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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.23 by root, Wed Jul 2 01:23:41 2008 UTC vs.
Revision 1.71 by root, Fri Dec 31 20:50:58 2010 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 = '1.03';	52	our $VERSION = '1.5';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
71	my %CO_SLOT; # number of open connections, and wait queue, per host	70	my %CO_SLOT; # number of open connections, and wait queue, per host
72		71
73	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
74		73
75	Executes an HTTP-GET request. See the http_request function for details on	74	Executes an HTTP-GET request. See the http_request function for details on
76	additional parameters.	75	additional parameters and the return value.
77		76
78	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
79		78
80	Executes an HTTP-HEAD request. See the http_request function for details on	79	Executes an HTTP-HEAD request. See the http_request function for details
81	additional parameters.	80	on additional parameters and the return value.
82		81
83	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
84		83
85	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
86	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
87		87
88	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
89		89
90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	91	must be an absolute http or https URL.
92		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
93	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers
95	response headers as second argument.	100	(and trailers) as second argument.
96		101
97	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
98	headers, the "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<< $headers->{Status} >> will be C<59x>
108	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
109		130
110	A typical callback might look like this:	131	A typical callback might look like this:
111		132
112	sub {	133	sub {
113	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
129	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
130	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
131		152
132	=item headers => hashref	153	=item headers => hashref
133		154
134	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
135	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
136	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).
137		160
138	=item timeout => $seconds	161	=item timeout => $seconds
139		162
140	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
141	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
142		168
143	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
144		170
145	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
146	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
147		173
148	C<$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
149	HTTPS.	175	HTTPS.
150		176
151	=item body => $string	177	=item body => $string
152		178
153	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
154	this module might offer more options).	180	this module might offer more options).
155		181
156	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
157		183
158	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
159	based on the original netscape specification.	185	based on the original netscape specification.
160		186
161	The C<$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
162	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
163	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
164	recommended, as expire times are currently being ignored.	190	recommended, as session-only cookies might survive longer than expected.
165		191
166	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
167	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
168	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
169	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
170	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.
171		303
172	=back	304	=back
173		305
174	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.
175		308
176	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
177	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
178	print "$body\n";	311	print "$body\n";
179	};	312	};
180		313
181	Example: make a HTTP HEAD request on https://www.google.com/, use a	314	Example: do a HTTP HEAD request on https://www.google.com/, use a
182	timeout of 30 seconds.	315	timeout of 30 seconds.
183		316
184	http_request	317	http_request
185	GET => "https://www.google.com",	318	GET => "https://www.google.com",
186	timeout => 30,	319	timeout => 30,
…		…
188	my ($body, $hdr) = @_;	321	my ($body, $hdr) = @_;
189	use Data::Dumper;	322	use Data::Dumper;
190	print Dumper $hdr;	323	print Dumper $hdr;
191	}	324	}
192	;	325	;
		326
		327	Example: do another simple HTTP GET request, but immediately try to
		328	cancel it.
		329
		330	my $request = http_request GET => "http://www.nethype.de/", sub {
		331	my ($body, $hdr) = @_;
		332	print "$body\n";
		333	};
		334
		335	undef $request;
193		336
194	=cut	337	=cut
195		338
196	sub _slot_schedule;	339	sub _slot_schedule;
197	sub _slot_schedule($) {	340	sub _slot_schedule($) {
…		…
221	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
222		365
223	_slot_schedule $_[0];	366	_slot_schedule $_[0];
224	}	367	}
225		368
		369	sub cookie_jar_extract($$$$) {
		370	my ($jar, $uscheme, $uhost, $upath) = @_;
		371
		372	%$jar = () if $jar->{version} != 1;
		373
		374	my @cookies;
		375
		376	while (my ($chost, $paths) = each %$jar) {
		377	next unless ref $paths;
		378
		379	if ($chost =~ /^\./) {
		380	next unless $chost eq substr $uhost, -length $chost;
		381	} elsif ($chost =~ /\./) {
		382	next unless $chost eq $uhost;
		383	} else {
		384	next;
		385	}
		386
		387	while (my ($cpath, $cookies) = each %$paths) {
		388	next unless $cpath eq substr $upath, 0, length $cpath;
		389
		390	while (my ($cookie, $kv) = each %$cookies) {
		391	next if $uscheme ne "https" && exists $kv->{secure};
		392
		393	if (exists $kv->{expires}) {
		394	if (AE::now > parse_date ($kv->{expires})) {
		395	delete $cookies->{$cookie};
		396	next;
		397	}
		398	}
		399
		400	my $value = $kv->{value};
		401
		402	if ($value =~ /[=;,[:space:]]/) {
		403	$value =~ s/([\\"])/\\$1/g;
		404	$value = "\"$value\"";
		405	}
		406
		407	push @cookies, "$cookie=$value";
		408	}
		409	}
		410	}
		411
		412	\@cookies
		413	}
		414
		415	# continue to parse $_ for headers and place them into the arg
		416	sub parse_hdr() {
		417	my %hdr;
		418
		419	# things seen, not parsed:
		420	# p3pP="NON CUR OTPi OUR NOR UNI"
		421
		422	$hdr{lc $1} .= ",$2"
		423	while /\G
		424	([^:\000-\037]*):
		425	[\011\040]*
		426	((?: [^\012]+ \| \012[\011\040] )*)
		427	\012
		428	/gxc;
		429
		430	/\G$/
		431	or return;
		432
		433	# remove the "," prefix we added to all headers above
		434	substr $_, 0, 1, ""
		435	for values %hdr;
		436
		437	\%hdr
		438	}
		439
		440	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		441
		442	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		443	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		444
226	sub http_request($$@) {	445	sub http_request($$@) {
227	my $cb = pop;	446	my $cb = pop;
228	my ($method, $url, %arg) = @_;	447	my ($method, $url, %arg) = @_;
229		448
230	my %hdr;	449	my %hdr;
		450
		451	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		452	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
231		453
232	$method = uc $method;	454	$method = uc $method;
233		455
234	if (my $hdr = $arg{headers}) {	456	if (my $hdr = $arg{headers}) {
235	while (my ($k, $v) = each %$hdr) {	457	while (my ($k, $v) = each %$hdr) {
236	$hdr{lc $k} = $v;	458	$hdr{lc $k} = $v;
237	}	459	}
238	}	460	}
239		461
		462	# pseudo headers for all subsequent responses
		463	my @pseudo = (URL => $url);
		464	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		465
240	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	466	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
241		467
242	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	468	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
243	if $recurse < 0;	469	if $recurse < 0;
244		470
245	my $proxy = $arg{proxy} \|\| $PROXY;	471	my $proxy = $arg{proxy} \|\| $PROXY;
246	my $timeout = $arg{timeout} \|\| $TIMEOUT;	472	my $timeout = $arg{timeout} \|\| $TIMEOUT;
247		473
248	$hdr{"user-agent"} \|\|= $USERAGENT;
249
250	my ($scheme, $authority, $upath, $query, $fragment) =	474	my ($uscheme, $uauthority, $upath, $query, $fragment) =
251	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	475	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
252		476
253	$scheme = lc $scheme;	477	$uscheme = lc $uscheme;
254		478
255	my $uport = $scheme eq "http" ? 80	479	my $uport = $uscheme eq "http" ? 80
256	: $scheme eq "https" ? 443	480	: $uscheme eq "https" ? 443
257	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	481	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
258		482
259	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
260
261	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	483	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
262	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	484	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
263		485
264	my $uhost = $1;	486	my $uhost = $1;
265	$uport = $2 if defined $2;	487	$uport = $2 if defined $2;
266		488
		489	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		490	unless exists $hdr{host};
		491
267	$uhost =~ s/^\[(.*)\]$/$1/;	492	$uhost =~ s/^\[(.*)\]$/$1/;
268	$upath .= "?$query" if length $query;	493	$upath .= $query if length $query;
269		494
270	$upath =~ s%^/?%/%;	495	$upath =~ s%^/?%/%;
271		496
272	# cookie processing	497	# cookie processing
273	if (my $jar = $arg{cookie_jar}) {	498	if (my $jar = $arg{cookie_jar}) {
274	%$jar = () if $jar->{version} < 1;	499	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
275		500
276	my @cookie;
277
278	while (my ($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	501	$hdr{cookie} = join "; ", @$cookies
293	if @cookie;	502	if @$cookies;
294	}	503	}
295		504
296	my ($rhost, $rport, $rpath); # request host, port, path	505	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
297		506
298	if ($proxy) {	507	if ($proxy) {
299	($rhost, $rport, $scheme) = @$proxy;	508	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
300	$rpath = $url;	509
		510	$rscheme = "http" unless defined $rscheme;
		511
		512	# don't support https requests over https-proxy transport,
		513	# can't be done with tls as spec'ed, unless you double-encrypt.
		514	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
301	} else {	515	} else {
302	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	516	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
303	$hdr{host} = $uhost;
304	}	517	}
305		518
		519	# leave out fragment and query string, just a heuristic
		520	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		521	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		522
306	$hdr{"content-length"} = length $arg{body};	523	$hdr{"content-length"} = length $arg{body}
		524	if length $arg{body} \|\| $method ne "GET";
		525
		526	$hdr{connection} = "close TE"; #1.1
		527	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
307		528
308	my %state = (connect_guard => 1);	529	my %state = (connect_guard => 1);
309		530
310	_get_slot $uhost, sub {	531	_get_slot $uhost, sub {
311	$state{slot_guard} = shift;	532	$state{slot_guard} = shift;
312		533
313	return unless $state{connect_guard};	534	return unless $state{connect_guard};
314		535
315	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	536	my $connect_cb = sub {
316	$state{fh} = shift	537	$state{fh} = shift
		538	or do {
		539	my $err = "$!";
		540	%state = ();
317	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	541	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		542	};
318		543
319	delete $state{connect_guard}; # reduce memory usage, save a tree	544	pop; # free memory, save a tree
		545
		546	return unless delete $state{connect_guard};
320		547
321	# get handle	548	# get handle
322	$state{handle} = new AnyEvent::Handle	549	$state{handle} = new AnyEvent::Handle
323	fh => $state{fh},	550	fh => $state{fh},
324	($scheme eq "https" ? (tls => "connect") : ());	551	peername => $rhost,
		552	tls_ctx => $arg{tls_ctx},
		553	# these need to be reconfigured on keepalive handles
		554	timeout => $timeout,
		555	on_error => sub {
		556	%state = ();
		557	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		558	},
		559	on_eof => sub {
		560	%state = ();
		561	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		562	},
		563	;
325		564
326	# limit the number of persistent connections	565	# limit the number of persistent connections
		566	# keepalive not yet supported
327	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	567	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
328	++$KA_COUNT{$_[1]};	568	# ++$KA_COUNT{$_[1]};
329	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	569	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		570	# --$KA_COUNT{$_[1]}
		571	# };
330	$hdr{connection} = "keep-alive";	572	# $hdr{connection} = "keep-alive";
331	delete $hdr{connection}; # keep-alive not yet supported
332	} else {
333	delete $hdr{connection};
334	}	573	# }
335		574
336	# (re-)configure handle	575	$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		576
		577	# handle actual, non-tunneled, request
		578	my $handle_actual_request = sub {
		579	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		580
348	# send request	581	# send request
349	$state{handle}->push_write (	582	$state{handle}->push_write (
350	"$method $rpath HTTP/1.0\015\012"	583	"$method $rpath HTTP/1.1\015\012"
351	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	584	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
352	. "\015\012"	585	. "\015\012"
353	. (delete $arg{body})	586	. (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	);	587	);
369		588
370	# headers, could be optimized a bit	589	# return if error occured during push_write()
371	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	590	return unless %state;
		591
		592	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		593
		594	# status line and headers
		595	$state{read_response} = sub {
372	for ("$_[1]\012") {	596	for ("$_[1]") {
373	# we support spaces in field names, as lotus domino	597	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		598
		599	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
		600	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		601
		602	# 100 Continue handling
		603	# should not happen as we don't send expect: 100-continue,
		604	# but we handle it just in case.
		605	# since we send the request body regardless, if we get an error
		606	# we are out of-sync, which we currently do NOT handle correctly.
		607	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		608	if $2 eq 100;
		609
		610	push @pseudo,
		611	HTTPVersion => $1,
		612	Status => $2,
		613	Reason => $3,
383	/\G$/	614	;
		615
		616	my $hdr = parse_hdr
384	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	617	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		618
		619	%hdr = (%$hdr, @pseudo);
385	}	620	}
386		621
387	substr $_, 0, 1, ""	622	# redirect handling
388	for values %hdr;	623	# microsoft and other shitheads don't give a shit for following standards,
		624	# try to support some common forms of broken Location headers.
		625	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		626	$hdr{location} =~ s/^\.\/+//;
389		627
390	my $finish = sub {	628	my $url = "$rscheme://$uhost:$uport";
		629
		630	unless ($hdr{location} =~ s/^\///) {
		631	$url .= $upath;
		632	$url =~ s/\/[^\/]*$//;
		633	}
		634
		635	$hdr{location} = "$url/$hdr{location}";
		636	}
		637
		638	my $redirect;
		639
		640	if ($recurse) {
		641	my $status = $hdr{Status};
		642
		643	# industry standard is to redirect POST as GET for
		644	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		645	# also, the UA should ask the user for 301 and 307 and POST,
		646	# industry standard seems to be to simply follow.
		647	# we go with the industry standard.
		648	if ($status == 301 or $status == 302 or $status == 303) {
		649	# HTTP/1.1 is unclear on how to mutate the method
		650	$method = "GET" unless $method eq "HEAD";
		651	$redirect = 1;
		652	} elsif ($status == 307) {
		653	$redirect = 1;
		654	}
		655	}
		656
		657	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		658	my $keepalive = pop;
		659
		660	$state{handle}->destroy if $state{handle};
391	%state = ();	661	%state = ();
392		662
		663	if (defined $_[1]) {
		664	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		665	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		666	}
		667
393	# set-cookie processing	668	# set-cookie processing
394	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	669	if ($arg{cookie_jar}) {
395	for (split /\x00/, $hdr{"set-cookie"}) {	670	for ($hdr{"set-cookie"}) {
396	my ($cookie, @arg) = split /;\s*/;	671	# parse NAME=VALUE
397	my ($name, $value) = split /=/, $cookie, 2;	672	my @kv;
398	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);	673
		674	while (
		675	m{
		676	\G\s*
		677	(?:
		678	expires \s=\s ([A-Z][a-z][a-z],\ [^,;]+)
		679	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )
		680	)
		681	}gcxsi
		682	) {
		683	my $name = $2;
		684	my $value = $4;
		685
		686	unless (defined $name) {
		687	# expires
		688	$name = "expires";
		689	$value = $1;
		690	} elsif (!defined $value) {
		691	# quoted
		692	$value = $3;
		693	$value =~ s/\\(.)/$1/gs;
		694	}
		695
		696	push @kv, lc $name, $value;
		697
		698	last unless /\G\s*;/gc;
		699	}
		700
		701	last unless @kv;
		702
		703	my $name = shift @kv;
		704	my %kv = (value => shift @kv, @kv);
		705
		706	$kv{expires} \|\|= format_date (AE::now + $kv{"max-age"})
		707	if exists $kv{"max-age"};
		708
		709	my $cdom;
		710	my $cpath = (delete $kv{path}) \|\| "/";
		711
		712	if (exists $kv{domain}) {
		713	$cdom = delete $kv{domain};
399		714
400	my $cdom = (delete $kv{domain}) \|\| $uhost;
401	my $cpath = (delete $kv{path}) \|\| "/";
402
403	$cdom =~ s/^.?/./; # make sure it starts with a "."	715	$cdom =~ s/^\.?/./; # make sure it starts with a "."
404		716
405	next if $cdom =~ /\.$/;	717	next if $cdom =~ /\.$/;
406		718
407	# this is not rfc-like and not netscape-like. go figure.	719	# this is not rfc-like and not netscape-like. go figure.
408	my $ndots = $cdom =~ y/.//;	720	my $ndots = $cdom =~ y/.//;
409	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	721	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		722	} else {
		723	$cdom = $uhost;
		724	}
410		725
411	# store it	726	# store it
412	$arg{cookie_jar}{version} = 1;	727	$arg{cookie_jar}{version} = 1;
413	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	728	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		729
		730	redo if /\G\s*,/gc;
414	}	731	}
415	}	732	}
416		733
417	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {	734	if ($redirect && exists $hdr{location}) {
418	# microsoft and other assholes don't give a shit for following standards,	735	# we ignore any errors, as it is very common to receive
419	# try to support a common form of broken Location header.	736	# Content-Length != 0 but no actual body
420	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;	737	# we also access %hdr, as $_[1] might be an erro
421		738	http_request (
422	# apparently, mozilla et al. just change POST to GET here	739	$method => $hdr{location},
423	# more research is needed before we do the same	740	%arg,
424		741	recurse => $recurse - 1,
425	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	742	Redirect => [$_[0], \%hdr],
426	} elsif ($_[1]{Status} == 303 && $recurse) {	743	$cb);
427	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
428
429	http_request (GET => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
430	} else {	744	} else {
431	$cb->($_[0], $_[1]);	745	$cb->($_[0], \%hdr);
432	}	746	}
433	};	747	};
434		748
435	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	749	my $len = $hdr{"content-length"};
		750
		751	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		752	$finish->(undef, 598 => "Request cancelled by on_header");
		753	} elsif (
		754	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		755	or $method eq "HEAD"
		756	or (defined $len && !$len)
		757	) {
		758	# no body
436	$finish->(undef, \%hdr);	759	$finish->("", undef, undef, 1);
437	} else {	760	} else {
438	if (exists $hdr{"content-length"}) {	761	# body handling, many different code paths
		762	# - no body expected
		763	# - want_body_handle
		764	# - te chunked
		765	# - 2x length known (with or without on_body)
		766	# - 2x length not known (with or without on_body)
		767	if (!$redirect && $arg{want_body_handle}) {
		768	$_[0]->on_eof (undef);
		769	$_[0]->on_error (undef);
		770	$_[0]->on_read (undef);
		771
		772	$finish->(delete $state{handle});
		773
		774	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		775	my $cl = 0;
		776	my $body = undef;
		777	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		778
		779	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		780
		781	my $read_chunk; $read_chunk = sub {
		782	$_[1] =~ /^([0-9a-fA-F]+)/
		783	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		784
		785	my $len = hex $1;
		786
		787	if ($len) {
		788	$cl += $len;
		789
439	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	790	$_[0]->push_read (chunk => $len, sub {
440	# could cache persistent connection now	791	$on_body->($_[1], \%hdr)
441	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	792	or return $finish->(undef, 598 => "Request cancelled by on_body");
442	# but we don't, due to misdesigns, this is annoyingly complex	793
		794	$_[0]->push_read (line => sub {
		795	length $_[1]
		796	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		797	$_[0]->push_read (line => $read_chunk);
		798	});
		799	});
		800	} else {
		801	$hdr{"content-length"} \|\|= $cl;
		802
		803	$_[0]->push_read (line => $qr_nlnl, sub {
		804	if (length $_[1]) {
		805	for ("$_[1]") {
		806	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		807
		808	my $hdr = parse_hdr
		809	or return $finish->(undef, 599 => "Garbled response trailers");
		810
		811	%hdr = (%hdr, %$hdr);
		812	}
		813	}
		814
		815	$finish->($body, undef, undef, 1);
		816	});
		817	}
		818	};
		819
		820	$_[0]->push_read (line => $read_chunk);
		821
		822	} elsif ($arg{on_body}) {
		823	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		824
		825	if ($len) {
		826	$_[0]->on_read (sub {
		827	$len -= length $_[0]{rbuf};
		828
		829	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		830	or return $finish->(undef, 598 => "Request cancelled by on_body");
		831
		832	$len > 0
		833	or $finish->("", undef, undef, 1);
443	};	834	});
444		835	} else {
		836	$_[0]->on_eof (sub {
445	$finish->($_[1], \%hdr);	837	$finish->("");
		838	});
		839	$_[0]->on_read (sub {
		840	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		841	or $finish->(undef, 598 => "Request cancelled by on_body");
		842	});
446	});	843	}
447	} else {	844	} else {
448	# too bad, need to read until we get an error or EOF,
449	# no way to detect winged data.
450	$_[0]->on_error (sub {
451	$finish->($_[0]{rbuf}, \%hdr);
452	});
453	$_[0]->on_eof (undef);	845	$_[0]->on_eof (undef);
		846
		847	if ($len) {
		848	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		849	$_[0]->on_read (sub {
		850	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		851	if $len <= length $_[0]{rbuf};
		852	});
		853	} else {
		854	$_[0]->on_error (sub {
		855	($! == Errno::EPIPE \|\| !$!)
		856	? $finish->(delete $_[0]{rbuf})
		857	: $finish->(undef, 599 => $_[2]);
		858	});
454	$_[0]->on_read (sub { });	859	$_[0]->on_read (sub { });
		860	}
455	}	861	}
456	}	862	}
		863	};
		864
		865	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
		866	};
		867
		868	# now handle proxy-CONNECT method
		869	if ($proxy && $uscheme eq "https") {
		870	# oh dear, we have to wrap it into a connect request
		871
		872	# maybe re-use $uauthority with patched port?
		873	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		874	$state{handle}->push_read (line => $qr_nlnl, sub {
		875	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		876	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		877
		878	if ($2 == 200) {
		879	$rpath = $upath;
		880	&$handle_actual_request;
		881	} else {
		882	%state = ();
		883	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
		884	}
457	});	885	});
		886	} else {
		887	&$handle_actual_request;
458	});	888	}
459	}, sub {
460	$timeout
461	};	889	};
		890
		891	my $tcp_connect = $arg{tcp_connect}
		892	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		893
		894	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		895
462	};	896	};
463		897
464	defined wantarray && AnyEvent::Util::guard { %state = () }	898	defined wantarray && AnyEvent::Util::guard { %state = () }
465	}	899	}
466		900
…		…
480	&http_request	914	&http_request
481	}	915	}
482		916
483	=back	917	=back
484		918
		919	=head2 DNS CACHING
		920
		921	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		922	the actual connection, which in turn uses AnyEvent::DNS to resolve
		923	hostnames. The latter is a simple stub resolver and does no caching
		924	on its own. If you want DNS caching, you currently have to provide
		925	your own default resolver (by storing a suitable resolver object in
		926	C<$AnyEvent::DNS::RESOLVER>).
		927
485	=head2 GLOBAL FUNCTIONS AND VARIABLES	928	=head2 GLOBAL FUNCTIONS AND VARIABLES
486		929
487	=over 4	930	=over 4
488		931
489	=item AnyEvent::HTTP::set_proxy "proxy-url"	932	=item AnyEvent::HTTP::set_proxy "proxy-url"
490		933
491	Sets the default proxy server to use. The proxy-url must begin with a	934	Sets the default proxy server to use. The proxy-url must begin with a
492	string of the form C<http://host:port> (optionally C<https:...>).	935	string of the form C<http://host:port> (optionally C<https:...>), croaks
		936	otherwise.
		937
		938	To clear an already-set proxy, use C<undef>.
		939
		940	=item $date = AnyEvent::HTTP::format_date $timestamp
		941
		942	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		943	Date (RFC 2616).
		944
		945	=item $timestamp = AnyEvent::HTTP::parse_date $date
		946
		947	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and
		948	returns the corresponding POSIX timestamp, or C<undef> if the date cannot
		949	be parsed.
493		950
494	=item $AnyEvent::HTTP::MAX_RECURSE	951	=item $AnyEvent::HTTP::MAX_RECURSE
495		952
496	The default value for the C<recurse> request parameter (default: C<10>).	953	The default value for the C<recurse> request parameter (default: C<10>).
497		954
498	=item $AnyEvent::HTTP::USERAGENT	955	=item $AnyEvent::HTTP::USERAGENT
499		956
500	The default value for the C<User-Agent> header (the default is	957	The default value for the C<User-Agent> header (the default is
501	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	958	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
502		959
503	=item $AnyEvent::HTTP::MAX_PERSISTENT	960	=item $AnyEvent::HTTP::MAX_PER_HOST
504		961
505	The maximum number of persistent connections to keep open (default: 8).	962	The maximum number of concurrent connections to the same host (identified
		963	by the hostname). If the limit is exceeded, then the additional requests
		964	are queued until previous connections are closed.
506		965
507	Not implemented currently.	966	The default value for this is C<4>, and it is highly advisable to not
508		967	increase it.
509	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
510
511	The maximum time to cache a persistent connection, in seconds (default: 2).
512
513	Not implemented currently.
514		968
515	=item $AnyEvent::HTTP::ACTIVE	969	=item $AnyEvent::HTTP::ACTIVE
516		970
517	The number of active connections. This is not the number of currently	971	The number of active connections. This is not the number of currently
518	running requests, but the number of currently open and non-idle TCP	972	running requests, but the number of currently open and non-idle TCP
…		…
520		974
521	=back	975	=back
522		976
523	=cut	977	=cut
524		978
		979	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		980	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		981
		982	sub format_date($) {
		983	my ($time) = @_;
		984
		985	# RFC 822/1123 format
		986	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		987
		988	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		989	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		990	$H, $M, $S;
		991	}
		992
		993	sub parse_date($) {
		994	my ($date) = @_;
		995
		996	my ($d, $m, $y, $H, $M, $S);
		997
		998	if ($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$/) {
		999	# RFC 822/1123, required by RFC 2616 (with " ")
		1000	# cookie dates (with "-")
		1001
		1002	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1003
		1004	} elsif ($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$/) {
		1005	# RFC 850
		1006	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1007
		1008	} elsif ($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])$/) {
		1009	# ISO C's asctime
		1010	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1011	}
		1012	# other formats fail in the loop below
		1013
		1014	for (0..11) {
		1015	if ($m eq $month[$_]) {
		1016	require Time::Local;
		1017	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1018	}
		1019	}
		1020
		1021	undef
		1022	}
		1023
525	sub set_proxy($) {	1024	sub set_proxy($) {
		1025	if (length $_[0]) {
526	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1026	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1027	or Carp::croak "$_[0]: invalid proxy URL";
		1028	$PROXY = [$2, $3 \|\| 3128, $1]
		1029	} else {
		1030	undef $PROXY;
		1031	}
527	}	1032	}
528		1033
529	# initialise proxy from environment	1034	# initialise proxy from environment
		1035	eval {
530	set_proxy $ENV{http_proxy};	1036	set_proxy $ENV{http_proxy};
		1037	};
		1038
		1039	=head2 SOCKS PROXIES
		1040
		1041	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1042	compile your perl to support socks, or use an external program such as
		1043	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1044	transparently.
		1045
		1046	Alternatively, for AnyEvent::HTTP only, you can use your own
		1047	C<tcp_connect> function that does the proxy handshake - here is an example
		1048	that works with socks4a proxies:
		1049
		1050	use Errno;
		1051	use AnyEvent::Util;
		1052	use AnyEvent::Socket;
		1053	use AnyEvent::Handle;
		1054
		1055	# host, port and username of/for your socks4a proxy
		1056	my $socks_host = "10.0.0.23";
		1057	my $socks_port = 9050;
		1058	my $socks_user = "";
		1059
		1060	sub socks4a_connect {
		1061	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1062
		1063	my $hdl = new AnyEvent::Handle
		1064	connect => [$socks_host, $socks_port],
		1065	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1066	on_error => sub { $connect_cb->() },
		1067	;
		1068
		1069	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1070
		1071	$hdl->push_read (chunk => 8, sub {
		1072	my ($hdl, $chunk) = @_;
		1073	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1074
		1075	if ($status == 0x5a) {
		1076	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1077	} else {
		1078	$! = Errno::ENXIO; $connect_cb->();
		1079	}
		1080	});
		1081
		1082	$hdl
		1083	}
		1084
		1085	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1086	possibly after switching off other proxy types:
		1087
		1088	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1089
		1090	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1091	my ($data, $headers) = @_;
		1092	...
		1093	};
531		1094
532	=head1 SEE ALSO	1095	=head1 SEE ALSO
533		1096
534	L<AnyEvent>.	1097	L<AnyEvent>.
535		1098
536	=head1 AUTHOR	1099	=head1 AUTHOR
537		1100
538	Marc Lehmann <schmorp@schmorp.de>	1101	Marc Lehmann <schmorp@schmorp.de>
539	http://home.schmorp.de/	1102	http://home.schmorp.de/
540		1103
		1104	With many thanks to Дмитрий Шалашов, who provided countless
		1105	testcases and bugreports.
		1106
541	=cut	1107	=cut
542		1108
543	1	1109	1
544		1110

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.23 by root, Wed Jul 2 01:23:41 2008 UTC vs. Revision 1.71 by root, Fri Dec 31 20:50:58 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.23 by root, Wed Jul 2 01:23:41 2008 UTC vs.
Revision 1.71 by root, Fri Dec 31 20:50:58 2010 UTC