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 1.60 by root, Thu Dec 30 02:56:28 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 ();
48use AnyEvent::Handle (); 47use AnyEvent::Handle ();
49 48
50use base Exporter::; 49use base Exporter::;
51 50
52our $VERSION = '1.46'; 51our $VERSION = '1.5';
53 52
54our @EXPORT = qw(http_get http_post http_head http_request); 53our @EXPORT = qw(http_get http_post http_head http_request);
55 54
56our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; 55our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
57our $MAX_RECURSE = 10; 56our $MAX_RECURSE = 10;
94C<http_request> returns a "cancellation guard" - you have to keep the 93C<http_request> returns a "cancellation guard" - you have to keep the
95object at least alive until the callback get called. If the object gets 94object at least alive until the callback get called. If the object gets
96destroyed before the callback is called, the request will be cancelled. 95destroyed before the callback is called, the request will be cancelled.
97 96
98The callback will be called with the response body data as first argument 97The callback will be called with the response body data as first argument
99(or C<undef> if an error occured), and a hash-ref with response headers as 98(or C<undef> if an error occured), and a hash-ref with response headers
100second argument. 99(and trailers) as second argument.
101 100
102All the headers in that hash are lowercased. In addition to the response 101All the headers in that hash are lowercased. In addition to the response
103headers, the "pseudo-headers" (uppercase to avoid clashing with possible 102headers, the "pseudo-headers" (uppercase to avoid clashing with possible
104response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the 103response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105three parts of the HTTP Status-Line of the same name. 104three parts of the HTTP Status-Line of the same name. If an error occurs
105during the body phase of a request, then the original C<Status> and
106C<Reason> values from the header are available as C<OrigStatus> and
107C<OrigReason>.
106 108
107The pseudo-header C<URL> contains the actual URL (which can differ from 109The pseudo-header C<URL> contains the actual URL (which can differ from
108the requested URL when following redirects - for example, you might get 110the requested URL when following redirects - for example, you might get
109an error that your URL scheme is not supported even though your URL is a 111an error that your URL scheme is not supported even though your URL is a
110valid http URL because it redirected to an ftp URL, in which case you can 112valid http URL because it redirected to an ftp URL, in which case you can
119 121
120If 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
121joined together with a comma (C<,>), as per the HTTP spec. 123joined together with a comma (C<,>), as per the HTTP spec.
122 124
123If 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,
124then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> 126then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
125(usually C<599>) and the C<Reason> pseudo-header will contain an error 127C<590>-C<599> and the C<Reason> pseudo-header will contain an error
126message. 128message. Currently the following status codes are used:
129
130=over 4
131
132=item 595 - errors during connection etsbalishment, proxy handshake.
133
134=item 596 - errors during TLS negotiation, request sending and header processing.
135
136=item 597 - errors during body receiving or processing.
137
138=item 598 - user aborted request via C<on_header> or C<on_body>.
139
140=item 599 - other, usually nonretryable, errors (garbled URL etc.).
141
142=back
127 143
128A typical callback might look like this: 144A typical callback might look like this:
129 145
130 sub { 146 sub {
131 my ($body, $hdr) = @_; 147 my ($body, $hdr) = @_;
147Whether to recurse requests or not, e.g. on redirects, authentication 163Whether to recurse requests or not, e.g. on redirects, authentication
148retries and so on, and how often to do so. 164retries and so on, and how often to do so.
149 165
150=item headers => hashref 166=item headers => hashref
151 167
152The request headers to use. Currently, C<http_request> may provide its 168The request headers to use. Currently, C<http_request> may provide its own
153own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers 169C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
154and will provide defaults for C<User-Agent:> and C<Referer:> (this can be 170will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
155suppressed by using C<undef> for these headers in which case they won't be 171(this can be suppressed by using C<undef> for these headers in which case
156sent at all). 172they won't be sent at all).
157 173
158=item timeout => $seconds 174=item timeout => $seconds
159 175
160The time-out to use for various stages - each connect attempt will reset 176The time-out to use for various stages - each connect attempt will reset
161the timeout, as will read or write activity, i.e. this is not an overall 177the timeout, as will read or write activity, i.e. this is not an overall
171C<$scheme> must be either missing, C<http> for HTTP or C<https> for 187C<$scheme> must be either missing, C<http> for HTTP or C<https> for
172HTTPS. 188HTTPS.
173 189
174=item body => $string 190=item body => $string
175 191
176The request body, usually empty. Will be-sent as-is (future versions of 192The request body, usually empty. Will be sent as-is (future versions of
177this module might offer more options). 193this module might offer more options).
178 194
179=item cookie_jar => $hash_ref 195=item cookie_jar => $hash_ref
180 196
181Passing this parameter enables (simplified) cookie-processing, loosely 197Passing this parameter enables (simplified) cookie-processing, loosely
182based on the original netscape specification. 198based on the original netscape specification.
183 199
184The C<$hash_ref> must be an (initially empty) hash reference which will 200The C<$hash_ref> must be an (initially empty) hash reference which
185get updated automatically. It is possible to save the cookie_jar to 201will get updated automatically. It is possible to save the cookie jar
186persistent storage with something like JSON or Storable, but this is not 202to persistent storage with something like JSON or Storable - see the
187recommended, as expiry times are currently being ignored. 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.
188 206
189Note that this cookie implementation is not of very high quality, nor 207Note that this cookie implementation is not meant to be complete. If
190meant to be complete. If you want complete cookie management you have to 208you want complete cookie management you have to do that on your
191do that on your own. C<cookie_jar> is meant as a quick fix to get some 209own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
192cookie-using sites working. Cookies are a privacy disaster, do not use 210working. Cookies are a privacy disaster, do not use them unless required
193them unless required to. 211to.
212
213When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
214headers will be set and handled by this module, otherwise they will be
215left untouched.
194 216
195=item tls_ctx => $scheme | $tls_ctx 217=item tls_ctx => $scheme | $tls_ctx
196 218
197Specifies the AnyEvent::TLS context to be used for https connections. This 219Specifies the AnyEvent::TLS context to be used for https connections. This
198parameter follows the same rules as the C<tls_ctx> parameter to 220parameter follows the same rules as the C<tls_ctx> parameter to
237 259
238This callback is useful, among other things, to quickly reject unwanted 260This callback is useful, among other things, to quickly reject unwanted
239content, which, if it is supposed to be rare, can be faster than first 261content, which, if it is supposed to be rare, can be faster than first
240doing a C<HEAD> request. 262doing a C<HEAD> request.
241 263
264The downside is that cancelling the request makes it impossible to re-use
265the connection. Also, the C<on_header> callback will not receive any
266trailer (headers sent after the response body).
267
242Example: cancel the request unless the content-type is "text/html". 268Example: cancel the request unless the content-type is "text/html".
243 269
244 on_header => sub { 270 on_header => sub {
245 $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ 271 $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/
246 }, 272 },
252string instead of the body data. 278string instead of the body data.
253 279
254It has to return either true (in which case AnyEvent::HTTP will continue), 280It has to return either true (in which case AnyEvent::HTTP will continue),
255or false, in which case AnyEvent::HTTP will cancel the download (and call 281or false, in which case AnyEvent::HTTP will cancel the download (and call
256the completion callback with an error code of C<598>). 282the completion callback with an error code of C<598>).
283
284The downside to cancelling the request is that it makes it impossible to
285re-use the connection.
257 286
258This callback is useful when the data is too large to be held in memory 287This callback is useful when the data is too large to be held in memory
259(so the callback writes it to a file) or when only some information should 288(so the callback writes it to a file) or when only some information should
260be extracted, or when the body should be processed incrementally. 289be extracted, or when the body should be processed incrementally.
261 290
287If you think you need this, first have a look at C<on_body>, to see if 316If you think you need this, first have a look at C<on_body>, to see if
288that doesn't solve your problem in a better way. 317that doesn't solve your problem in a better way.
289 318
290=back 319=back
291 320
292Example: make a simple HTTP GET request for http://www.nethype.de/ 321Example: do a simple HTTP GET request for http://www.nethype.de/ and print
322the response body.
293 323
294 http_request GET => "http://www.nethype.de/", sub { 324 http_request GET => "http://www.nethype.de/", sub {
295 my ($body, $hdr) = @_; 325 my ($body, $hdr) = @_;
296 print "$body\n"; 326 print "$body\n";
297 }; 327 };
298 328
299Example: make a HTTP HEAD request on https://www.google.com/, use a 329Example: do a HTTP HEAD request on https://www.google.com/, use a
300timeout of 30 seconds. 330timeout of 30 seconds.
301 331
302 http_request 332 http_request
303 GET => "https://www.google.com", 333 GET => "https://www.google.com",
304 timeout => 30, 334 timeout => 30,
307 use Data::Dumper; 337 use Data::Dumper;
308 print Dumper $hdr; 338 print Dumper $hdr;
309 } 339 }
310 ; 340 ;
311 341
312Example: make another simple HTTP GET request, but immediately try to 342Example: do another simple HTTP GET request, but immediately try to
313cancel it. 343cancel it.
314 344
315 my $request = http_request GET => "http://www.nethype.de/", sub { 345 my $request = http_request GET => "http://www.nethype.de/", sub {
316 my ($body, $hdr) = @_; 346 my ($body, $hdr) = @_;
317 print "$body\n"; 347 print "$body\n";
349 push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; 379 push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
350 380
351 _slot_schedule $_[0]; 381 _slot_schedule $_[0];
352} 382}
353 383
384#############################################################################
385
386# expire cookies
387sub cookie_jar_expire($;$) {
388 my ($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
417sub cookie_jar_extract($$$$) {
418 my ($jar, $uscheme, $uhost, $upath) = @_;
419
420 $uhost = lc $uhost;
421
422 %$jar = () if $jar->{version} != 1;
423
424 my @cookies;
425
426 while (my ($chost, $paths) = each %$jar) {
427 next unless ref $paths;
428
429 if ($chost =~ /^\./) {
430 next unless $chost eq substr $uhost, -length $chost;
431 } elsif ($chost =~ /\./) {
432 next unless $chost eq $uhost;
433 } else {
434 next;
435 }
436
437 while (my ($cpath, $cookies) = each %$paths) {
438 next unless $cpath eq substr $upath, 0, length $cpath;
439
440 while (my ($cookie, $kv) = each %$cookies) {
441 next if $uscheme ne "https" && exists $kv->{secure};
442
443 if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
444 delete $cookies->{$cookie};
445 next;
446 }
447
448 my $value = $kv->{value};
449
450 if ($value =~ /[=;,[:space:]]/) {
451 $value =~ s/([\\"])/\\$1/g;
452 $value = "\"$value\"";
453 }
454
455 push @cookies, "$cookie=$value";
456 }
457 }
458 }
459
460 \@cookies
461}
462
463# parse set_cookie header into jar
464sub cookie_jar_set_cookie($$$$) {
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
542# continue to parse $_ for headers and place them into the arg
543sub parse_hdr() {
544 my %hdr;
545
546 # things seen, not parsed:
547 # p3pP="NON CUR OTPi OUR NOR UNI"
548
549 $hdr{lc $1} .= ",$2"
550 while /\G
551 ([^:\000-\037]*):
552 [\011\040]*
553 ((?: [^\012]+ | \012[\011\040] )*)
554 \012
555 /gxc;
556
557 /\G$/
558 or return;
559
560 # remove the "," prefix we added to all headers above
561 substr $_, 0, 1, ""
562 for values %hdr;
563
564 \%hdr
565}
566
354our $qr_nlnl = qr{(?<![^\012])\015?\012}; 567our $qr_nlnl = qr{(?<![^\012])\015?\012};
355 568
356our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; 569our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
357our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; 570our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
358 571
377 my @pseudo = (URL => $url); 590 my @pseudo = (URL => $url);
378 push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; 591 push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
379 592
380 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; 593 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
381 594
382 return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo }) 595 return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
383 if $recurse < 0; 596 if $recurse < 0;
384 597
385 my $proxy = $arg{proxy} || $PROXY; 598 my $proxy = $arg{proxy} || $PROXY;
386 my $timeout = $arg{timeout} || $TIMEOUT; 599 my $timeout = $arg{timeout} || $TIMEOUT;
387 600
390 603
391 $uscheme = lc $uscheme; 604 $uscheme = lc $uscheme;
392 605
393 my $uport = $uscheme eq "http" ? 80 606 my $uport = $uscheme eq "http" ? 80
394 : $uscheme eq "https" ? 443 607 : $uscheme eq "https" ? 443
395 : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo }); 608 : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
396 609
397 $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 610 $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
398 or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo }); 611 or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
399 612
400 my $uhost = $1; 613 my $uhost = $1;
401 $uport = $2 if defined $2; 614 $uport = $2 if defined $2;
402 615
403 $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" 616 $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
408 621
409 $upath =~ s%^/?%/%; 622 $upath =~ s%^/?%/%;
410 623
411 # cookie processing 624 # cookie processing
412 if (my $jar = $arg{cookie_jar}) { 625 if (my $jar = $arg{cookie_jar}) {
413 %$jar = () if $jar->{version} != 1; 626 my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
414 627
415 my @cookie;
416
417 while (my ($chost, $v) = each %$jar) {
418 if ($chost =~ /^\./) {
419 next unless $chost eq substr $uhost, -length $chost;
420 } elsif ($chost =~ /\./) {
421 next unless $chost eq $uhost;
422 } else {
423 next;
424 }
425
426 while (my ($cpath, $v) = each %$v) {
427 next unless $cpath eq substr $upath, 0, length $cpath;
428
429 while (my ($k, $v) = each %$v) {
430 next if $uscheme ne "https" && exists $v->{secure};
431 my $value = $v->{value};
432 $value =~ s/([\\"])/\\$1/g;
433 push @cookie, "$k=\"$value\"";
434 }
435 }
436 }
437
438 $hdr{cookie} = join "; ", @cookie 628 $hdr{cookie} = join "; ", @$cookies
439 if @cookie; 629 if @$cookies;
440 } 630 }
441 631
442 my ($rhost, $rport, $rscheme, $rpath); # request host, port, path 632 my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
443 633
444 if ($proxy) { 634 if ($proxy) {
452 } else { 642 } else {
453 ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); 643 ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
454 } 644 }
455 645
456 # leave out fragment and query string, just a heuristic 646 # leave out fragment and query string, just a heuristic
457 $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; 647 $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
458 $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; 648 $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
459 649
460 $hdr{"content-length"} = length $arg{body} 650 $hdr{"content-length"} = length $arg{body}
461 if length $arg{body} || $method ne "GET"; 651 if length $arg{body} || $method ne "GET";
462 652
653 $hdr{connection} = "close TE"; #1.1
654 $hdr{te} = "trailers" unless exists $hdr{te}; #1.1
655
463 my %state = (connect_guard => 1); 656 my %state = (connect_guard => 1);
464 657
465 _get_slot $uhost, sub { 658 _get_slot $uhost, sub {
466 $state{slot_guard} = shift; 659 $state{slot_guard} = shift;
467 660
468 return unless $state{connect_guard}; 661 return unless $state{connect_guard};
469 662
470 my $tcp_connect = $arg{tcp_connect} 663 my $ae_error = 595; # connecting
471 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
472 664
473 $state{connect_guard} = $tcp_connect->( 665 # handle actual, non-tunneled, request
474 $rhost, 666 my $handle_actual_request = sub {
475 $rport, 667 $ae_error = 596; # request phase
476 sub { 668
477 $state{fh} = shift 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,
478 or do { 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";
479 my $err = "$!"; 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};
480 %state = (); 751 %state = ();
481 return $cb->(undef, { Status => 599, Reason => $err, @pseudo }); 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 }
482 }; 847 };
483 848
484 pop; # free memory, save a tree 849 $_[0]->push_read (line => $state{read_chunk});
485 850
851 } elsif ($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
893 my $connect_cb = sub {
894 $state{fh} = shift
895 or do {
896 my $err = "$!";
897 %state = ();
898 return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
899 };
900
486 return unless delete $state{connect_guard}; 901 return unless delete $state{connect_guard};
487 902
488 # get handle 903 # get handle
489 $state{handle} = new AnyEvent::Handle 904 $state{handle} = new AnyEvent::Handle
490 fh => $state{fh}, 905 fh => $state{fh},
491 peername => $rhost, 906 peername => $rhost,
492 tls_ctx => $arg{tls_ctx}, 907 tls_ctx => $arg{tls_ctx},
493 # these need to be reconfigured on keepalive handles 908 # these need to be reconfigured on keepalive handles
494 timeout => $timeout, 909 timeout => $timeout,
495 on_error => sub { 910 on_error => sub {
496 %state = (); 911 %state = ();
497 $cb->(undef, { Status => 599, Reason => $_[2], @pseudo }); 912 $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
498 }, 913 },
499 on_eof => sub { 914 on_eof => sub {
500 %state = (); 915 %state = ();
501 $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo }); 916 $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
502 }, 917 },
503 ; 918 ;
504 919
505 # limit the number of persistent connections 920 # limit the number of persistent connections
506 # keepalive not yet supported 921 # keepalive not yet supported
507# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { 922# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
508# ++$KA_COUNT{$_[1]}; 923# ++$KA_COUNT{$_[1]};
509# $state{handle}{ka_count_guard} = AnyEvent::Util::guard { 924# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
510# --$KA_COUNT{$_[1]} 925# --$KA_COUNT{$_[1]}
511# }; 926# };
512# $hdr{connection} = "keep-alive"; 927# $hdr{connection} = "keep-alive";
513# } else {
514 delete $hdr{connection};
515# } 928# }
516 929
517 $state{handle}->starttls ("connect") if $rscheme eq "https"; 930 $state{handle}->starttls ("connect") if $rscheme eq "https";
518 931
519 # handle actual, non-tunneled, request
520 my $handle_actual_request = sub {
521 $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
522
523 # send request
524 $state{handle}->push_write (
525 "$method $rpath HTTP/1.0\015\012"
526 . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
527 . "\015\012"
528 . (delete $arg{body})
529 );
530
531 # return if error occured during push_write()
532 return unless %state;
533
534 %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
535
536 # status line and headers
537 $state{handle}->push_read (line => $qr_nlnl, sub {
538 for ("$_[1]") {
539 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
540
541 /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
542 or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
543
544 push @pseudo,
545 HTTPVersion => $1,
546 Status => $2,
547 Reason => $3,
548 ;
549
550 # things seen, not parsed:
551 # p3pP="NON CUR OTPi OUR NOR UNI"
552
553 $hdr{lc $1} .= ",$2"
554 while /\G
555 ([^:\000-\037]*):
556 [\011\040]*
557 ((?: [^\012]+ | \012[\011\040] )*)
558 \012
559 /gxc;
560
561 /\G$/
562 or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
563 }
564
565 # remove the "," prefix we added to all headers above
566 substr $_, 0, 1, ""
567 for values %hdr;
568
569 # patch in all pseudo headers
570 %hdr = (%hdr, @pseudo);
571
572 # redirect handling
573 # microsoft and other shitheads don't give a shit for following standards,
574 # try to support some common forms of broken Location headers.
575 if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
576 $hdr{location} =~ s/^\.\/+//;
577
578 my $url = "$rscheme://$uhost:$uport";
579
580 unless ($hdr{location} =~ s/^\///) {
581 $url .= $upath;
582 $url =~ s/\/[^\/]*$//;
583 }
584
585 $hdr{location} = "$url/$hdr{location}";
586 }
587
588 my $redirect;
589
590 if ($recurse) {
591 my $status = $hdr{Status};
592
593 # industry standard is to redirect POST as GET for
594 # 301, 302 and 303, in contrast to http/1.0 and 1.1.
595 # also, the UA should ask the user for 301 and 307 and POST,
596 # industry standard seems to be to simply follow.
597 # we go with the industry standard.
598 if ($status == 301 or $status == 302 or $status == 303) {
599 # HTTP/1.1 is unclear on how to mutate the method
600 $method = "GET" unless $method eq "HEAD";
601 $redirect = 1;
602 } elsif ($status == 307) {
603 $redirect = 1;
604 }
605 }
606
607 my $finish = sub {
608 $state{handle}->destroy if $state{handle};
609 %state = ();
610
611 # set-cookie processing
612 if ($arg{cookie_jar}) {
613 for ($_[1]{"set-cookie"}) {
614 # parse NAME=VALUE
615 my @kv;
616
617 while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
618 my $name = $1;
619 my $value = $3;
620
621 unless ($value) {
622 $value = $2;
623 $value =~ s/\\(.)/$1/gs;
624 }
625
626 push @kv, $name => $value;
627
628 last unless /\G\s*;/gc;
629 }
630
631 last unless @kv;
632
633 my $name = shift @kv;
634 my %kv = (value => shift @kv, @kv);
635
636 my $cdom;
637 my $cpath = (delete $kv{path}) || "/";
638
639 if (exists $kv{domain}) {
640 $cdom = delete $kv{domain};
641
642 $cdom =~ s/^\.?/./; # make sure it starts with a "."
643
644 next if $cdom =~ /\.$/;
645
646 # this is not rfc-like and not netscape-like. go figure.
647 my $ndots = $cdom =~ y/.//;
648 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
649 } else {
650 $cdom = $uhost;
651 }
652
653 # store it
654 $arg{cookie_jar}{version} = 1;
655 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
656
657 redo if /\G\s*,/gc;
658 }
659 }
660
661 if ($redirect && exists $hdr{location}) {
662 # we ignore any errors, as it is very common to receive
663 # Content-Length != 0 but no actual body
664 # we also access %hdr, as $_[1] might be an erro
665 http_request (
666 $method => $hdr{location},
667 %arg,
668 recurse => $recurse - 1,
669 Redirect => \@_,
670 $cb);
671 } else {
672 $cb->($_[0], $_[1]);
673 }
674 };
675
676 my $len = $hdr{"content-length"};
677
678 if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
679 $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
680 } elsif (
681 $hdr{Status} =~ /^(?:1..|[23]04)$/
682 or $method eq "HEAD"
683 or (defined $len && !$len)
684 ) {
685 # no body
686 $finish->("", \%hdr);
687 } else {
688 # body handling, four different code paths
689 # for want_body_handle, on_body (2x), normal (2x)
690 # we might read too much here, but it does not matter yet (no pers. connections)
691 if (!$redirect && $arg{want_body_handle}) {
692 $_[0]->on_eof (undef);
693 $_[0]->on_error (undef);
694 $_[0]->on_read (undef);
695
696 $finish->(delete $state{handle}, \%hdr);
697
698 } elsif ($arg{on_body}) {
699 $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
700 if ($len) {
701 $_[0]->on_eof (undef);
702 $_[0]->on_read (sub {
703 $len -= length $_[0]{rbuf};
704
705 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
706 or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
707
708 $len > 0
709 or $finish->("", \%hdr);
710 });
711 } else {
712 $_[0]->on_eof (sub {
713 $finish->("", \%hdr);
714 });
715 $_[0]->on_read (sub {
716 $arg{on_body}(delete $_[0]{rbuf}, \%hdr)
717 or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
718 });
719 }
720 } else {
721 $_[0]->on_eof (undef);
722
723 if ($len) {
724 $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
725 $_[0]->on_read (sub {
726 $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
727 if $len <= length $_[0]{rbuf};
728 });
729 } else {
730 $_[0]->on_error (sub {
731 ($! == Errno::EPIPE || !$!)
732 ? $finish->(delete $_[0]{rbuf}, \%hdr)
733 : $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
734 });
735 $_[0]->on_read (sub { });
736 }
737 }
738 }
739 });
740 };
741
742 # now handle proxy-CONNECT method 932 # now handle proxy-CONNECT method
743 if ($proxy && $uscheme eq "https") { 933 if ($proxy && $uscheme eq "https") {
744 # oh dear, we have to wrap it into a connect request 934 # oh dear, we have to wrap it into a connect request
745 935
746 # maybe re-use $uauthority with patched port? 936 # maybe re-use $uauthority with patched port?
747 $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); 937 $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
748 $state{handle}->push_read (line => $qr_nlnl, sub { 938 $state{handle}->push_read (line => $qr_nlnl, sub {
749 $_[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
750 or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo })); 940 or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
751 941
752 if ($2 == 200) { 942 if ($2 == 200) {
753 $rpath = $upath; 943 $rpath = $upath;
754 &$handle_actual_request; 944 $handle_actual_request->();
755 } else { 945 } else {
756 %state = (); 946 %state = ();
757 $cb->(undef, { Status => $2, Reason => $3, @pseudo }); 947 $cb->(undef, { @pseudo, Status => $2, Reason => $3 });
758 }
759 }); 948 }
760 } else {
761 &$handle_actual_request;
762 } 949 });
763 950 } else {
951 $handle_actual_request->();
764 }, 952 }
765 $arg{on_prepare} || sub { $timeout }
766 ); 953 };
954
955 my $tcp_connect = $arg{tcp_connect}
956 || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
957
958 $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
767 }; 959 };
768 960
769 defined wantarray && AnyEvent::Util::guard { %state = () } 961 defined wantarray && AnyEvent::Util::guard { %state = () }
770} 962}
771 963
806string of the form C<http://host:port> (optionally C<https:...>), croaks 998string of the form C<http://host:port> (optionally C<https:...>), croaks
807otherwise. 999otherwise.
808 1000
809To clear an already-set proxy, use C<undef>. 1001To clear an already-set proxy, use C<undef>.
810 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
1042=item $date = AnyEvent::HTTP::format_date $timestamp
1043
1044Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
1045Date (RFC 2616).
1046
1047=item $timestamp = AnyEvent::HTTP::parse_date $date
1048
1049Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
1050bunch of minor variations of those, and returns the corresponding POSIX
1051timestamp, or C<undef> if the date cannot be parsed.
1052
811=item $AnyEvent::HTTP::MAX_RECURSE 1053=item $AnyEvent::HTTP::MAX_RECURSE
812 1054
813The default value for the C<recurse> request parameter (default: C<10>). 1055The default value for the C<recurse> request parameter (default: C<10>).
814 1056
815=item $AnyEvent::HTTP::USERAGENT 1057=item $AnyEvent::HTTP::USERAGENT
833connections. This number of can be useful for load-leveling. 1075connections. This number of can be useful for load-leveling.
834 1076
835=back 1077=back
836 1078
837=cut 1079=cut
1080
1081our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
1082our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
1083
1084sub format_date($) {
1085 my ($time) = @_;
1086
1087 # RFC 822/1123 format
1088 my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
1089
1090 sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
1091 $weekday[$wday], $mday, $month[$mon], $year + 1900,
1092 $H, $M, $S;
1093}
1094
1095sub parse_date($) {
1096 my ($date) = @_;
1097
1098 my ($d, $m, $y, $H, $M, $S);
1099
1100 if ($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$/) {
1101 # RFC 822/1123, required by RFC 2616 (with " ")
1102 # cookie dates (with "-")
1103
1104 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
1105
1106 } elsif ($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$/) {
1107 # RFC 850
1108 ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
1109
1110 } elsif ($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])$/) {
1111 # ISO C's asctime
1112 ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
1113 }
1114 # other formats fail in the loop below
1115
1116 for (0..11) {
1117 if ($m eq $month[$_]) {
1118 require Time::Local;
1119 return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
1120 }
1121 }
1122
1123 undef
1124}
838 1125
839sub set_proxy($) { 1126sub set_proxy($) {
840 if (length $_[0]) { 1127 if (length $_[0]) {
841 $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix 1128 $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
842 or Carp::croak "$_[0]: invalid proxy URL"; 1129 or Carp::croak "$_[0]: invalid proxy URL";

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines