ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.67 by root, Fri Dec 31 06:18:54 2010 UTC vs.
Revision 1.102 by root, Sat Feb 19 06:46:14 2011 UTC

…		…
15	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
16	run a supported event loop.	16	run a supported event loop.
17		17
18	This module implements a simple, stateless and non-blocking HTTP	18	This module implements a simple, stateless and non-blocking HTTP
19	client. It supports GET, POST and other request methods, cookies and more,	19	client. It supports GET, POST and other request methods, cookies and more,
20	all on a very low level. It can follow redirects supports proxies and	20	all on a very low level. It can follow redirects, supports proxies, and
21	automatically limits the number of connections to the values specified in	21	automatically limits the number of connections to the values specified in
22	the RFC.	22	the RFC.
23		23
24	It should generally be a "good client" that is enough for most HTTP	24	It should generally be a "good client" that is enough for most HTTP
25	tasks. Simple tasks should be simple, but complex tasks should still be	25	tasks. Simple tasks should be simple, but complex tasks should still be
…		…
36		36
37	=cut	37	=cut
38		38
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use common::sense;
42	no warnings;
43		42
44	use Errno ();	43	use Errno ();
45		44
46	use AnyEvent 5.0 ();	45	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	46	use AnyEvent::Util ();
48	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
49		48
50	use base Exporter::;	49	use base Exporter::;
51		50
52	our $VERSION = '1.5';	51	our $VERSION = '2.04';
53		52
54	our @EXPORT = qw(http_get http_post http_head http_request);	53	our @EXPORT = qw(http_get http_post http_head http_request);
55		54
56	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)";
57	our $MAX_RECURSE = 10;	56	our $MAX_RECURSE = 10;
58	our $MAX_PERSISTENT = 8;
59	our $PERSISTENT_TIMEOUT = 2;	57	our $PERSISTENT_TIMEOUT = 3;
60	our $TIMEOUT = 300;	58	our $TIMEOUT = 300;
61		59	our $MAX_PER_HOST = 4; # changing this is evil
62	# changing these is evil
63	our $MAX_PERSISTENT_PER_HOST = 0;
64	our $MAX_PER_HOST = 4;
65		60
66	our $PROXY;	61	our $PROXY;
67	our $ACTIVE = 0;	62	our $ACTIVE = 0;
68		63
69	my %KA_COUNT; # number of open keep-alive connections per host	64	my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array
70	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
71		66
72	=item http_get $url, key => value..., $cb->($data, $headers)	67	=item http_get $url, key => value..., $cb->($data, $headers)
73		68
74	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
…		…
94	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
95	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
96	destroyed before the callback is called, the request will be cancelled.	91	destroyed before the callback is called, the request will be cancelled.
97		92
98	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
99	(or C<undef> if an error occured), and a hash-ref with response headers as	94	(or C<undef> if an error occured), and a hash-ref with response headers
100	second argument.	95	(and trailers) as second argument.
101		96
102	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
103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible	98	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the	99	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	three parts of the HTTP Status-Line of the same name. If an error occurs	100	three parts of the HTTP Status-Line of the same name. If an error occurs
…		…
122		117
123	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
124	joined together with a comma (C<,>), as per the HTTP spec.	119	joined together with a comma (C<,>), as per the HTTP spec.
125		120
126	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,
127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>	122	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
128	(usually C<599>) and the C<Reason> pseudo-header will contain an error	123	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
129	message.	124	message. Currently the following status codes are used:
		125
		126	=over 4
		127
		128	=item 595 - errors during connection etsbalishment, proxy handshake.
		129
		130	=item 596 - errors during TLS negotiation, request sending and header processing.
		131
		132	=item 597 - errors during body receiving or processing.
		133
		134	=item 598 - user aborted request via C<on_header> or C<on_body>.
		135
		136	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		137
		138	=back
130		139
131	A typical callback might look like this:	140	A typical callback might look like this:
132		141
133	sub {	142	sub {
134	my ($body, $hdr) = @_;	143	my ($body, $hdr) = @_;
…		…
150	Whether to recurse requests or not, e.g. on redirects, authentication	159	Whether to recurse requests or not, e.g. on redirects, authentication
151	retries and so on, and how often to do so.	160	retries and so on, and how often to do so.
152		161
153	=item headers => hashref	162	=item headers => hashref
154		163
155	The request headers to use. Currently, C<http_request> may provide its	164	The request headers to use. Currently, C<http_request> may provide its own
156	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	165	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
157	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be	166	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
158	suppressed by using C<undef> for these headers in which case they won't be	167	(this can be suppressed by using C<undef> for these headers in which case
159	sent at all).	168	they won't be sent at all).
		169
		170	You really should provide your own C<User-Agent:> header value that is
		171	appropriate for your program - I wouldn't be surprised if the default
		172	AnyEvent string gets blocked by webservers sooner or later.
160		173
161	=item timeout => $seconds	174	=item timeout => $seconds
162		175
163	The time-out to use for various stages - each connect attempt will reset	176	The time-out to use for various stages - each connect attempt will reset
164	the timeout, as will read or write activity, i.e. this is not an overall	177	the timeout, as will read or write activity, i.e. this is not an overall
…		…
166		179
167	Default timeout is 5 minutes.	180	Default timeout is 5 minutes.
168		181
169	=item proxy => [$host, $port[, $scheme]] or undef	182	=item proxy => [$host, $port[, $scheme]] or undef
170		183
171	Use the given http proxy for all requests. If not specified, then the	184	Use the given http proxy for all requests, or no proxy if C<undef> is
172	default proxy (as specified by C<$ENV{http_proxy}>) is used.	185	used.
173		186
174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	187	C<$scheme> must be either missing or must be C<http> for HTTP.
175	HTTPS.	188
		189	If not specified, then the default proxy is used (see
		190	C<AnyEvent::HTTP::set_proxy>).
176		191
177	=item body => $string	192	=item body => $string
178		193
179	The request body, usually empty. Will be-sent as-is (future versions of	194	The request body, usually empty. Will be sent as-is (future versions of
180	this module might offer more options).	195	this module might offer more options).
181		196
182	=item cookie_jar => $hash_ref	197	=item cookie_jar => $hash_ref
183		198
184	Passing this parameter enables (simplified) cookie-processing, loosely	199	Passing this parameter enables (simplified) cookie-processing, loosely
185	based on the original netscape specification.	200	based on the original netscape specification.
186		201
187	The C<$hash_ref> must be an (initially empty) hash reference which will	202	The C<$hash_ref> must be an (initially empty) hash reference which
188	get updated automatically. It is possible to save the cookie_jar to	203	will get updated automatically. It is possible to save the cookie jar
189	persistent storage with something like JSON or Storable, but this is not	204	to persistent storage with something like JSON or Storable - see the
190	recommended, as expiry times are currently being ignored.	205	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		206	expired or session-only cookies, and also for documentation on the format
		207	of the cookie jar.
191		208
192	Note that this cookie implementation is not of very high quality, nor	209	Note that this cookie implementation is not meant to be complete. If
193	meant to be complete. If you want complete cookie management you have to	210	you want complete cookie management you have to do that on your
194	do that on your own. C<cookie_jar> is meant as a quick fix to get some	211	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
195	cookie-using sites working. Cookies are a privacy disaster, do not use	212	working. Cookies are a privacy disaster, do not use them unless required
196	them unless required to.	213	to.
		214
		215	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		216	headers will be set and handled by this module, otherwise they will be
		217	left untouched.
197		218
198	=item tls_ctx => $scheme | $tls_ctx	219	=item tls_ctx => $scheme | $tls_ctx
199		220
200	Specifies the AnyEvent::TLS context to be used for https connections. This	221	Specifies the AnyEvent::TLS context to be used for https connections. This
201	parameter follows the same rules as the C<tls_ctx> parameter to	222	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
205	verification) TLS context.	226	verification) TLS context.
206		227
207	The default for this option is C<low>, which could be interpreted as "give	228	The default for this option is C<low>, which could be interpreted as "give
208	me the page, no matter what".	229	me the page, no matter what".
209		230
		231	See also the C<sessionid> parameter.
		232
		233	=item session => $string
		234
		235	The module might reuse connections to the same host internally. Sometimes
		236	(e.g. when using TLS), you do not want to reuse connections from other
		237	sessions. This can be achieved by setting this parameter to some unique
		238	ID (such as the address of an object storing your state data, or the TLS
		239	context) - only connections using the same unique ID will be reused.
		240
210	=item on_prepare => $callback->($fh)	241	=item on_prepare => $callback->($fh)
211		242
212	In rare cases you need to "tune" the socket before it is used to	243	In rare cases you need to "tune" the socket before it is used to
213	connect (for exmaple, to bind it on a given IP address). This parameter	244	connect (for exmaple, to bind it on a given IP address). This parameter
214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>	245	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
…		…
240		271
241	This callback is useful, among other things, to quickly reject unwanted	272	This callback is useful, among other things, to quickly reject unwanted
242	content, which, if it is supposed to be rare, can be faster than first	273	content, which, if it is supposed to be rare, can be faster than first
243	doing a C<HEAD> request.	274	doing a C<HEAD> request.
244		275
		276	The downside is that cancelling the request makes it impossible to re-use
		277	the connection. Also, the C<on_header> callback will not receive any
		278	trailer (headers sent after the response body).
		279
245	Example: cancel the request unless the content-type is "text/html".	280	Example: cancel the request unless the content-type is "text/html".
246		281
247	on_header => sub {	282	on_header => sub {
248	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/	283	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/
249	},	284	},
…		…
255	string instead of the body data.	290	string instead of the body data.
256		291
257	It has to return either true (in which case AnyEvent::HTTP will continue),	292	It has to return either true (in which case AnyEvent::HTTP will continue),
258	or false, in which case AnyEvent::HTTP will cancel the download (and call	293	or false, in which case AnyEvent::HTTP will cancel the download (and call
259	the completion callback with an error code of C<598>).	294	the completion callback with an error code of C<598>).
		295
		296	The downside to cancelling the request is that it makes it impossible to
		297	re-use the connection.
260		298
261	This callback is useful when the data is too large to be held in memory	299	This callback is useful when the data is too large to be held in memory
262	(so the callback writes it to a file) or when only some information should	300	(so the callback writes it to a file) or when only some information should
263	be extracted, or when the body should be processed incrementally.	301	be extracted, or when the body should be processed incrementally.
264		302
…		…
276	called. Instead of the C<$body> argument containing the body data, the	314	called. Instead of the C<$body> argument containing the body data, the
277	callback will receive the L<AnyEvent::Handle> object associated with the	315	callback will receive the L<AnyEvent::Handle> object associated with the
278	connection. In error cases, C<undef> will be passed. When there is no body	316	connection. In error cases, C<undef> will be passed. When there is no body
279	(e.g. status C<304>), the empty string will be passed.	317	(e.g. status C<304>), the empty string will be passed.
280		318
281	The handle object might or might not be in TLS mode, might be connected to	319	The handle object might or might not be in TLS mode, might be connected
282	a proxy, be a persistent connection etc., and configured in unspecified	320	to a proxy, be a persistent connection, use chunked transfer encoding
283	ways. The user is responsible for this handle (it will not be used by this	321	etc., and configured in unspecified ways. The user is responsible for this
284	module anymore).	322	handle (it will not be used by this module anymore).
285		323
286	This is useful with some push-type services, where, after the initial	324	This is useful with some push-type services, where, after the initial
287	headers, an interactive protocol is used (typical example would be the	325	headers, an interactive protocol is used (typical example would be the
288	push-style twitter API which starts a JSON/XML stream).	326	push-style twitter API which starts a JSON/XML stream).
289		327
290	If you think you need this, first have a look at C<on_body>, to see if	328	If you think you need this, first have a look at C<on_body>, to see if
291	that doesn't solve your problem in a better way.	329	that doesn't solve your problem in a better way.
292		330
		331	=item persistent => $boolean
		332
		333	Try to create/reuse a persistent connection. When this flag is set
		334	(default: true for idempotent requests, false for all others), then
		335	C<http_request> tries to re-use an existing (previously-created)
		336	persistent connection to the host and, failing that, tries to create a new
		337	one.
		338
		339	Requests failing in certain ways will be automatically retried once, which
		340	is dangerous for non-idempotent requests, which is why it defaults to off
		341	for them. The reason for this is because the bozos who designed HTTP/1.1
		342	made it impossible to distinguish between a fatal error and a normal
		343	connection timeout, so you never know whether there was a problem with
		344	your request or not.
		345
		346	When reusing an existent connection, many parameters (such as TLS context)
		347	will be ignored. See the C<session> parameter for a workaround.
		348
		349	=item keepalive => $boolean
		350
		351	Only used when C<persistent> is also true. This parameter decides whether
		352	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		353	(as opposed to only a HTTP/1.1 persistent connection).
		354
		355	The default is true, except when using a proxy, in which case it defaults
		356	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		357
		358	=item handle_params => { key => value ... }
		359
		360	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		361	constructor that is called - not all requests will create a handle, and
		362	sometimes more than one is created, so this parameter is only good for
		363	setting hints.
		364
		365	Example: set the maximum read size to 4096, to potentially conserve memory
		366	at the cost of speed.
		367
		368	handle_params => {
		369	max_read_size => 4096,
		370	},
		371
293	=back	372	=back
294		373
295	Example: make a simple HTTP GET request for http://www.nethype.de/	374	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		375	the response body.
296		376
297	http_request GET => "http://www.nethype.de/", sub {	377	http_request GET => "http://www.nethype.de/", sub {
298	my ($body, $hdr) = @_;	378	my ($body, $hdr) = @_;
299	print "$body\n";	379	print "$body\n";
300	};	380	};
301		381
302	Example: make a HTTP HEAD request on https://www.google.com/, use a	382	Example: do a HTTP HEAD request on https://www.google.com/, use a
303	timeout of 30 seconds.	383	timeout of 30 seconds.
304		384
305	http_request	385	http_request
306	GET => "https://www.google.com",	386	GET => "https://www.google.com",
		387	headers => { "user-agent" => "MySearchClient 1.0" },
307	timeout => 30,	388	timeout => 30,
308	sub {	389	sub {
309	my ($body, $hdr) = @_;	390	my ($body, $hdr) = @_;
310	use Data::Dumper;	391	use Data::Dumper;
311	print Dumper $hdr;	392	print Dumper $hdr;
312	}	393	}
313	;	394	;
314		395
315	Example: make another simple HTTP GET request, but immediately try to	396	Example: do another simple HTTP GET request, but immediately try to
316	cancel it.	397	cancel it.
317		398
318	my $request = http_request GET => "http://www.nethype.de/", sub {	399	my $request = http_request GET => "http://www.nethype.de/", sub {
319	my ($body, $hdr) = @_;	400	my ($body, $hdr) = @_;
320	print "$body\n";	401	print "$body\n";
321	};	402	};
322		403
323	undef $request;	404	undef $request;
324		405
325	=cut	406	=cut
		407
		408	#############################################################################
		409	# wait queue/slots
326		410
327	sub _slot_schedule;	411	sub _slot_schedule;
328	sub _slot_schedule($) {	412	sub _slot_schedule($) {
329	my $host = shift;	413	my $host = shift;
330		414
…		…
352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	436	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
353		437
354	_slot_schedule $_[0];	438	_slot_schedule $_[0];
355	}	439	}
356		440
		441	#############################################################################
		442	# cookie handling
		443
		444	# expire cookies
		445	sub cookie_jar_expire($;$) {
		446	my ($jar, $session_end) = @_;
		447
		448	%$jar = () if $jar->{version} != 1;
		449
		450	my $anow = AE::now;
		451
		452	while (my ($chost, $paths) = each %$jar) {
		453	next unless ref $paths;
		454
		455	while (my ($cpath, $cookies) = each %$paths) {
		456	while (my ($cookie, $kv) = each %$cookies) {
		457	if (exists $kv->{_expires}) {
		458	delete $cookies->{$cookie}
		459	if $anow > $kv->{_expires};
		460	} elsif ($session_end) {
		461	delete $cookies->{$cookie};
		462	}
		463	}
		464
		465	delete $paths->{$cpath}
		466	unless %$cookies;
		467	}
		468
		469	delete $jar->{$chost}
		470	unless %$paths;
		471	}
		472	}
		473
		474	# extract cookies from jar
		475	sub cookie_jar_extract($$$$) {
		476	my ($jar, $scheme, $host, $path) = @_;
		477
		478	%$jar = () if $jar->{version} != 1;
		479
		480	my @cookies;
		481
		482	while (my ($chost, $paths) = each %$jar) {
		483	next unless ref $paths;
		484
		485	if ($chost =~ /^\./) {
		486	next unless $chost eq substr $host, -length $chost;
		487	} elsif ($chost =~ /\./) {
		488	next unless $chost eq $host;
		489	} else {
		490	next;
		491	}
		492
		493	while (my ($cpath, $cookies) = each %$paths) {
		494	next unless $cpath eq substr $path, 0, length $cpath;
		495
		496	while (my ($cookie, $kv) = each %$cookies) {
		497	next if $scheme ne "https" && exists $kv->{secure};
		498
		499	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		500	delete $cookies->{$cookie};
		501	next;
		502	}
		503
		504	my $value = $kv->{value};
		505
		506	if ($value =~ /[=;,[:space:]]/) {
		507	$value =~ s/([\\"])/\\$1/g;
		508	$value = "\"$value\"";
		509	}
		510
		511	push @cookies, "$cookie=$value";
		512	}
		513	}
		514	}
		515
		516	\@cookies
		517	}
		518
		519	# parse set_cookie header into jar
		520	sub cookie_jar_set_cookie($$$$) {
		521	my ($jar, $set_cookie, $host, $date) = @_;
		522
		523	my $anow = int AE::now;
		524	my $snow; # server-now
		525
		526	for ($set_cookie) {
		527	# parse NAME=VALUE
		528	my @kv;
		529
		530	# expires is not http-compliant in the original cookie-spec,
		531	# we support the official date format and some extensions
		532	while (
		533	m{
		534	\G\s*
		535	(?:
		536	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
		537	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )?
		538	)
		539	}gcxsi
		540	) {
		541	my $name = $2;
		542	my $value = $4;
		543
		544	if (defined $1) {
		545	# expires
		546	$name = "expires";
		547	$value = $1;
		548	} elsif (defined $3) {
		549	# quoted
		550	$value = $3;
		551	$value =~ s/\\(.)/$1/gs;
		552	}
		553
		554	push @kv, @kv ? lc $name : $name, $value;
		555
		556	last unless /\G\s*;/gc;
		557	}
		558
		559	last unless @kv;
		560
		561	my $name = shift @kv;
		562	my %kv = (value => shift @kv, @kv);
		563
		564	if (exists $kv{"max-age"}) {
		565	$kv{_expires} = $anow + delete $kv{"max-age"};
		566	} elsif (exists $kv{expires}) {
		567	$snow ||= parse_date ($date) || $anow;
		568	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		569	} else {
		570	delete $kv{_expires};
		571	}
		572
		573	my $cdom;
		574	my $cpath = (delete $kv{path}) || "/";
		575
		576	if (exists $kv{domain}) {
		577	$cdom = delete $kv{domain};
		578
		579	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		580
		581	next if $cdom =~ /\.$/;
		582
		583	# this is not rfc-like and not netscape-like. go figure.
		584	my $ndots = $cdom =~ y/.//;
		585	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		586	} else {
		587	$cdom = $host;
		588	}
		589
		590	# store it
		591	$jar->{version} = 1;
		592	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		593
		594	redo if /\G\s*,/gc;
		595	}
		596	}
		597
		598	#############################################################################
		599	# keepalive/persistent connection cache
		600
		601	# fetch a connection from the keepalive cache
		602	sub ka_fetch($) {
		603	my $ka_key = shift;
		604
		605	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		606	delete $KA_CACHE{$ka_key}
		607	unless @{ $KA_CACHE{$ka_key} };
		608
		609	$hdl
		610	}
		611
		612	sub ka_store($$) {
		613	my ($ka_key, $hdl) = @_;
		614
		615	my $kaa = $KA_CACHE{$ka_key} ||= [];
		616
		617	my $destroy = sub {
		618	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		619
		620	$hdl->destroy;
		621
		622	@ka
		623	? $KA_CACHE{$ka_key} = \@ka
		624	: delete $KA_CACHE{$ka_key};
		625	};
		626
		627	# on error etc., destroy
		628	$hdl->on_error ($destroy);
		629	$hdl->on_eof ($destroy);
		630	$hdl->on_read ($destroy);
		631	$hdl->timeout ($PERSISTENT_TIMEOUT);
		632
		633	push @$kaa, $hdl;
		634	shift @$kaa while @$kaa > $MAX_PER_HOST;
		635	}
		636
		637	#############################################################################
		638	# utilities
		639
357	# continue to parse $_ for headers and place them into the arg	640	# continue to parse $_ for headers and place them into the arg
358	sub parse_hdr() {	641	sub _parse_hdr() {
359	my %hdr;	642	my %hdr;
360		643
361	# things seen, not parsed:	644	# things seen, not parsed:
362	# p3pP="NON CUR OTPi OUR NOR UNI"	645	# p3pP="NON CUR OTPi OUR NOR UNI"
363		646
…		…
377	for values %hdr;	660	for values %hdr;
378		661
379	\%hdr	662	\%hdr
380	}	663	}
381		664
		665	#############################################################################
		666	# http_get
		667
382	our $qr_nlnl = qr{(?<![^\012])\015?\012};	668	our $qr_nlnl = qr{(?<![^\012])\015?\012};
383		669
384	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	670	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
385	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	671	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		672
		673	# maybe it should just become a normal object :/
		674
		675	sub _destroy_state(\%) {
		676	my ($state) = @_;
		677
		678	$state->{handle}->destroy if $state->{handle};
		679	%$state = ();
		680	}
		681
		682	sub _error(\%$$) {
		683	my ($state, $cb, $hdr) = @_;
		684
		685	&_destroy_state ($state);
		686
		687	$cb->(undef, $hdr);
		688	()
		689	}
386		690
387	sub http_request($$@) {	691	sub http_request($$@) {
388	my $cb = pop;	692	my $cb = pop;
389	my ($method, $url, %arg) = @_;	693	my ($method, $url, %arg) = @_;
390		694
…		…
408	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	712	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
409		713
410	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })	714	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
411	if $recurse < 0;	715	if $recurse < 0;
412		716
413	my $proxy = $arg{proxy} || $PROXY;	717	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
414	my $timeout = $arg{timeout} || $TIMEOUT;	718	my $timeout = $arg{timeout} || $TIMEOUT;
415		719
416	my ($uscheme, $uauthority, $upath, $query, $fragment) =	720	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
417	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;	721	$url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|;
418		722
419	$uscheme = lc $uscheme;	723	$uscheme = lc $uscheme;
420		724
421	my $uport = $uscheme eq "http" ? 80	725	my $uport = $uscheme eq "http" ? 80
422	: $uscheme eq "https" ? 443	726	: $uscheme eq "https" ? 443
423	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });	727	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
424		728
425	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	729	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
426	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	730	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
427		731
428	my $uhost = $1;	732	my $uhost = lc $1;
429	$uport = $2 if defined $2;	733	$uport = $2 if defined $2;
430		734
431	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	735	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
432	unless exists $hdr{host};	736	unless exists $hdr{host};
433		737
…		…
436		740
437	$upath =~ s%^/?%/%;	741	$upath =~ s%^/?%/%;
438		742
439	# cookie processing	743	# cookie processing
440	if (my $jar = $arg{cookie_jar}) {	744	if (my $jar = $arg{cookie_jar}) {
441	%$jar = () if $jar->{version} != 1;	745	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
442		746
443	my @cookie;
444
445	while (my ($chost, $v) = each %$jar) {
446	if ($chost =~ /^\./) {
447	next unless $chost eq substr $uhost, -length $chost;
448	} elsif ($chost =~ /\./) {
449	next unless $chost eq $uhost;
450	} else {
451	next;
452	}
453
454	while (my ($cpath, $v) = each %$v) {
455	next unless $cpath eq substr $upath, 0, length $cpath;
456
457	while (my ($k, $v) = each %$v) {
458	next if $uscheme ne "https" && exists $v->{secure};
459	my $value = $v->{value};
460	$value =~ s/([\\"])/\\$1/g;
461	push @cookie, "$k=\"$value\"";
462	}
463	}
464	}
465
466	$hdr{cookie} = join "; ", @cookie	747	$hdr{cookie} = join "; ", @$cookies
467	if @cookie;	748	if @$cookies;
468	}	749	}
469		750
470	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	751	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
471		752
472	if ($proxy) {	753	if ($proxy) {
…		…
475	$rscheme = "http" unless defined $rscheme;	756	$rscheme = "http" unless defined $rscheme;
476		757
477	# don't support https requests over https-proxy transport,	758	# don't support https requests over https-proxy transport,
478	# can't be done with tls as spec'ed, unless you double-encrypt.	759	# can't be done with tls as spec'ed, unless you double-encrypt.
479	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	760	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		761
		762	$rhost = lc $rhost;
		763	$rscheme = lc $rscheme;
480	} else {	764	} else {
481	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	765	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
482	}	766	}
483		767
484	# leave out fragment and query string, just a heuristic	768	# leave out fragment and query string, just a heuristic
…		…
486	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};	770	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
487		771
488	$hdr{"content-length"} = length $arg{body}	772	$hdr{"content-length"} = length $arg{body}
489	if length $arg{body} || $method ne "GET";	773	if length $arg{body} || $method ne "GET";
490		774
491	$hdr{connection} = "close TE";	775	my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/;
		776
		777	# default value for keepalive is true iff the request is for an idempotent method
		778	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : $idempotent;
		779	my $keepalive10 = exists $arg{keepalive10} ? $arg{keepalive10} : !$proxy;
		780	my $keptalive; # true if this is actually a recycled connection
		781
		782	# the key to use in the keepalive cache
		783	my $ka_key = "$uhost\x00$arg{sessionid}";
		784
		785	$hdr{connection} = ($keepalive ? $keepalive10 ? "keep-alive " : "" : "close ") . "Te"; #1.1
492	$hdr{te} = "trailers" unless exists $hdr{te};	786	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
493		787
494	my %state = (connect_guard => 1);	788	my %state = (connect_guard => 1);
		789
		790	my $ae_error = 595; # connecting
		791
		792	# handle actual, non-tunneled, request
		793	my $handle_actual_request = sub {
		794	$ae_error = 596; # request phase
		795
		796	my $hdl = $state{handle};
		797
		798	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		799
		800	# send request
		801	$hdl->push_write (
		802	"$method $rpath HTTP/1.1\015\012"
		803	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		804	. "\015\012"
		805	. (delete $arg{body})
		806	);
		807
		808	# return if error occured during push_write()
		809	return unless %state;
		810
		811	# reduce memory usage, save a kitten, also re-use it for the response headers.
		812	%hdr = ();
		813
		814	# status line and headers
		815	$state{read_response} = sub {
		816	return unless %state;
		817
		818	for ("$_[1]") {
		819	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		820
		821	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
		822	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		823
		824	# 100 Continue handling
		825	# should not happen as we don't send expect: 100-continue,
		826	# but we handle it just in case.
		827	# since we send the request body regardless, if we get an error
		828	# we are out of-sync, which we currently do NOT handle correctly.
		829	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		830	if $2 eq 100;
		831
		832	push @pseudo,
		833	HTTPVersion => $1,
		834	Status => $2,
		835	Reason => $3,
		836	;
		837
		838	my $hdr = _parse_hdr
		839	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		840
		841	%hdr = (%$hdr, @pseudo);
		842	}
		843
		844	# redirect handling
		845	# microsoft and other shitheads don't give a shit for following standards,
		846	# try to support some common forms of broken Location headers.
		847	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
		848	$hdr{location} =~ s/^\.\/+//;
		849
		850	my $url = "$rscheme://$uhost:$uport";
		851
		852	unless ($hdr{location} =~ s/^\///) {
		853	$url .= $upath;
		854	$url =~ s/\/[^\/]*$//;
		855	}
		856
		857	$hdr{location} = "$url/$hdr{location}";
		858	}
		859
		860	my $redirect;
		861
		862	if ($recurse) {
		863	my $status = $hdr{Status};
		864
		865	# industry standard is to redirect POST as GET for
		866	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		867	# also, the UA should ask the user for 301 and 307 and POST,
		868	# industry standard seems to be to simply follow.
		869	# we go with the industry standard.
		870	if ($status == 301 or $status == 302 or $status == 303) {
		871	# HTTP/1.1 is unclear on how to mutate the method
		872	$method = "GET" unless $method eq "HEAD";
		873	$redirect = 1;
		874	} elsif ($status == 307) {
		875	$redirect = 1;
		876	}
		877	}
		878
		879	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		880	if ($state{handle}) {
		881	# handle keepalive
		882	if (
		883	$keepalive
		884	&& $_[3]
		885	&& ($hdr{HTTPVersion} < 1.1
		886	? $hdr{connection} =~ /\bkeep-?alive\b/i
		887	: $hdr{connection} !~ /\bclose\b/i)
		888	) {
		889	ka_store $ka_key, delete $state{handle};
		890	} else {
		891	# no keepalive, destroy the handle
		892	$state{handle}->destroy;
		893	}
		894	}
		895
		896	%state = ();
		897
		898	if (defined $_[1]) {
		899	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		900	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		901	}
		902
		903	# set-cookie processing
		904	if ($arg{cookie_jar}) {
		905	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		906	}
		907
		908	if ($redirect && exists $hdr{location}) {
		909	# we ignore any errors, as it is very common to receive
		910	# Content-Length != 0 but no actual body
		911	# we also access %hdr, as $_[1] might be an erro
		912	http_request (
		913	$method => $hdr{location},
		914	%arg,
		915	recurse => $recurse - 1,
		916	Redirect => [$_[0], \%hdr],
		917	$cb
		918	);
		919	} else {
		920	$cb->($_[0], \%hdr);
		921	}
		922	};
		923
		924	$ae_error = 597; # body phase
		925
		926	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		927
		928	my $len = $chunked ? undef : $hdr{"content-length"};
		929
		930	# body handling, many different code paths
		931	# - no body expected
		932	# - want_body_handle
		933	# - te chunked
		934	# - 2x length known (with or without on_body)
		935	# - 2x length not known (with or without on_body)
		936	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		937	$finish->(undef, 598 => "Request cancelled by on_header");
		938	} elsif (
		939	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		940	or $method eq "HEAD"
		941	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		942	) {
		943	# no body
		944	$finish->("", undef, undef, 1);
		945
		946	} elsif (!$redirect && $arg{want_body_handle}) {
		947	$_[0]->on_eof (undef);
		948	$_[0]->on_error (undef);
		949	$_[0]->on_read (undef);
		950
		951	$finish->(delete $state{handle});
		952
		953	} elsif ($chunked) {
		954	my $cl = 0;
		955	my $body = "";
		956	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
		957
		958	$state{read_chunk} = sub {
		959	$_[1] =~ /^([0-9a-fA-F]+)/
		960	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		961
		962	my $len = hex $1;
		963
		964	if ($len) {
		965	$cl += $len;
		966
		967	$_[0]->push_read (chunk => $len, sub {
		968	$on_body->($_[1], \%hdr)
		969	or return $finish->(undef, 598 => "Request cancelled by on_body");
		970
		971	$_[0]->push_read (line => sub {
		972	length $_[1]
		973	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		974	$_[0]->push_read (line => $state{read_chunk});
		975	});
		976	});
		977	} else {
		978	$hdr{"content-length"} ||= $cl;
		979
		980	$_[0]->push_read (line => $qr_nlnl, sub {
		981	if (length $_[1]) {
		982	for ("$_[1]") {
		983	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		984
		985	my $hdr = _parse_hdr
		986	or return $finish->(undef, $ae_error => "Garbled response trailers");
		987
		988	%hdr = (%hdr, %$hdr);
		989	}
		990	}
		991
		992	$finish->($body, undef, undef, 1);
		993	});
		994	}
		995	};
		996
		997	$_[0]->push_read (line => $state{read_chunk});
		998
		999	} elsif ($arg{on_body}) {
		1000	if (defined $len) {
		1001	$_[0]->on_read (sub {
		1002	$len -= length $_[0]{rbuf};
		1003
		1004	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1005	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1006
		1007	$len > 0
		1008	or $finish->("", undef, undef, 1);
		1009	});
		1010	} else {
		1011	$_[0]->on_eof (sub {
		1012	$finish->("");
		1013	});
		1014	$_[0]->on_read (sub {
		1015	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1016	or $finish->(undef, 598 => "Request cancelled by on_body");
		1017	});
		1018	}
		1019	} else {
		1020	$_[0]->on_eof (undef);
		1021
		1022	if (defined $len) {
		1023	$_[0]->on_read (sub {
		1024	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1025	if $len <= length $_[0]{rbuf};
		1026	});
		1027	} else {
		1028	$_[0]->on_error (sub {
		1029	($! == Errno::EPIPE || !$!)
		1030	? $finish->(delete $_[0]{rbuf})
		1031	: $finish->(undef, $ae_error => $_[2]);
		1032	});
		1033	$_[0]->on_read (sub { });
		1034	}
		1035	}
		1036	};
		1037
		1038	# if keepalive is enabled, then the server closing the connection
		1039	# before a response can happen legally - we retry on idempotent methods.
		1040	if ($keptalive && $idempotent) {
		1041	my $old_eof = $hdl->{on_eof};
		1042	$hdl->{on_eof} = sub {
		1043	_destroy_state %state;
		1044
		1045	http_request (
		1046	$method => $url,
		1047	%arg,
		1048	keepalive => 0,
		1049	$cb
		1050	);
		1051	};
		1052	$hdl->on_read (sub {
		1053	return unless %state;
		1054
		1055	# as soon as we receive something, a connection close
		1056	# once more becomes a hard error
		1057	$hdl->{on_eof} = $old_eof;
		1058	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1059	});
		1060	} else {
		1061	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1062	}
		1063	};
		1064
		1065	my $prepare_handle = sub {
		1066	my ($hdl) = $state{handle};
		1067
		1068	$hdl->timeout ($timeout);
		1069	$hdl->on_error (sub {
		1070	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1071	});
		1072	$hdl->on_eof (sub {
		1073	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1074	});
		1075	};
		1076
		1077	# connected to proxy (or origin server)
		1078	my $connect_cb = sub {
		1079	my $fh = shift
		1080	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1081
		1082	return unless delete $state{connect_guard};
		1083
		1084	# get handle
		1085	$state{handle} = new AnyEvent::Handle
		1086	%{ $arg{handle_params} },
		1087	fh => $fh,
		1088	peername => $uhost,
		1089	tls_ctx => $arg{tls_ctx},
		1090	;
		1091
		1092	$prepare_handle->();
		1093
		1094	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1095
		1096	# now handle proxy-CONNECT method
		1097	if ($proxy && $uscheme eq "https") {
		1098	# oh dear, we have to wrap it into a connect request
		1099
		1100	# maybe re-use $uauthority with patched port?
		1101	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		1102	$state{handle}->push_read (line => $qr_nlnl, sub {
		1103	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1104	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1105
		1106	if ($2 == 200) {
		1107	$rpath = $upath;
		1108	$handle_actual_request->();
		1109	} else {
		1110	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1111	}
		1112	});
		1113	} else {
		1114	$handle_actual_request->();
		1115	}
		1116	};
495		1117
496	_get_slot $uhost, sub {	1118	_get_slot $uhost, sub {
497	$state{slot_guard} = shift;	1119	$state{slot_guard} = shift;
498		1120
499	return unless $state{connect_guard};	1121	return unless $state{connect_guard};
500		1122
501	my $connect_cb = sub {	1123	# try to use an existing keepalive connection, but only if we, ourselves, plan
502	$state{fh} = shift	1124	# on a keepalive request (in theory, this should be a separate config option).
503	or do {	1125	if ($keepalive && $KA_CACHE{$ka_key}) {
504	my $err = "$!";	1126	$keptalive = 1;
505	%state = ();	1127	$state{handle} = ka_fetch $ka_key;
506	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });	1128	$prepare_handle->();
507	};
508
509	pop; # free memory, save a tree
510
511	return unless delete $state{connect_guard};
512
513	# get handle
514	$state{handle} = new AnyEvent::Handle
515	fh => $state{fh},
516	peername => $rhost,
517	tls_ctx => $arg{tls_ctx},
518	# these need to be reconfigured on keepalive handles
519	timeout => $timeout,
520	on_error => sub {
521	%state = ();
522	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
523	},
524	on_eof => sub {
525	%state = ();
526	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
527	},
528	;
529
530	# limit the number of persistent connections
531	# keepalive not yet supported
532	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
533	# ++$KA_COUNT{$_[1]};
534	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
535	# --$KA_COUNT{$_[1]}
536	# };
537	# $hdr{connection} = "keep-alive";
538	# } else {
539	# delete $hdr{connection};
540	# }
541
542	$state{handle}->starttls ("connect") if $rscheme eq "https";
543
544	# handle actual, non-tunneled, request
545	my $handle_actual_request = sub {
546	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
547
548	# send request
549	$state{handle}->push_write (
550	"$method $rpath HTTP/1.1\015\012"
551	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
552	. "\015\012"
553	. (delete $arg{body})
554	);
555
556	# return if error occured during push_write()
557	return unless %state;
558
559	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
560
561	# status line and headers
562	$state{handle}->push_read (line => $qr_nlnl, sub {
563	my $keepalive = pop;
564
565	for ("$_[1]") {
566	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
567
568	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
569	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
570
571	push @pseudo,
572	HTTPVersion => $1,
573	Status => $2,
574	Reason => $3,
575	;
576
577	my $hdr = parse_hdr
578	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
579
580	%hdr = (%$hdr, @pseudo);
581	}
582
583	# redirect handling
584	# microsoft and other shitheads don't give a shit for following standards,
585	# try to support some common forms of broken Location headers.
586	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
587	$hdr{location} =~ s/^\.\/+//;
588
589	my $url = "$rscheme://$uhost:$uport";
590
591	unless ($hdr{location} =~ s/^\///) {
592	$url .= $upath;
593	$url =~ s/\/[^\/]*$//;
594	}
595
596	$hdr{location} = "$url/$hdr{location}";
597	}
598
599	my $redirect;
600
601	if ($recurse) {
602	my $status = $hdr{Status};
603
604	# industry standard is to redirect POST as GET for
605	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
606	# also, the UA should ask the user for 301 and 307 and POST,
607	# industry standard seems to be to simply follow.
608	# we go with the industry standard.
609	if ($status == 301 or $status == 302 or $status == 303) {
610	# HTTP/1.1 is unclear on how to mutate the method
611	$method = "GET" unless $method eq "HEAD";
612	$redirect = 1;
613	} elsif ($status == 307) {
614	$redirect = 1;
615	}
616	}
617
618	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
619	$state{handle}->destroy if $state{handle};
620	%state = ();
621
622	if (defined $_[1]) {
623	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
624	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
625	}
626
627	# set-cookie processing
628	if ($arg{cookie_jar}) {
629	for ($hdr{"set-cookie"}) {
630	# parse NAME=VALUE
631	my @kv;
632
633	while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
634	my $name = $1;
635	my $value = $3;
636
637	unless ($value) {
638	$value = $2;
639	$value =~ s/\\(.)/$1/gs;
640	}
641
642	push @kv, $name => $value;
643
644	last unless /\G\s*;/gc;
645	}
646
647	last unless @kv;
648
649	my $name = shift @kv;
650	my %kv = (value => shift @kv, @kv);
651
652	my $cdom;
653	my $cpath = (delete $kv{path}) || "/";
654
655	if (exists $kv{domain}) {
656	$cdom = delete $kv{domain};
657
658	$cdom =~ s/^\.?/./; # make sure it starts with a "."
659
660	next if $cdom =~ /\.$/;
661
662	# this is not rfc-like and not netscape-like. go figure.
663	my $ndots = $cdom =~ y/.//;
664	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
665	} else {
666	$cdom = $uhost;
667	}
668
669	# store it
670	$arg{cookie_jar}{version} = 1;
671	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
672
673	redo if /\G\s*,/gc;
674	}
675	}
676
677	if ($redirect && exists $hdr{location}) {
678	# we ignore any errors, as it is very common to receive
679	# Content-Length != 0 but no actual body
680	# we also access %hdr, as $_[1] might be an erro
681	http_request (
682	$method => $hdr{location},
683	%arg,
684	recurse => $recurse - 1,
685	Redirect => [$_[0], \%hdr],
686	$cb);
687	} else {
688	$cb->($_[0], \%hdr);
689	}
690	};
691
692	my $len = $hdr{"content-length"};
693
694	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
695	$finish->(undef, 598 => "Request cancelled by on_header");
696	} elsif (
697	$hdr{Status} =~ /^(?:1..|204|205|304)$/
698	or $method eq "HEAD"
699	or (defined $len && !$len)
700	) {
701	# no body
702	$finish->("", undef, undef, 1);
703	} else {
704	# body handling, many different code paths
705	# - no body expected
706	# - want_body_handle
707	# - te chunked
708	# - 2x length known (with or without on_body)
709	# - 2x length not known (with or without on_body)
710	if (!$redirect && $arg{want_body_handle}) {
711	$_[0]->on_eof (undef);
712	$_[0]->on_error (undef);
713	$_[0]->on_read (undef);
714
715	$finish->(delete $state{handle});
716
717	} elsif ($hdr{"transfer-encoding"} =~ /chunked/) {
718	my $body = undef;
719	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
720
721	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
722
723	my $read_chunk; $read_chunk = sub {
724	$_[1] =~ /^([0-9a-fA-F]+)/
725	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
726
727	my $len = hex $1;
728
729	if ($len) {
730	$_[0]->push_read (chunk => hex $1, sub {
731	$on_body->($_[1], \%hdr)
732	or return $finish->(undef, 598 => "Request cancelled by on_body");
733
734	$_[0]->push_read (line => sub {
735	length $_[1]
736	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
737	$_[0]->push_read (line => $read_chunk);
738	});
739	});
740	} else {
741	$_[0]->push_read (line => $qr_nlnl, sub {
742	if (length $_[1]) {
743	for ("$_[1]") {
744	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
745
746	my $hdr = parse_hdr
747	or return $finish->(undef, 599 => "Garbled response trailers");
748
749	%hdr = (%hdr, %$hdr);
750	}
751	}
752
753	$finish->($body, undef, undef, 1);
754	});
755	}
756	};
757
758	$_[0]->push_read (line => $read_chunk);
759
760	} elsif ($arg{on_body}) {
761	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
762
763	if ($len) {
764	$_[0]->on_read (sub {
765	$len -= length $_[0]{rbuf};
766
767	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
768	or return $finish->(undef, 598 => "Request cancelled by on_body");
769
770	$len > 0
771	or $finish->("", undef, undef, 1);
772	});
773	} else {
774	$_[0]->on_eof (sub {
775	$finish->("");
776	});
777	$_[0]->on_read (sub {
778	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
779	or $finish->(undef, 598 => "Request cancelled by on_body");
780	});
781	}
782	} else {
783	$_[0]->on_eof (undef);
784
785	if ($len) {
786	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
787	$_[0]->on_read (sub {
788	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
789	if $len <= length $_[0]{rbuf};
790	});
791	} else {
792	$_[0]->on_error (sub {
793	($! == Errno::EPIPE || !$!)
794	? $finish->(delete $_[0]{rbuf})
795	: $finish->(undef, 599 => $_[2]);
796	});
797	$_[0]->on_read (sub { });
798	}
799	}
800	}
801	});
802	};
803
804	# now handle proxy-CONNECT method
805	if ($proxy && $uscheme eq "https") {
806	# oh dear, we have to wrap it into a connect request
807
808	# maybe re-use $uauthority with patched port?
809	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
810	$state{handle}->push_read (line => $qr_nlnl, sub {
811	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
812	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
813
814	if ($2 == 200) {
815	$rpath = $upath;
816	&$handle_actual_request;	1129	$handle_actual_request->();
817	} else {	1130
818	%state = ();
819	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
820	}
821	});
822	} else {	1131	} else {
823	&$handle_actual_request;
824	}
825	};
826
827	my $tcp_connect = $arg{tcp_connect}	1132	my $tcp_connect = $arg{tcp_connect}
828	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1133	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
829		1134
830	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });	1135	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
831		1136	}
832	};	1137	};
833		1138
834	defined wantarray && AnyEvent::Util::guard { %state = () }	1139	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
835	}	1140	}
836		1141
837	sub http_get($@) {	1142	sub http_get($@) {
838	unshift @_, "GET";	1143	unshift @_, "GET";
839	&http_request	1144	&http_request
…		…
857	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1162	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
858	the actual connection, which in turn uses AnyEvent::DNS to resolve	1163	the actual connection, which in turn uses AnyEvent::DNS to resolve
859	hostnames. The latter is a simple stub resolver and does no caching	1164	hostnames. The latter is a simple stub resolver and does no caching
860	on its own. If you want DNS caching, you currently have to provide	1165	on its own. If you want DNS caching, you currently have to provide
861	your own default resolver (by storing a suitable resolver object in	1166	your own default resolver (by storing a suitable resolver object in
862	C<$AnyEvent::DNS::RESOLVER>).	1167	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
863		1168
864	=head2 GLOBAL FUNCTIONS AND VARIABLES	1169	=head2 GLOBAL FUNCTIONS AND VARIABLES
865		1170
866	=over 4	1171	=over 4
867		1172
868	=item AnyEvent::HTTP::set_proxy "proxy-url"	1173	=item AnyEvent::HTTP::set_proxy "proxy-url"
869		1174
870	Sets the default proxy server to use. The proxy-url must begin with a	1175	Sets the default proxy server to use. The proxy-url must begin with a
871	string of the form C<http://host:port> (optionally C<https:...>), croaks	1176	string of the form C<http://host:port>, croaks otherwise.
872	otherwise.
873		1177
874	To clear an already-set proxy, use C<undef>.	1178	To clear an already-set proxy, use C<undef>.
		1179
		1180	When AnyEvent::HTTP is laoded for the first time it will query the
		1181	default proxy from the operating system, currently by looking at
		1182	C<$ENV{http_proxy>}.
		1183
		1184	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1185
		1186	Remove all cookies from the cookie jar that have been expired. If
		1187	C<$session_end> is given and true, then additionally remove all session
		1188	cookies.
		1189
		1190	You should call this function (with a true C<$session_end>) before you
		1191	save cookies to disk, and you should call this function after loading them
		1192	again. If you have a long-running program you can additonally call this
		1193	function from time to time.
		1194
		1195	A cookie jar is initially an empty hash-reference that is managed by this
		1196	module. It's format is subject to change, but currently it is like this:
		1197
		1198	The key C<version> has to contain C<1>, otherwise the hash gets
		1199	emptied. All other keys are hostnames or IP addresses pointing to
		1200	hash-references. The key for these inner hash references is the
		1201	server path for which this cookie is meant, and the values are again
		1202	hash-references. The keys of those hash-references is the cookie name, and
		1203	the value, you guessed it, is another hash-reference, this time with the
		1204	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1205	which have been replaced by a C<_expires> key that contains the cookie
		1206	expiry timestamp.
		1207
		1208	Here is an example of a cookie jar with a single cookie, so you have a
		1209	chance of understanding the above paragraph:
		1210
		1211	{
		1212	version => 1,
		1213	"10.0.0.1" => {
		1214	"/" => {
		1215	"mythweb_id" => {
		1216	_expires => 1293917923,
		1217	value => "ooRung9dThee3ooyXooM1Ohm",
		1218	},
		1219	},
		1220	},
		1221	}
875		1222
876	=item $date = AnyEvent::HTTP::format_date $timestamp	1223	=item $date = AnyEvent::HTTP::format_date $timestamp
877		1224
878	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP	1225	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
879	Date (RFC 2616).	1226	Date (RFC 2616).
880		1227
881	=item $timestamp = AnyEvent::HTTP::parse_date $date	1228	=item $timestamp = AnyEvent::HTTP::parse_date $date
882		1229
883	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX	1230	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1231	bunch of minor variations of those, and returns the corresponding POSIX
884	timestamp, or C<undef> if the date cannot be parsed.	1232	timestamp, or C<undef> if the date cannot be parsed.
885		1233
886	=item $AnyEvent::HTTP::MAX_RECURSE	1234	=item $AnyEvent::HTTP::MAX_RECURSE
887		1235
888	The default value for the C<recurse> request parameter (default: C<10>).	1236	The default value for the C<recurse> request parameter (default: C<10>).
		1237
		1238	=item $AnyEvent::HTTP::TIMEOUT
		1239
		1240	The default timeout for conenction operations (default: C<300>).
889		1241
890	=item $AnyEvent::HTTP::USERAGENT	1242	=item $AnyEvent::HTTP::USERAGENT
891		1243
892	The default value for the C<User-Agent> header (the default is	1244	The default value for the C<User-Agent> header (the default is
893	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1245	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
894		1246
895	=item $AnyEvent::HTTP::MAX_PER_HOST	1247	=item $AnyEvent::HTTP::MAX_PER_HOST
896		1248
897	The maximum number of concurrent connections to the same host (identified	1249	The maximum number of concurrent connections to the same host (identified
898	by the hostname). If the limit is exceeded, then the additional requests	1250	by the hostname). If the limit is exceeded, then the additional requests
899	are queued until previous connections are closed.	1251	are queued until previous connections are closed. Both persistent and
		1252	non-persistent connections are counted in this limit.
900		1253
901	The default value for this is C<4>, and it is highly advisable to not	1254	The default value for this is C<4>, and it is highly advisable to not
902	increase it.	1255	increase it much.
		1256
		1257	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1258	connections, older browsers used 2, newers (such as firefox 3) typically
		1259	use 6, and Opera uses 8 because like, they have the fastest browser and
		1260	give a shit for everybody else on the planet.
		1261
		1262	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1263
		1264	The time after which idle persistent conenctions get closed by
		1265	AnyEvent::HTTP (default: C<3>).
903		1266
904	=item $AnyEvent::HTTP::ACTIVE	1267	=item $AnyEvent::HTTP::ACTIVE
905		1268
906	The number of active connections. This is not the number of currently	1269	The number of active connections. This is not the number of currently
907	running requests, but the number of currently open and non-idle TCP	1270	running requests, but the number of currently open and non-idle TCP
908	connections. This number of can be useful for load-leveling.	1271	connections. This number can be useful for load-leveling.
909		1272
910	=back	1273	=back
911		1274
912	=cut	1275	=cut
913		1276
…		…
928	sub parse_date($) {	1291	sub parse_date($) {
929	my ($date) = @_;	1292	my ($date) = @_;
930		1293
931	my ($d, $m, $y, $H, $M, $S);	1294	my ($d, $m, $y, $H, $M, $S);
932		1295
933	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$/) {	1296	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$/) {
934	# RFC 822/1123, required by RFC 2616	1297	# RFC 822/1123, required by RFC 2616 (with " ")
		1298	# cookie dates (with "-")
		1299
935	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);	1300	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
936		1301
937	} elsif ($date =~ /^[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$/) {	1302	} 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$/) {
938	# RFC 850	1303	# RFC 850
939	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);	1304	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
940		1305
941	} 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])$/) {	1306	} 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])$/) {
942	# ISO C's asctime	1307	# ISO C's asctime
943	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);	1308	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
944	}	1309	}
945	# other formats fail in the loop below	1310	# other formats fail in the loop below
946		1311
…		…
954	undef	1319	undef
955	}	1320	}
956		1321
957	sub set_proxy($) {	1322	sub set_proxy($) {
958	if (length $_[0]) {	1323	if (length $_[0]) {
959	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1324	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
960	or Carp::croak "$_[0]: invalid proxy URL";	1325	or Carp::croak "$_[0]: invalid proxy URL";
961	$PROXY = [$2, $3 || 3128, $1]	1326	$PROXY = [$2, $3 || 3128, $1]
962	} else {	1327	} else {
963	undef $PROXY;	1328	undef $PROXY;
964	}	1329	}
…		…
967	# initialise proxy from environment	1332	# initialise proxy from environment
968	eval {	1333	eval {
969	set_proxy $ENV{http_proxy};	1334	set_proxy $ENV{http_proxy};
970	};	1335	};
971		1336
		1337	=head2 SHOWCASE
		1338
		1339	This section contaisn some more elaborate "real-world" examples or code
		1340	snippets.
		1341
		1342	=head2 HTTP/1.1 FILE DOWNLOAD
		1343
		1344	Downloading files with HTTP can be quite tricky, especially when something
		1345	goes wrong and you want to resume.
		1346
		1347	Here is a function that initiates and resumes a download. It uses the
		1348	last modified time to check for file content changes, and works with many
		1349	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1350	on older servers.
		1351
		1352	It calls the completion callback with either C<undef>, which means a
		1353	nonretryable error occured, C<0> when the download was partial and should
		1354	be retried, and C<1> if it was successful.
		1355
		1356	use AnyEvent::HTTP;
		1357
		1358	sub download($$$) {
		1359	my ($url, $file, $cb) = @_;
		1360
		1361	open my $fh, "+<", $file
		1362	or die "$file: $!";
		1363
		1364	my %hdr;
		1365	my $ofs = 0;
		1366
		1367	warn stat $fh;
		1368	warn -s _;
		1369	if (stat $fh and -s _) {
		1370	$ofs = -s _;
		1371	warn "-s is ", $ofs;#d#
		1372	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1373	$hdr{"range"} = "bytes=$ofs-";
		1374	}
		1375
		1376	http_get $url,
		1377	headers => \%hdr,
		1378	on_header => sub {
		1379	my ($hdr) = @_;
		1380
		1381	if ($hdr->{Status} == 200 && $ofs) {
		1382	# resume failed
		1383	truncate $fh, $ofs = 0;
		1384	}
		1385
		1386	sysseek $fh, $ofs, 0;
		1387
		1388	1
		1389	},
		1390	on_body => sub {
		1391	my ($data, $hdr) = @_;
		1392
		1393	if ($hdr->{Status} =~ /^2/) {
		1394	length $data == syswrite $fh, $data
		1395	or return; # abort on write errors
		1396	}
		1397
		1398	1
		1399	},
		1400	sub {
		1401	my (undef, $hdr) = @_;
		1402
		1403	my $status = $hdr->{Status};
		1404
		1405	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1406	utime $fh, $time, $time;
		1407	}
		1408
		1409	if ($status == 200 || $status == 206 || $status == 416) {
		1410	# download ok || resume ok || file already fully downloaded
		1411	$cb->(1, $hdr);
		1412
		1413	} elsif ($status == 412) {
		1414	# file has changed while resuming, delete and retry
		1415	unlink $file;
		1416	$cb->(0, $hdr);
		1417
		1418	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1419	# retry later
		1420	$cb->(0, $hdr);
		1421
		1422	} else {
		1423	$cb->(undef, $hdr);
		1424	}
		1425	}
		1426	;
		1427	}
		1428
		1429	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1430	if ($_[0]) {
		1431	print "OK!\n";
		1432	} elsif (defined $_[0]) {
		1433	print "please retry later\n";
		1434	} else {
		1435	print "ERROR\n";
		1436	}
		1437	};
		1438
972	=head2 SOCKS PROXIES	1439	=head3 SOCKS PROXIES
973		1440
974	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1441	Socks proxies are not directly supported by AnyEvent::HTTP. You can
975	compile your perl to support socks, or use an external program such as	1442	compile your perl to support socks, or use an external program such as
976	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy	1443	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
977	transparently.	1444	transparently.

Diff Legend

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