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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.11 by root, Thu Jun 5 15:34:00 2008 UTC vs.
Revision 1.57 by root, Mon Sep 6 06:31:32 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 ();	48	use AnyEvent::Socket ();
45	use AnyEvent::Handle ();	49	use AnyEvent::Handle ();
46		50
47	use base Exporter::;	51	use base Exporter::;
48		52
49	our $VERSION = '1.0';	53	our $VERSION = '1.46';
50		54
51	our @EXPORT = qw(http_get http_request);	55	our @EXPORT = qw(http_get http_post http_head http_request);
52		56
53	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	57	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
54	our $MAX_RECURSE = 10;	58	our $MAX_RECURSE = 10;
55	our $MAX_PERSISTENT = 8;	59	our $MAX_PERSISTENT = 8;
56	our $PERSISTENT_TIMEOUT = 2;	60	our $PERSISTENT_TIMEOUT = 2;
57	our $TIMEOUT = 300;	61	our $TIMEOUT = 300;
58		62
59	# changing these is evil	63	# changing these is evil
60	our $MAX_PERSISTENT_PER_HOST = 2;	64	our $MAX_PERSISTENT_PER_HOST = 0;
61	our $MAX_PER_HOST = 4;	65	our $MAX_PER_HOST = 4;
62		66
63	our $PROXY;	67	our $PROXY;
		68	our $ACTIVE = 0;
64		69
65	my %KA_COUNT; # number of open keep-alive connections per host	70	my %KA_COUNT; # number of open keep-alive connections per host
66	my %CO_SLOT; # number of open connections, and wait queue, per host	71	my %CO_SLOT; # number of open connections, and wait queue, per host
67		72
68	=item http_get $url, key => value..., $cb->($data, $headers)	73	=item http_get $url, key => value..., $cb->($data, $headers)
69		74
70	Executes an HTTP-GET request. See the http_request function for details on	75	Executes an HTTP-GET request. See the http_request function for details on
71	additional parameters.	76	additional parameters and the return value.
72		77
73	=item http_head $url, key => value..., $cb->($data, $headers)	78	=item http_head $url, key => value..., $cb->($data, $headers)
74		79
75	Executes an HTTP-HEAD request. See the http_request function for details on	80	Executes an HTTP-HEAD request. See the http_request function for details
76	additional parameters.	81	on additional parameters and the return value.
77		82
78	=item http_post $url, $body, key => value..., $cb->($data, $headers)	83	=item http_post $url, $body, key => value..., $cb->($data, $headers)
79		84
80	Executes an HTTP-POST request with a request body of C<$bod>. See the	85	Executes an HTTP-POST request with a request body of C<$body>. See the
81	http_request function for details on additional parameters.	86	http_request function for details on additional parameters and the return
		87	value.
82		88
83	=item http_request $method => $url, key => value..., $cb->($data, $headers)	89	=item http_request $method => $url, key => value..., $cb->($data, $headers)
84		90
85	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	91	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
86	must be an absolute http or https URL.	92	must be an absolute http or https URL.
87		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
88	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
89	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
90	response headers as second argument.	101	second argument.
91		102
92	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
93	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	104	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		105	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
94	C<Reason> contain the three parts of the HTTP Status-Line of the same	106	three parts of the HTTP Status-Line of the same name.
		107
		108	The pseudo-header C<URL> contains the actual URL (which can differ from
		109	the requested URL when following redirects - for example, you might get
		110	an error that your URL scheme is not supported even though your URL is a
		111	valid http URL because it redirected to an ftp URL, in which case you can
		112	look at the URL pseudo header).
		113
		114	The pseudo-header C<Redirect> only exists when the request was a result
		115	of an internal redirect. In that case it is an array reference with
		116	the C<($data, $headers)> from the redirect response. Note that this
		117	response could in turn be the result of a redirect itself, and C<<
		118	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		119	response, and so on.
		120
95	name. If the server sends a header multiple lines, then their contents	121	If the server sends a header multiple times, then their contents will be
96	will be joined together with C<\x00>.	122	joined together with a comma (C<,>), as per the HTTP spec.
97		123
98	If an internal error occurs, such as not being able to resolve a hostname,	124	If an internal error occurs, such as not being able to resolve a hostname,
99	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	125	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
100	and the C<Reason> pseudo-header will contain an error message.	126	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		127	message.
101		128
102	A typical callback might look like this:	129	A typical callback might look like this:
103		130
104	sub {	131	sub {
105	my ($body, $hdr) = @_;	132	my ($body, $hdr) = @_;
…		…
121	Whether to recurse requests or not, e.g. on redirects, authentication	148	Whether to recurse requests or not, e.g. on redirects, authentication
122	retries and so on, and how often to do so.	149	retries and so on, and how often to do so.
123		150
124	=item headers => hashref	151	=item headers => hashref
125		152
126	The request headers to use.	153	The request headers to use. Currently, C<http_request> may provide its
		154	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
		155	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		156	suppressed by using C<undef> for these headers in which case they won't be
		157	sent at all).
127		158
128	=item timeout => $seconds	159	=item timeout => $seconds
129		160
130	The time-out to use for various stages - each connect attempt will reset	161	The time-out to use for various stages - each connect attempt will reset
131	the timeout, as will read or write activity. Default timeout is 5 minutes.	162	the timeout, as will read or write activity, i.e. this is not an overall
		163	timeout.
		164
		165	Default timeout is 5 minutes.
132		166
133	=item proxy => [$host, $port[, $scheme]] or undef	167	=item proxy => [$host, $port[, $scheme]] or undef
134		168
135	Use the given http proxy for all requests. If not specified, then the	169	Use the given http proxy for all requests. If not specified, then the
136	default proxy (as specified by C<$ENV{http_proxy}>) is used.	170	default proxy (as specified by C<$ENV{http_proxy}>) is used.
137		171
138	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	172	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
139	HTTPS.	173	HTTPS.
140		174
141	=item body => $string	175	=item body => $string
142		176
143	The request body, usually empty. Will be-sent as-is (future versions of	177	The request body, usually empty. Will be-sent as-is (future versions of
…		…
149	based on the original netscape specification.	183	based on the original netscape specification.
150		184
151	The C<$hash_ref> must be an (initially empty) hash reference which will	185	The C<$hash_ref> must be an (initially empty) hash reference which will
152	get updated automatically. It is possible to save the cookie_jar to	186	get updated automatically. It is possible to save the cookie_jar to
153	persistent storage with something like JSON or Storable, but this is not	187	persistent storage with something like JSON or Storable, but this is not
154	recommended, as expire times are currently being ignored.	188	recommended, as expiry times are currently being ignored.
155		189
156	Note that this cookie implementation is not of very high quality, nor	190	Note that this cookie implementation is not of very high quality, nor
157	meant to be complete. If you want complete cookie management you have to	191	meant to be complete. If you want complete cookie management you have to
158	do that on your own. C<cookie_jar> is meant as a quick fix to get some	192	do that on your own. C<cookie_jar> is meant as a quick fix to get some
159	cookie-using sites working. Cookies are a privacy disaster, do not use	193	cookie-using sites working. Cookies are a privacy disaster, do not use
160	them unless required to.	194	them unless required to.
		195
		196	=item tls_ctx => $scheme \| $tls_ctx
		197
		198	Specifies the AnyEvent::TLS context to be used for https connections. This
		199	parameter follows the same rules as the C<tls_ctx> parameter to
		200	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		201	C<high> can be specified, which give you a predefined low-security (no
		202	verification, highest compatibility) and high-security (CA and common-name
		203	verification) TLS context.
		204
		205	The default for this option is C<low>, which could be interpreted as "give
		206	me the page, no matter what".
		207
		208	=item on_prepare => $callback->($fh)
		209
		210	In rare cases you need to "tune" the socket before it is used to
		211	connect (for exmaple, to bind it on a given IP address). This parameter
		212	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		213	and behaves exactly the same way (e.g. it has to provide a
		214	timeout). See the description for the C<$prepare_cb> argument of
		215	C<AnyEvent::Socket::tcp_connect> for details.
		216
		217	=item on_header => $callback->($headers)
		218
		219	When specified, this callback will be called with the header hash as soon
		220	as headers have been successfully received from the remote server (not on
		221	locally-generated errors).
		222
		223	It has to return either true (in which case AnyEvent::HTTP will continue),
		224	or false, in which case AnyEvent::HTTP will cancel the download (and call
		225	the finish callback with an error code of C<598>).
		226
		227	This callback is useful, among other things, to quickly reject unwanted
		228	content, which, if it is supposed to be rare, can be faster than first
		229	doing a C<HEAD> request.
		230
		231	Example: cancel the request unless the content-type is "text/html".
		232
		233	on_header => sub {
		234	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		235	},
		236
		237	=item on_body => $callback->($partial_body, $headers)
		238
		239	When specified, all body data will be passed to this callback instead of
		240	to the completion callback. The completion callback will get the empty
		241	string instead of the body data.
		242
		243	It has to return either true (in which case AnyEvent::HTTP will continue),
		244	or false, in which case AnyEvent::HTTP will cancel the download (and call
		245	the completion callback with an error code of C<598>).
		246
		247	This callback is useful when the data is too large to be held in memory
		248	(so the callback writes it to a file) or when only some information should
		249	be extracted, or when the body should be processed incrementally.
		250
		251	It is usually preferred over doing your own body handling via
		252	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		253	only used to create a connection, C<want_body_handle> is the better
		254	alternative, as it allows you to install your own event handler, reducing
		255	resource usage.
		256
		257	=item want_body_handle => $enable
		258
		259	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		260	changes considerably: after parsing the headers, and instead of
		261	downloading the body (if any), the completion callback will be
		262	called. Instead of the C<$body> argument containing the body data, the
		263	callback will receive the L<AnyEvent::Handle> object associated with the
		264	connection. In error cases, C<undef> will be passed. When there is no body
		265	(e.g. status C<304>), the empty string will be passed.
		266
		267	The handle object might or might not be in TLS mode, might be connected to
		268	a proxy, be a persistent connection etc., and configured in unspecified
		269	ways. The user is responsible for this handle (it will not be used by this
		270	module anymore).
		271
		272	This is useful with some push-type services, where, after the initial
		273	headers, an interactive protocol is used (typical example would be the
		274	push-style twitter API which starts a JSON/XML stream).
		275
		276	If you think you need this, first have a look at C<on_body>, to see if
		277	that doesn't solve your problem in a better way.
161		278
162	=back	279	=back
163		280
164	Example: make a simple HTTP GET request for http://www.nethype.de/	281	Example: make a simple HTTP GET request for http://www.nethype.de/
165		282
…		…
179	use Data::Dumper;	296	use Data::Dumper;
180	print Dumper $hdr;	297	print Dumper $hdr;
181	}	298	}
182	;	299	;
183		300
		301	Example: make another simple HTTP GET request, but immediately try to
		302	cancel it.
		303
		304	my $request = http_request GET => "http://www.nethype.de/", sub {
		305	my ($body, $hdr) = @_;
		306	print "$body\n";
		307	};
		308
		309	undef $request;
		310
184	=cut	311	=cut
185		312
		313	sub _slot_schedule;
186	sub _slot_schedule($) {	314	sub _slot_schedule($) {
187	my $host = shift;	315	my $host = shift;
188		316
189	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {	317	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
190	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {	318	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
191	# somebody wnats that slot	319	# somebody wants that slot
192	++$CO_SLOT{$host}[0];	320	++$CO_SLOT{$host}[0];
		321	++$ACTIVE;
193		322
194	$cb->(AnyEvent::Util::guard {	323	$cb->(AnyEvent::Util::guard {
		324	--$ACTIVE;
195	--$CO_SLOT{$host}[0];	325	--$CO_SLOT{$host}[0];
196	_slot_schedule $host;	326	_slot_schedule $host;
197	});	327	});
198	} else {	328	} else {
199	# nobody wants the slot, maybe we can forget about it	329	# nobody wants the slot, maybe we can forget about it
200	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];	330	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
201	warn "$host deleted" unless $CO_SLOT{$host}[0];#d#
202	last;	331	last;
203	}	332	}
204	}	333	}
205	}	334	}
206		335
…		…
209	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
210		339
211	_slot_schedule $_[0];	340	_slot_schedule $_[0];
212	}	341	}
213		342
		343	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		344
		345	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		346	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		347
214	sub http_request($$$;@) {	348	sub http_request($$@) {
215	my $cb = pop;	349	my $cb = pop;
216	my ($method, $url, %arg) = @_;	350	my ($method, $url, %arg) = @_;
217		351
218	my %hdr;	352	my %hdr;
		353
		354	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		355	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
219		356
220	$method = uc $method;	357	$method = uc $method;
221		358
222	if (my $hdr = $arg{headers}) {	359	if (my $hdr = $arg{headers}) {
223	while (my ($k, $v) = each %$hdr) {	360	while (my ($k, $v) = each %$hdr) {
224	$hdr{lc $k} = $v;	361	$hdr{lc $k} = $v;
225	}	362	}
226	}	363	}
227		364
		365	# pseudo headers for all subsequent responses
		366	my @pseudo = (URL => $url);
		367	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		368
228	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	369	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
229		370
230	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	371	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
231	if $recurse < 0;	372	if $recurse < 0;
232		373
233	my $proxy = $arg{proxy} \|\| $PROXY;	374	my $proxy = $arg{proxy} \|\| $PROXY;
234	my $timeout = $arg{timeout} \|\| $TIMEOUT;	375	my $timeout = $arg{timeout} \|\| $TIMEOUT;
235		376
236	$hdr{"user-agent"} \|\|= $USERAGENT;
237
238	my ($scheme, $authority, $upath, $query, $fragment) =	377	my ($uscheme, $uauthority, $upath, $query, $fragment) =
239	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	378	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
240		379
241	$scheme = lc $scheme;	380	$uscheme = lc $uscheme;
242		381
243	my $uport = $scheme eq "http" ? 80	382	my $uport = $uscheme eq "http" ? 80
244	: $scheme eq "https" ? 443	383	: $uscheme eq "https" ? 443
245	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" });	384	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
246		385
247	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	386	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
248	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	387	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
249		388
250	my $uhost = $1;	389	my $uhost = $1;
251	$uport = $2 if defined $2;	390	$uport = $2 if defined $2;
252		391
		392	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		393	unless exists $hdr{host};
		394
253	$uhost =~ s/^\[(.*)\]$/$1/;	395	$uhost =~ s/^\[(.*)\]$/$1/;
254	$upath .= "?$query" if length $query;	396	$upath .= $query if length $query;
255		397
256	$upath =~ s%^/?%/%;	398	$upath =~ s%^/?%/%;
257		399
258	# cookie processing	400	# cookie processing
259	if (my $jar = $arg{cookie_jar}) {	401	if (my $jar = $arg{cookie_jar}) {
260	%$jar = () if $jar->{version} < 1;	402	%$jar = () if $jar->{version} != 1;
261		403
262	my @cookie;	404	my @cookie;
263		405
264	while (my ($chost, $v) = each %$jar) {	406	while (my ($chost, $v) = each %$jar) {
		407	if ($chost =~ /^\./) {
265	next unless $chost eq substr $uhost, -length $chost;	408	next unless $chost eq substr $uhost, -length $chost;
266	next unless $chost =~ /^\./;	409	} elsif ($chost =~ /\./) {
		410	next unless $chost eq $uhost;
		411	} else {
		412	next;
		413	}
267		414
268	while (my ($cpath, $v) = each %$v) {	415	while (my ($cpath, $v) = each %$v) {
269	next unless $cpath eq substr $upath, 0, length $cpath;	416	next unless $cpath eq substr $upath, 0, length $cpath;
270		417
271	while (my ($k, $v) = each %$v) {	418	while (my ($k, $v) = each %$v) {
272	next if $scheme ne "https" && exists $v->{secure};	419	next if $uscheme ne "https" && exists $v->{secure};
		420	my $value = $v->{value};
		421	$value =~ s/([\\"])/\\$1/g;
273	push @cookie, "$k=$v->{value}";	422	push @cookie, "$k=\"$value\"";
274	}	423	}
275	}	424	}
276	}	425	}
277		426
278	$hdr{cookie} = join "; ", @cookie	427	$hdr{cookie} = join "; ", @cookie
279	if @cookie;	428	if @cookie;
280	}	429	}
281		430
282	my ($rhost, $rport, $rpath); # request host, port, path	431	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
283		432
284	if ($proxy) {	433	if ($proxy) {
285	($rhost, $rport, $scheme) = @$proxy;	434	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
286	$rpath = $url;	435
		436	$rscheme = "http" unless defined $rscheme;
		437
		438	# don't support https requests over https-proxy transport,
		439	# can't be done with tls as spec'ed, unless you double-encrypt.
		440	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
287	} else {	441	} else {
288	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	442	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
289	$hdr{host} = $uhost;
290	}	443	}
291		444
		445	# leave out fragment and query string, just a heuristic
		446	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		447	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		448
292	$hdr{"content-length"} = length $arg{body};	449	$hdr{"content-length"} = length $arg{body}
		450	if length $arg{body} \|\| $method ne "GET";
293		451
294	my %state = (connect_guard => 1);	452	my %state = (connect_guard => 1);
295		453
296	_get_slot $uhost, sub {	454	_get_slot $uhost, sub {
297	$state{slot_guard} = shift;	455	$state{slot_guard} = shift;
298		456
299	return unless $state{connect_guard};	457	return unless $state{connect_guard};
300		458
301	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	459	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
302	$state{fh} = shift	460	$state{fh} = shift
		461	or do {
		462	my $err = "$!";
		463	%state = ();
303	or return $cb->(undef, { Status => 599, Reason => "$!" });	464	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		465	};
304		466
305	delete $state{connect_guard}; # reduce memory usage, save a tree	467	pop; # free memory, save a tree
		468
		469	return unless delete $state{connect_guard};
306		470
307	# get handle	471	# get handle
308	$state{handle} = new AnyEvent::Handle	472	$state{handle} = new AnyEvent::Handle
309	fh => $state{fh},	473	fh => $state{fh},
310	($scheme eq "https" ? (tls => "connect") : ());	474	peername => $rhost,
		475	tls_ctx => $arg{tls_ctx},
		476	# these need to be reconfigured on keepalive handles
		477	timeout => $timeout,
		478	on_error => sub {
		479	%state = ();
		480	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		481	},
		482	on_eof => sub {
		483	%state = ();
		484	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		485	},
		486	;
311		487
312	# limit the number of persistent connections	488	# limit the number of persistent connections
		489	# keepalive not yet supported
313	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	490	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
314	++$KA_COUNT{$_[1]};	491	# ++$KA_COUNT{$_[1]};
315	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	492	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		493	# --$KA_COUNT{$_[1]}
		494	# };
316	$hdr{connection} = "keep-alive";	495	# $hdr{connection} = "keep-alive";
317	delete $hdr{connection}; # keep-alive not yet supported
318	} else {	496	# } else {
319	delete $hdr{connection};	497	delete $hdr{connection};
320	}	498	# }
321		499
322	# (re-)configure handle	500	$state{handle}->starttls ("connect") if $rscheme eq "https";
323	$state{handle}->timeout ($timeout);
324	$state{handle}->on_error (sub {
325	%state = ();
326	$cb->(undef, { Status => 599, Reason => "$!" });
327	});
328	$state{handle}->on_eof (sub {
329	%state = ();
330	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
331	});
332		501
		502	# handle actual, non-tunneled, request
		503	my $handle_actual_request = sub {
		504	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		505
333	# send request	506	# send request
334	$state{handle}->push_write (	507	$state{handle}->push_write (
335	"$method $rpath HTTP/1.0\015\012"	508	"$method $rpath HTTP/1.0\015\012"
336	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	509	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
337	. "\015\012"	510	. "\015\012"
338	. (delete $arg{body})	511	. (delete $arg{body})
339	);
340
341	%hdr = (); # reduce memory usage, save a kitten
342
343	# status line
344	$state{handle}->push_read (line => qr/\015?\012/, sub {
345	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
346	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
347
348	my %hdr = ( # response headers
349	HTTPVersion => "\x00$1",
350	Status => "\x00$2",
351	Reason => "\x00$3",
352	);	512	);
353		513
354	# headers, could be optimized a bit	514	# return if error occured during push_write()
		515	return unless %state;
		516
		517	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		518
		519	# status line and headers
355	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	520	$state{handle}->push_read (line => $qr_nlnl, sub {
356	for ("$_[1]\012") {	521	for ("$_[1]") {
357	# we support spaces in field names, as lotus domino	522	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
358	# creates them.	523
		524	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
		525	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
		526
		527	push @pseudo,
		528	HTTPVersion => $1,
		529	Status => $2,
		530	Reason => $3,
		531	;
		532
		533	# things seen, not parsed:
		534	# p3pP="NON CUR OTPi OUR NOR UNI"
		535
359	$hdr{lc $1} .= "\x00$2"	536	$hdr{lc $1} .= ",$2"
360	while /\G	537	while /\G
361	([^:\000-\037]+):	538	([^:\000-\037]*):
362	[\011\040]*	539	[\011\040]*
363	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	540	((?: [^\012]+ \| \012[\011\040] )*)
364	\015?\012	541	\012
365	/gxc;	542	/gxc;
366		543
367	/\G$/	544	/\G$/
368	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));	545	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
369	}	546	}
370		547
		548	# remove the "," prefix we added to all headers above
371	substr $_, 0, 1, ""	549	substr $_, 0, 1, ""
372	for values %hdr;	550	for values %hdr;
373		551
		552	# patch in all pseudo headers
		553	%hdr = (%hdr, @pseudo);
		554
		555	# redirect handling
		556	# microsoft and other shitheads don't give a shit for following standards,
		557	# try to support some common forms of broken Location headers.
		558	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		559	$hdr{location} =~ s/^\.\/+//;
		560
		561	my $url = "$rscheme://$uhost:$uport";
		562
		563	unless ($hdr{location} =~ s/^\///) {
		564	$url .= $upath;
		565	$url =~ s/\/[^\/]*$//;
		566	}
		567
		568	$hdr{location} = "$url/$hdr{location}";
		569	}
		570
		571	my $redirect;
		572
		573	if ($recurse) {
		574	my $status = $hdr{Status};
		575
		576	# industry standard is to redirect POST as GET for
		577	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		578	# also, the UA should ask the user for 301 and 307 and POST,
		579	# industry standard seems to be to simply follow.
		580	# we go with the industry standard.
		581	if ($status == 301 or $status == 302 or $status == 303) {
		582	# HTTP/1.1 is unclear on how to mutate the method
		583	$method = "GET" unless $method eq "HEAD";
		584	$redirect = 1;
		585	} elsif ($status == 307) {
		586	$redirect = 1;
		587	}
		588	}
		589
374	my $finish = sub {	590	my $finish = sub {
		591	$state{handle}->destroy if $state{handle};
375	%state = ();	592	%state = ();
376		593
377	# set-cookie processing	594	# set-cookie processing
378	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	595	if ($arg{cookie_jar}) {
379	for (split /\x00/, $hdr{"set-cookie"}) {	596	for ($_[1]{"set-cookie"}) {
380	my ($cookie, @arg) = split /;\s*/;	597	# parse NAME=VALUE
381	my ($name, $value) = split /=/, $cookie, 2;	598	my @kv;
382	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);	599
		600	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		601	my $name = $1;
		602	my $value = $3;
		603
		604	unless ($value) {
		605	$value = $2;
		606	$value =~ s/\\(.)/$1/gs;
		607	}
		608
		609	push @kv, $name => $value;
		610
		611	last unless /\G\s*;/gc;
		612	}
		613
		614	last unless @kv;
		615
		616	my $name = shift @kv;
		617	my %kv = (value => shift @kv, @kv);
		618
		619	my $cdom;
		620	my $cpath = (delete $kv{path}) \|\| "/";
		621
		622	if (exists $kv{domain}) {
		623	$cdom = delete $kv{domain};
383		624
384	my $cdom = (delete $kv{domain}) \|\| $uhost;
385	my $cpath = (delete $kv{path}) \|\| "/";
386
387	$cdom =~ s/^.?/./; # make sure it starts with a "."	625	$cdom =~ s/^\.?/./; # make sure it starts with a "."
388		626
389	next if $cdom =~ /\.$/;	627	next if $cdom =~ /\.$/;
390		628
391	# this is not rfc-like and not netscape-like. go figure.	629	# this is not rfc-like and not netscape-like. go figure.
392	my $ndots = $cdom =~ y/.//;	630	my $ndots = $cdom =~ y/.//;
393	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	631	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		632	} else {
		633	$cdom = $uhost;
		634	}
394		635
395	# store it	636	# store it
396	$arg{cookie_jar}{version} = 1;	637	$arg{cookie_jar}{version} = 1;
397	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	638	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		639
		640	redo if /\G\s*,/gc;
398	}	641	}
399	}	642	}
400		643
401	if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {	644	if ($redirect && exists $hdr{location}) {
402	# microsoft and other assholes don't give a shit for following standards,	645	# we ignore any errors, as it is very common to receive
403	# try to support a common form of broken Location header.	646	# Content-Length != 0 but no actual body
404	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;	647	# we also access %hdr, as $_[1] might be an erro
405		648	http_request (
406	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	649	$method => $hdr{location},
		650	%arg,
		651	recurse => $recurse - 1,
		652	Redirect => \@_,
		653	$cb);
407	} else {	654	} else {
408	$cb->($_[0], $_[1]);	655	$cb->($_[0], $_[1]);
409	}	656	}
410	};	657	};
411		658
412	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	659	my $len = $hdr{"content-length"};
		660
		661	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		662	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		663	} elsif (
		664	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		665	or $method eq "HEAD"
		666	or (defined $len && !$len)
		667	) {
		668	# no body
413	$finish->(undef, \%hdr);	669	$finish->("", \%hdr);
414	} else {	670	} else {
415	if (exists $hdr{"content-length"}) {	671	# body handling, four different code paths
416	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	672	# for want_body_handle, on_body (2x), normal (2x)
417	# could cache persistent connection now	673	# we might read too much here, but it does not matter yet (no pers. connections)
418	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	674	if (!$redirect && $arg{want_body_handle}) {
419	# but we don't, due to misdesigns, this is annoyingly complex	675	$_[0]->on_eof (undef);
		676	$_[0]->on_error (undef);
		677	$_[0]->on_read (undef);
		678
		679	$finish->(delete $state{handle}, \%hdr);
		680
		681	} elsif ($arg{on_body}) {
		682	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		683	if ($len) {
		684	$_[0]->on_eof (undef);
		685	$_[0]->on_read (sub {
		686	$len -= length $_[0]{rbuf};
		687
		688	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		689	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		690
		691	$len > 0
		692	or $finish->("", \%hdr);
420	};	693	});
421		694	} else {
		695	$_[0]->on_eof (sub {
422	$finish->($_[1], \%hdr);	696	$finish->("", \%hdr);
		697	});
		698	$_[0]->on_read (sub {
		699	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		700	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		701	});
423	});	702	}
424	} else {	703	} else {
425	# too bad, need to read until we get an error or EOF,
426	# no way to detect winged data.
427	$_[0]->on_error (sub {
428	$finish->($_[0]{rbuf}, \%hdr);
429	});
430	$_[0]->on_eof (undef);	704	$_[0]->on_eof (undef);
		705
		706	if ($len) {
		707	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		708	$_[0]->on_read (sub {
		709	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		710	if $len <= length $_[0]{rbuf};
		711	});
		712	} else {
		713	$_[0]->on_error (sub {
		714	($! == Errno::EPIPE \|\| !$!)
		715	? $finish->(delete $_[0]{rbuf}, \%hdr)
		716	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		717	});
431	$_[0]->on_read (sub { });	718	$_[0]->on_read (sub { });
		719	}
432	}	720	}
433	}	721	}
434	});	722	});
435	});	723	};
436	}, sub {	724
437	$timeout	725	# now handle proxy-CONNECT method
		726	if ($proxy && $uscheme eq "https") {
		727	# oh dear, we have to wrap it into a connect request
		728
		729	# maybe re-use $uauthority with patched port?
		730	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		731	$state{handle}->push_read (line => $qr_nlnl, sub {
		732	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		733	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
		734
		735	if ($2 == 200) {
		736	$rpath = $upath;
		737	&$handle_actual_request;
		738	} else {
		739	%state = ();
		740	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
		741	}
		742	});
		743	} else {
		744	&$handle_actual_request;
438	};	745	}
		746
		747	}, $arg{on_prepare} \|\| sub { $timeout };
439	};	748	};
440		749
441	defined wantarray && AnyEvent::Util::guard { %state = () }	750	defined wantarray && AnyEvent::Util::guard { %state = () }
442	}	751	}
443		752
444	sub http_get($$;@) {	753	sub http_get($@) {
445	unshift @_, "GET";	754	unshift @_, "GET";
446	&http_request	755	&http_request
447	}	756	}
448		757
449	sub http_head($$;@) {	758	sub http_head($@) {
450	unshift @_, "HEAD";	759	unshift @_, "HEAD";
451	&http_request	760	&http_request
452	}	761	}
453		762
454	sub http_post($$$;@) {	763	sub http_post($$@) {
		764	my $url = shift;
455	unshift @_, "POST", "body";	765	unshift @_, "POST", $url, "body";
456	&http_request	766	&http_request
457	}	767	}
458		768
459	=back	769	=back
460		770
		771	=head2 DNS CACHING
		772
		773	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		774	the actual connection, which in turn uses AnyEvent::DNS to resolve
		775	hostnames. The latter is a simple stub resolver and does no caching
		776	on its own. If you want DNS caching, you currently have to provide
		777	your own default resolver (by storing a suitable resolver object in
		778	C<$AnyEvent::DNS::RESOLVER>).
		779
461	=head2 GLOBAL FUNCTIONS AND VARIABLES	780	=head2 GLOBAL FUNCTIONS AND VARIABLES
462		781
463	=over 4	782	=over 4
464		783
465	=item AnyEvent::HTTP::set_proxy "proxy-url"	784	=item AnyEvent::HTTP::set_proxy "proxy-url"
466		785
467	Sets the default proxy server to use. The proxy-url must begin with a	786	Sets the default proxy server to use. The proxy-url must begin with a
468	string of the form C<http://host:port> (optionally C<https:...>).	787	string of the form C<http://host:port> (optionally C<https:...>), croaks
		788	otherwise.
		789
		790	To clear an already-set proxy, use C<undef>.
469		791
470	=item $AnyEvent::HTTP::MAX_RECURSE	792	=item $AnyEvent::HTTP::MAX_RECURSE
471		793
472	The default value for the C<recurse> request parameter (default: C<10>).	794	The default value for the C<recurse> request parameter (default: C<10>).
473		795
474	=item $AnyEvent::HTTP::USERAGENT	796	=item $AnyEvent::HTTP::USERAGENT
475		797
476	The default value for the C<User-Agent> header (the default is	798	The default value for the C<User-Agent> header (the default is
477	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	799	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
478		800
479	=item $AnyEvent::HTTP::MAX_PERSISTENT	801	=item $AnyEvent::HTTP::MAX_PER_HOST
480		802
481	The maximum number of persistent connections to keep open (default: 8).	803	The maximum number of concurrent connections to the same host (identified
		804	by the hostname). If the limit is exceeded, then the additional requests
		805	are queued until previous connections are closed.
482		806
483	Not implemented currently.	807	The default value for this is C<4>, and it is highly advisable to not
		808	increase it.
484		809
485	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	810	=item $AnyEvent::HTTP::ACTIVE
486		811
487	The maximum time to cache a persistent connection, in seconds (default: 2).	812	The number of active connections. This is not the number of currently
488		813	running requests, but the number of currently open and non-idle TCP
489	Not implemented currently.	814	connections. This number of can be useful for load-leveling.
490		815
491	=back	816	=back
492		817
493	=cut	818	=cut
494		819
495	sub set_proxy($) {	820	sub set_proxy($) {
		821	if (length $_[0]) {
496	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	822	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		823	or Carp::croak "$_[0]: invalid proxy URL";
		824	$PROXY = [$2, $3 \|\| 3128, $1]
		825	} else {
		826	undef $PROXY;
		827	}
497	}	828	}
498		829
499	# initialise proxy from environment	830	# initialise proxy from environment
		831	eval {
500	set_proxy $ENV{http_proxy};	832	set_proxy $ENV{http_proxy};
		833	};
501		834
502	=head1 SEE ALSO	835	=head1 SEE ALSO
503		836
504	L<AnyEvent>.	837	L<AnyEvent>.
505		838
506	=head1 AUTHOR	839	=head1 AUTHOR
507		840
508	Marc Lehmann <schmorp@schmorp.de>	841	Marc Lehmann <schmorp@schmorp.de>
509	http://home.schmorp.de/	842	http://home.schmorp.de/
		843
		844	With many thanks to Дмитрий Шалашов, who provided countless
		845	testcases and bugreports.
510		846
511	=cut	847	=cut
512		848
513	1	849	1
514		850

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.11 by root, Thu Jun 5 15:34:00 2008 UTC vs. Revision 1.57 by root, Mon Sep 6 06:31:32 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.11 by root, Thu Jun 5 15:34:00 2008 UTC vs.
Revision 1.57 by root, Mon Sep 6 06:31:32 2010 UTC