[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 1.53 by root, Sat Dec 5 15:37:07 2009 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 ();	48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	49	use AnyEvent::Handle ();
50		50
51	use base Exporter::;	51	use base Exporter::;
52		52
53	our $VERSION = '1.01';	53	our $VERSION = '1.44';
54		54
55	our @EXPORT = qw(http_get http_post http_head http_request);	55	our @EXPORT = qw(http_get http_post http_head http_request);
56		56
57	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;	58	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	59	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	60	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	61	our $TIMEOUT = 300;
62		62
63	# changing these is evil	63	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	64	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	65	our $MAX_PER_HOST = 4;
66		66
67	our $PROXY;	67	our $PROXY;
68	our $ACTIVE = 0;	68	our $ACTIVE = 0;
69		69
…		…
71	my %CO_SLOT; # number of open connections, and wait queue, per host	71	my %CO_SLOT; # number of open connections, and wait queue, per host
72		72
73	=item http_get $url, key => value..., $cb->($data, $headers)	73	=item http_get $url, key => value..., $cb->($data, $headers)
74		74
75	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
76	additional parameters.	76	additional parameters and the return value.
77		77
78	=item http_head $url, key => value..., $cb->($data, $headers)	78	=item http_head $url, key => value..., $cb->($data, $headers)
79		79
80	Executes an HTTP-HEAD request. See the http_request function for details on	80	Executes an HTTP-HEAD request. See the http_request function for details
81	additional parameters.	81	on additional parameters and the return value.
82		82
83	=item http_post $url, $body, key => value..., $cb->($data, $headers)	83	=item http_post $url, $body, key => value..., $cb->($data, $headers)
84		84
85	Executes an HTTP-POST request with a request body of C<$bod>. See the	85	Executes an HTTP-POST request with a request body of C<$body>. See the
86	http_request function for details on additional parameters.	86	http_request function for details on additional parameters and the return
		87	value.
87		88
88	=item http_request $method => $url, key => value..., $cb->($data, $headers)	89	=item http_request $method => $url, key => value..., $cb->($data, $headers)
89		90
90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	91	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	92	must be an absolute http or https URL.
92		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
93	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
95	response headers as second argument.	101	second argument.
96		102
97	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
98	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
99	C<Reason> contain the three parts of the HTTP Status-Line of the same	105	contain the three parts of the HTTP Status-Line of the same name. The
		106	pseudo-header C<URL> contains the original URL (which can differ from the
		107	requested URL when following redirects).
		108
100	name. If the server sends a header multiple lines, then their contents	109	If the server sends a header multiple times, then their contents will be
101	will be joined together with C<\x00>.	110	joined together with a comma (C<,>), as per the HTTP spec.
102		111
103	If an internal error occurs, such as not being able to resolve a hostname,	112	If an internal error occurs, such as not being able to resolve a hostname,
104	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
105	and the C<Reason> pseudo-header will contain an error message.	114	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		115	message.
106		116
107	A typical callback might look like this:	117	A typical callback might look like this:
108		118
109	sub {	119	sub {
110	my ($body, $hdr) = @_;	120	my ($body, $hdr) = @_;
…		…
128		138
129	=item headers => hashref	139	=item headers => hashref
130		140
131	The request headers to use. Currently, C<http_request> may provide its	141	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	142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
133	and will provide defaults for C<User-Agent:> and C<Referer:>.	143	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		144	suppressed by using C<undef> for these headers in which case they won't be
		145	sent at all).
134		146
135	=item timeout => $seconds	147	=item timeout => $seconds
136		148
137	The time-out to use for various stages - each connect attempt will reset	149	The time-out to use for various stages - each connect attempt will reset
138	the timeout, as will read or write activity. Default timeout is 5 minutes.	150	the timeout, as will read or write activity, i.e. this is not an overall
		151	timeout.
		152
		153	Default timeout is 5 minutes.
139		154
140	=item proxy => [$host, $port[, $scheme]] or undef	155	=item proxy => [$host, $port[, $scheme]] or undef
141		156
142	Use the given http proxy for all requests. If not specified, then the	157	Use the given http proxy for all requests. If not specified, then the
143	default proxy (as specified by C<$ENV{http_proxy}>) is used.	158	default proxy (as specified by C<$ENV{http_proxy}>) is used.
144		159
145	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	160	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
146	HTTPS.	161	HTTPS.
147		162
148	=item body => $string	163	=item body => $string
149		164
150	The request body, usually empty. Will be-sent as-is (future versions of	165	The request body, usually empty. Will be-sent as-is (future versions of
…		…
156	based on the original netscape specification.	171	based on the original netscape specification.
157		172
158	The C<$hash_ref> must be an (initially empty) hash reference which will	173	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	174	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	175	persistent storage with something like JSON or Storable, but this is not
161	recommended, as expire times are currently being ignored.	176	recommended, as expiry times are currently being ignored.
162		177
163	Note that this cookie implementation is not of very high quality, nor	178	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	179	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	180	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	181	cookie-using sites working. Cookies are a privacy disaster, do not use
167	them unless required to.	182	them unless required to.
		183
		184	=item tls_ctx => $scheme \| $tls_ctx
		185
		186	Specifies the AnyEvent::TLS context to be used for https connections. This
		187	parameter follows the same rules as the C<tls_ctx> parameter to
		188	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		189	C<high> can be specified, which give you a predefined low-security (no
		190	verification, highest compatibility) and high-security (CA and common-name
		191	verification) TLS context.
		192
		193	The default for this option is C<low>, which could be interpreted as "give
		194	me the page, no matter what".
		195
		196	=item on_prepare => $callback->($fh)
		197
		198	In rare cases you need to "tune" the socket before it is used to
		199	connect (for exmaple, to bind it on a given IP address). This parameter
		200	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		201	and behaves exactly the same way (e.g. it has to provide a
		202	timeout). See the description for the C<$prepare_cb> argument of
		203	C<AnyEvent::Socket::tcp_connect> for details.
		204
		205	=item on_header => $callback->($headers)
		206
		207	When specified, this callback will be called with the header hash as soon
		208	as headers have been successfully received from the remote server (not on
		209	locally-generated errors).
		210
		211	It has to return either true (in which case AnyEvent::HTTP will continue),
		212	or false, in which case AnyEvent::HTTP will cancel the download (and call
		213	the finish callback with an error code of C<598>).
		214
		215	This callback is useful, among other things, to quickly reject unwanted
		216	content, which, if it is supposed to be rare, can be faster than first
		217	doing a C<HEAD> request.
		218
		219	Example: cancel the request unless the content-type is "text/html".
		220
		221	on_header => sub {
		222	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		223	},
		224
		225	=item on_body => $callback->($partial_body, $headers)
		226
		227	When specified, all body data will be passed to this callback instead of
		228	to the completion callback. The completion callback will get the empty
		229	string instead of the body data.
		230
		231	It has to return either true (in which case AnyEvent::HTTP will continue),
		232	or false, in which case AnyEvent::HTTP will cancel the download (and call
		233	the completion callback with an error code of C<598>).
		234
		235	This callback is useful when the data is too large to be held in memory
		236	(so the callback writes it to a file) or when only some information should
		237	be extracted, or when the body should be processed incrementally.
		238
		239	It is usually preferred over doing your own body handling via
		240	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		241	only used to create a connection, C<want_body_handle> is the better
		242	alternative, as it allows you to install your own event handler, reducing
		243	resource usage.
		244
		245	=item want_body_handle => $enable
		246
		247	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		248	changes considerably: after parsing the headers, and instead of
		249	downloading the body (if any), the completion callback will be
		250	called. Instead of the C<$body> argument containing the body data, the
		251	callback will receive the L<AnyEvent::Handle> object associated with the
		252	connection. In error cases, C<undef> will be passed. When there is no body
		253	(e.g. status C<304>), the empty string will be passed.
		254
		255	The handle object might or might not be in TLS mode, might be connected to
		256	a proxy, be a persistent connection etc., and configured in unspecified
		257	ways. The user is responsible for this handle (it will not be used by this
		258	module anymore).
		259
		260	This is useful with some push-type services, where, after the initial
		261	headers, an interactive protocol is used (typical example would be the
		262	push-style twitter API which starts a JSON/XML stream).
		263
		264	If you think you need this, first have a look at C<on_body>, to see if
		265	that doesn't solve your problem in a better way.
168		266
169	=back	267	=back
170		268
171	Example: make a simple HTTP GET request for http://www.nethype.de/	269	Example: make a simple HTTP GET request for http://www.nethype.de/
172		270
…		…
185	my ($body, $hdr) = @_;	283	my ($body, $hdr) = @_;
186	use Data::Dumper;	284	use Data::Dumper;
187	print Dumper $hdr;	285	print Dumper $hdr;
188	}	286	}
189	;	287	;
		288
		289	Example: make another simple HTTP GET request, but immediately try to
		290	cancel it.
		291
		292	my $request = http_request GET => "http://www.nethype.de/", sub {
		293	my ($body, $hdr) = @_;
		294	print "$body\n";
		295	};
		296
		297	undef $request;
190		298
191	=cut	299	=cut
192		300
193	sub _slot_schedule;	301	sub _slot_schedule;
194	sub _slot_schedule($) {	302	sub _slot_schedule($) {
…		…
218	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
219		327
220	_slot_schedule $_[0];	328	_slot_schedule $_[0];
221	}	329	}
222		330
		331	our $qr_nl = qr{\015?\012};
		332	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		333
		334	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		335	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		336
223	sub http_request($$@) {	337	sub http_request($$@) {
224	my $cb = pop;	338	my $cb = pop;
225	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
226		340
227	my %hdr;	341	my %hdr;
		342
		343	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		344	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
228		345
229	$method = uc $method;	346	$method = uc $method;
230		347
231	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
232	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
233	$hdr{lc $k} = $v;	350	$hdr{lc $k} = $v;
234	}	351	}
235	}	352	}
236		353
237	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
238		355
239	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
240	if $recurse < 0;	357	if $recurse < 0;
241		358
242	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
243	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
244		361
245	$hdr{"user-agent"} \|\|= $USERAGENT;
246
247	my ($scheme, $authority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
248	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
249		364
250	$scheme = lc $scheme;	365	$uscheme = lc $uscheme;
251		366
252	my $uport = $scheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
253	: $scheme eq "https" ? 443	368	: $uscheme eq "https" ? 443
254	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	369	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });
255		370
256	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
257
258	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
259	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
260		373
261	my $uhost = $1;	374	my $uhost = $1;
262	$uport = $2 if defined $2;	375	$uport = $2 if defined $2;
263		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		378	unless exists $hdr{host};
		379
264	$uhost =~ s/^\[(.*)\]$/$1/;	380	$uhost =~ s/^\[(.*)\]$/$1/;
265	$upath .= "?$query" if length $query;	381	$upath .= "?$query" if length $query;
266		382
267	$upath =~ s%^/?%/%;	383	$upath =~ s%^/?%/%;
268		384
269	# cookie processing	385	# cookie processing
270	if (my $jar = $arg{cookie_jar}) {	386	if (my $jar = $arg{cookie_jar}) {
271	%$jar = () if $jar->{version} < 1;	387	%$jar = () if $jar->{version} != 1;
272		388
273	my @cookie;	389	my @cookie;
274		390
275	while (my ($chost, $v) = each %$jar) {	391	while (my ($chost, $v) = each %$jar) {
		392	if ($chost =~ /^\./) {
276	next unless $chost eq substr $uhost, -length $chost;	393	next unless $chost eq substr $uhost, -length $chost;
277	next unless $chost =~ /^\./;	394	} elsif ($chost =~ /\./) {
		395	next unless $chost eq $uhost;
		396	} else {
		397	next;
		398	}
278		399
279	while (my ($cpath, $v) = each %$v) {	400	while (my ($cpath, $v) = each %$v) {
280	next unless $cpath eq substr $upath, 0, length $cpath;	401	next unless $cpath eq substr $upath, 0, length $cpath;
281		402
282	while (my ($k, $v) = each %$v) {	403	while (my ($k, $v) = each %$v) {
283	next if $scheme ne "https" && exists $v->{secure};	404	next if $uscheme ne "https" && exists $v->{secure};
		405	my $value = $v->{value};
		406	$value =~ s/([\\"])/\\$1/g;
284	push @cookie, "$k=$v->{value}";	407	push @cookie, "$k=\"$value\"";
285	}	408	}
286	}	409	}
287	}	410	}
288		411
289	$hdr{cookie} = join "; ", @cookie	412	$hdr{cookie} = join "; ", @cookie
290	if @cookie;	413	if @cookie;
291	}	414	}
292		415
293	my ($rhost, $rport, $rpath); # request host, port, path	416	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
294		417
295	if ($proxy) {	418	if ($proxy) {
296	($rhost, $rport, $scheme) = @$proxy;	419	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
297	$rpath = $url;	420
		421	$rscheme = "http" unless defined $rscheme;
		422
		423	# don't support https requests over https-proxy transport,
		424	# can't be done with tls as spec'ed, unless you double-encrypt.
		425	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
298	} else {	426	} else {
299	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
300	$hdr{host} = $uhost;
301	}	428	}
302		429
		430	# leave out fragment and query string, just a heuristic
		431	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		432	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		433
303	$hdr{"content-length"} = length $arg{body};	434	$hdr{"content-length"} = length $arg{body}
		435	if length $arg{body} \|\| $method ne "GET";
304		436
305	my %state = (connect_guard => 1);	437	my %state = (connect_guard => 1);
306		438
307	_get_slot $uhost, sub {	439	_get_slot $uhost, sub {
308	$state{slot_guard} = shift;	440	$state{slot_guard} = shift;
309		441
310	return unless $state{connect_guard};	442	return unless $state{connect_guard};
311		443
312	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
313	$state{fh} = shift	445	$state{fh} = shift
		446	or do {
		447	my $err = "$!";
		448	%state = ();
314	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		450	};
315		451
316	delete $state{connect_guard}; # reduce memory usage, save a tree	452	pop; # free memory, save a tree
		453
		454	return unless delete $state{connect_guard};
317		455
318	# get handle	456	# get handle
319	$state{handle} = new AnyEvent::Handle	457	$state{handle} = new AnyEvent::Handle
320	fh => $state{fh},	458	fh => $state{fh},
321	($scheme eq "https" ? (tls => "connect") : ());	459	timeout => $timeout,
		460	peername => $rhost,
		461	tls_ctx => $arg{tls_ctx};
322		462
323	# limit the number of persistent connections	463	# limit the number of persistent connections
		464	# keepalive not yet supported
324	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
325	++$KA_COUNT{$_[1]};	466	++$KA_COUNT{$_[1]};
326	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	467	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		468	--$KA_COUNT{$_[1]}
		469	};
327	$hdr{connection} = "keep-alive";	470	$hdr{connection} = "keep-alive";
328	delete $hdr{connection}; # keep-alive not yet supported
329	} else {	471	} else {
330	delete $hdr{connection};	472	delete $hdr{connection};
331	}	473	}
332		474
333	# (re-)configure handle	475	# (re-)configure handle
334	$state{handle}->timeout ($timeout);
335	$state{handle}->on_error (sub {	476	$state{handle}->on_error (sub {
336	my $errno = "$!";
337	%state = ();	477	%state = ();
338	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });	478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
339	});	479	});
340	$state{handle}->on_eof (sub {	480	$state{handle}->on_eof (sub {
341	%state = ();	481	%state = ();
342	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });	482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
343	});	483	});
344		484
		485	$state{handle}->starttls ("connect") if $rscheme eq "https";
		486
		487	# handle actual, non-tunneled, request
		488	my $handle_actual_request = sub {
		489	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		490
345	# send request	491	# send request
346	$state{handle}->push_write (	492	$state{handle}->push_write (
347	"$method $rpath HTTP/1.0\015\012"	493	"$method $rpath HTTP/1.0\015\012"
348	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
349	. "\015\012"	495	. "\015\012"
350	. (delete $arg{body})	496	. (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	);	497	);
366		498
		499	%hdr = (); # reduce memory usage, save a kitten
		500
		501	# status line
		502	$state{handle}->push_read (line => $qr_nl, sub {
		503	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		504	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
		505
		506	my %hdr = ( # response headers
		507	HTTPVersion => ",$1",
		508	Status => ",$2",
		509	Reason => ",$3",
		510	URL => ",$url"
		511	);
		512
367	# headers, could be optimized a bit	513	# headers, could be optimized a bit
368	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	514	$state{handle}->unshift_read (line => $qr_nlnl, sub {
369	for ("$_[1]\012") {	515	for ("$_[1]") {
370	# we support spaces in field names, as lotus domino	516	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
371	# creates them.	517
		518	# things seen, not parsed:
		519	# p3pP="NON CUR OTPi OUR NOR UNI"
		520
372	$hdr{lc $1} .= "\x00$2"	521	$hdr{lc $1} .= ",$2"
373	while /\G	522	while /\G
374	([^:\000-\037]+):	523	([^:\000-\037]*):
375	[\011\040]*	524	[\011\040]*
376	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	525	((?: [^\012]+ \| \012[\011\040] )*)
377	\015?\012	526	\012
378	/gxc;	527	/gxc;
379		528
380	/\G$/	529	/\G$/
381	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	530	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
382	}	531	}
383		532
384	substr $_, 0, 1, ""	533	substr $_, 0, 1, ""
385	for values %hdr;	534	for values %hdr;
386		535
387	my $finish = sub {	536	# redirect handling
388	%state = ();	537	# microsoft and other shitheads don't give a shit for following standards,
		538	# try to support some common forms of broken Location headers.
		539	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		540	$hdr{location} =~ s/^\.\/+//;
389		541
390	# set-cookie processing	542	my $url = "$rscheme://$uhost:$uport";
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		543
402	next if $cdom =~ /\.$/;	544	unless ($hdr{location} =~ s/^\///) {
403		545	$url .= $upath;
404	# this is not rfc-like and not netscape-like. go figure.	546	$url =~ s/\/[^\/]*$//;
405	my $ndots = $cdom =~ y/.//;	547	}
406	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	548
407		549	$hdr{location} = "$url/$hdr{location}";
		550	}
		551
		552	my $redirect;
		553
		554	if ($recurse) {
		555	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
		556	# apparently, mozilla et al. just change POST to GET here
		557	# more research is needed before we do the same
408	# store it	558	$redirect = 1;
409	$arg{cookie_jar}{version} = 1;	559	} elsif ($hdr{Status} == 303) {
410	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	560	# even http/1.1 is unclear on how to mutate the method
		561	$method = "GET" unless $method eq "HEAD";
		562	$redirect = 1;
		563	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		564	$redirect = 1;
411	}	565	}
412	}	566	}
413		567
414	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {	568	my $finish = sub {
415	# microsoft and other assholes don't give a shit for following standards,	569	$state{handle}->destroy if $state{handle};
416	# try to support a common form of broken Location header.	570	%state = ();
417	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
418		571
		572	# set-cookie processing
		573	if ($arg{cookie_jar}) {
		574	for ($_[1]{"set-cookie"}) {
		575	# parse NAME=VALUE
		576	my @kv;
		577
		578	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		579	my $name = $1;
		580	my $value = $3;
		581
		582	unless ($value) {
		583	$value = $2;
		584	$value =~ s/\\(.)/$1/gs;
		585	}
		586
		587	push @kv, $name => $value;
		588
		589	last unless /\G\s*;/gc;
		590	}
		591
		592	last unless @kv;
		593
		594	my $name = shift @kv;
		595	my %kv = (value => shift @kv, @kv);
		596
		597	my $cdom;
		598	my $cpath = (delete $kv{path}) \|\| "/";
		599
		600	if (exists $kv{domain}) {
		601	$cdom = delete $kv{domain};
		602
		603	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		604
		605	next if $cdom =~ /\.$/;
		606
		607	# this is not rfc-like and not netscape-like. go figure.
		608	my $ndots = $cdom =~ y/.//;
		609	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		610	} else {
		611	$cdom = $uhost;
		612	}
		613
		614	# store it
		615	$arg{cookie_jar}{version} = 1;
		616	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		617
		618	redo if /\G\s*,/gc;
		619	}
		620	}
		621
		622	if ($redirect && exists $hdr{location}) {
		623	# we ignore any errors, as it is very common to receive
		624	# Content-Length != 0 but no actual body
		625	# we also access %hdr, as $_[1] might be an erro
419	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	626	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
		627	} else {
		628	$cb->($_[0], $_[1]);
		629	}
		630	};
		631
		632	my $len = $hdr{"content-length"};
		633
		634	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		635	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
		636	} elsif (
		637	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		638	or $method eq "HEAD"
		639	or (defined $len && !$len)
		640	) {
		641	# no body
		642	$finish->("", \%hdr);
420	} else {	643	} else {
421	$cb->($_[0], $_[1]);	644	# body handling, four different code paths
		645	# for want_body_handle, on_body (2x), normal (2x)
		646	# we might read too much here, but it does not matter yet (no pers. connections)
		647	if (!$redirect && $arg{want_body_handle}) {
		648	$_[0]->on_eof (undef);
		649	$_[0]->on_error (undef);
		650	$_[0]->on_read (undef);
		651
		652	$finish->(delete $state{handle}, \%hdr);
		653
		654	} elsif ($arg{on_body}) {
		655	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		656	if ($len) {
		657	$_[0]->on_eof (undef);
		658	$_[0]->on_read (sub {
		659	$len -= length $_[0]{rbuf};
		660
		661	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		662	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		663
		664	$len > 0
		665	or $finish->("", \%hdr);
		666	});
		667	} else {
		668	$_[0]->on_eof (sub {
		669	$finish->("", \%hdr);
		670	});
		671	$_[0]->on_read (sub {
		672	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		673	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		674	});
		675	}
		676	} else {
		677	$_[0]->on_eof (undef);
		678
		679	if ($len) {
		680	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		681	$_[0]->on_read (sub {
		682	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		683	if $len <= length $_[0]{rbuf};
		684	});
		685	} else {
		686	$_[0]->on_error (sub {
		687	$! == Errno::EPIPE \|\| !$!
		688	? $finish->(delete $_[0]{rbuf}, \%hdr)
		689	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
		690	});
		691	$_[0]->on_read (sub { });
		692	}
		693	}
422	}	694	}
423	};	695	});
		696	});
		697	};
424		698
425	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	699	# now handle proxy-CONNECT method
426	$finish->(undef, \%hdr);	700	if ($proxy && $uscheme eq "https") {
		701	# oh dear, we have to wrap it into a connect request
		702
		703	# maybe re-use $uauthority with patched port?
		704	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		705	$state{handle}->push_read (line => $qr_nlnl, sub {
		706	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		707	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
		708
		709	if ($2 == 200) {
		710	$rpath = $upath;
		711	&$handle_actual_request;
427	} else {	712	} else {
428	if (exists $hdr{"content-length"}) {	713	%state = ();
429	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	714	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
430	# could cache persistent connection now
431	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
432	# but we don't, due to misdesigns, this is annoyingly complex
433	};
434
435	$finish->($_[1], \%hdr);
436	});
437	} 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	});
443	$_[0]->on_eof (undef);
444	$_[0]->on_read (sub { });
445	}
446	}	715	}
447	});	716	});
		717	} else {
		718	&$handle_actual_request;
448	});	719	}
449	}, sub {	720
450	$timeout	721	}, $arg{on_prepare} \|\| sub { $timeout };
451	};
452	};	722	};
453		723
454	defined wantarray && AnyEvent::Util::guard { %state = () }	724	defined wantarray && AnyEvent::Util::guard { %state = () }
455	}	725	}
456		726
…		…
463	unshift @_, "HEAD";	733	unshift @_, "HEAD";
464	&http_request	734	&http_request
465	}	735	}
466		736
467	sub http_post($$@) {	737	sub http_post($$@) {
		738	my $url = shift;
468	unshift @_, "POST", "body";	739	unshift @_, "POST", $url, "body";
469	&http_request	740	&http_request
470	}	741	}
471		742
472	=back	743	=back
473		744
…		…
476	=over 4	747	=over 4
477		748
478	=item AnyEvent::HTTP::set_proxy "proxy-url"	749	=item AnyEvent::HTTP::set_proxy "proxy-url"
479		750
480	Sets the default proxy server to use. The proxy-url must begin with a	751	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:...>).	752	string of the form C<http://host:port> (optionally C<https:...>), croaks
		753	otherwise.
		754
		755	To clear an already-set proxy, use C<undef>.
482		756
483	=item $AnyEvent::HTTP::MAX_RECURSE	757	=item $AnyEvent::HTTP::MAX_RECURSE
484		758
485	The default value for the C<recurse> request parameter (default: C<10>).	759	The default value for the C<recurse> request parameter (default: C<10>).
486		760
487	=item $AnyEvent::HTTP::USERAGENT	761	=item $AnyEvent::HTTP::USERAGENT
488		762
489	The default value for the C<User-Agent> header (the default is	763	The default value for the C<User-Agent> header (the default is
490	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	764	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
491		765
492	=item $AnyEvent::HTTP::MAX_PERSISTENT	766	=item $AnyEvent::HTTP::MAX_PER_HOST
493		767
494	The maximum number of persistent connections to keep open (default: 8).	768	The maximum number of concurrent connections to the same host (identified
		769	by the hostname). If the limit is exceeded, then the additional requests
		770	are queued until previous connections are closed.
495		771
496	Not implemented currently.	772	The default value for this is C<4>, and it is highly advisable to not
497		773	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		774
504	=item $AnyEvent::HTTP::ACTIVE	775	=item $AnyEvent::HTTP::ACTIVE
505		776
506	The number of active connections. This is not the number of currently	777	The number of active connections. This is not the number of currently
507	running requests, but the number of currently open and non-idle TCP	778	running requests, but the number of currently open and non-idle TCP
…		…
510	=back	781	=back
511		782
512	=cut	783	=cut
513		784
514	sub set_proxy($) {	785	sub set_proxy($) {
		786	if (length $_[0]) {
515	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	787	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		788	or Carp::croak "$_[0]: invalid proxy URL";
		789	$PROXY = [$2, $3 \|\| 3128, $1]
		790	} else {
		791	undef $PROXY;
		792	}
516	}	793	}
517		794
518	# initialise proxy from environment	795	# initialise proxy from environment
		796	eval {
519	set_proxy $ENV{http_proxy};	797	set_proxy $ENV{http_proxy};
		798	};
520		799
521	=head1 SEE ALSO	800	=head1 SEE ALSO
522		801
523	L<AnyEvent>.	802	L<AnyEvent>.
524		803
525	=head1 AUTHOR	804	=head1 AUTHOR
526		805
527	Marc Lehmann <schmorp@schmorp.de>	806	Marc Lehmann <schmorp@schmorp.de>
528	http://home.schmorp.de/	807	http://home.schmorp.de/
529		808
		809	With many thanks to Дмитрий Шалашов, who provided countless
		810	testcases and bugreports.
		811
530	=cut	812	=cut
531		813
532	1	814	1
533		815

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 1.53 by root, Sat Dec 5 15:37:07 2009 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 1.53 by root, Sat Dec 5 15:37:07 2009 UTC