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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.82 by root, Sun Jan 2 04:50:40 2011 UTC

…		…
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Carp;	44	use Errno ();
45		45
46	use AnyEvent ();	46	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
50		49
51	use base Exporter::;	50	use base Exporter::;
52		51
53	our $VERSION = '1.01';	52	our $VERSION = '1.5';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	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)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
71	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
72		71
73	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
74		73
75	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
76	additional parameters.	75	additional parameters and the return value.
77		76
78	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
79		78
80	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
81	additional parameters.	80	on additional parameters and the return value.
82		81
83	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
84		83
85	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
86	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
87		87
88	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
89		89
90	Executes a HTTP request of type C<$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
91	must be an absolute http or https URL.	91	must be an absolute http or https URL.
92		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
93	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
94	(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
95	response headers as second argument.	100	(and trailers) as second argument.
96		101
97	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
98	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
99	C<Reason> contain the three parts of the HTTP Status-Line of the same	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	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
100	name. If the server sends a header multiple lines, then their contents	123	If the server sends a header multiple times, then their contents will be
101	will be joined together with C<\x00>.	124	joined together with a comma (C<,>), as per the HTTP spec.
102		125
103	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
104	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
105	and the C<Reason> pseudo-header will contain an error message.	128	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
		129	message. Currently the following status codes are used:
		130
		131	=over 4
		132
		133	=item 595 - errors during connection etsbalishment, proxy handshake.
		134
		135	=item 596 - errors during TLS negotiation, request sending and header processing.
		136
		137	=item 597 - errors during body receiving or processing.
		138
		139	=item 598 - user aborted request via C<on_header> or C<on_body>.
		140
		141	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		142
		143	=back
106		144
107	A typical callback might look like this:	145	A typical callback might look like this:
108		146
109	sub {	147	sub {
110	my ($body, $hdr) = @_;	148	my ($body, $hdr) = @_;
…		…
126	Whether to recurse requests or not, e.g. on redirects, authentication	164	Whether to recurse requests or not, e.g. on redirects, authentication
127	retries and so on, and how often to do so.	165	retries and so on, and how often to do so.
128		166
129	=item headers => hashref	167	=item headers => hashref
130		168
131	The request headers to use. Currently, C<http_request> may provide its	169	The request headers to use. Currently, C<http_request> may provide its own
132	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	170	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
133	and will provide defaults for C<User-Agent:> and C<Referer:>.	171	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		172	(this can be suppressed by using C<undef> for these headers in which case
		173	they won't be sent at all).
134		174
135	=item timeout => $seconds	175	=item timeout => $seconds
136		176
137	The time-out to use for various stages - each connect attempt will reset	177	The time-out to use for various stages - each connect attempt will reset
138	the timeout, as will read or write activity. Default timeout is 5 minutes.	178	the timeout, as will read or write activity, i.e. this is not an overall
		179	timeout.
		180
		181	Default timeout is 5 minutes.
139		182
140	=item proxy => [$host, $port[, $scheme]] or undef	183	=item proxy => [$host, $port[, $scheme]] or undef
141		184
142	Use the given http proxy for all requests. If not specified, then the	185	Use the given http proxy for all requests. If not specified, then the
143	default proxy (as specified by C<$ENV{http_proxy}>) is used.	186	default proxy (as specified by C<$ENV{http_proxy}>) is used.
144		187
145	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	188	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
146	HTTPS.	189	HTTPS.
147		190
148	=item body => $string	191	=item body => $string
149		192
150	The request body, usually empty. Will be-sent as-is (future versions of	193	The request body, usually empty. Will be sent as-is (future versions of
151	this module might offer more options).	194	this module might offer more options).
152		195
153	=item cookie_jar => $hash_ref	196	=item cookie_jar => $hash_ref
154		197
155	Passing this parameter enables (simplified) cookie-processing, loosely	198	Passing this parameter enables (simplified) cookie-processing, loosely
156	based on the original netscape specification.	199	based on the original netscape specification.
157		200
158	The C<$hash_ref> must be an (initially empty) hash reference which will	201	The C<$hash_ref> must be an (initially empty) hash reference which
159	get updated automatically. It is possible to save the cookie_jar to	202	will get updated automatically. It is possible to save the cookie jar
160	persistent storage with something like JSON or Storable, but this is not	203	to persistent storage with something like JSON or Storable - see the
161	recommended, as expire times are currently being ignored.	204	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		205	expired or session-only cookies, and also for documentation on the format
		206	of the cookie jar.
162		207
163	Note that this cookie implementation is not of very high quality, nor	208	Note that this cookie implementation is not meant to be complete. If
164	meant to be complete. If you want complete cookie management you have to	209	you want complete cookie management you have to do that on your
165	do that on your own. C<cookie_jar> is meant as a quick fix to get some	210	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
166	cookie-using sites working. Cookies are a privacy disaster, do not use	211	working. Cookies are a privacy disaster, do not use them unless required
167	them unless required to.	212	to.
		213
		214	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		215	headers will be set and handled by this module, otherwise they will be
		216	left untouched.
		217
		218	=item tls_ctx => $scheme \| $tls_ctx
		219
		220	Specifies the AnyEvent::TLS context to be used for https connections. This
		221	parameter follows the same rules as the C<tls_ctx> parameter to
		222	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		223	C<high> can be specified, which give you a predefined low-security (no
		224	verification, highest compatibility) and high-security (CA and common-name
		225	verification) TLS context.
		226
		227	The default for this option is C<low>, which could be interpreted as "give
		228	me the page, no matter what".
		229
		230	=item on_prepare => $callback->($fh)
		231
		232	In rare cases you need to "tune" the socket before it is used to
		233	connect (for exmaple, to bind it on a given IP address). This parameter
		234	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		235	and behaves exactly the same way (e.g. it has to provide a
		236	timeout). See the description for the C<$prepare_cb> argument of
		237	C<AnyEvent::Socket::tcp_connect> for details.
		238
		239	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		240
		241	In even rarer cases you want total control over how AnyEvent::HTTP
		242	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		243	to do this, but you can provide your own C<tcp_connect> function -
		244	obviously, it has to follow the same calling conventions, except that it
		245	may always return a connection guard object.
		246
		247	There are probably lots of weird uses for this function, starting from
		248	tracing the hosts C<http_request> actually tries to connect, to (inexact
		249	but fast) host => IP address caching or even socks protocol support.
		250
		251	=item on_header => $callback->($headers)
		252
		253	When specified, this callback will be called with the header hash as soon
		254	as headers have been successfully received from the remote server (not on
		255	locally-generated errors).
		256
		257	It has to return either true (in which case AnyEvent::HTTP will continue),
		258	or false, in which case AnyEvent::HTTP will cancel the download (and call
		259	the finish callback with an error code of C<598>).
		260
		261	This callback is useful, among other things, to quickly reject unwanted
		262	content, which, if it is supposed to be rare, can be faster than first
		263	doing a C<HEAD> request.
		264
		265	The downside is that cancelling the request makes it impossible to re-use
		266	the connection. Also, the C<on_header> callback will not receive any
		267	trailer (headers sent after the response body).
		268
		269	Example: cancel the request unless the content-type is "text/html".
		270
		271	on_header => sub {
		272	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		273	},
		274
		275	=item on_body => $callback->($partial_body, $headers)
		276
		277	When specified, all body data will be passed to this callback instead of
		278	to the completion callback. The completion callback will get the empty
		279	string instead of the body data.
		280
		281	It has to return either true (in which case AnyEvent::HTTP will continue),
		282	or false, in which case AnyEvent::HTTP will cancel the download (and call
		283	the completion callback with an error code of C<598>).
		284
		285	The downside to cancelling the request is that it makes it impossible to
		286	re-use the connection.
		287
		288	This callback is useful when the data is too large to be held in memory
		289	(so the callback writes it to a file) or when only some information should
		290	be extracted, or when the body should be processed incrementally.
		291
		292	It is usually preferred over doing your own body handling via
		293	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		294	only used to create a connection, C<want_body_handle> is the better
		295	alternative, as it allows you to install your own event handler, reducing
		296	resource usage.
		297
		298	=item want_body_handle => $enable
		299
		300	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		301	changes considerably: after parsing the headers, and instead of
		302	downloading the body (if any), the completion callback will be
		303	called. Instead of the C<$body> argument containing the body data, the
		304	callback will receive the L<AnyEvent::Handle> object associated with the
		305	connection. In error cases, C<undef> will be passed. When there is no body
		306	(e.g. status C<304>), the empty string will be passed.
		307
		308	The handle object might or might not be in TLS mode, might be connected to
		309	a proxy, be a persistent connection etc., and configured in unspecified
		310	ways. The user is responsible for this handle (it will not be used by this
		311	module anymore).
		312
		313	This is useful with some push-type services, where, after the initial
		314	headers, an interactive protocol is used (typical example would be the
		315	push-style twitter API which starts a JSON/XML stream).
		316
		317	If you think you need this, first have a look at C<on_body>, to see if
		318	that doesn't solve your problem in a better way.
168		319
169	=back	320	=back
170		321
171	Example: make a simple HTTP GET request for http://www.nethype.de/	322	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		323	the response body.
172		324
173	http_request GET => "http://www.nethype.de/", sub {	325	http_request GET => "http://www.nethype.de/", sub {
174	my ($body, $hdr) = @_;	326	my ($body, $hdr) = @_;
175	print "$body\n";	327	print "$body\n";
176	};	328	};
177		329
178	Example: make a HTTP HEAD request on https://www.google.com/, use a	330	Example: do a HTTP HEAD request on https://www.google.com/, use a
179	timeout of 30 seconds.	331	timeout of 30 seconds.
180		332
181	http_request	333	http_request
182	GET => "https://www.google.com",	334	GET => "https://www.google.com",
183	timeout => 30,	335	timeout => 30,
…		…
185	my ($body, $hdr) = @_;	337	my ($body, $hdr) = @_;
186	use Data::Dumper;	338	use Data::Dumper;
187	print Dumper $hdr;	339	print Dumper $hdr;
188	}	340	}
189	;	341	;
		342
		343	Example: do another simple HTTP GET request, but immediately try to
		344	cancel it.
		345
		346	my $request = http_request GET => "http://www.nethype.de/", sub {
		347	my ($body, $hdr) = @_;
		348	print "$body\n";
		349	};
		350
		351	undef $request;
190		352
191	=cut	353	=cut
192		354
193	sub _slot_schedule;	355	sub _slot_schedule;
194	sub _slot_schedule($) {	356	sub _slot_schedule($) {
…		…
218	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	380	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
219		381
220	_slot_schedule $_[0];	382	_slot_schedule $_[0];
221	}	383	}
222		384
		385	#############################################################################
		386
		387	# expire cookies
		388	sub cookie_jar_expire($;$) {
		389	my ($jar, $session_end) = @_;
		390
		391	%$jar = () if $jar->{version} != 1;
		392
		393	my $anow = AE::now;
		394
		395	while (my ($chost, $paths) = each %$jar) {
		396	next unless ref $paths;
		397
		398	while (my ($cpath, $cookies) = each %$paths) {
		399	while (my ($cookie, $kv) = each %$cookies) {
		400	if (exists $kv->{_expires}) {
		401	delete $cookies->{$cookie}
		402	if $anow > $kv->{_expires};
		403	} elsif ($session_end) {
		404	delete $cookies->{$cookie};
		405	}
		406	}
		407
		408	delete $paths->{$cpath}
		409	unless %$cookies;
		410	}
		411
		412	delete $jar->{$chost}
		413	unless %$paths;
		414	}
		415	}
		416
		417	# extract cookies from jar
		418	sub cookie_jar_extract($$$$) {
		419	my ($jar, $uscheme, $uhost, $upath) = @_;
		420
		421	%$jar = () if $jar->{version} != 1;
		422
		423	my @cookies;
		424
		425	while (my ($chost, $paths) = each %$jar) {
		426	next unless ref $paths;
		427
		428	if ($chost =~ /^\./) {
		429	next unless $chost eq substr $uhost, -length $chost;
		430	} elsif ($chost =~ /\./) {
		431	next unless $chost eq $uhost;
		432	} else {
		433	next;
		434	}
		435
		436	while (my ($cpath, $cookies) = each %$paths) {
		437	next unless $cpath eq substr $upath, 0, length $cpath;
		438
		439	while (my ($cookie, $kv) = each %$cookies) {
		440	next if $uscheme ne "https" && exists $kv->{secure};
		441
		442	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		443	delete $cookies->{$cookie};
		444	next;
		445	}
		446
		447	my $value = $kv->{value};
		448
		449	if ($value =~ /[=;,[:space:]]/) {
		450	$value =~ s/([\\"])/\\$1/g;
		451	$value = "\"$value\"";
		452	}
		453
		454	push @cookies, "$cookie=$value";
		455	}
		456	}
		457	}
		458
		459	\@cookies
		460	}
		461
		462	# parse set_cookie header into jar
		463	sub cookie_jar_set_cookie($$$$) {
		464	my ($jar, $set_cookie, $uhost, $date) = @_;
		465
		466	my $anow = int AE::now;
		467	my $snow; # server-now
		468
		469	for ($set_cookie) {
		470	# parse NAME=VALUE
		471	my @kv;
		472
		473	# expires is not http-compliant in the original cookie-spec,
		474	# we support the official date format and some extensions
		475	while (
		476	m{
		477	\G\s*
		478	(?:
		479	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
		480	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) ) )?
		481	)
		482	}gcxsi
		483	) {
		484	my $name = $2;
		485	my $value = $4;
		486
		487	if (defined $1) {
		488	# expires
		489	$name = "expires";
		490	$value = $1;
		491	} elsif (defined $3) {
		492	# quoted
		493	$value = $3;
		494	$value =~ s/\\(.)/$1/gs;
		495	}
		496
		497	push @kv, lc $name, $value;
		498
		499	last unless /\G\s*;/gc;
		500	}
		501
		502	last unless @kv;
		503
		504	my $name = shift @kv;
		505	my %kv = (value => shift @kv, @kv);
		506
		507	if (exists $kv{"max-age"}) {
		508	$kv{_expires} = $anow + delete $kv{"max-age"};
		509	} elsif (exists $kv{expires}) {
		510	$snow \|\|= parse_date ($date) \|\| $anow;
		511	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		512	} else {
		513	delete $kv{_expires};
		514	}
		515
		516	my $cdom;
		517	my $cpath = (delete $kv{path}) \|\| "/";
		518
		519	if (exists $kv{domain}) {
		520	$cdom = delete $kv{domain};
		521
		522	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		523
		524	next if $cdom =~ /\.$/;
		525
		526	# this is not rfc-like and not netscape-like. go figure.
		527	my $ndots = $cdom =~ y/.//;
		528	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		529	} else {
		530	$cdom = $uhost;
		531	}
		532
		533	# store it
		534	$jar->{version} = 1;
		535	$jar->{$cdom}{$cpath}{$name} = \%kv;
		536
		537	redo if /\G\s*,/gc;
		538	}
		539	}
		540
		541	# continue to parse $_ for headers and place them into the arg
		542	sub parse_hdr() {
		543	my %hdr;
		544
		545	# things seen, not parsed:
		546	# p3pP="NON CUR OTPi OUR NOR UNI"
		547
		548	$hdr{lc $1} .= ",$2"
		549	while /\G
		550	([^:\000-\037]*):
		551	[\011\040]*
		552	((?: [^\012]+ \| \012[\011\040] )*)
		553	\012
		554	/gxc;
		555
		556	/\G$/
		557	or return;
		558
		559	# remove the "," prefix we added to all headers above
		560	substr $_, 0, 1, ""
		561	for values %hdr;
		562
		563	\%hdr
		564	}
		565
		566	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		567
		568	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		569	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		570
223	sub http_request($$@) {	571	sub http_request($$@) {
224	my $cb = pop;	572	my $cb = pop;
225	my ($method, $url, %arg) = @_;	573	my ($method, $url, %arg) = @_;
226		574
227	my %hdr;	575	my %hdr;
		576
		577	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		578	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
228		579
229	$method = uc $method;	580	$method = uc $method;
230		581
231	if (my $hdr = $arg{headers}) {	582	if (my $hdr = $arg{headers}) {
232	while (my ($k, $v) = each %$hdr) {	583	while (my ($k, $v) = each %$hdr) {
233	$hdr{lc $k} = $v;	584	$hdr{lc $k} = $v;
234	}	585	}
235	}	586	}
236		587
		588	# pseudo headers for all subsequent responses
		589	my @pseudo = (URL => $url);
		590	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		591
237	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	592	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
238		593
239	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	594	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
240	if $recurse < 0;	595	if $recurse < 0;
241		596
242	my $proxy = $arg{proxy} \|\| $PROXY;	597	my $proxy = $arg{proxy} \|\| $PROXY;
243	my $timeout = $arg{timeout} \|\| $TIMEOUT;	598	my $timeout = $arg{timeout} \|\| $TIMEOUT;
244		599
245	$hdr{"user-agent"} \|\|= $USERAGENT;
246
247	my ($scheme, $authority, $upath, $query, $fragment) =	600	my ($uscheme, $uauthority, $upath, $query, $fragment) =
248	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	601	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
249		602
250	$scheme = lc $scheme;	603	$uscheme = lc $uscheme;
251		604
252	my $uport = $scheme eq "http" ? 80	605	my $uport = $uscheme eq "http" ? 80
253	: $scheme eq "https" ? 443	606	: $uscheme eq "https" ? 443
254	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	607	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
255		608
256	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
257
258	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	609	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
259	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	610	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
260		611
261	my $uhost = $1;	612	my $uhost = $1;
262	$uport = $2 if defined $2;	613	$uport = $2 if defined $2;
263		614
		615	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		616	unless exists $hdr{host};
		617
264	$uhost =~ s/^\[(.*)\]$/$1/;	618	$uhost =~ s/^\[(.*)\]$/$1/;
265	$upath .= "?$query" if length $query;	619	$upath .= $query if length $query;
266		620
267	$upath =~ s%^/?%/%;	621	$upath =~ s%^/?%/%;
268		622
269	# cookie processing	623	# cookie processing
270	if (my $jar = $arg{cookie_jar}) {	624	if (my $jar = $arg{cookie_jar}) {
271	%$jar = () if $jar->{version} < 1;	625	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
272		626
273	my @cookie;
274
275	while (my ($chost, $v) = each %$jar) {
276	next unless $chost eq substr $uhost, -length $chost;
277	next unless $chost =~ /^\./;
278
279	while (my ($cpath, $v) = each %$v) {
280	next unless $cpath eq substr $upath, 0, length $cpath;
281
282	while (my ($k, $v) = each %$v) {
283	next if $scheme ne "https" && exists $v->{secure};
284	push @cookie, "$k=$v->{value}";
285	}
286	}
287	}
288
289	$hdr{cookie} = join "; ", @cookie	627	$hdr{cookie} = join "; ", @$cookies
290	if @cookie;	628	if @$cookies;
291	}	629	}
292		630
293	my ($rhost, $rport, $rpath); # request host, port, path	631	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
294		632
295	if ($proxy) {	633	if ($proxy) {
296	($rhost, $rport, $scheme) = @$proxy;	634	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
297	$rpath = $url;	635
		636	$rscheme = "http" unless defined $rscheme;
		637
		638	# don't support https requests over https-proxy transport,
		639	# can't be done with tls as spec'ed, unless you double-encrypt.
		640	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
298	} else {	641	} else {
299	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	642	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
300	$hdr{host} = $uhost;
301	}	643	}
302		644
		645	# leave out fragment and query string, just a heuristic
		646	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		647	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		648
303	$hdr{"content-length"} = length $arg{body};	649	$hdr{"content-length"} = length $arg{body}
		650	if length $arg{body} \|\| $method ne "GET";
		651
		652	$hdr{connection} = "close TE"; #1.1
		653	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
304		654
305	my %state = (connect_guard => 1);	655	my %state = (connect_guard => 1);
306		656
307	_get_slot $uhost, sub {	657	_get_slot $uhost, sub {
308	$state{slot_guard} = shift;	658	$state{slot_guard} = shift;
309		659
310	return unless $state{connect_guard};	660	return unless $state{connect_guard};
311		661
312	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	662	my $ae_error = 595; # connecting
313	$state{fh} = shift
314	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
315		663
316	delete $state{connect_guard}; # reduce memory usage, save a tree	664	# handle actual, non-tunneled, request
		665	my $handle_actual_request = sub {
		666	$ae_error = 596; # request phase
317		667
318	# get handle	668	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
319	$state{handle} = new AnyEvent::Handle
320	fh => $state{fh},
321	($scheme eq "https" ? (tls => "connect") : ());
322
323	# limit the number of persistent connections
324	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
325	++$KA_COUNT{$_[1]};
326	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
327	$hdr{connection} = "keep-alive";
328	delete $hdr{connection}; # keep-alive not yet supported
329	} else {
330	delete $hdr{connection};
331	}
332
333	# (re-)configure handle
334	$state{handle}->timeout ($timeout);
335	$state{handle}->on_error (sub {
336	my $errno = "$!";
337	%state = ();
338	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
339	});
340	$state{handle}->on_eof (sub {
341	%state = ();
342	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
343	});
344		669
345	# send request	670	# send request
346	$state{handle}->push_write (	671	$state{handle}->push_write (
347	"$method $rpath HTTP/1.0\015\012"	672	"$method $rpath HTTP/1.1\015\012"
348	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	673	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
349	. "\015\012"	674	. "\015\012"
350	. (delete $arg{body})	675	. (delete $arg{body})
351	);	676	);
352		677
		678	# return if error occured during push_write()
		679	return unless %state;
		680
353	%hdr = (); # reduce memory usage, save a kitten	681	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
354		682
355	# status line	683	# status line and headers
356	$state{handle}->push_read (line => qr/\015?\012/, sub {	684	$state{read_response} = sub {
357	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
358	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
359
360	my %hdr = ( # response headers
361	HTTPVersion => "\x00$1",
362	Status => "\x00$2",
363	Reason => "\x00$3",
364	URL => "\x00$url"
365	);
366
367	# headers, could be optimized a bit
368	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
369	for ("$_[1]\012") {	685	for ("$_[1]") {
370	# we support spaces in field names, as lotus domino	686	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
371	# creates them.
372	$hdr{lc $1} .= "\x00$2"
373	while /\G
374	([^:\000-\037]+):
375	[\011\040]*
376	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
377	\015?\012
378	/gxc;
379		687
		688	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		689	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		690
		691	# 100 Continue handling
		692	# should not happen as we don't send expect: 100-continue,
		693	# but we handle it just in case.
		694	# since we send the request body regardless, if we get an error
		695	# we are out of-sync, which we currently do NOT handle correctly.
		696	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		697	if $2 eq 100;
		698
		699	push @pseudo,
		700	HTTPVersion => $1,
		701	Status => $2,
		702	Reason => $3,
380	/\G$/	703	;
		704
		705	my $hdr = parse_hdr
381	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	706	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		707
		708	%hdr = (%$hdr, @pseudo);
		709	}
		710
		711	# redirect handling
		712	# microsoft and other shitheads don't give a shit for following standards,
		713	# try to support some common forms of broken Location headers.
		714	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		715	$hdr{location} =~ s/^\.\/+//;
		716
		717	my $url = "$rscheme://$uhost:$uport";
		718
		719	unless ($hdr{location} =~ s/^\///) {
		720	$url .= $upath;
		721	$url =~ s/\/[^\/]*$//;
382	}	722	}
383		723
384	substr $_, 0, 1, ""	724	$hdr{location} = "$url/$hdr{location}";
385	for values %hdr;	725	}
386		726
387	my $finish = sub {	727	my $redirect;
		728
		729	if ($recurse) {
		730	my $status = $hdr{Status};
		731
		732	# industry standard is to redirect POST as GET for
		733	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		734	# also, the UA should ask the user for 301 and 307 and POST,
		735	# industry standard seems to be to simply follow.
		736	# we go with the industry standard.
		737	if ($status == 301 or $status == 302 or $status == 303) {
		738	# HTTP/1.1 is unclear on how to mutate the method
		739	$method = "GET" unless $method eq "HEAD";
		740	$redirect = 1;
		741	} elsif ($status == 307) {
		742	$redirect = 1;
		743	}
		744	}
		745
		746	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		747	my $may_keep_alive = $_[3];
		748
		749	$state{handle}->destroy if $state{handle};
388	%state = ();	750	%state = ();
389		751
		752	if (defined $_[1]) {
		753	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		754	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		755	}
		756
390	# set-cookie processing	757	# set-cookie processing
391	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	758	if ($arg{cookie_jar}) {
392	for (split /\x00/, $hdr{"set-cookie"}) {	759	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
393	my ($cookie, @arg) = split /;\s*/;	760	}
394	my ($name, $value) = split /=/, $cookie, 2;
395	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
396
397	my $cdom = (delete $kv{domain}) \|\| $uhost;
398	my $cpath = (delete $kv{path}) \|\| "/";
399
400	$cdom =~ s/^.?/./; # make sure it starts with a "."
401		761
402	next if $cdom =~ /\.$/;	762	if ($redirect && exists $hdr{location}) {
403		763	# we ignore any errors, as it is very common to receive
404	# this is not rfc-like and not netscape-like. go figure.	764	# Content-Length != 0 but no actual body
405	my $ndots = $cdom =~ y/.//;	765	# we also access %hdr, as $_[1] might be an erro
406	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	766	http_request (
407		767	$method => $hdr{location},
		768	%arg,
		769	recurse => $recurse - 1,
		770	Redirect => [$_[0], \%hdr],
		771	$cb);
		772	} else {
		773	$cb->($_[0], \%hdr);
		774	}
		775	};
		776
		777	$ae_error = 597; # body phase
		778
		779	my $len = $hdr{"content-length"};
		780
		781	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		782	$finish->(undef, 598 => "Request cancelled by on_header");
		783	} elsif (
		784	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		785	or $method eq "HEAD"
		786	or (defined $len && !$len)
		787	) {
		788	# no body
		789	$finish->("", undef, undef, 1);
		790	} else {
		791	# body handling, many different code paths
		792	# - no body expected
		793	# - want_body_handle
		794	# - te chunked
		795	# - 2x length known (with or without on_body)
		796	# - 2x length not known (with or without on_body)
		797	if (!$redirect && $arg{want_body_handle}) {
		798	$_[0]->on_eof (undef);
		799	$_[0]->on_error (undef);
		800	$_[0]->on_read (undef);
		801
		802	$finish->(delete $state{handle});
		803
		804	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		805	my $cl = 0;
		806	my $body = undef;
		807	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		808
		809	$state{read_chunk} = sub {
		810	$_[1] =~ /^([0-9a-fA-F]+)/
		811	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		812
		813	my $len = hex $1;
		814
		815	if ($len) {
		816	$cl += $len;
		817
		818	$_[0]->push_read (chunk => $len, sub {
		819	$on_body->($_[1], \%hdr)
		820	or return $finish->(undef, 598 => "Request cancelled by on_body");
		821
		822	$_[0]->push_read (line => sub {
		823	length $_[1]
		824	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		825	$_[0]->push_read (line => $state{read_chunk});
		826	});
408	# store it	827	});
409	$arg{cookie_jar}{version} = 1;	828	} else {
410	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	829	$hdr{"content-length"} \|\|= $cl;
		830
		831	$_[0]->push_read (line => $qr_nlnl, sub {
		832	if (length $_[1]) {
		833	for ("$_[1]") {
		834	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		835
		836	my $hdr = parse_hdr
		837	or return $finish->(undef, $ae_error => "Garbled response trailers");
		838
		839	%hdr = (%hdr, %$hdr);
		840	}
		841	}
		842
		843	$finish->($body, undef, undef, 1);
		844	});
411	}	845	}
412	}	846	};
413		847
414	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {	848	$_[0]->push_read (line => $state{read_chunk});
415	# microsoft and other assholes don't give a shit for following standards,
416	# try to support a common form of broken Location header.
417	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
418		849
419	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	850	} elsif ($arg{on_body}) {
420	} else {	851	if ($len) {
421	$cb->($_[0], $_[1]);	852	$_[0]->on_read (sub {
422	}	853	$len -= length $_[0]{rbuf};
423	};
424		854
425	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	855	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
426	$finish->(undef, \%hdr);	856	or return $finish->(undef, 598 => "Request cancelled by on_body");
427	} else {	857
428	if (exists $hdr{"content-length"}) {
429	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
430	# could cache persistent connection now
431	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
432	# but we don't, due to misdesigns, this is annoyingly complex
433	};	858	$len > 0
434		859	or $finish->("", undef, undef, 1);
435	$finish->($_[1], \%hdr);
436	});	860	});
437	} else {	861	} else {
438	# too bad, need to read until we get an error or EOF,	862	$_[0]->on_eof (sub {
439	# no way to detect winged data.	863	$finish->("");
		864	});
		865	$_[0]->on_read (sub {
		866	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		867	or $finish->(undef, 598 => "Request cancelled by on_body");
		868	});
		869	}
		870	} else {
		871	$_[0]->on_eof (undef);
		872
		873	if ($len) {
		874	$_[0]->on_read (sub {
		875	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		876	if $len <= length $_[0]{rbuf};
		877	});
		878	} else {
440	$_[0]->on_error (sub {	879	$_[0]->on_error (sub {
		880	($! == Errno::EPIPE \|\| !$!)
441	$finish->($_[0]{rbuf}, \%hdr);	881	? $finish->(delete $_[0]{rbuf})
		882	: $finish->(undef, $ae_error => $_[2]);
442	});	883	});
443	$_[0]->on_eof (undef);
444	$_[0]->on_read (sub { });	884	$_[0]->on_read (sub { });
445	}	885	}
446	}	886	}
		887	}
		888	};
		889
		890	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
		891	};
		892
		893	my $connect_cb = sub {
		894	$state{fh} = shift
		895	or do {
		896	my $err = "$!";
		897	%state = ();
		898	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
		899	};
		900
		901	return unless delete $state{connect_guard};
		902
		903	# get handle
		904	$state{handle} = new AnyEvent::Handle
		905	fh => $state{fh},
		906	peername => $rhost,
		907	tls_ctx => $arg{tls_ctx},
		908	# these need to be reconfigured on keepalive handles
		909	timeout => $timeout,
		910	on_error => sub {
		911	%state = ();
		912	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
		913	},
		914	on_eof => sub {
		915	%state = ();
		916	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
		917	},
		918	;
		919
		920	# limit the number of persistent connections
		921	# keepalive not yet supported
		922	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		923	# ++$KA_COUNT{$_[1]};
		924	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		925	# --$KA_COUNT{$_[1]}
		926	# };
		927	# $hdr{connection} = "keep-alive";
		928	# }
		929
		930	$state{handle}->starttls ("connect") if $rscheme eq "https";
		931
		932	# now handle proxy-CONNECT method
		933	if ($proxy && $uscheme eq "https") {
		934	# oh dear, we have to wrap it into a connect request
		935
		936	# maybe re-use $uauthority with patched port?
		937	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		938	$state{handle}->push_read (line => $qr_nlnl, sub {
		939	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		940	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		941
		942	if ($2 == 200) {
		943	$rpath = $upath;
		944	$handle_actual_request->();
		945	} else {
		946	%state = ();
		947	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
		948	}
447	});	949	});
		950	} else {
		951	$handle_actual_request->();
448	});	952	}
449	}, sub {
450	$timeout
451	};	953	};
		954
		955	my $tcp_connect = $arg{tcp_connect}
		956	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		957
		958	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
452	};	959	};
453		960
454	defined wantarray && AnyEvent::Util::guard { %state = () }	961	defined wantarray && AnyEvent::Util::guard { %state = () }
455	}	962	}
456		963
…		…
463	unshift @_, "HEAD";	970	unshift @_, "HEAD";
464	&http_request	971	&http_request
465	}	972	}
466		973
467	sub http_post($$@) {	974	sub http_post($$@) {
		975	my $url = shift;
468	unshift @_, "POST", "body";	976	unshift @_, "POST", $url, "body";
469	&http_request	977	&http_request
470	}	978	}
471		979
472	=back	980	=back
473		981
		982	=head2 DNS CACHING
		983
		984	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		985	the actual connection, which in turn uses AnyEvent::DNS to resolve
		986	hostnames. The latter is a simple stub resolver and does no caching
		987	on its own. If you want DNS caching, you currently have to provide
		988	your own default resolver (by storing a suitable resolver object in
		989	C<$AnyEvent::DNS::RESOLVER>).
		990
474	=head2 GLOBAL FUNCTIONS AND VARIABLES	991	=head2 GLOBAL FUNCTIONS AND VARIABLES
475		992
476	=over 4	993	=over 4
477		994
478	=item AnyEvent::HTTP::set_proxy "proxy-url"	995	=item AnyEvent::HTTP::set_proxy "proxy-url"
479		996
480	Sets the default proxy server to use. The proxy-url must begin with a	997	Sets the default proxy server to use. The proxy-url must begin with a
481	string of the form C<http://host:port> (optionally C<https:...>).	998	string of the form C<http://host:port> (optionally C<https:...>), croaks
		999	otherwise.
		1000
		1001	To clear an already-set proxy, use C<undef>.
		1002
		1003	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1004
		1005	Remove all cookies from the cookie jar that have been expired. If
		1006	C<$session_end> is given and true, then additionally remove all session
		1007	cookies.
		1008
		1009	You should call this function (with a true C<$session_end>) before you
		1010	save cookies to disk, and you should call this function after loading them
		1011	again. If you have a long-running program you can additonally call this
		1012	function from time to time.
		1013
		1014	A cookie jar is initially an empty hash-reference that is managed by this
		1015	module. It's format is subject to change, but currently it is like this:
		1016
		1017	The key C<version> has to contain C<1>, otherwise the hash gets
		1018	emptied. All other keys are hostnames or IP addresses pointing to
		1019	hash-references. The key for these inner hash references is the
		1020	server path for which this cookie is meant, and the values are again
		1021	hash-references. The keys of those hash-references is the cookie name, and
		1022	the value, you guessed it, is another hash-reference, this time with the
		1023	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1024	which have been replaced by a C<_expires> key that contains the cookie
		1025	expiry timestamp.
		1026
		1027	Here is an example of a cookie jar with a single cookie, so you have a
		1028	chance of understanding the above paragraph:
		1029
		1030	{
		1031	version => 1,
		1032	"10.0.0.1" => {
		1033	"/" => {
		1034	"mythweb_id" => {
		1035	_expires => 1293917923,
		1036	value => "ooRung9dThee3ooyXooM1Ohm",
		1037	},
		1038	},
		1039	},
		1040	}
		1041
		1042	=item $date = AnyEvent::HTTP::format_date $timestamp
		1043
		1044	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1045	Date (RFC 2616).
		1046
		1047	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1048
		1049	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1050	bunch of minor variations of those, and returns the corresponding POSIX
		1051	timestamp, or C<undef> if the date cannot be parsed.
482		1052
483	=item $AnyEvent::HTTP::MAX_RECURSE	1053	=item $AnyEvent::HTTP::MAX_RECURSE
484		1054
485	The default value for the C<recurse> request parameter (default: C<10>).	1055	The default value for the C<recurse> request parameter (default: C<10>).
486		1056
487	=item $AnyEvent::HTTP::USERAGENT	1057	=item $AnyEvent::HTTP::USERAGENT
488		1058
489	The default value for the C<User-Agent> header (the default is	1059	The default value for the C<User-Agent> header (the default is
490	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1060	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
491		1061
492	=item $AnyEvent::HTTP::MAX_PERSISTENT	1062	=item $AnyEvent::HTTP::MAX_PER_HOST
493		1063
494	The maximum number of persistent connections to keep open (default: 8).	1064	The maximum number of concurrent connections to the same host (identified
		1065	by the hostname). If the limit is exceeded, then the additional requests
		1066	are queued until previous connections are closed.
495		1067
496	Not implemented currently.	1068	The default value for this is C<4>, and it is highly advisable to not
497		1069	increase it.
498	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
499
500	The maximum time to cache a persistent connection, in seconds (default: 2).
501
502	Not implemented currently.
503		1070
504	=item $AnyEvent::HTTP::ACTIVE	1071	=item $AnyEvent::HTTP::ACTIVE
505		1072
506	The number of active connections. This is not the number of currently	1073	The number of active connections. This is not the number of currently
507	running requests, but the number of currently open and non-idle TCP	1074	running requests, but the number of currently open and non-idle TCP
…		…
509		1076
510	=back	1077	=back
511		1078
512	=cut	1079	=cut
513		1080
		1081	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1082	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1083
		1084	sub format_date($) {
		1085	my ($time) = @_;
		1086
		1087	# RFC 822/1123 format
		1088	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1089
		1090	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1091	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1092	$H, $M, $S;
		1093	}
		1094
		1095	sub parse_date($) {
		1096	my ($date) = @_;
		1097
		1098	my ($d, $m, $y, $H, $M, $S);
		1099
		1100	if ($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$/) {
		1101	# RFC 822/1123, required by RFC 2616 (with " ")
		1102	# cookie dates (with "-")
		1103
		1104	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1105
		1106	} elsif ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) {
		1107	# RFC 850
		1108	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1109
		1110	} elsif ($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])$/) {
		1111	# ISO C's asctime
		1112	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1113	}
		1114	# other formats fail in the loop below
		1115
		1116	for (0..11) {
		1117	if ($m eq $month[$_]) {
		1118	require Time::Local;
		1119	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1120	}
		1121	}
		1122
		1123	undef
		1124	}
		1125
514	sub set_proxy($) {	1126	sub set_proxy($) {
		1127	if (length $_[0]) {
515	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1128	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1129	or Carp::croak "$_[0]: invalid proxy URL";
		1130	$PROXY = [$2, $3 \|\| 3128, $1]
		1131	} else {
		1132	undef $PROXY;
		1133	}
516	}	1134	}
517		1135
518	# initialise proxy from environment	1136	# initialise proxy from environment
		1137	eval {
519	set_proxy $ENV{http_proxy};	1138	set_proxy $ENV{http_proxy};
		1139	};
		1140
		1141	=head2 SOCKS PROXIES
		1142
		1143	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1144	compile your perl to support socks, or use an external program such as
		1145	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1146	transparently.
		1147
		1148	Alternatively, for AnyEvent::HTTP only, you can use your own
		1149	C<tcp_connect> function that does the proxy handshake - here is an example
		1150	that works with socks4a proxies:
		1151
		1152	use Errno;
		1153	use AnyEvent::Util;
		1154	use AnyEvent::Socket;
		1155	use AnyEvent::Handle;
		1156
		1157	# host, port and username of/for your socks4a proxy
		1158	my $socks_host = "10.0.0.23";
		1159	my $socks_port = 9050;
		1160	my $socks_user = "";
		1161
		1162	sub socks4a_connect {
		1163	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1164
		1165	my $hdl = new AnyEvent::Handle
		1166	connect => [$socks_host, $socks_port],
		1167	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1168	on_error => sub { $connect_cb->() },
		1169	;
		1170
		1171	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1172
		1173	$hdl->push_read (chunk => 8, sub {
		1174	my ($hdl, $chunk) = @_;
		1175	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1176
		1177	if ($status == 0x5a) {
		1178	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1179	} else {
		1180	$! = Errno::ENXIO; $connect_cb->();
		1181	}
		1182	});
		1183
		1184	$hdl
		1185	}
		1186
		1187	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1188	possibly after switching off other proxy types:
		1189
		1190	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1191
		1192	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1193	my ($data, $headers) = @_;
		1194	...
		1195	};
520		1196
521	=head1 SEE ALSO	1197	=head1 SEE ALSO
522		1198
523	L<AnyEvent>.	1199	L<AnyEvent>.
524		1200
525	=head1 AUTHOR	1201	=head1 AUTHOR
526		1202
527	Marc Lehmann <schmorp@schmorp.de>	1203	Marc Lehmann <schmorp@schmorp.de>
528	http://home.schmorp.de/	1204	http://home.schmorp.de/
529		1205
		1206	With many thanks to Дмитрий Шалашов, who provided countless
		1207	testcases and bugreports.
		1208
530	=cut	1209	=cut
531		1210
532	1	1211	1
533		1212

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs. Revision 1.82 by root, Sun Jan 2 04:50:40 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.82 by root, Sun Jan 2 04:50:40 2011 UTC