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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.12 by root, Thu Jun 5 16:33:02 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC

…		…
3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client	3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use AnyEvent::HTTP;	7	use AnyEvent::HTTP;
		8
		9	http_get "http://www.nethype.de/", sub { print $_[1] };
		10
		11	# ... do something else here
8		12
9	=head1 DESCRIPTION	13	=head1 DESCRIPTION
10		14
11	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
12	run a supported event loop.	16	run a supported event loop.
…		…
35	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
36		40
37	use strict;	41	use strict;
38	no warnings;	42	no warnings;
39		43
40	use Carp;	44	use Errno ();
41		45
42	use AnyEvent ();	46	use AnyEvent 5.0 ();
43	use AnyEvent::Util ();	47	use AnyEvent::Util ();
44	use AnyEvent::Socket ();
45	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
46		49
47	use base Exporter::;	50	use base Exporter::;
48		51
49	our $VERSION = '1.0';	52	our $VERSION = '1.46';
50		53
51	our @EXPORT = qw(http_get http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
52		55
53	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
54	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
55	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
56	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
57	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
58		61
59	# changing these is evil	62	# changing these is evil
60	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
61	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
62		65
63	our $PROXY;	66	our $PROXY;
		67	our $ACTIVE = 0;
64		68
65	my %KA_COUNT; # number of open keep-alive connections per host	69	my %KA_COUNT; # number of open keep-alive connections per host
66	my %CO_SLOT; # number of open connections, and wait queue, per host	70	my %CO_SLOT; # number of open connections, and wait queue, per host
67		71
68	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
69		73
70	Executes an HTTP-GET request. See the http_request function for details on	74	Executes an HTTP-GET request. See the http_request function for details on
71	additional parameters.	75	additional parameters and the return value.
72		76
73	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
74		78
75	Executes an HTTP-HEAD request. See the http_request function for details on	79	Executes an HTTP-HEAD request. See the http_request function for details
76	additional parameters.	80	on additional parameters and the return value.
77		81
78	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
79		83
80	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
81	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
82		87
83	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
84		89
85	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
86	must be an absolute http or https URL.	91	must be an absolute http or https URL.
87		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
88	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
89	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
90	response headers as second argument.	100	second argument.
91		101
92	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
93	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
94	C<Reason> contain the three parts of the HTTP Status-Line of the same	105	three parts of the HTTP Status-Line of the same name.
		106
		107	The pseudo-header C<URL> contains the actual URL (which can differ from
		108	the requested URL when following redirects - for example, you might get
		109	an error that your URL scheme is not supported even though your URL is a
		110	valid http URL because it redirected to an ftp URL, in which case you can
		111	look at the URL pseudo header).
		112
		113	The pseudo-header C<Redirect> only exists when the request was a result
		114	of an internal redirect. In that case it is an array reference with
		115	the C<($data, $headers)> from the redirect response. Note that this
		116	response could in turn be the result of a redirect itself, and C<<
		117	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		118	response, and so on.
		119
95	name. If the server sends a header multiple lines, then their contents	120	If the server sends a header multiple times, then their contents will be
96	will be joined together with C<\x00>.	121	joined together with a comma (C<,>), as per the HTTP spec.
97		122
98	If an internal error occurs, such as not being able to resolve a hostname,	123	If an internal error occurs, such as not being able to resolve a hostname,
99	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	124	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
100	and the C<Reason> pseudo-header will contain an error message.	125	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		126	message.
101		127
102	A typical callback might look like this:	128	A typical callback might look like this:
103		129
104	sub {	130	sub {
105	my ($body, $hdr) = @_;	131	my ($body, $hdr) = @_;
…		…
123		149
124	=item headers => hashref	150	=item headers => hashref
125		151
126	The request headers to use. Currently, C<http_request> may provide its	152	The request headers to use. Currently, C<http_request> may provide its
127	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	153	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
128	and will provide defaults for C<User-Agent:> and C<Referer:>.	154	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		155	suppressed by using C<undef> for these headers in which case they won't be
		156	sent at all).
129		157
130	=item timeout => $seconds	158	=item timeout => $seconds
131		159
132	The time-out to use for various stages - each connect attempt will reset	160	The time-out to use for various stages - each connect attempt will reset
133	the timeout, as will read or write activity. Default timeout is 5 minutes.	161	the timeout, as will read or write activity, i.e. this is not an overall
		162	timeout.
