… | |
… | |
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) = @_; |
… | |
… | |
152 | |
166 | |
153 | =item headers => hashref |
167 | =item headers => hashref |
154 | |
168 | |
155 | The request headers to use. Currently, C<http_request> may provide its own |
169 | The request headers to use. Currently, C<http_request> may provide its own |
156 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
170 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
157 | will provide defaults for C<TE:>, C<Referer:> and C<User-Agent:> (this can |
171 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
158 | be suppressed by using C<undef> for these headers in which case they won't |
172 | (this can be suppressed by using C<undef> for these headers in which case |
159 | be sent at all). |
173 | they won't be sent at all). |
160 | |
174 | |
161 | =item timeout => $seconds |
175 | =item timeout => $seconds |
162 | |
176 | |
163 | The time-out to use for various stages - each connect attempt will reset |
177 | The time-out to use for various stages - each connect attempt will reset |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
178 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
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 expiry times are currently being ignored. |
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 of very high quality, nor |
208 | Note that this cookie implementation is not meant to be complete. If |
193 | meant to be complete. If you want complete cookie management you have to |
209 | you want complete cookie management you have to do that on your |
194 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
210 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
195 | cookie-using sites working. Cookies are a privacy disaster, do not use |
211 | working. Cookies are a privacy disaster, do not use them unless required |
196 | them unless required to. |
212 | to. |
|
|
213 | |
|
|
214 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
215 | headers will be set and handled by this module, otherwise they will be |
|
|
216 | left untouched. |
197 | |
217 | |
198 | =item tls_ctx => $scheme | $tls_ctx |
218 | =item tls_ctx => $scheme | $tls_ctx |
199 | |
219 | |
200 | Specifies the AnyEvent::TLS context to be used for https connections. This |
220 | Specifies the AnyEvent::TLS context to be used for https connections. This |
201 | parameter follows the same rules as the C<tls_ctx> parameter to |
221 | parameter follows the same rules as the C<tls_ctx> parameter to |
… | |
… | |
360 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
380 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
361 | |
381 | |
362 | _slot_schedule $_[0]; |
382 | _slot_schedule $_[0]; |
363 | } |
383 | } |
364 | |
384 | |
|
|
385 | ############################################################################# |
|
|
386 | |
|
|
387 | # expire cookies |
|
|
388 | sub cookie_jar_expire($;$) { |
|
|
389 | my ($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 | |
|
|
417 | # extract cookies from jar |
|
|
418 | sub cookie_jar_extract($$$$) { |
|
|
419 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
420 | |
|
|
421 | %$jar = () if $jar->{version} != 1; |
|
|
422 | |
|
|
423 | my @cookies; |
|
|
424 | |
|
|
425 | while (my ($chost, $paths) = each %$jar) { |
|
|
426 | next unless ref $paths; |
|
|
427 | |
|
|
428 | if ($chost =~ /^\./) { |
|
|
429 | next unless $chost eq substr $uhost, -length $chost; |
|
|
430 | } elsif ($chost =~ /\./) { |
|
|
431 | next unless $chost eq $uhost; |
|
|
432 | } else { |
|
|
433 | next; |
|
|
434 | } |
|
|
435 | |
|
|
436 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
437 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
438 | |
|
|
439 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
440 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
441 | |
|
|
442 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
|
|
443 | delete $cookies->{$cookie}; |
|
|
444 | next; |
|
|
445 | } |
|
|
446 | |
|
|
447 | my $value = $kv->{value}; |
|
|
448 | |
|
|
449 | if ($value =~ /[=;,[:space:]]/) { |
|
|
450 | $value =~ s/([\\"])/\\$1/g; |
|
|
451 | $value = "\"$value\""; |
|
|
452 | } |
|
|
453 | |
|
|
454 | push @cookies, "$cookie=$value"; |
|
|
455 | } |
|
|
456 | } |
|
|
457 | } |
|
|
458 | |
|
|
459 | \@cookies |
|
|
460 | } |
|
|
461 | |
|
|
462 | # parse set_cookie header into jar |
|
|
463 | sub cookie_jar_set_cookie($$$$) { |
|
|
464 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
465 | |
|
|
466 | my $anow = int AE::now; |
|
|
467 | my $snow; # server-now |
|
|
468 | |
|
|
469 | for ($set_cookie) { |
|
|
470 | # parse NAME=VALUE |
|
|
471 | my @kv; |
|
|
472 | |
|
|
473 | # expires is not http-compliant in the original cookie-spec, |
|
|
474 | # we support the official date format and some extensions |
|
|
475 | while ( |
|
|
476 | m{ |
|
|
477 | \G\s* |
|
|
478 | (?: |
|
|
479 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
|
|
480 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
|
|
481 | ) |
|
|
482 | }gcxsi |
|
|
483 | ) { |
|
|
484 | my $name = $2; |
|
|
485 | my $value = $4; |
|
|
486 | |
|
|
487 | unless (defined $name) { |
|
|
488 | # expires |
|
|
489 | $name = "expires"; |
|
|
490 | $value = $1; |
|
|
491 | } elsif (!defined $value) { |
|
|
492 | # quoted |
|
|
493 | $value = $3; |
|
|
494 | $value =~ s/\\(.)/$1/gs; |
|
|
495 | } |
|
|
496 | |
|
|
497 | push @kv, lc $name, $value; |
|
|
498 | |
|
|
499 | last unless /\G\s*;/gc; |
|
|
500 | } |
|
|
501 | |
|
|
502 | last unless @kv; |
|
|
503 | |
|
|
504 | my $name = shift @kv; |
|
|
505 | my %kv = (value => shift @kv, @kv); |
|
|
506 | |
|
|
507 | if (exists $kv{"max-age"}) { |
|
|
508 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
509 | } elsif (exists $kv{expires}) { |
|
|
510 | $snow ||= parse_date ($date) || $anow; |
|
|
511 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
512 | } else { |
|
|
513 | delete $kv{_expires}; |
|
|
514 | } |
|
|
515 | |
|
|
516 | my $cdom; |
|
|
517 | my $cpath = (delete $kv{path}) || "/"; |
|
|
518 | |
|
|
519 | if (exists $kv{domain}) { |
|
|
520 | $cdom = delete $kv{domain}; |
|
|
521 | |
|
|
522 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
523 | |
|
|
524 | next if $cdom =~ /\.$/; |
|
|
525 | |
|
|
526 | # this is not rfc-like and not netscape-like. go figure. |
|
|
527 | my $ndots = $cdom =~ y/.//; |
|
|
528 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
529 | } else { |
|
|
530 | $cdom = $uhost; |
|
|
531 | } |
|
|
532 | |
|
|
533 | # store it |
|
|
534 | $jar->{version} = 1; |
|
|
535 | $jar->{$cdom}{$cpath}{$name} = \%kv; |
|
|
536 | |
|
|
537 | redo if /\G\s*,/gc; |
|
|
538 | } |
|
|
539 | } |
|
|
540 | |
365 | # continue to parse $_ for headers and place them into the arg |
541 | # continue to parse $_ for headers and place them into the arg |
366 | sub parse_hdr() { |
542 | sub parse_hdr() { |
367 | my %hdr; |
543 | my %hdr; |
368 | |
544 | |
369 | # things seen, not parsed: |
545 | # things seen, not parsed: |
… | |
… | |
444 | |
620 | |
445 | $upath =~ s%^/?%/%; |
621 | $upath =~ s%^/?%/%; |
446 | |
622 | |
447 | # cookie processing |
623 | # cookie processing |
448 | if (my $jar = $arg{cookie_jar}) { |
624 | if (my $jar = $arg{cookie_jar}) { |
449 | %$jar = () if $jar->{version} != 1; |
625 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
450 | |
626 | |
451 | my @cookie; |
|
|
452 | |
|
|
453 | while (my ($chost, $v) = each %$jar) { |
|
|
454 | if ($chost =~ /^\./) { |
|
|
455 | next unless $chost eq substr $uhost, -length $chost; |
|
|
456 | } elsif ($chost =~ /\./) { |
|
|
457 | next unless $chost eq $uhost; |
|
|
458 | } else { |
|
|
459 | next; |
|
|
460 | } |
|
|
461 | |
|
|
462 | while (my ($cpath, $v) = each %$v) { |
|
|
463 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
464 | |
|
|
465 | while (my ($k, $v) = each %$v) { |
|
|
466 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
467 | my $value = $v->{value}; |
|
|
468 | $value =~ s/([\\"])/\\$1/g; |
|
|
469 | push @cookie, "$k=\"$value\""; |
|
|
470 | } |
|
|
471 | } |
|
|
472 | } |
|
|
473 | |
|
|
474 | $hdr{cookie} = join "; ", @cookie |
627 | $hdr{cookie} = join "; ", @$cookies |
475 | if @cookie; |
628 | if @$cookies; |
476 | } |
629 | } |
477 | |
630 | |
478 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
631 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
479 | |
632 | |
480 | if ($proxy) { |
633 | if ($proxy) { |
… | |
… | |
504 | _get_slot $uhost, sub { |
657 | _get_slot $uhost, sub { |
505 | $state{slot_guard} = shift; |
658 | $state{slot_guard} = shift; |
506 | |
659 | |
507 | return unless $state{connect_guard}; |
660 | return unless $state{connect_guard}; |
508 | |
661 | |
|
|
662 | my $ae_error = 595; # connecting |
|
|
663 | |
509 | my $connect_cb = sub { |
664 | my $connect_cb = sub { |
510 | $state{fh} = shift |
665 | $state{fh} = shift |
511 | or do { |
666 | or do { |
512 | my $err = "$!"; |
667 | my $err = "$!"; |
513 | %state = (); |
668 | %state = (); |
514 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
669 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
515 | }; |
670 | }; |
516 | |
|
|
517 | pop; # free memory, save a tree |
|
|
518 | |
671 | |
519 | return unless delete $state{connect_guard}; |
672 | return unless delete $state{connect_guard}; |
520 | |
673 | |
521 | # get handle |
674 | # get handle |
522 | $state{handle} = new AnyEvent::Handle |
675 | $state{handle} = new AnyEvent::Handle |
… | |
… | |
525 | tls_ctx => $arg{tls_ctx}, |
678 | tls_ctx => $arg{tls_ctx}, |
526 | # these need to be reconfigured on keepalive handles |
679 | # these need to be reconfigured on keepalive handles |
527 | timeout => $timeout, |
680 | timeout => $timeout, |
528 | on_error => sub { |
681 | on_error => sub { |
529 | %state = (); |
682 | %state = (); |
530 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
683 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
531 | }, |
684 | }, |
532 | on_eof => sub { |
685 | on_eof => sub { |
533 | %state = (); |
686 | %state = (); |
534 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
687 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
535 | }, |
688 | }, |
536 | ; |
689 | ; |
537 | |
690 | |
538 | # limit the number of persistent connections |
691 | # limit the number of persistent connections |
539 | # keepalive not yet supported |
692 | # keepalive not yet supported |
… | |
… | |
547 | |
700 | |
548 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
701 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
549 | |
702 | |
550 | # handle actual, non-tunneled, request |
703 | # handle actual, non-tunneled, request |
551 | my $handle_actual_request = sub { |
704 | my $handle_actual_request = sub { |
|
|
705 | $ae_error = 596; # request phase |
|
|
706 | |
552 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
707 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
553 | |
708 | |
554 | # send request |
709 | # send request |
555 | $state{handle}->push_write ( |
710 | $state{handle}->push_write ( |
556 | "$method $rpath HTTP/1.1\015\012" |
711 | "$method $rpath HTTP/1.1\015\012" |
… | |
… | |
567 | # status line and headers |
722 | # status line and headers |
568 | $state{read_response} = sub { |
723 | $state{read_response} = sub { |
569 | for ("$_[1]") { |
724 | for ("$_[1]") { |
570 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
725 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
571 | |
726 | |
572 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc |
727 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
573 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
728 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
574 | |
729 | |
575 | # 100 Continue handling |
730 | # 100 Continue handling |
576 | # should not happen as we don't send expect: 100-continue, |
731 | # should not happen as we don't send expect: 100-continue, |
577 | # but we handle it just in case. |
732 | # but we handle it just in case. |
… | |
… | |
612 | |
767 | |
613 | if ($recurse) { |
768 | if ($recurse) { |
614 | my $status = $hdr{Status}; |
769 | my $status = $hdr{Status}; |
615 | |
770 | |
616 | # industry standard is to redirect POST as GET for |
771 | # industry standard is to redirect POST as GET for |
617 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
772 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
618 | # also, the UA should ask the user for 301 and 307 and POST, |
773 | # also, the UA should ask the user for 301 and 307 and POST, |
619 | # industry standard seems to be to simply follow. |
774 | # industry standard seems to be to simply follow. |
620 | # we go with the industry standard. |
775 | # we go with the industry standard. |
621 | if ($status == 301 or $status == 302 or $status == 303) { |
776 | if ($status == 301 or $status == 302 or $status == 303) { |
622 | # HTTP/1.1 is unclear on how to mutate the method |
777 | # HTTP/1.1 is unclear on how to mutate the method |
… | |
… | |
626 | $redirect = 1; |
781 | $redirect = 1; |
627 | } |
782 | } |
628 | } |
783 | } |
629 | |
784 | |
630 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
785 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
631 | my $keepalive = pop; |
786 | my $may_keep_alive = $_[3]; |
632 | |
787 | |
633 | $state{handle}->destroy if $state{handle}; |
788 | $state{handle}->destroy if $state{handle}; |
634 | %state = (); |
789 | %state = (); |
635 | |
790 | |
636 | if (defined $_[1]) { |
791 | if (defined $_[1]) { |
… | |
… | |
638 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
793 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
639 | } |
794 | } |
640 | |
795 | |
641 | # set-cookie processing |
796 | # set-cookie processing |
642 | if ($arg{cookie_jar}) { |
797 | if ($arg{cookie_jar}) { |
643 | for ($hdr{"set-cookie"}) { |
798 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
644 | # parse NAME=VALUE |
|
|
645 | my @kv; |
|
|
646 | |
|
|
647 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
648 | my $name = $1; |
|
|
649 | my $value = $3; |
|
|
650 | |
|
|
651 | unless ($value) { |
|
|
652 | $value = $2; |
|
|
653 | $value =~ s/\\(.)/$1/gs; |
|
|
654 | } |
|
|
655 | |
|
|
656 | push @kv, $name => $value; |
|
|
657 | |
|
|
658 | last unless /\G\s*;/gc; |
|
|
659 | } |
|
|
660 | |
|
|
661 | last unless @kv; |
|
|
662 | |
|
|
663 | my $name = shift @kv; |
|
|
664 | my %kv = (value => shift @kv, @kv); |
|
|
665 | |
|
|
666 | my $cdom; |
|
|
667 | my $cpath = (delete $kv{path}) || "/"; |
|
|
668 | |
|
|
669 | if (exists $kv{domain}) { |
|
|
670 | $cdom = delete $kv{domain}; |
|
|
671 | |
|
|
672 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
673 | |
|
|
674 | next if $cdom =~ /\.$/; |
|
|
675 | |
|
|
676 | # this is not rfc-like and not netscape-like. go figure. |
|
|
677 | my $ndots = $cdom =~ y/.//; |
|
|
678 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
679 | } else { |
|
|
680 | $cdom = $uhost; |
|
|
681 | } |
|
|
682 | |
|
|
683 | # store it |
|
|
684 | $arg{cookie_jar}{version} = 1; |
|
|
685 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
686 | |
|
|
687 | redo if /\G\s*,/gc; |
|
|
688 | } |
|
|
689 | } |
799 | } |
690 | |
800 | |
691 | if ($redirect && exists $hdr{location}) { |
801 | if ($redirect && exists $hdr{location}) { |
692 | # we ignore any errors, as it is very common to receive |
802 | # we ignore any errors, as it is very common to receive |
693 | # Content-Length != 0 but no actual body |
803 | # Content-Length != 0 but no actual body |
… | |
… | |
700 | $cb); |
810 | $cb); |
701 | } else { |
811 | } else { |
702 | $cb->($_[0], \%hdr); |
812 | $cb->($_[0], \%hdr); |
703 | } |
813 | } |
704 | }; |
814 | }; |
|
|
815 | |
|
|
816 | $ae_error = 597; # body phase |
705 | |
817 | |
706 | my $len = $hdr{"content-length"}; |
818 | my $len = $hdr{"content-length"}; |
707 | |
819 | |
708 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
820 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
709 | $finish->(undef, 598 => "Request cancelled by on_header"); |
821 | $finish->(undef, 598 => "Request cancelled by on_header"); |
… | |
… | |
731 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
843 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
732 | my $cl = 0; |
844 | my $cl = 0; |
733 | my $body = undef; |
845 | my $body = undef; |
734 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
846 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
735 | |
847 | |
736 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
737 | |
|
|
738 | my $read_chunk; $read_chunk = sub { |
848 | $state{read_chunk} = sub { |
739 | $_[1] =~ /^([0-9a-fA-F]+)/ |
849 | $_[1] =~ /^([0-9a-fA-F]+)/ |
740 | or $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
850 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
741 | |
851 | |
742 | my $len = hex $1; |
852 | my $len = hex $1; |
743 | |
853 | |
744 | if ($len) { |
854 | if ($len) { |
745 | $cl += $len; |
855 | $cl += $len; |
… | |
… | |
748 | $on_body->($_[1], \%hdr) |
858 | $on_body->($_[1], \%hdr) |
749 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
859 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
750 | |
860 | |
751 | $_[0]->push_read (line => sub { |
861 | $_[0]->push_read (line => sub { |
752 | length $_[1] |
862 | length $_[1] |
753 | and return $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
863 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
754 | $_[0]->push_read (line => $read_chunk); |
864 | $_[0]->push_read (line => $state{read_chunk}); |
755 | }); |
865 | }); |
756 | }); |
866 | }); |
757 | } else { |
867 | } else { |
758 | $hdr{"content-length"} ||= $cl; |
868 | $hdr{"content-length"} ||= $cl; |
759 | |
869 | |
… | |
… | |
761 | if (length $_[1]) { |
871 | if (length $_[1]) { |
762 | for ("$_[1]") { |
872 | for ("$_[1]") { |
763 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
873 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
764 | |
874 | |
765 | my $hdr = parse_hdr |
875 | my $hdr = parse_hdr |
766 | or return $finish->(undef, 599 => "Garbled response trailers"); |
876 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
767 | |
877 | |
768 | %hdr = (%hdr, %$hdr); |
878 | %hdr = (%hdr, %$hdr); |
769 | } |
879 | } |
770 | } |
880 | } |
771 | |
881 | |
772 | $finish->($body, undef, undef, 1); |
882 | $finish->($body, undef, undef, 1); |
773 | }); |
883 | }); |
774 | } |
884 | } |
775 | }; |
885 | }; |
776 | |
886 | |
777 | $_[0]->push_read (line => $read_chunk); |
887 | $_[0]->push_read (line => $state{read_chunk}); |
778 | |
888 | |
779 | } elsif ($arg{on_body}) { |
889 | } elsif ($arg{on_body}) { |
780 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
781 | |
|
|
782 | if ($len) { |
890 | if ($len) { |
783 | $_[0]->on_read (sub { |
891 | $_[0]->on_read (sub { |
784 | $len -= length $_[0]{rbuf}; |
892 | $len -= length $_[0]{rbuf}; |
785 | |
893 | |
786 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
894 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
800 | } |
908 | } |
801 | } else { |
909 | } else { |
802 | $_[0]->on_eof (undef); |
910 | $_[0]->on_eof (undef); |
803 | |
911 | |
804 | if ($len) { |
912 | if ($len) { |
805 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
806 | $_[0]->on_read (sub { |
913 | $_[0]->on_read (sub { |
807 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
914 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
808 | if $len <= length $_[0]{rbuf}; |
915 | if $len <= length $_[0]{rbuf}; |
809 | }); |
916 | }); |
810 | } else { |
917 | } else { |
811 | $_[0]->on_error (sub { |
918 | $_[0]->on_error (sub { |
812 | ($! == Errno::EPIPE || !$!) |
919 | ($! == Errno::EPIPE || !$!) |
813 | ? $finish->(delete $_[0]{rbuf}) |
920 | ? $finish->(delete $_[0]{rbuf}) |
814 | : $finish->(undef, 599 => $_[2]); |
921 | : $finish->(undef, $ae_error => $_[2]); |
815 | }); |
922 | }); |
816 | $_[0]->on_read (sub { }); |
923 | $_[0]->on_read (sub { }); |
817 | } |
924 | } |
818 | } |
925 | } |
819 | } |
926 | } |
… | |
… | |
832 | $_[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 |
833 | 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])" })); |
834 | |
941 | |
835 | if ($2 == 200) { |
942 | if ($2 == 200) { |
836 | $rpath = $upath; |
943 | $rpath = $upath; |
837 | &$handle_actual_request; |
944 | $handle_actual_request->(); |
838 | } else { |
945 | } else { |
839 | %state = (); |
946 | %state = (); |
840 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
947 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
841 | } |
948 | } |
842 | }); |
949 | }); |
843 | } else { |
950 | } else { |
844 | &$handle_actual_request; |
951 | $handle_actual_request->(); |
845 | } |
952 | } |
846 | }; |
953 | }; |
847 | |
954 | |
848 | my $tcp_connect = $arg{tcp_connect} |
955 | my $tcp_connect = $arg{tcp_connect} |
849 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
956 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
892 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
999 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
893 | otherwise. |
1000 | otherwise. |
894 | |
1001 | |
895 | To clear an already-set proxy, use C<undef>. |
1002 | To clear an already-set proxy, use C<undef>. |
896 | |
1003 | |
|
|
1004 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1005 | |
|
|
1006 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1007 | C<$session_end> is given and true, then additionally remove all session |
|
|
1008 | cookies. |
|
|
1009 | |
|
|
1010 | You should call this function (with a true C<$session_end>) before you |
|
|
1011 | save cookies to disk, and you should call this function after loading them |
|
|
1012 | again. If you have a long-running program you can additonally call this |
|
|
1013 | function from time to time. |
|
|
1014 | |
|
|
1015 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1016 | module. It's format is subject to change, but currently it is like this: |
|
|
1017 | |
|
|
1018 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1019 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1020 | hash-references. The key for these inner hash references is the |
|
|
1021 | server path for which this cookie is meant, and the values are again |
|
|
1022 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1023 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1024 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1025 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1026 | expiry timestamp. |
|
|
1027 | |
|
|
1028 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1029 | chance of understanding the above paragraph: |
|
|
1030 | |
|
|
1031 | { |
|
|
1032 | version => 1, |
|
|
1033 | "10.0.0.1" => { |
|
|
1034 | "/" => { |
|
|
1035 | "mythweb_id" => { |
|
|
1036 | _expires => 1293917923, |
|
|
1037 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1038 | }, |
|
|
1039 | }, |
|
|
1040 | }, |
|
|
1041 | } |
|
|
1042 | |
897 | =item $date = AnyEvent::HTTP::format_date $timestamp |
1043 | =item $date = AnyEvent::HTTP::format_date $timestamp |
898 | |
1044 | |
899 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
1045 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
900 | Date (RFC 2616). |
1046 | Date (RFC 2616). |
901 | |
1047 | |
902 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
1048 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
903 | |
1049 | |
904 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
1050 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
|
|
1051 | bunch of minor variations of those, and returns the corresponding POSIX |
905 | timestamp, or C<undef> if the date cannot be parsed. |
1052 | timestamp, or C<undef> if the date cannot be parsed. |
906 | |
1053 | |
907 | =item $AnyEvent::HTTP::MAX_RECURSE |
1054 | =item $AnyEvent::HTTP::MAX_RECURSE |
908 | |
1055 | |
909 | The default value for the C<recurse> request parameter (default: C<10>). |
1056 | The default value for the C<recurse> request parameter (default: C<10>). |
… | |
… | |
949 | sub parse_date($) { |
1096 | sub parse_date($) { |
950 | my ($date) = @_; |
1097 | my ($date) = @_; |
951 | |
1098 | |
952 | my ($d, $m, $y, $H, $M, $S); |
1099 | my ($d, $m, $y, $H, $M, $S); |
953 | |
1100 | |
954 | if ($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$/) { |
1101 | if ($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$/) { |
955 | # RFC 822/1123, required by RFC 2616 |
1102 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1103 | # cookie dates (with "-") |
|
|
1104 | |
956 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1105 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
957 | |
1106 | |
958 | } elsif ($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$/) { |
1107 | } elsif ($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$/) { |
959 | # RFC 850 |
1108 | # RFC 850 |
960 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1109 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
961 | |
1110 | |
962 | } elsif ($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])$/) { |
1111 | } elsif ($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])$/) { |
963 | # ISO C's asctime |
1112 | # ISO C's asctime |
964 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1113 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
965 | } |
1114 | } |
966 | # other formats fail in the loop below |
1115 | # other formats fail in the loop below |
967 | |
1116 | |