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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.24 by root, Wed Jul 2 01:30:33 2008 UTC vs.
Revision 1.68 by root, Fri Dec 31 19:22:18 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 for C<TE:>, C<Referer:> and C<User-Agent:> (this can
		158	be suppressed by using C<undef> for these headers in which case they won't
		159	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 expiry times are currently being ignored.
165		191
166	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
167	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
168	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
169	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
170	them unless required to.	196	them unless required to.
171		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	The downside is that cancelling the request makes it impossible to re-use
		246	the connection. Also, the C<on_header> callback will not receive any
		247	trailer (headers sent after the response body).
		248
		249	Example: cancel the request unless the content-type is "text/html".
		250
		251	on_header => sub {
		252	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		253	},
		254
		255	=item on_body => $callback->($partial_body, $headers)
		256
		257	When specified, all body data will be passed to this callback instead of
		258	to the completion callback. The completion callback will get the empty
		259	string instead of the body data.
		260
		261	It has to return either true (in which case AnyEvent::HTTP will continue),
		262	or false, in which case AnyEvent::HTTP will cancel the download (and call
		263	the completion callback with an error code of C<598>).
		264
		265	The downside to cancelling the request is that it makes it impossible to
		266	re-use the connection.
		267
		268	This callback is useful when the data is too large to be held in memory
		269	(so the callback writes it to a file) or when only some information should
		270	be extracted, or when the body should be processed incrementally.
		271
		272	It is usually preferred over doing your own body handling via
		273	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		274	only used to create a connection, C<want_body_handle> is the better
		275	alternative, as it allows you to install your own event handler, reducing
		276	resource usage.
		277
		278	=item want_body_handle => $enable
		279
		280	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		281	changes considerably: after parsing the headers, and instead of
		282	downloading the body (if any), the completion callback will be
		283	called. Instead of the C<$body> argument containing the body data, the
		284	callback will receive the L<AnyEvent::Handle> object associated with the
		285	connection. In error cases, C<undef> will be passed. When there is no body
		286	(e.g. status C<304>), the empty string will be passed.
		287
		288	The handle object might or might not be in TLS mode, might be connected to
		289	a proxy, be a persistent connection etc., and configured in unspecified
		290	ways. The user is responsible for this handle (it will not be used by this
		291	module anymore).
		292
		293	This is useful with some push-type services, where, after the initial
		294	headers, an interactive protocol is used (typical example would be the
		295	push-style twitter API which starts a JSON/XML stream).
		296
		297	If you think you need this, first have a look at C<on_body>, to see if
		298	that doesn't solve your problem in a better way.
		299
172	=back	300	=back
173		301
174	Example: make a simple HTTP GET request for http://www.nethype.de/	302	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		303	the response body.
175		304
176	http_request GET => "http://www.nethype.de/", sub {	305	http_request GET => "http://www.nethype.de/", sub {
177	my ($body, $hdr) = @_;	306	my ($body, $hdr) = @_;
178	print "$body\n";	307	print "$body\n";
179	};	308	};
180		309
181	Example: make a HTTP HEAD request on https://www.google.com/, use a	310	Example: do a HTTP HEAD request on https://www.google.com/, use a
182	timeout of 30 seconds.	311	timeout of 30 seconds.
183		312
184	http_request	313	http_request
185	GET => "https://www.google.com",	314	GET => "https://www.google.com",
186	timeout => 30,	315	timeout => 30,
…		…
188	my ($body, $hdr) = @_;	317	my ($body, $hdr) = @_;
189	use Data::Dumper;	318	use Data::Dumper;
190	print Dumper $hdr;	319	print Dumper $hdr;
191	}	320	}
192	;	321	;
		322
		323	Example: do another simple HTTP GET request, but immediately try to
		324	cancel it.
		325
		326	my $request = http_request GET => "http://www.nethype.de/", sub {
		327	my ($body, $hdr) = @_;
		328	print "$body\n";
		329	};
		330
		331	undef $request;
193		332
194	=cut	333	=cut
195		334
196	sub _slot_schedule;	335	sub _slot_schedule;
197	sub _slot_schedule($) {	336	sub _slot_schedule($) {
…		…
221	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	360	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
222		361
223	_slot_schedule $_[0];	362	_slot_schedule $_[0];
224	}	363	}
225		364
		365	# continue to parse $_ for headers and place them into the arg
		366	sub parse_hdr() {
		367	my %hdr;
		368
		369	# things seen, not parsed:
		370	# p3pP="NON CUR OTPi OUR NOR UNI"
		371
		372	$hdr{lc $1} .= ",$2"
		373	while /\G
		374	([^:\000-\037]*):
		375	[\011\040]*
		376	((?: [^\012]+ \| \012[\011\040] )*)
		377	\012
		378	/gxc;
		379
		380	/\G$/
		381	or return;
		382
		383	# remove the "," prefix we added to all headers above
		384	substr $_, 0, 1, ""
		385	for values %hdr;
		386
		387	\%hdr
		388	}
		389
		390	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		391
		392	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		393	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		394
226	sub http_request($$@) {	395	sub http_request($$@) {
227	my $cb = pop;	396	my $cb = pop;
228	my ($method, $url, %arg) = @_;	397	my ($method, $url, %arg) = @_;
229		398
230	my %hdr;	399	my %hdr;
		400
		401	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		402	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
231		403
232	$method = uc $method;	404	$method = uc $method;
233		405
234	if (my $hdr = $arg{headers}) {	406	if (my $hdr = $arg{headers}) {
235	while (my ($k, $v) = each %$hdr) {	407	while (my ($k, $v) = each %$hdr) {
236	$hdr{lc $k} = $v;	408	$hdr{lc $k} = $v;
237	}	409	}
238	}	410	}
239		411
		412	# pseudo headers for all subsequent responses
		413	my @pseudo = (URL => $url);
		414	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		415
240	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	416	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
241		417
242	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	418	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
243	if $recurse < 0;	419	if $recurse < 0;
244		420
245	my $proxy = $arg{proxy} \|\| $PROXY;	421	my $proxy = $arg{proxy} \|\| $PROXY;
246	my $timeout = $arg{timeout} \|\| $TIMEOUT;	422	my $timeout = $arg{timeout} \|\| $TIMEOUT;
247		423
248	$hdr{"user-agent"} \|\|= $USERAGENT;
249
250	my ($scheme, $authority, $upath, $query, $fragment) =	424	my ($uscheme, $uauthority, $upath, $query, $fragment) =
251	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	425	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
252		426
253	$scheme = lc $scheme;	427	$uscheme = lc $uscheme;
254		428
255	my $uport = $scheme eq "http" ? 80	429	my $uport = $uscheme eq "http" ? 80
256	: $scheme eq "https" ? 443	430	: $uscheme eq "https" ? 443
257	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	431	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
258		432
259	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
260
261	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	433	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
262	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	434	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
263		435
264	my $uhost = $1;	436	my $uhost = $1;
265	$uport = $2 if defined $2;	437	$uport = $2 if defined $2;
266		438
		439	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		440	unless exists $hdr{host};
		441
267	$uhost =~ s/^\[(.*)\]$/$1/;	442	$uhost =~ s/^\[(.*)\]$/$1/;
268	$upath .= "?$query" if length $query;	443	$upath .= $query if length $query;
269		444
270	$upath =~ s%^/?%/%;	445	$upath =~ s%^/?%/%;
271		446
272	# cookie processing	447	# cookie processing
273	if (my $jar = $arg{cookie_jar}) {	448	if (my $jar = $arg{cookie_jar}) {
274	%$jar = () if $jar->{version} < 1;	449	%$jar = () if $jar->{version} != 1;
275		450
276	my @cookie;	451	my @cookie;
277		452
278	while (my ($chost, $v) = each %$jar) {	453	while (my ($chost, $v) = each %$jar) {
		454	if ($chost =~ /^\./) {
279	next unless $chost eq substr $uhost, -length $chost;	455	next unless $chost eq substr $uhost, -length $chost;
280	next unless $chost =~ /^\./;	456	} elsif ($chost =~ /\./) {
		457	next unless $chost eq $uhost;
		458	} else {
		459	next;
		460	}
281		461
282	while (my ($cpath, $v) = each %$v) {	462	while (my ($cpath, $v) = each %$v) {
283	next unless $cpath eq substr $upath, 0, length $cpath;	463	next unless $cpath eq substr $upath, 0, length $cpath;
284		464
285	while (my ($k, $v) = each %$v) {	465	while (my ($k, $v) = each %$v) {
286	next if $scheme ne "https" && exists $v->{secure};	466	next if $uscheme ne "https" && exists $v->{secure};
		467	my $value = $v->{value};
		468	$value =~ s/([\\"])/\\$1/g;
287	push @cookie, "$k=$v->{value}";	469	push @cookie, "$k=\"$value\"";
288	}	470	}
289	}	471	}
290	}	472	}
291		473
292	$hdr{cookie} = join "; ", @cookie	474	$hdr{cookie} = join "; ", @cookie
293	if @cookie;	475	if @cookie;
294	}	476	}
295		477
296	my ($rhost, $rport, $rpath); # request host, port, path	478	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
297		479
298	if ($proxy) {	480	if ($proxy) {
299	($rhost, $rport, $scheme) = @$proxy;	481	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
300	$rpath = $url;	482
		483	$rscheme = "http" unless defined $rscheme;
		484
		485	# don't support https requests over https-proxy transport,
		486	# can't be done with tls as spec'ed, unless you double-encrypt.
		487	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
301	} else {	488	} else {
302	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	489	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
303	$hdr{host} = $uhost;
304	}	490	}
305		491
		492	# leave out fragment and query string, just a heuristic
		493	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		494	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		495
306	$hdr{"content-length"} = length $arg{body};	496	$hdr{"content-length"} = length $arg{body}
		497	if length $arg{body} \|\| $method ne "GET";
		498
		499	$hdr{connection} = "close TE"; #1.1
		500	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
307		501
308	my %state = (connect_guard => 1);	502	my %state = (connect_guard => 1);
309		503
310	_get_slot $uhost, sub {	504	_get_slot $uhost, sub {
311	$state{slot_guard} = shift;	505	$state{slot_guard} = shift;
312		506
313	return unless $state{connect_guard};	507	return unless $state{connect_guard};
314		508
315	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	509	my $connect_cb = sub {
316	$state{fh} = shift	510	$state{fh} = shift
		511	or do {
		512	my $err = "$!";
		513	%state = ();
317	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	514	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		515	};
318		516
319	delete $state{connect_guard}; # reduce memory usage, save a tree	517	pop; # free memory, save a tree
		518
		519	return unless delete $state{connect_guard};
320		520
321	# get handle	521	# get handle
322	$state{handle} = new AnyEvent::Handle	522	$state{handle} = new AnyEvent::Handle
323	fh => $state{fh},	523	fh => $state{fh},
324	($scheme eq "https" ? (tls => "connect") : ());	524	peername => $rhost,
		525	tls_ctx => $arg{tls_ctx},
		526	# these need to be reconfigured on keepalive handles
		527	timeout => $timeout,
		528	on_error => sub {
		529	%state = ();
		530	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		531	},
		532	on_eof => sub {
		533	%state = ();
		534	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		535	},
		536	;
325		537
326	# limit the number of persistent connections	538	# limit the number of persistent connections
		539	# keepalive not yet supported
327	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	540	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
328	++$KA_COUNT{$_[1]};	541	# ++$KA_COUNT{$_[1]};
329	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	542	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		543	# --$KA_COUNT{$_[1]}
		544	# };
330	$hdr{connection} = "keep-alive";	545	# $hdr{connection} = "keep-alive";
331	delete $hdr{connection}; # keep-alive not yet supported
332	} else {
333	delete $hdr{connection};
334	}	546	# }
335		547
336	# (re-)configure handle	548	$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		549
		550	# handle actual, non-tunneled, request
		551	my $handle_actual_request = sub {
		552	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		553
348	# send request	554	# send request
349	$state{handle}->push_write (	555	$state{handle}->push_write (
350	"$method $rpath HTTP/1.0\015\012"	556	"$method $rpath HTTP/1.1\015\012"
351	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	557	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
352	. "\015\012"	558	. "\015\012"
353	. (delete $arg{body})	559	. (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	);	560	);
369		561
370	# headers, could be optimized a bit	562	# return if error occured during push_write()
371	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	563	return unless %state;
		564
		565	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		566
		567	# status line and headers
		568	$state{read_response} = sub {
372	for ("$_[1]\012") {	569	for ("$_[1]") {
373	# we support spaces in field names, as lotus domino	570	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		571
		572	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
		573	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		574
		575	# 100 Continue handling
		576	# should not happen as we don't send expect: 100-continue,
		577	# but we handle it just in case.
		578	# since we send the request body regardless, if we get an error
		579	# we are out of-sync, which we currently do NOT handle correctly.
		580	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		581	if $2 eq 100;
		582
		583	push @pseudo,
		584	HTTPVersion => $1,
		585	Status => $2,
		586	Reason => $3,
383	/\G$/	587	;
		588
		589	my $hdr = parse_hdr
384	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	590	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		591
		592	%hdr = (%$hdr, @pseudo);
385	}	593	}
386		594
387	substr $_, 0, 1, ""	595	# redirect handling
388	for values %hdr;	596	# microsoft and other shitheads don't give a shit for following standards,
		597	# try to support some common forms of broken Location headers.
		598	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		599	$hdr{location} =~ s/^\.\/+//;
389		600
390	my $finish = sub {	601	my $url = "$rscheme://$uhost:$uport";
		602
		603	unless ($hdr{location} =~ s/^\///) {
		604	$url .= $upath;
		605	$url =~ s/\/[^\/]*$//;
		606	}
		607
		608	$hdr{location} = "$url/$hdr{location}";
		609	}
		610
		611	my $redirect;
		612
		613	if ($recurse) {
		614	my $status = $hdr{Status};
		615
		616	# industry standard is to redirect POST as GET for
		617	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		618	# also, the UA should ask the user for 301 and 307 and POST,
		619	# industry standard seems to be to simply follow.
		620	# we go with the industry standard.
		621	if ($status == 301 or $status == 302 or $status == 303) {
		622	# HTTP/1.1 is unclear on how to mutate the method
		623	$method = "GET" unless $method eq "HEAD";
		624	$redirect = 1;
		625	} elsif ($status == 307) {
		626	$redirect = 1;
		627	}
		628	}
		629
		630	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		631	my $keepalive = pop;
		632
		633	$state{handle}->destroy if $state{handle};
391	%state = ();	634	%state = ();
392		635
		636	if (defined $_[1]) {
		637	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		638	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		639	}
		640
393	# set-cookie processing	641	# set-cookie processing
394	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	642	if ($arg{cookie_jar}) {
395	for (split /\x00/, $hdr{"set-cookie"}) {	643	for ($hdr{"set-cookie"}) {
396	my ($cookie, @arg) = split /;\s*/;	644	# parse NAME=VALUE
397	my ($name, $value) = split /=/, $cookie, 2;	645	my @kv;
398	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);	646
		647	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		648	my $name = $1;
		649	my $value = $3;
		650
		651	unless ($value) {
		652	$value = $2;
		653	$value =~ s/\\(.)/$1/gs;
		654	}
		655
		656	push @kv, $name => $value;
		657
		658	last unless /\G\s*;/gc;
		659	}
		660
		661	last unless @kv;
		662
		663	my $name = shift @kv;
		664	my %kv = (value => shift @kv, @kv);
		665
		666	my $cdom;
		667	my $cpath = (delete $kv{path}) \|\| "/";
		668
		669	if (exists $kv{domain}) {
		670	$cdom = delete $kv{domain};
399		671
400	my $cdom = (delete $kv{domain}) \|\| $uhost;
401	my $cpath = (delete $kv{path}) \|\| "/";
402
403	$cdom =~ s/^.?/./; # make sure it starts with a "."	672	$cdom =~ s/^\.?/./; # make sure it starts with a "."
404		673
405	next if $cdom =~ /\.$/;	674	next if $cdom =~ /\.$/;
406		675
407	# this is not rfc-like and not netscape-like. go figure.	676	# this is not rfc-like and not netscape-like. go figure.
408	my $ndots = $cdom =~ y/.//;	677	my $ndots = $cdom =~ y/.//;
409	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	678	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		679	} else {
		680	$cdom = $uhost;
		681	}
410		682
411	# store it	683	# store it
412	$arg{cookie_jar}{version} = 1;	684	$arg{cookie_jar}{version} = 1;
413	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	685	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		686
		687	redo if /\G\s*,/gc;
414	}	688	}
415	}	689	}
416		690
417	# microsoft and other assholes don't give a shit for following standards,	691	if ($redirect && exists $hdr{location}) {
418	# try to support a common form of broken Location header.	692	# we ignore any errors, as it is very common to receive
419	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%	693	# Content-Length != 0 but no actual body
420	if exists $_[1]{location};	694	# we also access %hdr, as $_[1] might be an erro
421		695	http_request (
422	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {	696	$method => $hdr{location},
423	# apparently, mozilla et al. just change POST to GET here	697	%arg,
424	# more research is needed before we do the same	698	recurse => $recurse - 1,
425	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	699	Redirect => [$_[0], \%hdr],
426	} elsif ($_[1]{Status} == 303 && $recurse) {	700	$cb);
427	# even http/1.1 is unlear on how to mutate the method
428	$method = "GET" unless $method eq "HEAD";
429	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
430	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
431	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
432	} else {	701	} else {
433	$cb->($_[0], $_[1]);	702	$cb->($_[0], \%hdr);
434	}	703	}
435	};	704	};
436		705
437	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	706	my $len = $hdr{"content-length"};
		707
		708	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		709	$finish->(undef, 598 => "Request cancelled by on_header");
		710	} elsif (
		711	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		712	or $method eq "HEAD"
		713	or (defined $len && !$len)
		714	) {
		715	# no body
438	$finish->(undef, \%hdr);	716	$finish->("", undef, undef, 1);
439	} else {	717	} else {
440	if (exists $hdr{"content-length"}) {	718	# body handling, many different code paths
		719	# - no body expected
		720	# - want_body_handle
		721	# - te chunked
		722	# - 2x length known (with or without on_body)
		723	# - 2x length not known (with or without on_body)
		724	if (!$redirect && $arg{want_body_handle}) {
		725	$_[0]->on_eof (undef);
		726	$_[0]->on_error (undef);
		727	$_[0]->on_read (undef);
		728
		729	$finish->(delete $state{handle});
		730
		731	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		732	my $cl = 0;
		733	my $body = undef;
		734	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		735
		736	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		737
		738	my $read_chunk; $read_chunk = sub {
		739	$_[1] =~ /^([0-9a-fA-F]+)/
		740	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		741
		742	my $len = hex $1;
		743
		744	if ($len) {
		745	$cl += $len;
		746
441	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	747	$_[0]->push_read (chunk => $len, sub {
442	# could cache persistent connection now	748	$on_body->($_[1], \%hdr)
443	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	749	or return $finish->(undef, 598 => "Request cancelled by on_body");
444	# but we don't, due to misdesigns, this is annoyingly complex	750
		751	$_[0]->push_read (line => sub {
		752	length $_[1]
		753	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		754	$_[0]->push_read (line => $read_chunk);
		755	});
		756	});
		757	} else {
		758	$hdr{"content-length"} \|\|= $cl;
		759
		760	$_[0]->push_read (line => $qr_nlnl, sub {
		761	if (length $_[1]) {
		762	for ("$_[1]") {
		763	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		764
		765	my $hdr = parse_hdr
		766	or return $finish->(undef, 599 => "Garbled response trailers");
		767
		768	%hdr = (%hdr, %$hdr);
		769	}
		770	}
		771
		772	$finish->($body, undef, undef, 1);
		773	});
		774	}
		775	};
		776
		777	$_[0]->push_read (line => $read_chunk);
		778
		779	} elsif ($arg{on_body}) {
		780	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		781
		782	if ($len) {
		783	$_[0]->on_read (sub {
		784	$len -= length $_[0]{rbuf};
		785
		786	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		787	or return $finish->(undef, 598 => "Request cancelled by on_body");
		788
		789	$len > 0
		790	or $finish->("", undef, undef, 1);
445	};	791	});
446		792	} else {
		793	$_[0]->on_eof (sub {
447	$finish->($_[1], \%hdr);	794	$finish->("");
		795	});
		796	$_[0]->on_read (sub {
		797	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		798	or $finish->(undef, 598 => "Request cancelled by on_body");
		799	});
448	});	800	}
449	} else {	801	} else {
450	# too bad, need to read until we get an error or EOF,
451	# no way to detect winged data.
452	$_[0]->on_error (sub {
453	$finish->($_[0]{rbuf}, \%hdr);
454	});
455	$_[0]->on_eof (undef);	802	$_[0]->on_eof (undef);
		803
		804	if ($len) {
		805	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		806	$_[0]->on_read (sub {
		807	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		808	if $len <= length $_[0]{rbuf};
		809	});
		810	} else {
		811	$_[0]->on_error (sub {
		812	($! == Errno::EPIPE \|\| !$!)
		813	? $finish->(delete $_[0]{rbuf})
		814	: $finish->(undef, 599 => $_[2]);
		815	});
456	$_[0]->on_read (sub { });	816	$_[0]->on_read (sub { });
		817	}
457	}	818	}
458	}	819	}
		820	};
		821
		822	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
		823	};
		824
		825	# now handle proxy-CONNECT method
		826	if ($proxy && $uscheme eq "https") {
		827	# oh dear, we have to wrap it into a connect request
		828
		829	# maybe re-use $uauthority with patched port?
		830	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		831	$state{handle}->push_read (line => $qr_nlnl, sub {
		832	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		833	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		834
		835	if ($2 == 200) {
		836	$rpath = $upath;
		837	&$handle_actual_request;
		838	} else {
		839	%state = ();
		840	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
		841	}
459	});	842	});
		843	} else {
		844	&$handle_actual_request;
460	});	845	}
461	}, sub {
462	$timeout
463	};	846	};
		847
		848	my $tcp_connect = $arg{tcp_connect}
		849	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		850
		851	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		852
464	};	853	};
465		854
466	defined wantarray && AnyEvent::Util::guard { %state = () }	855	defined wantarray && AnyEvent::Util::guard { %state = () }
467	}	856	}
468		857
…		…
482	&http_request	871	&http_request
483	}	872	}
484		873
485	=back	874	=back
486		875
		876	=head2 DNS CACHING
		877
		878	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		879	the actual connection, which in turn uses AnyEvent::DNS to resolve
		880	hostnames. The latter is a simple stub resolver and does no caching
		881	on its own. If you want DNS caching, you currently have to provide
		882	your own default resolver (by storing a suitable resolver object in
		883	C<$AnyEvent::DNS::RESOLVER>).
		884
487	=head2 GLOBAL FUNCTIONS AND VARIABLES	885	=head2 GLOBAL FUNCTIONS AND VARIABLES
488		886
489	=over 4	887	=over 4
490		888
491	=item AnyEvent::HTTP::set_proxy "proxy-url"	889	=item AnyEvent::HTTP::set_proxy "proxy-url"
492		890
493	Sets the default proxy server to use. The proxy-url must begin with a	891	Sets the default proxy server to use. The proxy-url must begin with a
494	string of the form C<http://host:port> (optionally C<https:...>).	892	string of the form C<http://host:port> (optionally C<https:...>), croaks
		893	otherwise.
		894
		895	To clear an already-set proxy, use C<undef>.
		896
		897	=item $date = AnyEvent::HTTP::format_date $timestamp
		898
		899	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		900	Date (RFC 2616).
		901
		902	=item $timestamp = AnyEvent::HTTP::parse_date $date
		903
		904	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		905	timestamp, or C<undef> if the date cannot be parsed.
495		906
496	=item $AnyEvent::HTTP::MAX_RECURSE	907	=item $AnyEvent::HTTP::MAX_RECURSE
497		908
498	The default value for the C<recurse> request parameter (default: C<10>).	909	The default value for the C<recurse> request parameter (default: C<10>).
499		910
500	=item $AnyEvent::HTTP::USERAGENT	911	=item $AnyEvent::HTTP::USERAGENT
501		912
502	The default value for the C<User-Agent> header (the default is	913	The default value for the C<User-Agent> header (the default is
503	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	914	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
504		915
505	=item $AnyEvent::HTTP::MAX_PERSISTENT	916	=item $AnyEvent::HTTP::MAX_PER_HOST
506		917
507	The maximum number of persistent connections to keep open (default: 8).	918	The maximum number of concurrent connections to the same host (identified
		919	by the hostname). If the limit is exceeded, then the additional requests
		920	are queued until previous connections are closed.
508		921
509	Not implemented currently.	922	The default value for this is C<4>, and it is highly advisable to not
510		923	increase it.
