ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.65 by root, Fri Dec 31 03:47:32 2010 UTC vs.
Revision 1.103 by root, Thu Feb 24 12:13:11 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 = '2.1';
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
		640	# continue to parse $_ for headers and place them into the arg
		641	sub _parse_hdr() {
		642	my %hdr;
		643
		644	# things seen, not parsed:
		645	# p3pP="NON CUR OTPi OUR NOR UNI"
		646
		647	$hdr{lc $1} .= ",$2"
		648	while /\G
		649	([^:\000-\037]*):
		650	[\011\040]*
		651	((?: [^\012]+ | \012[\011\040] )*)
		652	\012
		653	/gxc;
		654
		655	/\G$/
		656	or return;
		657
		658	# remove the "," prefix we added to all headers above
		659	substr $_, 0, 1, ""
		660	for values %hdr;
		661
		662	\%hdr
		663	}
		664
		665	#############################################################################
		666	# http_get
		667
357	our $qr_nlnl = qr{(?<![^\012])\015?\012};	668	our $qr_nlnl = qr{(?<![^\012])\015?\012};
358		669
359	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	670	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
360	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(\%$$) {
		683	my ($state, $cb, $hdr) = @_;
		684
		685	&_destroy_state ($state);
		686
		687	$cb->(undef, $hdr);
		688	()
		689	}
361		690
362	sub http_request($$@) {	691	sub http_request($$@) {
363	my $cb = pop;	692	my $cb = pop;
364	my ($method, $url, %arg) = @_;	693	my ($method, $url, %arg) = @_;
365		694
…		…
383	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	712	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
384		713
385	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })	714	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
386	if $recurse < 0;	715	if $recurse < 0;
387		716
388	my $proxy = $arg{proxy} || $PROXY;	717	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
389	my $timeout = $arg{timeout} || $TIMEOUT;	718	my $timeout = $arg{timeout} || $TIMEOUT;
390		719
391	my ($uscheme, $uauthority, $upath, $query, $fragment) =	720	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
392	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;	721	$url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|;
393		722
394	$uscheme = lc $uscheme;	723	$uscheme = lc $uscheme;
395		724
396	my $uport = $uscheme eq "http" ? 80	725	my $uport = $uscheme eq "http" ? 80
397	: $uscheme eq "https" ? 443	726	: $uscheme eq "https" ? 443
398	: 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" });
399		728
400	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	729	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
401	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	730	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
402		731
403	my $uhost = $1;	732	my $uhost = lc $1;
404	$uport = $2 if defined $2;	733	$uport = $2 if defined $2;
405		734
406	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	735	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
407	unless exists $hdr{host};	736	unless exists $hdr{host};
408		737
…		…
411		740
412	$upath =~ s%^/?%/%;	741	$upath =~ s%^/?%/%;
413		742
414	# cookie processing	743	# cookie processing
415	if (my $jar = $arg{cookie_jar}) {	744	if (my $jar = $arg{cookie_jar}) {
416	%$jar = () if $jar->{version} != 1;	745	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
417		746
418	my @cookie;
419
420	while (my ($chost, $v) = each %$jar) {
421	if ($chost =~ /^\./) {
422	next unless $chost eq substr $uhost, -length $chost;
423	} elsif ($chost =~ /\./) {
424	next unless $chost eq $uhost;
425	} else {
426	next;
427	}
428
429	while (my ($cpath, $v) = each %$v) {
430	next unless $cpath eq substr $upath, 0, length $cpath;
431
432	while (my ($k, $v) = each %$v) {
433	next if $uscheme ne "https" && exists $v->{secure};
434	my $value = $v->{value};
435	$value =~ s/([\\"])/\\$1/g;
436	push @cookie, "$k=\"$value\"";
437	}
438	}
439	}
440
441	$hdr{cookie} = join "; ", @cookie	747	$hdr{cookie} = join "; ", @$cookies
442	if @cookie;	748	if @$cookies;
443	}	749	}
444		750
445	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	751	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
446		752
447	if ($proxy) {	753	if ($proxy) {
…		…
450	$rscheme = "http" unless defined $rscheme;	756	$rscheme = "http" unless defined $rscheme;
451		757
452	# don't support https requests over https-proxy transport,	758	# don't support https requests over https-proxy transport,
453	# 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.
454	$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;
455	} else {	764	} else {
456	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	765	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
457	}	766	}
458		767
459	# leave out fragment and query string, just a heuristic	768	# leave out fragment and query string, just a heuristic
460	$hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	769	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
461	$hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"};	770	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
462		771
463	$hdr{"content-length"} = length $arg{body}	772	$hdr{"content-length"} = length $arg{body}
464	if length $arg{body} || $method ne "GET";	773	if length $arg{body} || $method ne "GET";
465		774
		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 $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		779	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		780	my $was_persistent; # 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} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1
		786	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
		787
466	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[, $persistent])
		880	if ($state{handle}) {
		881	# handle keepalive
		882	if (
		883	$persistent
		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	$state{recurse} =
		913	http_request (
		914	$method => $hdr{location},
		915	%arg,
		916	recurse => $recurse - 1,
		917	Redirect => [$_[0], \%hdr],
		918	sub {
		919	%state = ();
		920	&$cb
		921	},
		922	);
		923	} else {
		924	$cb->($_[0], \%hdr);
		925	}
		926	};
		927
		928	$ae_error = 597; # body phase
		929
		930	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		931
		932	my $len = $chunked ? undef : $hdr{"content-length"};
		933
		934	# body handling, many different code paths
		935	# - no body expected
		936	# - want_body_handle
		937	# - te chunked
		938	# - 2x length known (with or without on_body)
		939	# - 2x length not known (with or without on_body)
		940	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		941	$finish->(undef, 598 => "Request cancelled by on_header");
		942	} elsif (
		943	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		944	or $method eq "HEAD"
		945	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		946	) {
		947	# no body
		948	$finish->("", undef, undef, 1);
		949
		950	} elsif (!$redirect && $arg{want_body_handle}) {
		951	$_[0]->on_eof (undef);
		952	$_[0]->on_error (undef);
		953	$_[0]->on_read (undef);
		954
		955	$finish->(delete $state{handle});
		956
		957	} elsif ($chunked) {
		958	my $cl = 0;
		959	my $body = "";
		960	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
		961
		962	$state{read_chunk} = sub {
		963	$_[1] =~ /^([0-9a-fA-F]+)/
		964	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		965
		966	my $len = hex $1;
		967
		968	if ($len) {
		969	$cl += $len;
		970
		971	$_[0]->push_read (chunk => $len, sub {
		972	$on_body->($_[1], \%hdr)
		973	or return $finish->(undef, 598 => "Request cancelled by on_body");
		974
		975	$_[0]->push_read (line => sub {
		976	length $_[1]
		977	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		978	$_[0]->push_read (line => $state{read_chunk});
		979	});
		980	});
		981	} else {
		982	$hdr{"content-length"} ||= $cl;
		983
		984	$_[0]->push_read (line => $qr_nlnl, sub {
		985	if (length $_[1]) {
		986	for ("$_[1]") {
		987	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		988
		989	my $hdr = _parse_hdr
		990	or return $finish->(undef, $ae_error => "Garbled response trailers");
		991
		992	%hdr = (%hdr, %$hdr);
		993	}
		994	}
		995
		996	$finish->($body, undef, undef, 1);
		997	});
		998	}
		999	};
		1000
		1001	$_[0]->push_read (line => $state{read_chunk});
		1002
		1003	} elsif ($arg{on_body}) {
		1004	if (defined $len) {
		1005	$_[0]->on_read (sub {
		1006	$len -= length $_[0]{rbuf};
		1007
		1008	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1009	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1010
		1011	$len > 0
		1012	or $finish->("", undef, undef, 1);
		1013	});
		1014	} else {
		1015	$_[0]->on_eof (sub {
		1016	$finish->("");
		1017	});
		1018	$_[0]->on_read (sub {
		1019	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1020	or $finish->(undef, 598 => "Request cancelled by on_body");
		1021	});
		1022	}
		1023	} else {
		1024	$_[0]->on_eof (undef);
		1025
		1026	if (defined $len) {
		1027	$_[0]->on_read (sub {
		1028	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1029	if $len <= length $_[0]{rbuf};
		1030	});
		1031	} else {
		1032	$_[0]->on_error (sub {
		1033	($! == Errno::EPIPE || !$!)
		1034	? $finish->(delete $_[0]{rbuf})
		1035	: $finish->(undef, $ae_error => $_[2]);
		1036	});
		1037	$_[0]->on_read (sub { });
		1038	}
		1039	}
		1040	};
		1041
		1042	# if keepalive is enabled, then the server closing the connection
		1043	# before a response can happen legally - we retry on idempotent methods.
		1044	if ($was_persistent && $idempotent) {
		1045	my $old_eof = $hdl->{on_eof};
		1046	$hdl->{on_eof} = sub {
		1047	_destroy_state %state;
		1048
		1049	%state = ();
		1050	$state{recurse} =
		1051	http_request (
		1052	$method => $url,
		1053	%arg,
		1054	keepalive => 0,
		1055	sub {
		1056	%state = ();
		1057	&$cb
		1058	}
		1059	);
		1060	};
		1061	$hdl->on_read (sub {
		1062	return unless %state;
		1063
		1064	# as soon as we receive something, a connection close
		1065	# once more becomes a hard error
		1066	$hdl->{on_eof} = $old_eof;
		1067	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1068	});
		1069	} else {
		1070	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1071	}
		1072	};
		1073
		1074	my $prepare_handle = sub {
		1075	my ($hdl) = $state{handle};
		1076
		1077	$hdl->on_error (sub {
		1078	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1079	});
		1080	$hdl->on_eof (sub {
		1081	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1082	});
		1083	$hdl->timeout_reset;
		1084	$hdl->timeout ($timeout);
		1085	};
		1086
		1087	# connected to proxy (or origin server)
		1088	my $connect_cb = sub {
		1089	my $fh = shift
		1090	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1091
		1092	return unless delete $state{connect_guard};
		1093
		1094	# get handle
		1095	$state{handle} = new AnyEvent::Handle
		1096	%{ $arg{handle_params} },
		1097	fh => $fh,
		1098	peername => $uhost,
		1099	tls_ctx => $arg{tls_ctx},
		1100	;
		1101
		1102	$prepare_handle->();
		1103
		1104	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1105
		1106	# now handle proxy-CONNECT method
		1107	if ($proxy && $uscheme eq "https") {
		1108	# oh dear, we have to wrap it into a connect request
		1109
		1110	# maybe re-use $uauthority with patched port?
		1111	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		1112	$state{handle}->push_read (line => $qr_nlnl, sub {
		1113	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1114	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1115
		1116	if ($2 == 200) {
		1117	$rpath = $upath;
		1118	$handle_actual_request->();
		1119	} else {
		1120	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1121	}
		1122	});
		1123	} else {
		1124	$handle_actual_request->();
		1125	}
		1126	};
467		1127
468	_get_slot $uhost, sub {	1128	_get_slot $uhost, sub {
469	$state{slot_guard} = shift;	1129	$state{slot_guard} = shift;
470		1130
471	return unless $state{connect_guard};	1131	return unless $state{connect_guard};
472		1132
473	my $connect_cb = sub {	1133	# try to use an existing keepalive connection, but only if we, ourselves, plan
474	$state{fh} = shift	1134	# on a keepalive request (in theory, this should be a separate config option).
475	or do {	1135	if ($persistent && $KA_CACHE{$ka_key}) {
476	my $err = "$!";	1136	$was_persistent = 1;
477	%state = ();
478	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
479	};
480		1137
481	pop; # free memory, save a tree	1138	$state{handle} = ka_fetch $ka_key;
482
483	return unless delete $state{connect_guard};
484
485	# get handle
486	$state{handle} = new AnyEvent::Handle
487	fh => $state{fh},
488	peername => $rhost,
489	tls_ctx => $arg{tls_ctx},
490	# these need to be reconfigured on keepalive handles
491	timeout => $timeout,
492	on_error => sub {
493	%state = ();
494	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
495	},
496	on_eof => sub {
497	%state = ();
498	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
499	},
500	;
501
502	# limit the number of persistent connections
503	# keepalive not yet supported
504	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
505	# ++$KA_COUNT{$_[1]};
506	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
507	# --$KA_COUNT{$_[1]}
508	# };
509	# $hdr{connection} = "keep-alive";
510	# } else {
511	delete $hdr{connection};
512	# }
513
514	$state{handle}->starttls ("connect") if $rscheme eq "https";
515
516	# handle actual, non-tunneled, request
517	my $handle_actual_request = sub {
518	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
519
520	# send request
521	$state{handle}->push_write (	1139	$state{handle}->destroyed
522	"$method $rpath HTTP/1.0\015\012"	1140	and die "got a destructed habndle. pah\n";#d#
523	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)	1141	$prepare_handle->();
524	. "\015\012"	1142	$state{handle}->destroyed
525	. (delete $arg{body})	1143	and die "got a destructed habndle. pa2\n";#d#
526	);
527
528	# return if error occured during push_write()
529	return unless %state;
530
531	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
532
533	# status line and headers
534	$state{handle}->push_read (line => $qr_nlnl, sub {
535	my $keepalive = pop;
536
537	for ("$_[1]") {
538	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
539
540	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
541	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
542
543	push @pseudo,
544	HTTPVersion => $1,
545	Status => $2,
546	Reason => $3,
547	;
548
549	# things seen, not parsed:
550	# p3pP="NON CUR OTPi OUR NOR UNI"
551
552	$hdr{lc $1} .= ",$2"
553	while /\G
554	([^:\000-\037]*):
555	[\011\040]*
556	((?: [^\012]+ | \012[\011\040] )*)
557	\012
558	/gxc;
559
560	/\G$/
561	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
562	}
563
564	# remove the "," prefix we added to all headers above
565	substr $_, 0, 1, ""
566	for values %hdr;
567
568	# patch in all pseudo headers
569	%hdr = (%hdr, @pseudo);
570
571	# redirect handling
572	# microsoft and other shitheads don't give a shit for following standards,
573	# try to support some common forms of broken Location headers.
574	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
575	$hdr{location} =~ s/^\.\/+//;
576
577	my $url = "$rscheme://$uhost:$uport";
578
579	unless ($hdr{location} =~ s/^\///) {
580	$url .= $upath;
581	$url =~ s/\/[^\/]*$//;
582	}
583
584	$hdr{location} = "$url/$hdr{location}";
585	}
586
587	my $redirect;
588
589	if ($recurse) {
590	my $status = $hdr{Status};
591
592	# industry standard is to redirect POST as GET for
593	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
594	# also, the UA should ask the user for 301 and 307 and POST,
595	# industry standard seems to be to simply follow.
596	# we go with the industry standard.
597	if ($status == 301 or $status == 302 or $status == 303) {
598	# HTTP/1.1 is unclear on how to mutate the method
599	$method = "GET" unless $method eq "HEAD";
600	$redirect = 1;
601	} elsif ($status == 307) {
602	$redirect = 1;
603	}
604	}
605
606	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
607	$state{handle}->destroy if $state{handle};
608	%state = ();
609
610	if (defined $_[1]) {
611	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
612	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
613	}
614
615	# set-cookie processing
616	if ($arg{cookie_jar}) {
617	for ($hdr{"set-cookie"}) {
618	# parse NAME=VALUE
619	my @kv;
620
621	while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
622	my $name = $1;
623	my $value = $3;
624
625	unless ($value) {
626	$value = $2;
627	$value =~ s/\\(.)/$1/gs;
628	}
629
630	push @kv, $name => $value;
631
632	last unless /\G\s*;/gc;
633	}
634
635	last unless @kv;
636
637	my $name = shift @kv;
638	my %kv = (value => shift @kv, @kv);
639
640	my $cdom;
641	my $cpath = (delete $kv{path}) || "/";
642
643	if (exists $kv{domain}) {
644	$cdom = delete $kv{domain};
645
646	$cdom =~ s/^\.?/./; # make sure it starts with a "."
647
648	next if $cdom =~ /\.$/;
649
650	# this is not rfc-like and not netscape-like. go figure.
651	my $ndots = $cdom =~ y/.//;
652	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
653	} else {
654	$cdom = $uhost;
655	}
656
657	# store it
658	$arg{cookie_jar}{version} = 1;
659	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
660
661	redo if /\G\s*,/gc;
662	}
663	}
664
665	if ($redirect && exists $hdr{location}) {
666	# we ignore any errors, as it is very common to receive
667	# Content-Length != 0 but no actual body
668	# we also access %hdr, as $_[1] might be an erro
669	http_request (
670	$method => $hdr{location},
671	%arg,
672	recurse => $recurse - 1,
673	Redirect => [$_[0], \%hdr],
674	$cb);
675	} else {
676	$cb->($_[0], \%hdr);
677	}
678	};
679
680	my $len = $hdr{"content-length"};
681
682	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
683	$finish->(undef, 598 => "Request cancelled by on_header");
684	} elsif (
685	$hdr{Status} =~ /^(?:1..|204|205|304)$/
686	or $method eq "HEAD"
687	or (defined $len && !$len)
688	) {
689	# no body
690	$finish->("", undef, undef, 1);
691	} else {
692	# body handling, four different code paths
693	# for want_body_handle, on_body (2x), normal (2x)
694	# we might read too much here, but it does not matter yet (no pipelining)
695	if (!$redirect && $arg{want_body_handle}) {
696	$_[0]->on_eof (undef);
697	$_[0]->on_error (undef);
698	$_[0]->on_read (undef);
699
700	$finish->(delete $state{handle});
701
702	} elsif ($arg{on_body}) {
703	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
704	if ($len) {
705	$_[0]->on_read (sub {
706	$len -= length $_[0]{rbuf};
707
708	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
709	or $finish->(undef, 598 => "Request cancelled by on_body");
710
711	$len > 0
712	or $finish->("", undef, undef, 1);
713	});
714	} else {
715	$_[0]->on_eof (sub {
716	$finish->("");
717	});
718	$_[0]->on_read (sub {
719	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
720	or $finish->(undef, 598 => "Request cancelled by on_body");
721	});
722	}
723	} else {
724	$_[0]->on_eof (undef);
725
726	if ($len) {
727	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
728	$_[0]->on_read (sub {
729	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
730	if $len <= length $_[0]{rbuf};
731	});
732	} else {
733	$_[0]->on_error (sub {
734	($! == Errno::EPIPE || !$!)
735	? $finish->(delete $_[0]{rbuf})
736	: $finish->(undef, 599 => $_[2]);
737	});
738	$_[0]->on_read (sub { });
739	}
740	}
741	}
742	});
743	};
744
745	# now handle proxy-CONNECT method
746	if ($proxy && $uscheme eq "https") {
747	# oh dear, we have to wrap it into a connect request
748
749	# maybe re-use $uauthority with patched port?
750	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
751	$state{handle}->push_read (line => $qr_nlnl, sub {
752	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
753	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
754
755	if ($2 == 200) {
756	$rpath = $upath;
757	&$handle_actual_request;	1144	$handle_actual_request->();
758	} else {	1145	$state{handle}->destroyed
759	%state = ();	1146	and die "got a destructed habndle. pa3\n";#d#
760	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });	1147
761	}
762	});
763	} else {	1148	} else {
764	&$handle_actual_request;
765	}
766	};
767
768	my $tcp_connect = $arg{tcp_connect}	1149	my $tcp_connect = $arg{tcp_connect}
769	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1150	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
770		1151
771	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });	1152	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
772		1153	}
773	};	1154	};
774		1155
775	defined wantarray && AnyEvent::Util::guard { %state = () }	1156	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
776	}	1157	}
777		1158
778	sub http_get($@) {	1159	sub http_get($@) {
779	unshift @_, "GET";	1160	unshift @_, "GET";
780	&http_request	1161	&http_request
…		…
798	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1179	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
799	the actual connection, which in turn uses AnyEvent::DNS to resolve	1180	the actual connection, which in turn uses AnyEvent::DNS to resolve
800	hostnames. The latter is a simple stub resolver and does no caching	1181	hostnames. The latter is a simple stub resolver and does no caching
801	on its own. If you want DNS caching, you currently have to provide	1182	on its own. If you want DNS caching, you currently have to provide
802	your own default resolver (by storing a suitable resolver object in	1183	your own default resolver (by storing a suitable resolver object in
803	C<$AnyEvent::DNS::RESOLVER>).	1184	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
804		1185
805	=head2 GLOBAL FUNCTIONS AND VARIABLES	1186	=head2 GLOBAL FUNCTIONS AND VARIABLES
806		1187
807	=over 4	1188	=over 4
808		1189
809	=item AnyEvent::HTTP::set_proxy "proxy-url"	1190	=item AnyEvent::HTTP::set_proxy "proxy-url"
810		1191
811	Sets the default proxy server to use. The proxy-url must begin with a	1192	Sets the default proxy server to use. The proxy-url must begin with a
812	string of the form C<http://host:port> (optionally C<https:...>), croaks	1193	string of the form C<http://host:port>, croaks otherwise.
813	otherwise.
814		1194
815	To clear an already-set proxy, use C<undef>.	1195	To clear an already-set proxy, use C<undef>.
		1196
		1197	When AnyEvent::HTTP is laoded for the first time it will query the
		1198	default proxy from the operating system, currently by looking at
		1199	C<$ENV{http_proxy>}.
		1200
		1201	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1202
		1203	Remove all cookies from the cookie jar that have been expired. If
		1204	C<$session_end> is given and true, then additionally remove all session
		1205	cookies.
		1206
		1207	You should call this function (with a true C<$session_end>) before you
		1208	save cookies to disk, and you should call this function after loading them
		1209	again. If you have a long-running program you can additonally call this
		1210	function from time to time.
		1211
		1212	A cookie jar is initially an empty hash-reference that is managed by this
		1213	module. It's format is subject to change, but currently it is like this:
		1214
		1215	The key C<version> has to contain C<1>, otherwise the hash gets
		1216	emptied. All other keys are hostnames or IP addresses pointing to
		1217	hash-references. The key for these inner hash references is the
		1218	server path for which this cookie is meant, and the values are again
		1219	hash-references. The keys of those hash-references is the cookie name, and
		1220	the value, you guessed it, is another hash-reference, this time with the
		1221	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1222	which have been replaced by a C<_expires> key that contains the cookie
		1223	expiry timestamp.
		1224
		1225	Here is an example of a cookie jar with a single cookie, so you have a
		1226	chance of understanding the above paragraph:
		1227
		1228	{
		1229	version => 1,
		1230	"10.0.0.1" => {
		1231	"/" => {
		1232	"mythweb_id" => {
		1233	_expires => 1293917923,
		1234	value => "ooRung9dThee3ooyXooM1Ohm",
		1235	},
		1236	},
		1237	},
		1238	}
816		1239
817	=item $date = AnyEvent::HTTP::format_date $timestamp	1240	=item $date = AnyEvent::HTTP::format_date $timestamp
818		1241
819	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP	1242	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
820	Date (RFC 2616).	1243	Date (RFC 2616).
821		1244
822	=item $timestamp = AnyEvent::HTTP::parse_date $date	1245	=item $timestamp = AnyEvent::HTTP::parse_date $date
823		1246
824	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX	1247	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1248	bunch of minor variations of those, and returns the corresponding POSIX
825	timestamp, or C<undef> if the date cannot be parsed.	1249	timestamp, or C<undef> if the date cannot be parsed.
826		1250
827	=item $AnyEvent::HTTP::MAX_RECURSE	1251	=item $AnyEvent::HTTP::MAX_RECURSE
828		1252
829	The default value for the C<recurse> request parameter (default: C<10>).	1253	The default value for the C<recurse> request parameter (default: C<10>).
		1254
		1255	=item $AnyEvent::HTTP::TIMEOUT
		1256
		1257	The default timeout for conenction operations (default: C<300>).
830		1258
831	=item $AnyEvent::HTTP::USERAGENT	1259	=item $AnyEvent::HTTP::USERAGENT
832		1260
833	The default value for the C<User-Agent> header (the default is	1261	The default value for the C<User-Agent> header (the default is
834	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1262	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
835		1263
836	=item $AnyEvent::HTTP::MAX_PER_HOST	1264	=item $AnyEvent::HTTP::MAX_PER_HOST
837		1265
838	The maximum number of concurrent connections to the same host (identified	1266	The maximum number of concurrent connections to the same host (identified
839	by the hostname). If the limit is exceeded, then the additional requests	1267	by the hostname). If the limit is exceeded, then the additional requests
840	are queued until previous connections are closed.	1268	are queued until previous connections are closed. Both persistent and
		1269	non-persistent connections are counted in this limit.
841		1270
842	The default value for this is C<4>, and it is highly advisable to not	1271	The default value for this is C<4>, and it is highly advisable to not
843	increase it.	1272	increase it much.
		1273
		1274	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1275	connections, older browsers used 2, newers (such as firefox 3) typically
		1276	use 6, and Opera uses 8 because like, they have the fastest browser and
		1277	give a shit for everybody else on the planet.
		1278
		1279	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1280
		1281	The time after which idle persistent conenctions get closed by
		1282	AnyEvent::HTTP (default: C<3>).
844		1283
845	=item $AnyEvent::HTTP::ACTIVE	1284	=item $AnyEvent::HTTP::ACTIVE
846		1285
847	The number of active connections. This is not the number of currently	1286	The number of active connections. This is not the number of currently
848	running requests, but the number of currently open and non-idle TCP	1287	running requests, but the number of currently open and non-idle TCP
849	connections. This number of can be useful for load-leveling.	1288	connections. This number can be useful for load-leveling.
850		1289
851	=back	1290	=back
852		1291
853	=cut	1292	=cut
854		1293
…		…
869	sub parse_date($) {	1308	sub parse_date($) {
870	my ($date) = @_;	1309	my ($date) = @_;
871		1310
872	my ($d, $m, $y, $H, $M, $S);	1311	my ($d, $m, $y, $H, $M, $S);
873		1312
874	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$/) {	1313	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$/) {
875	# RFC 822/1123, required by RFC 2616	1314	# RFC 822/1123, required by RFC 2616 (with " ")
		1315	# cookie dates (with "-")
		1316
876	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);	1317	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
877		1318
878	} 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$/) {	1319	} 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$/) {
879	# RFC 850	1320	# RFC 850
880	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);	1321	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
881		1322
882	} 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])$/) {	1323	} 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])$/) {
883	# ISO C's asctime	1324	# ISO C's asctime
884	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);	1325	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
885	}	1326	}
886	# other formats fail in the loop below	1327	# other formats fail in the loop below
887		1328
…		…
895	undef	1336	undef
896	}	1337	}
897		1338
898	sub set_proxy($) {	1339	sub set_proxy($) {
899	if (length $_[0]) {	1340	if (length $_[0]) {
900	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1341	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
901	or Carp::croak "$_[0]: invalid proxy URL";	1342	or Carp::croak "$_[0]: invalid proxy URL";
902	$PROXY = [$2, $3 || 3128, $1]	1343	$PROXY = [$2, $3 || 3128, $1]
903	} else {	1344	} else {
904	undef $PROXY;	1345	undef $PROXY;
905	}	1346	}
…		…
908	# initialise proxy from environment	1349	# initialise proxy from environment
909	eval {	1350	eval {
910	set_proxy $ENV{http_proxy};	1351	set_proxy $ENV{http_proxy};
911	};	1352	};
912		1353
		1354	=head2 SHOWCASE
		1355
		1356	This section contaisn some more elaborate "real-world" examples or code
		1357	snippets.
		1358
		1359	=head2 HTTP/1.1 FILE DOWNLOAD
		1360
		1361	Downloading files with HTTP can be quite tricky, especially when something
		1362	goes wrong and you want to resume.
		1363
		1364	Here is a function that initiates and resumes a download. It uses the
		1365	last modified time to check for file content changes, and works with many
		1366	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1367	on older servers.
		1368
		1369	It calls the completion callback with either C<undef>, which means a
		1370	nonretryable error occured, C<0> when the download was partial and should
		1371	be retried, and C<1> if it was successful.
		1372
		1373	use AnyEvent::HTTP;
		1374
		1375	sub download($$$) {
		1376	my ($url, $file, $cb) = @_;
		1377
		1378	open my $fh, "+<", $file
		1379	or die "$file: $!";
		1380
		1381	my %hdr;
		1382	my $ofs = 0;
		1383
		1384	warn stat $fh;
		1385	warn -s _;
		1386	if (stat $fh and -s _) {
		1387	$ofs = -s _;
		1388	warn "-s is ", $ofs;#d#
		1389	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1390	$hdr{"range"} = "bytes=$ofs-";
		1391	}
		1392
		1393	http_get $url,
		1394	headers => \%hdr,
		1395	on_header => sub {
		1396	my ($hdr) = @_;
		1397
		1398	if ($hdr->{Status} == 200 && $ofs) {
		1399	# resume failed
		1400	truncate $fh, $ofs = 0;
		1401	}
		1402
		1403	sysseek $fh, $ofs, 0;
		1404
		1405	1
		1406	},
		1407	on_body => sub {
		1408	my ($data, $hdr) = @_;
		1409
		1410	if ($hdr->{Status} =~ /^2/) {
		1411	length $data == syswrite $fh, $data
		1412	or return; # abort on write errors
		1413	}
		1414
		1415	1
		1416	},
		1417	sub {
		1418	my (undef, $hdr) = @_;
		1419
		1420	my $status = $hdr->{Status};
		1421
		1422	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1423	utime $fh, $time, $time;
		1424	}
		1425
		1426	if ($status == 200 || $status == 206 || $status == 416) {
		1427	# download ok || resume ok || file already fully downloaded
		1428	$cb->(1, $hdr);
		1429
		1430	} elsif ($status == 412) {
		1431	# file has changed while resuming, delete and retry
		1432	unlink $file;
		1433	$cb->(0, $hdr);
		1434
		1435	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1436	# retry later
		1437	$cb->(0, $hdr);
		1438
		1439	} else {
		1440	$cb->(undef, $hdr);
		1441	}
		1442	}
		1443	;
		1444	}
		1445
		1446	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1447	if ($_[0]) {
		1448	print "OK!\n";
		1449	} elsif (defined $_[0]) {
		1450	print "please retry later\n";
		1451	} else {
		1452	print "ERROR\n";
		1453	}
		1454	};
		1455
913	=head2 SOCKS PROXIES	1456	=head3 SOCKS PROXIES
914		1457
915	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1458	Socks proxies are not directly supported by AnyEvent::HTTP. You can
916	compile your perl to support socks, or use an external program such as	1459	compile your perl to support socks, or use an external program such as
917	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy	1460	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
918	transparently.	1461	transparently.

Diff Legend

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