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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.9 by root, Wed Jun 4 13:51:53 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.
13		17
		18	This module implements a simple, stateless and non-blocking HTTP
		19	client. It supports GET, POST and other request methods, cookies and more,
		20	all on a very low level. It can follow redirects supports proxies and
		21	automatically limits the number of connections to the values specified in
		22	the RFC.
		23
		24	It should generally be a "good client" that is enough for most HTTP
		25	tasks. Simple tasks should be simple, but complex tasks should still be
		26	possible as the user retains control over request and response headers.
		27
		28	The caller is responsible for authentication management, cookies (if
		29	the simplistic implementation in this module doesn't suffice), referer
		30	and other high-level protocol details for which this module offers only
		31	limited support.
		32
14	=head2 METHODS	33	=head2 METHODS
15		34
16	=over 4	35	=over 4
17		36
18	=cut	37	=cut
…		…
20	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
21		40
22	use strict;	41	use strict;
23	no warnings;	42	no warnings;
24		43
25	use Carp;	44	use Errno ();
26		45
27	use AnyEvent ();	46	use AnyEvent 5.0 ();
28	use AnyEvent::Util ();	47	use AnyEvent::Util ();
29	use AnyEvent::Socket ();	48	use AnyEvent::Socket ();
30	use AnyEvent::Handle ();	49	use AnyEvent::Handle ();
31		50
32	use base Exporter::;	51	use base Exporter::;
33		52
34	our $VERSION = '1.0';	53	our $VERSION = '1.44';
35		54
36	our @EXPORT = qw(http_get http_request);	55	our @EXPORT = qw(http_get http_post http_head http_request);
37		56
38	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)";
39	our $MAX_RECURSE = 10;	58	our $MAX_RECURSE = 10;
40	our $MAX_PERSISTENT = 8;	59	our $MAX_PERSISTENT = 8;
41	our $PERSISTENT_TIMEOUT = 2;	60	our $PERSISTENT_TIMEOUT = 2;
42	our $TIMEOUT = 300;	61	our $TIMEOUT = 300;
43		62
44	# changing these is evil	63	# changing these is evil
45	our $MAX_PERSISTENT_PER_HOST = 2;	64	our $MAX_PERSISTENT_PER_HOST = 0;
46	our $MAX_PER_HOST = 4; # not respected yet :(	65	our $MAX_PER_HOST = 4;
47		66
48	our $PROXY;	67	our $PROXY;
		68	our $ACTIVE = 0;
49		69
50	my %KA_COUNT; # number of open keep-alive connections per host	70	my %KA_COUNT; # number of open keep-alive connections per host
		71	my %CO_SLOT; # number of open connections, and wait queue, per host
51		72
52	=item http_get $url, key => value..., $cb->($data, $headers)	73	=item http_get $url, key => value..., $cb->($data, $headers)
53		74
54	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
55	additional parameters.	76	additional parameters and the return value.
56		77
57	=item http_head $url, key => value..., $cb->($data, $headers)	78	=item http_head $url, key => value..., $cb->($data, $headers)
58		79
59	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
60	additional parameters.	81	on additional parameters and the return value.
61		82
62	=item http_post $url, $body, key => value..., $cb->($data, $headers)	83	=item http_post $url, $body, key => value..., $cb->($data, $headers)
63		84
64	Executes an HTTP-POST request with a request body of C<$bod>. See the	85	Executes an HTTP-POST request with a request body of C<$body>. See the
65	http_request function for details on additional parameters.	86	http_request function for details on additional parameters and the return
		87	value.
66		88
67	=item http_request $method => $url, key => value..., $cb->($data, $headers)	89	=item http_request $method => $url, key => value..., $cb->($data, $headers)
68		90
69	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	91	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
70	must be an absolute http or https URL.	92	must be an absolute http or https URL.
71		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
72	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
73	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
74	response headers as second argument.	101	second argument.
75		102
76	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
77	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
78	C<Reason> contain the three parts of the HTTP Status-Line of the same	105	contain the three parts of the HTTP Status-Line of the same name. The
79	name.	106	pseudo-header C<URL> contains the original URL (which can differ from the
		107	requested URL when following redirects).
		108
		109	If the server sends a header multiple times, then their contents will be
		110	joined together with a comma (C<,>), as per the HTTP spec.
80		111
81	If an internal error occurs, such as not being able to resolve a hostname,	112	If an internal error occurs, such as not being able to resolve a hostname,
82	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
83	and the C<Reason> pseudo-header will contain an error message.	114	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		115	message.
84		116
85	A typical callback might look like this:	117	A typical callback might look like this:
86		118
87	sub {	119	sub {
88	my ($body, $hdr) = @_;	120	my ($body, $hdr) = @_;
…		…
104	Whether to recurse requests or not, e.g. on redirects, authentication	136	Whether to recurse requests or not, e.g. on redirects, authentication
105	retries and so on, and how often to do so.	137	retries and so on, and how often to do so.
106		138
107	=item headers => hashref	139	=item headers => hashref
108		140
109	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).
110		146
111	=item timeout => $seconds	147	=item timeout => $seconds
112		148
113	The time-out to use for various stages - each connect attempt will reset	149	The time-out to use for various stages - each connect attempt will reset
114	the timeout, as will read or write activity. Default timeout is 5 minutes.	150	the timeout, as will read or write activity, i.e. this is not an overall
		151	timeout.
		152
		153	Default timeout is 5 minutes.
115		154
116	=item proxy => [$host, $port[, $scheme]] or undef	155	=item proxy => [$host, $port[, $scheme]] or undef
117		156
118	Use the given http proxy for all requests. If not specified, then the	157	Use the given http proxy for all requests. If not specified, then the
119	default proxy (as specified by C<$ENV{http_proxy}>) is used.	158	default proxy (as specified by C<$ENV{http_proxy}>) is used.
120		159
121	C<$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
122	HTTPS.	161	HTTPS.
123		162
124	=item body => $string	163	=item body => $string
125		164
126	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
127	this module might offer more options).	166	this module might offer more options).
		167
		168	=item cookie_jar => $hash_ref
		169
		170	Passing this parameter enables (simplified) cookie-processing, loosely
		171	based on the original netscape specification.
		172
		173	The C<$hash_ref> must be an (initially empty) hash reference which will
		174	get updated automatically. It is possible to save the cookie_jar to
		175	persistent storage with something like JSON or Storable, but this is not
		176	recommended, as expiry times are currently being ignored.
		177
		178	Note that this cookie implementation is not of very high quality, nor
		179	meant to be complete. If you want complete cookie management you have to
		180	do that on your own. C<cookie_jar> is meant as a quick fix to get some
		181	cookie-using sites working. Cookies are a privacy disaster, do not use
		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.
128		266
129	=back	267	=back
130		268
131	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/
132		270
…		…
146	use Data::Dumper;	284	use Data::Dumper;
147	print Dumper $hdr;	285	print Dumper $hdr;
148	}	286	}
149	;	287	;
150		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 $request;
		298
151	=cut	299	=cut
152		300
		301	sub _slot_schedule;
		302	sub _slot_schedule($) {
		303	my $host = shift;
		304
		305	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		306	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		307	# somebody wants that slot
		308	++$CO_SLOT{$host}[0];
		309	++$ACTIVE;
		310
		311	$cb->(AnyEvent::Util::guard {
		312	--$ACTIVE;
		313	--$CO_SLOT{$host}[0];
		314	_slot_schedule $host;
		315	});
		316	} else {
		317	# nobody wants the slot, maybe we can forget about it
		318	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		319	last;
		320	}
		321	}
		322	}
		323
		324	# wait for a free slot on host, call callback
		325	sub _get_slot($$) {
		326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		327
		328	_slot_schedule $_[0];
		329	}
		330
		331	our $qr_nl = qr{\015?\012};
		332	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		333
		334	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		335	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		336
153	sub http_request($$$;@) {	337	sub http_request($$@) {
154	my $cb = pop;	338	my $cb = pop;
155	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
156		340
157	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";
158		345
159	$method = uc $method;	346	$method = uc $method;
160		347
161	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
162	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
163	$hdr{lc $k} = $v;	350	$hdr{lc $k} = $v;
164	}	351	}
165	}	352	}
166		353
167	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
168		355
169	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
170	if $recurse < 0;	357	if $recurse < 0;
171		358
172	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
173	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
174		361
175	$hdr{"user-agent"} \|\|= $USERAGENT;	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
		363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
176		364
177	my ($host, $port, $path, $scheme);	365	$uscheme = lc $uscheme;
		366
		367	my $uport = $uscheme eq "http" ? 80
		368	: $uscheme eq "https" ? 443
		369	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });
		370
		371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
		372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
		373
		374	my $uhost = $1;
		375	$uport = $2 if defined $2;
		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		378	unless exists $hdr{host};
		379
		380	$uhost =~ s/^\[(.*)\]$/$1/;
		381	$upath .= "?$query" if length $query;
		382
		383	$upath =~ s%^/?%/%;
		384
		385	# cookie processing
		386	if (my $jar = $arg{cookie_jar}) {
		387	%$jar = () if $jar->{version} != 1;
		388
		389	my @cookie;
		390
		391	while (my ($chost, $v) = each %$jar) {
		392	if ($chost =~ /^\./) {
		393	next unless $chost eq substr $uhost, -length $chost;
		394	} elsif ($chost =~ /\./) {
		395	next unless $chost eq $uhost;
		396	} else {
		397	next;
		398	}
		399
		400	while (my ($cpath, $v) = each %$v) {
		401	next unless $cpath eq substr $upath, 0, length $cpath;
		402
		403	while (my ($k, $v) = each %$v) {
		404	next if $uscheme ne "https" && exists $v->{secure};
		405	my $value = $v->{value};
		406	$value =~ s/([\\"])/\\$1/g;
		407	push @cookie, "$k=\"$value\"";
		408	}
		409	}
		410	}
		411
		412	$hdr{cookie} = join "; ", @cookie
		413	if @cookie;
		414	}
		415
		416	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
178		417
179	if ($proxy) {	418	if ($proxy) {
180	($host, $port, $scheme) = @$proxy;	419	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
181	$path = $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" && $rscheme eq "https";
182	} else {	426	} else {
183	($scheme, my $authority, $path, my $query, my $fragment) =	427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
184	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
185
186	$port = $scheme eq "http" ? 80
187	: $scheme eq "https" ? 443
188	: return $cb->(undef, { Status => 599, Reason => "$url: only http and https URLs supported" });
189
190	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
191	or return $cb->(undef, { Status => 599, Reason => "$url: unparsable URL" });
192
193	$host = $1;
194	$port = $2 if defined $2;
195
196	$host =~ s/^\[(.*)\]$/$1/;
197	$path .= "?$query" if length $query;
198
199	$path = "/" unless $path;
200
201	$hdr{host} = $host = lc $host;
202	}	428	}
203		429
204	$scheme = lc $scheme;	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"};
205		433
206	my %state;
207
208	$hdr{"content-length"} = length $arg{body};	434	$hdr{"content-length"} = length $arg{body}
		435	if length $arg{body} \|\| $method ne "GET";
209		436
		437	my %state = (connect_guard => 1);
		438
		439	_get_slot $uhost, sub {
		440	$state{slot_guard} = shift;
		441
		442	return unless $state{connect_guard};
		443
210	$state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub {	444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
211	$state{fh} = shift	445	$state{fh} = shift
		446	or do {
		447	my $err = "$!";
		448	%state = ();
212	or return $cb->(undef, { Status => 599, Reason => "$!" });	449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		450	};
213		451
214	delete $state{connect_guard}; # reduce memory usage, save a tree	452	pop; # free memory, save a tree
215		453
		454	return unless delete $state{connect_guard};
		455
216	# get handle	456	# get handle
217	$state{handle} = new AnyEvent::Handle	457	$state{handle} = new AnyEvent::Handle
218	fh => $state{fh},	458	fh => $state{fh},
219	($scheme eq "https" ? (tls => "connect") : ());	459	timeout => $timeout,
		460	peername => $rhost,
		461	tls_ctx => $arg{tls_ctx};
220		462
221	# limit the number of persistent connections	463	# limit the number of persistent connections
		464	# keepalive not yet supported
222	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
223	++$KA_COUNT{$_[1]};	466	++$KA_COUNT{$_[1]};
224	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	467	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		468	--$KA_COUNT{$_[1]}
		469	};
225	$hdr{connection} = "keep-alive";	470	$hdr{connection} = "keep-alive";
226	delete $hdr{connection}; # keep-alive not yet supported
227	} else {	471	} else {
228	delete $hdr{connection};	472	delete $hdr{connection};
229	}	473	}
230		474
231	# (re-)configure handle	475	# (re-)configure handle
232	$state{handle}->timeout ($timeout);
233	$state{handle}->on_error (sub {	476	$state{handle}->on_error (sub {
234	%state = ();	477	%state = ();
235	$cb->(undef, { Status => 599, Reason => "$!" });	478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
236	});	479	});
237	$state{handle}->on_eof (sub {	480	$state{handle}->on_eof (sub {
238	%state = ();	481	%state = ();
239	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });	482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
240	});
241
242	# send request
243	$state{handle}->push_write (
244	"$method $path HTTP/1.0\015\012"
245	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
246	. "\015\012"
247	. (delete $arg{body})
248	);
249
250	%hdr = (); # reduce memory usage, save a kitten
251
252	# status line
253	$state{handle}->push_read (line => qr/\015?\012/, sub {
254	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
255	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
256
257	my %hdr = ( # response headers
258	HTTPVersion => ",$1",
259	Status => ",$2",
260	Reason => ",$3",
261	);	483	});
262		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
		491	# send request
		492	$state{handle}->push_write (
		493	"$method $rpath HTTP/1.0\015\012"
		494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		495	. "\015\012"
		496	. (delete $arg{body})
		497	);
		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
263	# headers, could be optimized a bit	516	# headers, could be optimized a bit
264	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	517	$state{handle}->unshift_read (line => $qr_nlnl, sub {
265	for ("$_[1]\012") {	518	for ("$_[1]") {
266	# 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.
267	# creates them.	520
		521	# things seen, not parsed:
		522	# p3pP="NON CUR OTPi OUR NOR UNI"
		523
268	$hdr{lc $1} .= ",$2"	524	$hdr{lc $1} .= ",$2"
269	while /\G	525	while /\G
270	([^:\000-\037]+):	526	([^:\000-\037]*):
271	[\011\040]*	527	[\011\040]*
272	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	528	((?: [^\012]+ \| \012[\011\040] )*)
273	\015?\012	529	\012
274	/gxc;	530	/gxc;
275		531
276	/\G$/	532	/\G$/
277	or return $cb->(undef, { Status => 599, Reason => "garbled response headers" });	533	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
		534	}
		535
		536	substr $_, 0, 1, ""
		537	for values %hdr;
		538
		539	# redirect handling
		540	# microsoft and other shitheads don't give a shit for following standards,
		541	# try to support some common forms of broken Location headers.
		542	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		543	$hdr{location} =~ s/^\.\/+//;
		544
		545	my $url = "$rscheme://$uhost:$uport";
		546
		547	unless ($hdr{location} =~ s/^\///) {
		548	$url .= $upath;
		549	$url =~ s/\/[^\/]*$//;
		550	}
		551
		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
		561	$redirect = 1;
		562	} elsif ($hdr{Status} == 303) {
		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;
		568	}
		569	}
		570
		571	my $finish = sub {
		572	$state{handle}->destroy if $state{handle};
		573	%state = ();
		574
		575	# set-cookie processing
		576	if ($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 $_[1] might be an erro
		629	http_request ($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	$finish->("", \%hdr);
		646	} else {
		647	# body handling, four different code paths
		648	# for want_body_handle, on_body (2x), normal (2x)
		649	# we might read too much here, but it does not matter yet (no pers. connections)
		650	if (!$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	}
		697	}
		698	});
278	}	699	});
		700	};
279		701
280	substr $_, 0, 1, ""	702	# now handle proxy-CONNECT method
281	for values %hdr;	703	if ($proxy && $uscheme eq "https") {
		704	# oh dear, we have to wrap it into a connect request
282		705
283	my $finish = sub {	706	# maybe re-use $uauthority with patched port?
284	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {	707	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
285	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	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;
286	} else {	715	} else {
287	$cb->($_[0], $_[1]);	716	%state = ();
		717	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
288	}	718	}
289	};	719	});
290
291	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {
292	%state = ();
293	$finish->(undef, \%hdr);
294	} else {	720	} else {
295	if (exists $hdr{"content-length"}) {	721	&$handle_actual_request;
296	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
297	# could cache persistent connection now
298	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
299	# but we don't, due to misdesigns, this is annoyingly complex
300	};
301
302	%state = ();
303	$finish->($_[1], \%hdr);
304	});
305	} else {
306	# too bad, need to read until we get an error or EOF,
307	# no way to detect winged data.
308	$_[0]->on_error (sub {
309	%state = ();
310	$finish->($_[0]{rbuf}, \%hdr);
311	});
312	$_[0]->on_eof (undef);
313	$_[0]->on_read (sub { });
314	}
315	}
316	});	722	}
317	});	723
318	}, sub {	724	}, $arg{on_prepare} \|\| sub { $timeout };
319	$timeout
320	};	725	};
321		726
322	defined wantarray && AnyEvent::Util::guard { %state = () }	727	defined wantarray && AnyEvent::Util::guard { %state = () }
323	}	728	}
324		729
325	sub http_get($$;@) {	730	sub http_get($@) {
326	unshift @_, "GET";	731	unshift @_, "GET";
327	&http_request	732	&http_request
328	}	733	}
329		734
330	sub http_head($$;@) {	735	sub http_head($@) {
331	unshift @_, "HEAD";	736	unshift @_, "HEAD";
332	&http_request	737	&http_request
333	}	738	}
334		739
335	sub http_post($$$;@) {	740	sub http_post($$@) {
		741	my $url = shift;
336	unshift @_, "POST", "body";	742	unshift @_, "POST", $url, "body";
337	&http_request	743	&http_request
338	}	744	}
339		745
340	=back	746	=back
341		747
…		…
344	=over 4	750	=over 4
345		751
346	=item AnyEvent::HTTP::set_proxy "proxy-url"	752	=item AnyEvent::HTTP::set_proxy "proxy-url"
347		753
348	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
349	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>.
350		759
351	=item $AnyEvent::HTTP::MAX_RECURSE	760	=item $AnyEvent::HTTP::MAX_RECURSE
352		761
353	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>).
354		763
355	=item $AnyEvent::HTTP::USERAGENT	764	=item $AnyEvent::HTTP::USERAGENT
356		765
357	The default value for the C<User-Agent> header (the default is	766	The default value for the C<User-Agent> header (the default is
358	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	767	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
359		768
360	=item $AnyEvent::HTTP::MAX_PERSISTENT	769	=item $AnyEvent::HTTP::MAX_PER_HOST
361		770
362	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.
363		774
364	Not implemented currently.	775	The default value for this is C<4>, and it is highly advisable to not
		776	increase it.
365		777
366	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	778	=item $AnyEvent::HTTP::ACTIVE
367		779
368	The maximum time to cache a persistent connection, in seconds (default: 2).	780	The number of active connections. This is not the number of currently
369		781	running requests, but the number of currently open and non-idle TCP
370	Not implemented currently.	782	connections. This number of can be useful for load-leveling.
371		783
372	=back	784	=back
373		785
374	=cut	786	=cut
375		787
376	sub set_proxy($) {	788	sub set_proxy($) {
		789	if (length $_[0]) {
377	$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	}
378	}	796	}
379		797
380	# initialise proxy from environment	798	# initialise proxy from environment
		799	eval {
381	set_proxy $ENV{http_proxy};	800	set_proxy $ENV{http_proxy};
		801	};
382		802
383	=head1 SEE ALSO	803	=head1 SEE ALSO
384		804
385	L<AnyEvent>.	805	L<AnyEvent>.
386		806
387	=head1 AUTHOR	807	=head1 AUTHOR
388		808
389	Marc Lehmann <schmorp@schmorp.de>	809	Marc Lehmann <schmorp@schmorp.de>
390	http://home.schmorp.de/	810	http://home.schmorp.de/
		811
		812	With many thanks to Дмитрий Шалашов, who provided countless
		813	testcases and bugreports.
391		814
392	=cut	815	=cut
393		816
394	1	817	1
395		818

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.9 by root, Wed Jun 4 13:51:53 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 1.9 by root, Wed Jun 4 13:51:53 2008 UTC vs.
Revision 1.54 by root, Wed Jun 16 18:09:52 2010 UTC