		163
		164	Default timeout is 5 minutes.
134		165
135	=item proxy => [$host, $port[, $scheme]] or undef	166	=item proxy => [$host, $port[, $scheme]] or undef
136		167
137	Use the given http proxy for all requests. If not specified, then the	168	Use the given http proxy for all requests. If not specified, then the
138	default proxy (as specified by C<$ENV{http_proxy}>) is used.	169	default proxy (as specified by C<$ENV{http_proxy}>) is used.
139		170
140	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	171	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
141	HTTPS.	172	HTTPS.
142		173
143	=item body => $string	174	=item body => $string
144		175
145	The request body, usually empty. Will be-sent as-is (future versions of	176	The request body, usually empty. Will be-sent as-is (future versions of
…		…
151	based on the original netscape specification.	182	based on the original netscape specification.
152		183
153	The C<$hash_ref> must be an (initially empty) hash reference which will	184	The C<$hash_ref> must be an (initially empty) hash reference which will
154	get updated automatically. It is possible to save the cookie_jar to	185	get updated automatically. It is possible to save the cookie_jar to
155	persistent storage with something like JSON or Storable, but this is not	186	persistent storage with something like JSON or Storable, but this is not
156	recommended, as expire times are currently being ignored.	187	recommended, as expiry times are currently being ignored.
157		188
158	Note that this cookie implementation is not of very high quality, nor	189	Note that this cookie implementation is not of very high quality, nor
159	meant to be complete. If you want complete cookie management you have to	190	meant to be complete. If you want complete cookie management you have to
160	do that on your own. C<cookie_jar> is meant as a quick fix to get some	191	do that on your own. C<cookie_jar> is meant as a quick fix to get some
161	cookie-using sites working. Cookies are a privacy disaster, do not use	192	cookie-using sites working. Cookies are a privacy disaster, do not use
162	them unless required to.	193	them unless required to.
		194
		195	=item tls_ctx => $scheme \| $tls_ctx
		196
		197	Specifies the AnyEvent::TLS context to be used for https connections. This
		198	parameter follows the same rules as the C<tls_ctx> parameter to
		199	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		200	C<high> can be specified, which give you a predefined low-security (no
		201	verification, highest compatibility) and high-security (CA and common-name
		202	verification) TLS context.
		203
		204	The default for this option is C<low>, which could be interpreted as "give
		205	me the page, no matter what".
		206
		207	=item on_prepare => $callback->($fh)
		208
		209	In rare cases you need to "tune" the socket before it is used to
		210	connect (for exmaple, to bind it on a given IP address). This parameter
		211	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		212	and behaves exactly the same way (e.g. it has to provide a
		213	timeout). See the description for the C<$prepare_cb> argument of
		214	C<AnyEvent::Socket::tcp_connect> for details.
		215
		216	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		217
		218	In even rarer cases you want total control over how AnyEvent::HTTP
		219	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		220	to do this, but you can provide your own C<tcp_connect> function -
		221	obviously, it has to follow the same calling conventions.
		222
		223	There are probably lots of weird uses for this function, starting from
		224	tracing the hosts C<http_request> actually tries to connect, to (inexact
		225	but fast) host => IP address caching or even socks protocol support.
		226
		227	=item on_header => $callback->($headers)
		228
		229	When specified, this callback will be called with the header hash as soon
		230	as headers have been successfully received from the remote server (not on
		231	locally-generated errors).
		232
		233	It has to return either true (in which case AnyEvent::HTTP will continue),
		234	or false, in which case AnyEvent::HTTP will cancel the download (and call
		235	the finish callback with an error code of C<598>).
		236
		237	This callback is useful, among other things, to quickly reject unwanted
		238	content, which, if it is supposed to be rare, can be faster than first
		239	doing a C<HEAD> request.
		240
		241	Example: cancel the request unless the content-type is "text/html".
		242
		243	on_header => sub {
		244	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		245	},
		246
		247	=item on_body => $callback->($partial_body, $headers)
		248
		249	When specified, all body data will be passed to this callback instead of
		250	to the completion callback. The completion callback will get the empty
		251	string instead of the body data.
