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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs.
Revision 1.75 by root, Sat Jan 1 00:08:51 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 = '1.05';	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
…		…
92	must be an absolute http or https URL.	91	must be an absolute http or https URL.
93		92
94	When called in void context, nothing is returned. In other contexts,	93	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	94	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	95	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.	96	destroyed before the callback is called, the request will be cancelled.
98		97
99	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
100	(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
101	response headers as second argument.	100	(and trailers) as second argument.
102		101
103	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
104	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
105	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
106	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
107	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).
		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	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
108		122
109	If the server sends a header multiple times, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
115		130
116	A typical callback might look like this:	131	A typical callback might look like this:
117		132
118	sub {	133	sub {
119	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
135	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
136	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
137		152
138	=item headers => hashref	153	=item headers => hashref
139		154
140	The request headers to use. Currently, C<http_request> may provide its	155	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	156	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	157	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		158	(this can be suppressed by using C<undef> for these headers in which case
		159	they won't be sent at all).
143		160
144	=item timeout => $seconds	161	=item timeout => $seconds
145		162
146	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
148		168
149	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
150		170
151	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		173
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	175	HTTPS.
156		176
157	=item body => $string	177	=item body => $string
158		178
159	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be sent as-is (future versions of
160	this module might offer more options).	180	this module might offer more options).
161		181
162	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
163		183
164	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
165	based on the original netscape specification.	185	based on the original netscape specification.
166		186
167	The C<$hash_ref> must be an (initially empty) hash reference which will	187	The C<$hash_ref> must be an (initially empty) hash reference which will
168	get updated automatically. It is possible to save the cookie_jar to	188	get updated automatically. It is possible to save the cookie jar to
169	persistent storage with something like JSON or Storable, but this is not	189	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	190	recommended, as session-only cookies might survive longer than expected.
171		191
172	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not meant to be complete. If
173	meant to be complete. If you want complete cookie management you have to	193	you want complete cookie management you have to do that on your
174	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites
175	cookie-using sites working. Cookies are a privacy disaster, do not use	195	working. Cookies are a privacy disaster, do not use them unless required
176	them unless required to.	196	to.
		197
		198	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		199	headers will be set and handled by this module, otherwise they will be
		200	left untouched.
		201
		202	=item tls_ctx => $scheme \| $tls_ctx
		203
		204	Specifies the AnyEvent::TLS context to be used for https connections. This
		205	parameter follows the same rules as the C<tls_ctx> parameter to
		206	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		207	C<high> can be specified, which give you a predefined low-security (no
		208	verification, highest compatibility) and high-security (CA and common-name
		209	verification) TLS context.
		210
		211	The default for this option is C<low>, which could be interpreted as "give
		212	me the page, no matter what".
		213
		214	=item on_prepare => $callback->($fh)
		215
		216	In rare cases you need to "tune" the socket before it is used to
		217	connect (for exmaple, to bind it on a given IP address). This parameter
		218	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		219	and behaves exactly the same way (e.g. it has to provide a
		220	timeout). See the description for the C<$prepare_cb> argument of
		221	C<AnyEvent::Socket::tcp_connect> for details.
		222
		223	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		224
		225	In even rarer cases you want total control over how AnyEvent::HTTP
		226	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		227	to do this, but you can provide your own C<tcp_connect> function -
		228	obviously, it has to follow the same calling conventions, except that it
		229	may always return a connection guard object.
		230
		231	There are probably lots of weird uses for this function, starting from
		232	tracing the hosts C<http_request> actually tries to connect, to (inexact
		233	but fast) host => IP address caching or even socks protocol support.
		234
		235	=item on_header => $callback->($headers)
		236
		237	When specified, this callback will be called with the header hash as soon
		238	as headers have been successfully received from the remote server (not on
		239	locally-generated errors).
		240
		241	It has to return either true (in which case AnyEvent::HTTP will continue),
		242	or false, in which case AnyEvent::HTTP will cancel the download (and call
		243	the finish callback with an error code of C<598>).
		244
		245	This callback is useful, among other things, to quickly reject unwanted
		246	content, which, if it is supposed to be rare, can be faster than first
		247	doing a C<HEAD> request.
		248
		249	The downside is that cancelling the request makes it impossible to re-use
		250	the connection. Also, the C<on_header> callback will not receive any
		251	trailer (headers sent after the response body).
		252
		253	Example: cancel the request unless the content-type is "text/html".
		254
		255	on_header => sub {
		256	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		257	},
		258
		259	=item on_body => $callback->($partial_body, $headers)
		260
		261	When specified, all body data will be passed to this callback instead of
		262	to the completion callback. The completion callback will get the empty
		263	string instead of the body data.
		264
		265	It has to return either true (in which case AnyEvent::HTTP will continue),
		266	or false, in which case AnyEvent::HTTP will cancel the download (and call
		267	the completion callback with an error code of C<598>).
		268
		269	The downside to cancelling the request is that it makes it impossible to
		270	re-use the connection.
		271
		272	This callback is useful when the data is too large to be held in memory
		273	(so the callback writes it to a file) or when only some information should
		274	be extracted, or when the body should be processed incrementally.
		275
		276	It is usually preferred over doing your own body handling via
		277	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		278	only used to create a connection, C<want_body_handle> is the better
		279	alternative, as it allows you to install your own event handler, reducing
		280	resource usage.
		281
		282	=item want_body_handle => $enable
		283
		284	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		285	changes considerably: after parsing the headers, and instead of
		286	downloading the body (if any), the completion callback will be
		287	called. Instead of the C<$body> argument containing the body data, the
		288	callback will receive the L<AnyEvent::Handle> object associated with the
		289	connection. In error cases, C<undef> will be passed. When there is no body
		290	(e.g. status C<304>), the empty string will be passed.
		291
		292	The handle object might or might not be in TLS mode, might be connected to
		293	a proxy, be a persistent connection etc., and configured in unspecified
		294	ways. The user is responsible for this handle (it will not be used by this
		295	module anymore).
		296
		297	This is useful with some push-type services, where, after the initial
		298	headers, an interactive protocol is used (typical example would be the
		299	push-style twitter API which starts a JSON/XML stream).
		300
		301	If you think you need this, first have a look at C<on_body>, to see if
		302	that doesn't solve your problem in a better way.
177		303
178	=back	304	=back
179		305
180	Example: make a simple HTTP GET request for http://www.nethype.de/	306	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		307	the response body.
181		308
182	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
183	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
184	print "$body\n";	311	print "$body\n";
185	};	312	};
186		313
187	Example: make a HTTP HEAD request on https://www.google.com/, use a	314	Example: do a HTTP HEAD request on https://www.google.com/, use a
188	timeout of 30 seconds.	315	timeout of 30 seconds.
189		316
190	http_request	317	http_request
191	GET => "https://www.google.com",	318	GET => "https://www.google.com",
192	timeout => 30,	319	timeout => 30,
…		…
195	use Data::Dumper;	322	use Data::Dumper;
196	print Dumper $hdr;	323	print Dumper $hdr;
197	}	324	}
198	;	325	;
199		326
200	Example: make another simple HTTP GET request, but immediately try to	327	Example: do another simple HTTP GET request, but immediately try to
201	cancel it.	328	cancel it.
202		329
203	my $request = http_request GET => "http://www.nethype.de/", sub {	330	my $request = http_request GET => "http://www.nethype.de/", sub {
204	my ($body, $hdr) = @_;	331	my ($body, $hdr) = @_;
205	print "$body\n";	332	print "$body\n";
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		365
239	_slot_schedule $_[0];	366	_slot_schedule $_[0];
240	}	367	}
241		368
242	our $qr_nl = qr<\015?\012>;	369	# extract cookies from jar
243	our $qr_nlnl = qr<\015?\012\015?\012>;	370	sub cookie_jar_extract($$$$) {
		371	my ($jar, $uscheme, $uhost, $upath) = @_;
		372
		373	%$jar = () if $jar->{version} != 1;
		374
		375	my @cookies;
		376
		377	while (my ($chost, $paths) = each %$jar) {
		378	next unless ref $paths;
		379
		380	if ($chost =~ /^\./) {
		381	next unless $chost eq substr $uhost, -length $chost;
		382	} elsif ($chost =~ /\./) {
		383	next unless $chost eq $uhost;
		384	} else {
		385	next;
		386	}
		387
		388	while (my ($cpath, $cookies) = each %$paths) {
		389	next unless $cpath eq substr $upath, 0, length $cpath;
		390
		391	while (my ($cookie, $kv) = each %$cookies) {
		392	next if $uscheme ne "https" && exists $kv->{secure};
		393
		394	if (exists $kv->{expires}) {
		395	if (AE::now > parse_date ($kv->{expires})) {
		396	delete $cookies->{$cookie};
		397	next;
		398	}
		399	}
		400
		401	my $value = $kv->{value};
		402
		403	if ($value =~ /[=;,[:space:]]/) {
		404	$value =~ s/([\\"])/\\$1/g;
		405	$value = "\"$value\"";
		406	}
		407
		408	push @cookies, "$cookie=$value";
		409	}
		410	}
		411	}
		412
		413	\@cookies
		414	}
		415
		416	# parse set_cookie header into jar
		417	sub cookie_jar_set_cookie($$$) {
		418	my ($jar, $set_cookie, $uhost) = @_;
		419
		420	for ($set_cookie) {
		421	# parse NAME=VALUE
		422	my @kv;
		423
		424	while (
		425	m{
		426	\G\s*
		427	(?:
		428	expires \s=\s ([A-Z][a-z][a-z],\ [^,;]+)
		429	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )
		430	)
		431	}gcxsi
		432	) {
		433	my $name = $2;
		434	my $value = $4;
		435
		436	unless (defined $name) {
		437	# expires
		438	$name = "expires";
		439	$value = $1;
		440	} elsif (!defined $value) {
		441	# quoted
		442	$value = $3;
		443	$value =~ s/\\(.)/$1/gs;
		444	}
		445
		446	push @kv, lc $name, $value;
		447
		448	last unless /\G\s*;/gc;
		449	}
		450
		451	last unless @kv;
		452
		453	my $name = shift @kv;
		454	my %kv = (value => shift @kv, @kv);
		455
		456	$kv{expires} \|\|= format_date (AE::now + $kv{"max-age"})
		457	if exists $kv{"max-age"};
		458
		459	my $cdom;
		460	my $cpath = (delete $kv{path}) \|\| "/";
		461
		462	if (exists $kv{domain}) {
		463	$cdom = delete $kv{domain};
		464
		465	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		466
		467	next if $cdom =~ /\.$/;
		468
		469	# this is not rfc-like and not netscape-like. go figure.
		470	my $ndots = $cdom =~ y/.//;
		471	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		472	} else {
		473	$cdom = $uhost;
		474	}
		475
		476	# store it
		477	$jar->{version} = 1;
		478	$jar->{$cdom}{$cpath}{$name} = \%kv;
		479
		480	redo if /\G\s*,/gc;
		481	}
		482	}
		483
		484	# continue to parse $_ for headers and place them into the arg
		485	sub parse_hdr() {
		486	my %hdr;
		487
		488	# things seen, not parsed:
		489	# p3pP="NON CUR OTPi OUR NOR UNI"
		490
		491	$hdr{lc $1} .= ",$2"
		492	while /\G
		493	([^:\000-\037]*):
		494	[\011\040]*
		495	((?: [^\012]+ \| \012[\011\040] )*)
		496	\012
		497	/gxc;
		498
		499	/\G$/
		500	or return;
		501
		502	# remove the "," prefix we added to all headers above
		503	substr $_, 0, 1, ""
		504	for values %hdr;
		505
		506	\%hdr
		507	}
		508
		509	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		510
		511	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		512	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
244		513
245	sub http_request($$@) {	514	sub http_request($$@) {
246	my $cb = pop;	515	my $cb = pop;
247	my ($method, $url, %arg) = @_;	516	my ($method, $url, %arg) = @_;
248		517
249	my %hdr;	518	my %hdr;
		519
		520	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		521	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
250		522
251	$method = uc $method;	523	$method = uc $method;
252		524
253	if (my $hdr = $arg{headers}) {	525	if (my $hdr = $arg{headers}) {
254	while (my ($k, $v) = each %$hdr) {	526	while (my ($k, $v) = each %$hdr) {
255	$hdr{lc $k} = $v;	527	$hdr{lc $k} = $v;
256	}	528	}
257	}	529	}
258		530
		531	# pseudo headers for all subsequent responses
		532	my @pseudo = (URL => $url);
		533	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		534
259	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	535	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
260		536
261	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	537	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
262	if $recurse < 0;	538	if $recurse < 0;
263		539
264	my $proxy = $arg{proxy} \|\| $PROXY;	540	my $proxy = $arg{proxy} \|\| $PROXY;
265	my $timeout = $arg{timeout} \|\| $TIMEOUT;	541	my $timeout = $arg{timeout} \|\| $TIMEOUT;
266		542
267	$hdr{"user-agent"} \|\|= $USERAGENT;
268
269	my ($uscheme, $uauthority, $upath, $query, $fragment) =	543	my ($uscheme, $uauthority, $upath, $query, $fragment) =
270	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	544	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
271		545
272	$uscheme = lc $uscheme;	546	$uscheme = lc $uscheme;
273		547
274	my $uport = $uscheme eq "http" ? 80	548	my $uport = $uscheme eq "http" ? 80
275	: $uscheme eq "https" ? 443	549	: $uscheme eq "https" ? 443
276	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	550	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
277
278	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
279		551
280	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	552	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
281	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	553	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
282		554
283	my $uhost = $1;	555	my $uhost = $1;
284	$uport = $2 if defined $2;	556	$uport = $2 if defined $2;
285		557
		558	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		559	unless exists $hdr{host};
		560
286	$uhost =~ s/^\[(.*)\]$/$1/;	561	$uhost =~ s/^\[(.*)\]$/$1/;
287	$upath .= "?$query" if length $query;	562	$upath .= $query if length $query;
288		563
289	$upath =~ s%^/?%/%;	564	$upath =~ s%^/?%/%;
290		565
291	# cookie processing	566	# cookie processing
292	if (my $jar = $arg{cookie_jar}) {	567	if (my $jar = $arg{cookie_jar}) {
293	%$jar = () if $jar->{version} != 1;	568	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
294		569
295	my @cookie;
296
297	while (my ($chost, $v) = each %$jar) {
298	if ($chost =~ /^\./) {
299	next unless $chost eq substr $uhost, -length $chost;
300	} elsif ($chost =~ /\./) {
301	next unless $chost eq $uhost;
302	} else {
303	next;
304	}
305
306	while (my ($cpath, $v) = each %$v) {
307	next unless $cpath eq substr $upath, 0, length $cpath;
308
309	while (my ($k, $v) = each %$v) {
310	next if $uscheme ne "https" && exists $v->{secure};
311	my $value = $v->{value};
312	$value =~ s/([\\"])/\\$1/g;
313	push @cookie, "$k=\"$value\"";
314	}
315	}
316	}
317
318	$hdr{cookie} = join "; ", @cookie	570	$hdr{cookie} = join "; ", @$cookies
319	if @cookie;	571	if @$cookies;
320	}	572	}
321		573
322	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	574	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
323		575
324	if ($proxy) {	576	if ($proxy) {
325	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	577	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		578
		579	$rscheme = "http" unless defined $rscheme;
326		580
327	# don't support https requests over https-proxy transport,	581	# don't support https requests over https-proxy transport,
328	# can't be done with tls as spec'ed.	582	# can't be done with tls as spec'ed, unless you double-encrypt.
329	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	583	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
330	} else {	584	} else {
331	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	585	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
332	}	586	}
333		587
334	$hdr{host} = $uhost;	588	# leave out fragment and query string, just a heuristic
		589	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		590	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		591
335	$hdr{"content-length"} = length $arg{body};	592	$hdr{"content-length"} = length $arg{body}
		593	if length $arg{body} \|\| $method ne "GET";
		594
		595	$hdr{connection} = "close TE"; #1.1
		596	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
336		597
337	my %state = (connect_guard => 1);	598	my %state = (connect_guard => 1);
338		599
339	_get_slot $uhost, sub {	600	_get_slot $uhost, sub {
340	$state{slot_guard} = shift;	601	$state{slot_guard} = shift;
341		602
342	return unless $state{connect_guard};	603	return unless $state{connect_guard};
343		604
344	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	605	my $connect_cb = sub {
345	$state{fh} = shift	606	$state{fh} = shift
		607	or do {
		608	my $err = "$!";
		609	%state = ();
346	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	610	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
347	pop; # free memory, save a tree	611	};
348		612
349	return unless delete $state{connect_guard};	613	return unless delete $state{connect_guard};
350		614
351	# get handle	615	# get handle
352	$state{handle} = new AnyEvent::Handle	616	$state{handle} = new AnyEvent::Handle
353	fh => $state{fh},	617	fh => $state{fh},
		618	peername => $rhost,
		619	tls_ctx => $arg{tls_ctx},
		620	# these need to be reconfigured on keepalive handles
354	timeout => $timeout;	621	timeout => $timeout,
		622	on_error => sub {
		623	%state = ();
		624	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		625	},
		626	on_eof => sub {
		627	%state = ();
		628	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		629	},
		630	;
355		631
356	# limit the number of persistent connections	632	# limit the number of persistent connections
357	# keepalive not yet supported	633	# keepalive not yet supported
358	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	634	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
359	++$KA_COUNT{$_[1]};	635	# ++$KA_COUNT{$_[1]};
360	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	636	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
361	--$KA_COUNT{$_[1]}	637	# --$KA_COUNT{$_[1]}
362	};	638	# };
363	$hdr{connection} = "keep-alive";	639	# $hdr{connection} = "keep-alive";
364	} else {
365	delete $hdr{connection};
366	}	640	# }
367
368	# (re-)configure handle
369	$state{handle}->on_error (sub {
370	my $errno = "$!";
371	%state = ();
372	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
373	});
374	$state{handle}->on_eof (sub {
375	%state = ();
376	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
377	});
378		641
379	$state{handle}->starttls ("connect") if $rscheme eq "https";	642	$state{handle}->starttls ("connect") if $rscheme eq "https";
380		643
381	# handle actual, non-tunneled, request	644	# handle actual, non-tunneled, request
382	my $handle_actual_request = sub {	645	my $handle_actual_request = sub {
383	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	646	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384		647
385	# send request	648	# send request
386	$state{handle}->push_write (	649	$state{handle}->push_write (
387	"$method $rpath HTTP/1.0\015\012"	650	"$method $rpath HTTP/1.1\015\012"
388	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	651	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
389	. "\015\012"	652	. "\015\012"
390	. (delete $arg{body})	653	. (delete $arg{body})
391	);	654	);
392		655
		656	# return if error occured during push_write()
		657	return unless %state;
		658
393	%hdr = (); # reduce memory usage, save a kitten	659	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
394		660
395	# status line	661	# status line and headers
396	$state{handle}->push_read (line => $qr_nl, sub {	662	$state{read_response} = sub {
397	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
398	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
399
400	my %hdr = ( # response headers
401	HTTPVersion => ",$1",
402	Status => ",$2",
403	Reason => ",$3",
404	URL => ",$url"
405	);
406
407	# headers, could be optimized a bit
408	$state{handle}->unshift_read (line => $qr_nlnl, sub {
409	for ("$_[1]\012") {	663	for ("$_[1]") {
410	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	664	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411		665
412	# we support spaces in field names, as lotus domino	666	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
413	# creates them (actually spaces around seperators	667	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
414	# are strictly allowed in http, they are a security issue).
415	$hdr{lc $1} .= ",$2"
416	while /\G
417	([^:\000-\037]+):
418	[\011\040]*
419	((?: [^\012]+ \| \012[\011\040] )*)
420	\012
421	/gxc;
422		668
		669	# 100 Continue handling
		670	# should not happen as we don't send expect: 100-continue,
		671	# but we handle it just in case.
		672	# since we send the request body regardless, if we get an error
		673	# we are out of-sync, which we currently do NOT handle correctly.
		674	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		675	if $2 eq 100;
		676
		677	push @pseudo,
		678	HTTPVersion => $1,
		679	Status => $2,
		680	Reason => $3,
423	/\G$/	681	;
		682
		683	my $hdr = parse_hdr
424	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	684	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		685
		686	%hdr = (%$hdr, @pseudo);
		687	}
		688
		689	# redirect handling
		690	# microsoft and other shitheads don't give a shit for following standards,
		691	# try to support some common forms of broken Location headers.
		692	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		693	$hdr{location} =~ s/^\.\/+//;
		694
		695	my $url = "$rscheme://$uhost:$uport";
		696
		697	unless ($hdr{location} =~ s/^\///) {
		698	$url .= $upath;
		699	$url =~ s/\/[^\/]*$//;
425	}	700	}
426		701
427	substr $_, 0, 1, ""	702	$hdr{location} = "$url/$hdr{location}";
428	for values %hdr;	703	}
429		704
430	my $finish = sub {	705	my $redirect;
431	# TODO: use destroy method, when/if available	706
		707	if ($recurse) {
		708	my $status = $hdr{Status};
		709
		710	# industry standard is to redirect POST as GET for
		711	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		712	# also, the UA should ask the user for 301 and 307 and POST,
		713	# industry standard seems to be to simply follow.
		714	# we go with the industry standard.
		715	if ($status == 301 or $status == 302 or $status == 303) {
		716	# HTTP/1.1 is unclear on how to mutate the method
		717	$method = "GET" unless $method eq "HEAD";
		718	$redirect = 1;
		719	} elsif ($status == 307) {
		720	$redirect = 1;
		721	}
		722	}
		723
		724	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		725	my $may_keep_alive = $_[3];
		726
432	#$state{handle}->destroy;	727	$state{handle}->destroy if $state{handle};
433	$state{handle}->on_eof (undef);
434	$state{handle}->on_error (undef);
435	%state = ();	728	%state = ();
436		729
		730	if (defined $_[1]) {
		731	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		732	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		733	}
		734
437	# set-cookie processing	735	# set-cookie processing
438	if ($arg{cookie_jar}) {	736	if ($arg{cookie_jar}) {
439	for ($hdr{"set-cookie"}) {	737	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost;
440	# parse NAME=VALUE	738	}
		739
		740	if ($redirect && exists $hdr{location}) {
		741	# we ignore any errors, as it is very common to receive
		742	# Content-Length != 0 but no actual body
		743	# we also access %hdr, as $_[1] might be an erro
		744	http_request (
		745	$method => $hdr{location},
		746	%arg,
		747	recurse => $recurse - 1,
		748	Redirect => [$_[0], \%hdr],
		749	$cb);
		750	} else {
		751	$cb->($_[0], \%hdr);
		752	}
		753	};
		754
		755	my $len = $hdr{"content-length"};
		756
		757	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		758	$finish->(undef, 598 => "Request cancelled by on_header");
		759	} elsif (
		760	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		761	or $method eq "HEAD"
		762	or (defined $len && !$len)
		763	) {
		764	# no body
		765	$finish->("", undef, undef, 1);
		766	} else {
		767	# body handling, many different code paths
		768	# - no body expected
		769	# - want_body_handle
		770	# - te chunked
		771	# - 2x length known (with or without on_body)
		772	# - 2x length not known (with or without on_body)
		773	if (!$redirect && $arg{want_body_handle}) {
		774	$_[0]->on_eof (undef);
		775	$_[0]->on_error (undef);
		776	$_[0]->on_read (undef);
		777
		778	$finish->(delete $state{handle});
		779
		780	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		781	my $cl = 0;
		782	my $body = undef;
		783	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		784
		785	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		786
		787	my $read_chunk; $read_chunk = sub {
		788	$_[1] =~ /^([0-9a-fA-F]+)/
		789	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		790
		791	my $len = hex $1;
		792
		793	if ($len) {
		794	$cl += $len;
		795
		796	$_[0]->push_read (chunk => $len, sub {
		797	$on_body->($_[1], \%hdr)
		798	or return $finish->(undef, 598 => "Request cancelled by on_body");
		799
		800	$_[0]->push_read (line => sub {
		801	length $_[1]
		802	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		803	$_[0]->push_read (line => $read_chunk);
		804	});
441	my @kv;	805	});
		806	} else {
		807	$hdr{"content-length"} \|\|= $cl;
442		808
443	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	809	$_[0]->push_read (line => $qr_nlnl, sub {
444	my $name = $1;	810	if (length $_[1]) {
445	my $value = $3;
446
447	unless ($value) {	811	for ("$_[1]") {
		812	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		813
		814	my $hdr = parse_hdr
		815	or return $finish->(undef, 599 => "Garbled response trailers");
		816
		817	%hdr = (%hdr, %$hdr);
448	$value = $2;	818	}
449	$value =~ s/\\(.)/$1/gs;
450	}	819	}
451		820
452	push @kv, $name => $value;	821	$finish->($body, undef, undef, 1);
453
454	last unless /\G\s*;/gc;
455	}	822	});
456
457	last unless @kv;
458
459	my $name = shift @kv;
460	my %kv = (value => shift @kv, @kv);
461
462	my $cdom;
463	my $cpath = (delete $kv{path}) \|\| "/";
464
465	if (exists $kv{domain}) {
466	$cdom = delete $kv{domain};
467
468	$cdom =~ s/^\.?/./; # make sure it starts with a "."
469
470	next if $cdom =~ /\.$/;
471
472	# this is not rfc-like and not netscape-like. go figure.
473	my $ndots = $cdom =~ y/.//;
474	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
475	} else {
476	$cdom = $uhost;
477	}
478
479	# store it
480	$arg{cookie_jar}{version} = 1;
481	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
482
483	redo if /\G\s*,/gc;
484	}	823	}
485	}	824	};
486		825
487	# microsoft and other shitheads don't give a shit for following standards,	826	$_[0]->push_read (line => $read_chunk);
488	# try to support some common forms of broken Location headers.
489	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
490	$_[1]{location} =~ s/^\.\/+//;
491		827
492	my $url = "$rscheme://$uhost:$uport";	828	} elsif ($arg{on_body}) {
		829	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
493		830
494	unless ($_[1]{location} =~ s/^\///) {
495	$url .= $upath;
496	$url =~ s/\/[^\/]*$//;
497	}
498
499	$_[1]{location} = "$url/$_[1]{location}";
500	}
501
502	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
503	# apparently, mozilla et al. just change POST to GET here
504	# more research is needed before we do the same
505	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
506	} elsif ($_[1]{Status} == 303 && $recurse) {
507	# even http/1.1 is unclear on how to mutate the method
508	$method = "GET" unless $method eq "HEAD";
509	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
510	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
511	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
512	} else {	831	if ($len) {
513	$cb->($_[0], $_[1]);	832	$_[0]->on_read (sub {
514	}	833	$len -= length $_[0]{rbuf};
515	};
516		834
517	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	835	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
518	$finish->(undef, \%hdr);	836	or return $finish->(undef, 598 => "Request cancelled by on_body");
519	} else {	837
520	if (exists $hdr{"content-length"}) {
521	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
522	# could cache persistent connection now
523	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
524	# but we don't, due to misdesigns, this is annoyingly complex
525	};	838	$len > 0
526		839	or $finish->("", undef, undef, 1);
527	$finish->($_[1], \%hdr);
528	});	840	});
529	} else {	841	} else {
530	# too bad, need to read until we get an error or EOF,	842	$_[0]->on_eof (sub {
531	# no way to detect winged data.	843	$finish->("");
		844	});
		845	$_[0]->on_read (sub {
		846	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		847	or $finish->(undef, 598 => "Request cancelled by on_body");
		848	});
		849	}
		850	} else {
		851	$_[0]->on_eof (undef);
		852
		853	if ($len) {
		854	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		855	$_[0]->on_read (sub {
		856	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		857	if $len <= length $_[0]{rbuf};
		858	});
		859	} else {
532	$_[0]->on_error (sub {	860	$_[0]->on_error (sub {
		861	($! == Errno::EPIPE \|\| !$!)
533	$finish->($_[0]{rbuf}, \%hdr);	862	? $finish->(delete $_[0]{rbuf})
		863	: $finish->(undef, 599 => $_[2]);
534	});	864	});
535	$_[0]->on_eof (undef);
536	$_[0]->on_read (sub { });	865	$_[0]->on_read (sub { });
537	}	866	}
538	}	867	}
539	});	868	}
540	});	869	};
		870
		871	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
541	};	872	};
542		873
543	# now handle proxy-CONNECT method	874	# now handle proxy-CONNECT method
544	if ($proxy && $uscheme eq "https") {	875	if ($proxy && $uscheme eq "https") {
545	# oh dear, we have to wrap it into a connect request	876	# oh dear, we have to wrap it into a connect request
546		877
547	# maybe re-use $uauthority with patched port?	878	# maybe re-use $uauthority with patched port?
548	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	879	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
549	$state{handle}->push_read (line => $qr_nlnl, sub {	880	$state{handle}->push_read (line => $qr_nlnl, sub {
550	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	881	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
551	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));	882	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
552		883
553	if ($2 == 200) {	884	if ($2 == 200) {
554	$rpath = $upath;	885	$rpath = $upath;
555	&$handle_actual_request;	886	&$handle_actual_request;
556	} else {	887	} else {
557	%state = ();	888	%state = ();
558	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	889	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
559	}	890	}
560	});	891	});
561	} else {	892	} else {
562	&$handle_actual_request;	893	&$handle_actual_request;
563	}	894	}
564
565	}, sub {
566	$timeout
567	};	895	};
		896
		897	my $tcp_connect = $arg{tcp_connect}
		898	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		899
		900	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		901
568	};	902	};
569		903
570	defined wantarray && AnyEvent::Util::guard { %state = () }	904	defined wantarray && AnyEvent::Util::guard { %state = () }
571	}	905	}
572		906
…		…
586	&http_request	920	&http_request
587	}	921	}
588		922
589	=back	923	=back
590		924
		925	=head2 DNS CACHING
		926
		927	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		928	the actual connection, which in turn uses AnyEvent::DNS to resolve
		929	hostnames. The latter is a simple stub resolver and does no caching
		930	on its own. If you want DNS caching, you currently have to provide
		931	your own default resolver (by storing a suitable resolver object in
		932	C<$AnyEvent::DNS::RESOLVER>).
		933
591	=head2 GLOBAL FUNCTIONS AND VARIABLES	934	=head2 GLOBAL FUNCTIONS AND VARIABLES
592		935
593	=over 4	936	=over 4
594		937
595	=item AnyEvent::HTTP::set_proxy "proxy-url"	938	=item AnyEvent::HTTP::set_proxy "proxy-url"
596		939
597	Sets the default proxy server to use. The proxy-url must begin with a	940	Sets the default proxy server to use. The proxy-url must begin with a
598	string of the form C<http://host:port> (optionally C<https:...>).	941	string of the form C<http://host:port> (optionally C<https:...>), croaks
		942	otherwise.
		943
		944	To clear an already-set proxy, use C<undef>.
		945
		946	=item $date = AnyEvent::HTTP::format_date $timestamp
		947
		948	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		949	Date (RFC 2616).
		950
		951	=item $timestamp = AnyEvent::HTTP::parse_date $date
		952
		953	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and
		954	returns the corresponding POSIX timestamp, or C<undef> if the date cannot
		955	be parsed.
599		956
600	=item $AnyEvent::HTTP::MAX_RECURSE	957	=item $AnyEvent::HTTP::MAX_RECURSE
601		958
602	The default value for the C<recurse> request parameter (default: C<10>).	959	The default value for the C<recurse> request parameter (default: C<10>).
603		960
604	=item $AnyEvent::HTTP::USERAGENT	961	=item $AnyEvent::HTTP::USERAGENT
605		962
606	The default value for the C<User-Agent> header (the default is	963	The default value for the C<User-Agent> header (the default is
607	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	964	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
608		965
609	=item $AnyEvent::HTTP::MAX_PERSISTENT	966	=item $AnyEvent::HTTP::MAX_PER_HOST
610		967
611	The maximum number of persistent connections to keep open (default: 8).	968	The maximum number of concurrent connections to the same host (identified
		969	by the hostname). If the limit is exceeded, then the additional requests
		970	are queued until previous connections are closed.
612		971
613	Not implemented currently.	972	The default value for this is C<4>, and it is highly advisable to not
614		973	increase it.
615	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
616
617	The maximum time to cache a persistent connection, in seconds (default: 2).
618
619	Not implemented currently.
620		974
621	=item $AnyEvent::HTTP::ACTIVE	975	=item $AnyEvent::HTTP::ACTIVE
622		976
623	The number of active connections. This is not the number of currently	977	The number of active connections. This is not the number of currently
624	running requests, but the number of currently open and non-idle TCP	978	running requests, but the number of currently open and non-idle TCP
…		…
626		980
627	=back	981	=back
628		982
629	=cut	983	=cut
630		984
		985	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		986	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		987
		988	sub format_date($) {
		989	my ($time) = @_;
		990
		991	# RFC 822/1123 format
		992	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		993
		994	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		995	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		996	$H, $M, $S;
		997	}
		998
		999	sub parse_date($) {
		1000	my ($date) = @_;
		1001
		1002	my ($d, $m, $y, $H, $M, $S);
		1003
		1004	if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9])[\- ]([A-Z][a-z][a-z])[\- ]([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		1005	# RFC 822/1123, required by RFC 2616 (with " ")
		1006	# cookie dates (with "-")
		1007
		1008	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1009
		1010	} elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		1011	# RFC 850
		1012	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1013
		1014	} elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) {
		1015	# ISO C's asctime
		1016	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1017	}
		1018	# other formats fail in the loop below
		1019
		1020	for (0..11) {
		1021	if ($m eq $month[$_]) {
		1022	require Time::Local;
		1023	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1024	}
		1025	}
		1026
		1027	undef
		1028	}
		1029
631	sub set_proxy($) {	1030	sub set_proxy($) {
		1031	if (length $_[0]) {
632	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1032	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1033	or Carp::croak "$_[0]: invalid proxy URL";
		1034	$PROXY = [$2, $3 \|\| 3128, $1]
		1035	} else {
		1036	undef $PROXY;
		1037	}
633	}	1038	}
634		1039
635	# initialise proxy from environment	1040	# initialise proxy from environment
		1041	eval {
636	set_proxy $ENV{http_proxy};	1042	set_proxy $ENV{http_proxy};
		1043	};
		1044
		1045	=head2 SOCKS PROXIES
		1046
		1047	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1048	compile your perl to support socks, or use an external program such as
		1049	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1050	transparently.
		1051
		1052	Alternatively, for AnyEvent::HTTP only, you can use your own
		1053	C<tcp_connect> function that does the proxy handshake - here is an example
		1054	that works with socks4a proxies:
		1055
		1056	use Errno;
		1057	use AnyEvent::Util;
		1058	use AnyEvent::Socket;
		1059	use AnyEvent::Handle;
		1060
		1061	# host, port and username of/for your socks4a proxy
		1062	my $socks_host = "10.0.0.23";
		1063	my $socks_port = 9050;
		1064	my $socks_user = "";
		1065
		1066	sub socks4a_connect {
		1067	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1068
		1069	my $hdl = new AnyEvent::Handle
		1070	connect => [$socks_host, $socks_port],
		1071	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1072	on_error => sub { $connect_cb->() },
		1073	;
		1074
		1075	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1076
		1077	$hdl->push_read (chunk => 8, sub {
		1078	my ($hdl, $chunk) = @_;
		1079	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1080
		1081	if ($status == 0x5a) {
		1082	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1083	} else {
		1084	$! = Errno::ENXIO; $connect_cb->();
		1085	}
		1086	});
		1087
		1088	$hdl
		1089	}
		1090
		1091	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1092	possibly after switching off other proxy types:
		1093
		1094	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1095
		1096	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1097	my ($data, $headers) = @_;
		1098	...
		1099	};
637		1100
638	=head1 SEE ALSO	1101	=head1 SEE ALSO
639		1102
640	L<AnyEvent>.	1103	L<AnyEvent>.
641		1104
642	=head1 AUTHOR	1105	=head1 AUTHOR
643		1106
644	Marc Lehmann <schmorp@schmorp.de>	1107	Marc Lehmann <schmorp@schmorp.de>
645	http://home.schmorp.de/	1108	http://home.schmorp.de/
646		1109
		1110	With many thanks to Дмитрий Шалашов, who provided countless
		1111	testcases and bugreports.
		1112
647	=cut	1113	=cut
648		1114
649	1	1115	1
650		1116

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs. Revision 1.75 by root, Sat Jan 1 00:08:51 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs.
Revision 1.75 by root, Sat Jan 1 00:08:51 2011 UTC