ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.44 by root, Tue Jul 7 00:15:32 2009 UTC vs.
Revision 1.134 by root, Fri Sep 7 22:11:31 2018 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 4.8 ();	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 = '1.4';	51	our $VERSION = 2.24;
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 occurred), 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" C<HTTPVersion>, C<Status> and C<Reason>	98	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		99	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	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>.
		104
106	pseudo-header C<URL> contains the original URL (which can differ from the	105	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	106	the requested URL when following redirects - for example, you might get
		107	an error that your URL scheme is not supported even though your URL is a
		108	valid http URL because it redirected to an ftp URL, in which case you can
		109	look at the URL pseudo header).
		110
		111	The pseudo-header C<Redirect> only exists when the request was a result
		112	of an internal redirect. In that case it is an array reference with
		113	the C<($data, $headers)> from the redirect response. Note that this
		114	response could in turn be the result of a redirect itself, and C<<
		115	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		116	response, and so on.
108		117
109	If the server sends a header multiple times, then their contents will be	118	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	119	joined together with a comma (C<,>), as per the HTTP spec.
111		120
112	If an internal error occurs, such as not being able to resolve a hostname,	121	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>	122	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
114	(usually C<599>) and the C<Reason> pseudo-header will contain an error	123	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
115	message.	124	message. Currently the following status codes are used:
		125
		126	=over 4
		127
		128	=item 595 - errors during connection establishment, proxy handshake.
		129
		130	=item 596 - errors during TLS negotiation, request sending and header processing.
		131
		132	=item 597 - errors during body receiving or processing.
		133
		134	=item 598 - user aborted request via C<on_header> or C<on_body>.
		135
		136	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		137
		138	=back
116		139
117	A typical callback might look like this:	140	A typical callback might look like this:
118		141
119	sub {	142	sub {
120	my ($body, $hdr) = @_;	143	my ($body, $hdr) = @_;
…		…
131		154
132	=over 4	155	=over 4
133		156
134	=item recurse => $count (default: $MAX_RECURSE)	157	=item recurse => $count (default: $MAX_RECURSE)
135		158
136	Whether to recurse requests or not, e.g. on redirects, authentication	159	Whether to recurse requests or not, e.g. on redirects, authentication and
137	retries and so on, and how often to do so.	160	other retries and so on, and how often to do so.
		161
		162	Only redirects to http and https URLs are supported. While most common
		163	redirection forms are handled entirely within this module, some require
		164	the use of the optional L<URI> module. If it is required but missing, then
		165	the request will fail with an error.
138		166
139	=item headers => hashref	167	=item headers => hashref
140		168
141	The request headers to use. Currently, C<http_request> may provide its	169	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	170	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
143	and will provide defaults for C<User-Agent:> and C<Referer:>.	171	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		172	(this can be suppressed by using C<undef> for these headers in which case
		173	they won't be sent at all).
		174
		175	You really should provide your own C<User-Agent:> header value that is
		176	appropriate for your program - I wouldn't be surprised if the default
		177	AnyEvent string gets blocked by webservers sooner or later.
		178
		179	Also, make sure that your headers names and values do not contain any
		180	embedded newlines.
144		181
145	=item timeout => $seconds	182	=item timeout => $seconds
146		183
147	The time-out to use for various stages - each connect attempt will reset	184	The time-out to use for various stages - each connect attempt will reset
148	the timeout, as will read or write activity. Default timeout is 5 minutes.	185	the timeout, as will read or write activity, i.e. this is not an overall
		186	timeout.
		187
		188	Default timeout is 5 minutes.
149		189
150	=item proxy => [$host, $port[, $scheme]] or undef	190	=item proxy => [$host, $port[, $scheme]] or undef
151		191
152	Use the given http proxy for all requests. If not specified, then the	192	Use the given http proxy for all requests, or no proxy if C<undef> is
153	default proxy (as specified by C<$ENV{http_proxy}>) is used.	193	used.
154		194
155	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	195	C<$scheme> must be either missing or must be C<http> for HTTP.
156	HTTPS.	196
		197	If not specified, then the default proxy is used (see
		198	C<AnyEvent::HTTP::set_proxy>).
		199
		200	Currently, if your proxy requires authorization, you have to specify an
		201	appropriate "Proxy-Authorization" header in every request.
157		202
158	=item body => $string	203	=item body => $string
159		204
160	The request body, usually empty. Will be-sent as-is (future versions of	205	The request body, usually empty. Will be sent as-is (future versions of
161	this module might offer more options).	206	this module might offer more options).
162		207
163	=item cookie_jar => $hash_ref	208	=item cookie_jar => $hash_ref
164		209
165	Passing this parameter enables (simplified) cookie-processing, loosely	210	Passing this parameter enables (simplified) cookie-processing, loosely
166	based on the original netscape specification.	211	based on the original netscape specification.
167		212
168	The C<$hash_ref> must be an (initially empty) hash reference which will	213	The C<$hash_ref> must be an (initially empty) hash reference which
169	get updated automatically. It is possible to save the cookie_jar to	214	will get updated automatically. It is possible to save the cookie jar
170	persistent storage with something like JSON or Storable, but this is not	215	to persistent storage with something like JSON or Storable - see the
171	recommended, as expiry times are currently being ignored.	216	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		217	expired or session-only cookies, and also for documentation on the format
		218	of the cookie jar.
172		219
173	Note that this cookie implementation is not of very high quality, nor	220	Note that this cookie implementation is not meant to be complete. If
174	meant to be complete. If you want complete cookie management you have to	221	you want complete cookie management you have to do that on your
175	do that on your own. C<cookie_jar> is meant as a quick fix to get some	222	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
176	cookie-using sites working. Cookies are a privacy disaster, do not use	223	working. Cookies are a privacy disaster, do not use them unless required
177	them unless required to.	224	to.
		225
		226	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		227	headers will be set and handled by this module, otherwise they will be
		228	left untouched.
178		229
179	=item tls_ctx => $scheme | $tls_ctx	230	=item tls_ctx => $scheme | $tls_ctx
180		231
181	Specifies the AnyEvent::TLS context to be used for https connections. This	232	Specifies the AnyEvent::TLS context to be used for https connections. This
182	parameter follows the same rules as the C<tls_ctx> parameter to	233	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
186	verification) TLS context.	237	verification) TLS context.
187		238
188	The default for this option is C<low>, which could be interpreted as "give	239	The default for this option is C<low>, which could be interpreted as "give
189	me the page, no matter what".	240	me the page, no matter what".
190		241
		242	See also the C<sessionid> parameter.
		243
		244	=item session => $string
		245
		246	The module might reuse connections to the same host internally. Sometimes
		247	(e.g. when using TLS), you do not want to reuse connections from other
		248	sessions. This can be achieved by setting this parameter to some unique
		249	ID (such as the address of an object storing your state data, or the TLS
		250	context) - only connections using the same unique ID will be reused.
		251
		252	=item on_prepare => $callback->($fh)
		253
		254	In rare cases you need to "tune" the socket before it is used to
		255	connect (for example, to bind it on a given IP address). This parameter
		256	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		257	and behaves exactly the same way (e.g. it has to provide a
		258	timeout). See the description for the C<$prepare_cb> argument of
		259	C<AnyEvent::Socket::tcp_connect> for details.
		260
		261	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		262
		263	In even rarer cases you want total control over how AnyEvent::HTTP
		264	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		265	to do this, but you can provide your own C<tcp_connect> function -
		266	obviously, it has to follow the same calling conventions, except that it
		267	may always return a connection guard object.
		268
		269	The connections made by this hook will be treated as equivalent to
		270	connecitons made the built-in way, specifically, they will be put into
		271	and taken from the persistent conneciton cache. If your C<$tcp_connect>
		272	function is incompatible with this kind of re-use, consider switching off
		273	C<persistent> connections and/or providing a C<session> identifier.
		274
		275	There are probably lots of weird uses for this function, starting from
		276	tracing the hosts C<http_request> actually tries to connect, to (inexact
		277	but fast) host => IP address caching or even socks protocol support.
		278
191	=item on_header => $callback->($headers)	279	=item on_header => $callback->($headers)
192		280
193	When specified, this callback will be called with the header hash as soon	281	When specified, this callback will be called with the header hash as soon
194	as headers have been successfully received from the remote server (not on	282	as headers have been successfully received from the remote server (not on
195	locally-generated errors).	283	locally-generated errors).
…		…
200		288
201	This callback is useful, among other things, to quickly reject unwanted	289	This callback is useful, among other things, to quickly reject unwanted
202	content, which, if it is supposed to be rare, can be faster than first	290	content, which, if it is supposed to be rare, can be faster than first
203	doing a C<HEAD> request.	291	doing a C<HEAD> request.
204		292
		293	The downside is that cancelling the request makes it impossible to re-use
		294	the connection. Also, the C<on_header> callback will not receive any
		295	trailer (headers sent after the response body).
		296
205	Example: cancel the request unless the content-type is "text/html".	297	Example: cancel the request unless the content-type is "text/html".
206		298
207	on_header => sub {	299	on_header => sub {
208	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/	300	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/
209	},	301	},
…		…
216		308
217	It has to return either true (in which case AnyEvent::HTTP will continue),	309	It has to return either true (in which case AnyEvent::HTTP will continue),
218	or false, in which case AnyEvent::HTTP will cancel the download (and call	310	or false, in which case AnyEvent::HTTP will cancel the download (and call
219	the completion callback with an error code of C<598>).	311	the completion callback with an error code of C<598>).
220		312
		313	The downside to cancelling the request is that it makes it impossible to
		314	re-use the connection.
		315
221	This callback is useful when the data is too large to be held in memory	316	This callback is useful when the data is too large to be held in memory
222	(so the callback writes it to a file) or when only some information should	317	(so the callback writes it to a file) or when only some information should
223	be extracted, or when the body should be processed incrementally.	318	be extracted, or when the body should be processed incrementally.
224		319
225	It is usually preferred over doing your own body handling via	320	It is usually preferred over doing your own body handling via
226	C<want_body_handle>.	321	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		322	only used to create a connection, C<want_body_handle> is the better
		323	alternative, as it allows you to install your own event handler, reducing
		324	resource usage.
227		325
228	=item want_body_handle => $enable	326	=item want_body_handle => $enable
229		327
230	When enabled (default is disabled), the behaviour of AnyEvent::HTTP	328	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
231	changes considerably: after parsing the headers, and instead of	329	changes considerably: after parsing the headers, and instead of
…		…
233	called. Instead of the C<$body> argument containing the body data, the	331	called. Instead of the C<$body> argument containing the body data, the
234	callback will receive the L<AnyEvent::Handle> object associated with the	332	callback will receive the L<AnyEvent::Handle> object associated with the
235	connection. In error cases, C<undef> will be passed. When there is no body	333	connection. In error cases, C<undef> will be passed. When there is no body
236	(e.g. status C<304>), the empty string will be passed.	334	(e.g. status C<304>), the empty string will be passed.
237		335
238	The handle object might or might not be in TLS mode, might be connected to	336	The handle object might or might not be in TLS mode, might be connected
239	a proxy, be a persistent connection etc., and configured in unspecified	337	to a proxy, be a persistent connection, use chunked transfer encoding
240	ways. The user is responsible for this handle (it will not be used by this	338	etc., and configured in unspecified ways. The user is responsible for this
241	module anymore).	339	handle (it will not be used by this module anymore).
242		340
243	This is useful with some push-type services, where, after the initial	341	This is useful with some push-type services, where, after the initial
244	headers, an interactive protocol is used (typical example would be the	342	headers, an interactive protocol is used (typical example would be the
245	push-style twitter API which starts a JSON/XML stream).	343	push-style twitter API which starts a JSON/XML stream).
246		344
247	If you think you need this, first have a look at C<on_body>, to see if	345	If you think you need this, first have a look at C<on_body>, to see if
248	that doesn'T solve your problem in a better way.	346	that doesn't solve your problem in a better way.
		347
		348	=item persistent => $boolean
		349
		350	Try to create/reuse a persistent connection. When this flag is set
		351	(default: true for idempotent requests, false for all others), then
		352	C<http_request> tries to re-use an existing (previously-created)
		353	persistent connection to same host (i.e. identical URL scheme, hostname,
		354	port and session) and, failing that, tries to create a new one.
		355
		356	Requests failing in certain ways will be automatically retried once, which
		357	is dangerous for non-idempotent requests, which is why it defaults to off
		358	for them. The reason for this is because the bozos who designed HTTP/1.1
		359	made it impossible to distinguish between a fatal error and a normal
		360	connection timeout, so you never know whether there was a problem with
		361	your request or not.
		362
		363	When reusing an existent connection, many parameters (such as TLS context)
		364	will be ignored. See the C<session> parameter for a workaround.
		365
		366	=item keepalive => $boolean
		367
		368	Only used when C<persistent> is also true. This parameter decides whether
		369	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		370	(as opposed to only a HTTP/1.1 persistent connection).
		371
		372	The default is true, except when using a proxy, in which case it defaults
		373	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		374
		375	=item handle_params => { key => value ... }
		376
		377	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		378	constructor that is called - not all requests will create a handle, and
		379	sometimes more than one is created, so this parameter is only good for
		380	setting hints.
		381
		382	Example: set the maximum read size to 4096, to potentially conserve memory
		383	at the cost of speed.
		384
		385	handle_params => {
		386	max_read_size => 4096,
		387	},
249		388
250	=back	389	=back
251		390
252	Example: make a simple HTTP GET request for http://www.nethype.de/	391	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		392	the response body.
253		393
254	http_request GET => "http://www.nethype.de/", sub {	394	http_request GET => "http://www.nethype.de/", sub {
255	my ($body, $hdr) = @_;	395	my ($body, $hdr) = @_;
256	print "$body\n";	396	print "$body\n";
257	};	397	};
258		398
259	Example: make a HTTP HEAD request on https://www.google.com/, use a	399	Example: do a HTTP HEAD request on https://www.google.com/, use a
260	timeout of 30 seconds.	400	timeout of 30 seconds.
261		401
262	http_request	402	http_request
263	GET => "https://www.google.com",	403	HEAD => "https://www.google.com",
		404	headers => { "user-agent" => "MySearchClient 1.0" },
264	timeout => 30,	405	timeout => 30,
265	sub {	406	sub {
266	my ($body, $hdr) = @_;	407	my ($body, $hdr) = @_;
267	use Data::Dumper;	408	use Data::Dumper;
268	print Dumper $hdr;	409	print Dumper $hdr;
269	}	410	}
270	;	411	;
271		412
272	Example: make another simple HTTP GET request, but immediately try to	413	Example: do another simple HTTP GET request, but immediately try to
273	cancel it.	414	cancel it.
