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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.6 by root, Wed Jun 4 12:05:45 2008 UTC vs.
Revision 1.64 by root, Fri Dec 31 02:53:29 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 ();
30	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
31		49
32	use base Exporter::;	50	use base Exporter::;
33		51
34	our $VERSION = '1.0';	52	our $VERSION = '1.46';
35		53
36	our @EXPORT = qw(http_get http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
37		55
38	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
39	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
40	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
41	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
42	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
43		61
44	# changing these is evil	62	# changing these is evil
45	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
46	our $MAX_PER_HOST = 4; # not respected yet :(	64	our $MAX_PER_HOST = 4;
47		65
48	our $PROXY;	66	our $PROXY;
		67	our $ACTIVE = 0;
49		68
50	my %KA_COUNT; # number of open keep-alive connections per host	69	my %KA_COUNT; # number of open keep-alive connections per host
		70	my %CO_SLOT; # number of open connections, and wait queue, per host
51		71
52	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
53		73
54	Executes an HTTP-GET request. See the http_request function for details on	74	Executes an HTTP-GET request. See the http_request function for details on
55	additional parameters.	75	additional parameters and the return value.
56		76
57	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
58		78
59	Executes an HTTP-HEAD request. See the http_request function for details on	79	Executes an HTTP-HEAD request. See the http_request function for details
60	additional parameters.	80	on additional parameters and the return value.
61		81
62	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
63		83
64	Executes an HTTP-POST request with a requets body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
65	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
66		87
67	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
68		89
69	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
70	must be an absolute http or https URL.	91	must be an absolute http or https URL.
71		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
72	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
73	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
74	response headers as second argument.	100	second argument.
75		101
76	All the headers in that has are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
77	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
78	C<Reason> contain the three parts of the HTTP Status-Line of the same	104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
79	name.	105	three parts of the HTTP Status-Line of the same name. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
		110	The pseudo-header C<URL> contains the actual URL (which can differ from
		111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
		123	If the server sends a header multiple times, then their contents will be
		124	joined together with a comma (C<,>), as per the HTTP spec.
80		125
81	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
82	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
83	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
84		130
85	A typical callback might look like this:	131	A typical callback might look like this:
86		132
87	sub {	133	sub {
88	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
104	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
105	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
106		152
107	=item headers => hashref	153	=item headers => hashref
108		154
109	The request headers to use.	155	The request headers to use. Currently, C<http_request> may provide its
		156	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
		157	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		158	suppressed by using C<undef> for these headers in which case they won't be
		159	sent at all).
110		160
111	=item timeout => $seconds	161	=item timeout => $seconds
112		162
113	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
114	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
115		168
116	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
117		170
118	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
119	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
120		173
121	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
122	HTTPS.	175	HTTPS.
123		176
124	=item body => $string	177	=item body => $string
125		178
126	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be-sent as-is (future versions of
127	this module might offer more options).	180	this module might offer more options).
128		181
		182	=item cookie_jar => $hash_ref
		183
		184	Passing this parameter enables (simplified) cookie-processing, loosely
		185	based on the original netscape specification.
		186
		187	The C<$hash_ref> must be an (initially empty) hash reference which will
		188	get updated automatically. It is possible to save the cookie_jar to
		189	persistent storage with something like JSON or Storable, but this is not
		190	recommended, as expiry times are currently being ignored.
		191
		192	Note that this cookie implementation is not of very high quality, nor
		193	meant to be complete. If you want complete cookie management you have to
		194	do that on your own. C<cookie_jar> is meant as a quick fix to get some
		195	cookie-using sites working. Cookies are a privacy disaster, do not use
		196	them unless required to.
		197
		198	=item tls_ctx => $scheme \| $tls_ctx
		199
		200	Specifies the AnyEvent::TLS context to be used for https connections. This
		201	parameter follows the same rules as the C<tls_ctx> parameter to
		202	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		203	C<high> can be specified, which give you a predefined low-security (no
		204	verification, highest compatibility) and high-security (CA and common-name
		205	verification) TLS context.
		206
		207	The default for this option is C<low>, which could be interpreted as "give
		208	me the page, no matter what".
		209
		210	=item on_prepare => $callback->($fh)
		211
		212	In rare cases you need to "tune" the socket before it is used to
		213	connect (for exmaple, to bind it on a given IP address). This parameter
		214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		215	and behaves exactly the same way (e.g. it has to provide a
		216	timeout). See the description for the C<$prepare_cb> argument of
		217	C<AnyEvent::Socket::tcp_connect> for details.
		218
		219	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		220
		221	In even rarer cases you want total control over how AnyEvent::HTTP
		222	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		223	to do this, but you can provide your own C<tcp_connect> function -
		224	obviously, it has to follow the same calling conventions, except that it
		225	may always return a connection guard object.
		226
		227	There are probably lots of weird uses for this function, starting from
		228	tracing the hosts C<http_request> actually tries to connect, to (inexact
		229	but fast) host => IP address caching or even socks protocol support.
		230
		231	=item on_header => $callback->($headers)
		232
		233	When specified, this callback will be called with the header hash as soon
		234	as headers have been successfully received from the remote server (not on
		235	locally-generated errors).
		236
		237	It has to return either true (in which case AnyEvent::HTTP will continue),
		238	or false, in which case AnyEvent::HTTP will cancel the download (and call
		239	the finish callback with an error code of C<598>).
		240
		241	This callback is useful, among other things, to quickly reject unwanted
		242	content, which, if it is supposed to be rare, can be faster than first
		243	doing a C<HEAD> request.
		244
		245	Example: cancel the request unless the content-type is "text/html".
		246
		247	on_header => sub {
		248	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		249	},
		250
		251	=item on_body => $callback->($partial_body, $headers)
		252
		253	When specified, all body data will be passed to this callback instead of
		254	to the completion callback. The completion callback will get the empty
		255	string instead of the body data.
		256
		257	It has to return either true (in which case AnyEvent::HTTP will continue),
		258	or false, in which case AnyEvent::HTTP will cancel the download (and call
		259	the completion callback with an error code of C<598>).
		260
		261	This callback is useful when the data is too large to be held in memory
		262	(so the callback writes it to a file) or when only some information should
		263	be extracted, or when the body should be processed incrementally.
		264
		265	It is usually preferred over doing your own body handling via
		266	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		267	only used to create a connection, C<want_body_handle> is the better
		268	alternative, as it allows you to install your own event handler, reducing
		269	resource usage.
		270
		271	=item want_body_handle => $enable
		272
		273	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		274	changes considerably: after parsing the headers, and instead of
		275	downloading the body (if any), the completion callback will be
		276	called. Instead of the C<$body> argument containing the body data, the
		277	callback will receive the L<AnyEvent::Handle> object associated with the
		278	connection. In error cases, C<undef> will be passed. When there is no body
		279	(e.g. status C<304>), the empty string will be passed.
		280
		281	The handle object might or might not be in TLS mode, might be connected to
		282	a proxy, be a persistent connection etc., and configured in unspecified
		283	ways. The user is responsible for this handle (it will not be used by this
		284	module anymore).
		285
		286	This is useful with some push-type services, where, after the initial
		287	headers, an interactive protocol is used (typical example would be the
		288	push-style twitter API which starts a JSON/XML stream).
		289
		290	If you think you need this, first have a look at C<on_body>, to see if
		291	that doesn't solve your problem in a better way.
		292
129	=back	293	=back
130		294
131	=back	295	Example: make a simple HTTP GET request for http://www.nethype.de/
		296
		297	http_request GET => "http://www.nethype.de/", sub {
		298	my ($body, $hdr) = @_;
		299	print "$body\n";
		300	};
		301
		302	Example: make a HTTP HEAD request on https://www.google.com/, use a
		303	timeout of 30 seconds.
		304
		305	http_request
		306	GET => "https://www.google.com",
		307	timeout => 30,
		308	sub {
		309	my ($body, $hdr) = @_;
		310	use Data::Dumper;
		311	print Dumper $hdr;
		312	}
		313	;
		314
		315	Example: make another simple HTTP GET request, but immediately try to
		316	cancel it.
		317
		318	my $request = http_request GET => "http://www.nethype.de/", sub {
		319	my ($body, $hdr) = @_;
		320	print "$body\n";
		321	};
		322
		323	undef $request;
132		324
133	=cut	325	=cut
134		326
		327	sub _slot_schedule;
		328	sub _slot_schedule($) {
		329	my $host = shift;
		330
		331	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		332	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		333	# somebody wants that slot
		334	++$CO_SLOT{$host}[0];
		335	++$ACTIVE;
		336
		337	$cb->(AnyEvent::Util::guard {
		338	--$ACTIVE;
		339	--$CO_SLOT{$host}[0];
		340	_slot_schedule $host;
		341	});
		342	} else {
		343	# nobody wants the slot, maybe we can forget about it
		344	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		345	last;
		346	}
		347	}
		348	}
		349
		350	# wait for a free slot on host, call callback
		351	sub _get_slot($$) {
		352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		353
		354	_slot_schedule $_[0];
		355	}
		356
		357	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		358
		359	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		360	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		361
135	sub http_request($$$;@) {	362	sub http_request($$@) {
136	my $cb = pop;	363	my $cb = pop;
137	my ($method, $url, %arg) = @_;	364	my ($method, $url, %arg) = @_;
138		365
139	my %hdr;	366	my %hdr;
140		367
		368	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		369	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
		370
141	$method = uc $method;	371	$method = uc $method;
142		372
143	if (my $hdr = delete $arg{headers}) {	373	if (my $hdr = $arg{headers}) {
144	while (my ($k, $v) = each %$hdr) {	374	while (my ($k, $v) = each %$hdr) {
145	$hdr{lc $k} = $v;	375	$hdr{lc $k} = $v;
146	}	376	}
147	}	377	}
148		378
		379	# pseudo headers for all subsequent responses
		380	my @pseudo = (URL => $url);
		381	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		382
		383	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
		384
		385	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
		386	if $recurse < 0;
		387
149	my $proxy = $arg{proxy} \|\| $PROXY;	388	my $proxy = $arg{proxy} \|\| $PROXY;
150	my $timeout = $arg{timeout} \|\| $TIMEOUT;	389	my $timeout = $arg{timeout} \|\| $TIMEOUT;
151	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;
152		390
153	$hdr{"user-agent"} \|\|= $USERAGENT;	391	my ($uscheme, $uauthority, $upath, $query, $fragment) =
		392	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
154		393
155	my ($host, $port, $path, $scheme);	394	$uscheme = lc $uscheme;
		395
		396	my $uport = $uscheme eq "http" ? 80
		397	: $uscheme eq "https" ? 443
		398	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
		399
		400	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
		401	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
		402
		403	my $uhost = $1;
		404	$uport = $2 if defined $2;
		405
		406	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		407	unless exists $hdr{host};
		408
		409	$uhost =~ s/^\[(.*)\]$/$1/;
		410	$upath .= $query if length $query;
		411
		412	$upath =~ s%^/?%/%;
		413
		414	# cookie processing
		415	if (my $jar = $arg{cookie_jar}) {
		416	%$jar = () if $jar->{version} != 1;
		417
		418	my @cookie;
		419
		420	while (my ($chost, $v) = each %$jar) {
		421	if ($chost =~ /^\./) {
		422	next unless $chost eq substr $uhost, -length $chost;
		423	} elsif ($chost =~ /\./) {
		424	next unless $chost eq $uhost;
		425	} else {
		426	next;
		427	}
		428
		429	while (my ($cpath, $v) = each %$v) {
		430	next unless $cpath eq substr $upath, 0, length $cpath;
		431
		432	while (my ($k, $v) = each %$v) {
		433	next if $uscheme ne "https" && exists $v->{secure};
		434	my $value = $v->{value};
		435	$value =~ s/([\\"])/\\$1/g;
		436	push @cookie, "$k=\"$value\"";
		437	}
		438	}
		439	}
		440
		441	$hdr{cookie} = join "; ", @cookie
		442	if @cookie;
		443	}
		444
		445	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
156		446
157	if ($proxy) {	447	if ($proxy) {
158	($host, $port, $scheme) = @$proxy;	448	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
159	$path = $url;	449
		450	$rscheme = "http" unless defined $rscheme;
		451
		452	# don't support https requests over https-proxy transport,
		453	# can't be done with tls as spec'ed, unless you double-encrypt.
		454	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
160	} else {	455	} else {
161	($scheme, my $authority, $path, my $query, my $fragment) =	456	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
162	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
163
164	$port = $scheme eq "http" ? 80
165	: $scheme eq "https" ? 443
166	: croak "$url: only http and https URLs supported";
167
168	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
169	or croak "$authority: unparsable URL";
170
171	$host = $1;
172	$port = $2 if defined $2;
173
174	$host =~ s/^\[(.*)\]$/$1/;
175	$path .= "?$query" if length $query;
176
177	$path = "/" unless $path;
178
179	$hdr{host} = $host = lc $host;
180	}	457	}
181		458
182	$scheme = lc $scheme;	459	# leave out fragment and query string, just a heuristic
		460	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		461	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
183		462
184	my %state;
185
186	$state{body} = delete $arg{body};
187
188	$hdr{"content-length"} = length $state{body};	463	$hdr{"content-length"} = length $arg{body}
		464	if length $arg{body} \|\| $method ne "GET";
189		465
190	$state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub {	466	my %state = (connect_guard => 1);
		467
		468	_get_slot $uhost, sub {
		469	$state{slot_guard} = shift;
		470
		471	return unless $state{connect_guard};
		472
		473	my $connect_cb = sub {
191	$state{fh} = shift	474	$state{fh} = shift
192	or return $cb->(undef, { Status => 599, Reason => "$!" });
193
194	delete $state{connect_guard}; # reduce memory usage, save a tree
195
196	# get handle
197	$state{handle} = new AnyEvent::Handle
198	fh => $state{fh},
199	($scheme eq "https" ? (tls => "connect") : ());
200
201	# limit the number of persistent connections
202	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
203	++$KA_COUNT{$_[1]};
204	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
205	$hdr{connection} = "keep-alive";
206	delete $hdr{connection}; # keep-alive not yet supported
207	} else {
208	delete $hdr{connection};
209	}
210
211	# (re-)configure handle
212	$state{handle}->timeout ($timeout);
213	$state{handle}->on_error (sub {
214	%state = ();
215	$cb->(undef, { Status => 599, Reason => "$!" });
216	});
217	$state{handle}->on_eof (sub {
218	%state = ();
219	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
220	});
221
222	# send request
223	$state{handle}->push_write (
224	"$method $path HTTP/1.0\015\012"
225	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
226	. "\015\012"
227	. (delete $state{body})
228	);
229
230	%hdr = (); # reduce memory usage, save a kitten
231
232	# status line
233	$state{handle}->push_read (line => qr/\015?\012/, sub {
234	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
235	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
236
237	my %hdr = ( # response headers
238	HTTPVersion => ",$1",
239	Status => ",$2",
240	Reason => ",$3",
241	);
242
243	# headers, could be optimized a bit
244	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
245	for ("$_[1]\012") {
246	# we support spaces in field names, as lotus domino
247	# creates them.
248	$hdr{lc $1} .= ",$2"
249	while /\G
250	([^:\000-\037]+):
251	[\011\040]*
252	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
253	\015?\012
254	/gxc;
255
256	/\G$/
257	or return $cb->(undef, { Status => 599, Reason => "garbled response headers" });
258	}	475	or do {
259		476	my $err = "$!";
260	substr $_, 0, 1, ""
261	for values %hdr;
262
263	if ($method eq "HEAD") {
264	%state = ();	477	%state = ();
265	$cb->(undef, \%hdr);	478	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		479	};
		480
		481	pop; # free memory, save a tree
		482
		483	return unless delete $state{connect_guard};
		484
		485	# get handle
		486	$state{handle} = new AnyEvent::Handle
		487	fh => $state{fh},
		488	peername => $rhost,
		489	tls_ctx => $arg{tls_ctx},
		490	# these need to be reconfigured on keepalive handles
		491	timeout => $timeout,
		492	on_error => sub {
		493	%state = ();
		494	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		495	},
		496	on_eof => sub {
		497	%state = ();
		498	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		499	},
		500	;
		501
		502	# limit the number of persistent connections
		503	# keepalive not yet supported
		504	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		505	# ++$KA_COUNT{$_[1]};
		506	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		507	# --$KA_COUNT{$_[1]}
		508	# };
		509	# $hdr{connection} = "keep-alive";
266	} else {	510	# } else {
267	if (exists $hdr{"content-length"}) {	511	delete $hdr{connection};
268	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	512	# }
269	# could cache persistent connection now	513
270	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	514	$state{handle}->starttls ("connect") if $rscheme eq "https";
271	# but we don't, due to misdesigns, this is annoyingly complex	515
		516	# handle actual, non-tunneled, request
		517	my $handle_actual_request = sub {
		518	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		519
		520	# send request
		521	$state{handle}->push_write (
		522	"$method $rpath HTTP/1.0\015\012"
		523	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		524	. "\015\012"
		525	. (delete $arg{body})
		526	);
		527
		528	# return if error occured during push_write()
		529	return unless %state;
		530
		531	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		532
		533	# status line and headers
		534	$state{handle}->push_read (line => $qr_nlnl, sub {
		535	my $keepalive = pop;
		536
		537	for ("$_[1]") {
		538	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		539
		540	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
		541	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		542
		543	push @pseudo,
		544	HTTPVersion => $1,
		545	Status => $2,
		546	Reason => $3,
		547	;
		548
		549	# things seen, not parsed:
		550	# p3pP="NON CUR OTPi OUR NOR UNI"
		551
		552	$hdr{lc $1} .= ",$2"
		553	while /\G
		554	([^:\000-\037]*):
		555	[\011\040]*
		556	((?: [^\012]+ \| \012[\011\040] )*)
		557	\012
		558	/gxc;
		559
		560	/\G$/
		561	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		562	}
		563
		564	# remove the "," prefix we added to all headers above
		565	substr $_, 0, 1, ""
		566	for values %hdr;
		567
		568	# patch in all pseudo headers
		569	%hdr = (%hdr, @pseudo);
		570
		571	# redirect handling
		572	# microsoft and other shitheads don't give a shit for following standards,
		573	# try to support some common forms of broken Location headers.
		574	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		575	$hdr{location} =~ s/^\.\/+//;
		576
		577	my $url = "$rscheme://$uhost:$uport";
		578
		579	unless ($hdr{location} =~ s/^\///) {
		580	$url .= $upath;
		581	$url =~ s/\/[^\/]*$//;
		582	}
		583
		584	$hdr{location} = "$url/$hdr{location}";
		585	}
		586
		587	my $redirect;
		588
		589	if ($recurse) {
		590	my $status = $hdr{Status};
		591
		592	# industry standard is to redirect POST as GET for
		593	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		594	# also, the UA should ask the user for 301 and 307 and POST,
		595	# industry standard seems to be to simply follow.
		596	# we go with the industry standard.
		597	if ($status == 301 or $status == 302 or $status == 303) {
		598	# HTTP/1.1 is unclear on how to mutate the method
		599	$method = "GET" unless $method eq "HEAD";
		600	$redirect = 1;
		601	} elsif ($status == 307) {
		602	$redirect = 1;
		603	}
		604	}
		605
		606	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		607	$state{handle}->destroy if $state{handle};
		608	%state = ();
		609
		610	if (defined $_[1]) {
		611	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		612	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		613	}
		614
		615	# set-cookie processing
		616	if ($arg{cookie_jar}) {
		617	for ($hdr{"set-cookie"}) {
		618	# parse NAME=VALUE
		619	my @kv;
		620
		621	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		622	my $name = $1;
		623	my $value = $3;
		624
		625	unless ($value) {
		626	$value = $2;
		627	$value =~ s/\\(.)/$1/gs;
		628	}
		629
		630	push @kv, $name => $value;
		631
		632	last unless /\G\s*;/gc;
		633	}
		634
		635	last unless @kv;
		636
		637	my $name = shift @kv;
		638	my %kv = (value => shift @kv, @kv);
		639
		640	my $cdom;
		641	my $cpath = (delete $kv{path}) \|\| "/";
		642
		643	if (exists $kv{domain}) {
		644	$cdom = delete $kv{domain};
		645
		646	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		647
		648	next if $cdom =~ /\.$/;
		649
		650	# this is not rfc-like and not netscape-like. go figure.
		651	my $ndots = $cdom =~ y/.//;
		652	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		653	} else {
		654	$cdom = $uhost;
		655	}
		656
		657	# store it
		658	$arg{cookie_jar}{version} = 1;
		659	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		660
		661	redo if /\G\s*,/gc;
272	};	662	}
		663	}
273		664
274	%state = ();	665	if ($redirect && exists $hdr{location}) {
		666	# we ignore any errors, as it is very common to receive
		667	# Content-Length != 0 but no actual body
		668	# we also access %hdr, as $_[1] might be an erro
		669	http_request (
		670	$method => $hdr{location},
		671	%arg,
		672	recurse => $recurse - 1,
		673	Redirect => [$_[0], \%hdr],
		674	$cb);
		675	} else {
275	$cb->($_[1], \%hdr);	676	$cb->($_[0], \%hdr);
276	});	677	}
		678	};
		679
		680	my $len = $hdr{"content-length"};
		681
		682	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		683	$finish->(undef, 598 => "Request cancelled by on_header");
		684	} elsif (
		685	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		686	or $method eq "HEAD"
		687	or (defined $len && !$len)
		688	) {
		689	# no body
		690	$finish->("", undef, undef, 1);
277	} else {	691	} else {
278	# too bad, need to read until we get an error or EOF,	692	# body handling, four different code paths
279	# no way to detect winged data.	693	# for want_body_handle, on_body (2x), normal (2x)
		694	# we might read too much here, but it does not matter yet (no pipelining)
		695	if (!$redirect && $arg{want_body_handle}) {
		696	$_[0]->on_eof (undef);
		697	$_[0]->on_error (undef);
		698	$_[0]->on_read (undef);
		699
		700	$finish->(delete $state{handle});
		701
		702	} elsif ($arg{on_body}) {
		703	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		704	if ($len) {
		705	$_[0]->on_read (sub {
		706	$len -= length $_[0]{rbuf};
		707
		708	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		709	or $finish->(undef, 598 => "Request cancelled by on_body");
		710
		711	$len > 0
		712	or $finish->("", undef, undef, 1);
		713	});
		714	} else {
280	$_[0]->on_error (sub {	715	$_[0]->on_eof (sub {
		716	$finish->("");
281	%state = ();	717	});
		718	$_[0]->on_read (sub {
282	$cb->($_[0]{rbuf}, \%hdr);	719	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		720	or $finish->(undef, 598 => "Request cancelled by on_body");
		721	});
283	});	722	}
		723	} else {
284	$_[0]->on_eof (undef);	724	$_[0]->on_eof (undef);
		725
		726	if ($len) {
		727	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		728	$_[0]->on_read (sub {
		729	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		730	if $len <= length $_[0]{rbuf};
		731	});
		732	} else {
		733	$_[0]->on_error (sub {
		734	($! == Errno::EPIPE \|\| !$!)
		735	? $finish->(delete $_[0]{rbuf})
		736	: $finish->(undef, 599 => $_[2]);
		737	});
285	$_[0]->on_read (sub { });	738	$_[0]->on_read (sub { });
		739	}
		740	}
286	}	741	}
287	}	742	});
288	});	743	};
		744
		745	# now handle proxy-CONNECT method
		746	if ($proxy && $uscheme eq "https") {
		747	# oh dear, we have to wrap it into a connect request
		748
		749	# maybe re-use $uauthority with patched port?
		750	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		751	$state{handle}->push_read (line => $qr_nlnl, sub {
		752	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		753	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		754
		755	if ($2 == 200) {
		756	$rpath = $upath;
		757	&$handle_actual_request;
		758	} else {
		759	%state = ();
		760	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
		761	}
		762	});
		763	} else {
		764	&$handle_actual_request;
		765	}
289	});	766	};
290	}, sub {	767
291	$timeout	768	my $tcp_connect = $arg{tcp_connect}
		769	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		770
		771	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		772
292	};	773	};
293		774
294	defined wantarray && AnyEvent::Util::guard { %state = () }	775	defined wantarray && AnyEvent::Util::guard { %state = () }
295	}	776	}
296		777
297	sub http_get($$;@) {	778	sub http_get($@) {
298	unshift @_, "GET";	779	unshift @_, "GET";
299	&http_request	780	&http_request
300	}	781	}
301		782
302	sub http_head($$;@) {	783	sub http_head($@) {
303	unshift @_, "HEAD";	784	unshift @_, "HEAD";
304	&http_request	785	&http_request
305	}	786	}
306		787
307	sub http_post($$$;@) {	788	sub http_post($$@) {
		789	my $url = shift;
308	unshift @_, "POST", "body";	790	unshift @_, "POST", $url, "body";
309	&http_request	791	&http_request
310	}	792	}
311		793
		794	=back
		795
		796	=head2 DNS CACHING
		797
		798	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		799	the actual connection, which in turn uses AnyEvent::DNS to resolve
		800	hostnames. The latter is a simple stub resolver and does no caching
		801	on its own. If you want DNS caching, you currently have to provide
		802	your own default resolver (by storing a suitable resolver object in
		803	C<$AnyEvent::DNS::RESOLVER>).
		804
312	=head2 GLOBAL FUNCTIONS AND VARIABLES	805	=head2 GLOBAL FUNCTIONS AND VARIABLES
313		806
314	=over 4	807	=over 4
315		808
316	=item AnyEvent::HTTP::set_proxy "proxy-url"	809	=item AnyEvent::HTTP::set_proxy "proxy-url"
317		810
318	Sets the default proxy server to use. The proxy-url must begin with a	811	Sets the default proxy server to use. The proxy-url must begin with a
319	string of the form C<http://host:port> (optionally C<https:...>).	812	string of the form C<http://host:port> (optionally C<https:...>), croaks
		813	otherwise.
		814
		815	To clear an already-set proxy, use C<undef>.
		816
		817	=item $date = AnyEvent::HTTP::format_date $timestamp
		818
		819	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		820	Date (RFC 2616).
		821
		822	=item $timestamp = AnyEvent::HTTP::parse_date $date
		823
		824	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		825	timestamp, or C<undef> if the date cannot be parsed.
320		826
321	=item $AnyEvent::HTTP::MAX_RECURSE	827	=item $AnyEvent::HTTP::MAX_RECURSE
322		828
323	The default value for the C<recurse> request parameter (default: C<10>).	829	The default value for the C<recurse> request parameter (default: C<10>).
324		830
325	=item $AnyEvent::HTTP::USERAGENT	831	=item $AnyEvent::HTTP::USERAGENT
326		832
327	The default value for the C<User-Agent> header (the default is	833	The default value for the C<User-Agent> header (the default is
328	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	834	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
329		835
330	=item $AnyEvent::HTTP::MAX_PERSISTENT	836	=item $AnyEvent::HTTP::MAX_PER_HOST
331		837
332	The maximum number of persistent connections to keep open (default: 8).	838	The maximum number of concurrent connections to the same host (identified
		839	by the hostname). If the limit is exceeded, then the additional requests
		840	are queued until previous connections are closed.
333		841
334	Not implemented currently.	842	The default value for this is C<4>, and it is highly advisable to not
		843	increase it.
335		844
336	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	845	=item $AnyEvent::HTTP::ACTIVE
337		846
338	The maximum time to cache a persistent connection, in seconds (default: 2).	847	The number of active connections. This is not the number of currently
339		848	running requests, but the number of currently open and non-idle TCP
340	Not implemented currently.	849	connections. This number of can be useful for load-leveling.
341		850
342	=back	851	=back
343		852
344	=cut	853	=cut
345		854
		855	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		856	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		857
		858	sub format_date($) {
		859	my ($time) = @_;
		860
		861	# RFC 822/1123 format
		862	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		863
		864	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		865	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		866	$H, $M, $S;
		867	}
		868
		869	sub parse_date($) {
		870	my ($date) = @_;
		871
		872	my ($d, $m, $y, $H, $M, $S);
		873
		874	if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9]) ([A-Z][a-z][a-z]) ([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		875	# RFC 822/1123, required by RFC 2616
		876	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		877
		878	} elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		879	# RFC 850
		880	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		881
		882	} elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) {
		883	# ISO C's asctime
		884	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		885	}
		886	# other formats fail in the loop below
		887
		888	for (0..11) {
		889	if ($m eq $month[$_]) {
		890	require Time::Local;
		891	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		892	}
		893	}
		894
		895	undef
		896	}
		897
346	sub set_proxy($) {	898	sub set_proxy($) {
		899	if (length $_[0]) {
347	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	900	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		901	or Carp::croak "$_[0]: invalid proxy URL";
		902	$PROXY = [$2, $3 \|\| 3128, $1]
		903	} else {
		904	undef $PROXY;
		905	}
348	}	906	}
349		907
350	# initialise proxy from environment	908	# initialise proxy from environment
		909	eval {
351	set_proxy $ENV{http_proxy};	910	set_proxy $ENV{http_proxy};
		911	};
		912
		913	=head2 SOCKS PROXIES
		914
		915	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		916	compile your perl to support socks, or use an external program such as
		917	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		918	transparently.
		919
		920	Alternatively, for AnyEvent::HTTP only, you can use your own
		921	C<tcp_connect> function that does the proxy handshake - here is an example
		922	that works with socks4a proxies:
		923
		924	use Errno;
		925	use AnyEvent::Util;
		926	use AnyEvent::Socket;
		927	use AnyEvent::Handle;
		928
		929	# host, port and username of/for your socks4a proxy
		930	my $socks_host = "10.0.0.23";
		931	my $socks_port = 9050;
		932	my $socks_user = "";
		933
		934	sub socks4a_connect {
		935	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		936
		937	my $hdl = new AnyEvent::Handle
		938	connect => [$socks_host, $socks_port],
		939	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		940	on_error => sub { $connect_cb->() },
		941	;
		942
		943	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		944
		945	$hdl->push_read (chunk => 8, sub {
		946	my ($hdl, $chunk) = @_;
		947	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		948
		949	if ($status == 0x5a) {
		950	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		951	} else {
		952	$! = Errno::ENXIO; $connect_cb->();
		953	}
		954	});
		955
		956	$hdl
		957	}
		958
		959	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		960	possibly after switching off other proxy types:
		961
		962	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		963
		964	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		965	my ($data, $headers) = @_;
		966	...
		967	};
352		968
353	=head1 SEE ALSO	969	=head1 SEE ALSO
354		970
355	L<AnyEvent>.	971	L<AnyEvent>.
356		972
357	=head1 AUTHOR	973	=head1 AUTHOR
358		974
359	Marc Lehmann <schmorp@schmorp.de>	975	Marc Lehmann <schmorp@schmorp.de>
360	http://home.schmorp.de/	976	http://home.schmorp.de/
		977
		978	With many thanks to Дмитрий Шалашов, who provided countless
		979	testcases and bugreports.
361		980
362	=cut	981	=cut
363		982
364	1	983	1
365		984

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.6 by root, Wed Jun 4 12:05:45 2008 UTC vs. Revision 1.64 by root, Fri Dec 31 02:53:29 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.6 by root, Wed Jun 4 12:05:45 2008 UTC vs.
Revision 1.64 by root, Fri Dec 31 02:53:29 2010 UTC