ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.67 by root, Fri Dec 31 06:18:54 2010 UTC vs.
Revision 1.122 by root, Fri May 8 17:28:39 2015 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 = 2.21;
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 as	94	(or C<undef> if an error occurred), and a hash-ref with response headers
100	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
105	three parts of the HTTP Status-Line of the same name. If an error occurs	100	three parts of the HTTP Status-Line of the same name. If an error occurs
…		…
122		117
123	If the server sends a header multiple times, then their contents will be	118	If the server sends a header multiple times, then their contents will be
124	joined together with a comma (C<,>), as per the HTTP spec.	119	joined together with a comma (C<,>), as per the HTTP spec.
125		120
126	If an internal error occurs, such as not being able to resolve a hostname,	121	If an internal error occurs, such as not being able to resolve a hostname,
127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>	122	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
128	(usually C<599>) and the C<Reason> pseudo-header will contain an error	123	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
129	message.	124	message. Currently the following status codes are used:
		125
		126	=over 4
		127
		128	=item 595 - errors during connection establishment, proxy handshake.
		129
		130	=item 596 - errors during TLS negotiation, request sending and header processing.
		131
		132	=item 597 - errors during body receiving or processing.
		133
		134	=item 598 - user aborted request via C<on_header> or C<on_body>.
		135
		136	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		137
		138	=back
130		139
131	A typical callback might look like this:	140	A typical callback might look like this:
132		141
133	sub {	142	sub {
134	my ($body, $hdr) = @_;	143	my ($body, $hdr) = @_;
…		…
145		154
146	=over 4	155	=over 4
147		156
148	=item recurse => $count (default: $MAX_RECURSE)	157	=item recurse => $count (default: $MAX_RECURSE)
149		158
150	Whether to recurse requests or not, e.g. on redirects, authentication	159	Whether to recurse requests or not, e.g. on redirects, authentication and
151	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.
152		166
153	=item headers => hashref	167	=item headers => hashref
154		168
155	The request headers to use. Currently, C<http_request> may provide its	169	The request headers to use. Currently, C<http_request> may provide its own
156	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	170	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
157	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be	171	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
158	suppressed by using C<undef> for these headers in which case they won't be	172	(this can be suppressed by using C<undef> for these headers in which case
159	sent at all).	173	they won't be sent at all).
		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.
160		181
161	=item timeout => $seconds	182	=item timeout => $seconds
162		183
163	The time-out to use for various stages - each connect attempt will reset	184	The time-out to use for various stages - each connect attempt will reset
164	the timeout, as will read or write activity, i.e. this is not an overall	185	the timeout, as will read or write activity, i.e. this is not an overall
…		…
166		187
167	Default timeout is 5 minutes.	188	Default timeout is 5 minutes.
168		189
169	=item proxy => [$host, $port[, $scheme]] or undef	190	=item proxy => [$host, $port[, $scheme]] or undef
170		191
171	Use the given http proxy for all requests. If not specified, then the	192	Use the given http proxy for all requests, or no proxy if C<undef> is
172	default proxy (as specified by C<$ENV{http_proxy}>) is used.	193	used.
173		194
174	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.
175	HTTPS.	196
		197	If not specified, then the default proxy is used (see
		198	C<AnyEvent::HTTP::set_proxy>).
176		199
177	=item body => $string	200	=item body => $string
178		201
179	The request body, usually empty. Will be-sent as-is (future versions of	202	The request body, usually empty. Will be sent as-is (future versions of
180	this module might offer more options).	203	this module might offer more options).
181		204
182	=item cookie_jar => $hash_ref	205	=item cookie_jar => $hash_ref
183		206
184	Passing this parameter enables (simplified) cookie-processing, loosely	207	Passing this parameter enables (simplified) cookie-processing, loosely
185	based on the original netscape specification.	208	based on the original netscape specification.
186		209
187	The C<$hash_ref> must be an (initially empty) hash reference which will	210	The C<$hash_ref> must be an (initially empty) hash reference which
188	get updated automatically. It is possible to save the cookie_jar to	211	will get updated automatically. It is possible to save the cookie jar
189	persistent storage with something like JSON or Storable, but this is not	212	to persistent storage with something like JSON or Storable - see the
190	recommended, as expiry times are currently being ignored.	213	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		214	expired or session-only cookies, and also for documentation on the format
		215	of the cookie jar.
191		216
192	Note that this cookie implementation is not of very high quality, nor	217	Note that this cookie implementation is not meant to be complete. If
193	meant to be complete. If you want complete cookie management you have to	218	you want complete cookie management you have to do that on your
194	do that on your own. C<cookie_jar> is meant as a quick fix to get some	219	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
195	cookie-using sites working. Cookies are a privacy disaster, do not use	220	working. Cookies are a privacy disaster, do not use them unless required
196	them unless required to.	221	to.
		222
		223	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		224	headers will be set and handled by this module, otherwise they will be
		225	left untouched.
197		226
198	=item tls_ctx => $scheme | $tls_ctx	227	=item tls_ctx => $scheme | $tls_ctx
199		228
200	Specifies the AnyEvent::TLS context to be used for https connections. This	229	Specifies the AnyEvent::TLS context to be used for https connections. This
201	parameter follows the same rules as the C<tls_ctx> parameter to	230	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
205	verification) TLS context.	234	verification) TLS context.
206		235
207	The default for this option is C<low>, which could be interpreted as "give	236	The default for this option is C<low>, which could be interpreted as "give
208	me the page, no matter what".	237	me the page, no matter what".
209		238
		239	See also the C<sessionid> parameter.
		240
		241	=item session => $string
		242
		243	The module might reuse connections to the same host internally. Sometimes
		244	(e.g. when using TLS), you do not want to reuse connections from other
		245	sessions. This can be achieved by setting this parameter to some unique
		246	ID (such as the address of an object storing your state data, or the TLS
		247	context) - only connections using the same unique ID will be reused.
		248
210	=item on_prepare => $callback->($fh)	249	=item on_prepare => $callback->($fh)
211		250
212	In rare cases you need to "tune" the socket before it is used to	251	In rare cases you need to "tune" the socket before it is used to
213	connect (for exmaple, to bind it on a given IP address). This parameter	252	connect (for example, to bind it on a given IP address). This parameter
214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>	253	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
215	and behaves exactly the same way (e.g. it has to provide a	254	and behaves exactly the same way (e.g. it has to provide a
216	timeout). See the description for the C<$prepare_cb> argument of	255	timeout). See the description for the C<$prepare_cb> argument of
217	C<AnyEvent::Socket::tcp_connect> for details.	256	C<AnyEvent::Socket::tcp_connect> for details.
218		257
…		…
240		279
241	This callback is useful, among other things, to quickly reject unwanted	280	This callback is useful, among other things, to quickly reject unwanted
242	content, which, if it is supposed to be rare, can be faster than first	281	content, which, if it is supposed to be rare, can be faster than first
243	doing a C<HEAD> request.	282	doing a C<HEAD> request.
244		283
		284	The downside is that cancelling the request makes it impossible to re-use
		285	the connection. Also, the C<on_header> callback will not receive any
		286	trailer (headers sent after the response body).
		287
245	Example: cancel the request unless the content-type is "text/html".	288	Example: cancel the request unless the content-type is "text/html".
246		289
247	on_header => sub {	290	on_header => sub {
248	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/	291	$_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/
249	},	292	},
…		…
255	string instead of the body data.	298	string instead of the body data.
256		299
257	It has to return either true (in which case AnyEvent::HTTP will continue),	300	It has to return either true (in which case AnyEvent::HTTP will continue),
258	or false, in which case AnyEvent::HTTP will cancel the download (and call	301	or false, in which case AnyEvent::HTTP will cancel the download (and call
259	the completion callback with an error code of C<598>).	302	the completion callback with an error code of C<598>).
		303
		304	The downside to cancelling the request is that it makes it impossible to
		305	re-use the connection.
260		306
261	This callback is useful when the data is too large to be held in memory	307	This callback is useful when the data is too large to be held in memory
262	(so the callback writes it to a file) or when only some information should	308	(so the callback writes it to a file) or when only some information should
263	be extracted, or when the body should be processed incrementally.	309	be extracted, or when the body should be processed incrementally.
264		310
…		…
276	called. Instead of the C<$body> argument containing the body data, the	322	called. Instead of the C<$body> argument containing the body data, the
277	callback will receive the L<AnyEvent::Handle> object associated with the	323	callback will receive the L<AnyEvent::Handle> object associated with the
278	connection. In error cases, C<undef> will be passed. When there is no body	324	connection. In error cases, C<undef> will be passed. When there is no body
279	(e.g. status C<304>), the empty string will be passed.	325	(e.g. status C<304>), the empty string will be passed.
280		326
281	The handle object might or might not be in TLS mode, might be connected to	327	The handle object might or might not be in TLS mode, might be connected
282	a proxy, be a persistent connection etc., and configured in unspecified	328	to a proxy, be a persistent connection, use chunked transfer encoding
283	ways. The user is responsible for this handle (it will not be used by this	329	etc., and configured in unspecified ways. The user is responsible for this
284	module anymore).	330	handle (it will not be used by this module anymore).
285		331
286	This is useful with some push-type services, where, after the initial	332	This is useful with some push-type services, where, after the initial
287	headers, an interactive protocol is used (typical example would be the	333	headers, an interactive protocol is used (typical example would be the
288	push-style twitter API which starts a JSON/XML stream).	334	push-style twitter API which starts a JSON/XML stream).
289		335
290	If you think you need this, first have a look at C<on_body>, to see if	336	If you think you need this, first have a look at C<on_body>, to see if
291	that doesn't solve your problem in a better way.	337	that doesn't solve your problem in a better way.
292		338
		339	=item persistent => $boolean
		340
		341	Try to create/reuse a persistent connection. When this flag is set
		342	(default: true for idempotent requests, false for all others), then
		343	C<http_request> tries to re-use an existing (previously-created)
		344	persistent connection to the host and, failing that, tries to create a new
		345	one.
		346
		347	Requests failing in certain ways will be automatically retried once, which
		348	is dangerous for non-idempotent requests, which is why it defaults to off
		349	for them. The reason for this is because the bozos who designed HTTP/1.1
		350	made it impossible to distinguish between a fatal error and a normal
		351	connection timeout, so you never know whether there was a problem with
		352	your request or not.
		353
		354	When reusing an existent connection, many parameters (such as TLS context)
		355	will be ignored. See the C<session> parameter for a workaround.
		356
		357	=item keepalive => $boolean
		358
		359	Only used when C<persistent> is also true. This parameter decides whether
		360	C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection
		361	(as opposed to only a HTTP/1.1 persistent connection).
		362
		363	The default is true, except when using a proxy, in which case it defaults
		364	to false, as HTTP/1.0 proxies cannot support this in a meaningful way.
		365
		366	=item handle_params => { key => value ... }
		367
		368	The key-value pairs in this hash will be passed to any L<AnyEvent::Handle>
		369	constructor that is called - not all requests will create a handle, and
		370	sometimes more than one is created, so this parameter is only good for
		371	setting hints.
		372
		373	Example: set the maximum read size to 4096, to potentially conserve memory
		374	at the cost of speed.
		375
		376	handle_params => {
		377	max_read_size => 4096,
		378	},
		379
293	=back	380	=back
294		381
295	Example: make a simple HTTP GET request for http://www.nethype.de/	382	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		383	the response body.
296		384
297	http_request GET => "http://www.nethype.de/", sub {	385	http_request GET => "http://www.nethype.de/", sub {
298	my ($body, $hdr) = @_;	386	my ($body, $hdr) = @_;
299	print "$body\n";	387	print "$body\n";
300	};	388	};
301		389
302	Example: make a HTTP HEAD request on https://www.google.com/, use a	390	Example: do a HTTP HEAD request on https://www.google.com/, use a
303	timeout of 30 seconds.	391	timeout of 30 seconds.
304		392
305	http_request	393	http_request
306	GET => "https://www.google.com",	394	HEAD => "https://www.google.com",
		395	headers => { "user-agent" => "MySearchClient 1.0" },
307	timeout => 30,	396	timeout => 30,
308	sub {	397	sub {
309	my ($body, $hdr) = @_;	398	my ($body, $hdr) = @_;
310	use Data::Dumper;	399	use Data::Dumper;
311	print Dumper $hdr;	400	print Dumper $hdr;
312	}	401	}
313	;	402	;
314		403
315	Example: make another simple HTTP GET request, but immediately try to	404	Example: do another simple HTTP GET request, but immediately try to
316	cancel it.	405	cancel it.
317		406
318	my $request = http_request GET => "http://www.nethype.de/", sub {	407	my $request = http_request GET => "http://www.nethype.de/", sub {
319	my ($body, $hdr) = @_;	408	my ($body, $hdr) = @_;
320	print "$body\n";	409	print "$body\n";
321	};	410	};
322		411
323	undef $request;	412	undef $request;
324		413
325	=cut	414	=cut
		415
		416	#############################################################################
		417	# wait queue/slots
326		418
327	sub _slot_schedule;	419	sub _slot_schedule;
328	sub _slot_schedule($) {	420	sub _slot_schedule($) {
329	my $host = shift;	421	my $host = shift;
330		422
…		…
352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	444	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
353		445
354	_slot_schedule $_[0];	446	_slot_schedule $_[0];
355	}	447	}
356		448
		449	#############################################################################
		450	# cookie handling
		451
		452	# expire cookies
		453	sub cookie_jar_expire($;$) {
		454	my ($jar, $session_end) = @_;
		455
		456	%$jar = () if $jar->{version} != 1;
		457
		458	my $anow = AE::now;
		459
		460	while (my ($chost, $paths) = each %$jar) {
		461	next unless ref $paths;
		462
		463	while (my ($cpath, $cookies) = each %$paths) {
		464	while (my ($cookie, $kv) = each %$cookies) {
		465	if (exists $kv->{_expires}) {
		466	delete $cookies->{$cookie}
		467	if $anow > $kv->{_expires};
		468	} elsif ($session_end) {
		469	delete $cookies->{$cookie};
		470	}
		471	}
		472
		473	delete $paths->{$cpath}
		474	unless %$cookies;
		475	}
		476
		477	delete $jar->{$chost}
		478	unless %$paths;
		479	}
		480	}
		481
		482	# extract cookies from jar
		483	sub cookie_jar_extract($$$$) {
		484	my ($jar, $scheme, $host, $path) = @_;
		485
		486	%$jar = () if $jar->{version} != 1;
		487
		488	my @cookies;
		489
		490	while (my ($chost, $paths) = each %$jar) {
		491	next unless ref $paths;
		492
		493	if ($chost =~ /^\./) {
		494	next unless $chost eq substr $host, -length $chost;
		495	} elsif ($chost =~ /\./) {
		496	next unless $chost eq $host;
		497	} else {
		498	next;
		499	}
		500
		501	while (my ($cpath, $cookies) = each %$paths) {
		502	next unless $cpath eq substr $path, 0, length $cpath;
		503
		504	while (my ($cookie, $kv) = each %$cookies) {
		505	next if $scheme ne "https" && exists $kv->{secure};
		506
		507	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		508	delete $cookies->{$cookie};
		509	next;
		510	}
		511
		512	my $value = $kv->{value};
		513
		514	if ($value =~ /[=;,[:space:]]/) {
		515	$value =~ s/([\\"])/\\$1/g;
		516	$value = "\"$value\"";
		517	}
		518
		519	push @cookies, "$cookie=$value";
		520	}
		521	}
		522	}
		523
		524	\@cookies
		525	}
		526
		527	# parse set_cookie header into jar
		528	sub cookie_jar_set_cookie($$$$) {
		529	my ($jar, $set_cookie, $host, $date) = @_;
		530
		531	my $anow = int AE::now;
		532	my $snow; # server-now
		533
		534	for ($set_cookie) {
		535	# parse NAME=VALUE
		536	my @kv;
		537
		538	# expires is not http-compliant in the original cookie-spec,
		539	# we support the official date format and some extensions
		540	while (
		541	m{
		542	\G\s*
		543	(?:
		544	expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+)
		545	| ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )?
		546	)
		547	}gcxsi
		548	) {
		549	my $name = $2;
		550	my $value = $4;
		551
		552	if (defined $1) {
		553	# expires
		554	$name = "expires";
		555	$value = $1;
		556	} elsif (defined $3) {
		557	# quoted
		558	$value = $3;
		559	$value =~ s/\\(.)/$1/gs;
		560	}
		561
		562	push @kv, @kv ? lc $name : $name, $value;
		563
		564	last unless /\G\s*;/gc;
		565	}
		566
		567	last unless @kv;
		568
		569	my $name = shift @kv;
		570	my %kv = (value => shift @kv, @kv);
		571
		572	if (exists $kv{"max-age"}) {
		573	$kv{_expires} = $anow + delete $kv{"max-age"};
		574	} elsif (exists $kv{expires}) {
		575	$snow ||= parse_date ($date) || $anow;
		576	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		577	} else {
		578	delete $kv{_expires};
		579	}
		580
		581	my $cdom;
		582	my $cpath = (delete $kv{path}) || "/";
		583
		584	if (exists $kv{domain}) {
		585	$cdom = delete $kv{domain};
		586
		587	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		588
		589	next if $cdom =~ /\.$/;
		590
		591	# this is not rfc-like and not netscape-like. go figure.
		592	my $ndots = $cdom =~ y/.//;
		593	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		594	} else {
		595	$cdom = $host;
		596	}
		597
		598	# store it
		599	$jar->{version} = 1;
		600	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		601
		602	redo if /\G\s*,/gc;
		603	}
		604	}
		605
		606	#############################################################################
		607	# keepalive/persistent connection cache
		608
		609	# fetch a connection from the keepalive cache
		610	sub ka_fetch($) {
		611	my $ka_key = shift;
		612
		613	my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection
		614	delete $KA_CACHE{$ka_key}
		615	unless @{ $KA_CACHE{$ka_key} };
		616
		617	$hdl
		618	}
		619
		620	sub ka_store($$) {
		621	my ($ka_key, $hdl) = @_;
		622
		623	my $kaa = $KA_CACHE{$ka_key} ||= [];
		624
		625	my $destroy = sub {
		626	my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} };
		627
		628	$hdl->destroy;
		629
		630	@ka
		631	? $KA_CACHE{$ka_key} = \@ka
		632	: delete $KA_CACHE{$ka_key};
		633	};
		634
		635	# on error etc., destroy
		636	$hdl->on_error ($destroy);
		637	$hdl->on_eof ($destroy);
		638	$hdl->on_read ($destroy);
		639	$hdl->timeout ($PERSISTENT_TIMEOUT);
		640
		641	push @$kaa, $hdl;
		642	shift @$kaa while @$kaa > $MAX_PER_HOST;
		643	}
		644
		645	#############################################################################
		646	# utilities
		647
357	# continue to parse $_ for headers and place them into the arg	648	# continue to parse $_ for headers and place them into the arg
358	sub parse_hdr() {	649	sub _parse_hdr() {
359	my %hdr;	650	my %hdr;
360		651
361	# things seen, not parsed:	652	# things seen, not parsed:
362	# p3pP="NON CUR OTPi OUR NOR UNI"	653	# p3pP="NON CUR OTPi OUR NOR UNI"
363		654
…		…
377	for values %hdr;	668	for values %hdr;
378		669
379	\%hdr	670	\%hdr
380	}	671	}
381		672
		673	#############################################################################
		674	# http_get
		675
382	our $qr_nlnl = qr{(?<![^\012])\015?\012};	676	our $qr_nlnl = qr{(?<![^\012])\015?\012};
383		677
384	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	678	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
385	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	679	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		680
		681	# maybe it should just become a normal object :/
		682
		683	sub _destroy_state(\%) {
		684	my ($state) = @_;
		685
		686	$state->{handle}->destroy if $state->{handle};
		687	%$state = ();
		688	}
		689
		690	sub _error(\%$$) {
		691	my ($state, $cb, $hdr) = @_;
		692
		693	&_destroy_state ($state);
		694
		695	$cb->(undef, $hdr);
		696	()
		697	}
		698
		699	our %IDEMPOTENT = (
		700	DELETE => 1,
		701	GET => 1,
		702	HEAD => 1,
		703	OPTIONS => 1,
		704	PUT => 1,
		705	TRACE => 1,
		706
		707	ACL => 1,
		708	"BASELINE-CONTROL" => 1,
		709	BIND => 1,
		710	CHECKIN => 1,
		711	CHECKOUT => 1,
		712	COPY => 1,
		713	LABEL => 1,
		714	LINK => 1,
		715	MERGE => 1,
		716	MKACTIVITY => 1,
		717	MKCALENDAR => 1,
		718	MKCOL => 1,
		719	MKREDIRECTREF => 1,
		720	MKWORKSPACE => 1,
		721	MOVE => 1,
		722	ORDERPATCH => 1,
		723	PROPFIND => 1,
		724	PROPPATCH => 1,
		725	REBIND => 1,
		726	REPORT => 1,
		727	SEARCH => 1,
		728	UNBIND => 1,
		729	UNCHECKOUT => 1,
		730	UNLINK => 1,
		731	UNLOCK => 1,
		732	UPDATE => 1,
		733	UPDATEREDIRECTREF => 1,
		734	"VERSION-CONTROL" => 1,
		735	);
386		736
387	sub http_request($$@) {	737	sub http_request($$@) {
388	my $cb = pop;	738	my $cb = pop;
389	my ($method, $url, %arg) = @_;	739	my ($method, $url, %arg) = @_;
390		740
…		…
408	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	758	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
409		759
410	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })	760	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
411	if $recurse < 0;	761	if $recurse < 0;
412		762
413	my $proxy = $arg{proxy} || $PROXY;	763	my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY;
414	my $timeout = $arg{timeout} || $TIMEOUT;	764	my $timeout = $arg{timeout} || $TIMEOUT;
415		765
416	my ($uscheme, $uauthority, $upath, $query, $fragment) =	766	my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment
417	$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|;	767	$url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|;
418		768
419	$uscheme = lc $uscheme;	769	$uscheme = lc $uscheme;
420		770
421	my $uport = $uscheme eq "http" ? 80	771	my $uport = $uscheme eq "http" ? 80
422	: $uscheme eq "https" ? 443	772	: $uscheme eq "https" ? 443
423	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });	773	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
424		774
425	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	775	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
426	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });	776	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
427		777
428	my $uhost = $1;	778	my $uhost = lc $1;
429	$uport = $2 if defined $2;	779	$uport = $2 if defined $2;
430		780
431	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	781	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
432	unless exists $hdr{host};	782	unless exists $hdr{host};
433		783
…		…
436		786
437	$upath =~ s%^/?%/%;	787	$upath =~ s%^/?%/%;
438		788
439	# cookie processing	789	# cookie processing
440	if (my $jar = $arg{cookie_jar}) {	790	if (my $jar = $arg{cookie_jar}) {
441	%$jar = () if $jar->{version} != 1;	791	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
442		792
443	my @cookie;
444
445	while (my ($chost, $v) = each %$jar) {
446	if ($chost =~ /^\./) {
447	next unless $chost eq substr $uhost, -length $chost;
448	} elsif ($chost =~ /\./) {
449	next unless $chost eq $uhost;
450	} else {
451	next;
452	}
453
454	while (my ($cpath, $v) = each %$v) {
455	next unless $cpath eq substr $upath, 0, length $cpath;
456
457	while (my ($k, $v) = each %$v) {
458	next if $uscheme ne "https" && exists $v->{secure};
459	my $value = $v->{value};
460	$value =~ s/([\\"])/\\$1/g;
461	push @cookie, "$k=\"$value\"";
462	}
463	}
464	}
465
466	$hdr{cookie} = join "; ", @cookie	793	$hdr{cookie} = join "; ", @$cookies
467	if @cookie;	794	if @$cookies;
468	}	795	}
469		796
470	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	797	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
471		798
472	if ($proxy) {	799	if ($proxy) {
…		…
475	$rscheme = "http" unless defined $rscheme;	802	$rscheme = "http" unless defined $rscheme;
476		803
477	# don't support https requests over https-proxy transport,	804	# don't support https requests over https-proxy transport,
478	# can't be done with tls as spec'ed, unless you double-encrypt.	805	# can't be done with tls as spec'ed, unless you double-encrypt.
479	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	806	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		807
		808	$rhost = lc $rhost;
		809	$rscheme = lc $rscheme;
480	} else {	810	} else {
481	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	811	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
482	}	812	}
483		813
484	# leave out fragment and query string, just a heuristic	814	# leave out fragment and query string, just a heuristic
…		…
486	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};	816	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
487		817
488	$hdr{"content-length"} = length $arg{body}	818	$hdr{"content-length"} = length $arg{body}
489	if length $arg{body} || $method ne "GET";	819	if length $arg{body} || $method ne "GET";
490		820
491	$hdr{connection} = "close TE";	821	my $idempotent = $IDEMPOTENT{$method};
		822
		823	# default value for keepalive is true iff the request is for an idempotent method
		824	my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent;
		825	my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy;
		826	my $was_persistent; # true if this is actually a recycled connection
		827
		828	# the key to use in the keepalive cache
		829	my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}";
		830
		831	$hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1
492	$hdr{te} = "trailers" unless exists $hdr{te};	832	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
493		833
494	my %state = (connect_guard => 1);	834	my %state = (connect_guard => 1);
		835
		836	my $ae_error = 595; # connecting
		837
		838	# handle actual, non-tunneled, request
		839	my $handle_actual_request = sub {
		840	$ae_error = 596; # request phase
		841
		842	my $hdl = $state{handle};
		843
		844	$hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls};
		845
		846	# send request
		847	$hdl->push_write (
		848	"$method $rpath HTTP/1.1\015\012"
		849	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		850	. "\015\012"
		851	. $arg{body}
		852	);
		853
		854	# return if error occurred during push_write()
		855	return unless %state;
		856
		857	# reduce memory usage, save a kitten, also re-use it for the response headers.
		858	%hdr = ();
		859
		860	# status line and headers
		861	$state{read_response} = sub {
		862	return unless %state;
		863
		864	for ("$_[1]") {
		865	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		866
		867	/^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci
		868	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" };
		869
		870	# 100 Continue handling
		871	# should not happen as we don't send expect: 100-continue,
		872	# but we handle it just in case.
		873	# since we send the request body regardless, if we get an error
		874	# we are out of-sync, which we currently do NOT handle correctly.
		875	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		876	if $2 eq 100;
		877
		878	push @pseudo,
		879	HTTPVersion => $1,
		880	Status => $2,
		881	Reason => $3,
		882	;
		883
		884	my $hdr = _parse_hdr
		885	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" };
		886
		887	%hdr = (%$hdr, @pseudo);
		888	}
		889
		890	# redirect handling
		891	# relative uri handling forced by microsoft and other shitheads.
		892	# we give our best and fall back to URI if available.
		893	if (exists $hdr{location}) {
		894	my $loc = $hdr{location};
		895
		896	if ($loc =~ m%^//%) { # //
		897	$loc = "$rscheme:$loc";
		898
		899	} elsif ($loc eq "") {
		900	$loc = $url;
		901
		902	} elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple"
		903	$loc =~ s/^\.\/+//;
		904
		905	if ($loc !~ m%^[.?#]%) {
		906	my $prefix = "$rscheme://$uhost:$uport";
		907
		908	unless ($loc =~ s/^\///) {
		909	$prefix .= $upath;
		910	$prefix =~ s/\/[^\/]*$//;
		911	}
		912
		913	$loc = "$prefix/$loc";
		914
		915	} elsif (eval { require URI }) { # uri
		916	$loc = URI->new_abs ($loc, $url)->as_string;
		917
		918	} else {
		919	return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" };
		920	#$hdr{Status} = 599;
		921	#$hdr{Reason} = "Unparsable Redirect (URI module missing)";
		922	#$recurse = 0;
		923	}
		924	}
		925
		926	$hdr{location} = $loc;
		927	}
		928
		929	my $redirect;
		930
		931	if ($recurse) {
		932	my $status = $hdr{Status};
		933
		934	# industry standard is to redirect POST as GET for
		935	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		936	# also, the UA should ask the user for 301 and 307 and POST,
		937	# industry standard seems to be to simply follow.
		938	# we go with the industry standard. 308 is defined
		939	# by rfc7538
		940	if ($status == 301 or $status == 302 or $status == 303) {
		941	$redirect = 1;
		942	# HTTP/1.1 is unclear on how to mutate the method
		943	unless ($method eq "HEAD") {
		944	$method = "GET";
		945	delete $arg{body};
		946	}
		947	} elsif ($status == 307 or $status == 308) {
		948	$redirect = 1;
		949	}
		950	}
		951
		952	my $finish = sub { # ($data, $err_status, $err_reason[, $persistent])
		953	if ($state{handle}) {
		954	# handle keepalive
		955	if (
		956	$persistent
		957	&& $_[3]
		958	&& ($hdr{HTTPVersion} < 1.1
		959	? $hdr{connection} =~ /\bkeep-?alive\b/i
		960	: $hdr{connection} !~ /\bclose\b/i)
		961	) {
		962	ka_store $ka_key, delete $state{handle};
		963	} else {
		964	# no keepalive, destroy the handle
		965	$state{handle}->destroy;
		966	}
		967	}
		968
		969	%state = ();
		970
		971	if (defined $_[1]) {
		972	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		973	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		974	}
		975
		976	# set-cookie processing
		977	if ($arg{cookie_jar}) {
		978	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		979	}
		980
		981	if ($redirect && exists $hdr{location}) {
		982	# we ignore any errors, as it is very common to receive
		983	# Content-Length != 0 but no actual body
		984	# we also access %hdr, as $_[1] might be an erro
		985	$state{recurse} =
		986	http_request (
		987	$method => $hdr{location},
		988	%arg,
		989	recurse => $recurse - 1,
		990	Redirect => [$_[0], \%hdr],
		991	sub {
		992	%state = ();
		993	&$cb
		994	},
		995	);
		996	} else {
		997	$cb->($_[0], \%hdr);
		998	}
		999	};
		1000
		1001	$ae_error = 597; # body phase
		1002
		1003	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		1004
		1005	my $len = $chunked ? undef : $hdr{"content-length"};
		1006
		1007	# body handling, many different code paths
		1008	# - no body expected
		1009	# - want_body_handle
		1010	# - te chunked
		1011	# - 2x length known (with or without on_body)
		1012	# - 2x length not known (with or without on_body)
		1013	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		1014	$finish->(undef, 598 => "Request cancelled by on_header");
		1015	} elsif (
		1016	$hdr{Status} =~ /^(?:1..|204|205|304)$/
		1017	or $method eq "HEAD"
		1018	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		1019	) {
		1020	# no body
		1021	$finish->("", undef, undef, 1);
		1022
		1023	} elsif (!$redirect && $arg{want_body_handle}) {
		1024	$_[0]->on_eof (undef);
		1025	$_[0]->on_error (undef);
		1026	$_[0]->on_read (undef);
		1027
		1028	$finish->(delete $state{handle});
		1029
		1030	} elsif ($chunked) {
		1031	my $cl = 0;
		1032	my $body = "";
		1033	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
		1034
		1035	$state{read_chunk} = sub {
		1036	$_[1] =~ /^([0-9a-fA-F]+)/
		1037	or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1038
		1039	my $len = hex $1;
		1040
		1041	if ($len) {
		1042	$cl += $len;
		1043
		1044	$_[0]->push_read (chunk => $len, sub {
		1045	$on_body->($_[1], \%hdr)
		1046	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1047
		1048	$_[0]->push_read (line => sub {
		1049	length $_[1]
		1050	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		1051	$_[0]->push_read (line => $state{read_chunk});
		1052	});
		1053	});
		1054	} else {
		1055	$hdr{"content-length"} ||= $cl;
		1056
		1057	$_[0]->push_read (line => $qr_nlnl, sub {
		1058	if (length $_[1]) {
		1059	for ("$_[1]") {
		1060	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		1061
		1062	my $hdr = _parse_hdr
		1063	or return $finish->(undef, $ae_error => "Garbled response trailers");
		1064
		1065	%hdr = (%hdr, %$hdr);
		1066	}
		1067	}
		1068
		1069	$finish->($body, undef, undef, 1);
		1070	});
		1071	}
		1072	};
		1073
		1074	$_[0]->push_read (line => $state{read_chunk});
		1075
		1076	} elsif ($arg{on_body}) {
		1077	if (defined $len) {
		1078	$_[0]->on_read (sub {
		1079	$len -= length $_[0]{rbuf};
		1080
		1081	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1082	or return $finish->(undef, 598 => "Request cancelled by on_body");
		1083
		1084	$len > 0
		1085	or $finish->("", undef, undef, 1);
		1086	});
		1087	} else {
		1088	$_[0]->on_eof (sub {
		1089	$finish->("");
		1090	});
		1091	$_[0]->on_read (sub {
		1092	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		1093	or $finish->(undef, 598 => "Request cancelled by on_body");
		1094	});
		1095	}
		1096	} else {
		1097	$_[0]->on_eof (undef);
		1098
		1099	if (defined $len) {
		1100	$_[0]->on_read (sub {
		1101	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		1102	if $len <= length $_[0]{rbuf};
		1103	});
		1104	} else {
		1105	$_[0]->on_error (sub {
		1106	($! == Errno::EPIPE || !$!)
		1107	? $finish->(delete $_[0]{rbuf})
		1108	: $finish->(undef, $ae_error => $_[2]);
		1109	});
		1110	$_[0]->on_read (sub { });
		1111	}
		1112	}
		1113	};
		1114
		1115	# if keepalive is enabled, then the server closing the connection
		1116	# before a response can happen legally - we retry on idempotent methods.
		1117	if ($was_persistent && $idempotent) {
		1118	my $old_eof = $hdl->{on_eof};
		1119	$hdl->{on_eof} = sub {
		1120	_destroy_state %state;
		1121
		1122	%state = ();
		1123	$state{recurse} =
		1124	http_request (
		1125	$method => $url,
		1126	%arg,
		1127	recurse => $recurse - 1,
		1128	keepalive => 0,
		1129	sub {
		1130	%state = ();
		1131	&$cb
		1132	}
		1133	);
		1134	};
		1135	$hdl->on_read (sub {
		1136	return unless %state;
		1137
		1138	# as soon as we receive something, a connection close
		1139	# once more becomes a hard error
		1140	$hdl->{on_eof} = $old_eof;
		1141	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1142	});
		1143	} else {
		1144	$hdl->push_read (line => $qr_nlnl, $state{read_response});
		1145	}
		1146	};
		1147
		1148	my $prepare_handle = sub {
		1149	my ($hdl) = $state{handle};
		1150
		1151	$hdl->on_error (sub {
		1152	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] };
		1153	});
		1154	$hdl->on_eof (sub {
		1155	_error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" };
		1156	});
		1157	$hdl->timeout_reset;
		1158	$hdl->timeout ($timeout);
		1159	};
		1160
		1161	# connected to proxy (or origin server)
		1162	my $connect_cb = sub {
		1163	my $fh = shift
		1164	or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" };
		1165
		1166	return unless delete $state{connect_guard};
		1167
		1168	# get handle
		1169	$state{handle} = new AnyEvent::Handle
		1170	%{ $arg{handle_params} },
		1171	fh => $fh,
		1172	peername => $uhost,
		1173	tls_ctx => $arg{tls_ctx},
		1174	;
		1175
		1176	$prepare_handle->();
		1177
		1178	#$state{handle}->starttls ("connect") if $rscheme eq "https";
		1179
		1180	# now handle proxy-CONNECT method
		1181	if ($proxy && $uscheme eq "https") {
		1182	# oh dear, we have to wrap it into a connect request
		1183
		1184	my $auth = exists $hdr{"proxy-authorization"}
		1185	? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012"
		1186	: "";
		1187
		1188	# maybe re-use $uauthority with patched port?
		1189	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012");
		1190	$state{handle}->push_read (line => $qr_nlnl, sub {
		1191	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		1192	or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" };
		1193
		1194	if ($2 == 200) {
		1195	$rpath = $upath;
		1196	$handle_actual_request->();
		1197	} else {
		1198	_error %state, $cb, { @pseudo, Status => $2, Reason => $3 };
		1199	}
		1200	});
		1201	} else {
		1202	delete $hdr{"proxy-authorization"} unless $proxy;
		1203
		1204	$handle_actual_request->();
		1205	}
		1206	};
495		1207
496	_get_slot $uhost, sub {	1208	_get_slot $uhost, sub {
497	$state{slot_guard} = shift;	1209	$state{slot_guard} = shift;
498		1210
499	return unless $state{connect_guard};	1211	return unless $state{connect_guard};
500		1212
501	my $connect_cb = sub {	1213	# try to use an existing keepalive connection, but only if we, ourselves, plan
502	$state{fh} = shift	1214	# on a keepalive request (in theory, this should be a separate config option).
503	or do {	1215	if ($persistent && $KA_CACHE{$ka_key}) {
504	my $err = "$!";	1216	$was_persistent = 1;
505	%state = ();
506	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
507	};
508		1217
509	pop; # free memory, save a tree	1218	$state{handle} = ka_fetch $ka_key;
510
511	return unless delete $state{connect_guard};
512
513	# get handle
514	$state{handle} = new AnyEvent::Handle
515	fh => $state{fh},
516	peername => $rhost,
517	tls_ctx => $arg{tls_ctx},
518	# these need to be reconfigured on keepalive handles
519	timeout => $timeout,
520	on_error => sub {
521	%state = ();
522	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
523	},
524	on_eof => sub {
525	%state = ();
526	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
527	},
528	;
529
530	# limit the number of persistent connections
531	# keepalive not yet supported
532	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
533	# ++$KA_COUNT{$_[1]};
534	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
535	# --$KA_COUNT{$_[1]}
536	# };
537	# $hdr{connection} = "keep-alive";
538	# } else {
539	# delete $hdr{connection};
540	# }
541
542	$state{handle}->starttls ("connect") if $rscheme eq "https";
543
544	# handle actual, non-tunneled, request
545	my $handle_actual_request = sub {
546	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
547
548	# send request
549	$state{handle}->push_write (	1219	$state{handle}->destroyed
550	"$method $rpath HTTP/1.1\015\012"	1220	and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d#
551	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)	1221	$prepare_handle->();
552	. "\015\012"	1222	$state{handle}->destroyed
553	. (delete $arg{body})	1223	and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d#
554	);
555
556	# return if error occured during push_write()
557	return unless %state;
558
559	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
560
561	# status line and headers
562	$state{handle}->push_read (line => $qr_nlnl, sub {
563	my $keepalive = pop;
564
565	for ("$_[1]") {
566	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
567
568	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
569	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
570
571	push @pseudo,
572	HTTPVersion => $1,
573	Status => $2,
574	Reason => $3,
575	;
576
577	my $hdr = parse_hdr
578	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
579
580	%hdr = (%$hdr, @pseudo);
581	}
582
583	# redirect handling
584	# microsoft and other shitheads don't give a shit for following standards,
585	# try to support some common forms of broken Location headers.
586	if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
587	$hdr{location} =~ s/^\.\/+//;
588
589	my $url = "$rscheme://$uhost:$uport";
590
591	unless ($hdr{location} =~ s/^\///) {
592	$url .= $upath;
593	$url =~ s/\/[^\/]*$//;
594	}
595
596	$hdr{location} = "$url/$hdr{location}";
597	}
598
599	my $redirect;
600
601	if ($recurse) {
602	my $status = $hdr{Status};
603
604	# industry standard is to redirect POST as GET for
605	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
606	# also, the UA should ask the user for 301 and 307 and POST,
607	# industry standard seems to be to simply follow.
608	# we go with the industry standard.
609	if ($status == 301 or $status == 302 or $status == 303) {
610	# HTTP/1.1 is unclear on how to mutate the method
611	$method = "GET" unless $method eq "HEAD";
612	$redirect = 1;
613	} elsif ($status == 307) {
614	$redirect = 1;
615	}
616	}
617
618	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
619	$state{handle}->destroy if $state{handle};
620	%state = ();
621
622	if (defined $_[1]) {
623	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
624	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
625	}
626
627	# set-cookie processing
628	if ($arg{cookie_jar}) {
629	for ($hdr{"set-cookie"}) {
630	# parse NAME=VALUE
631	my @kv;
632
633	while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
634	my $name = $1;
635	my $value = $3;
636
637	unless ($value) {
638	$value = $2;
639	$value =~ s/\\(.)/$1/gs;
640	}
641
642	push @kv, $name => $value;
643
644	last unless /\G\s*;/gc;
645	}
646
647	last unless @kv;
648
649	my $name = shift @kv;
650	my %kv = (value => shift @kv, @kv);
651
652	my $cdom;
653	my $cpath = (delete $kv{path}) || "/";
654
655	if (exists $kv{domain}) {
656	$cdom = delete $kv{domain};
657
658	$cdom =~ s/^\.?/./; # make sure it starts with a "."
659
660	next if $cdom =~ /\.$/;
661
662	# this is not rfc-like and not netscape-like. go figure.
663	my $ndots = $cdom =~ y/.//;
664	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
665	} else {
666	$cdom = $uhost;
667	}
668
669	# store it
670	$arg{cookie_jar}{version} = 1;
671	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
672
673	redo if /\G\s*,/gc;
674	}
675	}
676
677	if ($redirect && exists $hdr{location}) {
678	# we ignore any errors, as it is very common to receive
679	# Content-Length != 0 but no actual body
680	# we also access %hdr, as $_[1] might be an erro
681	http_request (
682	$method => $hdr{location},
683	%arg,
684	recurse => $recurse - 1,
685	Redirect => [$_[0], \%hdr],
686	$cb);
687	} else {
688	$cb->($_[0], \%hdr);
689	}
690	};
691
692	my $len = $hdr{"content-length"};
693
694	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
695	$finish->(undef, 598 => "Request cancelled by on_header");
696	} elsif (
697	$hdr{Status} =~ /^(?:1..|204|205|304)$/
698	or $method eq "HEAD"
699	or (defined $len && !$len)
700	) {
701	# no body
702	$finish->("", undef, undef, 1);
703	} else {
704	# body handling, many different code paths
705	# - no body expected
706	# - want_body_handle
707	# - te chunked
708	# - 2x length known (with or without on_body)
709	# - 2x length not known (with or without on_body)
710	if (!$redirect && $arg{want_body_handle}) {
711	$_[0]->on_eof (undef);
712	$_[0]->on_error (undef);
713	$_[0]->on_read (undef);
714
715	$finish->(delete $state{handle});
716
717	} elsif ($hdr{"transfer-encoding"} =~ /chunked/) {
718	my $body = undef;
719	my $on_body = $arg{on_body} || sub { $body .= shift; 1 };
720
721	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
722
723	my $read_chunk; $read_chunk = sub {
724	$_[1] =~ /^([0-9a-fA-F]+)/
725	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
726
727	my $len = hex $1;
728
729	if ($len) {
730	$_[0]->push_read (chunk => hex $1, sub {
731	$on_body->($_[1], \%hdr)
732	or return $finish->(undef, 598 => "Request cancelled by on_body");
733
734	$_[0]->push_read (line => sub {
735	length $_[1]
736	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
737	$_[0]->push_read (line => $read_chunk);
738	});
739	});
740	} else {
741	$_[0]->push_read (line => $qr_nlnl, sub {
742	if (length $_[1]) {
743	for ("$_[1]") {
744	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
745
746	my $hdr = parse_hdr
747	or return $finish->(undef, 599 => "Garbled response trailers");
748
749	%hdr = (%hdr, %$hdr);
750	}
751	}
752
753	$finish->($body, undef, undef, 1);
754	});
755	}
756	};
757
758	$_[0]->push_read (line => $read_chunk);
759
760	} elsif ($arg{on_body}) {
761	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
762
763	if ($len) {
764	$_[0]->on_read (sub {
765	$len -= length $_[0]{rbuf};
766
767	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
768	or return $finish->(undef, 598 => "Request cancelled by on_body");
769
770	$len > 0
771	or $finish->("", undef, undef, 1);
772	});
773	} else {
774	$_[0]->on_eof (sub {
775	$finish->("");
776	});
777	$_[0]->on_read (sub {
778	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
779	or $finish->(undef, 598 => "Request cancelled by on_body");
780	});
781	}
782	} else {
783	$_[0]->on_eof (undef);
784
785	if ($len) {
786	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
787	$_[0]->on_read (sub {
788	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
789	if $len <= length $_[0]{rbuf};
790	});
791	} else {
792	$_[0]->on_error (sub {
793	($! == Errno::EPIPE || !$!)
794	? $finish->(delete $_[0]{rbuf})
795	: $finish->(undef, 599 => $_[2]);
796	});
797	$_[0]->on_read (sub { });
798	}
799	}
800	}
801	});
802	};
803
804	# now handle proxy-CONNECT method
805	if ($proxy && $uscheme eq "https") {
806	# oh dear, we have to wrap it into a connect request
807
808	# maybe re-use $uauthority with patched port?
809	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
810	$state{handle}->push_read (line => $qr_nlnl, sub {
811	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
812	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
813
814	if ($2 == 200) {
815	$rpath = $upath;
816	&$handle_actual_request;	1224	$handle_actual_request->();
817	} else {	1225
818	%state = ();
819	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
820	}
821	});
822	} else {	1226	} else {
823	&$handle_actual_request;
824	}
825	};
826
827	my $tcp_connect = $arg{tcp_connect}	1227	my $tcp_connect = $arg{tcp_connect}
828	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };	1228	|| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
829		1229
830	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });	1230	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout });
831		1231	}
832	};	1232	};
833		1233
834	defined wantarray && AnyEvent::Util::guard { %state = () }	1234	defined wantarray && AnyEvent::Util::guard { _destroy_state %state }
835	}	1235	}
836		1236
837	sub http_get($@) {	1237	sub http_get($@) {
838	unshift @_, "GET";	1238	unshift @_, "GET";
839	&http_request	1239	&http_request
…		…
857	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for	1257	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
858	the actual connection, which in turn uses AnyEvent::DNS to resolve	1258	the actual connection, which in turn uses AnyEvent::DNS to resolve
859	hostnames. The latter is a simple stub resolver and does no caching	1259	hostnames. The latter is a simple stub resolver and does no caching
860	on its own. If you want DNS caching, you currently have to provide	1260	on its own. If you want DNS caching, you currently have to provide
861	your own default resolver (by storing a suitable resolver object in	1261	your own default resolver (by storing a suitable resolver object in
862	C<$AnyEvent::DNS::RESOLVER>).	1262	C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback.
863		1263
864	=head2 GLOBAL FUNCTIONS AND VARIABLES	1264	=head2 GLOBAL FUNCTIONS AND VARIABLES
865		1265
866	=over 4	1266	=over 4
867		1267
868	=item AnyEvent::HTTP::set_proxy "proxy-url"	1268	=item AnyEvent::HTTP::set_proxy "proxy-url"
869		1269
870	Sets the default proxy server to use. The proxy-url must begin with a	1270	Sets the default proxy server to use. The proxy-url must begin with a
871	string of the form C<http://host:port> (optionally C<https:...>), croaks	1271	string of the form C<http://host:port>, croaks otherwise.
872	otherwise.
873		1272
874	To clear an already-set proxy, use C<undef>.	1273	To clear an already-set proxy, use C<undef>.
		1274
		1275	When AnyEvent::HTTP is loaded for the first time it will query the
		1276	default proxy from the operating system, currently by looking at
		1277	C<$ENV{http_proxy>}.
		1278
		1279	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1280
		1281	Remove all cookies from the cookie jar that have been expired. If
		1282	C<$session_end> is given and true, then additionally remove all session
		1283	cookies.
		1284
		1285	You should call this function (with a true C<$session_end>) before you
		1286	save cookies to disk, and you should call this function after loading them
		1287	again. If you have a long-running program you can additionally call this
		1288	function from time to time.
		1289
		1290	A cookie jar is initially an empty hash-reference that is managed by this
		1291	module. Its format is subject to change, but currently it is as follows:
		1292
		1293	The key C<version> has to contain C<1>, otherwise the hash gets
		1294	emptied. All other keys are hostnames or IP addresses pointing to
		1295	hash-references. The key for these inner hash references is the
		1296	server path for which this cookie is meant, and the values are again
		1297	hash-references. Each key of those hash-references is a cookie name, and
		1298	the value, you guessed it, is another hash-reference, this time with the
		1299	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1300	which have been replaced by a C<_expires> key that contains the cookie
		1301	expiry timestamp. Session cookies are indicated by not having an
		1302	C<_expires> key.
		1303
		1304	Here is an example of a cookie jar with a single cookie, so you have a
		1305	chance of understanding the above paragraph:
		1306
		1307	{
		1308	version => 1,
		1309	"10.0.0.1" => {
		1310	"/" => {
		1311	"mythweb_id" => {
		1312	_expires => 1293917923,
		1313	value => "ooRung9dThee3ooyXooM1Ohm",
		1314	},
		1315	},
		1316	},
		1317	}
875		1318
876	=item $date = AnyEvent::HTTP::format_date $timestamp	1319	=item $date = AnyEvent::HTTP::format_date $timestamp
877		1320
878	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP	1321	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
879	Date (RFC 2616).	1322	Date (RFC 2616).
880		1323
881	=item $timestamp = AnyEvent::HTTP::parse_date $date	1324	=item $timestamp = AnyEvent::HTTP::parse_date $date
882		1325
883	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX	1326	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1327	bunch of minor variations of those, and returns the corresponding POSIX
884	timestamp, or C<undef> if the date cannot be parsed.	1328	timestamp, or C<undef> if the date cannot be parsed.
885		1329
886	=item $AnyEvent::HTTP::MAX_RECURSE	1330	=item $AnyEvent::HTTP::MAX_RECURSE
887		1331
888	The default value for the C<recurse> request parameter (default: C<10>).	1332	The default value for the C<recurse> request parameter (default: C<10>).
		1333
		1334	=item $AnyEvent::HTTP::TIMEOUT
		1335
		1336	The default timeout for connection operations (default: C<300>).
889		1337
890	=item $AnyEvent::HTTP::USERAGENT	1338	=item $AnyEvent::HTTP::USERAGENT
891		1339
892	The default value for the C<User-Agent> header (the default is	1340	The default value for the C<User-Agent> header (the default is
893	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1341	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
894		1342
895	=item $AnyEvent::HTTP::MAX_PER_HOST	1343	=item $AnyEvent::HTTP::MAX_PER_HOST
896		1344
897	The maximum number of concurrent connections to the same host (identified	1345	The maximum number of concurrent connections to the same host (identified
898	by the hostname). If the limit is exceeded, then the additional requests	1346	by the hostname). If the limit is exceeded, then additional requests
899	are queued until previous connections are closed.	1347	are queued until previous connections are closed. Both persistent and
		1348	non-persistent connections are counted in this limit.
900		1349
901	The default value for this is C<4>, and it is highly advisable to not	1350	The default value for this is C<4>, and it is highly advisable to not
902	increase it.	1351	increase it much.
		1352
		1353	For comparison: the RFC's recommend 4 non-persistent or 2 persistent
		1354	connections, older browsers used 2, newer ones (such as firefox 3)
		1355	typically use 6, and Opera uses 8 because like, they have the fastest
		1356	browser and give a shit for everybody else on the planet.
		1357
		1358	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
		1359
		1360	The time after which idle persistent connections get closed by
		1361	AnyEvent::HTTP (default: C<3>).
903		1362
904	=item $AnyEvent::HTTP::ACTIVE	1363	=item $AnyEvent::HTTP::ACTIVE
905		1364
906	The number of active connections. This is not the number of currently	1365	The number of active connections. This is not the number of currently
907	running requests, but the number of currently open and non-idle TCP	1366	running requests, but the number of currently open and non-idle TCP
908	connections. This number of can be useful for load-leveling.	1367	connections. This number can be useful for load-leveling.
909		1368
910	=back	1369	=back
911		1370
912	=cut	1371	=cut
913		1372
…		…
928	sub parse_date($) {	1387	sub parse_date($) {
929	my ($date) = @_;	1388	my ($date) = @_;
930		1389
931	my ($d, $m, $y, $H, $M, $S);	1390	my ($d, $m, $y, $H, $M, $S);
932		1391
933	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$/) {	1392	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$/) {
934	# RFC 822/1123, required by RFC 2616	1393	# RFC 822/1123, required by RFC 2616 (with " ")
		1394	# cookie dates (with "-")
		1395
935	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);	1396	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
936		1397
937	} 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$/) {	1398	} elsif ($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]?) GMT$/) {
938	# RFC 850	1399	# RFC 850
939	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);	1400	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
940		1401
941	} 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])$/) {	1402	} 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])$/) {
942	# ISO C's asctime	1403	# ISO C's asctime
943	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);	1404	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
944	}	1405	}
945	# other formats fail in the loop below	1406	# other formats fail in the loop below
946		1407
947	for (0..11) {	1408	for (0..11) {
948	if ($m eq $month[$_]) {	1409	if ($m eq $month[$_]) {
949	require Time::Local;	1410	require Time::Local;
950	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);	1411	return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) };
951	}	1412	}
952	}	1413	}
953		1414
954	undef	1415	undef
955	}	1416	}
956		1417
957	sub set_proxy($) {	1418	sub set_proxy($) {
958	if (length $_[0]) {	1419	if (length $_[0]) {
959	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1420	$_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix
960	or Carp::croak "$_[0]: invalid proxy URL";	1421	or Carp::croak "$_[0]: invalid proxy URL";
961	$PROXY = [$2, $3 || 3128, $1]	1422	$PROXY = [$2, $3 || 3128, $1]
962	} else {	1423	} else {
963	undef $PROXY;	1424	undef $PROXY;
964	}	1425	}
…		…
967	# initialise proxy from environment	1428	# initialise proxy from environment
968	eval {	1429	eval {
969	set_proxy $ENV{http_proxy};	1430	set_proxy $ENV{http_proxy};
970	};	1431	};
971		1432
		1433	=head2 SHOWCASE
		1434
		1435	This section contains some more elaborate "real-world" examples or code
		1436	snippets.
		1437
		1438	=head2 HTTP/1.1 FILE DOWNLOAD
		1439
		1440	Downloading files with HTTP can be quite tricky, especially when something
		1441	goes wrong and you want to resume.
		1442
		1443	Here is a function that initiates and resumes a download. It uses the
		1444	last modified time to check for file content changes, and works with many
		1445	HTTP/1.0 servers as well, and usually falls back to a complete re-download
		1446	on older servers.
		1447
		1448	It calls the completion callback with either C<undef>, which means a
		1449	nonretryable error occurred, C<0> when the download was partial and should
		1450	be retried, and C<1> if it was successful.
		1451
		1452	use AnyEvent::HTTP;
		1453
		1454	sub download($$$) {
		1455	my ($url, $file, $cb) = @_;
		1456
		1457	open my $fh, "+<", $file
		1458	or die "$file: $!";
		1459
		1460	my %hdr;
		1461	my $ofs = 0;
		1462
		1463	warn stat $fh;
		1464	warn -s _;
		1465	if (stat $fh and -s _) {
		1466	$ofs = -s _;
		1467	warn "-s is ", $ofs;
		1468	$hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9];
		1469	$hdr{"range"} = "bytes=$ofs-";
		1470	}
		1471
		1472	http_get $url,
		1473	headers => \%hdr,
		1474	on_header => sub {
		1475	my ($hdr) = @_;
		1476
		1477	if ($hdr->{Status} == 200 && $ofs) {
		1478	# resume failed
		1479	truncate $fh, $ofs = 0;
		1480	}
		1481
		1482	sysseek $fh, $ofs, 0;
		1483
		1484	1
		1485	},
		1486	on_body => sub {
		1487	my ($data, $hdr) = @_;
		1488
		1489	if ($hdr->{Status} =~ /^2/) {
		1490	length $data == syswrite $fh, $data
		1491	or return; # abort on write errors
		1492	}
		1493
		1494	1
		1495	},
		1496	sub {
		1497	my (undef, $hdr) = @_;
		1498
		1499	my $status = $hdr->{Status};
		1500
		1501	if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) {
		1502	utime $fh, $time, $time;
		1503	}
		1504
		1505	if ($status == 200 || $status == 206 || $status == 416) {
		1506	# download ok || resume ok || file already fully downloaded
		1507	$cb->(1, $hdr);
		1508
		1509	} elsif ($status == 412) {
		1510	# file has changed while resuming, delete and retry
		1511	unlink $file;
		1512	$cb->(0, $hdr);
		1513
		1514	} elsif ($status == 500 or $status == 503 or $status =~ /^59/) {
		1515	# retry later
		1516	$cb->(0, $hdr);
		1517
		1518	} else {
		1519	$cb->(undef, $hdr);
		1520	}
		1521	}
		1522	;
		1523	}
		1524
		1525	download "http://server/somelargefile", "/tmp/somelargefile", sub {
		1526	if ($_[0]) {
		1527	print "OK!\n";
		1528	} elsif (defined $_[0]) {
		1529	print "please retry later\n";
		1530	} else {
		1531	print "ERROR\n";
		1532	}
		1533	};
		1534
972	=head2 SOCKS PROXIES	1535	=head3 SOCKS PROXIES
973		1536
974	Socks proxies are not directly supported by AnyEvent::HTTP. You can	1537	Socks proxies are not directly supported by AnyEvent::HTTP. You can
975	compile your perl to support socks, or use an external program such as	1538	compile your perl to support socks, or use an external program such as
976	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy	1539	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
977	transparently.	1540	transparently.

Diff Legend

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