[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 1.62 by root, Thu Dec 30 04:30:24 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) = @_;
…		…
135	Whether to recurse requests or not, e.g. on redirects, authentication	147	Whether to recurse requests or not, e.g. on redirects, authentication
136	retries and so on, and how often to do so.	148	retries and so on, and how often to do so.
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, with the header name (I<MUST be in lowercase>)
141	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	153	as key and header value as hash value.
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	154
		155	Currently, http_request> may provide its own C<host>, C<content-length>,
		156	C<connection> and C<cookie> headers and will provide defaults for
		157	C<user-agent> and C<referer> (this can be suppressed by using a value of
		158	C<undef> for these headers in which case they won't be sent at all).
143		159
144	=item timeout => $seconds	160	=item timeout => $seconds
145		161
146	The time-out to use for various stages - each connect attempt will reset	162	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	163	the timeout, as will read or write activity, i.e. this is not an overall
		164	timeout.
		165
		166	Default timeout is 5 minutes.
148		167
149	=item proxy => [$host, $port[, $scheme]] or undef	168	=item proxy => [$host, $port[, $scheme]] or undef
150		169
151	Use the given http proxy for all requests. If not specified, then the	170	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	171	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		172
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	173	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	174	HTTPS.
156		175
157	=item body => $string	176	=item body => $string
158		177
159	The request body, usually empty. Will be-sent as-is (future versions of	178	The request body, usually empty. Will be-sent as-is (future versions of
…		…
165	based on the original netscape specification.	184	based on the original netscape specification.
166		185
167	The C<$hash_ref> must be an (initially empty) hash reference which will	186	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	187	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	188	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	189	recommended, as expiry times are currently being ignored.
171		190
172	Note that this cookie implementation is not of very high quality, nor	191	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	192	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	193	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	194	cookie-using sites working. Cookies are a privacy disaster, do not use
176	them unless required to.	195	them unless required to.
		196
		197	=item tls_ctx => $scheme \| $tls_ctx
		198
		199	Specifies the AnyEvent::TLS context to be used for https connections. This
		200	parameter follows the same rules as the C<tls_ctx> parameter to
		201	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		202	C<high> can be specified, which give you a predefined low-security (no
		203	verification, highest compatibility) and high-security (CA and common-name
		204	verification) TLS context.
		205
		206	The default for this option is C<low>, which could be interpreted as "give
		207	me the page, no matter what".
		208
		209	=item on_prepare => $callback->($fh)
		210
		211	In rare cases you need to "tune" the socket before it is used to
		212	connect (for exmaple, to bind it on a given IP address). This parameter
		213	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		214	and behaves exactly the same way (e.g. it has to provide a
		215	timeout). See the description for the C<$prepare_cb> argument of
		216	C<AnyEvent::Socket::tcp_connect> for details.
		217
		218	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		219
		220	In even rarer cases you want total control over how AnyEvent::HTTP
		221	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		222	to do this, but you can provide your own C<tcp_connect> function -
		223	obviously, it has to follow the same calling conventions, except that it
		224	may always return a connection guard object.
		225
		226	There are probably lots of weird uses for this function, starting from
		227	tracing the hosts C<http_request> actually tries to connect, to (inexact
		228	but fast) host => IP address caching or even socks protocol support.
		229
		230	=item on_header => $callback->($headers)
		231
		232	When specified, this callback will be called with the header hash as soon
		233	as headers have been successfully received from the remote server (not on
		234	locally-generated errors).
		235
		236	It has to return either true (in which case AnyEvent::HTTP will continue),
		237	or false, in which case AnyEvent::HTTP will cancel the download (and call
		238	the finish callback with an error code of C<598>).
		239
		240	This callback is useful, among other things, to quickly reject unwanted
		241	content, which, if it is supposed to be rare, can be faster than first
		242	doing a C<HEAD> request.
		243
		244	Example: cancel the request unless the content-type is "text/html".
		245
		246	on_header => sub {
		247	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		248	},
		249
		250	=item on_body => $callback->($partial_body, $headers)
		251
		252	When specified, all body data will be passed to this callback instead of
		253	to the completion callback. The completion callback will get the empty
		254	string instead of the body data.
		255
		256	It has to return either true (in which case AnyEvent::HTTP will continue),
		257	or false, in which case AnyEvent::HTTP will cancel the download (and call
		258	the completion callback with an error code of C<598>).
		259
		260	This callback is useful when the data is too large to be held in memory
		261	(so the callback writes it to a file) or when only some information should
		262	be extracted, or when the body should be processed incrementally.
		263
		264	It is usually preferred over doing your own body handling via
		265	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		266	only used to create a connection, C<want_body_handle> is the better
		267	alternative, as it allows you to install your own event handler, reducing
		268	resource usage.
		269
		270	=item want_body_handle => $enable
		271
		272	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		273	changes considerably: after parsing the headers, and instead of
		274	downloading the body (if any), the completion callback will be
		275	called. Instead of the C<$body> argument containing the body data, the
		276	callback will receive the L<AnyEvent::Handle> object associated with the
		277	connection. In error cases, C<undef> will be passed. When there is no body
		278	(e.g. status C<304>), the empty string will be passed.
		279
		280	The handle object might or might not be in TLS mode, might be connected to
		281	a proxy, be a persistent connection etc., and configured in unspecified
		282	ways. The user is responsible for this handle (it will not be used by this
		283	module anymore).
		284
		285	This is useful with some push-type services, where, after the initial
		286	headers, an interactive protocol is used (typical example would be the
		287	push-style twitter API which starts a JSON/XML stream).
		288
		289	If you think you need this, first have a look at C<on_body>, to see if
		290	that doesn't solve your problem in a better way.
177		291
178	=back	292	=back
179		293
180	Example: make a simple HTTP GET request for http://www.nethype.de/	294	Example: make a simple HTTP GET request for http://www.nethype.de/
181		295
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	351	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		352
239	_slot_schedule $_[0];	353	_slot_schedule $_[0];
240	}	354	}
241		355
242	our $qr_nl = qr<\015?\012>;	356	our $qr_nlnl = qr{(?<![^\012])\015?\012};
243	our $qr_nlnl = qr<\015?\012\015?\012>;	357
		358	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		359	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
244		360
245	sub http_request($$@) {	361	sub http_request($$@) {
246	my $cb = pop;	362	my $cb = pop;
247	my ($method, $url, %arg) = @_;	363	my ($method, $url, %arg) = @_;
248		364
249	my %hdr;	365	my %hdr;
		366
		367	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		368	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
250		369
251	$method = uc $method;	370	$method = uc $method;
252		371
253	if (my $hdr = $arg{headers}) {	372	if (my $hdr = $arg{headers}) {
254	while (my ($k, $v) = each %$hdr) {	373	while (my ($k, $v) = each %$hdr) {
255	$hdr{lc $k} = $v;	374	$hdr{lc $k} = $v;
256	}	375	}
257	}	376	}
258		377
		378	# pseudo headers for all subsequent responses
		379	my @pseudo = (URL => $url);
		380	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		381
259	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	382	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
260		383
261	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	384	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
262	if $recurse < 0;	385	if $recurse < 0;
263		386
264	my $proxy = $arg{proxy} \|\| $PROXY;	387	my $proxy = $arg{proxy} \|\| $PROXY;
265	my $timeout = $arg{timeout} \|\| $TIMEOUT;	388	my $timeout = $arg{timeout} \|\| $TIMEOUT;
266		389
267	$hdr{"user-agent"} \|\|= $USERAGENT;
268
269	my ($uscheme, $uauthority, $upath, $query, $fragment) =	390	my ($uscheme, $uauthority, $upath, $query, $fragment) =
270	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	391	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
271		392
272	$uscheme = lc $uscheme;	393	$uscheme = lc $uscheme;
273		394
274	my $uport = $uscheme eq "http" ? 80	395	my $uport = $uscheme eq "http" ? 80
275	: $uscheme eq "https" ? 443	396	: $uscheme eq "https" ? 443
276	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	397	: 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		398
280	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	399	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
281	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	400	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
282		401
283	my $uhost = $1;	402	my $uhost = $1;
284	$uport = $2 if defined $2;	403	$uport = $2 if defined $2;
285		404
		405	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		406	unless exists $hdr{host};
		407
286	$uhost =~ s/^\[(.*)\]$/$1/;	408	$uhost =~ s/^\[(.*)\]$/$1/;
287	$upath .= "?$query" if length $query;	409	$upath .= $query if length $query;
288		410
289	$upath =~ s%^/?%/%;	411	$upath =~ s%^/?%/%;
290		412
291	# cookie processing	413	# cookie processing
292	if (my $jar = $arg{cookie_jar}) {	414	if (my $jar = $arg{cookie_jar}) {
…		…
320	}	442	}
321		443
322	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	444	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
323		445
324	if ($proxy) {	446	if ($proxy) {
325	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	447	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		448
		449	$rscheme = "http" unless defined $rscheme;
326		450
327	# don't support https requests over https-proxy transport,	451	# don't support https requests over https-proxy transport,
328	# can't be done with tls as spec'ed.	452	# can't be done with tls as spec'ed, unless you double-encrypt.
329	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	453	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
330	} else {	454	} else {
331	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	455	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
332	}	456	}
333		457
334	$hdr{host} = $uhost;	458	# leave out fragment and query string, just a heuristic
		459	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		460	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		461
335	$hdr{"content-length"} = length $arg{body};	462	$hdr{"content-length"} = length $arg{body}
		463	if length $arg{body} \|\| $method ne "GET";
336		464
337	my %state = (connect_guard => 1);	465	my %state = (connect_guard => 1);
338		466
339	_get_slot $uhost, sub {	467	_get_slot $uhost, sub {
340	$state{slot_guard} = shift;	468	$state{slot_guard} = shift;
341		469
342	return unless $state{connect_guard};	470	return unless $state{connect_guard};
343		471
344	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	472	my $tcp_connect = $arg{tcp_connect}
		473	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		474
		475	$state{connect_guard} = $tcp_connect->(
		476	$rhost,
		477	$rport,
		478	sub {
345	$state{fh} = shift	479	$state{fh} = shift
		480	or do {
		481	my $err = "$!";
		482	%state = ();
346	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	483	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		484	};
		485
347	pop; # free memory, save a tree	486	pop; # free memory, save a tree
348		487
349	return unless delete $state{connect_guard};	488	return unless delete $state{connect_guard};
350		489
351	# get handle	490	# get handle
352	$state{handle} = new AnyEvent::Handle	491	$state{handle} = new AnyEvent::Handle
353	fh => $state{fh},	492	fh => $state{fh},
		493	peername => $rhost,
		494	tls_ctx => $arg{tls_ctx},
		495	# these need to be reconfigured on keepalive handles
354	timeout => $timeout;	496	timeout => $timeout,
		497	on_error => sub {
		498	%state = ();
		499	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		500	},
		501	on_eof => sub {
		502	%state = ();
		503	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		504	},
		505	;
355		506
356	# limit the number of persistent connections	507	# limit the number of persistent connections
357	# keepalive not yet supported	508	# keepalive not yet supported
358	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	509	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
359	++$KA_COUNT{$_[1]};	510	# ++$KA_COUNT{$_[1]};
360	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	511	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
361	--$KA_COUNT{$_[1]}	512	# --$KA_COUNT{$_[1]}
362	};	513	# };
363	$hdr{connection} = "keep-alive";	514	# $hdr{connection} = "keep-alive";
364	} else {	515	# } else {
365	delete $hdr{connection};	516	delete $hdr{connection};
366	}	517	# }
367		518
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";	519	$state{handle}->starttls ("connect") if $rscheme eq "https";
380		520
381	# handle actual, non-tunneled, request	521	# handle actual, non-tunneled, request
382	my $handle_actual_request = sub {	522	my $handle_actual_request = sub {
383	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	523	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384		524
385	# send request	525	# send request
386	$state{handle}->push_write (	526	$state{handle}->push_write (
387	"$method $rpath HTTP/1.0\015\012"	527	"$method $rpath HTTP/1.0\015\012"
388	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	528	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
389	. "\015\012"	529	. "\015\012"
390	. (delete $arg{body})	530	. (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	);	531	);
406		532
407	# headers, could be optimized a bit	533	# return if error occured during push_write()
		534	return unless %state;
		535
		536	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		537
		538	# status line and headers
408	$state{handle}->unshift_read (line => $qr_nlnl, sub {	539	$state{handle}->push_read (line => $qr_nlnl, sub {
409	for ("$_[1]\012") {	540	for ("$_[1]") {
410	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	541	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411		542
412	# we support spaces in field names, as lotus domino	543	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
413	# creates them (actually spaces around seperators	544	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
414	# are strictly allowed in http, they are a security issue).	545
		546	push @pseudo,
		547	HTTPVersion => $1,
		548	Status => $2,
		549	Reason => $3,
		550	;
		551
		552	# things seen, not parsed:
		553	# p3pP="NON CUR OTPi OUR NOR UNI"
		554
415	$hdr{lc $1} .= ",$2"	555	$hdr{lc $1} .= ",$2"
416	while /\G	556	while /\G
417	([^:\000-\037]+):	557	([^:\000-\037]*):
418	[\011\040]*	558	[\011\040]*
419	((?: [^\012]+ \| \012[\011\040] )*)	559	((?: [^\012]+ \| \012[\011\040] )*)
420	\012	560	\012
421	/gxc;	561	/gxc;
422		562
423	/\G$/	563	/\G$/
424	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	564	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
425	}	565	}
426		566
		567	# remove the "," prefix we added to all headers above
427	substr $_, 0, 1, ""	568	substr $_, 0, 1, ""
428	for values %hdr;	569	for values %hdr;
429		570
		571	# patch in all pseudo headers
		572	%hdr = (%hdr, @pseudo);
		573
		574	# redirect handling
		575	# microsoft and other shitheads don't give a shit for following standards,
		576	# try to support some common forms of broken Location headers.
		577	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		578	$hdr{location} =~ s/^\.\/+//;
		579
		580	my $url = "$rscheme://$uhost:$uport";
		581
		582	unless ($hdr{location} =~ s/^\///) {
		583	$url .= $upath;
		584	$url =~ s/\/[^\/]*$//;
		585	}
		586
		587	$hdr{location} = "$url/$hdr{location}";
		588	}
		589
		590	my $redirect;
		591
		592	if ($recurse) {
		593	my $status = $hdr{Status};
		594
		595	# industry standard is to redirect POST as GET for
		596	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		597	# also, the UA should ask the user for 301 and 307 and POST,
		598	# industry standard seems to be to simply follow.
		599	# we go with the industry standard.
		600	if ($status == 301 or $status == 302 or $status == 303) {
		601	# HTTP/1.1 is unclear on how to mutate the method
		602	$method = "GET" unless $method eq "HEAD";
		603	$redirect = 1;
		604	} elsif ($status == 307) {
		605	$redirect = 1;
		606	}
		607	}
		608
430	my $finish = sub {	609	my $finish = sub {
431	# TODO: use destroy method, when/if available
432	#$state{handle}->destroy;	610	$state{handle}->destroy if $state{handle};
433	$state{handle}->on_eof (undef);
434	$state{handle}->on_error (undef);
435	%state = ();	611	%state = ();
436		612
437	# set-cookie processing	613	# set-cookie processing
438	if ($arg{cookie_jar}) {	614	if ($arg{cookie_jar}) {
439	for ($hdr{"set-cookie"}) {	615	for ($_[1]{"set-cookie"}) {
440	# parse NAME=VALUE	616	# parse NAME=VALUE
441	my @kv;	617	my @kv;
442		618
443	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	619	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
444	my $name = $1;	620	my $name = $1;
…		…
482		658
483	redo if /\G\s*,/gc;	659	redo if /\G\s*,/gc;
484	}	660	}
485	}	661	}
486		662
487	# microsoft and other shitheads don't give a shit for following standards,	663	if ($redirect && exists $hdr{location}) {
488	# try to support some common forms of broken Location headers.	664	# we ignore any errors, as it is very common to receive
489	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	665	# Content-Length != 0 but no actual body
490	$_[1]{location} =~ s/^\.\/+//;	666	# we also access %hdr, as $_[1] might be an erro
491		667	http_request (
492	my $url = "$rscheme://$uhost:$uport";	668	$method => $hdr{location},
493
494	unless ($_[1]{location} =~ s/^\///) {
495	$url .= $upath;
496	$url =~ s/\/[^\/]*$//;
497	}	669	%arg,
498		670	recurse => $recurse - 1,
499	$_[1]{location} = "$url/$_[1]{location}";	671	Redirect => \@_,
500	}	672	$cb);
501
502	if ($_[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 {	673	} else {
513	$cb->($_[0], $_[1]);	674	$cb->($_[0], $_[1]);
514	}	675	}
515	};	676	};
516		677
517	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	678	my $len = $hdr{"content-length"};
		679
		680	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		681	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		682	} elsif (
		683	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		684	or $method eq "HEAD"
		685	or (defined $len && !$len)
		686	) {
		687	# no body
518	$finish->(undef, \%hdr);	688	$finish->("", \%hdr);
519	} else {	689	} else {
520	if (exists $hdr{"content-length"}) {	690	# body handling, four different code paths
521	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	691	# for want_body_handle, on_body (2x), normal (2x)
522	# could cache persistent connection now	692	# we might read too much here, but it does not matter yet (no pers. connections)
523	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	693	if (!$redirect && $arg{want_body_handle}) {
524	# but we don't, due to misdesigns, this is annoyingly complex	694	$_[0]->on_eof (undef);
		695	$_[0]->on_error (undef);
		696	$_[0]->on_read (undef);
		697
		698	$finish->(delete $state{handle}, \%hdr);
		699
		700	} elsif ($arg{on_body}) {
		701	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		702	if ($len) {
		703	$_[0]->on_eof (undef);
		704	$_[0]->on_read (sub {
		705	$len -= length $_[0]{rbuf};
		706
		707	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		708	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		709
		710	$len > 0
		711	or $finish->("", \%hdr);
525	};	712	});
526		713	} else {
		714	$_[0]->on_eof (sub {
527	$finish->($_[1], \%hdr);	715	$finish->("", \%hdr);
		716	});
		717	$_[0]->on_read (sub {
		718	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		719	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		720	});
528	});	721	}
529	} else {	722	} 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);	723	$_[0]->on_eof (undef);
		724
		725	if ($len) {
		726	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		727	$_[0]->on_read (sub {
		728	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		729	if $len <= length $_[0]{rbuf};
		730	});
		731	} else {
		732	$_[0]->on_error (sub {
		733	($! == Errno::EPIPE \|\| !$!)
		734	? $finish->(delete $_[0]{rbuf}, \%hdr)
		735	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		736	});
536	$_[0]->on_read (sub { });	737	$_[0]->on_read (sub { });
		738	}
537	}	739	}
538	}	740	}
539	});	741	});
540	});	742	};
541	};
542		743
543	# now handle proxy-CONNECT method	744	# now handle proxy-CONNECT method
544	if ($proxy && $uscheme eq "https") {	745	if ($proxy && $uscheme eq "https") {
545	# oh dear, we have to wrap it into a connect request	746	# oh dear, we have to wrap it into a connect request
546		747
547	# maybe re-use $uauthority with patched port?	748	# 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");	749	$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 {	750	$state{handle}->push_read (line => $qr_nlnl, sub {
550	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	751	$_[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 }));	752	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
552		753
553	if ($2 == 200) {	754	if ($2 == 200) {
554	$rpath = $upath;	755	$rpath = $upath;
555	&$handle_actual_request;	756	&$handle_actual_request;
556	} else {	757	} else {
557	%state = ();	758	%state = ();
558	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	759	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
		760	}
559	}	761	});
560	});
561	} else {	762	} else {
562	&$handle_actual_request;	763	&$handle_actual_request;
		764	}
		765
563	}	766	},
564		767	$arg{on_prepare} \|\| sub { $timeout }
565	}, sub {
566	$timeout
567	};	768	);
568	};	769	};
569		770
570	defined wantarray && AnyEvent::Util::guard { %state = () }	771	defined wantarray && AnyEvent::Util::guard { %state = () }
571	}	772	}
572		773
…		…
586	&http_request	787	&http_request
587	}	788	}
588		789
589	=back	790	=back
590		791
		792	=head2 DNS CACHING
		793
		794	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		795	the actual connection, which in turn uses AnyEvent::DNS to resolve
		796	hostnames. The latter is a simple stub resolver and does no caching
		797	on its own. If you want DNS caching, you currently have to provide
		798	your own default resolver (by storing a suitable resolver object in
		799	C<$AnyEvent::DNS::RESOLVER>).
		800
591	=head2 GLOBAL FUNCTIONS AND VARIABLES	801	=head2 GLOBAL FUNCTIONS AND VARIABLES
592		802
593	=over 4	803	=over 4
594		804
595	=item AnyEvent::HTTP::set_proxy "proxy-url"	805	=item AnyEvent::HTTP::set_proxy "proxy-url"
596		806
597	Sets the default proxy server to use. The proxy-url must begin with a	807	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:...>).	808	string of the form C<http://host:port> (optionally C<https:...>), croaks
		809	otherwise.
		810
		811	To clear an already-set proxy, use C<undef>.
		812
		813	=item $date = AnyEvent::HTTP::format_date $timestamp
		814
		815	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		816	Date (RFC 2616).
		817
		818	=item $timestamp = AnyEvent::HTTP::parse_date $date
		819
		820	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		821	timestamp, or C<undef> if the date cannot be parsed.
599		822
600	=item $AnyEvent::HTTP::MAX_RECURSE	823	=item $AnyEvent::HTTP::MAX_RECURSE
601		824
602	The default value for the C<recurse> request parameter (default: C<10>).	825	The default value for the C<recurse> request parameter (default: C<10>).
603		826
604	=item $AnyEvent::HTTP::USERAGENT	827	=item $AnyEvent::HTTP::USERAGENT
605		828
606	The default value for the C<User-Agent> header (the default is	829	The default value for the C<User-Agent> header (the default is
607	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	830	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
608		831
609	=item $AnyEvent::HTTP::MAX_PERSISTENT	832	=item $AnyEvent::HTTP::MAX_PER_HOST
610		833
611	The maximum number of persistent connections to keep open (default: 8).	834	The maximum number of concurrent connections to the same host (identified
		835	by the hostname). If the limit is exceeded, then the additional requests
		836	are queued until previous connections are closed.
612		837
613	Not implemented currently.	838	The default value for this is C<4>, and it is highly advisable to not
614		839	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		840
621	=item $AnyEvent::HTTP::ACTIVE	841	=item $AnyEvent::HTTP::ACTIVE
622		842
623	The number of active connections. This is not the number of currently	843	The number of active connections. This is not the number of currently
624	running requests, but the number of currently open and non-idle TCP	844	running requests, but the number of currently open and non-idle TCP
…		…
626		846
627	=back	847	=back
628		848
629	=cut	849	=cut
630		850
		851	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		852	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		853
		854	sub format_date($) {
		855	my ($time) = @_;
		856
		857	# RFC 822/1123 format
		858	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		859
		860	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		861	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		862	$H, $M, $S;
		863	}
		864
		865	sub parse_date($) {
		866	my ($date) = @_;
		867
		868	my ($d, $m, $y, $H, $M, $S);
		869
		870	if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9]) ([A-Z][a-z][a-z]) ([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		871	# RFC 822/1123, required by RFC 2616
		872	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		873
		874	} elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		875	# RFC 850
		876	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		877
		878	} elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) {
		879	# ISO C's asctime
		880	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		881	}
		882	# other formats fail in the loop below
		883
		884	for (0..11) {
		885	if ($m eq $month[$_]) {
		886	require Time::Local;
		887	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		888	}
		889	}
		890
		891	undef
		892	}
		893
631	sub set_proxy($) {	894	sub set_proxy($) {
		895	if (length $_[0]) {
632	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	896	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		897	or Carp::croak "$_[0]: invalid proxy URL";
		898	$PROXY = [$2, $3 \|\| 3128, $1]
		899	} else {
		900	undef $PROXY;
		901	}
633	}	902	}
634		903
635	# initialise proxy from environment	904	# initialise proxy from environment
		905	eval {
636	set_proxy $ENV{http_proxy};	906	set_proxy $ENV{http_proxy};
		907	};
		908
		909	=head2 SOCKS PROXIES
		910
		911	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		912	compile your perl to support socks, or use an external program such as
		913	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		914	transparently.
		915
		916	Alternatively, for AnyEvent::HTTP only, you can use your own
		917	C<tcp_connect> function that does the proxy handshake - here is an example
		918	that works with socks4a proxies:
		919
		920	use Errno;
		921	use AnyEvent::Util;
		922	use AnyEvent::Socket;
		923	use AnyEvent::Handle;
		924
		925	# host, port and username of/for your socks4a proxy
		926	my $socks_host = "10.0.0.23";
		927	my $socks_port = 9050;
		928	my $socks_user = "";
		929
		930	sub socks4a_connect {
		931	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		932
		933	my $hdl = new AnyEvent::Handle
		934	connect => [$socks_host, $socks_port],
		935	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		936	on_error => sub { $connect_cb->() },
		937	;
		938
		939	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		940
		941	$hdl->push_read (chunk => 8, sub {
		942	my ($hdl, $chunk) = @_;
		943	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		944
		945	if ($status == 0x5a) {
		946	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		947	} else {
		948	$! = Errno::ENXIO; $connect_cb->();
		949	}
		950	});
		951
		952	$hdl
		953	}
		954
		955	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		956	possibly after switching off other proxy types:
		957
		958	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		959
		960	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		961	my ($data, $headers) = @_;
		962	...
		963	};
637		964
638	=head1 SEE ALSO	965	=head1 SEE ALSO
639		966
640	L<AnyEvent>.	967	L<AnyEvent>.
641		968
642	=head1 AUTHOR	969	=head1 AUTHOR
643		970
644	Marc Lehmann <schmorp@schmorp.de>	971	Marc Lehmann <schmorp@schmorp.de>
645	http://home.schmorp.de/	972	http://home.schmorp.de/
646		973
		974	With many thanks to Дмитрий Шалашов, who provided countless
		975	testcases and bugreports.
		976
647	=cut	977	=cut
648		978
649	1	979	1
650		980

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 1.62 by root, Thu Dec 30 04:30:24 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 1.62 by root, Thu Dec 30 04:30:24 2010 UTC