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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC

…		…
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Carp;	44	use Errno ();
45		45
46	use AnyEvent ();	46	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
50		49
51	use base Exporter::;	50	use base Exporter::;
52		51
53	our $VERSION = '1.05';	52	our $VERSION = '1.46';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
92	must be an absolute http or https URL.	91	must be an absolute http or https URL.
93		92
94	When called in void context, nothing is returned. In other contexts,	93	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	94	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	95	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.	96	destroyed before the callback is called, the request will be cancelled.
98		97
99	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
101	response headers as second argument.	100	second argument.
102		101
103	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	105	three parts of the HTTP Status-Line of the same name.
		106
106	pseudo-header C<URL> contains the original URL (which can differ from the	107	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	108	the requested URL when following redirects - for example, you might get
		109	an error that your URL scheme is not supported even though your URL is a
		110	valid http URL because it redirected to an ftp URL, in which case you can
		111	look at the URL pseudo header).
		112
		113	The pseudo-header C<Redirect> only exists when the request was a result
		114	of an internal redirect. In that case it is an array reference with
		115	the C<($data, $headers)> from the redirect response. Note that this
		116	response could in turn be the result of a redirect itself, and C<<
		117	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		118	response, and so on.
108		119
109	If the server sends a header multiple times, then their contents will be	120	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	121	joined together with a comma (C<,>), as per the HTTP spec.
111		122
112	If an internal error occurs, such as not being able to resolve a hostname,	123	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	124	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	125	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		126	message.
115		127
116	A typical callback might look like this:	128	A typical callback might look like this:
117		129
118	sub {	130	sub {
119	my ($body, $hdr) = @_;	131	my ($body, $hdr) = @_;
…		…
137		149
138	=item headers => hashref	150	=item headers => hashref
139		151
140	The request headers to use. Currently, C<http_request> may provide its	152	The request headers to use. Currently, C<http_request> may provide its
141	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	153	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	154	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		155	suppressed by using C<undef> for these headers in which case they won't be
		156	sent at all).
143		157
144	=item timeout => $seconds	158	=item timeout => $seconds
145		159
146	The time-out to use for various stages - each connect attempt will reset	160	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	161	the timeout, as will read or write activity, i.e. this is not an overall
		162	timeout.
		163
		164	Default timeout is 5 minutes.
148		165
149	=item proxy => [$host, $port[, $scheme]] or undef	166	=item proxy => [$host, $port[, $scheme]] or undef
150		167
151	Use the given http proxy for all requests. If not specified, then the	168	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	169	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		170
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	171	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	172	HTTPS.
156		173
157	=item body => $string	174	=item body => $string
158		175
159	The request body, usually empty. Will be-sent as-is (future versions of	176	The request body, usually empty. Will be-sent as-is (future versions of
…		…
165	based on the original netscape specification.	182	based on the original netscape specification.
166		183
167	The C<$hash_ref> must be an (initially empty) hash reference which will	184	The C<$hash_ref> must be an (initially empty) hash reference which will
168	get updated automatically. It is possible to save the cookie_jar to	185	get updated automatically. It is possible to save the cookie_jar to
169	persistent storage with something like JSON or Storable, but this is not	186	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	187	recommended, as expiry times are currently being ignored.
171		188
172	Note that this cookie implementation is not of very high quality, nor	189	Note that this cookie implementation is not of very high quality, nor
173	meant to be complete. If you want complete cookie management you have to	190	meant to be complete. If you want complete cookie management you have to
174	do that on your own. C<cookie_jar> is meant as a quick fix to get some	191	do that on your own. C<cookie_jar> is meant as a quick fix to get some
175	cookie-using sites working. Cookies are a privacy disaster, do not use	192	cookie-using sites working. Cookies are a privacy disaster, do not use
176	them unless required to.	193	them unless required to.
		194
		195	=item tls_ctx => $scheme \| $tls_ctx
		196
		197	Specifies the AnyEvent::TLS context to be used for https connections. This
		198	parameter follows the same rules as the C<tls_ctx> parameter to
		199	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		200	C<high> can be specified, which give you a predefined low-security (no
		201	verification, highest compatibility) and high-security (CA and common-name
		202	verification) TLS context.
		203
		204	The default for this option is C<low>, which could be interpreted as "give
		205	me the page, no matter what".
		206
		207	=item on_prepare => $callback->($fh)
		208
		209	In rare cases you need to "tune" the socket before it is used to
		210	connect (for exmaple, to bind it on a given IP address). This parameter
		211	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		212	and behaves exactly the same way (e.g. it has to provide a
		213	timeout). See the description for the C<$prepare_cb> argument of
		214	C<AnyEvent::Socket::tcp_connect> for details.
		215
		216	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		217
		218	In even rarer cases you want total control over how AnyEvent::HTTP
		219	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		220	to do this, but you can provide your own C<tcp_connect> function -
		221	obviously, it has to follow the same calling conventions.
		222
		223	There are probably lots of weird uses for this function, starting from
		224	tracing the hosts C<http_request> actually tries to connect, to (inexact
		225	but fast) host => IP address caching or even socks protocol support.
		226
		227	=item on_header => $callback->($headers)
		228
		229	When specified, this callback will be called with the header hash as soon
		230	as headers have been successfully received from the remote server (not on
		231	locally-generated errors).
		232
		233	It has to return either true (in which case AnyEvent::HTTP will continue),
		234	or false, in which case AnyEvent::HTTP will cancel the download (and call
		235	the finish callback with an error code of C<598>).
		236
		237	This callback is useful, among other things, to quickly reject unwanted
		238	content, which, if it is supposed to be rare, can be faster than first
		239	doing a C<HEAD> request.
		240
		241	Example: cancel the request unless the content-type is "text/html".
		242
		243	on_header => sub {
		244	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		245	},
		246
		247	=item on_body => $callback->($partial_body, $headers)
		248
		249	When specified, all body data will be passed to this callback instead of
		250	to the completion callback. The completion callback will get the empty
		251	string instead of the body data.
		252
		253	It has to return either true (in which case AnyEvent::HTTP will continue),
		254	or false, in which case AnyEvent::HTTP will cancel the download (and call
		255	the completion callback with an error code of C<598>).
		256
		257	This callback is useful when the data is too large to be held in memory
		258	(so the callback writes it to a file) or when only some information should
		259	be extracted, or when the body should be processed incrementally.
		260
		261	It is usually preferred over doing your own body handling via
		262	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		263	only used to create a connection, C<want_body_handle> is the better
		264	alternative, as it allows you to install your own event handler, reducing
		265	resource usage.
		266
		267	=item want_body_handle => $enable
		268
		269	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		270	changes considerably: after parsing the headers, and instead of
		271	downloading the body (if any), the completion callback will be
		272	called. Instead of the C<$body> argument containing the body data, the
		273	callback will receive the L<AnyEvent::Handle> object associated with the
		274	connection. In error cases, C<undef> will be passed. When there is no body
		275	(e.g. status C<304>), the empty string will be passed.
		276
		277	The handle object might or might not be in TLS mode, might be connected to
		278	a proxy, be a persistent connection etc., and configured in unspecified
		279	ways. The user is responsible for this handle (it will not be used by this
		280	module anymore).
		281
		282	This is useful with some push-type services, where, after the initial
		283	headers, an interactive protocol is used (typical example would be the
		284	push-style twitter API which starts a JSON/XML stream).
		285
		286	If you think you need this, first have a look at C<on_body>, to see if
		287	that doesn't solve your problem in a better way.
177		288
178	=back	289	=back
179		290
180	Example: make a simple HTTP GET request for http://www.nethype.de/	291	Example: make a simple HTTP GET request for http://www.nethype.de/
181		292
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	348	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		349
239	_slot_schedule $_[0];	350	_slot_schedule $_[0];
240	}	351	}
241		352
242	our $qr_nl = qr<\015?\012>;	353	our $qr_nlnl = qr{(?<![^\012])\015?\012};
243	our $qr_nlnl = qr<\015?\012\015?\012>;	354
		355	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		356	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
244		357
245	sub http_request($$@) {	358	sub http_request($$@) {
246	my $cb = pop;	359	my $cb = pop;
247	my ($method, $url, %arg) = @_;	360	my ($method, $url, %arg) = @_;
248		361
249	my %hdr;	362	my %hdr;
		363
		364	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		365	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
250		366
251	$method = uc $method;	367	$method = uc $method;
252		368
253	if (my $hdr = $arg{headers}) {	369	if (my $hdr = $arg{headers}) {
254	while (my ($k, $v) = each %$hdr) {	370	while (my ($k, $v) = each %$hdr) {
255	$hdr{lc $k} = $v;	371	$hdr{lc $k} = $v;
256	}	372	}
257	}	373	}
258		374
		375	# pseudo headers for all subsequent responses
		376	my @pseudo = (URL => $url);
		377	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		378
259	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	379	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
260		380
261	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	381	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
262	if $recurse < 0;	382	if $recurse < 0;
263		383
264	my $proxy = $arg{proxy} \|\| $PROXY;	384	my $proxy = $arg{proxy} \|\| $PROXY;
265	my $timeout = $arg{timeout} \|\| $TIMEOUT;	385	my $timeout = $arg{timeout} \|\| $TIMEOUT;
266		386
267	$hdr{"user-agent"} \|\|= $USERAGENT;
268
269	my ($uscheme, $uauthority, $upath, $query, $fragment) =	387	my ($uscheme, $uauthority, $upath, $query, $fragment) =
270	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	388	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
271		389
272	$uscheme = lc $uscheme;	390	$uscheme = lc $uscheme;
273		391
274	my $uport = $uscheme eq "http" ? 80	392	my $uport = $uscheme eq "http" ? 80
275	: $uscheme eq "https" ? 443	393	: $uscheme eq "https" ? 443
276	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	394	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
277
278	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
279		395
280	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	396	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
281	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	397	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
282		398
283	my $uhost = $1;	399	my $uhost = $1;
284	$uport = $2 if defined $2;	400	$uport = $2 if defined $2;
285		401
		402	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		403	unless exists $hdr{host};
		404
286	$uhost =~ s/^\[(.*)\]$/$1/;	405	$uhost =~ s/^\[(.*)\]$/$1/;
287	$upath .= "?$query" if length $query;	406	$upath .= $query if length $query;
288		407
289	$upath =~ s%^/?%/%;	408	$upath =~ s%^/?%/%;
290		409
291	# cookie processing	410	# cookie processing
292	if (my $jar = $arg{cookie_jar}) {	411	if (my $jar = $arg{cookie_jar}) {
…		…
320	}	439	}
321		440
322	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	441	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
323		442
324	if ($proxy) {	443	if ($proxy) {
325	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	444	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		445
		446	$rscheme = "http" unless defined $rscheme;
326		447
327	# don't support https requests over https-proxy transport,	448	# don't support https requests over https-proxy transport,
328	# can't be done with tls as spec'ed.	449	# can't be done with tls as spec'ed, unless you double-encrypt.
329	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	450	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
330	} else {	451	} else {
331	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	452	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
332	}	453	}
333		454
334	$hdr{host} = $uhost;	455	# leave out fragment and query string, just a heuristic
		456	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		457	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		458
335	$hdr{"content-length"} = length $arg{body};	459	$hdr{"content-length"} = length $arg{body}
		460	if length $arg{body} \|\| $method ne "GET";
336		461
337	my %state = (connect_guard => 1);	462	my %state = (connect_guard => 1);
338		463
339	_get_slot $uhost, sub {	464	_get_slot $uhost, sub {
340	$state{slot_guard} = shift;	465	$state{slot_guard} = shift;
341		466
342	return unless $state{connect_guard};	467	return unless $state{connect_guard};
343		468
344	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	469	my $tcp_connect = $arg{tcp_connect}
		470	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		471
		472	$state{connect_guard} = $tcp_connect->(
		473	$rhost,
		474	$rport,
		475	sub {
345	$state{fh} = shift	476	$state{fh} = shift
		477	or do {
		478	my $err = "$!";
		479	%state = ();
346	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	480	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		481	};
		482
347	pop; # free memory, save a tree	483	pop; # free memory, save a tree
348		484
349	return unless delete $state{connect_guard};	485	return unless delete $state{connect_guard};
350		486
351	# get handle	487	# get handle
352	$state{handle} = new AnyEvent::Handle	488	$state{handle} = new AnyEvent::Handle
353	fh => $state{fh},	489	fh => $state{fh},
		490	peername => $rhost,
		491	tls_ctx => $arg{tls_ctx},
		492	# these need to be reconfigured on keepalive handles
354	timeout => $timeout;	493	timeout => $timeout,
		494	on_error => sub {
		495	%state = ();
		496	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		497	},
		498	on_eof => sub {
		499	%state = ();
		500	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		501	},
		502	;
355		503
356	# limit the number of persistent connections	504	# limit the number of persistent connections
357	# keepalive not yet supported	505	# keepalive not yet supported
358	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	506	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
359	++$KA_COUNT{$_[1]};	507	# ++$KA_COUNT{$_[1]};
360	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	508	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
361	--$KA_COUNT{$_[1]}	509	# --$KA_COUNT{$_[1]}
362	};	510	# };
363	$hdr{connection} = "keep-alive";	511	# $hdr{connection} = "keep-alive";
364	} else {	512	# } else {
365	delete $hdr{connection};	513	delete $hdr{connection};
366	}	514	# }
367		515
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
379	$state{handle}->starttls ("connect") if $rscheme eq "https";	516	$state{handle}->starttls ("connect") if $rscheme eq "https";
380		517
381	# handle actual, non-tunneled, request	518	# handle actual, non-tunneled, request
382	my $handle_actual_request = sub {	519	my $handle_actual_request = sub {
383	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	520	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384		521
385	# send request	522	# send request
386	$state{handle}->push_write (	523	$state{handle}->push_write (
387	"$method $rpath HTTP/1.0\015\012"	524	"$method $rpath HTTP/1.0\015\012"
388	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	525	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
389	. "\015\012"	526	. "\015\012"
390	. (delete $arg{body})	527	. (delete $arg{body})
391	);
392
393	%hdr = (); # reduce memory usage, save a kitten
394
395	# status line
396	$state{handle}->push_read (line => $qr_nl, 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	);	528	);
406		529
407	# headers, could be optimized a bit	530	# return if error occured during push_write()
		531	return unless %state;
		532
		533	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		534
		535	# status line and headers
408	$state{handle}->unshift_read (line => $qr_nlnl, sub {	536	$state{handle}->push_read (line => $qr_nlnl, sub {
409	for ("$_[1]\012") {	537	for ("$_[1]") {
410	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	538	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411		539
412	# we support spaces in field names, as lotus domino	540	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
413	# creates them (actually spaces around seperators	541	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
414	# are strictly allowed in http, they are a security issue).	542
		543	push @pseudo,
		544	HTTPVersion => $1,
		545	Status => $2,
		546	Reason => $3,
		547	;
		548
		549	# things seen, not parsed:
		550	# p3pP="NON CUR OTPi OUR NOR UNI"
		551
415	$hdr{lc $1} .= ",$2"	552	$hdr{lc $1} .= ",$2"
416	while /\G	553	while /\G
417	([^:\000-\037]+):	554	([^:\000-\037]*):
418	[\011\040]*	555	[\011\040]*
419	((?: [^\012]+ \| \012[\011\040] )*)	556	((?: [^\012]+ \| \012[\011\040] )*)
420	\012	557	\012
421	/gxc;	558	/gxc;
422		559
423	/\G$/	560	/\G$/
424	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	561	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
425	}	562	}
426		563
		564	# remove the "," prefix we added to all headers above
427	substr $_, 0, 1, ""	565	substr $_, 0, 1, ""
428	for values %hdr;	566	for values %hdr;
429		567
		568	# patch in all pseudo headers
		569	%hdr = (%hdr, @pseudo);
		570
		571	# redirect handling
		572	# microsoft and other shitheads don't give a shit for following standards,
		573	# try to support some common forms of broken Location headers.
		574	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		575	$hdr{location} =~ s/^\.\/+//;
		576
		577	my $url = "$rscheme://$uhost:$uport";
		578
		579	unless ($hdr{location} =~ s/^\///) {
		580	$url .= $upath;
		581	$url =~ s/\/[^\/]*$//;
		582	}
		583
		584	$hdr{location} = "$url/$hdr{location}";
		585	}
		586
		587	my $redirect;
		588
		589	if ($recurse) {
		590	my $status = $hdr{Status};
		591
		592	# industry standard is to redirect POST as GET for
		593	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		594	# also, the UA should ask the user for 301 and 307 and POST,
		595	# industry standard seems to be to simply follow.
		596	# we go with the industry standard.
		597	if ($status == 301 or $status == 302 or $status == 303) {
		598	# HTTP/1.1 is unclear on how to mutate the method
		599	$method = "GET" unless $method eq "HEAD";
		600	$redirect = 1;
		601	} elsif ($status == 307) {
		602	$redirect = 1;
		603	}
		604	}
		605
430	my $finish = sub {	606	my $finish = sub {
431	# TODO: use destroy method, when/if available
432	#$state{handle}->destroy;	607	$state{handle}->destroy if $state{handle};
433	$state{handle}->on_eof (undef);
434	$state{handle}->on_error (undef);
435	%state = ();	608	%state = ();
436		609
437	# set-cookie processing	610	# set-cookie processing
438	if ($arg{cookie_jar}) {	611	if ($arg{cookie_jar}) {
439	for ($hdr{"set-cookie"}) {	612	for ($_[1]{"set-cookie"}) {
440	# parse NAME=VALUE	613	# parse NAME=VALUE
441	my @kv;	614	my @kv;
442		615
443	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	616	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
444	my $name = $1;	617	my $name = $1;
…		…
482		655
483	redo if /\G\s*,/gc;	656	redo if /\G\s*,/gc;
484	}	657	}
485	}	658	}
486		659
487	# microsoft and other shitheads don't give a shit for following standards,	660	if ($redirect && exists $hdr{location}) {
488	# try to support some common forms of broken Location headers.	661	# we ignore any errors, as it is very common to receive
489	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	662	# Content-Length != 0 but no actual body
490	$_[1]{location} =~ s/^\.\/+//;	663	# we also access %hdr, as $_[1] might be an erro
491		664	http_request (
492	my $url = "$rscheme://$uhost:$uport";	665	$method => $hdr{location},
493
494	unless ($_[1]{location} =~ s/^\///) {
495	$url .= $upath;
496	$url =~ s/\/[^\/]*$//;
497	}	666	%arg,
498		667	recurse => $recurse - 1,
499	$_[1]{location} = "$url/$_[1]{location}";	668	Redirect => \@_,
500	}	669	$cb);
501
502	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
503	# apparently, mozilla et al. just change POST to GET here
504	# more research is needed before we do the same
505	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
506	} elsif ($_[1]{Status} == 303 && $recurse) {
507	# even http/1.1 is unclear on how to mutate the method
508	$method = "GET" unless $method eq "HEAD";
509	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
510	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
511	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
512	} else {	670	} else {
513	$cb->($_[0], $_[1]);	671	$cb->($_[0], $_[1]);
514	}	672	}
515	};	673	};
516		674
517	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	675	my $len = $hdr{"content-length"};
		676
		677	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		678	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		679	} elsif (
		680	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		681	or $method eq "HEAD"
		682	or (defined $len && !$len)
		683	) {
		684	# no body
518	$finish->(undef, \%hdr);	685	$finish->("", \%hdr);
519	} else {	686	} else {
520	if (exists $hdr{"content-length"}) {	687	# body handling, four different code paths
521	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	688	# for want_body_handle, on_body (2x), normal (2x)
522	# could cache persistent connection now	689	# we might read too much here, but it does not matter yet (no pers. connections)
523	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	690	if (!$redirect && $arg{want_body_handle}) {
524	# but we don't, due to misdesigns, this is annoyingly complex	691	$_[0]->on_eof (undef);
		692	$_[0]->on_error (undef);
		693	$_[0]->on_read (undef);
		694
		695	$finish->(delete $state{handle}, \%hdr);
		696
		697	} elsif ($arg{on_body}) {
		698	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		699	if ($len) {
		700	$_[0]->on_eof (undef);
		701	$_[0]->on_read (sub {
		702	$len -= length $_[0]{rbuf};
		703
		704	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		705	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		706
		707	$len > 0
		708	or $finish->("", \%hdr);
525	};	709	});
526		710	} else {
		711	$_[0]->on_eof (sub {
527	$finish->($_[1], \%hdr);	712	$finish->("", \%hdr);
		713	});
		714	$_[0]->on_read (sub {
		715	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		716	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		717	});
528	});	718	}
529	} else {	719	} else {
530	# too bad, need to read until we get an error or EOF,
531	# no way to detect winged data.
532	$_[0]->on_error (sub {
533	$finish->($_[0]{rbuf}, \%hdr);
534	});
535	$_[0]->on_eof (undef);	720	$_[0]->on_eof (undef);
		721
		722	if ($len) {
		723	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		724	$_[0]->on_read (sub {
		725	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		726	if $len <= length $_[0]{rbuf};
		727	});
		728	} else {
		729	$_[0]->on_error (sub {
		730	($! == Errno::EPIPE \|\| !$!)
		731	? $finish->(delete $_[0]{rbuf}, \%hdr)
		732	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		733	});
536	$_[0]->on_read (sub { });	734	$_[0]->on_read (sub { });
		735	}
537	}	736	}
538	}	737	}
539	});	738	});
540	});	739	};
541	};
542		740
543	# now handle proxy-CONNECT method	741	# now handle proxy-CONNECT method
544	if ($proxy && $uscheme eq "https") {	742	if ($proxy && $uscheme eq "https") {
545	# oh dear, we have to wrap it into a connect request	743	# oh dear, we have to wrap it into a connect request
546		744
547	# maybe re-use $uauthority with patched port?	745	# maybe re-use $uauthority with patched port?
548	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	746	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
549	$state{handle}->push_read (line => $qr_nlnl, sub {	747	$state{handle}->push_read (line => $qr_nlnl, sub {
550	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	748	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
551	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));	749	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
552		750
553	if ($2 == 200) {	751	if ($2 == 200) {
554	$rpath = $upath;	752	$rpath = $upath;
555	&$handle_actual_request;	753	&$handle_actual_request;
556	} else {	754	} else {
557	%state = ();	755	%state = ();
558	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	756	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
		757	}
559	}	758	});
560	});
561	} else {	759	} else {
562	&$handle_actual_request;	760	&$handle_actual_request;
		761	}
		762
563	}	763	},
564		764	$arg{on_prepare} \|\| sub { $timeout }
565	}, sub {
566	$timeout
567	};	765	);
568	};	766	};
569		767
570	defined wantarray && AnyEvent::Util::guard { %state = () }	768	defined wantarray && AnyEvent::Util::guard { %state = () }
571	}	769	}
572		770
…		…
586	&http_request	784	&http_request
587	}	785	}
588		786
589	=back	787	=back
590		788
		789	=head2 DNS CACHING
		790
		791	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		792	the actual connection, which in turn uses AnyEvent::DNS to resolve
		793	hostnames. The latter is a simple stub resolver and does no caching
		794	on its own. If you want DNS caching, you currently have to provide
		795	your own default resolver (by storing a suitable resolver object in
		796	C<$AnyEvent::DNS::RESOLVER>).
		797
591	=head2 GLOBAL FUNCTIONS AND VARIABLES	798	=head2 GLOBAL FUNCTIONS AND VARIABLES
592		799
593	=over 4	800	=over 4
594		801
595	=item AnyEvent::HTTP::set_proxy "proxy-url"	802	=item AnyEvent::HTTP::set_proxy "proxy-url"
596		803
597	Sets the default proxy server to use. The proxy-url must begin with a	804	Sets the default proxy server to use. The proxy-url must begin with a
598	string of the form C<http://host:port> (optionally C<https:...>).	805	string of the form C<http://host:port> (optionally C<https:...>), croaks
		806	otherwise.
		807
		808	To clear an already-set proxy, use C<undef>.
599		809
600	=item $AnyEvent::HTTP::MAX_RECURSE	810	=item $AnyEvent::HTTP::MAX_RECURSE
601		811
602	The default value for the C<recurse> request parameter (default: C<10>).	812	The default value for the C<recurse> request parameter (default: C<10>).
603		813
604	=item $AnyEvent::HTTP::USERAGENT	814	=item $AnyEvent::HTTP::USERAGENT
605		815
606	The default value for the C<User-Agent> header (the default is	816	The default value for the C<User-Agent> header (the default is
607	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	817	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
608		818
609	=item $AnyEvent::HTTP::MAX_PERSISTENT	819	=item $AnyEvent::HTTP::MAX_PER_HOST
610		820
611	The maximum number of persistent connections to keep open (default: 8).	821	The maximum number of concurrent connections to the same host (identified
		822	by the hostname). If the limit is exceeded, then the additional requests
		823	are queued until previous connections are closed.
612		824
613	Not implemented currently.	825	The default value for this is C<4>, and it is highly advisable to not
614		826	increase it.
615	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
616
617	The maximum time to cache a persistent connection, in seconds (default: 2).
618
619	Not implemented currently.
620		827
621	=item $AnyEvent::HTTP::ACTIVE	828	=item $AnyEvent::HTTP::ACTIVE
622		829
623	The number of active connections. This is not the number of currently	830	The number of active connections. This is not the number of currently
624	running requests, but the number of currently open and non-idle TCP	831	running requests, but the number of currently open and non-idle TCP
…		…
627	=back	834	=back
628		835
629	=cut	836	=cut
630		837
631	sub set_proxy($) {	838	sub set_proxy($) {
		839	if (length $_[0]) {
632	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	840	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		841	or Carp::croak "$_[0]: invalid proxy URL";
		842	$PROXY = [$2, $3 \|\| 3128, $1]
		843	} else {
		844	undef $PROXY;
		845	}
633	}	846	}
634		847
635	# initialise proxy from environment	848	# initialise proxy from environment
		849	eval {
636	set_proxy $ENV{http_proxy};	850	set_proxy $ENV{http_proxy};
		851	};
637		852
638	=head1 SEE ALSO	853	=head1 SEE ALSO
639		854
640	L<AnyEvent>.	855	L<AnyEvent>.
641		856
642	=head1 AUTHOR	857	=head1 AUTHOR
643		858
644	Marc Lehmann <schmorp@schmorp.de>	859	Marc Lehmann <schmorp@schmorp.de>
645	http://home.schmorp.de/	860	http://home.schmorp.de/
646		861
		862	With many thanks to Дмитрий Шалашов, who provided countless
		863	testcases and bugreports.
		864
647	=cut	865	=cut
648		866
649	1	867	1
650		868

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs. Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.34 by root, Wed Oct 29 14:51:07 2008 UTC vs.
Revision 1.59 by root, Wed Dec 29 23:59:36 2010 UTC