[ViewVC] Diff of: cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.80 by root, Sat Jan 1 21:51:22 2011 UTC vs.
Revision 1.102 by root, Sat Feb 19 06:46:14 2011 UTC

…		…
15	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
16	run a supported event loop.	16	run a supported event loop.
17		17
18	This module implements a simple, stateless and non-blocking HTTP	18	This module implements a simple, stateless and non-blocking HTTP
19	client. It supports GET, POST and other request methods, cookies and more,	19	client. It supports GET, POST and other request methods, cookies and more,
20	all on a very low level. It can follow redirects supports proxies and	20	all on a very low level. It can follow redirects, supports proxies, and
21	automatically limits the number of connections to the values specified in	21	automatically limits the number of connections to the values specified in
22	the RFC.	22	the RFC.
23		23
24	It should generally be a "good client" that is enough for most HTTP	24	It should generally be a "good client" that is enough for most HTTP
25	tasks. Simple tasks should be simple, but complex tasks should still be	25	tasks. Simple tasks should be simple, but complex tasks should still be
…		…
36		36
37	=cut	37	=cut
38		38
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use common::sense;
42	no warnings;
43		42
44	use Errno ();	43	use Errno ();
45		44
46	use AnyEvent 5.0 ();	45	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	46	use AnyEvent::Util ();
48	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
49		48
50	use base Exporter::;	49	use base Exporter::;
51		50
52	our $VERSION = '1.5';	51	our $VERSION = '2.04';
53		52
54	our @EXPORT = qw(http_get http_post http_head http_request);	53	our @EXPORT = qw(http_get http_post http_head http_request);
55		54
56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	55	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
57	our $MAX_RECURSE = 10;	56	our $MAX_RECURSE = 10;
58	our $MAX_PERSISTENT = 8;
59	our $PERSISTENT_TIMEOUT = 2;	57	our $PERSISTENT_TIMEOUT = 3;
60	our $TIMEOUT = 300;	58	our $TIMEOUT = 300;
61		59	our $MAX_PER_HOST = 4; # changing this is evil
62	# changing these is evil
63	our $MAX_PERSISTENT_PER_HOST = 0;
64	our $MAX_PER_HOST = 4;
65		60
66	our $PROXY;	61	our $PROXY;
67	our $ACTIVE = 0;	62	our $ACTIVE = 0;
68		63
69	my %KA_COUNT; # number of open keep-alive connections per host	64	my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array
70	my %CO_SLOT; # number of open connections, and wait queue, per host	65	my %CO_SLOT; # number of open connections, and wait queue, per host
71		66
72	=item http_get $url, key => value..., $cb->($data, $headers)	67	=item http_get $url, key => value..., $cb->($data, $headers)
73		68
74	Executes an HTTP-GET request. See the http_request function for details on	69	Executes an HTTP-GET request. See the http_request function for details on
…		…
170	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and	165	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
171	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>	166	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
172	(this can be suppressed by using C<undef> for these headers in which case	167	(this can be suppressed by using C<undef> for these headers in which case
173	they won't be sent at all).	168	they won't be sent at all).
174		169
		170	You really should provide your own C<User-Agent:> header value that is
		171	appropriate for your program - I wouldn't be surprised if the default
		172	AnyEvent string gets blocked by webservers sooner or later.
		173
175	=item timeout => $seconds	174	=item timeout => $seconds
176		175
177	The time-out to use for various stages - each connect attempt will reset	176	The time-out to use for various stages - each connect attempt will reset
178	the timeout, as will read or write activity, i.e. this is not an overall	177	the timeout, as will read or write activity, i.e. this is not an overall
179	timeout.	178	timeout.
180		179
181	Default timeout is 5 minutes.	180	Default timeout is 5 minutes.
182		181
183	=item proxy => [$host, $port[, $scheme]] or undef	182	=item proxy => [$host, $port[, $scheme]] or undef
184		183
185	Use the given http proxy for all requests. If not specified, then the	184	Use the given http proxy for all requests, or no proxy if C<undef> is
186	default proxy (as specified by C<$ENV{http_proxy}>) is used.	185	used.
187		186
188	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	187	C<$scheme> must be either missing or must be C<http> for HTTP.
189	HTTPS.	188
		189	If not specified, then the default proxy is used (see
		190	C<AnyEvent::HTTP::set_proxy>).
190		191
191	=item body => $string	192	=item body => $string
192		193
193	The request body, usually empty. Will be sent as-is (future versions of	194	The request body, usually empty. Will be sent as-is (future versions of
194	this module might offer more options).	195	this module might offer more options).
…		…
224	verification, highest compatibility) and high-security (CA and common-name	225	verification, highest compatibility) and high-security (CA and common-name
225	verification) TLS context.	226	verification) TLS context.
226		227
227	The default for this option is C<low>, which could be interpreted as "give	228	The default for this option is C<low>, which could be interpreted as "give
228	me the page, no matter what".	229	me the page, no matter what".
		230
		231	See also the C<sessionid> parameter.
		232
		233	=item session => $string
		234
		235	The module might reuse connections to the same host internally. Sometimes
		236	(e.g. when using TLS), you do not want to reuse connections from other
		237	sessions. This can be achieved by setting this parameter to some unique
		238	ID (such as the address of an object storing your state data, or the TLS
		239	context) - only connections using the same unique ID will be reused.
229		240
230	=item on_prepare => $callback->($fh)	241	=item on_prepare => $callback->($fh)
231		242
232	In rare cases you need to "tune" the socket before it is used to	243	In rare cases you need to "tune" the socket before it is used to
233	connect (for exmaple, to bind it on a given IP address). This parameter	244	connect (for exmaple, to bind it on a given IP address). This parameter
…		…
303	called. Instead of the C<$body> argument containing the body data, the	314	called. Instead of the C<$body> argument containing the body data, the
304	callback will receive the L<AnyEvent::Handle> object associated with the	315	callback will receive the L<AnyEvent::Handle> object associated with the
305	connection. In error cases, C<undef> will be passed. When there is no body	316	connection. In error cases, C<undef> will be passed. When there is no body
306	(e.g. status C<304>), the empty string will be passed.	317	(e.g. status C<304>), the empty string will be passed.
