ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.79 by root, Sat Jan 1 20:01:07 2011 UTC vs.
Revision 1.98 by root, Mon Jan 24 20:03:24 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 = '2.03';
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).
…		…
196	=item cookie_jar => $hash_ref	194	=item cookie_jar => $hash_ref
197		195
198	Passing this parameter enables (simplified) cookie-processing, loosely	196	Passing this parameter enables (simplified) cookie-processing, loosely
199	based on the original netscape specification.	197	based on the original netscape specification.
200		198
201	The C<$hash_ref> must be an (initially empty) hash reference which will	199	The C<$hash_ref> must be an (initially empty) hash reference which
202	get updated automatically. It is possible to save the cookie jar to	200	will get updated automatically. It is possible to save the cookie jar
203	persistent storage with something like JSON or Storable, but this is not	201	to persistent storage with something like JSON or Storable - see the
204	recommended, as session-only cookies might survive longer than expected.	202	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		203	expired or session-only cookies, and also for documentation on the format
		204	of the cookie jar.
205		205
206	Note that this cookie implementation is not meant to be complete. If	206	Note that this cookie implementation is not meant to be complete. If
207	you want complete cookie management you have to do that on your	207	you want complete cookie management you have to do that on your
208	own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites	208	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
209	working. Cookies are a privacy disaster, do not use them unless required	209	working. Cookies are a privacy disaster, do not use them unless required
210	to.	210	to.
211		211
212	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>	212	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
213	headers will be set and handled by this module, otherwise they will be	213	headers will be set and handled by this module, otherwise they will be
…		…
222	verification, highest compatibility) and high-security (CA and common-name	222	verification, highest compatibility) and high-security (CA and common-name
223	verification) TLS context.	223	verification) TLS context.
224		224
225	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
226	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.
227		237
228	=item on_prepare => $callback->($fh)	238	=item on_prepare => $callback->($fh)
229		239
230	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
231	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
…		…
301	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
302	callback will receive the L<AnyEvent::Handle> object associated with the	312	callback will receive the L<AnyEvent::Handle> object associated with the
303	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
304	(e.g. status C<304>), the empty string will be passed.	314	(e.g. status C<304>), the empty string will be passed.
305		315
306	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
307	a proxy, be a persistent connection etc., and configured in unspecified	317	to a proxy, be a persistent connection, use chunked transfer encoding
308	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
309	module anymore).	319	handle (it will not be used by this module anymore).
310		320
311	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
312	headers, an interactive protocol is used (typical example would be the	322	headers, an interactive protocol is used (typical example would be the
313	push-style twitter API which starts a JSON/XML stream).	323	push-style twitter API which starts a JSON/XML stream).
314		324
315	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
316	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 => $boolean
		347
		348	Only used when C<persistent> is also true. This parameter decides whether
		349	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		350	(as opposed to only a HTTP/1.1 persistent connection).
		351
		352	The default is true, except when using a proxy, in which case it defaults
		353	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		354
		355	=item handle_params => { key => value ... }
		356
		357	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		358	constructor that is called - not all requests will create a handle, and
		359	sometimes more than one is created, so this parameter is only good for
		360	setting hints.
		361
		362	Example: set the maximum read size to 4096, to potentially conserve memory
		363	at the cost of speed.
		364
		365	handle_params => {
		366	max_read_size => 4096,
		367	},
317		368
318	=back	369	=back
319		370
320	Example: do a simple HTTP GET request for http://www.nethype.de/ and print	371	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
321	the response body.	372	the response body.
…		…
328	Example: do a HTTP HEAD request on https://www.google.com/, use a	379	Example: do a HTTP HEAD request on https://www.google.com/, use a
329	timeout of 30 seconds.	380	timeout of 30 seconds.
