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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.40 by root, Sun Jul 5 01:45:01 2009 UTC vs.
Revision 1.57 by root, Mon Sep 6 06:31:32 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 4.452 ();	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 = '1.12';	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 $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$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
…		…
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 callbakc 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
…		…
184	verification, highest compatibility) and high-security (CA and common-name	202	verification, highest compatibility) and high-security (CA and common-name
185	verification) TLS context.	203	verification) TLS context.
186		204
187	The default for this option is C<low>, which could be interpreted as "give	205	The default for this option is C<low>, which could be interpreted as "give
188	me the page, no matter what".	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.
189		278
190	=back	279	=back
191		280
192	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/
193		282
…		…
249	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
250		339
251	_slot_schedule $_[0];	340	_slot_schedule $_[0];
252	}	341	}
253		342
254	our $qr_nl = qr<\015?\012>;	343	our $qr_nlnl = qr{(?<![^\012])\015?\012};
255	our $qr_nlnl = qr<\015?\012\015?\012>;
256		344
257	our $TLS_CTX_LOW = { cache => 1, dh => undef, sslv2 => 1 };	345	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
258	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_cn => "https", dh => "skip4096" };	346	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
259		347
260	sub http_request($$@) {	348	sub http_request($$@) {
261	my $cb = pop;	349	my $cb = pop;
262	my ($method, $url, %arg) = @_;	350	my ($method, $url, %arg) = @_;
263		351
…		…
272	while (my ($k, $v) = each %$hdr) {	360	while (my ($k, $v) = each %$hdr) {
273	$hdr{lc $k} = $v;	361	$hdr{lc $k} = $v;
274	}	362	}
275	}	363	}
276		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
277	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	369	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
278		370
279	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	371	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
280	if $recurse < 0;	372	if $recurse < 0;
281		373
282	my $proxy = $arg{proxy} \|\| $PROXY;	374	my $proxy = $arg{proxy} \|\| $PROXY;
283	my $timeout = $arg{timeout} \|\| $TIMEOUT;	375	my $timeout = $arg{timeout} \|\| $TIMEOUT;
284		376
285	$hdr{"user-agent"} \|\|= $USERAGENT;
286
287	my ($uscheme, $uauthority, $upath, $query, $fragment) =	377	my ($uscheme, $uauthority, $upath, $query, $fragment) =
288	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	378	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
289		379
290	$uscheme = lc $uscheme;	380	$uscheme = lc $uscheme;
291		381
292	my $uport = $uscheme eq "http" ? 80	382	my $uport = $uscheme eq "http" ? 80
293	: $uscheme eq "https" ? 443	383	: $uscheme eq "https" ? 443
294	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported (not '$uscheme')", URL => $url });	384	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
295
296	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
297		385
298	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	386	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
299	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	387	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
300		388
301	my $uhost = $1;	389	my $uhost = $1;
302	$uport = $2 if defined $2;	390	$uport = $2 if defined $2;
303		391
		392	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		393	unless exists $hdr{host};
		394
304	$uhost =~ s/^\[(.*)\]$/$1/;	395	$uhost =~ s/^\[(.*)\]$/$1/;
305	$upath .= "?$query" if length $query;	396	$upath .= $query if length $query;
306		397
307	$upath =~ s%^/?%/%;	398	$upath =~ s%^/?%/%;
308		399
309	# cookie processing	400	# cookie processing
310	if (my $jar = $arg{cookie_jar}) {	401	if (my $jar = $arg{cookie_jar}) {
…		…
340	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	431	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
341		432
342	if ($proxy) {	433	if ($proxy) {
343	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	434	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
344		435
		436	$rscheme = "http" unless defined $rscheme;
		437
345	# don't support https requests over https-proxy transport,	438	# don't support https requests over https-proxy transport,
346	# 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.
347	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	440	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
348	} else {	441	} else {
349	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	442	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
350	}	443	}
351		444
352	$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
353	$hdr{"content-length"} = length $arg{body};	449	$hdr{"content-length"} = length $arg{body}
		450	if length $arg{body} \|\| $method ne "GET";
354		451
355	my %state = (connect_guard => 1);	452	my %state = (connect_guard => 1);
356		453
357	_get_slot $uhost, sub {	454	_get_slot $uhost, sub {
358	$state{slot_guard} = shift;	455	$state{slot_guard} = shift;
359		456
360	return unless $state{connect_guard};	457	return unless $state{connect_guard};
361		458
362	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	459	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
363	$state{fh} = shift	460	$state{fh} = shift
		461	or do {
		462	my $err = "$!";
		463	%state = ();
364	or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url }));	464	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		465	};
		466
365	pop; # free memory, save a tree	467	pop; # free memory, save a tree
366		468
367	return unless delete $state{connect_guard};	469	return unless delete $state{connect_guard};
368		470
369	# get handle	471	# get handle
370	$state{handle} = new AnyEvent::Handle	472	$state{handle} = new AnyEvent::Handle
371	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
372	timeout => $timeout,	477	timeout => $timeout,
373	peername => $rhost,	478	on_error => sub {
374	tls_ctx => $arg{tls_ctx};	479	%state = ();
		480	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		481	},
		482	on_eof => sub {
		483	%state = ();
		484	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		485	},
		486	;
375		487
376	# limit the number of persistent connections	488	# limit the number of persistent connections
377	# keepalive not yet supported	489	# keepalive not yet supported
378	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	490	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
379	++$KA_COUNT{$_[1]};	491	# ++$KA_COUNT{$_[1]};
380	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	492	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
381	--$KA_COUNT{$_[1]}	493	# --$KA_COUNT{$_[1]}
382	};	494	# };
383	$hdr{connection} = "keep-alive";	495	# $hdr{connection} = "keep-alive";
384	} else {	496	# } else {
385	delete $hdr{connection};	497	delete $hdr{connection};
386	}	498	# }
387
388	# (re-)configure handle
389	$state{handle}->on_error (sub {
390	%state = ();
391	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
392	});
393	$state{handle}->on_eof (sub {
394	%state = ();
395	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
396	});
397		499
398	$state{handle}->starttls ("connect") if $rscheme eq "https";	500	$state{handle}->starttls ("connect") if $rscheme eq "https";
399		501
400	# handle actual, non-tunneled, request	502	# handle actual, non-tunneled, request
401	my $handle_actual_request = sub {	503	my $handle_actual_request = sub {
402	$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};
403		505
404	# send request	506	# send request
405	$state{handle}->push_write (	507	$state{handle}->push_write (
406	"$method $rpath HTTP/1.0\015\012"	508	"$method $rpath HTTP/1.0\015\012"
407	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	509	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
408	. "\015\012"	510	. "\015\012"
409	. (delete $arg{body})	511	. (delete $arg{body})
410	);	512	);
411		513
		514	# return if error occured during push_write()
		515	return unless %state;
		516
412	%hdr = (); # reduce memory usage, save a kitten	517	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
413		518
414	# status line	519	# status line and headers
415	$state{handle}->push_read (line => $qr_nl, sub {	520	$state{handle}->push_read (line => $qr_nlnl, sub {
416	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
417	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
418
419	my %hdr = ( # response headers
420	HTTPVersion => ",$1",
421	Status => ",$2",
422	Reason => ",$3",
423	URL => ",$url"
424	);
425
426	# headers, could be optimized a bit
427	$state{handle}->unshift_read (line => $qr_nlnl, sub {
428	for ("$_[1]\012") {	521	for ("$_[1]") {
429	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.
430		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
431	# things seen, not parsed:	533	# things seen, not parsed:
432	# p3pP="NON CUR OTPi OUR NOR UNI"	534	# p3pP="NON CUR OTPi OUR NOR UNI"
433		535
434	$hdr{lc $1} .= ",$2"	536	$hdr{lc $1} .= ",$2"
435	while /\G	537	while /\G
436	([^:\000-\037]+):	538	([^:\000-\037]*):
437	[\011\040]*	539	[\011\040]*
438	((?: [^\012]+ \| \012[\011\040] )*)	540	((?: [^\012]+ \| \012[\011\040] )*)
439	\012	541	\012
440	/gxc;	542	/gxc;
441		543
442	/\G$/	544	/\G$/
443	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	$url =~ s/\/[^\/]*$//;
444	}	566	}
445		567
446	substr $_, 0, 1, ""	568	$hdr{location} = "$url/$hdr{location}";
447	for values %hdr;	569	}
448		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
449	my $finish = sub {	590	my $finish = sub {
450	$state{handle}->destroy;	591	$state{handle}->destroy if $state{handle};
451	%state = ();	592	%state = ();
452		593
453	# set-cookie processing	594	# set-cookie processing
454	if ($arg{cookie_jar}) {	595	if ($arg{cookie_jar}) {
455	for ($hdr{"set-cookie"}) {	596	for ($_[1]{"set-cookie"}) {
456	# parse NAME=VALUE	597	# parse NAME=VALUE
457	my @kv;	598	my @kv;
458		599
459	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	600	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
460	my $name = $1;	601	my $name = $1;
461	my $value = $3;	602	my $value = $3;
462		603
463	unless ($value) {	604	unless ($value) {
464	$value = $2;	605	$value = $2;
465	$value =~ s/\\(.)/$1/gs;	606	$value =~ s/\\(.)/$1/gs;
466	}
467
468	push @kv, $name => $value;
469
470	last unless /\G\s*;/gc;
471	}	607	}
472		608
		609	push @kv, $name => $value;
		610
		611	last unless /\G\s*;/gc;
		612	}
		613
473	last unless @kv;	614	last unless @kv;
474		615
475	my $name = shift @kv;	616	my $name = shift @kv;
476	my %kv = (value => shift @kv, @kv);	617	my %kv = (value => shift @kv, @kv);
477		618
478	my $cdom;	619	my $cdom;
479	my $cpath = (delete $kv{path}) \|\| "/";	620	my $cpath = (delete $kv{path}) \|\| "/";
480		621
481	if (exists $kv{domain}) {	622	if (exists $kv{domain}) {
482	$cdom = delete $kv{domain};	623	$cdom = delete $kv{domain};
		624
		625	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		626
		627	next if $cdom =~ /\.$/;
483		628
484	$cdom =~ s/^\.?/./; # make sure it starts with a "."
485
486	next if $cdom =~ /\.$/;
487
488	# this is not rfc-like and not netscape-like. go figure.	629	# this is not rfc-like and not netscape-like. go figure.
489	my $ndots = $cdom =~ y/.//;	630	my $ndots = $cdom =~ y/.//;
490	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	631	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
491	} else {	632	} else {
492	$cdom = $uhost;	633	$cdom = $uhost;
493	}
494
495	# store it
496	$arg{cookie_jar}{version} = 1;
497	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
498
499	redo if /\G\s*,/gc;
500	}	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;
501	}	641	}
502
503	# microsoft and other shitheads don't give a shit for following standards,
504	# try to support some common forms of broken Location headers.
505	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
506	$_[1]{location} =~ s/^\.\/+//;
507
508	my $url = "$rscheme://$uhost:$uport";
509
510	unless ($_[1]{location} =~ s/^\///) {
511	$url .= $upath;
512	$url =~ s/\/[^\/]*$//;
513	}
514
515	$_[1]{location} = "$url/$_[1]{location}";
516	}
517
518	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
519	# apparently, mozilla et al. just change POST to GET here
520	# more research is needed before we do the same
521	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
522	} elsif ($_[1]{Status} == 303 && $recurse) {
523	# even http/1.1 is unclear on how to mutate the method
524	$method = "GET" unless $method eq "HEAD";
525	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
526	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
527	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
528	} else {
529	$cb->($_[0], $_[1]);
530	}
531	};	642	}
532		643
533	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	644	if ($redirect && exists $hdr{location}) {
534	$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);
535	} else {	654	} else {
536	if (exists $hdr{"content-length"}) {	655	$cb->($_[0], $_[1]);
537	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	656	}
538	# could cache persistent connection now	657	};
539	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	658
540	# 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
541	};	691	$len > 0
542
543	$finish->($_[1], \%hdr);	692	or $finish->("", \%hdr);
544	});	693	});
545	} else {	694	} else {
546	# too bad, need to read until we get an error or EOF,	695	$_[0]->on_eof (sub {
547	# 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 {
548	$_[0]->on_error (sub {	713	$_[0]->on_error (sub {
549	# delete ought to be more efficient, as we would have to make	714	($! == Errno::EPIPE \|\| !$!)
550	# a copy otherwise as $_[0] gets destroyed.
551	$finish->(delete $_[0]{rbuf}, \%hdr);	715	? $finish->(delete $_[0]{rbuf}, \%hdr)
		716	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
552	});	717	});
553	$_[0]->on_eof (undef);
554	$_[0]->on_read (sub { });	718	$_[0]->on_read (sub { });
555	}	719	}
556	}	720	}
557	});	721	}
558	});	722	});
559	};	723	};
560		724
561	# now handle proxy-CONNECT method	725	# now handle proxy-CONNECT method
562	if ($proxy && $uscheme eq "https") {	726	if ($proxy && $uscheme eq "https") {
…		…
564		728
565	# maybe re-use $uauthority with patched port?	729	# maybe re-use $uauthority with patched port?
566	$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");
567	$state{handle}->push_read (line => $qr_nlnl, sub {	731	$state{handle}->push_read (line => $qr_nlnl, sub {
568	$_[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
569	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 }));
570		734
571	if ($2 == 200) {	735	if ($2 == 200) {
572	$rpath = $upath;	736	$rpath = $upath;
573	&$handle_actual_request;	737	&$handle_actual_request;
574	} else {	738	} else {
575	%state = ();	739	%state = ();
576	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	740	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
577	}	741	}
578	});	742	});
579	} else {	743	} else {
580	&$handle_actual_request;	744	&$handle_actual_request;
581	}	745	}
582		746
583	}, sub {	747	}, $arg{on_prepare} \|\| sub { $timeout };
584	$timeout
585	};
586	};	748	};
587		749
588	defined wantarray && AnyEvent::Util::guard { %state = () }	750	defined wantarray && AnyEvent::Util::guard { %state = () }
589	}	751	}
590		752
…		…
604	&http_request	766	&http_request
605	}	767	}
606		768
607	=back	769	=back
608		770
		771	=head2 DNS CACHING
		772
		773	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		774	the actual connection, which in turn uses AnyEvent::DNS to resolve
		775	hostnames. The latter is a simple stub resolver and does no caching
		776	on its own. If you want DNS caching, you currently have to provide
		777	your own default resolver (by storing a suitable resolver object in
		778	C<$AnyEvent::DNS::RESOLVER>).
		779
609	=head2 GLOBAL FUNCTIONS AND VARIABLES	780	=head2 GLOBAL FUNCTIONS AND VARIABLES
610		781
611	=over 4	782	=over 4
612		783
613	=item AnyEvent::HTTP::set_proxy "proxy-url"	784	=item AnyEvent::HTTP::set_proxy "proxy-url"
614		785
615	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
616	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>.
617		791
618	=item $AnyEvent::HTTP::MAX_RECURSE	792	=item $AnyEvent::HTTP::MAX_RECURSE
619		793
620	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>).
621		795
622	=item $AnyEvent::HTTP::USERAGENT	796	=item $AnyEvent::HTTP::USERAGENT
623		797
624	The default value for the C<User-Agent> header (the default is	798	The default value for the C<User-Agent> header (the default is
625	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	799	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
626		800
627	=item $AnyEvent::HTTP::MAX_PERSISTENT	801	=item $AnyEvent::HTTP::MAX_PER_HOST
628		802
629	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.
630		806
631	Not implemented currently.	807	The default value for this is C<4>, and it is highly advisable to not
632		808	increase it.
633	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
634
635	The maximum time to cache a persistent connection, in seconds (default: 2).
636
637	Not implemented currently.
638		809
639	=item $AnyEvent::HTTP::ACTIVE	810	=item $AnyEvent::HTTP::ACTIVE
640		811
641	The number of active connections. This is not the number of currently	812	The number of active connections. This is not the number of currently
642	running requests, but the number of currently open and non-idle TCP	813	running requests, but the number of currently open and non-idle TCP
…		…
645	=back	816	=back
646		817
647	=cut	818	=cut
648		819
649	sub set_proxy($) {	820	sub set_proxy($) {
		821	if (length $_[0]) {
650	$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	}
651	}	828	}
652		829
653	# initialise proxy from environment	830	# initialise proxy from environment
		831	eval {
654	set_proxy $ENV{http_proxy};	832	set_proxy $ENV{http_proxy};
		833	};
655		834
656	=head1 SEE ALSO	835	=head1 SEE ALSO
657		836
658	L<AnyEvent>.	837	L<AnyEvent>.
659		838

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.40 by root, Sun Jul 5 01:45:01 2009 UTC vs. Revision 1.57 by root, Mon Sep 6 06:31:32 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.40 by root, Sun Jul 5 01:45:01 2009 UTC vs.
Revision 1.57 by root, Mon Sep 6 06:31:32 2010 UTC