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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.10 by root, Thu Jun 5 13:06:43 2008 UTC vs.
Revision 1.74 by root, Fri Dec 31 22:40:54 2010 UTC

…		…
3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client	3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use AnyEvent::HTTP;	7	use AnyEvent::HTTP;
		8
		9	http_get "http://www.nethype.de/", sub { print $_[1] };
		10
		11	# ... do something else here
8		12
9	=head1 DESCRIPTION	13	=head1 DESCRIPTION
10		14
11	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
12	run a supported event loop.	16	run a supported event loop.
13		17
		18	This module implements a simple, stateless and non-blocking HTTP
		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
		21	automatically limits the number of connections to the values specified in
		22	the RFC.
		23
		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
		26	possible as the user retains control over request and response headers.
		27
		28	The caller is responsible for authentication management, cookies (if
		29	the simplistic implementation in this module doesn't suffice), referer
		30	and other high-level protocol details for which this module offers only
		31	limited support.
		32
14	=head2 METHODS	33	=head2 METHODS
15		34
16	=over 4	35	=over 4
17		36
18	=cut	37	=cut
…		…
20	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
21		40
22	use strict;	41	use strict;
23	no warnings;	42	no warnings;
24		43
25	use Carp;	44	use Errno ();
26		45
27	use AnyEvent ();	46	use AnyEvent 5.0 ();
28	use AnyEvent::Util ();	47	use AnyEvent::Util ();
29	use AnyEvent::Socket ();
30	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
31		49
32	use base Exporter::;	50	use base Exporter::;
33		51
34	our $VERSION = '1.0';	52	our $VERSION = '1.5';
35		53
36	our @EXPORT = qw(http_get http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
37		55
38	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
39	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
40	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
41	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
42	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
43		61
44	# changing these is evil	62	# changing these is evil
45	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
46	our $MAX_PER_HOST = 4; # not respected yet :(	64	our $MAX_PER_HOST = 4;
47		65
48	our $PROXY;	66	our $PROXY;
		67	our $ACTIVE = 0;
49		68
50	my %KA_COUNT; # number of open keep-alive connections per host	69	my %KA_COUNT; # number of open keep-alive connections per host
		70	my %CO_SLOT; # number of open connections, and wait queue, per host
51		71
52	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
53		73
54	Executes an HTTP-GET request. See the http_request function for details on	74	Executes an HTTP-GET request. See the http_request function for details on
55	additional parameters.	75	additional parameters and the return value.
56		76
57	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
58		78
59	Executes an HTTP-HEAD request. See the http_request function for details on	79	Executes an HTTP-HEAD request. See the http_request function for details
60	additional parameters.	80	on additional parameters and the return value.
61		81
62	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
63		83
64	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
65	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
66		87
67	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
68		89
69	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
70	must be an absolute http or https URL.	91	must be an absolute http or https URL.
71		92
		93	When called in void context, nothing is returned. In other contexts,
		94	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
		96	destroyed before the callback is called, the request will be cancelled.
		97
72	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
73	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers
74	response headers as second argument.	100	(and trailers) as second argument.
75		101
76	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
77	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
78	C<Reason> contain the three parts of the HTTP Status-Line of the same	104	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
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
		110	The pseudo-header C<URL> contains the actual URL (which can differ from
		111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
79	name. If the server sends a header multiple lines, then their contents	123	If the server sends a header multiple times, then their contents will be
80	will be joined together with C<\x00>.	124	joined together with a comma (C<,>), as per the HTTP spec.
81		125
82	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
83	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
84	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
85		130
86	A typical callback might look like this:	131	A typical callback might look like this:
87		132
88	sub {	133	sub {
89	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
105	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
106	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
107		152
108	=item headers => hashref	153	=item headers => hashref
109		154
110	The request headers to use.	155	The request headers to use. Currently, C<http_request> may provide its own
		156	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
		157	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		158	(this can be suppressed by using C<undef> for these headers in which case
		159	they won't be sent at all).
111		160
112	=item timeout => $seconds	161	=item timeout => $seconds
113		162
114	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
115	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
116		168
117	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
118		170
119	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
120	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
121		173
122	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
123	HTTPS.	175	HTTPS.
124		176
125	=item body => $string	177	=item body => $string
126		178
127	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be sent as-is (future versions of
128	this module might offer more options).	180	this module might offer more options).
129		181
130	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
131		183
132	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
133	based on the original netscape specification.	185	based on the original netscape specification.
134		186
135	The C<$hash_ref> must be an (initially empty) hash reference which will	187	The C<$hash_ref> must be an (initially empty) hash reference which will
136	get updated automatically. It is possible to save the cookie_jar to	188	get updated automatically. It is possible to save the cookie jar to
137	persistent storage with something like JSON or Storable, but this is not	189	persistent storage with something like JSON or Storable, but this is not
138	recommended, as expire times are currently being ignored.	190	recommended, as session-only cookies might survive longer than expected.
139		191
140	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not meant to be complete. If
141	meant to be complete. If you want complete cookie management you have to	193	you want complete cookie management you have to do that on your
142	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites
143	cookie-using sites working. Cookies are a privacy disaster, do not use	195	working. Cookies are a privacy disaster, do not use them unless required
144	them unless required to.	196	to.
		197
		198	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		199	headers will be set and handled by this module, otherwise they will be
		200	left untouched.
		201
		202	=item tls_ctx => $scheme \| $tls_ctx
		203
		204	Specifies the AnyEvent::TLS context to be used for https connections. This
		205	parameter follows the same rules as the C<tls_ctx> parameter to
		206	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		207	C<high> can be specified, which give you a predefined low-security (no
		208	verification, highest compatibility) and high-security (CA and common-name
		209	verification) TLS context.
		210
		211	The default for this option is C<low>, which could be interpreted as "give
		212	me the page, no matter what".
		213
		214	=item on_prepare => $callback->($fh)
		215
		216	In rare cases you need to "tune" the socket before it is used to
		217	connect (for exmaple, to bind it on a given IP address). This parameter
		218	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		219	and behaves exactly the same way (e.g. it has to provide a
		220	timeout). See the description for the C<$prepare_cb> argument of
		221	C<AnyEvent::Socket::tcp_connect> for details.
		222
		223	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		224
		225	In even rarer cases you want total control over how AnyEvent::HTTP
		226	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		227	to do this, but you can provide your own C<tcp_connect> function -
		228	obviously, it has to follow the same calling conventions, except that it
		229	may always return a connection guard object.
		230
		231	There are probably lots of weird uses for this function, starting from
		232	tracing the hosts C<http_request> actually tries to connect, to (inexact
		233	but fast) host => IP address caching or even socks protocol support.
		234
		235	=item on_header => $callback->($headers)
		236
		237	When specified, this callback will be called with the header hash as soon
		238	as headers have been successfully received from the remote server (not on
		239	locally-generated errors).
		240
		241	It has to return either true (in which case AnyEvent::HTTP will continue),
		242	or false, in which case AnyEvent::HTTP will cancel the download (and call
		243	the finish callback with an error code of C<598>).
		244
		245	This callback is useful, among other things, to quickly reject unwanted
		246	content, which, if it is supposed to be rare, can be faster than first
		247	doing a C<HEAD> request.
		248
		249	The downside is that cancelling the request makes it impossible to re-use
		250	the connection. Also, the C<on_header> callback will not receive any
		251	trailer (headers sent after the response body).
		252
		253	Example: cancel the request unless the content-type is "text/html".
		254
		255	on_header => sub {
		256	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		257	},
		258
		259	=item on_body => $callback->($partial_body, $headers)
		260
		261	When specified, all body data will be passed to this callback instead of
		262	to the completion callback. The completion callback will get the empty
		263	string instead of the body data.
		264
		265	It has to return either true (in which case AnyEvent::HTTP will continue),
		266	or false, in which case AnyEvent::HTTP will cancel the download (and call
		267	the completion callback with an error code of C<598>).
		268
		269	The downside to cancelling the request is that it makes it impossible to
		270	re-use the connection.
		271
		272	This callback is useful when the data is too large to be held in memory
		273	(so the callback writes it to a file) or when only some information should
		274	be extracted, or when the body should be processed incrementally.
		275
		276	It is usually preferred over doing your own body handling via
		277	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		278	only used to create a connection, C<want_body_handle> is the better
		279	alternative, as it allows you to install your own event handler, reducing
		280	resource usage.
		281
		282	=item want_body_handle => $enable
		283
		284	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		285	changes considerably: after parsing the headers, and instead of
		286	downloading the body (if any), the completion callback will be
		287	called. Instead of the C<$body> argument containing the body data, the
		288	callback will receive the L<AnyEvent::Handle> object associated with the
		289	connection. In error cases, C<undef> will be passed. When there is no body
		290	(e.g. status C<304>), the empty string will be passed.
		291
		292	The handle object might or might not be in TLS mode, might be connected to
		293	a proxy, be a persistent connection etc., and configured in unspecified
		294	ways. The user is responsible for this handle (it will not be used by this
		295	module anymore).
		296
		297	This is useful with some push-type services, where, after the initial
		298	headers, an interactive protocol is used (typical example would be the
		299	push-style twitter API which starts a JSON/XML stream).
		300
		301	If you think you need this, first have a look at C<on_body>, to see if
		302	that doesn't solve your problem in a better way.
145		303
146	=back	304	=back
147		305
148	Example: make a simple HTTP GET request for http://www.nethype.de/	306	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		307	the response body.
149		308
150	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
151	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
152	print "$body\n";	311	print "$body\n";
153	};	312	};
154		313
155	Example: make a HTTP HEAD request on https://www.google.com/, use a	314	Example: do a HTTP HEAD request on https://www.google.com/, use a
156	timeout of 30 seconds.	315	timeout of 30 seconds.
157		316
158	http_request	317	http_request
159	GET => "https://www.google.com",	318	GET => "https://www.google.com",
160	timeout => 30,	319	timeout => 30,
…		…
163	use Data::Dumper;	322	use Data::Dumper;
164	print Dumper $hdr;	323	print Dumper $hdr;
165	}	324	}
166	;	325	;
167		326
		327	Example: do another simple HTTP GET request, but immediately try to
		328	cancel it.
		329
		330	my $request = http_request GET => "http://www.nethype.de/", sub {
		331	my ($body, $hdr) = @_;
		332	print "$body\n";
		333	};
		334
		335	undef $request;
		336
168	=cut	337	=cut
169		338
		339	sub _slot_schedule;
		340	sub _slot_schedule($) {
		341	my $host = shift;
		342
		343	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		344	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		345	# somebody wants that slot
		346	++$CO_SLOT{$host}[0];
		347	++$ACTIVE;
		348
		349	$cb->(AnyEvent::Util::guard {
		350	--$ACTIVE;
		351	--$CO_SLOT{$host}[0];
		352	_slot_schedule $host;
		353	});
		354	} else {
		355	# nobody wants the slot, maybe we can forget about it
		356	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		357	last;
		358	}
		359	}
		360	}
		361
		362	# wait for a free slot on host, call callback
		363	sub _get_slot($$) {
		364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		365
		366	_slot_schedule $_[0];
		367	}
		368
		369	# extract cookies from jar
		370	sub cookie_jar_extract($$$$) {
		371	my ($jar, $uscheme, $uhost, $upath) = @_;
		372
		373	%$jar = () if $jar->{version} != 1;
		374
		375	my @cookies;
		376
		377	while (my ($chost, $paths) = each %$jar) {
		378	next unless ref $paths;
		379
		380	if ($chost =~ /^\./) {
		381	next unless $chost eq substr $uhost, -length $chost;
		382	} elsif ($chost =~ /\./) {
		383	next unless $chost eq $uhost;
		384	} else {
		385	next;
		386	}
		387
		388	while (my ($cpath, $cookies) = each %$paths) {
		389	next unless $cpath eq substr $upath, 0, length $cpath;
		390
		391	while (my ($cookie, $kv) = each %$cookies) {
		392	next if $uscheme ne "https" && exists $kv->{secure};
		393
		394	if (exists $kv->{expires}) {
		395	if (AE::now > parse_date ($kv->{expires})) {
		396	delete $cookies->{$cookie};
		397	next;
		398	}
		399	}
		400
		401	my $value = $kv->{value};
		402
		403	if ($value =~ /[=;,[:space:]]/) {
		404	$value =~ s/([\\"])/\\$1/g;
		405	$value = "\"$value\"";
		406	}
		407
		408	push @cookies, "$cookie=$value";
		409	}
		410	}
		411	}
		412
		413	\@cookies
		414	}
		415
		416	# parse set_cookie header into jar
		417	sub cookie_jar_set_cookie($$$) {
		418	my ($jar, $set_cookie, $uhost) = @_;
		419
		420	for ($set_cookie) {
		421	# parse NAME=VALUE
		422	my @kv;
		423
		424	while (
		425	m{
		426	\G\s*
		427	(?:
		428	expires \s=\s ([A-Z][a-z][a-z],\ [^,;]+)
		429	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )
		430	)
		431	}gcxsi
		432	) {
		433	my $name = $2;
		434	my $value = $4;
		435
		436	unless (defined $name) {
		437	# expires
		438	$name = "expires";
		439	$value = $1;
		440	} elsif (!defined $value) {
		441	# quoted
		442	$value = $3;
		443	$value =~ s/\\(.)/$1/gs;
		444	}
		445
		446	push @kv, lc $name, $value;
		447
		448	last unless /\G\s*;/gc;
		449	}
		450
		451	last unless @kv;
		452
		453	my $name = shift @kv;
		454	my %kv = (value => shift @kv, @kv);
		455
		456	$kv{expires} \|\|= format_date (AE::now + $kv{"max-age"})
		457	if exists $kv{"max-age"};
		458
		459	my $cdom;
		460	my $cpath = (delete $kv{path}) \|\| "/";
		461
		462	if (exists $kv{domain}) {
		463	$cdom = delete $kv{domain};
		464
		465	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		466
		467	next if $cdom =~ /\.$/;
		468
		469	# this is not rfc-like and not netscape-like. go figure.
		470	my $ndots = $cdom =~ y/.//;
		471	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		472	} else {
		473	$cdom = $uhost;
		474	}
		475
		476	# store it
		477	$jar->{version} = 1;
		478	$jar->{$cdom}{$cpath}{$name} = \%kv;
		479
		480	redo if /\G\s*,/gc;
		481	}
		482	}
		483
		484	# continue to parse $_ for headers and place them into the arg
		485	sub parse_hdr() {
		486	my %hdr;
		487
		488	# things seen, not parsed:
		489	# p3pP="NON CUR OTPi OUR NOR UNI"
		490
		491	$hdr{lc $1} .= ",$2"
		492	while /\G
		493	([^:\000-\037]*):
		494	[\011\040]*
		495	((?: [^\012]+ \| \012[\011\040] )*)
		496	\012
		497	/gxc;
		498
		499	/\G$/
		500	or return;
		501
		502	# remove the "," prefix we added to all headers above
		503	substr $_, 0, 1, ""
		504	for values %hdr;
		505
		506	\%hdr
		507	}
		508
		509	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		510
		511	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		512	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		513
170	sub http_request($$$;@) {	514	sub http_request($$@) {
171	my $cb = pop;	515	my $cb = pop;
172	my ($method, $url, %arg) = @_;	516	my ($method, $url, %arg) = @_;
173		517
174	my %hdr;	518	my %hdr;
		519
		520	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		521	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
175		522
176	$method = uc $method;	523	$method = uc $method;
177		524
178	if (my $hdr = $arg{headers}) {	525	if (my $hdr = $arg{headers}) {
179	while (my ($k, $v) = each %$hdr) {	526	while (my ($k, $v) = each %$hdr) {
180	$hdr{lc $k} = $v;	527	$hdr{lc $k} = $v;
181	}	528	}
182	}	529	}
183		530
		531	# pseudo headers for all subsequent responses
		532	my @pseudo = (URL => $url);
		533	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		534
184	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	535	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
185		536
186	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	537	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
187	if $recurse < 0;	538	if $recurse < 0;
188		539
189	my $proxy = $arg{proxy} \|\| $PROXY;	540	my $proxy = $arg{proxy} \|\| $PROXY;
190	my $timeout = $arg{timeout} \|\| $TIMEOUT;	541	my $timeout = $arg{timeout} \|\| $TIMEOUT;
191		542
192	$hdr{"user-agent"} \|\|= $USERAGENT;
193
194	my ($scheme, $authority, $upath, $query, $fragment) =	543	my ($uscheme, $uauthority, $upath, $query, $fragment) =
195	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	544	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
196		545
197	$scheme = lc $scheme;	546	$uscheme = lc $uscheme;
198		547
199	my $uport = $scheme eq "http" ? 80	548	my $uport = $uscheme eq "http" ? 80
200	: $scheme eq "https" ? 443	549	: $uscheme eq "https" ? 443
201	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" });	550	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
202		551
203	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	552	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
204	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	553	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
205		554
206	my $uhost = $1;	555	my $uhost = $1;
207	$uport = $2 if defined $2;	556	$uport = $2 if defined $2;
208		557
		558	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		559	unless exists $hdr{host};
		560
209	$uhost =~ s/^\[(.*)\]$/$1/;	561	$uhost =~ s/^\[(.*)\]$/$1/;
210	$upath .= "?$query" if length $query;	562	$upath .= $query if length $query;
211		563
212	$upath =~ s%^/?%/%;	564	$upath =~ s%^/?%/%;
213		565
214	# cookie processing	566	# cookie processing
215	if (my $jar = $arg{cookie_jar}) {	567	if (my $jar = $arg{cookie_jar}) {
216	%$jar = () if $jar->{version} < 1;	568	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
217		569
218	my @cookie;
219
220	while (my ($chost, $v) = each %$jar) {
221	next unless $chost eq substr $uhost, -length $chost;
222	next unless $chost =~ /^\./;
223
224	while (my ($cpath, $v) = each %$v) {
225	next unless $cpath eq substr $upath, 0, length $cpath;
226
227	while (my ($k, $v) = each %$v) {
228	next if $scheme ne "https" && exists $v->{secure};
229	push @cookie, "$k=$v->{value}";
230	}
231	}
232	}
233
234	$hdr{cookie} = join "; ", @cookie	570	$hdr{cookie} = join "; ", @$cookies
235	if @cookie;	571	if @$cookies;
236	}	572	}
237		573
238	my ($rhost, $rport, $rpath); # request host, port, path	574	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
239		575
240	if ($proxy) {	576	if ($proxy) {
241	($rhost, $rport, $scheme) = @$proxy;	577	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
242	$rpath = $url;	578
		579	$rscheme = "http" unless defined $rscheme;
		580
		581	# don't support https requests over https-proxy transport,
		582	# can't be done with tls as spec'ed, unless you double-encrypt.
		583	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
243	} else {	584	} else {
244	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	585	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
245	$hdr{host} = $uhost;
246	}	586	}
247		587
		588	# leave out fragment and query string, just a heuristic
		589	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		590	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		591
248	$hdr{"content-length"} = length $arg{body};	592	$hdr{"content-length"} = length $arg{body}
		593	if length $arg{body} \|\| $method ne "GET";
249		594
250	my %state;	595	$hdr{connection} = "close TE"; #1.1
		596	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
251		597
252	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	598	my %state = (connect_guard => 1);
		599
		600	_get_slot $uhost, sub {
		601	$state{slot_guard} = shift;
		602
		603	return unless $state{connect_guard};
		604
		605	my $connect_cb = sub {
253	$state{fh} = shift	606	$state{fh} = shift
254	or return $cb->(undef, { Status => 599, Reason => "$!" });
255
256	delete $state{connect_guard}; # reduce memory usage, save a tree
257
258	# get handle
259	$state{handle} = new AnyEvent::Handle
260	fh => $state{fh},
261	($scheme eq "https" ? (tls => "connect") : ());
262
263	# limit the number of persistent connections
264	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
265	++$KA_COUNT{$_[1]};
266	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
267	$hdr{connection} = "keep-alive";
268	delete $hdr{connection}; # keep-alive not yet supported
269	} else {
270	delete $hdr{connection};
271	}
272
273	# (re-)configure handle
274	$state{handle}->timeout ($timeout);
275	$state{handle}->on_error (sub {
276	%state = ();
277	$cb->(undef, { Status => 599, Reason => "$!" });
278	});
279	$state{handle}->on_eof (sub {
280	%state = ();
281	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
282	});
283
284	# send request
285	$state{handle}->push_write (
286	"$method $rpath HTTP/1.0\015\012"
287	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
288	. "\015\012"
289	. (delete $arg{body})
290	);
291
292	%hdr = (); # reduce memory usage, save a kitten
293
294	# status line
295	$state{handle}->push_read (line => qr/\015?\012/, sub {
296	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
297	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
298
299	my %hdr = ( # response headers
300	HTTPVersion => "\x00$1",
301	Status => "\x00$2",
302	Reason => "\x00$3",
303	);
304
305	# headers, could be optimized a bit
306	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
307	for ("$_[1]\012") {
308	# we support spaces in field names, as lotus domino
309	# creates them.
310	$hdr{lc $1} .= "\x00$2"
311	while /\G
312	([^:\000-\037]+):
313	[\011\040]*
314	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
315	\015?\012
316	/gxc;
317
318	/\G$/
319	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));
320	}	607	or do {
321		608	my $err = "$!";
322	substr $_, 0, 1, ""
323	for values %hdr;
324
325	my $finish = sub {
326	%state = ();	609	%state = ();
		610	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		611	};
327		612
328	# set-cookie processing	613	pop; # free memory, save a tree
329	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	614
330	for (split /\x00/, $hdr{"set-cookie"}) {	615	return unless delete $state{connect_guard};
331	my ($cookie, @arg) = split /;\s*/;	616
332	my ($name, $value) = split /=/, $cookie, 2;	617	# get handle
333	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);	618	$state{handle} = new AnyEvent::Handle
334		619	fh => $state{fh},
335	my $cdom = (delete $kv{domain}) \|\| $uhost;	620	peername => $rhost,
336	my $cpath = (delete $kv{path}) \|\| "/";	621	tls_ctx => $arg{tls_ctx},
337		622	# these need to be reconfigured on keepalive handles
338	$cdom =~ s/^.?/./; # make sure it starts with a "."	623	timeout => $timeout,
339		624	on_error => sub {
340	my $ndots = $cdom =~ y/.//;	625	%state = ();
341	next if $ndots < ($cdom =~ /[^.]{3}$/ ? 2 : 3);	626	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
342		627	},
		628	on_eof => sub {
		629	%state = ();
		630	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		631	},
		632	;
		633
		634	# limit the number of persistent connections
		635	# keepalive not yet supported
		636	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		637	# ++$KA_COUNT{$_[1]};
		638	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		639	# --$KA_COUNT{$_[1]}
		640	# };
		641	# $hdr{connection} = "keep-alive";
		642	# }
		643
		644	$state{handle}->starttls ("connect") if $rscheme eq "https";
		645
		646	# handle actual, non-tunneled, request
		647	my $handle_actual_request = sub {
		648	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		649
		650	# send request
		651	$state{handle}->push_write (
		652	"$method $rpath HTTP/1.1\015\012"
		653	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		654	. "\015\012"
		655	. (delete $arg{body})
		656	);
		657
		658	# return if error occured during push_write()
		659	return unless %state;
		660
		661	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		662
		663	# status line and headers
		664	$state{read_response} = sub {
		665	for ("$_[1]") {
		666	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		667
		668	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
		669	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		670
		671	# 100 Continue handling
		672	# should not happen as we don't send expect: 100-continue,
		673	# but we handle it just in case.
		674	# since we send the request body regardless, if we get an error
		675	# we are out of-sync, which we currently do NOT handle correctly.
		676	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		677	if $2 eq 100;
		678
		679	push @pseudo,
		680	HTTPVersion => $1,
		681	Status => $2,
		682	Reason => $3,
		683	;
		684
		685	my $hdr = parse_hdr
		686	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		687
		688	%hdr = (%$hdr, @pseudo);
		689	}
		690
		691	# redirect handling
		692	# microsoft and other shitheads don't give a shit for following standards,
		693	# try to support some common forms of broken Location headers.
		694	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		695	$hdr{location} =~ s/^\.\/+//;
		696
		697	my $url = "$rscheme://$uhost:$uport";
		698
		699	unless ($hdr{location} =~ s/^\///) {
		700	$url .= $upath;
		701	$url =~ s/\/[^\/]*$//;
		702	}
		703
		704	$hdr{location} = "$url/$hdr{location}";
		705	}
		706
		707	my $redirect;
		708
		709	if ($recurse) {
		710	my $status = $hdr{Status};
		711
		712	# industry standard is to redirect POST as GET for
		713	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		714	# also, the UA should ask the user for 301 and 307 and POST,
		715	# industry standard seems to be to simply follow.
		716	# we go with the industry standard.
		717	if ($status == 301 or $status == 302 or $status == 303) {
		718	# HTTP/1.1 is unclear on how to mutate the method
		719	$method = "GET" unless $method eq "HEAD";
343	# store it	720	$redirect = 1;
344	$arg{cookie_jar}{version} = 1;	721	} elsif ($status == 307) {
345	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	722	$redirect = 1;
346	}	723	}
347	}	724	}
348		725
349	if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {	726	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
350	# microsoft and other assholes don't give a shit for following standards,	727	my $may_keep_alive = $_[3];
351	# try to support a common form of broken Location header.
352	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
353		728
354	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	729	$state{handle}->destroy if $state{handle};
		730	%state = ();
		731
		732	if (defined $_[1]) {
		733	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		734	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		735	}
		736
		737	# set-cookie processing
		738	if ($arg{cookie_jar}) {
		739	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost;
		740	}
		741
		742	if ($redirect && exists $hdr{location}) {
		743	# we ignore any errors, as it is very common to receive
		744	# Content-Length != 0 but no actual body
		745	# we also access %hdr, as $_[1] might be an erro
		746	http_request (
		747	$method => $hdr{location},
		748	%arg,
		749	recurse => $recurse - 1,
		750	Redirect => [$_[0], \%hdr],
		751	$cb);
		752	} else {
		753	$cb->($_[0], \%hdr);
		754	}
		755	};
		756
		757	my $len = $hdr{"content-length"};
		758
		759	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		760	$finish->(undef, 598 => "Request cancelled by on_header");
		761	} elsif (
		762	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		763	or $method eq "HEAD"
		764	or (defined $len && !$len)
		765	) {
		766	# no body
		767	$finish->("", undef, undef, 1);
355	} else {	768	} else {
356	$cb->($_[0], $_[1]);	769	# body handling, many different code paths
		770	# - no body expected
		771	# - want_body_handle
		772	# - te chunked
		773	# - 2x length known (with or without on_body)
		774	# - 2x length not known (with or without on_body)
		775	if (!$redirect && $arg{want_body_handle}) {
		776	$_[0]->on_eof (undef);
		777	$_[0]->on_error (undef);
		778	$_[0]->on_read (undef);
		779
		780	$finish->(delete $state{handle});
		781
		782	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		783	my $cl = 0;
		784	my $body = undef;
		785	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		786
		787	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		788
		789	my $read_chunk; $read_chunk = sub {
		790	$_[1] =~ /^([0-9a-fA-F]+)/
		791	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		792
		793	my $len = hex $1;
		794
		795	if ($len) {
		796	$cl += $len;
		797
		798	$_[0]->push_read (chunk => $len, sub {
		799	$on_body->($_[1], \%hdr)
		800	or return $finish->(undef, 598 => "Request cancelled by on_body");
		801
		802	$_[0]->push_read (line => sub {
		803	length $_[1]
		804	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		805	$_[0]->push_read (line => $read_chunk);
		806	});
		807	});
		808	} else {
		809	$hdr{"content-length"} \|\|= $cl;
		810
		811	$_[0]->push_read (line => $qr_nlnl, sub {
		812	if (length $_[1]) {
		813	for ("$_[1]") {
		814	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		815
		816	my $hdr = parse_hdr
		817	or return $finish->(undef, 599 => "Garbled response trailers");
		818
		819	%hdr = (%hdr, %$hdr);
		820	}
		821	}
		822
		823	$finish->($body, undef, undef, 1);
		824	});
		825	}
		826	};
		827
		828	$_[0]->push_read (line => $read_chunk);
		829
		830	} elsif ($arg{on_body}) {
		831	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		832
		833	if ($len) {
		834	$_[0]->on_read (sub {
		835	$len -= length $_[0]{rbuf};
		836
		837	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		838	or return $finish->(undef, 598 => "Request cancelled by on_body");
		839
		840	$len > 0
		841	or $finish->("", undef, undef, 1);
		842	});
		843	} else {
		844	$_[0]->on_eof (sub {
		845	$finish->("");
		846	});
		847	$_[0]->on_read (sub {
		848	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		849	or $finish->(undef, 598 => "Request cancelled by on_body");
		850	});
		851	}
		852	} else {
		853	$_[0]->on_eof (undef);
		854
		855	if ($len) {
		856	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		857	$_[0]->on_read (sub {
		858	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		859	if $len <= length $_[0]{rbuf};
		860	});
		861	} else {
		862	$_[0]->on_error (sub {
		863	($! == Errno::EPIPE \|\| !$!)
		864	? $finish->(delete $_[0]{rbuf})
		865	: $finish->(undef, 599 => $_[2]);
		866	});
		867	$_[0]->on_read (sub { });
		868	}
		869	}
357	}	870	}
358	};	871	};
359		872
360	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	873	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
361	$finish->(undef, \%hdr);	874	};
362	} else {
363	if (exists $hdr{"content-length"}) {
364	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
365	# could cache persistent connection now
366	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
367	# but we don't, due to misdesigns, this is annoyingly complex
368	};
369		875
370	$finish->($_[1], \%hdr);	876	# now handle proxy-CONNECT method
371	});	877	if ($proxy && $uscheme eq "https") {
		878	# oh dear, we have to wrap it into a connect request
		879
		880	# maybe re-use $uauthority with patched port?
		881	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		882	$state{handle}->push_read (line => $qr_nlnl, sub {
		883	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		884	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		885
		886	if ($2 == 200) {
		887	$rpath = $upath;
		888	&$handle_actual_request;
372	} else {	889	} else {
373	# too bad, need to read until we get an error or EOF,
374	# no way to detect winged data.
375	$_[0]->on_error (sub {
376	$finish->($_[0]{rbuf}, \%hdr);
377	});	890	%state = ();
378	$_[0]->on_eof (undef);	891	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
379	$_[0]->on_read (sub { });
380	}	892	}
381	}	893	});
		894	} else {
		895	&$handle_actual_request;
382	});	896	}
383	});	897	};
384	}, sub {	898
385	$timeout	899	my $tcp_connect = $arg{tcp_connect}
		900	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		901
		902	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		903
386	};	904	};
387		905
388	defined wantarray && AnyEvent::Util::guard { %state = () }	906	defined wantarray && AnyEvent::Util::guard { %state = () }
389	}	907	}
390		908
391	sub http_get($$;@) {	909	sub http_get($@) {
392	unshift @_, "GET";	910	unshift @_, "GET";
393	&http_request	911	&http_request
394	}	912	}
395		913
396	sub http_head($$;@) {	914	sub http_head($@) {
397	unshift @_, "HEAD";	915	unshift @_, "HEAD";
398	&http_request	916	&http_request
399	}	917	}
400		918
401	sub http_post($$$;@) {	919	sub http_post($$@) {
		920	my $url = shift;
402	unshift @_, "POST", "body";	921	unshift @_, "POST", $url, "body";
403	&http_request	922	&http_request
404	}	923	}
405		924
406	=back	925	=back
407		926
		927	=head2 DNS CACHING
		928
		929	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		930	the actual connection, which in turn uses AnyEvent::DNS to resolve
		931	hostnames. The latter is a simple stub resolver and does no caching
		932	on its own. If you want DNS caching, you currently have to provide
		933	your own default resolver (by storing a suitable resolver object in
		934	C<$AnyEvent::DNS::RESOLVER>).
		935
408	=head2 GLOBAL FUNCTIONS AND VARIABLES	936	=head2 GLOBAL FUNCTIONS AND VARIABLES
409		937
410	=over 4	938	=over 4
411		939
412	=item AnyEvent::HTTP::set_proxy "proxy-url"	940	=item AnyEvent::HTTP::set_proxy "proxy-url"
413		941
414	Sets the default proxy server to use. The proxy-url must begin with a	942	Sets the default proxy server to use. The proxy-url must begin with a
415	string of the form C<http://host:port> (optionally C<https:...>).	943	string of the form C<http://host:port> (optionally C<https:...>), croaks
		944	otherwise.
		945
		946	To clear an already-set proxy, use C<undef>.
		947
		948	=item $date = AnyEvent::HTTP::format_date $timestamp
		949
		950	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		951	Date (RFC 2616).
		952
		953	=item $timestamp = AnyEvent::HTTP::parse_date $date
		954
		955	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and
		956	returns the corresponding POSIX timestamp, or C<undef> if the date cannot
		957	be parsed.
416		958
417	=item $AnyEvent::HTTP::MAX_RECURSE	959	=item $AnyEvent::HTTP::MAX_RECURSE
418		960
419	The default value for the C<recurse> request parameter (default: C<10>).	961	The default value for the C<recurse> request parameter (default: C<10>).
420		962
421	=item $AnyEvent::HTTP::USERAGENT	963	=item $AnyEvent::HTTP::USERAGENT
422		964
423	The default value for the C<User-Agent> header (the default is	965	The default value for the C<User-Agent> header (the default is
424	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	966	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
425		967
426	=item $AnyEvent::HTTP::MAX_PERSISTENT	968	=item $AnyEvent::HTTP::MAX_PER_HOST
427		969
428	The maximum number of persistent connections to keep open (default: 8).	970	The maximum number of concurrent connections to the same host (identified
		971	by the hostname). If the limit is exceeded, then the additional requests
		972	are queued until previous connections are closed.
429		973
430	Not implemented currently.	974	The default value for this is C<4>, and it is highly advisable to not
		975	increase it.
431		976
432	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	977	=item $AnyEvent::HTTP::ACTIVE
433		978
434	The maximum time to cache a persistent connection, in seconds (default: 2).	979	The number of active connections. This is not the number of currently
435		980	running requests, but the number of currently open and non-idle TCP
436	Not implemented currently.	981	connections. This number of can be useful for load-leveling.
437		982
438	=back	983	=back
439		984
440	=cut	985	=cut
441		986
		987	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		988	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		989
		990	sub format_date($) {
		991	my ($time) = @_;
		992
		993	# RFC 822/1123 format
		994	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		995
		996	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		997	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		998	$H, $M, $S;
		999	}
		1000
		1001	sub parse_date($) {
		1002	my ($date) = @_;
		1003
		1004	my ($d, $m, $y, $H, $M, $S);
		1005
		1006	if ($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$/) {
		1007	# RFC 822/1123, required by RFC 2616 (with " ")
		1008	# cookie dates (with "-")
		1009
		1010	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1011
		1012	} elsif ($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$/) {
		1013	# RFC 850
		1014	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1015
		1016	} elsif ($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])$/) {
		1017	# ISO C's asctime
		1018	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1019	}
		1020	# other formats fail in the loop below
		1021
		1022	for (0..11) {
		1023	if ($m eq $month[$_]) {
		1024	require Time::Local;
		1025	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1026	}
		1027	}
		1028
		1029	undef
		1030	}
		1031
442	sub set_proxy($) {	1032	sub set_proxy($) {
		1033	if (length $_[0]) {
443	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1034	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1035	or Carp::croak "$_[0]: invalid proxy URL";
		1036	$PROXY = [$2, $3 \|\| 3128, $1]
		1037	} else {
		1038	undef $PROXY;
		1039	}
444	}	1040	}
445		1041
446	# initialise proxy from environment	1042	# initialise proxy from environment
		1043	eval {
447	set_proxy $ENV{http_proxy};	1044	set_proxy $ENV{http_proxy};
		1045	};
		1046
		1047	=head2 SOCKS PROXIES
		1048
		1049	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1050	compile your perl to support socks, or use an external program such as
		1051	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1052	transparently.
		1053
		1054	Alternatively, for AnyEvent::HTTP only, you can use your own
		1055	C<tcp_connect> function that does the proxy handshake - here is an example
		1056	that works with socks4a proxies:
		1057
		1058	use Errno;
		1059	use AnyEvent::Util;
		1060	use AnyEvent::Socket;
		1061	use AnyEvent::Handle;
		1062
		1063	# host, port and username of/for your socks4a proxy
		1064	my $socks_host = "10.0.0.23";
		1065	my $socks_port = 9050;
		1066	my $socks_user = "";
		1067
		1068	sub socks4a_connect {
		1069	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1070
		1071	my $hdl = new AnyEvent::Handle
		1072	connect => [$socks_host, $socks_port],
		1073	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1074	on_error => sub { $connect_cb->() },
		1075	;
		1076
		1077	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1078
		1079	$hdl->push_read (chunk => 8, sub {
		1080	my ($hdl, $chunk) = @_;
		1081	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1082
		1083	if ($status == 0x5a) {
		1084	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1085	} else {
		1086	$! = Errno::ENXIO; $connect_cb->();
		1087	}
		1088	});
		1089
		1090	$hdl
		1091	}
		1092
		1093	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1094	possibly after switching off other proxy types:
		1095
		1096	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1097
		1098	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1099	my ($data, $headers) = @_;
		1100	...
		1101	};
448		1102
449	=head1 SEE ALSO	1103	=head1 SEE ALSO
450		1104
451	L<AnyEvent>.	1105	L<AnyEvent>.
452		1106
453	=head1 AUTHOR	1107	=head1 AUTHOR
454		1108
455	Marc Lehmann <schmorp@schmorp.de>	1109	Marc Lehmann <schmorp@schmorp.de>
456	http://home.schmorp.de/	1110	http://home.schmorp.de/
		1111
		1112	With many thanks to Дмитрий Шалашов, who provided countless
		1113	testcases and bugreports.
457		1114
458	=cut	1115	=cut
459		1116
460	1	1117	1
461		1118

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.10 by root, Thu Jun 5 13:06:43 2008 UTC vs. Revision 1.74 by root, Fri Dec 31 22:40:54 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.10 by root, Thu Jun 5 13:06:43 2008 UTC vs.
Revision 1.74 by root, Fri Dec 31 22:40:54 2010 UTC