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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.5 by root, Wed Jun 4 12:03:47 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 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<$method> (e.g. C<GET>, C<POST>). The URL
70	must be an absolute http or https URL.	91	must be an absolute http or https URL.
71		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
72	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
73	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
74	response headers as second argument.	100	second argument.
75		101
76	All the headers in that has are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
77	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
78	C<Reason> contain the three parts of the HTTP Status-Line of the same	105	three parts of the HTTP Status-Line of the same name.
79	name.	106
		107	The pseudo-header C<URL> contains the actual URL (which can differ from
		108	the requested URL when following redirects - for example, you might get
		109	an error that your URL scheme is not supported even though your URL is a
		110	valid http URL because it redirected to an ftp URL, in which case you can
		111	look at the URL pseudo header).
		112
		113	The pseudo-header C<Redirect> only exists when the request was a result
		114	of an internal redirect. In that case it is an array reference with
		115	the C<($data, $headers)> from the redirect response. Note that this
		116	response could in turn be the result of a redirect itself, and C<<
		117	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		118	response, and so on.
		119
		120	If the server sends a header multiple times, then their contents will be
		121	joined together with a comma (C<,>), as per the HTTP spec.
80		122
81	If an internal error occurs, such as not being able to resolve a hostname,	123	If an internal error occurs, such as not being able to resolve a hostname,
82	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	124	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
83	and the C<Reason> pseudo-header will contain an error message.	125	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		126	message.
		127
		128	A typical callback might look like this:
		129
		130	sub {
		131	my ($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	}
84		139
85	Additional parameters are key-value pairs, and are fully optional. They	140	Additional parameters are key-value pairs, and are fully optional. They
86	include:	141	include:
87		142
88	=over 4	143	=over 4
…		…
92	Whether to recurse requests or not, e.g. on redirects, authentication	147	Whether to recurse requests or not, e.g. on redirects, authentication
93	retries and so on, and how often to do so.	148	retries and so on, and how often to do so.
94		149
95	=item headers => hashref	150	=item headers => hashref
96		151
97	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).
98		157
99	=item timeout => $seconds	158	=item timeout => $seconds
100		159
101	The time-out to use for various stages - each connect attempt will reset	160	The time-out to use for various stages - each connect attempt will reset
102	the timeout, as will read or write activity. Default timeout is 5 minutes.	161	the timeout, as will read or write activity, i.e. this is not an overall
		162	timeout.
		163
		164	Default timeout is 5 minutes.
103		165
104	=item proxy => [$host, $port[, $scheme]] or undef	166	=item proxy => [$host, $port[, $scheme]] or undef
105		167
106	Use the given http proxy for all requests. If not specified, then the	168	Use the given http proxy for all requests. If not specified, then the
107	default proxy (as specified by C<$ENV{http_proxy}>) is used.	169	default proxy (as specified by C<$ENV{http_proxy}>) is used.
108		170
109	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	171	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
110	HTTPS.	172	HTTPS.
111		173
112	=item body => $string	174	=item body => $string
113		175
114	The request body, usually empty. Will be-sent as-is (future versions of	176	The request body, usually empty. Will be-sent as-is (future versions of
115	this module might offer more options).	177	this module might offer more options).
116		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.
		222
		223	There are probably lots of weird uses for this function, starting from
		224	tracing the hosts C<http_request> actually tries to connect, to (inexact
		225	but fast) host => IP address caching or even socks protocol support.
		226
		227	=item on_header => $callback->($headers)
		228
		229	When specified, this callback will be called with the header hash as soon
		230	as headers have been successfully received from the remote server (not on
		231	locally-generated errors).
		232
		233	It has to return either true (in which case AnyEvent::HTTP will continue),
		234	or false, in which case AnyEvent::HTTP will cancel the download (and call
		235	the finish callback with an error code of C<598>).
		236
		237	This callback is useful, among other things, to quickly reject unwanted
		238	content, which, if it is supposed to be rare, can be faster than first
		239	doing a C<HEAD> request.
		240
		241	Example: cancel the request unless the content-type is "text/html".
		242
		243	on_header => sub {
		244	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		245	},
		246
		247	=item on_body => $callback->($partial_body, $headers)
		248
		249	When specified, all body data will be passed to this callback instead of
		250	to the completion callback. The completion callback will get the empty
		251	string instead of the body data.
		252
		253	It has to return either true (in which case AnyEvent::HTTP will continue),
		254	or false, in which case AnyEvent::HTTP will cancel the download (and call
		255	the completion callback with an error code of C<598>).
		256
		257	This callback is useful when the data is too large to be held in memory
		258	(so the callback writes it to a file) or when only some information should
		259	be extracted, or when the body should be processed incrementally.
		260
		261	It is usually preferred over doing your own body handling via
		262	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		263	only used to create a connection, C<want_body_handle> is the better
		264	alternative, as it allows you to install your own event handler, reducing
		265	resource usage.
		266
		267	=item want_body_handle => $enable
		268
		269	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		270	changes considerably: after parsing the headers, and instead of
		271	downloading the body (if any), the completion callback will be
		272	called. Instead of the C<$body> argument containing the body data, the
		273	callback will receive the L<AnyEvent::Handle> object associated with the
		274	connection. In error cases, C<undef> will be passed. When there is no body
		275	(e.g. status C<304>), the empty string will be passed.
		276
		277	The handle object might or might not be in TLS mode, might be connected to
		278	a proxy, be a persistent connection etc., and configured in unspecified
		279	ways. The user is responsible for this handle (it will not be used by this
		280	module anymore).
		281
		282	This is useful with some push-type services, where, after the initial
		283	headers, an interactive protocol is used (typical example would be the
		284	push-style twitter API which starts a JSON/XML stream).
		285
		286	If you think you need this, first have a look at C<on_body>, to see if
		287	that doesn't solve your problem in a better way.
		288
117	=back	289	=back
118		290
119	=back	291	Example: make a simple HTTP GET request for http://www.nethype.de/
		292
		293	http_request GET => "http://www.nethype.de/", sub {
		294	my ($body, $hdr) = @_;
		295	print "$body\n";
		296	};
		297
		298	Example: make a HTTP HEAD request on https://www.google.com/, use a
		299	timeout of 30 seconds.
		300
		301	http_request
		302	GET => "https://www.google.com",
		303	timeout => 30,
		304	sub {
		305	my ($body, $hdr) = @_;
		306	use Data::Dumper;
		307	print Dumper $hdr;
		308	}
		309	;
		310
		311	Example: make another simple HTTP GET request, but immediately try to
		312	cancel it.
		313
		314	my $request = http_request GET => "http://www.nethype.de/", sub {
		315	my ($body, $hdr) = @_;
		316	print "$body\n";
		317	};
		318
		319	undef $request;
120		320
121	=cut	321	=cut
122		322
		323	sub _slot_schedule;
		324	sub _slot_schedule($) {
		325	my $host = shift;
		326
		327	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		328	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		329	# somebody wants that slot
		330	++$CO_SLOT{$host}[0];
		331	++$ACTIVE;
		332
		333	$cb->(AnyEvent::Util::guard {
		334	--$ACTIVE;
		335	--$CO_SLOT{$host}[0];
		336	_slot_schedule $host;
		337	});
		338	} else {
		339	# nobody wants the slot, maybe we can forget about it
		340	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		341	last;
		342	}
		343	}
		344	}
		345
		346	# wait for a free slot on host, call callback
		347	sub _get_slot($$) {
		348	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		349
		350	_slot_schedule $_[0];
		351	}
		352
		353	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		354
		355	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		356	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		357
123	sub http_request($$$;@) {	358	sub http_request($$@) {
124	my $cb = pop;	359	my $cb = pop;
125	my ($method, $url, %arg) = @_;	360	my ($method, $url, %arg) = @_;
126		361
127	my %hdr;	362	my %hdr;
128		363
		364	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		365	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
		366
129	$method = uc $method;	367	$method = uc $method;
130		368
131	if (my $hdr = delete $arg{headers}) {	369	if (my $hdr = $arg{headers}) {
132	while (my ($k, $v) = each %$hdr) {	370	while (my ($k, $v) = each %$hdr) {
133	$hdr{lc $k} = $v;	371	$hdr{lc $k} = $v;
134	}	372	}
135	}	373	}
136		374
		375	# pseudo headers for all subsequent responses
		376	my @pseudo = (URL => $url);
		377	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		378
		379	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
		380
		381	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
		382	if $recurse < 0;
		383
137	my $proxy = $arg{proxy} \|\| $PROXY;	384	my $proxy = $arg{proxy} \|\| $PROXY;
138	my $timeout = $arg{timeout} \|\| $TIMEOUT;	385	my $timeout = $arg{timeout} \|\| $TIMEOUT;
139	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;
140		386
141	$hdr{"user-agent"} \|\|= $USERAGENT;	387	my ($uscheme, $uauthority, $upath, $query, $fragment) =
		388	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
142		389
143	my ($host, $port, $path, $scheme);	390	$uscheme = lc $uscheme;
		391
		392	my $uport = $uscheme eq "http" ? 80
		393	: $uscheme eq "https" ? 443
		394	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
		395
		396	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
		397	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
		398
		399	my $uhost = $1;
		400	$uport = $2 if defined $2;
		401
		402	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		403	unless exists $hdr{host};
		404
		405	$uhost =~ s/^\[(.*)\]$/$1/;
		406	$upath .= $query if length $query;
		407
		408	$upath =~ s%^/?%/%;
		409
		410	# cookie processing
		411	if (my $jar = $arg{cookie_jar}) {
		412	%$jar = () if $jar->{version} != 1;
		413
		414	my @cookie;
		415
		416	while (my ($chost, $v) = each %$jar) {
		417	if ($chost =~ /^\./) {
		418	next unless $chost eq substr $uhost, -length $chost;
		419	} elsif ($chost =~ /\./) {
		420	next unless $chost eq $uhost;
		421	} else {
		422	next;
		423	}
		424
		425	while (my ($cpath, $v) = each %$v) {
		426	next unless $cpath eq substr $upath, 0, length $cpath;
		427
		428	while (my ($k, $v) = each %$v) {
		429	next if $uscheme ne "https" && exists $v->{secure};
		430	my $value = $v->{value};
		431	$value =~ s/([\\"])/\\$1/g;
		432	push @cookie, "$k=\"$value\"";
		433	}
		434	}
		435	}
		436
		437	$hdr{cookie} = join "; ", @cookie
		438	if @cookie;
		439	}
		440
		441	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
144		442
145	if ($proxy) {	443	if ($proxy) {
146	($host, $port, $scheme) = @$proxy;	444	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
147	$path = $url;	445
		446	$rscheme = "http" unless defined $rscheme;
		447
		448	# don't support https requests over https-proxy transport,
		449	# can't be done with tls as spec'ed, unless you double-encrypt.
		450	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
148	} else {	451	} else {
149	($scheme, my $authority, $path, my $query, my $fragment) =	452	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
150	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
151
152	$port = $scheme eq "http" ? 80
153	: $scheme eq "https" ? 443
154	: croak "$url: only http and https URLs supported";
155
156	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
157	or croak "$authority: unparsable URL";
158
159	$host = $1;
160	$port = $2 if defined $2;
161
162	$host =~ s/^\[(.*)\]$/$1/;
163	$path .= "?$query" if length $query;
164
165	$path = "/" unless $path;
166
167	$hdr{host} = $host = lc $host;
168	}	453	}
169		454
170	$scheme = lc $scheme;	455	# leave out fragment and query string, just a heuristic
		456	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		457	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
171		458
172	my %state;
173
174	$state{body} = delete $arg{body};
175
176	$hdr{"content-length"} = length $state{body};	459	$hdr{"content-length"} = length $arg{body}
		460	if length $arg{body} \|\| $method ne "GET";
177		461
178	$state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub {	462	my %state = (connect_guard => 1);
		463
		464	_get_slot $uhost, sub {
		465	$state{slot_guard} = shift;
		466
		467	return unless $state{connect_guard};
		468
		469	my $tcp_connect = $arg{tcp_connect}
		470	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		471
		472	$state{connect_guard} = $tcp_connect->(
		473	$rhost,
		474	$rport,
		475	sub {
179	$state{fh} = shift	476	$state{fh} = shift
		477	or do {
		478	my $err = "$!";
		479	%state = ();
180	or return $cb->(undef, { Status => 599, Reason => "$!" });	480	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		481	};
181		482
182	delete $state{connect_guard}; # reduce memory usage, save a tree	483	pop; # free memory, save a tree
183		484
		485	return unless delete $state{connect_guard};
		486
184	# get handle	487	# get handle
185	$state{handle} = new AnyEvent::Handle	488	$state{handle} = new AnyEvent::Handle
186	fh => $state{fh},	489	fh => $state{fh},
187	($scheme eq "https" ? (tls => "connect") : ());	490	peername => $rhost,
		491	tls_ctx => $arg{tls_ctx},
		492	# these need to be reconfigured on keepalive handles
		493	timeout => $timeout,
		494	on_error => sub {
		495	%state = ();
		496	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		497	},
		498	on_eof => sub {
		499	%state = ();
		500	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		501	},
		502	;
188		503
189	# limit the number of persistent connections	504	# limit the number of persistent connections
		505	# keepalive not yet supported
190	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	506	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
191	++$KA_COUNT{$_[1]};	507	# ++$KA_COUNT{$_[1]};
192	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	508	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		509	# --$KA_COUNT{$_[1]}
		510	# };
193	$hdr{connection} = "keep-alive";	511	# $hdr{connection} = "keep-alive";
194	delete $hdr{connection}; # keep-alive not yet supported
195	} else {	512	# } else {
196	delete $hdr{connection};	513	delete $hdr{connection};
197	}	514	# }
198		515
199	# (re-)configure handle	516	$state{handle}->starttls ("connect") if $rscheme eq "https";
200	$state{handle}->timeout ($timeout);
201	$state{handle}->on_error (sub {
202	%state = ();
203	$cb->(undef, { Status => 599, Reason => "$!" });
204	});
205	$state{handle}->on_eof (sub {
206	%state = ();
207	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
208	});
209		517
		518	# handle actual, non-tunneled, request
		519	my $handle_actual_request = sub {
		520	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		521
210	# send request	522	# send request
211	$state{handle}->push_write (	523	$state{handle}->push_write (
212	"$method $path HTTP/1.0\015\012"	524	"$method $rpath HTTP/1.0\015\012"
213	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	525	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
214	. "\015\012"	526	. "\015\012"
215	. (delete $state{body})	527	. (delete $arg{body})
		528	);
		529
		530	# return if error occured during push_write()
		531	return unless %state;
		532
		533	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		534
		535	# status line and headers
		536	$state{handle}->push_read (line => $qr_nlnl, sub {
		537	for ("$_[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, { Status => 599, Reason => "Invalid server response", @pseudo }));
		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, { Status => 599, Reason => "Garbled response headers", @pseudo }));
		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 {
		607	$state{handle}->destroy if $state{handle};
		608	%state = ();
		609
		610	# set-cookie processing
		611	if ($arg{cookie_jar}) {
		612	for ($_[1]{"set-cookie"}) {
		613	# parse NAME=VALUE
		614	my @kv;
		615
		616	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		617	my $name = $1;
		618	my $value = $3;
		619
		620	unless ($value) {
		621	$value = $2;
		622	$value =~ s/\\(.)/$1/gs;
		623	}
		624
		625	push @kv, $name => $value;
		626
		627	last unless /\G\s*;/gc;
		628	}
		629
		630	last unless @kv;
		631
		632	my $name = shift @kv;
		633	my %kv = (value => shift @kv, @kv);
		634
		635	my $cdom;
		636	my $cpath = (delete $kv{path}) \|\| "/";
		637
		638	if (exists $kv{domain}) {
		639	$cdom = delete $kv{domain};
		640
		641	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		642
		643	next if $cdom =~ /\.$/;
		644
		645	# this is not rfc-like and not netscape-like. go figure.
		646	my $ndots = $cdom =~ y/.//;
		647	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		648	} else {
		649	$cdom = $uhost;
		650	}
		651
		652	# store it
		653	$arg{cookie_jar}{version} = 1;
		654	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		655
		656	redo if /\G\s*,/gc;
		657	}
		658	}
		659
		660	if ($redirect && exists $hdr{location}) {
		661	# we ignore any errors, as it is very common to receive
		662	# Content-Length != 0 but no actual body
		663	# we also access %hdr, as $_[1] might be an erro
		664	http_request (
		665	$method => $hdr{location},
		666	%arg,
		667	recurse => $recurse - 1,
		668	Redirect => \@_,
		669	$cb);
		670	} else {
		671	$cb->($_[0], $_[1]);
		672	}
		673	};
		674
		675	my $len = $hdr{"content-length"};
		676
		677	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		678	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		679	} elsif (
		680	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		681	or $method eq "HEAD"
		682	or (defined $len && !$len)
		683	) {
		684	# no body
		685	$finish->("", \%hdr);
		686	} else {
		687	# body handling, four different code paths
		688	# for want_body_handle, on_body (2x), normal (2x)
		689	# we might read too much here, but it does not matter yet (no pers. connections)
		690	if (!$redirect && $arg{want_body_handle}) {
		691	$_[0]->on_eof (undef);
		692	$_[0]->on_error (undef);
		693	$_[0]->on_read (undef);
		694
		695	$finish->(delete $state{handle}, \%hdr);
		696
		697	} elsif ($arg{on_body}) {
		698	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		699	if ($len) {
		700	$_[0]->on_eof (undef);
		701	$_[0]->on_read (sub {
		702	$len -= length $_[0]{rbuf};
		703
		704	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		705	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		706
		707	$len > 0
		708	or $finish->("", \%hdr);
		709	});
		710	} else {
		711	$_[0]->on_eof (sub {
		712	$finish->("", \%hdr);
		713	});
		714	$_[0]->on_read (sub {
		715	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		716	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		717	});
		718	}
		719	} else {
		720	$_[0]->on_eof (undef);
		721
		722	if ($len) {
		723	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		724	$_[0]->on_read (sub {
		725	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		726	if $len <= length $_[0]{rbuf};
		727	});
		728	} else {
		729	$_[0]->on_error (sub {
		730	($! == Errno::EPIPE \|\| !$!)
		731	? $finish->(delete $_[0]{rbuf}, \%hdr)
		732	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		733	});
		734	$_[0]->on_read (sub { });
		735	}
		736	}
		737	}
		738	});
		739	};
		740
		741	# now handle proxy-CONNECT method
		742	if ($proxy && $uscheme eq "https") {
		743	# oh dear, we have to wrap it into a connect request
		744
		745	# maybe re-use $uauthority with patched port?
		746	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		747	$state{handle}->push_read (line => $qr_nlnl, sub {
		748	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		749	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
		750
		751	if ($2 == 200) {
		752	$rpath = $upath;
		753	&$handle_actual_request;
		754	} else {
		755	%state = ();
		756	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
		757	}
		758	});
		759	} else {
		760	&$handle_actual_request;
		761	}
		762
		763	},
		764	$arg{on_prepare} \|\| sub { $timeout }
216	);	765	);
217
218	%hdr = (); # reduce memory usage, save a kitten
219
220	# status line
221	$state{handle}->push_read (line => qr/\015?\012/, sub {
222	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
223	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
224
225	my %hdr = ( # response headers
226	HTTPVersion => ",$1",
227	Status => ",$2",
228	Reason => ",$3",
229	);
230
231	# headers, could be optimized a bit
232	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
233	for ("$_[1]\012") {
234	# we support spaces in field names, as lotus domino
235	# creates them.
236	$hdr{lc $1} .= ",$2"
237	while /\G
238	([^:\000-\037]+):
239	[\011\040]*
240	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
241	\015?\012
242	/gxc;
243
244	/\G$/
245	or return $cb->(undef, { Status => 599, Reason => "garbled response headers" });
246	}
247
248	substr $_, 0, 1, ""
249	for values %hdr;
250
251	if ($method eq "HEAD") {
252	%state = ();
253	$cb->(undef, \%hdr);
254	} else {
255	if (exists $hdr{"content-length"}) {
256	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
257	# could cache persistent connection now
258	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
259	# but we don't, due to misdesigns, this is annoyingly complex
260	};
261
262	%state = ();
263	$cb->($_[1], \%hdr);
264	});
265	} else {
266	# too bad, need to read until we get an error or EOF,
267	# no way to detect winged data.
268	$_[0]->on_error (sub {
269	%state = ();
270	$cb->($_[0]{rbuf}, \%hdr);
271	});
272	$_[0]->on_eof (undef);
273	$_[0]->on_read (sub { });
274	}
275	}
276	});
277	});
278	}, sub {
279	$timeout
280	};	766	};
281		767
282	defined wantarray && AnyEvent::Util::guard { %state = () }	768	defined wantarray && AnyEvent::Util::guard { %state = () }
283	}	769	}
284		770
285	sub http_get($$;@) {	771	sub http_get($@) {
286	unshift @_, "GET";	772	unshift @_, "GET";
287	&http_request	773	&http_request
288	}	774	}
289		775
290	sub http_head($$;@) {	776	sub http_head($@) {
291	unshift @_, "HEAD";	777	unshift @_, "HEAD";
292	&http_request	778	&http_request
293	}	779	}
294		780
295	sub http_post($$$;@) {	781	sub http_post($$@) {
		782	my $url = shift;
296	unshift @_, "POST", "body";	783	unshift @_, "POST", $url, "body";
297	&http_request	784	&http_request
298	}	785	}
299		786
		787	=back
		788
		789	=head2 DNS CACHING
		790
		791	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		792	the actual connection, which in turn uses AnyEvent::DNS to resolve
		793	hostnames. The latter is a simple stub resolver and does no caching
		794	on its own. If you want DNS caching, you currently have to provide
		795	your own default resolver (by storing a suitable resolver object in
		796	C<$AnyEvent::DNS::RESOLVER>).
		797
300	=head2 GLOBAL FUNCTIONS AND VARIABLES	798	=head2 GLOBAL FUNCTIONS AND VARIABLES
301		799
302	=over 4	800	=over 4
303		801
304	=item AnyEvent::HTTP::set_proxy "proxy-url"	802	=item AnyEvent::HTTP::set_proxy "proxy-url"
305		803
306	Sets the default proxy server to use. The proxy-url must begin with a	804	Sets the default proxy server to use. The proxy-url must begin with a
307	string of the form C<http://host:port> (optionally C<https:...>).	805	string of the form C<http://host:port> (optionally C<https:...>), croaks
		806	otherwise.
		807
		808	To clear an already-set proxy, use C<undef>.
308		809
309	=item $AnyEvent::HTTP::MAX_RECURSE	810	=item $AnyEvent::HTTP::MAX_RECURSE
310		811
311	The default value for the C<recurse> request parameter (default: C<10>).	812	The default value for the C<recurse> request parameter (default: C<10>).
312		813
313	=item $AnyEvent::HTTP::USERAGENT	814	=item $AnyEvent::HTTP::USERAGENT
314		815
315	The default value for the C<User-Agent> header (the default is	816	The default value for the C<User-Agent> header (the default is
316	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	817	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
317		818
318	=item $AnyEvent::HTTP::MAX_PERSISTENT	819	=item $AnyEvent::HTTP::MAX_PER_HOST
319		820
320	The maximum number of persistent connections to keep open (default: 8).	821	The maximum number of concurrent connections to the same host (identified
		822	by the hostname). If the limit is exceeded, then the additional requests
		823	are queued until previous connections are closed.
321		824
322	Not implemented currently.	825	The default value for this is C<4>, and it is highly advisable to not
		826	increase it.
323		827
324	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	828	=item $AnyEvent::HTTP::ACTIVE
325		829
326	The maximum time to cache a persistent connection, in seconds (default: 2).	830	The number of active connections. This is not the number of currently
327		831	running requests, but the number of currently open and non-idle TCP
328	Not implemented currently.	832	connections. This number of can be useful for load-leveling.
329		833
330	=back	834	=back
331		835
332	=cut	836	=cut
333		837
334	sub set_proxy($) {	838	sub set_proxy($) {
		839	if (length $_[0]) {
335	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	840	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		841	or Carp::croak "$_[0]: invalid proxy URL";
		842	$PROXY = [$2, $3 \|\| 3128, $1]
		843	} else {
		844	undef $PROXY;
		845	}
336	}	846	}
337		847
338	# initialise proxy from environment	848	# initialise proxy from environment
		849	eval {
339	set_proxy $ENV{http_proxy};	850	set_proxy $ENV{http_proxy};
		851	};
340		852
341	=head1 SEE ALSO	853	=head1 SEE ALSO
342		854
343	L<AnyEvent>.	855	L<AnyEvent>.
344		856
345	=head1 AUTHOR	857	=head1 AUTHOR
346		858
347	Marc Lehmann <schmorp@schmorp.de>	859	Marc Lehmann <schmorp@schmorp.de>
348	http://home.schmorp.de/	860	http://home.schmorp.de/
		861
		862	With many thanks to Дмитрий Шалашов, who provided countless
		863	testcases and bugreports.
349		864
350	=cut	865	=cut
351		866
352	1	867	1
353		868

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.5 by root, Wed Jun 4 12:03:47 2008 UTC vs. Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.5 by root, Wed Jun 4 12:03:47 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC