ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.81 by root, Sun Jan 2 01:20:17 2011 UTC vs.
Revision 1.134 by root, Fri Sep 7 22:11:31 2018 UTC

…		…
15	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
16	run a supported event loop.	16	run a supported event loop.
17		17
18	This module implements a simple, stateless and non-blocking HTTP	18	This module implements a simple, stateless and non-blocking HTTP
19	client. It supports GET, POST and other request methods, cookies and more,	19	client. It supports GET, POST and other request methods, cookies and more,
20	all on a very low level. It can follow redirects supports proxies and	20	all on a very low level. It can follow redirects, supports proxies, and
21	automatically limits the number of connections to the values specified in	21	automatically limits the number of connections to the values specified in
22	the RFC.	22	the RFC.
23		23
24	It should generally be a "good client" that is enough for most HTTP	24	It should generally be a "good client" that is enough for most HTTP
25	tasks. Simple tasks should be simple, but complex tasks should still be	25	tasks. Simple tasks should be simple, but complex tasks should still be
…		…
36		36
37	=cut	37	=cut
38		38
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use common::sense;
42	no warnings;
43		42
44	use Errno ();	43	use Errno ();
45		44
46	use AnyEvent 5.0 ();	45	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	46	use AnyEvent::Util ();
48	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
49		48
50	use base Exporter::;	49	use base Exporter::;
51		50
52	our $VERSION = '1.5';	51	our $VERSION = 2.24;
53		52
54	our @EXPORT = qw(http_get http_post http_head http_request);	53	our @EXPORT = qw(http_get http_post http_head http_request);
55		54
56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	55	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
57	our $MAX_RECURSE = 10;	56	our $MAX_RECURSE = 10;
58	our $MAX_PERSISTENT = 8;
59	our $PERSISTENT_TIMEOUT = 2;	57	our $PERSISTENT_TIMEOUT = 3;
60	our $TIMEOUT = 300;	58	our $TIMEOUT = 300;
61		59	our $MAX_PER_HOST = 4; # changing this is evil
62	# changing these is evil
63	our $MAX_PERSISTENT_PER_HOST = 0;
64	our $MAX_PER_HOST = 4;
65		60
66	our $PROXY;	61	our $PROXY;
67	our $ACTIVE = 0;	62	our $ACTIVE = 0;
68		63
69	my %KA_COUNT; # number of open keep-alive connections per host	64	my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array
70	my %CO_SLOT; # number of open connections, and wait queue, per host	65	my %CO_SLOT; # number of open connections, and wait queue, per host
71		66
72	=item http_get $url, key => value..., $cb->($data, $headers)	67	=item http_get $url, key => value..., $cb->($data, $headers)
73		68
74	Executes an HTTP-GET request. See the http_request function for details on	69	Executes an HTTP-GET request. See the http_request function for details on
…		…
94	C<http_request> returns a "cancellation guard" - you have to keep the	89	C<http_request> returns a "cancellation guard" - you have to keep the
95	object at least alive until the callback get called. If the object gets	90	object at least alive until the callback get called. If the object gets
96	destroyed before the callback is called, the request will be cancelled.	91	destroyed before the callback is called, the request will be cancelled.
97		92
98	The callback will be called with the response body data as first argument	93	The callback will be called with the response body data as first argument
99	(or C<undef> if an error occured), and a hash-ref with response headers	94	(or C<undef> if an error occurred), and a hash-ref with response headers
100	(and trailers) as second argument.	95	(and trailers) as second argument.
101		96
102	All the headers in that hash are lowercased. In addition to the response	97	All the headers in that hash are lowercased. In addition to the response
103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible	98	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the	99	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
…		…
128	C<590>-C<599> and the C<Reason> pseudo-header will contain an error	123	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
129	message. Currently the following status codes are used:	124	message. Currently the following status codes are used:
130		125
131	=over 4	126	=over 4
132		127
133	=item 595 - errors during connection etsbalishment, proxy handshake.	128	=item 595 - errors during connection establishment, proxy handshake.
134		129
135	=item 596 - errors during TLS negotiation, request sending and header processing.	130	=item 596 - errors during TLS negotiation, request sending and header processing.
136		131
137	=item 597 - errors during body receiving or processing.	132	=item 597 - errors during body receiving or processing.
138		133
…		…
159		154
160	=over 4	155	=over 4
161		156
162	=item recurse => $count (default: $MAX_RECURSE)	157	=item recurse => $count (default: $MAX_RECURSE)
163		158
164	Whether to recurse requests or not, e.g. on redirects, authentication	159	Whether to recurse requests or not, e.g. on redirects, authentication and
165	retries and so on, and how often to do so.	160	other retries and so on, and how often to do so.
		161
		162	Only redirects to http and https URLs are supported. While most common
		163	redirection forms are handled entirely within this module, some require
		164	the use of the optional L<URI> module. If it is required but missing, then
		165	the request will fail with an error.
166		166
167	=item headers => hashref	167	=item headers => hashref
168		168
169	The request headers to use. Currently, C<http_request> may provide its own	169	The request headers to use. Currently, C<http_request> may provide its own
170	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and	170	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
171	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>	171	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
172	(this can be suppressed by using C<undef> for these headers in which case	172	(this can be suppressed by using C<undef> for these headers in which case
173	they won't be sent at all).	173	they won't be sent at all).
174		174
		175	You really should provide your own C<User-Agent:> header value that is
		176	appropriate for your program - I wouldn't be surprised if the default
		177	AnyEvent string gets blocked by webservers sooner or later.
		178
		179	Also, make sure that your headers names and values do not contain any
		180	embedded newlines.
		181
175	=item timeout => $seconds	182	=item timeout => $seconds
176		183
177	The time-out to use for various stages - each connect attempt will reset	184	The time-out to use for various stages - each connect attempt will reset
178	the timeout, as will read or write activity, i.e. this is not an overall	185	the timeout, as will read or write activity, i.e. this is not an overall
179	timeout.	186	timeout.
180		187
181	Default timeout is 5 minutes.	188	Default timeout is 5 minutes.
182		189
183	=item proxy => [$host, $port[, $scheme]] or undef	190	=item proxy => [$host, $port[, $scheme]] or undef
184		191
185	Use the given http proxy for all requests. If not specified, then the	192	Use the given http proxy for all requests, or no proxy if C<undef> is
186	default proxy (as specified by C<$ENV{http_proxy}>) is used.	193	used.
187		194
188	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	195	C<$scheme> must be either missing or must be C<http> for HTTP.
189	HTTPS.	196
		197	If not specified, then the default proxy is used (see
		198	C<AnyEvent::HTTP::set_proxy>).
		199
		200	Currently, if your proxy requires authorization, you have to specify an
		201	appropriate "Proxy-Authorization" header in every request.
190		202
191	=item body => $string	203	=item body => $string
192		204
193	The request body, usually empty. Will be sent as-is (future versions of	205	The request body, usually empty. Will be sent as-is (future versions of
194	this module might offer more options).	206	this module might offer more options).
…		…
225	verification) TLS context.	237	verification) TLS context.
226		238
227	The default for this option is C<low>, which could be interpreted as "give	239	The default for this option is C<low>, which could be interpreted as "give
228	me the page, no matter what".	240	me the page, no matter what".
229		241
		242	See also the C<sessionid> parameter.
		243
		244	=item session => $string
		245
		246	The module might reuse connections to the same host internally. Sometimes
		247	(e.g. when using TLS), you do not want to reuse connections from other
		248	sessions. This can be achieved by setting this parameter to some unique
		249	ID (such as the address of an object storing your state data, or the TLS
		250	context) - only connections using the same unique ID will be reused.
		251
230	=item on_prepare => $callback->($fh)	252	=item on_prepare => $callback->($fh)
231		253
232	In rare cases you need to "tune" the socket before it is used to	254	In rare cases you need to "tune" the socket before it is used to
233	connect (for exmaple, to bind it on a given IP address). This parameter	255	connect (for example, to bind it on a given IP address). This parameter
234	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>	256	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
235	and behaves exactly the same way (e.g. it has to provide a	257	and behaves exactly the same way (e.g. it has to provide a
236	timeout). See the description for the C<$prepare_cb> argument of	258	timeout). See the description for the C<$prepare_cb> argument of
237	C<AnyEvent::Socket::tcp_connect> for details.	259	C<AnyEvent::Socket::tcp_connect> for details.
238		260
…		…
241	In even rarer cases you want total control over how AnyEvent::HTTP	263	In even rarer cases you want total control over how AnyEvent::HTTP
242	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>	264	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
243	to do this, but you can provide your own C<tcp_connect> function -	265	to do this, but you can provide your own C<tcp_connect> function -
244	obviously, it has to follow the same calling conventions, except that it	266	obviously, it has to follow the same calling conventions, except that it
245	may always return a connection guard object.	267	may always return a connection guard object.
		268
		269	The connections made by this hook will be treated as equivalent to
		270	connecitons made the built-in way, specifically, they will be put into
		271	and taken from the persistent conneciton cache. If your C<$tcp_connect>
		272	function is incompatible with this kind of re-use, consider switching off
		273	C<persistent> connections and/or providing a C<session> identifier.
246		274
247	There are probably lots of weird uses for this function, starting from	275	There are probably lots of weird uses for this function, starting from
248	tracing the hosts C<http_request> actually tries to connect, to (inexact	276	tracing the hosts C<http_request> actually tries to connect, to (inexact
249	but fast) host => IP address caching or even socks protocol support.	277	but fast) host => IP address caching or even socks protocol support.
250		278
…		…
303	called. Instead of the C<$body> argument containing the body data, the	331	called. Instead of the C<$body> argument containing the body data, the
304	callback will receive the L<AnyEvent::Handle> object associated with the	332	callback will receive the L<AnyEvent::Handle> object associated with the
305	connection. In error cases, C<undef> will be passed. When there is no body	333	connection. In error cases, C<undef> will be passed. When there is no body
306	(e.g. status C<304>), the empty string will be passed.	334	(e.g. status C<304>), the empty string will be passed.
307		335
308	The handle object might or might not be in TLS mode, might be connected to	336	The handle object might or might not be in TLS mode, might be connected
309	a proxy, be a persistent connection etc., and configured in unspecified	337	to a proxy, be a persistent connection, use chunked transfer encoding
310	ways. The user is responsible for this handle (it will not be used by this	338	etc., and configured in unspecified ways. The user is responsible for this
311	module anymore).	339	handle (it will not be used by this module anymore).
312		340
313	This is useful with some push-type services, where, after the initial	341	This is useful with some push-type services, where, after the initial
314	headers, an interactive protocol is used (typical example would be the	342	headers, an interactive protocol is used (typical example would be the
315	push-style twitter API which starts a JSON/XML stream).	343	push-style twitter API which starts a JSON/XML stream).
316		344
317	If you think you need this, first have a look at C<on_body>, to see if	345	If you think you need this, first have a look at C<on_body>, to see if
318	that doesn't solve your problem in a better way.	346	that doesn't solve your problem in a better way.
		347
		348	=item persistent => $boolean
		349
		350	Try to create/reuse a persistent connection. When this flag is set
		351	(default: true for idempotent requests, false for all others), then
		352	C<http_request> tries to re-use an existing (previously-created)
		353	persistent connection to same host (i.e. identical URL scheme, hostname,
		354	port and session) and, failing that, tries to create a new one.
		355
		356	Requests failing in certain ways will be automatically retried once, which
		357	is dangerous for non-idempotent requests, which is why it defaults to off
		358	for them. The reason for this is because the bozos who designed HTTP/1.1
		359	made it impossible to distinguish between a fatal error and a normal
		360	connection timeout, so you never know whether there was a problem with
		361	your request or not.
		362
		363	When reusing an existent connection, many parameters (such as TLS context)
		364	will be ignored. See the C<session> parameter for a workaround.
		365
		366	=item keepalive => $boolean
		367
		368	Only used when C<persistent> is also true. This parameter decides whether
		369	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		370	(as opposed to only a HTTP/1.1 persistent connection).
		371
		372	The default is true, except when using a proxy, in which case it defaults
		373	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		374
		375	=item handle_params => { key => value ... }
		376
		377	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		378	constructor that is called - not all requests will create a handle, and
		379	sometimes more than one is created, so this parameter is only good for
		380	setting hints.
		381
		382	Example: set the maximum read size to 4096, to potentially conserve memory
		383	at the cost of speed.
		384
		385	handle_params => {
		386	max_read_size => 4096,
		387	},
319		388
320	=back	389	=back
321		390
322	Example: do a simple HTTP GET request for http://www.nethype.de/ and print	391	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
323	the response body.	392	the response body.
…		…
329		398
330	Example: do a HTTP HEAD request on https://www.google.com/, use a	399	Example: do a HTTP HEAD request on https://www.google.com/, use a
331	timeout of 30 seconds.	400	timeout of 30 seconds.
332		401
333	http_request	402	http_request
334	GET => "https://www.google.com",	403	HEAD => "https://www.google.com",
		404	headers => { "user-agent" => "MySearchClient 1.0" },
335	timeout => 30,	405	timeout => 30,
336	sub {	406	sub {
337	my ($body, $hdr) = @_;	407	my ($body, $hdr) = @_;
338	use Data::Dumper;	408	use Data::Dumper;
339	print Dumper $hdr;	409	print Dumper $hdr;
…		…
349	};	419	};
350		420
351	undef $request;	421	undef $request;
352		422
353	=cut	423	=cut
		424
		425	#############################################################################
		426	# wait queue/slots
354		427
355	sub _slot_schedule;	428	sub _slot_schedule;
356	sub _slot_schedule($) {	429	sub _slot_schedule($) {
357	my $host = shift;	430	my $host = shift;
358		431
…		…
381		454
382	_slot_schedule $_[0];	455	_slot_schedule $_[0];
383	}	456	}
384		457
385	#############################################################################	458	#############################################################################
		459	# cookie handling
386		460
387	# expire cookies	461	# expire cookies
388	sub cookie_jar_expire($;$) {	462	sub cookie_jar_expire($;$) {
389	my ($jar, $session_end) = @_;	463	my ($jar, $session_end) = @_;
390		464
391	%$jar = () if $jar->{version} != 1;	465	%$jar = () if $jar->{version} != 2;
392		466
393	my $anow = AE::now;	467	my $anow = AE::now;
394		468
395	while (my ($chost, $paths) = each %$jar) {	469	while (my ($chost, $paths) = each %$jar) {
396	next unless ref $paths;	470	next unless ref $paths;
…		…
414	}	488	}
415	}	489	}
416		490
417	# extract cookies from jar	491	# extract cookies from jar
418	sub cookie_jar_extract($$$$) {	492	sub cookie_jar_extract($$$$) {
419	my ($jar, $uscheme, $uhost, $upath) = @_;	493	my ($jar, $scheme, $host, $path) = @_;
420		494
421	%$jar = () if $jar->{version} != 1;	495	%$jar = () if $jar->{version} != 2;
		496
		497	$host = AnyEvent::Util::idn_to_ascii $host
		498	if $host =~ /[^\x00-\x7f]/;
422		499
423	my @cookies;	500	my @cookies;
424		501
425	while (my ($chost, $paths) = each %$jar) {	502	while (my ($chost, $paths) = each %$jar) {
426	next unless ref $paths;	503	next unless ref $paths;
427		504
428	if ($chost =~ /^\./) {	505	# exact match or suffix including . match
429	next unless $chost eq substr $uhost, -length $chost;	506	$chost eq $host or ".$chost" eq substr $host, -1 - length $chost
430	} elsif ($chost =~ /\./) {
431	next unless $chost eq $uhost;
432	} else {
433	next;	507	or next;
434	}
435		508
436	while (my ($cpath, $cookies) = each %$paths) {	509	while (my ($cpath, $cookies) = each %$paths) {
437	next unless $cpath eq substr $upath, 0, length $cpath;	510	next unless $cpath eq substr $path, 0, length $cpath;
438		511
439	while (my ($cookie, $kv) = each %$cookies) {	512	while (my ($cookie, $kv) = each %$cookies) {
440	next if $uscheme ne "https" && exists $kv->{secure};	513	next if $scheme ne "https" && exists $kv->{secure};
441		514
442	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {	515	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
443	delete $cookies->{$cookie};	516	delete $cookies->{$cookie};
444	next;	517	next;
445	}	518	}
…		…
459	\@cookies	532	\@cookies
460	}	533	}
461		534
462	# parse set_cookie header into jar	535	# parse set_cookie header into jar
463	sub cookie_jar_set_cookie($$$$) {	536	sub cookie_jar_set_cookie($$$$) {
464	my ($jar, $set_cookie, $uhost, $date) = @_;	537	my ($jar, $set_cookie, $host, $date) = @_;
		538
		539	%$jar = () if $jar->{version} != 2;
465		540
466	my $anow = int AE::now;	541	my $anow = int AE::now;
467	my $snow; # server-now	542	my $snow; # server-now
468		543
469	for ($set_cookie) {	544	for ($set_cookie) {
…		…
475	while (	550	while (
476	m{	551	m{
477	\G\s*	552	\G\s*
478	(?:	553	(?:
479	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)	554	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
480	| ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )	555	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )?
481	)	556	)
482	}gcxsi	557	}gcxsi
483	) {	558	) {
484	my $name = $2;	559	my $name = $2;
485	my $value = $4;	560	my $value = $4;
486		561
487	unless (defined $name) {	562	if (defined $1) {
488	# expires	563	# expires
489	$name = "expires";	564	$name = "expires";
490	$value = $1;	565	$value = $1;
491	} elsif (!defined $value) {	566	} elsif (defined $3) {
492	# quoted	567	# quoted
493	$value = $3;	568	$value = $3;
494	$value =~ s/\\(.)/$1/gs;	569	$value =~ s/\\(.)/$1/gs;
495	}	570	}
496		571
497	push @kv, lc $name, $value;	572	push @kv, @kv ? lc $name : $name, $value;
498		573
499	last unless /\G\s*;/gc;	574	last unless /\G\s*;/gc;
500	}	575	}
501		576
502	last unless @kv;	577	last unless @kv;
…		…
515		590
516	my $cdom;	591	my $cdom;
517	my $cpath = (delete $kv{path}) || "/";	592	my $cpath = (delete $kv{path}) || "/";
518		593
519	if (exists $kv{domain}) {	594	if (exists $kv{domain}) {
520	$cdom = delete $kv{domain};	595	$cdom = $kv{domain};
521		596
522	$cdom =~ s/^\.?/./; # make sure it starts with a "."	597	$cdom =~ s/^\.?/./; # make sure it starts with a "."
523		598
524	next if $cdom =~ /\.$/;	599	next if $cdom =~ /\.$/;
525		600
526	# this is not rfc-like and not netscape-like. go figure.	601	# this is not rfc-like and not netscape-like. go figure.
527	my $ndots = $cdom =~ y/.//;	602	my $ndots = $cdom =~ y/.//;
528	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	603	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		604
		605	$cdom = substr $cdom, 1; # remove initial .
529	} else {	606	} else {
530	$cdom = $uhost;	607	$cdom = $host;
531	}	608	}
532		609
533	# store it	610	# store it
534	$jar->{version} = 1;	611	$jar->{version} = 2;
535	$jar->{$cdom}{$cpath}{$name} = \%kv;	612	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
536		613
537	redo if /\G\s*,/gc;	614	redo if /\G\s*,/gc;
538	}	615	}
539	}	616	}
540		617
		618	#############################################################################
		619	# keepalive/persistent connection cache
		620
		621	# fetch a connection from the keepalive cache
		622	sub ka_fetch($) {
		623	my $ka_key = shift;
		624
		625	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		626	delete $KA_CACHE{$ka_key}
		627	unless @{ $KA_CACHE{$ka_key} };
		628
		629	$hdl
		630	}
		631
		632	sub ka_store($$) {
		633	my ($ka_key, $hdl) = @_;
		634
		635	my $kaa = $KA_CACHE{$ka_key} ||= [];
		636
		637	my $destroy = sub {
		638	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		639
		640	$hdl->destroy;
		641
		642	@ka
		643	? $KA_CACHE{$ka_key} = \@ka
		644	: delete $KA_CACHE{$ka_key};
		645	};
		646
		647	# on error etc., destroy
		648	$hdl->on_error ($destroy);
		649	$hdl->on_eof ($destroy);
		650	$hdl->on_read ($destroy);
		651	$hdl->timeout ($PERSISTENT_TIMEOUT);
		652
		653	push @$kaa, $hdl;
		654	shift @$kaa while @$kaa > $MAX_PER_HOST;
		655	}
		656
		657	#############################################################################
		658	# utilities
		659
541	# continue to parse $_ for headers and place them into the arg	660	# continue to parse $_ for headers and place them into the arg
542	sub parse_hdr() {	661	sub _parse_hdr() {
543	my %hdr;	662	my %hdr;
544		663
545	# things seen, not parsed:	664	# things seen, not parsed:
546	# p3pP="NON CUR OTPi OUR NOR UNI"	665	# p3pP="NON CUR OTPi OUR NOR UNI"
547		666
…		…
561	for values %hdr;	680	for values %hdr;
562		681
563	\%hdr	682	\%hdr
564	}	683	}
565		684
		685	#############################################################################
		686	# http_get
		687
566	our $qr_nlnl = qr{(?<![^\012])\015?\012};	688	our $qr_nlnl = qr{(?<![^\012])\015?\012};
567		689
568	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	690	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
569	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	691	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		692
		693	# maybe it should just become a normal object :/
		694
		695	sub _destroy_state(\%) {
		696	my ($state) = @_;
		697
		698	$state->{handle}->destroy if $state->{handle};
		699	%$state = ();
		700	}
		701
		702	sub _error(\%$$) {
		703	my ($state, $cb, $hdr) = @_;
		704
		705	&_destroy_state ($state);
		706
		707	$cb->(undef, $hdr);
		708	()
		709	}
		710
		711	our %IDEMPOTENT = (
		712	DELETE => 1,
		713	GET => 1,
		714	HEAD => 1,
		715	OPTIONS => 1,
		716	PUT => 1,
		717	TRACE => 1,
		718
		719	ACL => 1,
		720	"BASELINE-CONTROL" => 1,
		721	BIND => 1,
		722	CHECKIN => 1,
		723	CHECKOUT => 1,
		724	COPY => 1,
		725	LABEL => 1,
		726	LINK => 1,
		727	MERGE => 1,
		728	MKACTIVITY => 1,
		729	MKCALENDAR => 1,
		730	MKCOL => 1,
		731	MKREDIRECTREF => 1,
		732	MKWORKSPACE => 1,
		733	MOVE => 1,
		734	ORDERPATCH => 1,
		735	PROPFIND => 1,
		736	PROPPATCH => 1,
		737	REBIND => 1,
		738	REPORT => 1,
		739	SEARCH => 1,
		740	UNBIND => 1,
		741	UNCHECKOUT => 1,
		742	UNLINK => 1,
		743	UNLOCK => 1,
		744	UPDATE => 1,
		745	UPDATEREDIRECTREF => 1,
		746	"VERSION-CONTROL" => 1,
		747	);
570		748
571	sub http_request($$@) {	749	sub http_request($$@) {
572	my $cb = pop;	750	my $cb = pop;
573	my ($method, $url, %arg) = @_;	751	my ($method, $url, %arg) = @_;
574		752
…		…
592	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	770	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
593		771
594	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })	772	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
595	if $recurse < 0;	773	if $recurse < 0;
596		774
597	my $proxy = $arg{proxy} || $PROXY;	775	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
598	my $timeout = $arg{timeout} || $TIMEOUT;	776	my $timeout = $arg{timeout} || $TIMEOUT;
599		777
600	my ($uscheme, $uauthority, $upath, $query, $fragment) =	778	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
601	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;	779	$url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|;
602		780
603	$uscheme = lc $uscheme;	781	$uscheme = lc $uscheme;
604		782
605	my $uport = $uscheme eq "http" ? 80	783	my $uport = $uscheme eq "http" ? 80
606	: $uscheme eq "https" ? 443	784	: $uscheme eq "https" ? 443
607	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });	785	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
608		786
609	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	787	$uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x
610	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	788	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
611		789
612	my $uhost = $1;	790	my $uhost = lc $1;
613	$uport = $2 if defined $2;	791	$uport = $2 if defined $2;
614		792
615	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	793	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
616	unless exists $hdr{host};	794	unless exists $hdr{host};
617		795
…		…
636	$rscheme = "http" unless defined $rscheme;	814	$rscheme = "http" unless defined $rscheme;
637		815
638	# don't support https requests over https-proxy transport,	816	# don't support https requests over https-proxy transport,
639	# can't be done with tls as spec'ed, unless you double-encrypt.	817	# can't be done with tls as spec'ed, unless you double-encrypt.
640	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	818	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		819
		820	$rhost = lc $rhost;
		821	$rscheme = lc $rscheme;
641	} else {	822	} else {
642	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	823	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
643	}	824	}
644		825
645	# leave out fragment and query string, just a heuristic	826	# leave out fragment and query string, just a heuristic
…		…
647	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};	828	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
648		829
649	$hdr{"content-length"} = length $arg{body}	830	$hdr{"content-length"} = length $arg{body}
650	if length $arg{body} || $method ne "GET";	831	if length $arg{body} || $method ne "GET";
651		832
652	$hdr{connection} = "close TE"; #1.1	833	my $idempotent = $IDEMPOTENT{$method};
		834
		835	# default value for keepalive is true iff the request is for an idempotent method
		836	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		837	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		838	my $was_persistent; # true if this is actually a recycled connection
		839
		840	# the key to use in the keepalive cache
		841	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		842
		843	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1
653	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1	844	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
654		845
655	my %state = (connect_guard => 1);	846	my %state = (connect_guard => 1);
		847
		848	my $ae_error = 595; # connecting
		849
		850	# handle actual, non-tunneled, request
		851	my $handle_actual_request = sub {
		852	$ae_error = 596; # request phase
		853
		854	my $hdl = $state{handle};
		855
		856	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		857
		858	# send request
		859	$hdl->push_write (
		860	"$method $rpath HTTP/1.1\015\012"
		861	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		862	. "\015\012"
		863	. $arg{body}
		864	);
		865
		866	# return if error occurred during push_write()
		867	return unless %state;
		868
		869	# reduce memory usage, save a kitten, also re-use it for the response headers.
		870	%hdr = ();
		871
		872	# status line and headers
		873	$state{read_response} = sub {
		874	return unless %state;
		875
		876	for ("$_[1]") {
		877	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		878
		879	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
		880	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		881
		882	# 100 Continue handling
		883	# should not happen as we don't send expect: 100-continue,
		884	# but we handle it just in case.
		885	# since we send the request body regardless, if we get an error
		886	# we are out of-sync, which we currently do NOT handle correctly.
		887	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		888	if $2 eq 100;
		889
		890	push @pseudo,
		891	HTTPVersion => $1,
		892	Status => $2,
		893	Reason => $3,
		894	;
		895
		896	my $hdr = _parse_hdr
		897	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		898
		899	%hdr = (%$hdr, @pseudo);
		900	}
		901
		902	# redirect handling
		903	# relative uri handling forced by microsoft and other shitheads.
		904	# we give our best and fall back to URI if available.
		905	if (exists $hdr{location}) {
		906	my $loc = $hdr{location};
		907
		908	if ($loc =~ m%^//%) { # //
		909	$loc = "$uscheme:$loc";
		910
		911	} elsif ($loc eq "") {
		912	$loc = $url;
		913
		914	} elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple"
		915	$loc =~ s/^\.\/+//;
		916
		917	if ($loc !~ m%^[.?#]%) {
		918	my $prefix = "$uscheme://$uauthority";
		919
		920	unless ($loc =~ s/^\///) {
		921	$prefix .= $upath;
		922	$prefix =~ s/\/[^\/]*$//;
		923	}
		924
		925	$loc = "$prefix/$loc";
		926
		927	} elsif (eval { require URI }) { # uri
		928	$loc = URI->new_abs ($loc, $url)->as_string;
		929
		930	} else {
		931	return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" };
		932	#$hdr{Status} = 599;
		933	#$hdr{Reason} = "Unparsable Redirect (URI module missing)";
		934	#$recurse = 0;
		935	}
		936	}
		937
		938	$hdr{location} = $loc;
		939	}
		940
		941	my $redirect;
		942
		943	if ($recurse) {
		944	my $status = $hdr{Status};
		945
		946	# industry standard is to redirect POST as GET for
		947	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		948	# also, the UA should ask the user for 301 and 307 and POST,
		949	# industry standard seems to be to simply follow.
		950	# we go with the industry standard. 308 is defined
		951	# by rfc7538
		952	if ($status == 301 or $status == 302 or $status == 303) {
		953	$redirect = 1;
		954	# HTTP/1.1 is unclear on how to mutate the method
		955	unless ($method eq "HEAD") {
		956	$method = "GET";
		957	delete $arg{body};
		958	}
		959	} elsif ($status == 307 or $status == 308) {
		960	$redirect = 1;
		961	}
		962	}
		963
		964	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		965	if ($state{handle}) {
		966	# handle keepalive
		967	if (
		968	$persistent
		969	&& $_[3]
		970	&& ($hdr{HTTPVersion} < 1.1
		971	? $hdr{connection} =~ /\bkeep-?alive\b/i
		972	: $hdr{connection} !~ /\bclose\b/i)
		973	) {
		974	ka_store $ka_key, delete $state{handle};
		975	} else {
		976	# no keepalive, destroy the handle
		977	$state{handle}->destroy;
		978	}
		979	}
		980
		981	%state = ();
		982
		983	if (defined $_[1]) {
		984	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		985	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		986	}
		987
		988	# set-cookie processing
		989	if ($arg{cookie_jar}) {
		990	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		991	}
		992
		993	if ($redirect && exists $hdr{location}) {
		994	# we ignore any errors, as it is very common to receive
		995	# Content-Length != 0 but no actual body
		996	# we also access %hdr, as $_[1] might be an erro
		997	$state{recurse} =
		998	http_request (
		999	$method => $hdr{location},
		1000	%arg,
		1001	recurse => $recurse - 1,
		1002	Redirect => [$_[0], \%hdr],
		1003	sub {
		1004	%state = ();
		1005	&$cb
		1006	},
		1007	);
		1008	} else {
		1009	$cb->($_[0], \%hdr);
		1010	}
		1011	};
		1012
		1013	$ae_error = 597; # body phase
		1014
		1015	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		1016
		1017	my $len = $chunked ? undef : $hdr{"content-length"};
		1018
		1019	# body handling, many different code paths
		1020	# - no body expected
		1021	# - want_body_handle
		1022	# - te chunked
		1023	# - 2x length known (with or without on_body)
		1024	# - 2x length not known (with or without on_body)
		1025	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		1026	$finish->(undef, 598 => "Request cancelled by on_header");
		1027	} elsif (
		1028	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		1029	or $method eq "HEAD"
		1030	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		1031	) {
		1032	# no body
		1033	$finish->("", undef, undef, 1);
		1034
		1035	} elsif (!$redirect && $arg{want_body_handle}) {
		1036	$_[0]->on_eof (undef);
		1037	$_[0]->on_error (undef);
		1038	$_[0]->on_read (undef);
		1039
		1040	$finish->(delete $state{handle});
		1041
		1042	} elsif ($chunked) {
		1043	my $cl = 0;
		1044	my $body = "";
		1045	my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 };
		1046
		1047	$state{read_chunk} = sub {
		1048	$_[1] =~ /^([0-9a-fA-F]+)/
		1049	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1050
		1051	my $len = hex $1;
		1052
		1053	if ($len) {
		1054	$cl += $len;
		1055
		1056	$_[0]->push_read (chunk => $len, sub {
		1057	$on_body->($_[1], \%hdr)
		1058	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1059
		1060	$_[0]->push_read (line => sub {
		1061	length $_[1]
		1062	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1063	$_[0]->push_read (line => $state{read_chunk});
		1064	});
		1065	});
		1066	} else {
		1067	$hdr{"content-length"} ||= $cl;
		1068
		1069	$_[0]->push_read (line => $qr_nlnl, sub {
		1070	if (length $_[1]) {
		1071	for ("$_[1]") {
		1072	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		1073
		1074	my $hdr = _parse_hdr
		1075	or return $finish->(undef, $ae_error => "Garbled response trailers");
		1076
		1077	%hdr = (%hdr, %$hdr);
		1078	}
		1079	}
		1080
		1081	$finish->($body, undef, undef, 1);
		1082	});
		1083	}
		1084	};
		1085
		1086	$_[0]->push_read (line => $state{read_chunk});
		1087
		1088	} elsif (!$redirect && $arg{on_body}) {
		1089	if (defined $len) {
		1090	$_[0]->on_read (sub {
		1091	$len -= length $_[0]{rbuf};
		1092
		1093	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1094	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1095
		1096	$len > 0
		1097	or $finish->("", undef, undef, 1);
		1098	});
		1099	} else {
		1100	$_[0]->on_eof (sub {
		1101	$finish->("");
		1102	});
		1103	$_[0]->on_read (sub {
		1104	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1105	or $finish->(undef, 598 => "Request cancelled by on_body");
		1106	});
		1107	}
		1108	} else {
		1109	$_[0]->on_eof (undef);
		1110
		1111	if (defined $len) {
		1112	$_[0]->on_read (sub {
		1113	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1114	if $len <= length $_[0]{rbuf};
		1115	});
		1116	} else {
		1117	$_[0]->on_error (sub {
		1118	($! == Errno::EPIPE || !$!)
		1119	? $finish->(delete $_[0]{rbuf})
		1120	: $finish->(undef, $ae_error => $_[2]);
		1121	});
		1122	$_[0]->on_read (sub { });
		1123	}
		1124	}
		1125	};
		1126
		1127	# if keepalive is enabled, then the server closing the connection
		1128	# before a response can happen legally - we retry on idempotent methods.
		1129	if ($was_persistent && $idempotent) {
		1130	my $old_eof = $hdl->{on_eof};
		1131	$hdl->{on_eof} = sub {
		1132	_destroy_state %state;
		1133
		1134	%state = ();
		1135	$state{recurse} =
		1136	http_request (
		1137	$method => $url,
		1138	%arg,
		1139	recurse => $recurse - 1,
		1140	persistent => 0,
		1141	sub {
		1142	%state = ();
		1143	&$cb
		1144	}
		1145	);
		1146	};
		1147	$hdl->on_read (sub {
		1148	return unless %state;
		1149
		1150	# as soon as we receive something, a connection close
		1151	# once more becomes a hard error
		1152	$hdl->{on_eof} = $old_eof;
		1153	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1154	});
		1155	} else {
		1156	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1157	}
		1158	};
		1159
		1160	my $prepare_handle = sub {
		1161	my ($hdl) = $state{handle};
		1162
		1163	$hdl->on_error (sub {
		1164	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1165	});
		1166	$hdl->on_eof (sub {
		1167	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1168	});
		1169	$hdl->timeout_reset;
		1170	$hdl->timeout ($timeout);
		1171	};
		1172
		1173	# connected to proxy (or origin server)
		1174	my $connect_cb = sub {
		1175	my $fh = shift
		1176	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1177
		1178	return unless delete $state{connect_guard};
		1179
		1180	# get handle
		1181	$state{handle} = new AnyEvent::Handle
		1182	%{ $arg{handle_params} },
		1183	fh => $fh,
		1184	peername => $uhost,
		1185	tls_ctx => $arg{tls_ctx},
		1186	;
		1187
		1188	$prepare_handle->();
		1189
		1190	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1191
		1192	# now handle proxy-CONNECT method
		1193	if ($proxy && $uscheme eq "https") {
		1194	# oh dear, we have to wrap it into a connect request
		1195
		1196	my $auth = exists $hdr{"proxy-authorization"}
		1197	? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012"
		1198	: "";
		1199
		1200	# maybe re-use $uauthority with patched port?
		1201	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012");
		1202	$state{handle}->push_read (line => $qr_nlnl, sub {
		1203	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1204	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1205
		1206	if ($2 == 200) {
		1207	$rpath = $upath;
		1208	$handle_actual_request->();
		1209	} else {
		1210	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1211	}
		1212	});
		1213	} else {
		1214	delete $hdr{"proxy-authorization"} unless $proxy;
		1215
		1216	$handle_actual_request->();
		1217	}
		1218	};
656		1219
657	_get_slot $uhost, sub {	1220	_get_slot $uhost, sub {
658	$state{slot_guard} = shift;	1221	$state{slot_guard} = shift;
659		1222
660	return unless $state{connect_guard};	1223	return unless $state{connect_guard};
661		1224
662	my $ae_error = 595; # connecting	1225	# try to use an existing keepalive connection, but only if we, ourselves, plan
		1226	# on a keepalive request (in theory, this should be a separate config option).
		1227	if ($persistent && $KA_CACHE{$ka_key}) {
		1228	$was_persistent = 1;
663		1229
664	my $connect_cb = sub {	1230	$state{handle} = ka_fetch $ka_key;
665	$state{fh} = shift	1231	# $state{handle}->destroyed
666	or do {	1232	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
667	my $err = "$!";	1233	$prepare_handle->();
668	%state = ();	1234	# $state{handle}->destroyed
669	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });	1235	# and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
670	};
671
672	return unless delete $state{connect_guard};
673
674	# get handle
675	$state{handle} = new AnyEvent::Handle
676	fh => $state{fh},
677	peername => $rhost,
678	tls_ctx => $arg{tls_ctx},
679	# these need to be reconfigured on keepalive handles
680	timeout => $timeout,
681	on_error => sub {
682	%state = ();
683	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
684	},
685	on_eof => sub {
686	%state = ();
687	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
688	},
689	;
690
691	# limit the number of persistent connections
692	# keepalive not yet supported
693	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
694	# ++$KA_COUNT{$_[1]};
695	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
696	# --$KA_COUNT{$_[1]}
697	# };
698	# $hdr{connection} = "keep-alive";
699	# }
700
701	$state{handle}->starttls ("connect") if $rscheme eq "https";
702
703	# handle actual, non-tunneled, request
704	my $handle_actual_request = sub {
705	$ae_error = 596; # request phase
706
707	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
708
709	# send request
710	$state{handle}->push_write (
711	"$method $rpath HTTP/1.1\015\012"
712	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
713	. "\015\012"
714	. (delete $arg{body})
715	);
716
717	# return if error occured during push_write()
718	return unless %state;
719
720	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
721
722	# status line and headers
723	$state{read_response} = sub {
724	for ("$_[1]") {
725	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
726
727	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
728	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
729
730	# 100 Continue handling
731	# should not happen as we don't send expect: 100-continue,
732	# but we handle it just in case.
733	# since we send the request body regardless, if we get an error
734	# we are out of-sync, which we currently do NOT handle correctly.
735	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
736	if $2 eq 100;
737
738	push @pseudo,
739	HTTPVersion => $1,
740	Status => $2,
741	Reason => $3,
742	;
743
744	my $hdr = parse_hdr
745	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
746
747	%hdr = (%$hdr, @pseudo);
748	}
749
750	# redirect handling
751	# microsoft and other shitheads don't give a shit for following standards,
752	# try to support some common forms of broken Location headers.
753	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
754	$hdr{location} =~ s/^\.\/+//;
755
756	my $url = "$rscheme://$uhost:$uport";
757
758	unless ($hdr{location} =~ s/^\///) {
759	$url .= $upath;
760	$url =~ s/\/[^\/]*$//;
761	}
762
763	$hdr{location} = "$url/$hdr{location}";
764	}
765
766	my $redirect;
767
768	if ($recurse) {
769	my $status = $hdr{Status};
770
771	# industry standard is to redirect POST as GET for
772	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
773	# also, the UA should ask the user for 301 and 307 and POST,
774	# industry standard seems to be to simply follow.
775	# we go with the industry standard.
776	if ($status == 301 or $status == 302 or $status == 303) {
777	# HTTP/1.1 is unclear on how to mutate the method
778	$method = "GET" unless $method eq "HEAD";
779	$redirect = 1;
780	} elsif ($status == 307) {
781	$redirect = 1;
782	}
783	}
784
785	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
786	my $may_keep_alive = $_[3];
787
788	$state{handle}->destroy if $state{handle};
789	%state = ();
790
791	if (defined $_[1]) {
792	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
793	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
794	}
795
796	# set-cookie processing
797	if ($arg{cookie_jar}) {
798	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
799	}
800
801	if ($redirect && exists $hdr{location}) {
802	# we ignore any errors, as it is very common to receive
803	# Content-Length != 0 but no actual body
804	# we also access %hdr, as $_[1] might be an erro
805	http_request (
806	$method => $hdr{location},
807	%arg,
808	recurse => $recurse - 1,
809	Redirect => [$_[0], \%hdr],
810	$cb);
811	} else {
812	$cb->($_[0], \%hdr);
813	}
814	};
815
816	$ae_error = 597; # body phase
817
818	my $len = $hdr{"content-length"};
819
820	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
821	$finish->(undef, 598 => "Request cancelled by on_header");
822	} elsif (
823	$hdr{Status} =~ /^(?:1..|204|205|304)$/
824	or $method eq "HEAD"
825	or (defined $len && !$len)
826	) {
827	# no body
828	$finish->("", undef, undef, 1);
829	} else {
830	# body handling, many different code paths
831	# - no body expected
832	# - want_body_handle
833	# - te chunked
834	# - 2x length known (with or without on_body)
835	# - 2x length not known (with or without on_body)
836	if (!$redirect && $arg{want_body_handle}) {
837	$_[0]->on_eof (undef);
838	$_[0]->on_error (undef);
839	$_[0]->on_read (undef);
840
841	$finish->(delete $state{handle});
842
843	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
844	my $cl = 0;
845	my $body = undef;
846	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
847
848	$state{read_chunk} = sub {
849	$_[1] =~ /^([0-9a-fA-F]+)/
850	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
851
852	my $len = hex $1;
853
854	if ($len) {
855	$cl += $len;
856
857	$_[0]->push_read (chunk => $len, sub {
858	$on_body->($_[1], \%hdr)
859	or return $finish->(undef, 598 => "Request cancelled by on_body");
860
861	$_[0]->push_read (line => sub {
862	length $_[1]
863	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
864	$_[0]->push_read (line => $state{read_chunk});
865	});
866	});
867	} else {
868	$hdr{"content-length"} ||= $cl;
869
870	$_[0]->push_read (line => $qr_nlnl, sub {
871	if (length $_[1]) {
872	for ("$_[1]") {
873	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
874
875	my $hdr = parse_hdr
876	or return $finish->(undef, $ae_error => "Garbled response trailers");
877
878	%hdr = (%hdr, %$hdr);
879	}
880	}
881
882	$finish->($body, undef, undef, 1);
883	});
884	}
885	};
886
887	$_[0]->push_read (line => $state{read_chunk});
888
889	} elsif ($arg{on_body}) {
890	if ($len) {
891	$_[0]->on_read (sub {
892	$len -= length $_[0]{rbuf};
893
894	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
895	or return $finish->(undef, 598 => "Request cancelled by on_body");
896
897	$len > 0
898	or $finish->("", undef, undef, 1);
899	});
900	} else {
901	$_[0]->on_eof (sub {
902	$finish->("");
903	});
904	$_[0]->on_read (sub {
905	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
906	or $finish->(undef, 598 => "Request cancelled by on_body");
907	});
908	}
909	} else {
910	$_[0]->on_eof (undef);
911
912	if ($len) {
913	$_[0]->on_read (sub {
914	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
915	if $len <= length $_[0]{rbuf};
916	});
917	} else {
918	$_[0]->on_error (sub {
919	($! == Errno::EPIPE || !$!)
920	? $finish->(delete $_[0]{rbuf})
921	: $finish->(undef, $ae_error => $_[2]);
922	});
923	$_[0]->on_read (sub { });
924	}
925	}
926	}
927	};
928
929	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
930	};
931
932	# now handle proxy-CONNECT method
933	if ($proxy && $uscheme eq "https") {
934	# oh dear, we have to wrap it into a connect request
935
936	# maybe re-use $uauthority with patched port?
937	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
938	$state{handle}->push_read (line => $qr_nlnl, sub {
939	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
940	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
941
942	if ($2 == 200) {
943	$rpath = $upath;
944	$handle_actual_request->();
945	} else {
946	%state = ();
947	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
948	}
949	});
950	} else {
951	$handle_actual_request->();	1236	$handle_actual_request->();
952	}
953	};
954		1237
		1238	} else {
955	my $tcp_connect = $arg{tcp_connect}	1239	my $tcp_connect = $arg{tcp_connect}
956	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1240	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
957		1241
958	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });	1242	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
959		1243	}
960	};	1244	};
961		1245
962	defined wantarray && AnyEvent::Util::guard { %state = () }	1246	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
963	}	1247	}
964		1248
965	sub http_get($@) {	1249	sub http_get($@) {
966	unshift @_, "GET";	1250	unshift @_, "GET";
967	&http_request	1251	&http_request
…		…
985	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1269	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
986	the actual connection, which in turn uses AnyEvent::DNS to resolve	1270	the actual connection, which in turn uses AnyEvent::DNS to resolve
987	hostnames. The latter is a simple stub resolver and does no caching	1271	hostnames. The latter is a simple stub resolver and does no caching
988	on its own. If you want DNS caching, you currently have to provide	1272	on its own. If you want DNS caching, you currently have to provide
989	your own default resolver (by storing a suitable resolver object in	1273	your own default resolver (by storing a suitable resolver object in
990	C<$AnyEvent::DNS::RESOLVER>).	1274	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
991		1275
992	=head2 GLOBAL FUNCTIONS AND VARIABLES	1276	=head2 GLOBAL FUNCTIONS AND VARIABLES
993		1277
994	=over 4	1278	=over 4
995		1279
996	=item AnyEvent::HTTP::set_proxy "proxy-url"	1280	=item AnyEvent::HTTP::set_proxy "proxy-url"
997		1281
998	Sets the default proxy server to use. The proxy-url must begin with a	1282	Sets the default proxy server to use. The proxy-url must begin with a
999	string of the form C<http://host:port> (optionally C<https:...>), croaks	1283	string of the form C<http://host:port>, croaks otherwise.
1000	otherwise.
1001		1284
1002	To clear an already-set proxy, use C<undef>.	1285	To clear an already-set proxy, use C<undef>.
		1286
		1287	When AnyEvent::HTTP is loaded for the first time it will query the
		1288	default proxy from the operating system, currently by looking at
		1289	C<$ENV{http_proxy>}.
1003		1290
1004	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]	1291	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
1005		1292
1006	Remove all cookies from the cookie jar that have been expired. If	1293	Remove all cookies from the cookie jar that have been expired. If
1007	C<$session_end> is given and true, then additionally remove all session	1294	C<$session_end> is given and true, then additionally remove all session
1008	cookies.	1295	cookies.
1009		1296
1010	You should call this function (with a true C<$session_end>) before you	1297	You should call this function (with a true C<$session_end>) before you
1011	save cookies to disk, and you should call this function after loading them	1298	save cookies to disk, and you should call this function after loading them
1012	again. If you have a long-running program you can additonally call this	1299	again. If you have a long-running program you can additionally call this
1013	function from time to time.	1300	function from time to time.
1014		1301
1015	A cookie jar is initially an empty hash-reference that is managed by this	1302	A cookie jar is initially an empty hash-reference that is managed by this
1016	module. It's format is subject to change, but currently it is like this:	1303	module. Its format is subject to change, but currently it is as follows:
1017		1304
1018	The key C<version> has to contain C<1>, otherwise the hash gets	1305	The key C<version> has to contain C<2>, otherwise the hash gets
1019	emptied. All other keys are hostnames or IP addresses pointing to	1306	cleared. All other keys are hostnames or IP addresses pointing to
1020	hash-references. The key for these inner hash references is the	1307	hash-references. The key for these inner hash references is the
1021	server path for which this cookie is meant, and the values are again	1308	server path for which this cookie is meant, and the values are again
1022	hash-references. The keys of those hash-references is the cookie name, and	1309	hash-references. Each key of those hash-references is a cookie name, and
1023	the value, you guessed it, is another hash-reference, this time with the	1310	the value, you guessed it, is another hash-reference, this time with the
1024	key-value pairs from the cookie, except for C<expires> and C<max-age>,	1311	key-value pairs from the cookie, except for C<expires> and C<max-age>,
1025	which have been replaced by a C<_expires> key that contains the cookie	1312	which have been replaced by a C<_expires> key that contains the cookie
1026	expiry timestamp.	1313	expiry timestamp. Session cookies are indicated by not having an
		1314	C<_expires> key.
1027		1315
1028	Here is an example of a cookie jar with a single cookie, so you have a	1316	Here is an example of a cookie jar with a single cookie, so you have a
1029	chance of understanding the above paragraph:	1317	chance of understanding the above paragraph:
1030		1318
1031	{	1319	{
1032	version => 1,	1320	version => 2,
1033	"10.0.0.1" => {	1321	"10.0.0.1" => {
1034	"/" => {	1322	"/" => {
1035	"mythweb_id" => {	1323	"mythweb_id" => {
1036	_expires => 1293917923,	1324	_expires => 1293917923,
1037	value => "ooRung9dThee3ooyXooM1Ohm",	1325	value => "ooRung9dThee3ooyXooM1Ohm",
…		…
1053		1341
1054	=item $AnyEvent::HTTP::MAX_RECURSE	1342	=item $AnyEvent::HTTP::MAX_RECURSE
1055		1343
1056	The default value for the C<recurse> request parameter (default: C<10>).	1344	The default value for the C<recurse> request parameter (default: C<10>).
1057		1345
		1346	=item $AnyEvent::HTTP::TIMEOUT
		1347
		1348	The default timeout for connection operations (default: C<300>).
		1349
1058	=item $AnyEvent::HTTP::USERAGENT	1350	=item $AnyEvent::HTTP::USERAGENT
1059		1351
1060	The default value for the C<User-Agent> header (the default is	1352	The default value for the C<User-Agent> header (the default is
1061	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1353	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
1062		1354
1063	=item $AnyEvent::HTTP::MAX_PER_HOST	1355	=item $AnyEvent::HTTP::MAX_PER_HOST
1064		1356
1065	The maximum number of concurrent connections to the same host (identified	1357	The maximum number of concurrent connections to the same host (identified
1066	by the hostname). If the limit is exceeded, then the additional requests	1358	by the hostname). If the limit is exceeded, then additional requests
1067	are queued until previous connections are closed.	1359	are queued until previous connections are closed. Both persistent and
		1360	non-persistent connections are counted in this limit.
1068		1361
1069	The default value for this is C<4>, and it is highly advisable to not	1362	The default value for this is C<4>, and it is highly advisable to not
1070	increase it.	1363	increase it much.
		1364
		1365	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1366	connections, older browsers used 2, newer ones (such as firefox 3)
		1367	typically use 6, and Opera uses 8 because like, they have the fastest
		1368	browser and give a shit for everybody else on the planet.
		1369
		1370	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1371
		1372	The time after which idle persistent connections get closed by
		1373	AnyEvent::HTTP (default: C<3>).
1071		1374
1072	=item $AnyEvent::HTTP::ACTIVE	1375	=item $AnyEvent::HTTP::ACTIVE
1073		1376
1074	The number of active connections. This is not the number of currently	1377	The number of active connections. This is not the number of currently
1075	running requests, but the number of currently open and non-idle TCP	1378	running requests, but the number of currently open and non-idle TCP
1076	connections. This number of can be useful for load-leveling.	1379	connections. This number can be useful for load-leveling.
1077		1380
1078	=back	1381	=back
1079		1382
1080	=cut	1383	=cut
1081		1384
…		…
1115	# other formats fail in the loop below	1418	# other formats fail in the loop below
1116		1419
1117	for (0..11) {	1420	for (0..11) {
1118	if ($m eq $month[$_]) {	1421	if ($m eq $month[$_]) {
1119	require Time::Local;	1422	require Time::Local;
1120	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);	1423	return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) };
1121	}	1424	}
1122	}	1425	}
1123		1426
1124	undef	1427	undef
1125	}	1428	}
1126		1429
1127	sub set_proxy($) {	1430	sub set_proxy($) {
1128	if (length $_[0]) {	1431	if (length $_[0]) {
1129	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1432	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
1130	or Carp::croak "$_[0]: invalid proxy URL";	1433	or Carp::croak "$_[0]: invalid proxy URL";
1131	$PROXY = [$2, $3 || 3128, $1]	1434	$PROXY = [$2, $3 || 3128, $1]
1132	} else {	1435	} else {
1133	undef $PROXY;	1436	undef $PROXY;
1134	}	1437	}
…		…
1137	# initialise proxy from environment	1440	# initialise proxy from environment
1138	eval {	1441	eval {
1139	set_proxy $ENV{http_proxy};	1442	set_proxy $ENV{http_proxy};
1140	};	1443	};
1141		1444
		1445	=head2 SHOWCASE
		1446
		1447	This section contains some more elaborate "real-world" examples or code
		1448	snippets.
		1449
		1450	=head2 HTTP/1.1 FILE DOWNLOAD
		1451
		1452	Downloading files with HTTP can be quite tricky, especially when something
		1453	goes wrong and you want to resume.
		1454
		1455	Here is a function that initiates and resumes a download. It uses the
		1456	last modified time to check for file content changes, and works with many
		1457	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1458	on older servers.
		1459
		1460	It calls the completion callback with either C<undef>, which means a
		1461	nonretryable error occurred, C<0> when the download was partial and should
		1462	be retried, and C<1> if it was successful.
		1463
		1464	use AnyEvent::HTTP;
		1465
		1466	sub download($$$) {
		1467	my ($url, $file, $cb) = @_;
		1468
		1469	open my $fh, "+<", $file
		1470	or die "$file: $!";
		1471
		1472	my %hdr;
		1473	my $ofs = 0;
		1474
		1475	if (stat $fh and -s _) {
		1476	$ofs = -s _;
		1477	warn "-s is ", $ofs;
		1478	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1479	$hdr{"range"} = "bytes=$ofs-";
		1480	}
		1481
		1482	http_get $url,
		1483	headers => \%hdr,
		1484	on_header => sub {
		1485	my ($hdr) = @_;
		1486
		1487	if ($hdr->{Status} == 200 && $ofs) {
		1488	# resume failed
		1489	truncate $fh, $ofs = 0;
		1490	}
		1491
		1492	sysseek $fh, $ofs, 0;
		1493
		1494	1
		1495	},
		1496	on_body => sub {
		1497	my ($data, $hdr) = @_;
		1498
		1499	if ($hdr->{Status} =~ /^2/) {
		1500	length $data == syswrite $fh, $data
		1501	or return; # abort on write errors
		1502	}
		1503
		1504	1
		1505	},
		1506	sub {
		1507	my (undef, $hdr) = @_;
		1508
		1509	my $status = $hdr->{Status};
		1510
		1511	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1512	utime $time, $time, $fh;
		1513	}
		1514
		1515	if ($status == 200 || $status == 206 || $status == 416) {
		1516	# download ok || resume ok || file already fully downloaded
		1517	$cb->(1, $hdr);
		1518
		1519	} elsif ($status == 412) {
		1520	# file has changed while resuming, delete and retry
		1521	unlink $file;
		1522	$cb->(0, $hdr);
		1523
		1524	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1525	# retry later
		1526	$cb->(0, $hdr);
		1527
		1528	} else {
		1529	$cb->(undef, $hdr);
		1530	}
		1531	}
		1532	;
		1533	}
		1534
		1535	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1536	if ($_[0]) {
		1537	print "OK!\n";
		1538	} elsif (defined $_[0]) {
		1539	print "please retry later\n";
		1540	} else {
		1541	print "ERROR\n";
		1542	}
		1543	};
		1544
1142	=head2 SOCKS PROXIES	1545	=head3 SOCKS PROXIES
1143		1546
1144	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1547	Socks proxies are not directly supported by AnyEvent::HTTP. You can
1145	compile your perl to support socks, or use an external program such as	1548	compile your perl to support socks, or use an external program such as
1146	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy	1549	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
1147	transparently.	1550	transparently.

Diff Legend

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