[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 1.54 by root, Wed Jun 16 18:09:52 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 = '1.44';
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<$method> (e.g. C<GET>, C<POST>). The URL
86	must be an absolute http or https URL.	92	must be an absolute http or https URL.
87		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
88	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
89	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
90	response headers as second argument.	101	second argument.
91		102
92	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
93	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
94	C<Reason> contain the three parts of the HTTP Status-Line of the same	105	contain the three parts of the HTTP Status-Line of the same name. The
		106	pseudo-header C<URL> contains the original URL (which can differ from the
		107	requested URL when following redirects).
		108
95	name. If the server sends a header multiple lines, then their contents	109	If the server sends a header multiple times, then their contents will be
96	will be joined together with C<\x00>.	110	joined together with a comma (C<,>), as per the HTTP spec.
97		111
98	If an internal error occurs, such as not being able to resolve a hostname,	112	If an internal error occurs, such as not being able to resolve a hostname,
99	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
100	and the C<Reason> pseudo-header will contain an error message.	114	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		115	message.
101		116
102	A typical callback might look like this:	117	A typical callback might look like this:
103		118
104	sub {	119	sub {
105	my ($body, $hdr) = @_;	120	my ($body, $hdr) = @_;
…		…
123		138
124	=item headers => hashref	139	=item headers => hashref
125		140
126	The request headers to use. Currently, C<http_request> may provide its	141	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	142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
128	and will provide defaults for C<User-Agent:> and C<Referer:>.	143	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		144	suppressed by using C<undef> for these headers in which case they won't be
		145	sent at all).
129		146
130	=item timeout => $seconds	147	=item timeout => $seconds
131		148
132	The time-out to use for various stages - each connect attempt will reset	149	The time-out to use for various stages - each connect attempt will reset
133	the timeout, as will read or write activity. Default timeout is 5 minutes.	150	the timeout, as will read or write activity, i.e. this is not an overall
		151	timeout.
		152
		153	Default timeout is 5 minutes.
134		154
135	=item proxy => [$host, $port[, $scheme]] or undef	155	=item proxy => [$host, $port[, $scheme]] or undef
136		156
137	Use the given http proxy for all requests. If not specified, then the	157	Use the given http proxy for all requests. If not specified, then the
138	default proxy (as specified by C<$ENV{http_proxy}>) is used.	158	default proxy (as specified by C<$ENV{http_proxy}>) is used.
139		159
140	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	160	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
141	HTTPS.	161	HTTPS.
142		162
143	=item body => $string	163	=item body => $string
144		164
145	The request body, usually empty. Will be-sent as-is (future versions of	165	The request body, usually empty. Will be-sent as-is (future versions of
…		…
151	based on the original netscape specification.	171	based on the original netscape specification.
152		172
153	The C<$hash_ref> must be an (initially empty) hash reference which will	173	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	174	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	175	persistent storage with something like JSON or Storable, but this is not
156	recommended, as expire times are currently being ignored.	176	recommended, as expiry times are currently being ignored.
157		177
158	Note that this cookie implementation is not of very high quality, nor	178	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	179	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	180	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	181	cookie-using sites working. Cookies are a privacy disaster, do not use
162	them unless required to.	182	them unless required to.
		183
		184	=item tls_ctx => $scheme \| $tls_ctx
		185
		186	Specifies the AnyEvent::TLS context to be used for https connections. This
		187	parameter follows the same rules as the C<tls_ctx> parameter to
		188	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		189	C<high> can be specified, which give you a predefined low-security (no
		190	verification, highest compatibility) and high-security (CA and common-name
		191	verification) TLS context.
		192
		193	The default for this option is C<low>, which could be interpreted as "give
		194	me the page, no matter what".
		195
		196	=item on_prepare => $callback->($fh)
		197
		198	In rare cases you need to "tune" the socket before it is used to
		199	connect (for exmaple, to bind it on a given IP address). This parameter
		200	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		201	and behaves exactly the same way (e.g. it has to provide a
		202	timeout). See the description for the C<$prepare_cb> argument of
		203	C<AnyEvent::Socket::tcp_connect> for details.
		204
		205	=item on_header => $callback->($headers)
		206
		207	When specified, this callback will be called with the header hash as soon
		208	as headers have been successfully received from the remote server (not on
		209	locally-generated errors).
		210
		211	It has to return either true (in which case AnyEvent::HTTP will continue),
		212	or false, in which case AnyEvent::HTTP will cancel the download (and call
		213	the finish callback with an error code of C<598>).
		214
		215	This callback is useful, among other things, to quickly reject unwanted
		216	content, which, if it is supposed to be rare, can be faster than first
		217	doing a C<HEAD> request.
		218
		219	Example: cancel the request unless the content-type is "text/html".
		220
		221	on_header => sub {
		222	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		223	},
		224
		225	=item on_body => $callback->($partial_body, $headers)
		226
		227	When specified, all body data will be passed to this callback instead of
		228	to the completion callback. The completion callback will get the empty
		229	string instead of the body data.
		230
		231	It has to return either true (in which case AnyEvent::HTTP will continue),
		232	or false, in which case AnyEvent::HTTP will cancel the download (and call
		233	the completion callback with an error code of C<598>).
		234
		235	This callback is useful when the data is too large to be held in memory
		236	(so the callback writes it to a file) or when only some information should
		237	be extracted, or when the body should be processed incrementally.
		238
		239	It is usually preferred over doing your own body handling via
		240	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		241	only used to create a connection, C<want_body_handle> is the better
		242	alternative, as it allows you to install your own event handler, reducing
		243	resource usage.
		244
		245	=item want_body_handle => $enable
		246
		247	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		248	changes considerably: after parsing the headers, and instead of
		249	downloading the body (if any), the completion callback will be
		250	called. Instead of the C<$body> argument containing the body data, the
		251	callback will receive the L<AnyEvent::Handle> object associated with the
		252	connection. In error cases, C<undef> will be passed. When there is no body
		253	(e.g. status C<304>), the empty string will be passed.
		254
		255	The handle object might or might not be in TLS mode, might be connected to
		256	a proxy, be a persistent connection etc., and configured in unspecified
		257	ways. The user is responsible for this handle (it will not be used by this
		258	module anymore).
		259
		260	This is useful with some push-type services, where, after the initial
		261	headers, an interactive protocol is used (typical example would be the
		262	push-style twitter API which starts a JSON/XML stream).
		263
		264	If you think you need this, first have a look at C<on_body>, to see if
		265	that doesn't solve your problem in a better way.
163		266
164	=back	267	=back
165		268
166	Example: make a simple HTTP GET request for http://www.nethype.de/	269	Example: make a simple HTTP GET request for http://www.nethype.de/
167		270
…		…
181	use Data::Dumper;	284	use Data::Dumper;
182	print Dumper $hdr;	285	print Dumper $hdr;
183	}	286	}
184	;	287	;
185		288
		289	Example: make another simple HTTP GET request, but immediately try to
		290	cancel it.
		291
		292	my $request = http_request GET => "http://www.nethype.de/", sub {
		293	my ($body, $hdr) = @_;
		294	print "$body\n";
		295	};
		296
		297	undef $request;
		298
186	=cut	299	=cut
187		300
188	sub _slot_schedule;	301	sub _slot_schedule;
189	sub _slot_schedule($) {	302	sub _slot_schedule($) {
190	my $host = shift;	303	my $host = shift;
191		304
192	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {	305	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
193	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {	306	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
194	# somebody wants that slot	307	# somebody wants that slot
195	++$CO_SLOT{$host}[0];	308	++$CO_SLOT{$host}[0];
		309	++$ACTIVE;
196		310
197	$cb->(AnyEvent::Util::guard {	311	$cb->(AnyEvent::Util::guard {
		312	--$ACTIVE;
198	--$CO_SLOT{$host}[0];	313	--$CO_SLOT{$host}[0];
199	_slot_schedule $host;	314	_slot_schedule $host;
200	});	315	});
201	} else {	316	} else {
202	# nobody wants the slot, maybe we can forget about it	317	# nobody wants the slot, maybe we can forget about it
…		…
211	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
212		327
213	_slot_schedule $_[0];	328	_slot_schedule $_[0];
214	}	329	}
215		330
		331	our $qr_nl = qr{\015?\012};
		332	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		333
		334	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		335	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		336
216	sub http_request($$$;@) {	337	sub http_request($$@) {
217	my $cb = pop;	338	my $cb = pop;
218	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
219		340
220	my %hdr;	341	my %hdr;
		342
		343	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		344	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
221		345
222	$method = uc $method;	346	$method = uc $method;
223		347
224	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
225	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
226	$hdr{lc $k} = $v;	350	$hdr{lc $k} = $v;
227	}	351	}
228	}	352	}
229		353
230	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
231		355
232	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
233	if $recurse < 0;	357	if $recurse < 0;
234		358
235	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
236	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
237		361
238	$hdr{"user-agent"} \|\|= $USERAGENT;
239
240	my ($scheme, $authority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
241	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
242		364
243	$scheme = lc $scheme;	365	$uscheme = lc $uscheme;
244		366
245	my $uport = $scheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
246	: $scheme eq "https" ? 443	368	: $uscheme eq "https" ? 443
247	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" });	369	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });
248		370
249	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
250	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
251		373
252	my $uhost = $1;	374	my $uhost = $1;
253	$uport = $2 if defined $2;	375	$uport = $2 if defined $2;
254		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		378	unless exists $hdr{host};
		379
255	$uhost =~ s/^\[(.*)\]$/$1/;	380	$uhost =~ s/^\[(.*)\]$/$1/;
256	$upath .= "?$query" if length $query;	381	$upath .= "?$query" if length $query;
257		382
258	$upath =~ s%^/?%/%;	383	$upath =~ s%^/?%/%;
259		384
260	$hdr{referer} \|\|= "$scheme://$authority$upath";
261
262	# cookie processing	385	# cookie processing
263	if (my $jar = $arg{cookie_jar}) {	386	if (my $jar = $arg{cookie_jar}) {
264	%$jar = () if $jar->{version} < 1;	387	%$jar = () if $jar->{version} != 1;
265		388
266	my @cookie;	389	my @cookie;
267		390
268	while (my ($chost, $v) = each %$jar) {	391	while (my ($chost, $v) = each %$jar) {
		392	if ($chost =~ /^\./) {
269	next unless $chost eq substr $uhost, -length $chost;	393	next unless $chost eq substr $uhost, -length $chost;
270	next unless $chost =~ /^\./;	394	} elsif ($chost =~ /\./) {
		395	next unless $chost eq $uhost;
		396	} else {
		397	next;
		398	}
271		399
272	while (my ($cpath, $v) = each %$v) {	400	while (my ($cpath, $v) = each %$v) {
273	next unless $cpath eq substr $upath, 0, length $cpath;	401	next unless $cpath eq substr $upath, 0, length $cpath;
274		402
275	while (my ($k, $v) = each %$v) {	403	while (my ($k, $v) = each %$v) {
276	next if $scheme ne "https" && exists $v->{secure};	404	next if $uscheme ne "https" && exists $v->{secure};
		405	my $value = $v->{value};
		406	$value =~ s/([\\"])/\\$1/g;
277	push @cookie, "$k=$v->{value}";	407	push @cookie, "$k=\"$value\"";
278	}	408	}
279	}	409	}
280	}	410	}
281		411
282	$hdr{cookie} = join "; ", @cookie	412	$hdr{cookie} = join "; ", @cookie
283	if @cookie;	413	if @cookie;
284	}	414	}
285		415
286	my ($rhost, $rport, $rpath); # request host, port, path	416	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
287		417
288	if ($proxy) {	418	if ($proxy) {
289	($rhost, $rport, $scheme) = @$proxy;	419	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
290	$rpath = $url;	420
		421	$rscheme = "http" unless defined $rscheme;
		422
		423	# don't support https requests over https-proxy transport,
		424	# can't be done with tls as spec'ed, unless you double-encrypt.
		425	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
291	} else {	426	} else {
292	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
293	$hdr{host} = $uhost;
294	}	428	}
295		429
		430	# leave out fragment and query string, just a heuristic
		431	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		432	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		433
296	$hdr{"content-length"} = length $arg{body};	434	$hdr{"content-length"} = length $arg{body}
		435	if length $arg{body} \|\| $method ne "GET";
297		436
298	my %state = (connect_guard => 1);	437	my %state = (connect_guard => 1);
299		438
300	_get_slot $uhost, sub {	439	_get_slot $uhost, sub {
301	$state{slot_guard} = shift;	440	$state{slot_guard} = shift;
302		441
303	return unless $state{connect_guard};	442	return unless $state{connect_guard};
304		443
305	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
306	$state{fh} = shift	445	$state{fh} = shift
		446	or do {
		447	my $err = "$!";
		448	%state = ();
307	or return $cb->(undef, { Status => 599, Reason => "$!" });	449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		450	};
308		451
309	delete $state{connect_guard}; # reduce memory usage, save a tree	452	pop; # free memory, save a tree
		453
		454	return unless delete $state{connect_guard};
310		455
311	# get handle	456	# get handle
312	$state{handle} = new AnyEvent::Handle	457	$state{handle} = new AnyEvent::Handle
313	fh => $state{fh},	458	fh => $state{fh},
314	($scheme eq "https" ? (tls => "connect") : ());	459	timeout => $timeout,
		460	peername => $rhost,
		461	tls_ctx => $arg{tls_ctx};
315		462
316	# limit the number of persistent connections	463	# limit the number of persistent connections
		464	# keepalive not yet supported
317	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
318	++$KA_COUNT{$_[1]};	466	++$KA_COUNT{$_[1]};
319	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	467	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		468	--$KA_COUNT{$_[1]}
		469	};
320	$hdr{connection} = "keep-alive";	470	$hdr{connection} = "keep-alive";
321	delete $hdr{connection}; # keep-alive not yet supported
322	} else {	471	} else {
323	delete $hdr{connection};	472	delete $hdr{connection};
324	}	473	}
325		474
326	# (re-)configure handle	475	# (re-)configure handle
327	$state{handle}->timeout ($timeout);
328	$state{handle}->on_error (sub {	476	$state{handle}->on_error (sub {
329	%state = ();	477	%state = ();
330	$cb->(undef, { Status => 599, Reason => "$!" });	478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
331	});	479	});
332	$state{handle}->on_eof (sub {	480	$state{handle}->on_eof (sub {
333	%state = ();	481	%state = ();
334	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });	482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
335	});	483	});
336		484
		485	$state{handle}->starttls ("connect") if $rscheme eq "https";
		486
		487	# handle actual, non-tunneled, request
		488	my $handle_actual_request = sub {
		489	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		490
337	# send request	491	# send request
338	$state{handle}->push_write (	492	$state{handle}->push_write (
339	"$method $rpath HTTP/1.0\015\012"	493	"$method $rpath HTTP/1.0\015\012"
340	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
341	. "\015\012"	495	. "\015\012"
342	. (delete $arg{body})	496	. (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	);	497	);
357		498
		499	# return if error occured during push_write()
		500	return unless %state;
		501
		502	%hdr = (); # reduce memory usage, save a kitten
		503
		504	# status line
		505	$state{handle}->push_read (line => $qr_nl, sub {
		506	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		507	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
		508
		509	my %hdr = ( # response headers
		510	HTTPVersion => ",$1",
		511	Status => ",$2",
		512	Reason => ",$3",
		513	URL => ",$url"
		514	);
		515
358	# headers, could be optimized a bit	516	# headers, could be optimized a bit
359	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	517	$state{handle}->unshift_read (line => $qr_nlnl, sub {
360	for ("$_[1]\012") {	518	for ("$_[1]") {
361	# we support spaces in field names, as lotus domino	519	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
362	# creates them.	520
		521	# things seen, not parsed:
		522	# p3pP="NON CUR OTPi OUR NOR UNI"
		523
363	$hdr{lc $1} .= "\x00$2"	524	$hdr{lc $1} .= ",$2"
364	while /\G	525	while /\G
365	([^:\000-\037]+):	526	([^:\000-\037]*):
366	[\011\040]*	527	[\011\040]*
367	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	528	((?: [^\012]+ \| \012[\011\040] )*)
368	\015?\012	529	\012
369	/gxc;	530	/gxc;
370		531
371	/\G$/	532	/\G$/
372	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));	533	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
373	}	534	}
374		535
375	substr $_, 0, 1, ""	536	substr $_, 0, 1, ""
376	for values %hdr;	537	for values %hdr;
377		538
378	my $finish = sub {	539	# redirect handling
379	%state = ();	540	# microsoft and other shitheads don't give a shit for following standards,
		541	# try to support some common forms of broken Location headers.
		542	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		543	$hdr{location} =~ s/^\.\/+//;
380		544
381	# set-cookie processing	545	my $url = "$rscheme://$uhost:$uport";
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		546
393	next if $cdom =~ /\.$/;	547	unless ($hdr{location} =~ s/^\///) {
394		548	$url .= $upath;
395	# this is not rfc-like and not netscape-like. go figure.	549	$url =~ s/\/[^\/]*$//;
396	my $ndots = $cdom =~ y/.//;	550	}
397	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	551
398		552	$hdr{location} = "$url/$hdr{location}";
		553	}
		554
		555	my $redirect;
		556
		557	if ($recurse) {
		558	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
		559	# apparently, mozilla et al. just change POST to GET here
		560	# more research is needed before we do the same
399	# store it	561	$redirect = 1;
400	$arg{cookie_jar}{version} = 1;	562	} elsif ($hdr{Status} == 303) {
401	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	563	# even http/1.1 is unclear on how to mutate the method
		564	$method = "GET" unless $method eq "HEAD";
		565	$redirect = 1;
		566	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		567	$redirect = 1;
402	}	568	}
403	}	569	}
404		570
405	if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {	571	my $finish = sub {
406	# microsoft and other assholes don't give a shit for following standards,	572	$state{handle}->destroy if $state{handle};
407	# try to support a common form of broken Location header.	573	%state = ();
408	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
409		574
		575	# set-cookie processing
		576	if ($arg{cookie_jar}) {
		577	for ($_[1]{"set-cookie"}) {
		578	# parse NAME=VALUE
		579	my @kv;
		580
		581	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		582	my $name = $1;
		583	my $value = $3;
		584
		585	unless ($value) {
		586	$value = $2;
		587	$value =~ s/\\(.)/$1/gs;
		588	}
		589
		590	push @kv, $name => $value;
		591
		592	last unless /\G\s*;/gc;
		593	}
		594
		595	last unless @kv;
		596
		597	my $name = shift @kv;
		598	my %kv = (value => shift @kv, @kv);
		599
		600	my $cdom;
		601	my $cpath = (delete $kv{path}) \|\| "/";
		602
		603	if (exists $kv{domain}) {
		604	$cdom = delete $kv{domain};
		605
		606	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		607
		608	next if $cdom =~ /\.$/;
		609
		610	# this is not rfc-like and not netscape-like. go figure.
		611	my $ndots = $cdom =~ y/.//;
		612	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		613	} else {
		614	$cdom = $uhost;
		615	}
		616
		617	# store it
		618	$arg{cookie_jar}{version} = 1;
		619	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		620
		621	redo if /\G\s*,/gc;
		622	}
		623	}
		624
		625	if ($redirect && exists $hdr{location}) {
		626	# we ignore any errors, as it is very common to receive
		627	# Content-Length != 0 but no actual body
		628	# we also access %hdr, as $_[1] might be an erro
410	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	629	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
		630	} else {
		631	$cb->($_[0], $_[1]);
		632	}
		633	};
		634
		635	my $len = $hdr{"content-length"};
		636
		637	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		638	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
		639	} elsif (
		640	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		641	or $method eq "HEAD"
		642	or (defined $len && !$len)
		643	) {
		644	# no body
		645	$finish->("", \%hdr);
411	} else {	646	} else {
412	$cb->($_[0], $_[1]);	647	# body handling, four different code paths
		648	# for want_body_handle, on_body (2x), normal (2x)
		649	# we might read too much here, but it does not matter yet (no pers. connections)
		650	if (!$redirect && $arg{want_body_handle}) {
		651	$_[0]->on_eof (undef);
		652	$_[0]->on_error (undef);
		653	$_[0]->on_read (undef);
		654
		655	$finish->(delete $state{handle}, \%hdr);
		656
		657	} elsif ($arg{on_body}) {
		658	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		659	if ($len) {
		660	$_[0]->on_eof (undef);
		661	$_[0]->on_read (sub {
		662	$len -= length $_[0]{rbuf};
		663
		664	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		665	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		666
		667	$len > 0
		668	or $finish->("", \%hdr);
		669	});
		670	} else {
		671	$_[0]->on_eof (sub {
		672	$finish->("", \%hdr);
		673	});
		674	$_[0]->on_read (sub {
		675	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		676	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		677	});
		678	}
		679	} else {
		680	$_[0]->on_eof (undef);
		681
		682	if ($len) {
		683	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		684	$_[0]->on_read (sub {
		685	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		686	if $len <= length $_[0]{rbuf};
		687	});
		688	} else {
		689	$_[0]->on_error (sub {
		690	$! == Errno::EPIPE \|\| !$!
		691	? $finish->(delete $_[0]{rbuf}, \%hdr)
		692	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
		693	});
		694	$_[0]->on_read (sub { });
		695	}
		696	}
413	}	697	}
414	};	698	});
		699	});
		700	};
415		701
416	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	702	# now handle proxy-CONNECT method
417	$finish->(undef, \%hdr);	703	if ($proxy && $uscheme eq "https") {
		704	# oh dear, we have to wrap it into a connect request
		705
		706	# maybe re-use $uauthority with patched port?
		707	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		708	$state{handle}->push_read (line => $qr_nlnl, sub {
		709	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		710	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
		711
		712	if ($2 == 200) {
		713	$rpath = $upath;
		714	&$handle_actual_request;
418	} else {	715	} else {
419	if (exists $hdr{"content-length"}) {	716	%state = ();
420	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	717	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
421	# could cache persistent connection now
422	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
423	# but we don't, due to misdesigns, this is annoyingly complex
424	};
425
426	$finish->($_[1], \%hdr);
427	});
428	} 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	});
434	$_[0]->on_eof (undef);
435	$_[0]->on_read (sub { });
436	}
437	}	718	}
438	});	719	});
		720	} else {
		721	&$handle_actual_request;
439	});	722	}
440	}, sub {	723
441	$timeout	724	}, $arg{on_prepare} \|\| sub { $timeout };
442	};
443	};	725	};
444		726
445	defined wantarray && AnyEvent::Util::guard { %state = () }	727	defined wantarray && AnyEvent::Util::guard { %state = () }
446	}	728	}
447		729
448	sub http_get($$;@) {	730	sub http_get($@) {
449	unshift @_, "GET";	731	unshift @_, "GET";
450	&http_request	732	&http_request
451	}	733	}
452		734
453	sub http_head($$;@) {	735	sub http_head($@) {
454	unshift @_, "HEAD";	736	unshift @_, "HEAD";
455	&http_request	737	&http_request
456	}	738	}
457		739
458	sub http_post($$$;@) {	740	sub http_post($$@) {
		741	my $url = shift;
459	unshift @_, "POST", "body";	742	unshift @_, "POST", $url, "body";
460	&http_request	743	&http_request
461	}	744	}
462		745
463	=back	746	=back
464		747
…		…
467	=over 4	750	=over 4
468		751
469	=item AnyEvent::HTTP::set_proxy "proxy-url"	752	=item AnyEvent::HTTP::set_proxy "proxy-url"
470		753
471	Sets the default proxy server to use. The proxy-url must begin with a	754	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:...>).	755	string of the form C<http://host:port> (optionally C<https:...>), croaks
		756	otherwise.
		757
		758	To clear an already-set proxy, use C<undef>.
473		759
474	=item $AnyEvent::HTTP::MAX_RECURSE	760	=item $AnyEvent::HTTP::MAX_RECURSE
475		761
476	The default value for the C<recurse> request parameter (default: C<10>).	762	The default value for the C<recurse> request parameter (default: C<10>).
477		763
478	=item $AnyEvent::HTTP::USERAGENT	764	=item $AnyEvent::HTTP::USERAGENT
479		765
480	The default value for the C<User-Agent> header (the default is	766	The default value for the C<User-Agent> header (the default is
481	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	767	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
482		768
483	=item $AnyEvent::HTTP::MAX_PERSISTENT	769	=item $AnyEvent::HTTP::MAX_PER_HOST
484		770
485	The maximum number of persistent connections to keep open (default: 8).	771	The maximum number of concurrent connections to the same host (identified
		772	by the hostname). If the limit is exceeded, then the additional requests
		773	are queued until previous connections are closed.
486		774
487	Not implemented currently.	775	The default value for this is C<4>, and it is highly advisable to not
		776	increase it.
488		777
489	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	778	=item $AnyEvent::HTTP::ACTIVE
490		779
491	The maximum time to cache a persistent connection, in seconds (default: 2).	780	The number of active connections. This is not the number of currently
492		781	running requests, but the number of currently open and non-idle TCP
493	Not implemented currently.	782	connections. This number of can be useful for load-leveling.
494		783
495	=back	784	=back
496		785
497	=cut	786	=cut
498		787
499	sub set_proxy($) {	788	sub set_proxy($) {
		789	if (length $_[0]) {
500	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	790	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		791	or Carp::croak "$_[0]: invalid proxy URL";
		792	$PROXY = [$2, $3 \|\| 3128, $1]
		793	} else {
		794	undef $PROXY;
		795	}
501	}	796	}
502		797
503	# initialise proxy from environment	798	# initialise proxy from environment
		799	eval {
504	set_proxy $ENV{http_proxy};	800	set_proxy $ENV{http_proxy};
		801	};
505		802
506	=head1 SEE ALSO	803	=head1 SEE ALSO
507		804
508	L<AnyEvent>.	805	L<AnyEvent>.
509		806
510	=head1 AUTHOR	807	=head1 AUTHOR
511		808
512	Marc Lehmann <schmorp@schmorp.de>	809	Marc Lehmann <schmorp@schmorp.de>
513	http://home.schmorp.de/	810	http://home.schmorp.de/
		811
		812	With many thanks to Дмитрий Шалашов, who provided countless
		813	testcases and bugreports.
514		814
515	=cut	815	=cut
516		816
517	1	817	1
518		818

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 1.54 by root, Wed Jun 16 18:09:52 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 1.54 by root, Wed Jun 16 18:09:52 2010 UTC