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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.1 by root, Tue Jun 3 16:37:13 2008 UTC vs.
Revision 1.60 by root, Thu Dec 30 02:56:28 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 $MAX_REDIRECTS = 10;
39	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)";
		57	our $MAX_RECURSE = 10;
40	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
41	our $PERSISTENT_TIMEOUT = 15;	59	our $PERSISTENT_TIMEOUT = 2;
42	our $TIMEOUT = 60;	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;
		65
		66	our $PROXY;
		67	our $ACTIVE = 0;
47		68
48	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
49		71
50	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
51		73
52	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
53	additional parameters.	75	additional parameters and the return value.
		76
		77	=item http_head $url, key => value..., $cb->($data, $headers)
		78
		79	Executes an HTTP-HEAD request. See the http_request function for details
		80	on additional parameters and the return value.
		81
		82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
		83
		84	Executes an HTTP-POST request with a request body of C<$body>. See the
		85	http_request function for details on additional parameters and the return
		86	value.
54		87
55	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
56		89
57	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
58	must be an absolute http or https URL.	91	must be an absolute http or https URL.
59		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
		98	The callback will be called with the response body data as first argument
		99	(or C<undef> if an error occured), and a hash-ref with response headers as
		100	second argument.
		101
		102	All the headers in that hash are lowercased. In addition to the response
		103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
		105	three parts of the HTTP Status-Line of the same name.
		106
		107	The pseudo-header C<URL> contains the actual URL (which can differ from
		108	the requested URL when following redirects - for example, you might get
		109	an error that your URL scheme is not supported even though your URL is a
		110	valid http URL because it redirected to an ftp URL, in which case you can
		111	look at the URL pseudo header).
		112
		113	The pseudo-header C<Redirect> only exists when the request was a result
		114	of an internal redirect. In that case it is an array reference with
		115	the C<($data, $headers)> from the redirect response. Note that this
		116	response could in turn be the result of a redirect itself, and C<<
		117	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		118	response, and so on.
		119
		120	If the server sends a header multiple times, then their contents will be
		121	joined together with a comma (C<,>), as per the HTTP spec.
		122
		123	If an internal error occurs, such as not being able to resolve a hostname,
		124	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
		125	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		126	message.
		127
		128	A typical callback might look like this:
		129
		130	sub {
		131	my ($body, $hdr) = @_;
		132
		133	if ($hdr->{Status} =~ /^2/) {
		134	... everything should be ok
		135	} else {
		136	print "error, $hdr->{Status} $hdr->{Reason}\n";
		137	}
		138	}
		139
60	Additional parameters are key-value pairs, and are fully optional. They	140	Additional parameters are key-value pairs, and are fully optional. They
61	include:	141	include:
62		142
63	=over 4	143	=over 4
64		144
65	=item recurse => $boolean (default: true)	145	=item recurse => $count (default: $MAX_RECURSE)
66		146
67	Whether to recurse requests or not, e.g. on redirects, authentication	147	Whether to recurse requests or not, e.g. on redirects, authentication
68	retries and so on.	148	retries and so on, and how often to do so.
69		149
70	=item headers => hashref	150	=item headers => hashref
71		151
72	The request headers to use.	152	The request headers to use. Currently, C<http_request> may provide its
		153	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
		154	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		155	suppressed by using C<undef> for these headers in which case they won't be
		156	sent at all).
73		157
74	=item timeout => $seconds	158	=item timeout => $seconds
75		159
76	The time-out to use for various stages - each connect attempt will reset	160	The time-out to use for various stages - each connect attempt will reset
77	the timeout, as will read or write activity.	161	the timeout, as will read or write activity, i.e. this is not an overall
		162	timeout.
		163
		164	Default timeout is 5 minutes.
		165
		166	=item proxy => [$host, $port[, $scheme]] or undef
		167
		168	Use the given http proxy for all requests. If not specified, then the
		169	default proxy (as specified by C<$ENV{http_proxy}>) is used.
		170
		171	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
		172	HTTPS.
		173
		174	=item body => $string
		175
		176	The request body, usually empty. Will be-sent as-is (future versions of
		177	this module might offer more options).
		178
		179	=item cookie_jar => $hash_ref
		180
		181	Passing this parameter enables (simplified) cookie-processing, loosely
		182	based on the original netscape specification.
		183
		184	The C<$hash_ref> must be an (initially empty) hash reference which will
		185	get updated automatically. It is possible to save the cookie_jar to
		186	persistent storage with something like JSON or Storable, but this is not
		187	recommended, as expiry times are currently being ignored.
		188
		189	Note that this cookie implementation is not of very high quality, nor
		190	meant to be complete. If you want complete cookie management you have to
		191	do that on your own. C<cookie_jar> is meant as a quick fix to get some
		192	cookie-using sites working. Cookies are a privacy disaster, do not use
		193	them unless required to.
		194
		195	=item tls_ctx => $scheme \| $tls_ctx
		196
		197	Specifies the AnyEvent::TLS context to be used for https connections. This
		198	parameter follows the same rules as the C<tls_ctx> parameter to
		199	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		200	C<high> can be specified, which give you a predefined low-security (no
		201	verification, highest compatibility) and high-security (CA and common-name
		202	verification) TLS context.
		203
		204	The default for this option is C<low>, which could be interpreted as "give
		205	me the page, no matter what".
		206
		207	=item on_prepare => $callback->($fh)
		208
		209	In rare cases you need to "tune" the socket before it is used to
		210	connect (for exmaple, to bind it on a given IP address). This parameter
		211	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		212	and behaves exactly the same way (e.g. it has to provide a
		213	timeout). See the description for the C<$prepare_cb> argument of
		214	C<AnyEvent::Socket::tcp_connect> for details.
		215
		216	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		217
		218	In even rarer cases you want total control over how AnyEvent::HTTP
		219	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		220	to do this, but you can provide your own C<tcp_connect> function -
		221	obviously, it has to follow the same calling conventions, except that it
		222	may always return a connection guard object.
		223
		224	There are probably lots of weird uses for this function, starting from
		225	tracing the hosts C<http_request> actually tries to connect, to (inexact
		226	but fast) host => IP address caching or even socks protocol support.
		227
		228	=item on_header => $callback->($headers)
		229
		230	When specified, this callback will be called with the header hash as soon
		231	as headers have been successfully received from the remote server (not on
		232	locally-generated errors).
		233
		234	It has to return either true (in which case AnyEvent::HTTP will continue),
		235	or false, in which case AnyEvent::HTTP will cancel the download (and call
		236	the finish callback with an error code of C<598>).
		237
		238	This callback is useful, among other things, to quickly reject unwanted
		239	content, which, if it is supposed to be rare, can be faster than first
		240	doing a C<HEAD> request.
		241
		242	Example: cancel the request unless the content-type is "text/html".
		243
		244	on_header => sub {
		245	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		246	},
		247
		248	=item on_body => $callback->($partial_body, $headers)
		249
		250	When specified, all body data will be passed to this callback instead of
		251	to the completion callback. The completion callback will get the empty
		252	string instead of the body data.
		253
		254	It has to return either true (in which case AnyEvent::HTTP will continue),
		255	or false, in which case AnyEvent::HTTP will cancel the download (and call
		256	the completion callback with an error code of C<598>).
		257
		258	This callback is useful when the data is too large to be held in memory
		259	(so the callback writes it to a file) or when only some information should
		260	be extracted, or when the body should be processed incrementally.
		261
		262	It is usually preferred over doing your own body handling via
		263	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		264	only used to create a connection, C<want_body_handle> is the better
		265	alternative, as it allows you to install your own event handler, reducing
		266	resource usage.
		267
		268	=item want_body_handle => $enable
		269
		270	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		271	changes considerably: after parsing the headers, and instead of
		272	downloading the body (if any), the completion callback will be
		273	called. Instead of the C<$body> argument containing the body data, the
		274	callback will receive the L<AnyEvent::Handle> object associated with the
		275	connection. In error cases, C<undef> will be passed. When there is no body
		276	(e.g. status C<304>), the empty string will be passed.
		277
		278	The handle object might or might not be in TLS mode, might be connected to
		279	a proxy, be a persistent connection etc., and configured in unspecified
		280	ways. The user is responsible for this handle (it will not be used by this
		281	module anymore).
		282
		283	This is useful with some push-type services, where, after the initial
		284	headers, an interactive protocol is used (typical example would be the
		285	push-style twitter API which starts a JSON/XML stream).
		286
		287	If you think you need this, first have a look at C<on_body>, to see if
		288	that doesn't solve your problem in a better way.
