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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs.
Revision 1.68 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 = '1.05';	52	our $VERSION = '1.5';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
92	must be an absolute http or https URL.	91	must be an absolute http or https URL.
93		92
94	When called in void context, nothing is returned. In other contexts,	93	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	94	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	95	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	96	destroyed before the callback is called, the request will be cancelled.
98		97
99	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers
101	response headers as second argument.	100	(and trailers) as second argument.
102		101
103	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	105	three parts of the HTTP Status-Line of the same name. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
106	pseudo-header C<URL> contains the original URL (which can differ from the	110	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
108		122
109	If the server sends a header multiple times, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
115		130
116	A typical callback might look like this:	131	A typical callback might look like this:
117		132
118	sub {	133	sub {
119	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
135	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
136	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
137		152
138	=item headers => hashref	153	=item headers => hashref
139		154
140	The request headers to use. Currently, C<http_request> may provide its	155	The request headers to use. Currently, C<http_request> may provide its own
141	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	156	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	157	will provide defaults 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).
143		160
144	=item timeout => $seconds	161	=item timeout => $seconds
145		162
146	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
148		168
149	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
150		170
151	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		173
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	175	HTTPS.
156		176
157	=item body => $string	177	=item body => $string
158		178
159	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be sent as-is (future versions of
160	this module might offer more options).	180	this module might offer more options).
161		181
162	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
163		183
164	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
165	based on the original netscape specification.	185	based on the original netscape specification.
166		186
167	The C<$hash_ref> must be an (initially empty) hash reference which will	187	The C<$hash_ref> must be an (initially empty) hash reference which will
168	get updated automatically. It is possible to save the cookie_jar to	188	get updated automatically. It is possible to save the cookie_jar to
169	persistent storage with something like JSON or Storable, but this is not	189	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	190	recommended, as expiry times are currently being ignored.
171		191
172	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
173	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
174	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
175	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
176	them unless required to.	196	them unless required to.
177		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
178	=back	300	=back
179		301
180	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.
181		304
182	http_request GET => "http://www.nethype.de/", sub {	305	http_request GET => "http://www.nethype.de/", sub {
183	my ($body, $hdr) = @_;	306	my ($body, $hdr) = @_;
184	print "$body\n";	307	print "$body\n";
185	};	308	};
186		309
187	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
188	timeout of 30 seconds.	311	timeout of 30 seconds.
189		312
190	http_request	313	http_request
191	GET => "https://www.google.com",	314	GET => "https://www.google.com",
192	timeout => 30,	315	timeout => 30,
…		…
195	use Data::Dumper;	318	use Data::Dumper;
196	print Dumper $hdr;	319	print Dumper $hdr;
197	}	320	}
198	;	321	;
199		322
200	Example: make another simple HTTP GET request, but immediately try to	323	Example: do another simple HTTP GET request, but immediately try to
201	cancel it.	324	cancel it.
202		325
203	my $request = http_request GET => "http://www.nethype.de/", sub {	326	my $request = http_request GET => "http://www.nethype.de/", sub {
204	my ($body, $hdr) = @_;	327	my ($body, $hdr) = @_;
205	print "$body\n";	328	print "$body\n";
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	360	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		361
239	_slot_schedule $_[0];	362	_slot_schedule $_[0];
240	}	363	}
241		364
242	our $qr_nl = qr<\015?\012>;	365	# continue to parse $_ for headers and place them into the arg
243	our $qr_nlnl = qr<\015?\012\015?\012>;	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" };
244		394
245	sub http_request($$@) {	395	sub http_request($$@) {
246	my $cb = pop;	396	my $cb = pop;
247	my ($method, $url, %arg) = @_;	397	my ($method, $url, %arg) = @_;
248		398
249	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";
250		403
251	$method = uc $method;	404	$method = uc $method;
252		405
253	if (my $hdr = $arg{headers}) {	406	if (my $hdr = $arg{headers}) {
254	while (my ($k, $v) = each %$hdr) {	407	while (my ($k, $v) = each %$hdr) {
255	$hdr{lc $k} = $v;	408	$hdr{lc $k} = $v;
256	}	409	}
257	}	410	}
258		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
259	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	416	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
260		417
261	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	418	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
262	if $recurse < 0;	419	if $recurse < 0;
263		420
264	my $proxy = $arg{proxy} \|\| $PROXY;	421	my $proxy = $arg{proxy} \|\| $PROXY;
265	my $timeout = $arg{timeout} \|\| $TIMEOUT;	422	my $timeout = $arg{timeout} \|\| $TIMEOUT;
266		423
267	$hdr{"user-agent"} \|\|= $USERAGENT;
268
269	my ($uscheme, $uauthority, $upath, $query, $fragment) =	424	my ($uscheme, $uauthority, $upath, $query, $fragment) =
270	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	425	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
271		426
272	$uscheme = lc $uscheme;	427	$uscheme = lc $uscheme;
273		428
274	my $uport = $uscheme eq "http" ? 80	429	my $uport = $uscheme eq "http" ? 80
275	: $uscheme eq "https" ? 443	430	: $uscheme eq "https" ? 443
276	: 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" });
277
278	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
279		432
280	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	433	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
281	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	434	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
282		435
283	my $uhost = $1;	436	my $uhost = $1;
284	$uport = $2 if defined $2;	437	$uport = $2 if defined $2;
285		438
		439	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		440	unless exists $hdr{host};
		441
286	$uhost =~ s/^\[(.*)\]$/$1/;	442	$uhost =~ s/^\[(.*)\]$/$1/;
287	$upath .= "?$query" if length $query;	443	$upath .= $query if length $query;
288		444
289	$upath =~ s%^/?%/%;	445	$upath =~ s%^/?%/%;
290		446
291	# cookie processing	447	# cookie processing
292	if (my $jar = $arg{cookie_jar}) {	448	if (my $jar = $arg{cookie_jar}) {
…		…
320	}	476	}
321		477
322	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	478	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
323		479
324	if ($proxy) {	480	if ($proxy) {
325	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	481	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		482
		483	$rscheme = "http" unless defined $rscheme;
326		484
327	# don't support https requests over https-proxy transport,	485	# don't support https requests over https-proxy transport,
328	# can't be done with tls as spec'ed.	486	# can't be done with tls as spec'ed, unless you double-encrypt.
329	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	487	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
330	} else {	488	} else {
331	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	489	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
332	}	490	}
333		491
334	$hdr{host} = $uhost;	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
335	$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
336		501
337	my %state = (connect_guard => 1);	502	my %state = (connect_guard => 1);
338		503
339	_get_slot $uhost, sub {	504	_get_slot $uhost, sub {
340	$state{slot_guard} = shift;	505	$state{slot_guard} = shift;
341		506
342	return unless $state{connect_guard};	507	return unless $state{connect_guard};
343		508
344	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	509	my $connect_cb = sub {
345	$state{fh} = shift	510	$state{fh} = shift
		511	or do {
		512	my $err = "$!";
		513	%state = ();
346	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	514	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		515	};
		516
347	pop; # free memory, save a tree	517	pop; # free memory, save a tree
348		518
349	return unless delete $state{connect_guard};	519	return unless delete $state{connect_guard};
350		520
351	# get handle	521	# get handle
352	$state{handle} = new AnyEvent::Handle	522	$state{handle} = new AnyEvent::Handle
353	fh => $state{fh},	523	fh => $state{fh},
		524	peername => $rhost,
		525	tls_ctx => $arg{tls_ctx},
		526	# these need to be reconfigured on keepalive handles
354	timeout => $timeout;	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	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		535	},
		536	;
355		537
356	# limit the number of persistent connections	538	# limit the number of persistent connections
357	# keepalive not yet supported	539	# keepalive not yet supported
358	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	540	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
359	++$KA_COUNT{$_[1]};	541	# ++$KA_COUNT{$_[1]};
360	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	542	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
361	--$KA_COUNT{$_[1]}	543	# --$KA_COUNT{$_[1]}
362	};	544	# };
363	$hdr{connection} = "keep-alive";	545	# $hdr{connection} = "keep-alive";
364	} else {
365	delete $hdr{connection};
366	}	546	# }
367
368	# (re-)configure handle
369	$state{handle}->on_error (sub {
370	my $errno = "$!";
371	%state = ();
372	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
373	});
374	$state{handle}->on_eof (sub {
375	%state = ();
376	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
377	});
378		547
379	$state{handle}->starttls ("connect") if $rscheme eq "https";	548	$state{handle}->starttls ("connect") if $rscheme eq "https";
380		549
381	# handle actual, non-tunneled, request	550	# handle actual, non-tunneled, request
382	my $handle_actual_request = sub {	551	my $handle_actual_request = sub {
383	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	552	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384		553
385	# send request	554	# send request
386	$state{handle}->push_write (	555	$state{handle}->push_write (
387	"$method $rpath HTTP/1.0\015\012"	556	"$method $rpath HTTP/1.1\015\012"
388	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	557	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
389	. "\015\012"	558	. "\015\012"
390	. (delete $arg{body})	559	. (delete $arg{body})
391	);	560	);
392		561
		562	# return if error occured during push_write()
		563	return unless %state;
		564
393	%hdr = (); # reduce memory usage, save a kitten	565	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
394		566
395	# status line	567	# status line and headers
396	$state{handle}->push_read (line => $qr_nl, sub {	568	$state{read_response} = sub {
397	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
398	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
399
400	my %hdr = ( # response headers
401	HTTPVersion => ",$1",
402	Status => ",$2",
403	Reason => ",$3",
404	URL => ",$url"
405	);
406
407	# headers, could be optimized a bit
408	$state{handle}->unshift_read (line => $qr_nlnl, sub {
409	for ("$_[1]\012") {	569	for ("$_[1]") {
410	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	570	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411		571
412	# we support spaces in field names, as lotus domino	572	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
413	# creates them (actually spaces around seperators	573	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
414	# are strictly allowed in http, they are a security issue).
415	$hdr{lc $1} .= ",$2"
416	while /\G
417	([^:\000-\037]+):
418	[\011\040]*
419	((?: [^\012]+ \| \012[\011\040] )*)
420	\012
421	/gxc;
422		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 => $3,
423	/\G$/	587	;
		588
		589	my $hdr = parse_hdr
424	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);
		593	}
		594
		595	# redirect handling
		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/^\.\/+//;
		600
		601	my $url = "$rscheme://$uhost:$uport";
		602
		603	unless ($hdr{location} =~ s/^\///) {
		604	$url .= $upath;
		605	$url =~ s/\/[^\/]*$//;
425	}	606	}
426		607
427	substr $_, 0, 1, ""	608	$hdr{location} = "$url/$hdr{location}";
428	for values %hdr;	609	}
429		610
430	my $finish = sub {	611	my $redirect;
431	# TODO: use destroy method, when/if available	612
		613	if ($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 $keepalive = pop;
		632
432	#$state{handle}->destroy;	633	$state{handle}->destroy if $state{handle};
433	$state{handle}->on_eof (undef);
434	$state{handle}->on_error (undef);
435	%state = ();	634	%state = ();
436		635
		636	if (defined $_[1]) {
		637	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		638	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		639	}
		640
437	# set-cookie processing	641	# set-cookie processing
438	if ($arg{cookie_jar}) {	642	if ($arg{cookie_jar}) {
439	for ($hdr{"set-cookie"}) {	643	for ($hdr{"set-cookie"}) {
440	# parse NAME=VALUE	644	# parse NAME=VALUE
441	my @kv;	645	my @kv;
442		646
443	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	647	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
444	my $name = $1;	648	my $name = $1;
445	my $value = $3;	649	my $value = $3;
446		650
447	unless ($value) {	651	unless ($value) {
448	$value = $2;	652	$value = $2;
449	$value =~ s/\\(.)/$1/gs;	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};
		671
		672	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		673
		674	next if $cdom =~ /\.$/;
		675
		676	# this is not rfc-like and not netscape-like. go figure.
		677	my $ndots = $cdom =~ y/.//;
		678	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		679	} else {
		680	$cdom = $uhost;
		681	}
		682
		683	# store it
		684	$arg{cookie_jar}{version} = 1;
		685	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		686
		687	redo if /\G\s*,/gc;
		688	}
		689	}
		690
		691	if ($redirect && exists $hdr{location}) {
		692	# we ignore any errors, as it is very common to receive
		693	# Content-Length != 0 but no actual body
		694	# we also access %hdr, as $_[1] might be an erro
		695	http_request (
		696	$method => $hdr{location},
		697	%arg,
		698	recurse => $recurse - 1,
		699	Redirect => [$_[0], \%hdr],
		700	$cb);
		701	} else {
		702	$cb->($_[0], \%hdr);
		703	}
		704	};
		705
		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
		716	$finish->("", undef, undef, 1);
		717	} else {
		718	# body handling, many different code paths
		719	# - no body expected
		720	# - want_body_handle
		721	# - te chunked
		722	# - 2x length known (with or without on_body)
		723	# - 2x length not known (with or without on_body)
		724	if (!$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
		747	$_[0]->push_read (chunk => $len, sub {
		748	$on_body->($_[1], \%hdr)
		749	or return $finish->(undef, 598 => "Request cancelled by on_body");
		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	}
450	}	770	}
451		771
452	push @kv, $name => $value;	772	$finish->($body, undef, undef, 1);
453
454	last unless /\G\s*;/gc;
455	}	773	});
456
457	last unless @kv;
458
459	my $name = shift @kv;
460	my %kv = (value => shift @kv, @kv);
461
462	my $cdom;
463	my $cpath = (delete $kv{path}) \|\| "/";
464
465	if (exists $kv{domain}) {
466	$cdom = delete $kv{domain};
467
468	$cdom =~ s/^\.?/./; # make sure it starts with a "."
469
470	next if $cdom =~ /\.$/;
471
472	# this is not rfc-like and not netscape-like. go figure.
473	my $ndots = $cdom =~ y/.//;
474	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
475	} else {
476	$cdom = $uhost;
477	}
478
479	# store it
480	$arg{cookie_jar}{version} = 1;
481	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
482
483	redo if /\G\s*,/gc;
484	}	774	}
485	}	775	};
486		776
487	# microsoft and other shitheads don't give a shit for following standards,	777	$_[0]->push_read (line => $read_chunk);
488	# try to support some common forms of broken Location headers.
489	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
490	$_[1]{location} =~ s/^\.\/+//;
491		778
492	my $url = "$rscheme://$uhost:$uport";	779	} elsif ($arg{on_body}) {
		780	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
493		781
494	unless ($_[1]{location} =~ s/^\///) {
495	$url .= $upath;
496	$url =~ s/\/[^\/]*$//;
497	}
498
499	$_[1]{location} = "$url/$_[1]{location}";
500	}
501
502	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
503	# apparently, mozilla et al. just change POST to GET here
504	# more research is needed before we do the same
505	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
506	} elsif ($_[1]{Status} == 303 && $recurse) {
507	# even http/1.1 is unclear on how to mutate the method
508	$method = "GET" unless $method eq "HEAD";
509	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
510	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
511	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
512	} else {	782	if ($len) {
513	$cb->($_[0], $_[1]);	783	$_[0]->on_read (sub {
514	}	784	$len -= length $_[0]{rbuf};
515	};
516		785
517	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	786	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
518	$finish->(undef, \%hdr);	787	or return $finish->(undef, 598 => "Request cancelled by on_body");
519	} else {	788
520	if (exists $hdr{"content-length"}) {
521	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
522	# could cache persistent connection now
523	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
524	# but we don't, due to misdesigns, this is annoyingly complex
525	};	789	$len > 0
526		790	or $finish->("", undef, undef, 1);
527	$finish->($_[1], \%hdr);
528	});	791	});
529	} else {	792	} else {
530	# too bad, need to read until we get an error or EOF,	793	$_[0]->on_eof (sub {
531	# no way to detect winged data.	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	});
		800	}
		801	} else {
		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 {
532	$_[0]->on_error (sub {	811	$_[0]->on_error (sub {
		812	($! == Errno::EPIPE \|\| !$!)
533	$finish->($_[0]{rbuf}, \%hdr);	813	? $finish->(delete $_[0]{rbuf})
		814	: $finish->(undef, 599 => $_[2]);
534	});	815	});
535	$_[0]->on_eof (undef);
536	$_[0]->on_read (sub { });	816	$_[0]->on_read (sub { });
537	}	817	}
538	}	818	}
539	});	819	}
540	});	820	};
		821
		822	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
541	};	823	};
542		824
543	# now handle proxy-CONNECT method	825	# now handle proxy-CONNECT method
544	if ($proxy && $uscheme eq "https") {	826	if ($proxy && $uscheme eq "https") {
545	# oh dear, we have to wrap it into a connect request	827	# oh dear, we have to wrap it into a connect request
546		828
547	# maybe re-use $uauthority with patched port?	829	# maybe re-use $uauthority with patched port?
548	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	830	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
549	$state{handle}->push_read (line => $qr_nlnl, sub {	831	$state{handle}->push_read (line => $qr_nlnl, sub {
550	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	832	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
551	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));	833	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
552		834
553	if ($2 == 200) {	835	if ($2 == 200) {
554	$rpath = $upath;	836	$rpath = $upath;
555	&$handle_actual_request;	837	&$handle_actual_request;
556	} else {	838	} else {
557	%state = ();	839	%state = ();
558	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	840	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
559	}	841	}
560	});	842	});
561	} else {	843	} else {
562	&$handle_actual_request;	844	&$handle_actual_request;
563	}	845	}
564
565	}, sub {
566	$timeout
567	};	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 { $timeout });
		852
568	};	853	};
569		854
570	defined wantarray && AnyEvent::Util::guard { %state = () }	855	defined wantarray && AnyEvent::Util::guard { %state = () }
571	}	856	}
572		857
…		…
586	&http_request	871	&http_request
587	}	872	}
588		873
589	=back	874	=back
590		875
		876	=head2 DNS CACHING
		877
		878	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		879	the actual connection, which in turn uses AnyEvent::DNS to resolve
		880	hostnames. The latter is a simple stub resolver and does no caching
		881	on its own. If you want DNS caching, you currently have to provide
		882	your own default resolver (by storing a suitable resolver object in
		883	C<$AnyEvent::DNS::RESOLVER>).
		884
591	=head2 GLOBAL FUNCTIONS AND VARIABLES	885	=head2 GLOBAL FUNCTIONS AND VARIABLES
592		886
593	=over 4	887	=over 4
594		888
595	=item AnyEvent::HTTP::set_proxy "proxy-url"	889	=item AnyEvent::HTTP::set_proxy "proxy-url"
596		890
597	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
598	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.
599		906
600	=item $AnyEvent::HTTP::MAX_RECURSE	907	=item $AnyEvent::HTTP::MAX_RECURSE
601		908
602	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>).
603		910
604	=item $AnyEvent::HTTP::USERAGENT	911	=item $AnyEvent::HTTP::USERAGENT
605		912
606	The default value for the C<User-Agent> header (the default is	913	The default value for the C<User-Agent> header (the default is
607	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	914	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
608		915
609	=item $AnyEvent::HTTP::MAX_PERSISTENT	916	=item $AnyEvent::HTTP::MAX_PER_HOST
610		917
611	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.
612		921
613	Not implemented currently.	922	The default value for this is C<4>, and it is highly advisable to not
614		923	increase it.
615	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
616
617	The maximum time to cache a persistent connection, in seconds (default: 2).
618
619	Not implemented currently.
620		924
621	=item $AnyEvent::HTTP::ACTIVE	925	=item $AnyEvent::HTTP::ACTIVE
622		926
623	The number of active connections. This is not the number of currently	927	The number of active connections. This is not the number of currently
624	running requests, but the number of currently open and non-idle TCP	928	running requests, but the number of currently open and non-idle TCP
…		…
626		930
627	=back	931	=back
628		932
629	=cut	933	=cut
630		934
		935	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		936	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		937
		938	sub format_date($) {
		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, $_, $y);
		972	}
		973	}
		974
		975	undef
		976	}
		977
631	sub set_proxy($) {	978	sub set_proxy($) {
		979	if (length $_[0]) {
632	$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	}
633	}	986	}
634		987
635	# initialise proxy from environment	988	# initialise proxy from environment
		989	eval {
636	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	};
637		1048
638	=head1 SEE ALSO	1049	=head1 SEE ALSO
639		1050
640	L<AnyEvent>.	1051	L<AnyEvent>.
641		1052
642	=head1 AUTHOR	1053	=head1 AUTHOR
643		1054
644	Marc Lehmann <schmorp@schmorp.de>	1055	Marc Lehmann <schmorp@schmorp.de>
645	http://home.schmorp.de/	1056	http://home.schmorp.de/
646		1057
		1058	With many thanks to Дмитрий Шалашов, who provided countless
		1059	testcases and bugreports.
		1060
647	=cut	1061	=cut
648		1062
649	1	1063	1
650		1064

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs. Revision 1.68 by root, Fri Dec 31 19:22:18 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs.
Revision 1.68 by root, Fri Dec 31 19:22:18 2010 UTC