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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.27 by root, Thu Jul 24 06:01:10 2008 UTC vs.
Revision 1.79 by root, Sat Jan 1 20:01:07 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 = '1.04';	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, $headers)
84		83
85	Executes an HTTP-POST request with a request body of C<$body>. 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 "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
99	contain the three parts of the HTTP Status-Line of the same name. 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
100	pseudo-header C<URL> contains the original URL (which can differ from the	110	The pseudo-header C<URL> contains the actual URL (which can differ from
101	requested URL when following redirects).	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).
102		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	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
103	If the server sends a header multiple lines, then their contents will be	123	If the server sends a header multiple times, then their contents will be
104	joined together with C<\x00>.	124	joined together with a comma (C<,>), as per the HTTP spec.
105		125
106	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
107	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
108	and the C<Reason> pseudo-header will contain an error message.	128	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
		129	message. Currently the following status codes are used:
		130
		131	=over 4
		132
		133	=item 595 - errors during connection etsbalishment, proxy handshake.
		134
		135	=item 596 - errors during TLS negotiation, request sending and header processing.
		136
		137	=item 597 - errors during body receiving or processing.
		138
		139	=item 598 - user aborted request via C<on_header> or C<on_body>.
		140
		141	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		142
		143	=back
109		144
110	A typical callback might look like this:	145	A typical callback might look like this:
111		146
112	sub {	147	sub {
113	my ($body, $hdr) = @_;	148	my ($body, $hdr) = @_;
…		…
129	Whether to recurse requests or not, e.g. on redirects, authentication	164	Whether to recurse requests or not, e.g. on redirects, authentication
130	retries and so on, and how often to do so.	165	retries and so on, and how often to do so.
131		166
132	=item headers => hashref	167	=item headers => hashref
133		168
134	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
135	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
136	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).
137		174
138	=item timeout => $seconds	175	=item timeout => $seconds
139		176
140	The time-out to use for various stages - each connect attempt will reset	177	The time-out to use for various stages - each connect attempt will reset
141	the timeout, as will read or write activity. Default timeout is 5 minutes.	178	the timeout, as will read or write activity, i.e. this is not an overall
		179	timeout.
		180
		181	Default timeout is 5 minutes.
142		182
143	=item proxy => [$host, $port[, $scheme]] or undef	183	=item proxy => [$host, $port[, $scheme]] or undef
144		184
145	Use the given http proxy for all requests. If not specified, then the	185	Use the given http proxy for all requests. If not specified, then the
146	default proxy (as specified by C<$ENV{http_proxy}>) is used.	186	default proxy (as specified by C<$ENV{http_proxy}>) is used.
147		187
148	C<$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
149	HTTPS.	189	HTTPS.
150		190
151	=item body => $string	191	=item body => $string
152		192
153	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
154	this module might offer more options).	194	this module might offer more options).
155		195
156	=item cookie_jar => $hash_ref	196	=item cookie_jar => $hash_ref
157		197
158	Passing this parameter enables (simplified) cookie-processing, loosely	198	Passing this parameter enables (simplified) cookie-processing, loosely
159	based on the original netscape specification.	199	based on the original netscape specification.
160		200
161	The C<$hash_ref> must be an (initially empty) hash reference which will	201	The C<$hash_ref> must be an (initially empty) hash reference which will
162	get updated automatically. It is possible to save the cookie_jar to	202	get updated automatically. It is possible to save the cookie jar to
163	persistent storage with something like JSON or Storable, but this is not	203	persistent storage with something like JSON or Storable, but this is not
164	recommended, as expire times are currently being ignored.	204	recommended, as session-only cookies might survive longer than expected.
165		205
166	Note that this cookie implementation is not of very high quality, nor	206	Note that this cookie implementation is not meant to be complete. If
167	meant to be complete. If you want complete cookie management you have to	207	you want complete cookie management you have to do that on your
168	do that on your own. C<cookie_jar> is meant as a quick fix to get some	208	own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites
169	cookie-using sites working. Cookies are a privacy disaster, do not use	209	working. Cookies are a privacy disaster, do not use them unless required
170	them unless required to.	210	to.
		211
		212	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		213	headers will be set and handled by this module, otherwise they will be
		214	left untouched.
		215
		216	=item tls_ctx => $scheme \| $tls_ctx
		217
		218	Specifies the AnyEvent::TLS context to be used for https connections. This
		219	parameter follows the same rules as the C<tls_ctx> parameter to
		220	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		221	C<high> can be specified, which give you a predefined low-security (no
		222	verification, highest compatibility) and high-security (CA and common-name
		223	verification) TLS context.
		224
		225	The default for this option is C<low>, which could be interpreted as "give
		226	me the page, no matter what".
		227
		228	=item on_prepare => $callback->($fh)
		229
		230	In rare cases you need to "tune" the socket before it is used to
		231	connect (for exmaple, to bind it on a given IP address). This parameter
		232	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		233	and behaves exactly the same way (e.g. it has to provide a
		234	timeout). See the description for the C<$prepare_cb> argument of
		235	C<AnyEvent::Socket::tcp_connect> for details.
		236
		237	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		238
		239	In even rarer cases you want total control over how AnyEvent::HTTP
		240	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		241	to do this, but you can provide your own C<tcp_connect> function -
		242	obviously, it has to follow the same calling conventions, except that it
		243	may always return a connection guard object.
		244
		245	There are probably lots of weird uses for this function, starting from
		246	tracing the hosts C<http_request> actually tries to connect, to (inexact
		247	but fast) host => IP address caching or even socks protocol support.
		248
		249	=item on_header => $callback->($headers)
		250
		251	When specified, this callback will be called with the header hash as soon
		252	as headers have been successfully received from the remote server (not on
		253	locally-generated errors).
		254
		255	It has to return either true (in which case AnyEvent::HTTP will continue),
		256	or false, in which case AnyEvent::HTTP will cancel the download (and call
		257	the finish callback with an error code of C<598>).
		258
		259	This callback is useful, among other things, to quickly reject unwanted
		260	content, which, if it is supposed to be rare, can be faster than first
		261	doing a C<HEAD> request.
		262
		263	The downside is that cancelling the request makes it impossible to re-use
		264	the connection. Also, the C<on_header> callback will not receive any
		265	trailer (headers sent after the response body).
		266
		267	Example: cancel the request unless the content-type is "text/html".
		268
		269	on_header => sub {
		270	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		271	},
		272
		273	=item on_body => $callback->($partial_body, $headers)
		274
		275	When specified, all body data will be passed to this callback instead of
		276	to the completion callback. The completion callback will get the empty
		277	string instead of the body data.
		278
		279	It has to return either true (in which case AnyEvent::HTTP will continue),
		280	or false, in which case AnyEvent::HTTP will cancel the download (and call
		281	the completion callback with an error code of C<598>).
		282
		283	The downside to cancelling the request is that it makes it impossible to
		284	re-use the connection.
		285
		286	This callback is useful when the data is too large to be held in memory
		287	(so the callback writes it to a file) or when only some information should
		288	be extracted, or when the body should be processed incrementally.
		289
		290	It is usually preferred over doing your own body handling via
		291	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		292	only used to create a connection, C<want_body_handle> is the better
		293	alternative, as it allows you to install your own event handler, reducing
		294	resource usage.
		295
		296	=item want_body_handle => $enable
		297
		298	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		299	changes considerably: after parsing the headers, and instead of
		300	downloading the body (if any), the completion callback will be
		301	called. Instead of the C<$body> argument containing the body data, the
		302	callback will receive the L<AnyEvent::Handle> object associated with the
		303	connection. In error cases, C<undef> will be passed. When there is no body
		304	(e.g. status C<304>), the empty string will be passed.
		305
		306	The handle object might or might not be in TLS mode, might be connected to
		307	a proxy, be a persistent connection etc., and configured in unspecified
		308	ways. The user is responsible for this handle (it will not be used by this
		309	module anymore).
		310
		311	This is useful with some push-type services, where, after the initial
		312	headers, an interactive protocol is used (typical example would be the
		313	push-style twitter API which starts a JSON/XML stream).
		314
		315	If you think you need this, first have a look at C<on_body>, to see if
		316	that doesn't solve your problem in a better way.
171		317
172	=back	318	=back
173		319
174	Example: make a simple HTTP GET request for http://www.nethype.de/	320	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		321	the response body.
175		322
176	http_request GET => "http://www.nethype.de/", sub {	323	http_request GET => "http://www.nethype.de/", sub {
177	my ($body, $hdr) = @_;	324	my ($body, $hdr) = @_;
178	print "$body\n";	325	print "$body\n";
179	};	326	};
180		327
181	Example: make a HTTP HEAD request on https://www.google.com/, use a	328	Example: do a HTTP HEAD request on https://www.google.com/, use a
182	timeout of 30 seconds.	329	timeout of 30 seconds.
183		330
184	http_request	331	http_request
185	GET => "https://www.google.com",	332	GET => "https://www.google.com",
186	timeout => 30,	333	timeout => 30,
…		…
188	my ($body, $hdr) = @_;	335	my ($body, $hdr) = @_;
189	use Data::Dumper;	336	use Data::Dumper;
190	print Dumper $hdr;	337	print Dumper $hdr;
191	}	338	}
192	;	339	;
		340
		341	Example: do another simple HTTP GET request, but immediately try to
		342	cancel it.
		343
		344	my $request = http_request GET => "http://www.nethype.de/", sub {
		345	my ($body, $hdr) = @_;
		346	print "$body\n";
		347	};
		348
		349	undef $request;
193		350
194	=cut	351	=cut
195		352
196	sub _slot_schedule;	353	sub _slot_schedule;
197	sub _slot_schedule($) {	354	sub _slot_schedule($) {
…		…
221	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	378	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
222		379
223	_slot_schedule $_[0];	380	_slot_schedule $_[0];
224	}	381	}
225		382
		383	# extract cookies from jar
		384	sub cookie_jar_extract($$$$) {
		385	my ($jar, $uscheme, $uhost, $upath) = @_;
		386
		387	%$jar = () if $jar->{version} != 1;
		388
		389	my @cookies;
		390
		391	while (my ($chost, $paths) = each %$jar) {
		392	next unless ref $paths;
		393
		394	if ($chost =~ /^\./) {
		395	next unless $chost eq substr $uhost, -length $chost;
		396	} elsif ($chost =~ /\./) {
		397	next unless $chost eq $uhost;
		398	} else {
		399	next;
		400	}
		401
		402	while (my ($cpath, $cookies) = each %$paths) {
		403	next unless $cpath eq substr $upath, 0, length $cpath;
		404
		405	while (my ($cookie, $kv) = each %$cookies) {
		406	next if $uscheme ne "https" && exists $kv->{secure};
		407
		408	if (exists $kv->{expires}) {
		409	if (AE::now > parse_date ($kv->{expires})) {
		410	delete $cookies->{$cookie};
		411	next;
		412	}
		413	}
		414
		415	my $value = $kv->{value};
		416
		417	if ($value =~ /[=;,[:space:]]/) {
		418	$value =~ s/([\\"])/\\$1/g;
		419	$value = "\"$value\"";
		420	}
		421
		422	push @cookies, "$cookie=$value";
		423	}
		424	}
		425	}
		426
		427	\@cookies
		428	}
		429
		430	# parse set_cookie header into jar
		431	sub cookie_jar_set_cookie($$$) {
		432	my ($jar, $set_cookie, $uhost) = @_;
		433
		434	for ($set_cookie) {
		435	# parse NAME=VALUE
		436	my @kv;
		437
		438	# expires is not http-compliant in the original cookie-spec,
		439	# we support the official date format and some extensions
		440	while (
		441	m{
		442	\G\s*
		443	(?:
		444	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
		445	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )
		446	)
		447	}gcxsi
		448	) {
		449	my $name = $2;
		450	my $value = $4;
		451
		452	unless (defined $name) {
		453	# expires
		454	$name = "expires";
		455	$value = $1;
		456	} elsif (!defined $value) {
		457	# quoted
		458	$value = $3;
		459	$value =~ s/\\(.)/$1/gs;
		460	}
		461
		462	push @kv, lc $name, $value;
		463
		464	last unless /\G\s*;/gc;
		465	}
		466
		467	last unless @kv;
		468
		469	my $name = shift @kv;
		470	my %kv = (value => shift @kv, @kv);
		471
		472	$kv{expires} \|\|= format_date (AE::now + $kv{"max-age"})
		473	if exists $kv{"max-age"};
		474
		475	my $cdom;
		476	my $cpath = (delete $kv{path}) \|\| "/";
		477
		478	if (exists $kv{domain}) {
		479	$cdom = delete $kv{domain};
		480
		481	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		482
		483	next if $cdom =~ /\.$/;
		484
		485	# this is not rfc-like and not netscape-like. go figure.
		486	my $ndots = $cdom =~ y/.//;
		487	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		488	} else {
		489	$cdom = $uhost;
		490	}
		491
		492	# store it
		493	$jar->{version} = 1;
		494	$jar->{$cdom}{$cpath}{$name} = \%kv;
		495
		496	redo if /\G\s*,/gc;
		497	}
		498	}
		499
		500	# continue to parse $_ for headers and place them into the arg
		501	sub parse_hdr() {
		502	my %hdr;
		503
		504	# things seen, not parsed:
		505	# p3pP="NON CUR OTPi OUR NOR UNI"
		506
		507	$hdr{lc $1} .= ",$2"
		508	while /\G
		509	([^:\000-\037]*):
		510	[\011\040]*
		511	((?: [^\012]+ \| \012[\011\040] )*)
		512	\012
		513	/gxc;
		514
		515	/\G$/
		516	or return;
		517
		518	# remove the "," prefix we added to all headers above
		519	substr $_, 0, 1, ""
		520	for values %hdr;
		521
		522	\%hdr
		523	}
		524
		525	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		526
		527	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		528	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		529
226	sub http_request($$@) {	530	sub http_request($$@) {
227	my $cb = pop;	531	my $cb = pop;
228	my ($method, $url, %arg) = @_;	532	my ($method, $url, %arg) = @_;
229		533
230	my %hdr;	534	my %hdr;
		535
		536	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		537	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
231		538
232	$method = uc $method;	539	$method = uc $method;
233		540
234	if (my $hdr = $arg{headers}) {	541	if (my $hdr = $arg{headers}) {
235	while (my ($k, $v) = each %$hdr) {	542	while (my ($k, $v) = each %$hdr) {
236	$hdr{lc $k} = $v;	543	$hdr{lc $k} = $v;
237	}	544	}
238	}	545	}
239		546
		547	# pseudo headers for all subsequent responses
		548	my @pseudo = (URL => $url);
		549	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		550
240	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	551	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
241		552
242	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	553	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
243	if $recurse < 0;	554	if $recurse < 0;
244		555
245	my $proxy = $arg{proxy} \|\| $PROXY;	556	my $proxy = $arg{proxy} \|\| $PROXY;
246	my $timeout = $arg{timeout} \|\| $TIMEOUT;	557	my $timeout = $arg{timeout} \|\| $TIMEOUT;
247		558
248	$hdr{"user-agent"} \|\|= $USERAGENT;
249
250	my ($scheme, $authority, $upath, $query, $fragment) =	559	my ($uscheme, $uauthority, $upath, $query, $fragment) =
251	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	560	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
252		561
253	$scheme = lc $scheme;	562	$uscheme = lc $uscheme;
254		563
255	my $uport = $scheme eq "http" ? 80	564	my $uport = $uscheme eq "http" ? 80
256	: $scheme eq "https" ? 443	565	: $uscheme eq "https" ? 443
257	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	566	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
258		567
259	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
260
261	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	568	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
262	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	569	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
263		570
264	my $uhost = $1;	571	my $uhost = $1;
265	$uport = $2 if defined $2;	572	$uport = $2 if defined $2;
266		573
		574	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		575	unless exists $hdr{host};
		576
267	$uhost =~ s/^\[(.*)\]$/$1/;	577	$uhost =~ s/^\[(.*)\]$/$1/;
268	$upath .= "?$query" if length $query;	578	$upath .= $query if length $query;
269		579
270	$upath =~ s%^/?%/%;	580	$upath =~ s%^/?%/%;
271		581
272	# cookie processing	582	# cookie processing
273	if (my $jar = $arg{cookie_jar}) {	583	if (my $jar = $arg{cookie_jar}) {
274	%$jar = () if $jar->{version} < 1;	584	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
275		585
276	my @cookie;
277
278	while (my ($chost, $v) = each %$jar) {
279	next unless $chost eq substr $uhost, -length $chost;
280	next unless $chost =~ /^\./;
281
282	while (my ($cpath, $v) = each %$v) {
283	next unless $cpath eq substr $upath, 0, length $cpath;
284
285	while (my ($k, $v) = each %$v) {
286	next if $scheme ne "https" && exists $v->{secure};
287	push @cookie, "$k=$v->{value}";
288	}
289	}
290	}
291
292	$hdr{cookie} = join "; ", @cookie	586	$hdr{cookie} = join "; ", @$cookies
293	if @cookie;	587	if @$cookies;
294	}	588	}
295		589
296	my ($rhost, $rport, $rpath); # request host, port, path	590	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
297		591
298	if ($proxy) {	592	if ($proxy) {
299	($rhost, $rport, $scheme) = @$proxy;	593	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
300	$rpath = $url;	594
		595	$rscheme = "http" unless defined $rscheme;
		596
		597	# don't support https requests over https-proxy transport,
		598	# can't be done with tls as spec'ed, unless you double-encrypt.
		599	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
301	} else {	600	} else {
302	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	601	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
303	$hdr{host} = $uhost;
304	}	602	}
305		603
		604	# leave out fragment and query string, just a heuristic
		605	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		606	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		607
306	$hdr{"content-length"} = length $arg{body};	608	$hdr{"content-length"} = length $arg{body}
		609	if length $arg{body} \|\| $method ne "GET";
		610
		611	$hdr{connection} = "close TE"; #1.1
		612	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
307		613
308	my %state = (connect_guard => 1);	614	my %state = (connect_guard => 1);
309		615
310	_get_slot $uhost, sub {	616	_get_slot $uhost, sub {
311	$state{slot_guard} = shift;	617	$state{slot_guard} = shift;
312		618
313	return unless $state{connect_guard};	619	return unless $state{connect_guard};
314		620
315	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	621	my $ae_error = 595; # connecting
		622
		623	my $connect_cb = sub {
316	$state{fh} = shift	624	$state{fh} = shift
		625	or do {
		626	my $err = "$!";
		627	%state = ();
317	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	628	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
		629	};
318		630
319	delete $state{connect_guard}; # reduce memory usage, save a tree	631	return unless delete $state{connect_guard};
320		632
321	# get handle	633	# get handle
322	$state{handle} = new AnyEvent::Handle	634	$state{handle} = new AnyEvent::Handle
323	fh => $state{fh},	635	fh => $state{fh},
324	($scheme eq "https" ? (tls => "connect") : ());	636	peername => $rhost,
		637	tls_ctx => $arg{tls_ctx},
		638	# these need to be reconfigured on keepalive handles
		639	timeout => $timeout,
		640	on_error => sub {
		641	%state = ();
		642	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
		643	},
		644	on_eof => sub {
		645	%state = ();
		646	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
		647	},
		648	;
325		649
326	# limit the number of persistent connections	650	# limit the number of persistent connections
		651	# keepalive not yet supported
327	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	652	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
328	++$KA_COUNT{$_[1]};	653	# ++$KA_COUNT{$_[1]};
329	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	654	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		655	# --$KA_COUNT{$_[1]}
		656	# };
330	$hdr{connection} = "keep-alive";	657	# $hdr{connection} = "keep-alive";
331	delete $hdr{connection}; # keep-alive not yet supported
332	} else {
333	delete $hdr{connection};
334	}	658	# }
335		659
336	# (re-)configure handle	660	$state{handle}->starttls ("connect") if $rscheme eq "https";
337	$state{handle}->timeout ($timeout);
338	$state{handle}->on_error (sub {
339	my $errno = "$!";
340	%state = ();
341	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
342	});
343	$state{handle}->on_eof (sub {
344	%state = ();
345	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
346	});
347		661
		662	# handle actual, non-tunneled, request
		663	my $handle_actual_request = sub {
		664	$ae_error = 596; # request phase
		665
		666	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		667
348	# send request	668	# send request
349	$state{handle}->push_write (	669	$state{handle}->push_write (
350	"$method $rpath HTTP/1.0\015\012"	670	"$method $rpath HTTP/1.1\015\012"
351	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	671	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
352	. "\015\012"	672	. "\015\012"
353	. (delete $arg{body})	673	. (delete $arg{body})
354	);
355
356	%hdr = (); # reduce memory usage, save a kitten
357
358	# status line
359	$state{handle}->push_read (line => qr/\015?\012/, sub {
360	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
361	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
362
363	my %hdr = ( # response headers
364	HTTPVersion => "\x00$1",
365	Status => "\x00$2",
366	Reason => "\x00$3",
367	URL => "\x00$url"
368	);	674	);
369		675
370	# headers, could be optimized a bit	676	# return if error occured during push_write()
371	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	677	return unless %state;
		678
		679	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		680
		681	# status line and headers
		682	$state{read_response} = sub {
372	for ("$_[1]\012") {	683	for ("$_[1]") {
373	# we support spaces in field names, as lotus domino	684	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
374	# creates them.
375	$hdr{lc $1} .= "\x00$2"
376	while /\G
377	([^:\000-\037]+):
378	[\011\040]*
379	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
380	\015?\012
381	/gxc;
382		685
		686	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		687	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		688
		689	# 100 Continue handling
		690	# should not happen as we don't send expect: 100-continue,
		691	# but we handle it just in case.
		692	# since we send the request body regardless, if we get an error
		693	# we are out of-sync, which we currently do NOT handle correctly.
		694	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		695	if $2 eq 100;
		696
		697	push @pseudo,
		698	HTTPVersion => $1,
		699	Status => $2,
		700	Reason => $3,
383	/\G$/	701	;
		702
		703	my $hdr = parse_hdr
384	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	704	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		705
		706	%hdr = (%$hdr, @pseudo);
385	}	707	}
386		708
387	substr $_, 0, 1, ""	709	# redirect handling
388	for values %hdr;	710	# microsoft and other shitheads don't give a shit for following standards,
		711	# try to support some common forms of broken Location headers.
		712	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		713	$hdr{location} =~ s/^\.\/+//;
389		714
390	my $finish = sub {	715	my $url = "$rscheme://$uhost:$uport";
		716
		717	unless ($hdr{location} =~ s/^\///) {
		718	$url .= $upath;
		719	$url =~ s/\/[^\/]*$//;
		720	}
		721
		722	$hdr{location} = "$url/$hdr{location}";
		723	}
		724
		725	my $redirect;
		726
		727	if ($recurse) {
		728	my $status = $hdr{Status};
		729
		730	# industry standard is to redirect POST as GET for
		731	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		732	# also, the UA should ask the user for 301 and 307 and POST,
		733	# industry standard seems to be to simply follow.
		734	# we go with the industry standard.
		735	if ($status == 301 or $status == 302 or $status == 303) {
		736	# HTTP/1.1 is unclear on how to mutate the method
		737	$method = "GET" unless $method eq "HEAD";
		738	$redirect = 1;
		739	} elsif ($status == 307) {
		740	$redirect = 1;
		741	}
		742	}
		743
		744	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		745	my $may_keep_alive = $_[3];
		746
		747	$state{handle}->destroy if $state{handle};
391	%state = ();	748	%state = ();
392		749
		750	if (defined $_[1]) {
		751	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		752	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		753	}
		754
393	# set-cookie processing	755	# set-cookie processing
394	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	756	if ($arg{cookie_jar}) {
395	for (split /\x00/, $hdr{"set-cookie"}) {	757	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost;
396	my ($cookie, @arg) = split /;\s*/;	758	}
397	my ($name, $value) = split /=/, $cookie, 2;
398	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
399
400	my $cdom = (delete $kv{domain}) \|\| $uhost;
401	my $cpath = (delete $kv{path}) \|\| "/";
402
403	$cdom =~ s/^.?/./; # make sure it starts with a "."
404		759
405	next if $cdom =~ /\.$/;	760	if ($redirect && exists $hdr{location}) {
406		761	# we ignore any errors, as it is very common to receive
407	# this is not rfc-like and not netscape-like. go figure.	762	# Content-Length != 0 but no actual body
408	my $ndots = $cdom =~ y/.//;	763	# we also access %hdr, as $_[1] might be an erro
409	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	764	http_request (
410		765	$method => $hdr{location},
		766	%arg,
		767	recurse => $recurse - 1,
		768	Redirect => [$_[0], \%hdr],
		769	$cb);
		770	} else {
		771	$cb->($_[0], \%hdr);
		772	}
		773	};
		774
		775	$ae_error = 597; # body phase
		776
		777	my $len = $hdr{"content-length"};
		778
		779	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		780	$finish->(undef, 598 => "Request cancelled by on_header");
		781	} elsif (
		782	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		783	or $method eq "HEAD"
		784	or (defined $len && !$len)
		785	) {
		786	# no body
		787	$finish->("", undef, undef, 1);
		788	} else {
		789	# body handling, many different code paths
		790	# - no body expected
		791	# - want_body_handle
		792	# - te chunked
		793	# - 2x length known (with or without on_body)
		794	# - 2x length not known (with or without on_body)
		795	if (!$redirect && $arg{want_body_handle}) {
		796	$_[0]->on_eof (undef);
		797	$_[0]->on_error (undef);
		798	$_[0]->on_read (undef);
		799
		800	$finish->(delete $state{handle});
		801
		802	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		803	my $cl = 0;
		804	my $body = undef;
		805	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		806
		807	my $read_chunk; $read_chunk = sub {
		808	$_[1] =~ /^([0-9a-fA-F]+)/
		809	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		810
		811	my $len = hex $1;
		812
		813	if ($len) {
		814	$cl += $len;
		815
		816	$_[0]->push_read (chunk => $len, sub {
		817	$on_body->($_[1], \%hdr)
		818	or return $finish->(undef, 598 => "Request cancelled by on_body");
		819
		820	$_[0]->push_read (line => sub {
		821	length $_[1]
		822	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		823	$_[0]->push_read (line => $read_chunk);
		824	});
		825	});
411	# store it	826	} else {
412	$arg{cookie_jar}{version} = 1;	827	$hdr{"content-length"} \|\|= $cl;
413	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	828
		829	$_[0]->push_read (line => $qr_nlnl, sub {
		830	if (length $_[1]) {
		831	for ("$_[1]") {
		832	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		833
		834	my $hdr = parse_hdr
		835	or return $finish->(undef, $ae_error => "Garbled response trailers");
		836
		837	%hdr = (%hdr, %$hdr);
		838	}
		839	}
		840
		841	$finish->($body, undef, undef, 1);
		842	});
		843	}
		844	};
		845
		846	$_[0]->push_read (line => $read_chunk);
		847
		848	} elsif ($arg{on_body}) {
		849	if ($len) {
		850	$_[0]->on_read (sub {
		851	$len -= length $_[0]{rbuf};
		852
		853	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		854	or return $finish->(undef, 598 => "Request cancelled by on_body");
		855
		856	$len > 0
		857	or $finish->("", undef, undef, 1);
		858	});
		859	} else {
		860	$_[0]->on_eof (sub {
		861	$finish->("");
		862	});
		863	$_[0]->on_read (sub {
		864	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		865	or $finish->(undef, 598 => "Request cancelled by on_body");
		866	});
		867	}
		868	} else {
		869	$_[0]->on_eof (undef);
		870
		871	if ($len) {
		872	$_[0]->on_read (sub {
		873	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		874	if $len <= length $_[0]{rbuf};
		875	});
		876	} else {
		877	$_[0]->on_error (sub {
		878	($! == Errno::EPIPE \|\| !$!)
		879	? $finish->(delete $_[0]{rbuf})
		880	: $finish->(undef, $ae_error => $_[2]);
		881	});
		882	$_[0]->on_read (sub { });
414	}	883	}
415	}	884	}
416
417	# microsoft and other shitheads don't give a shit for following standards,
418	# try to support some common forms of broken Location headers.
419	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
420	$_[1]{location} =~ s/^\.\/+//;
421
422	my $url = "$scheme://$uhost:$uport";
423
424	unless ($_[1]{location} =~ s/^\///) {
425	$url .= $upath;
426	$url =~ s/\/[^\/]*$//;
427	}
428
429	$_[1]{location} = "$url/$_[1]{location}";
430	}
431
432	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
433	# apparently, mozilla et al. just change POST to GET here
434	# more research is needed before we do the same
435	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
436	} elsif ($_[1]{Status} == 303 && $recurse) {
437	# even http/1.1 is unlear on how to mutate the method
438	$method = "GET" unless $method eq "HEAD";
439	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
440	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
441	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
442	} else {
443	$cb->($_[0], $_[1]);
444	}
445	};	885	}
		886	};
446		887
447	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	888	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
448	$finish->(undef, \%hdr);	889	};
		890
		891	# now handle proxy-CONNECT method
		892	if ($proxy && $uscheme eq "https") {
		893	# oh dear, we have to wrap it into a connect request
		894
		895	# maybe re-use $uauthority with patched port?
		896	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		897	$state{handle}->push_read (line => $qr_nlnl, sub {
		898	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		899	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		900
		901	if ($2 == 200) {
		902	$rpath = $upath;
		903	&$handle_actual_request;
449	} else {	904	} else {
450	if (exists $hdr{"content-length"}) {	905	%state = ();
451	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	906	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
452	# could cache persistent connection now
453	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
454	# but we don't, due to misdesigns, this is annoyingly complex
455	};
456
457	$finish->($_[1], \%hdr);
458	});
459	} else {
460	# too bad, need to read until we get an error or EOF,
461	# no way to detect winged data.
462	$_[0]->on_error (sub {
463	$finish->($_[0]{rbuf}, \%hdr);
464	});
465	$_[0]->on_eof (undef);
466	$_[0]->on_read (sub { });
467	}
468	}	907	}
469	});	908	});
		909	} else {
		910	&$handle_actual_request;
470	});	911	}
471	}, sub {
472	$timeout
473	};	912	};
		913
		914	my $tcp_connect = $arg{tcp_connect}
		915	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		916
		917	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		918
474	};	919	};
475		920
476	defined wantarray && AnyEvent::Util::guard { %state = () }	921	defined wantarray && AnyEvent::Util::guard { %state = () }
477	}	922	}
478		923
…		…
492	&http_request	937	&http_request
493	}	938	}
494		939
495	=back	940	=back
496		941
		942	=head2 DNS CACHING
		943
		944	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		945	the actual connection, which in turn uses AnyEvent::DNS to resolve
		946	hostnames. The latter is a simple stub resolver and does no caching
		947	on its own. If you want DNS caching, you currently have to provide
		948	your own default resolver (by storing a suitable resolver object in
		949	C<$AnyEvent::DNS::RESOLVER>).
		950
497	=head2 GLOBAL FUNCTIONS AND VARIABLES	951	=head2 GLOBAL FUNCTIONS AND VARIABLES
498		952
499	=over 4	953	=over 4
500		954
501	=item AnyEvent::HTTP::set_proxy "proxy-url"	955	=item AnyEvent::HTTP::set_proxy "proxy-url"
502		956
503	Sets the default proxy server to use. The proxy-url must begin with a	957	Sets the default proxy server to use. The proxy-url must begin with a
504	string of the form C<http://host:port> (optionally C<https:...>).	958	string of the form C<http://host:port> (optionally C<https:...>), croaks
		959	otherwise.
		960
		961	To clear an already-set proxy, use C<undef>.
		962
		963	=item $date = AnyEvent::HTTP::format_date $timestamp
		964
		965	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		966	Date (RFC 2616).
		967
		968	=item $timestamp = AnyEvent::HTTP::parse_date $date
		969
		970	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		971	bunch of minor variations of those, and returns the corresponding POSIX
		972	timestamp, or C<undef> if the date cannot be parsed.
505		973
506	=item $AnyEvent::HTTP::MAX_RECURSE	974	=item $AnyEvent::HTTP::MAX_RECURSE
507		975
508	The default value for the C<recurse> request parameter (default: C<10>).	976	The default value for the C<recurse> request parameter (default: C<10>).
509		977
510	=item $AnyEvent::HTTP::USERAGENT	978	=item $AnyEvent::HTTP::USERAGENT
511		979
512	The default value for the C<User-Agent> header (the default is	980	The default value for the C<User-Agent> header (the default is
513	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	981	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
514		982
515	=item $AnyEvent::HTTP::MAX_PERSISTENT	983	=item $AnyEvent::HTTP::MAX_PER_HOST
516		984
517	The maximum number of persistent connections to keep open (default: 8).	985	The maximum number of concurrent connections to the same host (identified
		986	by the hostname). If the limit is exceeded, then the additional requests
		987	are queued until previous connections are closed.
518		988
519	Not implemented currently.	989	The default value for this is C<4>, and it is highly advisable to not
520		990	increase it.
521	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
522
523	The maximum time to cache a persistent connection, in seconds (default: 2).
524
525	Not implemented currently.
526		991
527	=item $AnyEvent::HTTP::ACTIVE	992	=item $AnyEvent::HTTP::ACTIVE
528		993
529	The number of active connections. This is not the number of currently	994	The number of active connections. This is not the number of currently
530	running requests, but the number of currently open and non-idle TCP	995	running requests, but the number of currently open and non-idle TCP
…		…
532		997
533	=back	998	=back
534		999
535	=cut	1000	=cut
536		1001
		1002	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1003	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1004
		1005	sub format_date($) {
		1006	my ($time) = @_;
		1007
		1008	# RFC 822/1123 format
		1009	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1010
		1011	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1012	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1013	$H, $M, $S;
		1014	}
		1015
		1016	sub parse_date($) {
		1017	my ($date) = @_;
		1018
		1019	my ($d, $m, $y, $H, $M, $S);
		1020
		1021	if ($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$/) {
		1022	# RFC 822/1123, required by RFC 2616 (with " ")
		1023	# cookie dates (with "-")
		1024
		1025	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1026
		1027	} elsif ($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$/) {
		1028	# RFC 850
		1029	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1030
		1031	} elsif ($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])$/) {
		1032	# ISO C's asctime
		1033	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1034	}
		1035	# other formats fail in the loop below
		1036
		1037	for (0..11) {
		1038	if ($m eq $month[$_]) {
		1039	require Time::Local;
		1040	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1041	}
		1042	}
		1043
		1044	undef
		1045	}
		1046
537	sub set_proxy($) {	1047	sub set_proxy($) {
		1048	if (length $_[0]) {
538	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1049	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1050	or Carp::croak "$_[0]: invalid proxy URL";
		1051	$PROXY = [$2, $3 \|\| 3128, $1]
		1052	} else {
		1053	undef $PROXY;
		1054	}
539	}	1055	}
540		1056
541	# initialise proxy from environment	1057	# initialise proxy from environment
		1058	eval {
542	set_proxy $ENV{http_proxy};	1059	set_proxy $ENV{http_proxy};
		1060	};
		1061
		1062	=head2 SOCKS PROXIES
		1063
		1064	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1065	compile your perl to support socks, or use an external program such as
		1066	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1067	transparently.
		1068
		1069	Alternatively, for AnyEvent::HTTP only, you can use your own
		1070	C<tcp_connect> function that does the proxy handshake - here is an example
		1071	that works with socks4a proxies:
		1072
		1073	use Errno;
		1074	use AnyEvent::Util;
		1075	use AnyEvent::Socket;
		1076	use AnyEvent::Handle;
		1077
		1078	# host, port and username of/for your socks4a proxy
		1079	my $socks_host = "10.0.0.23";
		1080	my $socks_port = 9050;
		1081	my $socks_user = "";
		1082
		1083	sub socks4a_connect {
		1084	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1085
		1086	my $hdl = new AnyEvent::Handle
		1087	connect => [$socks_host, $socks_port],
		1088	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1089	on_error => sub { $connect_cb->() },
		1090	;
		1091
		1092	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1093
		1094	$hdl->push_read (chunk => 8, sub {
		1095	my ($hdl, $chunk) = @_;
		1096	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1097
		1098	if ($status == 0x5a) {
		1099	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1100	} else {
		1101	$! = Errno::ENXIO; $connect_cb->();
		1102	}
		1103	});
		1104
		1105	$hdl
		1106	}
		1107
		1108	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1109	possibly after switching off other proxy types:
		1110
		1111	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1112
		1113	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1114	my ($data, $headers) = @_;
		1115	...
		1116	};
543		1117
544	=head1 SEE ALSO	1118	=head1 SEE ALSO
545		1119
546	L<AnyEvent>.	1120	L<AnyEvent>.
547		1121
548	=head1 AUTHOR	1122	=head1 AUTHOR
549		1123
550	Marc Lehmann <schmorp@schmorp.de>	1124	Marc Lehmann <schmorp@schmorp.de>
551	http://home.schmorp.de/	1125	http://home.schmorp.de/
552		1126
		1127	With many thanks to Дмитрий Шалашов, who provided countless
		1128	testcases and bugreports.
		1129
553	=cut	1130	=cut
554		1131
555	1	1132	1
556		1133

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.27 by root, Thu Jul 24 06:01:10 2008 UTC vs. Revision 1.79 by root, Sat Jan 1 20:01:07 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.27 by root, Thu Jul 24 06:01:10 2008 UTC vs.
Revision 1.79 by root, Sat Jan 1 20:01:07 2011 UTC