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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC

…		…
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Carp;	44	use Errno ();
45		45
46	use AnyEvent ();	46	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
50		49
51	use base Exporter::;	50	use base Exporter::;
52		51
53	our $VERSION = '1.01';	52	our $VERSION = '1.46';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	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)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
71	my %CO_SLOT; # number of open connections, and wait queue, per host	70	my %CO_SLOT; # number of open connections, and wait queue, per host
72		71
73	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
74		73
75	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
76	additional parameters.	75	additional parameters and the return value.
77		76
78	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
79		78
80	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
81	additional parameters.	80	on additional parameters and the return value.
82		81
83	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
84		83
85	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
86	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
87		87
88	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
89		89
90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	91	must be an absolute http or https URL.
92		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
93	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
95	response headers as second argument.	100	second argument.
96		101
97	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
98	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
99	C<Reason> contain the three parts of the HTTP Status-Line of the same	105	three parts of the HTTP Status-Line of the same name.
		106
		107	The pseudo-header C<URL> contains the actual URL (which can differ from
		108	the requested URL when following redirects - for example, you might get
		109	an error that your URL scheme is not supported even though your URL is a
		110	valid http URL because it redirected to an ftp URL, in which case you can
		111	look at the URL pseudo header).
		112
		113	The pseudo-header C<Redirect> only exists when the request was a result
		114	of an internal redirect. In that case it is an array reference with
		115	the C<($data, $headers)> from the redirect response. Note that this
		116	response could in turn be the result of a redirect itself, and C<<
		117	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		118	response, and so on.
		119
100	name. If the server sends a header multiple lines, then their contents	120	If the server sends a header multiple times, then their contents will be
101	will be joined together with C<\x00>.	121	joined together with a comma (C<,>), as per the HTTP spec.
102		122
103	If an internal error occurs, such as not being able to resolve a hostname,	123	If an internal error occurs, such as not being able to resolve a hostname,
104	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	124	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
105	and the C<Reason> pseudo-header will contain an error message.	125	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		126	message.
106		127
107	A typical callback might look like this:	128	A typical callback might look like this:
108		129
109	sub {	130	sub {
110	my ($body, $hdr) = @_;	131	my ($body, $hdr) = @_;
…		…
128		149
129	=item headers => hashref	150	=item headers => hashref
130		151
131	The request headers to use. Currently, C<http_request> may provide its	152	The request headers to use. Currently, C<http_request> may provide its
132	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	153	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
133	and will provide defaults for C<User-Agent:> and C<Referer:>.	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).
134		157
135	=item timeout => $seconds	158	=item timeout => $seconds
136		159
137	The time-out to use for various stages - each connect attempt will reset	160	The time-out to use for various stages - each connect attempt will reset
138	the timeout, as will read or write activity. Default timeout is 5 minutes.	161	the timeout, as will read or write activity, i.e. this is not an overall
		162	timeout.
		163
		164	Default timeout is 5 minutes.
139		165
140	=item proxy => [$host, $port[, $scheme]] or undef	166	=item proxy => [$host, $port[, $scheme]] or undef
141		167
142	Use the given http proxy for all requests. If not specified, then the	168	Use the given http proxy for all requests. If not specified, then the
143	default proxy (as specified by C<$ENV{http_proxy}>) is used.	169	default proxy (as specified by C<$ENV{http_proxy}>) is used.
144		170
145	C<$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
146	HTTPS.	172	HTTPS.
147		173
148	=item body => $string	174	=item body => $string
149		175
150	The request body, usually empty. Will be-sent as-is (future versions of	176	The request body, usually empty. Will be-sent as-is (future versions of
…		…
156	based on the original netscape specification.	182	based on the original netscape specification.
157		183
158	The C<$hash_ref> must be an (initially empty) hash reference which will	184	The C<$hash_ref> must be an (initially empty) hash reference which will
159	get updated automatically. It is possible to save the cookie_jar to	185	get updated automatically. It is possible to save the cookie_jar to
160	persistent storage with something like JSON or Storable, but this is not	186	persistent storage with something like JSON or Storable, but this is not
161	recommended, as expire times are currently being ignored.	187	recommended, as expiry times are currently being ignored.
