set proxy, use C<undef>. |
1003 | To clear an already-set proxy, use C<undef>. |
947 | |
1004 | |
|
|
1005 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1006 | |
|
|
1007 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1008 | C<$session_end> is given and true, then additionally remove all session |
|
|
1009 | cookies. |
|
|
1010 | |
|
|
1011 | You should call this function (with a true C<$session_end>) before you |
|
|
1012 | save cookies to disk, and you should call this function after loading them |
|
|
1013 | again. If you have a long-running program you can additonally call this |
|
|
1014 | function from time to time. |
|
|
1015 | |
|
|
1016 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1017 | module. It's format is subject to change, but currently it is like this: |
|
|
1018 | |
|
|
1019 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1020 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1021 | hash-references. The key for these inner hash references is the |
|
|
1022 | server path for which this cookie is meant, and the values are again |
|
|
1023 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1024 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1025 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1026 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1027 | expiry timestamp. |
|
|
1028 | |
|
|
1029 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1030 | chance of understanding the above paragraph: |
|
|
1031 | |
|
|
1032 | { |
|
|
1033 | version => 1, |
|
|
1034 | "10.0.0.1" => { |
|
|
1035 | "/" => { |
|
|
1036 | "mythweb_id" => { |
|
|
1037 | _expires => 1293917923, |
|
|
1038 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1039 | }, |
|
|
1040 | }, |
|
|
1041 | }, |
|
|
1042 | } |
|
|
1043 | |
948 | =item $date = AnyEvent::HTTP::format_date $timestamp |
1044 | =item $date = AnyEvent::HTTP::format_date $timestamp |
949 | |
1045 | |
950 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
1046 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
951 | Date (RFC 2616). |
1047 | Date (RFC 2616). |
952 | |
1048 | |
953 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
1049 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
954 | |
1050 | |
955 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and |
1051 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
956 | returns the corresponding POSIX timestamp, or C<undef> if the date cannot |
1052 | bunch of minor variations of those, and returns the corresponding POSIX |
957 | be parsed. |
1053 | timestamp, or C<undef> if the date cannot be parsed. |
958 | |
1054 | |
959 | =item $AnyEvent::HTTP::MAX_RECURSE |
1055 | =item $AnyEvent::HTTP::MAX_RECURSE |
960 | |
1056 | |
961 | The default value for the C<recurse> request parameter (default: C<10>). |
1057 | The default value for the C<recurse> request parameter (default: C<10>). |
962 | |
1058 | |
… | |
… | |
1001 | sub parse_date($) { |
1097 | sub parse_date($) { |
1002 | my ($date) = @_; |
1098 | my ($date) = @_; |
1003 | |
1099 | |
1004 | my ($d, $m, $y, $H, $M, $S); |
1100 | my ($d, $m, $y, $H, $M, $S); |
1005 | |
1101 | |
1006 | if ($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$/) { |
1102 | if ($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$/) { |
1007 | # RFC 822/1123, required by RFC 2616 (with " ") |
1103 | # RFC 822/1123, required by RFC 2616 (with " ") |
1008 | # cookie dates (with "-") |
1104 | # cookie dates (with "-") |
1009 | |
1105 | |
1010 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1106 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1011 | |
1107 | |
1012 | } elsif ($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$/) { |
1108 | } elsif ($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$/) { |
1013 | # RFC 850 |
1109 | # RFC 850 |
1014 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1110 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1015 | |
1111 | |
1016 | } elsif ($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])$/) { |
1112 | } elsif ($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])$/) { |
1017 | # ISO C's asctime |
1113 | # ISO C's asctime |
1018 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1114 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1019 | } |
1115 | } |
1020 | # other formats fail in the loop below |
1116 | # other formats fail in the loop below |
1021 | |
1117 | |