330		381
331	http_request	382	http_request
332	GET => "https://www.google.com",	383	GET => "https://www.google.com",
		384	headers => { "user-agent" => "MySearchClient 1.0" },
333	timeout => 30,	385	timeout => 30,
334	sub {	386	sub {
335	my ($body, $hdr) = @_;	387	my ($body, $hdr) = @_;
336	use Data::Dumper;	388	use Data::Dumper;
337	print Dumper $hdr;	389	print Dumper $hdr;
…		…
347	};	399	};
348		400
349	undef $request;	401	undef $request;
350		402
351	=cut	403	=cut
		404
		405	#############################################################################
		406	# wait queue/slots
352		407
353	sub _slot_schedule;	408	sub _slot_schedule;
354	sub _slot_schedule($) {	409	sub _slot_schedule($) {
355	my $host = shift;	410	my $host = shift;
356		411
…		…
378	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	433	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
379		434
380	_slot_schedule $_[0];	435	_slot_schedule $_[0];
381	}	436	}
382		437
		438	#############################################################################
		439	# cookie handling
		440
		441	# expire cookies
		442	sub cookie_jar_expire($;$) {
		443	my ($jar, $session_end) = @_;
		444
		445	%$jar = () if $jar->{version} != 1;
		446
		447	my $anow = AE::now;
		448
		449	while (my ($chost, $paths) = each %$jar) {
		450	next unless ref $paths;
		451
		452	while (my ($cpath, $cookies) = each %$paths) {
		453	while (my ($cookie, $kv) = each %$cookies) {
		454	if (exists $kv->{_expires}) {
		455	delete $cookies->{$cookie}
		456	if $anow > $kv->{_expires};
		457	} elsif ($session_end) {
		458	delete $cookies->{$cookie};
		459	}
		460	}
		461
		462	delete $paths->{$cpath}
		463	unless %$cookies;
		464	}
		465
		466	delete $jar->{$chost}
		467	unless %$paths;
		468	}
		469	}
		470
383	# extract cookies from jar	471	# extract cookies from jar
384	sub cookie_jar_extract($$$$) {	472	sub cookie_jar_extract($$$$) {
385	my ($jar, $uscheme, $uhost, $upath) = @_;	473	my ($jar, $scheme, $host, $path) = @_;
386		474
387	%$jar = () if $jar->{version} != 1;	475	%$jar = () if $jar->{version} != 1;
388		476
389	my @cookies;	477	my @cookies;
390		478
391	while (my ($chost, $paths) = each %$jar) {	479	while (my ($chost, $paths) = each %$jar) {
392	next unless ref $paths;	480	next unless ref $paths;
393		481
394	if ($chost =~ /^\./) {	482	if ($chost =~ /^\./) {
395	next unless $chost eq substr $uhost, -length $chost;	483	next unless $chost eq substr $host, -length $chost;
396	} elsif ($chost =~ /\./) {	484	} elsif ($chost =~ /\./) {
397	next unless $chost eq $uhost;	485	next unless $chost eq $host;
398	} else {	486	} else {
399	next;	487	next;
400	}	488	}
401		489
402	while (my ($cpath, $cookies) = each %$paths) {	490	while (my ($cpath, $cookies) = each %$paths) {
403	next unless $cpath eq substr $upath, 0, length $cpath;	491	next unless $cpath eq substr $path, 0, length $cpath;
404		492
405	while (my ($cookie, $kv) = each %$cookies) {	493	while (my ($cookie, $kv) = each %$cookies) {
406	next if $uscheme ne "https" && exists $kv->{secure};	494	next if $scheme ne "https" && exists $kv->{secure};
407		495
408	if (exists $kv->{expires}) {	496	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
409	if (AE::now > parse_date ($kv->{expires})) {
410	delete $cookies->{$cookie};	497	delete $cookies->{$cookie};
411	next;	498	next;
412	}
413	}	499	}
414		500
415	my $value = $kv->{value};	501	my $value = $kv->{value};
416		502
417	if ($value =~ /[=;,[:space:]]/) {	503	if ($value =~ /[=;,[:space:]]/) {
…		…
426		512
427	\@cookies	513	\@cookies
428	}	514	}
429		515
430	# parse set_cookie header into jar	516	# parse set_cookie header into jar
431	sub cookie_jar_set_cookie($$$) {	517	sub cookie_jar_set_cookie($$$$) {
432	my ($jar, $set_cookie, $uhost) = @_;	518	my ($jar, $set_cookie, $host, $date) = @_;
		519
		520	my $anow = int AE::now;
		521	my $snow; # server-now
433		522
434	for ($set_cookie) {	523	for ($set_cookie) {
435	# parse NAME=VALUE	524	# parse NAME=VALUE
436	my @kv;	525	my @kv;
437		526
…		…
440	while (	529	while (
441	m{	530	m{
442	\G\s*	531	\G\s*
443	(?:	532	(?:
444	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)	533	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
445	| ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )	534	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )?
446	)	535	)
447	}gcxsi	536	}gcxsi
448	) {	537	) {
449	my $name = $2;	538	my $name = $2;
450	my $value = $4;	539	my $value = $4;
451		540
452	unless (defined $name) {	541	if (defined $1) {
453	# expires	542	# expires
454	$name = "expires";	543	$name = "expires";
455	$value = $1;	544	$value = $1;
456	} elsif (!defined $value) {	545	} elsif (defined $3) {
457	# quoted	546	# quoted
458	$value = $3;	547	$value = $3;
459	$value =~ s/\\(.)/$1/gs;	548	$value =~ s/\\(.)/$1/gs;
460	}	549	}
461		550
462	push @kv, lc $name, $value;	551	push @kv, @kv ? lc $name : $name, $value;
463		552
464	last unless /\G\s*;/gc;	553	last unless /\G\s*;/gc;
465	}	554	}
466		555
467	last unless @kv;	556	last unless @kv;
468		557
469	my $name = shift @kv;	558	my $name = shift @kv;
470	my %kv = (value => shift @kv, @kv);	559	my %kv = (value => shift @kv, @kv);
471		560
472	$kv{expires} ||= format_date (AE::now + $kv{"max-age"})
473	if exists $kv{"max-age"};	561	if (exists $kv{"max-age"}) {
		562	$kv{_expires} = $anow + delete $kv{"max-age"};
		563	} elsif (exists $kv{expires}) {
		564	$snow ||= parse_date ($date) || $anow;
		565	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		566	} else {
		567	delete $kv{_expires};
		568	}
474		569
475	my $cdom;	570	my $cdom;
476	my $cpath = (delete $kv{path}) || "/";	571	my $cpath = (delete $kv{path}) || "/";
477		572
478	if (exists $kv{domain}) {	573	if (exists $kv{domain}) {
…		…
484		579
485	# this is not rfc-like and not netscape-like. go figure.	580	# this is not rfc-like and not netscape-like. go figure.
486	my $ndots = $cdom =~ y/.//;	581	my $ndots = $cdom =~ y/.//;
487	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	582	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
488	} else {	583	} else {
489	$cdom = $uhost;	584	$cdom = $host;
490	}	585	}
491		586
492	# store it	587	# store it
493	$jar->{version} = 1;	588	$jar->{version} = 1;
494	$jar->{$cdom}{$cpath}{$name} = \%kv;	589	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
495		590
496	redo if /\G\s*,/gc;	591	redo if /\G\s*,/gc;
497	}	592	}
498	}	593	}
499		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
500	# continue to parse $_ for headers and place them into the arg	637	# continue to parse $_ for headers and place them into the arg
501	sub parse_hdr() {	638	sub _parse_hdr() {
502	my %hdr;	639	my %hdr;
503		640
504	# things seen, not parsed:	641	# things seen, not parsed:
505	# p3pP="NON CUR OTPi OUR NOR UNI"	642	# p3pP="NON CUR OTPi OUR NOR UNI"
506		643
…		…
520	for values %hdr;	657	for values %hdr;
521		658
522	\%hdr	659	\%hdr
523	}	660	}
524		661
		662	#############################################################################
		663	# http_get
		664
525	our $qr_nlnl = qr{(?<![^\012])\015?\012};	665	our $qr_nlnl = qr{(?<![^\012])\015?\012};
526		666
527	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	667	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
528	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(\%$$) {
		680	my ($state, $cb, $hdr) = @_;
		681
		682	&_destroy_state ($state);
		683
		684	$cb->(undef, $hdr);
		685	()
		686	}
529		687
530	sub http_request($$@) {	688	sub http_request($$@) {
531	my $cb = pop;	689	my $cb = pop;
532	my ($method, $url, %arg) = @_;	690	my ($method, $url, %arg) = @_;
533		691
…		…
554	if $recurse < 0;	712	if $recurse < 0;
555		713
556	my $proxy = $arg{proxy} || $PROXY;	714	my $proxy = $arg{proxy} || $PROXY;
557	my $timeout = $arg{timeout} || $TIMEOUT;	715	my $timeout = $arg{timeout} || $TIMEOUT;
558		716
559	my ($uscheme, $uauthority, $upath, $query, $fragment) =	717	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
560	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;	718	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;
561		719
562	$uscheme = lc $uscheme;	720	$uscheme = lc $uscheme;
563		721
564	my $uport = $uscheme eq "http" ? 80	722	my $uport = $uscheme eq "http" ? 80
…		…
566	: 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" });
567		725
568	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	726	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
569	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	727	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
570		728
571	my $uhost = $1;	729	my $uhost = lc $1;
572	$uport = $2 if defined $2;	730	$uport = $2 if defined $2;
573		731
574	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	732	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
575	unless exists $hdr{host};	733	unless exists $hdr{host};
576		734
…		…
595	$rscheme = "http" unless defined $rscheme;	753	$rscheme = "http" unless defined $rscheme;
596		754
597	# don't support https requests over https-proxy transport,	755	# don't support https requests over https-proxy transport,
598	# 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.
599	$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;
600	} else {	761	} else {
601	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	762	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
602	}	763	}
603		764
604	# leave out fragment and query string, just a heuristic	765	# leave out fragment and query string, just a heuristic
…		…
606	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};	767	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
607		768
608	$hdr{"content-length"} = length $arg{body}	769	$hdr{"content-length"} = length $arg{body}
609	if length $arg{body} || $method ne "GET";	770	if length $arg{body} || $method ne "GET";
610		771
611	$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
612	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1	783	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
613		784
614	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	};
615		1114
616	_get_slot $uhost, sub {	1115	_get_slot $uhost, sub {
617	$state{slot_guard} = shift;	1116	$state{slot_guard} = shift;
618		1117
619	return unless $state{connect_guard};	1118	return unless $state{connect_guard};
620		1119
621	my $ae_error = 595; # connecting	1120	# try to use an existing keepalive connection, but only if we, ourselves, plan
622		1121	# on a keepalive request (in theory, this should be a separate config option).
623	my $connect_cb = sub {	1122	if ($keepalive && $KA_CACHE{$ka_key}) {
624	$state{fh} = shift	1123	$keptalive = 1;
625	or do {	1124	$state{handle} = ka_fetch $ka_key;
626	my $err = "$!";	1125	$prepare_handle->();
627	%state = ();
628	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
629	};
630
631	return unless delete $state{connect_guard};
632
633	# get handle
634	$state{handle} = new AnyEvent::Handle
635	fh => $state{fh},
636	peername => $rhost,
637	tls_ctx => $arg{tls_ctx},
638	# these need to be reconfigured on keepalive handles
639	timeout => $timeout,
640	on_error => sub {
641	%state = ();
642	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
643	},
644	on_eof => sub {
645	%state = ();
646	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
647	},
648	;
649
650	# limit the number of persistent connections
651	# keepalive not yet supported
652	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
653	# ++$KA_COUNT{$_[1]};
654	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
655	# --$KA_COUNT{$_[1]}
656	# };
657	# $hdr{connection} = "keep-alive";
658	# }
659
660	$state{handle}->starttls ("connect") if $rscheme eq "https";
661
662	# handle actual, non-tunneled, request
663	my $handle_actual_request = sub {
664	$ae_error = 596; # request phase
665
666	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
667
668	# send request
669	$state{handle}->push_write (
670	"$method $rpath HTTP/1.1\015\012"
671	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
672	. "\015\012"
673	. (delete $arg{body})
674	);
675
676	# return if error occured during push_write()
677	return unless %state;
678
679	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
680
681	# status line and headers
682	$state{read_response} = sub {
683	for ("$_[1]") {
684	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
685
686	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
687	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
688
689	# 100 Continue handling
690	# should not happen as we don't send expect: 100-continue,
691	# but we handle it just in case.
692	# since we send the request body regardless, if we get an error
693	# we are out of-sync, which we currently do NOT handle correctly.
694	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
695	if $2 eq 100;
696
697	push @pseudo,
698	HTTPVersion => $1,
699	Status => $2,
700	Reason => $3,
701	;
702
703	my $hdr = parse_hdr
704	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
705
706	%hdr = (%$hdr, @pseudo);
707	}
708
709	# redirect handling
710	# microsoft and other shitheads don't give a shit for following standards,
711	# try to support some common forms of broken Location headers.
712	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
713	$hdr{location} =~ s/^\.\/+//;
714
715	my $url = "$rscheme://$uhost:$uport";
716
717	unless ($hdr{location} =~ s/^\///) {
718	$url .= $upath;
719	$url =~ s/\/[^\/]*$//;
720	}
721
722	$hdr{location} = "$url/$hdr{location}";
723	}
724
725	my $redirect;
726
727	if ($recurse) {
728	my $status = $hdr{Status};
729
730	# industry standard is to redirect POST as GET for
731	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
732	# also, the UA should ask the user for 301 and 307 and POST,
733	# industry standard seems to be to simply follow.
734	# we go with the industry standard.
735	if ($status == 301 or $status == 302 or $status == 303) {
736	# HTTP/1.1 is unclear on how to mutate the method
737	$method = "GET" unless $method eq "HEAD";
738	$redirect = 1;
739	} elsif ($status == 307) {
740	$redirect = 1;
741	}
742	}
743
744	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
745	my $may_keep_alive = $_[3];
746
747	$state{handle}->destroy if $state{handle};
748	%state = ();
749
750	if (defined $_[1]) {
751	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
752	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
753	}
754
755	# set-cookie processing
756	if ($arg{cookie_jar}) {
757	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost;
758	}
759
760	if ($redirect && exists $hdr{location}) {
761	# we ignore any errors, as it is very common to receive
762	# Content-Length != 0 but no actual body
763	# we also access %hdr, as $_[1] might be an erro
764	http_request (
765	$method => $hdr{location},
766	%arg,
767	recurse => $recurse - 1,
768	Redirect => [$_[0], \%hdr],
769	$cb);
770	} else {
771	$cb->($_[0], \%hdr);
772	}
773	};
774
775	$ae_error = 597; # body phase
776
777	my $len = $hdr{"content-length"};
778
779	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
780	$finish->(undef, 598 => "Request cancelled by on_header");
781	} elsif (
782	$hdr{Status} =~ /^(?:1..|204|205|304)$/
783	or $method eq "HEAD"
784	or (defined $len && !$len)
785	) {
786	# no body
787	$finish->("", undef, undef, 1);
788	} else {
789	# body handling, many different code paths
790	# - no body expected
791	# - want_body_handle
792	# - te chunked
793	# - 2x length known (with or without on_body)
794	# - 2x length not known (with or without on_body)
795	if (!$redirect && $arg{want_body_handle}) {
796	$_[0]->on_eof (undef);
797	$_[0]->on_error (undef);
798	$_[0]->on_read (undef);
799
800	$finish->(delete $state{handle});
801
802	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
803	my $cl = 0;
804	my $body = undef;
805	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
806
807	my $read_chunk; $read_chunk = sub {
808	$_[1] =~ /^([0-9a-fA-F]+)/
809	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
810
811	my $len = hex $1;
812
813	if ($len) {
814	$cl += $len;
815
816	$_[0]->push_read (chunk => $len, sub {
817	$on_body->($_[1], \%hdr)
818	or return $finish->(undef, 598 => "Request cancelled by on_body");
819
820	$_[0]->push_read (line => sub {
821	length $_[1]
822	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
823	$_[0]->push_read (line => $read_chunk);
824	});
825	});
826	} else {
827	$hdr{"content-length"} ||= $cl;
828
829	$_[0]->push_read (line => $qr_nlnl, sub {
830	if (length $_[1]) {
831	for ("$_[1]") {
832	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
833
834	my $hdr = parse_hdr
835	or return $finish->(undef, $ae_error => "Garbled response trailers");
836
837	%hdr = (%hdr, %$hdr);
838	}
839	}
840
841	$finish->($body, undef, undef, 1);
842	});
843	}
844	};
845
846	$_[0]->push_read (line => $read_chunk);
847
848	} elsif ($arg{on_body}) {
849	if ($len) {
850	$_[0]->on_read (sub {
851	$len -= length $_[0]{rbuf};
852
853	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
854	or return $finish->(undef, 598 => "Request cancelled by on_body");
855
856	$len > 0
857	or $finish->("", undef, undef, 1);
858	});
859	} else {
860	$_[0]->on_eof (sub {
861	$finish->("");
862	});
863	$_[0]->on_read (sub {
864	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
865	or $finish->(undef, 598 => "Request cancelled by on_body");
866	});
867	}
868	} else {
869	$_[0]->on_eof (undef);
870
871	if ($len) {
872	$_[0]->on_read (sub {
873	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
874	if $len <= length $_[0]{rbuf};
875	});
876	} else {
877	$_[0]->on_error (sub {
878	($! == Errno::EPIPE || !$!)
879	? $finish->(delete $_[0]{rbuf})
880	: $finish->(undef, $ae_error => $_[2]);
881	});
882	$_[0]->on_read (sub { });
883	}
884	}
885	}
886	};
887
888	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
889	};
890
891	# now handle proxy-CONNECT method
892	if ($proxy && $uscheme eq "https") {
893	# oh dear, we have to wrap it into a connect request
894
895	# maybe re-use $uauthority with patched port?
896	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
897	$state{handle}->push_read (line => $qr_nlnl, sub {
898	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
899	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
900
901	if ($2 == 200) {
902	$rpath = $upath;
903	&$handle_actual_request;	1126	$handle_actual_request->();
904	} else {	1127
905	%state = ();
906	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
907	}
908	});
909	} else {	1128	} else {
910	&$handle_actual_request;
911	}
912	};
913
914	my $tcp_connect = $arg{tcp_connect}	1129	my $tcp_connect = $arg{tcp_connect}
915	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1130	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
916		1131
917	$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 });
918		1133	}
919	};	1134	};
920		1135
921	defined wantarray && AnyEvent::Util::guard { %state = () }	1136	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
922	}	1137	}
923		1138
924	sub http_get($@) {	1139	sub http_get($@) {
925	unshift @_, "GET";	1140	unshift @_, "GET";
926	&http_request	1141	&http_request
…		…
944	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1159	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
945	the actual connection, which in turn uses AnyEvent::DNS to resolve	1160	the actual connection, which in turn uses AnyEvent::DNS to resolve
946	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
947	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
948	your own default resolver (by storing a suitable resolver object in	1163	your own default resolver (by storing a suitable resolver object in
949	C<$AnyEvent::DNS::RESOLVER>).	1164	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
950		1165
951	=head2 GLOBAL FUNCTIONS AND VARIABLES	1166	=head2 GLOBAL FUNCTIONS AND VARIABLES
952		1167
953	=over 4	1168	=over 4
954		1169
955	=item AnyEvent::HTTP::set_proxy "proxy-url"	1170	=item AnyEvent::HTTP::set_proxy "proxy-url"
956		1171
957	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
958	string of the form C<http://host:port> (optionally C<https:...>), croaks	1173	string of the form C<http://host:port>, croaks otherwise.
959	otherwise.
960		1174
961	To clear an already-set proxy, use C<undef>.	1175	To clear an already-set proxy, use C<undef>.
		1176
		1177	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1178
		1179	Remove all cookies from the cookie jar that have been expired. If
		1180	C<$session_end> is given and true, then additionally remove all session
		1181	cookies.
		1182
		1183	You should call this function (with a true C<$session_end>) before you
		1184	save cookies to disk, and you should call this function after loading them
		1185	again. If you have a long-running program you can additonally call this
		1186	function from time to time.
		1187
		1188	A cookie jar is initially an empty hash-reference that is managed by this
		1189	module. It's format is subject to change, but currently it is like this:
		1190
		1191	The key C<version> has to contain C<1>, otherwise the hash gets
		1192	emptied. All other keys are hostnames or IP addresses pointing to
		1193	hash-references. The key for these inner hash references is the
		1194	server path for which this cookie is meant, and the values are again
		1195	hash-references. The keys of those hash-references is the cookie name, and
		1196	the value, you guessed it, is another hash-reference, this time with the
		1197	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1198	which have been replaced by a C<_expires> key that contains the cookie
		1199	expiry timestamp.
		1200
		1201	Here is an example of a cookie jar with a single cookie, so you have a
		1202	chance of understanding the above paragraph:
		1203
		1204	{
		1205	version => 1,
		1206	"10.0.0.1" => {
		1207	"/" => {
		1208	"mythweb_id" => {
		1209	_expires => 1293917923,
		1210	value => "ooRung9dThee3ooyXooM1Ohm",
		1211	},
		1212	},
		1213	},
		1214	}
962		1215
963	=item $date = AnyEvent::HTTP::format_date $timestamp	1216	=item $date = AnyEvent::HTTP::format_date $timestamp
964		1217
965	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP	1218	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
966	Date (RFC 2616).	1219	Date (RFC 2616).
…		…
973		1226
974	=item $AnyEvent::HTTP::MAX_RECURSE	1227	=item $AnyEvent::HTTP::MAX_RECURSE
975		1228
976	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>).
977		1230
		1231	=item $AnyEvent::HTTP::TIMEOUT
		1232
		1233	The default timeout for conenction operations (default: C<300>).
		1234
978	=item $AnyEvent::HTTP::USERAGENT	1235	=item $AnyEvent::HTTP::USERAGENT
979		1236
980	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
981	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)>).
982		1239
983	=item $AnyEvent::HTTP::MAX_PER_HOST	1240	=item $AnyEvent::HTTP::MAX_PER_HOST
984		1241
985	The maximum number of concurrent connections to the same host (identified	1242	The maximum number of concurrent connections to the same host (identified
986	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
987	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.
988		1246
989	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
990	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>).
991		1259
992	=item $AnyEvent::HTTP::ACTIVE	1260	=item $AnyEvent::HTTP::ACTIVE
993		1261
994	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
995	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
996	connections. This number of can be useful for load-leveling.	1264	connections. This number can be useful for load-leveling.
997		1265
998	=back	1266	=back
999		1267
1000	=cut	1268	=cut
1001		1269
…		…
1044	undef	1312	undef
1045	}	1313	}
1046		1314
1047	sub set_proxy($) {	1315	sub set_proxy($) {
1048	if (length $_[0]) {	1316	if (length $_[0]) {
1049	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1317	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
1050	or Carp::croak "$_[0]: invalid proxy URL";	1318	or Carp::croak "$_[0]: invalid proxy URL";
1051	$PROXY = [$2, $3 || 3128, $1]	1319	$PROXY = [$2, $3 || 3128, $1]
1052	} else {	1320	} else {
1053	undef $PROXY;	1321	undef $PROXY;
1054	}	1322	}
…		…
1057	# initialise proxy from environment	1325	# initialise proxy from environment
1058	eval {	1326	eval {
1059	set_proxy $ENV{http_proxy};	1327	set_proxy $ENV{http_proxy};
1060	};	1328	};
1061		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 can be quite tricky, especially when something
		1338	goes wrong and you want to resume.
		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
1062	=head2 SOCKS PROXIES	1432	=head3 SOCKS PROXIES
1063		1433
1064	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1434	Socks proxies are not directly supported by AnyEvent::HTTP. You can
1065	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
1066	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
1067	transparently.	1437	transparently.

Diff Legend

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