162		188
163	Note that this cookie implementation is not of very high quality, nor	189	Note that this cookie implementation is not of very high quality, nor
164	meant to be complete. If you want complete cookie management you have to	190	meant to be complete. If you want complete cookie management you have to
165	do that on your own. C<cookie_jar> is meant as a quick fix to get some	191	do that on your own. C<cookie_jar> is meant as a quick fix to get some
166	cookie-using sites working. Cookies are a privacy disaster, do not use	192	cookie-using sites working. Cookies are a privacy disaster, do not use
167	them unless required to.	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.
168		288
169	=back	289	=back
170		290
171	Example: make a simple HTTP GET request for http://www.nethype.de/	291	Example: make a simple HTTP GET request for http://www.nethype.de/
172		292
…		…
185	my ($body, $hdr) = @_;	305	my ($body, $hdr) = @_;
186	use Data::Dumper;	306	use Data::Dumper;
187	print Dumper $hdr;	307	print Dumper $hdr;
188	}	308	}
189	;	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 $request;
190		320
191	=cut	321	=cut
192		322
193	sub _slot_schedule;	323	sub _slot_schedule;
194	sub _slot_schedule($) {	324	sub _slot_schedule($) {
…		…
218	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	348	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
219		349
220	_slot_schedule $_[0];	350	_slot_schedule $_[0];
221	}	351	}
222		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
223	sub http_request($$@) {	358	sub http_request($$@) {
224	my $cb = pop;	359	my $cb = pop;
225	my ($method, $url, %arg) = @_;	360	my ($method, $url, %arg) = @_;
226		361
227	my %hdr;	362	my %hdr;
		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";
228		366
229	$method = uc $method;	367	$method = uc $method;
230		368
231	if (my $hdr = $arg{headers}) {	369	if (my $hdr = $arg{headers}) {
232	while (my ($k, $v) = each %$hdr) {	370	while (my ($k, $v) = each %$hdr) {
233	$hdr{lc $k} = $v;	371	$hdr{lc $k} = $v;
234	}	372	}
235	}	373	}
236		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
237	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	379	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
238		380
239	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	381	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
240	if $recurse < 0;	382	if $recurse < 0;
241		383
242	my $proxy = $arg{proxy} \|\| $PROXY;	384	my $proxy = $arg{proxy} \|\| $PROXY;
243	my $timeout = $arg{timeout} \|\| $TIMEOUT;	385	my $timeout = $arg{timeout} \|\| $TIMEOUT;
244		386
245	$hdr{"user-agent"} \|\|= $USERAGENT;
246
247	my ($scheme, $authority, $upath, $query, $fragment) =	387	my ($uscheme, $uauthority, $upath, $query, $fragment) =
248	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	388	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
249		389
250	$scheme = lc $scheme;	390	$uscheme = lc $uscheme;
251		391
252	my $uport = $scheme eq "http" ? 80	392	my $uport = $uscheme eq "http" ? 80
253	: $scheme eq "https" ? 443	393	: $uscheme eq "https" ? 443
254	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	394	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
255		395
256	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
257
258	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	396	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
259	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	397	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
260		398
261	my $uhost = $1;	399	my $uhost = $1;
262	$uport = $2 if defined $2;	400	$uport = $2 if defined $2;
263		401
		402	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		403	unless exists $hdr{host};
		404
264	$uhost =~ s/^\[(.*)\]$/$1/;	405	$uhost =~ s/^\[(.*)\]$/$1/;
265	$upath .= "?$query" if length $query;	406	$upath .= $query if length $query;
266		407
267	$upath =~ s%^/?%/%;	408	$upath =~ s%^/?%/%;
268		409
269	# cookie processing	410	# cookie processing
270	if (my $jar = $arg{cookie_jar}) {	411	if (my $jar = $arg{cookie_jar}) {
271	%$jar = () if $jar->{version} < 1;	412	%$jar = () if $jar->{version} != 1;
272		413
273	my @cookie;	414	my @cookie;
274		415
275	while (my ($chost, $v) = each %$jar) {	416	while (my ($chost, $v) = each %$jar) {
		417	if ($chost =~ /^\./) {
276	next unless $chost eq substr $uhost, -length $chost;	418	next unless $chost eq substr $uhost, -length $chost;
277	next unless $chost =~ /^\./;	419	} elsif ($chost =~ /\./) {
		420	next unless $chost eq $uhost;
		421	} else {
		422	next;
		423	}
278		424
279	while (my ($cpath, $v) = each %$v) {	425	while (my ($cpath, $v) = each %$v) {
280	next unless $cpath eq substr $upath, 0, length $cpath;	426	next unless $cpath eq substr $upath, 0, length $cpath;
281		427
282	while (my ($k, $v) = each %$v) {	428	while (my ($k, $v) = each %$v) {
283	next if $scheme ne "https" && exists $v->{secure};	429	next if $uscheme ne "https" && exists $v->{secure};
		430	my $value = $v->{value};
		431	$value =~ s/([\\"])/\\$1/g;
284	push @cookie, "$k=$v->{value}";	432	push @cookie, "$k=\"$value\"";
285	}	433	}
286	}	434	}
287	}	435	}
288		436
289	$hdr{cookie} = join "; ", @cookie	437	$hdr{cookie} = join "; ", @cookie
290	if @cookie;	438	if @cookie;
291	}	439	}
292		440
293	my ($rhost, $rport, $rpath); # request host, port, path	441	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
294		442
295	if ($proxy) {	443	if ($proxy) {
296	($rhost, $rport, $scheme) = @$proxy;	444	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
297	$rpath = $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" && $rscheme eq "https";
298	} else {	451	} else {
299	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	452	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
300	$hdr{host} = $uhost;
301	}	453	}
302		454
		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"};
		458
303	$hdr{"content-length"} = length $arg{body};	459	$hdr{"content-length"} = length $arg{body}
		460	if length $arg{body} \|\| $method ne "GET";
304		461
305	my %state = (connect_guard => 1);	462	my %state = (connect_guard => 1);
306		463
307	_get_slot $uhost, sub {	464	_get_slot $uhost, sub {
308	$state{slot_guard} = shift;	465	$state{slot_guard} = shift;
309		466
310	return unless $state{connect_guard};	467	return unless $state{connect_guard};
311		468
312	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	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 {
313	$state{fh} = shift	476	$state{fh} = shift
314	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	477	or do {
315
316	delete $state{connect_guard}; # reduce memory usage, save a tree
317
318	# get handle
319	$state{handle} = new AnyEvent::Handle
320	fh => $state{fh},
321	($scheme eq "https" ? (tls => "connect") : ());
322
323	# limit the number of persistent connections
324	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
325	++$KA_COUNT{$_[1]};
326	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
327	$hdr{connection} = "keep-alive";
328	delete $hdr{connection}; # keep-alive not yet supported
329	} else {
330	delete $hdr{connection};
331	}
332
333	# (re-)configure handle
334	$state{handle}->timeout ($timeout);
335	$state{handle}->on_error (sub {
336	my $errno = "$!";	478	my $err = "$!";
337	%state = ();
338	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
339	});
340	$state{handle}->on_eof (sub {
341	%state = ();
342	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
343	});
344
345	# send request
346	$state{handle}->push_write (
347	"$method $rpath HTTP/1.0\015\012"
348	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
349	. "\015\012"
350	. (delete $arg{body})
351	);
352
353	%hdr = (); # reduce memory usage, save a kitten
354
355	# status line
356	$state{handle}->push_read (line => qr/\015?\012/, sub {
357	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
358	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
359
360	my %hdr = ( # response headers
361	HTTPVersion => "\x00$1",
362	Status => "\x00$2",
363	Reason => "\x00$3",
364	URL => "\x00$url"
365	);
366
367	# headers, could be optimized a bit
368	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
369	for ("$_[1]\012") {
370	# we support spaces in field names, as lotus domino
371	# creates them.
372	$hdr{lc $1} .= "\x00$2"
373	while /\G
374	([^:\000-\037]+):
375	[\011\040]*
376	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
377	\015?\012
378	/gxc;
379
380	/\G$/
381	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
382	}
383
384	substr $_, 0, 1, ""
385	for values %hdr;
386
387	my $finish = sub {
388	%state = ();	479	%state = ();
		480	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		481	};
389		482
390	# set-cookie processing	483	pop; # free memory, save a tree
391	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
392	for (split /\x00/, $hdr{"set-cookie"}) {
393	my ($cookie, @arg) = split /;\s*/;
394	my ($name, $value) = split /=/, $cookie, 2;
395	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
396
397	my $cdom = (delete $kv{domain}) \|\| $uhost;
398	my $cpath = (delete $kv{path}) \|\| "/";
399
400	$cdom =~ s/^.?/./; # make sure it starts with a "."
401		484
402	next if $cdom =~ /\.$/;	485	return unless delete $state{connect_guard};
403		486
404	# this is not rfc-like and not netscape-like. go figure.	487	# get handle
405	my $ndots = $cdom =~ y/.//;	488	$state{handle} = new AnyEvent::Handle
406	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	489	fh => $state{fh},
407		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	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		501	},
		502	;
		503
		504	# limit the number of persistent connections
		505	# keepalive not yet supported
		506	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		507	# ++$KA_COUNT{$_[1]};
		508	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		509	# --$KA_COUNT{$_[1]}
		510	# };
		511	# $hdr{connection} = "keep-alive";
		512	# } else {
		513	delete $hdr{connection};
		514	# }
		515
		516	$state{handle}->starttls ("connect") if $rscheme eq "https";
		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
		522	# send request
		523	$state{handle}->push_write (
		524	"$method $rpath HTTP/1.0\015\012"
		525	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		526	. "\015\012"
		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";
408	# store it	600	$redirect = 1;
409	$arg{cookie_jar}{version} = 1;	601	} elsif ($status == 307) {
410	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	602	$redirect = 1;
411	}	603	}
412	}	604	}
413		605
414	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {	606	my $finish = sub {
415	# microsoft and other assholes don't give a shit for following standards,	607	$state{handle}->destroy if $state{handle};
416	# try to support a common form of broken Location header.	608	%state = ();
417	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
418		609
419	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	610	# set-cookie processing
		611	if ($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);
420	} else {	686	} else {
421	$cb->($_[0], $_[1]);	687	# body handling, four different code paths
		688	# for want_body_handle, on_body (2x), normal (2x)
		689	# we might read too much here, but it does not matter yet (no pers. connections)
		690	if (!$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	$_[0]->on_read (sub { });
		735	}
		736	}
422	}	737	}
423	};	738	});
		739	};
424		740
425	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	741	# now handle proxy-CONNECT method
426	$finish->(undef, \%hdr);	742	if ($proxy && $uscheme eq "https") {
427	} else {	743	# oh dear, we have to wrap it into a connect request
428	if (exists $hdr{"content-length"}) {
429	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
430	# could cache persistent connection now
431	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
432	# but we don't, due to misdesigns, this is annoyingly complex
433	};
434		744
435	$finish->($_[1], \%hdr);	745	# maybe re-use $uauthority with patched port?
436	});	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;
437	} else {	754	} else {
438	# too bad, need to read until we get an error or EOF,
439	# no way to detect winged data.
440	$_[0]->on_error (sub {
441	$finish->($_[0]{rbuf}, \%hdr);
442	});	755	%state = ();
443	$_[0]->on_eof (undef);	756	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
444	$_[0]->on_read (sub { });
445	}	757	}
446	}	758	});
		759	} else {
		760	&$handle_actual_request;
447	});	761	}
		762
448	});	763	},
449	}, sub {	764	$arg{on_prepare} \|\| sub { $timeout }
450	$timeout
451	};	765	);
452	};	766	};
453		767
454	defined wantarray && AnyEvent::Util::guard { %state = () }	768	defined wantarray && AnyEvent::Util::guard { %state = () }
455	}	769	}
456		770
…		…
463	unshift @_, "HEAD";	777	unshift @_, "HEAD";
464	&http_request	778	&http_request
465	}	779	}
466		780
467	sub http_post($$@) {	781	sub http_post($$@) {
		782	my $url = shift;
468	unshift @_, "POST", "body";	783	unshift @_, "POST", $url, "body";
469	&http_request	784	&http_request
470	}	785	}
471		786
472	=back	787	=back
473		788
		789	=head2 DNS CACHING
		790
		791	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		792	the actual connection, which in turn uses AnyEvent::DNS to resolve
		793	hostnames. The latter is a simple stub resolver and does no caching
		794	on its own. If you want DNS caching, you currently have to provide
		795	your own default resolver (by storing a suitable resolver object in
		796	C<$AnyEvent::DNS::RESOLVER>).
		797
474	=head2 GLOBAL FUNCTIONS AND VARIABLES	798	=head2 GLOBAL FUNCTIONS AND VARIABLES
475		799
476	=over 4	800	=over 4
477		801
478	=item AnyEvent::HTTP::set_proxy "proxy-url"	802	=item AnyEvent::HTTP::set_proxy "proxy-url"
479		803
480	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
481	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>.
482		809
483	=item $AnyEvent::HTTP::MAX_RECURSE	810	=item $AnyEvent::HTTP::MAX_RECURSE
484		811
485	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>).
486		813
487	=item $AnyEvent::HTTP::USERAGENT	814	=item $AnyEvent::HTTP::USERAGENT
488		815
489	The default value for the C<User-Agent> header (the default is	816	The default value for the C<User-Agent> header (the default is
490	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	817	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
491		818
492	=item $AnyEvent::HTTP::MAX_PERSISTENT	819	=item $AnyEvent::HTTP::MAX_PER_HOST
493		820
494	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.
495		824
496	Not implemented currently.	825	The default value for this is C<4>, and it is highly advisable to not
497		826	increase it.
498	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
499
500	The maximum time to cache a persistent connection, in seconds (default: 2).
501
502	Not implemented currently.
503		827
504	=item $AnyEvent::HTTP::ACTIVE	828	=item $AnyEvent::HTTP::ACTIVE
505		829
506	The number of active connections. This is not the number of currently	830	The number of active connections. This is not the number of currently
507	running requests, but the number of currently open and non-idle TCP	831	running requests, but the number of currently open and non-idle TCP
…		…
510	=back	834	=back
511		835
512	=cut	836	=cut
513		837
514	sub set_proxy($) {	838	sub set_proxy($) {
		839	if (length $_[0]) {
515	$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	}
516	}	846	}
517		847
518	# initialise proxy from environment	848	# initialise proxy from environment
		849	eval {
519	set_proxy $ENV{http_proxy};	850	set_proxy $ENV{http_proxy};
		851	};
520		852
521	=head1 SEE ALSO	853	=head1 SEE ALSO
522		854
523	L<AnyEvent>.	855	L<AnyEvent>.
524		856
525	=head1 AUTHOR	857	=head1 AUTHOR
526		858
527	Marc Lehmann <schmorp@schmorp.de>	859	Marc Lehmann <schmorp@schmorp.de>
528	http://home.schmorp.de/	860	http://home.schmorp.de/
529		861
		862	With many thanks to Дмитрий Шалашов, who provided countless
		863	testcases and bugreports.
		864
530	=cut	865	=cut
531		866
532	1	867	1
533		868

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.19 by elmex, Mon Jun 9 13:02:13 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 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC