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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.81 by root, Sun Jan 2 01:20:17 2011 UTC vs.
Revision 1.95 by root, Wed Jan 12 03:30:05 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 = '2.02';
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 => $seconds
176		175
177	The time-out to use for various stages - each connect attempt will reset	176	The time-out to use for various stages - each connect attempt will reset
178	the timeout, as will read or write activity, i.e. this is not an overall	177	the timeout, as will read or write activity, i.e. this is not an overall
179	timeout.	178	timeout.
…		…
183	=item proxy => [$host, $port[, $scheme]] or undef	182	=item proxy => [$host, $port[, $scheme]] or undef
184		183
185	Use the given http proxy for all requests. If not specified, then the	184	Use the given http proxy for all requests. If not specified, then the
186	default proxy (as specified by C<$ENV{http_proxy}>) is used.	185	default proxy (as specified by C<$ENV{http_proxy}>) is used.
187		186
188	C<$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.
190		188
191	=item body => $string	189	=item body => $string
192		190
193	The request body, usually empty. Will be sent as-is (future versions of	191	The request body, usually empty. Will be sent as-is (future versions of
194	this module might offer more options).	192	this module might offer more options).
…		…
224	verification, highest compatibility) and high-security (CA and common-name	222	verification, highest compatibility) and high-security (CA and common-name
225	verification) TLS context.	223	verification) TLS context.
226		224
227	The default for this option is C<low>, which could be interpreted as "give	225	The default for this option is C<low>, which could be interpreted as "give
228	me the page, no matter what".	226	me the page, no matter what".
		227
		228	See also the C<sessionid> parameter.
		229
		230	=item session => $string
		231
		232	The module might reuse connections to the same host internally. Sometimes
		233	(e.g. when using TLS), you do not want to reuse connections from other
		234	sessions. This can be achieved by setting this parameter to some unique
		235	ID (such as the address of an object storing your state data, or the TLS
		236	context) - only connections using the same unique ID will be reused.
229		237
230	=item on_prepare => $callback->($fh)	238	=item on_prepare => $callback->($fh)
231		239
232	In rare cases you need to "tune" the socket before it is used to	240	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	241	connect (for exmaple, to bind it on a given IP address). This parameter
…		…
303	called. Instead of the C<$body> argument containing the body data, the	311	called. Instead of the C<$body> argument containing the body data, the
304	callback will receive the L<AnyEvent::Handle> object associated with the	312	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	313	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.	314	(e.g. status C<304>), the empty string will be passed.
307		315
308	The handle object might or might not be in TLS mode, might be connected to	316	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	317	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	318	etc., and configured in unspecified ways. The user is responsible for this
311	module anymore).	319	handle (it will not be used by this module anymore).
312		320
313	This is useful with some push-type services, where, after the initial	321	This is useful with some push-type services, where, after the initial
314	headers, an interactive protocol is used (typical example would be the	322	headers, an interactive protocol is used (typical example would be the
315	push-style twitter API which starts a JSON/XML stream).	323	push-style twitter API which starts a JSON/XML stream).
316		324
317	If you think you need this, first have a look at C<on_body>, to see if	325	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.	326	that doesn't solve your problem in a better way.
		327
		328	=item persistent => $boolean
		329
		330	Try to create/reuse a persistent connection. When this flag is set
		331	(default: true for idempotent requests, false for all others), then
		332	C<http_request> tries to re-use an existing (previously-created)
		333	persistent connection to the host and, failing that, tries to create a new
		334	one.
		335
		336	Requests failing in certain ways will be automatically retried once, which
		337	is dangerous for non-idempotent requests, which is why it defaults to off
		338	for them. The reason for this is because the bozos who designed HTTP/1.1
		339	made it impossible to distinguish between a fatal error and a normal
		340	connection timeout, so you never know whether there was a problem with
		341	your request or not.
		342
		343	When reusing an existent connection, many parameters (such as TLS context)
		344	will be ignored. See the C<session> parameter for a workaround.
		345
		346	=item keepalive => $boolean
		347
		348	Only used when C<persistent> is also true. This parameter decides whether
		349	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		350	(as opposed to only a HTTP/1.1 persistent connection).
		351
		352	The default is true, except when using a proxy, in which case it defaults
		353	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		354
		355	=item handle_params => { key => value ... }
		356
		357	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		358	constructor that is called - not all requests will create a handle, and
		359	sometimes more than one is created, so this parameter is only good for
		360	setting hints.
		361
		362	Example: set the maximum read size to 4096, to potentially conserve memory
		363	at the cost of speed.
		364
		365	handle_params => {
		366	max_read_size => 4096,
		367	},
319		368
320	=back	369	=back
321		370
322	Example: do a simple HTTP GET request for http://www.nethype.de/ and print	371	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
323	the response body.	372	the response body.
…		…
330	Example: do a HTTP HEAD request on https://www.google.com/, use a	379	Example: do a HTTP HEAD request on https://www.google.com/, use a
331	timeout of 30 seconds.	380	timeout of 30 seconds.
332		381
333	http_request	382	http_request
334	GET => "https://www.google.com",	383	GET => "https://www.google.com",
		384	headers => { "user-agent" => "MySearchClient 1.0" },
335	timeout => 30,	385	timeout => 30,
336	sub {	386	sub {
337	my ($body, $hdr) = @_;	387	my ($body, $hdr) = @_;
338	use Data::Dumper;	388	use Data::Dumper;
339	print Dumper $hdr;	389	print Dumper $hdr;
…		…
349	};	399	};
350		400
351	undef $request;	401	undef $request;
352		402
353	=cut	403	=cut
		404
		405	#############################################################################
		406	# wait queue/slots
354		407
355	sub _slot_schedule;	408	sub _slot_schedule;
356	sub _slot_schedule($) {	409	sub _slot_schedule($) {
357	my $host = shift;	410	my $host = shift;
358		411
…		…
381		434
382	_slot_schedule $_[0];	435	_slot_schedule $_[0];
383	}	436	}
384		437
385	#############################################################################	438	#############################################################################
		439	# cookie handling
386		440
387	# expire cookies	441	# expire cookies
388	sub cookie_jar_expire($;$) {	442	sub cookie_jar_expire($;$) {
389	my ($jar, $session_end) = @_;	443	my ($jar, $session_end) = @_;
390		444
…		…
414	}	468	}
415	}	469	}
416		470
417	# extract cookies from jar	471	# extract cookies from jar
418	sub cookie_jar_extract($$$$) {	472	sub cookie_jar_extract($$$$) {
419	my ($jar, $uscheme, $uhost, $upath) = @_;	473	my ($jar, $scheme, $host, $path) = @_;
420		474
421	%$jar = () if $jar->{version} != 1;	475	%$jar = () if $jar->{version} != 1;
422		476
423	my @cookies;	477	my @cookies;
424		478
425	while (my ($chost, $paths) = each %$jar) {	479	while (my ($chost, $paths) = each %$jar) {
426	next unless ref $paths;	480	next unless ref $paths;
427		481
428	if ($chost =~ /^\./) {	482	if ($chost =~ /^\./) {
429	next unless $chost eq substr $uhost, -length $chost;	483	next unless $chost eq substr $host, -length $chost;
430	} elsif ($chost =~ /\./) {	484	} elsif ($chost =~ /\./) {
431	next unless $chost eq $uhost;	485	next unless $chost eq $host;
432	} else {	486	} else {
433	next;	487	next;
434	}	488	}
435		489
436	while (my ($cpath, $cookies) = each %$paths) {	490	while (my ($cpath, $cookies) = each %$paths) {
437	next unless $cpath eq substr $upath, 0, length $cpath;	491	next unless $cpath eq substr $path, 0, length $cpath;
438		492
439	while (my ($cookie, $kv) = each %$cookies) {	493	while (my ($cookie, $kv) = each %$cookies) {
440	next if $uscheme ne "https" && exists $kv->{secure};	494	next if $scheme ne "https" && exists $kv->{secure};
441		495
442	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {	496	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
443	delete $cookies->{$cookie};	497	delete $cookies->{$cookie};
444	next;	498	next;
445	}	499	}
…		…
459	\@cookies	513	\@cookies
460	}	514	}
461		515
462	# parse set_cookie header into jar	516	# parse set_cookie header into jar
463	sub cookie_jar_set_cookie($$$$) {	517	sub cookie_jar_set_cookie($$$$) {
464	my ($jar, $set_cookie, $uhost, $date) = @_;	518	my ($jar, $set_cookie, $host, $date) = @_;
465		519
466	my $anow = int AE::now;	520	my $anow = int AE::now;
467	my $snow; # server-now	521	my $snow; # server-now
468		522
469	for ($set_cookie) {	523	for ($set_cookie) {
…		…
475	while (	529	while (
476	m{	530	m{
477	\G\s*	531	\G\s*
478	(?:	532	(?:
479	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)	533	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
480	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )	534	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) ) )?
481	)	535	)
482	}gcxsi	536	}gcxsi
483	) {	537	) {
484	my $name = $2;	538	my $name = $2;
485	my $value = $4;	539	my $value = $4;
486		540
487	unless (defined $name) {	541	if (defined $1) {
488	# expires	542	# expires
489	$name = "expires";	543	$name = "expires";
490	$value = $1;	544	$value = $1;
491	} elsif (!defined $value) {	545	} elsif (defined $3) {
492	# quoted	546	# quoted
493	$value = $3;	547	$value = $3;
494	$value =~ s/\\(.)/$1/gs;	548	$value =~ s/\\(.)/$1/gs;
495	}	549	}
496		550
497	push @kv, lc $name, $value;	551	push @kv, @kv ? lc $name : $name, $value;
498		552
499	last unless /\G\s*;/gc;	553	last unless /\G\s*;/gc;
500	}	554	}
501		555
502	last unless @kv;	556	last unless @kv;
…		…
525		579
526	# this is not rfc-like and not netscape-like. go figure.	580	# this is not rfc-like and not netscape-like. go figure.
527	my $ndots = $cdom =~ y/.//;	581	my $ndots = $cdom =~ y/.//;
528	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	582	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
529	} else {	583	} else {
530	$cdom = $uhost;	584	$cdom = $host;
531	}	585	}
532		586
533	# store it	587	# store it
534	$jar->{version} = 1;	588	$jar->{version} = 1;
535	$jar->{$cdom}{$cpath}{$name} = \%kv;	589	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
536		590
537	redo if /\G\s*,/gc;	591	redo if /\G\s*,/gc;
538	}	592	}
539	}	593	}
540		594
		595	#############################################################################
		596	# keepalive/persistent connection cache
		597
		598	# fetch a connection from the keepalive cache
		599	sub ka_fetch($) {
		600	my $ka_key = shift;
		601
		602	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		603	delete $KA_CACHE{$ka_key}
		604	unless @{ $KA_CACHE{$ka_key} };
		605
		606	$hdl
		607	}
		608
		609	sub ka_store($$) {
		610	my ($ka_key, $hdl) = @_;
		611
		612	my $kaa = $KA_CACHE{$ka_key} \|\|= [];
		613
		614	my $destroy = sub {
		615	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		616
		617	$hdl->destroy;
		618
		619	@ka
		620	? $KA_CACHE{$ka_key} = \@ka
		621	: delete $KA_CACHE{$ka_key};
		622	};
		623
		624	# on error etc., destroy
		625	$hdl->on_error ($destroy);
		626	$hdl->on_eof ($destroy);
		627	$hdl->on_read ($destroy);
		628	$hdl->timeout ($PERSISTENT_TIMEOUT);
		629
		630	push @$kaa, $hdl;
		631	shift @$kaa while @$kaa > $MAX_PER_HOST;
		632	}
		633
		634	#############################################################################
		635	# utilities
		636
541	# continue to parse $_ for headers and place them into the arg	637	# continue to parse $_ for headers and place them into the arg
542	sub parse_hdr() {	638	sub _parse_hdr() {
543	my %hdr;	639	my %hdr;
544		640
545	# things seen, not parsed:	641	# things seen, not parsed:
546	# p3pP="NON CUR OTPi OUR NOR UNI"	642	# p3pP="NON CUR OTPi OUR NOR UNI"
547		643
…		…
561	for values %hdr;	657	for values %hdr;
562		658
563	\%hdr	659	\%hdr
564	}	660	}
565		661
		662	#############################################################################
		663	# http_get
		664
566	our $qr_nlnl = qr{(?<![^\012])\015?\012};	665	our $qr_nlnl = qr{(?<![^\012])\015?\012};
567		666
568	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	667	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
569	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	668	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		669
		670	# maybe it should just become a normal object :/
		671
		672	sub _destroy_state(\%) {
		673	my ($state) = @_;
		674
		675	$state->{handle}->destroy if $state->{handle};
		676	%$state = ();
		677	}
		678
		679	sub _error(\%$$) {
		680	my ($state, $cb, $hdr) = @_;
		681
		682	&_destroy_state ($state);
		683
		684	$cb->(undef, $hdr);
		685	()
		686	}
570		687
571	sub http_request($$@) {	688	sub http_request($$@) {
572	my $cb = pop;	689	my $cb = pop;
573	my ($method, $url, %arg) = @_;	690	my ($method, $url, %arg) = @_;
574		691
…		…
595	if $recurse < 0;	712	if $recurse < 0;
596		713
597	my $proxy = $arg{proxy} \|\| $PROXY;	714	my $proxy = $arg{proxy} \|\| $PROXY;
598	my $timeout = $arg{timeout} \|\| $TIMEOUT;	715	my $timeout = $arg{timeout} \|\| $TIMEOUT;
599		716
600	my ($uscheme, $uauthority, $upath, $query, $fragment) =	717	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
601	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;	718	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
602		719
603	$uscheme = lc $uscheme;	720	$uscheme = lc $uscheme;
604		721
605	my $uport = $uscheme eq "http" ? 80	722	my $uport = $uscheme eq "http" ? 80
…		…
607	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });	724	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
608		725
609	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	726	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
610	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	727	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
611		728
612	my $uhost = $1;	729	my $uhost = lc $1;
613	$uport = $2 if defined $2;	730	$uport = $2 if defined $2;
614		731
615	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	732	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
616	unless exists $hdr{host};	733	unless exists $hdr{host};
617		734
…		…
636	$rscheme = "http" unless defined $rscheme;	753	$rscheme = "http" unless defined $rscheme;
637		754
638	# don't support https requests over https-proxy transport,	755	# don't support https requests over https-proxy transport,
639	# can't be done with tls as spec'ed, unless you double-encrypt.	756	# can't be done with tls as spec'ed, unless you double-encrypt.
640	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	757	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		758
		759	$rhost = lc $rhost;
		760	$rscheme = lc $rscheme;
641	} else {	761	} else {
642	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	762	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
643	}	763	}
644		764
645	# leave out fragment and query string, just a heuristic	765	# leave out fragment and query string, just a heuristic
…		…
647	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};	767	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
648		768
649	$hdr{"content-length"} = length $arg{body}	769	$hdr{"content-length"} = length $arg{body}
650	if length $arg{body} \|\| $method ne "GET";	770	if length $arg{body} \|\| $method ne "GET";
651		771
652	$hdr{connection} = "close TE"; #1.1	772	my $idempotent = $method =~ /^(?:GET\|HEAD\|PUT\|DELETE\|OPTIONS\|TRACE)$/;
		773
		774	# default value for keepalive is true iff the request is for an idempotent method
		775	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : $idempotent;
		776	my $keepalive10 = exists $arg{keepalive10} ? $arg{keepalive10} : !$proxy;
		777	my $keptalive; # true if this is actually a recycled connection
		778
		779	# the key to use in the keepalive cache
		780	my $ka_key = "$uhost\x00$arg{sessionid}";
		781
		782	$hdr{connection} = ($keepalive ? $keepalive10 ? "keep-alive " : "" : "close ") . "Te"; #1.1
653	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1	783	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
654		784
655	my %state = (connect_guard => 1);	785	my %state = (connect_guard => 1);
		786
		787	my $ae_error = 595; # connecting
		788
		789	# handle actual, non-tunneled, request
		790	my $handle_actual_request = sub {
		791	$ae_error = 596; # request phase
		792
		793	my $hdl = $state{handle};
		794
		795	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		796
		797	# send request
		798	$hdl->push_write (
		799	"$method $rpath HTTP/1.1\015\012"
		800	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		801	. "\015\012"
		802	. (delete $arg{body})
		803	);
		804
		805	# return if error occured during push_write()
		806	return unless %state;
		807
		808	# reduce memory usage, save a kitten, also re-use it for the response headers.
		809	%hdr = ();
		810
		811	# status line and headers
		812	$state{read_response} = sub {
		813	return unless %state;
		814
		815	for ("$_[1]") {
		816	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		817
		818	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		819	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		820
		821	# 100 Continue handling
		822	# should not happen as we don't send expect: 100-continue,
		823	# but we handle it just in case.
		824	# since we send the request body regardless, if we get an error
		825	# we are out of-sync, which we currently do NOT handle correctly.
		826	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		827	if $2 eq 100;
		828
		829	push @pseudo,
		830	HTTPVersion => $1,
		831	Status => $2,
		832	Reason => $3,
		833	;
		834
		835	my $hdr = _parse_hdr
		836	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		837
		838	%hdr = (%$hdr, @pseudo);
		839	}
		840
		841	# redirect handling
		842	# microsoft and other shitheads don't give a shit for following standards,
		843	# try to support some common forms of broken Location headers.
		844	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		845	$hdr{location} =~ s/^\.\/+//;
		846
		847	my $url = "$rscheme://$uhost:$uport";
		848
		849	unless ($hdr{location} =~ s/^\///) {
		850	$url .= $upath;
		851	$url =~ s/\/[^\/]*$//;
		852	}
		853
		854	$hdr{location} = "$url/$hdr{location}";
		855	}
		856
		857	my $redirect;
		858
		859	if ($recurse) {
		860	my $status = $hdr{Status};
		861
		862	# industry standard is to redirect POST as GET for
		863	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		864	# also, the UA should ask the user for 301 and 307 and POST,
		865	# industry standard seems to be to simply follow.
		866	# we go with the industry standard.
		867	if ($status == 301 or $status == 302 or $status == 303) {
		868	# HTTP/1.1 is unclear on how to mutate the method
		869	$method = "GET" unless $method eq "HEAD";
		870	$redirect = 1;
		871	} elsif ($status == 307) {
		872	$redirect = 1;
		873	}
		874	}
		875
		876	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		877	if ($state{handle}) {
		878	# handle keepalive
		879	if (
		880	$keepalive
		881	&& $_[3]
		882	&& ($hdr{HTTPVersion} < 1.1
		883	? $hdr{connection} =~ /\bkeep-?alive\b/i
		884	: $hdr{connection} !~ /\bclose\b/i)
		885	) {
		886	ka_store $ka_key, delete $state{handle};
		887	} else {
		888	# no keepalive, destroy the handle
		889	$state{handle}->destroy;
		890	}
		891	}
		892
		893	%state = ();
		894
		895	if (defined $_[1]) {
		896	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		897	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		898	}
		899
		900	# set-cookie processing
		901	if ($arg{cookie_jar}) {
		902	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		903	}
		904
		905	if ($redirect && exists $hdr{location}) {
		906	# we ignore any errors, as it is very common to receive
		907	# Content-Length != 0 but no actual body
		908	# we also access %hdr, as $_[1] might be an erro
		909	http_request (
		910	$method => $hdr{location},
		911	%arg,
		912	recurse => $recurse - 1,
		913	Redirect => [$_[0], \%hdr],
		914	$cb
		915	);
		916	} else {
		917	$cb->($_[0], \%hdr);
		918	}
		919	};
		920
		921	$ae_error = 597; # body phase
		922
		923	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		924
		925	my $len = $chunked ? undef : $hdr{"content-length"};
		926
		927	# body handling, many different code paths
		928	# - no body expected
		929	# - want_body_handle
		930	# - te chunked
		931	# - 2x length known (with or without on_body)
		932	# - 2x length not known (with or without on_body)
		933	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		934	$finish->(undef, 598 => "Request cancelled by on_header");
		935	} elsif (
		936	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		937	or $method eq "HEAD"
		938	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		939	) {
		940	# no body
		941	$finish->("", undef, undef, 1);
		942
		943	} elsif (!$redirect && $arg{want_body_handle}) {
		944	$_[0]->on_eof (undef);
		945	$_[0]->on_error (undef);
		946	$_[0]->on_read (undef);
		947
		948	$finish->(delete $state{handle});
		949
		950	} elsif ($chunked) {
		951	my $cl = 0;
		952	my $body = "";
		953	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		954
		955	$state{read_chunk} = sub {
		956	$_[1] =~ /^([0-9a-fA-F]+)/
		957	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		958
		959	my $len = hex $1;
		960
		961	if ($len) {
		962	$cl += $len;
		963
		964	$_[0]->push_read (chunk => $len, sub {
		965	$on_body->($_[1], \%hdr)
		966	or return $finish->(undef, 598 => "Request cancelled by on_body");
		967
		968	$_[0]->push_read (line => sub {
		969	length $_[1]
		970	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		971	$_[0]->push_read (line => $state{read_chunk});
		972	});
		973	});
		974	} else {
		975	$hdr{"content-length"} \|\|= $cl;
		976
		977	$_[0]->push_read (line => $qr_nlnl, sub {
		978	if (length $_[1]) {
		979	for ("$_[1]") {
		980	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		981
		982	my $hdr = _parse_hdr
		983	or return $finish->(undef, $ae_error => "Garbled response trailers");
		984
		985	%hdr = (%hdr, %$hdr);
		986	}
		987	}
		988
		989	$finish->($body, undef, undef, 1);
		990	});
		991	}
		992	};
		993
		994	$_[0]->push_read (line => $state{read_chunk});
		995
		996	} elsif ($arg{on_body}) {
		997	if (defined $len) {
		998	$_[0]->on_read (sub {
		999	$len -= length $_[0]{rbuf};
		1000
		1001	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1002	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1003
		1004	$len > 0
		1005	or $finish->("", undef, undef, 1);
		1006	});
		1007	} else {
		1008	$_[0]->on_eof (sub {
		1009	$finish->("");
		1010	});
		1011	$_[0]->on_read (sub {
		1012	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1013	or $finish->(undef, 598 => "Request cancelled by on_body");
		1014	});
		1015	}
		1016	} else {
		1017	$_[0]->on_eof (undef);
		1018
		1019	if (defined $len) {
		1020	$_[0]->on_read (sub {
		1021	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1022	if $len <= length $_[0]{rbuf};
		1023	});
		1024	} else {
		1025	$_[0]->on_error (sub {
		1026	($! == Errno::EPIPE \|\| !$!)
		1027	? $finish->(delete $_[0]{rbuf})
		1028	: $finish->(undef, $ae_error => $_[2]);
		1029	});
		1030	$_[0]->on_read (sub { });
		1031	}
		1032	}
		1033	};
		1034
		1035	# if keepalive is enabled, then the server closing the connection
		1036	# before a response can happen legally - we retry on idempotent methods.
		1037	if ($keptalive && $idempotent) {
		1038	my $old_eof = $hdl->{on_eof};
		1039	$hdl->{on_eof} = sub {
		1040	_destroy_state %state;
		1041
		1042	http_request (
		1043	$method => $url,
		1044	%arg,
		1045	keepalive => 0,
		1046	$cb
		1047	);
		1048	};
		1049	$hdl->on_read (sub {
		1050	return unless %state;
		1051
		1052	# as soon as we receive something, a connection close
		1053	# once more becomes a hard error
		1054	$hdl->{on_eof} = $old_eof;
		1055	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1056	});
		1057	} else {
		1058	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1059	}
		1060	};
		1061
		1062	my $prepare_handle = sub {
		1063	my ($hdl) = $state{handle};
		1064
		1065	$hdl->timeout ($timeout);
		1066	$hdl->on_error (sub {
		1067	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1068	});
		1069	$hdl->on_eof (sub {
		1070	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1071	});
		1072	};
		1073
		1074	# connected to proxy (or origin server)
		1075	my $connect_cb = sub {
		1076	my $fh = shift
		1077	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1078
		1079	return unless delete $state{connect_guard};
		1080
		1081	# get handle
		1082	$state{handle} = new AnyEvent::Handle
		1083	%{ $arg{handle_params} },
		1084	fh => $fh,
		1085	peername => $uhost,
		1086	tls_ctx => $arg{tls_ctx},
		1087	;
		1088
		1089	$prepare_handle->();
		1090
		1091	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1092
		1093	# now handle proxy-CONNECT method
		1094	if ($proxy && $uscheme eq "https") {
		1095	# oh dear, we have to wrap it into a connect request
		1096
		1097	# maybe re-use $uauthority with patched port?
		1098	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		1099	$state{handle}->push_read (line => $qr_nlnl, sub {
		1100	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1101	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1102
		1103	if ($2 == 200) {
		1104	$rpath = $upath;
		1105	$handle_actual_request->();
		1106	} else {
		1107	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1108	}
		1109	});
		1110	} else {
		1111	$handle_actual_request->();
		1112	}
		1113	};
656		1114
657	_get_slot $uhost, sub {	1115	_get_slot $uhost, sub {
658	$state{slot_guard} = shift;	1116	$state{slot_guard} = shift;
659		1117
660	return unless $state{connect_guard};	1118	return unless $state{connect_guard};
661		1119
662	my $ae_error = 595; # connecting	1120	# try to use an existing keepalive connection, but only if we, ourselves, plan
663		1121	# on a keepalive request (in theory, this should be a separate config option).
664	my $connect_cb = sub {	1122	if ($keepalive && $KA_CACHE{$ka_key}) {
665	$state{fh} = shift	1123	$keptalive = 1;
666	or do {	1124	$state{handle} = ka_fetch $ka_key;
667	my $err = "$!";	1125	$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	$state{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 => $state{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 => $state{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->();
945	} else {
946	%state = ();
947	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
948	}
949	});
950	} else {
951	$handle_actual_request->();	1126	$handle_actual_request->();
952	}
953	};
954		1127
		1128	} else {
955	my $tcp_connect = $arg{tcp_connect}	1129	my $tcp_connect = $arg{tcp_connect}
956	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1130	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
957		1131
958	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });	1132	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
959		1133	}
960	};	1134	};
961		1135
962	defined wantarray && AnyEvent::Util::guard { %state = () }	1136	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
963	}	1137	}
964		1138
965	sub http_get($@) {	1139	sub http_get($@) {
966	unshift @_, "GET";	1140	unshift @_, "GET";
967	&http_request	1141	&http_request
…		…
985	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1159	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
986	the actual connection, which in turn uses AnyEvent::DNS to resolve	1160	the actual connection, which in turn uses AnyEvent::DNS to resolve
987	hostnames. The latter is a simple stub resolver and does no caching	1161	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	1162	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	1163	your own default resolver (by storing a suitable resolver object in
990	C<$AnyEvent::DNS::RESOLVER>).	1164	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
991		1165
992	=head2 GLOBAL FUNCTIONS AND VARIABLES	1166	=head2 GLOBAL FUNCTIONS AND VARIABLES
993		1167
994	=over 4	1168	=over 4
995		1169
996	=item AnyEvent::HTTP::set_proxy "proxy-url"	1170	=item AnyEvent::HTTP::set_proxy "proxy-url"
997		1171
998	Sets the default proxy server to use. The proxy-url must begin with a	1172	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	1173	string of the form C<http://host:port>, croaks otherwise.
1000	otherwise.
1001		1174
1002	To clear an already-set proxy, use C<undef>.	1175	To clear an already-set proxy, use C<undef>.
1003		1176
1004	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]	1177	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
1005		1178
…		…
1053		1226
1054	=item $AnyEvent::HTTP::MAX_RECURSE	1227	=item $AnyEvent::HTTP::MAX_RECURSE
1055		1228
1056	The default value for the C<recurse> request parameter (default: C<10>).	1229	The default value for the C<recurse> request parameter (default: C<10>).
1057		1230
		1231	=item $AnyEvent::HTTP::TIMEOUT
		1232
		1233	The default timeout for conenction operations (default: C<300>).
		1234
1058	=item $AnyEvent::HTTP::USERAGENT	1235	=item $AnyEvent::HTTP::USERAGENT
1059		1236
1060	The default value for the C<User-Agent> header (the default is	1237	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)>).	1238	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
1062		1239
1063	=item $AnyEvent::HTTP::MAX_PER_HOST	1240	=item $AnyEvent::HTTP::MAX_PER_HOST
1064		1241
1065	The maximum number of concurrent connections to the same host (identified	1242	The maximum number of concurrent connections to the same host (identified
1066	by the hostname). If the limit is exceeded, then the additional requests	1243	by the hostname). If the limit is exceeded, then the additional requests
1067	are queued until previous connections are closed.	1244	are queued until previous connections are closed. Both persistent and
		1245	non-persistent connections are counted in this limit.
1068		1246
1069	The default value for this is C<4>, and it is highly advisable to not	1247	The default value for this is C<4>, and it is highly advisable to not
1070	increase it.	1248	increase it much.
		1249
		1250	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1251	connections, older browsers used 2, newers (such as firefox 3) typically
		1252	use 6, and Opera uses 8 because like, they have the fastest browser and
		1253	give a shit for everybody else on the planet.
		1254
		1255	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1256
		1257	The time after which idle persistent conenctions get closed by
		1258	AnyEvent::HTTP (default: C<3>).
1071		1259
1072	=item $AnyEvent::HTTP::ACTIVE	1260	=item $AnyEvent::HTTP::ACTIVE
1073		1261
1074	The number of active connections. This is not the number of currently	1262	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	1263	running requests, but the number of currently open and non-idle TCP
1076	connections. This number of can be useful for load-leveling.	1264	connections. This number can be useful for load-leveling.
1077		1265
1078	=back	1266	=back
1079		1267
1080	=cut	1268	=cut
1081		1269
…		…
1124	undef	1312	undef
1125	}	1313	}
1126		1314
1127	sub set_proxy($) {	1315	sub set_proxy($) {
1128	if (length $_[0]) {	1316	if (length $_[0]) {
1129	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1317	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
1130	or Carp::croak "$_[0]: invalid proxy URL";	1318	or Carp::croak "$_[0]: invalid proxy URL";
1131	$PROXY = [$2, $3 \|\| 3128, $1]	1319	$PROXY = [$2, $3 \|\| 3128, $1]
1132	} else {	1320	} else {
1133	undef $PROXY;	1321	undef $PROXY;
1134	}	1322	}
…		…
1137	# initialise proxy from environment	1325	# initialise proxy from environment
1138	eval {	1326	eval {
1139	set_proxy $ENV{http_proxy};	1327	set_proxy $ENV{http_proxy};
1140	};	1328	};
1141		1329
		1330	=head2 SHOWCASE
		1331
		1332	This section contaisn some more elaborate "real-world" examples or code
		1333	snippets.
		1334
		1335	=head2 HTTP/1.1 FILE DOWNLOAD
		1336
		1337	Downloading files with HTTP cna be quite tricky, especially when something
		1338	goes wrong and you want tor esume.
		1339
		1340	Here is a function that initiates and resumes a download. It uses the
		1341	last modified time to check for file content changes, and works with many
		1342	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1343	on older servers.
		1344
		1345	It calls the completion callback with either C<undef>, which means a
		1346	nonretryable error occured, C<0> when the download was partial and should
		1347	be retried, and C<1> if it was successful.
		1348
		1349	use AnyEvent::HTTP;
		1350
		1351	sub download($$$) {
		1352	my ($url, $file, $cb) = @_;
		1353
		1354	open my $fh, "+<", $file
		1355	or die "$file: $!";
		1356
		1357	my %hdr;
		1358	my $ofs = 0;
		1359
		1360	warn stat $fh;
		1361	warn -s _;
		1362	if (stat $fh and -s _) {
		1363	$ofs = -s _;
		1364	warn "-s is ", $ofs;#d#
		1365	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1366	$hdr{"range"} = "bytes=$ofs-";
		1367	}
		1368
		1369	http_get $url,
		1370	headers => \%hdr,
		1371	on_header => sub {
		1372	my ($hdr) = @_;
		1373
		1374	if ($hdr->{Status} == 200 && $ofs) {
		1375	# resume failed
		1376	truncate $fh, $ofs = 0;
		1377	}
		1378
		1379	sysseek $fh, $ofs, 0;
		1380
		1381	1
		1382	},
		1383	on_body => sub {
		1384	my ($data, $hdr) = @_;
		1385
		1386	if ($hdr->{Status} =~ /^2/) {
		1387	length $data == syswrite $fh, $data
		1388	or return; # abort on write errors
		1389	}
		1390
		1391	1
		1392	},
		1393	sub {
		1394	my (undef, $hdr) = @_;
		1395
		1396	my $status = $hdr->{Status};
		1397
		1398	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1399	utime $fh, $time, $time;
		1400	}
		1401
		1402	if ($status == 200 \|\| $status == 206 \|\| $status == 416) {
		1403	# download ok \|\| resume ok \|\| file already fully downloaded
		1404	$cb->(1, $hdr);
		1405
		1406	} elsif ($status == 412) {
		1407	# file has changed while resuming, delete and retry
		1408	unlink $file;
		1409	$cb->(0, $hdr);
		1410
		1411	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1412	# retry later
		1413	$cb->(0, $hdr);
		1414
		1415	} else {
		1416	$cb->(undef, $hdr);
		1417	}
		1418	}
		1419	;
		1420	}
		1421
		1422	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1423	if ($_[0]) {
		1424	print "OK!\n";
		1425	} elsif (defined $_[0]) {
		1426	print "please retry later\n";
		1427	} else {
		1428	print "ERROR\n";
		1429	}
		1430	};
		1431
1142	=head2 SOCKS PROXIES	1432	=head3 SOCKS PROXIES
1143		1433
1144	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1434	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	1435	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	1436	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
1147	transparently.	1437	transparently.

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.81 by root, Sun Jan 2 01:20:17 2011 UTC vs. Revision 1.95 by root, Wed Jan 12 03:30:05 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.81 by root, Sun Jan 2 01:20:17 2011 UTC vs.
Revision 1.95 by root, Wed Jan 12 03:30:05 2011 UTC