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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.23 by root, Wed Jul 2 01:23:41 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 = '1.03';	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<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	91	must be an absolute http or https URL.
92		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
93	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
95	response headers as second argument.	100	second argument.
96		101
97	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
98	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
99	contain the three parts of the HTTP Status-Line of the same name. The	105	three parts of the HTTP Status-Line of the same name.
		106
100	pseudo-header C<URL> contains the original URL (which can differ from the	107	The pseudo-header C<URL> contains the actual URL (which can differ from
101	requested URL when following redirects).	108	the requested URL when following redirects - for example, you might get
		109	an error that your URL scheme is not supported even though your URL is a
		110	valid http URL because it redirected to an ftp URL, in which case you can
		111	look at the URL pseudo header).
102		112
		113	The pseudo-header C<Redirect> only exists when the request was a result
		114	of an internal redirect. In that case it is an array reference with
		115	the C<($data, $headers)> from the redirect response. Note that this
		116	response could in turn be the result of a redirect itself, and C<<
		117	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		118	response, and so on.
		119
103	If the server sends a header multiple lines, then their contents will be	120	If the server sends a header multiple times, then their contents will be
104	joined together with C<\x00>.	121	joined together with a comma (C<,>), as per the HTTP spec.
105		122
106	If an internal error occurs, such as not being able to resolve a hostname,	123	If an internal error occurs, such as not being able to resolve a hostname,
107	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	124	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
108	and the C<Reason> pseudo-header will contain an error message.	125	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		126	message.
109		127
110	A typical callback might look like this:	128	A typical callback might look like this:
111		129
112	sub {	130	sub {
113	my ($body, $hdr) = @_;	131	my ($body, $hdr) = @_;
…		…
131		149
132	=item headers => hashref	150	=item headers => hashref
133		151
134	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
135	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
136	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).
137		157
138	=item timeout => $seconds	158	=item timeout => $seconds
139		159
140	The time-out to use for various stages - each connect attempt will reset	160	The time-out to use for various stages - each connect attempt will reset
141	the timeout, as will read or write activity. Default timeout is 5 minutes.	161	the timeout, as will read or write activity, i.e. this is not an overall
		162	timeout.
		163
		164	Default timeout is 5 minutes.
142		165
143	=item proxy => [$host, $port[, $scheme]] or undef	166	=item proxy => [$host, $port[, $scheme]] or undef
144		167
145	Use the given http proxy for all requests. If not specified, then the	168	Use the given http proxy for all requests. If not specified, then the
146	default proxy (as specified by C<$ENV{http_proxy}>) is used.	169	default proxy (as specified by C<$ENV{http_proxy}>) is used.
147		170
148	C<$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
149	HTTPS.	172	HTTPS.
150		173
151	=item body => $string	174	=item body => $string
152		175
153	The request body, usually empty. Will be-sent as-is (future versions of	176	The request body, usually empty. Will be-sent as-is (future versions of
…		…
159	based on the original netscape specification.	182	based on the original netscape specification.
160		183
161	The C<$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
162	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
163	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
164	recommended, as expire times are currently being ignored.	187	recommended, as expiry times are currently being ignored.
165		188
166	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
167	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
168	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
169	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
170	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.
171		288
172	=back	289	=back
173		290
174	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/
175		292
…		…
188	my ($body, $hdr) = @_;	305	my ($body, $hdr) = @_;
189	use Data::Dumper;	306	use Data::Dumper;
190	print Dumper $hdr;	307	print Dumper $hdr;
191	}	308	}
192	;	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 $request;
193		320
194	=cut	321	=cut
195		322
196	sub _slot_schedule;	323	sub _slot_schedule;
197	sub _slot_schedule($) {	324	sub _slot_schedule($) {
…		…
221	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	348	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
222		349
223	_slot_schedule $_[0];	350	_slot_schedule $_[0];
224	}	351	}
225		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
226	sub http_request($$@) {	358	sub http_request($$@) {
227	my $cb = pop;	359	my $cb = pop;
228	my ($method, $url, %arg) = @_;	360	my ($method, $url, %arg) = @_;
229		361
230	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";
231		366
232	$method = uc $method;	367	$method = uc $method;
233		368
234	if (my $hdr = $arg{headers}) {	369	if (my $hdr = $arg{headers}) {
235	while (my ($k, $v) = each %$hdr) {	370	while (my ($k, $v) = each %$hdr) {
236	$hdr{lc $k} = $v;	371	$hdr{lc $k} = $v;
237	}	372	}
238	}	373	}
239		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
240	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	379	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
241		380
242	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	381	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
243	if $recurse < 0;	382	if $recurse < 0;
244		383
245	my $proxy = $arg{proxy} \|\| $PROXY;	384	my $proxy = $arg{proxy} \|\| $PROXY;
246	my $timeout = $arg{timeout} \|\| $TIMEOUT;	385	my $timeout = $arg{timeout} \|\| $TIMEOUT;
247		386
248	$hdr{"user-agent"} \|\|= $USERAGENT;
249
250	my ($scheme, $authority, $upath, $query, $fragment) =	387	my ($uscheme, $uauthority, $upath, $query, $fragment) =
251	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	388	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
252		389
253	$scheme = lc $scheme;	390	$uscheme = lc $uscheme;
254		391
255	my $uport = $scheme eq "http" ? 80	392	my $uport = $uscheme eq "http" ? 80
256	: $scheme eq "https" ? 443	393	: $uscheme eq "https" ? 443
257	: 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 });
258		395
259	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
260
261	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	396	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
262	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	397	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
263		398
264	my $uhost = $1;	399	my $uhost = $1;
265	$uport = $2 if defined $2;	400	$uport = $2 if defined $2;
266		401
		402	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		403	unless exists $hdr{host};
		404
267	$uhost =~ s/^\[(.*)\]$/$1/;	405	$uhost =~ s/^\[(.*)\]$/$1/;
268	$upath .= "?$query" if length $query;	406	$upath .= $query if length $query;
269		407
270	$upath =~ s%^/?%/%;	408	$upath =~ s%^/?%/%;
271		409
272	# cookie processing	410	# cookie processing
273	if (my $jar = $arg{cookie_jar}) {	411	if (my $jar = $arg{cookie_jar}) {
274	%$jar = () if $jar->{version} < 1;	412	%$jar = () if $jar->{version} != 1;
275		413
276	my @cookie;	414	my @cookie;
277		415
278	while (my ($chost, $v) = each %$jar) {	416	while (my ($chost, $v) = each %$jar) {
		417	if ($chost =~ /^\./) {
279	next unless $chost eq substr $uhost, -length $chost;	418	next unless $chost eq substr $uhost, -length $chost;
280	next unless $chost =~ /^\./;	419	} elsif ($chost =~ /\./) {
		420	next unless $chost eq $uhost;
		421	} else {
		422	next;
		423	}
281		424
282	while (my ($cpath, $v) = each %$v) {	425	while (my ($cpath, $v) = each %$v) {
283	next unless $cpath eq substr $upath, 0, length $cpath;	426	next unless $cpath eq substr $upath, 0, length $cpath;
284		427
285	while (my ($k, $v) = each %$v) {	428	while (my ($k, $v) = each %$v) {
286	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;
287	push @cookie, "$k=$v->{value}";	432	push @cookie, "$k=\"$value\"";
288	}	433	}
289	}	434	}
290	}	435	}
291		436
292	$hdr{cookie} = join "; ", @cookie	437	$hdr{cookie} = join "; ", @cookie
293	if @cookie;	438	if @cookie;
294	}	439	}
295		440
296	my ($rhost, $rport, $rpath); # request host, port, path	441	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
297		442
298	if ($proxy) {	443	if ($proxy) {
299	($rhost, $rport, $scheme) = @$proxy;	444	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
300	$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" && $rscheme eq "https";
301	} else {	451	} else {
302	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	452	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
303	$hdr{host} = $uhost;
304	}	453	}
305		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
306	$hdr{"content-length"} = length $arg{body};	459	$hdr{"content-length"} = length $arg{body}
		460	if length $arg{body} \|\| $method ne "GET";
307		461
308	my %state = (connect_guard => 1);	462	my %state = (connect_guard => 1);
309		463
310	_get_slot $uhost, sub {	464	_get_slot $uhost, sub {
311	$state{slot_guard} = shift;	465	$state{slot_guard} = shift;
312		466
313	return unless $state{connect_guard};	467	return unless $state{connect_guard};
314		468
315	$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 {
316	$state{fh} = shift	476	$state{fh} = shift
317	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	477	or do {
318
319	delete $state{connect_guard}; # reduce memory usage, save a tree
320
321	# get handle
322	$state{handle} = new AnyEvent::Handle
323	fh => $state{fh},
324	($scheme eq "https" ? (tls => "connect") : ());
325
326	# limit the number of persistent connections
327	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
328	++$KA_COUNT{$_[1]};
329	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
330	$hdr{connection} = "keep-alive";
331	delete $hdr{connection}; # keep-alive not yet supported
332	} else {
333	delete $hdr{connection};
334	}
335
336	# (re-)configure handle
337	$state{handle}->timeout ($timeout);
338	$state{handle}->on_error (sub {
339	my $errno = "$!";	478	my $err = "$!";
340	%state = ();
341	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
342	});
343	$state{handle}->on_eof (sub {
344	%state = ();
345	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
346	});
347
348	# send request
349	$state{handle}->push_write (
350	"$method $rpath HTTP/1.0\015\012"
351	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
352	. "\015\012"
353	. (delete $arg{body})
354	);
355
356	%hdr = (); # reduce memory usage, save a kitten
357
358	# status line
359	$state{handle}->push_read (line => qr/\015?\012/, sub {
360	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
361	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
362
363	my %hdr = ( # response headers
364	HTTPVersion => "\x00$1",
365	Status => "\x00$2",
366	Reason => "\x00$3",
367	URL => "\x00$url"
368	);
369
370	# headers, could be optimized a bit
371	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
372	for ("$_[1]\012") {
373	# we support spaces in field names, as lotus domino
374	# creates them.
375	$hdr{lc $1} .= "\x00$2"
376	while /\G
377	([^:\000-\037]+):
378	[\011\040]*
379	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
380	\015?\012
381	/gxc;
382
383	/\G$/
384	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
385	}
386
387	substr $_, 0, 1, ""
388	for values %hdr;
389
390	my $finish = sub {
391	%state = ();	479	%state = ();
		480	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		481	};
392		482
393	# set-cookie processing	483	pop; # free memory, save a tree
394	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
395	for (split /\x00/, $hdr{"set-cookie"}) {
396	my ($cookie, @arg) = split /;\s*/;
397	my ($name, $value) = split /=/, $cookie, 2;
398	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
399
400	my $cdom = (delete $kv{domain}) \|\| $uhost;
401	my $cpath = (delete $kv{path}) \|\| "/";
402
403	$cdom =~ s/^.?/./; # make sure it starts with a "."
404		484
405	next if $cdom =~ /\.$/;	485	return unless delete $state{connect_guard};
406		486
407	# this is not rfc-like and not netscape-like. go figure.	487	# get handle
408	my $ndots = $cdom =~ y/.//;	488	$state{handle} = new AnyEvent::Handle
409	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	489	fh => $state{fh},
410		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";
411	# store it	600	$redirect = 1;
412	$arg{cookie_jar}{version} = 1;	601	} elsif ($status == 307) {
413	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	602	$redirect = 1;
414	}	603	}
415	}	604	}
416		605
417	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {	606	my $finish = sub {
418	# microsoft and other assholes don't give a shit for following standards,	607	$state{handle}->destroy if $state{handle};
419	# try to support a common form of broken Location header.	608	%state = ();
420	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
421		609
422	# apparently, mozilla et al. just change POST to GET here	610	# set-cookie processing
423	# more research is needed before we do the same	611	if ($arg{cookie_jar}) {
		612	for ($_[1]{"set-cookie"}) {
		613	# parse NAME=VALUE
		614	my @kv;
424		615
425	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	616	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
426	} elsif ($_[1]{Status} == 303 && $recurse) {	617	my $name = $1;
427	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;	618	my $value = $3;
428		619
429	http_request (GET => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	620	unless ($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);
430	} else {	686	} else {
431	$cb->($_[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	$_[0]->on_read (sub { });
		735	}
		736	}
432	}	737	}
433	};	738	});
		739	};
434		740
435	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	741	# now handle proxy-CONNECT method
436	$finish->(undef, \%hdr);	742	if ($proxy && $uscheme eq "https") {
437	} else {	743	# oh dear, we have to wrap it into a connect request
438	if (exists $hdr{"content-length"}) {
439	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
440	# could cache persistent connection now
441	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
442	# but we don't, due to misdesigns, this is annoyingly complex
443	};
444		744
445	$finish->($_[1], \%hdr);	745	# maybe re-use $uauthority with patched port?
446	});	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;
447	} else {	754	} else {
448	# too bad, need to read until we get an error or EOF,
449	# no way to detect winged data.
450	$_[0]->on_error (sub {
451	$finish->($_[0]{rbuf}, \%hdr);
452	});	755	%state = ();
453	$_[0]->on_eof (undef);	756	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
454	$_[0]->on_read (sub { });
455	}	757	}
456	}	758	});
		759	} else {
		760	&$handle_actual_request;
457	});	761	}
		762
458	});	763	},
459	}, sub {	764	$arg{on_prepare} \|\| sub { $timeout }
460	$timeout
461	};	765	);
462	};	766	};
463		767
464	defined wantarray && AnyEvent::Util::guard { %state = () }	768	defined wantarray && AnyEvent::Util::guard { %state = () }
465	}	769	}
466		770
…		…
480	&http_request	784	&http_request
481	}	785	}
482		786
483	=back	787	=back
484		788
		789	=head2 DNS CACHING
		790
		791	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		792	the actual connection, which in turn uses AnyEvent::DNS to resolve
		793	hostnames. The latter is a simple stub resolver and does no caching
		794	on its own. If you want DNS caching, you currently have to provide
		795	your own default resolver (by storing a suitable resolver object in
		796	C<$AnyEvent::DNS::RESOLVER>).
		797
485	=head2 GLOBAL FUNCTIONS AND VARIABLES	798	=head2 GLOBAL FUNCTIONS AND VARIABLES
486		799
487	=over 4	800	=over 4
488		801
489	=item AnyEvent::HTTP::set_proxy "proxy-url"	802	=item AnyEvent::HTTP::set_proxy "proxy-url"
490		803
491	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
492	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>.
493		809
494	=item $AnyEvent::HTTP::MAX_RECURSE	810	=item $AnyEvent::HTTP::MAX_RECURSE
495		811
496	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>).
497		813
498	=item $AnyEvent::HTTP::USERAGENT	814	=item $AnyEvent::HTTP::USERAGENT
499		815
500	The default value for the C<User-Agent> header (the default is	816	The default value for the C<User-Agent> header (the default is
501	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	817	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
502		818
503	=item $AnyEvent::HTTP::MAX_PERSISTENT	819	=item $AnyEvent::HTTP::MAX_PER_HOST
504		820
505	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.
506		824
507	Not implemented currently.	825	The default value for this is C<4>, and it is highly advisable to not
508		826	increase it.
509	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
510
511	The maximum time to cache a persistent connection, in seconds (default: 2).
512
513	Not implemented currently.
514		827
515	=item $AnyEvent::HTTP::ACTIVE	828	=item $AnyEvent::HTTP::ACTIVE
516		829
517	The number of active connections. This is not the number of currently	830	The number of active connections. This is not the number of currently
518	running requests, but the number of currently open and non-idle TCP	831	running requests, but the number of currently open and non-idle TCP
…		…
521	=back	834	=back
522		835
523	=cut	836	=cut
524		837
525	sub set_proxy($) {	838	sub set_proxy($) {
		839	if (length $_[0]) {
526	$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	}
527	}	846	}
528		847
529	# initialise proxy from environment	848	# initialise proxy from environment
		849	eval {
530	set_proxy $ENV{http_proxy};	850	set_proxy $ENV{http_proxy};
		851	};
531		852
532	=head1 SEE ALSO	853	=head1 SEE ALSO
533		854
534	L<AnyEvent>.	855	L<AnyEvent>.
535		856
536	=head1 AUTHOR	857	=head1 AUTHOR
537		858
538	Marc Lehmann <schmorp@schmorp.de>	859	Marc Lehmann <schmorp@schmorp.de>
539	http://home.schmorp.de/	860	http://home.schmorp.de/
540		861
		862	With many thanks to Дмитрий Шалашов, who provided countless
		863	testcases and bugreports.
		864
541	=cut	865	=cut
542		866
543	1	867	1
544		868

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.23 by root, Wed Jul 2 01:23:41 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 1.23 by root, Wed Jul 2 01:23:41 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC