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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.83 by root, Sun Jan 2 05:02:28 2011 UTC vs.
Revision 1.103 by root, Thu Feb 24 12:13:11 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 = '2.1';
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($$$$) {	475	sub cookie_jar_extract($$$$) {
419	my ($jar, $uscheme, $uhost, $upath) = @_;	476	my ($jar, $scheme, $host, $path) = @_;
420
421	$uhost = lc $uhost;
422		477
423	%$jar = () if $jar->{version} != 1;	478	%$jar = () if $jar->{version} != 1;
424		479
425	my @cookies;	480	my @cookies;
426		481
427	while (my ($chost, $paths) = each %$jar) {	482	while (my ($chost, $paths) = each %$jar) {
428	next unless ref $paths;	483	next unless ref $paths;
429		484
430	if ($chost =~ /^\./) {	485	if ($chost =~ /^\./) {
431	next unless $chost eq substr $uhost, -length $chost;	486	next unless $chost eq substr $host, -length $chost;
432	} elsif ($chost =~ /\./) {	487	} elsif ($chost =~ /\./) {
433	next unless $chost eq $uhost;	488	next unless $chost eq $host;
434	} else {	489	} else {
435	next;	490	next;
436	}	491	}
437		492
438	while (my ($cpath, $cookies) = each %$paths) {	493	while (my ($cpath, $cookies) = each %$paths) {
439	next unless $cpath eq substr $upath, 0, length $cpath;	494	next unless $cpath eq substr $path, 0, length $cpath;
440		495
441	while (my ($cookie, $kv) = each %$cookies) {	496	while (my ($cookie, $kv) = each %$cookies) {
442	next if $uscheme ne "https" && exists $kv->{secure};	497	next if $scheme ne "https" && exists $kv->{secure};
443		498
444	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {	499	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
445	delete $cookies->{$cookie};	500	delete $cookies->{$cookie};
446	next;	501	next;
447	}	502	}
…		…
461	\@cookies	516	\@cookies
462	}	517	}
463		518
464	# parse set_cookie header into jar	519	# parse set_cookie header into jar
465	sub cookie_jar_set_cookie($$$$) {	520	sub cookie_jar_set_cookie($$$$) {
466	my ($jar, $set_cookie, $uhost, $date) = @_;	521	my ($jar, $set_cookie, $host, $date) = @_;
467		522
468	my $anow = int AE::now;	523	my $anow = int AE::now;
469	my $snow; # server-now	524	my $snow; # server-now
470		525
471	for ($set_cookie) {	526	for ($set_cookie) {
…		…
477	while (	532	while (
478	m{	533	m{
479	\G\s*	534	\G\s*
480	(?:	535	(?:
481	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)	536	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
482	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) ) )?	537	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^;,[:space:]]) ) )?
483	)	538	)
484	}gcxsi	539	}gcxsi
485	) {	540	) {
486	my $name = $2;	541	my $name = $2;
487	my $value = $4;	542	my $value = $4;
…		…
494	# quoted	549	# quoted
495	$value = $3;	550	$value = $3;
496	$value =~ s/\\(.)/$1/gs;	551	$value =~ s/\\(.)/$1/gs;
497	}	552	}
498		553
499	push @kv, lc $name, $value;	554	push @kv, @kv ? lc $name : $name, $value;
500		555
501	last unless /\G\s*;/gc;	556	last unless /\G\s*;/gc;
502	}	557	}
503		558
504	last unless @kv;	559	last unless @kv;
…		…
527		582
528	# this is not rfc-like and not netscape-like. go figure.	583	# this is not rfc-like and not netscape-like. go figure.
