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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.42 by root, Mon Jul 6 00:08:16 2009 UTC vs.
Revision 1.70 by root, Fri Dec 31 20:31:47 2010 UTC

…		…
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Errno ();	44	use Errno ();
45		45
46	use AnyEvent 4.452 ();	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 = '1.12';	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 $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$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 body data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if an error occured), and a hash-ref with response headers as	99	(or C<undef> if an error occured), and a hash-ref with response headers
101	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,
…		…
136	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
137	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
138		152
139	=item headers => hashref	153	=item headers => hashref
140		154
141	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
142	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
143	and will provide defaults for C<User-Agent:> and C<Referer:>.	157	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		158	(this can be suppressed by using C<undef> for these headers in which case
		159	they won't be sent at all).
144		160
145	=item timeout => $seconds	161	=item timeout => $seconds
146		162
147	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
148	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
149		168
150	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
151		170
152	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
153	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
154		173
155	C<$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
156	HTTPS.	175	HTTPS.
157		176
158	=item body => $string	177	=item body => $string
159		178
160	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
161	this module might offer more options).	180	this module might offer more options).
162		181
163	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
164		183
165	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
166	based on the original netscape specification.	185	based on the original netscape specification.
167		186
168	The C<$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
169	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
170	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
171	recommended, as expiry times are currently being ignored.	190	recommended, as session-only cookies might survive longer than expected.
172		191
173	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not meant to be complete. If
174	meant to be complete. If you want complete cookie management you have to	193	you want complete cookie management you have to do that on your
175	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites
176	cookie-using sites working. Cookies are a privacy disaster, do not use	195	working. Cookies are a privacy disaster, do not use them unless required
177	them unless required to.	196	to.
		197
		198	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		199	headers will be set and handled by this module, otherwise they will be
		200	left untouched.
178		201
179	=item tls_ctx => $scheme \| $tls_ctx	202	=item tls_ctx => $scheme \| $tls_ctx
180		203
181	Specifies the AnyEvent::TLS context to be used for https connections. This	204	Specifies the AnyEvent::TLS context to be used for https connections. This
182	parameter follows the same rules as the C<tls_ctx> parameter to	205	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
186	verification) TLS context.	209	verification) TLS context.
187		210
188	The default for this option is C<low>, which could be interpreted as "give	211	The default for this option is C<low>, which could be interpreted as "give
189	me the page, no matter what".	212	me the page, no matter what".
190		213
		214	=item on_prepare => $callback->($fh)
		215
		216	In rare cases you need to "tune" the socket before it is used to
		217	connect (for exmaple, to bind it on a given IP address). This parameter
		218	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		219	and behaves exactly the same way (e.g. it has to provide a
		220	timeout). See the description for the C<$prepare_cb> argument of
		221	C<AnyEvent::Socket::tcp_connect> for details.
		222
		223	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		224
		225	In even rarer cases you want total control over how AnyEvent::HTTP
		226	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		227	to do this, but you can provide your own C<tcp_connect> function -
		228	obviously, it has to follow the same calling conventions, except that it
		229	may always return a connection guard object.
		230
		231	There are probably lots of weird uses for this function, starting from
		232	tracing the hosts C<http_request> actually tries to connect, to (inexact
		233	but fast) host => IP address caching or even socks protocol support.
		234
191	=item on_header => $callback->($headers)	235	=item on_header => $callback->($headers)
192		236
193	When specified, this callback will be called with the header hash as soon	237	When specified, this callback will be called with the header hash as soon
194	as headers have been successfully received from the remote server (not on	238	as headers have been successfully received from the remote server (not on
195	locally-generated errors).	239	locally-generated errors).
…		…
200		244
201	This callback is useful, among other things, to quickly reject unwanted	245	This callback is useful, among other things, to quickly reject unwanted
202	content, which, if it is supposed to be rare, can be faster than first	246	content, which, if it is supposed to be rare, can be faster than first
203	doing a C<HEAD> request.	247	doing a C<HEAD> request.
204		248
		249	The downside is that cancelling the request makes it impossible to re-use
		250	the connection. Also, the C<on_header> callback will not receive any
		251	trailer (headers sent after the response body).
		252
205	Example: cancel the request unless the content-type is "text/html".	253	Example: cancel the request unless the content-type is "text/html".
206		254
207	on_header => sub {	255	on_header => sub {
208	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/	256	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
209	},	257	},
…		…
216		264
217	It has to return either true (in which case AnyEvent::HTTP will continue),	265	It has to return either true (in which case AnyEvent::HTTP will continue),
218	or false, in which case AnyEvent::HTTP will cancel the download (and call	266	or false, in which case AnyEvent::HTTP will cancel the download (and call
219	the completion callback with an error code of C<598>).	267	the completion callback with an error code of C<598>).
220		268
		269	The downside to cancelling the request is that it makes it impossible to
		270	re-use the connection.
		271
221	This callback is useful when the data is too large to be held in memory	272	This callback is useful when the data is too large to be held in memory
222	(so the callback writes it to a file) or when only some information should	273	(so the callback writes it to a file) or when only some information should
223	be extracted, or when the body should be processed incrementally.	274	be extracted, or when the body should be processed incrementally.
224		275
225	It is usually preferred over doing your own body handling via	276	It is usually preferred over doing your own body handling via
226	C<want_body_handle>.	277	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		278	only used to create a connection, C<want_body_handle> is the better
		279	alternative, as it allows you to install your own event handler, reducing
		280	resource usage.
227		281
228	=item want_body_handle => $enable	282	=item want_body_handle => $enable
229		283
230	When enabled (default is disabled), the behaviour of AnyEvent::HTTP	284	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
231	changes considerably: after parsing the headers, and instead of	285	changes considerably: after parsing the headers, and instead of
…		…
243	This is useful with some push-type services, where, after the initial	297	This is useful with some push-type services, where, after the initial
244	headers, an interactive protocol is used (typical example would be the	298	headers, an interactive protocol is used (typical example would be the
245	push-style twitter API which starts a JSON/XML stream).	299	push-style twitter API which starts a JSON/XML stream).
246		300
247	If you think you need this, first have a look at C<on_body>, to see if	301	If you think you need this, first have a look at C<on_body>, to see if
248	that doesn'T solve your problem in a better way.	302	that doesn't solve your problem in a better way.
249		303
250	=back	304	=back
251		305
252	Example: make a simple HTTP GET request for http://www.nethype.de/	306	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		307	the response body.
253		308
254	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
255	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
256	print "$body\n";	311	print "$body\n";
257	};	312	};
258		313
259	Example: make a HTTP HEAD request on https://www.google.com/, use a	314	Example: do a HTTP HEAD request on https://www.google.com/, use a
260	timeout of 30 seconds.	315	timeout of 30 seconds.
261		316
262	http_request	317	http_request
263	GET => "https://www.google.com",	318	GET => "https://www.google.com",
264	timeout => 30,	319	timeout => 30,
…		…
267	use Data::Dumper;	322	use Data::Dumper;
268	print Dumper $hdr;	323	print Dumper $hdr;
269	}	324	}
270	;	325	;
271		326
272	Example: make another simple HTTP GET request, but immediately try to	327	Example: do another simple HTTP GET request, but immediately try to
273	cancel it.	328	cancel it.
274		329
275	my $request = http_request GET => "http://www.nethype.de/", sub {	330	my $request = http_request GET => "http://www.nethype.de/", sub {
276	my ($body, $hdr) = @_;	331	my ($body, $hdr) = @_;
277	print "$body\n";	332	print "$body\n";
…		…
309	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
310		365
311	_slot_schedule $_[0];	366	_slot_schedule $_[0];
312	}	367	}
313		368
314	our $qr_nl = qr<\015?\012>;	369	# continue to parse $_ for headers and place them into the arg
315	our $qr_nlnl = qr<\015?\012\015?\012>;	370	sub parse_hdr() {
		371	my %hdr;
		372
		373	# things seen, not parsed:
		374	# p3pP="NON CUR OTPi OUR NOR UNI"
		375
		376	$hdr{lc $1} .= ",$2"
		377	while /\G
		378	([^:\000-\037]*):
		379	[\011\040]*
		380	((?: [^\012]+ \| \012[\011\040] )*)
		381	\012
		382	/gxc;
		383
		384	/\G$/
		385	or return;
		386
		387	# remove the "," prefix we added to all headers above
		388	substr $_, 0, 1, ""
		389	for values %hdr;
		390
		391	\%hdr
		392	}
		393
		394	our $qr_nlnl = qr{(?<![^\012])\015?\012};
316		395
317	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	396	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
318	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	397	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
319		398
320	sub http_request($$@) {	399	sub http_request($$@) {
…		…
332	while (my ($k, $v) = each %$hdr) {	411	while (my ($k, $v) = each %$hdr) {
333	$hdr{lc $k} = $v;	412	$hdr{lc $k} = $v;
334	}	413	}
335	}	414	}
336		415
		416	# pseudo headers for all subsequent responses
		417	my @pseudo = (URL => $url);
		418	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		419
337	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	420	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
338		421
339	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	422	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
340	if $recurse < 0;	423	if $recurse < 0;
341		424
342	my $proxy = $arg{proxy} \|\| $PROXY;	425	my $proxy = $arg{proxy} \|\| $PROXY;
343	my $timeout = $arg{timeout} \|\| $TIMEOUT;	426	my $timeout = $arg{timeout} \|\| $TIMEOUT;
344		427
345	my ($uscheme, $uauthority, $upath, $query, $fragment) =	428	my ($uscheme, $uauthority, $upath, $query, $fragment) =
346	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	429	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
347		430
348	$uscheme = lc $uscheme;	431	$uscheme = lc $uscheme;
349		432
350	my $uport = $uscheme eq "http" ? 80	433	my $uport = $uscheme eq "http" ? 80
351	: $uscheme eq "https" ? 443	434	: $uscheme eq "https" ? 443
352	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });	435	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
353		436
354	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	437	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
355	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	438	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
356		439
357	my $uhost = $1;	440	my $uhost = $1;
358	$uport = $2 if defined $2;	441	$uport = $2 if defined $2;
359		442
		443	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		444	unless exists $hdr{host};
		445
360	$uhost =~ s/^\[(.*)\]$/$1/;	446	$uhost =~ s/^\[(.*)\]$/$1/;
361	$upath .= "?$query" if length $query;	447	$upath .= $query if length $query;
362		448
363	$upath =~ s%^/?%/%;	449	$upath =~ s%^/?%/%;
364		450
365	# cookie processing	451	# cookie processing
366	if (my $jar = $arg{cookie_jar}) {	452	if (my $jar = $arg{cookie_jar}) {
367	%$jar = () if $jar->{version} != 1;	453	%$jar = () if $jar->{version} != 1;
368		454
369	my @cookie;	455	my @cookie;
370		456
371	while (my ($chost, $v) = each %$jar) {	457	while (my ($chost, $paths) = each %$jar) {
372	if ($chost =~ /^\./) {	458	if ($chost =~ /^\./) {
373	next unless $chost eq substr $uhost, -length $chost;	459	next unless $chost eq substr $uhost, -length $chost;
374	} elsif ($chost =~ /\./) {	460	} elsif ($chost =~ /\./) {
375	next unless $chost eq $uhost;	461	next unless $chost eq $uhost;
376	} else {	462	} else {
377	next;	463	next;
378	}	464	}
379		465
380	while (my ($cpath, $v) = each %$v) {	466	while (my ($cpath, $cookies) = each %$paths) {
381	next unless $cpath eq substr $upath, 0, length $cpath;	467	next unless $cpath eq substr $upath, 0, length $cpath;
382		468
383	while (my ($k, $v) = each %$v) {	469	while (my ($cookie, $kv) = each %$cookies) {
384	next if $uscheme ne "https" && exists $v->{secure};	470	next if $uscheme ne "https" && exists $kv->{secure};
		471
		472	if (exists $kv->{expires}) {
		473	if (AE::now > parse_date ($kv->{expires})) {
		474	delete $cookies->{$cookie};
		475	next;
		476	}
		477	}
		478
385	my $value = $v->{value};	479	my $value = $kv->{value};
386	$value =~ s/([\\"])/\\$1/g;	480	$value =~ s/([\\"])/\\$1/g;
387	push @cookie, "$k=\"$value\"";	481	push @cookie, "$cookie=\"$value\"";
388	}	482	}
389	}	483	}
390	}	484	}
391		485
392	$hdr{cookie} = join "; ", @cookie	486	$hdr{cookie} = join "; ", @cookie
…		…
396	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	490	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
397		491
398	if ($proxy) {	492	if ($proxy) {
399	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	493	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
400		494
		495	$rscheme = "http" unless defined $rscheme;
		496
401	# don't support https requests over https-proxy transport,	497	# don't support https requests over https-proxy transport,
402	# can't be done with tls as spec'ed, unless you double-encrypt.	498	# can't be done with tls as spec'ed, unless you double-encrypt.
403	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	499	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
404	} else {	500	} else {
405	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	501	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
406	}	502	}
407		503
408	$hdr{"user-agent"} \|\|= $USERAGENT;	504	# leave out fragment and query string, just a heuristic
409	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic	505	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		506	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
410		507
411	$hdr{host} = "$uhost:$uport";
412	$hdr{"content-length"} = length $arg{body};	508	$hdr{"content-length"} = length $arg{body}
		509	if length $arg{body} \|\| $method ne "GET";
		510
		511	$hdr{connection} = "close TE"; #1.1
		512	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
413		513
414	my %state = (connect_guard => 1);	514	my %state = (connect_guard => 1);
415		515
416	_get_slot $uhost, sub {	516	_get_slot $uhost, sub {
417	$state{slot_guard} = shift;	517	$state{slot_guard} = shift;
418		518
419	return unless $state{connect_guard};	519	return unless $state{connect_guard};
420		520
421	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	521	my $connect_cb = sub {
422	$state{fh} = shift	522	$state{fh} = shift
423	or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url }));	523	or do {
		524	my $err = "$!";
		525	%state = ();
		526	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		527	};
		528
424	pop; # free memory, save a tree	529	pop; # free memory, save a tree
425		530
426	return unless delete $state{connect_guard};	531	return unless delete $state{connect_guard};
427		532
428	# get handle	533	# get handle
429	$state{handle} = new AnyEvent::Handle	534	$state{handle} = new AnyEvent::Handle
430	fh => $state{fh},	535	fh => $state{fh},
		536	peername => $rhost,
		537	tls_ctx => $arg{tls_ctx},
		538	# these need to be reconfigured on keepalive handles
431	timeout => $timeout,	539	timeout => $timeout,
432	peername => $rhost,	540	on_error => sub {
433	tls_ctx => $arg{tls_ctx};	541	%state = ();
		542	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		543	},
		544	on_eof => sub {
		545	%state = ();
		546	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		547	},
		548	;
434		549
435	# limit the number of persistent connections	550	# limit the number of persistent connections
436	# keepalive not yet supported	551	# keepalive not yet supported
437	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	552	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
438	++$KA_COUNT{$_[1]};	553	# ++$KA_COUNT{$_[1]};
439	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	554	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
440	--$KA_COUNT{$_[1]}	555	# --$KA_COUNT{$_[1]}
441	};	556	# };
442	$hdr{connection} = "keep-alive";	557	# $hdr{connection} = "keep-alive";
443	} else {
444	delete $hdr{connection};
445	}	558	# }
446
447	# (re-)configure handle
448	$state{handle}->on_error (sub {
449	%state = ();
450	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
451	});
452	$state{handle}->on_eof (sub {
453	%state = ();
454	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
455	});
456		559
457	$state{handle}->starttls ("connect") if $rscheme eq "https";	560	$state{handle}->starttls ("connect") if $rscheme eq "https";
458		561
459	# handle actual, non-tunneled, request	562	# handle actual, non-tunneled, request
460	my $handle_actual_request = sub {	563	my $handle_actual_request = sub {
461	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	564	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
462		565
463	# send request	566	# send request
464	$state{handle}->push_write (	567	$state{handle}->push_write (
465	"$method $rpath HTTP/1.0\015\012"	568	"$method $rpath HTTP/1.1\015\012"
466	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	569	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
467	. "\015\012"	570	. "\015\012"
468	. (delete $arg{body})	571	. (delete $arg{body})
469	);	572	);
470		573
		574	# return if error occured during push_write()
		575	return unless %state;
		576
471	%hdr = (); # reduce memory usage, save a kitten	577	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
472		578
473	# status line	579	# status line and headers
474	$state{handle}->push_read (line => $qr_nl, sub {	580	$state{read_response} = sub {
475	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
476	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
477
478	my %hdr = ( # response headers
479	HTTPVersion => ",$1",
480	Status => ",$2",
481	Reason => ",$3",
482	URL => ",$url"
483	);
484
485	# headers, could be optimized a bit
486	$state{handle}->unshift_read (line => $qr_nlnl, sub {
487	for ("$_[1]\012") {	581	for ("$_[1]") {
488	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	582	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
489		583
490	# things seen, not parsed:	584	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
491	# p3pP="NON CUR OTPi OUR NOR UNI"	585	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
492		586
493	$hdr{lc $1} .= ",$2"	587	# 100 Continue handling
494	while /\G	588	# should not happen as we don't send expect: 100-continue,
495	([^:\000-\037]+):	589	# but we handle it just in case.
496	[\011\040]*	590	# since we send the request body regardless, if we get an error
497	((?: [^\012]+ \| \012[\011\040] )*)	591	# we are out of-sync, which we currently do NOT handle correctly.
498	\012	592	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
499	/gxc;	593	if $2 eq 100;
500		594
		595	push @pseudo,
		596	HTTPVersion => $1,
		597	Status => $2,
		598	Reason => $3,
501	/\G$/	599	;
		600
		601	my $hdr = parse_hdr
502	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));	602	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		603
		604	%hdr = (%$hdr, @pseudo);
		605	}
		606
		607	# redirect handling
		608	# microsoft and other shitheads don't give a shit for following standards,
		609	# try to support some common forms of broken Location headers.
		610	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		611	$hdr{location} =~ s/^\.\/+//;
		612
		613	my $url = "$rscheme://$uhost:$uport";
		614
		615	unless ($hdr{location} =~ s/^\///) {
		616	$url .= $upath;
		617	$url =~ s/\/[^\/]*$//;
503	}	618	}
504		619
505	substr $_, 0, 1, ""
506	for values %hdr;
507
508	# redirect handling
509	# microsoft and other shitheads don't give a shit for following standards,
510	# try to support some common forms of broken Location headers.
511	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
512	$hdr{location} =~ s/^\.\/+//;
513
514	my $url = "$rscheme://$uhost:$uport";
515
516	unless ($hdr{location} =~ s/^\///) {
517	$url .= $upath;
518	$url =~ s/\/[^\/]*$//;
519	}
520
521	$hdr{location} = "$url/$hdr{location}";	620	$hdr{location} = "$url/$hdr{location}";
		621	}
		622
		623	my $redirect;
		624
		625	if ($recurse) {
		626	my $status = $hdr{Status};
		627
		628	# industry standard is to redirect POST as GET for
		629	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		630	# also, the UA should ask the user for 301 and 307 and POST,
		631	# industry standard seems to be to simply follow.
		632	# we go with the industry standard.
		633	if ($status == 301 or $status == 302 or $status == 303) {
		634	# HTTP/1.1 is unclear on how to mutate the method
		635	$method = "GET" unless $method eq "HEAD";
		636	$redirect = 1;
		637	} elsif ($status == 307) {
		638	$redirect = 1;
522	}	639	}
		640	}
523		641
		642	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
524	my $redirect;	643	my $keepalive = pop;
525		644
		645	$state{handle}->destroy if $state{handle};
		646	%state = ();
		647
		648	if (defined $_[1]) {
		649	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		650	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		651	}
		652
		653	# set-cookie processing
526	if ($recurse) {	654	if ($arg{cookie_jar}) {
527	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {	655	for ($hdr{"set-cookie"}) {
528	# apparently, mozilla et al. just change POST to GET here	656	# parse NAME=VALUE
529	# more research is needed before we do the same	657	my @kv;
		658
		659	while (
		660	m{
		661	\G\s*
		662	(?:
		663	expires \s=\s ([A-Z][a-z][a-z],\ [^,;]+)
		664	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )
		665	)
		666	}gcxsi
		667	) {
		668	my $name = $2;
		669	my $value = $4;
		670
		671	unless (defined $name) {
		672	# expires
		673	$name = "expires";
		674	$value = $1;
		675	} elsif (!defined $value) {
		676	# quoted
		677	$value = $3;
		678	$value =~ s/\\(.)/$1/gs;
		679	}
		680
		681	push @kv, lc $name, $value;
		682
		683	last unless /\G\s*;/gc;
		684	}
		685
		686	last unless @kv;
		687
		688	my $name = shift @kv;
		689	my %kv = (value => shift @kv, @kv);
		690
		691	$kv{expires} \|\|= format_date (AE::now + $kv{"max-age"})
		692	if exists $kv{"max-age"};
		693
		694	my $cdom;
		695	my $cpath = (delete $kv{path}) \|\| "/";
		696
		697	if (exists $kv{domain}) {
		698	$cdom = delete $kv{domain};
		699
		700	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		701
		702	next if $cdom =~ /\.$/;
		703
		704	# this is not rfc-like and not netscape-like. go figure.
		705	my $ndots = $cdom =~ y/.//;
		706	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		707	} else {
		708	$cdom = $uhost;
		709	}
		710
530	$redirect = 1;	711	# store it
531	} elsif ($hdr{Status} == 303) {	712	$arg{cookie_jar}{version} = 1;
532	# even http/1.1 is unclear on how to mutate the method	713	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
533	$method = "GET" unless $method eq "HEAD";	714
534	$redirect = 1;	715	redo if /\G\s*,/gc;
535	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
536	$redirect = 1;
537	}	716	}
538	}	717	}
539		718
540	my $finish = sub {	719	if ($redirect && exists $hdr{location}) {
541	$state{handle}->destroy if $state{handle};
542	%state = ();
543
544	# set-cookie processing
545	if ($arg{cookie_jar}) {
546	for ($_[1]{"set-cookie"}) {
547	# parse NAME=VALUE
548	my @kv;
549
550	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
551	my $name = $1;
552	my $value = $3;
553
554	unless ($value) {
555	$value = $2;
556	$value =~ s/\\(.)/$1/gs;
557	}
558
559	push @kv, $name => $value;
560
561	last unless /\G\s*;/gc;
562	}
563
564	last unless @kv;
565
566	my $name = shift @kv;
567	my %kv = (value => shift @kv, @kv);
568
569	my $cdom;
570	my $cpath = (delete $kv{path}) \|\| "/";
571
572	if (exists $kv{domain}) {
573	$cdom = delete $kv{domain};
574
575	$cdom =~ s/^\.?/./; # make sure it starts with a "."
576
577	next if $cdom =~ /\.$/;
578
579	# this is not rfc-like and not netscape-like. go figure.
580	my $ndots = $cdom =~ y/.//;
581	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
582	} else {
583	$cdom = $uhost;
584	}
585
586	# store it
587	$arg{cookie_jar}{version} = 1;
588	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
589
590	redo if /\G\s*,/gc;
591	}
592	}
593
594	if ($redirect) {
595	# we ignore any errors, as it is very common to receive	720	# we ignore any errors, as it is very common to receive
596	# Content-Length != 0 but no actual body	721	# Content-Length != 0 but no actual body
597	# we also access %hdr, as $_[1] might be an erro	722	# we also access %hdr, as $_[1] might be an erro
598	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);	723	http_request (
599	} else {	724	$method => $hdr{location},
600	$cb->($_[0], $_[1]);
601	}	725	%arg,
		726	recurse => $recurse - 1,
		727	Redirect => [$_[0], \%hdr],
602	};	728	$cb);
603
604	my $len = $hdr{"content-length"};
605
606	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
607	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
608	} elsif (
609	$hdr{Status} =~ /^(?:1..\|[23]04)$/
610	or $method eq "HEAD"
611	or (defined $len && !$len)
612	) {
613	# no body
614	$finish->("", \%hdr);
615	} else {	729	} else {
		730	$cb->($_[0], \%hdr);
		731	}
		732	};
		733
		734	my $len = $hdr{"content-length"};
		735
		736	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		737	$finish->(undef, 598 => "Request cancelled by on_header");
		738	} elsif (
		739	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		740	or $method eq "HEAD"
		741	or (defined $len && !$len)
		742	) {
		743	# no body
		744	$finish->("", undef, undef, 1);
		745	} else {
616	# body handling, four different code paths	746	# body handling, many different code paths
617	# for want_body_handle, on_body (2x), normal (2x)	747	# - no body expected
618	# we might read too much here, but it does not matter yet (no pers. connections)	748	# - want_body_handle
		749	# - te chunked
		750	# - 2x length known (with or without on_body)
		751	# - 2x length not known (with or without on_body)
619	if (!$redirect && $arg{want_body_handle}) {	752	if (!$redirect && $arg{want_body_handle}) {
620	$_[0]->on_eof (undef);	753	$_[0]->on_eof (undef);
621	$_[0]->on_error (undef);	754	$_[0]->on_error (undef);
622	$_[0]->on_read (undef);	755	$_[0]->on_read (undef);
623		756
624	$finish->(delete $state{handle}, \%hdr);	757	$finish->(delete $state{handle});
625		758
626	} elsif ($arg{on_body}) {	759	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		760	my $cl = 0;
		761	my $body = undef;
		762	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		763
627	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });	764	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		765
		766	my $read_chunk; $read_chunk = sub {
		767	$_[1] =~ /^([0-9a-fA-F]+)/
		768	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		769
		770	my $len = hex $1;
		771
628	if ($len) {	772	if ($len) {
629	$_[0]->on_eof (undef);	773	$cl += $len;
		774
		775	$_[0]->push_read (chunk => $len, sub {
		776	$on_body->($_[1], \%hdr)
		777	or return $finish->(undef, 598 => "Request cancelled by on_body");
		778
630	$_[0]->on_read (sub {	779	$_[0]->push_read (line => sub {
631	$len -= length $_[0]{rbuf};	780	length $_[1]
632		781	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
633	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	782	$_[0]->push_read (line => $read_chunk);
634	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
635
636	$len > 0	783	});
637	or $finish->("", \%hdr);
638	});	784	});
639	} else {	785	} else {
640	$_[0]->on_eof (sub {	786	$hdr{"content-length"} \|\|= $cl;
641	$finish->("", \%hdr);	787
		788	$_[0]->push_read (line => $qr_nlnl, sub {
		789	if (length $_[1]) {
		790	for ("$_[1]") {
		791	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		792
		793	my $hdr = parse_hdr
		794	or return $finish->(undef, 599 => "Garbled response trailers");
		795
		796	%hdr = (%hdr, %$hdr);
		797	}
642	});	798	}
643	$_[0]->on_read (sub {	799
644	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	800	$finish->($body, undef, undef, 1);
645	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
646	});	801	});
647	}	802	}
		803	};
		804
		805	$_[0]->push_read (line => $read_chunk);
		806
		807	} elsif ($arg{on_body}) {
		808	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		809
		810	if ($len) {
		811	$_[0]->on_read (sub {
		812	$len -= length $_[0]{rbuf};
		813
		814	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		815	or return $finish->(undef, 598 => "Request cancelled by on_body");
		816
		817	$len > 0
		818	or $finish->("", undef, undef, 1);
		819	});
648	} else {	820	} else {
649	$_[0]->on_eof (undef);	821	$_[0]->on_eof (sub {
650		822	$finish->("");
651	if ($len) {	823	});
652	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
653	$_[0]->on_read (sub {	824	$_[0]->on_read (sub {
		825	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		826	or $finish->(undef, 598 => "Request cancelled by on_body");
		827	});
		828	}
		829	} else {
		830	$_[0]->on_eof (undef);
		831
		832	if ($len) {
		833	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		834	$_[0]->on_read (sub {
654	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)	835	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
655	if $len <= length $_[0]{rbuf};	836	if $len <= length $_[0]{rbuf};
656	});	837	});
657	} else {	838	} else {
658	$_[0]->on_error (sub {	839	$_[0]->on_error (sub {
659	$! == Errno::EPIPE	840	($! == Errno::EPIPE \|\| !$!)
660	? $finish->(delete $_[0]{rbuf}, \%hdr)	841	? $finish->(delete $_[0]{rbuf})
661	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });	842	: $finish->(undef, 599 => $_[2]);
662	});	843	});
663	$_[0]->on_read (sub { });	844	$_[0]->on_read (sub { });
664	}
665	}	845	}
666	}	846	}
667	});	847	}
668	});	848	};
		849
		850	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
669	};	851	};
670		852
671	# now handle proxy-CONNECT method	853	# now handle proxy-CONNECT method
672	if ($proxy && $uscheme eq "https") {	854	if ($proxy && $uscheme eq "https") {
673	# oh dear, we have to wrap it into a connect request	855	# oh dear, we have to wrap it into a connect request
674		856
675	# maybe re-use $uauthority with patched port?	857	# maybe re-use $uauthority with patched port?
676	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	858	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
677	$state{handle}->push_read (line => $qr_nlnl, sub {	859	$state{handle}->push_read (line => $qr_nlnl, sub {
678	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	860	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
679	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));	861	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
680		862
681	if ($2 == 200) {	863	if ($2 == 200) {
682	$rpath = $upath;	864	$rpath = $upath;
683	&$handle_actual_request;	865	&$handle_actual_request;
684	} else {	866	} else {
685	%state = ();	867	%state = ();
686	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	868	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
687	}	869	}
688	});	870	});
689	} else {	871	} else {
690	&$handle_actual_request;	872	&$handle_actual_request;
691	}	873	}
692
693	}, sub {
694	$timeout
695	};	874	};
		875
		876	my $tcp_connect = $arg{tcp_connect}
		877	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		878
		879	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		880
696	};	881	};
697		882
698	defined wantarray && AnyEvent::Util::guard { %state = () }	883	defined wantarray && AnyEvent::Util::guard { %state = () }
699	}	884	}
700		885
…		…
714	&http_request	899	&http_request
715	}	900	}
716		901
717	=back	902	=back
718		903
		904	=head2 DNS CACHING
		905
		906	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		907	the actual connection, which in turn uses AnyEvent::DNS to resolve
		908	hostnames. The latter is a simple stub resolver and does no caching
		909	on its own. If you want DNS caching, you currently have to provide
		910	your own default resolver (by storing a suitable resolver object in
		911	C<$AnyEvent::DNS::RESOLVER>).
		912
719	=head2 GLOBAL FUNCTIONS AND VARIABLES	913	=head2 GLOBAL FUNCTIONS AND VARIABLES
720		914
721	=over 4	915	=over 4
722		916
723	=item AnyEvent::HTTP::set_proxy "proxy-url"	917	=item AnyEvent::HTTP::set_proxy "proxy-url"
724		918
725	Sets the default proxy server to use. The proxy-url must begin with a	919	Sets the default proxy server to use. The proxy-url must begin with a
726	string of the form C<http://host:port> (optionally C<https:...>).	920	string of the form C<http://host:port> (optionally C<https:...>), croaks
		921	otherwise.
		922
		923	To clear an already-set proxy, use C<undef>.
		924
		925	=item $date = AnyEvent::HTTP::format_date $timestamp
		926
		927	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		928	Date (RFC 2616).
		929
		930	=item $timestamp = AnyEvent::HTTP::parse_date $date
		931
		932	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and
		933	returns the corresponding POSIX timestamp, or C<undef> if the date cannot
		934	be parsed.
727		935
728	=item $AnyEvent::HTTP::MAX_RECURSE	936	=item $AnyEvent::HTTP::MAX_RECURSE
729		937
730	The default value for the C<recurse> request parameter (default: C<10>).	938	The default value for the C<recurse> request parameter (default: C<10>).
731		939
732	=item $AnyEvent::HTTP::USERAGENT	940	=item $AnyEvent::HTTP::USERAGENT
733		941
734	The default value for the C<User-Agent> header (the default is	942	The default value for the C<User-Agent> header (the default is
735	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	943	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
736		944
737	=item $AnyEvent::HTTP::MAX_PERSISTENT	945	=item $AnyEvent::HTTP::MAX_PER_HOST
738		946
739	The maximum number of persistent connections to keep open (default: 8).	947	The maximum number of concurrent connections to the same host (identified
		948	by the hostname). If the limit is exceeded, then the additional requests
		949	are queued until previous connections are closed.
740		950
741	Not implemented currently.	951	The default value for this is C<4>, and it is highly advisable to not
742		952	increase it.
743	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
744
745	The maximum time to cache a persistent connection, in seconds (default: 2).
746
747	Not implemented currently.
748		953
749	=item $AnyEvent::HTTP::ACTIVE	954	=item $AnyEvent::HTTP::ACTIVE
750		955
751	The number of active connections. This is not the number of currently	956	The number of active connections. This is not the number of currently
752	running requests, but the number of currently open and non-idle TCP	957	running requests, but the number of currently open and non-idle TCP
…		…
754		959
755	=back	960	=back
756		961
757	=cut	962	=cut
758		963
		964	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		965	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		966
		967	sub format_date($) {
		968	my ($time) = @_;
		969
		970	# RFC 822/1123 format
		971	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		972
		973	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		974	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		975	$H, $M, $S;
		976	}
		977
		978	sub parse_date($) {
		979	my ($date) = @_;
		980
		981	my ($d, $m, $y, $H, $M, $S);
		982
		983	if ($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$/) {
		984	# RFC 822/1123, required by RFC 2616 (with " ")
		985	# cookie dates (with "-")
		986
		987	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		988
		989	} elsif ($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$/) {
		990	# RFC 850
		991	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		992
		993	} elsif ($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])$/) {
		994	# ISO C's asctime
		995	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		996	}
		997	# other formats fail in the loop below
		998
		999	for (0..11) {
		1000	if ($m eq $month[$_]) {
		1001	require Time::Local;
		1002	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1003	}
		1004	}
		1005
		1006	undef
		1007	}
		1008
759	sub set_proxy($) {	1009	sub set_proxy($) {
		1010	if (length $_[0]) {
760	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1011	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1012	or Carp::croak "$_[0]: invalid proxy URL";
		1013	$PROXY = [$2, $3 \|\| 3128, $1]
		1014	} else {
		1015	undef $PROXY;
		1016	}
761	}	1017	}
762		1018
763	# initialise proxy from environment	1019	# initialise proxy from environment
		1020	eval {
764	set_proxy $ENV{http_proxy};	1021	set_proxy $ENV{http_proxy};
		1022	};
		1023
		1024	=head2 SOCKS PROXIES
		1025
		1026	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1027	compile your perl to support socks, or use an external program such as
		1028	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1029	transparently.
		1030
		1031	Alternatively, for AnyEvent::HTTP only, you can use your own
		1032	C<tcp_connect> function that does the proxy handshake - here is an example
		1033	that works with socks4a proxies:
		1034
		1035	use Errno;
		1036	use AnyEvent::Util;
		1037	use AnyEvent::Socket;
		1038	use AnyEvent::Handle;
		1039
		1040	# host, port and username of/for your socks4a proxy
		1041	my $socks_host = "10.0.0.23";
		1042	my $socks_port = 9050;
		1043	my $socks_user = "";
		1044
		1045	sub socks4a_connect {
		1046	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1047
		1048	my $hdl = new AnyEvent::Handle
		1049	connect => [$socks_host, $socks_port],
		1050	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1051	on_error => sub { $connect_cb->() },
		1052	;
		1053
		1054	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1055
		1056	$hdl->push_read (chunk => 8, sub {
		1057	my ($hdl, $chunk) = @_;
		1058	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1059
		1060	if ($status == 0x5a) {
		1061	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1062	} else {
		1063	$! = Errno::ENXIO; $connect_cb->();
		1064	}
		1065	});
		1066
		1067	$hdl
		1068	}
		1069
		1070	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1071	possibly after switching off other proxy types:
		1072
		1073	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1074
		1075	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1076	my ($data, $headers) = @_;
		1077	...
		1078	};
765		1079
766	=head1 SEE ALSO	1080	=head1 SEE ALSO
767		1081
768	L<AnyEvent>.	1082	L<AnyEvent>.
769		1083

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.42 by root, Mon Jul 6 00:08:16 2009 UTC vs. Revision 1.70 by root, Fri Dec 31 20:31:47 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.42 by root, Mon Jul 6 00:08:16 2009 UTC vs.
Revision 1.70 by root, Fri Dec 31 20:31:47 2010 UTC