511	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
512
513	The maximum time to cache a persistent connection, in seconds (default: 2).
514
515	Not implemented currently.
516		924
517	=item $AnyEvent::HTTP::ACTIVE	925	=item $AnyEvent::HTTP::ACTIVE
518		926
519	The number of active connections. This is not the number of currently	927	The number of active connections. This is not the number of currently
520	running requests, but the number of currently open and non-idle TCP	928	running requests, but the number of currently open and non-idle TCP
…		…
522		930
523	=back	931	=back
524		932
525	=cut	933	=cut
526		934
		935	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		936	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		937
		938	sub format_date($) {
		939	my ($time) = @_;
		940
		941	# RFC 822/1123 format
		942	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		943
		944	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		945	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		946	$H, $M, $S;
		947	}
		948
		949	sub parse_date($) {
		950	my ($date) = @_;
		951
		952	my ($d, $m, $y, $H, $M, $S);
		953
		954	if ($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$/) {
		955	# RFC 822/1123, required by RFC 2616
		956	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		957
		958	} elsif ($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$/) {
		959	# RFC 850
		960	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		961
		962	} elsif ($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])$/) {
		963	# ISO C's asctime
		964	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		965	}
		966	# other formats fail in the loop below
		967
		968	for (0..11) {
		969	if ($m eq $month[$_]) {
		970	require Time::Local;
		971	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		972	}
		973	}
		974
		975	undef
		976	}
		977
527	sub set_proxy($) {	978	sub set_proxy($) {
		979	if (length $_[0]) {
528	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	980	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		981	or Carp::croak "$_[0]: invalid proxy URL";
		982	$PROXY = [$2, $3 \|\| 3128, $1]
		983	} else {
		984	undef $PROXY;
		985	}
529	}	986	}
530		987
531	# initialise proxy from environment	988	# initialise proxy from environment
		989	eval {
532	set_proxy $ENV{http_proxy};	990	set_proxy $ENV{http_proxy};
		991	};
		992
		993	=head2 SOCKS PROXIES
		994
		995	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		996	compile your perl to support socks, or use an external program such as
		997	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		998	transparently.
		999
		1000	Alternatively, for AnyEvent::HTTP only, you can use your own
		1001	C<tcp_connect> function that does the proxy handshake - here is an example
		1002	that works with socks4a proxies:
		1003
		1004	use Errno;
		1005	use AnyEvent::Util;
		1006	use AnyEvent::Socket;
		1007	use AnyEvent::Handle;
		1008
		1009	# host, port and username of/for your socks4a proxy
		1010	my $socks_host = "10.0.0.23";
		1011	my $socks_port = 9050;
		1012	my $socks_user = "";
		1013
		1014	sub socks4a_connect {
		1015	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1016
		1017	my $hdl = new AnyEvent::Handle
		1018	connect => [$socks_host, $socks_port],
		1019	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1020	on_error => sub { $connect_cb->() },
		1021	;
		1022
		1023	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1024
		1025	$hdl->push_read (chunk => 8, sub {
		1026	my ($hdl, $chunk) = @_;
		1027	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1028
		1029	if ($status == 0x5a) {
		1030	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1031	} else {
		1032	$! = Errno::ENXIO; $connect_cb->();
		1033	}
		1034	});
		1035
		1036	$hdl
		1037	}
		1038
		1039	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1040	possibly after switching off other proxy types:
		1041
		1042	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1043
		1044	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1045	my ($data, $headers) = @_;
		1046	...
		1047	};
533		1048
534	=head1 SEE ALSO	1049	=head1 SEE ALSO
535		1050
536	L<AnyEvent>.	1051	L<AnyEvent>.
537		1052
538	=head1 AUTHOR	1053	=head1 AUTHOR
539		1054
540	Marc Lehmann <schmorp@schmorp.de>	1055	Marc Lehmann <schmorp@schmorp.de>
541	http://home.schmorp.de/	1056	http://home.schmorp.de/
542		1057
		1058	With many thanks to Дмитрий Шалашов, who provided countless
		1059	testcases and bugreports.
		1060
543	=cut	1061	=cut
544		1062
545	1	1063	1
546		1064

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.24 by root, Wed Jul 2 01:30:33 2008 UTC vs. Revision 1.68 by root, Fri Dec 31 19:22:18 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.24 by root, Wed Jul 2 01:30:33 2008 UTC vs.
Revision 1.68 by root, Fri Dec 31 19:22:18 2010 UTC