		252
		253	It has to return either true (in which case AnyEvent::HTTP will continue),
		254	or false, in which case AnyEvent::HTTP will cancel the download (and call
		255	the completion callback with an error code of C<598>).
		256
		257	This callback is useful when the data is too large to be held in memory
		258	(so the callback writes it to a file) or when only some information should
		259	be extracted, or when the body should be processed incrementally.
		260
		261	It is usually preferred over doing your own body handling via
		262	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		263	only used to create a connection, C<want_body_handle> is the better
		264	alternative, as it allows you to install your own event handler, reducing
		265	resource usage.
		266
		267	=item want_body_handle => $enable
		268
		269	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		270	changes considerably: after parsing the headers, and instead of
		271	downloading the body (if any), the completion callback will be
		272	called. Instead of the C<$body> argument containing the body data, the
		273	callback will receive the L<AnyEvent::Handle> object associated with the
		274	connection. In error cases, C<undef> will be passed. When there is no body
		275	(e.g. status C<304>), the empty string will be passed.
		276
		277	The handle object might or might not be in TLS mode, might be connected to
		278	a proxy, be a persistent connection etc., and configured in unspecified
		279	ways. The user is responsible for this handle (it will not be used by this
		280	module anymore).
		281
		282	This is useful with some push-type services, where, after the initial
		283	headers, an interactive protocol is used (typical example would be the
		284	push-style twitter API which starts a JSON/XML stream).
		285
		286	If you think you need this, first have a look at C<on_body>, to see if
		287	that doesn't solve your problem in a better way.
163		288
164	=back	289	=back
165		290
166	Example: make a simple HTTP GET request for http://www.nethype.de/	291	Example: make a simple HTTP GET request for http://www.nethype.de/
167		292
…		…
181	use Data::Dumper;	306	use Data::Dumper;
182	print Dumper $hdr;	307	print Dumper $hdr;
183	}	308	}
184	;	309	;
185		310
		311	Example: make another simple HTTP GET request, but immediately try to
		312	cancel it.
		313
		314	my $request = http_request GET => "http://www.nethype.de/", sub {
		315	my ($body, $hdr) = @_;
		316	print "$body\n";
		317	};
		318
		319	undef $request;
		320
186	=cut	321	=cut
187		322
188	sub _slot_schedule;	323	sub _slot_schedule;
189	sub _slot_schedule($) {	324	sub _slot_schedule($) {
190	my $host = shift;	325	my $host = shift;
191		326
192	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {	327	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
193	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {	328	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
194	# somebody wants that slot	329	# somebody wants that slot
195	++$CO_SLOT{$host}[0];	330	++$CO_SLOT{$host}[0];
		331	++$ACTIVE;
196		332
197	$cb->(AnyEvent::Util::guard {	333	$cb->(AnyEvent::Util::guard {
		334	--$ACTIVE;
198	--$CO_SLOT{$host}[0];	335	--$CO_SLOT{$host}[0];
199	_slot_schedule $host;	336	_slot_schedule $host;
200	});	337	});
201	} else {	338	} else {
202	# nobody wants the slot, maybe we can forget about it	339	# nobody wants the slot, maybe we can forget about it
…		…
211	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	348	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
212		349
213	_slot_schedule $_[0];	350	_slot_schedule $_[0];
214	}	351	}
215		352
		353	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		354
		355	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		356	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		357
216	sub http_request($$$;@) {	358	sub http_request($$@) {
217	my $cb = pop;	359	my $cb = pop;
218	my ($method, $url, %arg) = @_;	360	my ($method, $url, %arg) = @_;
219		361
220	my %hdr;	362	my %hdr;
		363
		364	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		365	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
221		366
222	$method = uc $method;	367	$method = uc $method;
223		368
224	if (my $hdr = $arg{headers}) {	369	if (my $hdr = $arg{headers}) {
225	while (my ($k, $v) = each %$hdr) {	370	while (my ($k, $v) = each %$hdr) {
226	$hdr{lc $k} = $v;	371	$hdr{lc $k} = $v;
227	}	372	}
228	}	373	}
229		374
		375	# pseudo headers for all subsequent responses
		376	my @pseudo = (URL => $url);
		377	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		378
230	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	379	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
231		380
232	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	381	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
233	if $recurse < 0;	382	if $recurse < 0;
234		383
235	my $proxy = $arg{proxy} \|\| $PROXY;	384	my $proxy = $arg{proxy} \|\| $PROXY;
236	my $timeout = $arg{timeout} \|\| $TIMEOUT;	385	my $timeout = $arg{timeout} \|\| $TIMEOUT;
237		386
238	$hdr{"user-agent"} \|\|= $USERAGENT;
239
240	my ($scheme, $authority, $upath, $query, $fragment) =	387	my ($uscheme, $uauthority, $upath, $query, $fragment) =
241	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	388	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
242		389
243	$scheme = lc $scheme;	390	$uscheme = lc $uscheme;
244		391
245	my $uport = $scheme eq "http" ? 80	392	my $uport = $uscheme eq "http" ? 80
246	: $scheme eq "https" ? 443	393	: $uscheme eq "https" ? 443
247	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" });	394	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
248		395
249	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	396	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
250	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	397	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
251		398
252	my $uhost = $1;	399	my $uhost = $1;
253	$uport = $2 if defined $2;	400	$uport = $2 if defined $2;
254		401
		402	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		403	unless exists $hdr{host};
		404
255	$uhost =~ s/^\[(.*)\]$/$1/;	405	$uhost =~ s/^\[(.*)\]$/$1/;
256	$upath .= "?$query" if length $query;	406	$upath .= $query if length $query;
257		407
258	$upath =~ s%^/?%/%;	408	$upath =~ s%^/?%/%;
259
260	$hdr{referer} \|\|= "$scheme://$authority$upath";
261		409
262	# cookie processing	410	# cookie processing
263	if (my $jar = $arg{cookie_jar}) {	411	if (my $jar = $arg{cookie_jar}) {
264	%$jar = () if $jar->{version} < 1;	412	%$jar = () if $jar->{version} != 1;
265		413
266	my @cookie;	414	my @cookie;
267		415
268	while (my ($chost, $v) = each %$jar) {	416	while (my ($chost, $v) = each %$jar) {
		417	if ($chost =~ /^\./) {
269	next unless $chost eq substr $uhost, -length $chost;	418	next unless $chost eq substr $uhost, -length $chost;
270	next unless $chost =~ /^\./;	419	} elsif ($chost =~ /\./) {
		420	next unless $chost eq $uhost;
		421	} else {
		422	next;
		423	}
271		424
272	while (my ($cpath, $v) = each %$v) {	425	while (my ($cpath, $v) = each %$v) {
273	next unless $cpath eq substr $upath, 0, length $cpath;	426	next unless $cpath eq substr $upath, 0, length $cpath;
274		427
275	while (my ($k, $v) = each %$v) {	428	while (my ($k, $v) = each %$v) {
276	next if $scheme ne "https" && exists $v->{secure};	429	next if $uscheme ne "https" && exists $v->{secure};
		430	my $value = $v->{value};
		431	$value =~ s/([\\"])/\\$1/g;
277	push @cookie, "$k=$v->{value}";	432	push @cookie, "$k=\"$value\"";
278	}	433	}
279	}	434	}
280	}	435	}
281		436
282	$hdr{cookie} = join "; ", @cookie	437	$hdr{cookie} = join "; ", @cookie
283	if @cookie;	438	if @cookie;
284	}	439	}
285		440
286	my ($rhost, $rport, $rpath); # request host, port, path	441	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
287		442
288	if ($proxy) {	443	if ($proxy) {
289	($rhost, $rport, $scheme) = @$proxy;	444	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
290	$rpath = $url;	445
		446	$rscheme = "http" unless defined $rscheme;
		447
		448	# don't support https requests over https-proxy transport,
		449	# can't be done with tls as spec'ed, unless you double-encrypt.
