[ViewVC] Diff of: 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 1.132 by root, Thu Aug 30 17:05:45 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 = '1.42';	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:> (this can be	171	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	172	(this can be suppressed by using C<undef> for these headers in which case
145	sent at all).	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.
146		181
147	=item timeout => $seconds	182	=item timeout => $seconds
148		183
149	The time-out to use for various stages - each connect attempt will reset	184	The time-out to use for various stages - each connect attempt will reset
150	the timeout, as will read or write activity. Default timeout is 5 minutes.	185	the timeout, as will read or write activity, i.e. this is not an overall
		186	timeout.
		187
		188	Default timeout is 5 minutes.
151		189
152	=item proxy => [$host, $port[, $scheme]] or undef	190	=item proxy => [$host, $port[, $scheme]] or undef
153		191
154	Use the given http proxy for all requests. If not specified, then the	192	Use the given http proxy for all requests, or no proxy if C<undef> is
155	default proxy (as specified by C<$ENV{http_proxy}>) is used.	193	used.
156		194
157	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	195	C<$scheme> must be either missing or must be C<http> for HTTP.
158	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.
159		202
160	=item body => $string	203	=item body => $string
161		204
162	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
163	this module might offer more options).	206	this module might offer more options).
164		207
165	=item cookie_jar => $hash_ref	208	=item cookie_jar => $hash_ref
166		209
167	Passing this parameter enables (simplified) cookie-processing, loosely	210	Passing this parameter enables (simplified) cookie-processing, loosely
168	based on the original netscape specification.	211	based on the original netscape specification.
169		212
170	The C<$hash_ref> must be an (initially empty) hash reference which will	213	The C<$hash_ref> must be an (initially empty) hash reference which
171	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
172	persistent storage with something like JSON or Storable, but this is not	215	to persistent storage with something like JSON or Storable - see the
173	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.
174		219
175	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
176	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
177	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
178	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
179	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.
180		229
181	=item tls_ctx => $scheme \| $tls_ctx	230	=item tls_ctx => $scheme \| $tls_ctx
182		231
183	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
184	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
…		…
188	verification) TLS context.	237	verification) TLS context.
189		238
190	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
191	me the page, no matter what".	240	me the page, no matter what".
192		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	There are probably lots of weird uses for this function, starting from
		270	tracing the hosts C<http_request> actually tries to connect, to (inexact
		271	but fast) host => IP address caching or even socks protocol support.
		272
193	=item on_header => $callback->($headers)	273	=item on_header => $callback->($headers)
194		274
195	When specified, this callback will be called with the header hash as soon	275	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	276	as headers have been successfully received from the remote server (not on
197	locally-generated errors).	277	locally-generated errors).
…		…
202		282
203	This callback is useful, among other things, to quickly reject unwanted	283	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	284	content, which, if it is supposed to be rare, can be faster than first
205	doing a C<HEAD> request.	285	doing a C<HEAD> request.
206		286
		287	The downside is that cancelling the request makes it impossible to re-use
		288	the connection. Also, the C<on_header> callback will not receive any
		289	trailer (headers sent after the response body).
		290
207	Example: cancel the request unless the content-type is "text/html".	291	Example: cancel the request unless the content-type is "text/html".
208		292
209	on_header => sub {	293	on_header => sub {
210	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/	294	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
211	},	295	},
…		…
217	string instead of the body data.	301	string instead of the body data.
218		302
219	It has to return either true (in which case AnyEvent::HTTP will continue),	303	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	304	or false, in which case AnyEvent::HTTP will cancel the download (and call
221	the completion callback with an error code of C<598>).	305	the completion callback with an error code of C<598>).
		306
		307	The downside to cancelling the request is that it makes it impossible to
		308	re-use the connection.
222		309
223	This callback is useful when the data is too large to be held in memory	310	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	311	(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.	312	be extracted, or when the body should be processed incrementally.
226		313
…		…
238	called. Instead of the C<$body> argument containing the body data, the	325	called. Instead of the C<$body> argument containing the body data, the
239	callback will receive the L<AnyEvent::Handle> object associated with the	326	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	327	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.	328	(e.g. status C<304>), the empty string will be passed.
242		329
243	The handle object might or might not be in TLS mode, might be connected to	330	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	331	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	332	etc., and configured in unspecified ways. The user is responsible for this
246	module anymore).	333	handle (it will not be used by this module anymore).
247		334
248	This is useful with some push-type services, where, after the initial	335	This is useful with some push-type services, where, after the initial
249	headers, an interactive protocol is used (typical example would be the	336	headers, an interactive protocol is used (typical example would be the
250	push-style twitter API which starts a JSON/XML stream).	337	push-style twitter API which starts a JSON/XML stream).
251		338
252	If you think you need this, first have a look at C<on_body>, to see if	339	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.	340	that doesn't solve your problem in a better way.
254		341
		342	=item persistent => $boolean
		343
		344	Try to create/reuse a persistent connection. When this flag is set
		345	(default: true for idempotent requests, false for all others), then
		346	C<http_request> tries to re-use an existing (previously-created)
		347	persistent connection to the host and, failing that, tries to create a new
		348	one.
		349
		350	Requests failing in certain ways will be automatically retried once, which
		351	is dangerous for non-idempotent requests, which is why it defaults to off
		352	for them. The reason for this is because the bozos who designed HTTP/1.1
		353	made it impossible to distinguish between a fatal error and a normal
		354	connection timeout, so you never know whether there was a problem with
		355	your request or not.
		356
		357	When reusing an existent connection, many parameters (such as TLS context)
		358	will be ignored. See the C<session> parameter for a workaround.
		359
		360	=item keepalive => $boolean
		361
		362	Only used when C<persistent> is also true. This parameter decides whether
		363	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		364	(as opposed to only a HTTP/1.1 persistent connection).
		365
		366	The default is true, except when using a proxy, in which case it defaults
		367	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		368
		369	=item handle_params => { key => value ... }
		370
		371	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		372	constructor that is called - not all requests will create a handle, and
		373	sometimes more than one is created, so this parameter is only good for
		374	setting hints.
		375
		376	Example: set the maximum read size to 4096, to potentially conserve memory
		377	at the cost of speed.
		378
		379	handle_params => {
		380	max_read_size => 4096,
		381	},
		382
255	=back	383	=back
256		384
257	Example: make a simple HTTP GET request for http://www.nethype.de/	385	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		386	the response body.
258		387
259	http_request GET => "http://www.nethype.de/", sub {	388	http_request GET => "http://www.nethype.de/", sub {
260	my ($body, $hdr) = @_;	389	my ($body, $hdr) = @_;
261	print "$body\n";	390	print "$body\n";
262	};	391	};
263		392
264	Example: make a HTTP HEAD request on https://www.google.com/, use a	393	Example: do a HTTP HEAD request on https://www.google.com/, use a
265	timeout of 30 seconds.	394	timeout of 30 seconds.
266		395
267	http_request	396	http_request
268	GET => "https://www.google.com",	397	HEAD => "https://www.google.com",
		398	headers => { "user-agent" => "MySearchClient 1.0" },
269	timeout => 30,	399	timeout => 30,
270	sub {	400	sub {
271	my ($body, $hdr) = @_;	401	my ($body, $hdr) = @_;
272	use Data::Dumper;	402	use Data::Dumper;
273	print Dumper $hdr;	403	print Dumper $hdr;
274	}	404	}
275	;	405	;
276		406
277	Example: make another simple HTTP GET request, but immediately try to	407	Example: do another simple HTTP GET request, but immediately try to
278	cancel it.	408	cancel it.
279		409
280	my $request = http_request GET => "http://www.nethype.de/", sub {	410	my $request = http_request GET => "http://www.nethype.de/", sub {
281	my ($body, $hdr) = @_;	411	my ($body, $hdr) = @_;
282	print "$body\n";	412	print "$body\n";
283	};	413	};
284		414
285	undef $request;	415	undef $request;
286		416
287	=cut	417	=cut
		418
		419	#############################################################################
		420	# wait queue/slots
288		421
289	sub _slot_schedule;	422	sub _slot_schedule;
290	sub _slot_schedule($) {	423	sub _slot_schedule($) {
291	my $host = shift;	424	my $host = shift;
292		425
…		…
314	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	447	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
315		448
316	_slot_schedule $_[0];	449	_slot_schedule $_[0];
317	}	450	}
318		451
319	our $qr_nl = qr{\015?\012};	452	#############################################################################
		453	# cookie handling
		454
		455	# expire cookies
		456	sub cookie_jar_expire($;$) {
		457	my ($jar, $session_end) = @_;
		458
		459	%$jar = () if $jar->{version} != 2;
		460
		461	my $anow = AE::now;
		462
		463	while (my ($chost, $paths) = each %$jar) {
		464	next unless ref $paths;
		465
		466	while (my ($cpath, $cookies) = each %$paths) {
		467	while (my ($cookie, $kv) = each %$cookies) {
		468	if (exists $kv->{_expires}) {
		469	delete $cookies->{$cookie}
		470	if $anow > $kv->{_expires};
		471	} elsif ($session_end) {
		472	delete $cookies->{$cookie};
		473	}
		474	}
		475
		476	delete $paths->{$cpath}
		477	unless %$cookies;
		478	}
		479
		480	delete $jar->{$chost}
		481	unless %$paths;
		482	}
		483	}
		484
		485	# extract cookies from jar
		486	sub cookie_jar_extract($$$$) {
		487	my ($jar, $scheme, $host, $path) = @_;
		488
		489	%$jar = () if $jar->{version} != 2;
		490
		491	$host = AnyEvent::Util::idn_to_ascii $host
		492	if $host =~ /[^\x00-\x7f]/;
		493
		494	my @cookies;
		495
		496	while (my ($chost, $paths) = each %$jar) {
		497	next unless ref $paths;
		498
		499	# exact match or suffix including . match
		500	$chost eq $host or ".$chost" eq substr $host, -1 - length $chost
		501	or next;
		502
		503	while (my ($cpath, $cookies) = each %$paths) {
		504	next unless $cpath eq substr $path, 0, length $cpath;
		505
		506	while (my ($cookie, $kv) = each %$cookies) {
		507	next if $scheme ne "https" && exists $kv->{secure};
		508
		509	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		510	delete $cookies->{$cookie};
		511	next;
		512	}
		513
		514	my $value = $kv->{value};
		515
		516	if ($value =~ /[=;,[:space:]]/) {
		517	$value =~ s/([\\"])/\\$1/g;
		518	$value = "\"$value\"";
		519	}
		520
		521	push @cookies, "$cookie=$value";
		522	}
		523	}
		524	}
		525
		526	\@cookies
		527	}
		528
		529	# parse set_cookie header into jar
		530	sub cookie_jar_set_cookie($$$$) {
		531	my ($jar, $set_cookie, $host, $date) = @_;
		532
		533	%$jar = () if $jar->{version} != 2;
		534
		535	my $anow = int AE::now;
		536	my $snow; # server-now
		537
		538	for ($set_cookie) {
		539	# parse NAME=VALUE
		540	my @kv;
		541
		542	# expires is not http-compliant in the original cookie-spec,
		543	# we support the official date format and some extensions
		544	while (
		545	m{
		546	\G\s*
		547	(?:
		548	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
		549	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^;,[:space:]]) ) )?
		550	)
		551	}gcxsi
		552	) {
		553	my $name = $2;
		554	my $value = $4;
		555
		556	if (defined $1) {
		557	# expires
		558	$name = "expires";
		559	$value = $1;
		560	} elsif (defined $3) {
		561	# quoted
		562	$value = $3;
		563	$value =~ s/\\(.)/$1/gs;
		564	}
		565
		566	push @kv, @kv ? lc $name : $name, $value;
		567
		568	last unless /\G\s*;/gc;
		569	}
		570
		571	last unless @kv;
		572
		573	my $name = shift @kv;
		574	my %kv = (value => shift @kv, @kv);
		575
		576	if (exists $kv{"max-age"}) {
		577	$kv{_expires} = $anow + delete $kv{"max-age"};
		578	} elsif (exists $kv{expires}) {
		579	$snow \|\|= parse_date ($date) \|\| $anow;
		580	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		581	} else {
		582	delete $kv{_expires};
		583	}
		584
		585	my $cdom;
		586	my $cpath = (delete $kv{path}) \|\| "/";
		587
		588	if (exists $kv{domain}) {
		589	$cdom = $kv{domain};
		590
		591	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		592
		593	next if $cdom =~ /\.$/;
		594
		595	# this is not rfc-like and not netscape-like. go figure.
		596	my $ndots = $cdom =~ y/.//;
		597	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		598
		599	$cdom = substr $cdom, 1; # remove initial .
		600	} else {
		601	$cdom = $host;
		602	}
		603
		604	# store it
		605	$jar->{version} = 2;
		606	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		607
		608	redo if /\G\s*,/gc;
		609	}
		610	}
		611
		612	#############################################################################
		613	# keepalive/persistent connection cache
		614
		615	# fetch a connection from the keepalive cache
		616	sub ka_fetch($) {
		617	my $ka_key = shift;
		618
		619	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		620	delete $KA_CACHE{$ka_key}
		621	unless @{ $KA_CACHE{$ka_key} };
		622
		623	$hdl
		624	}
		625
		626	sub ka_store($$) {
		627	my ($ka_key, $hdl) = @_;
		628
		629	my $kaa = $KA_CACHE{$ka_key} \|\|= [];
		630
		631	my $destroy = sub {
		632	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		633
		634	$hdl->destroy;
		635
		636	@ka
		637	? $KA_CACHE{$ka_key} = \@ka
		638	: delete $KA_CACHE{$ka_key};
		639	};
		640
		641	# on error etc., destroy
		642	$hdl->on_error ($destroy);
		643	$hdl->on_eof ($destroy);
		644	$hdl->on_read ($destroy);
		645	$hdl->timeout ($PERSISTENT_TIMEOUT);
		646
		647	push @$kaa, $hdl;
		648	shift @$kaa while @$kaa > $MAX_PER_HOST;
		649	}
		650
		651	#############################################################################
		652	# utilities
		653
		654	# continue to parse $_ for headers and place them into the arg
		655	sub _parse_hdr() {
		656	my %hdr;
		657
		658	# things seen, not parsed:
		659	# p3pP="NON CUR OTPi OUR NOR UNI"
		660
		661	$hdr{lc $1} .= ",$2"
		662	while /\G
		663	([^:\000-\037]*):
		664	[\011\040]*
		665	((?: [^\012]+ \| \012[\011\040] )*)
		666	\012
		667	/gxc;
		668
		669	/\G$/
		670	or return;
		671
		672	# remove the "," prefix we added to all headers above
		673	substr $_, 0, 1, ""
		674	for values %hdr;
		675
		676	\%hdr
		677	}
		678
		679	#############################################################################
		680	# http_get
		681
320	our $qr_nlnl = qr{(?<![^\012])\015?\012};	682	our $qr_nlnl = qr{(?<![^\012])\015?\012};
321		683
322	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	684	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
323	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	685	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		686
		687	# maybe it should just become a normal object :/
		688
		689	sub _destroy_state(\%) {
		690	my ($state) = @_;
		691
		692	$state->{handle}->destroy if $state->{handle};
		693	%$state = ();
		694	}
		695
		696	sub _error(\%$$) {
		697	my ($state, $cb, $hdr) = @_;
		698
		699	&_destroy_state ($state);
		700
		701	$cb->(undef, $hdr);
		702	()
		703	}
		704
		705	our %IDEMPOTENT = (
		706	DELETE => 1,
		707	GET => 1,
		708	HEAD => 1,
		709	OPTIONS => 1,
		710	PUT => 1,
		711	TRACE => 1,
		712
		713	ACL => 1,
		714	"BASELINE-CONTROL" => 1,
		715	BIND => 1,
		716	CHECKIN => 1,
		717	CHECKOUT => 1,
		718	COPY => 1,
		719	LABEL => 1,
		720	LINK => 1,
		721	MERGE => 1,
		722	MKACTIVITY => 1,
		723	MKCALENDAR => 1,
		724	MKCOL => 1,
		725	MKREDIRECTREF => 1,
		726	MKWORKSPACE => 1,
		727	MOVE => 1,
		728	ORDERPATCH => 1,
		729	PROPFIND => 1,
		730	PROPPATCH => 1,
		731	REBIND => 1,
		732	REPORT => 1,
		733	SEARCH => 1,
		734	UNBIND => 1,
		735	UNCHECKOUT => 1,
		736	UNLINK => 1,
		737	UNLOCK => 1,
		738	UPDATE => 1,
		739	UPDATEREDIRECTREF => 1,
		740	"VERSION-CONTROL" => 1,
		741	);
324		742
325	sub http_request($$@) {	743	sub http_request($$@) {
326	my $cb = pop;	744	my $cb = pop;
327	my ($method, $url, %arg) = @_;	745	my ($method, $url, %arg) = @_;
328		746
…		…
337	while (my ($k, $v) = each %$hdr) {	755	while (my ($k, $v) = each %$hdr) {
338	$hdr{lc $k} = $v;	756	$hdr{lc $k} = $v;
339	}	757	}
340	}	758	}
341		759
		760	# pseudo headers for all subsequent responses
		761	my @pseudo = (URL => $url);
		762	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		763
342	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	764	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
343		765
344	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	766	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
345	if $recurse < 0;	767	if $recurse < 0;
346		768
347	my $proxy = $arg{proxy} \|\| $PROXY;	769	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
348	my $timeout = $arg{timeout} \|\| $TIMEOUT;	770	my $timeout = $arg{timeout} \|\| $TIMEOUT;
349		771
350	my ($uscheme, $uauthority, $upath, $query, $fragment) =	772	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
351	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	773	$url =~ m\|^([^:]+):(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?$\|;
352		774
353	$uscheme = lc $uscheme;	775	$uscheme = lc $uscheme;
354		776
355	my $uport = $uscheme eq "http" ? 80	777	my $uport = $uscheme eq "http" ? 80
356	: $uscheme eq "https" ? 443	778	: $uscheme eq "https" ? 443
357	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });	779	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
358		780
359	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	781	$uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x
360	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	782	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
361		783
362	my $uhost = $1;	784	my $uhost = lc $1;
363	$uport = $2 if defined $2;	785	$uport = $2 if defined $2;
364		786
365	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";	787	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		788	unless exists $hdr{host};
366		789
367	$uhost =~ s/^\[(.*)\]$/$1/;	790	$uhost =~ s/^\[(.*)\]$/$1/;
368	$upath .= "?$query" if length $query;	791	$upath .= $query if length $query;
369		792
370	$upath =~ s%^/?%/%;	793	$upath =~ s%^/?%/%;
371		794
372	# cookie processing	795	# cookie processing
373	if (my $jar = $arg{cookie_jar}) {	796	if (my $jar = $arg{cookie_jar}) {
374	%$jar = () if $jar->{version} != 1;	797	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
375		798
376	my @cookie;
377
378	while (my ($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	799	$hdr{cookie} = join "; ", @$cookies
400	if @cookie;	800	if @$cookies;
401	}	801	}
402		802
403	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	803	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
404		804
405	if ($proxy) {	805	if ($proxy) {
…		…
408	$rscheme = "http" unless defined $rscheme;	808	$rscheme = "http" unless defined $rscheme;
409		809
410	# don't support https requests over https-proxy transport,	810	# don't support https requests over https-proxy transport,
411	# can't be done with tls as spec'ed, unless you double-encrypt.	811	# can't be done with tls as spec'ed, unless you double-encrypt.
412	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	812	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		813
		814	$rhost = lc $rhost;
		815	$rscheme = lc $rscheme;
413	} else {	816	} else {
414	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	817	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
415	}	818	}
416		819
417	# leave out fragment and query string, just a heuristic	820	# leave out fragment and query string, just a heuristic
418	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	821	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
419	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};	822	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
420		823
421	$hdr{"content-length"} = length $arg{body};	824	$hdr{"content-length"} = length $arg{body}
		825	if length $arg{body} \|\| $method ne "GET";
		826
		827	my $idempotent = $IDEMPOTENT{$method};
		828
		829	# default value for keepalive is true iff the request is for an idempotent method
		830	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		831	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		832	my $was_persistent; # true if this is actually a recycled connection
		833
		834	# the key to use in the keepalive cache
		835	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		836
		837	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1
		838	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
422		839
423	my %state = (connect_guard => 1);	840	my %state = (connect_guard => 1);
		841
		842	my $ae_error = 595; # connecting
		843
		844	# handle actual, non-tunneled, request
		845	my $handle_actual_request = sub {
		846	$ae_error = 596; # request phase
		847
		848	my $hdl = $state{handle};
		849
		850	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		851
		852	# send request
		853	$hdl->push_write (
		854	"$method $rpath HTTP/1.1\015\012"
		855	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		856	. "\015\012"
		857	. $arg{body}
		858	);
		859
		860	# return if error occurred during push_write()
		861	return unless %state;
		862
		863	# reduce memory usage, save a kitten, also re-use it for the response headers.
		864	%hdr = ();
		865
		866	# status line and headers
		867	$state{read_response} = sub {
		868	return unless %state;
		869
		870	for ("$_[1]") {
		871	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		872
		873	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		874	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		875
		876	# 100 Continue handling
		877	# should not happen as we don't send expect: 100-continue,
		878	# but we handle it just in case.
		879	# since we send the request body regardless, if we get an error
		880	# we are out of-sync, which we currently do NOT handle correctly.
		881	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		882	if $2 eq 100;
		883
		884	push @pseudo,
		885	HTTPVersion => $1,
		886	Status => $2,
		887	Reason => $3,
		888	;
		889
		890	my $hdr = _parse_hdr
		891	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		892
		893	%hdr = (%$hdr, @pseudo);
		894	}
		895
		896	# redirect handling
		897	# relative uri handling forced by microsoft and other shitheads.
		898	# we give our best and fall back to URI if available.
		899	if (exists $hdr{location}) {
		900	my $loc = $hdr{location};
		901
		902	if ($loc =~ m%^//%) { # //
		903	$loc = "$uscheme:$loc";
		904
		905	} elsif ($loc eq "") {
		906	$loc = $url;
		907
		908	} elsif ($loc !~ /^(?: $ \| [^:\/?\#]+ : )/x) { # anything "simple"
		909	$loc =~ s/^\.\/+//;
		910
		911	if ($loc !~ m%^[.?#]%) {
		912	my $prefix = "$uscheme://$uauthority";
		913
		914	unless ($loc =~ s/^\///) {
		915	$prefix .= $upath;
		916	$prefix =~ s/\/[^\/]*$//;
		917	}
		918
		919	$loc = "$prefix/$loc";
		920
		921	} elsif (eval { require URI }) { # uri
		922	$loc = URI->new_abs ($loc, $url)->as_string;
		923
		924	} else {
		925	return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" };
		926	#$hdr{Status} = 599;
		927	#$hdr{Reason} = "Unparsable Redirect (URI module missing)";
		928	#$recurse = 0;
		929	}
		930	}
		931
		932	$hdr{location} = $loc;
		933	}
		934
		935	my $redirect;
		936
		937	if ($recurse) {
		938	my $status = $hdr{Status};
		939
		940	# industry standard is to redirect POST as GET for
		941	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		942	# also, the UA should ask the user for 301 and 307 and POST,
		943	# industry standard seems to be to simply follow.
		944	# we go with the industry standard. 308 is defined
		945	# by rfc7538
		946	if ($status == 301 or $status == 302 or $status == 303) {
		947	$redirect = 1;
		948	# HTTP/1.1 is unclear on how to mutate the method
		949	unless ($method eq "HEAD") {
		950	$method = "GET";
		951	delete $arg{body};
		952	}
		953	} elsif ($status == 307 or $status == 308) {
		954	$redirect = 1;
		955	}
		956	}
		957
		958	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		959	if ($state{handle}) {
		960	# handle keepalive
		961	if (
		962	$persistent
		963	&& $_[3]
		964	&& ($hdr{HTTPVersion} < 1.1
		965	? $hdr{connection} =~ /\bkeep-?alive\b/i
		966	: $hdr{connection} !~ /\bclose\b/i)
		967	) {
		968	ka_store $ka_key, delete $state{handle};
		969	} else {
		970	# no keepalive, destroy the handle
		971	$state{handle}->destroy;
		972	}
		973	}
		974
		975	%state = ();
		976
		977	if (defined $_[1]) {
		978	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		979	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		980	}
		981
		982	# set-cookie processing
		983	if ($arg{cookie_jar}) {
		984	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		985	}
		986
		987	if ($redirect && exists $hdr{location}) {
		988	# we ignore any errors, as it is very common to receive
		989	# Content-Length != 0 but no actual body
		990	# we also access %hdr, as $_[1] might be an erro
		991	$state{recurse} =
		992	http_request (
		993	$method => $hdr{location},
		994	%arg,
		995	recurse => $recurse - 1,
		996	Redirect => [$_[0], \%hdr],
		997	sub {
		998	%state = ();
		999	&$cb
		1000	},
		1001	);
		1002	} else {
		1003	$cb->($_[0], \%hdr);
		1004	}
		1005	};
		1006
		1007	$ae_error = 597; # body phase
		1008
		1009	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		1010
		1011	my $len = $chunked ? undef : $hdr{"content-length"};
		1012
		1013	# body handling, many different code paths
		1014	# - no body expected
		1015	# - want_body_handle
		1016	# - te chunked
		1017	# - 2x length known (with or without on_body)
		1018	# - 2x length not known (with or without on_body)
		1019	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		1020	$finish->(undef, 598 => "Request cancelled by on_header");
		1021	} elsif (
		1022	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		1023	or $method eq "HEAD"
		1024	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		1025	) {
		1026	# no body
		1027	$finish->("", undef, undef, 1);
		1028
		1029	} elsif (!$redirect && $arg{want_body_handle}) {
		1030	$_[0]->on_eof (undef);
		1031	$_[0]->on_error (undef);
		1032	$_[0]->on_read (undef);
		1033
		1034	$finish->(delete $state{handle});
		1035
		1036	} elsif ($chunked) {
		1037	my $cl = 0;
		1038	my $body = "";
		1039	my $on_body = (!$redirect && $arg{on_body}) \|\| sub { $body .= shift; 1 };
		1040
		1041	$state{read_chunk} = sub {
		1042	$_[1] =~ /^([0-9a-fA-F]+)/
		1043	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1044
		1045	my $len = hex $1;
		1046
		1047	if ($len) {
		1048	$cl += $len;
		1049
		1050	$_[0]->push_read (chunk => $len, sub {
		1051	$on_body->($_[1], \%hdr)
		1052	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1053
		1054	$_[0]->push_read (line => sub {
		1055	length $_[1]
		1056	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1057	$_[0]->push_read (line => $state{read_chunk});
		1058	});
		1059	});
		1060	} else {
		1061	$hdr{"content-length"} \|\|= $cl;
		1062
		1063	$_[0]->push_read (line => $qr_nlnl, sub {
		1064	if (length $_[1]) {
		1065	for ("$_[1]") {
		1066	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		1067
		1068	my $hdr = _parse_hdr
		1069	or return $finish->(undef, $ae_error => "Garbled response trailers");
		1070
		1071	%hdr = (%hdr, %$hdr);
		1072	}
		1073	}
		1074
		1075	$finish->($body, undef, undef, 1);
		1076	});
		1077	}
		1078	};
		1079
		1080	$_[0]->push_read (line => $state{read_chunk});
		1081
		1082	} elsif (!$redirect && $arg{on_body}) {
		1083	if (defined $len) {
		1084	$_[0]->on_read (sub {
		1085	$len -= length $_[0]{rbuf};
		1086
		1087	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1088	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1089
		1090	$len > 0
		1091	or $finish->("", undef, undef, 1);
		1092	});
		1093	} else {
		1094	$_[0]->on_eof (sub {
		1095	$finish->("");
		1096	});
		1097	$_[0]->on_read (sub {
		1098	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1099	or $finish->(undef, 598 => "Request cancelled by on_body");
		1100	});
		1101	}
		1102	} else {
		1103	$_[0]->on_eof (undef);
		1104
		1105	if (defined $len) {
		1106	$_[0]->on_read (sub {
		1107	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1108	if $len <= length $_[0]{rbuf};
		1109	});
		1110	} else {
		1111	$_[0]->on_error (sub {
		1112	($! == Errno::EPIPE \|\| !$!)
		1113	? $finish->(delete $_[0]{rbuf})
		1114	: $finish->(undef, $ae_error => $_[2]);
		1115	});
		1116	$_[0]->on_read (sub { });
		1117	}
		1118	}
		1119	};
		1120
		1121	# if keepalive is enabled, then the server closing the connection
		1122	# before a response can happen legally - we retry on idempotent methods.
		1123	if ($was_persistent && $idempotent) {
		1124	my $old_eof = $hdl->{on_eof};
		1125	$hdl->{on_eof} = sub {
		1126	_destroy_state %state;
		1127
		1128	%state = ();
		1129	$state{recurse} =
		1130	http_request (
		1131	$method => $url,
		1132	%arg,
		1133	recurse => $recurse - 1,
		1134	persistent => 0,
		1135	sub {
		1136	%state = ();
		1137	&$cb
		1138	}
		1139	);
		1140	};
		1141	$hdl->on_read (sub {
		1142	return unless %state;
		1143
		1144	# as soon as we receive something, a connection close
		1145	# once more becomes a hard error
		1146	$hdl->{on_eof} = $old_eof;
		1147	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1148	});
		1149	} else {
		1150	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1151	}
		1152	};
		1153
		1154	my $prepare_handle = sub {
		1155	my ($hdl) = $state{handle};
		1156
		1157	$hdl->on_error (sub {
		1158	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1159	});
		1160	$hdl->on_eof (sub {
		1161	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1162	});
		1163	$hdl->timeout_reset;
		1164	$hdl->timeout ($timeout);
		1165	};
		1166
		1167	# connected to proxy (or origin server)
		1168	my $connect_cb = sub {
		1169	my $fh = shift
		1170	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1171
		1172	return unless delete $state{connect_guard};
		1173
		1174	# get handle
		1175	$state{handle} = new AnyEvent::Handle
		1176	%{ $arg{handle_params} },
		1177	fh => $fh,
		1178	peername => $uhost,
		1179	tls_ctx => $arg{tls_ctx},
		1180	;
		1181
		1182	$prepare_handle->();
		1183
		1184	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1185
		1186	# now handle proxy-CONNECT method
		1187	if ($proxy && $uscheme eq "https") {
		1188	# oh dear, we have to wrap it into a connect request
		1189
		1190	my $auth = exists $hdr{"proxy-authorization"}
		1191	? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012"
		1192	: "";
		1193
		1194	# maybe re-use $uauthority with patched port?
		1195	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012");
		1196	$state{handle}->push_read (line => $qr_nlnl, sub {
		1197	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1198	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1199
		1200	if ($2 == 200) {
		1201	$rpath = $upath;
		1202	$handle_actual_request->();
		1203	} else {
		1204	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1205	}
		1206	});
		1207	} else {
		1208	delete $hdr{"proxy-authorization"} unless $proxy;
		1209
		1210	$handle_actual_request->();
		1211	}
		1212	};
424		1213
425	_get_slot $uhost, sub {	1214	_get_slot $uhost, sub {
426	$state{slot_guard} = shift;	1215	$state{slot_guard} = shift;
427		1216
428	return unless $state{connect_guard};	1217	return unless $state{connect_guard};
429		1218
430	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	1219	# try to use an existing keepalive connection, but only if we, ourselves, plan
431	$state{fh} = shift	1220	# on a keepalive request (in theory, this should be a separate config option).
432	or do {	1221	if ($persistent && $KA_CACHE{$ka_key}) {
433	my $err = "$!";	1222	$was_persistent = 1;
434	%state = ();
435	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
436	};
437		1223
438	pop; # free memory, save a tree	1224	$state{handle} = ka_fetch $ka_key;
		1225	# $state{handle}->destroyed
		1226	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
		1227	$prepare_handle->();
		1228	# $state{handle}->destroyed
		1229	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
		1230	$handle_actual_request->();
439		1231
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 {	1232	} else {
458	delete $hdr{connection};	1233	my $tcp_connect = $arg{tcp_connect}
459	}	1234	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
460		1235
461	# (re-)configure handle	1236	$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		1237	}
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 { $timeout };
708	};	1238	};
709		1239
710	defined wantarray && AnyEvent::Util::guard { %state = () }	1240	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
711	}	1241	}
712		1242
713	sub http_get($@) {	1243	sub http_get($@) {
714	unshift @_, "GET";	1244	unshift @_, "GET";
715	&http_request	1245	&http_request
…		…
726	&http_request	1256	&http_request
727	}	1257	}
728		1258
729	=back	1259	=back
730		1260
		1261	=head2 DNS CACHING
		1262
		1263	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		1264	the actual connection, which in turn uses AnyEvent::DNS to resolve
		1265	hostnames. The latter is a simple stub resolver and does no caching
		1266	on its own. If you want DNS caching, you currently have to provide
		1267	your own default resolver (by storing a suitable resolver object in
		1268	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
		1269
731	=head2 GLOBAL FUNCTIONS AND VARIABLES	1270	=head2 GLOBAL FUNCTIONS AND VARIABLES
732		1271
733	=over 4	1272	=over 4
734		1273
735	=item AnyEvent::HTTP::set_proxy "proxy-url"	1274	=item AnyEvent::HTTP::set_proxy "proxy-url"
736		1275
737	Sets the default proxy server to use. The proxy-url must begin with a	1276	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:...>).	1277	string of the form C<http://host:port>, croaks otherwise.
		1278
		1279	To clear an already-set proxy, use C<undef>.
		1280
		1281	When AnyEvent::HTTP is loaded for the first time it will query the
		1282	default proxy from the operating system, currently by looking at
		1283	C<$ENV{http_proxy>}.
		1284
		1285	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1286
		1287	Remove all cookies from the cookie jar that have been expired. If
		1288	C<$session_end> is given and true, then additionally remove all session
		1289	cookies.
		1290
		1291	You should call this function (with a true C<$session_end>) before you
		1292	save cookies to disk, and you should call this function after loading them
		1293	again. If you have a long-running program you can additionally call this
		1294	function from time to time.
		1295
		1296	A cookie jar is initially an empty hash-reference that is managed by this
		1297	module. Its format is subject to change, but currently it is as follows:
		1298
		1299	The key C<version> has to contain C<2>, otherwise the hash gets
		1300	cleared. All other keys are hostnames or IP addresses pointing to
		1301	hash-references. The key for these inner hash references is the
		1302	server path for which this cookie is meant, and the values are again
		1303	hash-references. Each key of those hash-references is a cookie name, and
		1304	the value, you guessed it, is another hash-reference, this time with the
		1305	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1306	which have been replaced by a C<_expires> key that contains the cookie
		1307	expiry timestamp. Session cookies are indicated by not having an
		1308	C<_expires> key.
		1309
		1310	Here is an example of a cookie jar with a single cookie, so you have a
		1311	chance of understanding the above paragraph:
		1312
		1313	{
		1314	version => 2,
		1315	"10.0.0.1" => {
		1316	"/" => {
		1317	"mythweb_id" => {
		1318	_expires => 1293917923,
		1319	value => "ooRung9dThee3ooyXooM1Ohm",
		1320	},
		1321	},
		1322	},
		1323	}
		1324
		1325	=item $date = AnyEvent::HTTP::format_date $timestamp
		1326
		1327	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1328	Date (RFC 2616).
		1329
		1330	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1331
		1332	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1333	bunch of minor variations of those, and returns the corresponding POSIX
		1334	timestamp, or C<undef> if the date cannot be parsed.
739		1335
740	=item $AnyEvent::HTTP::MAX_RECURSE	1336	=item $AnyEvent::HTTP::MAX_RECURSE
741		1337
742	The default value for the C<recurse> request parameter (default: C<10>).	1338	The default value for the C<recurse> request parameter (default: C<10>).
		1339
		1340	=item $AnyEvent::HTTP::TIMEOUT
		1341
		1342	The default timeout for connection operations (default: C<300>).
743		1343
744	=item $AnyEvent::HTTP::USERAGENT	1344	=item $AnyEvent::HTTP::USERAGENT
745		1345
746	The default value for the C<User-Agent> header (the default is	1346	The default value for the C<User-Agent> header (the default is
747	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1347	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
748		1348
749	=item $AnyEvent::HTTP::MAX_PER_HOST	1349	=item $AnyEvent::HTTP::MAX_PER_HOST
750		1350
751	The maximum number of concurrent connections to the same host (identified	1351	The maximum number of concurrent connections to the same host (identified
752	by the hostname). If the limit is exceeded, then the additional requests	1352	by the hostname). If the limit is exceeded, then additional requests
753	are queued until previous connections are closed.	1353	are queued until previous connections are closed. Both persistent and
		1354	non-persistent connections are counted in this limit.
754		1355
755	The default value for this is C<4>, and it is highly advisable to not	1356	The default value for this is C<4>, and it is highly advisable to not
756	increase it.	1357	increase it much.
		1358
		1359	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1360	connections, older browsers used 2, newer ones (such as firefox 3)
		1361	typically use 6, and Opera uses 8 because like, they have the fastest
		1362	browser and give a shit for everybody else on the planet.
		1363
		1364	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1365
		1366	The time after which idle persistent connections get closed by
		1367	AnyEvent::HTTP (default: C<3>).
757		1368
758	=item $AnyEvent::HTTP::ACTIVE	1369	=item $AnyEvent::HTTP::ACTIVE
759		1370
760	The number of active connections. This is not the number of currently	1371	The number of active connections. This is not the number of currently
761	running requests, but the number of currently open and non-idle TCP	1372	running requests, but the number of currently open and non-idle TCP
762	connections. This number of can be useful for load-leveling.	1373	connections. This number can be useful for load-leveling.
763		1374
764	=back	1375	=back
765		1376
766	=cut	1377	=cut
767		1378
		1379	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1380	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1381
		1382	sub format_date($) {
		1383	my ($time) = @_;
		1384
		1385	# RFC 822/1123 format
		1386	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1387
		1388	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1389	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1390	$H, $M, $S;
		1391	}
		1392
		1393	sub parse_date($) {
		1394	my ($date) = @_;
		1395
		1396	my ($d, $m, $y, $H, $M, $S);
		1397
		1398	if ($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$/) {
		1399	# RFC 822/1123, required by RFC 2616 (with " ")
		1400	# cookie dates (with "-")
		1401
		1402	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1403
		1404	} elsif ($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$/) {
		1405	# RFC 850
		1406	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1407
		1408	} elsif ($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])$/) {
		1409	# ISO C's asctime
		1410	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1411	}
		1412	# other formats fail in the loop below
		1413
		1414	for (0..11) {
		1415	if ($m eq $month[$_]) {
		1416	require Time::Local;
		1417	return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) };
		1418	}
		1419	}
		1420
		1421	undef
		1422	}
		1423
768	sub set_proxy($) {	1424	sub set_proxy($) {
769	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1425	if (length $_[0]) {
		1426	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
		1427	or Carp::croak "$_[0]: invalid proxy URL";
		1428	$PROXY = [$2, $3 \|\| 3128, $1]
		1429	} else {
		1430	undef $PROXY;
		1431	}
770	}	1432	}
771		1433
772	# initialise proxy from environment	1434	# initialise proxy from environment
		1435	eval {
773	set_proxy $ENV{http_proxy};	1436	set_proxy $ENV{http_proxy};
		1437	};
		1438
		1439	=head2 SHOWCASE
		1440
		1441	This section contains some more elaborate "real-world" examples or code
		1442	snippets.
		1443
		1444	=head2 HTTP/1.1 FILE DOWNLOAD
		1445
		1446	Downloading files with HTTP can be quite tricky, especially when something
		1447	goes wrong and you want to resume.
		1448
		1449	Here is a function that initiates and resumes a download. It uses the
		1450	last modified time to check for file content changes, and works with many
		1451	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1452	on older servers.
		1453
		1454	It calls the completion callback with either C<undef>, which means a
		1455	nonretryable error occurred, C<0> when the download was partial and should
		1456	be retried, and C<1> if it was successful.
		1457
		1458	use AnyEvent::HTTP;
		1459
		1460	sub download($$$) {
		1461	my ($url, $file, $cb) = @_;
		1462
		1463	open my $fh, "+<", $file
		1464	or die "$file: $!";
		1465
		1466	my %hdr;
		1467	my $ofs = 0;
		1468
		1469	if (stat $fh and -s _) {
		1470	$ofs = -s _;
		1471	warn "-s is ", $ofs;
		1472	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1473	$hdr{"range"} = "bytes=$ofs-";
		1474	}
		1475
		1476	http_get $url,
		1477	headers => \%hdr,
		1478	on_header => sub {
		1479	my ($hdr) = @_;
		1480
		1481	if ($hdr->{Status} == 200 && $ofs) {
		1482	# resume failed
		1483	truncate $fh, $ofs = 0;
		1484	}
		1485
		1486	sysseek $fh, $ofs, 0;
		1487
		1488	1
		1489	},
		1490	on_body => sub {
		1491	my ($data, $hdr) = @_;
		1492
		1493	if ($hdr->{Status} =~ /^2/) {
		1494	length $data == syswrite $fh, $data
		1495	or return; # abort on write errors
		1496	}
		1497
		1498	1
		1499	},
		1500	sub {
		1501	my (undef, $hdr) = @_;
		1502
		1503	my $status = $hdr->{Status};
		1504
		1505	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1506	utime $time, $time, $fh;
		1507	}
		1508
		1509	if ($status == 200 \|\| $status == 206 \|\| $status == 416) {
		1510	# download ok \|\| resume ok \|\| file already fully downloaded
		1511	$cb->(1, $hdr);
		1512
		1513	} elsif ($status == 412) {
		1514	# file has changed while resuming, delete and retry
		1515	unlink $file;
		1516	$cb->(0, $hdr);
		1517
		1518	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1519	# retry later
		1520	$cb->(0, $hdr);
		1521
		1522	} else {
		1523	$cb->(undef, $hdr);
		1524	}
		1525	}
		1526	;
		1527	}
		1528
		1529	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1530	if ($_[0]) {
		1531	print "OK!\n";
		1532	} elsif (defined $_[0]) {
		1533	print "please retry later\n";
		1534	} else {
		1535	print "ERROR\n";
		1536	}
		1537	};
		1538
		1539	=head3 SOCKS PROXIES
		1540
		1541	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1542	compile your perl to support socks, or use an external program such as
		1543	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1544	transparently.
		1545
		1546	Alternatively, for AnyEvent::HTTP only, you can use your own
		1547	C<tcp_connect> function that does the proxy handshake - here is an example
		1548	that works with socks4a proxies:
		1549
		1550	use Errno;
		1551	use AnyEvent::Util;
		1552	use AnyEvent::Socket;
		1553	use AnyEvent::Handle;
		1554
		1555	# host, port and username of/for your socks4a proxy
		1556	my $socks_host = "10.0.0.23";
		1557	my $socks_port = 9050;
		1558	my $socks_user = "";
		1559
		1560	sub socks4a_connect {
		1561	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1562
		1563	my $hdl = new AnyEvent::Handle
		1564	connect => [$socks_host, $socks_port],
		1565	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1566	on_error => sub { $connect_cb->() },
		1567	;
		1568
		1569	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1570
		1571	$hdl->push_read (chunk => 8, sub {
		1572	my ($hdl, $chunk) = @_;
		1573	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1574
		1575	if ($status == 0x5a) {
		1576	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1577	} else {
		1578	$! = Errno::ENXIO; $connect_cb->();
		1579	}
		1580	});
		1581
		1582	$hdl
		1583	}
		1584
		1585	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1586	possibly after switching off other proxy types:
		1587
		1588	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1589
		1590	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1591	my ($data, $headers) = @_;
		1592	...
		1593	};
774		1594
775	=head1 SEE ALSO	1595	=head1 SEE ALSO
776		1596
777	L<AnyEvent>.	1597	L<AnyEvent>.
778		1598

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.50 by root, Tue Aug 11 13:20:42 2009 UTC vs. Revision 1.132 by root, Thu Aug 30 17:05:45 2018 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.50 by root, Tue Aug 11 13:20:42 2009 UTC vs.
Revision 1.132 by root, Thu Aug 30 17:05:45 2018 UTC