ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.50 by root, Tue Aug 11 13:20:42 2009 UTC vs.
Revision 1.140 by root, Wed Mar 6 19:29:18 2024 UTC

…		…
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use AnyEvent::HTTP;	7	use AnyEvent::HTTP;
8		8
9	http_get "http://www.nethype.de/", sub { print $_[1] };	9	http_get "http://www.nethype.de/", sub {
		10	my ($body, $hdr) = @_;
		11	print "$hdr->{URL} Status: $hdr->{Status}\n";
		12	print $body;
		13	};
10		14
11	# ... do something else here	15	# ... do something else here
12		16
13	=head1 DESCRIPTION	17	=head1 DESCRIPTION
14		18
15	This module is an L<AnyEvent> user, you need to make sure that you use and	19	This module is an L<AnyEvent> user, you need to make sure that you use and
16	run a supported event loop.	20	run a supported event loop.
17		21
18	This module implements a simple, stateless and non-blocking HTTP	22	This module implements a simple, stateless and non-blocking HTTP
19	client. It supports GET, POST and other request methods, cookies and more,	23	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	24	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	25	automatically limits the number of connections to the values specified in
22	the RFC.	26	the RFC.
23		27
24	It should generally be a "good client" that is enough for most HTTP	28	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	29	tasks. Simple tasks should be simple, but complex tasks should still be
…		…
36		40
37	=cut	41	=cut
38		42
39	package AnyEvent::HTTP;	43	package AnyEvent::HTTP;
40		44
41	use strict;	45	use common::sense;
42	no warnings;
43		46
44	use Errno ();	47	use Errno ();
45		48
46	use AnyEvent 4.8 ();	49	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	50	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	51	use AnyEvent::Handle ();
50		52
51	use base Exporter::;	53	use base Exporter::;
52		54
53	our $VERSION = '1.42';	55	our $VERSION = 2.25;
54		56
55	our @EXPORT = qw(http_get http_post http_head http_request);	57	our @EXPORT = qw(http_get http_post http_head http_request);
56		58
57	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	59	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	60	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	61	our $PERSISTENT_TIMEOUT = 3;
61	our $TIMEOUT = 300;	62	our $TIMEOUT = 300;
62		63	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		64
67	our $PROXY;	65	our $PROXY;
68	our $ACTIVE = 0;	66	our $ACTIVE = 0;
69		67
70	my %KA_COUNT; # number of open keep-alive connections per host	68	my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array
71	my %CO_SLOT; # number of open connections, and wait queue, per host	69	my %CO_SLOT; # number of open connections, and wait queue, per host
72		70
73	=item http_get $url, key => value..., $cb->($data, $headers)	71	=item http_get $url, key => value..., $cb->($data, $headers)
74		72
75	Executes an HTTP-GET request. See the http_request function for details on	73	Executes an HTTP-GET request. See the http_request function for details on
…		…
92	must be an absolute http or https URL.	90	must be an absolute http or https URL.
93		91
94	When called in void context, nothing is returned. In other contexts,	92	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	93	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	94	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.	95	destroyed before the callback is called, the request will be cancelled.
98		96
99	The callback will be called with the response body data as first argument	97	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	98	(or C<undef> if an error occurred), and a hash-ref with response headers
101	second argument.	99	(and trailers) as second argument.
102		100
103	All the headers in that hash are lowercased. In addition to the response	101	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	102	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		103	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	104	three parts of the HTTP Status-Line of the same name. If an error occurs
		105	during the body phase of a request, then the original C<Status> and
		106	C<Reason> values from the header are available as C<OrigStatus> and
		107	C<OrigReason>.
		108
106	pseudo-header C<URL> contains the original URL (which can differ from the	109	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	110	the requested URL when following redirects - for example, you might get
		111	an error that your URL scheme is not supported even though your URL is a
		112	valid http URL because it redirected to an ftp URL, in which case you can
		113	look at the URL pseudo header).
		114
		115	The pseudo-header C<Redirect> only exists when the request was a result
		116	of an internal redirect. In that case it is an array reference with
		117	the C<($data, $headers)> from the redirect response. Note that this
		118	response could in turn be the result of a redirect itself, and C<<
		119	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		120	response, and so on.
108		121
109	If the server sends a header multiple times, then their contents will be	122	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	123	joined together with a comma (C<,>), as per the HTTP spec.
111		124
112	If an internal error occurs, such as not being able to resolve a hostname,	125	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>	126	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
114	(usually C<599>) and the C<Reason> pseudo-header will contain an error	127	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
115	message.	128	message. Currently the following status codes are used:
		129
		130	=over 4
		131
		132	=item 595 - errors during connection establishment, proxy handshake.
		133
		134	=item 596 - errors during TLS negotiation, request sending and header processing.
		135
		136	=item 597 - errors during body receiving or processing.
		137
		138	=item 598 - user aborted request via C<on_header> or C<on_body>.
		139
		140	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		141
		142	=back
116		143
117	A typical callback might look like this:	144	A typical callback might look like this:
118		145
119	sub {	146	sub {
120	my ($body, $hdr) = @_;	147	my ($body, $hdr) = @_;
…		…
131		158
132	=over 4	159	=over 4
133		160
134	=item recurse => $count (default: $MAX_RECURSE)	161	=item recurse => $count (default: $MAX_RECURSE)
135		162
136	Whether to recurse requests or not, e.g. on redirects, authentication	163	Whether to recurse requests or not, e.g. on redirects, authentication and
137	retries and so on, and how often to do so.	164	other retries and so on, and how often to do so.
		165
		166	Only redirects to http and https URLs are supported. While most common
		167	redirection forms are handled entirely within this module, some require
		168	the use of the optional L<URI> module. If it is required but missing, then
		169	the request will fail with an error.
138		170
139	=item headers => hashref	171	=item headers => hashref
140		172
141	The request headers to use. Currently, C<http_request> may provide its	173	The request headers to use. Currently, C<http_request> may provide its own
142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	174	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
143	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be	175	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
144	suppressed by using C<undef> for these headers in which case they won't be	176	(this can be suppressed by using C<undef> for these headers in which case
145	sent at all).	177	they won't be sent at all).
		178
		179	You really should provide your own C<User-Agent:> header value that is
		180	appropriate for your program - I wouldn't be surprised if the default
		181	AnyEvent string gets blocked by webservers sooner or later.
		182
		183	Also, make sure that your headers names and values do not contain any
		184	embedded newlines.
146		185
147	=item timeout => $seconds	186	=item timeout => $seconds
148		187
149	The time-out to use for various stages - each connect attempt will reset	188	The time-out to use for various stages - each connect attempt will reset
150	the timeout, as will read or write activity. Default timeout is 5 minutes.	189	the timeout, as will read or write activity, i.e. this is not an overall
		190	timeout.
		191
		192	Default timeout is 5 minutes.
151		193
152	=item proxy => [$host, $port[, $scheme]] or undef	194	=item proxy => [$host, $port[, $scheme]] or undef
153		195
154	Use the given http proxy for all requests. If not specified, then the	196	Use the given http proxy for all requests, or no proxy if C<undef> is
155	default proxy (as specified by C<$ENV{http_proxy}>) is used.	197	used.
156		198
157	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	199	C<$scheme> must be either missing or must be C<http> for HTTP.
158	HTTPS.	200
		201	If not specified, then the default proxy is used (see
		202	C<AnyEvent::HTTP::set_proxy>).
		203
		204	Currently, if your proxy requires authorization, you have to specify an
		205	appropriate "Proxy-Authorization" header in every request.
		206
		207	Note that this module will prefer an existing persistent connection,
		208	even if that connection was made using another proxy. If you need to
		209	ensure that a new connection is made in this case, you can either force
		210	C<persistent> to false or e.g. use the proxy address in your C<sessionid>.
159		211
160	=item body => $string	212	=item body => $string
161		213
162	The request body, usually empty. Will be-sent as-is (future versions of	214	The request body, usually empty. Will be sent as-is (future versions of
163	this module might offer more options).	215	this module might offer more options).