274		415
275	my $request = http_request GET => "http://www.nethype.de/", sub {	416	my $request = http_request GET => "http://www.nethype.de/", sub {
276	my ($body, $hdr) = @_;	417	my ($body, $hdr) = @_;
277	print "$body\n";	418	print "$body\n";
278	};	419	};
279		420
280	undef $request;	421	undef $request;
281		422
282	=cut	423	=cut
		424
		425	#############################################################################
		426	# wait queue/slots
283		427
284	sub _slot_schedule;	428	sub _slot_schedule;
285	sub _slot_schedule($) {	429	sub _slot_schedule($) {
286	my $host = shift;	430	my $host = shift;
287		431
…		…
309	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	453	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
310		454
311	_slot_schedule $_[0];	455	_slot_schedule $_[0];
312	}	456	}
313		457
314	our $qr_nl = qr<\015?\012>;	458	#############################################################################
315	our $qr_nlnl = qr<\015?\012\015?\012>;	459	# cookie handling
		460
		461	# expire cookies
		462	sub cookie_jar_expire($;$) {
		463	my ($jar, $session_end) = @_;
		464
		465	%$jar = () if $jar->{version} != 2;
		466
		467	my $anow = AE::now;
		468
		469	while (my ($chost, $paths) = each %$jar) {
		470	next unless ref $paths;
		471
		472	while (my ($cpath, $cookies) = each %$paths) {
		473	while (my ($cookie, $kv) = each %$cookies) {
		474	if (exists $kv->{_expires}) {
		475	delete $cookies->{$cookie}
		476	if $anow > $kv->{_expires};
		477	} elsif ($session_end) {
		478	delete $cookies->{$cookie};
		479	}
		480	}
		481
		482	delete $paths->{$cpath}
		483	unless %$cookies;
		484	}
		485
		486	delete $jar->{$chost}
		487	unless %$paths;
		488	}
		489	}
		490
		491	# extract cookies from jar
		492	sub cookie_jar_extract($$$$) {
		493	my ($jar, $scheme, $host, $path) = @_;
		494
		495	%$jar = () if $jar->{version} != 2;
		496
		497	$host = AnyEvent::Util::idn_to_ascii $host
		498	if $host =~ /[^\x00-\x7f]/;
		499
		500	my @cookies;
		501
		502	while (my ($chost, $paths) = each %$jar) {
		503	next unless ref $paths;
		504
		505	# exact match or suffix including . match
		506	$chost eq $host or ".$chost" eq substr $host, -1 - length $chost
		507	or next;
		508
		509	while (my ($cpath, $cookies) = each %$paths) {
		510	next unless $cpath eq substr $path, 0, length $cpath;
		511
		512	while (my ($cookie, $kv) = each %$cookies) {
		513	next if $scheme ne "https" && exists $kv->{secure};
		514
		515	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		516	delete $cookies->{$cookie};
		517	next;
		518	}
		519
		520	my $value = $kv->{value};
		521
		522	if ($value =~ /[=;,[:space:]]/) {
		523	$value =~ s/([\\"])/\\$1/g;
		524	$value = "\"$value\"";
		525	}
		526
		527	push @cookies, "$cookie=$value";
		528	}
		529	}
		530	}
		531
		532	\@cookies
		533	}
		534
		535	# parse set_cookie header into jar
		536	sub cookie_jar_set_cookie($$$$) {
		537	my ($jar, $set_cookie, $host, $date) = @_;
		538
		539	%$jar = () if $jar->{version} != 2;
		540
		541	my $anow = int AE::now;
		542	my $snow; # server-now
		543
		544	for ($set_cookie) {
		545	# parse NAME=VALUE
		546	my @kv;
		547
		548	# expires is not http-compliant in the original cookie-spec,
		549	# we support the official date format and some extensions
		550	while (
		551	m{
		552	\G\s*
		553	(?:
		554	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
		555	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )?
		556	)
		557	}gcxsi
		558	) {
		559	my $name = $2;
		560	my $value = $4;
		561
		562	if (defined $1) {
		563	# expires
		564	$name = "expires";
		565	$value = $1;
		566	} elsif (defined $3) {
		567	# quoted
		568	$value = $3;
		569	$value =~ s/\\(.)/$1/gs;
		570	}
		571
		572	push @kv, @kv ? lc $name : $name, $value;
		573
		574	last unless /\G\s*;/gc;
		575	}
		576
		577	last unless @kv;
		578
		579	my $name = shift @kv;
		580	my %kv = (value => shift @kv, @kv);
		581
		582	if (exists $kv{"max-age"}) {
		583	$kv{_expires} = $anow + delete $kv{"max-age"};
		584	} elsif (exists $kv{expires}) {
		585	$snow ||= parse_date ($date) || $anow;
		586	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		587	} else {
		588	delete $kv{_expires};
		589	}
		590
		591	my $cdom;
		592	my $cpath = (delete $kv{path}) || "/";
		593
		594	if (exists $kv{domain}) {
		595	$cdom = $kv{domain};
		596
		597	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		598
		599	next if $cdom =~ /\.$/;
		600
		601	# this is not rfc-like and not netscape-like. go figure.
		602	my $ndots = $cdom =~ y/.//;
		603	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		604
		605	$cdom = substr $cdom, 1; # remove initial .
		606	} else {
		607	$cdom = $host;
		608	}
		609
		610	# store it
		611	$jar->{version} = 2;
		612	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		613
		614	redo if /\G\s*,/gc;
		615	}
		616	}
		617
		618	#############################################################################
		619	# keepalive/persistent connection cache
		620
		621	# fetch a connection from the keepalive cache
		622	sub ka_fetch($) {
		623	my $ka_key = shift;
		624
		625	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		626	delete $KA_CACHE{$ka_key}
		627	unless @{ $KA_CACHE{$ka_key} };
		628
		629	$hdl
		630	}
		631
		632	sub ka_store($$) {
		633	my ($ka_key, $hdl) = @_;
		634
		635	my $kaa = $KA_CACHE{$ka_key} ||= [];
		636
		637	my $destroy = sub {
		638	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		639
		640	$hdl->destroy;
		641
		642	@ka
		643	? $KA_CACHE{$ka_key} = \@ka
		644	: delete $KA_CACHE{$ka_key};
		645	};
		646
		647	# on error etc., destroy
		648	$hdl->on_error ($destroy);
		649	$hdl->on_eof ($destroy);
		650	$hdl->on_read ($destroy);
		651	$hdl->timeout ($PERSISTENT_TIMEOUT);
		652
		653	push @$kaa, $hdl;
		654	shift @$kaa while @$kaa > $MAX_PER_HOST;
		655	}
		656
		657	#############################################################################
		658	# utilities
		659
		660	# continue to parse $_ for headers and place them into the arg
		661	sub _parse_hdr() {
		662	my %hdr;
		663
		664	# things seen, not parsed:
		665	# p3pP="NON CUR OTPi OUR NOR UNI"
		666
		667	$hdr{lc $1} .= ",$2"
		668	while /\G
		669	([^:\000-\037]*):
		670	[\011\040]*
		671	((?: [^\012]+ | \012[\011\040] )*)
		672	\012
		673	/gxc;
		674
		675	/\G$/
		676	or return;
		677
		678	# remove the "," prefix we added to all headers above
		679	substr $_, 0, 1, ""
		680	for values %hdr;
		681
		682	\%hdr
		683	}
		684
		685	#############################################################################
		686	# http_get
		687
		688	our $qr_nlnl = qr{(?<![^\012])\015?\012};
316		689
317	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	690	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
318	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	691	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		692
		693	# maybe it should just become a normal object :/
		694
		695	sub _destroy_state(\%) {
		696	my ($state) = @_;
		697
		698	$state->{handle}->destroy if $state->{handle};
		699	%$state = ();
		700	}
		701
		702	sub _error(\%$$) {
		703	my ($state, $cb, $hdr) = @_;
		704
		705	&_destroy_state ($state);
		706
		707	$cb->(undef, $hdr);
		708	()
		709	}
		710
		711	our %IDEMPOTENT = (
		712	DELETE => 1,
		713	GET => 1,
		714	HEAD => 1,
		715	OPTIONS => 1,
		716	PUT => 1,
		717	TRACE => 1,
		718
		719	ACL => 1,
		720	"BASELINE-CONTROL" => 1,
		721	BIND => 1,
		722	CHECKIN => 1,
		723	CHECKOUT => 1,
		724	COPY => 1,
		725	LABEL => 1,
		726	LINK => 1,
		727	MERGE => 1,
		728	MKACTIVITY => 1,
		729	MKCALENDAR => 1,
		730	MKCOL => 1,
		731	MKREDIRECTREF => 1,
		732	MKWORKSPACE => 1,
		733	MOVE => 1,
		734	ORDERPATCH => 1,
		735	PROPFIND => 1,
		736	PROPPATCH => 1,
		737	REBIND => 1,
		738	REPORT => 1,
		739	SEARCH => 1,
		740	UNBIND => 1,
		741	UNCHECKOUT => 1,
		742	UNLINK => 1,
		743	UNLOCK => 1,
		744	UPDATE => 1,
		745	UPDATEREDIRECTREF => 1,
		746	"VERSION-CONTROL" => 1,
		747	);
319		748
320	sub http_request($$@) {	749	sub http_request($$@) {
321	my $cb = pop;	750	my $cb = pop;
322	my ($method, $url, %arg) = @_;	751	my ($method, $url, %arg) = @_;
323		752
…		…
332	while (my ($k, $v) = each %$hdr) {	761	while (my ($k, $v) = each %$hdr) {
333	$hdr{lc $k} = $v;	762	$hdr{lc $k} = $v;
334	}	763	}
335	}	764	}
336		765
		766	# pseudo headers for all subsequent responses
		767	my @pseudo = (URL => $url);
		768	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		769
337	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	770	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
338		771
339	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	772	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
340	if $recurse < 0;	773	if $recurse < 0;
341		774
342	my $proxy = $arg{proxy} || $PROXY;	775	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
343	my $timeout = $arg{timeout} || $TIMEOUT;	776	my $timeout = $arg{timeout} || $TIMEOUT;
344		777
345	my ($uscheme, $uauthority, $upath, $query, $fragment) =	778	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
346	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|;	779	$url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|;
347		780
348	$uscheme = lc $uscheme;	781	$uscheme = lc $uscheme;
349		782
350	my $uport = $uscheme eq "http" ? 80	783	my $uport = $uscheme eq "http" ? 80
351	: $uscheme eq "https" ? 443	784	: $uscheme eq "https" ? 443
352	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });	785	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
353		786
354	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	787	$uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x
355	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	788	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
356		789
357	my $uhost = $1;	790	my $uhost = lc $1;
358	$uport = $2 if defined $2;	791	$uport = $2 if defined $2;
359		792
360	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";	793	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		794	unless exists $hdr{host};
361		795
362	$uhost =~ s/^\[(.*)\]$/$1/;	796	$uhost =~ s/^\[(.*)\]$/$1/;
363	$upath .= "?$query" if length $query;	797	$upath .= $query if length $query;
364		798
365	$upath =~ s%^/?%/%;	799	$upath =~ s%^/?%/%;
366		800
367	# cookie processing	801	# cookie processing
368	if (my $jar = $arg{cookie_jar}) {	802	if (my $jar = $arg{cookie_jar}) {
369	%$jar = () if $jar->{version} != 1;	803	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
370		804
371	my @cookie;
372
373	while (my ($chost, $v) = each %$jar) {
374	if ($chost =~ /^\./) {
375	next unless $chost eq substr $uhost, -length $chost;
376	} elsif ($chost =~ /\./) {
377	next unless $chost eq $uhost;
378	} else {
379	next;
380	}
381
382	while (my ($cpath, $v) = each %$v) {
383	next unless $cpath eq substr $upath, 0, length $cpath;
384
385	while (my ($k, $v) = each %$v) {
386	next if $uscheme ne "https" && exists $v->{secure};
387	my $value = $v->{value};
388	$value =~ s/([\\"])/\\$1/g;
389	push @cookie, "$k=\"$value\"";
390	}
391	}
392	}
393
394	$hdr{cookie} = join "; ", @cookie	805	$hdr{cookie} = join "; ", @$cookies
395	if @cookie;	806	if @$cookies;
396	}	807	}
397		808
398	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	809	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
399		810
400	if ($proxy) {	811	if ($proxy) {
401	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	812	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		813
		814	$rscheme = "http" unless defined $rscheme;
402		815
403	# don't support https requests over https-proxy transport,	816	# don't support https requests over https-proxy transport,
404	# can't be done with tls as spec'ed, unless you double-encrypt.	817	# can't be done with tls as spec'ed, unless you double-encrypt.
405	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	818	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		819
		820	$rhost = lc $rhost;
		821	$rscheme = lc $rscheme;
406	} else {	822	} else {
407	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	823	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
408	}	824	}
409		825
410	$hdr{"user-agent"} ||= $USERAGENT;	826	# leave out fragment and query string, just a heuristic
411	$hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic	827	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		828	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
412		829
413	$hdr{"content-length"} = length $arg{body};	830	$hdr{"content-length"} = length $arg{body}
		831	if length $arg{body} || $method ne "GET";
		832
		833	my $idempotent = $IDEMPOTENT{$method};
		834
		835	# default value for keepalive is true iff the request is for an idempotent method
		836	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		837	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		838	my $was_persistent; # true if this is actually a recycled connection
		839
		840	# the key to use in the keepalive cache
		841	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		842
		843	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1
		844	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
414		845
415	my %state = (connect_guard => 1);	846	my %state = (connect_guard => 1);
		847
		848	my $ae_error = 595; # connecting
		849
		850	# handle actual, non-tunneled, request
		851	my $handle_actual_request = sub {
		852	$ae_error = 596; # request phase
		853
		854	my $hdl = $state{handle};
		855
		856	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		857
		858	# send request
		859	$hdl->push_write (
		860	"$method $rpath HTTP/1.1\015\012"
		861	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		862	. "\015\012"
		863	. $arg{body}
		864	);
		865
		866	# return if error occurred during push_write()
		867	return unless %state;
		868
		869	# reduce memory usage, save a kitten, also re-use it for the response headers.
		870	%hdr = ();
		871
		872	# status line and headers
		873	$state{read_response} = sub {
		874	return unless %state;
		875
		876	for ("$_[1]") {
		877	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		878
		879	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
		880	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		881
		882	# 100 Continue handling
		883	# should not happen as we don't send expect: 100-continue,
		884	# but we handle it just in case.
		885	# since we send the request body regardless, if we get an error
		886	# we are out of-sync, which we currently do NOT handle correctly.
		887	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		888	if $2 eq 100;
		889
		890	push @pseudo,
		891	HTTPVersion => $1,
		892	Status => $2,
		893	Reason => $3,
		894	;
		895
		896	my $hdr = _parse_hdr
		897	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		898
		899	%hdr = (%$hdr, @pseudo);
		900	}
		901
		902	# redirect handling
		903	# relative uri handling forced by microsoft and other shitheads.
		904	# we give our best and fall back to URI if available.
		905	if (exists $hdr{location}) {
		906	my $loc = $hdr{location};
		907
		908	if ($loc =~ m%^//%) { # //
		909	$loc = "$uscheme:$loc";
		910
		911	} elsif ($loc eq "") {
		912	$loc = $url;
		913
		914	} elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple"
		915	$loc =~ s/^\.\/+//;
		916
		917	if ($loc !~ m%^[.?#]%) {
		918	my $prefix = "$uscheme://$uauthority";
		919
		920	unless ($loc =~ s/^\///) {
		921	$prefix .= $upath;
		922	$prefix =~ s/\/[^\/]*$//;
		923	}
		924
		925	$loc = "$prefix/$loc";
		926
		927	} elsif (eval { require URI }) { # uri
		928	$loc = URI->new_abs ($loc, $url)->as_string;
		929
		930	} else {
		931	return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" };
		932	#$hdr{Status} = 599;
		933	#$hdr{Reason} = "Unparsable Redirect (URI module missing)";
		934	#$recurse = 0;
		935	}
		936	}
		937
		938	$hdr{location} = $loc;
		939	}
		940
		941	my $redirect;
		942
		943	if ($recurse) {
		944	my $status = $hdr{Status};
		945
		946	# industry standard is to redirect POST as GET for
		947	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		948	# also, the UA should ask the user for 301 and 307 and POST,
		949	# industry standard seems to be to simply follow.
		950	# we go with the industry standard. 308 is defined
		951	# by rfc7538
		952	if ($status == 301 or $status == 302 or $status == 303) {
		953	$redirect = 1;
		954	# HTTP/1.1 is unclear on how to mutate the method
		955	unless ($method eq "HEAD") {
		956	$method = "GET";
		957	delete $arg{body};
		958	}
		959	} elsif ($status == 307 or $status == 308) {
		960	$redirect = 1;
		961	}
		962	}
		963
		964	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		965	if ($state{handle}) {
		966	# handle keepalive
		967	if (
		968	$persistent
		969	&& $_[3]
		970	&& ($hdr{HTTPVersion} < 1.1
		971	? $hdr{connection} =~ /\bkeep-?alive\b/i
		972	: $hdr{connection} !~ /\bclose\b/i)
		973	) {
		974	ka_store $ka_key, delete $state{handle};
		975	} else {
		976	# no keepalive, destroy the handle
		977	$state{handle}->destroy;
		978	}
		979	}
		980
		981	%state = ();
		982
		983	if (defined $_[1]) {
		984	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		985	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		986	}
		987
		988	# set-cookie processing
		989	if ($arg{cookie_jar}) {
		990	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		991	}
		992
		993	if ($redirect && exists $hdr{location}) {
		994	# we ignore any errors, as it is very common to receive
		995	# Content-Length != 0 but no actual body
		996	# we also access %hdr, as $_[1] might be an erro
		997	$state{recurse} =
		998	http_request (
		999	$method => $hdr{location},
		1000	%arg,
		1001	recurse => $recurse - 1,
		1002	Redirect => [$_[0], \%hdr],
		1003	sub {
		1004	%state = ();
		1005	&$cb
		1006	},
		1007	);
		1008	} else {
		1009	$cb->($_[0], \%hdr);
		1010	}
		1011	};
		1012
		1013	$ae_error = 597; # body phase
		1014
		1015	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		1016
		1017	my $len = $chunked ? undef : $hdr{"content-length"};
		1018
		1019	# body handling, many different code paths
		1020	# - no body expected
		1021	# - want_body_handle
		1022	# - te chunked
		1023	# - 2x length known (with or without on_body)
		1024	# - 2x length not known (with or without on_body)
		1025	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		1026	$finish->(undef, 598 => "Request cancelled by on_header");
		1027	} elsif (
		1028	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		1029	or $method eq "HEAD"
		1030	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		1031	) {
		1032	# no body
		1033	$finish->("", undef, undef, 1);
		1034
		1035	} elsif (!$redirect && $arg{want_body_handle}) {
		1036	$_[0]->on_eof (undef);
		1037	$_[0]->on_error (undef);
		1038	$_[0]->on_read (undef);
		1039
		1040	$finish->(delete $state{handle});
		1041
		1042	} elsif ($chunked) {
		1043	my $cl = 0;
		1044	my $body = "";
		1045	my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 };
		1046
		1047	$state{read_chunk} = sub {
		1048	$_[1] =~ /^([0-9a-fA-F]+)/
		1049	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1050
		1051	my $len = hex $1;
		1052
		1053	if ($len) {
		1054	$cl += $len;
		1055
		1056	$_[0]->push_read (chunk => $len, sub {
		1057	$on_body->($_[1], \%hdr)
		1058	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1059
		1060	$_[0]->push_read (line => sub {
		1061	length $_[1]
		1062	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1063	$_[0]->push_read (line => $state{read_chunk});
		1064	});
		1065	});
		1066	} else {
		1067	$hdr{"content-length"} ||= $cl;
		1068
		1069	$_[0]->push_read (line => $qr_nlnl, sub {
		1070	if (length $_[1]) {
		1071	for ("$_[1]") {
		1072	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		1073
		1074	my $hdr = _parse_hdr
		1075	or return $finish->(undef, $ae_error => "Garbled response trailers");
		1076
		1077	%hdr = (%hdr, %$hdr);
		1078	}
		1079	}
		1080
		1081	$finish->($body, undef, undef, 1);
		1082	});
		1083	}
		1084	};
		1085
		1086	$_[0]->push_read (line => $state{read_chunk});
		1087
		1088	} elsif (!$redirect && $arg{on_body}) {
		1089	if (defined $len) {
		1090	$_[0]->on_read (sub {
		1091	$len -= length $_[0]{rbuf};
		1092
		1093	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1094	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1095
		1096	$len > 0
		1097	or $finish->("", undef, undef, 1);
		1098	});
		1099	} else {
		1100	$_[0]->on_eof (sub {
		1101	$finish->("");
		1102	});
		1103	$_[0]->on_read (sub {
		1104	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1105	or $finish->(undef, 598 => "Request cancelled by on_body");
		1106	});
		1107	}
		1108	} else {
		1109	$_[0]->on_eof (undef);
		1110
		1111	if (defined $len) {
		1112	$_[0]->on_read (sub {
		1113	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1114	if $len <= length $_[0]{rbuf};
		1115	});
		1116	} else {
		1117	$_[0]->on_error (sub {
		1118	($! == Errno::EPIPE || !$!)
		1119	? $finish->(delete $_[0]{rbuf})
		1120	: $finish->(undef, $ae_error => $_[2]);
		1121	});
		1122	$_[0]->on_read (sub { });
		1123	}
		1124	}
		1125	};
		1126
		1127	# if keepalive is enabled, then the server closing the connection
		1128	# before a response can happen legally - we retry on idempotent methods.
		1129	if ($was_persistent && $idempotent) {
		1130	my $old_eof = $hdl->{on_eof};
		1131	$hdl->{on_eof} = sub {
		1132	_destroy_state %state;
		1133
		1134	%state = ();
		1135	$state{recurse} =
		1136	http_request (
		1137	$method => $url,
		1138	%arg,
		1139	recurse => $recurse - 1,
		1140	persistent => 0,
		1141	sub {
		1142	%state = ();
		1143	&$cb
		1144	}
		1145	);
		1146	};
		1147	$hdl->on_read (sub {
		1148	return unless %state;
		1149
		1150	# as soon as we receive something, a connection close
		1151	# once more becomes a hard error
		1152	$hdl->{on_eof} = $old_eof;
		1153	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1154	});
		1155	} else {
		1156	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1157	}
		1158	};
		1159
		1160	my $prepare_handle = sub {
		1161	my ($hdl) = $state{handle};
		1162
		1163	$hdl->on_error (sub {
		1164	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1165	});
		1166	$hdl->on_eof (sub {
		1167	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1168	});
		1169	$hdl->timeout_reset;
		1170	$hdl->timeout ($timeout);
		1171	};
		1172
		1173	# connected to proxy (or origin server)
		1174	my $connect_cb = sub {
		1175	my $fh = shift
		1176	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1177
		1178	return unless delete $state{connect_guard};
		1179
		1180	# get handle
		1181	$state{handle} = new AnyEvent::Handle
		1182	%{ $arg{handle_params} },
		1183	fh => $fh,
		1184	peername => $uhost,
		1185	tls_ctx => $arg{tls_ctx},
		1186	;
		1187
		1188	$prepare_handle->();
		1189
		1190	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1191
		1192	# now handle proxy-CONNECT method
		1193	if ($proxy && $uscheme eq "https") {
		1194	# oh dear, we have to wrap it into a connect request
		1195
		1196	my $auth = exists $hdr{"proxy-authorization"}
		1197	? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012"
		1198	: "";
		1199
		1200	# maybe re-use $uauthority with patched port?
		1201	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012");
		1202	$state{handle}->push_read (line => $qr_nlnl, sub {
		1203	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1204	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1205
		1206	if ($2 == 200) {
		1207	$rpath = $upath;
		1208	$handle_actual_request->();
		1209	} else {
		1210	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1211	}
		1212	});
		1213	} else {
		1214	delete $hdr{"proxy-authorization"} unless $proxy;
		1215
		1216	$handle_actual_request->();
		1217	}
		1218	};
416		1219
417	_get_slot $uhost, sub {	1220	_get_slot $uhost, sub {
418	$state{slot_guard} = shift;	1221	$state{slot_guard} = shift;
419		1222
420	return unless $state{connect_guard};	1223	return unless $state{connect_guard};
421		1224
422	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	1225	# try to use an existing keepalive connection, but only if we, ourselves, plan
423	$state{fh} = shift	1226	# on a keepalive request (in theory, this should be a separate config option).
424	or do {	1227	if ($persistent && $KA_CACHE{$ka_key}) {
425	my $err = "$!";	1228	$was_persistent = 1;
426	%state = ();
427	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
428	};
429		1229
430	pop; # free memory, save a tree	1230	$state{handle} = ka_fetch $ka_key;
		1231	# $state{handle}->destroyed
		1232	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
		1233	$prepare_handle->();
		1234	# $state{handle}->destroyed
		1235	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
		1236	$handle_actual_request->();
431		1237
432	return unless delete $state{connect_guard};
433
434	# get handle
435	$state{handle} = new AnyEvent::Handle
436	fh => $state{fh},
437	timeout => $timeout,
438	peername => $rhost,
439	tls_ctx => $arg{tls_ctx};
440
441	# limit the number of persistent connections
442	# keepalive not yet supported
443	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
444	++$KA_COUNT{$_[1]};
445	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
446	--$KA_COUNT{$_[1]}
447	};
448	$hdr{connection} = "keep-alive";
449	} else {	1238	} else {
450	delete $hdr{connection};	1239	my $tcp_connect = $arg{tcp_connect}
451	}	1240	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
452		1241
453	# (re-)configure handle	1242	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
454	$state{handle}->on_error (sub {
455	%state = ();
456	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
457	});
458	$state{handle}->on_eof (sub {
459	%state = ();
460	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
461	});
462
463	$state{handle}->starttls ("connect") if $rscheme eq "https";
464
465	# handle actual, non-tunneled, request
466	my $handle_actual_request = sub {
467	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
468
469	# send request
470	$state{handle}->push_write (
471	"$method $rpath HTTP/1.0\015\012"
472	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)
473	. "\015\012"
474	. (delete $arg{body})
475	);
476
477	%hdr = (); # reduce memory usage, save a kitten
478
479	# status line
480	$state{handle}->push_read (line => $qr_nl, sub {
481	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
482	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
483
484	my %hdr = ( # response headers
485	HTTPVersion => ",$1",
486	Status => ",$2",
487	Reason => ",$3",
488	URL => ",$url"
489	);
490
491	# headers, could be optimized a bit
492	$state{handle}->unshift_read (line => $qr_nlnl, sub {
493	for ("$_[1]\012") {
494	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
495
496	# things seen, not parsed:
497	# p3pP="NON CUR OTPi OUR NOR UNI"
498
499	$hdr{lc $1} .= ",$2"
500	while /\G
501	([^:\000-\037]*):
502	[\011\040]*
503	((?: [^\012]+ | \012[\011\040] )*)
504	\012
505	/gxc;
506
507	/\G$/
508	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
509	}
510
511	substr $_, 0, 1, ""
512	for values %hdr;
513
514	# redirect handling
515	# microsoft and other shitheads don't give a shit for following standards,
516	# try to support some common forms of broken Location headers.
517	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
518	$hdr{location} =~ s/^\.\/+//;
519
520	my $url = "$rscheme://$uhost:$uport";
521
522	unless ($hdr{location} =~ s/^\///) {
523	$url .= $upath;
524	$url =~ s/\/[^\/]*$//;
525	}
526
527	$hdr{location} = "$url/$hdr{location}";
528	}
529
530	my $redirect;
531
532	if ($recurse) {
533	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
534	# apparently, mozilla et al. just change POST to GET here
535	# more research is needed before we do the same
536	$redirect = 1;
537	} elsif ($hdr{Status} == 303) {
538	# even http/1.1 is unclear on how to mutate the method
539	$method = "GET" unless $method eq "HEAD";
540	$redirect = 1;
541	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) {
542	$redirect = 1;
543	}
544	}
545
546	my $finish = sub {
547	$state{handle}->destroy if $state{handle};
548	%state = ();
549
550	# set-cookie processing
551	if ($arg{cookie_jar}) {
552	for ($_[1]{"set-cookie"}) {
553	# parse NAME=VALUE
554	my @kv;
555
556	while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
557	my $name = $1;
558	my $value = $3;
559
560	unless ($value) {
561	$value = $2;
562	$value =~ s/\\(.)/$1/gs;
563	}
564
565	push @kv, $name => $value;
566
567	last unless /\G\s*;/gc;
568	}
569
570	last unless @kv;
571
572	my $name = shift @kv;
573	my %kv = (value => shift @kv, @kv);
574
575	my $cdom;
576	my $cpath = (delete $kv{path}) || "/";
577
578	if (exists $kv{domain}) {
579	$cdom = delete $kv{domain};
580
581	$cdom =~ s/^\.?/./; # make sure it starts with a "."
582
583	next if $cdom =~ /\.$/;
584
585	# this is not rfc-like and not netscape-like. go figure.
586	my $ndots = $cdom =~ y/.//;
587	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
588	} else {
589	$cdom = $uhost;
590	}
591
592	# store it
593	$arg{cookie_jar}{version} = 1;
594	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
595
596	redo if /\G\s*,/gc;
597	}
598	}
599
600	if ($redirect) {
601	# we ignore any errors, as it is very common to receive
602	# Content-Length != 0 but no actual body
603	# we also access %hdr, as $_[1] might be an erro
604	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
605	} else {
606	$cb->($_[0], $_[1]);
607	}
608	};
609
610	my $len = $hdr{"content-length"};
611
612	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
613	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
614	} elsif (
615	$hdr{Status} =~ /^(?:1..|[23]04)$/
616	or $method eq "HEAD"
617	or (defined $len && !$len)
618	) {
619	# no body
620	$finish->("", \%hdr);
621	} else {
622	# body handling, four different code paths
623	# for want_body_handle, on_body (2x), normal (2x)
624	# we might read too much here, but it does not matter yet (no pers. connections)
625	if (!$redirect && $arg{want_body_handle}) {
626	$_[0]->on_eof (undef);
627	$_[0]->on_error (undef);
628	$_[0]->on_read (undef);
629
630	$finish->(delete $state{handle}, \%hdr);
631
632	} elsif ($arg{on_body}) {
633	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
634	if ($len) {
635	$_[0]->on_eof (undef);
636	$_[0]->on_read (sub {
637	$len -= length $_[0]{rbuf};
638
639	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
640	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
641
642	$len > 0
643	or $finish->("", \%hdr);
644	});
645	} else {
646	$_[0]->on_eof (sub {
647	$finish->("", \%hdr);
648	});
649	$_[0]->on_read (sub {
650	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
651	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
652	});
653	}
654	} else {
655	$_[0]->on_eof (undef);
656
657	if ($len) {
658	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
659	$_[0]->on_read (sub {
660	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
661	if $len <= length $_[0]{rbuf};
662	});
663	} else {
664	$_[0]->on_error (sub {
665	$! == Errno::EPIPE || !$!
666	? $finish->(delete $_[0]{rbuf}, \%hdr)
667	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
668	});
669	$_[0]->on_read (sub { });
670	}
671	}
672	}
673	});
674	});
675	};
676
677	# now handle proxy-CONNECT method
678	if ($proxy && $uscheme eq "https") {
679	# oh dear, we have to wrap it into a connect request
680
681	# maybe re-use $uauthority with patched port?
682	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
683	$state{handle}->push_read (line => $qr_nlnl, sub {
684	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
685	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
686
687	if ($2 == 200) {
688	$rpath = $upath;
689	&$handle_actual_request;
690	} else {
691	%state = ();
692	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
693	}
694	});
695	} else {
696	&$handle_actual_request;
697	}
698
699	}, sub {
700	$timeout
701	};	1243	}
702	};	1244	};
703		1245
704	defined wantarray && AnyEvent::Util::guard { %state = () }	1246	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
705	}	1247	}
706		1248
707	sub http_get($@) {	1249	sub http_get($@) {
708	unshift @_, "GET";	1250	unshift @_, "GET";
709	&http_request	1251	&http_request
…		…
720	&http_request	1262	&http_request
721	}	1263	}
722		1264
723	=back	1265	=back
724		1266
		1267	=head2 DNS CACHING
		1268
		1269	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		1270	the actual connection, which in turn uses AnyEvent::DNS to resolve
		1271	hostnames. The latter is a simple stub resolver and does no caching
		1272	on its own. If you want DNS caching, you currently have to provide
		1273	your own default resolver (by storing a suitable resolver object in
		1274	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
		1275
725	=head2 GLOBAL FUNCTIONS AND VARIABLES	1276	=head2 GLOBAL FUNCTIONS AND VARIABLES
726		1277
727	=over 4	1278	=over 4
728		1279
729	=item AnyEvent::HTTP::set_proxy "proxy-url"	1280	=item AnyEvent::HTTP::set_proxy "proxy-url"
730		1281
731	Sets the default proxy server to use. The proxy-url must begin with a	1282	Sets the default proxy server to use. The proxy-url must begin with a
732	string of the form C<http://host:port> (optionally C<https:...>).	1283	string of the form C<http://host:port>, croaks otherwise.
		1284
		1285	To clear an already-set proxy, use C<undef>.
		1286
		1287	When AnyEvent::HTTP is loaded for the first time it will query the
		1288	default proxy from the operating system, currently by looking at
		1289	C<$ENV{http_proxy>}.
		1290
		1291	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1292
		1293	Remove all cookies from the cookie jar that have been expired. If
		1294	C<$session_end> is given and true, then additionally remove all session
		1295	cookies.
		1296
		1297	You should call this function (with a true C<$session_end>) before you
		1298	save cookies to disk, and you should call this function after loading them
		1299	again. If you have a long-running program you can additionally call this
		1300	function from time to time.
		1301
		1302	A cookie jar is initially an empty hash-reference that is managed by this
		1303	module. Its format is subject to change, but currently it is as follows:
		1304
		1305	The key C<version> has to contain C<2>, otherwise the hash gets
		1306	cleared. All other keys are hostnames or IP addresses pointing to
		1307	hash-references. The key for these inner hash references is the
		1308	server path for which this cookie is meant, and the values are again
		1309	hash-references. Each key of those hash-references is a cookie name, and
		1310	the value, you guessed it, is another hash-reference, this time with the
		1311	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1312	which have been replaced by a C<_expires> key that contains the cookie
		1313	expiry timestamp. Session cookies are indicated by not having an
		1314	C<_expires> key.
		1315
		1316	Here is an example of a cookie jar with a single cookie, so you have a
		1317	chance of understanding the above paragraph:
		1318
		1319	{
		1320	version => 2,
		1321	"10.0.0.1" => {
		1322	"/" => {
		1323	"mythweb_id" => {
		1324	_expires => 1293917923,
		1325	value => "ooRung9dThee3ooyXooM1Ohm",
		1326	},
		1327	},
		1328	},
		1329	}
		1330
		1331	=item $date = AnyEvent::HTTP::format_date $timestamp
		1332
		1333	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1334	Date (RFC 2616).
		1335
		1336	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1337
		1338	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1339	bunch of minor variations of those, and returns the corresponding POSIX
		1340	timestamp, or C<undef> if the date cannot be parsed.
733		1341
734	=item $AnyEvent::HTTP::MAX_RECURSE	1342	=item $AnyEvent::HTTP::MAX_RECURSE
735		1343
736	The default value for the C<recurse> request parameter (default: C<10>).	1344	The default value for the C<recurse> request parameter (default: C<10>).
		1345
		1346	=item $AnyEvent::HTTP::TIMEOUT
		1347
		1348	The default timeout for connection operations (default: C<300>).
737		1349
738	=item $AnyEvent::HTTP::USERAGENT	1350	=item $AnyEvent::HTTP::USERAGENT
739		1351
740	The default value for the C<User-Agent> header (the default is	1352	The default value for the C<User-Agent> header (the default is
741	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1353	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
742		1354
743	=item $AnyEvent::HTTP::MAX_PER_HOST	1355	=item $AnyEvent::HTTP::MAX_PER_HOST
744		1356
745	The maximum number of concurrent conenctions to the same host (identified	1357	The maximum number of concurrent connections to the same host (identified
746	by the hostname). If the limit is exceeded, then the additional requests	1358	by the hostname). If the limit is exceeded, then additional requests
747	are queued until previous connections are closed.	1359	are queued until previous connections are closed. Both persistent and
		1360	non-persistent connections are counted in this limit.
748		1361
749	The default value for this is C<4>, and it is highly advisable to not	1362	The default value for this is C<4>, and it is highly advisable to not
750	increase it.	1363	increase it much.
		1364
		1365	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1366	connections, older browsers used 2, newer ones (such as firefox 3)
		1367	typically use 6, and Opera uses 8 because like, they have the fastest
		1368	browser and give a shit for everybody else on the planet.
		1369
		1370	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1371
		1372	The time after which idle persistent connections get closed by
		1373	AnyEvent::HTTP (default: C<3>).
751		1374
752	=item $AnyEvent::HTTP::ACTIVE	1375	=item $AnyEvent::HTTP::ACTIVE
753		1376
754	The number of active connections. This is not the number of currently	1377	The number of active connections. This is not the number of currently
755	running requests, but the number of currently open and non-idle TCP	1378	running requests, but the number of currently open and non-idle TCP
756	connections. This number of can be useful for load-leveling.	1379	connections. This number can be useful for load-leveling.
757		1380
758	=back	1381	=back
759		1382
760	=cut	1383	=cut
761		1384
		1385	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1386	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1387
		1388	sub format_date($) {
		1389	my ($time) = @_;
		1390
		1391	# RFC 822/1123 format
		1392	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1393
		1394	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1395	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1396	$H, $M, $S;
		1397	}
		1398
		1399	sub parse_date($) {
		1400	my ($date) = @_;
		1401
		1402	my ($d, $m, $y, $H, $M, $S);
		1403
		1404	if ($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$/) {
		1405	# RFC 822/1123, required by RFC 2616 (with " ")
		1406	# cookie dates (with "-")
		1407
		1408	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1409
		1410	} elsif ($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$/) {
		1411	# RFC 850
		1412	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1413
		1414	} elsif ($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])$/) {
		1415	# ISO C's asctime
		1416	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1417	}
		1418	# other formats fail in the loop below
		1419
		1420	for (0..11) {
		1421	if ($m eq $month[$_]) {
		1422	require Time::Local;
		1423	return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) };
		1424	}
		1425	}
		1426
		1427	undef
		1428	}
		1429
762	sub set_proxy($) {	1430	sub set_proxy($) {
763	$PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1431	if (length $_[0]) {
		1432	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
		1433	or Carp::croak "$_[0]: invalid proxy URL";
		1434	$PROXY = [$2, $3 || 3128, $1]
		1435	} else {
		1436	undef $PROXY;
		1437	}
764	}	1438	}
765		1439
766	# initialise proxy from environment	1440	# initialise proxy from environment
		1441	eval {
767	set_proxy $ENV{http_proxy};	1442	set_proxy $ENV{http_proxy};
		1443	};
		1444
		1445	=head2 SHOWCASE
		1446
		1447	This section contains some more elaborate "real-world" examples or code
		1448	snippets.
		1449
		1450	=head2 HTTP/1.1 FILE DOWNLOAD
		1451
		1452	Downloading files with HTTP can be quite tricky, especially when something
		1453	goes wrong and you want to resume.
		1454
		1455	Here is a function that initiates and resumes a download. It uses the
		1456	last modified time to check for file content changes, and works with many
		1457	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1458	on older servers.
		1459
		1460	It calls the completion callback with either C<undef>, which means a
		1461	nonretryable error occurred, C<0> when the download was partial and should
		1462	be retried, and C<1> if it was successful.
		1463
		1464	use AnyEvent::HTTP;
		1465
		1466	sub download($$$) {
		1467	my ($url, $file, $cb) = @_;
		1468
		1469	open my $fh, "+<", $file
		1470	or die "$file: $!";
		1471
		1472	my %hdr;
		1473	my $ofs = 0;
		1474
		1475	if (stat $fh and -s _) {
		1476	$ofs = -s _;
		1477	warn "-s is ", $ofs;
		1478	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1479	$hdr{"range"} = "bytes=$ofs-";
		1480	}
		1481
		1482	http_get $url,
		1483	headers => \%hdr,
		1484	on_header => sub {
		1485	my ($hdr) = @_;
		1486
		1487	if ($hdr->{Status} == 200 && $ofs) {
		1488	# resume failed
		1489	truncate $fh, $ofs = 0;
		1490	}
		1491
		1492	sysseek $fh, $ofs, 0;
		1493
		1494	1
		1495	},
		1496	on_body => sub {
		1497	my ($data, $hdr) = @_;
		1498
		1499	if ($hdr->{Status} =~ /^2/) {
		1500	length $data == syswrite $fh, $data
		1501	or return; # abort on write errors
		1502	}
		1503
		1504	1
		1505	},
		1506	sub {
		1507	my (undef, $hdr) = @_;
		1508
		1509	my $status = $hdr->{Status};
		1510
		1511	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1512	utime $time, $time, $fh;
		1513	}
		1514
		1515	if ($status == 200 || $status == 206 || $status == 416) {
		1516	# download ok || resume ok || file already fully downloaded
		1517	$cb->(1, $hdr);
		1518
		1519	} elsif ($status == 412) {
		1520	# file has changed while resuming, delete and retry
		1521	unlink $file;
		1522	$cb->(0, $hdr);
		1523
		1524	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1525	# retry later
		1526	$cb->(0, $hdr);
		1527
		1528	} else {
		1529	$cb->(undef, $hdr);
		1530	}
		1531	}
		1532	;
		1533	}
		1534
		1535	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1536	if ($_[0]) {
		1537	print "OK!\n";
		1538	} elsif (defined $_[0]) {
		1539	print "please retry later\n";
		1540	} else {
		1541	print "ERROR\n";
		1542	}
		1543	};
		1544
		1545	=head3 SOCKS PROXIES
		1546
		1547	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1548	compile your perl to support socks, or use an external program such as
		1549	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1550	transparently.
		1551
		1552	Alternatively, for AnyEvent::HTTP only, you can use your own
		1553	C<tcp_connect> function that does the proxy handshake - here is an example
		1554	that works with socks4a proxies:
		1555
		1556	use Errno;
		1557	use AnyEvent::Util;
		1558	use AnyEvent::Socket;
		1559	use AnyEvent::Handle;
		1560
		1561	# host, port and username of/for your socks4a proxy
		1562	my $socks_host = "10.0.0.23";
		1563	my $socks_port = 9050;
		1564	my $socks_user = "";
		1565
		1566	sub socks4a_connect {
		1567	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1568
		1569	my $hdl = new AnyEvent::Handle
		1570	connect => [$socks_host, $socks_port],
		1571	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1572	on_error => sub { $connect_cb->() },
		1573	;
		1574
		1575	$hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host);
		1576
		1577	$hdl->push_read (chunk => 8, sub {
		1578	my ($hdl, $chunk) = @_;
		1579	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1580
		1581	if ($status == 0x5a) {
		1582	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1583	} else {
		1584	$! = Errno::ENXIO; $connect_cb->();
		1585	}
		1586	});
		1587
		1588	$hdl
		1589	}
		1590
		1591	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1592	possibly after switching off other proxy types:
		1593
		1594	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1595
		1596	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1597	my ($data, $headers) = @_;
		1598	...
		1599	};
768		1600
769	=head1 SEE ALSO	1601	=head1 SEE ALSO
770		1602
771	L<AnyEvent>.	1603	L<AnyEvent>.
772		1604

Diff Legend

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