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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.117 by root, Mon Sep 9 21:41:43 2013 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 Carp;	43	use Errno ();
45		44
46	use AnyEvent ();	45	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	46	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
50		48
51	use base Exporter::;	49	use base Exporter::;
52		50
53	our $VERSION = '1.01';	51	our $VERSION = '2.15';
54		52
55	our @EXPORT = qw(http_get http_post http_head http_request);	53	our @EXPORT = qw(http_get http_post http_head http_request);
56		54
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	55	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	56	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	57	our $PERSISTENT_TIMEOUT = 3;
61	our $TIMEOUT = 300;	58	our $TIMEOUT = 300;
62		59	our $MAX_PER_HOST = 4; # changing this is evil
63	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;
65	our $MAX_PER_HOST = 4;
66		60
67	our $PROXY;	61	our $PROXY;
68	our $ACTIVE = 0;	62	our $ACTIVE = 0;
69		63
70	my %KA_COUNT; # number of open keep-alive connections per host	64	my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array
71	my %CO_SLOT; # number of open connections, and wait queue, per host	65	my %CO_SLOT; # number of open connections, and wait queue, per host
72		66
73	=item http_get $url, key => value..., $cb->($data, $headers)	67	=item http_get $url, key => value..., $cb->($data, $headers)
74		68
75	Executes an HTTP-GET request. See the http_request function for details on	69	Executes an HTTP-GET request. See the http_request function for details on
76	additional parameters.	70	additional parameters and the return value.
77		71
78	=item http_head $url, key => value..., $cb->($data, $headers)	72	=item http_head $url, key => value..., $cb->($data, $headers)
79		73
80	Executes an HTTP-HEAD request. See the http_request function for details on	74	Executes an HTTP-HEAD request. See the http_request function for details
81	additional parameters.	75	on additional parameters and the return value.
82		76
83	=item http_post $url, $body, key => value..., $cb->($data, $headers)	77	=item http_post $url, $body, key => value..., $cb->($data, $headers)
84		78
85	Executes an HTTP-POST request with a request body of C<$bod>. See the	79	Executes an HTTP-POST request with a request body of C<$body>. See the
86	http_request function for details on additional parameters.	80	http_request function for details on additional parameters and the return
		81	value.
87		82
88	=item http_request $method => $url, key => value..., $cb->($data, $headers)	83	=item http_request $method => $url, key => value..., $cb->($data, $headers)
89		84
90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	85	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	86	must be an absolute http or https URL.
92		87
		88	When called in void context, nothing is returned. In other contexts,
		89	C<http_request> returns a "cancellation guard" - you have to keep the
		90	object at least alive until the callback get called. If the object gets
		91	destroyed before the callback is called, the request will be cancelled.
		92
93	The callback will be called with the response data as first argument	93	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	94	(or C<undef> if an error occurred), and a hash-ref with response headers
95	response headers as second argument.	95	(and trailers) as second argument.
96		96
97	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
98	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	98	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
99	C<Reason> contain the three parts of the HTTP Status-Line of the same	99	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
		100	three parts of the HTTP Status-Line of the same name. If an error occurs
		101	during the body phase of a request, then the original C<Status> and
		102	C<Reason> values from the header are available as C<OrigStatus> and
		103	C<OrigReason>.
		104
		105	The pseudo-header C<URL> contains the actual URL (which can differ from
		106	the requested URL when following redirects - for example, you might get
		107	an error that your URL scheme is not supported even though your URL is a
		108	valid http URL because it redirected to an ftp URL, in which case you can
		109	look at the URL pseudo header).
		110
		111	The pseudo-header C<Redirect> only exists when the request was a result
		112	of an internal redirect. In that case it is an array reference with
		113	the C<($data, $headers)> from the redirect response. Note that this
		114	response could in turn be the result of a redirect itself, and C<<
		115	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		116	response, and so on.
		117
100	name. If the server sends a header multiple lines, then their contents	118	If the server sends a header multiple times, then their contents will be
101	will be joined together with C<\x00>.	119	joined together with a comma (C<,>), as per the HTTP spec.
102		120
103	If an internal error occurs, such as not being able to resolve a hostname,	121	If an internal error occurs, such as not being able to resolve a hostname,
104	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	122	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
105	and the C<Reason> pseudo-header will contain an error message.	123	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
		124	message. Currently the following status codes are used:
		125
		126	=over 4
		127
		128	=item 595 - errors during connection establishment, proxy handshake.
		129
		130	=item 596 - errors during TLS negotiation, request sending and header processing.
		131
		132	=item 597 - errors during body receiving or processing.
		133
		134	=item 598 - user aborted request via C<on_header> or C<on_body>.
		135
		136	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		137
		138	=back
106		139
107	A typical callback might look like this:	140	A typical callback might look like this:
108		141
109	sub {	142	sub {
110	my ($body, $hdr) = @_;	143	my ($body, $hdr) = @_;
…		…
121		154
122	=over 4	155	=over 4
123		156
124	=item recurse => $count (default: $MAX_RECURSE)	157	=item recurse => $count (default: $MAX_RECURSE)
125		158
126	Whether to recurse requests or not, e.g. on redirects, authentication	159	Whether to recurse requests or not, e.g. on redirects, authentication and
127	retries and so on, and how often to do so.	160	other retries and so on, and how often to do so.
128		161
129	=item headers => hashref	162	=item headers => hashref
130		163
131	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
132	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
133	and will provide defaults for C<User-Agent:> and C<Referer:>.	166	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		167	(this can be suppressed by using C<undef> for these headers in which case
		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.
		173
		174	Also, make sure that your headers names and values do not contain any
		175	embedded newlines.
134		176
135	=item timeout => $seconds	177	=item timeout => $seconds
136		178
137	The time-out to use for various stages - each connect attempt will reset	179	The time-out to use for various stages - each connect attempt will reset
138	the timeout, as will read or write activity. Default timeout is 5 minutes.	180	the timeout, as will read or write activity, i.e. this is not an overall
		181	timeout.
		182
		183	Default timeout is 5 minutes.
139		184
140	=item proxy => [$host, $port[, $scheme]] or undef	185	=item proxy => [$host, $port[, $scheme]] or undef
141		186
142	Use the given http proxy for all requests. If not specified, then the	187	Use the given http proxy for all requests, or no proxy if C<undef> is
143	default proxy (as specified by C<$ENV{http_proxy}>) is used.	188	used.
144		189
145	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	190	C<$scheme> must be either missing or must be C<http> for HTTP.
146	HTTPS.	191
		192	If not specified, then the default proxy is used (see
		193	C<AnyEvent::HTTP::set_proxy>).
147		194
148	=item body => $string	195	=item body => $string
149		196
150	The request body, usually empty. Will be-sent as-is (future versions of	197	The request body, usually empty. Will be sent as-is (future versions of
151	this module might offer more options).	198	this module might offer more options).
152		199
153	=item cookie_jar => $hash_ref	200	=item cookie_jar => $hash_ref
154		201
155	Passing this parameter enables (simplified) cookie-processing, loosely	202	Passing this parameter enables (simplified) cookie-processing, loosely
156	based on the original netscape specification.	203	based on the original netscape specification.
157		204
158	The C<$hash_ref> must be an (initially empty) hash reference which will	205	The C<$hash_ref> must be an (initially empty) hash reference which
159	get updated automatically. It is possible to save the cookie_jar to	206	will get updated automatically. It is possible to save the cookie jar
160	persistent storage with something like JSON or Storable, but this is not	207	to persistent storage with something like JSON or Storable - see the
161	recommended, as expire times are currently being ignored.	208	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		209	expired or session-only cookies, and also for documentation on the format
		210	of the cookie jar.
162		211
163	Note that this cookie implementation is not of very high quality, nor	212	Note that this cookie implementation is not meant to be complete. If
164	meant to be complete. If you want complete cookie management you have to	213	you want complete cookie management you have to do that on your
165	do that on your own. C<cookie_jar> is meant as a quick fix to get some	214	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
166	cookie-using sites working. Cookies are a privacy disaster, do not use	215	working. Cookies are a privacy disaster, do not use them unless required
167	them unless required to.	216	to.
		217
		218	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		219	headers will be set and handled by this module, otherwise they will be
		220	left untouched.
		221
		222	=item tls_ctx => $scheme \| $tls_ctx
		223
		224	Specifies the AnyEvent::TLS context to be used for https connections. This
		225	parameter follows the same rules as the C<tls_ctx> parameter to
		226	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		227	C<high> can be specified, which give you a predefined low-security (no
		228	verification, highest compatibility) and high-security (CA and common-name
		229	verification) TLS context.
		230
		231	The default for this option is C<low>, which could be interpreted as "give
		232	me the page, no matter what".
		233
		234	See also the C<sessionid> parameter.
		235
		236	=item session => $string
		237
		238	The module might reuse connections to the same host internally. Sometimes
		239	(e.g. when using TLS), you do not want to reuse connections from other
		240	sessions. This can be achieved by setting this parameter to some unique
		241	ID (such as the address of an object storing your state data, or the TLS
		242	context) - only connections using the same unique ID will be reused.
		243
		244	=item on_prepare => $callback->($fh)
		245
		246	In rare cases you need to "tune" the socket before it is used to
		247	connect (for example, to bind it on a given IP address). This parameter
		248	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		249	and behaves exactly the same way (e.g. it has to provide a
		250	timeout). See the description for the C<$prepare_cb> argument of
		251	C<AnyEvent::Socket::tcp_connect> for details.
		252
		253	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		254
		255	In even rarer cases you want total control over how AnyEvent::HTTP
		256	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		257	to do this, but you can provide your own C<tcp_connect> function -
		258	obviously, it has to follow the same calling conventions, except that it
		259	may always return a connection guard object.
		260
		261	There are probably lots of weird uses for this function, starting from
		262	tracing the hosts C<http_request> actually tries to connect, to (inexact
		263	but fast) host => IP address caching or even socks protocol support.
		264
		265	=item on_header => $callback->($headers)
		266
		267	When specified, this callback will be called with the header hash as soon
		268	as headers have been successfully received from the remote server (not on
		269	locally-generated errors).
		270
		271	It has to return either true (in which case AnyEvent::HTTP will continue),
		272	or false, in which case AnyEvent::HTTP will cancel the download (and call
		273	the finish callback with an error code of C<598>).
		274
		275	This callback is useful, among other things, to quickly reject unwanted
		276	content, which, if it is supposed to be rare, can be faster than first
		277	doing a C<HEAD> request.
		278
		279	The downside is that cancelling the request makes it impossible to re-use
		280	the connection. Also, the C<on_header> callback will not receive any
		281	trailer (headers sent after the response body).
		282
		283	Example: cancel the request unless the content-type is "text/html".
		284
		285	on_header => sub {
		286	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		287	},
		288
		289	=item on_body => $callback->($partial_body, $headers)
		290
		291	When specified, all body data will be passed to this callback instead of
		292	to the completion callback. The completion callback will get the empty
		293	string instead of the body data.
		294
		295	It has to return either true (in which case AnyEvent::HTTP will continue),
		296	or false, in which case AnyEvent::HTTP will cancel the download (and call
		297	the completion callback with an error code of C<598>).
		298
		299	The downside to cancelling the request is that it makes it impossible to
		300	re-use the connection.
		301
		302	This callback is useful when the data is too large to be held in memory
		303	(so the callback writes it to a file) or when only some information should
		304	be extracted, or when the body should be processed incrementally.
		305
		306	It is usually preferred over doing your own body handling via
		307	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		308	only used to create a connection, C<want_body_handle> is the better
		309	alternative, as it allows you to install your own event handler, reducing
		310	resource usage.
		311
		312	=item want_body_handle => $enable
		313
		314	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		315	changes considerably: after parsing the headers, and instead of
		316	downloading the body (if any), the completion callback will be
		317	called. Instead of the C<$body> argument containing the body data, the
		318	callback will receive the L<AnyEvent::Handle> object associated with the
		319	connection. In error cases, C<undef> will be passed. When there is no body
		320	(e.g. status C<304>), the empty string will be passed.
		321
		322	The handle object might or might not be in TLS mode, might be connected
		323	to a proxy, be a persistent connection, use chunked transfer encoding
		324	etc., and configured in unspecified ways. The user is responsible for this
		325	handle (it will not be used by this module anymore).
		326
		327	This is useful with some push-type services, where, after the initial
		328	headers, an interactive protocol is used (typical example would be the
		329	push-style twitter API which starts a JSON/XML stream).
		330
		331	If you think you need this, first have a look at C<on_body>, to see if
		332	that doesn't solve your problem in a better way.
		333
		334	=item persistent => $boolean
		335
		336	Try to create/reuse a persistent connection. When this flag is set
		337	(default: true for idempotent requests, false for all others), then
		338	C<http_request> tries to re-use an existing (previously-created)
		339	persistent connection to the host and, failing that, tries to create a new
		340	one.
		341
		342	Requests failing in certain ways will be automatically retried once, which
		343	is dangerous for non-idempotent requests, which is why it defaults to off
		344	for them. The reason for this is because the bozos who designed HTTP/1.1
		345	made it impossible to distinguish between a fatal error and a normal
		346	connection timeout, so you never know whether there was a problem with
		347	your request or not.
		348
		349	When reusing an existent connection, many parameters (such as TLS context)
		350	will be ignored. See the C<session> parameter for a workaround.
		351
		352	=item keepalive => $boolean
		353
		354	Only used when C<persistent> is also true. This parameter decides whether
		355	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		356	(as opposed to only a HTTP/1.1 persistent connection).
		357
		358	The default is true, except when using a proxy, in which case it defaults
		359	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		360
		361	=item handle_params => { key => value ... }
		362
		363	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		364	constructor that is called - not all requests will create a handle, and
		365	sometimes more than one is created, so this parameter is only good for
		366	setting hints.
		367
		368	Example: set the maximum read size to 4096, to potentially conserve memory
		369	at the cost of speed.
		370
		371	handle_params => {
		372	max_read_size => 4096,
		373	},
168		374
169	=back	375	=back
170		376
171	Example: make a simple HTTP GET request for http://www.nethype.de/	377	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		378	the response body.
172		379
173	http_request GET => "http://www.nethype.de/", sub {	380	http_request GET => "http://www.nethype.de/", sub {
174	my ($body, $hdr) = @_;	381	my ($body, $hdr) = @_;
175	print "$body\n";	382	print "$body\n";
176	};	383	};
177		384
178	Example: make a HTTP HEAD request on https://www.google.com/, use a	385	Example: do a HTTP HEAD request on https://www.google.com/, use a
179	timeout of 30 seconds.	386	timeout of 30 seconds.
180		387
181	http_request	388	http_request
182	GET => "https://www.google.com",	389	HEAD => "https://www.google.com",
		390	headers => { "user-agent" => "MySearchClient 1.0" },
183	timeout => 30,	391	timeout => 30,
184	sub {	392	sub {
185	my ($body, $hdr) = @_;	393	my ($body, $hdr) = @_;
186	use Data::Dumper;	394	use Data::Dumper;
187	print Dumper $hdr;	395	print Dumper $hdr;
188	}	396	}
189	;	397	;
190		398
		399	Example: do another simple HTTP GET request, but immediately try to
		400	cancel it.
		401
		402	my $request = http_request GET => "http://www.nethype.de/", sub {
		403	my ($body, $hdr) = @_;
		404	print "$body\n";
		405	};
		406
		407	undef $request;
		408
191	=cut	409	=cut
		410
		411	#############################################################################
		412	# wait queue/slots
192		413
193	sub _slot_schedule;	414	sub _slot_schedule;
194	sub _slot_schedule($) {	415	sub _slot_schedule($) {
195	my $host = shift;	416	my $host = shift;
196		417
…		…
218	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	439	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
219		440
220	_slot_schedule $_[0];	441	_slot_schedule $_[0];
221	}	442	}
222		443
		444	#############################################################################
		445	# cookie handling
		446
		447	# expire cookies
		448	sub cookie_jar_expire($;$) {
		449	my ($jar, $session_end) = @_;
		450
		451	%$jar = () if $jar->{version} != 1;
		452
		453	my $anow = AE::now;
		454
		455	while (my ($chost, $paths) = each %$jar) {
		456	next unless ref $paths;
		457
		458	while (my ($cpath, $cookies) = each %$paths) {
		459	while (my ($cookie, $kv) = each %$cookies) {
		460	if (exists $kv->{_expires}) {
		461	delete $cookies->{$cookie}
		462	if $anow > $kv->{_expires};
		463	} elsif ($session_end) {
		464	delete $cookies->{$cookie};
		465	}
		466	}
		467
		468	delete $paths->{$cpath}
		469	unless %$cookies;
		470	}
		471
		472	delete $jar->{$chost}
		473	unless %$paths;
		474	}
		475	}
		476
		477	# extract cookies from jar
		478	sub cookie_jar_extract($$$$) {
		479	my ($jar, $scheme, $host, $path) = @_;
		480
		481	%$jar = () if $jar->{version} != 1;
		482
		483	my @cookies;
		484
		485	while (my ($chost, $paths) = each %$jar) {
		486	next unless ref $paths;
		487
		488	if ($chost =~ /^\./) {
		489	next unless $chost eq substr $host, -length $chost;
		490	} elsif ($chost =~ /\./) {
		491	next unless $chost eq $host;
		492	} else {
		493	next;
		494	}
		495
		496	while (my ($cpath, $cookies) = each %$paths) {
		497	next unless $cpath eq substr $path, 0, length $cpath;
		498
		499	while (my ($cookie, $kv) = each %$cookies) {
		500	next if $scheme ne "https" && exists $kv->{secure};
		501
		502	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		503	delete $cookies->{$cookie};
		504	next;
		505	}
		506
		507	my $value = $kv->{value};
		508
		509	if ($value =~ /[=;,[:space:]]/) {
		510	$value =~ s/([\\"])/\\$1/g;
		511	$value = "\"$value\"";
		512	}
		513
		514	push @cookies, "$cookie=$value";
		515	}
		516	}
		517	}
		518
		519	\@cookies
		520	}
		521
		522	# parse set_cookie header into jar
		523	sub cookie_jar_set_cookie($$$$) {
		524	my ($jar, $set_cookie, $host, $date) = @_;
		525
		526	my $anow = int AE::now;
		527	my $snow; # server-now
		528
		529	for ($set_cookie) {
		530	# parse NAME=VALUE
		531	my @kv;
		532
		533	# expires is not http-compliant in the original cookie-spec,
		534	# we support the official date format and some extensions
		535	while (
		536	m{
		537	\G\s*
		538	(?:
		539	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
		540	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^;,[:space:]]) ) )?
		541	)
		542	}gcxsi
		543	) {
		544	my $name = $2;
		545	my $value = $4;
		546
		547	if (defined $1) {
		548	# expires
		549	$name = "expires";
		550	$value = $1;
		551	} elsif (defined $3) {
		552	# quoted
		553	$value = $3;
		554	$value =~ s/\\(.)/$1/gs;
		555	}
		556
		557	push @kv, @kv ? lc $name : $name, $value;
		558
		559	last unless /\G\s*;/gc;
		560	}
		561
		562	last unless @kv;
		563
		564	my $name = shift @kv;
		565	my %kv = (value => shift @kv, @kv);
		566
		567	if (exists $kv{"max-age"}) {
		568	$kv{_expires} = $anow + delete $kv{"max-age"};
		569	} elsif (exists $kv{expires}) {
		570	$snow \|\|= parse_date ($date) \|\| $anow;
		571	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		572	} else {
		573	delete $kv{_expires};
		574	}
		575
		576	my $cdom;
		577	my $cpath = (delete $kv{path}) \|\| "/";
		578
		579	if (exists $kv{domain}) {
		580	$cdom = delete $kv{domain};
		581
		582	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		583
		584	next if $cdom =~ /\.$/;
		585
		586	# this is not rfc-like and not netscape-like. go figure.
		587	my $ndots = $cdom =~ y/.//;
		588	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		589	} else {
		590	$cdom = $host;
		591	}
		592
		593	# store it
		594	$jar->{version} = 1;
		595	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		596
		597	redo if /\G\s*,/gc;
		598	}
		599	}
		600
		601	#############################################################################
		602	# keepalive/persistent connection cache
		603
		604	# fetch a connection from the keepalive cache
		605	sub ka_fetch($) {
		606	my $ka_key = shift;
		607
		608	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		609	delete $KA_CACHE{$ka_key}
		610	unless @{ $KA_CACHE{$ka_key} };
		611
		612	$hdl
		613	}
		614
		615	sub ka_store($$) {
		616	my ($ka_key, $hdl) = @_;
		617
		618	my $kaa = $KA_CACHE{$ka_key} \|\|= [];
		619
		620	my $destroy = sub {
		621	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		622
		623	$hdl->destroy;
		624
		625	@ka
		626	? $KA_CACHE{$ka_key} = \@ka
		627	: delete $KA_CACHE{$ka_key};
		628	};
		629
		630	# on error etc., destroy
		631	$hdl->on_error ($destroy);
		632	$hdl->on_eof ($destroy);
		633	$hdl->on_read ($destroy);
		634	$hdl->timeout ($PERSISTENT_TIMEOUT);
		635
		636	push @$kaa, $hdl;
		637	shift @$kaa while @$kaa > $MAX_PER_HOST;
		638	}
		639
		640	#############################################################################
		641	# utilities
		642
		643	# continue to parse $_ for headers and place them into the arg
		644	sub _parse_hdr() {
		645	my %hdr;
		646
		647	# things seen, not parsed:
		648	# p3pP="NON CUR OTPi OUR NOR UNI"
		649
		650	$hdr{lc $1} .= ",$2"
		651	while /\G
		652	([^:\000-\037]*):
		653	[\011\040]*
		654	((?: [^\012]+ \| \012[\011\040] )*)
		655	\012
		656	/gxc;
		657
		658	/\G$/
		659	or return;
		660
		661	# remove the "," prefix we added to all headers above
		662	substr $_, 0, 1, ""
		663	for values %hdr;
		664
		665	\%hdr
		666	}
		667
		668	#############################################################################
		669	# http_get
		670
		671	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		672
		673	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		674	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		675
		676	# maybe it should just become a normal object :/
		677
		678	sub _destroy_state(\%) {
		679	my ($state) = @_;
		680
		681	$state->{handle}->destroy if $state->{handle};
		682	%$state = ();
		683	}
		684
		685	sub _error(\%$$) {
		686	my ($state, $cb, $hdr) = @_;
		687
		688	&_destroy_state ($state);
		689
		690	$cb->(undef, $hdr);
		691	()
		692	}
		693
		694	our %IDEMPOTENT = (
		695	DELETE => 1,
		696	GET => 1,
		697	HEAD => 1,
		698	OPTIONS => 1,
		699	PUT => 1,
		700	TRACE => 1,
		701
		702	ACL => 1,
		703	"BASELINE-CONTROL" => 1,
		704	BIND => 1,
		705	CHECKIN => 1,
		706	CHECKOUT => 1,
		707	COPY => 1,
		708	LABEL => 1,
		709	LINK => 1,
		710	MERGE => 1,
		711	MKACTIVITY => 1,
		712	MKCALENDAR => 1,
		713	MKCOL => 1,
		714	MKREDIRECTREF => 1,
		715	MKWORKSPACE => 1,
		716	MOVE => 1,
		717	ORDERPATCH => 1,
		718	PROPFIND => 1,
		719	PROPPATCH => 1,
		720	REBIND => 1,
		721	REPORT => 1,
		722	SEARCH => 1,
		723	UNBIND => 1,
		724	UNCHECKOUT => 1,
		725	UNLINK => 1,
		726	UNLOCK => 1,
		727	UPDATE => 1,
		728	UPDATEREDIRECTREF => 1,
		729	"VERSION-CONTROL" => 1,
		730	);
		731
223	sub http_request($$@) {	732	sub http_request($$@) {
224	my $cb = pop;	733	my $cb = pop;
225	my ($method, $url, %arg) = @_;	734	my ($method, $url, %arg) = @_;
226		735
227	my %hdr;	736	my %hdr;
		737
		738	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		739	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
228		740
229	$method = uc $method;	741	$method = uc $method;
230		742
231	if (my $hdr = $arg{headers}) {	743	if (my $hdr = $arg{headers}) {
232	while (my ($k, $v) = each %$hdr) {	744	while (my ($k, $v) = each %$hdr) {
233	$hdr{lc $k} = $v;	745	$hdr{lc $k} = $v;
234	}	746	}
235	}	747	}
236		748
		749	# pseudo headers for all subsequent responses
		750	my @pseudo = (URL => $url);
		751	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		752
237	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	753	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
238		754
239	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	755	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
240	if $recurse < 0;	756	if $recurse < 0;
241		757
242	my $proxy = $arg{proxy} \|\| $PROXY;	758	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
243	my $timeout = $arg{timeout} \|\| $TIMEOUT;	759	my $timeout = $arg{timeout} \|\| $TIMEOUT;
244		760
245	$hdr{"user-agent"} \|\|= $USERAGENT;
246
247	my ($scheme, $authority, $upath, $query, $fragment) =	761	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
248	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	762	$url =~ m\|^([^:]+):(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?$\|;
249		763
250	$scheme = lc $scheme;	764	$uscheme = lc $uscheme;
251		765
252	my $uport = $scheme eq "http" ? 80	766	my $uport = $uscheme eq "http" ? 80
253	: $scheme eq "https" ? 443	767	: $uscheme eq "https" ? 443
254	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	768	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
255		769
256	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
257
258	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	770	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
259	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	771	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
260		772
261	my $uhost = $1;	773	my $uhost = lc $1;
262	$uport = $2 if defined $2;	774	$uport = $2 if defined $2;
263		775
		776	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		777	unless exists $hdr{host};
		778
264	$uhost =~ s/^\[(.*)\]$/$1/;	779	$uhost =~ s/^\[(.*)\]$/$1/;
265	$upath .= "?$query" if length $query;	780	$upath .= $query if length $query;
266		781
267	$upath =~ s%^/?%/%;	782	$upath =~ s%^/?%/%;
268		783
269	# cookie processing	784	# cookie processing
270	if (my $jar = $arg{cookie_jar}) {	785	if (my $jar = $arg{cookie_jar}) {
271	%$jar = () if $jar->{version} < 1;	786	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
272		787
		788	$hdr{cookie} = join "; ", @$cookies
273	my @cookie;	789	if @$cookies;
274		790	}
275	while (my ($chost, $v) = each %$jar) {	791
276	next unless $chost eq substr $uhost, -length $chost;	792	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
277	next unless $chost =~ /^\./;	793
278		794	if ($proxy) {
279	while (my ($cpath, $v) = each %$v) {	795	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
280	next unless $cpath eq substr $upath, 0, length $cpath;	796
281		797	$rscheme = "http" unless defined $rscheme;
282	while (my ($k, $v) = each %$v) {	798
283	next if $scheme ne "https" && exists $v->{secure};	799	# don't support https requests over https-proxy transport,
284	push @cookie, "$k=$v->{value}";	800	# can't be done with tls as spec'ed, unless you double-encrypt.
		801	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		802
		803	$rhost = lc $rhost;
		804	$rscheme = lc $rscheme;
		805	} else {
		806	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
		807	}
		808
		809	# leave out fragment and query string, just a heuristic
		810	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		811	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		812
		813	$hdr{"content-length"} = length $arg{body}
		814	if length $arg{body} \|\| $method ne "GET";
		815
		816	my $idempotent = $IDEMPOTENT{$method};
		817
		818	# default value for keepalive is true iff the request is for an idempotent method
		819	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		820	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		821	my $was_persistent; # true if this is actually a recycled connection
		822
		823	# the key to use in the keepalive cache
		824	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		825
		826	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1
		827	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
		828
		829	my %state = (connect_guard => 1);
		830
		831	my $ae_error = 595; # connecting
		832
		833	# handle actual, non-tunneled, request
		834	my $handle_actual_request = sub {
		835	$ae_error = 596; # request phase
		836
		837	my $hdl = $state{handle};
		838
		839	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		840
		841	# send request
		842	$hdl->push_write (
		843	"$method $rpath HTTP/1.1\015\012"
		844	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		845	. "\015\012"
		846	. (delete $arg{body})
		847	);
		848
		849	# return if error occurred during push_write()
		850	return unless %state;
		851
		852	# reduce memory usage, save a kitten, also re-use it for the response headers.
		853	%hdr = ();
		854
		855	# status line and headers
		856	$state{read_response} = sub {
		857	return unless %state;
		858
		859	for ("$_[1]") {
		860	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		861
		862	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		863	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		864
		865	# 100 Continue handling
		866	# should not happen as we don't send expect: 100-continue,
		867	# but we handle it just in case.
		868	# since we send the request body regardless, if we get an error
		869	# we are out of-sync, which we currently do NOT handle correctly.
		870	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		871	if $2 eq 100;
		872
		873	push @pseudo,
		874	HTTPVersion => $1,
		875	Status => $2,
		876	Reason => $3,
		877	;
		878
		879	my $hdr = _parse_hdr
		880	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		881
		882	%hdr = (%$hdr, @pseudo);
		883	}
		884
		885	# redirect handling
		886	# microsoft and other shitheads don't give a shit for following standards,
		887	# try to support some common forms of broken Location headers.
		888	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		889	$hdr{location} =~ s/^\.\/+//;
		890
		891	my $url = "$rscheme://$uhost:$uport";
		892
		893	unless ($hdr{location} =~ s/^\///) {
		894	$url .= $upath;
		895	$url =~ s/\/[^\/]*$//;
		896	}
		897
		898	$hdr{location} = "$url/$hdr{location}";
		899	}
		900
		901	my $redirect;
		902
		903	if ($recurse) {
		904	my $status = $hdr{Status};
		905
		906	# industry standard is to redirect POST as GET for
		907	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		908	# also, the UA should ask the user for 301 and 307 and POST,
		909	# industry standard seems to be to simply follow.
		910	# we go with the industry standard.
		911	if ($status == 301 or $status == 302 or $status == 303) {
		912	# HTTP/1.1 is unclear on how to mutate the method
		913	$method = "GET" unless $method eq "HEAD";
		914	$redirect = 1;
		915	} elsif ($status == 307) {
		916	$redirect = 1;
285	}	917	}
286	}	918	}
		919
		920	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		921	if ($state{handle}) {
		922	# handle keepalive
		923	if (
		924	$persistent
		925	&& $_[3]
		926	&& ($hdr{HTTPVersion} < 1.1
		927	? $hdr{connection} =~ /\bkeep-?alive\b/i
		928	: $hdr{connection} !~ /\bclose\b/i)
		929	) {
		930	ka_store $ka_key, delete $state{handle};
		931	} else {
		932	# no keepalive, destroy the handle
		933	$state{handle}->destroy;
		934	}
		935	}
		936
		937	%state = ();
		938
		939	if (defined $_[1]) {
		940	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		941	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		942	}
		943
		944	# set-cookie processing
		945	if ($arg{cookie_jar}) {
		946	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		947	}
		948
		949	if ($redirect && exists $hdr{location}) {
		950	# we ignore any errors, as it is very common to receive
		951	# Content-Length != 0 but no actual body
		952	# we also access %hdr, as $_[1] might be an erro
		953	$state{recurse} =
		954	http_request (
		955	$method => $hdr{location},
		956	%arg,
		957	recurse => $recurse - 1,
		958	Redirect => [$_[0], \%hdr],
		959	sub {
		960	%state = ();
		961	&$cb
		962	},
		963	);
		964	} else {
		965	$cb->($_[0], \%hdr);
		966	}
		967	};
		968
		969	$ae_error = 597; # body phase
		970
		971	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		972
		973	my $len = $chunked ? undef : $hdr{"content-length"};
		974
		975	# body handling, many different code paths
		976	# - no body expected
		977	# - want_body_handle
		978	# - te chunked
		979	# - 2x length known (with or without on_body)
		980	# - 2x length not known (with or without on_body)
		981	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		982	$finish->(undef, 598 => "Request cancelled by on_header");
		983	} elsif (
		984	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		985	or $method eq "HEAD"
		986	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		987	) {
		988	# no body
		989	$finish->("", undef, undef, 1);
		990
		991	} elsif (!$redirect && $arg{want_body_handle}) {
		992	$_[0]->on_eof (undef);
		993	$_[0]->on_error (undef);
		994	$_[0]->on_read (undef);
		995
		996	$finish->(delete $state{handle});
		997
		998	} elsif ($chunked) {
		999	my $cl = 0;
		1000	my $body = "";
		1001	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		1002
		1003	$state{read_chunk} = sub {
		1004	$_[1] =~ /^([0-9a-fA-F]+)/
		1005	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1006
		1007	my $len = hex $1;
		1008
		1009	if ($len) {
		1010	$cl += $len;
		1011
		1012	$_[0]->push_read (chunk => $len, sub {
		1013	$on_body->($_[1], \%hdr)
		1014	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1015
		1016	$_[0]->push_read (line => sub {
		1017	length $_[1]
		1018	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1019	$_[0]->push_read (line => $state{read_chunk});
		1020	});
		1021	});
		1022	} else {
		1023	$hdr{"content-length"} \|\|= $cl;
		1024
		1025	$_[0]->push_read (line => $qr_nlnl, sub {
		1026	if (length $_[1]) {
		1027	for ("$_[1]") {
		1028	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		1029
		1030	my $hdr = _parse_hdr
		1031	or return $finish->(undef, $ae_error => "Garbled response trailers");
		1032
		1033	%hdr = (%hdr, %$hdr);
		1034	}
		1035	}
		1036
		1037	$finish->($body, undef, undef, 1);
		1038	});
		1039	}
		1040	};
		1041
		1042	$_[0]->push_read (line => $state{read_chunk});
		1043
		1044	} elsif ($arg{on_body}) {
		1045	if (defined $len) {
		1046	$_[0]->on_read (sub {
		1047	$len -= length $_[0]{rbuf};
		1048
		1049	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1050	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1051
		1052	$len > 0
		1053	or $finish->("", undef, undef, 1);
		1054	});
		1055	} else {
		1056	$_[0]->on_eof (sub {
		1057	$finish->("");
		1058	});
		1059	$_[0]->on_read (sub {
		1060	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1061	or $finish->(undef, 598 => "Request cancelled by on_body");
		1062	});
		1063	}
		1064	} else {
		1065	$_[0]->on_eof (undef);
		1066
		1067	if (defined $len) {
		1068	$_[0]->on_read (sub {
		1069	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1070	if $len <= length $_[0]{rbuf};
		1071	});
		1072	} else {
		1073	$_[0]->on_error (sub {
		1074	($! == Errno::EPIPE \|\| !$!)
		1075	? $finish->(delete $_[0]{rbuf})
		1076	: $finish->(undef, $ae_error => $_[2]);
		1077	});
		1078	$_[0]->on_read (sub { });
		1079	}
		1080	}
		1081	};
		1082
		1083	# if keepalive is enabled, then the server closing the connection
		1084	# before a response can happen legally - we retry on idempotent methods.
		1085	if ($was_persistent && $idempotent) {
		1086	my $old_eof = $hdl->{on_eof};
		1087	$hdl->{on_eof} = sub {
		1088	_destroy_state %state;
		1089
		1090	%state = ();
		1091	$state{recurse} =
		1092	http_request (
		1093	$method => $url,
		1094	%arg,
		1095	recurse => $recurse - 1,
		1096	keepalive => 0,
		1097	sub {
		1098	%state = ();
		1099	&$cb
		1100	}
		1101	);
		1102	};
		1103	$hdl->on_read (sub {
		1104	return unless %state;
		1105
		1106	# as soon as we receive something, a connection close
		1107	# once more becomes a hard error
		1108	$hdl->{on_eof} = $old_eof;
		1109	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1110	});
		1111	} else {
		1112	$hdl->push_read (line => $qr_nlnl, $state{read_response});
287	}	1113	}
288
289	$hdr{cookie} = join "; ", @cookie
290	if @cookie;
291	}	1114	};
292		1115
293	my ($rhost, $rport, $rpath); # request host, port, path	1116	my $prepare_handle = sub {
		1117	my ($hdl) = $state{handle};
294		1118
295	if ($proxy) {	1119	$hdl->on_error (sub {
296	($rhost, $rport, $scheme) = @$proxy;	1120	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
297	$rpath = $url;	1121	});
298	} else {	1122	$hdl->on_eof (sub {
299	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	1123	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
300	$hdr{host} = $uhost;	1124	});
		1125	$hdl->timeout_reset;
		1126	$hdl->timeout ($timeout);
301	}	1127	};
302		1128
303	$hdr{"content-length"} = length $arg{body};	1129	# connected to proxy (or origin server)
		1130	my $connect_cb = sub {
		1131	my $fh = shift
		1132	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
304		1133
305	my %state = (connect_guard => 1);	1134	return unless delete $state{connect_guard};
		1135
		1136	# get handle
		1137	$state{handle} = new AnyEvent::Handle
		1138	%{ $arg{handle_params} },
		1139	fh => $fh,
		1140	peername => $uhost,
		1141	tls_ctx => $arg{tls_ctx},
		1142	;
		1143
		1144	$prepare_handle->();
		1145
		1146	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1147
		1148	# now handle proxy-CONNECT method
		1149	if ($proxy && $uscheme eq "https") {
		1150	# oh dear, we have to wrap it into a connect request
		1151
		1152	# maybe re-use $uauthority with patched port?
		1153	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		1154	$state{handle}->push_read (line => $qr_nlnl, sub {
		1155	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1156	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1157
		1158	if ($2 == 200) {
		1159	$rpath = $upath;
		1160	$handle_actual_request->();
		1161	} else {
		1162	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1163	}
		1164	});
		1165	} else {
		1166	$handle_actual_request->();
		1167	}
		1168	};
306		1169
307	_get_slot $uhost, sub {	1170	_get_slot $uhost, sub {
308	$state{slot_guard} = shift;	1171	$state{slot_guard} = shift;
309		1172
310	return unless $state{connect_guard};	1173	return unless $state{connect_guard};
311		1174
312	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	1175	# try to use an existing keepalive connection, but only if we, ourselves, plan
313	$state{fh} = shift	1176	# on a keepalive request (in theory, this should be a separate config option).
314	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	1177	if ($persistent && $KA_CACHE{$ka_key}) {
		1178	$was_persistent = 1;
315		1179
316	delete $state{connect_guard}; # reduce memory usage, save a tree	1180	$state{handle} = ka_fetch $ka_key;
		1181	$state{handle}->destroyed
		1182	and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
		1183	$prepare_handle->();
		1184	$state{handle}->destroyed
		1185	and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
		1186	$handle_actual_request->();
317		1187
318	# get handle
319	$state{handle} = new AnyEvent::Handle
320	fh => $state{fh},
321	($scheme eq "https" ? (tls => "connect") : ());
322
323	# limit the number of persistent connections
324	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
325	++$KA_COUNT{$_[1]};
326	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
327	$hdr{connection} = "keep-alive";
328	delete $hdr{connection}; # keep-alive not yet supported
329	} else {	1188	} else {
330	delete $hdr{connection};	1189	my $tcp_connect = $arg{tcp_connect}
331	}	1190	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
332		1191
333	# (re-)configure handle	1192	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
334	$state{handle}->timeout ($timeout);
335	$state{handle}->on_error (sub {
336	my $errno = "$!";
337	%state = ();
338	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
339	});
340	$state{handle}->on_eof (sub {
341	%state = ();
342	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
343	});
344
345	# send request
346	$state{handle}->push_write (
347	"$method $rpath HTTP/1.0\015\012"
348	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
349	. "\015\012"
350	. (delete $arg{body})
351	);
352
353	%hdr = (); # reduce memory usage, save a kitten
354
355	# status line
356	$state{handle}->push_read (line => qr/\015?\012/, sub {
357	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
358	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
359
360	my %hdr = ( # response headers
361	HTTPVersion => "\x00$1",
362	Status => "\x00$2",
363	Reason => "\x00$3",
364	URL => "\x00$url"
365	);
366
367	# headers, could be optimized a bit
368	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
369	for ("$_[1]\012") {
370	# we support spaces in field names, as lotus domino
371	# creates them.
372	$hdr{lc $1} .= "\x00$2"
373	while /\G
374	([^:\000-\037]+):
375	[\011\040]*
376	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
377	\015?\012
378	/gxc;
379
380	/\G$/
381	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
382	}
383
384	substr $_, 0, 1, ""
385	for values %hdr;
386
387	my $finish = sub {
388	%state = ();
389
390	# set-cookie processing
391	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
392	for (split /\x00/, $hdr{"set-cookie"}) {
393	my ($cookie, @arg) = split /;\s*/;
394	my ($name, $value) = split /=/, $cookie, 2;
395	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
396
397	my $cdom = (delete $kv{domain}) \|\| $uhost;
398	my $cpath = (delete $kv{path}) \|\| "/";
399
400	$cdom =~ s/^.?/./; # make sure it starts with a "."
401
402	next if $cdom =~ /\.$/;
403
404	# this is not rfc-like and not netscape-like. go figure.
405	my $ndots = $cdom =~ y/.//;
406	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
407
408	# store it
409	$arg{cookie_jar}{version} = 1;
410	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
411	}
412	}
413
414	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {
415	# microsoft and other assholes don't give a shit for following standards,
416	# try to support a common form of broken Location header.
417	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
418
419	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
420	} else {
421	$cb->($_[0], $_[1]);
422	}
423	};
424
425	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {
426	$finish->(undef, \%hdr);
427	} else {
428	if (exists $hdr{"content-length"}) {
429	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
430	# could cache persistent connection now
431	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
432	# but we don't, due to misdesigns, this is annoyingly complex
433	};
434
435	$finish->($_[1], \%hdr);
436	});
437	} else {
438	# too bad, need to read until we get an error or EOF,
439	# no way to detect winged data.
440	$_[0]->on_error (sub {
441	$finish->($_[0]{rbuf}, \%hdr);
442	});
443	$_[0]->on_eof (undef);
444	$_[0]->on_read (sub { });
445	}
446	}
447	});
448	});
449	}, sub {
450	$timeout
451	};	1193	}
452	};	1194	};
453		1195
454	defined wantarray && AnyEvent::Util::guard { %state = () }	1196	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
455	}	1197	}
456		1198
457	sub http_get($@) {	1199	sub http_get($@) {
458	unshift @_, "GET";	1200	unshift @_, "GET";
459	&http_request	1201	&http_request
…		…
463	unshift @_, "HEAD";	1205	unshift @_, "HEAD";
464	&http_request	1206	&http_request
465	}	1207	}
466		1208
467	sub http_post($$@) {	1209	sub http_post($$@) {
		1210	my $url = shift;
468	unshift @_, "POST", "body";	1211	unshift @_, "POST", $url, "body";
469	&http_request	1212	&http_request
470	}	1213	}
471		1214
472	=back	1215	=back
473		1216
		1217	=head2 DNS CACHING
		1218
		1219	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		1220	the actual connection, which in turn uses AnyEvent::DNS to resolve
		1221	hostnames. The latter is a simple stub resolver and does no caching
		1222	on its own. If you want DNS caching, you currently have to provide
		1223	your own default resolver (by storing a suitable resolver object in
		1224	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
		1225
474	=head2 GLOBAL FUNCTIONS AND VARIABLES	1226	=head2 GLOBAL FUNCTIONS AND VARIABLES
475		1227
476	=over 4	1228	=over 4
477		1229
478	=item AnyEvent::HTTP::set_proxy "proxy-url"	1230	=item AnyEvent::HTTP::set_proxy "proxy-url"
479		1231
480	Sets the default proxy server to use. The proxy-url must begin with a	1232	Sets the default proxy server to use. The proxy-url must begin with a
481	string of the form C<http://host:port> (optionally C<https:...>).	1233	string of the form C<http://host:port>, croaks otherwise.
		1234
		1235	To clear an already-set proxy, use C<undef>.
		1236
		1237	When AnyEvent::HTTP is loaded for the first time it will query the
		1238	default proxy from the operating system, currently by looking at
		1239	C<$ENV{http_proxy>}.
		1240
		1241	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1242
		1243	Remove all cookies from the cookie jar that have been expired. If
		1244	C<$session_end> is given and true, then additionally remove all session
		1245	cookies.
		1246
		1247	You should call this function (with a true C<$session_end>) before you
		1248	save cookies to disk, and you should call this function after loading them
		1249	again. If you have a long-running program you can additionally call this
		1250	function from time to time.
		1251
		1252	A cookie jar is initially an empty hash-reference that is managed by this
		1253	module. It's format is subject to change, but currently it is like this:
		1254
		1255	The key C<version> has to contain C<1>, otherwise the hash gets
		1256	emptied. All other keys are hostnames or IP addresses pointing to
		1257	hash-references. The key for these inner hash references is the
		1258	server path for which this cookie is meant, and the values are again
		1259	hash-references. Each key of those hash-references is a cookie name, and
		1260	the value, you guessed it, is another hash-reference, this time with the
		1261	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1262	which have been replaced by a C<_expires> key that contains the cookie
		1263	expiry timestamp. Session cookies are indicated by not having an
		1264	C<_expires> key.
		1265
		1266	Here is an example of a cookie jar with a single cookie, so you have a
		1267	chance of understanding the above paragraph:
		1268
		1269	{
		1270	version => 1,
		1271	"10.0.0.1" => {
		1272	"/" => {
		1273	"mythweb_id" => {
		1274	_expires => 1293917923,
		1275	value => "ooRung9dThee3ooyXooM1Ohm",
		1276	},
		1277	},
		1278	},
		1279	}
		1280
		1281	=item $date = AnyEvent::HTTP::format_date $timestamp
		1282
		1283	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1284	Date (RFC 2616).
		1285
		1286	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1287
		1288	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1289	bunch of minor variations of those, and returns the corresponding POSIX
		1290	timestamp, or C<undef> if the date cannot be parsed.
482		1291
483	=item $AnyEvent::HTTP::MAX_RECURSE	1292	=item $AnyEvent::HTTP::MAX_RECURSE
484		1293
485	The default value for the C<recurse> request parameter (default: C<10>).	1294	The default value for the C<recurse> request parameter (default: C<10>).
486		1295
		1296	=item $AnyEvent::HTTP::TIMEOUT
		1297
		1298	The default timeout for connection operations (default: C<300>).
		1299
487	=item $AnyEvent::HTTP::USERAGENT	1300	=item $AnyEvent::HTTP::USERAGENT
488		1301
489	The default value for the C<User-Agent> header (the default is	1302	The default value for the C<User-Agent> header (the default is
490	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1303	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
491		1304
492	=item $AnyEvent::HTTP::MAX_PERSISTENT	1305	=item $AnyEvent::HTTP::MAX_PER_HOST
493		1306
494	The maximum number of persistent connections to keep open (default: 8).	1307	The maximum number of concurrent connections to the same host (identified
		1308	by the hostname). If the limit is exceeded, then the additional requests
		1309	are queued until previous connections are closed. Both persistent and
		1310	non-persistent connections are counted in this limit.
495		1311
496	Not implemented currently.	1312	The default value for this is C<4>, and it is highly advisable to not
		1313	increase it much.
		1314
		1315	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1316	connections, older browsers used 2, newer ones (such as firefox 3)
		1317	typically use 6, and Opera uses 8 because like, they have the fastest
		1318	browser and give a shit for everybody else on the planet.
497		1319
498	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	1320	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
499		1321
500	The maximum time to cache a persistent connection, in seconds (default: 2).	1322	The time after which idle persistent connections get closed by
501		1323	AnyEvent::HTTP (default: C<3>).
502	Not implemented currently.
503		1324
504	=item $AnyEvent::HTTP::ACTIVE	1325	=item $AnyEvent::HTTP::ACTIVE
505		1326
506	The number of active connections. This is not the number of currently	1327	The number of active connections. This is not the number of currently
507	running requests, but the number of currently open and non-idle TCP	1328	running requests, but the number of currently open and non-idle TCP
508	connections. This number of can be useful for load-leveling.	1329	connections. This number can be useful for load-leveling.
509		1330
510	=back	1331	=back
511		1332
512	=cut	1333	=cut
513		1334
		1335	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1336	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1337
		1338	sub format_date($) {
		1339	my ($time) = @_;
		1340
		1341	# RFC 822/1123 format
		1342	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1343
		1344	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1345	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1346	$H, $M, $S;
		1347	}
		1348
		1349	sub parse_date($) {
		1350	my ($date) = @_;
		1351
		1352	my ($d, $m, $y, $H, $M, $S);
		1353
		1354	if ($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$/) {
		1355	# RFC 822/1123, required by RFC 2616 (with " ")
		1356	# cookie dates (with "-")
		1357
		1358	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1359
		1360	} elsif ($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$/) {
		1361	# RFC 850
		1362	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1363
		1364	} elsif ($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])$/) {
		1365	# ISO C's asctime
		1366	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1367	}
		1368	# other formats fail in the loop below
		1369
		1370	for (0..11) {
		1371	if ($m eq $month[$_]) {
		1372	require Time::Local;
		1373	return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) };
		1374	}
		1375	}
		1376
		1377	undef
		1378	}
		1379
514	sub set_proxy($) {	1380	sub set_proxy($) {
515	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1381	if (length $_[0]) {
		1382	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
		1383	or Carp::croak "$_[0]: invalid proxy URL";
		1384	$PROXY = [$2, $3 \|\| 3128, $1]
		1385	} else {
		1386	undef $PROXY;
		1387	}
516	}	1388	}
517		1389
518	# initialise proxy from environment	1390	# initialise proxy from environment
		1391	eval {
519	set_proxy $ENV{http_proxy};	1392	set_proxy $ENV{http_proxy};
		1393	};
		1394
		1395	=head2 SHOWCASE
		1396
		1397	This section contains some more elaborate "real-world" examples or code
		1398	snippets.
		1399
		1400	=head2 HTTP/1.1 FILE DOWNLOAD
		1401
		1402	Downloading files with HTTP can be quite tricky, especially when something
		1403	goes wrong and you want to resume.
		1404
		1405	Here is a function that initiates and resumes a download. It uses the
		1406	last modified time to check for file content changes, and works with many
		1407	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1408	on older servers.
		1409
		1410	It calls the completion callback with either C<undef>, which means a
		1411	nonretryable error occurred, C<0> when the download was partial and should
		1412	be retried, and C<1> if it was successful.
		1413
		1414	use AnyEvent::HTTP;
		1415
		1416	sub download($$$) {
		1417	my ($url, $file, $cb) = @_;
		1418
		1419	open my $fh, "+<", $file
		1420	or die "$file: $!";
		1421
		1422	my %hdr;
		1423	my $ofs = 0;
		1424
		1425	warn stat $fh;
		1426	warn -s _;
		1427	if (stat $fh and -s _) {
		1428	$ofs = -s _;
		1429	warn "-s is ", $ofs;
		1430	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1431	$hdr{"range"} = "bytes=$ofs-";
		1432	}
		1433
		1434	http_get $url,
		1435	headers => \%hdr,
		1436	on_header => sub {
		1437	my ($hdr) = @_;
		1438
		1439	if ($hdr->{Status} == 200 && $ofs) {
		1440	# resume failed
		1441	truncate $fh, $ofs = 0;
		1442	}
		1443
		1444	sysseek $fh, $ofs, 0;
		1445
		1446	1
		1447	},
		1448	on_body => sub {
		1449	my ($data, $hdr) = @_;
		1450
		1451	if ($hdr->{Status} =~ /^2/) {
		1452	length $data == syswrite $fh, $data
		1453	or return; # abort on write errors
		1454	}
		1455
		1456	1
		1457	},
		1458	sub {
		1459	my (undef, $hdr) = @_;
		1460
		1461	my $status = $hdr->{Status};
		1462
		1463	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1464	utime $fh, $time, $time;
		1465	}
		1466
		1467	if ($status == 200 \|\| $status == 206 \|\| $status == 416) {
		1468	# download ok \|\| resume ok \|\| file already fully downloaded
		1469	$cb->(1, $hdr);
		1470
		1471	} elsif ($status == 412) {
		1472	# file has changed while resuming, delete and retry
		1473	unlink $file;
		1474	$cb->(0, $hdr);
		1475
		1476	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1477	# retry later
		1478	$cb->(0, $hdr);
		1479
		1480	} else {
		1481	$cb->(undef, $hdr);
		1482	}
		1483	}
		1484	;
		1485	}
		1486
		1487	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1488	if ($_[0]) {
		1489	print "OK!\n";
		1490	} elsif (defined $_[0]) {
		1491	print "please retry later\n";
		1492	} else {
		1493	print "ERROR\n";
		1494	}
		1495	};
		1496
		1497	=head3 SOCKS PROXIES
		1498
		1499	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1500	compile your perl to support socks, or use an external program such as
		1501	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1502	transparently.
		1503
		1504	Alternatively, for AnyEvent::HTTP only, you can use your own
		1505	C<tcp_connect> function that does the proxy handshake - here is an example
		1506	that works with socks4a proxies:
		1507
		1508	use Errno;
		1509	use AnyEvent::Util;
		1510	use AnyEvent::Socket;
		1511	use AnyEvent::Handle;
		1512
		1513	# host, port and username of/for your socks4a proxy
		1514	my $socks_host = "10.0.0.23";
		1515	my $socks_port = 9050;
		1516	my $socks_user = "";
		1517
		1518	sub socks4a_connect {
		1519	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1520
		1521	my $hdl = new AnyEvent::Handle
		1522	connect => [$socks_host, $socks_port],
		1523	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1524	on_error => sub { $connect_cb->() },
		1525	;
		1526
		1527	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1528
		1529	$hdl->push_read (chunk => 8, sub {
		1530	my ($hdl, $chunk) = @_;
		1531	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1532
		1533	if ($status == 0x5a) {
		1534	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1535	} else {
		1536	$! = Errno::ENXIO; $connect_cb->();
		1537	}
		1538	});
		1539
		1540	$hdl
		1541	}
		1542
		1543	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1544	possibly after switching off other proxy types:
		1545
		1546	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1547
		1548	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1549	my ($data, $headers) = @_;
		1550	...
		1551	};
520		1552
521	=head1 SEE ALSO	1553	=head1 SEE ALSO
522		1554
523	L<AnyEvent>.	1555	L<AnyEvent>.
524		1556
525	=head1 AUTHOR	1557	=head1 AUTHOR
526		1558
527	Marc Lehmann <schmorp@schmorp.de>	1559	Marc Lehmann <schmorp@schmorp.de>
528	http://home.schmorp.de/	1560	http://home.schmorp.de/
529		1561
		1562	With many thanks to Дмитрий Шалашов, who provided countless
		1563	testcases and bugreports.
		1564
530	=cut	1565	=cut
531		1566
532	1	1567	1
533		1568

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs. Revision 1.117 by root, Mon Sep 9 21:41:43 2013 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.117 by root, Mon Sep 9 21:41:43 2013 UTC