529	my $ndots = $cdom =~ y/.//;	584	my $ndots = $cdom =~ y/.//;
530	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	585	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
531	} else {	586	} else {
532	$cdom = $uhost;	587	$cdom = $host;
533	}	588	}
534		589
535	# store it	590	# store it
536	$jar->{version} = 1;	591	$jar->{version} = 1;
537	$jar->{lc $cdom}{$cpath}{$name} = \%kv;	592	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
538		593
539	redo if /\G\s*,/gc;	594	redo if /\G\s*,/gc;
540	}	595	}
541	}	596	}
542		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
543	# continue to parse $_ for headers and place them into the arg	640	# continue to parse $_ for headers and place them into the arg
544	sub parse_hdr() {	641	sub _parse_hdr() {
545	my %hdr;	642	my %hdr;
546		643
547	# things seen, not parsed:	644	# things seen, not parsed:
548	# p3pP="NON CUR OTPi OUR NOR UNI"	645	# p3pP="NON CUR OTPi OUR NOR UNI"
549		646
…		…
563	for values %hdr;	660	for values %hdr;
564		661
565	\%hdr	662	\%hdr
566	}	663	}
567		664
		665	#############################################################################
		666	# http_get
		667
568	our $qr_nlnl = qr{(?<![^\012])\015?\012};	668	our $qr_nlnl = qr{(?<![^\012])\015?\012};
569		669
570	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	670	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
571	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(\%$$) {
		683	my ($state, $cb, $hdr) = @_;
		684
		685	&_destroy_state ($state);
		686
		687	$cb->(undef, $hdr);
		688	()
		689	}
572		690
573	sub http_request($$@) {	691	sub http_request($$@) {
574	my $cb = pop;	692	my $cb = pop;
575	my ($method, $url, %arg) = @_;	693	my ($method, $url, %arg) = @_;
576		694
…		…
594	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	712	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
595		713
596	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })	714	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
597	if $recurse < 0;	715	if $recurse < 0;
598		716
599	my $proxy = $arg{proxy} \|\| $PROXY;	717	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
600	my $timeout = $arg{timeout} \|\| $TIMEOUT;	718	my $timeout = $arg{timeout} \|\| $TIMEOUT;
601		719
602	my ($uscheme, $uauthority, $upath, $query, $fragment) =	720	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
603	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;	721	$url =~ m\|^([^:]+):(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?$\|;
604		722
605	$uscheme = lc $uscheme;	723	$uscheme = lc $uscheme;
606		724
607	my $uport = $uscheme eq "http" ? 80	725	my $uport = $uscheme eq "http" ? 80
608	: $uscheme eq "https" ? 443	726	: $uscheme eq "https" ? 443
609	: 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" });
610		728
611	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	729	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
612	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	730	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
613		731
614	my $uhost = $1;	732	my $uhost = lc $1;
615	$uport = $2 if defined $2;	733	$uport = $2 if defined $2;
616		734
617	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	735	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
618	unless exists $hdr{host};	736	unless exists $hdr{host};
619		737
…		…
638	$rscheme = "http" unless defined $rscheme;	756	$rscheme = "http" unless defined $rscheme;
639		757
640	# don't support https requests over https-proxy transport,	758	# don't support https requests over https-proxy transport,
641	# 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.
642	$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;
643	} else {	764	} else {
644	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	765	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
645	}	766	}
646		767
647	# leave out fragment and query string, just a heuristic	768	# leave out fragment and query string, just a heuristic
…		…
649	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};	770	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
650		771
651	$hdr{"content-length"} = length $arg{body}	772	$hdr{"content-length"} = length $arg{body}
652	if length $arg{body} \|\| $method ne "GET";	773	if length $arg{body} \|\| $method ne "GET";
653		774
654	$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 $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		779	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		780	my $was_persistent; # 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} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1
655	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1	786	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
656		787
657	my %state = (connect_guard => 1);	788	my %state = (connect_guard => 1);
658		789
659	_get_slot $uhost, sub {
660	$state{slot_guard} = shift;
661
662	return unless $state{connect_guard};
663
664	my $ae_error = 595; # connecting	790	my $ae_error = 595; # connecting
665		791
666	# handle actual, non-tunneled, request	792	# handle actual, non-tunneled, request
667	my $handle_actual_request = sub {	793	my $handle_actual_request = sub {
668	$ae_error = 596; # request phase	794	$ae_error = 596; # request phase
669		795
		796	my $hdl = $state{handle};
		797
670	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	798	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
671		799
672	# send request	800	# send request
673	$state{handle}->push_write (	801	$hdl->push_write (
674	"$method $rpath HTTP/1.1\015\012"	802	"$method $rpath HTTP/1.1\015\012"
675	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)	803	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
676	. "\015\012"	804	. "\015\012"
677	. (delete $arg{body})	805	. (delete $arg{body})
678	);	806	);
679		807
680	# return if error occured during push_write()	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 {
681	return unless %state;	816	return unless %state;
682		817
683	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
684
685	# status line and headers
686	$state{read_response} = sub {
687	for ("$_[1]") {	818	for ("$_[1]") {
688	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	819	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
689		820
690	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci	821	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
691	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));	822	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
692		823
693	# 100 Continue handling	824	# 100 Continue handling
694	# should not happen as we don't send expect: 100-continue,	825	# should not happen as we don't send expect: 100-continue,
695	# but we handle it just in case.	826	# but we handle it just in case.
696	# since we send the request body regardless, if we get an error	827	# since we send the request body regardless, if we get an error
697	# we are out of-sync, which we currently do NOT handle correctly.	828	# we are out of-sync, which we currently do NOT handle correctly.
698	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})	829	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
699	if $2 eq 100;	830	if $2 eq 100;
700		831
701	push @pseudo,	832	push @pseudo,
702	HTTPVersion => $1,	833	HTTPVersion => $1,
703	Status => $2,	834	Status => $2,
704	Reason => $3,	835	Reason => $3,
705	;	836	;
706		837
707	my $hdr = parse_hdr	838	my $hdr = _parse_hdr
708	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));	839	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
709		840
710	%hdr = (%$hdr, @pseudo);	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/\/[^\/]*$//;
711	}	855	}
712		856
713	# redirect handling
714	# microsoft and other shitheads don't give a shit for following standards,
715	# try to support some common forms of broken Location headers.
716	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
717	$hdr{location} =~ s/^\.\/+//;
718
719	my $url = "$rscheme://$uhost:$uport";
720
721	unless ($hdr{location} =~ s/^\///) {
722	$url .= $upath;
723	$url =~ s/\/[^\/]*$//;
724	}
725
726	$hdr{location} = "$url/$hdr{location}";	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;
727	}	876	}
		877	}
728		878
729	my $redirect;	879	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
730		880	if ($state{handle}) {
731	if ($recurse) {	881	# handle keepalive
732	my $status = $hdr{Status};	882	if (
733		883	$persistent
734	# industry standard is to redirect POST as GET for	884	&& $_[3]
735	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.	885	&& ($hdr{HTTPVersion} < 1.1
736	# also, the UA should ask the user for 301 and 307 and POST,	886	? $hdr{connection} =~ /\bkeep-?alive\b/i
737	# industry standard seems to be to simply follow.	887	: $hdr{connection} !~ /\bclose\b/i)
738	# we go with the industry standard.	888	) {
739	if ($status == 301 or $status == 302 or $status == 303) {	889	ka_store $ka_key, delete $state{handle};
740	# HTTP/1.1 is unclear on how to mutate the method	890	} else {
741	$method = "GET" unless $method eq "HEAD";	891	# no keepalive, destroy the handle
742	$redirect = 1;	892	$state{handle}->destroy;
743	} elsif ($status == 307) {
744	$redirect = 1;
745	}	893	}
746	}	894	}
747		895
748	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
749	my $may_keep_alive = $_[3];
750
751	$state{handle}->destroy if $state{handle};
752	%state = ();	896	%state = ();
753		897
754	if (defined $_[1]) {	898	if (defined $_[1]) {
755	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];	899	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
756	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];	900	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
757	}	901	}
758		902
759	# set-cookie processing	903	# set-cookie processing
760	if ($arg{cookie_jar}) {	904	if ($arg{cookie_jar}) {
761	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};	905	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
762	}	906	}
763		907
764	if ($redirect && exists $hdr{location}) {	908	if ($redirect && exists $hdr{location}) {
765	# we ignore any errors, as it is very common to receive	909	# we ignore any errors, as it is very common to receive
766	# Content-Length != 0 but no actual body	910	# Content-Length != 0 but no actual body
767	# we also access %hdr, as $_[1] might be an erro	911	# we also access %hdr, as $_[1] might be an erro
		912	$state{recurse} =
768	http_request (	913	http_request (
769	$method => $hdr{location},	914	$method => $hdr{location},
770	%arg,	915	%arg,
771	recurse => $recurse - 1,	916	recurse => $recurse - 1,
772	Redirect => [$_[0], \%hdr],	917	Redirect => [$_[0], \%hdr],
		918	sub {
		919	%state = ();
		920	&$cb
		921	},
		922	);
		923	} else {
		924	$cb->($_[0], \%hdr);
		925	}
		926	};
		927
		928	$ae_error = 597; # body phase
		929
		930	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		931
		932	my $len = $chunked ? undef : $hdr{"content-length"};
		933
		934	# body handling, many different code paths
		935	# - no body expected
		936	# - want_body_handle
		937	# - te chunked
		938	# - 2x length known (with or without on_body)
		939	# - 2x length not known (with or without on_body)
		940	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		941	$finish->(undef, 598 => "Request cancelled by on_header");
		942	} elsif (
		943	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		944	or $method eq "HEAD"
		945	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		946	) {
		947	# no body
		948	$finish->("", undef, undef, 1);
		949
		950	} elsif (!$redirect && $arg{want_body_handle}) {
		951	$_[0]->on_eof (undef);
		952	$_[0]->on_error (undef);
		953	$_[0]->on_read (undef);
		954
		955	$finish->(delete $state{handle});
		956
		957	} elsif ($chunked) {
		958	my $cl = 0;
		959	my $body = "";
		960	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		961
		962	$state{read_chunk} = sub {
		963	$_[1] =~ /^([0-9a-fA-F]+)/
		964	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		965
		966	my $len = hex $1;
		967
		968	if ($len) {
		969	$cl += $len;
		970
		971	$_[0]->push_read (chunk => $len, sub {
		972	$on_body->($_[1], \%hdr)
		973	or return $finish->(undef, 598 => "Request cancelled by on_body");
		974
		975	$_[0]->push_read (line => sub {
		976	length $_[1]
		977	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		978	$_[0]->push_read (line => $state{read_chunk});
773	$cb);	979	});
		980	});
774	} else {	981	} else {
775	$cb->($_[0], \%hdr);	982	$hdr{"content-length"} \|\|= $cl;
		983
		984	$_[0]->push_read (line => $qr_nlnl, sub {
		985	if (length $_[1]) {
		986	for ("$_[1]") {
		987	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		988
		989	my $hdr = _parse_hdr
		990	or return $finish->(undef, $ae_error => "Garbled response trailers");
		991
		992	%hdr = (%hdr, %$hdr);
		993	}
		994	}
		995
		996	$finish->($body, undef, undef, 1);
		997	});
776	}	998	}
777	};	999	};
778		1000
779	$ae_error = 597; # body phase	1001	$_[0]->push_read (line => $state{read_chunk});
780		1002
781	my $len = $hdr{"content-length"};	1003	} elsif ($arg{on_body}) {
		1004	if (defined $len) {
		1005	$_[0]->on_read (sub {
		1006	$len -= length $_[0]{rbuf};
782		1007
783	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {	1008	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
784	$finish->(undef, 598 => "Request cancelled by on_header");	1009	or return $finish->(undef, 598 => "Request cancelled by on_body");
785	} elsif (	1010
786	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/	1011	$len > 0
787	or $method eq "HEAD"
788	or (defined $len && !$len)
789	) {
790	# no body
791	$finish->("", undef, undef, 1);	1012	or $finish->("", undef, undef, 1);
		1013	});
792	} else {	1014	} else {
793	# body handling, many different code paths
794	# - no body expected
795	# - want_body_handle
796	# - te chunked
797	# - 2x length known (with or without on_body)
798	# - 2x length not known (with or without on_body)
799	if (!$redirect && $arg{want_body_handle}) {
800	$_[0]->on_eof (undef);	1015	$_[0]->on_eof (sub {
801	$_[0]->on_error (undef);	1016	$finish->("");
802	$_[0]->on_read (undef);
803
804	$finish->(delete $state{handle});
805
806	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
807	my $cl = 0;
808	my $body = undef;
809	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
810
811	$state{read_chunk} = sub {
812	$_[1] =~ /^([0-9a-fA-F]+)/
813	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
814
815	my $len = hex $1;
816
817	if ($len) {
818	$cl += $len;
819
820	$_[0]->push_read (chunk => $len, sub {
821	$on_body->($_[1], \%hdr)
822	or return $finish->(undef, 598 => "Request cancelled by on_body");
823
824	$_[0]->push_read (line => sub {
825	length $_[1]
826	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
827	$_[0]->push_read (line => $state{read_chunk});
828	});
829	});
830	} else {
831	$hdr{"content-length"} \|\|= $cl;
832
833	$_[0]->push_read (line => $qr_nlnl, sub {
834	if (length $_[1]) {
835	for ("$_[1]") {
836	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
837
838	my $hdr = parse_hdr
839	or return $finish->(undef, $ae_error => "Garbled response trailers");
840
841	%hdr = (%hdr, %$hdr);
842	}
843	}
844
845	$finish->($body, undef, undef, 1);
846	});
847	}
848	};	1017	});
849
850	$_[0]->push_read (line => $state{read_chunk});
851
852	} elsif ($arg{on_body}) {
853	if ($len) {
854	$_[0]->on_read (sub {	1018	$_[0]->on_read (sub {
855	$len -= length $_[0]{rbuf};
856
857	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	1019	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
858	or return $finish->(undef, 598 => "Request cancelled by on_body");
859
860	$len > 0
861	or $finish->("", undef, undef, 1);
862	});
863	} else {
864	$_[0]->on_eof (sub {
865	$finish->("");
866	});
867	$_[0]->on_read (sub {
868	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
869	or $finish->(undef, 598 => "Request cancelled by on_body");	1020	or $finish->(undef, 598 => "Request cancelled by on_body");
870	});
871	}
872	} else {
873	$_[0]->on_eof (undef);
874
875	if ($len) {
876	$_[0]->on_read (sub {
877	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
878	if $len <= length $_[0]{rbuf};
879	});
880	} else {
881	$_[0]->on_error (sub {
882	($! == Errno::EPIPE \|\| !$!)
883	? $finish->(delete $_[0]{rbuf})
884	: $finish->(undef, $ae_error => $_[2]);
885	});
886	$_[0]->on_read (sub { });
887	}
888	}	1021	});
889	}	1022	}
890	};
891
892	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
893	};
894
895	my $connect_cb = sub {
896	$state{fh} = shift
897	or do {
898	my $err = "$!";
899	%state = ();
900	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
901	};
902
903	return unless delete $state{connect_guard};
904
905	# get handle
906	$state{handle} = new AnyEvent::Handle
907	fh => $state{fh},
908	peername => $rhost,
909	tls_ctx => $arg{tls_ctx},
910	# these need to be reconfigured on keepalive handles
911	timeout => $timeout,
912	on_error => sub {
913	%state = ();
914	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
915	},
916	on_eof => sub {
917	%state = ();
918	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
919	},
920	;
921
922	# limit the number of persistent connections
923	# keepalive not yet supported
924	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
925	# ++$KA_COUNT{$_[1]};
926	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
927	# --$KA_COUNT{$_[1]}
928	# };
929	# $hdr{connection} = "keep-alive";
930	# }
931
932	$state{handle}->starttls ("connect") if $rscheme eq "https";
933
934	# now handle proxy-CONNECT method
935	if ($proxy && $uscheme eq "https") {
936	# oh dear, we have to wrap it into a connect request
937
938	# maybe re-use $uauthority with patched port?
939	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
940	$state{handle}->push_read (line => $qr_nlnl, sub {
941	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
942	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
943
944	if ($2 == 200) {
945	$rpath = $upath;
946	$handle_actual_request->();
947	} else {
948	%state = ();
949	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
950	}
951	});
952	} else {	1023	} else {
953	$handle_actual_request->();	1024	$_[0]->on_eof (undef);
		1025
		1026	if (defined $len) {
		1027	$_[0]->on_read (sub {
		1028	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1029	if $len <= length $_[0]{rbuf};
		1030	});
		1031	} else {
		1032	$_[0]->on_error (sub {
		1033	($! == Errno::EPIPE \|\| !$!)
		1034	? $finish->(delete $_[0]{rbuf})
		1035	: $finish->(undef, $ae_error => $_[2]);
		1036	});
		1037	$_[0]->on_read (sub { });
		1038	}
954	}	1039	}
955	};	1040	};
956		1041
957	my $tcp_connect = $arg{tcp_connect}	1042	# if keepalive is enabled, then the server closing the connection
958	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1043	# before a response can happen legally - we retry on idempotent methods.
		1044	if ($was_persistent && $idempotent) {
		1045	my $old_eof = $hdl->{on_eof};
		1046	$hdl->{on_eof} = sub {
		1047	_destroy_state %state;
959		1048
960	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });	1049	%state = ();
		1050	$state{recurse} =
		1051	http_request (
		1052	$method => $url,
		1053	%arg,
		1054	keepalive => 0,
		1055	sub {
		1056	%state = ();
		1057	&$cb
		1058	}
		1059	);
		1060	};
		1061	$hdl->on_read (sub {
		1062	return unless %state;
		1063
		1064	# as soon as we receive something, a connection close
		1065	# once more becomes a hard error
		1066	$hdl->{on_eof} = $old_eof;
		1067	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1068	});
		1069	} else {
		1070	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1071	}
961	};	1072	};
962		1073
		1074	my $prepare_handle = sub {
		1075	my ($hdl) = $state{handle};
		1076
		1077	$hdl->on_error (sub {
		1078	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1079	});
		1080	$hdl->on_eof (sub {
		1081	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1082	});
		1083	$hdl->timeout_reset;
		1084	$hdl->timeout ($timeout);
		1085	};
		1086
		1087	# connected to proxy (or origin server)
		1088	my $connect_cb = sub {
		1089	my $fh = shift
		1090	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1091
		1092	return unless delete $state{connect_guard};
		1093
		1094	# get handle
		1095	$state{handle} = new AnyEvent::Handle
		1096	%{ $arg{handle_params} },
		1097	fh => $fh,
		1098	peername => $uhost,
		1099	tls_ctx => $arg{tls_ctx},
		1100	;
		1101
		1102	$prepare_handle->();
		1103
		1104	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1105
		1106	# now handle proxy-CONNECT method
		1107	if ($proxy && $uscheme eq "https") {
		1108	# oh dear, we have to wrap it into a connect request
		1109
		1110	# maybe re-use $uauthority with patched port?
		1111	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		1112	$state{handle}->push_read (line => $qr_nlnl, sub {
		1113	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1114	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1115
		1116	if ($2 == 200) {
		1117	$rpath = $upath;
		1118	$handle_actual_request->();
		1119	} else {
		1120	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1121	}
		1122	});
		1123	} else {
		1124	$handle_actual_request->();
		1125	}
		1126	};
		1127
		1128	_get_slot $uhost, sub {
		1129	$state{slot_guard} = shift;
		1130
		1131	return unless $state{connect_guard};
		1132
		1133	# try to use an existing keepalive connection, but only if we, ourselves, plan
		1134	# on a keepalive request (in theory, this should be a separate config option).
		1135	if ($persistent && $KA_CACHE{$ka_key}) {
		1136	$was_persistent = 1;
		1137
		1138	$state{handle} = ka_fetch $ka_key;
		1139	$state{handle}->destroyed
		1140	and die "got a destructed habndle. pah\n";#d#
		1141	$prepare_handle->();
		1142	$state{handle}->destroyed
		1143	and die "got a destructed habndle. pa2\n";#d#
		1144	$handle_actual_request->();
		1145	$state{handle}->destroyed
		1146	and die "got a destructed habndle. pa3\n";#d#
		1147
		1148	} else {
		1149	my $tcp_connect = $arg{tcp_connect}
		1150	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		1151
		1152	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		1153	}
		1154	};
		1155
963	defined wantarray && AnyEvent::Util::guard { %state = () }	1156	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
964	}	1157	}
965		1158
966	sub http_get($@) {	1159	sub http_get($@) {
967	unshift @_, "GET";	1160	unshift @_, "GET";
968	&http_request	1161	&http_request
…		…
986	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1179	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
987	the actual connection, which in turn uses AnyEvent::DNS to resolve	1180	the actual connection, which in turn uses AnyEvent::DNS to resolve
988	hostnames. The latter is a simple stub resolver and does no caching	1181	hostnames. The latter is a simple stub resolver and does no caching
989	on its own. If you want DNS caching, you currently have to provide	1182	on its own. If you want DNS caching, you currently have to provide
990	your own default resolver (by storing a suitable resolver object in	1183	your own default resolver (by storing a suitable resolver object in
991	C<$AnyEvent::DNS::RESOLVER>).	1184	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
992		1185
993	=head2 GLOBAL FUNCTIONS AND VARIABLES	1186	=head2 GLOBAL FUNCTIONS AND VARIABLES
994		1187
995	=over 4	1188	=over 4
996		1189
997	=item AnyEvent::HTTP::set_proxy "proxy-url"	1190	=item AnyEvent::HTTP::set_proxy "proxy-url"
998		1191
999	Sets the default proxy server to use. The proxy-url must begin with a	1192	Sets the default proxy server to use. The proxy-url must begin with a
1000	string of the form C<http://host:port> (optionally C<https:...>), croaks	1193	string of the form C<http://host:port>, croaks otherwise.
1001	otherwise.
1002		1194
1003	To clear an already-set proxy, use C<undef>.	1195	To clear an already-set proxy, use C<undef>.
		1196
		1197	When AnyEvent::HTTP is laoded for the first time it will query the
		1198	default proxy from the operating system, currently by looking at
		1199	C<$ENV{http_proxy>}.
1004		1200
1005	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]	1201	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
1006		1202
1007	Remove all cookies from the cookie jar that have been expired. If	1203	Remove all cookies from the cookie jar that have been expired. If
1008	C<$session_end> is given and true, then additionally remove all session	1204	C<$session_end> is given and true, then additionally remove all session
…		…
1054		1250
1055	=item $AnyEvent::HTTP::MAX_RECURSE	1251	=item $AnyEvent::HTTP::MAX_RECURSE
1056		1252
1057	The default value for the C<recurse> request parameter (default: C<10>).	1253	The default value for the C<recurse> request parameter (default: C<10>).
1058		1254
		1255	=item $AnyEvent::HTTP::TIMEOUT
		1256
		1257	The default timeout for conenction operations (default: C<300>).
		1258
1059	=item $AnyEvent::HTTP::USERAGENT	1259	=item $AnyEvent::HTTP::USERAGENT
1060		1260
1061	The default value for the C<User-Agent> header (the default is	1261	The default value for the C<User-Agent> header (the default is
1062	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1262	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
1063		1263
1064	=item $AnyEvent::HTTP::MAX_PER_HOST	1264	=item $AnyEvent::HTTP::MAX_PER_HOST
1065		1265
1066	The maximum number of concurrent connections to the same host (identified	1266	The maximum number of concurrent connections to the same host (identified
1067	by the hostname). If the limit is exceeded, then the additional requests	1267	by the hostname). If the limit is exceeded, then the additional requests
1068	are queued until previous connections are closed.	1268	are queued until previous connections are closed. Both persistent and
		1269	non-persistent connections are counted in this limit.
1069		1270
1070	The default value for this is C<4>, and it is highly advisable to not	1271	The default value for this is C<4>, and it is highly advisable to not
1071	increase it.	1272	increase it much.
		1273
		1274	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1275	connections, older browsers used 2, newers (such as firefox 3) typically
		1276	use 6, and Opera uses 8 because like, they have the fastest browser and
		1277	give a shit for everybody else on the planet.
		1278
		1279	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1280
		1281	The time after which idle persistent conenctions get closed by
		1282	AnyEvent::HTTP (default: C<3>).
1072		1283
1073	=item $AnyEvent::HTTP::ACTIVE	1284	=item $AnyEvent::HTTP::ACTIVE
1074		1285
1075	The number of active connections. This is not the number of currently	1286	The number of active connections. This is not the number of currently
1076	running requests, but the number of currently open and non-idle TCP	1287	running requests, but the number of currently open and non-idle TCP
1077	connections. This number of can be useful for load-leveling.	1288	connections. This number can be useful for load-leveling.
1078		1289
1079	=back	1290	=back
1080		1291
1081	=cut	1292	=cut
1082		1293
…		…
1125	undef	1336	undef
1126	}	1337	}
1127		1338
1128	sub set_proxy($) {	1339	sub set_proxy($) {
1129	if (length $_[0]) {	1340	if (length $_[0]) {
1130	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1341	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
1131	or Carp::croak "$_[0]: invalid proxy URL";	1342	or Carp::croak "$_[0]: invalid proxy URL";
1132	$PROXY = [$2, $3 \|\| 3128, $1]	1343	$PROXY = [$2, $3 \|\| 3128, $1]
1133	} else {	1344	} else {
1134	undef $PROXY;	1345	undef $PROXY;
1135	}	1346	}
…		…
1138	# initialise proxy from environment	1349	# initialise proxy from environment
1139	eval {	1350	eval {
1140	set_proxy $ENV{http_proxy};	1351	set_proxy $ENV{http_proxy};
1141	};	1352	};
1142		1353
		1354	=head2 SHOWCASE
		1355
		1356	This section contaisn some more elaborate "real-world" examples or code
		1357	snippets.
		1358
		1359	=head2 HTTP/1.1 FILE DOWNLOAD
		1360
		1361	Downloading files with HTTP can be quite tricky, especially when something
		1362	goes wrong and you want to resume.
		1363
		1364	Here is a function that initiates and resumes a download. It uses the
		1365	last modified time to check for file content changes, and works with many
		1366	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1367	on older servers.
		1368
		1369	It calls the completion callback with either C<undef>, which means a
		1370	nonretryable error occured, C<0> when the download was partial and should
		1371	be retried, and C<1> if it was successful.
		1372
		1373	use AnyEvent::HTTP;
		1374
		1375	sub download($$$) {
		1376	my ($url, $file, $cb) = @_;
		1377
		1378	open my $fh, "+<", $file
		1379	or die "$file: $!";
		1380
		1381	my %hdr;
		1382	my $ofs = 0;
		1383
		1384	warn stat $fh;
		1385	warn -s _;
		1386	if (stat $fh and -s _) {
		1387	$ofs = -s _;
		1388	warn "-s is ", $ofs;#d#
		1389	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1390	$hdr{"range"} = "bytes=$ofs-";
		1391	}
		1392
		1393	http_get $url,
		1394	headers => \%hdr,
		1395	on_header => sub {
		1396	my ($hdr) = @_;
		1397
		1398	if ($hdr->{Status} == 200 && $ofs) {
		1399	# resume failed
		1400	truncate $fh, $ofs = 0;
		1401	}
		1402
		1403	sysseek $fh, $ofs, 0;
		1404
		1405	1
		1406	},
		1407	on_body => sub {
		1408	my ($data, $hdr) = @_;
		1409
		1410	if ($hdr->{Status} =~ /^2/) {
		1411	length $data == syswrite $fh, $data
		1412	or return; # abort on write errors
		1413	}
		1414
		1415	1
		1416	},
		1417	sub {
		1418	my (undef, $hdr) = @_;
		1419
		1420	my $status = $hdr->{Status};
		1421
		1422	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1423	utime $fh, $time, $time;
		1424	}
		1425
		1426	if ($status == 200 \|\| $status == 206 \|\| $status == 416) {
		1427	# download ok \|\| resume ok \|\| file already fully downloaded
		1428	$cb->(1, $hdr);
		1429
		1430	} elsif ($status == 412) {
		1431	# file has changed while resuming, delete and retry
		1432	unlink $file;
		1433	$cb->(0, $hdr);
		1434
		1435	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1436	# retry later
		1437	$cb->(0, $hdr);
		1438
		1439	} else {
		1440	$cb->(undef, $hdr);
		1441	}
		1442	}
		1443	;
		1444	}
		1445
		1446	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1447	if ($_[0]) {
		1448	print "OK!\n";
		1449	} elsif (defined $_[0]) {
		1450	print "please retry later\n";
		1451	} else {
		1452	print "ERROR\n";
		1453	}
		1454	};
		1455
1143	=head2 SOCKS PROXIES	1456	=head3 SOCKS PROXIES
1144		1457
1145	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1458	Socks proxies are not directly supported by AnyEvent::HTTP. You can
1146	compile your perl to support socks, or use an external program such as	1459	compile your perl to support socks, or use an external program such as
1147	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy	1460	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
1148	transparently.	1461	transparently.

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.83 by root, Sun Jan 2 05:02:28 2011 UTC vs. Revision 1.103 by root, Thu Feb 24 12:13:11 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.83 by root, Sun Jan 2 05:02:28 2011 UTC vs.
Revision 1.103 by root, Thu Feb 24 12:13:11 2011 UTC