78		289
79	=back	290	=back
80		291
81	=back	292	Example: make a simple HTTP GET request for http://www.nethype.de/
		293
		294	http_request GET => "http://www.nethype.de/", sub {
		295	my ($body, $hdr) = @_;
		296	print "$body\n";
		297	};
		298
		299	Example: make a HTTP HEAD request on https://www.google.com/, use a
		300	timeout of 30 seconds.
		301
		302	http_request
		303	GET => "https://www.google.com",
		304	timeout => 30,
		305	sub {
		306	my ($body, $hdr) = @_;
		307	use Data::Dumper;
		308	print Dumper $hdr;
		309	}
		310	;
		311
		312	Example: make another simple HTTP GET request, but immediately try to
		313	cancel it.
		314
		315	my $request = http_request GET => "http://www.nethype.de/", sub {
		316	my ($body, $hdr) = @_;
		317	print "$body\n";
		318	};
		319
		320	undef $request;
82		321
83	=cut	322	=cut
84		323
		324	sub _slot_schedule;
		325	sub _slot_schedule($) {
		326	my $host = shift;
		327
		328	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		329	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		330	# somebody wants that slot
		331	++$CO_SLOT{$host}[0];
		332	++$ACTIVE;
		333
		334	$cb->(AnyEvent::Util::guard {
		335	--$ACTIVE;
		336	--$CO_SLOT{$host}[0];
		337	_slot_schedule $host;
		338	});
		339	} else {
		340	# nobody wants the slot, maybe we can forget about it
		341	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		342	last;
		343	}
		344	}
		345	}
		346
		347	# wait for a free slot on host, call callback
		348	sub _get_slot($$) {
		349	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		350
		351	_slot_schedule $_[0];
		352	}
		353
		354	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		355
		356	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		357	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		358
85	sub http_request($$$;@) {	359	sub http_request($$@) {
86	my $cb = pop;	360	my $cb = pop;
87	my ($method, $url, %arg) = @_;	361	my ($method, $url, %arg) = @_;
88		362
89	my %hdr;	363	my %hdr;
90		364
		365	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		366	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
		367
		368	$method = uc $method;
		369
91	if (my $hdr = delete $arg{headers}) {	370	if (my $hdr = $arg{headers}) {
92	while (my ($k, $v) = each %$hdr) {	371	while (my ($k, $v) = each %$hdr) {
93	$hdr{lc $k} = $v;	372	$hdr{lc $k} = $v;
94	}	373	}
95	}	374	}
96		375
		376	# pseudo headers for all subsequent responses
		377	my @pseudo = (URL => $url);
		378	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		379
		380	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
		381
		382	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
		383	if $recurse < 0;
		384
		385	my $proxy = $arg{proxy} \|\| $PROXY;
97	my $timeout = $arg{timeout} \|\| $TIMEOUT;	386	my $timeout = $arg{timeout} \|\| $TIMEOUT;
98		387
99	$hdr{"user-agent"} \|\|= $USERAGENT;
100
101	my ($scheme, $authority, $path, $query, $fragment) =	388	my ($uscheme, $uauthority, $upath, $query, $fragment) =
102	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	389	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
103		390
104	$scheme = lc $scheme;	391	$uscheme = lc $uscheme;
		392
105	my $port = $scheme eq "http" ? 80	393	my $uport = $uscheme eq "http" ? 80
106	: $scheme eq "https" ? 443	394	: $uscheme eq "https" ? 443
107	: croak "$url: only http and https URLs supported";	395	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
108		396
109	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	397	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
110	or croak "$authority: unparsable URL";	398	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
111		399
112	my $host = $1;	400	my $uhost = $1;
113	$port = $2 if defined $2;	401	$uport = $2 if defined $2;
114		402
		403	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		404	unless exists $hdr{host};
		405
115	$host =~ s/^\[(.*)\]$/$1/;	406	$uhost =~ s/^\[(.*)\]$/$1/;
116	$path .= "?$query" if length $query;	407	$upath .= $query if length $query;
117		408
118	$hdr{host} = $host = lc $host;	409	$upath =~ s%^/?%/%;
119		410
120	my %state;	411	# cookie processing
121		412	if (my $jar = $arg{cookie_jar}) {
122	my $body = "";	413	%$jar = () if $jar->{version} != 1;
123	$state{body} = $body;	414
124		415	my @cookie;
125	$hdr{"content-length"} = length $body;	416
126		417	while (my ($chost, $v) = each %$jar) {
127	$state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub {	418	if ($chost =~ /^\./) {
128	$state{fh} = shift	419	next unless $chost eq substr $uhost, -length $chost;
129	or return $cb->(undef, { Status => 599, Reason => "$!" });	420	} elsif ($chost =~ /\./) {
130		421	next unless $chost eq $uhost;
131	delete $state{connect_guard}; # reduce memory usage, save a tree
132
133	# get handle
134	$state{handle} = new AnyEvent::Handle
135	fh => $state{fh},
136	($scheme eq "https" ? (tls => "connect") : ());
137
138	# limit the number of persistent connections
139	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
140	++$KA_COUNT{$_[1]};
141	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
142	$hdr{connection} = "keep-alive";
143	} else {	422	} else {
144	delete $hdr{connection};	423	next;
		424	}
		425
		426	while (my ($cpath, $v) = each %$v) {
		427	next unless $cpath eq substr $upath, 0, length $cpath;
		428
		429	while (my ($k, $v) = each %$v) {
		430	next if $uscheme ne "https" && exists $v->{secure};
		431	my $value = $v->{value};
		432	$value =~ s/([\\"])/\\$1/g;
		433	push @cookie, "$k=\"$value\"";
		434	}
		435	}
145	}	436	}
		437
		438	$hdr{cookie} = join "; ", @cookie
		439	if @cookie;
		440	}
146		441
147	# (re-)configure handle	442	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
148	$state{handle}->timeout ($timeout);	443
149	$state{handle}->on_error (sub {	444	if ($proxy) {
		445	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		446
		447	$rscheme = "http" unless defined $rscheme;
		448
		449	# don't support https requests over https-proxy transport,
		450	# can't be done with tls as spec'ed, unless you double-encrypt.
		451	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		452	} else {
		453	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
		454	}
		455
		456	# leave out fragment and query string, just a heuristic
		457	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		458	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		459
		460	$hdr{"content-length"} = length $arg{body}
		461	if length $arg{body} \|\| $method ne "GET";
		462
		463	my %state = (connect_guard => 1);
		464
		465	_get_slot $uhost, sub {
		466	$state{slot_guard} = shift;
		467
		468	return unless $state{connect_guard};
		469
		470	my $tcp_connect = $arg{tcp_connect}
		471	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		472
		473	$state{connect_guard} = $tcp_connect->(
		474	$rhost,
		475	$rport,
		476	sub {
		477	$state{fh} = shift
		478	or do {
		479	my $err = "$!";
150	%state = ();	480	%state = ();
151	$cb->(undef, { Status => 599, Reason => "$!" });	481	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
152	});	482	};
153	$state{handle}->on_eof (sub {	483
		484	pop; # free memory, save a tree
		485
		486	return unless delete $state{connect_guard};
		487
		488	# get handle
		489	$state{handle} = new AnyEvent::Handle
		490	fh => $state{fh},
		491	peername => $rhost,
		492	tls_ctx => $arg{tls_ctx},
		493	# these need to be reconfigured on keepalive handles
		494	timeout => $timeout,
		495	on_error => sub {
154	%state = ();	496	%state = ();
		497	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		498	},
		499	on_eof => sub {
		500	%state = ();
155	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });	501	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
156	});	502	},
157
158	# send request
159	$state{handle}->push_write (
160	"\U$method\E $path HTTP/1.0\015\012"
161	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
162	. "\015\012"
163	. (delete $state{body})
164	);
165
166	%hdr = (); # reduce memory usage, save a kitten
167
168	# status line
169	$state{handle}->push_read (line => qr/\015?\012/, sub {
170	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
171	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
172
173	my %hdr = ( # response headers
174	HTTPVersion => ",$1",
175	Status => ",$2",
176	Reason => ",$3",
177	);	503	;
178		504
179	# headers, could be optimized a bit	505	# limit the number of persistent connections
180	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	506	# keepalive not yet supported
181	for ("$_[1]\012") {	507	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
182	$hdr{lc $1} .= ",$2"	508	# ++$KA_COUNT{$_[1]};
183	while /\G	509	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
184	([^:\000-\040]+):	510	# --$KA_COUNT{$_[1]}
185	[\011\040]*
186	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
187	\015?\012
188	/gxc;
189
190	/\G$/
191	or return $cb->(undef, { Status => 599, Reason => "garbled response headers" });
192	}	511	# };
		512	# $hdr{connection} = "keep-alive";
		513	# } else {
		514	delete $hdr{connection};
		515	# }
193		516
		517	$state{handle}->starttls ("connect") if $rscheme eq "https";
		518
		519	# handle actual, non-tunneled, request
		520	my $handle_actual_request = sub {
		521	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		522
		523	# send request
		524	$state{handle}->push_write (
		525	"$method $rpath HTTP/1.0\015\012"
		526	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		527	. "\015\012"
		528	. (delete $arg{body})
		529	);
		530
		531	# return if error occured during push_write()
		532	return unless %state;
		533
		534	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		535
		536	# status line and headers
		537	$state{handle}->push_read (line => $qr_nlnl, sub {
		538	for ("$_[1]") {
		539	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		540
		541	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
		542	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
		543
		544	push @pseudo,
		545	HTTPVersion => $1,
		546	Status => $2,
		547	Reason => $3,
		548	;
		549
		550	# things seen, not parsed:
		551	# p3pP="NON CUR OTPi OUR NOR UNI"
		552
		553	$hdr{lc $1} .= ",$2"
		554	while /\G
		555	([^:\000-\037]*):
		556	[\011\040]*
		557	((?: [^\012]+ \| \012[\011\040] )*)
		558	\012
		559	/gxc;
		560
		561	/\G$/
		562	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
		563	}
		564
		565	# remove the "," prefix we added to all headers above
194	substr $_, 0, 1, ""	566	substr $_, 0, 1, ""
195	for values %hdr;	567	for values %hdr;
196		568
197	if (exists $hdr{"content-length"}) {	569	# patch in all pseudo headers
198	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	570	%hdr = (%hdr, @pseudo);
199	# could cache persistent connection now	571
200	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	572	# redirect handling
		573	# microsoft and other shitheads don't give a shit for following standards,
		574	# try to support some common forms of broken Location headers.
		575	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		576	$hdr{location} =~ s/^\.\/+//;
		577
		578	my $url = "$rscheme://$uhost:$uport";
		579
		580	unless ($hdr{location} =~ s/^\///) {
		581	$url .= $upath;
		582	$url =~ s/\/[^\/]*$//;
		583	}
		584
		585	$hdr{location} = "$url/$hdr{location}";
		586	}
		587
		588	my $redirect;
		589
		590	if ($recurse) {
		591	my $status = $hdr{Status};
		592
		593	# industry standard is to redirect POST as GET for
		594	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		595	# also, the UA should ask the user for 301 and 307 and POST,
		596	# industry standard seems to be to simply follow.
		597	# we go with the industry standard.
		598	if ($status == 301 or $status == 302 or $status == 303) {
		599	# HTTP/1.1 is unclear on how to mutate the method
		600	$method = "GET" unless $method eq "HEAD";
		601	$redirect = 1;
		602	} elsif ($status == 307) {
		603	$redirect = 1;
		604	}
		605	}
		606
		607	my $finish = sub {
		608	$state{handle}->destroy if $state{handle};
		609	%state = ();
		610
		611	# set-cookie processing
		612	if ($arg{cookie_jar}) {
		613	for ($_[1]{"set-cookie"}) {
		614	# parse NAME=VALUE
		615	my @kv;
		616
		617	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		618	my $name = $1;
		619	my $value = $3;
		620
		621	unless ($value) {
		622	$value = $2;
		623	$value =~ s/\\(.)/$1/gs;
		624	}
		625
		626	push @kv, $name => $value;
		627
		628	last unless /\G\s*;/gc;
		629	}
		630
		631	last unless @kv;
		632
		633	my $name = shift @kv;
		634	my %kv = (value => shift @kv, @kv);
		635
		636	my $cdom;
		637	my $cpath = (delete $kv{path}) \|\| "/";
		638
		639	if (exists $kv{domain}) {
		640	$cdom = delete $kv{domain};
		641
		642	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		643
		644	next if $cdom =~ /\.$/;
		645
		646	# this is not rfc-like and not netscape-like. go figure.
		647	my $ndots = $cdom =~ y/.//;
		648	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		649	} else {
		650	$cdom = $uhost;
		651	}
		652
		653	# store it
		654	$arg{cookie_jar}{version} = 1;
		655	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		656
		657	redo if /\G\s*,/gc;
		658	}
		659	}
		660
		661	if ($redirect && exists $hdr{location}) {
		662	# we ignore any errors, as it is very common to receive
		663	# Content-Length != 0 but no actual body
		664	# we also access %hdr, as $_[1] might be an erro
		665	http_request (
		666	$method => $hdr{location},
		667	%arg,
		668	recurse => $recurse - 1,
		669	Redirect => \@_,
		670	$cb);
		671	} else {
		672	$cb->($_[0], $_[1]);
		673	}
201	};	674	};
202		675
		676	my $len = $hdr{"content-length"};
		677
		678	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		679	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		680	} elsif (
		681	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		682	or $method eq "HEAD"
		683	or (defined $len && !$len)
		684	) {
		685	# no body
		686	$finish->("", \%hdr);
		687	} else {
		688	# body handling, four different code paths
		689	# for want_body_handle, on_body (2x), normal (2x)
		690	# we might read too much here, but it does not matter yet (no pers. connections)
		691	if (!$redirect && $arg{want_body_handle}) {
		692	$_[0]->on_eof (undef);
		693	$_[0]->on_error (undef);
		694	$_[0]->on_read (undef);
		695
		696	$finish->(delete $state{handle}, \%hdr);
		697
		698	} elsif ($arg{on_body}) {
		699	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		700	if ($len) {
		701	$_[0]->on_eof (undef);
		702	$_[0]->on_read (sub {
		703	$len -= length $_[0]{rbuf};
		704
		705	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		706	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		707
		708	$len > 0
		709	or $finish->("", \%hdr);
		710	});
		711	} else {
		712	$_[0]->on_eof (sub {
		713	$finish->("", \%hdr);
		714	});
		715	$_[0]->on_read (sub {
		716	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		717	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		718	});
		719	}
		720	} else {
		721	$_[0]->on_eof (undef);
		722
		723	if ($len) {
		724	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		725	$_[0]->on_read (sub {
		726	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		727	if $len <= length $_[0]{rbuf};
		728	});
		729	} else {
		730	$_[0]->on_error (sub {
		731	($! == Errno::EPIPE \|\| !$!)
		732	? $finish->(delete $_[0]{rbuf}, \%hdr)
		733	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		734	});
		735	$_[0]->on_read (sub { });
		736	}
		737	}
		738	}
		739	});
		740	};
		741
		742	# now handle proxy-CONNECT method
		743	if ($proxy && $uscheme eq "https") {
		744	# oh dear, we have to wrap it into a connect request
		745
		746	# maybe re-use $uauthority with patched port?
		747	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		748	$state{handle}->push_read (line => $qr_nlnl, sub {
		749	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		750	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
		751
		752	if ($2 == 200) {
		753	$rpath = $upath;
		754	&$handle_actual_request;
		755	} else {
203	%state = ();	756	%state = ();
204	$cb->($_[1], \%hdr);	757	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
		758	}
205	});	759	});
206	} else {	760	} else {
207	# too bad, need to read until we get an error or EOF,	761	&$handle_actual_request;
208	# no way to detect winged data.
209	$_[0]->on_error (sub {
210	%state = ();
211	$cb->($_[0]{rbuf}, \%hdr);
212	});
213	$_[0]->on_eof (undef);
214	$_[0]->on_read (sub { });
215	}	762	}
		763
216	});	764	},
		765	$arg{on_prepare} \|\| sub { $timeout }
217	});	766	);
218	}, sub {
219	$timeout
220	};	767	};
221		768
222	defined wantarray && AnyEvent::Util::guard { %state = () }	769	defined wantarray && AnyEvent::Util::guard { %state = () }
223	}	770	}
224		771
225	sub http_get($$;@) {	772	sub http_get($@) {
226	unshift @_, "GET";	773	unshift @_, "GET";
227	&http_request	774	&http_request
228	}	775	}
229		776
		777	sub http_head($@) {
		778	unshift @_, "HEAD";
		779	&http_request
		780	}
		781
		782	sub http_post($$@) {
		783	my $url = shift;
		784	unshift @_, "POST", $url, "body";
		785	&http_request
		786	}
		787
		788	=back
		789
		790	=head2 DNS CACHING
		791
		792	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		793	the actual connection, which in turn uses AnyEvent::DNS to resolve
		794	hostnames. The latter is a simple stub resolver and does no caching
		795	on its own. If you want DNS caching, you currently have to provide
		796	your own default resolver (by storing a suitable resolver object in
		797	C<$AnyEvent::DNS::RESOLVER>).
		798
230	=head2 GLOBAL VARIABLES	799	=head2 GLOBAL FUNCTIONS AND VARIABLES
231		800
232	=over 4	801	=over 4
233		802
		803	=item AnyEvent::HTTP::set_proxy "proxy-url"
		804
		805	Sets the default proxy server to use. The proxy-url must begin with a
		806	string of the form C<http://host:port> (optionally C<https:...>), croaks
		807	otherwise.
		808
		809	To clear an already-set proxy, use C<undef>.
		810
234	=item $AnyEvent::HTTP::MAX_REDIRECTS	811	=item $AnyEvent::HTTP::MAX_RECURSE
235		812
236	The default value for the C<max_redirects> request parameter	813	The default value for the C<recurse> request parameter (default: C<10>).
237	(default: C<10>).
238		814
239	=item $AnyEvent::HTTP::USERAGENT	815	=item $AnyEvent::HTTP::USERAGENT
240		816
241	The default value for the C<User-Agent> header (the default is	817	The default value for the C<User-Agent> header (the default is
242	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	818	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
243		819
244	=item $AnyEvent::HTTP::MAX_PERSISTENT	820	=item $AnyEvent::HTTP::MAX_PER_HOST
245		821
246	The maximum number of persistent connections to keep open (default: 8).	822	The maximum number of concurrent connections to the same host (identified
		823	by the hostname). If the limit is exceeded, then the additional requests
		824	are queued until previous connections are closed.
247		825
248	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	826	The default value for this is C<4>, and it is highly advisable to not
		827	increase it.
249		828
250	The maximum time to cache a persistent connection, in seconds (default: 15).	829	=item $AnyEvent::HTTP::ACTIVE
		830
		831	The number of active connections. This is not the number of currently
		832	running requests, but the number of currently open and non-idle TCP
		833	connections. This number of can be useful for load-leveling.
251		834
252	=back	835	=back
253		836
254	=cut	837	=cut
255		838
		839	sub set_proxy($) {
		840	if (length $_[0]) {
		841	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		842	or Carp::croak "$_[0]: invalid proxy URL";
		843	$PROXY = [$2, $3 \|\| 3128, $1]
		844	} else {
		845	undef $PROXY;
		846	}
		847	}
		848
		849	# initialise proxy from environment
		850	eval {
		851	set_proxy $ENV{http_proxy};
		852	};
		853
		854	=head2 SOCKS PROXIES
		855
		856	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		857	compile your perl to support socks, or use an external program such as
		858	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		859	transparently.
		860
		861	Alternatively, for AnyEvent::HTTP only, you can use your own
		862	C<tcp_connect> function that does the proxy handshake - here is an example
		863	that works with socks4a proxies:
		864
		865	use Errno;
		866	use AnyEvent::Util;
		867	use AnyEvent::Socket;
		868	use AnyEvent::Handle;
		869
		870	# host, port and username of/for your socks4a proxy
		871	my $socks_host = "10.0.0.23";
		872	my $socks_port = 9050;
		873	my $socks_user = "";
		874
		875	sub socks4a_connect {
		876	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		877
		878	my $hdl = new AnyEvent::Handle
		879	connect => [$socks_host, $socks_port],
		880	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		881	on_error => sub { $connect_cb->() },
		882	;
		883
		884	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		885
		886	$hdl->push_read (chunk => 8, sub {
		887	my ($hdl, $chunk) = @_;
		888	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		889
		890	if ($status == 0x5a) {
		891	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		892	} else {
		893	$! = Errno::ENXIO; $connect_cb->();
		894	}
		895	});
		896
		897	$hdl
		898	}
		899
		900	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		901	possibly after switching off other proxy types:
		902
		903	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		904
		905	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		906	my ($data, $headers) = @_;
		907	...
		908	};
		909
256	=head1 SEE ALSO	910	=head1 SEE ALSO
257		911
258	L<AnyEvent>.	912	L<AnyEvent>.
259		913
260	=head1 AUTHOR	914	=head1 AUTHOR
261		915
262	Marc Lehmann <schmorp@schmorp.de>	916	Marc Lehmann <schmorp@schmorp.de>
263	http://home.schmorp.de/	917	http://home.schmorp.de/
		918
		919	With many thanks to Дмитрий Шалашов, who provided countless
		920	testcases and bugreports.
264		921
265	=cut	922	=cut
266		923
267	1	924	1
268		925

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.1 by root, Tue Jun 3 16:37:13 2008 UTC vs. Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.1 by root, Tue Jun 3 16:37:13 2008 UTC vs.
Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC