[ViewVC] Diff of: cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.58 by root, Sun Nov 14 20:23:00 2010 UTC vs.
Revision 1.137 by root, Mon Apr 27 12:14:12 2020 UTC

…		…
15	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
16	run a supported event loop.	16	run a supported event loop.
17		17
18	This module implements a simple, stateless and non-blocking HTTP	18	This module implements a simple, stateless and non-blocking HTTP
19	client. It supports GET, POST and other request methods, cookies and more,	19	client. It supports GET, POST and other request methods, cookies and more,
20	all on a very low level. It can follow redirects supports proxies and	20	all on a very low level. It can follow redirects, supports proxies, and
21	automatically limits the number of connections to the values specified in	21	automatically limits the number of connections to the values specified in
22	the RFC.	22	the RFC.
23		23
24	It should generally be a "good client" that is enough for most HTTP	24	It should generally be a "good client" that is enough for most HTTP
25	tasks. Simple tasks should be simple, but complex tasks should still be	25	tasks. Simple tasks should be simple, but complex tasks should still be
…		…
36		36
37	=cut	37	=cut
38		38
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use common::sense;
42	no warnings;
43		42
44	use Errno ();	43	use Errno ();
45		44
46	use AnyEvent 5.0 ();	45	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	46	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
50		48
51	use base Exporter::;	49	use base Exporter::;
52		50
53	our $VERSION = '1.46';	51	our $VERSION = 2.25;
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
…		…
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 callback 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" (uppercase to avoid clashing with possible	98	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
105	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the	99	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
106	three parts of the HTTP Status-Line of the same name.	100	three parts of the HTTP Status-Line of the same name. If an error occurs
		101	during the body phase of a request, then the original C<Status> and
		102	C<Reason> values from the header are available as C<OrigStatus> and
		103	C<OrigReason>.
107		104
108	The pseudo-header C<URL> contains the actual URL (which can differ from	105	The pseudo-header C<URL> contains the actual URL (which can differ from
109	the requested URL when following redirects - for example, you might get	106	the requested URL when following redirects - for example, you might get
110	an error that your URL scheme is not supported even though your URL is a	107	an error that your URL scheme is not supported even though your URL is a
111	valid http URL because it redirected to an ftp URL, in which case you can	108	valid http URL because it redirected to an ftp URL, in which case you can
…		…
120		117
121	If the server sends a header multiple times, then their contents will be	118	If the server sends a header multiple times, then their contents will be
122	joined together with a comma (C<,>), as per the HTTP spec.	119	joined together with a comma (C<,>), as per the HTTP spec.
123		120
124	If an internal error occurs, such as not being able to resolve a hostname,	121	If an internal error occurs, such as not being able to resolve a hostname,
125	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>	122	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
126	(usually C<599>) and the C<Reason> pseudo-header will contain an error	123	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
127	message.	124	message. Currently the following status codes are used:
		125
		126	=over 4
		127
		128	=item 595 - errors during connection establishment, proxy handshake.
		129
		130	=item 596 - errors during TLS negotiation, request sending and header processing.
		131
		132	=item 597 - errors during body receiving or processing.
		133
		134	=item 598 - user aborted request via C<on_header> or C<on_body>.
		135
		136	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		137
		138	=back
128		139
129	A typical callback might look like this:	140	A typical callback might look like this:
130		141
131	sub {	142	sub {
132	my ($body, $hdr) = @_;	143	my ($body, $hdr) = @_;
…		…
143		154
144	=over 4	155	=over 4
145		156
146	=item recurse => $count (default: $MAX_RECURSE)	157	=item recurse => $count (default: $MAX_RECURSE)
147		158
148	Whether to recurse requests or not, e.g. on redirects, authentication	159	Whether to recurse requests or not, e.g. on redirects, authentication and
149	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.
150		166
151	=item headers => hashref	167	=item headers => hashref
152		168
153	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
154	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
155	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:>
156	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
157	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.
158		181
159	=item timeout => $seconds	182	=item timeout => $seconds
160		183
161	The time-out to use for various stages - each connect attempt will reset	184	The time-out to use for various stages - each connect attempt will reset
162	the timeout, as will read or write activity, i.e. this is not an overall	185	the timeout, as will read or write activity, i.e. this is not an overall
…		…
164		187
165	Default timeout is 5 minutes.	188	Default timeout is 5 minutes.
166		189
167	=item proxy => [$host, $port[, $scheme]] or undef	190	=item proxy => [$host, $port[, $scheme]] or undef
168		191
169	Use the given http proxy for all requests. If not specified, then the	192	Use the given http proxy for all requests, or no proxy if C<undef> is
170	default proxy (as specified by C<$ENV{http_proxy}>) is used.	193	used.
171		194
172	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.
173	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.
		202
		203	Note that this module will prefer an existing persistent connection,
		204	even if that connection was made using another proxy. If you need to
		205	ensure that a new connection is made in this case, you can either force
		206	C<persistent> to false or e.g. use the proxy address in your C<sessionid>.
174		207
175	=item body => $string	208	=item body => $string
176		209
177	The request body, usually empty. Will be-sent as-is (future versions of	210	The request body, usually empty. Will be sent as-is (future versions of
178	this module might offer more options).	211	this module might offer more options).
179		212
180	=item cookie_jar => $hash_ref	213	=item cookie_jar => $hash_ref
181		214
182	Passing this parameter enables (simplified) cookie-processing, loosely	215	Passing this parameter enables (simplified) cookie-processing, loosely
183	based on the original netscape specification.	216	based on the original netscape specification.
184		217
185	The C<$hash_ref> must be an (initially empty) hash reference which will	218	The C<$hash_ref> must be an (initially empty) hash reference which
186	get updated automatically. It is possible to save the cookie_jar to	219	will get updated automatically. It is possible to save the cookie jar
187	persistent storage with something like JSON or Storable, but this is not	220	to persistent storage with something like JSON or Storable - see the
188	recommended, as expiry times are currently being ignored.	221	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		222	expired or session-only cookies, and also for documentation on the format
		223	of the cookie jar.
189		224
190	Note that this cookie implementation is not of very high quality, nor	225	Note that this cookie implementation is not meant to be complete. If
191	meant to be complete. If you want complete cookie management you have to	226	you want complete cookie management you have to do that on your
192	do that on your own. C<cookie_jar> is meant as a quick fix to get some	227	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
193	cookie-using sites working. Cookies are a privacy disaster, do not use	228	working. Cookies are a privacy disaster, do not use them unless required
194	them unless required to.	229	to.
		230
		231	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		232	headers will be set and handled by this module, otherwise they will be
		233	left untouched.
195		234
196	=item tls_ctx => $scheme \| $tls_ctx	235	=item tls_ctx => $scheme \| $tls_ctx
197		236
198	Specifies the AnyEvent::TLS context to be used for https connections. This	237	Specifies the AnyEvent::TLS context to be used for https connections. This
199	parameter follows the same rules as the C<tls_ctx> parameter to	238	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
203	verification) TLS context.	242	verification) TLS context.
204		243
205	The default for this option is C<low>, which could be interpreted as "give	244	The default for this option is C<low>, which could be interpreted as "give
206	me the page, no matter what".	245	me the page, no matter what".
207		246
		247	See also the C<sessionid> parameter.
		248
		249	=item sessionid => $string
		250
		251	The module might reuse connections to the same host internally (regardless
		252	of other settings, such as C<tcp_connect> or C<proxy>). Sometimes (e.g.
		253	when using TLS or a specfic proxy), you do not want to reuse connections
		254	from other sessions. This can be achieved by setting this parameter to
		255	some unique ID (such as the address of an object storing your state data
		256	or the TLS context, or the proxy IP) - only connections using the same
		257	unique ID will be reused.
		258
208	=item on_prepare => $callback->($fh)	259	=item on_prepare => $callback->($fh)
209		260
210	In rare cases you need to "tune" the socket before it is used to	261	In rare cases you need to "tune" the socket before it is used to
211	connect (for exmaple, to bind it on a given IP address). This parameter	262	connect (for example, to bind it on a given IP address). This parameter
212	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>	263	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
213	and behaves exactly the same way (e.g. it has to provide a	264	and behaves exactly the same way (e.g. it has to provide a
214	timeout). See the description for the C<$prepare_cb> argument of	265	timeout). See the description for the C<$prepare_cb> argument of
215	C<AnyEvent::Socket::tcp_connect> for details.	266	C<AnyEvent::Socket::tcp_connect> for details.
216		267
		268	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		269
		270	In even rarer cases you want total control over how AnyEvent::HTTP
		271	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		272	to do this, but you can provide your own C<tcp_connect> function -
		273	obviously, it has to follow the same calling conventions, except that it
		274	may always return a connection guard object.
		275
		276	The connections made by this hook will be treated as equivalent to
		277	connections made the built-in way, specifically, they will be put into
		278	and taken from the persistent connection cache. If your C<$tcp_connect>
		279	function is incompatible with this kind of re-use, consider switching off
		280	C<persistent> connections and/or providing a C<sessionid> identifier.
		281
		282	There are probably lots of weird uses for this function, starting from
		283	tracing the hosts C<http_request> actually tries to connect, to (inexact
		284	but fast) host => IP address caching or even socks protocol support.
		285
217	=item on_header => $callback->($headers)	286	=item on_header => $callback->($headers)
218		287
219	When specified, this callback will be called with the header hash as soon	288	When specified, this callback will be called with the header hash as soon
220	as headers have been successfully received from the remote server (not on	289	as headers have been successfully received from the remote server (not on
221	locally-generated errors).	290	locally-generated errors).
…		…
226		295
227	This callback is useful, among other things, to quickly reject unwanted	296	This callback is useful, among other things, to quickly reject unwanted
228	content, which, if it is supposed to be rare, can be faster than first	297	content, which, if it is supposed to be rare, can be faster than first
229	doing a C<HEAD> request.	298	doing a C<HEAD> request.
230		299
		300	The downside is that cancelling the request makes it impossible to re-use
		301	the connection. Also, the C<on_header> callback will not receive any
		302	trailer (headers sent after the response body).
		303
231	Example: cancel the request unless the content-type is "text/html".	304	Example: cancel the request unless the content-type is "text/html".
232		305
233	on_header => sub {	306	on_header => sub {
234	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/	307	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
235	},	308	},
…		…
241	string instead of the body data.	314	string instead of the body data.
242		315
243	It has to return either true (in which case AnyEvent::HTTP will continue),	316	It has to return either true (in which case AnyEvent::HTTP will continue),
244	or false, in which case AnyEvent::HTTP will cancel the download (and call	317	or false, in which case AnyEvent::HTTP will cancel the download (and call
245	the completion callback with an error code of C<598>).	318	the completion callback with an error code of C<598>).
		319
		320	The downside to cancelling the request is that it makes it impossible to
		321	re-use the connection.
246		322
247	This callback is useful when the data is too large to be held in memory	323	This callback is useful when the data is too large to be held in memory
248	(so the callback writes it to a file) or when only some information should	324	(so the callback writes it to a file) or when only some information should
249	be extracted, or when the body should be processed incrementally.	325	be extracted, or when the body should be processed incrementally.
250		326
…		…
262	called. Instead of the C<$body> argument containing the body data, the	338	called. Instead of the C<$body> argument containing the body data, the
263	callback will receive the L<AnyEvent::Handle> object associated with the	339	callback will receive the L<AnyEvent::Handle> object associated with the
264	connection. In error cases, C<undef> will be passed. When there is no body	340	connection. In error cases, C<undef> will be passed. When there is no body
265	(e.g. status C<304>), the empty string will be passed.	341	(e.g. status C<304>), the empty string will be passed.
266		342
267	The handle object might or might not be in TLS mode, might be connected to	343	The handle object might or might not be in TLS mode, might be connected
268	a proxy, be a persistent connection etc., and configured in unspecified	344	to a proxy, be a persistent connection, use chunked transfer encoding
269	ways. The user is responsible for this handle (it will not be used by this	345	etc., and configured in unspecified ways. The user is responsible for this
270	module anymore).	346	handle (it will not be used by this module anymore).
271		347
272	This is useful with some push-type services, where, after the initial	348	This is useful with some push-type services, where, after the initial
273	headers, an interactive protocol is used (typical example would be the	349	headers, an interactive protocol is used (typical example would be the
274	push-style twitter API which starts a JSON/XML stream).	350	push-style twitter API which starts a JSON/XML stream).
275		351
276	If you think you need this, first have a look at C<on_body>, to see if	352	If you think you need this, first have a look at C<on_body>, to see if
277	that doesn't solve your problem in a better way.	353	that doesn't solve your problem in a better way.
278		354
		355	=item persistent => $boolean
		356
		357	Try to create/reuse a persistent connection. When this flag is set
		358	(default: true for idempotent requests, false for all others), then
		359	C<http_request> tries to re-use an existing (previously-created)
		360	persistent connection to same host (i.e. identical URL scheme, hostname,
		361	port and sessionid) and, failing that, tries to create a new one.
		362
		363	Requests failing in certain ways will be automatically retried once, which
		364	is dangerous for non-idempotent requests, which is why it defaults to off
		365	for them. The reason for this is because the bozos who designed HTTP/1.1
		366	made it impossible to distinguish between a fatal error and a normal
		367	connection timeout, so you never know whether there was a problem with
		368	your request or not.
		369
		370	When reusing an existent connection, many parameters (such as TLS context)
		371	will be ignored. See the C<sessionid> parameter for a workaround.
		372
		373	=item keepalive => $boolean
		374
		375	Only used when C<persistent> is also true. This parameter decides whether
		376	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		377	(as opposed to only a HTTP/1.1 persistent connection).
		378
		379	The default is true, except when using a proxy, in which case it defaults
		380	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		381
		382	=item handle_params => { key => value ... }
		383
		384	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		385	constructor that is called - not all requests will create a handle, and
		386	sometimes more than one is created, so this parameter is only good for
		387	setting hints.
		388
		389	Example: set the maximum read size to 4096, to potentially conserve memory
		390	at the cost of speed.
		391
		392	handle_params => {
		393	max_read_size => 4096,
		394	},
		395
279	=back	396	=back
280		397
281	Example: make a simple HTTP GET request for http://www.nethype.de/	398	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		399	the response body.
282		400
283	http_request GET => "http://www.nethype.de/", sub {	401	http_request GET => "http://www.nethype.de/", sub {
284	my ($body, $hdr) = @_;	402	my ($body, $hdr) = @_;
285	print "$body\n";	403	print "$body\n";
286	};	404	};
287		405
288	Example: make a HTTP HEAD request on https://www.google.com/, use a	406	Example: do a HTTP HEAD request on https://www.google.com/, use a
289	timeout of 30 seconds.	407	timeout of 30 seconds.
290		408
291	http_request	409	http_request
292	GET => "https://www.google.com",	410	HEAD => "https://www.google.com",
		411	headers => { "user-agent" => "MySearchClient 1.0" },
293	timeout => 30,	412	timeout => 30,
294	sub {	413	sub {
295	my ($body, $hdr) = @_;	414	my ($body, $hdr) = @_;
296	use Data::Dumper;	415	use Data::Dumper;
297	print Dumper $hdr;	416	print Dumper $hdr;
298	}	417	}
299	;	418	;
300		419
301	Example: make another simple HTTP GET request, but immediately try to	420	Example: do another simple HTTP GET request, but immediately try to
302	cancel it.	421	cancel it.
303		422
304	my $request = http_request GET => "http://www.nethype.de/", sub {	423	my $request = http_request GET => "http://www.nethype.de/", sub {
305	my ($body, $hdr) = @_;	424	my ($body, $hdr) = @_;
306	print "$body\n";	425	print "$body\n";
307	};	426	};
308		427
309	undef $request;	428	undef $request;
310		429
311	=cut	430	=cut
		431
		432	#############################################################################
		433	# wait queue/slots
312		434
313	sub _slot_schedule;	435	sub _slot_schedule;
314	sub _slot_schedule($) {	436	sub _slot_schedule($) {
315	my $host = shift;	437	my $host = shift;
316		438
…		…
338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	460	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
339		461
340	_slot_schedule $_[0];	462	_slot_schedule $_[0];
341	}	463	}
342		464
		465	#############################################################################
		466	# cookie handling
		467
		468	# expire cookies
		469	sub cookie_jar_expire($;$) {
		470	my ($jar, $session_end) = @_;
		471
		472	%$jar = () if $jar->{version} != 2;
		473
		474	my $anow = AE::now;
		475
		476	while (my ($chost, $paths) = each %$jar) {
		477	next unless ref $paths;
		478
		479	while (my ($cpath, $cookies) = each %$paths) {
		480	while (my ($cookie, $kv) = each %$cookies) {
		481	if (exists $kv->{_expires}) {
		482	delete $cookies->{$cookie}
		483	if $anow > $kv->{_expires};
		484	} elsif ($session_end) {
		485	delete $cookies->{$cookie};
		486	}
		487	}
		488
		489	delete $paths->{$cpath}
		490	unless %$cookies;
		491	}
		492
		493	delete $jar->{$chost}
		494	unless %$paths;
		495	}
		496	}
		497
		498	# extract cookies from jar
		499	sub cookie_jar_extract($$$$) {
		500	my ($jar, $scheme, $host, $path) = @_;
		501
		502	%$jar = () if $jar->{version} != 2;
		503
		504	$host = AnyEvent::Util::idn_to_ascii $host
		505	if $host =~ /[^\x00-\x7f]/;
		506
		507	my @cookies;
		508
		509	while (my ($chost, $paths) = each %$jar) {
		510	next unless ref $paths;
		511
		512	# exact match or suffix including . match
		513	$chost eq $host or ".$chost" eq substr $host, -1 - length $chost
		514	or next;
		515
		516	while (my ($cpath, $cookies) = each %$paths) {
		517	next unless $cpath eq substr $path, 0, length $cpath;
		518
		519	while (my ($cookie, $kv) = each %$cookies) {
		520	next if $scheme ne "https" && exists $kv->{secure};
		521
		522	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		523	delete $cookies->{$cookie};
		524	next;
		525	}
		526
		527	my $value = $kv->{value};
		528
		529	if ($value =~ /[=;,[:space:]]/) {
		530	$value =~ s/([\\"])/\\$1/g;
		531	$value = "\"$value\"";
		532	}
		533
		534	push @cookies, "$cookie=$value";
		535	}
		536	}
		537	}
		538
		539	\@cookies
		540	}
		541
		542	# parse set_cookie header into jar
		543	sub cookie_jar_set_cookie($$$$) {
		544	my ($jar, $set_cookie, $host, $date) = @_;
		545
		546	%$jar = () if $jar->{version} != 2;
		547
		548	my $anow = int AE::now;
		549	my $snow; # server-now
		550
		551	for ($set_cookie) {
		552	# parse NAME=VALUE
		553	my @kv;
		554
		555	# expires is not http-compliant in the original cookie-spec,
		556	# we support the official date format and some extensions
		557	while (
		558	m{
		559	\G\s*
		560	(?:
		561	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
		562	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^;,[:space:]]) ) )?
		563	)
		564	}gcxsi
		565	) {
		566	my $name = $2;
		567	my $value = $4;
		568
		569	if (defined $1) {
		570	# expires
		571	$name = "expires";
		572	$value = $1;
		573	} elsif (defined $3) {
		574	# quoted
		575	$value = $3;
		576	$value =~ s/\\(.)/$1/gs;
		577	}
		578
		579	push @kv, @kv ? lc $name : $name, $value;
		580
		581	last unless /\G\s*;/gc;
		582	}
		583
		584	last unless @kv;
		585
		586	my $name = shift @kv;
		587	my %kv = (value => shift @kv, @kv);
		588
		589	if (exists $kv{"max-age"}) {
		590	$kv{_expires} = $anow + delete $kv{"max-age"};
		591	} elsif (exists $kv{expires}) {
		592	$snow \|\|= parse_date ($date) \|\| $anow;
		593	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		594	} else {
		595	delete $kv{_expires};
		596	}
		597
		598	my $cdom;
		599	my $cpath = (delete $kv{path}) \|\| "/";
		600
		601	if (exists $kv{domain}) {
		602	$cdom = $kv{domain};
		603
		604	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		605
		606	next if $cdom =~ /\.$/;
		607
		608	# this is not rfc-like and not netscape-like. go figure.
		609	my $ndots = $cdom =~ y/.//;
		610	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		611
		612	$cdom = substr $cdom, 1; # remove initial .
		613	} else {
		614	$cdom = $host;
		615	}
		616
		617	# store it
		618	$jar->{version} = 2;
		619	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		620
		621	redo if /\G\s*,/gc;
		622	}
		623	}
		624
		625	#############################################################################
		626	# keepalive/persistent connection cache
		627
		628	# fetch a connection from the keepalive cache
		629	sub ka_fetch($) {
		630	my $ka_key = shift;
		631
		632	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		633	delete $KA_CACHE{$ka_key}
		634	unless @{ $KA_CACHE{$ka_key} };
		635
		636	$hdl
		637	}
		638
		639	sub ka_store($$) {
		640	my ($ka_key, $hdl) = @_;
		641
		642	my $kaa = $KA_CACHE{$ka_key} \|\|= [];
		643
		644	my $destroy = sub {
		645	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		646
		647	$hdl->destroy;
		648
		649	@ka
		650	? $KA_CACHE{$ka_key} = \@ka
		651	: delete $KA_CACHE{$ka_key};
		652	};
		653
		654	# on error etc., destroy
		655	$hdl->on_error ($destroy);
		656	$hdl->on_eof ($destroy);
		657	$hdl->on_read ($destroy);
		658	$hdl->timeout ($PERSISTENT_TIMEOUT);
		659
		660	push @$kaa, $hdl;
		661	shift @$kaa while @$kaa > $MAX_PER_HOST;
		662	}
		663
		664	#############################################################################
		665	# utilities
		666
		667	# continue to parse $_ for headers and place them into the arg
		668	sub _parse_hdr() {
		669	my %hdr;
		670
		671	# things seen, not parsed:
		672	# p3pP="NON CUR OTPi OUR NOR UNI"
		673
		674	$hdr{lc $1} .= ",$2"
		675	while /\G
		676	([^:\000-\037]*):
		677	[\011\040]*
		678	((?: [^\012]+ \| \012[\011\040] )*)
		679	\012
		680	/gxc;
		681
		682	/\G$/
		683	or return;
		684
		685	# remove the "," prefix we added to all headers above
		686	substr $_, 0, 1, ""
		687	for values %hdr;
		688
		689	\%hdr
		690	}
		691
		692	#############################################################################
		693	# http_get
		694
343	our $qr_nlnl = qr{(?<![^\012])\015?\012};	695	our $qr_nlnl = qr{(?<![^\012])\015?\012};
344		696
345	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	697	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
346	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	698	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		699
		700	# maybe it should just become a normal object :/
		701
		702	sub _destroy_state(\%) {
		703	my ($state) = @_;
		704
		705	$state->{handle}->destroy if $state->{handle};
		706	%$state = ();
		707	}
		708
		709	sub _error(\%$$) {
		710	my ($state, $cb, $hdr) = @_;
		711
		712	&_destroy_state ($state);
		713
		714	$cb->(undef, $hdr);
		715	()
		716	}
		717
		718	our %IDEMPOTENT = (
		719	DELETE => 1,
		720	GET => 1,
		721	HEAD => 1,
		722	OPTIONS => 1,
		723	PUT => 1,
		724	TRACE => 1,
		725
		726	ACL => 1,
		727	"BASELINE-CONTROL" => 1,
		728	BIND => 1,
		729	CHECKIN => 1,
		730	CHECKOUT => 1,
		731	COPY => 1,
		732	LABEL => 1,
		733	LINK => 1,
		734	MERGE => 1,
		735	MKACTIVITY => 1,
		736	MKCALENDAR => 1,
		737	MKCOL => 1,
		738	MKREDIRECTREF => 1,
		739	MKWORKSPACE => 1,
		740	MOVE => 1,
		741	ORDERPATCH => 1,
		742	PROPFIND => 1,
		743	PROPPATCH => 1,
		744	REBIND => 1,
		745	REPORT => 1,
		746	SEARCH => 1,
		747	UNBIND => 1,
		748	UNCHECKOUT => 1,
		749	UNLINK => 1,
		750	UNLOCK => 1,
		751	UPDATE => 1,
		752	UPDATEREDIRECTREF => 1,
		753	"VERSION-CONTROL" => 1,
		754	);
347		755
348	sub http_request($$@) {	756	sub http_request($$@) {
349	my $cb = pop;	757	my $cb = pop;
350	my ($method, $url, %arg) = @_;	758	my ($method, $url, %arg) = @_;
351		759
…		…
366	my @pseudo = (URL => $url);	774	my @pseudo = (URL => $url);
367	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};	775	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
368		776
369	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	777	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
370		778
371	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })	779	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
372	if $recurse < 0;	780	if $recurse < 0;
373		781
374	my $proxy = $arg{proxy} \|\| $PROXY;	782	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
375	my $timeout = $arg{timeout} \|\| $TIMEOUT;	783	my $timeout = $arg{timeout} \|\| $TIMEOUT;
376		784
377	my ($uscheme, $uauthority, $upath, $query, $fragment) =	785	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
378	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;	786	$url =~ m\|^([^:]+):(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?$\|;
379		787
380	$uscheme = lc $uscheme;	788	$uscheme = lc $uscheme;
381		789
382	my $uport = $uscheme eq "http" ? 80	790	my $uport = $uscheme eq "http" ? 80
383	: $uscheme eq "https" ? 443	791	: $uscheme eq "https" ? 443
384	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });	792	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
385		793
386	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	794	$uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x
387	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });	795	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
388		796
389	my $uhost = $1;	797	my $uhost = lc $1;
390	$uport = $2 if defined $2;	798	$uport = $2 if defined $2;
391		799
392	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	800	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
393	unless exists $hdr{host};	801	unless exists $hdr{host};
394		802
…		…
397		805
398	$upath =~ s%^/?%/%;	806	$upath =~ s%^/?%/%;
399		807
400	# cookie processing	808	# cookie processing
401	if (my $jar = $arg{cookie_jar}) {	809	if (my $jar = $arg{cookie_jar}) {
402	%$jar = () if $jar->{version} != 1;	810	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
403		811
404	my @cookie;
405
406	while (my ($chost, $v) = each %$jar) {
407	if ($chost =~ /^\./) {
408	next unless $chost eq substr $uhost, -length $chost;
409	} elsif ($chost =~ /\./) {
410	next unless $chost eq $uhost;
411	} else {
412	next;
413	}
414
415	while (my ($cpath, $v) = each %$v) {
416	next unless $cpath eq substr $upath, 0, length $cpath;
417
418	while (my ($k, $v) = each %$v) {
419	next if $uscheme ne "https" && exists $v->{secure};
420	my $value = $v->{value};
421	$value =~ s/([\\"])/\\$1/g;
422	push @cookie, "$k=\"$value\"";
423	}
424	}
425	}
426
427	$hdr{cookie} = join "; ", @cookie	812	$hdr{cookie} = join "; ", @$cookies
428	if @cookie;	813	if @$cookies;
429	}	814	}
430		815
431	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	816	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
432		817
433	if ($proxy) {	818	if ($proxy) {
…		…
436	$rscheme = "http" unless defined $rscheme;	821	$rscheme = "http" unless defined $rscheme;
437		822
438	# don't support https requests over https-proxy transport,	823	# don't support https requests over https-proxy transport,
439	# can't be done with tls as spec'ed, unless you double-encrypt.	824	# can't be done with tls as spec'ed, unless you double-encrypt.
440	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	825	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		826
		827	$rhost = lc $rhost;
		828	$rscheme = lc $rscheme;
441	} else {	829	} else {
442	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	830	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
443	}	831	}
444		832
445	# leave out fragment and query string, just a heuristic	833	# leave out fragment and query string, just a heuristic
446	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	834	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
447	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};	835	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
448		836
449	$hdr{"content-length"} = length $arg{body}	837	$hdr{"content-length"} = length $arg{body}
450	if length $arg{body} \|\| $method ne "GET";	838	if length $arg{body} \|\| $method ne "GET";
451		839
		840	my $idempotent = $IDEMPOTENT{$method};
		841
		842	# default value for keepalive is true iff the request is for an idempotent method
		843	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		844	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		845	my $was_persistent; # true if this is actually a recycled connection
		846
		847	# the key to use in the keepalive cache
		848	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		849
		850	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1
		851	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
		852
452	my %state = (connect_guard => 1);	853	my %state = (connect_guard => 1);
		854
		855	my $ae_error = 595; # connecting
		856
		857	# handle actual, non-tunneled, request
		858	my $handle_actual_request = sub {
		859	$ae_error = 596; # request phase
		860
		861	my $hdl = $state{handle};
		862
		863	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		864
		865	# send request
		866	$hdl->push_write (
		867	"$method $rpath HTTP/1.1\015\012"
		868	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		869	. "\015\012"
		870	. $arg{body}
		871	);
		872
		873	# return if error occurred during push_write()
		874	return unless %state;
		875
		876	# reduce memory usage, save a kitten, also re-use it for the response headers.
		877	%hdr = ();
		878
		879	# status line and headers
		880	$state{read_response} = sub {
		881	return unless %state;
		882
		883	for ("$_[1]") {
		884	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		885
		886	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		887	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		888
		889	# 100 Continue handling
		890	# should not happen as we don't send expect: 100-continue,
		891	# but we handle it just in case.
		892	# since we send the request body regardless, if we get an error
		893	# we are out of-sync, which we currently do NOT handle correctly.
		894	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		895	if $2 eq 100;
		896
		897	push @pseudo,
		898	HTTPVersion => $1,
		899	Status => $2,
		900	Reason => $3,
		901	;
		902
		903	my $hdr = _parse_hdr
		904	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		905
		906	%hdr = (%$hdr, @pseudo);
		907	}
		908
		909	# redirect handling
		910	# relative uri handling forced by microsoft and other shitheads.
		911	# we give our best and fall back to URI if available.
		912	if (exists $hdr{location}) {
		913	my $loc = $hdr{location};
		914
		915	if ($loc =~ m%^//%) { # //
		916	$loc = "$uscheme:$loc";
		917
		918	} elsif ($loc eq "") {
		919	$loc = $url;
		920
		921	} elsif ($loc !~ /^(?: $ \| [^:\/?\#]+ : )/x) { # anything "simple"
		922	$loc =~ s/^\.\/+//;
		923
		924	if ($loc !~ m%^[.?#]%) {
		925	my $prefix = "$uscheme://$uauthority";
		926
		927	unless ($loc =~ s/^\///) {
		928	$prefix .= $upath;
		929	$prefix =~ s/\/[^\/]*$//;
		930	}
		931
		932	$loc = "$prefix/$loc";
		933
		934	} elsif (eval { require URI }) { # uri
		935	$loc = URI->new_abs ($loc, $url)->as_string;
		936
		937	} else {
		938	return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" };
		939	#$hdr{Status} = 599;
		940	#$hdr{Reason} = "Unparsable Redirect (URI module missing)";
		941	#$recurse = 0;
		942	}
		943	}
		944
		945	$hdr{location} = $loc;
		946	}
		947
		948	my $redirect;
		949
		950	if ($recurse) {
		951	my $status = $hdr{Status};
		952
		953	# industry standard is to redirect POST as GET for
		954	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		955	# also, the UA should ask the user for 301 and 307 and POST,
		956	# industry standard seems to be to simply follow.
		957	# we go with the industry standard. 308 is defined
		958	# by rfc7538
		959	if ($status == 301 or $status == 302 or $status == 303) {
		960	$redirect = 1;
		961	# HTTP/1.1 is unclear on how to mutate the method
		962	unless ($method eq "HEAD") {
		963	$method = "GET";
		964	delete $arg{body};
		965	}
		966	} elsif ($status == 307 or $status == 308) {
		967	$redirect = 1;
		968	}
		969	}
		970
		971	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		972	if ($state{handle}) {
		973	# handle keepalive
		974	if (
		975	$persistent
		976	&& $_[3]
		977	&& ($hdr{HTTPVersion} < 1.1
		978	? $hdr{connection} =~ /\bkeep-?alive\b/i
		979	: $hdr{connection} !~ /\bclose\b/i)
		980	) {
		981	ka_store $ka_key, delete $state{handle};
		982	} else {
		983	# no keepalive, destroy the handle
		984	$state{handle}->destroy;
		985	}
		986	}
		987
		988	%state = ();
		989
		990	if (defined $_[1]) {
		991	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		992	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		993	}
		994
		995	# set-cookie processing
		996	if ($arg{cookie_jar}) {
		997	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		998	}
		999
		1000	if ($redirect && exists $hdr{location}) {
		1001	# we ignore any errors, as it is very common to receive
		1002	# Content-Length != 0 but no actual body
		1003	# we also access %hdr, as $_[1] might be an erro
		1004	$state{recurse} =
		1005	http_request (
		1006	$method => $hdr{location},
		1007	%arg,
		1008	recurse => $recurse - 1,
		1009	Redirect => [$_[0], \%hdr],
		1010	sub {
		1011	%state = ();
		1012	&$cb
		1013	},
		1014	);
		1015	} else {
		1016	$cb->($_[0], \%hdr);
		1017	}
		1018	};
		1019
		1020	$ae_error = 597; # body phase
		1021
		1022	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		1023
		1024	my $len = $chunked ? undef : $hdr{"content-length"};
		1025
		1026	# body handling, many different code paths
		1027	# - no body expected
		1028	# - want_body_handle
		1029	# - te chunked
		1030	# - 2x length known (with or without on_body)
		1031	# - 2x length not known (with or without on_body)
		1032	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		1033	$finish->(undef, 598 => "Request cancelled by on_header");
		1034	} elsif (
		1035	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		1036	or $method eq "HEAD"
		1037	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		1038	) {
		1039	# no body
		1040	$finish->("", undef, undef, 1);
		1041
		1042	} elsif (!$redirect && $arg{want_body_handle}) {
		1043	$_[0]->on_eof (undef);
		1044	$_[0]->on_error (undef);
		1045	$_[0]->on_read (undef);
		1046
		1047	$finish->(delete $state{handle});
		1048
		1049	} elsif ($chunked) {
		1050	my $cl = 0;
		1051	my $body = "";
		1052	my $on_body = (!$redirect && $arg{on_body}) \|\| sub { $body .= shift; 1 };
		1053
		1054	$state{read_chunk} = sub {
		1055	$_[1] =~ /^([0-9a-fA-F]+)/
		1056	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1057
		1058	my $len = hex $1;
		1059
		1060	if ($len) {
		1061	$cl += $len;
		1062
		1063	$_[0]->push_read (chunk => $len, sub {
		1064	$on_body->($_[1], \%hdr)
		1065	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1066
		1067	$_[0]->push_read (line => sub {
		1068	length $_[1]
		1069	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1070	$_[0]->push_read (line => $state{read_chunk});
		1071	});
		1072	});
		1073	} else {
		1074	$hdr{"content-length"} \|\|= $cl;
		1075
		1076	$_[0]->push_read (line => $qr_nlnl, sub {
		1077	if (length $_[1]) {
		1078	for ("$_[1]") {
		1079	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		1080
		1081	my $hdr = _parse_hdr
		1082	or return $finish->(undef, $ae_error => "Garbled response trailers");
		1083
		1084	%hdr = (%hdr, %$hdr);
		1085	}
		1086	}
		1087
		1088	$finish->($body, undef, undef, 1);
		1089	});
		1090	}
		1091	};
		1092
		1093	$_[0]->push_read (line => $state{read_chunk});
		1094
		1095	} elsif (!$redirect && $arg{on_body}) {
		1096	if (defined $len) {
		1097	$_[0]->on_read (sub {
		1098	$len -= length $_[0]{rbuf};
		1099
		1100	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1101	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1102
		1103	$len > 0
		1104	or $finish->("", undef, undef, 1);
		1105	});
		1106	} else {
		1107	$_[0]->on_eof (sub {
		1108	$finish->("");
		1109	});
		1110	$_[0]->on_read (sub {
		1111	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1112	or $finish->(undef, 598 => "Request cancelled by on_body");
		1113	});
		1114	}
		1115	} else {
		1116	$_[0]->on_eof (undef);
		1117
		1118	if (defined $len) {
		1119	$_[0]->on_read (sub {
		1120	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1121	if $len <= length $_[0]{rbuf};
		1122	});
		1123	} else {
		1124	$_[0]->on_error (sub {
		1125	($! == Errno::EPIPE \|\| !$!)
		1126	? $finish->(delete $_[0]{rbuf})
		1127	: $finish->(undef, $ae_error => $_[2]);
		1128	});
		1129	$_[0]->on_read (sub { });
		1130	}
		1131	}
		1132	};
		1133
		1134	# if keepalive is enabled, then the server closing the connection
		1135	# before a response can happen legally - we retry on idempotent methods.
		1136	if ($was_persistent && $idempotent) {
		1137	my $old_eof = $hdl->{on_eof};
		1138	$hdl->{on_eof} = sub {
		1139	_destroy_state %state;
		1140
		1141	%state = ();
		1142	$state{recurse} =
		1143	http_request (
		1144	$method => $url,
		1145	%arg,
		1146	recurse => $recurse - 1,
		1147	persistent => 0,
		1148	sub {
		1149	%state = ();
		1150	&$cb
		1151	}
		1152	);
		1153	};
		1154	$hdl->on_read (sub {
		1155	return unless %state;
		1156
		1157	# as soon as we receive something, a connection close
		1158	# once more becomes a hard error
		1159	$hdl->{on_eof} = $old_eof;
		1160	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1161	});
		1162	} else {
		1163	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1164	}
		1165	};
		1166
		1167	my $prepare_handle = sub {
		1168	my ($hdl) = $state{handle};
		1169
		1170	$hdl->on_error (sub {
		1171	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1172	});
		1173	$hdl->on_eof (sub {
		1174	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1175	});
		1176	$hdl->timeout_reset;
		1177	$hdl->timeout ($timeout);
		1178	};
		1179
		1180	# connected to proxy (or origin server)
		1181	my $connect_cb = sub {
		1182	my $fh = shift
		1183	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1184
		1185	return unless delete $state{connect_guard};
		1186
		1187	# get handle
		1188	$state{handle} = new AnyEvent::Handle
		1189	%{ $arg{handle_params} },
		1190	fh => $fh,
		1191	peername => $uhost,
		1192	tls_ctx => $arg{tls_ctx},
		1193	;
		1194
		1195	$prepare_handle->();
		1196
		1197	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1198
		1199	# now handle proxy-CONNECT method
		1200	if ($proxy && $uscheme eq "https") {
		1201	# oh dear, we have to wrap it into a connect request
		1202
		1203	my $auth = exists $hdr{"proxy-authorization"}
		1204	? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012"
		1205	: "";
		1206
		1207	# maybe re-use $uauthority with patched port?
		1208	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012");
		1209	$state{handle}->push_read (line => $qr_nlnl, sub {
		1210	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1211	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1212
		1213	if ($2 == 200) {
		1214	$rpath = $upath;
		1215	$handle_actual_request->();
		1216	} else {
		1217	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1218	}
		1219	});
		1220	} else {
		1221	delete $hdr{"proxy-authorization"} unless $proxy;
		1222
		1223	$handle_actual_request->();
		1224	}
		1225	};
453		1226
454	_get_slot $uhost, sub {	1227	_get_slot $uhost, sub {
455	$state{slot_guard} = shift;	1228	$state{slot_guard} = shift;
456		1229
457	return unless $state{connect_guard};	1230	return unless $state{connect_guard};
458		1231
459	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	1232	# try to use an existing keepalive connection, but only if we, ourselves, plan
460	$state{fh} = shift	1233	# on a keepalive request (in theory, this should be a separate config option).
461	or do {	1234	if ($persistent && $KA_CACHE{$ka_key}) {
462	my $err = "$!";	1235	$was_persistent = 1;
463	%state = ();
464	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
465	};
466		1236
467	pop; # free memory, save a tree	1237	$state{handle} = ka_fetch $ka_key;
468		1238	# $state{handle}->destroyed
469	return unless delete $state{connect_guard};	1239	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
470		1240	$prepare_handle->();
471	# get handle	1241	# $state{handle}->destroyed
472	$state{handle} = new AnyEvent::Handle	1242	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
473	fh => $state{fh},
474	peername => $rhost,
475	tls_ctx => $arg{tls_ctx},
476	# these need to be reconfigured on keepalive handles
477	timeout => $timeout,
478	on_error => sub {
479	%state = ();
480	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
481	},
482	on_eof => sub {
483	%state = ();
484	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
485	},
486	;
487
488	# limit the number of persistent connections
489	# keepalive not yet supported
490	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
491	# ++$KA_COUNT{$_[1]};
492	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
493	# --$KA_COUNT{$_[1]}
494	# };
495	# $hdr{connection} = "keep-alive";
496	# } else {
497	delete $hdr{connection};
498	# }
499
500	$state{handle}->starttls ("connect") if $rscheme eq "https";
501
502	# handle actual, non-tunneled, request
503	my $handle_actual_request = sub {
504	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
505
506	# send request
507	$state{handle}->push_write (
508	"$method $rpath HTTP/1.0\015\012"
509	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
510	. "\015\012"
511	. (delete $arg{body})
512	);
513
514	# return if error occured during push_write()
515	return unless %state;
516
517	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
518
519	# status line and headers
520	$state{handle}->push_read (line => $qr_nlnl, sub {
521	for ("$_[1]") {
522	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
523
524	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
525	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
526
527	push @pseudo,
528	HTTPVersion => $1,
529	Status => $2,
530	Reason => $3,
531	;
532
533	# things seen, not parsed:
534	# p3pP="NON CUR OTPi OUR NOR UNI"
535
536	$hdr{lc $1} .= ",$2"
537	while /\G
538	([^:\000-\037]*):
539	[\011\040]*
540	((?: [^\012]+ \| \012[\011\040] )*)
541	\012
542	/gxc;
543
544	/\G$/
545	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
546	}
547
548	# remove the "," prefix we added to all headers above
549	substr $_, 0, 1, ""
550	for values %hdr;
551
552	# patch in all pseudo headers
553	%hdr = (%hdr, @pseudo);
554
555	# redirect handling
556	# microsoft and other shitheads don't give a shit for following standards,
557	# try to support some common forms of broken Location headers.
558	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
559	$hdr{location} =~ s/^\.\/+//;
560
561	my $url = "$rscheme://$uhost:$uport";
562
563	unless ($hdr{location} =~ s/^\///) {
564	$url .= $upath;
565	$url =~ s/\/[^\/]*$//;
566	}
567
568	$hdr{location} = "$url/$hdr{location}";
569	}
570
571	my $redirect;
572
573	if ($recurse) {
574	my $status = $hdr{Status};
575
576	# industry standard is to redirect POST as GET for
577	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
578	# also, the UA should ask the user for 301 and 307 and POST,
579	# industry standard seems to be to simply follow.
580	# we go with the industry standard.
581	if ($status == 301 or $status == 302 or $status == 303) {
582	# HTTP/1.1 is unclear on how to mutate the method
583	$method = "GET" unless $method eq "HEAD";
584	$redirect = 1;
585	} elsif ($status == 307) {
586	$redirect = 1;
587	}
588	}
589
590	my $finish = sub {
591	$state{handle}->destroy if $state{handle};
592	%state = ();
593
594	# set-cookie processing
595	if ($arg{cookie_jar}) {
596	for ($_[1]{"set-cookie"}) {
597	# parse NAME=VALUE
598	my @kv;
599
600	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
601	my $name = $1;
602	my $value = $3;
603
604	unless ($value) {
605	$value = $2;
606	$value =~ s/\\(.)/$1/gs;
607	}
608
609	push @kv, $name => $value;
610
611	last unless /\G\s*;/gc;
612	}
613
614	last unless @kv;
615
616	my $name = shift @kv;
617	my %kv = (value => shift @kv, @kv);
618
619	my $cdom;
620	my $cpath = (delete $kv{path}) \|\| "/";
621
622	if (exists $kv{domain}) {
623	$cdom = delete $kv{domain};
624
625	$cdom =~ s/^\.?/./; # make sure it starts with a "."
626
627	next if $cdom =~ /\.$/;
628
629	# this is not rfc-like and not netscape-like. go figure.
630	my $ndots = $cdom =~ y/.//;
631	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
632	} else {
633	$cdom = $uhost;
634	}
635
636	# store it
637	$arg{cookie_jar}{version} = 1;
638	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
639
640	redo if /\G\s*,/gc;
641	}
642	}
643
644	if ($redirect && exists $hdr{location}) {
645	# we ignore any errors, as it is very common to receive
646	# Content-Length != 0 but no actual body
647	# we also access %hdr, as $_[1] might be an erro
648	http_request (
649	$method => $hdr{location},
650	%arg,
651	recurse => $recurse - 1,
652	Redirect => \@_,
653	$cb);
654	} else {
655	$cb->($_[0], $_[1]);
656	}
657	};
658
659	my $len = $hdr{"content-length"};
660
661	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
662	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
663	} elsif (
664	$hdr{Status} =~ /^(?:1..\|[23]04)$/
665	or $method eq "HEAD"
666	or (defined $len && !$len)
667	) {
668	# no body
669	$finish->("", \%hdr);
670	} else {
671	# body handling, four different code paths
672	# for want_body_handle, on_body (2x), normal (2x)
673	# we might read too much here, but it does not matter yet (no pers. connections)
674	if (!$redirect && $arg{want_body_handle}) {
675	$_[0]->on_eof (undef);
676	$_[0]->on_error (undef);
677	$_[0]->on_read (undef);
678
679	$finish->(delete $state{handle}, \%hdr);
680
681	} elsif ($arg{on_body}) {
682	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
683	if ($len) {
684	$_[0]->on_eof (undef);
685	$_[0]->on_read (sub {
686	$len -= length $_[0]{rbuf};
687
688	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
689	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
690
691	$len > 0
692	or $finish->("", \%hdr);
693	});
694	} else {
695	$_[0]->on_eof (sub {
696	$finish->("", \%hdr);
697	});
698	$_[0]->on_read (sub {
699	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
700	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
701	});
702	}
703	} else {
704	$_[0]->on_eof (undef);
705
706	if ($len) {
707	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
708	$_[0]->on_read (sub {
709	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
710	if $len <= length $_[0]{rbuf};
711	});
712	} else {
713	$_[0]->on_error (sub {
714	($! == Errno::EPIPE \|\| !$!)
715	? $finish->(delete $_[0]{rbuf}, \%hdr)
716	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
717	});
718	$_[0]->on_read (sub { });
719	}
720	}
721	}
722	});
723	};
724
725	# now handle proxy-CONNECT method
726	if ($proxy && $uscheme eq "https") {
727	# oh dear, we have to wrap it into a connect request
728
729	# maybe re-use $uauthority with patched port?
730	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
731	$state{handle}->push_read (line => $qr_nlnl, sub {
732	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
733	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
734
735	if ($2 == 200) {
736	$rpath = $upath;	1243	$rpath = $upath;
737	&$handle_actual_request;	1244	$handle_actual_request->();
738	} else {	1245
739	%state = ();
740	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
741	}
742	});
743	} else {	1246	} else {
744	&$handle_actual_request;	1247	my $tcp_connect = $arg{tcp_connect}
		1248	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		1249
		1250	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
745	}	1251	}
746
747	}, $arg{on_prepare} \|\| sub { $timeout };
748	};	1252	};
749		1253
750	defined wantarray && AnyEvent::Util::guard { %state = () }	1254	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
751	}	1255	}
752		1256
753	sub http_get($@) {	1257	sub http_get($@) {
754	unshift @_, "GET";	1258	unshift @_, "GET";
755	&http_request	1259	&http_request
…		…
773	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1277	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
774	the actual connection, which in turn uses AnyEvent::DNS to resolve	1278	the actual connection, which in turn uses AnyEvent::DNS to resolve
775	hostnames. The latter is a simple stub resolver and does no caching	1279	hostnames. The latter is a simple stub resolver and does no caching
776	on its own. If you want DNS caching, you currently have to provide	1280	on its own. If you want DNS caching, you currently have to provide
777	your own default resolver (by storing a suitable resolver object in	1281	your own default resolver (by storing a suitable resolver object in
778	C<$AnyEvent::DNS::RESOLVER>).	1282	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
779		1283
780	=head2 GLOBAL FUNCTIONS AND VARIABLES	1284	=head2 GLOBAL FUNCTIONS AND VARIABLES
781		1285
782	=over 4	1286	=over 4
783		1287
784	=item AnyEvent::HTTP::set_proxy "proxy-url"	1288	=item AnyEvent::HTTP::set_proxy "proxy-url"
785		1289
786	Sets the default proxy server to use. The proxy-url must begin with a	1290	Sets the default proxy server to use. The proxy-url must begin with a
787	string of the form C<http://host:port> (optionally C<https:...>), croaks	1291	string of the form C<http://host:port>, croaks otherwise.
788	otherwise.
789		1292
790	To clear an already-set proxy, use C<undef>.	1293	To clear an already-set proxy, use C<undef>.
791		1294
		1295	When AnyEvent::HTTP is loaded for the first time it will query the
		1296	default proxy from the operating system, currently by looking at
		1297	C<$ENV{http_proxy>}.
		1298
		1299	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1300
		1301	Remove all cookies from the cookie jar that have been expired. If
		1302	C<$session_end> is given and true, then additionally remove all session
		1303	cookies.
		1304
		1305	You should call this function (with a true C<$session_end>) before you
		1306	save cookies to disk, and you should call this function after loading them
		1307	again. If you have a long-running program you can additionally call this
		1308	function from time to time.
		1309
		1310	A cookie jar is initially an empty hash-reference that is managed by this
		1311	module. Its format is subject to change, but currently it is as follows:
		1312
		1313	The key C<version> has to contain C<2>, otherwise the hash gets
		1314	cleared. All other keys are hostnames or IP addresses pointing to
		1315	hash-references. The key for these inner hash references is the
		1316	server path for which this cookie is meant, and the values are again
		1317	hash-references. Each key of those hash-references is a cookie name, and
		1318	the value, you guessed it, is another hash-reference, this time with the
		1319	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1320	which have been replaced by a C<_expires> key that contains the cookie
		1321	expiry timestamp. Session cookies are indicated by not having an
		1322	C<_expires> key.
		1323
		1324	Here is an example of a cookie jar with a single cookie, so you have a
		1325	chance of understanding the above paragraph:
		1326
		1327	{
		1328	version => 2,
		1329	"10.0.0.1" => {
		1330	"/" => {
		1331	"mythweb_id" => {
		1332	_expires => 1293917923,
		1333	value => "ooRung9dThee3ooyXooM1Ohm",
		1334	},
		1335	},
		1336	},
		1337	}
		1338
		1339	=item $date = AnyEvent::HTTP::format_date $timestamp
		1340
		1341	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1342	Date (RFC 2616).
		1343
		1344	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1345
		1346	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1347	bunch of minor variations of those, and returns the corresponding POSIX
		1348	timestamp, or C<undef> if the date cannot be parsed.
		1349
792	=item $AnyEvent::HTTP::MAX_RECURSE	1350	=item $AnyEvent::HTTP::MAX_RECURSE
793		1351
794	The default value for the C<recurse> request parameter (default: C<10>).	1352	The default value for the C<recurse> request parameter (default: C<10>).
		1353
		1354	=item $AnyEvent::HTTP::TIMEOUT
		1355
		1356	The default timeout for connection operations (default: C<300>).
795		1357
796	=item $AnyEvent::HTTP::USERAGENT	1358	=item $AnyEvent::HTTP::USERAGENT
797		1359
798	The default value for the C<User-Agent> header (the default is	1360	The default value for the C<User-Agent> header (the default is
799	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1361	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
800		1362
801	=item $AnyEvent::HTTP::MAX_PER_HOST	1363	=item $AnyEvent::HTTP::MAX_PER_HOST
802		1364
803	The maximum number of concurrent connections to the same host (identified	1365	The maximum number of concurrent connections to the same host (identified
804	by the hostname). If the limit is exceeded, then the additional requests	1366	by the hostname). If the limit is exceeded, then additional requests
805	are queued until previous connections are closed.	1367	are queued until previous connections are closed. Both persistent and
		1368	non-persistent connections are counted in this limit.
806		1369
807	The default value for this is C<4>, and it is highly advisable to not	1370	The default value for this is C<4>, and it is highly advisable to not
808	increase it.	1371	increase it much.
		1372
		1373	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1374	connections, older browsers used 2, newer ones (such as firefox 3)
		1375	typically use 6, and Opera uses 8 because like, they have the fastest
		1376	browser and give a shit for everybody else on the planet.
		1377
		1378	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1379
		1380	The time after which idle persistent connections get closed by
		1381	AnyEvent::HTTP (default: C<3>).
809		1382
810	=item $AnyEvent::HTTP::ACTIVE	1383	=item $AnyEvent::HTTP::ACTIVE
811		1384
812	The number of active connections. This is not the number of currently	1385	The number of active connections. This is not the number of currently
813	running requests, but the number of currently open and non-idle TCP	1386	running requests, but the number of currently open and non-idle TCP
814	connections. This number of can be useful for load-leveling.	1387	connections. This number can be useful for load-leveling.
815		1388
816	=back	1389	=back
817		1390
818	=cut	1391	=cut
		1392
		1393	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1394	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1395
		1396	sub format_date($) {
		1397	my ($time) = @_;
		1398
		1399	# RFC 822/1123 format
		1400	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1401
		1402	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1403	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1404	$H, $M, $S;
		1405	}
		1406
		1407	sub parse_date($) {
		1408	my ($date) = @_;
		1409
		1410	my ($d, $m, $y, $H, $M, $S);
		1411
		1412	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$/) {
		1413	# RFC 822/1123, required by RFC 2616 (with " ")
		1414	# cookie dates (with "-")
		1415
		1416	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1417
		1418	} 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$/) {
		1419	# RFC 850
		1420	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1421
		1422	} 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])$/) {
		1423	# ISO C's asctime
		1424	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1425	}
		1426	# other formats fail in the loop below
		1427
		1428	for (0..11) {
		1429	if ($m eq $month[$_]) {
		1430	require Time::Local;
		1431	return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) };
		1432	}
		1433	}
		1434
		1435	undef
		1436	}
819		1437
820	sub set_proxy($) {	1438	sub set_proxy($) {
821	if (length $_[0]) {	1439	if (length $_[0]) {
822	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1440	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
823	or Carp::croak "$_[0]: invalid proxy URL";	1441	or Carp::croak "$_[0]: invalid proxy URL";
824	$PROXY = [$2, $3 \|\| 3128, $1]	1442	$PROXY = [$2, $3 \|\| 3128, $1]
825	} else {	1443	} else {
826	undef $PROXY;	1444	undef $PROXY;
827	}	1445	}
…		…
830	# initialise proxy from environment	1448	# initialise proxy from environment
831	eval {	1449	eval {
832	set_proxy $ENV{http_proxy};	1450	set_proxy $ENV{http_proxy};
833	};	1451	};
834		1452
		1453	=head2 SHOWCASE
		1454
		1455	This section contains some more elaborate "real-world" examples or code
		1456	snippets.
		1457
		1458	=head2 HTTP/1.1 FILE DOWNLOAD
		1459
		1460	Downloading files with HTTP can be quite tricky, especially when something
		1461	goes wrong and you want to resume.
		1462
		1463	Here is a function that initiates and resumes a download. It uses the
		1464	last modified time to check for file content changes, and works with many
		1465	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1466	on older servers.
		1467
		1468	It calls the completion callback with either C<undef>, which means a
		1469	nonretryable error occurred, C<0> when the download was partial and should
		1470	be retried, and C<1> if it was successful.
		1471
		1472	use AnyEvent::HTTP;
		1473
		1474	sub download($$$) {
		1475	my ($url, $file, $cb) = @_;
		1476
		1477	open my $fh, "+<", $file
		1478	or die "$file: $!";
		1479
		1480	my %hdr;
		1481	my $ofs = 0;
		1482
		1483	if (stat $fh and -s _) {
		1484	$ofs = -s _;
		1485	warn "-s is ", $ofs;
		1486	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1487	$hdr{"range"} = "bytes=$ofs-";
		1488	}
		1489
		1490	http_get $url,
		1491	headers => \%hdr,
		1492	on_header => sub {
		1493	my ($hdr) = @_;
		1494
		1495	if ($hdr->{Status} == 200 && $ofs) {
		1496	# resume failed
		1497	truncate $fh, $ofs = 0;
		1498	}
		1499
		1500	sysseek $fh, $ofs, 0;
		1501
		1502	1
		1503	},
		1504	on_body => sub {
		1505	my ($data, $hdr) = @_;
		1506
		1507	if ($hdr->{Status} =~ /^2/) {
		1508	length $data == syswrite $fh, $data
		1509	or return; # abort on write errors
		1510	}
		1511
		1512	1
		1513	},
		1514	sub {
		1515	my (undef, $hdr) = @_;
		1516
		1517	my $status = $hdr->{Status};
		1518
		1519	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1520	utime $time, $time, $fh;
		1521	}
		1522
		1523	if ($status == 200 \|\| $status == 206 \|\| $status == 416) {
		1524	# download ok \|\| resume ok \|\| file already fully downloaded
		1525	$cb->(1, $hdr);
		1526
		1527	} elsif ($status == 412) {
		1528	# file has changed while resuming, delete and retry
		1529	unlink $file;
		1530	$cb->(0, $hdr);
		1531
		1532	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1533	# retry later
		1534	$cb->(0, $hdr);
		1535
		1536	} else {
		1537	$cb->(undef, $hdr);
		1538	}
		1539	}
		1540	;
		1541	}
		1542
		1543	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1544	if ($_[0]) {
		1545	print "OK!\n";
		1546	} elsif (defined $_[0]) {
		1547	print "please retry later\n";
		1548	} else {
		1549	print "ERROR\n";
		1550	}
		1551	};
		1552
		1553	=head3 SOCKS PROXIES
		1554
		1555	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1556	compile your perl to support socks, or use an external program such as
		1557	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1558	transparently.
		1559
		1560	Alternatively, for AnyEvent::HTTP only, you can use your own
		1561	C<tcp_connect> function that does the proxy handshake - here is an example
		1562	that works with socks4a proxies:
		1563
		1564	use Errno;
		1565	use AnyEvent::Util;
		1566	use AnyEvent::Socket;
		1567	use AnyEvent::Handle;
		1568
		1569	# host, port and username of/for your socks4a proxy
		1570	my $socks_host = "10.0.0.23";
		1571	my $socks_port = 9050;
		1572	my $socks_user = "";
		1573
		1574	sub socks4a_connect {
		1575	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1576
		1577	my $hdl = new AnyEvent::Handle
		1578	connect => [$socks_host, $socks_port],
		1579	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1580	on_error => sub { $connect_cb->() },
		1581	;
		1582
		1583	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1584
		1585	$hdl->push_read (chunk => 8, sub {
		1586	my ($hdl, $chunk) = @_;
		1587	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1588
		1589	if ($status == 0x5a) {
		1590	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1591	} else {
		1592	$! = Errno::ENXIO; $connect_cb->();
		1593	}
		1594	});
		1595
		1596	$hdl
		1597	}
		1598
		1599	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1600	possibly after switching off other proxy types:
		1601
		1602	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1603
		1604	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1605	my ($data, $headers) = @_;
		1606	...
		1607	};
		1608
835	=head1 SEE ALSO	1609	=head1 SEE ALSO
836		1610
837	L<AnyEvent>.	1611	L<AnyEvent>.
838		1612
839	=head1 AUTHOR	1613	=head1 AUTHOR

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.58 by root, Sun Nov 14 20:23:00 2010 UTC vs. Revision 1.137 by root, Mon Apr 27 12:14:12 2020 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.58 by root, Sun Nov 14 20:23:00 2010 UTC vs.
Revision 1.137 by root, Mon Apr 27 12:14:12 2020 UTC