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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.10 by root, Thu Jun 5 13:06:43 2008 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC

…		…
3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client	3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use AnyEvent::HTTP;	7	use AnyEvent::HTTP;
		8
		9	http_get "http://www.nethype.de/", sub { print $_[1] };
		10
		11	# ... do something else here
8		12
9	=head1 DESCRIPTION	13	=head1 DESCRIPTION
10		14
11	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
12	run a supported event loop.	16	run a supported event loop.
13		17
		18	This module implements a simple, stateless and non-blocking HTTP
		19	client. It supports GET, POST and other request methods, cookies and more,
		20	all on a very low level. It can follow redirects supports proxies and
		21	automatically limits the number of connections to the values specified in
		22	the RFC.
		23
		24	It should generally be a "good client" that is enough for most HTTP
		25	tasks. Simple tasks should be simple, but complex tasks should still be
		26	possible as the user retains control over request and response headers.
		27
		28	The caller is responsible for authentication management, cookies (if
		29	the simplistic implementation in this module doesn't suffice), referer
		30	and other high-level protocol details for which this module offers only
		31	limited support.
		32
14	=head2 METHODS	33	=head2 METHODS
15		34
16	=over 4	35	=over 4
17		36
18	=cut	37	=cut
…		…
20	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
21		40
22	use strict;	41	use strict;
23	no warnings;	42	no warnings;
24		43
25	use Carp;	44	use Errno ();
26		45
27	use AnyEvent ();	46	use AnyEvent 5.0 ();
28	use AnyEvent::Util ();	47	use AnyEvent::Util ();
29	use AnyEvent::Socket ();
30	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
31		49
32	use base Exporter::;	50	use base Exporter::;
33		51
34	our $VERSION = '1.0';	52	our $VERSION = '1.5';
35		53
36	our @EXPORT = qw(http_get http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
37		55
38	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)";
39	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
40	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
41	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
42	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
43		61
44	# changing these is evil	62	# changing these is evil
45	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
46	our $MAX_PER_HOST = 4; # not respected yet :(	64	our $MAX_PER_HOST = 4;
47		65
48	our $PROXY;	66	our $PROXY;
		67	our $ACTIVE = 0;
49		68
50	my %KA_COUNT; # number of open keep-alive connections per host	69	my %KA_COUNT; # number of open keep-alive connections per host
		70	my %CO_SLOT; # number of open connections, and wait queue, per host
51		71
52	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
53		73
54	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
55	additional parameters.	75	additional parameters and the return value.
56		76
57	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
58		78
59	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
60	additional parameters.	80	on additional parameters and the return value.
61		81
62	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
63		83
64	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
65	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
66		87
67	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
68		89
69	Executes a HTTP request of type C<$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
70	must be an absolute http or https URL.	91	must be an absolute http or https URL.
71		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
72	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
73	(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 as
74	response headers as second argument.	100	second argument.
75		101
76	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
77	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
78	C<Reason> contain the three parts of the HTTP Status-Line of the same	104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
		105	three parts of the HTTP Status-Line of the same name. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
		110	The pseudo-header C<URL> contains the actual URL (which can differ from
		111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
79	name. If the server sends a header multiple lines, then their contents	123	If the server sends a header multiple times, then their contents will be
80	will be joined together with C<\x00>.	124	joined together with a comma (C<,>), as per the HTTP spec.
81		125
82	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
83	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
84	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
85		130
86	A typical callback might look like this:	131	A typical callback might look like this:
87		132
88	sub {	133	sub {
89	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
105	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
106	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
107		152
108	=item headers => hashref	153	=item headers => hashref
109		154
110	The request headers to use.	155	The request headers to use. Currently, C<http_request> may provide its
		156	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
		157	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		158	suppressed by using C<undef> for these headers in which case they won't be
		159	sent at all).
111		160
112	=item timeout => $seconds	161	=item timeout => $seconds
113		162
114	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
115	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
116		168
117	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
118		170
119	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
120	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
121		173
122	C<$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
123	HTTPS.	175	HTTPS.
124		176
125	=item body => $string	177	=item body => $string
126		178
127	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be-sent as-is (future versions of
…		…
133	based on the original netscape specification.	185	based on the original netscape specification.
134		186
135	The C<$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
136	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
137	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
138	recommended, as expire times are currently being ignored.	190	recommended, as expiry times are currently being ignored.
139		191
140	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not of very high quality, nor
141	meant to be complete. If you want complete cookie management you have to	193	meant to be complete. If you want complete cookie management you have to
142	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	do that on your own. C<cookie_jar> is meant as a quick fix to get some
143	cookie-using sites working. Cookies are a privacy disaster, do not use	195	cookie-using sites working. Cookies are a privacy disaster, do not use
144	them unless required to.	196	them unless required to.
		197
		198	=item tls_ctx => $scheme \| $tls_ctx
		199
		200	Specifies the AnyEvent::TLS context to be used for https connections. This
		201	parameter follows the same rules as the C<tls_ctx> parameter to
		202	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		203	C<high> can be specified, which give you a predefined low-security (no
		204	verification, highest compatibility) and high-security (CA and common-name
		205	verification) TLS context.
		206
		207	The default for this option is C<low>, which could be interpreted as "give
		208	me the page, no matter what".
		209
		210	=item on_prepare => $callback->($fh)
		211
		212	In rare cases you need to "tune" the socket before it is used to
		213	connect (for exmaple, to bind it on a given IP address). This parameter
		214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		215	and behaves exactly the same way (e.g. it has to provide a
		216	timeout). See the description for the C<$prepare_cb> argument of
		217	C<AnyEvent::Socket::tcp_connect> for details.
		218
		219	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		220
		221	In even rarer cases you want total control over how AnyEvent::HTTP
		222	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		223	to do this, but you can provide your own C<tcp_connect> function -
		224	obviously, it has to follow the same calling conventions, except that it
		225	may always return a connection guard object.
		226
		227	There are probably lots of weird uses for this function, starting from
		228	tracing the hosts C<http_request> actually tries to connect, to (inexact
		229	but fast) host => IP address caching or even socks protocol support.
		230
		231	=item on_header => $callback->($headers)
		232
		233	When specified, this callback will be called with the header hash as soon
		234	as headers have been successfully received from the remote server (not on
		235	locally-generated errors).
		236
		237	It has to return either true (in which case AnyEvent::HTTP will continue),
		238	or false, in which case AnyEvent::HTTP will cancel the download (and call
		239	the finish callback with an error code of C<598>).
		240
		241	This callback is useful, among other things, to quickly reject unwanted
		242	content, which, if it is supposed to be rare, can be faster than first
		243	doing a C<HEAD> request.
		244
		245	Example: cancel the request unless the content-type is "text/html".
		246
		247	on_header => sub {
		248	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		249	},
		250
		251	=item on_body => $callback->($partial_body, $headers)
		252
		253	When specified, all body data will be passed to this callback instead of
		254	to the completion callback. The completion callback will get the empty
		255	string instead of the body data.
		256
		257	It has to return either true (in which case AnyEvent::HTTP will continue),
		258	or false, in which case AnyEvent::HTTP will cancel the download (and call
		259	the completion callback with an error code of C<598>).
		260
		261	This callback is useful when the data is too large to be held in memory
		262	(so the callback writes it to a file) or when only some information should
		263	be extracted, or when the body should be processed incrementally.
		264
		265	It is usually preferred over doing your own body handling via
		266	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		267	only used to create a connection, C<want_body_handle> is the better
		268	alternative, as it allows you to install your own event handler, reducing
		269	resource usage.
		270
		271	=item want_body_handle => $enable
		272
		273	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		274	changes considerably: after parsing the headers, and instead of
		275	downloading the body (if any), the completion callback will be
		276	called. Instead of the C<$body> argument containing the body data, the
		277	callback will receive the L<AnyEvent::Handle> object associated with the
		278	connection. In error cases, C<undef> will be passed. When there is no body
		279	(e.g. status C<304>), the empty string will be passed.
		280
		281	The handle object might or might not be in TLS mode, might be connected to
		282	a proxy, be a persistent connection etc., and configured in unspecified
		283	ways. The user is responsible for this handle (it will not be used by this
		284	module anymore).
		285
		286	This is useful with some push-type services, where, after the initial
		287	headers, an interactive protocol is used (typical example would be the
		288	push-style twitter API which starts a JSON/XML stream).
		289
		290	If you think you need this, first have a look at C<on_body>, to see if
		291	that doesn't solve your problem in a better way.
145		292
146	=back	293	=back
147		294
148	Example: make a simple HTTP GET request for http://www.nethype.de/	295	Example: make a simple HTTP GET request for http://www.nethype.de/
149		296
…		…
163	use Data::Dumper;	310	use Data::Dumper;
164	print Dumper $hdr;	311	print Dumper $hdr;
165	}	312	}
166	;	313	;
167		314
		315	Example: make another simple HTTP GET request, but immediately try to
		316	cancel it.