164		216
165	=item cookie_jar => $hash_ref	217	=item cookie_jar => $hash_ref
166		218
167	Passing this parameter enables (simplified) cookie-processing, loosely	219	Passing this parameter enables (simplified) cookie-processing, loosely
168	based on the original netscape specification.	220	based on the original netscape specification.
169		221
170	The C<$hash_ref> must be an (initially empty) hash reference which will	222	The C<$hash_ref> must be an (initially empty) hash reference which
171	get updated automatically. It is possible to save the cookie_jar to	223	will get updated automatically. It is possible to save the cookie jar
172	persistent storage with something like JSON or Storable, but this is not	224	to persistent storage with something like JSON or Storable - see the
173	recommended, as expiry times are currently being ignored.	225	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		226	expired or session-only cookies, and also for documentation on the format
		227	of the cookie jar.
174		228
175	Note that this cookie implementation is not of very high quality, nor	229	Note that this cookie implementation is not meant to be complete. If
176	meant to be complete. If you want complete cookie management you have to	230	you want complete cookie management you have to do that on your
177	do that on your own. C<cookie_jar> is meant as a quick fix to get some	231	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
178	cookie-using sites working. Cookies are a privacy disaster, do not use	232	working. Cookies are a privacy disaster, do not use them unless required
179	them unless required to.	233	to.
		234
		235	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		236	headers will be set and handled by this module, otherwise they will be
		237	left untouched.
180		238
181	=item tls_ctx => $scheme | $tls_ctx	239	=item tls_ctx => $scheme | $tls_ctx
182		240
183	Specifies the AnyEvent::TLS context to be used for https connections. This	241	Specifies the AnyEvent::TLS context to be used for https connections. This
184	parameter follows the same rules as the C<tls_ctx> parameter to	242	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
188	verification) TLS context.	246	verification) TLS context.
189		247
190	The default for this option is C<low>, which could be interpreted as "give	248	The default for this option is C<low>, which could be interpreted as "give
191	me the page, no matter what".	249	me the page, no matter what".
192		250
		251	See also the C<sessionid> parameter.
		252
		253	=item sessionid => $string
		254
		255	The module might reuse connections to the same host internally (regardless
		256	of other settings, such as C<tcp_connect> or C<proxy>). Sometimes (e.g.
		257	when using TLS or a specfic proxy), you do not want to reuse connections
		258	from other sessions. This can be achieved by setting this parameter to
		259	some unique ID (such as the address of an object storing your state data
		260	or the TLS context, or the proxy IP) - only connections using the same
		261	unique ID will be reused.
		262
		263	=item on_prepare => $callback->($fh)
		264
		265	In rare cases you need to "tune" the socket before it is used to
		266	connect (for example, to bind it on a given IP address). This parameter
		267	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		268	and behaves exactly the same way (e.g. it has to provide a
		269	timeout). See the description for the C<$prepare_cb> argument of
		270	C<AnyEvent::Socket::tcp_connect> for details.
		271
		272	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		273
		274	In even rarer cases you want total control over how AnyEvent::HTTP
		275	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		276	to do this, but you can provide your own C<tcp_connect> function -
		277	obviously, it has to follow the same calling conventions, except that it
		278	may always return a connection guard object.
		279
		280	The connections made by this hook will be treated as equivalent to
		281	connections made the built-in way, specifically, they will be put into
		282	and taken from the persistent connection cache. If your C<$tcp_connect>
		283	function is incompatible with this kind of re-use, consider switching off
		284	C<persistent> connections and/or providing a C<sessionid> identifier.
		285
		286	There are probably lots of weird uses for this function, starting from
		287	tracing the hosts C<http_request> actually tries to connect, to (inexact
		288	but fast) host => IP address caching or even socks protocol support.
		289
193	=item on_header => $callback->($headers)	290	=item on_header => $callback->($headers)
194		291
195	When specified, this callback will be called with the header hash as soon	292	When specified, this callback will be called with the header hash as soon
196	as headers have been successfully received from the remote server (not on	293	as headers have been successfully received from the remote server (not on
197	locally-generated errors).	294	locally-generated errors).
…		…
202		299
203	This callback is useful, among other things, to quickly reject unwanted	300	This callback is useful, among other things, to quickly reject unwanted
204	content, which, if it is supposed to be rare, can be faster than first	301	content, which, if it is supposed to be rare, can be faster than first
205	doing a C<HEAD> request.	302	doing a C<HEAD> request.
206		303
		304	The downside is that cancelling the request makes it impossible to re-use
		305	the connection. Also, the C<on_header> callback will not receive any
		306	trailer (headers sent after the response body).
		307
207	Example: cancel the request unless the content-type is "text/html".	308	Example: cancel the request unless the content-type is "text/html".
208		309
209	on_header => sub {	310	on_header => sub {
210	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/	311	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/
211	},	312	},
…		…
217	string instead of the body data.	318	string instead of the body data.
218		319
219	It has to return either true (in which case AnyEvent::HTTP will continue),	320	It has to return either true (in which case AnyEvent::HTTP will continue),
220	or false, in which case AnyEvent::HTTP will cancel the download (and call	321	or false, in which case AnyEvent::HTTP will cancel the download (and call
221	the completion callback with an error code of C<598>).	322	the completion callback with an error code of C<598>).
		323
		324	The downside to cancelling the request is that it makes it impossible to
		325	re-use the connection.
222		326
223	This callback is useful when the data is too large to be held in memory	327	This callback is useful when the data is too large to be held in memory
224	(so the callback writes it to a file) or when only some information should	328	(so the callback writes it to a file) or when only some information should
225	be extracted, or when the body should be processed incrementally.	329	be extracted, or when the body should be processed incrementally.
226		330
…		…
238	called. Instead of the C<$body> argument containing the body data, the	342	called. Instead of the C<$body> argument containing the body data, the
239	callback will receive the L<AnyEvent::Handle> object associated with the	343	callback will receive the L<AnyEvent::Handle> object associated with the
240	connection. In error cases, C<undef> will be passed. When there is no body	344	connection. In error cases, C<undef> will be passed. When there is no body
241	(e.g. status C<304>), the empty string will be passed.	345	(e.g. status C<304>), the empty string will be passed.
242		346
243	The handle object might or might not be in TLS mode, might be connected to	347	The handle object might or might not be in TLS mode, might be connected
244	a proxy, be a persistent connection etc., and configured in unspecified	348	to a proxy, be a persistent connection, use chunked transfer encoding
245	ways. The user is responsible for this handle (it will not be used by this	349	etc., and configured in unspecified ways. The user is responsible for this
246	module anymore).	350	handle (it will not be used by this module anymore).
247		351
248	This is useful with some push-type services, where, after the initial	352	This is useful with some push-type services, where, after the initial
249	headers, an interactive protocol is used (typical example would be the	353	headers, an interactive protocol is used (typical example would be the
250	push-style twitter API which starts a JSON/XML stream).	354	push-style twitter API which starts a JSON/XML stream).
251		355
252	If you think you need this, first have a look at C<on_body>, to see if	356	If you think you need this, first have a look at C<on_body>, to see if
253	that doesn't solve your problem in a better way.	357	that doesn't solve your problem in a better way.
254		358
		359	=item persistent => $boolean
		360
		361	Try to create/reuse a persistent connection. When this flag is set
		362	(default: true for idempotent requests, false for all others), then
		363	C<http_request> tries to re-use an existing (previously-created)
		364	persistent connection to same host (i.e. identical URL scheme, hostname,
		365	port and sessionid) and, failing that, tries to create a new one.
		366
		367	Requests failing in certain ways will be automatically retried once, which
		368	is dangerous for non-idempotent requests, which is why it defaults to off
		369	for them. The reason for this is because the bozos who designed HTTP/1.1
		370	made it impossible to distinguish between a fatal error and a normal
		371	connection timeout, so you never know whether there was a problem with
		372	your request or not.
		373
		374	When reusing an existent connection, many parameters (such as TLS context)
		375	will be ignored. See the C<sessionid> parameter for a workaround.
		376
		377	=item keepalive => $boolean
		378
		379	Only used when C<persistent> is also true. This parameter decides whether
		380	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		381	(as opposed to only a HTTP/1.1 persistent connection).
		382
		383	The default is true, except when using a proxy, in which case it defaults
		384	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		385
		386	=item handle_params => { key => value ... }
		387
		388	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		389	constructor that is called - not all requests will create a handle, and
		390	sometimes more than one is created, so this parameter is only good for
		391	setting hints.
		392
		393	Example: set the maximum read size to 4096, to potentially conserve memory
		394	at the cost of speed.
		395
		396	handle_params => {
		397	max_read_size => 4096,
		398	},
		399
255	=back	400	=back
256		401
257	Example: make a simple HTTP GET request for http://www.nethype.de/	402	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		403	the response body.
258		404
259	http_request GET => "http://www.nethype.de/", sub {	405	http_request GET => "http://www.nethype.de/", sub {
260	my ($body, $hdr) = @_;	406	my ($body, $hdr) = @_;
261	print "$body\n";	407	print "$body\n";
262	};	408	};
263		409
264	Example: make a HTTP HEAD request on https://www.google.com/, use a	410	Example: do a HTTP HEAD request on https://www.google.com/, use a
265	timeout of 30 seconds.	411	timeout of 30 seconds.
266		412
267	http_request	413	http_request
268	GET => "https://www.google.com",	414	HEAD => "https://www.google.com",
		415	headers => { "user-agent" => "MySearchClient 1.0" },
269	timeout => 30,	416	timeout => 30,
270	sub {	417	sub {
271	my ($body, $hdr) = @_;	418	my ($body, $hdr) = @_;
272	use Data::Dumper;	419	use Data::Dumper;
273	print Dumper $hdr;	420	print Dumper $hdr;
274	}	421	}
275	;	422	;
276		423
277	Example: make another simple HTTP GET request, but immediately try to	424	Example: do another simple HTTP GET request, but immediately try to
278	cancel it.	425	cancel it.
279		426
280	my $request = http_request GET => "http://www.nethype.de/", sub {	427	my $request = http_request GET => "http://www.nethype.de/", sub {
281	my ($body, $hdr) = @_;	428	my ($body, $hdr) = @_;
282	print "$body\n";	429	print "$body\n";
283	};	430	};
284		431
285	undef $request;	432	undef $request;
286		433
287	=cut	434	=cut
		435
		436	#############################################################################
		437	# wait queue/slots
288		438
289	sub _slot_schedule;	439	sub _slot_schedule;
290	sub _slot_schedule($) {	440	sub _slot_schedule($) {
291	my $host = shift;	441	my $host = shift;
292		442
…		…
314	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	464	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
315		465
316	_slot_schedule $_[0];	466	_slot_schedule $_[0];
317	}	467	}
318		468
319	our $qr_nl = qr{\015?\012};	469	#############################################################################
		470	# cookie handling
		471
		472	# expire cookies
		473	sub cookie_jar_expire($;$) {
		474	my ($jar, $session_end) = @_;
		475
		476	%$jar = () if $jar->{version} != 2;
		477
		478	my $anow = AE::now;
		479
		480	while (my ($chost, $paths) = each %$jar) {
		481	next unless ref $paths;
		482
		483	while (my ($cpath, $cookies) = each %$paths) {
		484	while (my ($cookie, $kv) = each %$cookies) {
		485	if (exists $kv->{_expires}) {
		486	delete $cookies->{$cookie}
		487	if $anow > $kv->{_expires};
		488	} elsif ($session_end) {
		489	delete $cookies->{$cookie};
		490	}
		491	}
		492
		493	delete $paths->{$cpath}
		494	unless %$cookies;
		495	}
		496
		497	delete $jar->{$chost}
		498	unless %$paths;
		499	}
		500	}
		501
		502	# extract cookies from jar
		503	sub cookie_jar_extract($$$$) {
		504	my ($jar, $scheme, $host, $path) = @_;
		505
		506	%$jar = () if $jar->{version} != 2;
		507
		508	$host = AnyEvent::Util::idn_to_ascii $host
		509	if $host =~ /[^\x00-\x7f]/;
		510
		511	my @cookies;
		512
		513	while (my ($chost, $paths) = each %$jar) {
		514	next unless ref $paths;
		515
		516	# exact match or suffix including . match
		517	$chost eq $host or ".$chost" eq substr $host, -1 - length $chost
		518	or next;
		519
		520	while (my ($cpath, $cookies) = each %$paths) {
		521	next unless $cpath eq substr $path, 0, length $cpath;
		522
		523	while (my ($cookie, $kv) = each %$cookies) {
		524	next if $scheme ne "https" && exists $kv->{secure};
		525
		526	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		527	delete $cookies->{$cookie};
		528	next;
		529	}
		530
		531	my $value = $kv->{value};
		532
		533	if ($value =~ /[=;,[:space:]]/) {
		534	$value =~ s/([\\"])/\\$1/g;
		535	$value = "\"$value\"";
		536	}
		537
		538	push @cookies, "$cookie=$value";
		539	}
		540	}
		541	}
		542
		543	\@cookies
		544	}
		545
		546	# parse set_cookie header into jar
		547	sub cookie_jar_set_cookie($$$$) {
		548	my ($jar, $set_cookie, $host, $date) = @_;
		549
		550	%$jar = () if $jar->{version} != 2;
		551
		552	my $anow = int AE::now;
		553	my $snow; # server-now
		554
		555	for ($set_cookie) {
		556	# parse NAME=VALUE
		557	my @kv;
		558
		559	# expires is not http-compliant in the original cookie-spec,
		560	# we support the official date format and some extensions
		561	while (
		562	m{
		563	\G\s*
		564	(?:
		565	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
		566	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )?
		567	)
		568	}gcxsi
		569	) {
		570	my $name = $2;
		571	my $value = $4;
		572
		573	if (defined $1) {
		574	# expires
		575	$name = "expires";
		576	$value = $1;
		577	} elsif (defined $3) {
		578	# quoted
		579	$value = $3;
		580	$value =~ s/\\(.)/$1/gs;
		581	}
		582
		583	push @kv, @kv ? lc $name : $name, $value;
		584
		585	last unless /\G\s*;/gc;
		586	}
		587
		588	last unless @kv;
		589
		590	my $name = shift @kv;
		591	my %kv = (value => shift @kv, @kv);
		592
		593	if (exists $kv{"max-age"}) {
		594	$kv{_expires} = $anow + delete $kv{"max-age"};
		595	} elsif (exists $kv{expires}) {
		596	$snow ||= parse_date ($date) || $anow;
		597	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		598	} else {
		599	delete $kv{_expires};
		600	}
		601
		602	my $cdom;
		603	my $cpath = (delete $kv{path}) || "/";
		604
		605	if (exists $kv{domain}) {
		606	$cdom = $kv{domain};
		607
		608	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		609
		610	next if $cdom =~ /\.$/;
		611
		612	# this is not rfc-like and not netscape-like. go figure.
		613	my $ndots = $cdom =~ y/.//;
		614	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		615
		616	$cdom = substr $cdom, 1; # remove initial .
		617	} else {
		618	$cdom = $host;
		619	}
		620
		621	# store it
		622	$jar->{version} = 2;
		623	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		624
		625	redo if /\G\s*,/gc;
		626	}
		627	}
		628
		629	#############################################################################
		630	# keepalive/persistent connection cache
		631
		632	# fetch a connection from the keepalive cache
		633	sub ka_fetch($) {
		634	my $ka_key = shift;
		635
		636	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		637	delete $KA_CACHE{$ka_key}
		638	unless @{ $KA_CACHE{$ka_key} };
		639
		640	$hdl
		641	}
		642
		643	sub ka_store($$) {
		644	my ($ka_key, $hdl) = @_;
		645
		646	my $kaa = $KA_CACHE{$ka_key} ||= [];
		647
		648	my $destroy = sub {
		649	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		650
		651	$hdl->destroy;
		652
		653	@ka
		654	? $KA_CACHE{$ka_key} = \@ka
		655	: delete $KA_CACHE{$ka_key};
		656	};
		657
		658	# on error etc., destroy
		659	$hdl->on_error ($destroy);
		660	$hdl->on_eof ($destroy);
		661	$hdl->on_read ($destroy);
		662	$hdl->timeout ($PERSISTENT_TIMEOUT);
		663
		664	push @$kaa, $hdl;
		665	shift @$kaa while @$kaa > $MAX_PER_HOST;
		666	}
		667
		668	#############################################################################
		669	# utilities
		670
		671	# continue to parse $_ for headers and place them into the arg
		672	sub _parse_hdr() {
		673	my %hdr;
		674
		675	# things seen, not parsed:
		676	# p3pP="NON CUR OTPi OUR NOR UNI"
		677
		678	$hdr{lc $1} .= ",$2"
		679	while /\G
		680	([^:\000-\037]*):
		681	[\011\040]*
		682	((?: [^\012]+ | \012[\011\040] )*)
		683	\012
		684	/gxc;
		685
		686	/\G$/
		687	or return;
		688
		689	# remove the "," prefix we added to all headers above
		690	substr $_, 0, 1, ""
		691	for values %hdr;
		692
		693	\%hdr
		694	}
		695
		696	#############################################################################
		697	# http_get
		698
320	our $qr_nlnl = qr{(?<![^\012])\015?\012};	699	our $qr_nlnl = qr{(?<![^\012])\015?\012};
321		700
322	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	701	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
323	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	702	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		703
		704	# maybe it should just become a normal object :/
		705
		706	sub _destroy_state(\%) {
		707	my ($state) = @_;
		708
		709	$state->{handle}->destroy if $state->{handle};
		710	%$state = ();
		711	}
		712
		713	sub _error(\%$$) {
		714	my ($state, $cb, $hdr) = @_;
		715
		716	&_destroy_state ($state);
		717
		718	$cb->(undef, $hdr);
		719	()
		720	}
		721
		722	our %IDEMPOTENT = (
		723	DELETE => 1,
		724	GET => 1,
		725	QUERY => 1,
		726	HEAD => 1,
		727	OPTIONS => 1,
		728	PUT => 1,
		729	TRACE => 1,
		730
		731	ACL => 1,
		732	"BASELINE-CONTROL" => 1,
		733	BIND => 1,
		734	CHECKIN => 1,
		735	CHECKOUT => 1,
		736	COPY => 1,
		737	LABEL => 1,
		738	LINK => 1,
		739	MERGE => 1,
		740	MKACTIVITY => 1,
		741	MKCALENDAR => 1,
		742	MKCOL => 1,
		743	MKREDIRECTREF => 1,
		744	MKWORKSPACE => 1,
		745	MOVE => 1,
		746	ORDERPATCH => 1,
		747	PRI => 1,
		748	PROPFIND => 1,
		749	PROPPATCH => 1,
		750	REBIND => 1,
		751	REPORT => 1,
		752	SEARCH => 1,
		753	UNBIND => 1,
		754	UNCHECKOUT => 1,
		755	UNLINK => 1,
		756	UNLOCK => 1,
		757	UPDATE => 1,
		758	UPDATEREDIRECTREF => 1,
		759	"VERSION-CONTROL" => 1,
		760	);
324		761
325	sub http_request($$@) {	762	sub http_request($$@) {
326	my $cb = pop;	763	my $cb = pop;
327	my ($method, $url, %arg) = @_;	764	my ($method, $url, %arg) = @_;
328		765
…		…
337	while (my ($k, $v) = each %$hdr) {	774	while (my ($k, $v) = each %$hdr) {
338	$hdr{lc $k} = $v;	775	$hdr{lc $k} = $v;
339	}	776	}
340	}	777	}
341		778
		779	# pseudo headers for all subsequent responses
		780	my @pseudo = (URL => $url);
		781	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		782
342	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	783	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
343		784
344	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	785	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
345	if $recurse < 0;	786	if $recurse < 0;
346		787
347	my $proxy = $arg{proxy} || $PROXY;	788	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
348	my $timeout = $arg{timeout} || $TIMEOUT;	789	my $timeout = $arg{timeout} || $TIMEOUT;
349		790
350	my ($uscheme, $uauthority, $upath, $query, $fragment) =	791	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
351	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|;	792	$url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|;
352		793
353	$uscheme = lc $uscheme;	794	$uscheme = lc $uscheme;
354		795
355	my $uport = $uscheme eq "http" ? 80	796	my $uport = $uscheme eq "http" ? 80
356	: $uscheme eq "https" ? 443	797	: $uscheme eq "https" ? 443
357	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });	798	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
358		799
359	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	800	$uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x
360	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	801	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
361		802
362	my $uhost = $1;	803	my $uhost = lc $1;
363	$uport = $2 if defined $2;	804	$uport = $2 if defined $2;
364		805
365	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";	806	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		807	unless exists $hdr{host};
366		808
367	$uhost =~ s/^\[(.*)\]$/$1/;	809	$uhost =~ s/^\[(.*)\]$/$1/;
368	$upath .= "?$query" if length $query;	810	$upath .= $query if length $query;
369		811
370	$upath =~ s%^/?%/%;	812	$upath =~ s%^/?%/%;
371		813
372	# cookie processing	814	# cookie processing
373	if (my $jar = $arg{cookie_jar}) {	815	if (my $jar = $arg{cookie_jar}) {
374	%$jar = () if $jar->{version} != 1;	816	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
375		817
376	my @cookie;
377
378	while (my ($chost, $v) = each %$jar) {
379	if ($chost =~ /^\./) {
380	next unless $chost eq substr $uhost, -length $chost;
381	} elsif ($chost =~ /\./) {
382	next unless $chost eq $uhost;
383	} else {
384	next;
385	}
386
387	while (my ($cpath, $v) = each %$v) {
388	next unless $cpath eq substr $upath, 0, length $cpath;
389
390	while (my ($k, $v) = each %$v) {
391	next if $uscheme ne "https" && exists $v->{secure};
392	my $value = $v->{value};
393	$value =~ s/([\\"])/\\$1/g;
394	push @cookie, "$k=\"$value\"";
395	}
396	}
397	}
398
399	$hdr{cookie} = join "; ", @cookie	818	$hdr{cookie} = join "; ", @$cookies
400	if @cookie;	819	if @$cookies;
401	}	820	}
402		821
403	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	822	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
404		823
405	if ($proxy) {	824	if ($proxy) {
…		…
408	$rscheme = "http" unless defined $rscheme;	827	$rscheme = "http" unless defined $rscheme;
409		828
410	# don't support https requests over https-proxy transport,	829	# don't support https requests over https-proxy transport,
411	# can't be done with tls as spec'ed, unless you double-encrypt.	830	# can't be done with tls as spec'ed, unless you double-encrypt.
412	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	831	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		832
		833	$rhost = lc $rhost;
		834	$rscheme = lc $rscheme;
413	} else {	835	} else {
414	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	836	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
415	}	837	}
416		838
417	# leave out fragment and query string, just a heuristic	839	# leave out fragment and query string, just a heuristic
418	$hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	840	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
419	$hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"};	841	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
420		842
421	$hdr{"content-length"} = length $arg{body};	843	$hdr{"content-length"} = length $arg{body}
		844	if length $arg{body} || $method ne "GET";
		845
		846	my $idempotent = $IDEMPOTENT{$method};
		847
		848	# default value for keepalive is true iff the request is for an idempotent method
		849	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		850	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		851	my $was_persistent; # true if this is actually a recycled connection
		852
		853	# the key to use in the keepalive cache
		854	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		855
		856	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1
		857	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
422		858
423	my %state = (connect_guard => 1);	859	my %state = (connect_guard => 1);
		860
		861	my $ae_error = 595; # connecting
		862
		863	# handle actual, non-tunneled, request
		864	my $handle_actual_request = sub {
		865	$ae_error = 596; # request phase
		866
		867	my $hdl = $state{handle};
		868
		869	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		870
		871	# send request
		872	$hdl->push_write (
		873	"$method $rpath HTTP/1.1\015\012"
		874	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		875	. "\015\012"
		876	. $arg{body}
		877	);
		878
		879	# return if error occurred during push_write()
		880	return unless %state;
		881
		882	# reduce memory usage, save a kitten, also re-use it for the response headers.
		883	%hdr = ();
		884
		885	# status line and headers
		886	$state{read_response} = sub {
		887	return unless %state;
		888
		889	for ("$_[1]") {
		890	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		891
		892	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
		893	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		894
		895	# 100 Continue handling
		896	# should not happen as we don't send expect: 100-continue,
		897	# but we handle it just in case.
		898	# since we send the request body regardless, if we get an error
		899	# we are out of-sync, which we currently do NOT handle correctly.
		900	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		901	if $2 eq 100;
		902
		903	push @pseudo,
		904	HTTPVersion => $1,
		905	Status => $2,
		906	Reason => $3,
		907	;
		908
		909	my $hdr = _parse_hdr
		910	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		911
		912	%hdr = (%$hdr, @pseudo);
		913	}
		914
		915	# redirect handling
		916	# relative uri handling forced by microsoft and other shitheads.
		917	# we give our best and fall back to URI if available.
		918	if (exists $hdr{location}) {
		919	my $loc = $hdr{location};
		920
		921	if ($loc =~ m%^//%) { # //
		922	$loc = "$uscheme:$loc";
		923
		924	} elsif ($loc eq "") {
		925	$loc = $url;
		926
		927	} elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple"
		928	$loc =~ s/^\.\/+//;
		929
		930	if ($loc !~ m%^[.?#]%) {
		931	my $prefix = "$uscheme://$uauthority";
		932
		933	unless ($loc =~ s/^\///) {
		934	$prefix .= $upath;
		935	$prefix =~ s/\/[^\/]*$//;
		936	}
		937
		938	$loc = "$prefix/$loc";
		939
		940	} elsif (eval { require URI }) { # uri
		941	$loc = URI->new_abs ($loc, $url)->as_string;
		942
		943	} else {
		944	return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" };
		945	#$hdr{Status} = 599;
		946	#$hdr{Reason} = "Unparsable Redirect (URI module missing)";
		947	#$recurse = 0;
		948	}
		949	}
		950
		951	$hdr{location} = $loc;
		952	}
		953
		954	my $redirect;
		955
		956	if ($recurse) {
		957	my $status = $hdr{Status};
		958
		959	# industry standard is to redirect POST as GET for
		960	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		961	# also, the UA should ask the user for 301 and 307 and POST,
		962	# industry standard seems to be to simply follow.
		963	# we go with the industry standard. 308 is defined
		964	# by rfc7538
		965	if ($status == 301 or $status == 302 or $status == 303) {
		966	$redirect = 1;
		967	# HTTP/1.1 is unclear on how to mutate the method
		968	unless ($method eq "HEAD") {
		969	$method = "GET";
		970	delete $arg{body};
		971	}
		972	} elsif ($status == 307 or $status == 308) {
		973	$redirect = 1;
		974	}
		975	}
		976
		977	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		978	if ($state{handle}) {
		979	# handle keepalive
		980	if (
		981	$persistent
		982	&& $_[3]
		983	&& ($hdr{HTTPVersion} < 1.1
		984	? $hdr{connection} =~ /\bkeep-?alive\b/i
		985	: $hdr{connection} !~ /\bclose\b/i)
		986	) {
		987	ka_store $ka_key, delete $state{handle};
		988	} else {
		989	# no keepalive, destroy the handle
		990	$state{handle}->destroy;
		991	}
		992	}
		993
		994	%state = ();
		995
		996	if (defined $_[1]) {
		997	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		998	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		999	}
		1000
		1001	# set-cookie processing
		1002	if ($arg{cookie_jar}) {
		1003	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		1004	}
		1005
		1006	if ($redirect && exists $hdr{location}) {
		1007	# we ignore any errors, as it is very common to receive
		1008	# Content-Length != 0 but no actual body
		1009	# we also access %hdr, as $_[1] might be an erro
		1010	$state{recurse} =
		1011	http_request (
		1012	$method => $hdr{location},
		1013	%arg,
		1014	recurse => $recurse - 1,
		1015	Redirect => [$_[0], \%hdr],
		1016	sub {
		1017	%state = ();
		1018	&$cb
		1019	},
		1020	);
		1021	} else {
		1022	$cb->($_[0], \%hdr);
		1023	}
		1024	};
		1025
		1026	$ae_error = 597; # body phase
		1027
		1028	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		1029
		1030	my $len = $chunked ? undef : $hdr{"content-length"};
		1031
		1032	# body handling, many different code paths
		1033	# - no body expected
		1034	# - want_body_handle
		1035	# - te chunked
		1036	# - 2x length known (with or without on_body)
		1037	# - 2x length not known (with or without on_body)
		1038	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		1039	$finish->(undef, 598 => "Request cancelled by on_header");
		1040	} elsif (
		1041	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		1042	or $method eq "HEAD"
		1043	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		1044	) {
		1045	# no body
		1046	$finish->("", undef, undef, 1);
		1047
		1048	} elsif (!$redirect && $arg{want_body_handle}) {
		1049	$_[0]->on_eof (undef);
		1050	$_[0]->on_error (undef);
		1051	$_[0]->on_read (undef);
		1052
		1053	$finish->(delete $state{handle});
		1054
		1055	} elsif ($chunked) {
		1056	my $cl = 0;
		1057	my $body = "";
		1058	my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 };
		1059
		1060	$state{read_chunk} = sub {
		1061	$_[1] =~ /^([0-9a-fA-F]+)/
		1062	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1063
		1064	my $len = hex $1;
		1065
		1066	if ($len) {
		1067	$cl += $len;
		1068
		1069	$_[0]->push_read (chunk => $len, sub {
		1070	$on_body->($_[1], \%hdr)
		1071	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1072
		1073	$_[0]->push_read (line => sub {
		1074	length $_[1]
		1075	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1076	$_[0]->push_read (line => $state{read_chunk});
		1077	});
		1078	});
		1079	} else {
		1080	$hdr{"content-length"} ||= $cl;
		1081
		1082	$_[0]->push_read (line => $qr_nlnl, sub {
		1083	if (length $_[1]) {
		1084	for ("$_[1]") {
		1085	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		1086
		1087	my $hdr = _parse_hdr
		1088	or return $finish->(undef, $ae_error => "Garbled response trailers");
		1089
		1090	%hdr = (%hdr, %$hdr);
		1091	}
		1092	}
		1093
		1094	$finish->($body, undef, undef, 1);
		1095	});
		1096	}
		1097	};
		1098
		1099	$_[0]->push_read (line => $state{read_chunk});
		1100
		1101	} elsif (!$redirect && $arg{on_body}) {
		1102	if (defined $len) {
		1103	$_[0]->on_read (sub {
		1104	$len -= length $_[0]{rbuf};
		1105
		1106	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1107	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1108
		1109	$len > 0
		1110	or $finish->("", undef, undef, 1);
		1111	});
		1112	} else {
		1113	$_[0]->on_eof (sub {
		1114	$finish->("");
		1115	});
		1116	$_[0]->on_read (sub {
		1117	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1118	or $finish->(undef, 598 => "Request cancelled by on_body");
		1119	});
		1120	}
		1121	} else {
		1122	$_[0]->on_eof (undef);
		1123
		1124	if (defined $len) {
		1125	$_[0]->on_read (sub {
		1126	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1127	if $len <= length $_[0]{rbuf};
		1128	});
		1129	} else {
		1130	$_[0]->on_error (sub {
		1131	($! == Errno::EPIPE || !$!)
		1132	? $finish->(delete $_[0]{rbuf})
		1133	: $finish->(undef, $ae_error => $_[2]);
		1134	});
		1135	$_[0]->on_read (sub { });
		1136	}
		1137	}
		1138	};
		1139
		1140	# if keepalive is enabled, then the server closing the connection
		1141	# before a response can happen legally - we retry on idempotent methods.
		1142	if ($was_persistent && $idempotent) {
		1143	my $old_eof = $hdl->{on_eof};
		1144	$hdl->{on_eof} = sub {
		1145	_destroy_state %state;
		1146
		1147	%state = ();
		1148	$state{recurse} =
		1149	http_request (
		1150	$method => $url,
		1151	%arg,
		1152	recurse => $recurse - 1,
		1153	persistent => 0,
		1154	sub {
		1155	%state = ();
		1156	&$cb
		1157	}
		1158	);
		1159	};
		1160	$hdl->on_read (sub {
		1161	return unless %state;
		1162
		1163	# as soon as we receive something, a connection close
		1164	# once more becomes a hard error
		1165	$hdl->{on_eof} = $old_eof;
		1166	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1167	});
		1168	} else {
		1169	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1170	}
		1171	};
		1172
		1173	my $prepare_handle = sub {
		1174	my ($hdl) = $state{handle};
		1175
		1176	$hdl->on_error (sub {
		1177	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1178	});
		1179	$hdl->on_eof (sub {
		1180	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1181	});
		1182	$hdl->timeout_reset;
		1183	$hdl->timeout ($timeout);
		1184	};
		1185
		1186	# connected to proxy (or origin server)
		1187	my $connect_cb = sub {
		1188	my $fh = shift
		1189	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1190
		1191	return unless delete $state{connect_guard};
		1192
		1193	# get handle
		1194	$state{handle} = new AnyEvent::Handle
		1195	%{ $arg{handle_params} },
		1196	fh => $fh,
		1197	peername => $uhost,
		1198	tls_ctx => $arg{tls_ctx},
		1199	;
		1200
		1201	$prepare_handle->();
		1202
		1203	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1204
		1205	# now handle proxy-CONNECT method
		1206	if ($proxy && $uscheme eq "https") {
		1207	# oh dear, we have to wrap it into a connect request
		1208
		1209	my $auth = exists $hdr{"proxy-authorization"}
		1210	? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012"
		1211	: "";
		1212
		1213	# maybe re-use $uauthority with patched port?
		1214	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012");
		1215	$state{handle}->push_read (line => $qr_nlnl, sub {
		1216	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1217	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1218
		1219	if ($2 == 200) {
		1220	$rpath = $upath;
		1221	$handle_actual_request->();
		1222	} else {
		1223	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1224	}
		1225	});
		1226	} else {
		1227	delete $hdr{"proxy-authorization"} unless $proxy;
		1228
		1229	$handle_actual_request->();
		1230	}
		1231	};
424		1232
425	_get_slot $uhost, sub {	1233	_get_slot $uhost, sub {
426	$state{slot_guard} = shift;	1234	$state{slot_guard} = shift;
427		1235
428	return unless $state{connect_guard};	1236	return unless $state{connect_guard};
429		1237
430	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	1238	# try to use an existing keepalive connection, but only if we, ourselves, plan
431	$state{fh} = shift	1239	# on a keepalive request (in theory, this should be a separate config option).
432	or do {	1240	if ($persistent && $KA_CACHE{$ka_key}) {
433	my $err = "$!";	1241	$was_persistent = 1;
434	%state = ();
435	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
436	};
437		1242
438	pop; # free memory, save a tree	1243	$state{handle} = ka_fetch $ka_key;
		1244	# $state{handle}->destroyed
		1245	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
		1246	$prepare_handle->();
		1247	# $state{handle}->destroyed
		1248	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
		1249	$rpath = $upath;
		1250	$handle_actual_request->();
439		1251
440	return unless delete $state{connect_guard};
441
442	# get handle
443	$state{handle} = new AnyEvent::Handle
444	fh => $state{fh},
445	timeout => $timeout,
446	peername => $rhost,
447	tls_ctx => $arg{tls_ctx};
448
449	# limit the number of persistent connections
450	# keepalive not yet supported
451	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
452	++$KA_COUNT{$_[1]};
453	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
454	--$KA_COUNT{$_[1]}
455	};
456	$hdr{connection} = "keep-alive";
457	} else {	1252	} else {
458	delete $hdr{connection};	1253	my $tcp_connect = $arg{tcp_connect}
459	}	1254	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
460		1255
461	# (re-)configure handle	1256	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
462	$state{handle}->on_error (sub {
463	%state = ();
464	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
465	});
466	$state{handle}->on_eof (sub {
467	%state = ();
468	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
469	});
470
471	$state{handle}->starttls ("connect") if $rscheme eq "https";
472
473	# handle actual, non-tunneled, request
474	my $handle_actual_request = sub {
475	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
476
477	# send request
478	$state{handle}->push_write (
479	"$method $rpath HTTP/1.0\015\012"
480	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
481	. "\015\012"
482	. (delete $arg{body})
483	);
484
485	%hdr = (); # reduce memory usage, save a kitten
486
487	# status line
488	$state{handle}->push_read (line => $qr_nl, sub {
489	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
490	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
491
492	my %hdr = ( # response headers
493	HTTPVersion => ",$1",
494	Status => ",$2",
495	Reason => ",$3",
496	URL => ",$url"
497	);
498
499	# headers, could be optimized a bit
500	$state{handle}->unshift_read (line => $qr_nlnl, sub {
501	for ("$_[1]") {
502	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
503
504	# things seen, not parsed:
505	# p3pP="NON CUR OTPi OUR NOR UNI"
506
507	$hdr{lc $1} .= ",$2"
508	while /\G
509	([^:\000-\037]*):
510	[\011\040]*
511	((?: [^\012]+ | \012[\011\040] )*)
512	\012
513	/gxc;
514
515	/\G$/
516	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
517	}
518
519	substr $_, 0, 1, ""
520	for values %hdr;
521
522	# redirect handling
523	# microsoft and other shitheads don't give a shit for following standards,
524	# try to support some common forms of broken Location headers.
525	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
526	$hdr{location} =~ s/^\.\/+//;
527
528	my $url = "$rscheme://$uhost:$uport";
529
530	unless ($hdr{location} =~ s/^\///) {
531	$url .= $upath;
532	$url =~ s/\/[^\/]*$//;
533	}
534
535	$hdr{location} = "$url/$hdr{location}";
536	}
537
538	my $redirect;
539
540	if ($recurse) {
541	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
542	# apparently, mozilla et al. just change POST to GET here
543	# more research is needed before we do the same
544	$redirect = 1;
545	} elsif ($hdr{Status} == 303) {
546	# even http/1.1 is unclear on how to mutate the method
547	$method = "GET" unless $method eq "HEAD";
548	$redirect = 1;
549	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) {
550	$redirect = 1;
551	}
552	}
553
554	my $finish = sub {
555	$state{handle}->destroy if $state{handle};
556	%state = ();
557
558	# set-cookie processing
559	if ($arg{cookie_jar}) {
560	for ($_[1]{"set-cookie"}) {
561	# parse NAME=VALUE
562	my @kv;
563
564	while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
565	my $name = $1;
566	my $value = $3;
567
568	unless ($value) {
569	$value = $2;
570	$value =~ s/\\(.)/$1/gs;
571	}
572
573	push @kv, $name => $value;
574
575	last unless /\G\s*;/gc;
576	}
577
578	last unless @kv;
579
580	my $name = shift @kv;
581	my %kv = (value => shift @kv, @kv);
582
583	my $cdom;
584	my $cpath = (delete $kv{path}) || "/";
585
586	if (exists $kv{domain}) {
587	$cdom = delete $kv{domain};
588		1257	}
589	$cdom =~ s/^\.?/./; # make sure it starts with a "."
590
591	next if $cdom =~ /\.$/;
592
593	# this is not rfc-like and not netscape-like. go figure.
594	my $ndots = $cdom =~ y/.//;
595	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
596	} else {
597	$cdom = $uhost;
598	}
599
600	# store it
601	$arg{cookie_jar}{version} = 1;
602	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
603
604	redo if /\G\s*,/gc;
605	}
606	}
607
608	if ($redirect && exists $hdr{location}) {
609	# we ignore any errors, as it is very common to receive
610	# Content-Length != 0 but no actual body
611	# we also access %hdr, as $_[1] might be an erro
612	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
613	} else {
614	$cb->($_[0], $_[1]);
615	}
616	};
617
618	my $len = $hdr{"content-length"};
619
620	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
621	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
622	} elsif (
623	$hdr{Status} =~ /^(?:1..|[23]04)$/
624	or $method eq "HEAD"
625	or (defined $len && !$len)
626	) {
627	# no body
628	$finish->("", \%hdr);
629	} else {
630	# body handling, four different code paths
631	# for want_body_handle, on_body (2x), normal (2x)
632	# we might read too much here, but it does not matter yet (no pers. connections)
633	if (!$redirect && $arg{want_body_handle}) {
634	$_[0]->on_eof (undef);
635	$_[0]->on_error (undef);
636	$_[0]->on_read (undef);
637
638	$finish->(delete $state{handle}, \%hdr);
639
640	} elsif ($arg{on_body}) {
641	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
642	if ($len) {
643	$_[0]->on_eof (undef);
644	$_[0]->on_read (sub {
645	$len -= length $_[0]{rbuf};
646
647	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
648	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
649
650	$len > 0
651	or $finish->("", \%hdr);
652	});
653	} else {
654	$_[0]->on_eof (sub {
655	$finish->("", \%hdr);
656	});
657	$_[0]->on_read (sub {
658	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
659	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
660	});
661	}
662	} else {
663	$_[0]->on_eof (undef);
664
665	if ($len) {
666	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
667	$_[0]->on_read (sub {
668	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
669	if $len <= length $_[0]{rbuf};
670	});
671	} else {
672	$_[0]->on_error (sub {
673	$! == Errno::EPIPE || !$!
674	? $finish->(delete $_[0]{rbuf}, \%hdr)
675	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
676	});
677	$_[0]->on_read (sub { });
678	}
679	}
680	}
681	});
682	});
683	};
684
685	# now handle proxy-CONNECT method
686	if ($proxy && $uscheme eq "https") {
687	# oh dear, we have to wrap it into a connect request
688
689	# maybe re-use $uauthority with patched port?
690	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
691	$state{handle}->push_read (line => $qr_nlnl, sub {
692	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
693	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
694
695	if ($2 == 200) {
696	$rpath = $upath;
697	&$handle_actual_request;
698	} else {
699	%state = ();
700	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
701	}
702	});
703	} else {
704	&$handle_actual_request;
705	}
706
707	}, $arg{on_prepare} || sub { $timeout };
708	};	1258	};
709		1259
710	defined wantarray && AnyEvent::Util::guard { %state = () }	1260	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
711	}	1261	}
712		1262
713	sub http_get($@) {	1263	sub http_get($@) {
714	unshift @_, "GET";	1264	unshift @_, "GET";
715	&http_request	1265	&http_request
…		…
726	&http_request	1276	&http_request
727	}	1277	}
728		1278
729	=back	1279	=back
730		1280
		1281	=head2 DNS CACHING
		1282
		1283	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		1284	the actual connection, which in turn uses AnyEvent::DNS to resolve
		1285	hostnames. The latter is a simple stub resolver and does no caching
		1286	on its own. If you want DNS caching, you currently have to provide
		1287	your own default resolver (by storing a suitable resolver object in
		1288	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
		1289
731	=head2 GLOBAL FUNCTIONS AND VARIABLES	1290	=head2 GLOBAL FUNCTIONS AND VARIABLES
732		1291
733	=over 4	1292	=over 4
734		1293
735	=item AnyEvent::HTTP::set_proxy "proxy-url"	1294	=item AnyEvent::HTTP::set_proxy "proxy-url"
736		1295
737	Sets the default proxy server to use. The proxy-url must begin with a	1296	Sets the default proxy server to use. The proxy-url must begin with a
738	string of the form C<http://host:port> (optionally C<https:...>).	1297	string of the form C<http://host:port>, croaks otherwise.
		1298
		1299	To clear an already-set proxy, use C<undef>.
		1300
		1301	When AnyEvent::HTTP is loaded for the first time it will query the
		1302	default proxy from the operating system, currently by looking at
		1303	C<$ENV{http_proxy>}.
		1304
		1305	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1306
		1307	Remove all cookies from the cookie jar that have been expired. If
		1308	C<$session_end> is given and true, then additionally remove all session
		1309	cookies.
		1310
		1311	You should call this function (with a true C<$session_end>) before you
		1312	save cookies to disk, and you should call this function after loading them
		1313	again. If you have a long-running program you can additionally call this
		1314	function from time to time.
		1315
		1316	A cookie jar is initially an empty hash-reference that is managed by this
		1317	module. Its format is subject to change, but currently it is as follows:
		1318
		1319	The key C<version> has to contain C<2>, otherwise the hash gets
		1320	cleared. All other keys are hostnames or IP addresses pointing to
		1321	hash-references. The key for these inner hash references is the
		1322	server path for which this cookie is meant, and the values are again
		1323	hash-references. Each key of those hash-references is a cookie name, and
		1324	the value, you guessed it, is another hash-reference, this time with the
		1325	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1326	which have been replaced by a C<_expires> key that contains the cookie
		1327	expiry timestamp. Session cookies are indicated by not having an
		1328	C<_expires> key.
		1329
		1330	Here is an example of a cookie jar with a single cookie, so you have a
		1331	chance of understanding the above paragraph:
		1332
		1333	{
		1334	version => 2,
		1335	"10.0.0.1" => {
		1336	"/" => {
		1337	"mythweb_id" => {
		1338	_expires => 1293917923,
		1339	value => "ooRung9dThee3ooyXooM1Ohm",
		1340	},
		1341	},
		1342	},
		1343	}
		1344
		1345	=item $date = AnyEvent::HTTP::format_date $timestamp
		1346
		1347	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1348	Date (RFC 2616).
		1349
		1350	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1351
		1352	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1353	bunch of minor variations of those, and returns the corresponding POSIX
		1354	timestamp, or C<undef> if the date cannot be parsed.
739		1355
740	=item $AnyEvent::HTTP::MAX_RECURSE	1356	=item $AnyEvent::HTTP::MAX_RECURSE
741		1357
742	The default value for the C<recurse> request parameter (default: C<10>).	1358	The default value for the C<recurse> request parameter (default: C<10>).
		1359
		1360	=item $AnyEvent::HTTP::TIMEOUT
		1361
		1362	The default timeout for connection operations (default: C<300>).
743		1363
744	=item $AnyEvent::HTTP::USERAGENT	1364	=item $AnyEvent::HTTP::USERAGENT
745		1365
746	The default value for the C<User-Agent> header (the default is	1366	The default value for the C<User-Agent> header (the default is
747	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1367	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
748		1368
749	=item $AnyEvent::HTTP::MAX_PER_HOST	1369	=item $AnyEvent::HTTP::MAX_PER_HOST
750		1370
751	The maximum number of concurrent connections to the same host (identified	1371	The maximum number of concurrent connections to the same host (identified
752	by the hostname). If the limit is exceeded, then the additional requests	1372	by the hostname). If the limit is exceeded, then additional requests
753	are queued until previous connections are closed.	1373	are queued until previous connections are closed. Both persistent and
		1374	non-persistent connections are counted in this limit.
754		1375
755	The default value for this is C<4>, and it is highly advisable to not	1376	The default value for this is C<4>, and it is highly advisable to not
756	increase it.	1377	increase it much.
		1378
		1379	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1380	connections, older browsers used 2, newer ones (such as firefox 3)
		1381	typically use 6, and Opera uses 8 because like, they have the fastest
		1382	browser and give a shit for everybody else on the planet.
		1383
		1384	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1385
		1386	The time after which idle persistent connections get closed by
		1387	AnyEvent::HTTP (default: C<3>).
757		1388
758	=item $AnyEvent::HTTP::ACTIVE	1389	=item $AnyEvent::HTTP::ACTIVE
759		1390
760	The number of active connections. This is not the number of currently	1391	The number of active connections. This is not the number of currently
761	running requests, but the number of currently open and non-idle TCP	1392	running requests, but the number of currently open and non-idle TCP
762	connections. This number of can be useful for load-leveling.	1393	connections. This number can be useful for load-leveling.
763		1394
764	=back	1395	=back
765		1396
766	=cut	1397	=cut
767		1398
		1399	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1400	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1401
		1402	sub format_date($) {
		1403	my ($time) = @_;
		1404
		1405	# RFC 822/1123 format
		1406	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1407
		1408	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1409	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1410	$H, $M, $S;
		1411	}
		1412
		1413	sub parse_date($) {
		1414	my ($date) = @_;
		1415
		1416	my ($d, $m, $y, $H, $M, $S);
		1417
		1418	if ($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$/) {
		1419	# RFC 822/1123, required by RFC 2616 (with " ")
		1420	# cookie dates (with "-")
		1421
		1422	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1423
		1424	} elsif ($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$/) {
		1425	# RFC 850
		1426	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1427
		1428	} elsif ($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])$/) {
		1429	# ISO C's asctime
		1430	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1431	}
		1432	# other formats fail in the loop below
		1433
		1434	for (0..11) {
		1435	if ($m eq $month[$_]) {
		1436	require Time::Local;
		1437	return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) };
		1438	}
		1439	}
		1440
		1441	undef
		1442	}
		1443
768	sub set_proxy($) {	1444	sub set_proxy($) {
769	$PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1445	if (length $_[0]) {
		1446	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
		1447	or Carp::croak "$_[0]: invalid proxy URL";
		1448	$PROXY = [$2, $3 || 3128, $1]
		1449	} else {
		1450	undef $PROXY;
		1451	}
770	}	1452	}
771		1453
772	# initialise proxy from environment	1454	# initialise proxy from environment
		1455	eval {
773	set_proxy $ENV{http_proxy};	1456	set_proxy $ENV{http_proxy};
		1457	};
		1458
		1459	=head2 SHOWCASE
		1460
		1461	This section contains some more elaborate "real-world" examples or code
		1462	snippets.
		1463
		1464	=head2 HTTP/1.1 FILE DOWNLOAD
		1465
		1466	Downloading files with HTTP can be quite tricky, especially when something
		1467	goes wrong and you want to resume.
		1468
		1469	Here is a function that initiates and resumes a download. It uses the
		1470	last modified time to check for file content changes, and works with many
		1471	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1472	on older servers.
		1473
		1474	It calls the completion callback with either C<undef>, which means a
		1475	nonretryable error occurred, C<0> when the download was partial and should
		1476	be retried, and C<1> if it was successful.
		1477
		1478	use AnyEvent::HTTP;
		1479
		1480	sub download($$$) {
		1481	my ($url, $file, $cb) = @_;
		1482
		1483	open my $fh, "+<", $file
		1484	or die "$file: $!";
		1485
		1486	my %hdr;
		1487	my $ofs = 0;
		1488
		1489	if (stat $fh and -s _) {
		1490	$ofs = -s _;
		1491	warn "-s is ", $ofs;
		1492	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1493	$hdr{"range"} = "bytes=$ofs-";
		1494	}
		1495
		1496	http_get $url,
		1497	headers => \%hdr,
		1498	on_header => sub {
		1499	my ($hdr) = @_;
		1500
		1501	if ($hdr->{Status} == 200 && $ofs) {
		1502	# resume failed
		1503	truncate $fh, $ofs = 0;
		1504	}
		1505
		1506	sysseek $fh, $ofs, 0;
		1507
		1508	1
		1509	},
		1510	on_body => sub {
		1511	my ($data, $hdr) = @_;
		1512
		1513	if ($hdr->{Status} =~ /^2/) {
		1514	length $data == syswrite $fh, $data
		1515	or return; # abort on write errors
		1516	}
		1517
		1518	1
		1519	},
		1520	sub {
		1521	my (undef, $hdr) = @_;
		1522
		1523	my $status = $hdr->{Status};
		1524
		1525	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1526	utime $time, $time, $fh;
		1527	}
		1528
		1529	if ($status == 200 || $status == 206 || $status == 416) {
		1530	# download ok || resume ok || file already fully downloaded
		1531	$cb->(1, $hdr);
		1532
		1533	} elsif ($status == 412) {
		1534	# file has changed while resuming, delete and retry
		1535	unlink $file;
		1536	$cb->(0, $hdr);
		1537
		1538	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1539	# retry later
		1540	$cb->(0, $hdr);
		1541
		1542	} else {
		1543	$cb->(undef, $hdr);
		1544	}
		1545	}
		1546	;
		1547	}
		1548
		1549	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1550	if ($_[0]) {
		1551	print "OK!\n";
		1552	} elsif (defined $_[0]) {
		1553	print "please retry later\n";
		1554	} else {
		1555	print "ERROR\n";
		1556	}
		1557	};
		1558
		1559	=head3 SOCKS PROXIES
		1560
		1561	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1562	compile your perl to support socks, or use an external program such as
		1563	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1564	transparently.
		1565
		1566	Alternatively, for AnyEvent::HTTP only, you can use your own
		1567	C<tcp_connect> function that does the proxy handshake - here is an example
		1568	that works with socks4a proxies:
		1569
		1570	use Errno;
		1571	use AnyEvent::Util;
		1572	use AnyEvent::Socket;
		1573	use AnyEvent::Handle;
		1574
		1575	# host, port and username of/for your socks4a proxy
		1576	my $socks_host = "10.0.0.23";
		1577	my $socks_port = 9050;
		1578	my $socks_user = "";
		1579
		1580	sub socks4a_connect {
		1581	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1582
		1583	my $hdl = new AnyEvent::Handle
		1584	connect => [$socks_host, $socks_port],
		1585	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1586	on_error => sub { $connect_cb->() },
		1587	;
		1588
		1589	$hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host);
		1590
		1591	$hdl->push_read (chunk => 8, sub {
		1592	my ($hdl, $chunk) = @_;
		1593	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1594
		1595	if ($status == 0x5a) {
		1596	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1597	} else {
		1598	$! = Errno::ENXIO; $connect_cb->();
		1599	}
		1600	});
		1601
		1602	$hdl
		1603	}
		1604
		1605	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1606	possibly after switching off other proxy types:
		1607
		1608	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1609
		1610	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1611	my ($data, $headers) = @_;
		1612	...
		1613	};
774		1614
775	=head1 SEE ALSO	1615	=head1 SEE ALSO
776		1616
777	L<AnyEvent>.	1617	L<AnyEvent>.
778		1618

Diff Legend

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