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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.11 by root, Thu Jun 5 15:34:00 2008 UTC vs.
Revision 1.76 by root, Sat Jan 1 02:20:49 2011 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.
…		…
35	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
36		40
37	use strict;	41	use strict;
38	no warnings;	42	no warnings;
39		43
40	use Carp;	44	use Errno ();
41		45
42	use AnyEvent ();	46	use AnyEvent 5.0 ();
43	use AnyEvent::Util ();	47	use AnyEvent::Util ();
44	use AnyEvent::Socket ();
45	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
46		49
47	use base Exporter::;	50	use base Exporter::;
48		51
49	our $VERSION = '1.0';	52	our $VERSION = '1.5';
50		53
51	our @EXPORT = qw(http_get http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
52		55
53	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)";
54	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
55	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
56	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
57	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
58		61
59	# changing these is evil	62	# changing these is evil
60	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
61	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
62		65
63	our $PROXY;	66	our $PROXY;
		67	our $ACTIVE = 0;
64		68
65	my %KA_COUNT; # number of open keep-alive connections per host	69	my %KA_COUNT; # number of open keep-alive connections per host
66	my %CO_SLOT; # number of open connections, and wait queue, per host	70	my %CO_SLOT; # number of open connections, and wait queue, per host
67		71
68	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
69		73
70	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
71	additional parameters.	75	additional parameters and the return value.
72		76
73	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
74		78
75	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
76	additional parameters.	80	on additional parameters and the return value.
77		81
78	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
79		83
80	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
81	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
82		87
83	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
84		89
85	Executes a HTTP request of type C<$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
86	must be an absolute http or https URL.	91	must be an absolute http or https URL.
87		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
88	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
89	(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
90	response headers as second argument.	100	(and trailers) as second argument.
91		101
92	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
93	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
94	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	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
95	name. If the server sends a header multiple lines, then their contents	123	If the server sends a header multiple times, then their contents will be
96	will be joined together with C<\x00>.	124	joined together with a comma (C<,>), as per the HTTP spec.
97		125
98	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
99	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
100	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
101		130
102	A typical callback might look like this:	131	A typical callback might look like this:
103		132
104	sub {	133	sub {
105	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
121	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
122	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
123		152
124	=item headers => hashref	153	=item headers => hashref
125		154
126	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).
127		160
128	=item timeout => $seconds	161	=item timeout => $seconds
129		162
130	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
131	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
132		168
133	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
134		170
135	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
136	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
137		173
138	C<$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
139	HTTPS.	175	HTTPS.
140		176
141	=item body => $string	177	=item body => $string
142		178
143	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
144	this module might offer more options).	180	this module might offer more options).
145		181
146	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
147		183
148	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
149	based on the original netscape specification.	185	based on the original netscape specification.
150		186
151	The C<$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
152	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
153	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
154	recommended, as expire times are currently being ignored.	190	recommended, as session-only cookies might survive longer than expected.
155		191
156	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
157	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
158	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
159	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
160	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.
161		303
162	=back	304	=back
163		305
164	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.
165		308
166	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
167	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
168	print "$body\n";	311	print "$body\n";
169	};	312	};
170		313
171	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
172	timeout of 30 seconds.	315	timeout of 30 seconds.
173		316
174	http_request	317	http_request
175	GET => "https://www.google.com",	318	GET => "https://www.google.com",
176	timeout => 30,	319	timeout => 30,
…		…
179	use Data::Dumper;	322	use Data::Dumper;
180	print Dumper $hdr;	323	print Dumper $hdr;
181	}	324	}
182	;	325	;
183		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 $request;
		336
184	=cut	337	=cut
185		338
		339	sub _slot_schedule;
186	sub _slot_schedule($) {	340	sub _slot_schedule($) {
187	my $host = shift;	341	my $host = shift;
188		342
189	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {	343	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
190	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {	344	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
191	# somebody wnats that slot	345	# somebody wants that slot
192	++$CO_SLOT{$host}[0];	346	++$CO_SLOT{$host}[0];
		347	++$ACTIVE;
193		348
194	$cb->(AnyEvent::Util::guard {	349	$cb->(AnyEvent::Util::guard {
		350	--$ACTIVE;
195	--$CO_SLOT{$host}[0];	351	--$CO_SLOT{$host}[0];
196	_slot_schedule $host;	352	_slot_schedule $host;
197	});	353	});
198	} else {	354	} else {
199	# nobody wants the slot, maybe we can forget about it	355	# nobody wants the slot, maybe we can forget about it
200	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];	356	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
201	warn "$host deleted" unless $CO_SLOT{$host}[0];#d#
202	last;	357	last;
203	}	358	}
204	}	359	}
205	}	360	}
206		361
…		…
209	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
210		365
211	_slot_schedule $_[0];	366	_slot_schedule $_[0];
212	}	367	}
213		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
214	sub http_request($$$;@) {	514	sub http_request($$@) {
215	my $cb = pop;	515	my $cb = pop;
216	my ($method, $url, %arg) = @_;	516	my ($method, $url, %arg) = @_;
217		517
218	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";
219		522
220	$method = uc $method;	523	$method = uc $method;
221		524
222	if (my $hdr = $arg{headers}) {	525	if (my $hdr = $arg{headers}) {
223	while (my ($k, $v) = each %$hdr) {	526	while (my ($k, $v) = each %$hdr) {
224	$hdr{lc $k} = $v;	527	$hdr{lc $k} = $v;
225	}	528	}
226	}	529	}
227		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
228	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	535	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
229		536
230	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	537	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
231	if $recurse < 0;	538	if $recurse < 0;
232		539
233	my $proxy = $arg{proxy} \|\| $PROXY;	540	my $proxy = $arg{proxy} \|\| $PROXY;
234	my $timeout = $arg{timeout} \|\| $TIMEOUT;	541	my $timeout = $arg{timeout} \|\| $TIMEOUT;
235		542
236	$hdr{"user-agent"} \|\|= $USERAGENT;
237
238	my ($scheme, $authority, $upath, $query, $fragment) =	543	my ($uscheme, $uauthority, $upath, $query, $fragment) =
239	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	544	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
240		545
241	$scheme = lc $scheme;	546	$uscheme = lc $uscheme;
242		547
243	my $uport = $scheme eq "http" ? 80	548	my $uport = $uscheme eq "http" ? 80
244	: $scheme eq "https" ? 443	549	: $uscheme eq "https" ? 443
245	: 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" });
246		551
247	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	552	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
248	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	553	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
249		554
250	my $uhost = $1;	555	my $uhost = $1;
251	$uport = $2 if defined $2;	556	$uport = $2 if defined $2;
252		557
		558	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		559	unless exists $hdr{host};
		560
253	$uhost =~ s/^\[(.*)\]$/$1/;	561	$uhost =~ s/^\[(.*)\]$/$1/;
254	$upath .= "?$query" if length $query;	562	$upath .= $query if length $query;
255		563
256	$upath =~ s%^/?%/%;	564	$upath =~ s%^/?%/%;
257		565
258	# cookie processing	566	# cookie processing
259	if (my $jar = $arg{cookie_jar}) {	567	if (my $jar = $arg{cookie_jar}) {
260	%$jar = () if $jar->{version} < 1;	568	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
261		569
262	my @cookie;
263
264	while (my ($chost, $v) = each %$jar) {
265	next unless $chost eq substr $uhost, -length $chost;
266	next unless $chost =~ /^\./;
267
268	while (my ($cpath, $v) = each %$v) {
269	next unless $cpath eq substr $upath, 0, length $cpath;
270
271	while (my ($k, $v) = each %$v) {
272	next if $scheme ne "https" && exists $v->{secure};
273	push @cookie, "$k=$v->{value}";
274	}
275	}
276	}
277
278	$hdr{cookie} = join "; ", @cookie	570	$hdr{cookie} = join "; ", @$cookies
279	if @cookie;	571	if @$cookies;
280	}	572	}
281		573
282	my ($rhost, $rport, $rpath); # request host, port, path	574	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
283		575
284	if ($proxy) {	576	if ($proxy) {
285	($rhost, $rport, $scheme) = @$proxy;	577	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
286	$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" && $rscheme eq "https";
287	} else {	584	} else {
288	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	585	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
289	$hdr{host} = $uhost;
290	}	586	}
291		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
292	$hdr{"content-length"} = length $arg{body};	592	$hdr{"content-length"} = length $arg{body}
		593	if length $arg{body} \|\| $method ne "GET";
		594
		595	$hdr{connection} = "close TE"; #1.1
		596	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
293		597
294	my %state = (connect_guard => 1);	598	my %state = (connect_guard => 1);
295		599
296	_get_slot $uhost, sub {	600	_get_slot $uhost, sub {
297	$state{slot_guard} = shift;	601	$state{slot_guard} = shift;
298		602
299	return unless $state{connect_guard};	603	return unless $state{connect_guard};
300		604
301	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	605	my $connect_cb = sub {
302	$state{fh} = shift	606	$state{fh} = shift
		607	or do {
		608	my $err = "$!";
		609	%state = ();
303	or return $cb->(undef, { Status => 599, Reason => "$!" });	610	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		611	};
304		612
305	delete $state{connect_guard}; # reduce memory usage, save a tree	613	return unless delete $state{connect_guard};
306		614
307	# get handle	615	# get handle
308	$state{handle} = new AnyEvent::Handle	616	$state{handle} = new AnyEvent::Handle
309	fh => $state{fh},	617	fh => $state{fh},
310	($scheme eq "https" ? (tls => "connect") : ());	618	peername => $rhost,
		619	tls_ctx => $arg{tls_ctx},
		620	# these need to be reconfigured on keepalive handles
		621	timeout => $timeout,
		622	on_error => sub {
		623	%state = ();
		624	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		625	},
		626	on_eof => sub {
		627	%state = ();
		628	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		629	},
		630	;
311		631
312	# limit the number of persistent connections	632	# limit the number of persistent connections
		633	# keepalive not yet supported
313	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	634	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
314	++$KA_COUNT{$_[1]};	635	# ++$KA_COUNT{$_[1]};
315	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	636	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		637	# --$KA_COUNT{$_[1]}
		638	# };
316	$hdr{connection} = "keep-alive";	639	# $hdr{connection} = "keep-alive";
317	delete $hdr{connection}; # keep-alive not yet supported
318	} else {
319	delete $hdr{connection};
320	}	640	# }
321		641
322	# (re-)configure handle	642	$state{handle}->starttls ("connect") if $rscheme eq "https";
323	$state{handle}->timeout ($timeout);
324	$state{handle}->on_error (sub {
325	%state = ();
326	$cb->(undef, { Status => 599, Reason => "$!" });
327	});
328	$state{handle}->on_eof (sub {
329	%state = ();
330	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
331	});
332		643
		644	# handle actual, non-tunneled, request
		645	my $handle_actual_request = sub {
		646	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		647
333	# send request	648	# send request
334	$state{handle}->push_write (	649	$state{handle}->push_write (
335	"$method $rpath HTTP/1.0\015\012"	650	"$method $rpath HTTP/1.1\015\012"
336	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	651	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
337	. "\015\012"	652	. "\015\012"
338	. (delete $arg{body})	653	. (delete $arg{body})
339	);
340
341	%hdr = (); # reduce memory usage, save a kitten
342
343	# status line
344	$state{handle}->push_read (line => qr/\015?\012/, sub {
345	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
346	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
347
348	my %hdr = ( # response headers
349	HTTPVersion => "\x00$1",
350	Status => "\x00$2",
351	Reason => "\x00$3",
352	);	654	);
353		655
354	# headers, could be optimized a bit	656	# return if error occured during push_write()
355	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	657	return unless %state;
		658
		659	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		660
		661	# status line and headers
		662	$state{read_response} = sub {
356	for ("$_[1]\012") {	663	for ("$_[1]") {
357	# we support spaces in field names, as lotus domino	664	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
358	# creates them.
359	$hdr{lc $1} .= "\x00$2"
360	while /\G
361	([^:\000-\037]+):
362	[\011\040]*
363	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
364	\015?\012
365	/gxc;
366		665
		666	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		667	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		668
		669	# 100 Continue handling
		670	# should not happen as we don't send expect: 100-continue,
		671	# but we handle it just in case.
		672	# since we send the request body regardless, if we get an error
		673	# we are out of-sync, which we currently do NOT handle correctly.
		674	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		675	if $2 eq 100;
		676
		677	push @pseudo,
		678	HTTPVersion => $1,
		679	Status => $2,
		680	Reason => $3,
367	/\G$/	681	;
		682
		683	my $hdr = parse_hdr
368	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));	684	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		685
		686	%hdr = (%$hdr, @pseudo);
369	}	687	}
370		688
371	substr $_, 0, 1, ""	689	# redirect handling
372	for values %hdr;	690	# microsoft and other shitheads don't give a shit for following standards,
		691	# try to support some common forms of broken Location headers.
		692	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		693	$hdr{location} =~ s/^\.\/+//;
373		694
374	my $finish = sub {	695	my $url = "$rscheme://$uhost:$uport";
		696
		697	unless ($hdr{location} =~ s/^\///) {
		698	$url .= $upath;
		699	$url =~ s/\/[^\/]*$//;
		700	}
		701
		702	$hdr{location} = "$url/$hdr{location}";
		703	}
		704
		705	my $redirect;
		706
		707	if ($recurse) {
		708	my $status = $hdr{Status};
		709
		710	# industry standard is to redirect POST as GET for
		711	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		712	# also, the UA should ask the user for 301 and 307 and POST,
		713	# industry standard seems to be to simply follow.
		714	# we go with the industry standard.
		715	if ($status == 301 or $status == 302 or $status == 303) {
		716	# HTTP/1.1 is unclear on how to mutate the method
		717	$method = "GET" unless $method eq "HEAD";
		718	$redirect = 1;
		719	} elsif ($status == 307) {
		720	$redirect = 1;
		721	}
		722	}
		723
		724	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		725	my $may_keep_alive = $_[3];
		726
		727	$state{handle}->destroy if $state{handle};
375	%state = ();	728	%state = ();
376		729
		730	if (defined $_[1]) {
		731	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		732	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		733	}
		734
377	# set-cookie processing	735	# set-cookie processing
378	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	736	if ($arg{cookie_jar}) {
379	for (split /\x00/, $hdr{"set-cookie"}) {	737	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost;
380	my ($cookie, @arg) = split /;\s*/;	738	}
381	my ($name, $value) = split /=/, $cookie, 2;
382	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
383
384	my $cdom = (delete $kv{domain}) \|\| $uhost;
385	my $cpath = (delete $kv{path}) \|\| "/";
386
387	$cdom =~ s/^.?/./; # make sure it starts with a "."
388		739
389	next if $cdom =~ /\.$/;	740	if ($redirect && exists $hdr{location}) {
390		741	# we ignore any errors, as it is very common to receive
391	# this is not rfc-like and not netscape-like. go figure.	742	# Content-Length != 0 but no actual body
392	my $ndots = $cdom =~ y/.//;	743	# we also access %hdr, as $_[1] might be an erro
393	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	744	http_request (
394		745	$method => $hdr{location},
		746	%arg,
		747	recurse => $recurse - 1,
		748	Redirect => [$_[0], \%hdr],
		749	$cb);
		750	} else {
		751	$cb->($_[0], \%hdr);
		752	}
		753	};
		754
		755	my $len = $hdr{"content-length"};
		756
		757	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		758	$finish->(undef, 598 => "Request cancelled by on_header");
		759	} elsif (
		760	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		761	or $method eq "HEAD"
		762	or (defined $len && !$len)
		763	) {
		764	# no body
		765	$finish->("", undef, undef, 1);
		766	} else {
		767	# body handling, many different code paths
		768	# - no body expected
		769	# - want_body_handle
		770	# - te chunked
		771	# - 2x length known (with or without on_body)
		772	# - 2x length not known (with or without on_body)
		773	if (!$redirect && $arg{want_body_handle}) {
		774	$_[0]->on_eof (undef);
		775	$_[0]->on_error (undef);
		776	$_[0]->on_read (undef);
		777
		778	$finish->(delete $state{handle});
		779
		780	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		781	my $cl = 0;
		782	my $body = undef;
		783	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		784
		785	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		786
		787	my $read_chunk; $read_chunk = sub {
		788	$_[1] =~ /^([0-9a-fA-F]+)/
		789	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		790
		791	my $len = hex $1;
		792
		793	if ($len) {
		794	$cl += $len;
		795
		796	$_[0]->push_read (chunk => $len, sub {
		797	$on_body->($_[1], \%hdr)
		798	or return $finish->(undef, 598 => "Request cancelled by on_body");
		799
		800	$_[0]->push_read (line => sub {
		801	length $_[1]
		802	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		803	$_[0]->push_read (line => $read_chunk);
		804	});
		805	});
395	# store it	806	} else {
396	$arg{cookie_jar}{version} = 1;	807	$hdr{"content-length"} \|\|= $cl;
397	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	808
		809	$_[0]->push_read (line => $qr_nlnl, sub {
		810	if (length $_[1]) {
		811	for ("$_[1]") {
		812	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		813
		814	my $hdr = parse_hdr
		815	or return $finish->(undef, 599 => "Garbled response trailers");
		816
		817	%hdr = (%hdr, %$hdr);
		818	}
		819	}
		820
		821	$finish->($body, undef, undef, 1);
		822	});
		823	}
		824	};
		825
		826	$_[0]->push_read (line => $read_chunk);
		827
		828	} elsif ($arg{on_body}) {
		829	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		830
		831	if ($len) {
		832	$_[0]->on_read (sub {
		833	$len -= length $_[0]{rbuf};
		834
		835	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		836	or return $finish->(undef, 598 => "Request cancelled by on_body");
		837
		838	$len > 0
		839	or $finish->("", undef, undef, 1);
		840	});
		841	} else {
		842	$_[0]->on_eof (sub {
		843	$finish->("");
		844	});
		845	$_[0]->on_read (sub {
		846	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		847	or $finish->(undef, 598 => "Request cancelled by on_body");
		848	});
		849	}
		850	} else {
		851	$_[0]->on_eof (undef);
		852
		853	if ($len) {
		854	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		855	$_[0]->on_read (sub {
		856	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		857	if $len <= length $_[0]{rbuf};
		858	});
		859	} else {
		860	$_[0]->on_error (sub {
		861	($! == Errno::EPIPE \|\| !$!)
		862	? $finish->(delete $_[0]{rbuf})
		863	: $finish->(undef, 599 => $_[2]);
		864	});
		865	$_[0]->on_read (sub { });
398	}	866	}
399	}	867	}
400
401	if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {
402	# microsoft and other assholes don't give a shit for following standards,
403	# try to support a common form of broken Location header.
404	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
405
406	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
407	} else {
408	$cb->($_[0], $_[1]);
409	}
410	};	868	}
		869	};
411		870
412	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	871	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
413	$finish->(undef, \%hdr);	872	};
		873
		874	# now handle proxy-CONNECT method
		875	if ($proxy && $uscheme eq "https") {
		876	# oh dear, we have to wrap it into a connect request
		877
		878	# maybe re-use $uauthority with patched port?
		879	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		880	$state{handle}->push_read (line => $qr_nlnl, sub {
		881	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		882	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		883
		884	if ($2 == 200) {
		885	$rpath = $upath;
		886	&$handle_actual_request;
414	} else {	887	} else {
415	if (exists $hdr{"content-length"}) {	888	%state = ();
416	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	889	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
417	# could cache persistent connection now
418	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
419	# but we don't, due to misdesigns, this is annoyingly complex
420	};
421
422	$finish->($_[1], \%hdr);
423	});
424	} else {
425	# too bad, need to read until we get an error or EOF,
426	# no way to detect winged data.
427	$_[0]->on_error (sub {
428	$finish->($_[0]{rbuf}, \%hdr);
429	});
430	$_[0]->on_eof (undef);
431	$_[0]->on_read (sub { });
432	}
433	}	890	}
434	});	891	});
		892	} else {
		893	&$handle_actual_request;
435	});	894	}
436	}, sub {
437	$timeout
438	};	895	};
		896
		897	my $tcp_connect = $arg{tcp_connect}
		898	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		899
		900	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		901
439	};	902	};
440		903
441	defined wantarray && AnyEvent::Util::guard { %state = () }	904	defined wantarray && AnyEvent::Util::guard { %state = () }
442	}	905	}
443		906
444	sub http_get($$;@) {	907	sub http_get($@) {
445	unshift @_, "GET";	908	unshift @_, "GET";
446	&http_request	909	&http_request
447	}	910	}
448		911
449	sub http_head($$;@) {	912	sub http_head($@) {
450	unshift @_, "HEAD";	913	unshift @_, "HEAD";
451	&http_request	914	&http_request
452	}	915	}
453		916
454	sub http_post($$$;@) {	917	sub http_post($$@) {
		918	my $url = shift;
455	unshift @_, "POST", "body";	919	unshift @_, "POST", $url, "body";
456	&http_request	920	&http_request
457	}	921	}
458		922
459	=back	923	=back
460		924
		925	=head2 DNS CACHING
		926
		927	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		928	the actual connection, which in turn uses AnyEvent::DNS to resolve
		929	hostnames. The latter is a simple stub resolver and does no caching
		930	on its own. If you want DNS caching, you currently have to provide
		931	your own default resolver (by storing a suitable resolver object in
		932	C<$AnyEvent::DNS::RESOLVER>).
		933
461	=head2 GLOBAL FUNCTIONS AND VARIABLES	934	=head2 GLOBAL FUNCTIONS AND VARIABLES
462		935
463	=over 4	936	=over 4
464		937
465	=item AnyEvent::HTTP::set_proxy "proxy-url"	938	=item AnyEvent::HTTP::set_proxy "proxy-url"
466		939
467	Sets the default proxy server to use. The proxy-url must begin with a	940	Sets the default proxy server to use. The proxy-url must begin with a
468	string of the form C<http://host:port> (optionally C<https:...>).	941	string of the form C<http://host:port> (optionally C<https:...>), croaks
		942	otherwise.
		943
		944	To clear an already-set proxy, use C<undef>.
		945
		946	=item $date = AnyEvent::HTTP::format_date $timestamp
		947
		948	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		949	Date (RFC 2616).
		950
		951	=item $timestamp = AnyEvent::HTTP::parse_date $date
		952
		953	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and
		954	returns the corresponding POSIX timestamp, or C<undef> if the date cannot
		955	be parsed.
469		956
470	=item $AnyEvent::HTTP::MAX_RECURSE	957	=item $AnyEvent::HTTP::MAX_RECURSE
471		958
472	The default value for the C<recurse> request parameter (default: C<10>).	959	The default value for the C<recurse> request parameter (default: C<10>).
473		960
474	=item $AnyEvent::HTTP::USERAGENT	961	=item $AnyEvent::HTTP::USERAGENT
475		962
476	The default value for the C<User-Agent> header (the default is	963	The default value for the C<User-Agent> header (the default is
477	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	964	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
478		965
479	=item $AnyEvent::HTTP::MAX_PERSISTENT	966	=item $AnyEvent::HTTP::MAX_PER_HOST
480		967
481	The maximum number of persistent connections to keep open (default: 8).	968	The maximum number of concurrent connections to the same host (identified
		969	by the hostname). If the limit is exceeded, then the additional requests
		970	are queued until previous connections are closed.
482		971
483	Not implemented currently.	972	The default value for this is C<4>, and it is highly advisable to not
		973	increase it.
484		974
485	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	975	=item $AnyEvent::HTTP::ACTIVE
486		976
487	The maximum time to cache a persistent connection, in seconds (default: 2).	977	The number of active connections. This is not the number of currently
488		978	running requests, but the number of currently open and non-idle TCP
489	Not implemented currently.	979	connections. This number of can be useful for load-leveling.
490		980
491	=back	981	=back
492		982
493	=cut	983	=cut
494		984
		985	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		986	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		987
		988	sub format_date($) {
		989	my ($time) = @_;
		990
		991	# RFC 822/1123 format
		992	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		993
		994	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		995	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		996	$H, $M, $S;
		997	}
		998
		999	sub parse_date($) {
		1000	my ($date) = @_;
		1001
		1002	my ($d, $m, $y, $H, $M, $S);
		1003
		1004	if ($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$/) {
		1005	# RFC 822/1123, required by RFC 2616 (with " ")
		1006	# cookie dates (with "-")
		1007
		1008	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1009
		1010	} elsif ($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$/) {
		1011	# RFC 850
		1012	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1013
		1014	} elsif ($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])$/) {
		1015	# ISO C's asctime
		1016	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1017	}
		1018	# other formats fail in the loop below
		1019
		1020	for (0..11) {
		1021	if ($m eq $month[$_]) {
		1022	require Time::Local;
		1023	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1024	}
		1025	}
		1026
		1027	undef
		1028	}
		1029
495	sub set_proxy($) {	1030	sub set_proxy($) {
		1031	if (length $_[0]) {
496	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1032	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1033	or Carp::croak "$_[0]: invalid proxy URL";
		1034	$PROXY = [$2, $3 \|\| 3128, $1]
		1035	} else {
		1036	undef $PROXY;
		1037	}
497	}	1038	}
498		1039
499	# initialise proxy from environment	1040	# initialise proxy from environment
		1041	eval {
500	set_proxy $ENV{http_proxy};	1042	set_proxy $ENV{http_proxy};
		1043	};
		1044
		1045	=head2 SOCKS PROXIES
		1046
		1047	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1048	compile your perl to support socks, or use an external program such as
		1049	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1050	transparently.
		1051
		1052	Alternatively, for AnyEvent::HTTP only, you can use your own
		1053	C<tcp_connect> function that does the proxy handshake - here is an example
		1054	that works with socks4a proxies:
		1055
		1056	use Errno;
		1057	use AnyEvent::Util;
		1058	use AnyEvent::Socket;
		1059	use AnyEvent::Handle;
		1060
		1061	# host, port and username of/for your socks4a proxy
		1062	my $socks_host = "10.0.0.23";
		1063	my $socks_port = 9050;
		1064	my $socks_user = "";
		1065
		1066	sub socks4a_connect {
		1067	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1068
		1069	my $hdl = new AnyEvent::Handle
		1070	connect => [$socks_host, $socks_port],
		1071	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1072	on_error => sub { $connect_cb->() },
		1073	;
		1074
		1075	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1076
		1077	$hdl->push_read (chunk => 8, sub {
		1078	my ($hdl, $chunk) = @_;
		1079	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1080
		1081	if ($status == 0x5a) {
		1082	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1083	} else {
		1084	$! = Errno::ENXIO; $connect_cb->();
		1085	}
		1086	});
		1087
		1088	$hdl
		1089	}
		1090
		1091	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1092	possibly after switching off other proxy types:
		1093
		1094	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1095
		1096	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1097	my ($data, $headers) = @_;
		1098	...
		1099	};
501		1100
502	=head1 SEE ALSO	1101	=head1 SEE ALSO
503		1102
504	L<AnyEvent>.	1103	L<AnyEvent>.
505		1104
506	=head1 AUTHOR	1105	=head1 AUTHOR
507		1106
508	Marc Lehmann <schmorp@schmorp.de>	1107	Marc Lehmann <schmorp@schmorp.de>
509	http://home.schmorp.de/	1108	http://home.schmorp.de/
		1109
		1110	With many thanks to Дмитрий Шалашов, who provided countless
		1111	testcases and bugreports.
510		1112
511	=cut	1113	=cut
512		1114
513	1	1115	1
514		1116

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.11 by root, Thu Jun 5 15:34:00 2008 UTC vs. Revision 1.76 by root, Sat Jan 1 02:20:49 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.11 by root, Thu Jun 5 15:34:00 2008 UTC vs.
Revision 1.76 by root, Sat Jan 1 02:20:49 2011 UTC