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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.25 by root, Mon Jul 21 05:42:07 2008 UTC vs.
Revision 1.58 by root, Sun Nov 14 20:23:00 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 ();	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 = '1.03';	53	our $VERSION = '1.46';
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<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	92	must be an absolute http or https URL.
92		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callback is called, the request will be cancelled.
		98
93	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
95	response headers as second argument.	101	second argument.
96		102
97	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
98	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	104	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		105	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
99	contain the three parts of the HTTP Status-Line of the same name. The	106	three parts of the HTTP Status-Line of the same name.
		107
100	pseudo-header C<URL> contains the original URL (which can differ from the	108	The pseudo-header C<URL> contains the actual URL (which can differ from
101	requested URL when following redirects).	109	the requested URL when following redirects - for example, you might get
		110	an error that your URL scheme is not supported even though your URL is a
		111	valid http URL because it redirected to an ftp URL, in which case you can
		112	look at the URL pseudo header).
102		113
		114	The pseudo-header C<Redirect> only exists when the request was a result
		115	of an internal redirect. In that case it is an array reference with
		116	the C<($data, $headers)> from the redirect response. Note that this
		117	response could in turn be the result of a redirect itself, and C<<
		118	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		119	response, and so on.
		120
103	If the server sends a header multiple lines, then their contents will be	121	If the server sends a header multiple times, then their contents will be
104	joined together with C<\x00>.	122	joined together with a comma (C<,>), as per the HTTP spec.
105		123
106	If an internal error occurs, such as not being able to resolve a hostname,	124	If an internal error occurs, such as not being able to resolve a hostname,
107	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	125	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
108	and the C<Reason> pseudo-header will contain an error message.	126	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		127	message.
109		128
110	A typical callback might look like this:	129	A typical callback might look like this:
111		130
112	sub {	131	sub {
113	my ($body, $hdr) = @_;	132	my ($body, $hdr) = @_;
…		…
131		150
132	=item headers => hashref	151	=item headers => hashref
133		152
134	The request headers to use. Currently, C<http_request> may provide its	153	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	154	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
136	and will provide defaults for C<User-Agent:> and C<Referer:>.	155	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		156	suppressed by using C<undef> for these headers in which case they won't be
		157	sent at all).
137		158
138	=item timeout => $seconds	159	=item timeout => $seconds
139		160
140	The time-out to use for various stages - each connect attempt will reset	161	The time-out to use for various stages - each connect attempt will reset
141	the timeout, as will read or write activity. Default timeout is 5 minutes.	162	the timeout, as will read or write activity, i.e. this is not an overall
		163	timeout.
		164
		165	Default timeout is 5 minutes.
142		166
143	=item proxy => [$host, $port[, $scheme]] or undef	167	=item proxy => [$host, $port[, $scheme]] or undef
144		168
145	Use the given http proxy for all requests. If not specified, then the	169	Use the given http proxy for all requests. If not specified, then the
146	default proxy (as specified by C<$ENV{http_proxy}>) is used.	170	default proxy (as specified by C<$ENV{http_proxy}>) is used.
147		171
148	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	172	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
149	HTTPS.	173	HTTPS.
150		174
151	=item body => $string	175	=item body => $string
152		176
153	The request body, usually empty. Will be-sent as-is (future versions of	177	The request body, usually empty. Will be-sent as-is (future versions of
…		…
159	based on the original netscape specification.	183	based on the original netscape specification.
160		184
161	The C<$hash_ref> must be an (initially empty) hash reference which will	185	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	186	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	187	persistent storage with something like JSON or Storable, but this is not
164	recommended, as expire times are currently being ignored.	188	recommended, as expiry times are currently being ignored.
165		189
166	Note that this cookie implementation is not of very high quality, nor	190	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	191	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	192	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	193	cookie-using sites working. Cookies are a privacy disaster, do not use
170	them unless required to.	194	them unless required to.
		195
		196	=item tls_ctx => $scheme \| $tls_ctx
		197
		198	Specifies the AnyEvent::TLS context to be used for https connections. This
		199	parameter follows the same rules as the C<tls_ctx> parameter to
		200	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		201	C<high> can be specified, which give you a predefined low-security (no
		202	verification, highest compatibility) and high-security (CA and common-name
		203	verification) TLS context.
		204
		205	The default for this option is C<low>, which could be interpreted as "give
		206	me the page, no matter what".
		207
		208	=item on_prepare => $callback->($fh)
		209
		210	In rare cases you need to "tune" the socket before it is used to
		211	connect (for exmaple, to bind it on a given IP address). This parameter
		212	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		213	and behaves exactly the same way (e.g. it has to provide a
		214	timeout). See the description for the C<$prepare_cb> argument of
		215	C<AnyEvent::Socket::tcp_connect> for details.
		216
		217	=item on_header => $callback->($headers)
		218
		219	When specified, this callback will be called with the header hash as soon
		220	as headers have been successfully received from the remote server (not on
		221	locally-generated errors).
		222
		223	It has to return either true (in which case AnyEvent::HTTP will continue),
		224	or false, in which case AnyEvent::HTTP will cancel the download (and call
		225	the finish callback with an error code of C<598>).
		226
		227	This callback is useful, among other things, to quickly reject unwanted
		228	content, which, if it is supposed to be rare, can be faster than first
		229	doing a C<HEAD> request.
		230
		231	Example: cancel the request unless the content-type is "text/html".
		232
		233	on_header => sub {
		234	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		235	},
		236
		237	=item on_body => $callback->($partial_body, $headers)
		238
		239	When specified, all body data will be passed to this callback instead of
		240	to the completion callback. The completion callback will get the empty
		241	string instead of the body data.
		242
		243	It has to return either true (in which case AnyEvent::HTTP will continue),
		244	or false, in which case AnyEvent::HTTP will cancel the download (and call
		245	the completion callback with an error code of C<598>).
		246
		247	This callback is useful when the data is too large to be held in memory
		248	(so the callback writes it to a file) or when only some information should
		249	be extracted, or when the body should be processed incrementally.
		250
		251	It is usually preferred over doing your own body handling via
		252	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		253	only used to create a connection, C<want_body_handle> is the better
		254	alternative, as it allows you to install your own event handler, reducing
		255	resource usage.
		256
		257	=item want_body_handle => $enable
		258
		259	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		260	changes considerably: after parsing the headers, and instead of
		261	downloading the body (if any), the completion callback will be
		262	called. Instead of the C<$body> argument containing the body data, the
		263	callback will receive the L<AnyEvent::Handle> object associated with the
		264	connection. In error cases, C<undef> will be passed. When there is no body
		265	(e.g. status C<304>), the empty string will be passed.
		266
		267	The handle object might or might not be in TLS mode, might be connected to
		268	a proxy, be a persistent connection etc., and configured in unspecified
		269	ways. The user is responsible for this handle (it will not be used by this
		270	module anymore).
		271
		272	This is useful with some push-type services, where, after the initial
		273	headers, an interactive protocol is used (typical example would be the
		274	push-style twitter API which starts a JSON/XML stream).
		275
		276	If you think you need this, first have a look at C<on_body>, to see if
		277	that doesn't solve your problem in a better way.
171		278
172	=back	279	=back
173		280
174	Example: make a simple HTTP GET request for http://www.nethype.de/	281	Example: make a simple HTTP GET request for http://www.nethype.de/
175		282
…		…
188	my ($body, $hdr) = @_;	295	my ($body, $hdr) = @_;
189	use Data::Dumper;	296	use Data::Dumper;
190	print Dumper $hdr;	297	print Dumper $hdr;
191	}	298	}
192	;	299	;
		300
		301	Example: make another simple HTTP GET request, but immediately try to
		302	cancel it.
		303
		304	my $request = http_request GET => "http://www.nethype.de/", sub {
		305	my ($body, $hdr) = @_;
		306	print "$body\n";
		307	};
		308
		309	undef $request;
193		310
194	=cut	311	=cut
195		312
196	sub _slot_schedule;	313	sub _slot_schedule;
197	sub _slot_schedule($) {	314	sub _slot_schedule($) {
…		…
221	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
222		339
223	_slot_schedule $_[0];	340	_slot_schedule $_[0];
224	}	341	}
225		342
		343	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		344
		345	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		346	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		347
226	sub http_request($$@) {	348	sub http_request($$@) {
227	my $cb = pop;	349	my $cb = pop;
228	my ($method, $url, %arg) = @_;	350	my ($method, $url, %arg) = @_;
229		351
230	my %hdr;	352	my %hdr;
		353
		354	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		355	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
231		356
232	$method = uc $method;	357	$method = uc $method;
233		358
234	if (my $hdr = $arg{headers}) {	359	if (my $hdr = $arg{headers}) {
235	while (my ($k, $v) = each %$hdr) {	360	while (my ($k, $v) = each %$hdr) {
236	$hdr{lc $k} = $v;	361	$hdr{lc $k} = $v;
237	}	362	}
238	}	363	}
239		364
		365	# pseudo headers for all subsequent responses
		366	my @pseudo = (URL => $url);
		367	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		368
240	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	369	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
241		370
242	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	371	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
243	if $recurse < 0;	372	if $recurse < 0;
244		373
245	my $proxy = $arg{proxy} \|\| $PROXY;	374	my $proxy = $arg{proxy} \|\| $PROXY;
246	my $timeout = $arg{timeout} \|\| $TIMEOUT;	375	my $timeout = $arg{timeout} \|\| $TIMEOUT;
247		376
248	$hdr{"user-agent"} \|\|= $USERAGENT;
249
250	my ($scheme, $authority, $upath, $query, $fragment) =	377	my ($uscheme, $uauthority, $upath, $query, $fragment) =
251	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	378	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
252		379
253	$scheme = lc $scheme;	380	$uscheme = lc $uscheme;
254		381
255	my $uport = $scheme eq "http" ? 80	382	my $uport = $uscheme eq "http" ? 80
256	: $scheme eq "https" ? 443	383	: $uscheme eq "https" ? 443
257	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	384	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
258		385
259	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
260
261	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	386	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
262	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	387	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
263		388
264	my $uhost = $1;	389	my $uhost = $1;
265	$uport = $2 if defined $2;	390	$uport = $2 if defined $2;
266		391
		392	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		393	unless exists $hdr{host};
		394
267	$uhost =~ s/^\[(.*)\]$/$1/;	395	$uhost =~ s/^\[(.*)\]$/$1/;
268	$upath .= "?$query" if length $query;	396	$upath .= $query if length $query;
269		397
270	$upath =~ s%^/?%/%;	398	$upath =~ s%^/?%/%;
271		399
272	# cookie processing	400	# cookie processing
273	if (my $jar = $arg{cookie_jar}) {	401	if (my $jar = $arg{cookie_jar}) {
274	%$jar = () if $jar->{version} < 1;	402	%$jar = () if $jar->{version} != 1;
275		403
276	my @cookie;	404	my @cookie;
277		405
278	while (my ($chost, $v) = each %$jar) {	406	while (my ($chost, $v) = each %$jar) {
		407	if ($chost =~ /^\./) {
279	next unless $chost eq substr $uhost, -length $chost;	408	next unless $chost eq substr $uhost, -length $chost;
280	next unless $chost =~ /^\./;	409	} elsif ($chost =~ /\./) {
		410	next unless $chost eq $uhost;
		411	} else {
		412	next;
		413	}
281		414
282	while (my ($cpath, $v) = each %$v) {	415	while (my ($cpath, $v) = each %$v) {
283	next unless $cpath eq substr $upath, 0, length $cpath;	416	next unless $cpath eq substr $upath, 0, length $cpath;
284		417
285	while (my ($k, $v) = each %$v) {	418	while (my ($k, $v) = each %$v) {
286	next if $scheme ne "https" && exists $v->{secure};	419	next if $uscheme ne "https" && exists $v->{secure};
		420	my $value = $v->{value};
		421	$value =~ s/([\\"])/\\$1/g;
287	push @cookie, "$k=$v->{value}";	422	push @cookie, "$k=\"$value\"";
288	}	423	}
289	}	424	}
290	}	425	}
291		426
292	$hdr{cookie} = join "; ", @cookie	427	$hdr{cookie} = join "; ", @cookie
293	if @cookie;	428	if @cookie;
294	}	429	}
295		430
296	my ($rhost, $rport, $rpath); # request host, port, path	431	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
297		432
298	if ($proxy) {	433	if ($proxy) {
299	($rhost, $rport, $scheme) = @$proxy;	434	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
300	$rpath = $url;	435
		436	$rscheme = "http" unless defined $rscheme;
		437
		438	# don't support https requests over https-proxy transport,
		439	# can't be done with tls as spec'ed, unless you double-encrypt.
		440	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
301	} else {	441	} else {
302	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	442	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
303	$hdr{host} = $uhost;
304	}	443	}
305		444
		445	# leave out fragment and query string, just a heuristic
		446	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		447	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		448
306	$hdr{"content-length"} = length $arg{body};	449	$hdr{"content-length"} = length $arg{body}
		450	if length $arg{body} \|\| $method ne "GET";
307		451
308	my %state = (connect_guard => 1);	452	my %state = (connect_guard => 1);
309		453
310	_get_slot $uhost, sub {	454	_get_slot $uhost, sub {
311	$state{slot_guard} = shift;	455	$state{slot_guard} = shift;
312		456
313	return unless $state{connect_guard};	457	return unless $state{connect_guard};
314		458
315	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	459	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
316	$state{fh} = shift	460	$state{fh} = shift
		461	or do {
		462	my $err = "$!";
		463	%state = ();
317	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	464	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		465	};
318		466
319	delete $state{connect_guard}; # reduce memory usage, save a tree	467	pop; # free memory, save a tree
		468
		469	return unless delete $state{connect_guard};
320		470
321	# get handle	471	# get handle
322	$state{handle} = new AnyEvent::Handle	472	$state{handle} = new AnyEvent::Handle
323	fh => $state{fh},	473	fh => $state{fh},
324	($scheme eq "https" ? (tls => "connect") : ());	474	peername => $rhost,
		475	tls_ctx => $arg{tls_ctx},
		476	# these need to be reconfigured on keepalive handles
		477	timeout => $timeout,
		478	on_error => sub {
		479	%state = ();
		480	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		481	},
		482	on_eof => sub {
		483	%state = ();
		484	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		485	},
		486	;
325		487
326	# limit the number of persistent connections	488	# limit the number of persistent connections
		489	# keepalive not yet supported
327	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	490	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
328	++$KA_COUNT{$_[1]};	491	# ++$KA_COUNT{$_[1]};
329	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	492	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		493	# --$KA_COUNT{$_[1]}
		494	# };
330	$hdr{connection} = "keep-alive";	495	# $hdr{connection} = "keep-alive";
331	delete $hdr{connection}; # keep-alive not yet supported
332	} else {	496	# } else {
333	delete $hdr{connection};	497	delete $hdr{connection};
334	}	498	# }
335		499
336	# (re-)configure handle	500	$state{handle}->starttls ("connect") if $rscheme eq "https";
337	$state{handle}->timeout ($timeout);
338	$state{handle}->on_error (sub {
339	my $errno = "$!";
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		501
		502	# handle actual, non-tunneled, request
		503	my $handle_actual_request = sub {
		504	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		505
348	# send request	506	# send request
349	$state{handle}->push_write (	507	$state{handle}->push_write (
350	"$method $rpath HTTP/1.0\015\012"	508	"$method $rpath HTTP/1.0\015\012"
351	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	509	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
352	. "\015\012"	510	. "\015\012"
353	. (delete $arg{body})	511	. (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	);	512	);
369		513
370	# headers, could be optimized a bit	514	# return if error occured during push_write()
		515	return unless %state;
		516
		517	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		518
		519	# status line and headers
371	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	520	$state{handle}->push_read (line => $qr_nlnl, sub {
372	for ("$_[1]\012") {	521	for ("$_[1]") {
373	# we support spaces in field names, as lotus domino	522	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
374	# creates them.	523
		524	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
		525	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
		526
		527	push @pseudo,
		528	HTTPVersion => $1,
		529	Status => $2,
		530	Reason => $3,
		531	;
		532
		533	# things seen, not parsed:
		534	# p3pP="NON CUR OTPi OUR NOR UNI"
		535
375	$hdr{lc $1} .= "\x00$2"	536	$hdr{lc $1} .= ",$2"
376	while /\G	537	while /\G
377	([^:\000-\037]+):	538	([^:\000-\037]*):
378	[\011\040]*	539	[\011\040]*
379	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	540	((?: [^\012]+ \| \012[\011\040] )*)
380	\015?\012	541	\012
381	/gxc;	542	/gxc;
382		543
383	/\G$/	544	/\G$/
384	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	545	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
385	}	546	}
386		547
		548	# remove the "," prefix we added to all headers above
387	substr $_, 0, 1, ""	549	substr $_, 0, 1, ""
388	for values %hdr;	550	for values %hdr;
389		551
		552	# patch in all pseudo headers
		553	%hdr = (%hdr, @pseudo);
		554
		555	# redirect handling
		556	# microsoft and other shitheads don't give a shit for following standards,
		557	# try to support some common forms of broken Location headers.
		558	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		559	$hdr{location} =~ s/^\.\/+//;
		560
		561	my $url = "$rscheme://$uhost:$uport";
		562
		563	unless ($hdr{location} =~ s/^\///) {
		564	$url .= $upath;
		565	$url =~ s/\/[^\/]*$//;
		566	}
		567
		568	$hdr{location} = "$url/$hdr{location}";
		569	}
		570
		571	my $redirect;
		572
		573	if ($recurse) {
		574	my $status = $hdr{Status};
		575
		576	# industry standard is to redirect POST as GET for
		577	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		578	# also, the UA should ask the user for 301 and 307 and POST,
		579	# industry standard seems to be to simply follow.
		580	# we go with the industry standard.
		581	if ($status == 301 or $status == 302 or $status == 303) {
		582	# HTTP/1.1 is unclear on how to mutate the method
		583	$method = "GET" unless $method eq "HEAD";
		584	$redirect = 1;
		585	} elsif ($status == 307) {
		586	$redirect = 1;
		587	}
		588	}
		589
390	my $finish = sub {	590	my $finish = sub {
		591	$state{handle}->destroy if $state{handle};
391	%state = ();	592	%state = ();
392		593
393	# set-cookie processing	594	# set-cookie processing
394	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	595	if ($arg{cookie_jar}) {
395	for (split /\x00/, $hdr{"set-cookie"}) {	596	for ($_[1]{"set-cookie"}) {
396	my ($cookie, @arg) = split /;\s*/;	597	# parse NAME=VALUE
397	my ($name, $value) = split /=/, $cookie, 2;	598	my @kv;
398	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);	599
		600	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		601	my $name = $1;
		602	my $value = $3;
		603
		604	unless ($value) {
		605	$value = $2;
		606	$value =~ s/\\(.)/$1/gs;
		607	}
		608
		609	push @kv, $name => $value;
		610
		611	last unless /\G\s*;/gc;
		612	}
		613
		614	last unless @kv;
		615
		616	my $name = shift @kv;
		617	my %kv = (value => shift @kv, @kv);
		618
		619	my $cdom;
		620	my $cpath = (delete $kv{path}) \|\| "/";
		621
		622	if (exists $kv{domain}) {
		623	$cdom = delete $kv{domain};
399		624
400	my $cdom = (delete $kv{domain}) \|\| $uhost;
401	my $cpath = (delete $kv{path}) \|\| "/";
402
403	$cdom =~ s/^.?/./; # make sure it starts with a "."	625	$cdom =~ s/^\.?/./; # make sure it starts with a "."
404		626
405	next if $cdom =~ /\.$/;	627	next if $cdom =~ /\.$/;
406		628
407	# this is not rfc-like and not netscape-like. go figure.	629	# this is not rfc-like and not netscape-like. go figure.
408	my $ndots = $cdom =~ y/.//;	630	my $ndots = $cdom =~ y/.//;
409	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	631	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		632	} else {
		633	$cdom = $uhost;
		634	}
410		635
411	# store it	636	# store it
412	$arg{cookie_jar}{version} = 1;	637	$arg{cookie_jar}{version} = 1;
413	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	638	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		639
		640	redo if /\G\s*,/gc;
414	}	641	}
415	}	642	}
416		643
417	# microsoft and other shitheads don't give a shit for following standards,	644	if ($redirect && exists $hdr{location}) {
418	# try to support some common forms of broken Location headers.	645	# we ignore any errors, as it is very common to receive
419	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	646	# Content-Length != 0 but no actual body
420	$_[1]{location} =~ s/^\.\/+//;	647	# we also access %hdr, as $_[1] might be an erro
421		648	http_request (
422	my $url = "$scheme://$uhost:$uport";	649	$method => $hdr{location},
423
424	unless ($_[1]{location} =~ s/^\///) {
425	$url .= $upath;
426	$url =~ s/\/[^\/]*$//;
427	}	650	%arg,
428		651	recurse => $recurse - 1,
429	$_[1]{location} = "$url/$_[1]{location}";	652	Redirect => \@_,
430	}	653	$cb);
431
432	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
433	# apparently, mozilla et al. just change POST to GET here
434	# more research is needed before we do the same
435	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
436	} elsif ($_[1]{Status} == 303 && $recurse) {
437	# even http/1.1 is unlear on how to mutate the method
438	$method = "GET" unless $method eq "HEAD";
439	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
440	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
441	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
442	} else {	654	} else {
443	$cb->($_[0], $_[1]);	655	$cb->($_[0], $_[1]);
444	}	656	}
445	};	657	};
446		658
447	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	659	my $len = $hdr{"content-length"};
		660
		661	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		662	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		663	} elsif (
		664	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		665	or $method eq "HEAD"
		666	or (defined $len && !$len)
		667	) {
		668	# no body
448	$finish->(undef, \%hdr);	669	$finish->("", \%hdr);
449	} else {	670	} else {
450	if (exists $hdr{"content-length"}) {	671	# body handling, four different code paths
451	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	672	# for want_body_handle, on_body (2x), normal (2x)
452	# could cache persistent connection now	673	# we might read too much here, but it does not matter yet (no pers. connections)
453	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	674	if (!$redirect && $arg{want_body_handle}) {
454	# but we don't, due to misdesigns, this is annoyingly complex	675	$_[0]->on_eof (undef);
		676	$_[0]->on_error (undef);
		677	$_[0]->on_read (undef);
		678
		679	$finish->(delete $state{handle}, \%hdr);
		680
		681	} elsif ($arg{on_body}) {
		682	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		683	if ($len) {
		684	$_[0]->on_eof (undef);
		685	$_[0]->on_read (sub {
		686	$len -= length $_[0]{rbuf};
		687
		688	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		689	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		690
		691	$len > 0
		692	or $finish->("", \%hdr);
455	};	693	});
456		694	} else {
		695	$_[0]->on_eof (sub {
457	$finish->($_[1], \%hdr);	696	$finish->("", \%hdr);
		697	});
		698	$_[0]->on_read (sub {
		699	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		700	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		701	});
458	});	702	}
459	} else {	703	} else {
460	# too bad, need to read until we get an error or EOF,
461	# no way to detect winged data.
462	$_[0]->on_error (sub {
463	$finish->($_[0]{rbuf}, \%hdr);
464	});
465	$_[0]->on_eof (undef);	704	$_[0]->on_eof (undef);
		705
		706	if ($len) {
		707	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		708	$_[0]->on_read (sub {
		709	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		710	if $len <= length $_[0]{rbuf};
		711	});
		712	} else {
		713	$_[0]->on_error (sub {
		714	($! == Errno::EPIPE \|\| !$!)
		715	? $finish->(delete $_[0]{rbuf}, \%hdr)
		716	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		717	});
466	$_[0]->on_read (sub { });	718	$_[0]->on_read (sub { });
		719	}
467	}	720	}
468	}	721	}
469	});	722	});
470	});	723	};
471	}, sub {	724
472	$timeout	725	# now handle proxy-CONNECT method
		726	if ($proxy && $uscheme eq "https") {
		727	# oh dear, we have to wrap it into a connect request
		728
		729	# maybe re-use $uauthority with patched port?
		730	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		731	$state{handle}->push_read (line => $qr_nlnl, sub {
		732	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		733	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
		734
		735	if ($2 == 200) {
		736	$rpath = $upath;
		737	&$handle_actual_request;
		738	} else {
		739	%state = ();
		740	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
		741	}
		742	});
		743	} else {
		744	&$handle_actual_request;
473	};	745	}
		746
		747	}, $arg{on_prepare} \|\| sub { $timeout };
474	};	748	};
475		749
476	defined wantarray && AnyEvent::Util::guard { %state = () }	750	defined wantarray && AnyEvent::Util::guard { %state = () }
477	}	751	}
478		752
…		…
492	&http_request	766	&http_request
493	}	767	}
494		768
495	=back	769	=back
496		770
		771	=head2 DNS CACHING
		772
		773	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		774	the actual connection, which in turn uses AnyEvent::DNS to resolve
		775	hostnames. The latter is a simple stub resolver and does no caching
		776	on its own. If you want DNS caching, you currently have to provide
		777	your own default resolver (by storing a suitable resolver object in
		778	C<$AnyEvent::DNS::RESOLVER>).
		779
497	=head2 GLOBAL FUNCTIONS AND VARIABLES	780	=head2 GLOBAL FUNCTIONS AND VARIABLES
498		781
499	=over 4	782	=over 4
500		783
501	=item AnyEvent::HTTP::set_proxy "proxy-url"	784	=item AnyEvent::HTTP::set_proxy "proxy-url"
502		785
503	Sets the default proxy server to use. The proxy-url must begin with a	786	Sets the default proxy server to use. The proxy-url must begin with a
504	string of the form C<http://host:port> (optionally C<https:...>).	787	string of the form C<http://host:port> (optionally C<https:...>), croaks
		788	otherwise.
		789
		790	To clear an already-set proxy, use C<undef>.
505		791
506	=item $AnyEvent::HTTP::MAX_RECURSE	792	=item $AnyEvent::HTTP::MAX_RECURSE
507		793
508	The default value for the C<recurse> request parameter (default: C<10>).	794	The default value for the C<recurse> request parameter (default: C<10>).
509		795
510	=item $AnyEvent::HTTP::USERAGENT	796	=item $AnyEvent::HTTP::USERAGENT
511		797
512	The default value for the C<User-Agent> header (the default is	798	The default value for the C<User-Agent> header (the default is
513	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	799	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
514		800
515	=item $AnyEvent::HTTP::MAX_PERSISTENT	801	=item $AnyEvent::HTTP::MAX_PER_HOST
516		802
517	The maximum number of persistent connections to keep open (default: 8).	803	The maximum number of concurrent connections to the same host (identified
		804	by the hostname). If the limit is exceeded, then the additional requests
		805	are queued until previous connections are closed.
518		806
519	Not implemented currently.	807	The default value for this is C<4>, and it is highly advisable to not
520		808	increase it.
521	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
522
523	The maximum time to cache a persistent connection, in seconds (default: 2).
524
525	Not implemented currently.
526		809
527	=item $AnyEvent::HTTP::ACTIVE	810	=item $AnyEvent::HTTP::ACTIVE
528		811
529	The number of active connections. This is not the number of currently	812	The number of active connections. This is not the number of currently
530	running requests, but the number of currently open and non-idle TCP	813	running requests, but the number of currently open and non-idle TCP
…		…
533	=back	816	=back
534		817
535	=cut	818	=cut
536		819
537	sub set_proxy($) {	820	sub set_proxy($) {
		821	if (length $_[0]) {
538	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	822	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		823	or Carp::croak "$_[0]: invalid proxy URL";
		824	$PROXY = [$2, $3 \|\| 3128, $1]
		825	} else {
		826	undef $PROXY;
		827	}
539	}	828	}
540		829
541	# initialise proxy from environment	830	# initialise proxy from environment
		831	eval {
542	set_proxy $ENV{http_proxy};	832	set_proxy $ENV{http_proxy};
		833	};
543		834
544	=head1 SEE ALSO	835	=head1 SEE ALSO
545		836
546	L<AnyEvent>.	837	L<AnyEvent>.
547		838
548	=head1 AUTHOR	839	=head1 AUTHOR
549		840
550	Marc Lehmann <schmorp@schmorp.de>	841	Marc Lehmann <schmorp@schmorp.de>
551	http://home.schmorp.de/	842	http://home.schmorp.de/
552		843
		844	With many thanks to Дмитрий Шалашов, who provided countless
		845	testcases and bugreports.
		846
553	=cut	847	=cut
554		848
555	1	849	1
556		850

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.25 by root, Mon Jul 21 05:42:07 2008 UTC vs. Revision 1.58 by root, Sun Nov 14 20:23:00 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.25 by root, Mon Jul 21 05:42:07 2008 UTC vs.
Revision 1.58 by root, Sun Nov 14 20:23:00 2010 UTC