ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.33 by root, Mon Oct 27 11:09:54 2008 UTC vs.
Revision 1.90 by root, Mon Jan 3 00:41:25 2011 UTC

…		…
36		36
37	=cut	37	=cut
38		38
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use common::sense;
42	no warnings;
43		42
44	use Carp;	43	use Errno ();
45		44
46	use AnyEvent ();	45	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	46	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
50		48
51	use base Exporter::;	49	use base Exporter::;
52		50
53	our $VERSION = '1.05';	51	our $VERSION = '1.5';
54		52
55	our @EXPORT = qw(http_get http_post http_head http_request);	53	our @EXPORT = qw(http_get http_post http_head http_request);
56		54
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	55	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	56	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	57	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	58	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	59	our $TIMEOUT = 300;
62		60
…		…
92	must be an absolute http or https URL.	90	must be an absolute http or https URL.
93		91
94	When called in void context, nothing is returned. In other contexts,	92	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	93	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	94	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	95	destroyed before the callback is called, the request will be cancelled.
98		96
99	The callback will be called with the response data as first argument	97	The callback will be called with the response body data as first argument
100	(or C<undef> if it wasn't available due to errors), and a hash-ref with	98	(or C<undef> if an error occured), and a hash-ref with response headers
101	response headers as second argument.	99	(and trailers) as second argument.
102		100
103	All the headers in that hash are lowercased. In addition to the response	101	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	102	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		103	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	104	three parts of the HTTP Status-Line of the same name. If an error occurs
		105	during the body phase of a request, then the original C<Status> and
		106	C<Reason> values from the header are available as C<OrigStatus> and
		107	C<OrigReason>.
		108
106	pseudo-header C<URL> contains the original URL (which can differ from the	109	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	110	the requested URL when following redirects - for example, you might get
		111	an error that your URL scheme is not supported even though your URL is a
		112	valid http URL because it redirected to an ftp URL, in which case you can
		113	look at the URL pseudo header).
		114
		115	The pseudo-header C<Redirect> only exists when the request was a result
		116	of an internal redirect. In that case it is an array reference with
		117	the C<($data, $headers)> from the redirect response. Note that this
		118	response could in turn be the result of a redirect itself, and C<<
		119	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		120	response, and so on.
108		121
109	If the server sends a header multiple times, then their contents will be	122	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	123	joined together with a comma (C<,>), as per the HTTP spec.
111		124
112	If an internal error occurs, such as not being able to resolve a hostname,	125	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	126	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
114	and the C<Reason> pseudo-header will contain an error message.	127	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
		128	message. Currently the following status codes are used:
		129
		130	=over 4
		131
		132	=item 595 - errors during connection etsbalishment, proxy handshake.
		133
		134	=item 596 - errors during TLS negotiation, request sending and header processing.
		135
		136	=item 597 - errors during body receiving or processing.
		137
		138	=item 598 - user aborted request via C<on_header> or C<on_body>.
		139
		140	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		141
		142	=back
115		143
116	A typical callback might look like this:	144	A typical callback might look like this:
117		145
118	sub {	146	sub {
119	my ($body, $hdr) = @_;	147	my ($body, $hdr) = @_;
…		…
135	Whether to recurse requests or not, e.g. on redirects, authentication	163	Whether to recurse requests or not, e.g. on redirects, authentication
136	retries and so on, and how often to do so.	164	retries and so on, and how often to do so.
137		165
138	=item headers => hashref	166	=item headers => hashref
139		167
140	The request headers to use. Currently, C<http_request> may provide its	168	The request headers to use. Currently, C<http_request> may provide its own
141	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	169	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	170	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		171	(this can be suppressed by using C<undef> for these headers in which case
		172	they won't be sent at all).
		173
		174	You really should provide your own C<User-Agent:> header value that is
		175	appropriate for your program - I wouldn't be surprised if the default
		176	AnyEvent string gets blocked by webservers sooner or later.
143		177
144	=item timeout => $seconds	178	=item timeout => $seconds
145		179
146	The time-out to use for various stages - each connect attempt will reset	180	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	181	the timeout, as will read or write activity, i.e. this is not an overall
		182	timeout.
		183
		184	Default timeout is 5 minutes.
148		185
149	=item proxy => [$host, $port[, $scheme]] or undef	186	=item proxy => [$host, $port[, $scheme]] or undef
150		187
151	Use the given http proxy for all requests. If not specified, then the	188	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	189	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		190
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	191	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	192	HTTPS.
156		193
157	=item body => $string	194	=item body => $string
158		195
159	The request body, usually empty. Will be-sent as-is (future versions of	196	The request body, usually empty. Will be sent as-is (future versions of
160	this module might offer more options).	197	this module might offer more options).
161		198
162	=item cookie_jar => $hash_ref	199	=item cookie_jar => $hash_ref
163		200
164	Passing this parameter enables (simplified) cookie-processing, loosely	201	Passing this parameter enables (simplified) cookie-processing, loosely
165	based on the original netscape specification.	202	based on the original netscape specification.
166		203
167	The C<$hash_ref> must be an (initially empty) hash reference which will	204	The C<$hash_ref> must be an (initially empty) hash reference which
168	get updated automatically. It is possible to save the cookie_jar to	205	will get updated automatically. It is possible to save the cookie jar
169	persistent storage with something like JSON or Storable, but this is not	206	to persistent storage with something like JSON or Storable - see the
170	recommended, as expire times are currently being ignored.	207	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		208	expired or session-only cookies, and also for documentation on the format
		209	of the cookie jar.
171		210
172	Note that this cookie implementation is not of very high quality, nor	211	Note that this cookie implementation is not meant to be complete. If
173	meant to be complete. If you want complete cookie management you have to	212	you want complete cookie management you have to do that on your
174	do that on your own. C<cookie_jar> is meant as a quick fix to get some	213	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
175	cookie-using sites working. Cookies are a privacy disaster, do not use	214	working. Cookies are a privacy disaster, do not use them unless required
176	them unless required to.	215	to.
		216
		217	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		218	headers will be set and handled by this module, otherwise they will be
		219	left untouched.
		220
		221	=item tls_ctx => $scheme | $tls_ctx
		222
		223	Specifies the AnyEvent::TLS context to be used for https connections. This
		224	parameter follows the same rules as the C<tls_ctx> parameter to
		225	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		226	C<high> can be specified, which give you a predefined low-security (no
		227	verification, highest compatibility) and high-security (CA and common-name
		228	verification) TLS context.
		229
		230	The default for this option is C<low>, which could be interpreted as "give
		231	me the page, no matter what".
		232
		233	=item on_prepare => $callback->($fh)
		234
		235	In rare cases you need to "tune" the socket before it is used to
		236	connect (for exmaple, to bind it on a given IP address). This parameter
		237	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		238	and behaves exactly the same way (e.g. it has to provide a
		239	timeout). See the description for the C<$prepare_cb> argument of
		240	C<AnyEvent::Socket::tcp_connect> for details.
		241
		242	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		243
		244	In even rarer cases you want total control over how AnyEvent::HTTP
		245	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		246	to do this, but you can provide your own C<tcp_connect> function -
		247	obviously, it has to follow the same calling conventions, except that it
		248	may always return a connection guard object.
		249
		250	There are probably lots of weird uses for this function, starting from
		251	tracing the hosts C<http_request> actually tries to connect, to (inexact
		252	but fast) host => IP address caching or even socks protocol support.
		253
		254	=item on_header => $callback->($headers)
		255
		256	When specified, this callback will be called with the header hash as soon
		257	as headers have been successfully received from the remote server (not on
		258	locally-generated errors).
		259
		260	It has to return either true (in which case AnyEvent::HTTP will continue),
		261	or false, in which case AnyEvent::HTTP will cancel the download (and call
		262	the finish callback with an error code of C<598>).
		263
		264	This callback is useful, among other things, to quickly reject unwanted
		265	content, which, if it is supposed to be rare, can be faster than first
		266	doing a C<HEAD> request.
		267
		268	The downside is that cancelling the request makes it impossible to re-use
		269	the connection. Also, the C<on_header> callback will not receive any
		270	trailer (headers sent after the response body).
		271
		272	Example: cancel the request unless the content-type is "text/html".
		273
		274	on_header => sub {
		275	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/
		276	},
		277
		278	=item on_body => $callback->($partial_body, $headers)
		279
		280	When specified, all body data will be passed to this callback instead of
		281	to the completion callback. The completion callback will get the empty
		282	string instead of the body data.
		283
		284	It has to return either true (in which case AnyEvent::HTTP will continue),
		285	or false, in which case AnyEvent::HTTP will cancel the download (and call
		286	the completion callback with an error code of C<598>).
		287
		288	The downside to cancelling the request is that it makes it impossible to
		289	re-use the connection.
		290
		291	This callback is useful when the data is too large to be held in memory
		292	(so the callback writes it to a file) or when only some information should
		293	be extracted, or when the body should be processed incrementally.
		294
		295	It is usually preferred over doing your own body handling via
		296	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		297	only used to create a connection, C<want_body_handle> is the better
		298	alternative, as it allows you to install your own event handler, reducing
		299	resource usage.
		300
		301	=item want_body_handle => $enable
		302
		303	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		304	changes considerably: after parsing the headers, and instead of
		305	downloading the body (if any), the completion callback will be
		306	called. Instead of the C<$body> argument containing the body data, the
		307	callback will receive the L<AnyEvent::Handle> object associated with the
		308	connection. In error cases, C<undef> will be passed. When there is no body
		309	(e.g. status C<304>), the empty string will be passed.
		310
		311	The handle object might or might not be in TLS mode, might be connected to
		312	a proxy, be a persistent connection etc., and configured in unspecified
		313	ways. The user is responsible for this handle (it will not be used by this
		314	module anymore).
		315
		316	This is useful with some push-type services, where, after the initial
		317	headers, an interactive protocol is used (typical example would be the
		318	push-style twitter API which starts a JSON/XML stream).
		319
		320	If you think you need this, first have a look at C<on_body>, to see if
		321	that doesn't solve your problem in a better way.
177		322
178	=back	323	=back
179		324
180	Example: make a simple HTTP GET request for http://www.nethype.de/	325	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		326	the response body.
181		327
182	http_request GET => "http://www.nethype.de/", sub {	328	http_request GET => "http://www.nethype.de/", sub {
183	my ($body, $hdr) = @_;	329	my ($body, $hdr) = @_;
184	print "$body\n";	330	print "$body\n";
185	};	331	};
186		332
187	Example: make a HTTP HEAD request on https://www.google.com/, use a	333	Example: do a HTTP HEAD request on https://www.google.com/, use a
188	timeout of 30 seconds.	334	timeout of 30 seconds.
189		335
190	http_request	336	http_request
191	GET => "https://www.google.com",	337	GET => "https://www.google.com",
		338	headers => { "user-agent" => "MySearchClient 1.0" },
192	timeout => 30,	339	timeout => 30,
193	sub {	340	sub {
194	my ($body, $hdr) = @_;	341	my ($body, $hdr) = @_;
195	use Data::Dumper;	342	use Data::Dumper;
196	print Dumper $hdr;	343	print Dumper $hdr;
197	}	344	}
198	;	345	;
199		346
200	Example: make another simple HTTP GET request, but immediately try to	347	Example: do another simple HTTP GET request, but immediately try to
201	cancel it.	348	cancel it.
202		349
203	my $request = http_request GET => "http://www.nethype.de/", sub {	350	my $request = http_request GET => "http://www.nethype.de/", sub {
204	my ($body, $hdr) = @_;	351	my ($body, $hdr) = @_;
205	print "$body\n";	352	print "$body\n";
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	384	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		385
239	_slot_schedule $_[0];	386	_slot_schedule $_[0];
240	}	387	}
241		388
		389	#############################################################################
		390
		391	# expire cookies
		392	sub cookie_jar_expire($;$) {
		393	my ($jar, $session_end) = @_;
		394
		395	%$jar = () if $jar->{version} != 1;
		396
		397	my $anow = AE::now;
		398
		399	while (my ($chost, $paths) = each %$jar) {
		400	next unless ref $paths;
		401
		402	while (my ($cpath, $cookies) = each %$paths) {
		403	while (my ($cookie, $kv) = each %$cookies) {
		404	if (exists $kv->{_expires}) {
		405	delete $cookies->{$cookie}
		406	if $anow > $kv->{_expires};
		407	} elsif ($session_end) {
		408	delete $cookies->{$cookie};
		409	}
		410	}
		411
		412	delete $paths->{$cpath}
		413	unless %$cookies;
		414	}
		415
		416	delete $jar->{$chost}
		417	unless %$paths;
		418	}
		419	}
		420
		421	# extract cookies from jar
		422	sub cookie_jar_extract($$$$) {
		423	my ($jar, $uscheme, $uhost, $upath) = @_;
		424
		425	%$jar = () if $jar->{version} != 1;
		426
		427	my @cookies;
		428
		429	while (my ($chost, $paths) = each %$jar) {
		430	next unless ref $paths;
		431
		432	if ($chost =~ /^\./) {
		433	next unless $chost eq substr $uhost, -length $chost;
		434	} elsif ($chost =~ /\./) {
		435	next unless $chost eq $uhost;
		436	} else {
		437	next;
		438	}
		439
		440	while (my ($cpath, $cookies) = each %$paths) {
		441	next unless $cpath eq substr $upath, 0, length $cpath;
		442
		443	while (my ($cookie, $kv) = each %$cookies) {
		444	next if $uscheme ne "https" && exists $kv->{secure};
		445
		446	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		447	delete $cookies->{$cookie};
		448	next;
		449	}
		450
		451	my $value = $kv->{value};
		452
		453	if ($value =~ /[=;,[:space:]]/) {
		454	$value =~ s/([\\"])/\\$1/g;
		455	$value = "\"$value\"";
		456	}
		457
		458	push @cookies, "$cookie=$value";
		459	}
		460	}
		461	}
		462
		463	\@cookies
		464	}
		465
		466	# parse set_cookie header into jar
		467	sub cookie_jar_set_cookie($$$$) {
		468	my ($jar, $set_cookie, $uhost, $date) = @_;
		469
		470	my $anow = int AE::now;
		471	my $snow; # server-now
		472
		473	for ($set_cookie) {
		474	# parse NAME=VALUE
		475	my @kv;
		476
		477	# expires is not http-compliant in the original cookie-spec,
		478	# we support the official date format and some extensions
		479	while (
		480	m{
		481	\G\s*
		482	(?:
		483	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
		484	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )?
		485	)
		486	}gcxsi
		487	) {
		488	my $name = $2;
		489	my $value = $4;
		490
		491	if (defined $1) {
		492	# expires
		493	$name = "expires";
		494	$value = $1;
		495	} elsif (defined $3) {
		496	# quoted
		497	$value = $3;
		498	$value =~ s/\\(.)/$1/gs;
		499	}
		500
		501	push @kv, lc $name, $value;
		502
		503	last unless /\G\s*;/gc;
		504	}
		505
		506	last unless @kv;
		507
		508	my $name = shift @kv;
		509	my %kv = (value => shift @kv, @kv);
		510
		511	if (exists $kv{"max-age"}) {
		512	$kv{_expires} = $anow + delete $kv{"max-age"};
		513	} elsif (exists $kv{expires}) {
		514	$snow ||= parse_date ($date) || $anow;
		515	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		516	} else {
		517	delete $kv{_expires};
		518	}
		519
		520	my $cdom;
		521	my $cpath = (delete $kv{path}) || "/";
		522
		523	if (exists $kv{domain}) {
		524	$cdom = delete $kv{domain};
		525
		526	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		527
		528	next if $cdom =~ /\.$/;
		529
		530	# this is not rfc-like and not netscape-like. go figure.
		531	my $ndots = $cdom =~ y/.//;
		532	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		533	} else {
		534	$cdom = $uhost;
		535	}
		536
		537	# store it
		538	$jar->{version} = 1;
		539	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		540
		541	redo if /\G\s*,/gc;
		542	}
		543	}
		544
		545	# continue to parse $_ for headers and place them into the arg
		546	sub parse_hdr() {
		547	my %hdr;
		548
		549	# things seen, not parsed:
		550	# p3pP="NON CUR OTPi OUR NOR UNI"
		551
		552	$hdr{lc $1} .= ",$2"
		553	while /\G
		554	([^:\000-\037]*):
		555	[\011\040]*
		556	((?: [^\012]+ | \012[\011\040] )*)
		557	\012
		558	/gxc;
		559
		560	/\G$/
		561	or return;
		562
		563	# remove the "," prefix we added to all headers above
		564	substr $_, 0, 1, ""
		565	for values %hdr;
		566
		567	\%hdr
		568	}
		569
		570	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		571
		572	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		573	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		574
242	sub http_request($$@) {	575	sub http_request($$@) {
243	my $cb = pop;	576	my $cb = pop;
244	my ($method, $url, %arg) = @_;	577	my ($method, $url, %arg) = @_;
245		578
246	my %hdr;	579	my %hdr;
		580
		581	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx};
		582	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
247		583
248	$method = uc $method;	584	$method = uc $method;
249		585
250	if (my $hdr = $arg{headers}) {	586	if (my $hdr = $arg{headers}) {
251	while (my ($k, $v) = each %$hdr) {	587	while (my ($k, $v) = each %$hdr) {
252	$hdr{lc $k} = $v;	588	$hdr{lc $k} = $v;
253	}	589	}
254	}	590	}
255		591
		592	# pseudo headers for all subsequent responses
		593	my @pseudo = (URL => $url);
		594	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		595
256	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	596	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
257		597
258	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	598	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
259	if $recurse < 0;	599	if $recurse < 0;
260		600
261	my $proxy = $arg{proxy} || $PROXY;	601	my $proxy = $arg{proxy} || $PROXY;
262	my $timeout = $arg{timeout} || $TIMEOUT;	602	my $timeout = $arg{timeout} || $TIMEOUT;
263		603
264	$hdr{"user-agent"} ||= $USERAGENT;
265
266	my ($uscheme, $uauthority, $upath, $query, $fragment) =	604	my ($uscheme, $uauthority, $upath, $query, $fragment) =
267	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|;	605	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;
268		606
269	$uscheme = lc $uscheme;	607	$uscheme = lc $uscheme;
270		608
271	my $uport = $uscheme eq "http" ? 80	609	my $uport = $uscheme eq "http" ? 80
272	: $uscheme eq "https" ? 443	610	: $uscheme eq "https" ? 443
273	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	611	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
274
275	$hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
276		612
277	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	613	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
278	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	614	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
279		615
280	my $uhost = $1;	616	my $uhost = lc $1;
281	$uport = $2 if defined $2;	617	$uport = $2 if defined $2;
282		618
		619	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		620	unless exists $hdr{host};
		621
283	$uhost =~ s/^\[(.*)\]$/$1/;	622	$uhost =~ s/^\[(.*)\]$/$1/;
284	$upath .= "?$query" if length $query;	623	$upath .= $query if length $query;
285		624
286	$upath =~ s%^/?%/%;	625	$upath =~ s%^/?%/%;
287		626
288	# cookie processing	627	# cookie processing
289	if (my $jar = $arg{cookie_jar}) {	628	if (my $jar = $arg{cookie_jar}) {
290	%$jar = () if $jar->{version} != 1;	629	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
291		630
292	my @cookie;
293
294	while (my ($chost, $v) = each %$jar) {
295	if ($chost =~ /^\./) {
296	next unless $chost eq substr $uhost, -length $chost;
297	} elsif ($chost =~ /\./) {
298	next unless $chost eq $uhost;
299	} else {
300	next;
301	}
302
303	while (my ($cpath, $v) = each %$v) {
304	next unless $cpath eq substr $upath, 0, length $cpath;
305
306	while (my ($k, $v) = each %$v) {
307	next if $uscheme ne "https" && exists $v->{secure};
308	my $value = $v->{value};
309	$value =~ s/([\\"])/\\$1/g;
310	push @cookie, "$k=\"$value\"";
311	}
312	}
313	}
314
315	$hdr{cookie} = join "; ", @cookie	631	$hdr{cookie} = join "; ", @$cookies
316	if @cookie;	632	if @$cookies;
317	}	633	}
318		634
319	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	635	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
320		636
321	if ($proxy) {	637	if ($proxy) {
322	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	638	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		639
		640	$rscheme = "http" unless defined $rscheme;
323		641
324	# don't support https requests over https-proxy transport,	642	# don't support https requests over https-proxy transport,
325	# can't be done with tls as spec'ed.	643	# can't be done with tls as spec'ed, unless you double-encrypt.
326	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	644	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		645
		646	$rhost = lc $rhost;
		647	$rscheme = lc $rscheme;
327	} else {	648	} else {
328	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	649	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
329	}	650	}
330		651
331	$hdr{host} = $uhost;	652	# leave out fragment and query string, just a heuristic
		653	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		654	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		655
332	$hdr{"content-length"} = length $arg{body};	656	$hdr{"content-length"} = length $arg{body}
		657	if length $arg{body} || $method ne "GET";
		658
		659	my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/;
		660
		661	# default value for keepalive is true iff the request is for an idempotent method
		662	my $keepalive = exists $arg{keepalive}
		663	? $arg{keepalive}*1
		664	: $idempotent ? $PERSISTENT_TIMEOUT : 0;
		665
		666	$hdr{connection} = ($keepalive ? "" : "close ") . "Te"; #1.1
		667	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
333		668
334	my %state = (connect_guard => 1);	669	my %state = (connect_guard => 1);
		670
		671	my $ae_error = 595; # connecting
		672
		673	# handle actual, non-tunneled, request
		674	my $handle_actual_request = sub {
		675	$ae_error = 596; # request phase
		676
		677	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		678
		679	# send request
		680	$state{handle}->push_write (
		681	"$method $rpath HTTP/1.1\015\012"
		682	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		683	. "\015\012"
		684	. (delete $arg{body})
		685	);
		686
		687	# return if error occured during push_write()
		688	return unless %state;
		689
		690	# reduce memory usage, save a kitten, also re-use it for the response headers.
		691	%hdr = ();
		692
		693	# status line and headers
		694	$state{read_response} = sub {
		695	for ("$_[1]") {
		696	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		697
		698	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
		699	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		700
		701	# 100 Continue handling
		702	# should not happen as we don't send expect: 100-continue,
		703	# but we handle it just in case.
		704	# since we send the request body regardless, if we get an error
		705	# we are out of-sync, which we currently do NOT handle correctly.
		706	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		707	if $2 eq 100;
		708
		709	push @pseudo,
		710	HTTPVersion => $1,
		711	Status => $2,
		712	Reason => $3,
		713	;
		714
		715	my $hdr = parse_hdr
		716	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		717
		718	%hdr = (%$hdr, @pseudo);
		719	}
		720
		721	# redirect handling
		722	# microsoft and other shitheads don't give a shit for following standards,
		723	# try to support some common forms of broken Location headers.
		724	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
		725	$hdr{location} =~ s/^\.\/+//;
		726
		727	my $url = "$rscheme://$uhost:$uport";
		728
		729	unless ($hdr{location} =~ s/^\///) {
		730	$url .= $upath;
		731	$url =~ s/\/[^\/]*$//;
		732	}
		733
		734	$hdr{location} = "$url/$hdr{location}";
		735	}
		736
		737	my $redirect;
		738
		739	if ($recurse) {
		740	my $status = $hdr{Status};
		741
		742	# industry standard is to redirect POST as GET for
		743	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		744	# also, the UA should ask the user for 301 and 307 and POST,
		745	# industry standard seems to be to simply follow.
		746	# we go with the industry standard.
		747	if ($status == 301 or $status == 302 or $status == 303) {
		748	# HTTP/1.1 is unclear on how to mutate the method
		749	$method = "GET" unless $method eq "HEAD";
		750	$redirect = 1;
		751	} elsif ($status == 307) {
		752	$redirect = 1;
		753	}
		754	}
		755
		756	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		757	my $may_keep_alive = $_[3];
		758
		759	$state{handle}->destroy if $state{handle};
		760	%state = ();
		761
		762	if (defined $_[1]) {
		763	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		764	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		765	}
		766
		767	# set-cookie processing
		768	if ($arg{cookie_jar}) {
		769	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		770	}
		771
		772	if ($redirect && exists $hdr{location}) {
		773	# we ignore any errors, as it is very common to receive
		774	# Content-Length != 0 but no actual body
		775	# we also access %hdr, as $_[1] might be an erro
		776	http_request (
		777	$method => $hdr{location},
		778	%arg,
		779	recurse => $recurse - 1,
		780	Redirect => [$_[0], \%hdr],
		781	$cb);
		782	} else {
		783	$cb->($_[0], \%hdr);
		784	}
		785	};
		786
		787	$ae_error = 597; # body phase
		788
		789	my $len = $hdr{"content-length"};
		790
		791	# body handling, many different code paths
		792	# - no body expected
		793	# - want_body_handle
		794	# - te chunked
		795	# - 2x length known (with or without on_body)
		796	# - 2x length not known (with or without on_body)
		797	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		798	$finish->(undef, 598 => "Request cancelled by on_header");
		799	} elsif (
		800	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		801	or $method eq "HEAD"
		802	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		803	) {
		804	# no body
		805	$finish->("", undef, undef, 1);
		806
		807	} elsif (!$redirect && $arg{want_body_handle}) {
		808	$_[0]->on_eof (undef);
		809	$_[0]->on_error (undef);
		810	$_[0]->on_read (undef);
		811
		812	$finish->(delete $state{handle});
		813
		814	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		815	my $cl = 0;
		816	my $body = undef;
		817	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
		818
		819	$state{read_chunk} = sub {
		820	$_[1] =~ /^([0-9a-fA-F]+)/
		821	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		822
		823	my $len = hex $1;
		824
		825	if ($len) {
		826	$cl += $len;
		827
		828	$_[0]->push_read (chunk => $len, sub {
		829	$on_body->($_[1], \%hdr)
		830	or return $finish->(undef, 598 => "Request cancelled by on_body");
		831
		832	$_[0]->push_read (line => sub {
		833	length $_[1]
		834	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		835	$_[0]->push_read (line => $state{read_chunk});
		836	});
		837	});
		838	} else {
		839	$hdr{"content-length"} ||= $cl;
		840
		841	$_[0]->push_read (line => $qr_nlnl, sub {
		842	if (length $_[1]) {
		843	for ("$_[1]") {
		844	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		845
		846	my $hdr = parse_hdr
		847	or return $finish->(undef, $ae_error => "Garbled response trailers");
		848
		849	%hdr = (%hdr, %$hdr);
		850	}
		851	}
		852
		853	$finish->($body, undef, undef, 1);
		854	});
		855	}
		856	};
		857
		858	$_[0]->push_read (line => $state{read_chunk});
		859
		860	} elsif ($arg{on_body}) {
		861	if (defined $len) {
		862	$_[0]->on_read (sub {
		863	$len -= length $_[0]{rbuf};
		864
		865	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		866	or return $finish->(undef, 598 => "Request cancelled by on_body");
		867
		868	$len > 0
		869	or $finish->("", undef, undef, 1);
		870	});
		871	} else {
		872	$_[0]->on_eof (sub {
		873	$finish->("");
		874	});
		875	$_[0]->on_read (sub {
		876	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		877	or $finish->(undef, 598 => "Request cancelled by on_body");
		878	});
		879	}
		880	} else {
		881	$_[0]->on_eof (undef);
		882
		883	if (defined $len) {
		884	$_[0]->on_read (sub {
		885	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		886	if $len <= length $_[0]{rbuf};
		887	});
		888	} else {
		889	$_[0]->on_error (sub {
		890	($! == Errno::EPIPE || !$!)
		891	? $finish->(delete $_[0]{rbuf})
		892	: $finish->(undef, $ae_error => $_[2]);
		893	});
		894	$_[0]->on_read (sub { });
		895	}
		896	}
		897	};
		898
		899	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
		900	};
		901
		902	my $connect_cb = sub {
		903	$state{fh} = shift
		904	or do {
		905	my $err = "$!";
		906	%state = ();
		907	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
		908	};
		909
		910	return unless delete $state{connect_guard};
		911
		912	# get handle
		913	$state{handle} = new AnyEvent::Handle
		914	fh => $state{fh},
		915	peername => $rhost,
		916	tls_ctx => $arg{tls_ctx},
		917	# these need to be reconfigured on keepalive handles
		918	timeout => $timeout,
		919	on_error => sub {
		920	%state = ();
		921	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
		922	},
		923	on_eof => sub {
		924	%state = ();
		925	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
		926	},
		927	;
		928
		929	# limit the number of persistent connections
		930	# keepalive not yet supported
		931	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		932	# ++$KA_COUNT{$_[1]};
		933	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		934	# --$KA_COUNT{$_[1]}
		935	# };
		936	# $hdr{connection} = "keep-alive";
		937	# }
		938
		939	$state{handle}->starttls ("connect") if $rscheme eq "https";
		940
		941	# now handle proxy-CONNECT method
		942	if ($proxy && $uscheme eq "https") {
		943	# oh dear, we have to wrap it into a connect request
		944
		945	# maybe re-use $uauthority with patched port?
		946	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
		947	$state{handle}->push_read (line => $qr_nlnl, sub {
		948	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		949	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		950
		951	if ($2 == 200) {
		952	$rpath = $upath;
		953	$handle_actual_request->();
		954	} else {
		955	%state = ();
		956	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
		957	}
		958	});
		959	} else {
		960	$handle_actual_request->();
		961	}
		962	};
335		963
336	_get_slot $uhost, sub {	964	_get_slot $uhost, sub {
337	$state{slot_guard} = shift;	965	$state{slot_guard} = shift;
338		966
339	return unless $state{connect_guard};	967	return unless $state{connect_guard};
340		968
341	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	969	my $tcp_connect = $arg{tcp_connect}
342	$state{fh} = shift	970	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
343	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
344		971
345	delete $state{connect_guard}; # reduce memory usage, save a tree	972	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
346
347	# get handle
348	$state{handle} = new AnyEvent::Handle
349	fh => $state{fh};
350
351	# limit the number of persistent connections
352	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
353	++$KA_COUNT{$_[1]};
354	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
355	$hdr{connection} = "keep-alive";
356	delete $hdr{connection}; # keep-alive not yet supported
357	} else {
358	delete $hdr{connection};
359	}
360
361	# (re-)configure handle
362	$state{handle}->timeout ($timeout);
363	$state{handle}->on_error (sub {
364	my $errno = "$!";
365	%state = ();
366	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
367	});
368	$state{handle}->on_eof (sub {
369	%state = ();
370	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
371	});
372
373	$state{handle}->starttls ("connect") if $rscheme eq "https";
374
375	# handle actual, non-tunneled, request
376	my $handle_actual_request = sub {
377	$state{handle}->starttls ("connect") if $uscheme eq "https";
378
379	# send request
380	$state{handle}->push_write (
381	"$method $rpath HTTP/1.0\015\012"
382	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)
383	. "\015\012"
384	. (delete $arg{body})
385	);
386
387	%hdr = (); # reduce memory usage, save a kitten
388
389	# status line
390	$state{handle}->push_read (line => qr/\015?\012/, sub {
391	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
392	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
393
394	my %hdr = ( # response headers
395	HTTPVersion => ",$1",
396	Status => ",$2",
397	Reason => ",$3",
398	URL => ",$url"
399	);
400
401	# headers, could be optimized a bit
402	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
403	for ("$_[1]\012") {
404	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
405
406	# we support spaces in field names, as lotus domino
407	# creates them (actually spaces around seperators
408	# are strictly allowed in http, they are a security issue).
409	$hdr{lc $1} .= ",$2"
410	while /\G
411	([^:\000-\037]+):
412	[\011\040]*
413	((?: [^\012]+ | \012[\011\040] )*)
414	\012
415	/gxc;
416
417	/\G$/
418	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
419	}
420
421	substr $_, 0, 1, ""
422	for values %hdr;
423
424	my $finish = sub {
425	# TODO: use destroy method, when/if available
426	#$state{handle}->destroy;
427	$state{handle}->on_eof (undef);
428	$state{handle}->on_error (undef);
429	%state = ();
430
431	# set-cookie processing
432	if ($arg{cookie_jar}) {
433	for ($hdr{"set-cookie"}) {
434	# parse NAME=VALUE
435	my @kv;
436
437	while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
438	my $name = $1;
439	my $value = $3;
440
441	unless ($value) {
442	$value = $2;
443	$value =~ s/\\(.)/$1/gs;
444	}
445
446	push @kv, $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	my $cdom;
457	my $cpath = (delete $kv{path}) || "/";
458
459	if (exists $kv{domain}) {
460	$cdom = delete $kv{domain};
461
462	$cdom =~ s/^\.?/./; # make sure it starts with a "."
463
464	next if $cdom =~ /\.$/;
465
466	# this is not rfc-like and not netscape-like. go figure.
467	my $ndots = $cdom =~ y/.//;
468	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
469	} else {
470	$cdom = $uhost;
471	}
472
473	# store it
474	$arg{cookie_jar}{version} = 1;
475	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
476
477	redo if /\G\s*,/gc;
478	}
479	}
480
481	# microsoft and other shitheads don't give a shit for following standards,
482	# try to support some common forms of broken Location headers.
483	if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
484	$_[1]{location} =~ s/^\.\/+//;
485
486	my $url = "$rscheme://$uhost:$uport";
487
488	unless ($_[1]{location} =~ s/^\///) {
489	$url .= $upath;
490	$url =~ s/\/[^\/]*$//;
491	}
492
493	$_[1]{location} = "$url/$_[1]{location}";
494	}
495
496	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
497	# apparently, mozilla et al. just change POST to GET here
498	# more research is needed before we do the same
499	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
500	} elsif ($_[1]{Status} == 303 && $recurse) {
501	# even http/1.1 is unclear on how to mutate the method
502	$method = "GET" unless $method eq "HEAD";
503	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
504	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) {
505	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
506	} else {
507	$cb->($_[0], $_[1]);
508	}
509	};
510
511	if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") {
512	$finish->(undef, \%hdr);
513	} else {
514	if (exists $hdr{"content-length"}) {
515	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
516	# could cache persistent connection now
517	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
518	# but we don't, due to misdesigns, this is annoyingly complex
519	};
520
521	$finish->($_[1], \%hdr);
522	});
523	} else {
524	# too bad, need to read until we get an error or EOF,
525	# no way to detect winged data.
526	$_[0]->on_error (sub {
527	$finish->($_[0]{rbuf}, \%hdr);
528	});
529	$_[0]->on_eof (undef);
530	$_[0]->on_read (sub { });
531	}
532	}
533	});
534	});
535	};
536
537	# now handle proxy-CONNECT method
538	if ($proxy && $uscheme eq "https") {
539	# oh dear, we have to wrap it into a connect request
540
541	# maybe re-use $uauthority with patched port?
542	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
543	$state{handle}->push_read (line => qr/\015?\012\015?\012/, sub {
544	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
545	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));
546
547	if ($2 == 200) {
548	$rpath = $upath;
549	&$handle_actual_request;
550	} else {
551	%state = ();
552	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
553	}
554	});
555	} else {
556	&$handle_actual_request;
557	}
558
559	}, sub {
560	$timeout
561	};
562	};	973	};
563		974
564	defined wantarray && AnyEvent::Util::guard { %state = () }	975	defined wantarray && AnyEvent::Util::guard { %state = () }
565	}	976	}
566		977
…		…
580	&http_request	991	&http_request
581	}	992	}
582		993
583	=back	994	=back
584		995
		996	=head2 DNS CACHING
		997
		998	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		999	the actual connection, which in turn uses AnyEvent::DNS to resolve
		1000	hostnames. The latter is a simple stub resolver and does no caching
		1001	on its own. If you want DNS caching, you currently have to provide
		1002	your own default resolver (by storing a suitable resolver object in
		1003	C<$AnyEvent::DNS::RESOLVER>).
		1004
585	=head2 GLOBAL FUNCTIONS AND VARIABLES	1005	=head2 GLOBAL FUNCTIONS AND VARIABLES
586		1006
587	=over 4	1007	=over 4
588		1008
589	=item AnyEvent::HTTP::set_proxy "proxy-url"	1009	=item AnyEvent::HTTP::set_proxy "proxy-url"
590		1010
591	Sets the default proxy server to use. The proxy-url must begin with a	1011	Sets the default proxy server to use. The proxy-url must begin with a
592	string of the form C<http://host:port> (optionally C<https:...>).	1012	string of the form C<http://host:port> (optionally C<https:...>), croaks
		1013	otherwise.
		1014
		1015	To clear an already-set proxy, use C<undef>.
		1016
		1017	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1018
		1019	Remove all cookies from the cookie jar that have been expired. If
		1020	C<$session_end> is given and true, then additionally remove all session
		1021	cookies.
		1022
		1023	You should call this function (with a true C<$session_end>) before you
		1024	save cookies to disk, and you should call this function after loading them
		1025	again. If you have a long-running program you can additonally call this
		1026	function from time to time.
		1027
		1028	A cookie jar is initially an empty hash-reference that is managed by this
		1029	module. It's format is subject to change, but currently it is like this:
		1030
		1031	The key C<version> has to contain C<1>, otherwise the hash gets
		1032	emptied. All other keys are hostnames or IP addresses pointing to
		1033	hash-references. The key for these inner hash references is the
		1034	server path for which this cookie is meant, and the values are again
		1035	hash-references. The keys of those hash-references is the cookie name, and
		1036	the value, you guessed it, is another hash-reference, this time with the
		1037	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1038	which have been replaced by a C<_expires> key that contains the cookie
		1039	expiry timestamp.
		1040
		1041	Here is an example of a cookie jar with a single cookie, so you have a
		1042	chance of understanding the above paragraph:
		1043
		1044	{
		1045	version => 1,
		1046	"10.0.0.1" => {
		1047	"/" => {
		1048	"mythweb_id" => {
		1049	_expires => 1293917923,
		1050	value => "ooRung9dThee3ooyXooM1Ohm",
		1051	},
		1052	},
		1053	},
		1054	}
		1055
		1056	=item $date = AnyEvent::HTTP::format_date $timestamp
		1057
		1058	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1059	Date (RFC 2616).
		1060
		1061	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1062
		1063	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1064	bunch of minor variations of those, and returns the corresponding POSIX
		1065	timestamp, or C<undef> if the date cannot be parsed.
593		1066
594	=item $AnyEvent::HTTP::MAX_RECURSE	1067	=item $AnyEvent::HTTP::MAX_RECURSE
595		1068
596	The default value for the C<recurse> request parameter (default: C<10>).	1069	The default value for the C<recurse> request parameter (default: C<10>).
597		1070
598	=item $AnyEvent::HTTP::USERAGENT	1071	=item $AnyEvent::HTTP::USERAGENT
599		1072
600	The default value for the C<User-Agent> header (the default is	1073	The default value for the C<User-Agent> header (the default is
601	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1074	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
602		1075
603	=item $AnyEvent::HTTP::MAX_PERSISTENT	1076	=item $AnyEvent::HTTP::MAX_PER_HOST
604		1077
605	The maximum number of persistent connections to keep open (default: 8).	1078	The maximum number of concurrent connections to the same host (identified
		1079	by the hostname). If the limit is exceeded, then the additional requests
		1080	are queued until previous connections are closed.
606		1081
607	Not implemented currently.	1082	The default value for this is C<4>, and it is highly advisable to not
608		1083	increase it.
609	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
610
611	The maximum time to cache a persistent connection, in seconds (default: 2).
612
613	Not implemented currently.
614		1084
615	=item $AnyEvent::HTTP::ACTIVE	1085	=item $AnyEvent::HTTP::ACTIVE
616		1086
617	The number of active connections. This is not the number of currently	1087	The number of active connections. This is not the number of currently
618	running requests, but the number of currently open and non-idle TCP	1088	running requests, but the number of currently open and non-idle TCP
…		…
620		1090
621	=back	1091	=back
622		1092
623	=cut	1093	=cut
624		1094
		1095	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1096	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1097
		1098	sub format_date($) {
		1099	my ($time) = @_;
		1100
		1101	# RFC 822/1123 format
		1102	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1103
		1104	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1105	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1106	$H, $M, $S;
		1107	}
		1108
		1109	sub parse_date($) {
		1110	my ($date) = @_;
		1111
		1112	my ($d, $m, $y, $H, $M, $S);
		1113
		1114	if ($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$/) {
		1115	# RFC 822/1123, required by RFC 2616 (with " ")
		1116	# cookie dates (with "-")
		1117
		1118	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1119
		1120	} elsif ($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$/) {
		1121	# RFC 850
		1122	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1123
		1124	} elsif ($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])$/) {
		1125	# ISO C's asctime
		1126	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1127	}
		1128	# other formats fail in the loop below
		1129
		1130	for (0..11) {
		1131	if ($m eq $month[$_]) {
		1132	require Time::Local;
		1133	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1134	}
		1135	}
		1136
		1137	undef
		1138	}
		1139
625	sub set_proxy($) {	1140	sub set_proxy($) {
		1141	if (length $_[0]) {
626	$PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1142	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1143	or Carp::croak "$_[0]: invalid proxy URL";
		1144	$PROXY = [$2, $3 || 3128, $1]
		1145	} else {
		1146	undef $PROXY;
		1147	}
627	}	1148	}
628		1149
629	# initialise proxy from environment	1150	# initialise proxy from environment
		1151	eval {
630	set_proxy $ENV{http_proxy};	1152	set_proxy $ENV{http_proxy};
		1153	};
		1154
		1155	=head2 SOCKS PROXIES
		1156
		1157	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1158	compile your perl to support socks, or use an external program such as
		1159	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1160	transparently.
		1161
		1162	Alternatively, for AnyEvent::HTTP only, you can use your own
		1163	C<tcp_connect> function that does the proxy handshake - here is an example
		1164	that works with socks4a proxies:
		1165
		1166	use Errno;
		1167	use AnyEvent::Util;
		1168	use AnyEvent::Socket;
		1169	use AnyEvent::Handle;
		1170
		1171	# host, port and username of/for your socks4a proxy
		1172	my $socks_host = "10.0.0.23";
		1173	my $socks_port = 9050;
		1174	my $socks_user = "";
		1175
		1176	sub socks4a_connect {
		1177	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1178
		1179	my $hdl = new AnyEvent::Handle
		1180	connect => [$socks_host, $socks_port],
		1181	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1182	on_error => sub { $connect_cb->() },
		1183	;
		1184
		1185	$hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host);
		1186
		1187	$hdl->push_read (chunk => 8, sub {
		1188	my ($hdl, $chunk) = @_;
		1189	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1190
		1191	if ($status == 0x5a) {
		1192	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1193	} else {
		1194	$! = Errno::ENXIO; $connect_cb->();
		1195	}
		1196	});
		1197
		1198	$hdl
		1199	}
		1200
		1201	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1202	possibly after switching off other proxy types:
		1203
		1204	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1205
		1206	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1207	my ($data, $headers) = @_;
		1208	...
		1209	};
631		1210
632	=head1 SEE ALSO	1211	=head1 SEE ALSO
633		1212
634	L<AnyEvent>.	1213	L<AnyEvent>.
635		1214
636	=head1 AUTHOR	1215	=head1 AUTHOR
637		1216
638	Marc Lehmann <schmorp@schmorp.de>	1217	Marc Lehmann <schmorp@schmorp.de>
639	http://home.schmorp.de/	1218	http://home.schmorp.de/
640		1219
		1220	With many thanks to Дмитрий Шалашов, who provided countless
		1221	testcases and bugreports.
		1222
641	=cut	1223	=cut
642		1224
643	1	1225	1
644		1226

Diff Legend

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