ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.57 by root, Mon Sep 6 06:31:32 2010 UTC vs.
Revision 1.108 by root, Thu Jun 30 09:12:39 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::Socket ();
49	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
50		48
51	use base Exporter::;	49	use base Exporter::;
52		50
53	our $VERSION = '1.46';	51	our $VERSION = '2.12';
54		52
55	our @EXPORT = qw(http_get http_post http_head http_request);	53	our @EXPORT = qw(http_get http_post http_head http_request);
56		54
57	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)";
58	our $MAX_RECURSE = 10;	56	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	57	our $PERSISTENT_TIMEOUT = 3;
61	our $TIMEOUT = 300;	58	our $TIMEOUT = 300;
62		59	our $MAX_PER_HOST = 4; # changing this is evil
63	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;
66		60
67	our $PROXY;	61	our $PROXY;
68	our $ACTIVE = 0;	62	our $ACTIVE = 0;
69		63
70	my %KA_COUNT; # number of open keep-alive connections per host	64	my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array
71	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
72		66
73	=item http_get $url, key => value..., $cb->($data, $headers)	67	=item http_get $url, key => value..., $cb->($data, $headers)
74		68
75	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
…		…
92	must be an absolute http or https URL.	86	must be an absolute http or https URL.
93		87
94	When called in void context, nothing is returned. In other contexts,	88	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	89	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	90	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	91	destroyed before the callback is called, the request will be cancelled.
98		92
99	The callback will be called with the response body data as first argument	93	The callback will be called with the response body data as first argument
100	(or C<undef> if an error occured), and a hash-ref with response headers as	94	(or C<undef> if an error occured), and a hash-ref with response headers
101	second argument.	95	(and trailers) as second argument.
102		96
103	All the headers in that hash are lowercased. In addition to the response	97	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" (uppercase to avoid clashing with possible	98	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
105	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the	99	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
106	three parts of the HTTP Status-Line of the same name.	100	three parts of the HTTP Status-Line of the same name. If an error occurs
		101	during the body phase of a request, then the original C<Status> and
		102	C<Reason> values from the header are available as C<OrigStatus> and
		103	C<OrigReason>.
107		104
108	The pseudo-header C<URL> contains the actual URL (which can differ from	105	The pseudo-header C<URL> contains the actual URL (which can differ from
109	the requested URL when following redirects - for example, you might get	106	the requested URL when following redirects - for example, you might get
110	an error that your URL scheme is not supported even though your URL is a	107	an error that your URL scheme is not supported even though your URL is a
111	valid http URL because it redirected to an ftp URL, in which case you can	108	valid http URL because it redirected to an ftp URL, in which case you can
…		…
120		117
121	If the server sends a header multiple times, then their contents will be	118	If the server sends a header multiple times, then their contents will be
122	joined together with a comma (C<,>), as per the HTTP spec.	119	joined together with a comma (C<,>), as per the HTTP spec.
123		120
124	If an internal error occurs, such as not being able to resolve a hostname,	121	If an internal error occurs, such as not being able to resolve a hostname,
125	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>	122	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
126	(usually C<599>) and the C<Reason> pseudo-header will contain an error	123	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
127	message.	124	message. Currently the following status codes are used:
		125
		126	=over 4
		127
		128	=item 595 - errors during connection etsbalishment, proxy handshake.
		129
		130	=item 596 - errors during TLS negotiation, request sending and header processing.
		131
		132	=item 597 - errors during body receiving or processing.
		133
		134	=item 598 - user aborted request via C<on_header> or C<on_body>.
		135
		136	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		137
		138	=back
128		139
129	A typical callback might look like this:	140	A typical callback might look like this:
130		141
131	sub {	142	sub {
132	my ($body, $hdr) = @_;	143	my ($body, $hdr) = @_;
…		…
148	Whether to recurse requests or not, e.g. on redirects, authentication	159	Whether to recurse requests or not, e.g. on redirects, authentication
149	retries and so on, and how often to do so.	160	retries and so on, and how often to do so.
150		161
151	=item headers => hashref	162	=item headers => hashref
152		163
153	The request headers to use. Currently, C<http_request> may provide its	164	The request headers to use. Currently, C<http_request> may provide its own
154	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	165	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
155	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be	166	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
156	suppressed by using C<undef> for these headers in which case they won't be	167	(this can be suppressed by using C<undef> for these headers in which case
157	sent at all).	168	they won't be sent at all).
		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
		174	Also, make sure that your headers names and values do not contain any
		175	embedded newlines.
158		176
159	=item timeout => $seconds	177	=item timeout => $seconds
160		178
161	The time-out to use for various stages - each connect attempt will reset	179	The time-out to use for various stages - each connect attempt will reset
162	the timeout, as will read or write activity, i.e. this is not an overall	180	the timeout, as will read or write activity, i.e. this is not an overall
…		…
164		182
165	Default timeout is 5 minutes.	183	Default timeout is 5 minutes.
166		184
167	=item proxy => [$host, $port[, $scheme]] or undef	185	=item proxy => [$host, $port[, $scheme]] or undef
168		186
169	Use the given http proxy for all requests. If not specified, then the	187	Use the given http proxy for all requests, or no proxy if C<undef> is
170	default proxy (as specified by C<$ENV{http_proxy}>) is used.	188	used.
171		189
172	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	190	C<$scheme> must be either missing or must be C<http> for HTTP.
173	HTTPS.	191
		192	If not specified, then the default proxy is used (see
		193	C<AnyEvent::HTTP::set_proxy>).
174		194
175	=item body => $string	195	=item body => $string
176		196
177	The request body, usually empty. Will be-sent as-is (future versions of	197	The request body, usually empty. Will be sent as-is (future versions of
178	this module might offer more options).	198	this module might offer more options).
179		199
180	=item cookie_jar => $hash_ref	200	=item cookie_jar => $hash_ref
181		201
182	Passing this parameter enables (simplified) cookie-processing, loosely	202	Passing this parameter enables (simplified) cookie-processing, loosely
183	based on the original netscape specification.	203	based on the original netscape specification.
184		204
185	The C<$hash_ref> must be an (initially empty) hash reference which will	205	The C<$hash_ref> must be an (initially empty) hash reference which
186	get updated automatically. It is possible to save the cookie_jar to	206	will get updated automatically. It is possible to save the cookie jar
187	persistent storage with something like JSON or Storable, but this is not	207	to persistent storage with something like JSON or Storable - see the
188	recommended, as expiry times are currently being ignored.	208	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		209	expired or session-only cookies, and also for documentation on the format
		210	of the cookie jar.
189		211
190	Note that this cookie implementation is not of very high quality, nor	212	Note that this cookie implementation is not meant to be complete. If
191	meant to be complete. If you want complete cookie management you have to	213	you want complete cookie management you have to do that on your
192	do that on your own. C<cookie_jar> is meant as a quick fix to get some	214	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
193	cookie-using sites working. Cookies are a privacy disaster, do not use	215	working. Cookies are a privacy disaster, do not use them unless required
194	them unless required to.	216	to.
		217
		218	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		219	headers will be set and handled by this module, otherwise they will be
		220	left untouched.
195		221
196	=item tls_ctx => $scheme | $tls_ctx	222	=item tls_ctx => $scheme | $tls_ctx
197		223
198	Specifies the AnyEvent::TLS context to be used for https connections. This	224	Specifies the AnyEvent::TLS context to be used for https connections. This
199	parameter follows the same rules as the C<tls_ctx> parameter to	225	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
203	verification) TLS context.	229	verification) TLS context.
204		230
205	The default for this option is C<low>, which could be interpreted as "give	231	The default for this option is C<low>, which could be interpreted as "give
206	me the page, no matter what".	232	me the page, no matter what".
207		233
		234	See also the C<sessionid> parameter.
		235
		236	=item session => $string
		237
		238	The module might reuse connections to the same host internally. Sometimes
		239	(e.g. when using TLS), you do not want to reuse connections from other
		240	sessions. This can be achieved by setting this parameter to some unique
		241	ID (such as the address of an object storing your state data, or the TLS
		242	context) - only connections using the same unique ID will be reused.
		243
208	=item on_prepare => $callback->($fh)	244	=item on_prepare => $callback->($fh)
209		245
210	In rare cases you need to "tune" the socket before it is used to	246	In rare cases you need to "tune" the socket before it is used to
211	connect (for exmaple, to bind it on a given IP address). This parameter	247	connect (for exmaple, to bind it on a given IP address). This parameter
212	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>	248	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
213	and behaves exactly the same way (e.g. it has to provide a	249	and behaves exactly the same way (e.g. it has to provide a
214	timeout). See the description for the C<$prepare_cb> argument of	250	timeout). See the description for the C<$prepare_cb> argument of
215	C<AnyEvent::Socket::tcp_connect> for details.	251	C<AnyEvent::Socket::tcp_connect> for details.
216		252
		253	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		254
		255	In even rarer cases you want total control over how AnyEvent::HTTP
		256	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		257	to do this, but you can provide your own C<tcp_connect> function -
		258	obviously, it has to follow the same calling conventions, except that it
		259	may always return a connection guard object.
		260
		261	There are probably lots of weird uses for this function, starting from
		262	tracing the hosts C<http_request> actually tries to connect, to (inexact
		263	but fast) host => IP address caching or even socks protocol support.
		264
217	=item on_header => $callback->($headers)	265	=item on_header => $callback->($headers)
218		266
219	When specified, this callback will be called with the header hash as soon	267	When specified, this callback will be called with the header hash as soon
220	as headers have been successfully received from the remote server (not on	268	as headers have been successfully received from the remote server (not on
221	locally-generated errors).	269	locally-generated errors).
…		…
226		274
227	This callback is useful, among other things, to quickly reject unwanted	275	This callback is useful, among other things, to quickly reject unwanted
228	content, which, if it is supposed to be rare, can be faster than first	276	content, which, if it is supposed to be rare, can be faster than first
229	doing a C<HEAD> request.	277	doing a C<HEAD> request.
230		278
		279	The downside is that cancelling the request makes it impossible to re-use
		280	the connection. Also, the C<on_header> callback will not receive any
		281	trailer (headers sent after the response body).
		282
231	Example: cancel the request unless the content-type is "text/html".	283	Example: cancel the request unless the content-type is "text/html".
232		284
233	on_header => sub {	285	on_header => sub {
234	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/	286	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/
235	},	287	},
…		…
241	string instead of the body data.	293	string instead of the body data.
242		294
243	It has to return either true (in which case AnyEvent::HTTP will continue),	295	It has to return either true (in which case AnyEvent::HTTP will continue),
244	or false, in which case AnyEvent::HTTP will cancel the download (and call	296	or false, in which case AnyEvent::HTTP will cancel the download (and call
245	the completion callback with an error code of C<598>).	297	the completion callback with an error code of C<598>).
		298
		299	The downside to cancelling the request is that it makes it impossible to
		300	re-use the connection.
246		301
247	This callback is useful when the data is too large to be held in memory	302	This callback is useful when the data is too large to be held in memory
248	(so the callback writes it to a file) or when only some information should	303	(so the callback writes it to a file) or when only some information should
249	be extracted, or when the body should be processed incrementally.	304	be extracted, or when the body should be processed incrementally.
250		305
…		…
262	called. Instead of the C<$body> argument containing the body data, the	317	called. Instead of the C<$body> argument containing the body data, the
263	callback will receive the L<AnyEvent::Handle> object associated with the	318	callback will receive the L<AnyEvent::Handle> object associated with the
264	connection. In error cases, C<undef> will be passed. When there is no body	319	connection. In error cases, C<undef> will be passed. When there is no body
265	(e.g. status C<304>), the empty string will be passed.	320	(e.g. status C<304>), the empty string will be passed.
266		321
267	The handle object might or might not be in TLS mode, might be connected to	322	The handle object might or might not be in TLS mode, might be connected
268	a proxy, be a persistent connection etc., and configured in unspecified	323	to a proxy, be a persistent connection, use chunked transfer encoding
269	ways. The user is responsible for this handle (it will not be used by this	324	etc., and configured in unspecified ways. The user is responsible for this
270	module anymore).	325	handle (it will not be used by this module anymore).
271		326
272	This is useful with some push-type services, where, after the initial	327	This is useful with some push-type services, where, after the initial
273	headers, an interactive protocol is used (typical example would be the	328	headers, an interactive protocol is used (typical example would be the
274	push-style twitter API which starts a JSON/XML stream).	329	push-style twitter API which starts a JSON/XML stream).
275		330
276	If you think you need this, first have a look at C<on_body>, to see if	331	If you think you need this, first have a look at C<on_body>, to see if
277	that doesn't solve your problem in a better way.	332	that doesn't solve your problem in a better way.
278		333
		334	=item persistent => $boolean
		335
		336	Try to create/reuse a persistent connection. When this flag is set
		337	(default: true for idempotent requests, false for all others), then
		338	C<http_request> tries to re-use an existing (previously-created)
		339	persistent connection to the host and, failing that, tries to create a new
		340	one.
		341
		342	Requests failing in certain ways will be automatically retried once, which
		343	is dangerous for non-idempotent requests, which is why it defaults to off
		344	for them. The reason for this is because the bozos who designed HTTP/1.1
		345	made it impossible to distinguish between a fatal error and a normal
		346	connection timeout, so you never know whether there was a problem with
		347	your request or not.
		348
		349	When reusing an existent connection, many parameters (such as TLS context)
		350	will be ignored. See the C<session> parameter for a workaround.
		351
		352	=item keepalive => $boolean
		353
		354	Only used when C<persistent> is also true. This parameter decides whether
		355	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		356	(as opposed to only a HTTP/1.1 persistent connection).
		357
		358	The default is true, except when using a proxy, in which case it defaults
		359	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		360
		361	=item handle_params => { key => value ... }
		362
		363	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		364	constructor that is called - not all requests will create a handle, and
		365	sometimes more than one is created, so this parameter is only good for
		366	setting hints.
		367
		368	Example: set the maximum read size to 4096, to potentially conserve memory
		369	at the cost of speed.
		370
		371	handle_params => {
		372	max_read_size => 4096,
		373	},
		374
279	=back	375	=back
280		376
281	Example: make a simple HTTP GET request for http://www.nethype.de/	377	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		378	the response body.
282		379
283	http_request GET => "http://www.nethype.de/", sub {	380	http_request GET => "http://www.nethype.de/", sub {
284	my ($body, $hdr) = @_;	381	my ($body, $hdr) = @_;
285	print "$body\n";	382	print "$body\n";
286	};	383	};
287		384
288	Example: make a HTTP HEAD request on https://www.google.com/, use a	385	Example: do a HTTP HEAD request on https://www.google.com/, use a
289	timeout of 30 seconds.	386	timeout of 30 seconds.
290		387
291	http_request	388	http_request
292	GET => "https://www.google.com",	389	GET => "https://www.google.com",
		390	headers => { "user-agent" => "MySearchClient 1.0" },
293	timeout => 30,	391	timeout => 30,
294	sub {	392	sub {
295	my ($body, $hdr) = @_;	393	my ($body, $hdr) = @_;
296	use Data::Dumper;	394	use Data::Dumper;
297	print Dumper $hdr;	395	print Dumper $hdr;
298	}	396	}
299	;	397	;
300		398
301	Example: make another simple HTTP GET request, but immediately try to	399	Example: do another simple HTTP GET request, but immediately try to
302	cancel it.	400	cancel it.
303		401
304	my $request = http_request GET => "http://www.nethype.de/", sub {	402	my $request = http_request GET => "http://www.nethype.de/", sub {
305	my ($body, $hdr) = @_;	403	my ($body, $hdr) = @_;
306	print "$body\n";	404	print "$body\n";
307	};	405	};
308		406
309	undef $request;	407	undef $request;
310		408
311	=cut	409	=cut
		410
		411	#############################################################################
		412	# wait queue/slots
312		413
313	sub _slot_schedule;	414	sub _slot_schedule;
314	sub _slot_schedule($) {	415	sub _slot_schedule($) {
315	my $host = shift;	416	my $host = shift;
316		417
…		…
338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	439	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
339		440
340	_slot_schedule $_[0];	441	_slot_schedule $_[0];
341	}	442	}
342		443
		444	#############################################################################
		445	# cookie handling
		446
		447	# expire cookies
		448	sub cookie_jar_expire($;$) {
		449	my ($jar, $session_end) = @_;
		450
		451	%$jar = () if $jar->{version} != 1;
		452
		453	my $anow = AE::now;
		454
		455	while (my ($chost, $paths) = each %$jar) {
		456	next unless ref $paths;
		457
		458	while (my ($cpath, $cookies) = each %$paths) {
		459	while (my ($cookie, $kv) = each %$cookies) {
		460	if (exists $kv->{_expires}) {
		461	delete $cookies->{$cookie}
		462	if $anow > $kv->{_expires};
		463	} elsif ($session_end) {
		464	delete $cookies->{$cookie};
		465	}
		466	}
		467
		468	delete $paths->{$cpath}
		469	unless %$cookies;
		470	}
		471
		472	delete $jar->{$chost}
		473	unless %$paths;
		474	}
		475	}
		476
		477	# extract cookies from jar
		478	sub cookie_jar_extract($$$$) {
		479	my ($jar, $scheme, $host, $path) = @_;
		480
		481	%$jar = () if $jar->{version} != 1;
		482
		483	my @cookies;
		484
		485	while (my ($chost, $paths) = each %$jar) {
		486	next unless ref $paths;
		487
		488	if ($chost =~ /^\./) {
		489	next unless $chost eq substr $host, -length $chost;
		490	} elsif ($chost =~ /\./) {
		491	next unless $chost eq $host;
		492	} else {
		493	next;
		494	}
		495
		496	while (my ($cpath, $cookies) = each %$paths) {
		497	next unless $cpath eq substr $path, 0, length $cpath;
		498
		499	while (my ($cookie, $kv) = each %$cookies) {
		500	next if $scheme ne "https" && exists $kv->{secure};
		501
		502	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		503	delete $cookies->{$cookie};
		504	next;
		505	}
		506
		507	my $value = $kv->{value};
		508
		509	if ($value =~ /[=;,[:space:]]/) {
		510	$value =~ s/([\\"])/\\$1/g;
		511	$value = "\"$value\"";
		512	}
		513
		514	push @cookies, "$cookie=$value";
		515	}
		516	}
		517	}
		518
		519	\@cookies
		520	}
		521
		522	# parse set_cookie header into jar
		523	sub cookie_jar_set_cookie($$$$) {
		524	my ($jar, $set_cookie, $host, $date) = @_;
		525
		526	my $anow = int AE::now;
		527	my $snow; # server-now
		528
		529	for ($set_cookie) {
		530	# parse NAME=VALUE
		531	my @kv;
		532
		533	# expires is not http-compliant in the original cookie-spec,
		534	# we support the official date format and some extensions
		535	while (
		536	m{
		537	\G\s*
		538	(?:
		539	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
		540	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )?
		541	)
		542	}gcxsi
		543	) {
		544	my $name = $2;
		545	my $value = $4;
		546
		547	if (defined $1) {
		548	# expires
		549	$name = "expires";
		550	$value = $1;
		551	} elsif (defined $3) {
		552	# quoted
		553	$value = $3;
		554	$value =~ s/\\(.)/$1/gs;
		555	}
		556
		557	push @kv, @kv ? lc $name : $name, $value;
		558
		559	last unless /\G\s*;/gc;
		560	}
		561
		562	last unless @kv;
		563
		564	my $name = shift @kv;
		565	my %kv = (value => shift @kv, @kv);
		566
		567	if (exists $kv{"max-age"}) {
		568	$kv{_expires} = $anow + delete $kv{"max-age"};
		569	} elsif (exists $kv{expires}) {
		570	$snow ||= parse_date ($date) || $anow;
		571	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		572	} else {
		573	delete $kv{_expires};
		574	}
		575
		576	my $cdom;
		577	my $cpath = (delete $kv{path}) || "/";
		578
		579	if (exists $kv{domain}) {
		580	$cdom = delete $kv{domain};
		581
		582	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		583
		584	next if $cdom =~ /\.$/;
		585
		586	# this is not rfc-like and not netscape-like. go figure.
		587	my $ndots = $cdom =~ y/.//;
		588	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		589	} else {
		590	$cdom = $host;
		591	}
		592
		593	# store it
		594	$jar->{version} = 1;
		595	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		596
		597	redo if /\G\s*,/gc;
		598	}
		599	}
		600
		601	#############################################################################
		602	# keepalive/persistent connection cache
		603
		604	# fetch a connection from the keepalive cache
		605	sub ka_fetch($) {
		606	my $ka_key = shift;
		607
		608	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		609	delete $KA_CACHE{$ka_key}
		610	unless @{ $KA_CACHE{$ka_key} };
		611
		612	$hdl
		613	}
		614
		615	sub ka_store($$) {
		616	my ($ka_key, $hdl) = @_;
		617
		618	my $kaa = $KA_CACHE{$ka_key} ||= [];
		619
		620	my $destroy = sub {
		621	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		622
		623	$hdl->destroy;
		624
		625	@ka
		626	? $KA_CACHE{$ka_key} = \@ka
		627	: delete $KA_CACHE{$ka_key};
		628	};
		629
		630	# on error etc., destroy
		631	$hdl->on_error ($destroy);
		632	$hdl->on_eof ($destroy);
		633	$hdl->on_read ($destroy);
		634	$hdl->timeout ($PERSISTENT_TIMEOUT);
		635
		636	push @$kaa, $hdl;
		637	shift @$kaa while @$kaa > $MAX_PER_HOST;
		638	}
		639
		640	#############################################################################
		641	# utilities
		642
		643	# continue to parse $_ for headers and place them into the arg
		644	sub _parse_hdr() {
		645	my %hdr;
		646
		647	# things seen, not parsed:
		648	# p3pP="NON CUR OTPi OUR NOR UNI"
		649
		650	$hdr{lc $1} .= ",$2"
		651	while /\G
		652	([^:\000-\037]*):
		653	[\011\040]*
		654	((?: [^\012]+ | \012[\011\040] )*)
		655	\012
		656	/gxc;
		657
		658	/\G$/
		659	or return;
		660
		661	# remove the "," prefix we added to all headers above
		662	substr $_, 0, 1, ""
		663	for values %hdr;
		664
		665	\%hdr
		666	}
		667
		668	#############################################################################
		669	# http_get
		670
343	our $qr_nlnl = qr{(?<![^\012])\015?\012};	671	our $qr_nlnl = qr{(?<![^\012])\015?\012};
344		672
345	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	673	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
346	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	674	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		675
		676	# maybe it should just become a normal object :/
		677
		678	sub _destroy_state(\%) {
		679	my ($state) = @_;
		680
		681	$state->{handle}->destroy if $state->{handle};
		682	%$state = ();
		683	}
		684
		685	sub _error(\%$$) {
		686	my ($state, $cb, $hdr) = @_;
		687
		688	&_destroy_state ($state);
		689
		690	$cb->(undef, $hdr);
		691	()
		692	}
347		693
348	sub http_request($$@) {	694	sub http_request($$@) {
349	my $cb = pop;	695	my $cb = pop;
350	my ($method, $url, %arg) = @_;	696	my ($method, $url, %arg) = @_;
351		697
…		…
366	my @pseudo = (URL => $url);	712	my @pseudo = (URL => $url);
367	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};	713	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
368		714
369	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	715	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
370		716
371	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })	717	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
372	if $recurse < 0;	718	if $recurse < 0;
373		719
374	my $proxy = $arg{proxy} || $PROXY;	720	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
375	my $timeout = $arg{timeout} || $TIMEOUT;	721	my $timeout = $arg{timeout} || $TIMEOUT;
376		722
377	my ($uscheme, $uauthority, $upath, $query, $fragment) =	723	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
378	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;	724	$url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|;
379		725
380	$uscheme = lc $uscheme;	726	$uscheme = lc $uscheme;
381		727
382	my $uport = $uscheme eq "http" ? 80	728	my $uport = $uscheme eq "http" ? 80
383	: $uscheme eq "https" ? 443	729	: $uscheme eq "https" ? 443
384	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });	730	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
385		731
386	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	732	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
387	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });	733	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
388		734
389	my $uhost = $1;	735	my $uhost = lc $1;
390	$uport = $2 if defined $2;	736	$uport = $2 if defined $2;
391		737
392	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	738	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
393	unless exists $hdr{host};	739	unless exists $hdr{host};
394		740
…		…
397		743
398	$upath =~ s%^/?%/%;	744	$upath =~ s%^/?%/%;
399		745
400	# cookie processing	746	# cookie processing
401	if (my $jar = $arg{cookie_jar}) {	747	if (my $jar = $arg{cookie_jar}) {
402	%$jar = () if $jar->{version} != 1;	748	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
403		749
404	my @cookie;
405
406	while (my ($chost, $v) = each %$jar) {
407	if ($chost =~ /^\./) {
408	next unless $chost eq substr $uhost, -length $chost;
409	} elsif ($chost =~ /\./) {
410	next unless $chost eq $uhost;
411	} else {
412	next;
413	}
414
415	while (my ($cpath, $v) = each %$v) {
416	next unless $cpath eq substr $upath, 0, length $cpath;
417
418	while (my ($k, $v) = each %$v) {
419	next if $uscheme ne "https" && exists $v->{secure};
420	my $value = $v->{value};
421	$value =~ s/([\\"])/\\$1/g;
422	push @cookie, "$k=\"$value\"";
423	}
424	}
425	}
426
427	$hdr{cookie} = join "; ", @cookie	750	$hdr{cookie} = join "; ", @$cookies
428	if @cookie;	751	if @$cookies;
429	}	752	}
430		753
431	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	754	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
432		755
433	if ($proxy) {	756	if ($proxy) {
…		…
436	$rscheme = "http" unless defined $rscheme;	759	$rscheme = "http" unless defined $rscheme;
437		760
438	# don't support https requests over https-proxy transport,	761	# don't support https requests over https-proxy transport,
439	# can't be done with tls as spec'ed, unless you double-encrypt.	762	# can't be done with tls as spec'ed, unless you double-encrypt.
440	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	763	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		764
		765	$rhost = lc $rhost;
		766	$rscheme = lc $rscheme;
441	} else {	767	} else {
442	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	768	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
443	}	769	}
444		770
445	# leave out fragment and query string, just a heuristic	771	# leave out fragment and query string, just a heuristic
446	$hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	772	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
447	$hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"};	773	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
448		774
449	$hdr{"content-length"} = length $arg{body}	775	$hdr{"content-length"} = length $arg{body}
450	if length $arg{body} || $method ne "GET";	776	if length $arg{body} || $method ne "GET";
451		777
		778	my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/;
		779
		780	# default value for keepalive is true iff the request is for an idempotent method
		781	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		782	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		783	my $was_persistent; # true if this is actually a recycled connection
		784
		785	# the key to use in the keepalive cache
		786	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		787
		788	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1
		789	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
		790
452	my %state = (connect_guard => 1);	791	my %state = (connect_guard => 1);
		792
		793	my $ae_error = 595; # connecting
		794
		795	# handle actual, non-tunneled, request
		796	my $handle_actual_request = sub {
		797	$ae_error = 596; # request phase
		798
		799	my $hdl = $state{handle};
		800
		801	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		802
		803	# send request
		804	$hdl->push_write (
		805	"$method $rpath HTTP/1.1\015\012"
		806	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		807	. "\015\012"
		808	. (delete $arg{body})
		809	);
		810
		811	# return if error occured during push_write()
		812	return unless %state;
		813
		814	# reduce memory usage, save a kitten, also re-use it for the response headers.
		815	%hdr = ();
		816
		817	# status line and headers
		818	$state{read_response} = sub {
		819	return unless %state;
		820
		821	for ("$_[1]") {
		822	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		823
		824	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
		825	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		826
		827	# 100 Continue handling
		828	# should not happen as we don't send expect: 100-continue,
		829	# but we handle it just in case.
		830	# since we send the request body regardless, if we get an error
		831	# we are out of-sync, which we currently do NOT handle correctly.
		832	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		833	if $2 eq 100;
		834
		835	push @pseudo,
		836	HTTPVersion => $1,
		837	Status => $2,
		838	Reason => $3,
		839	;
		840
		841	my $hdr = _parse_hdr
		842	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		843
		844	%hdr = (%$hdr, @pseudo);
		845	}
		846
		847	# redirect handling
		848	# microsoft and other shitheads don't give a shit for following standards,
		849	# try to support some common forms of broken Location headers.
		850	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
		851	$hdr{location} =~ s/^\.\/+//;
		852
		853	my $url = "$rscheme://$uhost:$uport";
		854
		855	unless ($hdr{location} =~ s/^\///) {
		856	$url .= $upath;
		857	$url =~ s/\/[^\/]*$//;
		858	}
		859
		860	$hdr{location} = "$url/$hdr{location}";
		861	}
		862
		863	my $redirect;
		864
		865	if ($recurse) {
		866	my $status = $hdr{Status};
		867
		868	# industry standard is to redirect POST as GET for
		869	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		870	# also, the UA should ask the user for 301 and 307 and POST,
		871	# industry standard seems to be to simply follow.
		872	# we go with the industry standard.
		873	if ($status == 301 or $status == 302 or $status == 303) {
		874	# HTTP/1.1 is unclear on how to mutate the method
		875	$method = "GET" unless $method eq "HEAD";
		876	$redirect = 1;
		877	} elsif ($status == 307) {
		878	$redirect = 1;
		879	}
		880	}
		881
		882	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		883	if ($state{handle}) {
		884	# handle keepalive
		885	if (
		886	$persistent
		887	&& $_[3]
		888	&& ($hdr{HTTPVersion} < 1.1
		889	? $hdr{connection} =~ /\bkeep-?alive\b/i
		890	: $hdr{connection} !~ /\bclose\b/i)
		891	) {
		892	ka_store $ka_key, delete $state{handle};
		893	} else {
		894	# no keepalive, destroy the handle
		895	$state{handle}->destroy;
		896	}
		897	}
		898
		899	%state = ();
		900
		901	if (defined $_[1]) {
		902	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		903	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		904	}
		905
		906	# set-cookie processing
		907	if ($arg{cookie_jar}) {
		908	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		909	}
		910
		911	if ($redirect && exists $hdr{location}) {
		912	# we ignore any errors, as it is very common to receive
		913	# Content-Length != 0 but no actual body
		914	# we also access %hdr, as $_[1] might be an erro
		915	$state{recurse} =
		916	http_request (
		917	$method => $hdr{location},
		918	%arg,
		919	recurse => $recurse - 1,
		920	Redirect => [$_[0], \%hdr],
		921	sub {
		922	%state = ();
		923	&$cb
		924	},
		925	);
		926	} else {
		927	$cb->($_[0], \%hdr);
		928	}
		929	};
		930
		931	$ae_error = 597; # body phase
		932
		933	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		934
		935	my $len = $chunked ? undef : $hdr{"content-length"};
		936
		937	# body handling, many different code paths
		938	# - no body expected
		939	# - want_body_handle
		940	# - te chunked
		941	# - 2x length known (with or without on_body)
		942	# - 2x length not known (with or without on_body)
		943	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		944	$finish->(undef, 598 => "Request cancelled by on_header");
		945	} elsif (
		946	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		947	or $method eq "HEAD"
		948	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		949	) {
		950	# no body
		951	$finish->("", undef, undef, 1);
		952
		953	} elsif (!$redirect && $arg{want_body_handle}) {
		954	$_[0]->on_eof (undef);
		955	$_[0]->on_error (undef);
		956	$_[0]->on_read (undef);
		957
		958	$finish->(delete $state{handle});
		959
		960	} elsif ($chunked) {
		961	my $cl = 0;
		962	my $body = "";
		963	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
		964
		965	$state{read_chunk} = sub {
		966	$_[1] =~ /^([0-9a-fA-F]+)/
		967	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		968
		969	my $len = hex $1;
		970
		971	if ($len) {
		972	$cl += $len;
		973
		974	$_[0]->push_read (chunk => $len, sub {
		975	$on_body->($_[1], \%hdr)
		976	or return $finish->(undef, 598 => "Request cancelled by on_body");
		977
		978	$_[0]->push_read (line => sub {
		979	length $_[1]
		980	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		981	$_[0]->push_read (line => $state{read_chunk});
		982	});
		983	});
		984	} else {
		985	$hdr{"content-length"} ||= $cl;
		986
		987	$_[0]->push_read (line => $qr_nlnl, sub {
		988	if (length $_[1]) {
		989	for ("$_[1]") {
		990	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		991
		992	my $hdr = _parse_hdr
		993	or return $finish->(undef, $ae_error => "Garbled response trailers");
		994
		995	%hdr = (%hdr, %$hdr);
		996	}
		997	}
		998
		999	$finish->($body, undef, undef, 1);
		1000	});
		1001	}
		1002	};
		1003
		1004	$_[0]->push_read (line => $state{read_chunk});
		1005
		1006	} elsif ($arg{on_body}) {
		1007	if (defined $len) {
		1008	$_[0]->on_read (sub {
		1009	$len -= length $_[0]{rbuf};
		1010
		1011	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1012	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1013
		1014	$len > 0
		1015	or $finish->("", undef, undef, 1);
		1016	});
		1017	} else {
		1018	$_[0]->on_eof (sub {
		1019	$finish->("");
		1020	});
		1021	$_[0]->on_read (sub {
		1022	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1023	or $finish->(undef, 598 => "Request cancelled by on_body");
		1024	});
		1025	}
		1026	} else {
		1027	$_[0]->on_eof (undef);
		1028
		1029	if (defined $len) {
		1030	$_[0]->on_read (sub {
		1031	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1032	if $len <= length $_[0]{rbuf};
		1033	});
		1034	} else {
		1035	$_[0]->on_error (sub {
		1036	($! == Errno::EPIPE || !$!)
		1037	? $finish->(delete $_[0]{rbuf})
		1038	: $finish->(undef, $ae_error => $_[2]);
		1039	});
		1040	$_[0]->on_read (sub { });
		1041	}
		1042	}
		1043	};
		1044
		1045	# if keepalive is enabled, then the server closing the connection
		1046	# before a response can happen legally - we retry on idempotent methods.
		1047	if ($was_persistent && $idempotent) {
		1048	my $old_eof = $hdl->{on_eof};
		1049	$hdl->{on_eof} = sub {
		1050	_destroy_state %state;
		1051
		1052	%state = ();
		1053	$state{recurse} =
		1054	http_request (
		1055	$method => $url,
		1056	%arg,
		1057	keepalive => 0,
		1058	sub {
		1059	%state = ();
		1060	&$cb
		1061	}
		1062	);
		1063	};
		1064	$hdl->on_read (sub {
		1065	return unless %state;
		1066
		1067	# as soon as we receive something, a connection close
		1068	# once more becomes a hard error
		1069	$hdl->{on_eof} = $old_eof;
		1070	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1071	});
		1072	} else {
		1073	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1074	}
		1075	};
		1076
		1077	my $prepare_handle = sub {
		1078	my ($hdl) = $state{handle};
		1079
		1080	$hdl->on_error (sub {
		1081	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1082	});
		1083	$hdl->on_eof (sub {
		1084	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1085	});
		1086	$hdl->timeout_reset;
		1087	$hdl->timeout ($timeout);
		1088	};
		1089
		1090	# connected to proxy (or origin server)
		1091	my $connect_cb = sub {
		1092	my $fh = shift
		1093	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1094
		1095	return unless delete $state{connect_guard};
		1096
		1097	# get handle
		1098	$state{handle} = new AnyEvent::Handle
		1099	%{ $arg{handle_params} },
		1100	fh => $fh,
		1101	peername => $uhost,
		1102	tls_ctx => $arg{tls_ctx},
		1103	;
		1104
		1105	$prepare_handle->();
		1106
		1107	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1108
		1109	# now handle proxy-CONNECT method
		1110	if ($proxy && $uscheme eq "https") {
		1111	# oh dear, we have to wrap it into a connect request
		1112
		1113	# maybe re-use $uauthority with patched port?
		1114	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		1115	$state{handle}->push_read (line => $qr_nlnl, sub {
		1116	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1117	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1118
		1119	if ($2 == 200) {
		1120	$rpath = $upath;
		1121	$handle_actual_request->();
		1122	} else {
		1123	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1124	}
		1125	});
		1126	} else {
		1127	$handle_actual_request->();
		1128	}
		1129	};
453		1130
454	_get_slot $uhost, sub {	1131	_get_slot $uhost, sub {
455	$state{slot_guard} = shift;	1132	$state{slot_guard} = shift;
456		1133
457	return unless $state{connect_guard};	1134	return unless $state{connect_guard};
458		1135
459	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	1136	# try to use an existing keepalive connection, but only if we, ourselves, plan
460	$state{fh} = shift	1137	# on a keepalive request (in theory, this should be a separate config option).
461	or do {	1138	if ($persistent && $KA_CACHE{$ka_key}) {
462	my $err = "$!";	1139	$was_persistent = 1;
463	%state = ();
464	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
465	};
466		1140
467	pop; # free memory, save a tree	1141	$state{handle} = ka_fetch $ka_key;
468
469	return unless delete $state{connect_guard};
470
471	# get handle
472	$state{handle} = new AnyEvent::Handle
473	fh => $state{fh},
474	peername => $rhost,
475	tls_ctx => $arg{tls_ctx},
476	# these need to be reconfigured on keepalive handles
477	timeout => $timeout,
478	on_error => sub {
479	%state = ();
480	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
481	},
482	on_eof => sub {
483	%state = ();
484	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
485	},
486	;
487
488	# limit the number of persistent connections
489	# keepalive not yet supported
490	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
491	# ++$KA_COUNT{$_[1]};
492	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
493	# --$KA_COUNT{$_[1]}
494	# };
495	# $hdr{connection} = "keep-alive";
496	# } else {
497	delete $hdr{connection};
498	# }
499
500	$state{handle}->starttls ("connect") if $rscheme eq "https";
501
502	# handle actual, non-tunneled, request
503	my $handle_actual_request = sub {
504	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
505
506	# send request
507	$state{handle}->push_write (	1142	$state{handle}->destroyed
508	"$method $rpath HTTP/1.0\015\012"	1143	and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
509	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)	1144	$prepare_handle->();
510	. "\015\012"	1145	$state{handle}->destroyed
511	. (delete $arg{body})	1146	and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
512	);
513
514	# return if error occured during push_write()
515	return unless %state;
516
517	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
518
519	# status line and headers
520	$state{handle}->push_read (line => $qr_nlnl, sub {
521	for ("$_[1]") {
522	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
523
524	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
525	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
526
527	push @pseudo,
528	HTTPVersion => $1,
529	Status => $2,
530	Reason => $3,
531	;
532
533	# things seen, not parsed:
534	# p3pP="NON CUR OTPi OUR NOR UNI"
535
536	$hdr{lc $1} .= ",$2"
537	while /\G
538	([^:\000-\037]*):
539	[\011\040]*
540	((?: [^\012]+ | \012[\011\040] )*)
541	\012
542	/gxc;
543
544	/\G$/
545	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
546	}
547
548	# remove the "," prefix we added to all headers above
549	substr $_, 0, 1, ""
550	for values %hdr;
551
552	# patch in all pseudo headers
553	%hdr = (%hdr, @pseudo);
554
555	# redirect handling
556	# microsoft and other shitheads don't give a shit for following standards,
557	# try to support some common forms of broken Location headers.
558	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
559	$hdr{location} =~ s/^\.\/+//;
560
561	my $url = "$rscheme://$uhost:$uport";
562
563	unless ($hdr{location} =~ s/^\///) {
564	$url .= $upath;
565	$url =~ s/\/[^\/]*$//;
566	}
567
568	$hdr{location} = "$url/$hdr{location}";
569	}
570
571	my $redirect;
572
573	if ($recurse) {
574	my $status = $hdr{Status};
575
576	# industry standard is to redirect POST as GET for
577	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
578	# also, the UA should ask the user for 301 and 307 and POST,
579	# industry standard seems to be to simply follow.
580	# we go with the industry standard.
581	if ($status == 301 or $status == 302 or $status == 303) {
582	# HTTP/1.1 is unclear on how to mutate the method
583	$method = "GET" unless $method eq "HEAD";
584	$redirect = 1;
585	} elsif ($status == 307) {
586	$redirect = 1;
587	}
588	}
589
590	my $finish = sub {
591	$state{handle}->destroy if $state{handle};
592	%state = ();
593
594	# set-cookie processing
595	if ($arg{cookie_jar}) {
596	for ($_[1]{"set-cookie"}) {
597	# parse NAME=VALUE
598	my @kv;
599
600	while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
601	my $name = $1;
602	my $value = $3;
603
604	unless ($value) {
605	$value = $2;
606	$value =~ s/\\(.)/$1/gs;
607	}
608
609	push @kv, $name => $value;
610
611	last unless /\G\s*;/gc;
612	}
613
614	last unless @kv;
615
616	my $name = shift @kv;
617	my %kv = (value => shift @kv, @kv);
618
619	my $cdom;
620	my $cpath = (delete $kv{path}) || "/";
621
622	if (exists $kv{domain}) {
623	$cdom = delete $kv{domain};
624
625	$cdom =~ s/^\.?/./; # make sure it starts with a "."
626
627	next if $cdom =~ /\.$/;
628
629	# this is not rfc-like and not netscape-like. go figure.
630	my $ndots = $cdom =~ y/.//;
631	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
632	} else {
633	$cdom = $uhost;
634	}
635
636	# store it
637	$arg{cookie_jar}{version} = 1;
638	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
639
640	redo if /\G\s*,/gc;
641	}
642	}
643
644	if ($redirect && exists $hdr{location}) {
645	# we ignore any errors, as it is very common to receive
646	# Content-Length != 0 but no actual body
647	# we also access %hdr, as $_[1] might be an erro
648	http_request (
649	$method => $hdr{location},
650	%arg,
651	recurse => $recurse - 1,
652	Redirect => \@_,
653	$cb);
654	} else {
655	$cb->($_[0], $_[1]);
656	}
657	};
658
659	my $len = $hdr{"content-length"};
660
661	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
662	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
663	} elsif (
664	$hdr{Status} =~ /^(?:1..|[23]04)$/
665	or $method eq "HEAD"
666	or (defined $len && !$len)
667	) {
668	# no body
669	$finish->("", \%hdr);
670	} else {
671	# body handling, four different code paths
672	# for want_body_handle, on_body (2x), normal (2x)
673	# we might read too much here, but it does not matter yet (no pers. connections)
674	if (!$redirect && $arg{want_body_handle}) {
675	$_[0]->on_eof (undef);
676	$_[0]->on_error (undef);
677	$_[0]->on_read (undef);
678
679	$finish->(delete $state{handle}, \%hdr);
680
681	} elsif ($arg{on_body}) {
682	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
683	if ($len) {
684	$_[0]->on_eof (undef);
685	$_[0]->on_read (sub {
686	$len -= length $_[0]{rbuf};
687
688	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
689	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
690
691	$len > 0
692	or $finish->("", \%hdr);
693	});
694	} else {
695	$_[0]->on_eof (sub {
696	$finish->("", \%hdr);
697	});
698	$_[0]->on_read (sub {
699	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
700	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
701	});
702	}
703	} else {
704	$_[0]->on_eof (undef);
705
706	if ($len) {
707	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
708	$_[0]->on_read (sub {
709	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
710	if $len <= length $_[0]{rbuf};
711	});
712	} else {
713	$_[0]->on_error (sub {
714	($! == Errno::EPIPE || !$!)
715	? $finish->(delete $_[0]{rbuf}, \%hdr)
716	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
717	});
718	$_[0]->on_read (sub { });
719	}
720	}
721	}
722	});
723	};
724
725	# now handle proxy-CONNECT method
726	if ($proxy && $uscheme eq "https") {
727	# oh dear, we have to wrap it into a connect request
728
729	# maybe re-use $uauthority with patched port?
730	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
731	$state{handle}->push_read (line => $qr_nlnl, sub {
732	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
733	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
734
735	if ($2 == 200) {
736	$rpath = $upath;
737	&$handle_actual_request;	1147	$handle_actual_request->();
738	} else {	1148
739	%state = ();
740	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
741	}
742	});
743	} else {	1149	} else {
744	&$handle_actual_request;	1150	my $tcp_connect = $arg{tcp_connect}
		1151	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		1152
		1153	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
745	}	1154	}
746
747	}, $arg{on_prepare} || sub { $timeout };
748	};	1155	};
749		1156
750	defined wantarray && AnyEvent::Util::guard { %state = () }	1157	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
751	}	1158	}
752		1159
753	sub http_get($@) {	1160	sub http_get($@) {
754	unshift @_, "GET";	1161	unshift @_, "GET";
755	&http_request	1162	&http_request
…		…
773	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1180	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
774	the actual connection, which in turn uses AnyEvent::DNS to resolve	1181	the actual connection, which in turn uses AnyEvent::DNS to resolve
775	hostnames. The latter is a simple stub resolver and does no caching	1182	hostnames. The latter is a simple stub resolver and does no caching
776	on its own. If you want DNS caching, you currently have to provide	1183	on its own. If you want DNS caching, you currently have to provide
777	your own default resolver (by storing a suitable resolver object in	1184	your own default resolver (by storing a suitable resolver object in
778	C<$AnyEvent::DNS::RESOLVER>).	1185	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
779		1186
780	=head2 GLOBAL FUNCTIONS AND VARIABLES	1187	=head2 GLOBAL FUNCTIONS AND VARIABLES
781		1188
782	=over 4	1189	=over 4
783		1190
784	=item AnyEvent::HTTP::set_proxy "proxy-url"	1191	=item AnyEvent::HTTP::set_proxy "proxy-url"
785		1192
786	Sets the default proxy server to use. The proxy-url must begin with a	1193	Sets the default proxy server to use. The proxy-url must begin with a
787	string of the form C<http://host:port> (optionally C<https:...>), croaks	1194	string of the form C<http://host:port>, croaks otherwise.
788	otherwise.
789		1195
790	To clear an already-set proxy, use C<undef>.	1196	To clear an already-set proxy, use C<undef>.
791		1197
		1198	When AnyEvent::HTTP is laoded for the first time it will query the
		1199	default proxy from the operating system, currently by looking at
		1200	C<$ENV{http_proxy>}.
		1201
		1202	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1203
		1204	Remove all cookies from the cookie jar that have been expired. If
		1205	C<$session_end> is given and true, then additionally remove all session
		1206	cookies.
		1207
		1208	You should call this function (with a true C<$session_end>) before you
		1209	save cookies to disk, and you should call this function after loading them
		1210	again. If you have a long-running program you can additonally call this
		1211	function from time to time.
		1212
		1213	A cookie jar is initially an empty hash-reference that is managed by this
		1214	module. It's format is subject to change, but currently it is like this:
		1215
		1216	The key C<version> has to contain C<1>, otherwise the hash gets
		1217	emptied. All other keys are hostnames or IP addresses pointing to
		1218	hash-references. The key for these inner hash references is the
		1219	server path for which this cookie is meant, and the values are again
		1220	hash-references. The keys of those hash-references is the cookie name, and
		1221	the value, you guessed it, is another hash-reference, this time with the
		1222	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1223	which have been replaced by a C<_expires> key that contains the cookie
		1224	expiry timestamp.
		1225
		1226	Here is an example of a cookie jar with a single cookie, so you have a
		1227	chance of understanding the above paragraph:
		1228
		1229	{
		1230	version => 1,
		1231	"10.0.0.1" => {
		1232	"/" => {
		1233	"mythweb_id" => {
		1234	_expires => 1293917923,
		1235	value => "ooRung9dThee3ooyXooM1Ohm",
		1236	},
		1237	},
		1238	},
		1239	}
		1240
		1241	=item $date = AnyEvent::HTTP::format_date $timestamp
		1242
		1243	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1244	Date (RFC 2616).
		1245
		1246	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1247
		1248	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1249	bunch of minor variations of those, and returns the corresponding POSIX
		1250	timestamp, or C<undef> if the date cannot be parsed.
		1251
792	=item $AnyEvent::HTTP::MAX_RECURSE	1252	=item $AnyEvent::HTTP::MAX_RECURSE
793		1253
794	The default value for the C<recurse> request parameter (default: C<10>).	1254	The default value for the C<recurse> request parameter (default: C<10>).
		1255
		1256	=item $AnyEvent::HTTP::TIMEOUT
		1257
		1258	The default timeout for conenction operations (default: C<300>).
795		1259
796	=item $AnyEvent::HTTP::USERAGENT	1260	=item $AnyEvent::HTTP::USERAGENT
797		1261
798	The default value for the C<User-Agent> header (the default is	1262	The default value for the C<User-Agent> header (the default is
799	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1263	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
800		1264
801	=item $AnyEvent::HTTP::MAX_PER_HOST	1265	=item $AnyEvent::HTTP::MAX_PER_HOST
802		1266
803	The maximum number of concurrent connections to the same host (identified	1267	The maximum number of concurrent connections to the same host (identified
804	by the hostname). If the limit is exceeded, then the additional requests	1268	by the hostname). If the limit is exceeded, then the additional requests
805	are queued until previous connections are closed.	1269	are queued until previous connections are closed. Both persistent and
		1270	non-persistent connections are counted in this limit.
806		1271
807	The default value for this is C<4>, and it is highly advisable to not	1272	The default value for this is C<4>, and it is highly advisable to not
808	increase it.	1273	increase it much.
		1274
		1275	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1276	connections, older browsers used 2, newers (such as firefox 3) typically
		1277	use 6, and Opera uses 8 because like, they have the fastest browser and
		1278	give a shit for everybody else on the planet.
		1279
		1280	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1281
		1282	The time after which idle persistent conenctions get closed by
		1283	AnyEvent::HTTP (default: C<3>).
809		1284
810	=item $AnyEvent::HTTP::ACTIVE	1285	=item $AnyEvent::HTTP::ACTIVE
811		1286
812	The number of active connections. This is not the number of currently	1287	The number of active connections. This is not the number of currently
813	running requests, but the number of currently open and non-idle TCP	1288	running requests, but the number of currently open and non-idle TCP
814	connections. This number of can be useful for load-leveling.	1289	connections. This number can be useful for load-leveling.
815		1290
816	=back	1291	=back
817		1292
818	=cut	1293	=cut
		1294
		1295	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1296	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1297
		1298	sub format_date($) {
		1299	my ($time) = @_;
		1300
		1301	# RFC 822/1123 format
		1302	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1303
		1304	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1305	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1306	$H, $M, $S;
		1307	}
		1308
		1309	sub parse_date($) {
		1310	my ($date) = @_;
		1311
		1312	my ($d, $m, $y, $H, $M, $S);
		1313
		1314	if ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)[\- ]([A-Z][a-z][a-z])[\- ]([0-9][0-9][0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) {
		1315	# RFC 822/1123, required by RFC 2616 (with " ")
		1316	# cookie dates (with "-")
		1317
		1318	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1319
		1320	} elsif ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) {
		1321	# RFC 850
		1322	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1323
		1324	} elsif ($date =~ /^[A-Z][a-z][a-z]+ ([A-Z][a-z][a-z]) ([0-9 ]?[0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) ([0-9][0-9][0-9][0-9])$/) {
		1325	# ISO C's asctime
		1326	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1327	}
		1328	# other formats fail in the loop below
		1329
		1330	for (0..11) {
		1331	if ($m eq $month[$_]) {
		1332	require Time::Local;
		1333	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1334	}
		1335	}
		1336
		1337	undef
		1338	}
819		1339
820	sub set_proxy($) {	1340	sub set_proxy($) {
821	if (length $_[0]) {	1341	if (length $_[0]) {
822	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1342	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
823	or Carp::croak "$_[0]: invalid proxy URL";	1343	or Carp::croak "$_[0]: invalid proxy URL";
824	$PROXY = [$2, $3 || 3128, $1]	1344	$PROXY = [$2, $3 || 3128, $1]
825	} else {	1345	} else {
826	undef $PROXY;	1346	undef $PROXY;
827	}	1347	}
…		…
830	# initialise proxy from environment	1350	# initialise proxy from environment
831	eval {	1351	eval {
832	set_proxy $ENV{http_proxy};	1352	set_proxy $ENV{http_proxy};
833	};	1353	};
834		1354
		1355	=head2 SHOWCASE
		1356
		1357	This section contaisn some more elaborate "real-world" examples or code
		1358	snippets.
		1359
		1360	=head2 HTTP/1.1 FILE DOWNLOAD
		1361
		1362	Downloading files with HTTP can be quite tricky, especially when something
		1363	goes wrong and you want to resume.
		1364
		1365	Here is a function that initiates and resumes a download. It uses the
		1366	last modified time to check for file content changes, and works with many
		1367	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1368	on older servers.
		1369
		1370	It calls the completion callback with either C<undef>, which means a
		1371	nonretryable error occured, C<0> when the download was partial and should
		1372	be retried, and C<1> if it was successful.
		1373
		1374	use AnyEvent::HTTP;
		1375
		1376	sub download($$$) {
		1377	my ($url, $file, $cb) = @_;
		1378
		1379	open my $fh, "+<", $file
		1380	or die "$file: $!";
		1381
		1382	my %hdr;
		1383	my $ofs = 0;
		1384
		1385	warn stat $fh;
		1386	warn -s _;
		1387	if (stat $fh and -s _) {
		1388	$ofs = -s _;
		1389	warn "-s is ", $ofs;
		1390	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1391	$hdr{"range"} = "bytes=$ofs-";
		1392	}
		1393
		1394	http_get $url,
		1395	headers => \%hdr,
		1396	on_header => sub {
		1397	my ($hdr) = @_;
		1398
		1399	if ($hdr->{Status} == 200 && $ofs) {
		1400	# resume failed
		1401	truncate $fh, $ofs = 0;
		1402	}
		1403
		1404	sysseek $fh, $ofs, 0;
		1405
		1406	1
		1407	},
		1408	on_body => sub {
		1409	my ($data, $hdr) = @_;
		1410
		1411	if ($hdr->{Status} =~ /^2/) {
		1412	length $data == syswrite $fh, $data
		1413	or return; # abort on write errors
		1414	}
		1415
		1416	1
		1417	},
		1418	sub {
		1419	my (undef, $hdr) = @_;
		1420
		1421	my $status = $hdr->{Status};
		1422
		1423	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1424	utime $fh, $time, $time;
		1425	}
		1426
		1427	if ($status == 200 || $status == 206 || $status == 416) {
		1428	# download ok || resume ok || file already fully downloaded
		1429	$cb->(1, $hdr);
		1430
		1431	} elsif ($status == 412) {
		1432	# file has changed while resuming, delete and retry
		1433	unlink $file;
		1434	$cb->(0, $hdr);
		1435
		1436	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1437	# retry later
		1438	$cb->(0, $hdr);
		1439
		1440	} else {
		1441	$cb->(undef, $hdr);
		1442	}
		1443	}
		1444	;
		1445	}
		1446
		1447	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1448	if ($_[0]) {
		1449	print "OK!\n";
		1450	} elsif (defined $_[0]) {
		1451	print "please retry later\n";
		1452	} else {
		1453	print "ERROR\n";
		1454	}
		1455	};
		1456
		1457	=head3 SOCKS PROXIES
		1458
		1459	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1460	compile your perl to support socks, or use an external program such as
		1461	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1462	transparently.
		1463
		1464	Alternatively, for AnyEvent::HTTP only, you can use your own
		1465	C<tcp_connect> function that does the proxy handshake - here is an example
		1466	that works with socks4a proxies:
		1467
		1468	use Errno;
		1469	use AnyEvent::Util;
		1470	use AnyEvent::Socket;
		1471	use AnyEvent::Handle;
		1472
		1473	# host, port and username of/for your socks4a proxy
		1474	my $socks_host = "10.0.0.23";
		1475	my $socks_port = 9050;
		1476	my $socks_user = "";
		1477
		1478	sub socks4a_connect {
		1479	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1480
		1481	my $hdl = new AnyEvent::Handle
		1482	connect => [$socks_host, $socks_port],
		1483	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1484	on_error => sub { $connect_cb->() },
		1485	;
		1486
		1487	$hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host);
		1488
		1489	$hdl->push_read (chunk => 8, sub {
		1490	my ($hdl, $chunk) = @_;
		1491	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1492
		1493	if ($status == 0x5a) {
		1494	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1495	} else {
		1496	$! = Errno::ENXIO; $connect_cb->();
		1497	}
		1498	});
		1499
		1500	$hdl
		1501	}
		1502
		1503	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1504	possibly after switching off other proxy types:
		1505
		1506	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1507
		1508	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1509	my ($data, $headers) = @_;
		1510	...
		1511	};
		1512
835	=head1 SEE ALSO	1513	=head1 SEE ALSO
836		1514
837	L<AnyEvent>.	1515	L<AnyEvent>.
838		1516
839	=head1 AUTHOR	1517	=head1 AUTHOR

Diff Legend

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