		317
		318	my $request = http_request GET => "http://www.nethype.de/", sub {
		319	my ($body, $hdr) = @_;
		320	print "$body\n";
		321	};
		322
		323	undef $request;
		324
168	=cut	325	=cut
169		326
		327	sub _slot_schedule;
		328	sub _slot_schedule($) {
		329	my $host = shift;
		330
		331	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		332	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		333	# somebody wants that slot
		334	++$CO_SLOT{$host}[0];
		335	++$ACTIVE;
		336
		337	$cb->(AnyEvent::Util::guard {
		338	--$ACTIVE;
		339	--$CO_SLOT{$host}[0];
		340	_slot_schedule $host;
		341	});
		342	} else {
		343	# nobody wants the slot, maybe we can forget about it
		344	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		345	last;
		346	}
		347	}
		348	}
		349
		350	# wait for a free slot on host, call callback
		351	sub _get_slot($$) {
		352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		353
		354	_slot_schedule $_[0];
		355	}
		356
		357	# continue to parse $_ for headers and place them into the arg
		358	sub parse_hdr() {
		359	my %hdr;
		360
		361	# things seen, not parsed:
		362	# p3pP="NON CUR OTPi OUR NOR UNI"
		363
		364	$hdr{lc $1} .= ",$2"
		365	while /\G
		366	([^:\000-\037]*):
		367	[\011\040]*
		368	((?: [^\012]+ \| \012[\011\040] )*)
		369	\012
		370	/gxc;
		371
		372	/\G$/
		373	or return;
		374
		375	# remove the "," prefix we added to all headers above
		376	substr $_, 0, 1, ""
		377	for values %hdr;
		378
		379	\%hdr
		380	}
		381
		382	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		383
		384	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		385	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		386
170	sub http_request($$$;@) {	387	sub http_request($$@) {
171	my $cb = pop;	388	my $cb = pop;
172	my ($method, $url, %arg) = @_;	389	my ($method, $url, %arg) = @_;
173		390
174	my %hdr;	391	my %hdr;
		392
		393	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		394	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
175		395
176	$method = uc $method;	396	$method = uc $method;
177		397
178	if (my $hdr = $arg{headers}) {	398	if (my $hdr = $arg{headers}) {
179	while (my ($k, $v) = each %$hdr) {	399	while (my ($k, $v) = each %$hdr) {
180	$hdr{lc $k} = $v;	400	$hdr{lc $k} = $v;
181	}	401	}
182	}	402	}
183		403
		404	# pseudo headers for all subsequent responses
		405	my @pseudo = (URL => $url);
		406	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		407
184	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	408	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
185		409
186	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	410	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
187	if $recurse < 0;	411	if $recurse < 0;
188		412
189	my $proxy = $arg{proxy} \|\| $PROXY;	413	my $proxy = $arg{proxy} \|\| $PROXY;
190	my $timeout = $arg{timeout} \|\| $TIMEOUT;	414	my $timeout = $arg{timeout} \|\| $TIMEOUT;
191		415
192	$hdr{"user-agent"} \|\|= $USERAGENT;
193
194	my ($scheme, $authority, $upath, $query, $fragment) =	416	my ($uscheme, $uauthority, $upath, $query, $fragment) =
195	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	417	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
196		418
197	$scheme = lc $scheme;	419	$uscheme = lc $uscheme;
198		420
199	my $uport = $scheme eq "http" ? 80	421	my $uport = $uscheme eq "http" ? 80
200	: $scheme eq "https" ? 443	422	: $uscheme eq "https" ? 443
201	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" });	423	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
202		424
203	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	425	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
204	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	426	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
205		427
206	my $uhost = $1;	428	my $uhost = $1;
207	$uport = $2 if defined $2;	429	$uport = $2 if defined $2;
208		430
		431	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		432	unless exists $hdr{host};
		433
209	$uhost =~ s/^\[(.*)\]$/$1/;	434	$uhost =~ s/^\[(.*)\]$/$1/;
210	$upath .= "?$query" if length $query;	435	$upath .= $query if length $query;
211		436
212	$upath =~ s%^/?%/%;	437	$upath =~ s%^/?%/%;
213		438
214	# cookie processing	439	# cookie processing
215	if (my $jar = $arg{cookie_jar}) {	440	if (my $jar = $arg{cookie_jar}) {
216	%$jar = () if $jar->{version} < 1;	441	%$jar = () if $jar->{version} != 1;
217		442
218	my @cookie;	443	my @cookie;
219		444
220	while (my ($chost, $v) = each %$jar) {	445	while (my ($chost, $v) = each %$jar) {
		446	if ($chost =~ /^\./) {
221	next unless $chost eq substr $uhost, -length $chost;	447	next unless $chost eq substr $uhost, -length $chost;
222	next unless $chost =~ /^\./;	448	} elsif ($chost =~ /\./) {
		449	next unless $chost eq $uhost;
		450	} else {
		451	next;
		452	}
223		453
224	while (my ($cpath, $v) = each %$v) {	454	while (my ($cpath, $v) = each %$v) {
225	next unless $cpath eq substr $upath, 0, length $cpath;	455	next unless $cpath eq substr $upath, 0, length $cpath;
226		456
227	while (my ($k, $v) = each %$v) {	457	while (my ($k, $v) = each %$v) {
228	next if $scheme ne "https" && exists $v->{secure};	458	next if $uscheme ne "https" && exists $v->{secure};
		459	my $value = $v->{value};
		460	$value =~ s/([\\"])/\\$1/g;
229	push @cookie, "$k=$v->{value}";	461	push @cookie, "$k=\"$value\"";
230	}	462	}
231	}	463	}
232	}	464	}
233		465
234	$hdr{cookie} = join "; ", @cookie	466	$hdr{cookie} = join "; ", @cookie
235	if @cookie;	467	if @cookie;
236	}	468	}
237		469
238	my ($rhost, $rport, $rpath); # request host, port, path	470	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
239		471
240	if ($proxy) {	472	if ($proxy) {
241	($rhost, $rport, $scheme) = @$proxy;	473	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
242	$rpath = $url;	474
		475	$rscheme = "http" unless defined $rscheme;
		476
		477	# don't support https requests over https-proxy transport,
		478	# can't be done with tls as spec'ed, unless you double-encrypt.
		479	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
243	} else {	480	} else {
244	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	481	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
245	$hdr{host} = $uhost;
246	}	482	}
247		483
		484	# leave out fragment and query string, just a heuristic
		485	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		486	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		487
248	$hdr{"content-length"} = length $arg{body};	488	$hdr{"content-length"} = length $arg{body}
		489	if length $arg{body} \|\| $method ne "GET";
249		490
250	my %state;	491	$hdr{connection} = "close TE";
		492	$hdr{te} = "trailers" unless exists $hdr{te};
251		493
252	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	494	my %state = (connect_guard => 1);
		495
		496	_get_slot $uhost, sub {
		497	$state{slot_guard} = shift;
		498
		499	return unless $state{connect_guard};
		500
		501	my $connect_cb = sub {
253	$state{fh} = shift	502	$state{fh} = shift
254	or return $cb->(undef, { Status => 599, Reason => "$!" });
255
256	delete $state{connect_guard}; # reduce memory usage, save a tree
257
258	# get handle
259	$state{handle} = new AnyEvent::Handle
260	fh => $state{fh},
261	($scheme eq "https" ? (tls => "connect") : ());
262
263	# limit the number of persistent connections
264	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
265	++$KA_COUNT{$_[1]};
266	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
267	$hdr{connection} = "keep-alive";
268	delete $hdr{connection}; # keep-alive not yet supported
269	} else {
270	delete $hdr{connection};
271	}
272
273	# (re-)configure handle
274	$state{handle}->timeout ($timeout);
275	$state{handle}->on_error (sub {
276	%state = ();
277	$cb->(undef, { Status => 599, Reason => "$!" });
278	});
279	$state{handle}->on_eof (sub {
280	%state = ();
281	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
282	});
283
284	# send request
285	$state{handle}->push_write (
286	"$method $rpath HTTP/1.0\015\012"
287	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
288	. "\015\012"
289	. (delete $arg{body})
290	);
291
292	%hdr = (); # reduce memory usage, save a kitten
293
294	# status line
295	$state{handle}->push_read (line => qr/\015?\012/, sub {
296	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
297	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
298
299	my %hdr = ( # response headers
300	HTTPVersion => "\x00$1",
301	Status => "\x00$2",
302	Reason => "\x00$3",
303	);
304
305	# headers, could be optimized a bit
306	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
307	for ("$_[1]\012") {
308	# we support spaces in field names, as lotus domino
309	# creates them.
310	$hdr{lc $1} .= "\x00$2"
311	while /\G
312	([^:\000-\037]+):
313	[\011\040]*
314	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
315	\015?\012
316	/gxc;
317
318	/\G$/
319	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));
320	}	503	or do {
321		504	my $err = "$!";
322	substr $_, 0, 1, ""
323	for values %hdr;
324
325	my $finish = sub {
326	%state = ();	505	%state = ();
		506	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		507	};
327		508
328	# set-cookie processing	509	pop; # free memory, save a tree
329	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	510
330	for (split /\x00/, $hdr{"set-cookie"}) {	511	return unless delete $state{connect_guard};
331	my ($cookie, @arg) = split /;\s*/;	512
332	my ($name, $value) = split /=/, $cookie, 2;	513	# get handle
333	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);	514	$state{handle} = new AnyEvent::Handle
334		515	fh => $state{fh},
335	my $cdom = (delete $kv{domain}) \|\| $uhost;	516	peername => $rhost,
336	my $cpath = (delete $kv{path}) \|\| "/";	517	tls_ctx => $arg{tls_ctx},
337		518	# these need to be reconfigured on keepalive handles
338	$cdom =~ s/^.?/./; # make sure it starts with a "."	519	timeout => $timeout,
339		520	on_error => sub {
340	my $ndots = $cdom =~ y/.//;	521	%state = ();
341	next if $ndots < ($cdom =~ /[^.]{3}$/ ? 2 : 3);	522	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
342		523	},
		524	on_eof => sub {
		525	%state = ();
		526	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		527	},
		528	;
		529
		530	# limit the number of persistent connections
		531	# keepalive not yet supported
		532	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		533	# ++$KA_COUNT{$_[1]};
		534	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		535	# --$KA_COUNT{$_[1]}
		536	# };
		537	# $hdr{connection} = "keep-alive";
		538	# } else {
		539	# delete $hdr{connection};
		540	# }
		541
		542	$state{handle}->starttls ("connect") if $rscheme eq "https";
		543
		544	# handle actual, non-tunneled, request
		545	my $handle_actual_request = sub {
		546	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		547
		548	# send request
		549	$state{handle}->push_write (
		550	"$method $rpath HTTP/1.1\015\012"
		551	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		552	. "\015\012"
		553	. (delete $arg{body})
		554	);
		555
		556	# return if error occured during push_write()
		557	return unless %state;
		558
		559	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		560
		561	# status line and headers
		562	$state{handle}->push_read (line => $qr_nlnl, sub {
		563	my $keepalive = pop;
		564
		565	for ("$_[1]") {
		566	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		567
		568	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
		569	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		570
		571	push @pseudo,
		572	HTTPVersion => $1,
		573	Status => $2,
		574	Reason => $3,
		575	;
		576
		577	my $hdr = parse_hdr
		578	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		579
		580	%hdr = (%$hdr, @pseudo);
		581	}
		582
		583	# redirect handling
		584	# microsoft and other shitheads don't give a shit for following standards,
		585	# try to support some common forms of broken Location headers.
		586	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		587	$hdr{location} =~ s/^\.\/+//;
		588
		589	my $url = "$rscheme://$uhost:$uport";
		590
		591	unless ($hdr{location} =~ s/^\///) {
		592	$url .= $upath;
		593	$url =~ s/\/[^\/]*$//;
		594	}
		595
		596	$hdr{location} = "$url/$hdr{location}";
		597	}
		598
		599	my $redirect;
		600
		601	if ($recurse) {
		602	my $status = $hdr{Status};
		603
		604	# industry standard is to redirect POST as GET for
		605	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		606	# also, the UA should ask the user for 301 and 307 and POST,
		607	# industry standard seems to be to simply follow.
		608	# we go with the industry standard.
		609	if ($status == 301 or $status == 302 or $status == 303) {
		610	# HTTP/1.1 is unclear on how to mutate the method
		611	$method = "GET" unless $method eq "HEAD";
343	# store it	612	$redirect = 1;
344	$arg{cookie_jar}{version} = 1;	613	} elsif ($status == 307) {
345	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	614	$redirect = 1;
346	}	615	}
347	}	616	}
348		617
349	if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {	618	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
350	# microsoft and other assholes don't give a shit for following standards,	619	$state{handle}->destroy if $state{handle};
351	# try to support a common form of broken Location header.	620	%state = ();
352	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
353		621
354	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	622	if (defined $_[1]) {
		623	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		624	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		625	}
		626
		627	# set-cookie processing
		628	if ($arg{cookie_jar}) {
		629	for ($hdr{"set-cookie"}) {
		630	# parse NAME=VALUE
		631	my @kv;
		632
		633	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		634	my $name = $1;
		635	my $value = $3;
		636
		637	unless ($value) {
		638	$value = $2;
		639	$value =~ s/\\(.)/$1/gs;
		640	}
		641
		642	push @kv, $name => $value;
		643
		644	last unless /\G\s*;/gc;
		645	}
		646
		647	last unless @kv;
		648
		649	my $name = shift @kv;
		650	my %kv = (value => shift @kv, @kv);
		651
		652	my $cdom;
		653	my $cpath = (delete $kv{path}) \|\| "/";
		654
		655	if (exists $kv{domain}) {
		656	$cdom = delete $kv{domain};
		657
		658	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		659
		660	next if $cdom =~ /\.$/;
		661
		662	# this is not rfc-like and not netscape-like. go figure.
		663	my $ndots = $cdom =~ y/.//;
		664	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		665	} else {
		666	$cdom = $uhost;
		667	}
		668
		669	# store it
		670	$arg{cookie_jar}{version} = 1;
		671	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		672
		673	redo if /\G\s*,/gc;
		674	}
		675	}
		676
		677	if ($redirect && exists $hdr{location}) {
		678	# we ignore any errors, as it is very common to receive
		679	# Content-Length != 0 but no actual body
		680	# we also access %hdr, as $_[1] might be an erro
		681	http_request (
		682	$method => $hdr{location},
		683	%arg,
		684	recurse => $recurse - 1,
		685	Redirect => [$_[0], \%hdr],
		686	$cb);
		687	} else {
		688	$cb->($_[0], \%hdr);
		689	}
		690	};
		691
		692	my $len = $hdr{"content-length"};
		693
		694	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		695	$finish->(undef, 598 => "Request cancelled by on_header");
		696	} elsif (
		697	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		698	or $method eq "HEAD"
		699	or (defined $len && !$len)
		700	) {
		701	# no body
		702	$finish->("", undef, undef, 1);
355	} else {	703	} else {
356	$cb->($_[0], $_[1]);	704	# body handling, many different code paths
		705	# - no body expected
		706	# - want_body_handle
		707	# - te chunked
		708	# - 2x length known (with or without on_body)
		709	# - 2x length not known (with or without on_body)
		710	if (!$redirect && $arg{want_body_handle}) {
		711	$_[0]->on_eof (undef);
		712	$_[0]->on_error (undef);
		713	$_[0]->on_read (undef);
		714
		715	$finish->(delete $state{handle});
		716
		717	} elsif ($hdr{"transfer-encoding"} =~ /chunked/) {
		718	my $body = undef;
		719	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		720
		721	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		722
		723	my $read_chunk; $read_chunk = sub {
		724	warn $_[1];#d#
		725	$_[1] =~ /^([0-9a-fA-F]+)/
		726	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		727
		728	my $len = hex $1;
		729
		730	if ($len) {
		731	$_[0]->push_read (chunk => hex $1, sub {
		732	$on_body->($_[1], \%hdr)
		733	or return $finish->(undef, 598 => "Request cancelled by on_body");
		734
		735	$_[0]->push_read (line => sub {
		736	length $_[1]
		737	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		738	$_[0]->push_read (line => $read_chunk);
		739	});
		740	});
		741	} else {
		742	$_[0]->push_read (line => $qr_nlnl, sub {
		743	if (length $_[1]) {
		744	for ("$_[1]") {
		745	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		746
		747	my $hdr = parse_hdr
		748	or return $finish->(undef, 599 => "Garbled response trailers");
		749
		750	%hdr = (%hdr, %$hdr);
		751	}
		752	}
		753
		754	$finish->($body, undef, undef, 1);
		755	});
		756	}
		757	};
		758
		759	$_[0]->push_read (line => $read_chunk);
		760
		761	} elsif ($arg{on_body}) {
		762	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		763
		764	if ($len) {
		765	$_[0]->on_read (sub {
		766	$len -= length $_[0]{rbuf};
		767
		768	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		769	or return $finish->(undef, 598 => "Request cancelled by on_body");
		770
		771	$len > 0
		772	or $finish->("", undef, undef, 1);
		773	});
		774	} else {
		775	$_[0]->on_eof (sub {
		776	$finish->("");
		777	});
		778	$_[0]->on_read (sub {
		779	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		780	or $finish->(undef, 598 => "Request cancelled by on_body");
		781	});
		782	}
		783	} else {
		784	$_[0]->on_eof (undef);
		785
		786	if ($len) {
		787	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		788	$_[0]->on_read (sub {
		789	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		790	if $len <= length $_[0]{rbuf};
		791	});
		792	} else {
		793	$_[0]->on_error (sub {
		794	($! == Errno::EPIPE \|\| !$!)
		795	? $finish->(delete $_[0]{rbuf})
		796	: $finish->(undef, 599 => $_[2]);
		797	});
		798	$_[0]->on_read (sub { });
		799	}
		800	}
357	}	801	}
358	};	802	});
		803	};
359		804
360	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	805	# now handle proxy-CONNECT method
361	$finish->(undef, \%hdr);	806	if ($proxy && $uscheme eq "https") {
362	} else {	807	# oh dear, we have to wrap it into a connect request
363	if (exists $hdr{"content-length"}) {
364	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
365	# could cache persistent connection now
366	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
367	# but we don't, due to misdesigns, this is annoyingly complex
368	};
369		808
370	$finish->($_[1], \%hdr);	809	# maybe re-use $uauthority with patched port?
371	});	810	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		811	$state{handle}->push_read (line => $qr_nlnl, sub {
		812	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		813	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		814
		815	if ($2 == 200) {
		816	$rpath = $upath;
		817	&$handle_actual_request;
372	} else {	818	} else {
373	# too bad, need to read until we get an error or EOF,
374	# no way to detect winged data.
375	$_[0]->on_error (sub {
376	$finish->($_[0]{rbuf}, \%hdr);
377	});	819	%state = ();
378	$_[0]->on_eof (undef);	820	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
379	$_[0]->on_read (sub { });
380	}	821	}
381	}	822	});
		823	} else {
		824	&$handle_actual_request;
382	});	825	}
383	});	826	};
384	}, sub {	827
385	$timeout	828	my $tcp_connect = $arg{tcp_connect}
		829	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		830
		831	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		832
386	};	833	};
387		834
388	defined wantarray && AnyEvent::Util::guard { %state = () }	835	defined wantarray && AnyEvent::Util::guard { %state = () }
389	}	836	}
390		837
391	sub http_get($$;@) {	838	sub http_get($@) {
392	unshift @_, "GET";	839	unshift @_, "GET";
393	&http_request	840	&http_request
394	}	841	}
395		842
396	sub http_head($$;@) {	843	sub http_head($@) {
397	unshift @_, "HEAD";	844	unshift @_, "HEAD";
398	&http_request	845	&http_request
399	}	846	}
400		847
401	sub http_post($$$;@) {	848	sub http_post($$@) {
		849	my $url = shift;
402	unshift @_, "POST", "body";	850	unshift @_, "POST", $url, "body";
403	&http_request	851	&http_request
404	}	852	}
405		853
406	=back	854	=back
407		855
		856	=head2 DNS CACHING
		857
		858	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		859	the actual connection, which in turn uses AnyEvent::DNS to resolve
		860	hostnames. The latter is a simple stub resolver and does no caching
		861	on its own. If you want DNS caching, you currently have to provide
		862	your own default resolver (by storing a suitable resolver object in
		863	C<$AnyEvent::DNS::RESOLVER>).
		864
408	=head2 GLOBAL FUNCTIONS AND VARIABLES	865	=head2 GLOBAL FUNCTIONS AND VARIABLES
409		866
410	=over 4	867	=over 4
411		868
412	=item AnyEvent::HTTP::set_proxy "proxy-url"	869	=item AnyEvent::HTTP::set_proxy "proxy-url"
413		870
414	Sets the default proxy server to use. The proxy-url must begin with a	871	Sets the default proxy server to use. The proxy-url must begin with a
415	string of the form C<http://host:port> (optionally C<https:...>).	872	string of the form C<http://host:port> (optionally C<https:...>), croaks
		873	otherwise.
		874
		875	To clear an already-set proxy, use C<undef>.
		876
		877	=item $date = AnyEvent::HTTP::format_date $timestamp
		878
		879	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		880	Date (RFC 2616).
		881
		882	=item $timestamp = AnyEvent::HTTP::parse_date $date
		883
		884	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		885	timestamp, or C<undef> if the date cannot be parsed.
416		886
417	=item $AnyEvent::HTTP::MAX_RECURSE	887	=item $AnyEvent::HTTP::MAX_RECURSE
418		888
419	The default value for the C<recurse> request parameter (default: C<10>).	889	The default value for the C<recurse> request parameter (default: C<10>).
420		890
421	=item $AnyEvent::HTTP::USERAGENT	891	=item $AnyEvent::HTTP::USERAGENT
422		892
423	The default value for the C<User-Agent> header (the default is	893	The default value for the C<User-Agent> header (the default is
424	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	894	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
425		895
426	=item $AnyEvent::HTTP::MAX_PERSISTENT	896	=item $AnyEvent::HTTP::MAX_PER_HOST
427		897
428	The maximum number of persistent connections to keep open (default: 8).	898	The maximum number of concurrent connections to the same host (identified
		899	by the hostname). If the limit is exceeded, then the additional requests
		900	are queued until previous connections are closed.
429		901
430	Not implemented currently.	902	The default value for this is C<4>, and it is highly advisable to not
		903	increase it.
431		904
432	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	905	=item $AnyEvent::HTTP::ACTIVE
433		906
434	The maximum time to cache a persistent connection, in seconds (default: 2).	907	The number of active connections. This is not the number of currently
435		908	running requests, but the number of currently open and non-idle TCP
436	Not implemented currently.	909	connections. This number of can be useful for load-leveling.
437		910
438	=back	911	=back
439		912
440	=cut	913	=cut
441		914
		915	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		916	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		917
		918	sub format_date($) {
		919	my ($time) = @_;
		920
		921	# RFC 822/1123 format
		922	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		923
		924	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		925	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		926	$H, $M, $S;
		927	}
		928
		929	sub parse_date($) {
		930	my ($date) = @_;
		931
		932	my ($d, $m, $y, $H, $M, $S);
		933
		934	if ($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$/) {
		935	# RFC 822/1123, required by RFC 2616
		936	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		937
		938	} elsif ($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$/) {
		939	# RFC 850
		940	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		941
		942	} elsif ($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])$/) {
		943	# ISO C's asctime
		944	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		945	}
		946	# other formats fail in the loop below
		947
		948	for (0..11) {
		949	if ($m eq $month[$_]) {
		950	require Time::Local;
		951	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		952	}
		953	}
		954
		955	undef
		956	}
		957
442	sub set_proxy($) {	958	sub set_proxy($) {
		959	if (length $_[0]) {
443	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	960	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		961	or Carp::croak "$_[0]: invalid proxy URL";
		962	$PROXY = [$2, $3 \|\| 3128, $1]
		963	} else {
		964	undef $PROXY;
		965	}
444	}	966	}
445		967
446	# initialise proxy from environment	968	# initialise proxy from environment
		969	eval {
447	set_proxy $ENV{http_proxy};	970	set_proxy $ENV{http_proxy};
		971	};
		972
		973	=head2 SOCKS PROXIES
		974
		975	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		976	compile your perl to support socks, or use an external program such as
		977	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		978	transparently.
		979
		980	Alternatively, for AnyEvent::HTTP only, you can use your own
		981	C<tcp_connect> function that does the proxy handshake - here is an example
		982	that works with socks4a proxies:
		983
		984	use Errno;
		985	use AnyEvent::Util;
		986	use AnyEvent::Socket;
		987	use AnyEvent::Handle;
		988
		989	# host, port and username of/for your socks4a proxy
		990	my $socks_host = "10.0.0.23";
		991	my $socks_port = 9050;
		992	my $socks_user = "";
		993
		994	sub socks4a_connect {
		995	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		996
		997	my $hdl = new AnyEvent::Handle
		998	connect => [$socks_host, $socks_port],
		999	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1000	on_error => sub { $connect_cb->() },
		1001	;
		1002
		1003	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1004
		1005	$hdl->push_read (chunk => 8, sub {
		1006	my ($hdl, $chunk) = @_;
		1007	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1008
		1009	if ($status == 0x5a) {
		1010	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1011	} else {
		1012	$! = Errno::ENXIO; $connect_cb->();
		1013	}
		1014	});
		1015
		1016	$hdl
		1017	}
		1018
		1019	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1020	possibly after switching off other proxy types:
		1021
		1022	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1023
		1024	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1025	my ($data, $headers) = @_;
		1026	...
		1027	};
448		1028
449	=head1 SEE ALSO	1029	=head1 SEE ALSO
450		1030
451	L<AnyEvent>.	1031	L<AnyEvent>.
452		1032
453	=head1 AUTHOR	1033	=head1 AUTHOR
454		1034
455	Marc Lehmann <schmorp@schmorp.de>	1035	Marc Lehmann <schmorp@schmorp.de>
456	http://home.schmorp.de/	1036	http://home.schmorp.de/
		1037
		1038	With many thanks to Дмитрий Шалашов, who provided countless
		1039	testcases and bugreports.
457		1040
458	=cut	1041	=cut
459		1042
460	1	1043	1
461		1044

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.10 by root, Thu Jun 5 13:06:43 2008 UTC vs. Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.10 by root, Thu Jun 5 13:06:43 2008 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC