[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 1.52 by root, Sat Sep 26 10:13:12 2009 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 = '1.43';
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) = @_;
…		…
121	Whether to recurse requests or not, e.g. on redirects, authentication	136	Whether to recurse requests or not, e.g. on redirects, authentication
122	retries and so on, and how often to do so.	137	retries and so on, and how often to do so.
123		138
124	=item headers => hashref	139	=item headers => hashref
125		140
126	The request headers to use.	141	The request headers to use. Currently, C<http_request> may provide its
		142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
		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).
127		146
128	=item timeout => $seconds	147	=item timeout => $seconds
129		148
130	The time-out to use for various stages - each connect attempt will reset	149	The time-out to use for various stages - each connect attempt will reset
131	the timeout, as will read or write activity. Default timeout is 5 minutes.	150	the timeout, as will read or write activity, i.e. this is not an overall
		151	timeout.
		152
		153	Default timeout is 5 minutes.
132		154
133	=item proxy => [$host, $port[, $scheme]] or undef	155	=item proxy => [$host, $port[, $scheme]] or undef
134		156
135	Use the given http proxy for all requests. If not specified, then the	157	Use the given http proxy for all requests. If not specified, then the
136	default proxy (as specified by C<$ENV{http_proxy}>) is used.	158	default proxy (as specified by C<$ENV{http_proxy}>) is used.
137		159
138	C<$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
139	HTTPS.	161	HTTPS.
140		162
141	=item body => $string	163	=item body => $string
142		164
143	The request body, usually empty. Will be-sent as-is (future versions of	165	The request body, usually empty. Will be-sent as-is (future versions of
…		…
149	based on the original netscape specification.	171	based on the original netscape specification.
150		172
151	The C<$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
152	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
153	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
154	recommended, as expire times are currently being ignored.	176	recommended, as expiry times are currently being ignored.
155		177
156	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
157	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
158	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
159	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
160	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.
161		266
162	=back	267	=back
163		268
164	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/
165		270
…		…
179	use Data::Dumper;	284	use Data::Dumper;
180	print Dumper $hdr;	285	print Dumper $hdr;
181	}	286	}
182	;	287	;
183		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 $request;
		298
184	=cut	299	=cut
185		300
		301	sub _slot_schedule;
186	sub _slot_schedule($) {	302	sub _slot_schedule($) {
187	my $host = shift;	303	my $host = shift;
188		304
189	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {	305	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
190	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {	306	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
191	# somebody wnats that slot	307	# somebody wants that slot
192	++$CO_SLOT{$host}[0];	308	++$CO_SLOT{$host}[0];
		309	++$ACTIVE;
193		310
194	$cb->(AnyEvent::Util::guard {	311	$cb->(AnyEvent::Util::guard {
		312	--$ACTIVE;
195	--$CO_SLOT{$host}[0];	313	--$CO_SLOT{$host}[0];
196	_slot_schedule $host;	314	_slot_schedule $host;
197	});	315	});
198	} else {	316	} else {
199	# nobody wants the slot, maybe we can forget about it	317	# nobody wants the slot, maybe we can forget about it
200	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];	318	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
201	warn "$host deleted" unless $CO_SLOT{$host}[0];#d#
202	last;	319	last;
203	}	320	}
204	}	321	}
205	}	322	}
206		323
…		…
209	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
210		327
211	_slot_schedule $_[0];	328	_slot_schedule $_[0];
212	}	329	}
213		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
214	sub http_request($$$;@) {	337	sub http_request($$@) {
215	my $cb = pop;	338	my $cb = pop;
216	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
217		340
218	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";
219		345
220	$method = uc $method;	346	$method = uc $method;
221		347
222	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
223	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
224	$hdr{lc $k} = $v;	350	$hdr{lc $k} = $v;
225	}	351	}
226	}	352	}
227		353
228	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
229		355
230	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
231	if $recurse < 0;	357	if $recurse < 0;
232		358
233	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
234	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
235		361
236	$hdr{"user-agent"} \|\|= $USERAGENT;
237
238	my ($scheme, $authority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
239	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
240		364
241	$scheme = lc $scheme;	365	$uscheme = lc $uscheme;
242		366
243	my $uport = $scheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
244	: $scheme eq "https" ? 443	368	: $uscheme eq "https" ? 443
245	: 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 });
246		370
247	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
248	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
249		373
250	my $uhost = $1;	374	my $uhost = $1;
251	$uport = $2 if defined $2;	375	$uport = $2 if defined $2;
252		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";
		378
253	$uhost =~ s/^\[(.*)\]$/$1/;	379	$uhost =~ s/^\[(.*)\]$/$1/;
254	$upath .= "?$query" if length $query;	380	$upath .= "?$query" if length $query;
255		381
256	$upath =~ s%^/?%/%;	382	$upath =~ s%^/?%/%;
257		383
258	# cookie processing	384	# cookie processing
259	if (my $jar = $arg{cookie_jar}) {	385	if (my $jar = $arg{cookie_jar}) {
260	%$jar = () if $jar->{version} < 1;	386	%$jar = () if $jar->{version} != 1;
261		387
262	my @cookie;	388	my @cookie;
263		389
264	while (my ($chost, $v) = each %$jar) {	390	while (my ($chost, $v) = each %$jar) {
		391	if ($chost =~ /^\./) {
265	next unless $chost eq substr $uhost, -length $chost;	392	next unless $chost eq substr $uhost, -length $chost;
266	next unless $chost =~ /^\./;	393	} elsif ($chost =~ /\./) {
		394	next unless $chost eq $uhost;
		395	} else {
		396	next;
		397	}
267		398
268	while (my ($cpath, $v) = each %$v) {	399	while (my ($cpath, $v) = each %$v) {
269	next unless $cpath eq substr $upath, 0, length $cpath;	400	next unless $cpath eq substr $upath, 0, length $cpath;
270		401
271	while (my ($k, $v) = each %$v) {	402	while (my ($k, $v) = each %$v) {
272	next if $scheme ne "https" && exists $v->{secure};	403	next if $uscheme ne "https" && exists $v->{secure};
		404	my $value = $v->{value};
		405	$value =~ s/([\\"])/\\$1/g;
273	push @cookie, "$k=$v->{value}";	406	push @cookie, "$k=\"$value\"";
274	}	407	}
275	}	408	}
276	}	409	}
277		410
278	$hdr{cookie} = join "; ", @cookie	411	$hdr{cookie} = join "; ", @cookie
279	if @cookie;	412	if @cookie;
280	}	413	}
281		414
282	my ($rhost, $rport, $rpath); # request host, port, path	415	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
283		416
284	if ($proxy) {	417	if ($proxy) {
285	($rhost, $rport, $scheme) = @$proxy;	418	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
286	$rpath = $url;	419
		420	$rscheme = "http" unless defined $rscheme;
		421
		422	# don't support https requests over https-proxy transport,
		423	# can't be done with tls as spec'ed, unless you double-encrypt.
		424	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
287	} else {	425	} else {
288	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	426	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
289	$hdr{host} = $uhost;
290	}	427	}
		428
		429	# leave out fragment and query string, just a heuristic
		430	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		431	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
291		432
292	$hdr{"content-length"} = length $arg{body};	433	$hdr{"content-length"} = length $arg{body};
293		434
294	my %state = (connect_guard => 1);	435	my %state = (connect_guard => 1);
295		436
…		…
298		439
299	return unless $state{connect_guard};	440	return unless $state{connect_guard};
300		441
301	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	442	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
302	$state{fh} = shift	443	$state{fh} = shift
		444	or do {
		445	my $err = "$!";
		446	%state = ();
303	or return $cb->(undef, { Status => 599, Reason => "$!" });	447	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		448	};
304		449
305	delete $state{connect_guard}; # reduce memory usage, save a tree	450	pop; # free memory, save a tree
		451
		452	return unless delete $state{connect_guard};
306		453
307	# get handle	454	# get handle
308	$state{handle} = new AnyEvent::Handle	455	$state{handle} = new AnyEvent::Handle
309	fh => $state{fh},	456	fh => $state{fh},
310	($scheme eq "https" ? (tls => "connect") : ());	457	timeout => $timeout,
		458	peername => $rhost,
		459	tls_ctx => $arg{tls_ctx};
311		460
312	# limit the number of persistent connections	461	# limit the number of persistent connections
		462	# keepalive not yet supported
313	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	463	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
314	++$KA_COUNT{$_[1]};	464	++$KA_COUNT{$_[1]};
315	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	465	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		466	--$KA_COUNT{$_[1]}
		467	};
316	$hdr{connection} = "keep-alive";	468	$hdr{connection} = "keep-alive";
317	delete $hdr{connection}; # keep-alive not yet supported
318	} else {	469	} else {
319	delete $hdr{connection};	470	delete $hdr{connection};
320	}	471	}
321		472
322	# (re-)configure handle	473	# (re-)configure handle
323	$state{handle}->timeout ($timeout);
324	$state{handle}->on_error (sub {	474	$state{handle}->on_error (sub {
325	%state = ();	475	%state = ();
326	$cb->(undef, { Status => 599, Reason => "$!" });	476	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
327	});	477	});
328	$state{handle}->on_eof (sub {	478	$state{handle}->on_eof (sub {
329	%state = ();	479	%state = ();
330	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });	480	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
331	});	481	});
332		482
		483	$state{handle}->starttls ("connect") if $rscheme eq "https";
		484
		485	# handle actual, non-tunneled, request
		486	my $handle_actual_request = sub {
		487	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		488
333	# send request	489	# send request
334	$state{handle}->push_write (	490	$state{handle}->push_write (
335	"$method $rpath HTTP/1.0\015\012"	491	"$method $rpath HTTP/1.0\015\012"
336	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	492	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
337	. "\015\012"	493	. "\015\012"
338	. (delete $arg{body})	494	. (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	);	495	);
353		496
		497	%hdr = (); # reduce memory usage, save a kitten
		498
		499	# status line
		500	$state{handle}->push_read (line => $qr_nl, sub {
		501	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		502	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
		503
		504	my %hdr = ( # response headers
		505	HTTPVersion => ",$1",
		506	Status => ",$2",
		507	Reason => ",$3",
		508	URL => ",$url"
		509	);
		510
354	# headers, could be optimized a bit	511	# headers, could be optimized a bit
355	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	512	$state{handle}->unshift_read (line => $qr_nlnl, sub {
356	for ("$_[1]\012") {	513	for ("$_[1]") {
357	# we support spaces in field names, as lotus domino	514	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
358	# creates them.	515
		516	# things seen, not parsed:
		517	# p3pP="NON CUR OTPi OUR NOR UNI"
		518
359	$hdr{lc $1} .= "\x00$2"	519	$hdr{lc $1} .= ",$2"
360	while /\G	520	while /\G
361	([^:\000-\037]+):	521	([^:\000-\037]*):
362	[\011\040]*	522	[\011\040]*
363	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	523	((?: [^\012]+ \| \012[\011\040] )*)
364	\015?\012	524	\012
365	/gxc;	525	/gxc;
366		526
367	/\G$/	527	/\G$/
368	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));	528	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
369	}	529	}
370		530
371	substr $_, 0, 1, ""	531	substr $_, 0, 1, ""
372	for values %hdr;	532	for values %hdr;
373		533
374	my $finish = sub {	534	# redirect handling
375	%state = ();	535	# microsoft and other shitheads don't give a shit for following standards,
		536	# try to support some common forms of broken Location headers.
		537	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		538	$hdr{location} =~ s/^\.\/+//;
376		539
377	# set-cookie processing	540	my $url = "$rscheme://$uhost:$uport";
378	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
379	for (split /\x00/, $hdr{"set-cookie"}) {
380	my ($cookie, @arg) = split /;\s*/;
381	my ($name, $value) = split /=/, $cookie, 2;
382	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
383
384	my $cdom = (delete $kv{domain}) \|\| $uhost;
385	my $cpath = (delete $kv{path}) \|\| "/";
386
387	$cdom =~ s/^.?/./; # make sure it starts with a "."
388		541
389	next if $cdom =~ /\.$/;	542	unless ($hdr{location} =~ s/^\///) {
390		543	$url .= $upath;
391	# this is not rfc-like and not netscape-like. go figure.	544	$url =~ s/\/[^\/]*$//;
392	my $ndots = $cdom =~ y/.//;	545	}
393	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	546
394		547	$hdr{location} = "$url/$hdr{location}";
		548	}
		549
		550	my $redirect;
		551
		552	if ($recurse) {
		553	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
		554	# apparently, mozilla et al. just change POST to GET here
		555	# more research is needed before we do the same
395	# store it	556	$redirect = 1;
396	$arg{cookie_jar}{version} = 1;	557	} elsif ($hdr{Status} == 303) {
397	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	558	# even http/1.1 is unclear on how to mutate the method
		559	$method = "GET" unless $method eq "HEAD";
		560	$redirect = 1;
		561	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		562	$redirect = 1;
398	}	563	}
399	}	564	}
400		565
401	if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {	566	my $finish = sub {
402	# microsoft and other assholes don't give a shit for following standards,	567	$state{handle}->destroy if $state{handle};
403	# try to support a common form of broken Location header.	568	%state = ();
404	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
405		569
		570	# set-cookie processing
		571	if ($arg{cookie_jar}) {
		572	for ($_[1]{"set-cookie"}) {
		573	# parse NAME=VALUE
		574	my @kv;
		575
		576	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		577	my $name = $1;
		578	my $value = $3;
		579
		580	unless ($value) {
		581	$value = $2;
		582	$value =~ s/\\(.)/$1/gs;
		583	}
		584
		585	push @kv, $name => $value;
		586
		587	last unless /\G\s*;/gc;
		588	}
		589
		590	last unless @kv;
		591
		592	my $name = shift @kv;
		593	my %kv = (value => shift @kv, @kv);
		594
		595	my $cdom;
		596	my $cpath = (delete $kv{path}) \|\| "/";
		597
		598	if (exists $kv{domain}) {
		599	$cdom = delete $kv{domain};
		600
		601	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		602
		603	next if $cdom =~ /\.$/;
		604
		605	# this is not rfc-like and not netscape-like. go figure.
		606	my $ndots = $cdom =~ y/.//;
		607	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		608	} else {
		609	$cdom = $uhost;
		610	}
		611
		612	# store it
		613	$arg{cookie_jar}{version} = 1;
		614	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		615
		616	redo if /\G\s*,/gc;
		617	}
		618	}
		619
		620	if ($redirect && exists $hdr{location}) {
		621	# we ignore any errors, as it is very common to receive
		622	# Content-Length != 0 but no actual body
		623	# we also access %hdr, as $_[1] might be an erro
406	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	624	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
		625	} else {
		626	$cb->($_[0], $_[1]);
		627	}
		628	};
		629
		630	my $len = $hdr{"content-length"};
		631
		632	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		633	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
		634	} elsif (
		635	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		636	or $method eq "HEAD"
		637	or (defined $len && !$len)
		638	) {
		639	# no body
		640	$finish->("", \%hdr);
407	} else {	641	} else {
408	$cb->($_[0], $_[1]);	642	# body handling, four different code paths
		643	# for want_body_handle, on_body (2x), normal (2x)
		644	# we might read too much here, but it does not matter yet (no pers. connections)
		645	if (!$redirect && $arg{want_body_handle}) {
		646	$_[0]->on_eof (undef);
		647	$_[0]->on_error (undef);
		648	$_[0]->on_read (undef);
		649
		650	$finish->(delete $state{handle}, \%hdr);
		651
		652	} elsif ($arg{on_body}) {
		653	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		654	if ($len) {
		655	$_[0]->on_eof (undef);
		656	$_[0]->on_read (sub {
		657	$len -= length $_[0]{rbuf};
		658
		659	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		660	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		661
		662	$len > 0
		663	or $finish->("", \%hdr);
		664	});
		665	} else {
		666	$_[0]->on_eof (sub {
		667	$finish->("", \%hdr);
		668	});
		669	$_[0]->on_read (sub {
		670	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		671	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		672	});
		673	}
		674	} else {
		675	$_[0]->on_eof (undef);
		676
		677	if ($len) {
		678	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		679	$_[0]->on_read (sub {
		680	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		681	if $len <= length $_[0]{rbuf};
		682	});
		683	} else {
		684	$_[0]->on_error (sub {
		685	$! == Errno::EPIPE \|\| !$!
		686	? $finish->(delete $_[0]{rbuf}, \%hdr)
		687	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
		688	});
		689	$_[0]->on_read (sub { });
		690	}
		691	}
409	}	692	}
410	};	693	});
		694	});
		695	};
411		696
412	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	697	# now handle proxy-CONNECT method
413	$finish->(undef, \%hdr);	698	if ($proxy && $uscheme eq "https") {
		699	# oh dear, we have to wrap it into a connect request
		700
		701	# maybe re-use $uauthority with patched port?
		702	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		703	$state{handle}->push_read (line => $qr_nlnl, sub {
		704	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		705	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
		706
		707	if ($2 == 200) {
		708	$rpath = $upath;
		709	&$handle_actual_request;
414	} else {	710	} else {
415	if (exists $hdr{"content-length"}) {	711	%state = ();
416	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	712	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
417	# could cache persistent connection now
418	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
419	# but we don't, due to misdesigns, this is annoyingly complex
420	};
421
422	$finish->($_[1], \%hdr);
423	});
424	} 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);
431	$_[0]->on_read (sub { });
432	}
433	}	713	}
434	});	714	});
		715	} else {
		716	&$handle_actual_request;
435	});	717	}
436	}, sub {	718
437	$timeout	719	}, $arg{on_prepare} \|\| sub { $timeout };
438	};
439	};	720	};
440		721
441	defined wantarray && AnyEvent::Util::guard { %state = () }	722	defined wantarray && AnyEvent::Util::guard { %state = () }
442	}	723	}
443		724
444	sub http_get($$;@) {	725	sub http_get($@) {
445	unshift @_, "GET";	726	unshift @_, "GET";
446	&http_request	727	&http_request
447	}	728	}
448		729
449	sub http_head($$;@) {	730	sub http_head($@) {
450	unshift @_, "HEAD";	731	unshift @_, "HEAD";
451	&http_request	732	&http_request
452	}	733	}
453		734
454	sub http_post($$$;@) {	735	sub http_post($$@) {
		736	my $url = shift;
455	unshift @_, "POST", "body";	737	unshift @_, "POST", $url, "body";
456	&http_request	738	&http_request
457	}	739	}
458		740
459	=back	741	=back
460		742
…		…
463	=over 4	745	=over 4
464		746
465	=item AnyEvent::HTTP::set_proxy "proxy-url"	747	=item AnyEvent::HTTP::set_proxy "proxy-url"
466		748
467	Sets the default proxy server to use. The proxy-url must begin with a	749	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:...>).	750	string of the form C<http://host:port> (optionally C<https:...>), croaks
		751	otherwise.
		752
		753	To clear an already-set proxy, use C<undef>.
469		754
470	=item $AnyEvent::HTTP::MAX_RECURSE	755	=item $AnyEvent::HTTP::MAX_RECURSE
471		756
472	The default value for the C<recurse> request parameter (default: C<10>).	757	The default value for the C<recurse> request parameter (default: C<10>).
473		758
474	=item $AnyEvent::HTTP::USERAGENT	759	=item $AnyEvent::HTTP::USERAGENT
475		760
476	The default value for the C<User-Agent> header (the default is	761	The default value for the C<User-Agent> header (the default is
477	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	762	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
478		763
479	=item $AnyEvent::HTTP::MAX_PERSISTENT	764	=item $AnyEvent::HTTP::MAX_PER_HOST
480		765
481	The maximum number of persistent connections to keep open (default: 8).	766	The maximum number of concurrent connections to the same host (identified
		767	by the hostname). If the limit is exceeded, then the additional requests
		768	are queued until previous connections are closed.
482		769
483	Not implemented currently.	770	The default value for this is C<4>, and it is highly advisable to not
		771	increase it.
484		772
485	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	773	=item $AnyEvent::HTTP::ACTIVE
486		774
487	The maximum time to cache a persistent connection, in seconds (default: 2).	775	The number of active connections. This is not the number of currently
488		776	running requests, but the number of currently open and non-idle TCP
489	Not implemented currently.	777	connections. This number of can be useful for load-leveling.
490		778
491	=back	779	=back
492		780
493	=cut	781	=cut
494		782
495	sub set_proxy($) {	783	sub set_proxy($) {
		784	if (length $_[0]) {
496	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	785	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		786	or Carp::croak "$_[0]: invalid proxy URL";
		787	$PROXY = [$2, $3 \|\| 3128, $1]
		788	} else {
		789	undef $PROXY;
		790	}
497	}	791	}
498		792
499	# initialise proxy from environment	793	# initialise proxy from environment
		794	eval {
500	set_proxy $ENV{http_proxy};	795	set_proxy $ENV{http_proxy};
		796	};
501		797
502	=head1 SEE ALSO	798	=head1 SEE ALSO
503		799
504	L<AnyEvent>.	800	L<AnyEvent>.
505		801
506	=head1 AUTHOR	802	=head1 AUTHOR
507		803
508	Marc Lehmann <schmorp@schmorp.de>	804	Marc Lehmann <schmorp@schmorp.de>
509	http://home.schmorp.de/	805	http://home.schmorp.de/
		806
		807	With many thanks to Дмитрий Шалашов, who provided countless
		808	testcases and bugreports.
510		809
511	=cut	810	=cut
512		811
513	1	812	1
514		813

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 1.52 by root, Sat Sep 26 10:13:12 2009 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 1.52 by root, Sat Sep 26 10:13:12 2009 UTC