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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.38 by root, Sat Mar 7 03:43:09 2009 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 = '1.11';	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
…		…
92	must be an absolute http or https URL.	92	must be an absolute http or https URL.
93		93
94	When called in void context, nothing is returned. In other contexts,	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	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	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.	97	destroyed before the callback is called, the request will be cancelled.
98		98
99	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
100	(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
101	response headers as second argument.	101	second argument.
102		102
103	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
104	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
105	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
106	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
107	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).
		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	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		119	response, and so on.
108		120
109	If the server sends a header multiple times, then their contents will be	121	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	122	joined together with a comma (C<,>), as per the HTTP spec.
111		123
112	If an internal error occurs, such as not being able to resolve a hostname,	124	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	125	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	126	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		127	message.
115		128
116	A typical callback might look like this:	129	A typical callback might look like this:
117		130
118	sub {	131	sub {
119	my ($body, $hdr) = @_;	132	my ($body, $hdr) = @_;
…		…
137		150
138	=item headers => hashref	151	=item headers => hashref
139		152
140	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
141	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
142	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).
143		158
144	=item timeout => $seconds	159	=item timeout => $seconds
145		160
146	The time-out to use for various stages - each connect attempt will reset	161	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	162	the timeout, as will read or write activity, i.e. this is not an overall
		163	timeout.
		164
		165	Default timeout is 5 minutes.
148		166
149	=item proxy => [$host, $port[, $scheme]] or undef	167	=item proxy => [$host, $port[, $scheme]] or undef
150		168
151	Use the given http proxy for all requests. If not specified, then the	169	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	170	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		171
154	C<$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
155	HTTPS.	173	HTTPS.
156		174
157	=item body => $string	175	=item body => $string
158		176
159	The request body, usually empty. Will be-sent as-is (future versions of	177	The request body, usually empty. Will be-sent as-is (future versions of
…		…
165	based on the original netscape specification.	183	based on the original netscape specification.
166		184
167	The C<$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
168	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
169	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
170	recommended, as expire times are currently being ignored.	188	recommended, as expiry times are currently being ignored.
171		189
172	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
173	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
174	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
175	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
176	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.
177		278
178	=back	279	=back
179		280
180	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/
181		282
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		339
239	_slot_schedule $_[0];	340	_slot_schedule $_[0];
240	}	341	}
241		342
242	our $qr_nl = qr<\015?\012>;	343	our $qr_nlnl = qr{(?<![^\012])\015?\012};
243	our $qr_nlnl = qr<\015?\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" };
244		347
245	sub http_request($$@) {	348	sub http_request($$@) {
246	my $cb = pop;	349	my $cb = pop;
247	my ($method, $url, %arg) = @_;	350	my ($method, $url, %arg) = @_;
248		351
249	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";
250		356
251	$method = uc $method;	357	$method = uc $method;
252		358
253	if (my $hdr = $arg{headers}) {	359	if (my $hdr = $arg{headers}) {
254	while (my ($k, $v) = each %$hdr) {	360	while (my ($k, $v) = each %$hdr) {
255	$hdr{lc $k} = $v;	361	$hdr{lc $k} = $v;
256	}	362	}
257	}	363	}
258		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
259	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	369	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
260		370
261	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	371	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
262	if $recurse < 0;	372	if $recurse < 0;
263		373
264	my $proxy = $arg{proxy} \|\| $PROXY;	374	my $proxy = $arg{proxy} \|\| $PROXY;
265	my $timeout = $arg{timeout} \|\| $TIMEOUT;	375	my $timeout = $arg{timeout} \|\| $TIMEOUT;
266		376
267	$hdr{"user-agent"} \|\|= $USERAGENT;
268
269	my ($uscheme, $uauthority, $upath, $query, $fragment) =	377	my ($uscheme, $uauthority, $upath, $query, $fragment) =
270	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	378	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
271		379
272	$uscheme = lc $uscheme;	380	$uscheme = lc $uscheme;
273		381
274	my $uport = $uscheme eq "http" ? 80	382	my $uport = $uscheme eq "http" ? 80
275	: $uscheme eq "https" ? 443	383	: $uscheme eq "https" ? 443
276	: 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 });
277
278	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
279		385
280	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	386	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
281	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	387	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
282		388
283	my $uhost = $1;	389	my $uhost = $1;
284	$uport = $2 if defined $2;	390	$uport = $2 if defined $2;
285		391
		392	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		393	unless exists $hdr{host};
		394
286	$uhost =~ s/^\[(.*)\]$/$1/;	395	$uhost =~ s/^\[(.*)\]$/$1/;
287	$upath .= "?$query" if length $query;	396	$upath .= $query if length $query;
288		397
289	$upath =~ s%^/?%/%;	398	$upath =~ s%^/?%/%;
290		399
291	# cookie processing	400	# cookie processing
292	if (my $jar = $arg{cookie_jar}) {	401	if (my $jar = $arg{cookie_jar}) {
…		…
322	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	431	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
323		432
324	if ($proxy) {	433	if ($proxy) {
325	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	434	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
326		435
		436	$rscheme = "http" unless defined $rscheme;
		437
327	# don't support https requests over https-proxy transport,	438	# don't support https requests over https-proxy transport,
328	# can't be done with tls as spec'ed, unless you double-encrypt.	439	# can't be done with tls as spec'ed, unless you double-encrypt.
329	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	440	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
330	} else {	441	} else {
331	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	442	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
332	}	443	}
333		444
334	$hdr{host} = $uhost;	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
335	$hdr{"content-length"} = length $arg{body};	449	$hdr{"content-length"} = length $arg{body}
		450	if length $arg{body} \|\| $method ne "GET";
336		451
337	my %state = (connect_guard => 1);	452	my %state = (connect_guard => 1);
338		453
339	_get_slot $uhost, sub {	454	_get_slot $uhost, sub {
340	$state{slot_guard} = shift;	455	$state{slot_guard} = shift;
341		456
342	return unless $state{connect_guard};	457	return unless $state{connect_guard};
343		458
344	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	459	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
345	$state{fh} = shift	460	$state{fh} = shift
		461	or do {
		462	my $err = "$!";
		463	%state = ();
346	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	464	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		465	};
		466
347	pop; # free memory, save a tree	467	pop; # free memory, save a tree
348		468
349	return unless delete $state{connect_guard};	469	return unless delete $state{connect_guard};
350		470
351	# get handle	471	# get handle
352	$state{handle} = new AnyEvent::Handle	472	$state{handle} = new AnyEvent::Handle
353	fh => $state{fh},	473	fh => $state{fh},
		474	peername => $rhost,
		475	tls_ctx => $arg{tls_ctx},
		476	# these need to be reconfigured on keepalive handles
354	timeout => $timeout;	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	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		485	},
		486	;
355		487
356	# limit the number of persistent connections	488	# limit the number of persistent connections
357	# keepalive not yet supported	489	# keepalive not yet supported
358	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	490	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
359	++$KA_COUNT{$_[1]};	491	# ++$KA_COUNT{$_[1]};
360	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	492	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
361	--$KA_COUNT{$_[1]}	493	# --$KA_COUNT{$_[1]}
362	};	494	# };
363	$hdr{connection} = "keep-alive";	495	# $hdr{connection} = "keep-alive";
364	} else {	496	# } else {
365	delete $hdr{connection};	497	delete $hdr{connection};
366	}	498	# }
367
368	# (re-)configure handle
369	$state{handle}->on_error (sub {
370	my $errno = "$!";
371	%state = ();
372	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
373	});
374	$state{handle}->on_eof (sub {
375	%state = ();
376	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
377	});
378		499
379	$state{handle}->starttls ("connect") if $rscheme eq "https";	500	$state{handle}->starttls ("connect") if $rscheme eq "https";
380		501
381	# handle actual, non-tunneled, request	502	# handle actual, non-tunneled, request
382	my $handle_actual_request = sub {	503	my $handle_actual_request = sub {
383	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	504	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384		505
385	# send request	506	# send request
386	$state{handle}->push_write (	507	$state{handle}->push_write (
387	"$method $rpath HTTP/1.0\015\012"	508	"$method $rpath HTTP/1.0\015\012"
388	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	509	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
389	. "\015\012"	510	. "\015\012"
390	. (delete $arg{body})	511	. (delete $arg{body})
391	);	512	);
392		513
		514	# return if error occured during push_write()
		515	return unless %state;
		516
393	%hdr = (); # reduce memory usage, save a kitten	517	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
394		518
395	# status line	519	# status line and headers
396	$state{handle}->push_read (line => $qr_nl, sub {	520	$state{handle}->push_read (line => $qr_nlnl, sub {
397	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
398	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
399
400	my %hdr = ( # response headers
401	HTTPVersion => ",$1",
402	Status => ",$2",
403	Reason => ",$3",
404	URL => ",$url"
405	);
406
407	# headers, could be optimized a bit
408	$state{handle}->unshift_read (line => $qr_nlnl, sub {
409	for ("$_[1]\012") {	521	for ("$_[1]") {
410	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	522	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411		523
412	# we support spaces in field names, as lotus domino	524	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
413	# creates them (actually spaces around seperators	525	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
414	# are strictly allowed in http, they are a security issue).	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
415	$hdr{lc $1} .= ",$2"	536	$hdr{lc $1} .= ",$2"
416	while /\G	537	while /\G
417	([^:\000-\037]+):	538	([^:\000-\037]*):
418	[\011\040]*	539	[\011\040]*
419	((?: [^\012]+ \| \012[\011\040] )*)	540	((?: [^\012]+ \| \012[\011\040] )*)
420	\012	541	\012
421	/gxc;	542	/gxc;
422		543
423	/\G$/	544	/\G$/
424	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 }));
		546	}
		547
		548	# remove the "," prefix we added to all headers above
		549	substr $_, 0, 1, ""
		550	for values %hdr;
		551
		552	# patch in all pseudo headers
		553	%hdr = (%hdr, @pseudo);
		554
		555	# redirect handling
		556	# microsoft and other shitheads don't give a shit for following standards,
		557	# try to support some common forms of broken Location headers.
		558	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		559	$hdr{location} =~ s/^\.\/+//;
		560
		561	my $url = "$rscheme://$uhost:$uport";
		562
		563	unless ($hdr{location} =~ s/^\///) {
		564	$url .= $upath;
		565	$url =~ s/\/[^\/]*$//;
425	}	566	}
426		567
427	substr $_, 0, 1, ""	568	$hdr{location} = "$url/$hdr{location}";
428	for values %hdr;	569	}
429		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
430	my $finish = sub {	590	my $finish = sub {
431	$state{handle}->destroy;	591	$state{handle}->destroy if $state{handle};
432	%state = ();	592	%state = ();
433		593
434	# set-cookie processing	594	# set-cookie processing
435	if ($arg{cookie_jar}) {	595	if ($arg{cookie_jar}) {
436	for ($hdr{"set-cookie"}) {	596	for ($_[1]{"set-cookie"}) {
437	# parse NAME=VALUE	597	# parse NAME=VALUE
438	my @kv;	598	my @kv;
439		599
440	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	600	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
441	my $name = $1;	601	my $name = $1;
442	my $value = $3;	602	my $value = $3;
443		603
444	unless ($value) {	604	unless ($value) {
445	$value = $2;	605	$value = $2;
446	$value =~ s/\\(.)/$1/gs;	606	$value =~ s/\\(.)/$1/gs;
447	}
448
449	push @kv, $name => $value;
450
451	last unless /\G\s*;/gc;
452	}	607	}
453		608
		609	push @kv, $name => $value;
		610
		611	last unless /\G\s*;/gc;
		612	}
		613
454	last unless @kv;	614	last unless @kv;
455		615
456	my $name = shift @kv;	616	my $name = shift @kv;
457	my %kv = (value => shift @kv, @kv);	617	my %kv = (value => shift @kv, @kv);
458		618
459	my $cdom;	619	my $cdom;
460	my $cpath = (delete $kv{path}) \|\| "/";	620	my $cpath = (delete $kv{path}) \|\| "/";
461		621
462	if (exists $kv{domain}) {	622	if (exists $kv{domain}) {
463	$cdom = delete $kv{domain};	623	$cdom = delete $kv{domain};
		624
		625	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		626
		627	next if $cdom =~ /\.$/;
464		628
465	$cdom =~ s/^\.?/./; # make sure it starts with a "."
466
467	next if $cdom =~ /\.$/;
468
469	# this is not rfc-like and not netscape-like. go figure.	629	# this is not rfc-like and not netscape-like. go figure.
470	my $ndots = $cdom =~ y/.//;	630	my $ndots = $cdom =~ y/.//;
471	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	631	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
472	} else {	632	} else {
473	$cdom = $uhost;	633	$cdom = $uhost;
474	}
475
476	# store it
477	$arg{cookie_jar}{version} = 1;
478	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
479
480	redo if /\G\s*,/gc;
481	}	634	}
		635
		636	# store it
		637	$arg{cookie_jar}{version} = 1;
		638	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		639
		640	redo if /\G\s*,/gc;
482	}	641	}
483
484	# microsoft and other shitheads don't give a shit for following standards,
485	# try to support some common forms of broken Location headers.
486	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
487	$_[1]{location} =~ s/^\.\/+//;
488
489	my $url = "$rscheme://$uhost:$uport";
490
491	unless ($_[1]{location} =~ s/^\///) {
492	$url .= $upath;
493	$url =~ s/\/[^\/]*$//;
494	}
495
496	$_[1]{location} = "$url/$_[1]{location}";
497	}
498
499	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
500	# apparently, mozilla et al. just change POST to GET here
501	# more research is needed before we do the same
502	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
503	} elsif ($_[1]{Status} == 303 && $recurse) {
504	# even http/1.1 is unclear on how to mutate the method
505	$method = "GET" unless $method eq "HEAD";
506	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
507	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
508	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
509	} else {
510	$cb->($_[0], $_[1]);
511	}
512	};	642	}
513		643
514	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	644	if ($redirect && exists $hdr{location}) {
515	$finish->(undef, \%hdr);	645	# we ignore any errors, as it is very common to receive
		646	# Content-Length != 0 but no actual body
		647	# we also access %hdr, as $_[1] might be an erro
		648	http_request (
		649	$method => $hdr{location},
		650	%arg,
		651	recurse => $recurse - 1,
		652	Redirect => \@_,
		653	$cb);
516	} else {	654	} else {
517	if (exists $hdr{"content-length"}) {	655	$cb->($_[0], $_[1]);
518	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	656	}
519	# could cache persistent connection now	657	};
520	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	658
521	# but we don't, due to misdesigns, this is annoyingly complex	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
		669	$finish->("", \%hdr);
		670	} else {
		671	# body handling, four different code paths
		672	# for want_body_handle, on_body (2x), normal (2x)
		673	# we might read too much here, but it does not matter yet (no pers. connections)
		674	if (!$redirect && $arg{want_body_handle}) {
		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
522	};	691	$len > 0
523
524	$finish->($_[1], \%hdr);	692	or $finish->("", \%hdr);
525	});	693	});
526	} else {	694	} else {
527	# too bad, need to read until we get an error or EOF,	695	$_[0]->on_eof (sub {
528	# no way to detect winged data.	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	});
		702	}
		703	} else {
		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 {
529	$_[0]->on_error (sub {	713	$_[0]->on_error (sub {
530	# delete ought to be more efficient, as we would have to make	714	($! == Errno::EPIPE \|\| !$!)
531	# a copy otherwise as $_[0] gets destroyed.
532	$finish->(delete $_[0]{rbuf}, \%hdr);	715	? $finish->(delete $_[0]{rbuf}, \%hdr)
		716	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
533	});	717	});
534	$_[0]->on_eof (undef);
535	$_[0]->on_read (sub { });	718	$_[0]->on_read (sub { });
536	}	719	}
537	}	720	}
538	});	721	}
539	});	722	});
540	};	723	};
541		724
542	# now handle proxy-CONNECT method	725	# now handle proxy-CONNECT method
543	if ($proxy && $uscheme eq "https") {	726	if ($proxy && $uscheme eq "https") {
…		…
545		728
546	# maybe re-use $uauthority with patched port?	729	# maybe re-use $uauthority with patched port?
547	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	730	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
548	$state{handle}->push_read (line => $qr_nlnl, sub {	731	$state{handle}->push_read (line => $qr_nlnl, sub {
549	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	732	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
550	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));	733	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
551		734
552	if ($2 == 200) {	735	if ($2 == 200) {
553	$rpath = $upath;	736	$rpath = $upath;
554	&$handle_actual_request;	737	&$handle_actual_request;
555	} else {	738	} else {
556	%state = ();	739	%state = ();
557	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	740	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
558	}	741	}
559	});	742	});
560	} else {	743	} else {
561	&$handle_actual_request;	744	&$handle_actual_request;
562	}	745	}
563		746
564	}, sub {	747	}, $arg{on_prepare} \|\| sub { $timeout };
565	$timeout
566	};
567	};	748	};
568		749
569	defined wantarray && AnyEvent::Util::guard { %state = () }	750	defined wantarray && AnyEvent::Util::guard { %state = () }
570	}	751	}
571		752
…		…
585	&http_request	766	&http_request
586	}	767	}
587		768
588	=back	769	=back
589		770
		771	=head2 DNS CACHING
		772
		773	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		774	the actual connection, which in turn uses AnyEvent::DNS to resolve
		775	hostnames. The latter is a simple stub resolver and does no caching
		776	on its own. If you want DNS caching, you currently have to provide
		777	your own default resolver (by storing a suitable resolver object in
		778	C<$AnyEvent::DNS::RESOLVER>).
		779
590	=head2 GLOBAL FUNCTIONS AND VARIABLES	780	=head2 GLOBAL FUNCTIONS AND VARIABLES
591		781
592	=over 4	782	=over 4
593		783
594	=item AnyEvent::HTTP::set_proxy "proxy-url"	784	=item AnyEvent::HTTP::set_proxy "proxy-url"
595		785
596	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
597	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>.
598		791
599	=item $AnyEvent::HTTP::MAX_RECURSE	792	=item $AnyEvent::HTTP::MAX_RECURSE
600		793
601	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>).
602		795
603	=item $AnyEvent::HTTP::USERAGENT	796	=item $AnyEvent::HTTP::USERAGENT
604		797
605	The default value for the C<User-Agent> header (the default is	798	The default value for the C<User-Agent> header (the default is
606	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	799	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
607		800
608	=item $AnyEvent::HTTP::MAX_PERSISTENT	801	=item $AnyEvent::HTTP::MAX_PER_HOST
609		802
610	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.
611		806
612	Not implemented currently.	807	The default value for this is C<4>, and it is highly advisable to not
613		808	increase it.
614	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
615
616	The maximum time to cache a persistent connection, in seconds (default: 2).
617
618	Not implemented currently.
619		809
620	=item $AnyEvent::HTTP::ACTIVE	810	=item $AnyEvent::HTTP::ACTIVE
621		811
622	The number of active connections. This is not the number of currently	812	The number of active connections. This is not the number of currently
623	running requests, but the number of currently open and non-idle TCP	813	running requests, but the number of currently open and non-idle TCP
…		…
626	=back	816	=back
627		817
628	=cut	818	=cut
629		819
630	sub set_proxy($) {	820	sub set_proxy($) {
		821	if (length $_[0]) {
631	$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	}
632	}	828	}
633		829
634	# initialise proxy from environment	830	# initialise proxy from environment
		831	eval {
635	set_proxy $ENV{http_proxy};	832	set_proxy $ENV{http_proxy};
		833	};
636		834
637	=head1 SEE ALSO	835	=head1 SEE ALSO
638		836
639	L<AnyEvent>.	837	L<AnyEvent>.
640		838

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.38 by root, Sat Mar 7 03:43:09 2009 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 1.38 by root, Sat Mar 7 03:43:09 2009 UTC vs.
Revision 1.58 by root, Sun Nov 14 20:23:00 2010 UTC