307		318
308	The handle object might or might not be in TLS mode, might be connected to	319	The handle object might or might not be in TLS mode, might be connected
309	a proxy, be a persistent connection etc., and configured in unspecified	320	to a proxy, be a persistent connection, use chunked transfer encoding
310	ways. The user is responsible for this handle (it will not be used by this	321	etc., and configured in unspecified ways. The user is responsible for this
311	module anymore).	322	handle (it will not be used by this module anymore).
312		323
313	This is useful with some push-type services, where, after the initial	324	This is useful with some push-type services, where, after the initial
314	headers, an interactive protocol is used (typical example would be the	325	headers, an interactive protocol is used (typical example would be the
315	push-style twitter API which starts a JSON/XML stream).	326	push-style twitter API which starts a JSON/XML stream).
316		327
317	If you think you need this, first have a look at C<on_body>, to see if	328	If you think you need this, first have a look at C<on_body>, to see if
318	that doesn't solve your problem in a better way.	329	that doesn't solve your problem in a better way.
		330
		331	=item persistent => $boolean
		332
		333	Try to create/reuse a persistent connection. When this flag is set
		334	(default: true for idempotent requests, false for all others), then
		335	C<http_request> tries to re-use an existing (previously-created)
		336	persistent connection to the host and, failing that, tries to create a new
		337	one.
		338
		339	Requests failing in certain ways will be automatically retried once, which
		340	is dangerous for non-idempotent requests, which is why it defaults to off
		341	for them. The reason for this is because the bozos who designed HTTP/1.1
		342	made it impossible to distinguish between a fatal error and a normal
		343	connection timeout, so you never know whether there was a problem with
		344	your request or not.
		345
		346	When reusing an existent connection, many parameters (such as TLS context)
		347	will be ignored. See the C<session> parameter for a workaround.
		348
		349	=item keepalive => $boolean
		350
		351	Only used when C<persistent> is also true. This parameter decides whether
		352	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		353	(as opposed to only a HTTP/1.1 persistent connection).
		354
		355	The default is true, except when using a proxy, in which case it defaults
		356	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		357
		358	=item handle_params => { key => value ... }
		359
		360	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		361	constructor that is called - not all requests will create a handle, and
		362	sometimes more than one is created, so this parameter is only good for
		363	setting hints.
		364
		365	Example: set the maximum read size to 4096, to potentially conserve memory
		366	at the cost of speed.
		367
		368	handle_params => {
		369	max_read_size => 4096,
		370	},
319		371
320	=back	372	=back
321		373
322	Example: do a simple HTTP GET request for http://www.nethype.de/ and print	374	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
323	the response body.	375	the response body.
…		…
330	Example: do a HTTP HEAD request on https://www.google.com/, use a	382	Example: do a HTTP HEAD request on https://www.google.com/, use a
331	timeout of 30 seconds.	383	timeout of 30 seconds.
332		384
333	http_request	385	http_request
334	GET => "https://www.google.com",	386	GET => "https://www.google.com",
		387	headers => { "user-agent" => "MySearchClient 1.0" },
335	timeout => 30,	388	timeout => 30,
336	sub {	389	sub {
337	my ($body, $hdr) = @_;	390	my ($body, $hdr) = @_;
338	use Data::Dumper;	391	use Data::Dumper;
339	print Dumper $hdr;	392	print Dumper $hdr;
…		…
349	};	402	};
350		403
351	undef $request;	404	undef $request;
352		405
353	=cut	406	=cut
		407
		408	#############################################################################
		409	# wait queue/slots
354		410
355	sub _slot_schedule;	411	sub _slot_schedule;
356	sub _slot_schedule($) {	412	sub _slot_schedule($) {
357	my $host = shift;	413	my $host = shift;
358		414
…		…
381		437
382	_slot_schedule $_[0];	438	_slot_schedule $_[0];
383	}	439	}
384		440
385	#############################################################################	441	#############################################################################
		442	# cookie handling
386		443
387	# expire cookies	444	# expire cookies
388	sub cookie_jar_expire($;$) {	445	sub cookie_jar_expire($;$) {
389	my ($jar, $session_end) = @_;	446	my ($jar, $session_end) = @_;
390		447
…		…
414	}	471	}
415	}	472	}
416		473
417	# extract cookies from jar	474	# extract cookies from jar
418	sub cookie_jar_extract($$$$) {	475	sub cookie_jar_extract($$$$) {
419	my ($jar, $uscheme, $uhost, $upath) = @_;	476	my ($jar, $scheme, $host, $path) = @_;
420		477
421	%$jar = () if $jar->{version} != 1;	478	%$jar = () if $jar->{version} != 1;
422		479
423	my @cookies;	480	my @cookies;
424		481
425	while (my ($chost, $paths) = each %$jar) {	482	while (my ($chost, $paths) = each %$jar) {
426	next unless ref $paths;	483	next unless ref $paths;
427		484
428	if ($chost =~ /^\./) {	485	if ($chost =~ /^\./) {
429	next unless $chost eq substr $uhost, -length $chost;	486	next unless $chost eq substr $host, -length $chost;
430	} elsif ($chost =~ /\./) {	487	} elsif ($chost =~ /\./) {
431	next unless $chost eq $uhost;	488	next unless $chost eq $host;
432	} else {	489	} else {
433	next;	490	next;
434	}	491	}
435		492
436	while (my ($cpath, $cookies) = each %$paths) {	493	while (my ($cpath, $cookies) = each %$paths) {
437	next unless $cpath eq substr $upath, 0, length $cpath;	494	next unless $cpath eq substr $path, 0, length $cpath;
438		495
439	while (my ($cookie, $kv) = each %$cookies) {	496	while (my ($cookie, $kv) = each %$cookies) {
440	next if $uscheme ne "https" && exists $kv->{secure};	497	next if $scheme ne "https" && exists $kv->{secure};
441		498
442	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {	499	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
443	delete $cookies->{$cookie};	500	delete $cookies->{$cookie};
444	next;	501	next;
445	}	502	}
…		…
459	\@cookies	516	\@cookies
460	}	517	}
461		518
462	# parse set_cookie header into jar	519	# parse set_cookie header into jar
463	sub cookie_jar_set_cookie($$$$) {	520	sub cookie_jar_set_cookie($$$$) {
464	my ($jar, $set_cookie, $uhost, $date) = @_;	521	my ($jar, $set_cookie, $host, $date) = @_;
465		522
466	my $anow = int AE::now;	523	my $anow = int AE::now;
467	my $snow; # server-now	524	my $snow; # server-now
468		525
469	for ($set_cookie) {	526	for ($set_cookie) {
…		…
475	while (	532	while (
476	m{	533	m{
477	\G\s*	534	\G\s*
478	(?:	535	(?:
479	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)	536	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
480	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )	537	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^;,[:space:]]) ) )?
481	)	538	)
482	}gcxsi	539	}gcxsi
483	) {	540	) {
484	my $name = $2;	541	my $name = $2;
485	my $value = $4;	542	my $value = $4;
486		543
487	unless (defined $name) {	544	if (defined $1) {
488	# expires	545	# expires
489	$name = "expires";	546	$name = "expires";
490	$value = $1;	547	$value = $1;
491	} elsif (!defined $value) {	548	} elsif (defined $3) {
492	# quoted	549	# quoted
493	$value = $3;	550	$value = $3;
494	$value =~ s/\\(.)/$1/gs;	551	$value =~ s/\\(.)/$1/gs;
495	}	552	}
496		553
497	push @kv, lc $name, $value;	554	push @kv, @kv ? lc $name : $name, $value;
498		555
499	last unless /\G\s*;/gc;	556	last unless /\G\s*;/gc;
500	}	557	}
501		558
502	last unless @kv;	559	last unless @kv;
…		…
525		582
526	# this is not rfc-like and not netscape-like. go figure.	583	# this is not rfc-like and not netscape-like. go figure.
527	my $ndots = $cdom =~ y/.//;	584	my $ndots = $cdom =~ y/.//;
528	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	585	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
529	} else {	586	} else {
530	$cdom = $uhost;	587	$cdom = $host;
531	}	588	}
532		589
533	# store it	590	# store it
534	$jar->{version} = 1;	591	$jar->{version} = 1;
535	$jar->{$cdom}{$cpath}{$name} = \%kv;	592	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
536		593
537	redo if /\G\s*,/gc;	594	redo if /\G\s*,/gc;
538	}	595	}
539	}	596	}
540		597
		598	#############################################################################
		599	# keepalive/persistent connection cache
		600
		601	# fetch a connection from the keepalive cache
		602	sub ka_fetch($) {
		603	my $ka_key = shift;
		604
		605	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		606	delete $KA_CACHE{$ka_key}
		607	unless @{ $KA_CACHE{$ka_key} };
		608
		609	$hdl
		610	}
		611
		612	sub ka_store($$) {
		613	my ($ka_key, $hdl) = @_;
		614
		615	my $kaa = $KA_CACHE{$ka_key} \|\|= [];
		616
		617	my $destroy = sub {
		618	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		619
		620	$hdl->destroy;
		621
		622	@ka
		623	? $KA_CACHE{$ka_key} = \@ka
		624	: delete $KA_CACHE{$ka_key};
		625	};
		626
		627	# on error etc., destroy
		628	$hdl->on_error ($destroy);
		629	$hdl->on_eof ($destroy);
		630	$hdl->on_read ($destroy);
		631	$hdl->timeout ($PERSISTENT_TIMEOUT);
		632
		633	push @$kaa, $hdl;
		634	shift @$kaa while @$kaa > $MAX_PER_HOST;
		635	}
		636
		637	#############################################################################
		638	# utilities
		639
541	# continue to parse $_ for headers and place them into the arg	640	# continue to parse $_ for headers and place them into the arg
542	sub parse_hdr() {	641	sub _parse_hdr() {
543	my %hdr;	642	my %hdr;
544		643
545	# things seen, not parsed:	644	# things seen, not parsed:
546	# p3pP="NON CUR OTPi OUR NOR UNI"	645	# p3pP="NON CUR OTPi OUR NOR UNI"
547		646
…		…
561	for values %hdr;	660	for values %hdr;
562		661
563	\%hdr	662	\%hdr
564	}	663	}
565		664
		665	#############################################################################
		666	# http_get
		667
566	our $qr_nlnl = qr{(?<![^\012])\015?\012};	668	our $qr_nlnl = qr{(?<![^\012])\015?\012};
567		669
568	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	670	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
569	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	671	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		672
		673	# maybe it should just become a normal object :/
		674
		675	sub _destroy_state(\%) {
		676	my ($state) = @_;
		677
		678	$state->{handle}->destroy if $state->{handle};
		679	%$state = ();
		680	}
		681
		682	sub _error(\%$$) {
		683	my ($state, $cb, $hdr) = @_;
		684
		685	&_destroy_state ($state);
		686
		687	$cb->(undef, $hdr);
		688	()
		689	}
570		690
571	sub http_request($$@) {	691	sub http_request($$@) {
572	my $cb = pop;	692	my $cb = pop;
573	my ($method, $url, %arg) = @_;	693	my ($method, $url, %arg) = @_;
574		694
…		…
592	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	712	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
593		713
594	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })	714	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
595	if $recurse < 0;	715	if $recurse < 0;
596		716
597	my $proxy = $arg{proxy} \|\| $PROXY;	717	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
598	my $timeout = $arg{timeout} \|\| $TIMEOUT;	718	my $timeout = $arg{timeout} \|\| $TIMEOUT;
599		719
600	my ($uscheme, $uauthority, $upath, $query, $fragment) =	720	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
601	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;	721	$url =~ m\|^([^:]+):(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?$\|;
602		722
603	$uscheme = lc $uscheme;	723	$uscheme = lc $uscheme;
604		724
605	my $uport = $uscheme eq "http" ? 80	725	my $uport = $uscheme eq "http" ? 80
606	: $uscheme eq "https" ? 443	726	: $uscheme eq "https" ? 443
607	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });	727	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
608		728
609	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	729	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
610	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	730	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
611		731
612	my $uhost = $1;	732	my $uhost = lc $1;
613	$uport = $2 if defined $2;	733	$uport = $2 if defined $2;
614		734
615	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	735	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
616	unless exists $hdr{host};	736	unless exists $hdr{host};
617		737
…		…
636	$rscheme = "http" unless defined $rscheme;	756	$rscheme = "http" unless defined $rscheme;
637		757
638	# don't support https requests over https-proxy transport,	758	# don't support https requests over https-proxy transport,
639	# can't be done with tls as spec'ed, unless you double-encrypt.	759	# can't be done with tls as spec'ed, unless you double-encrypt.
640	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	760	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		761
		762	$rhost = lc $rhost;
		763	$rscheme = lc $rscheme;
641	} else {	764	} else {
642	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	765	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
643	}	766	}
644		767
645	# leave out fragment and query string, just a heuristic	768	# leave out fragment and query string, just a heuristic
…		…
647	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};	770	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
648		771
649	$hdr{"content-length"} = length $arg{body}	772	$hdr{"content-length"} = length $arg{body}
650	if length $arg{body} \|\| $method ne "GET";	773	if length $arg{body} \|\| $method ne "GET";
651		774
652	$hdr{connection} = "close TE"; #1.1	775	my $idempotent = $method =~ /^(?:GET\|HEAD\|PUT\|DELETE\|OPTIONS\|TRACE)$/;
		776
		777	# default value for keepalive is true iff the request is for an idempotent method
		778	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : $idempotent;
		779	my $keepalive10 = exists $arg{keepalive10} ? $arg{keepalive10} : !$proxy;
		780	my $keptalive; # true if this is actually a recycled connection
		781
		782	# the key to use in the keepalive cache
		783	my $ka_key = "$uhost\x00$arg{sessionid}";
		784
		785	$hdr{connection} = ($keepalive ? $keepalive10 ? "keep-alive " : "" : "close ") . "Te"; #1.1
653	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1	786	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
654		787
655	my %state = (connect_guard => 1);	788	my %state = (connect_guard => 1);
		789
		790	my $ae_error = 595; # connecting
		791
		792	# handle actual, non-tunneled, request
		793	my $handle_actual_request = sub {
		794	$ae_error = 596; # request phase
		795
		796	my $hdl = $state{handle};
		797
		798	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		799
		800	# send request
		801	$hdl->push_write (
		802	"$method $rpath HTTP/1.1\015\012"
		803	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		804	. "\015\012"
		805	. (delete $arg{body})
		806	);
		807
		808	# return if error occured during push_write()
		809	return unless %state;
		810
		811	# reduce memory usage, save a kitten, also re-use it for the response headers.
		812	%hdr = ();
		813
		814	# status line and headers
		815	$state{read_response} = sub {
		816	return unless %state;
		817
		818	for ("$_[1]") {
		819	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		820
		821	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		822	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		823
		824	# 100 Continue handling
		825	# should not happen as we don't send expect: 100-continue,
		826	# but we handle it just in case.
		827	# since we send the request body regardless, if we get an error
		828	# we are out of-sync, which we currently do NOT handle correctly.
		829	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		830	if $2 eq 100;
		831
		832	push @pseudo,
		833	HTTPVersion => $1,
		834	Status => $2,
		835	Reason => $3,
		836	;
		837
		838	my $hdr = _parse_hdr
		839	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		840
		841	%hdr = (%$hdr, @pseudo);
		842	}
		843
		844	# redirect handling
		845	# microsoft and other shitheads don't give a shit for following standards,
		846	# try to support some common forms of broken Location headers.
		847	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		848	$hdr{location} =~ s/^\.\/+//;
		849
		850	my $url = "$rscheme://$uhost:$uport";
		851
		852	unless ($hdr{location} =~ s/^\///) {
		853	$url .= $upath;
		854	$url =~ s/\/[^\/]*$//;
		855	}
		856
		857	$hdr{location} = "$url/$hdr{location}";
		858	}
		859
		860	my $redirect;
		861
		862	if ($recurse) {
		863	my $status = $hdr{Status};
		864
		865	# industry standard is to redirect POST as GET for
		866	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		867	# also, the UA should ask the user for 301 and 307 and POST,
		868	# industry standard seems to be to simply follow.
		869	# we go with the industry standard.
		870	if ($status == 301 or $status == 302 or $status == 303) {
		871	# HTTP/1.1 is unclear on how to mutate the method
		872	$method = "GET" unless $method eq "HEAD";
		873	$redirect = 1;
		874	} elsif ($status == 307) {
		875	$redirect = 1;
		876	}
		877	}
		878
		879	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		880	if ($state{handle}) {
		881	# handle keepalive
		882	if (
		883	$keepalive
		884	&& $_[3]
		885	&& ($hdr{HTTPVersion} < 1.1
		886	? $hdr{connection} =~ /\bkeep-?alive\b/i
		887	: $hdr{connection} !~ /\bclose\b/i)
		888	) {
		889	ka_store $ka_key, delete $state{handle};
		890	} else {
		891	# no keepalive, destroy the handle
		892	$state{handle}->destroy;
		893	}
		894	}
		895
		896	%state = ();
		897
		898	if (defined $_[1]) {
		899	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		900	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		901	}
		902
		903	# set-cookie processing
		904	if ($arg{cookie_jar}) {
		905	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		906	}
		907
		908	if ($redirect && exists $hdr{location}) {
		909	# we ignore any errors, as it is very common to receive
		910	# Content-Length != 0 but no actual body
		911	# we also access %hdr, as $_[1] might be an erro
		912	http_request (
		913	$method => $hdr{location},
		914	%arg,
		915	recurse => $recurse - 1,
		916	Redirect => [$_[0], \%hdr],
		917	$cb
		918	);
		919	} else {
		920	$cb->($_[0], \%hdr);
		921	}
		922	};
		923
		924	$ae_error = 597; # body phase
		925
		926	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		927
		928	my $len = $chunked ? undef : $hdr{"content-length"};
		929
		930	# body handling, many different code paths
		931	# - no body expected
		932	# - want_body_handle
		933	# - te chunked
		934	# - 2x length known (with or without on_body)
		935	# - 2x length not known (with or without on_body)
		936	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		937	$finish->(undef, 598 => "Request cancelled by on_header");
		938	} elsif (
		939	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		940	or $method eq "HEAD"
		941	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		942	) {
		943	# no body
		944	$finish->("", undef, undef, 1);
		945
		946	} elsif (!$redirect && $arg{want_body_handle}) {
		947	$_[0]->on_eof (undef);
		948	$_[0]->on_error (undef);
		949	$_[0]->on_read (undef);
		950
		951	$finish->(delete $state{handle});
		952
		953	} elsif ($chunked) {
		954	my $cl = 0;
		955	my $body = "";
		956	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		957
		958	$state{read_chunk} = sub {
		959	$_[1] =~ /^([0-9a-fA-F]+)/
		960	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		961
		962	my $len = hex $1;
		963
		964	if ($len) {
		965	$cl += $len;
		966
		967	$_[0]->push_read (chunk => $len, sub {
		968	$on_body->($_[1], \%hdr)
		969	or return $finish->(undef, 598 => "Request cancelled by on_body");
		970
		971	$_[0]->push_read (line => sub {
		972	length $_[1]
		973	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		974	$_[0]->push_read (line => $state{read_chunk});
		975	});
		976	});
		977	} else {
		978	$hdr{"content-length"} \|\|= $cl;
		979
		980	$_[0]->push_read (line => $qr_nlnl, sub {
		981	if (length $_[1]) {
		982	for ("$_[1]") {
		983	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		984
		985	my $hdr = _parse_hdr
		986	or return $finish->(undef, $ae_error => "Garbled response trailers");
		987
		988	%hdr = (%hdr, %$hdr);
		989	}
		990	}
		991
		992	$finish->($body, undef, undef, 1);
		993	});
		994	}
		995	};
		996
		997	$_[0]->push_read (line => $state{read_chunk});
		998
		999	} elsif ($arg{on_body}) {
		1000	if (defined $len) {
		1001	$_[0]->on_read (sub {
		1002	$len -= length $_[0]{rbuf};
		1003
		1004	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1005	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1006
		1007	$len > 0
		1008	or $finish->("", undef, undef, 1);
		1009	});
		1010	} else {
		1011	$_[0]->on_eof (sub {
		1012	$finish->("");
		1013	});
		1014	$_[0]->on_read (sub {
		1015	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1016	or $finish->(undef, 598 => "Request cancelled by on_body");
		1017	});
		1018	}
		1019	} else {
		1020	$_[0]->on_eof (undef);
		1021
		1022	if (defined $len) {
		1023	$_[0]->on_read (sub {
		1024	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1025	if $len <= length $_[0]{rbuf};
		1026	});
		1027	} else {
		1028	$_[0]->on_error (sub {
		1029	($! == Errno::EPIPE \|\| !$!)
		1030	? $finish->(delete $_[0]{rbuf})
		1031	: $finish->(undef, $ae_error => $_[2]);
		1032	});
		1033	$_[0]->on_read (sub { });
		1034	}
		1035	}
		1036	};
		1037
		1038	# if keepalive is enabled, then the server closing the connection
		1039	# before a response can happen legally - we retry on idempotent methods.
		1040	if ($keptalive && $idempotent) {
		1041	my $old_eof = $hdl->{on_eof};
		1042	$hdl->{on_eof} = sub {
		1043	_destroy_state %state;
		1044
		1045	http_request (
		1046	$method => $url,
		1047	%arg,
		1048	keepalive => 0,
		1049	$cb
		1050	);
		1051	};
		1052	$hdl->on_read (sub {
		1053	return unless %state;
		1054
		1055	# as soon as we receive something, a connection close
		1056	# once more becomes a hard error
		1057	$hdl->{on_eof} = $old_eof;
		1058	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1059	});
		1060	} else {
		1061	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1062	}
		1063	};
		1064
		1065	my $prepare_handle = sub {
		1066	my ($hdl) = $state{handle};
		1067
		1068	$hdl->timeout ($timeout);
		1069	$hdl->on_error (sub {
		1070	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1071	});
		1072	$hdl->on_eof (sub {
		1073	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1074	});
		1075	};
		1076
		1077	# connected to proxy (or origin server)
		1078	my $connect_cb = sub {
		1079	my $fh = shift
		1080	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1081
		1082	return unless delete $state{connect_guard};
		1083
		1084	# get handle
		1085	$state{handle} = new AnyEvent::Handle
		1086	%{ $arg{handle_params} },
		1087	fh => $fh,
		1088	peername => $uhost,
		1089	tls_ctx => $arg{tls_ctx},
		1090	;
		1091
		1092	$prepare_handle->();
		1093
		1094	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1095
		1096	# now handle proxy-CONNECT method
		1097	if ($proxy && $uscheme eq "https") {
		1098	# oh dear, we have to wrap it into a connect request
		1099
		1100	# maybe re-use $uauthority with patched port?
		1101	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		1102	$state{handle}->push_read (line => $qr_nlnl, sub {
		1103	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1104	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1105
		1106	if ($2 == 200) {
		1107	$rpath = $upath;
		1108	$handle_actual_request->();
		1109	} else {
		1110	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1111	}
		1112	});
		1113	} else {
		1114	$handle_actual_request->();
		1115	}
		1116	};
656		1117
657	_get_slot $uhost, sub {	1118	_get_slot $uhost, sub {
658	$state{slot_guard} = shift;	1119	$state{slot_guard} = shift;
659		1120
660	return unless $state{connect_guard};	1121	return unless $state{connect_guard};
661		1122
662	my $ae_error = 595; # connecting	1123	# try to use an existing keepalive connection, but only if we, ourselves, plan
663		1124	# on a keepalive request (in theory, this should be a separate config option).
664	my $connect_cb = sub {	1125	if ($keepalive && $KA_CACHE{$ka_key}) {
665	$state{fh} = shift	1126	$keptalive = 1;
666	or do {	1127	$state{handle} = ka_fetch $ka_key;
667	my $err = "$!";	1128	$prepare_handle->();
668	%state = ();
669	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
670	};
671
672	return unless delete $state{connect_guard};
673
674	# get handle
675	$state{handle} = new AnyEvent::Handle
676	fh => $state{fh},
677	peername => $rhost,
678	tls_ctx => $arg{tls_ctx},
679	# these need to be reconfigured on keepalive handles
680	timeout => $timeout,
681	on_error => sub {
682	%state = ();
683	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
684	},
685	on_eof => sub {
686	%state = ();
687	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
688	},
689	;
690
691	# limit the number of persistent connections
692	# keepalive not yet supported
693	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
694	# ++$KA_COUNT{$_[1]};
695	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
696	# --$KA_COUNT{$_[1]}
697	# };
698	# $hdr{connection} = "keep-alive";
699	# }
700
701	$state{handle}->starttls ("connect") if $rscheme eq "https";
702
703	# handle actual, non-tunneled, request
704	my $handle_actual_request = sub {
705	$ae_error = 596; # request phase
706
707	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
708
709	# send request
710	$state{handle}->push_write (
711	"$method $rpath HTTP/1.1\015\012"
712	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
713	. "\015\012"
714	. (delete $arg{body})
715	);
716
717	# return if error occured during push_write()
718	return unless %state;
719
720	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
721
722	# status line and headers
723	$state{read_response} = sub {
724	for ("$_[1]") {
725	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
726
727	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
728	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
729
730	# 100 Continue handling
731	# should not happen as we don't send expect: 100-continue,
732	# but we handle it just in case.
733	# since we send the request body regardless, if we get an error
734	# we are out of-sync, which we currently do NOT handle correctly.
735	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
736	if $2 eq 100;
737
738	push @pseudo,
739	HTTPVersion => $1,
740	Status => $2,
741	Reason => $3,
742	;
743
744	my $hdr = parse_hdr
745	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
746
747	%hdr = (%$hdr, @pseudo);
748	}
749
750	# redirect handling
751	# microsoft and other shitheads don't give a shit for following standards,
752	# try to support some common forms of broken Location headers.
753	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
754	$hdr{location} =~ s/^\.\/+//;
755
756	my $url = "$rscheme://$uhost:$uport";
757
758	unless ($hdr{location} =~ s/^\///) {
759	$url .= $upath;
760	$url =~ s/\/[^\/]*$//;
761	}
762
763	$hdr{location} = "$url/$hdr{location}";
764	}
765
766	my $redirect;
767
768	if ($recurse) {
769	my $status = $hdr{Status};
770
771	# industry standard is to redirect POST as GET for
772	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
773	# also, the UA should ask the user for 301 and 307 and POST,
774	# industry standard seems to be to simply follow.
775	# we go with the industry standard.
776	if ($status == 301 or $status == 302 or $status == 303) {
777	# HTTP/1.1 is unclear on how to mutate the method
778	$method = "GET" unless $method eq "HEAD";
779	$redirect = 1;
780	} elsif ($status == 307) {
781	$redirect = 1;
782	}
783	}
784
785	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
786	my $may_keep_alive = $_[3];
787
788	$state{handle}->destroy if $state{handle};
789	%state = ();
790
791	if (defined $_[1]) {
792	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
793	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
794	}
795
796	# set-cookie processing
797	if ($arg{cookie_jar}) {
798	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
799	}
800
801	if ($redirect && exists $hdr{location}) {
802	# we ignore any errors, as it is very common to receive
803	# Content-Length != 0 but no actual body
804	# we also access %hdr, as $_[1] might be an erro
805	http_request (
806	$method => $hdr{location},
807	%arg,
808	recurse => $recurse - 1,
809	Redirect => [$_[0], \%hdr],
810	$cb);
811	} else {
812	$cb->($_[0], \%hdr);
813	}
814	};
815
816	$ae_error = 597; # body phase
817
818	my $len = $hdr{"content-length"};
819
820	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
821	$finish->(undef, 598 => "Request cancelled by on_header");
822	} elsif (
823	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
824	or $method eq "HEAD"
825	or (defined $len && !$len)
826	) {
827	# no body
828	$finish->("", undef, undef, 1);
829	} else {
830	# body handling, many different code paths
831	# - no body expected
832	# - want_body_handle
833	# - te chunked
834	# - 2x length known (with or without on_body)
835	# - 2x length not known (with or without on_body)
836	if (!$redirect && $arg{want_body_handle}) {
837	$_[0]->on_eof (undef);
838	$_[0]->on_error (undef);
839	$_[0]->on_read (undef);
840
841	$finish->(delete $state{handle});
842
843	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
844	my $cl = 0;
845	my $body = undef;
846	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
847
848	my $read_chunk; $read_chunk = sub {
849	$_[1] =~ /^([0-9a-fA-F]+)/
850	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
851
852	my $len = hex $1;
853
854	if ($len) {
855	$cl += $len;
856
857	$_[0]->push_read (chunk => $len, sub {
858	$on_body->($_[1], \%hdr)
859	or return $finish->(undef, 598 => "Request cancelled by on_body");
860
861	$_[0]->push_read (line => sub {
862	length $_[1]
863	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
864	$_[0]->push_read (line => $read_chunk);
865	});
866	});
867	} else {
868	$hdr{"content-length"} \|\|= $cl;
869
870	$_[0]->push_read (line => $qr_nlnl, sub {
871	if (length $_[1]) {
872	for ("$_[1]") {
873	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
874
875	my $hdr = parse_hdr
876	or return $finish->(undef, $ae_error => "Garbled response trailers");
877
878	%hdr = (%hdr, %$hdr);
879	}
880	}
881
882	$finish->($body, undef, undef, 1);
883	});
884	}
885	};
886
887	$_[0]->push_read (line => $read_chunk);
888
889	} elsif ($arg{on_body}) {
890	if ($len) {
891	$_[0]->on_read (sub {
892	$len -= length $_[0]{rbuf};
893
894	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
895	or return $finish->(undef, 598 => "Request cancelled by on_body");
896
897	$len > 0
898	or $finish->("", undef, undef, 1);
899	});
900	} else {
901	$_[0]->on_eof (sub {
902	$finish->("");
903	});
904	$_[0]->on_read (sub {
905	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
906	or $finish->(undef, 598 => "Request cancelled by on_body");
907	});
908	}
909	} else {
910	$_[0]->on_eof (undef);
911
912	if ($len) {
913	$_[0]->on_read (sub {
914	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
915	if $len <= length $_[0]{rbuf};
916	});
917	} else {
918	$_[0]->on_error (sub {
919	($! == Errno::EPIPE \|\| !$!)
920	? $finish->(delete $_[0]{rbuf})
921	: $finish->(undef, $ae_error => $_[2]);
922	});
923	$_[0]->on_read (sub { });
924	}
925	}
926	}
927	};
928
929	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
930	};
931
932	# now handle proxy-CONNECT method
933	if ($proxy && $uscheme eq "https") {
934	# oh dear, we have to wrap it into a connect request
935
936	# maybe re-use $uauthority with patched port?
937	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
938	$state{handle}->push_read (line => $qr_nlnl, sub {
939	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
940	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
941
942	if ($2 == 200) {
943	$rpath = $upath;
944	&$handle_actual_request;	1129	$handle_actual_request->();
945	} else {	1130
946	%state = ();
947	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
948	}
949	});
950	} else {	1131	} else {
951	&$handle_actual_request;
952	}
953	};
954
955	my $tcp_connect = $arg{tcp_connect}	1132	my $tcp_connect = $arg{tcp_connect}
956	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1133	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
957		1134
958	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });	1135	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
959		1136	}
960	};	1137	};
961		1138
962	defined wantarray && AnyEvent::Util::guard { %state = () }	1139	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
963	}	1140	}
964		1141
965	sub http_get($@) {	1142	sub http_get($@) {
966	unshift @_, "GET";	1143	unshift @_, "GET";
967	&http_request	1144	&http_request
…		…
985	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1162	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
986	the actual connection, which in turn uses AnyEvent::DNS to resolve	1163	the actual connection, which in turn uses AnyEvent::DNS to resolve
987	hostnames. The latter is a simple stub resolver and does no caching	1164	hostnames. The latter is a simple stub resolver and does no caching
988	on its own. If you want DNS caching, you currently have to provide	1165	on its own. If you want DNS caching, you currently have to provide
989	your own default resolver (by storing a suitable resolver object in	1166	your own default resolver (by storing a suitable resolver object in
990	C<$AnyEvent::DNS::RESOLVER>).	1167	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
991		1168
992	=head2 GLOBAL FUNCTIONS AND VARIABLES	1169	=head2 GLOBAL FUNCTIONS AND VARIABLES
993		1170
994	=over 4	1171	=over 4
995		1172
996	=item AnyEvent::HTTP::set_proxy "proxy-url"	1173	=item AnyEvent::HTTP::set_proxy "proxy-url"
997		1174
998	Sets the default proxy server to use. The proxy-url must begin with a	1175	Sets the default proxy server to use. The proxy-url must begin with a
999	string of the form C<http://host:port> (optionally C<https:...>), croaks	1176	string of the form C<http://host:port>, croaks otherwise.
1000	otherwise.
1001		1177
1002	To clear an already-set proxy, use C<undef>.	1178	To clear an already-set proxy, use C<undef>.
		1179
		1180	When AnyEvent::HTTP is laoded for the first time it will query the
		1181	default proxy from the operating system, currently by looking at
		1182	C<$ENV{http_proxy>}.
1003		1183
1004	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]	1184	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
1005		1185
1006	Remove all cookies from the cookie jar that have been expired. If	1186	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	1187	C<$session_end> is given and true, then additionally remove all session
…		…
1053		1233
1054	=item $AnyEvent::HTTP::MAX_RECURSE	1234	=item $AnyEvent::HTTP::MAX_RECURSE
1055		1235
1056	The default value for the C<recurse> request parameter (default: C<10>).	1236	The default value for the C<recurse> request parameter (default: C<10>).
1057		1237
		1238	=item $AnyEvent::HTTP::TIMEOUT
		1239
		1240	The default timeout for conenction operations (default: C<300>).
		1241
1058	=item $AnyEvent::HTTP::USERAGENT	1242	=item $AnyEvent::HTTP::USERAGENT
1059		1243
1060	The default value for the C<User-Agent> header (the default is	1244	The default value for the C<User-Agent> header (the default is
1061	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1245	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
1062		1246
1063	=item $AnyEvent::HTTP::MAX_PER_HOST	1247	=item $AnyEvent::HTTP::MAX_PER_HOST
1064		1248
1065	The maximum number of concurrent connections to the same host (identified	1249	The maximum number of concurrent connections to the same host (identified
1066	by the hostname). If the limit is exceeded, then the additional requests	1250	by the hostname). If the limit is exceeded, then the additional requests
1067	are queued until previous connections are closed.	1251	are queued until previous connections are closed. Both persistent and
		1252	non-persistent connections are counted in this limit.
1068		1253
1069	The default value for this is C<4>, and it is highly advisable to not	1254	The default value for this is C<4>, and it is highly advisable to not
1070	increase it.	1255	increase it much.
		1256
		1257	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1258	connections, older browsers used 2, newers (such as firefox 3) typically
		1259	use 6, and Opera uses 8 because like, they have the fastest browser and
		1260	give a shit for everybody else on the planet.
		1261
		1262	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1263
		1264	The time after which idle persistent conenctions get closed by
		1265	AnyEvent::HTTP (default: C<3>).
1071		1266
1072	=item $AnyEvent::HTTP::ACTIVE	1267	=item $AnyEvent::HTTP::ACTIVE
1073		1268
1074	The number of active connections. This is not the number of currently	1269	The number of active connections. This is not the number of currently
1075	running requests, but the number of currently open and non-idle TCP	1270	running requests, but the number of currently open and non-idle TCP
1076	connections. This number of can be useful for load-leveling.	1271	connections. This number can be useful for load-leveling.
1077		1272
1078	=back	1273	=back
1079		1274
1080	=cut	1275	=cut
1081		1276
…		…
1124	undef	1319	undef
1125	}	1320	}
1126		1321
1127	sub set_proxy($) {	1322	sub set_proxy($) {
1128	if (length $_[0]) {	1323	if (length $_[0]) {
1129	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1324	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
1130	or Carp::croak "$_[0]: invalid proxy URL";	1325	or Carp::croak "$_[0]: invalid proxy URL";
1131	$PROXY = [$2, $3 \|\| 3128, $1]	1326	$PROXY = [$2, $3 \|\| 3128, $1]
1132	} else {	1327	} else {
1133	undef $PROXY;	1328	undef $PROXY;
1134	}	1329	}
…		…
1137	# initialise proxy from environment	1332	# initialise proxy from environment
1138	eval {	1333	eval {
1139	set_proxy $ENV{http_proxy};	1334	set_proxy $ENV{http_proxy};
1140	};	1335	};
1141		1336
		1337	=head2 SHOWCASE
		1338
		1339	This section contaisn some more elaborate "real-world" examples or code
		1340	snippets.
		1341
		1342	=head2 HTTP/1.1 FILE DOWNLOAD
		1343
		1344	Downloading files with HTTP can be quite tricky, especially when something
		1345	goes wrong and you want to resume.
		1346
		1347	Here is a function that initiates and resumes a download. It uses the
		1348	last modified time to check for file content changes, and works with many
		1349	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1350	on older servers.
		1351
		1352	It calls the completion callback with either C<undef>, which means a
		1353	nonretryable error occured, C<0> when the download was partial and should
		1354	be retried, and C<1> if it was successful.
		1355
		1356	use AnyEvent::HTTP;
		1357
		1358	sub download($$$) {
		1359	my ($url, $file, $cb) = @_;
		1360
		1361	open my $fh, "+<", $file
		1362	or die "$file: $!";
		1363
		1364	my %hdr;
		1365	my $ofs = 0;
		1366
		1367	warn stat $fh;
		1368	warn -s _;
		1369	if (stat $fh and -s _) {
		1370	$ofs = -s _;
		1371	warn "-s is ", $ofs;#d#
		1372	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1373	$hdr{"range"} = "bytes=$ofs-";
		1374	}
		1375
		1376	http_get $url,
		1377	headers => \%hdr,
		1378	on_header => sub {
		1379	my ($hdr) = @_;
		1380
		1381	if ($hdr->{Status} == 200 && $ofs) {
		1382	# resume failed
		1383	truncate $fh, $ofs = 0;
		1384	}
		1385
		1386	sysseek $fh, $ofs, 0;
		1387
		1388	1
		1389	},
		1390	on_body => sub {
		1391	my ($data, $hdr) = @_;
		1392
		1393	if ($hdr->{Status} =~ /^2/) {
		1394	length $data == syswrite $fh, $data
		1395	or return; # abort on write errors
		1396	}
		1397
		1398	1
		1399	},
		1400	sub {
		1401	my (undef, $hdr) = @_;
		1402
		1403	my $status = $hdr->{Status};
		1404
		1405	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1406	utime $fh, $time, $time;
		1407	}
		1408
		1409	if ($status == 200 \|\| $status == 206 \|\| $status == 416) {
		1410	# download ok \|\| resume ok \|\| file already fully downloaded
		1411	$cb->(1, $hdr);
		1412
		1413	} elsif ($status == 412) {
		1414	# file has changed while resuming, delete and retry
		1415	unlink $file;
		1416	$cb->(0, $hdr);
		1417
		1418	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1419	# retry later
		1420	$cb->(0, $hdr);
		1421
		1422	} else {
		1423	$cb->(undef, $hdr);
		1424	}
		1425	}
		1426	;
		1427	}
		1428
		1429	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1430	if ($_[0]) {
		1431	print "OK!\n";
		1432	} elsif (defined $_[0]) {
		1433	print "please retry later\n";
		1434	} else {
		1435	print "ERROR\n";
		1436	}
		1437	};
		1438
1142	=head2 SOCKS PROXIES	1439	=head3 SOCKS PROXIES
1143		1440
1144	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1441	Socks proxies are not directly supported by AnyEvent::HTTP. You can
1145	compile your perl to support socks, or use an external program such as	1442	compile your perl to support socks, or use an external program such as
1146	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy	1443	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
1147	transparently.	1444	transparently.

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.80 by root, Sat Jan 1 21:51:22 2011 UTC vs. Revision 1.102 by root, Sat Feb 19 06:46:14 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.80 by root, Sat Jan 1 21:51:22 2011 UTC vs.
Revision 1.102 by root, Sat Feb 19 06:46:14 2011 UTC