		450	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
291	} else {	451	} else {
292	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	452	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
293	$hdr{host} = $uhost;
294	}	453	}
295		454
		455	# leave out fragment and query string, just a heuristic
		456	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		457	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		458
296	$hdr{"content-length"} = length $arg{body};	459	$hdr{"content-length"} = length $arg{body}
		460	if length $arg{body} \|\| $method ne "GET";
297		461
298	my %state = (connect_guard => 1);	462	my %state = (connect_guard => 1);
299		463
300	_get_slot $uhost, sub {	464	_get_slot $uhost, sub {
301	$state{slot_guard} = shift;	465	$state{slot_guard} = shift;
302		466
303	return unless $state{connect_guard};	467	return unless $state{connect_guard};
304		468
305	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	469	my $tcp_connect = $arg{tcp_connect}
		470	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		471
		472	$state{connect_guard} = $tcp_connect->(
		473	$rhost,
		474	$rport,
		475	sub {
306	$state{fh} = shift	476	$state{fh} = shift
307	or return $cb->(undef, { Status => 599, Reason => "$!" });
308
309	delete $state{connect_guard}; # reduce memory usage, save a tree
310
311	# get handle
312	$state{handle} = new AnyEvent::Handle
313	fh => $state{fh},
314	($scheme eq "https" ? (tls => "connect") : ());
315
316	# limit the number of persistent connections
317	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
318	++$KA_COUNT{$_[1]};
319	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
320	$hdr{connection} = "keep-alive";
321	delete $hdr{connection}; # keep-alive not yet supported
322	} else {
323	delete $hdr{connection};
324	}
325
326	# (re-)configure handle
327	$state{handle}->timeout ($timeout);
328	$state{handle}->on_error (sub {
329	%state = ();
330	$cb->(undef, { Status => 599, Reason => "$!" });
331	});
332	$state{handle}->on_eof (sub {
333	%state = ();
334	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
335	});
336
337	# send request
338	$state{handle}->push_write (
339	"$method $rpath HTTP/1.0\015\012"
340	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
341	. "\015\012"
342	. (delete $arg{body})
343	);
344
345	%hdr = (); # reduce memory usage, save a kitten
346
347	# status line
348	$state{handle}->push_read (line => qr/\015?\012/, sub {
349	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
350	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
351
352	my %hdr = ( # response headers
353	HTTPVersion => "\x00$1",
354	Status => "\x00$2",
355	Reason => "\x00$3",
356	);
357
358	# headers, could be optimized a bit
359	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
360	for ("$_[1]\012") {
361	# we support spaces in field names, as lotus domino
362	# creates them.
363	$hdr{lc $1} .= "\x00$2"
364	while /\G
365	([^:\000-\037]+):
366	[\011\040]*
367	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
368	\015?\012
369	/gxc;
370
371	/\G$/
372	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));
373	}	477	or do {
374		478	my $err = "$!";
375	substr $_, 0, 1, ""
376	for values %hdr;
377
378	my $finish = sub {
379	%state = ();	479	%state = ();
		480	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		481	};
380		482
381	# set-cookie processing	483	pop; # free memory, save a tree
382	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
383	for (split /\x00/, $hdr{"set-cookie"}) {
384	my ($cookie, @arg) = split /;\s*/;
385	my ($name, $value) = split /=/, $cookie, 2;
386	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
387
388	my $cdom = (delete $kv{domain}) \|\| $uhost;
389	my $cpath = (delete $kv{path}) \|\| "/";
390
391	$cdom =~ s/^.?/./; # make sure it starts with a "."
392		484
393	next if $cdom =~ /\.$/;	485	return unless delete $state{connect_guard};
394		486
395	# this is not rfc-like and not netscape-like. go figure.	487	# get handle
396	my $ndots = $cdom =~ y/.//;	488	$state{handle} = new AnyEvent::Handle
397	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	489	fh => $state{fh},
398		490	peername => $rhost,
		491	tls_ctx => $arg{tls_ctx},
		492	# these need to be reconfigured on keepalive handles
		493	timeout => $timeout,
		494	on_error => sub {
		495	%state = ();
		496	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		497	},
		498	on_eof => sub {
		499	%state = ();
		500	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		501	},
		502	;
		503
		504	# limit the number of persistent connections
		505	# keepalive not yet supported
		506	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		507	# ++$KA_COUNT{$_[1]};
		508	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		509	# --$KA_COUNT{$_[1]}
		510	# };
		511	# $hdr{connection} = "keep-alive";
		512	# } else {
		513	delete $hdr{connection};
		514	# }
		515
		516	$state{handle}->starttls ("connect") if $rscheme eq "https";
		517
		518	# handle actual, non-tunneled, request
		519	my $handle_actual_request = sub {
		520	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		521
		522	# send request
		523	$state{handle}->push_write (
		524	"$method $rpath HTTP/1.0\015\012"
		525	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		526	. "\015\012"
		527	. (delete $arg{body})
		528	);
		529
		530	# return if error occured during push_write()
		531	return unless %state;
		532
		533	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		534
		535	# status line and headers
		536	$state{handle}->push_read (line => $qr_nlnl, sub {
		537	for ("$_[1]") {
		538	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		539
		540	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
		541	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
		542
		543	push @pseudo,
		544	HTTPVersion => $1,
		545	Status => $2,
		546	Reason => $3,
		547	;
		548
		549	# things seen, not parsed:
		550	# p3pP="NON CUR OTPi OUR NOR UNI"
		551
		552	$hdr{lc $1} .= ",$2"
		553	while /\G
		554	([^:\000-\037]*):
		555	[\011\040]*
		556	((?: [^\012]+ \| \012[\011\040] )*)
		557	\012
		558	/gxc;
		559
		560	/\G$/
		561	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
		562	}
		563
		564	# remove the "," prefix we added to all headers above
		565	substr $_, 0, 1, ""
		566	for values %hdr;
		567
		568	# patch in all pseudo headers
		569	%hdr = (%hdr, @pseudo);
		570
		571	# redirect handling
		572	# microsoft and other shitheads don't give a shit for following standards,
		573	# try to support some common forms of broken Location headers.
		574	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		575	$hdr{location} =~ s/^\.\/+//;
		576
		577	my $url = "$rscheme://$uhost:$uport";
		578
		579	unless ($hdr{location} =~ s/^\///) {
		580	$url .= $upath;
		581	$url =~ s/\/[^\/]*$//;
		582	}
		583
		584	$hdr{location} = "$url/$hdr{location}";
		585	}
		586
		587	my $redirect;
		588
		589	if ($recurse) {
		590	my $status = $hdr{Status};
		591
		592	# industry standard is to redirect POST as GET for
		593	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		594	# also, the UA should ask the user for 301 and 307 and POST,
		595	# industry standard seems to be to simply follow.
		596	# we go with the industry standard.
		597	if ($status == 301 or $status == 302 or $status == 303) {
		598	# HTTP/1.1 is unclear on how to mutate the method
		599	$method = "GET" unless $method eq "HEAD";
399	# store it	600	$redirect = 1;
400	$arg{cookie_jar}{version} = 1;	601	} elsif ($status == 307) {
401	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	602	$redirect = 1;
402	}	603	}
403	}	604	}
404		605
405	if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {	606	my $finish = sub {
406	# microsoft and other assholes don't give a shit for following standards,	607	$state{handle}->destroy if $state{handle};
407	# try to support a common form of broken Location header.	608	%state = ();
408	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
409		609
410	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	610	# set-cookie processing
		611	if ($arg{cookie_jar}) {
		612	for ($_[1]{"set-cookie"}) {
		613	# parse NAME=VALUE
		614	my @kv;
		615
		616	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		617	my $name = $1;
		618	my $value = $3;
		619
		620	unless ($value) {
		621	$value = $2;
		622	$value =~ s/\\(.)/$1/gs;
		623	}
		624
		625	push @kv, $name => $value;
		626
		627	last unless /\G\s*;/gc;
		628	}
		629
		630	last unless @kv;
		631
		632	my $name = shift @kv;
		633	my %kv = (value => shift @kv, @kv);
		634
		635	my $cdom;
		636	my $cpath = (delete $kv{path}) \|\| "/";
		637
		638	if (exists $kv{domain}) {
		639	$cdom = delete $kv{domain};
		640
		641	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		642
		643	next if $cdom =~ /\.$/;
		644
		645	# this is not rfc-like and not netscape-like. go figure.
		646	my $ndots = $cdom =~ y/.//;
		647	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		648	} else {
		649	$cdom = $uhost;
		650	}
		651
		652	# store it
		653	$arg{cookie_jar}{version} = 1;
		654	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		655
		656	redo if /\G\s*,/gc;
		657	}
		658	}
		659
		660	if ($redirect && exists $hdr{location}) {
		661	# we ignore any errors, as it is very common to receive
		662	# Content-Length != 0 but no actual body
		663	# we also access %hdr, as $_[1] might be an erro
		664	http_request (
		665	$method => $hdr{location},
		666	%arg,
		667	recurse => $recurse - 1,
		668	Redirect => \@_,
		669	$cb);
		670	} else {
		671	$cb->($_[0], $_[1]);
		672	}
		673	};
		674
		675	my $len = $hdr{"content-length"};
		676
		677	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		678	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		679	} elsif (
		680	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		681	or $method eq "HEAD"
		682	or (defined $len && !$len)
		683	) {
		684	# no body
		685	$finish->("", \%hdr);
411	} else {	686	} else {
412	$cb->($_[0], $_[1]);	687	# body handling, four different code paths
		688	# for want_body_handle, on_body (2x), normal (2x)
		689	# we might read too much here, but it does not matter yet (no pers. connections)
		690	if (!$redirect && $arg{want_body_handle}) {
		691	$_[0]->on_eof (undef);
		692	$_[0]->on_error (undef);
		693	$_[0]->on_read (undef);
		694
		695	$finish->(delete $state{handle}, \%hdr);
		696
		697	} elsif ($arg{on_body}) {
		698	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		699	if ($len) {
		700	$_[0]->on_eof (undef);
		701	$_[0]->on_read (sub {
		702	$len -= length $_[0]{rbuf};
		703
		704	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		705	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		706
		707	$len > 0
		708	or $finish->("", \%hdr);
		709	});
		710	} else {
		711	$_[0]->on_eof (sub {
		712	$finish->("", \%hdr);
		713	});
		714	$_[0]->on_read (sub {
		715	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		716	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		717	});
		718	}
		719	} else {
		720	$_[0]->on_eof (undef);
		721
		722	if ($len) {
		723	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		724	$_[0]->on_read (sub {
		725	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		726	if $len <= length $_[0]{rbuf};
		727	});
		728	} else {
		729	$_[0]->on_error (sub {
		730	($! == Errno::EPIPE \|\| !$!)
		731	? $finish->(delete $_[0]{rbuf}, \%hdr)
		732	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		733	});
		734	$_[0]->on_read (sub { });
		735	}
		736	}
413	}	737	}
414	};	738	});
		739	};
415		740
416	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	741	# now handle proxy-CONNECT method
417	$finish->(undef, \%hdr);	742	if ($proxy && $uscheme eq "https") {
418	} else {	743	# oh dear, we have to wrap it into a connect request
419	if (exists $hdr{"content-length"}) {
420	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
421	# could cache persistent connection now
422	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
423	# but we don't, due to misdesigns, this is annoyingly complex
424	};
425		744
426	$finish->($_[1], \%hdr);	745	# maybe re-use $uauthority with patched port?
427	});	746	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		747	$state{handle}->push_read (line => $qr_nlnl, sub {
		748	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		749	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
		750
		751	if ($2 == 200) {
		752	$rpath = $upath;
		753	&$handle_actual_request;
428	} else {	754	} else {
429	# too bad, need to read until we get an error or EOF,
430	# no way to detect winged data.
431	$_[0]->on_error (sub {
432	$finish->($_[0]{rbuf}, \%hdr);
433	});	755	%state = ();
434	$_[0]->on_eof (undef);	756	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
435	$_[0]->on_read (sub { });
436	}	757	}
437	}	758	});
		759	} else {
		760	&$handle_actual_request;
438	});	761	}
		762
439	});	763	},
440	}, sub {	764	$arg{on_prepare} \|\| sub { $timeout }
441	$timeout
442	};	765	);
443	};	766	};
444		767
445	defined wantarray && AnyEvent::Util::guard { %state = () }	768	defined wantarray && AnyEvent::Util::guard { %state = () }
446	}	769	}
447		770
448	sub http_get($$;@) {	771	sub http_get($@) {
449	unshift @_, "GET";	772	unshift @_, "GET";
450	&http_request	773	&http_request
451	}	774	}
452		775
453	sub http_head($$;@) {	776	sub http_head($@) {
454	unshift @_, "HEAD";	777	unshift @_, "HEAD";
455	&http_request	778	&http_request
456	}	779	}
457		780
458	sub http_post($$$;@) {	781	sub http_post($$@) {
		782	my $url = shift;
459	unshift @_, "POST", "body";	783	unshift @_, "POST", $url, "body";
460	&http_request	784	&http_request
461	}	785	}
462		786
463	=back	787	=back
464		788
		789	=head2 DNS CACHING
		790
		791	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		792	the actual connection, which in turn uses AnyEvent::DNS to resolve
		793	hostnames. The latter is a simple stub resolver and does no caching
		794	on its own. If you want DNS caching, you currently have to provide
		795	your own default resolver (by storing a suitable resolver object in
		796	C<$AnyEvent::DNS::RESOLVER>).
		797
465	=head2 GLOBAL FUNCTIONS AND VARIABLES	798	=head2 GLOBAL FUNCTIONS AND VARIABLES
466		799
467	=over 4	800	=over 4
468		801
469	=item AnyEvent::HTTP::set_proxy "proxy-url"	802	=item AnyEvent::HTTP::set_proxy "proxy-url"
470		803
471	Sets the default proxy server to use. The proxy-url must begin with a	804	Sets the default proxy server to use. The proxy-url must begin with a
472	string of the form C<http://host:port> (optionally C<https:...>).	805	string of the form C<http://host:port> (optionally C<https:...>), croaks
		806	otherwise.
		807
		808	To clear an already-set proxy, use C<undef>.
473		809
474	=item $AnyEvent::HTTP::MAX_RECURSE	810	=item $AnyEvent::HTTP::MAX_RECURSE
475		811
476	The default value for the C<recurse> request parameter (default: C<10>).	812	The default value for the C<recurse> request parameter (default: C<10>).
477		813
478	=item $AnyEvent::HTTP::USERAGENT	814	=item $AnyEvent::HTTP::USERAGENT
479		815
480	The default value for the C<User-Agent> header (the default is	816	The default value for the C<User-Agent> header (the default is
481	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	817	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
482		818
483	=item $AnyEvent::HTTP::MAX_PERSISTENT	819	=item $AnyEvent::HTTP::MAX_PER_HOST
484		820
485	The maximum number of persistent connections to keep open (default: 8).	821	The maximum number of concurrent connections to the same host (identified
		822	by the hostname). If the limit is exceeded, then the additional requests
		823	are queued until previous connections are closed.
486		824
487	Not implemented currently.	825	The default value for this is C<4>, and it is highly advisable to not
		826	increase it.
488		827
489	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	828	=item $AnyEvent::HTTP::ACTIVE
490		829
491	The maximum time to cache a persistent connection, in seconds (default: 2).	830	The number of active connections. This is not the number of currently
492		831	running requests, but the number of currently open and non-idle TCP
493	Not implemented currently.	832	connections. This number of can be useful for load-leveling.
494		833
495	=back	834	=back
496		835
497	=cut	836	=cut
498		837
499	sub set_proxy($) {	838	sub set_proxy($) {
		839	if (length $_[0]) {
500	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	840	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		841	or Carp::croak "$_[0]: invalid proxy URL";
		842	$PROXY = [$2, $3 \|\| 3128, $1]
		843	} else {
		844	undef $PROXY;
		845	}
501	}	846	}
502		847
503	# initialise proxy from environment	848	# initialise proxy from environment
		849	eval {
504	set_proxy $ENV{http_proxy};	850	set_proxy $ENV{http_proxy};
		851	};
505		852
506	=head1 SEE ALSO	853	=head1 SEE ALSO
507		854
508	L<AnyEvent>.	855	L<AnyEvent>.
509		856
510	=head1 AUTHOR	857	=head1 AUTHOR
511		858
512	Marc Lehmann <schmorp@schmorp.de>	859	Marc Lehmann <schmorp@schmorp.de>
513	http://home.schmorp.de/	860	http://home.schmorp.de/
		861
		862	With many thanks to Дмитрий Шалашов, who provided countless
		863	testcases and bugreports.
514		864
515	=cut	865	=cut
516		866
517	1	867	1
518		868

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.12 by root, Thu Jun 5 16:33:02 2008 UTC vs. Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.12 by root, Thu Jun 5 16:33:02 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC