[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 1.63 by root, Thu Dec 30 04:31:55 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, except that it
		222	may always return a connection guard object.
		223
		224	There are probably lots of weird uses for this function, starting from
		225	tracing the hosts C<http_request> actually tries to connect, to (inexact
		226	but fast) host => IP address caching or even socks protocol support.
		227
		228	=item on_header => $callback->($headers)
		229
		230	When specified, this callback will be called with the header hash as soon
		231	as headers have been successfully received from the remote server (not on
		232	locally-generated errors).
		233
		234	It has to return either true (in which case AnyEvent::HTTP will continue),
		235	or false, in which case AnyEvent::HTTP will cancel the download (and call
		236	the finish callback with an error code of C<598>).
		237
		238	This callback is useful, among other things, to quickly reject unwanted
		239	content, which, if it is supposed to be rare, can be faster than first
		240	doing a C<HEAD> request.
		241
		242	Example: cancel the request unless the content-type is "text/html".
		243
		244	on_header => sub {
		245	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		246	},
		247
		248	=item on_body => $callback->($partial_body, $headers)
		249
		250	When specified, all body data will be passed to this callback instead of
		251	to the completion callback. The completion callback will get the empty
		252	string instead of the body data.
		253
		254	It has to return either true (in which case AnyEvent::HTTP will continue),
		255	or false, in which case AnyEvent::HTTP will cancel the download (and call
		256	the completion callback with an error code of C<598>).
		257
		258	This callback is useful when the data is too large to be held in memory
		259	(so the callback writes it to a file) or when only some information should
		260	be extracted, or when the body should be processed incrementally.
		261
		262	It is usually preferred over doing your own body handling via
		263	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		264	only used to create a connection, C<want_body_handle> is the better
		265	alternative, as it allows you to install your own event handler, reducing
		266	resource usage.
		267
		268	=item want_body_handle => $enable
		269
		270	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		271	changes considerably: after parsing the headers, and instead of
		272	downloading the body (if any), the completion callback will be
		273	called. Instead of the C<$body> argument containing the body data, the
		274	callback will receive the L<AnyEvent::Handle> object associated with the
		275	connection. In error cases, C<undef> will be passed. When there is no body
		276	(e.g. status C<304>), the empty string will be passed.
		277
		278	The handle object might or might not be in TLS mode, might be connected to
		279	a proxy, be a persistent connection etc., and configured in unspecified
		280	ways. The user is responsible for this handle (it will not be used by this
		281	module anymore).
		282
		283	This is useful with some push-type services, where, after the initial
		284	headers, an interactive protocol is used (typical example would be the
		285	push-style twitter API which starts a JSON/XML stream).
		286
		287	If you think you need this, first have a look at C<on_body>, to see if
		288	that doesn't solve your problem in a better way.
177		289
178	=back	290	=back
179		291
180	Example: make a simple HTTP GET request for http://www.nethype.de/	292	Example: make a simple HTTP GET request for http://www.nethype.de/
181		293
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	349	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		350
239	_slot_schedule $_[0];	351	_slot_schedule $_[0];
240	}	352	}
241		353
242	our $qr_nl = qr<\015?\012>;	354	our $qr_nlnl = qr{(?<![^\012])\015?\012};
243	our $qr_nlnl = qr<\015?\012\015?\012>;	355
		356	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		357	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
244		358
245	sub http_request($$@) {	359	sub http_request($$@) {
246	my $cb = pop;	360	my $cb = pop;
247	my ($method, $url, %arg) = @_;	361	my ($method, $url, %arg) = @_;
248		362
249	my %hdr;	363	my %hdr;
		364
		365	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		366	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
250		367
251	$method = uc $method;	368	$method = uc $method;
252		369
253	if (my $hdr = $arg{headers}) {	370	if (my $hdr = $arg{headers}) {
254	while (my ($k, $v) = each %$hdr) {	371	while (my ($k, $v) = each %$hdr) {
255	$hdr{lc $k} = $v;	372	$hdr{lc $k} = $v;
256	}	373	}
257	}	374	}
258		375
		376	# pseudo headers for all subsequent responses
		377	my @pseudo = (URL => $url);
		378	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		379
259	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	380	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
260		381
261	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	382	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
262	if $recurse < 0;	383	if $recurse < 0;
263		384
264	my $proxy = $arg{proxy} \|\| $PROXY;	385	my $proxy = $arg{proxy} \|\| $PROXY;
265	my $timeout = $arg{timeout} \|\| $TIMEOUT;	386	my $timeout = $arg{timeout} \|\| $TIMEOUT;
266		387
267	$hdr{"user-agent"} \|\|= $USERAGENT;
268
269	my ($uscheme, $uauthority, $upath, $query, $fragment) =	388	my ($uscheme, $uauthority, $upath, $query, $fragment) =
270	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	389	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
271		390
272	$uscheme = lc $uscheme;	391	$uscheme = lc $uscheme;
273		392
274	my $uport = $uscheme eq "http" ? 80	393	my $uport = $uscheme eq "http" ? 80
275	: $uscheme eq "https" ? 443	394	: $uscheme eq "https" ? 443
276	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	395	: 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		396
280	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	397	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
281	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	398	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
282		399
283	my $uhost = $1;	400	my $uhost = $1;
284	$uport = $2 if defined $2;	401	$uport = $2 if defined $2;
285		402
		403	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		404	unless exists $hdr{host};
		405
286	$uhost =~ s/^\[(.*)\]$/$1/;	406	$uhost =~ s/^\[(.*)\]$/$1/;
287	$upath .= "?$query" if length $query;	407	$upath .= $query if length $query;
288		408
289	$upath =~ s%^/?%/%;	409	$upath =~ s%^/?%/%;
290		410
291	# cookie processing	411	# cookie processing
292	if (my $jar = $arg{cookie_jar}) {	412	if (my $jar = $arg{cookie_jar}) {
…		…
320	}	440	}
321		441
322	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	442	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
323		443
324	if ($proxy) {	444	if ($proxy) {
325	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	445	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		446
		447	$rscheme = "http" unless defined $rscheme;
326		448
327	# don't support https requests over https-proxy transport,	449	# don't support https requests over https-proxy transport,
328	# can't be done with tls as spec'ed.	450	# can't be done with tls as spec'ed, unless you double-encrypt.
329	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	451	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
330	} else {	452	} else {
331	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	453	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
332	}	454	}
333		455
334	$hdr{host} = $uhost;	456	# leave out fragment and query string, just a heuristic
		457	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		458	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		459
335	$hdr{"content-length"} = length $arg{body};	460	$hdr{"content-length"} = length $arg{body}
		461	if length $arg{body} \|\| $method ne "GET";
336		462
337	my %state = (connect_guard => 1);	463	my %state = (connect_guard => 1);
338		464
339	_get_slot $uhost, sub {	465	_get_slot $uhost, sub {
340	$state{slot_guard} = shift;	466	$state{slot_guard} = shift;
341		467
342	return unless $state{connect_guard};	468	return unless $state{connect_guard};
343		469
344	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	470	my $tcp_connect = $arg{tcp_connect}
		471	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		472
		473	$state{connect_guard} = $tcp_connect->(
		474	$rhost,
		475	$rport,
		476	sub {
345	$state{fh} = shift	477	$state{fh} = shift
		478	or do {
		479	my $err = "$!";
		480	%state = ();
346	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	481	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		482	};
		483
347	pop; # free memory, save a tree	484	pop; # free memory, save a tree
348		485
349	return unless delete $state{connect_guard};	486	return unless delete $state{connect_guard};
350		487
351	# get handle	488	# get handle
352	$state{handle} = new AnyEvent::Handle	489	$state{handle} = new AnyEvent::Handle
353	fh => $state{fh},	490	fh => $state{fh},
		491	peername => $rhost,
		492	tls_ctx => $arg{tls_ctx},
		493	# these need to be reconfigured on keepalive handles
354	timeout => $timeout;	494	timeout => $timeout,
		495	on_error => sub {
		496	%state = ();
		497	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		498	},
		499	on_eof => sub {
		500	%state = ();
		501	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		502	},
		503	;
355		504
356	# limit the number of persistent connections	505	# limit the number of persistent connections
357	# keepalive not yet supported	506	# keepalive not yet supported
358	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	507	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
359	++$KA_COUNT{$_[1]};	508	# ++$KA_COUNT{$_[1]};
360	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	509	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
361	--$KA_COUNT{$_[1]}	510	# --$KA_COUNT{$_[1]}
362	};	511	# };
363	$hdr{connection} = "keep-alive";	512	# $hdr{connection} = "keep-alive";
364	} else {	513	# } else {
365	delete $hdr{connection};	514	delete $hdr{connection};
366	}	515	# }
367		516
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";	517	$state{handle}->starttls ("connect") if $rscheme eq "https";
380		518
381	# handle actual, non-tunneled, request	519	# handle actual, non-tunneled, request
382	my $handle_actual_request = sub {	520	my $handle_actual_request = sub {
383	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	521	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384		522
385	# send request	523	# send request
386	$state{handle}->push_write (	524	$state{handle}->push_write (
387	"$method $rpath HTTP/1.0\015\012"	525	"$method $rpath HTTP/1.0\015\012"
388	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	526	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
389	. "\015\012"	527	. "\015\012"
390	. (delete $arg{body})	528	. (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	);	529	);
406		530
407	# headers, could be optimized a bit	531	# return if error occured during push_write()
		532	return unless %state;
		533
		534	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		535
		536	# status line and headers
408	$state{handle}->unshift_read (line => $qr_nlnl, sub {	537	$state{handle}->push_read (line => $qr_nlnl, sub {
409	for ("$_[1]\012") {	538	for ("$_[1]") {
410	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	539	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411		540
412	# we support spaces in field names, as lotus domino	541	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
413	# creates them (actually spaces around seperators	542	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
414	# are strictly allowed in http, they are a security issue).	543
		544	push @pseudo,
		545	HTTPVersion => $1,
		546	Status => $2,
		547	Reason => $3,
		548	;
		549
		550	# things seen, not parsed:
		551	# p3pP="NON CUR OTPi OUR NOR UNI"
		552
415	$hdr{lc $1} .= ",$2"	553	$hdr{lc $1} .= ",$2"
416	while /\G	554	while /\G
417	([^:\000-\037]+):	555	([^:\000-\037]*):
418	[\011\040]*	556	[\011\040]*
419	((?: [^\012]+ \| \012[\011\040] )*)	557	((?: [^\012]+ \| \012[\011\040] )*)
420	\012	558	\012
421	/gxc;	559	/gxc;
422		560
423	/\G$/	561	/\G$/
424	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	562	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
425	}	563	}
426		564
		565	# remove the "," prefix we added to all headers above
427	substr $_, 0, 1, ""	566	substr $_, 0, 1, ""
428	for values %hdr;	567	for values %hdr;
429		568
		569	# patch in all pseudo headers
		570	%hdr = (%hdr, @pseudo);
		571
		572	# redirect handling
		573	# microsoft and other shitheads don't give a shit for following standards,
		574	# try to support some common forms of broken Location headers.
		575	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		576	$hdr{location} =~ s/^\.\/+//;
		577
		578	my $url = "$rscheme://$uhost:$uport";
		579
		580	unless ($hdr{location} =~ s/^\///) {
		581	$url .= $upath;
		582	$url =~ s/\/[^\/]*$//;
		583	}
		584
		585	$hdr{location} = "$url/$hdr{location}";
		586	}
		587
		588	my $redirect;
		589
		590	if ($recurse) {
		591	my $status = $hdr{Status};
		592
		593	# industry standard is to redirect POST as GET for
		594	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		595	# also, the UA should ask the user for 301 and 307 and POST,
		596	# industry standard seems to be to simply follow.
		597	# we go with the industry standard.
		598	if ($status == 301 or $status == 302 or $status == 303) {
		599	# HTTP/1.1 is unclear on how to mutate the method
		600	$method = "GET" unless $method eq "HEAD";
		601	$redirect = 1;
		602	} elsif ($status == 307) {
		603	$redirect = 1;
		604	}
		605	}
		606
430	my $finish = sub {	607	my $finish = sub {
431	# TODO: use destroy method, when/if available
432	#$state{handle}->destroy;	608	$state{handle}->destroy if $state{handle};
433	$state{handle}->on_eof (undef);
434	$state{handle}->on_error (undef);
435	%state = ();	609	%state = ();
436		610
437	# set-cookie processing	611	# set-cookie processing
438	if ($arg{cookie_jar}) {	612	if ($arg{cookie_jar}) {
439	for ($hdr{"set-cookie"}) {	613	for ($_[1]{"set-cookie"}) {
440	# parse NAME=VALUE	614	# parse NAME=VALUE
441	my @kv;	615	my @kv;
442		616
443	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	617	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
444	my $name = $1;	618	my $name = $1;
…		…
482		656
483	redo if /\G\s*,/gc;	657	redo if /\G\s*,/gc;
484	}	658	}
485	}	659	}
486		660
487	# microsoft and other shitheads don't give a shit for following standards,	661	if ($redirect && exists $hdr{location}) {
488	# try to support some common forms of broken Location headers.	662	# we ignore any errors, as it is very common to receive
489	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	663	# Content-Length != 0 but no actual body
490	$_[1]{location} =~ s/^\.\/+//;	664	# we also access %hdr, as $_[1] might be an erro
491		665	http_request (
492	my $url = "$rscheme://$uhost:$uport";	666	$method => $hdr{location},
493
494	unless ($_[1]{location} =~ s/^\///) {
495	$url .= $upath;
496	$url =~ s/\/[^\/]*$//;
497	}	667	%arg,
498		668	recurse => $recurse - 1,
499	$_[1]{location} = "$url/$_[1]{location}";	669	Redirect => \@_,
500	}	670	$cb);
501
502	if ($_[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 {	671	} else {
513	$cb->($_[0], $_[1]);	672	$cb->($_[0], $_[1]);
514	}	673	}
515	};	674	};
516		675
517	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	676	my $len = $hdr{"content-length"};
		677
		678	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		679	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		680	} elsif (
		681	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		682	or $method eq "HEAD"
		683	or (defined $len && !$len)
		684	) {
		685	# no body
518	$finish->(undef, \%hdr);	686	$finish->("", \%hdr);
519	} else {	687	} else {
520	if (exists $hdr{"content-length"}) {	688	# body handling, four different code paths
521	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	689	# for want_body_handle, on_body (2x), normal (2x)
522	# could cache persistent connection now	690	# we might read too much here, but it does not matter yet (no pers. connections)
523	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	691	if (!$redirect && $arg{want_body_handle}) {
524	# but we don't, due to misdesigns, this is annoyingly complex	692	$_[0]->on_eof (undef);
		693	$_[0]->on_error (undef);
		694	$_[0]->on_read (undef);
		695
		696	$finish->(delete $state{handle}, \%hdr);
		697
		698	} elsif ($arg{on_body}) {
		699	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		700	if ($len) {
		701	$_[0]->on_eof (undef);
		702	$_[0]->on_read (sub {
		703	$len -= length $_[0]{rbuf};
		704
		705	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		706	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		707
		708	$len > 0
		709	or $finish->("", \%hdr);
525	};	710	});
526		711	} else {
		712	$_[0]->on_eof (sub {
527	$finish->($_[1], \%hdr);	713	$finish->("", \%hdr);
		714	});
		715	$_[0]->on_read (sub {
		716	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		717	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		718	});
528	});	719	}
529	} else {	720	} 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);	721	$_[0]->on_eof (undef);
		722
		723	if ($len) {
		724	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		725	$_[0]->on_read (sub {
		726	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		727	if $len <= length $_[0]{rbuf};
		728	});
		729	} else {
		730	$_[0]->on_error (sub {
		731	($! == Errno::EPIPE \|\| !$!)
		732	? $finish->(delete $_[0]{rbuf}, \%hdr)
		733	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		734	});
536	$_[0]->on_read (sub { });	735	$_[0]->on_read (sub { });
		736	}
537	}	737	}
538	}	738	}
539	});	739	});
540	});	740	};
541	};
542		741
543	# now handle proxy-CONNECT method	742	# now handle proxy-CONNECT method
544	if ($proxy && $uscheme eq "https") {	743	if ($proxy && $uscheme eq "https") {
545	# oh dear, we have to wrap it into a connect request	744	# oh dear, we have to wrap it into a connect request
546		745
547	# maybe re-use $uauthority with patched port?	746	# 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");	747	$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 {	748	$state{handle}->push_read (line => $qr_nlnl, sub {
550	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	749	$_[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 }));	750	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
552		751
553	if ($2 == 200) {	752	if ($2 == 200) {
554	$rpath = $upath;	753	$rpath = $upath;
555	&$handle_actual_request;	754	&$handle_actual_request;
556	} else {	755	} else {
557	%state = ();	756	%state = ();
558	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	757	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
		758	}
559	}	759	});
560	});
561	} else {	760	} else {
562	&$handle_actual_request;	761	&$handle_actual_request;
		762	}
		763
563	}	764	},
564		765	$arg{on_prepare} \|\| sub { $timeout }
565	}, sub {
566	$timeout
567	};	766	);
568	};	767	};
569		768
570	defined wantarray && AnyEvent::Util::guard { %state = () }	769	defined wantarray && AnyEvent::Util::guard { %state = () }
571	}	770	}
572		771
…		…
586	&http_request	785	&http_request
587	}	786	}
588		787
589	=back	788	=back
590		789
		790	=head2 DNS CACHING
		791
		792	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		793	the actual connection, which in turn uses AnyEvent::DNS to resolve
		794	hostnames. The latter is a simple stub resolver and does no caching
		795	on its own. If you want DNS caching, you currently have to provide
		796	your own default resolver (by storing a suitable resolver object in
		797	C<$AnyEvent::DNS::RESOLVER>).
		798
591	=head2 GLOBAL FUNCTIONS AND VARIABLES	799	=head2 GLOBAL FUNCTIONS AND VARIABLES
592		800
593	=over 4	801	=over 4
594		802
595	=item AnyEvent::HTTP::set_proxy "proxy-url"	803	=item AnyEvent::HTTP::set_proxy "proxy-url"
596		804
597	Sets the default proxy server to use. The proxy-url must begin with a	805	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:...>).	806	string of the form C<http://host:port> (optionally C<https:...>), croaks
		807	otherwise.
		808
		809	To clear an already-set proxy, use C<undef>.
		810
		811	=item $date = AnyEvent::HTTP::format_date $timestamp
		812
		813	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		814	Date (RFC 2616).
		815
		816	=item $timestamp = AnyEvent::HTTP::parse_date $date
		817
		818	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		819	timestamp, or C<undef> if the date cannot be parsed.
599		820
600	=item $AnyEvent::HTTP::MAX_RECURSE	821	=item $AnyEvent::HTTP::MAX_RECURSE
601		822
602	The default value for the C<recurse> request parameter (default: C<10>).	823	The default value for the C<recurse> request parameter (default: C<10>).
603		824
604	=item $AnyEvent::HTTP::USERAGENT	825	=item $AnyEvent::HTTP::USERAGENT
605		826
606	The default value for the C<User-Agent> header (the default is	827	The default value for the C<User-Agent> header (the default is
607	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	828	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
608		829
609	=item $AnyEvent::HTTP::MAX_PERSISTENT	830	=item $AnyEvent::HTTP::MAX_PER_HOST
610		831
611	The maximum number of persistent connections to keep open (default: 8).	832	The maximum number of concurrent connections to the same host (identified
		833	by the hostname). If the limit is exceeded, then the additional requests
		834	are queued until previous connections are closed.
612		835
613	Not implemented currently.	836	The default value for this is C<4>, and it is highly advisable to not
614		837	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		838
621	=item $AnyEvent::HTTP::ACTIVE	839	=item $AnyEvent::HTTP::ACTIVE
622		840
623	The number of active connections. This is not the number of currently	841	The number of active connections. This is not the number of currently
624	running requests, but the number of currently open and non-idle TCP	842	running requests, but the number of currently open and non-idle TCP
…		…
626		844
627	=back	845	=back
628		846
629	=cut	847	=cut
630		848
		849	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		850	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		851
		852	sub format_date($) {
		853	my ($time) = @_;
		854
		855	# RFC 822/1123 format
		856	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		857
		858	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		859	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		860	$H, $M, $S;
		861	}
		862
		863	sub parse_date($) {
		864	my ($date) = @_;
		865
		866	my ($d, $m, $y, $H, $M, $S);
		867
		868	if ($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$/) {
		869	# RFC 822/1123, required by RFC 2616
		870	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		871
		872	} elsif ($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$/) {
		873	# RFC 850
		874	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		875
		876	} elsif ($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])$/) {
		877	# ISO C's asctime
		878	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		879	}
		880	# other formats fail in the loop below
		881
		882	for (0..11) {
		883	if ($m eq $month[$_]) {
		884	require Time::Local;
		885	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		886	}
		887	}
		888
		889	undef
		890	}
		891
631	sub set_proxy($) {	892	sub set_proxy($) {
		893	if (length $_[0]) {
632	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	894	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		895	or Carp::croak "$_[0]: invalid proxy URL";
		896	$PROXY = [$2, $3 \|\| 3128, $1]
		897	} else {
		898	undef $PROXY;
		899	}
633	}	900	}
634		901
635	# initialise proxy from environment	902	# initialise proxy from environment
		903	eval {
636	set_proxy $ENV{http_proxy};	904	set_proxy $ENV{http_proxy};
		905	};
		906
		907	=head2 SOCKS PROXIES
		908
		909	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		910	compile your perl to support socks, or use an external program such as
		911	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		912	transparently.
		913
		914	Alternatively, for AnyEvent::HTTP only, you can use your own
		915	C<tcp_connect> function that does the proxy handshake - here is an example
		916	that works with socks4a proxies:
		917
		918	use Errno;
		919	use AnyEvent::Util;
		920	use AnyEvent::Socket;
		921	use AnyEvent::Handle;
		922
		923	# host, port and username of/for your socks4a proxy
		924	my $socks_host = "10.0.0.23";
		925	my $socks_port = 9050;
		926	my $socks_user = "";
		927
		928	sub socks4a_connect {
		929	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		930
		931	my $hdl = new AnyEvent::Handle
		932	connect => [$socks_host, $socks_port],
		933	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		934	on_error => sub { $connect_cb->() },
		935	;
		936
		937	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		938
		939	$hdl->push_read (chunk => 8, sub {
		940	my ($hdl, $chunk) = @_;
		941	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		942
		943	if ($status == 0x5a) {
		944	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		945	} else {
		946	$! = Errno::ENXIO; $connect_cb->();
		947	}
		948	});
		949
		950	$hdl
		951	}
		952
		953	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		954	possibly after switching off other proxy types:
		955
		956	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		957
		958	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		959	my ($data, $headers) = @_;
		960	...
		961	};
637		962
638	=head1 SEE ALSO	963	=head1 SEE ALSO
639		964
640	L<AnyEvent>.	965	L<AnyEvent>.
641		966
642	=head1 AUTHOR	967	=head1 AUTHOR
643		968
644	Marc Lehmann <schmorp@schmorp.de>	969	Marc Lehmann <schmorp@schmorp.de>
645	http://home.schmorp.de/	970	http://home.schmorp.de/
646		971
		972	With many thanks to Дмитрий Шалашов, who provided countless
		973	testcases and bugreports.
		974
647	=cut	975	=cut
648		976
649	1	977	1
650		978

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 1.63 by root, Thu Dec 30 04:31:55 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 1.63 by root, Thu Dec 30 04:31:55 2010 UTC