[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 1.40 by root, Sun Jul 5 01:45:01 2009 UTC

…		…
3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client	3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use AnyEvent::HTTP;	7	use AnyEvent::HTTP;
		8
		9	http_get "http://www.nethype.de/", sub { print $_[1] };
		10
		11	# ... do something else here
8		12
9	=head1 DESCRIPTION	13	=head1 DESCRIPTION
10		14
11	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
12	run a supported event loop.	16	run a supported event loop.
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
…		…
22	use strict;	41	use strict;
23	no warnings;	42	no warnings;
24		43
25	use Carp;	44	use Carp;
26		45
27	use AnyEvent ();	46	use AnyEvent 4.452 ();
28	use AnyEvent::Util ();	47	use AnyEvent::Util ();
29	use AnyEvent::Socket ();	48	use AnyEvent::Socket ();
30	use AnyEvent::Handle ();	49	use AnyEvent::Handle ();
31		50
32	use base Exporter::;	51	use base Exporter::;
33		52
34	our $VERSION = '1.0';	53	our $VERSION = '1.12';
35		54
36	our @EXPORT = qw(http_get http_request);	55	our @EXPORT = qw(http_get http_post http_head http_request);
37		56
38	our $MAX_REDIRECTS = 10;
39	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	57	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
		58	our $MAX_RECURSE = 10;
40	our $MAX_PERSISTENT = 8;	59	our $MAX_PERSISTENT = 8;
41	our $PERSISTENT_TIMEOUT = 15;	60	our $PERSISTENT_TIMEOUT = 2;
42	our $TIMEOUT = 60;	61	our $TIMEOUT = 300;
43		62
44	# changing these is evil	63	# changing these is evil
45	our $MAX_PERSISTENT_PER_HOST = 2;	64	our $MAX_PERSISTENT_PER_HOST = 2;
46	our $MAX_PER_HOST = 4; # not respected yet :(	65	our $MAX_PER_HOST = 4;
		66
		67	our $PROXY;
		68	our $ACTIVE = 0;
47		69
48	my %KA_COUNT; # number of open keep-alive connections per host	70	my %KA_COUNT; # number of open keep-alive connections per host
		71	my %CO_SLOT; # number of open connections, and wait queue, per host
49		72
50	=item http_get $url, key => value..., $cb->($data, $headers)	73	=item http_get $url, key => value..., $cb->($data, $headers)
51		74
52	Executes an HTTP-GET request. See the http_request function for details on	75	Executes an HTTP-GET request. See the http_request function for details on
53	additional parameters.	76	additional parameters and the return value.
		77
		78	=item http_head $url, key => value..., $cb->($data, $headers)
		79
		80	Executes an HTTP-HEAD request. See the http_request function for details
		81	on additional parameters and the return value.
		82
		83	=item http_post $url, $body, key => value..., $cb->($data, $headers)
		84
		85	Executes an HTTP-POST request with a request body of C<$body>. See the
		86	http_request function for details on additional parameters and the return
		87	value.
54		88
55	=item http_request $method => $url, key => value..., $cb->($data, $headers)	89	=item http_request $method => $url, key => value..., $cb->($data, $headers)
56		90
57	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	91	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
58	must be an absolute http or https URL.	92	must be an absolute http or https URL.
59		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
		99	The callback will be called with the response data as first argument
		100	(or C<undef> if it wasn't available due to errors), and a hash-ref with
		101	response headers as second argument.
		102
		103	All the headers in that hash are lowercased. In addition to the response
		104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
		105	contain the three parts of the HTTP Status-Line of the same name. The
		106	pseudo-header C<URL> contains the original URL (which can differ from the
		107	requested URL when following redirects).
		108
		109	If the server sends a header multiple times, then their contents will be
		110	joined together with a comma (C<,>), as per the HTTP spec.
		111
		112	If an internal error occurs, such as not being able to resolve a hostname,
		113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>
		114	and the C<Reason> pseudo-header will contain an error message.
		115
		116	A typical callback might look like this:
		117
		118	sub {
		119	my ($body, $hdr) = @_;
		120
		121	if ($hdr->{Status} =~ /^2/) {
		122	... everything should be ok
		123	} else {
		124	print "error, $hdr->{Status} $hdr->{Reason}\n";
		125	}
		126	}
		127
60	Additional parameters are key-value pairs, and are fully optional. They	128	Additional parameters are key-value pairs, and are fully optional. They
61	include:	129	include:
62		130
63	=over 4	131	=over 4
64		132
65	=item recurse => $boolean (default: true)	133	=item recurse => $count (default: $MAX_RECURSE)
66		134
67	Whether to recurse requests or not, e.g. on redirects, authentication	135	Whether to recurse requests or not, e.g. on redirects, authentication
68	retries and so on.	136	retries and so on, and how often to do so.
69		137
70	=item headers => hashref	138	=item headers => hashref
71		139
72	The request headers to use.	140	The request headers to use. Currently, C<http_request> may provide its
		141	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
		142	and will provide defaults for C<User-Agent:> and C<Referer:>.
73		143
74	=item timeout => $seconds	144	=item timeout => $seconds
75		145
76	The time-out to use for various stages - each connect attempt will reset	146	The time-out to use for various stages - each connect attempt will reset
77	the timeout, as will read or write activity.	147	the timeout, as will read or write activity. Default timeout is 5 minutes.
		148
		149	=item proxy => [$host, $port[, $scheme]] or undef
		150
		151	Use the given http proxy for all requests. If not specified, then the
		152	default proxy (as specified by C<$ENV{http_proxy}>) is used.
		153
		154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for
		155	HTTPS.
		156
		157	=item body => $string
		158
		159	The request body, usually empty. Will be-sent as-is (future versions of
		160	this module might offer more options).
		161
		162	=item cookie_jar => $hash_ref
		163
		164	Passing this parameter enables (simplified) cookie-processing, loosely
		165	based on the original netscape specification.
		166
		167	The C<$hash_ref> must be an (initially empty) hash reference which will
		168	get updated automatically. It is possible to save the cookie_jar to
		169	persistent storage with something like JSON or Storable, but this is not
		170	recommended, as expiry times are currently being ignored.
		171
		172	Note that this cookie implementation is not of very high quality, nor
		173	meant to be complete. If you want complete cookie management you have to
		174	do that on your own. C<cookie_jar> is meant as a quick fix to get some
		175	cookie-using sites working. Cookies are a privacy disaster, do not use
		176	them unless required to.
		177
		178	=item tls_ctx => $scheme \| $tls_ctx
		179
		180	Specifies the AnyEvent::TLS context to be used for https connections. This
		181	parameter follows the same rules as the C<tls_ctx> parameter to
		182	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		183	C<high> can be specified, which give you a predefined low-security (no
		184	verification, highest compatibility) and high-security (CA and common-name
		185	verification) TLS context.
		186
		187	The default for this option is C<low>, which could be interpreted as "give
		188	me the page, no matter what".
78		189
79	=back	190	=back
80		191
81	=back	192	Example: make a simple HTTP GET request for http://www.nethype.de/
		193
		194	http_request GET => "http://www.nethype.de/", sub {
		195	my ($body, $hdr) = @_;
		196	print "$body\n";
		197	};
		198
		199	Example: make a HTTP HEAD request on https://www.google.com/, use a
		200	timeout of 30 seconds.
		201
		202	http_request
		203	GET => "https://www.google.com",
		204	timeout => 30,
		205	sub {
		206	my ($body, $hdr) = @_;
		207	use Data::Dumper;
		208	print Dumper $hdr;
		209	}
		210	;
		211
		212	Example: make another simple HTTP GET request, but immediately try to
		213	cancel it.
		214
		215	my $request = http_request GET => "http://www.nethype.de/", sub {
		216	my ($body, $hdr) = @_;
		217	print "$body\n";
		218	};
		219
		220	undef $request;
82		221
83	=cut	222	=cut
84		223
		224	sub _slot_schedule;
		225	sub _slot_schedule($) {
		226	my $host = shift;
		227
		228	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		229	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		230	# somebody wants that slot
		231	++$CO_SLOT{$host}[0];
		232	++$ACTIVE;
		233
		234	$cb->(AnyEvent::Util::guard {
		235	--$ACTIVE;
		236	--$CO_SLOT{$host}[0];
		237	_slot_schedule $host;
		238	});
		239	} else {
		240	# nobody wants the slot, maybe we can forget about it
		241	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		242	last;
		243	}
		244	}
		245	}
		246
		247	# wait for a free slot on host, call callback
		248	sub _get_slot($$) {
		249	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		250
		251	_slot_schedule $_[0];
		252	}
		253
		254	our $qr_nl = qr<\015?\012>;
		255	our $qr_nlnl = qr<\015?\012\015?\012>;
		256
		257	our $TLS_CTX_LOW = { cache => 1, dh => undef, sslv2 => 1 };
		258	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_cn => "https", dh => "skip4096" };
		259
85	sub http_request($$$;@) {	260	sub http_request($$@) {
86	my $cb = pop;	261	my $cb = pop;
87	my ($method, $url, %arg) = @_;	262	my ($method, $url, %arg) = @_;
88		263
89	my %hdr;	264	my %hdr;
90		265
		266	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		267	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
		268
		269	$method = uc $method;
		270
91	if (my $hdr = delete $arg{headers}) {	271	if (my $hdr = $arg{headers}) {
92	while (my ($k, $v) = each %$hdr) {	272	while (my ($k, $v) = each %$hdr) {
93	$hdr{lc $k} = $v;	273	$hdr{lc $k} = $v;
94	}	274	}
95	}	275	}
96		276
		277	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
		278
		279	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
		280	if $recurse < 0;
		281
		282	my $proxy = $arg{proxy} \|\| $PROXY;
97	my $timeout = $arg{timeout} \|\| $TIMEOUT;	283	my $timeout = $arg{timeout} \|\| $TIMEOUT;
98		284
99	$hdr{"user-agent"} \|\|= $USERAGENT;	285	$hdr{"user-agent"} \|\|= $USERAGENT;
100		286
101	my ($scheme, $authority, $path, $query, $fragment) =	287	my ($uscheme, $uauthority, $upath, $query, $fragment) =
102	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	288	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
103		289
104	$scheme = lc $scheme;	290	$uscheme = lc $uscheme;
		291
105	my $port = $scheme eq "http" ? 80	292	my $uport = $uscheme eq "http" ? 80
106	: $scheme eq "https" ? 443	293	: $uscheme eq "https" ? 443
107	: croak "$url: only http and https URLs supported";	294	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported (not '$uscheme')", URL => $url });
108		295
		296	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
		297
109	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	298	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
110	or croak "$authority: unparsable URL";	299	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
111		300
112	my $host = $1;	301	my $uhost = $1;
113	$port = $2 if defined $2;	302	$uport = $2 if defined $2;
114		303
115	$host =~ s/^\[(.*)\]$/$1/;	304	$uhost =~ s/^\[(.*)\]$/$1/;
116	$path .= "?$query" if length $query;	305	$upath .= "?$query" if length $query;
117		306
118	$hdr{host} = $host = lc $host;	307	$upath =~ s%^/?%/%;
119		308
120	my %state;	309	# cookie processing
121		310	if (my $jar = $arg{cookie_jar}) {
122	my $body = "";	311	%$jar = () if $jar->{version} != 1;
123	$state{body} = $body;	312
124		313	my @cookie;
125	$hdr{"content-length"} = length $body;	314
126		315	while (my ($chost, $v) = each %$jar) {
127	$state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub {	316	if ($chost =~ /^\./) {
128	$state{fh} = shift	317	next unless $chost eq substr $uhost, -length $chost;
129	or return $cb->(undef, { Status => 599, Reason => "$!" });	318	} elsif ($chost =~ /\./) {
130		319	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 {	320	} else {
144	delete $hdr{connection};	321	next;
		322	}
		323
		324	while (my ($cpath, $v) = each %$v) {
		325	next unless $cpath eq substr $upath, 0, length $cpath;
		326
		327	while (my ($k, $v) = each %$v) {
		328	next if $uscheme ne "https" && exists $v->{secure};
		329	my $value = $v->{value};
		330	$value =~ s/([\\"])/\\$1/g;
		331	push @cookie, "$k=\"$value\"";
		332	}
		333	}
145	}	334	}
		335
		336	$hdr{cookie} = join "; ", @cookie
		337	if @cookie;
		338	}
146		339
147	# (re-)configure handle	340	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
148	$state{handle}->timeout ($timeout);
149	$state{handle}->on_error (sub {
150	%state = ();
151	$cb->(undef, { Status => 599, Reason => "$!" });
152	});
153	$state{handle}->on_eof (sub {
154	%state = ();
155	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
156	});
157		341
158	# send request	342	if ($proxy) {
159	$state{handle}->push_write (	343	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
160	"\U$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		344
166	%hdr = (); # reduce memory usage, save a kitten	345	# don't support https requests over https-proxy transport,
		346	# can't be done with tls as spec'ed, unless you double-encrypt.
		347	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		348	} else {
		349	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
		350	}
167		351
168	# status line	352	$hdr{host} = $uhost;
169	$state{handle}->push_read (line => qr/\015?\012/, sub {	353	$hdr{"content-length"} = length $arg{body};
170	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix	354
		355	my %state = (connect_guard => 1);
		356
		357	_get_slot $uhost, sub {
		358	$state{slot_guard} = shift;
		359
		360	return unless $state{connect_guard};
		361
		362	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
		363	$state{fh} = shift
171	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));	364	or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url }));
		365	pop; # free memory, save a tree
172		366
173	my %hdr = ( # response headers	367	return unless delete $state{connect_guard};
174	HTTPVersion => ",$1",
175	Status => ",$2",
176	Reason => ",$3",
177	);
178		368
179	# headers, could be optimized a bit	369	# get handle
180	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	370	$state{handle} = new AnyEvent::Handle
181	for ("$_[1]\012") {	371	fh => $state{fh},
182	$hdr{lc $1} .= ",$2"	372	timeout => $timeout,
183	while /\G	373	peername => $rhost,
184	([^:\000-\040]+):	374	tls_ctx => $arg{tls_ctx};
185	[\011\040]*
186	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
187	\015?\012
188	/gxc;
189		375
190	/\G$/	376	# limit the number of persistent connections
191	or return $cb->(undef, { Status => 599, Reason => "garbled response headers" });	377	# keepalive not yet supported
		378	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		379	++$KA_COUNT{$_[1]};
		380	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		381	--$KA_COUNT{$_[1]}
192	}	382	};
		383	$hdr{connection} = "keep-alive";
		384	} else {
		385	delete $hdr{connection};
		386	}
193		387
		388	# (re-)configure handle
		389	$state{handle}->on_error (sub {
		390	%state = ();
		391	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
		392	});
		393	$state{handle}->on_eof (sub {
		394	%state = ();
		395	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
		396	});
		397
		398	$state{handle}->starttls ("connect") if $rscheme eq "https";
		399
		400	# handle actual, non-tunneled, request
		401	my $handle_actual_request = sub {
		402	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		403
		404	# send request
		405	$state{handle}->push_write (
		406	"$method $rpath HTTP/1.0\015\012"
		407	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)
		408	. "\015\012"
		409	. (delete $arg{body})
		410	);
		411
		412	%hdr = (); # reduce memory usage, save a kitten
		413
		414	# status line
		415	$state{handle}->push_read (line => $qr_nl, sub {
		416	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		417	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
		418
		419	my %hdr = ( # response headers
		420	HTTPVersion => ",$1",
		421	Status => ",$2",
		422	Reason => ",$3",
		423	URL => ",$url"
		424	);
		425
		426	# headers, could be optimized a bit
		427	$state{handle}->unshift_read (line => $qr_nlnl, sub {
		428	for ("$_[1]\012") {
		429	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		430
		431	# things seen, not parsed:
		432	# p3pP="NON CUR OTPi OUR NOR UNI"
		433
		434	$hdr{lc $1} .= ",$2"
		435	while /\G
		436	([^:\000-\037]+):
		437	[\011\040]*
		438	((?: [^\012]+ \| \012[\011\040] )*)
		439	\012
		440	/gxc;
		441
		442	/\G$/
		443	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
		444	}
		445
194	substr $_, 0, 1, ""	446	substr $_, 0, 1, ""
195	for values %hdr;	447	for values %hdr;
196		448
197	if (exists $hdr{"content-length"}) {	449	my $finish = sub {
198	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	450	$state{handle}->destroy;
199	# could cache persistent connection now	451	%state = ();
200	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	452
		453	# set-cookie processing
		454	if ($arg{cookie_jar}) {
		455	for ($hdr{"set-cookie"}) {
		456	# parse NAME=VALUE
		457	my @kv;
		458
		459	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		460	my $name = $1;
		461	my $value = $3;
		462
		463	unless ($value) {
		464	$value = $2;
		465	$value =~ s/\\(.)/$1/gs;
		466	}
		467
		468	push @kv, $name => $value;
		469
		470	last unless /\G\s*;/gc;
		471	}
		472
		473	last unless @kv;
		474
		475	my $name = shift @kv;
		476	my %kv = (value => shift @kv, @kv);
		477
		478	my $cdom;
		479	my $cpath = (delete $kv{path}) \|\| "/";
		480
		481	if (exists $kv{domain}) {
		482	$cdom = delete $kv{domain};
		483
		484	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		485
		486	next if $cdom =~ /\.$/;
		487
		488	# this is not rfc-like and not netscape-like. go figure.
		489	my $ndots = $cdom =~ y/.//;
		490	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		491	} else {
		492	$cdom = $uhost;
		493	}
		494
		495	# store it
		496	$arg{cookie_jar}{version} = 1;
		497	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		498
		499	redo if /\G\s*,/gc;
		500	}
		501	}
		502
		503	# microsoft and other shitheads don't give a shit for following standards,
		504	# try to support some common forms of broken Location headers.
		505	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		506	$_[1]{location} =~ s/^\.\/+//;
		507
		508	my $url = "$rscheme://$uhost:$uport";
		509
		510	unless ($_[1]{location} =~ s/^\///) {
		511	$url .= $upath;
		512	$url =~ s/\/[^\/]*$//;
		513	}
		514
		515	$_[1]{location} = "$url/$_[1]{location}";
		516	}
		517
		518	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
		519	# apparently, mozilla et al. just change POST to GET here
		520	# more research is needed before we do the same
		521	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
		522	} elsif ($_[1]{Status} == 303 && $recurse) {
		523	# even http/1.1 is unclear on how to mutate the method
		524	$method = "GET" unless $method eq "HEAD";
		525	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
		526	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
		527	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
		528	} else {
		529	$cb->($_[0], $_[1]);
		530	}
201	};	531	};
202		532
		533	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {
		534	$finish->(undef, \%hdr);
		535	} else {
		536	if (exists $hdr{"content-length"}) {
		537	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
		538	# could cache persistent connection now
		539	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
		540	# but we don't, due to misdesigns, this is annoyingly complex
		541	};
		542
		543	$finish->($_[1], \%hdr);
		544	});
		545	} else {
		546	# too bad, need to read until we get an error or EOF,
		547	# no way to detect winged data.
		548	$_[0]->on_error (sub {
		549	# delete ought to be more efficient, as we would have to make
		550	# a copy otherwise as $_[0] gets destroyed.
		551	$finish->(delete $_[0]{rbuf}, \%hdr);
		552	});
		553	$_[0]->on_eof (undef);
		554	$_[0]->on_read (sub { });
		555	}
		556	}
		557	});
		558	});
		559	};
		560
		561	# now handle proxy-CONNECT method
		562	if ($proxy && $uscheme eq "https") {
		563	# oh dear, we have to wrap it into a connect request
		564
		565	# maybe re-use $uauthority with patched port?
		566	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		567	$state{handle}->push_read (line => $qr_nlnl, sub {
		568	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		569	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
		570
		571	if ($2 == 200) {
		572	$rpath = $upath;
		573	&$handle_actual_request;
		574	} else {
203	%state = ();	575	%state = ();
204	$cb->($_[1], \%hdr);	576	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
205	});	577	}
206	} else {
207	# too bad, need to read until we get an error or EOF,
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	$_[0]->on_read (sub { });
215	}	578	});
		579	} else {
		580	&$handle_actual_request;
216	});	581	}
		582
		583	}, sub {
		584	$timeout
217	});	585	};
218	}, sub {
219	$timeout
220	};	586	};
221		587
222	defined wantarray && AnyEvent::Util::guard { %state = () }	588	defined wantarray && AnyEvent::Util::guard { %state = () }
223	}	589	}
224		590
225	sub http_get($$;@) {	591	sub http_get($@) {
226	unshift @_, "GET";	592	unshift @_, "GET";
227	&http_request	593	&http_request
228	}	594	}
229		595
		596	sub http_head($@) {
		597	unshift @_, "HEAD";
		598	&http_request
		599	}
		600
		601	sub http_post($$@) {
		602	my $url = shift;
		603	unshift @_, "POST", $url, "body";
		604	&http_request
		605	}
		606
		607	=back
		608
230	=head2 GLOBAL VARIABLES	609	=head2 GLOBAL FUNCTIONS AND VARIABLES
231		610
232	=over 4	611	=over 4
233		612
		613	=item AnyEvent::HTTP::set_proxy "proxy-url"
		614
		615	Sets the default proxy server to use. The proxy-url must begin with a
		616	string of the form C<http://host:port> (optionally C<https:...>).
		617
234	=item $AnyEvent::HTTP::MAX_REDIRECTS	618	=item $AnyEvent::HTTP::MAX_RECURSE
235		619
236	The default value for the C<max_redirects> request parameter	620	The default value for the C<recurse> request parameter (default: C<10>).
237	(default: C<10>).
238		621
239	=item $AnyEvent::HTTP::USERAGENT	622	=item $AnyEvent::HTTP::USERAGENT
240		623
241	The default value for the C<User-Agent> header (the default is	624	The default value for the C<User-Agent> header (the default is
242	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	625	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
243		626
244	=item $AnyEvent::HTTP::MAX_PERSISTENT	627	=item $AnyEvent::HTTP::MAX_PERSISTENT
245		628
246	The maximum number of persistent connections to keep open (default: 8).	629	The maximum number of persistent connections to keep open (default: 8).
247		630
		631	Not implemented currently.
		632
248	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	633	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
249		634
250	The maximum time to cache a persistent connection, in seconds (default: 15).	635	The maximum time to cache a persistent connection, in seconds (default: 2).
		636
		637	Not implemented currently.
		638
		639	=item $AnyEvent::HTTP::ACTIVE
		640
		641	The number of active connections. This is not the number of currently
		642	running requests, but the number of currently open and non-idle TCP
		643	connections. This number of can be useful for load-leveling.
251		644
252	=back	645	=back
253		646
254	=cut	647	=cut
255		648
		649	sub set_proxy($) {
		650	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;
		651	}
		652
		653	# initialise proxy from environment
		654	set_proxy $ENV{http_proxy};
		655
256	=head1 SEE ALSO	656	=head1 SEE ALSO
257		657
258	L<AnyEvent>.	658	L<AnyEvent>.
259		659
260	=head1 AUTHOR	660	=head1 AUTHOR
261		661
262	Marc Lehmann <schmorp@schmorp.de>	662	Marc Lehmann <schmorp@schmorp.de>
263	http://home.schmorp.de/	663	http://home.schmorp.de/
		664
		665	With many thanks to Дмитрий Шалашов, who provided countless
		666	testcases and bugreports.
264		667
265	=cut	668	=cut
266		669
267	1	670	1
268		671

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 1.40 by root, Sun Jul 5 01:45:01 2009 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 1.40 by root, Sun Jul 5 01:45:01 2009 UTC