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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.31 by root, Fri Oct 24 01:25:54 2008 UTC vs.
Revision 1.65 by root, Fri Dec 31 03:47:32 2010 UTC

…		…
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Carp;	44	use Errno ();
45		45
46	use AnyEvent ();	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 = '1.5';
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. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
106	pseudo-header C<URL> contains the original URL (which can differ from the	110	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
108		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
109	If the server sends a header multiple lines, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with a command (C<,>).	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
115		130
116	A typical callback might look like this:	131	A typical callback might look like this:
117		132
118	sub {	133	sub {
119	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
137		152
138	=item headers => hashref	153	=item headers => hashref
139		154
140	The request headers to use. Currently, C<http_request> may provide its	155	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	156	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	157	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		158	suppressed by using C<undef> for these headers in which case they won't be
		159	sent at all).
143		160
144	=item timeout => $seconds	161	=item timeout => $seconds
145		162
146	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
148		168
149	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
150		170
151	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		173
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	175	HTTPS.
156		176
157	=item body => $string	177	=item body => $string
158		178
159	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be-sent as-is (future versions of
…		…
165	based on the original netscape specification.	185	based on the original netscape specification.
166		186
167	The C<$hash_ref> must be an (initially empty) hash reference which will	187	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	188	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	189	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	190	recommended, as expiry times are currently being ignored.
171		191
172	Note that this cookie implementation is not of very high quality, nor	192	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	193	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	194	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	195	cookie-using sites working. Cookies are a privacy disaster, do not use
176	them unless required to.	196	them unless required to.
		197
		198	=item tls_ctx => $scheme \| $tls_ctx
		199
		200	Specifies the AnyEvent::TLS context to be used for https connections. This
		201	parameter follows the same rules as the C<tls_ctx> parameter to
		202	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		203	C<high> can be specified, which give you a predefined low-security (no
		204	verification, highest compatibility) and high-security (CA and common-name
		205	verification) TLS context.
		206
		207	The default for this option is C<low>, which could be interpreted as "give
		208	me the page, no matter what".
		209
		210	=item on_prepare => $callback->($fh)
		211
		212	In rare cases you need to "tune" the socket before it is used to
		213	connect (for exmaple, to bind it on a given IP address). This parameter
		214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		215	and behaves exactly the same way (e.g. it has to provide a
		216	timeout). See the description for the C<$prepare_cb> argument of
		217	C<AnyEvent::Socket::tcp_connect> for details.
		218
		219	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		220
		221	In even rarer cases you want total control over how AnyEvent::HTTP
		222	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		223	to do this, but you can provide your own C<tcp_connect> function -
		224	obviously, it has to follow the same calling conventions, except that it
		225	may always return a connection guard object.
		226
		227	There are probably lots of weird uses for this function, starting from
		228	tracing the hosts C<http_request> actually tries to connect, to (inexact
		229	but fast) host => IP address caching or even socks protocol support.
		230
		231	=item on_header => $callback->($headers)
		232
		233	When specified, this callback will be called with the header hash as soon
		234	as headers have been successfully received from the remote server (not on
		235	locally-generated errors).
		236
		237	It has to return either true (in which case AnyEvent::HTTP will continue),
		238	or false, in which case AnyEvent::HTTP will cancel the download (and call
		239	the finish callback with an error code of C<598>).
		240
		241	This callback is useful, among other things, to quickly reject unwanted
		242	content, which, if it is supposed to be rare, can be faster than first
		243	doing a C<HEAD> request.
		244
		245	Example: cancel the request unless the content-type is "text/html".
		246
		247	on_header => sub {
		248	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		249	},
		250
		251	=item on_body => $callback->($partial_body, $headers)
		252
		253	When specified, all body data will be passed to this callback instead of
		254	to the completion callback. The completion callback will get the empty
		255	string instead of the body data.
		256
		257	It has to return either true (in which case AnyEvent::HTTP will continue),
		258	or false, in which case AnyEvent::HTTP will cancel the download (and call
		259	the completion callback with an error code of C<598>).
		260
		261	This callback is useful when the data is too large to be held in memory
		262	(so the callback writes it to a file) or when only some information should
		263	be extracted, or when the body should be processed incrementally.
		264
		265	It is usually preferred over doing your own body handling via
		266	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		267	only used to create a connection, C<want_body_handle> is the better
		268	alternative, as it allows you to install your own event handler, reducing
		269	resource usage.
		270
		271	=item want_body_handle => $enable
		272
		273	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		274	changes considerably: after parsing the headers, and instead of
		275	downloading the body (if any), the completion callback will be
		276	called. Instead of the C<$body> argument containing the body data, the
		277	callback will receive the L<AnyEvent::Handle> object associated with the
		278	connection. In error cases, C<undef> will be passed. When there is no body
		279	(e.g. status C<304>), the empty string will be passed.
		280
		281	The handle object might or might not be in TLS mode, might be connected to
		282	a proxy, be a persistent connection etc., and configured in unspecified
		283	ways. The user is responsible for this handle (it will not be used by this
		284	module anymore).
		285
		286	This is useful with some push-type services, where, after the initial
		287	headers, an interactive protocol is used (typical example would be the
		288	push-style twitter API which starts a JSON/XML stream).
		289
		290	If you think you need this, first have a look at C<on_body>, to see if
		291	that doesn't solve your problem in a better way.
177		292
178	=back	293	=back
179		294
180	Example: make a simple HTTP GET request for http://www.nethype.de/	295	Example: make a simple HTTP GET request for http://www.nethype.de/
181		296
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		353
239	_slot_schedule $_[0];	354	_slot_schedule $_[0];
240	}	355	}
241		356
		357	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		358
		359	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		360	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		361
242	sub http_request($$@) {	362	sub http_request($$@) {
243	my $cb = pop;	363	my $cb = pop;
244	my ($method, $url, %arg) = @_;	364	my ($method, $url, %arg) = @_;
245		365
246	my %hdr;	366	my %hdr;
		367
		368	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		369	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
247		370
248	$method = uc $method;	371	$method = uc $method;
249		372
250	if (my $hdr = $arg{headers}) {	373	if (my $hdr = $arg{headers}) {
251	while (my ($k, $v) = each %$hdr) {	374	while (my ($k, $v) = each %$hdr) {
252	$hdr{lc $k} = $v;	375	$hdr{lc $k} = $v;
253	}	376	}
254	}	377	}
255		378
		379	# pseudo headers for all subsequent responses
		380	my @pseudo = (URL => $url);
		381	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		382
256	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	383	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
257		384
258	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	385	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
259	if $recurse < 0;	386	if $recurse < 0;
260		387
261	my $proxy = $arg{proxy} \|\| $PROXY;	388	my $proxy = $arg{proxy} \|\| $PROXY;
262	my $timeout = $arg{timeout} \|\| $TIMEOUT;	389	my $timeout = $arg{timeout} \|\| $TIMEOUT;
263		390
264	$hdr{"user-agent"} \|\|= $USERAGENT;
265
266	my ($uscheme, $uauthority, $upath, $query, $fragment) =	391	my ($uscheme, $uauthority, $upath, $query, $fragment) =
267	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	392	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
268		393
269	$uscheme = lc $uscheme;	394	$uscheme = lc $uscheme;
270		395
271	my $uport = $uscheme eq "http" ? 80	396	my $uport = $uscheme eq "http" ? 80
272	: $uscheme eq "https" ? 443	397	: $uscheme eq "https" ? 443
273	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	398	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
274
275	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
276		399
277	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	400	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
278	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	401	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
279		402
280	my $uhost = $1;	403	my $uhost = $1;
281	$uport = $2 if defined $2;	404	$uport = $2 if defined $2;
282		405
		406	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		407	unless exists $hdr{host};
		408
283	$uhost =~ s/^\[(.*)\]$/$1/;	409	$uhost =~ s/^\[(.*)\]$/$1/;
284	$upath .= "?$query" if length $query;	410	$upath .= $query if length $query;
285		411
286	$upath =~ s%^/?%/%;	412	$upath =~ s%^/?%/%;
287		413
288	# cookie processing	414	# cookie processing
289	if (my $jar = $arg{cookie_jar}) {	415	if (my $jar = $arg{cookie_jar}) {
…		…
317	}	443	}
318		444
319	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	445	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
320		446
321	if ($proxy) {	447	if ($proxy) {
322	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	448	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		449
		450	$rscheme = "http" unless defined $rscheme;
323		451
324	# don't support https requests over https-proxy transport,	452	# don't support https requests over https-proxy transport,
325	# can't be done with tls as spec'ed.	453	# can't be done with tls as spec'ed, unless you double-encrypt.
326	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	454	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
327	} else {	455	} else {
328	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	456	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
329	}	457	}
330		458
331	$hdr{host} = $uhost;	459	# leave out fragment and query string, just a heuristic
		460	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		461	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		462
332	$hdr{"content-length"} = length $arg{body};	463	$hdr{"content-length"} = length $arg{body}
		464	if length $arg{body} \|\| $method ne "GET";
333		465
334	my %state = (connect_guard => 1);	466	my %state = (connect_guard => 1);
335		467
336	_get_slot $uhost, sub {	468	_get_slot $uhost, sub {
337	$state{slot_guard} = shift;	469	$state{slot_guard} = shift;
338		470
339	return unless $state{connect_guard};	471	return unless $state{connect_guard};
340		472
341	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	473	my $connect_cb = sub {
342	$state{fh} = shift	474	$state{fh} = shift
		475	or do {
		476	my $err = "$!";
		477	%state = ();
343	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	478	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		479	};
344		480
345	delete $state{connect_guard}; # reduce memory usage, save a tree	481	pop; # free memory, save a tree
		482
		483	return unless delete $state{connect_guard};
346		484
347	# get handle	485	# get handle
348	$state{handle} = new AnyEvent::Handle	486	$state{handle} = new AnyEvent::Handle
349	fh => $state{fh};	487	fh => $state{fh},
		488	peername => $rhost,
		489	tls_ctx => $arg{tls_ctx},
		490	# these need to be reconfigured on keepalive handles
		491	timeout => $timeout,
		492	on_error => sub {
		493	%state = ();
		494	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		495	},
		496	on_eof => sub {
		497	%state = ();
		498	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		499	},
		500	;
350		501
351	# limit the number of persistent connections	502	# limit the number of persistent connections
		503	# keepalive not yet supported
352	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	504	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
353	++$KA_COUNT{$_[1]};	505	# ++$KA_COUNT{$_[1]};
354	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	506	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		507	# --$KA_COUNT{$_[1]}
		508	# };
355	$hdr{connection} = "keep-alive";	509	# $hdr{connection} = "keep-alive";
356	delete $hdr{connection}; # keep-alive not yet supported
357	} else {	510	# } else {
358	delete $hdr{connection};	511	delete $hdr{connection};
359	}	512	# }
360
361	# (re-)configure handle
362	$state{handle}->timeout ($timeout);
363	$state{handle}->on_error (sub {
364	my $errno = "$!";
365	%state = ();
366	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
367	});
368	$state{handle}->on_eof (sub {
369	%state = ();
370	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
371	});
372		513
373	$state{handle}->starttls ("connect") if $rscheme eq "https";	514	$state{handle}->starttls ("connect") if $rscheme eq "https";
374		515
375	# handle actual, non-tunneled, request	516	# handle actual, non-tunneled, request
376	my $handle_actual_request = sub {	517	my $handle_actual_request = sub {
377	# $state{handle}->starttls ("connect") if $uscheme eq "https";	518	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
378		519
379	# send request	520	# send request
380	$state{handle}->push_write (	521	$state{handle}->push_write (
381	"$method $rpath HTTP/1.0\015\012"	522	"$method $rpath HTTP/1.0\015\012"
382	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	523	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
383	. "\015\012"	524	. "\015\012"
384	. (delete $arg{body})	525	. (delete $arg{body})
385	);	526	);
386		527
		528	# return if error occured during push_write()
		529	return unless %state;
		530
387	%hdr = (); # reduce memory usage, save a kitten	531	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
388		532
389	# status line	533	# status line and headers
390	$state{handle}->push_read (line => qr/\015?\012/, sub {	534	$state{handle}->push_read (line => $qr_nlnl, sub {
391	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	535	my $keepalive = pop;
392	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
393		536
394	my %hdr = ( # response headers
395	HTTPVersion => ",$1",
396	Status => ",$2",
397	Reason => ",$3",
398	URL => ",$url"
399	);
400
401	# headers, could be optimized a bit
402	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
403	for ("$_[1]\012") {	537	for ("$_[1]") {
404	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.
405		539
406	# we support spaces in field names, as lotus domino	540	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
407	# creates them (actually spaces around seperators	541	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
408	# 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
409	$hdr{lc $1} .= ",$2"	552	$hdr{lc $1} .= ",$2"
410	while /\G	553	while /\G
411	([^:\000-\037]+):	554	([^:\000-\037]*):
412	[\011\040]*	555	[\011\040]*
413	((?: [^\012]+ \| \012[\011\040] )*)	556	((?: [^\012]+ \| \012[\011\040] )*)
414	\012	557	\012
415	/gxc;	558	/gxc;
416		559
417	/\G$/	560	/\G$/
418	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	561	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		562	}
		563
		564	# remove the "," prefix we added to all headers above
		565	substr $_, 0, 1, ""
		566	for values %hdr;
		567
		568	# patch in all pseudo headers
		569	%hdr = (%hdr, @pseudo);
		570
		571	# redirect handling
		572	# microsoft and other shitheads don't give a shit for following standards,
		573	# try to support some common forms of broken Location headers.
		574	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		575	$hdr{location} =~ s/^\.\/+//;
		576
		577	my $url = "$rscheme://$uhost:$uport";
		578
		579	unless ($hdr{location} =~ s/^\///) {
		580	$url .= $upath;
		581	$url =~ s/\/[^\/]*$//;
419	}	582	}
420		583
421	substr $_, 0, 1, ""	584	$hdr{location} = "$url/$hdr{location}";
422	for values %hdr;	585	}
423		586
424	my $finish = sub {	587	my $redirect;
425	# TODO: use destroy method, when/if available	588
		589	if ($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
		606	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
426	#$state{handle}->destroy;	607	$state{handle}->destroy if $state{handle};
427	$state{handle}->on_eof (undef);
428	$state{handle}->on_error (undef);
429	%state = ();	608	%state = ();
430		609
		610	if (defined $_[1]) {
		611	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		612	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		613	}
		614
431	# set-cookie processing	615	# set-cookie processing
432	if ($arg{cookie_jar}) {	616	if ($arg{cookie_jar}) {
433	for ($hdr{"set-cookie"}) {	617	for ($hdr{"set-cookie"}) {
434	# parse NAME=VALUE	618	# parse NAME=VALUE
435	my @kv;	619	my @kv;
436		620
437	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	621	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
438	my $name = $1;	622	my $name = $1;
439	my $value = $3;	623	my $value = $3;
440		624
441	unless ($value) {	625	unless ($value) {
442	$value = $2;	626	$value = $2;
443	$value =~ s/\\(.)/$1/gs;	627	$value =~ s/\\(.)/$1/gs;
444	}
445
446	push @kv, $name => $value;
447
448	last unless /\G\s*;/gc;
449	}	628	}
450		629
		630	push @kv, $name => $value;
		631
		632	last unless /\G\s*;/gc;
		633	}
		634
451	last unless @kv;	635	last unless @kv;
452		636
453	my $name = shift @kv;	637	my $name = shift @kv;
454	my %kv = (value => shift @kv, @kv);	638	my %kv = (value => shift @kv, @kv);
455		639
456	my $cdom;	640	my $cdom;
457	my $cpath = (delete $kv{path}) \|\| "/";	641	my $cpath = (delete $kv{path}) \|\| "/";
458		642
459	if (exists $kv{domain}) {	643	if (exists $kv{domain}) {
460	$cdom = delete $kv{domain};	644	$cdom = delete $kv{domain};
		645
		646	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		647
		648	next if $cdom =~ /\.$/;
461		649
462	$cdom =~ s/^\.?/./; # make sure it starts with a "."
463
464	next if $cdom =~ /\.$/;
465
466	# this is not rfc-like and not netscape-like. go figure.	650	# this is not rfc-like and not netscape-like. go figure.
467	my $ndots = $cdom =~ y/.//;	651	my $ndots = $cdom =~ y/.//;
468	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	652	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
469	} else {	653	} else {
470	$cdom = $uhost;	654	$cdom = $uhost;
471	}
472
473	# store it
474	$arg{cookie_jar}{version} = 1;
475	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
476
477	redo if /\G\s*,/gc;
478	}	655	}
		656
		657	# store it
		658	$arg{cookie_jar}{version} = 1;
		659	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		660
		661	redo if /\G\s*,/gc;
479	}	662	}
480
481	# microsoft and other shitheads don't give a shit for following standards,
482	# try to support some common forms of broken Location headers.
483	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
484	$_[1]{location} =~ s/^\.\/+//;
485
486	my $url = "$rscheme://$uhost:$uport";
487
488	unless ($_[1]{location} =~ s/^\///) {
489	$url .= $upath;
490	$url =~ s/\/[^\/]*$//;
491	}
492
493	$_[1]{location} = "$url/$_[1]{location}";
494	}
495
496	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
497	# apparently, mozilla et al. just change POST to GET here
498	# more research is needed before we do the same
499	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
500	} elsif ($_[1]{Status} == 303 && $recurse) {
501	# even http/1.1 is unclear on how to mutate the method
502	$method = "GET" unless $method eq "HEAD";
503	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
504	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
505	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
506	} else {
507	$cb->($_[0], $_[1]);
508	}
509	};	663	}
510		664
511	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	665	if ($redirect && exists $hdr{location}) {
512	$finish->(undef, \%hdr);	666	# we ignore any errors, as it is very common to receive
		667	# Content-Length != 0 but no actual body
		668	# we also access %hdr, as $_[1] might be an erro
		669	http_request (
		670	$method => $hdr{location},
		671	%arg,
		672	recurse => $recurse - 1,
		673	Redirect => [$_[0], \%hdr],
		674	$cb);
513	} else {	675	} else {
514	if (exists $hdr{"content-length"}) {	676	$cb->($_[0], \%hdr);
515	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	677	}
516	# could cache persistent connection now	678	};
517	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	679
518	# but we don't, due to misdesigns, this is annoyingly complex	680	my $len = $hdr{"content-length"};
		681
		682	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		683	$finish->(undef, 598 => "Request cancelled by on_header");
		684	} elsif (
		685	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		686	or $method eq "HEAD"
		687	or (defined $len && !$len)
		688	) {
		689	# no body
		690	$finish->("", undef, undef, 1);
		691	} else {
		692	# body handling, four different code paths
		693	# for want_body_handle, on_body (2x), normal (2x)
		694	# we might read too much here, but it does not matter yet (no pipelining)
		695	if (!$redirect && $arg{want_body_handle}) {
		696	$_[0]->on_eof (undef);
		697	$_[0]->on_error (undef);
		698	$_[0]->on_read (undef);
		699
		700	$finish->(delete $state{handle});
		701
		702	} elsif ($arg{on_body}) {
		703	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		704	if ($len) {
		705	$_[0]->on_read (sub {
		706	$len -= length $_[0]{rbuf};
		707
		708	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		709	or $finish->(undef, 598 => "Request cancelled by on_body");
		710
519	};	711	$len > 0
520		712	or $finish->("", undef, undef, 1);
521	$finish->($_[1], \%hdr);
522	});	713	});
523	} else {	714	} else {
524	# too bad, need to read until we get an error or EOF,	715	$_[0]->on_eof (sub {
525	# no way to detect winged data.	716	$finish->("");
		717	});
		718	$_[0]->on_read (sub {
		719	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		720	or $finish->(undef, 598 => "Request cancelled by on_body");
		721	});
		722	}
		723	} else {
		724	$_[0]->on_eof (undef);
		725
		726	if ($len) {
		727	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		728	$_[0]->on_read (sub {
		729	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		730	if $len <= length $_[0]{rbuf};
		731	});
		732	} else {
526	$_[0]->on_error (sub {	733	$_[0]->on_error (sub {
		734	($! == Errno::EPIPE \|\| !$!)
527	$finish->($_[0]{rbuf}, \%hdr);	735	? $finish->(delete $_[0]{rbuf})
		736	: $finish->(undef, 599 => $_[2]);
528	});	737	});
529	$_[0]->on_eof (undef);
530	$_[0]->on_read (sub { });	738	$_[0]->on_read (sub { });
531	}	739	}
532	}	740	}
533	});	741	}
534	});	742	});
535	};	743	};
536		744
537	# now handle proxy-CONNECT method	745	# now handle proxy-CONNECT method
538	if ($proxy && $uscheme eq "https") {	746	if ($proxy && $uscheme eq "https") {
539	# oh dear, we have to wrap it into a connect request	747	# oh dear, we have to wrap it into a connect request
540		748
541	# maybe re-use $uauthority with patched port?	749	# maybe re-use $uauthority with patched port?
542	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	750	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
543	$state{handle}->push_read (line => qr/\015?\012\015?\012/, sub {	751	$state{handle}->push_read (line => $qr_nlnl, sub {
544	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	752	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
545	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));	753	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
546		754
547	if ($2 == 200) {	755	if ($2 == 200) {
548	$rpath = $upath;	756	$rpath = $upath;
549	&$handle_actual_request;	757	&$handle_actual_request;
550	} else {	758	} else {
551	%state = ();	759	%state = ();
552	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	760	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
553	}	761	}
554	});	762	});
555	} else {	763	} else {
556	&$handle_actual_request;	764	&$handle_actual_request;
557	}	765	}
558
559	}, sub {
560	$timeout
561	};	766	};
		767
		768	my $tcp_connect = $arg{tcp_connect}
		769	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		770
		771	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		772
562	};	773	};
563		774
564	defined wantarray && AnyEvent::Util::guard { %state = () }	775	defined wantarray && AnyEvent::Util::guard { %state = () }
565	}	776	}
566		777
…		…
580	&http_request	791	&http_request
581	}	792	}
582		793
583	=back	794	=back
584		795
		796	=head2 DNS CACHING
		797
		798	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		799	the actual connection, which in turn uses AnyEvent::DNS to resolve
		800	hostnames. The latter is a simple stub resolver and does no caching
		801	on its own. If you want DNS caching, you currently have to provide
		802	your own default resolver (by storing a suitable resolver object in
		803	C<$AnyEvent::DNS::RESOLVER>).
		804
585	=head2 GLOBAL FUNCTIONS AND VARIABLES	805	=head2 GLOBAL FUNCTIONS AND VARIABLES
586		806
587	=over 4	807	=over 4
588		808
589	=item AnyEvent::HTTP::set_proxy "proxy-url"	809	=item AnyEvent::HTTP::set_proxy "proxy-url"
590		810
591	Sets the default proxy server to use. The proxy-url must begin with a	811	Sets the default proxy server to use. The proxy-url must begin with a
592	string of the form C<http://host:port> (optionally C<https:...>).	812	string of the form C<http://host:port> (optionally C<https:...>), croaks
		813	otherwise.
		814
		815	To clear an already-set proxy, use C<undef>.
		816
		817	=item $date = AnyEvent::HTTP::format_date $timestamp
		818
		819	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		820	Date (RFC 2616).
		821
		822	=item $timestamp = AnyEvent::HTTP::parse_date $date
		823
		824	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		825	timestamp, or C<undef> if the date cannot be parsed.
593		826
594	=item $AnyEvent::HTTP::MAX_RECURSE	827	=item $AnyEvent::HTTP::MAX_RECURSE
595		828
596	The default value for the C<recurse> request parameter (default: C<10>).	829	The default value for the C<recurse> request parameter (default: C<10>).
597		830
598	=item $AnyEvent::HTTP::USERAGENT	831	=item $AnyEvent::HTTP::USERAGENT
599		832
600	The default value for the C<User-Agent> header (the default is	833	The default value for the C<User-Agent> header (the default is
601	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	834	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
602		835
603	=item $AnyEvent::HTTP::MAX_PERSISTENT	836	=item $AnyEvent::HTTP::MAX_PER_HOST
604		837
605	The maximum number of persistent connections to keep open (default: 8).	838	The maximum number of concurrent connections to the same host (identified
		839	by the hostname). If the limit is exceeded, then the additional requests
		840	are queued until previous connections are closed.
606		841
607	Not implemented currently.	842	The default value for this is C<4>, and it is highly advisable to not
608		843	increase it.
609	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
610
611	The maximum time to cache a persistent connection, in seconds (default: 2).
612
613	Not implemented currently.
614		844
615	=item $AnyEvent::HTTP::ACTIVE	845	=item $AnyEvent::HTTP::ACTIVE
616		846
617	The number of active connections. This is not the number of currently	847	The number of active connections. This is not the number of currently
618	running requests, but the number of currently open and non-idle TCP	848	running requests, but the number of currently open and non-idle TCP
…		…
620		850
621	=back	851	=back
622		852
623	=cut	853	=cut
624		854
		855	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		856	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		857
		858	sub format_date($) {
		859	my ($time) = @_;
		860
		861	# RFC 822/1123 format
		862	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		863
		864	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		865	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		866	$H, $M, $S;
		867	}
		868
		869	sub parse_date($) {
		870	my ($date) = @_;
		871
		872	my ($d, $m, $y, $H, $M, $S);
		873
		874	if ($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$/) {
		875	# RFC 822/1123, required by RFC 2616
		876	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		877
		878	} elsif ($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$/) {
		879	# RFC 850
		880	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		881
		882	} elsif ($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])$/) {
		883	# ISO C's asctime
		884	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		885	}
		886	# other formats fail in the loop below
		887
		888	for (0..11) {
		889	if ($m eq $month[$_]) {
		890	require Time::Local;
		891	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		892	}
		893	}
		894
		895	undef
		896	}
		897
625	sub set_proxy($) {	898	sub set_proxy($) {
		899	if (length $_[0]) {
626	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	900	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		901	or Carp::croak "$_[0]: invalid proxy URL";
		902	$PROXY = [$2, $3 \|\| 3128, $1]
		903	} else {
		904	undef $PROXY;
		905	}
627	}	906	}
628		907
629	# initialise proxy from environment	908	# initialise proxy from environment
		909	eval {
630	set_proxy $ENV{http_proxy};	910	set_proxy $ENV{http_proxy};
		911	};
		912
		913	=head2 SOCKS PROXIES
		914
		915	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		916	compile your perl to support socks, or use an external program such as
		917	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		918	transparently.
		919
		920	Alternatively, for AnyEvent::HTTP only, you can use your own
		921	C<tcp_connect> function that does the proxy handshake - here is an example
		922	that works with socks4a proxies:
		923
		924	use Errno;
		925	use AnyEvent::Util;
		926	use AnyEvent::Socket;
		927	use AnyEvent::Handle;
		928
		929	# host, port and username of/for your socks4a proxy
		930	my $socks_host = "10.0.0.23";
		931	my $socks_port = 9050;
		932	my $socks_user = "";
		933
		934	sub socks4a_connect {
		935	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		936
		937	my $hdl = new AnyEvent::Handle
		938	connect => [$socks_host, $socks_port],
		939	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		940	on_error => sub { $connect_cb->() },
		941	;
		942
		943	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		944
		945	$hdl->push_read (chunk => 8, sub {
		946	my ($hdl, $chunk) = @_;
		947	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		948
		949	if ($status == 0x5a) {
		950	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		951	} else {
		952	$! = Errno::ENXIO; $connect_cb->();
		953	}
		954	});
		955
		956	$hdl
		957	}
		958
		959	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		960	possibly after switching off other proxy types:
		961
		962	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		963
		964	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		965	my ($data, $headers) = @_;
		966	...
		967	};
631		968
632	=head1 SEE ALSO	969	=head1 SEE ALSO
633		970
634	L<AnyEvent>.	971	L<AnyEvent>.
635		972
636	=head1 AUTHOR	973	=head1 AUTHOR
637		974
638	Marc Lehmann <schmorp@schmorp.de>	975	Marc Lehmann <schmorp@schmorp.de>
639	http://home.schmorp.de/	976	http://home.schmorp.de/
640		977
		978	With many thanks to Дмитрий Шалашов, who provided countless
		979	testcases and bugreports.
		980
641	=cut	981	=cut
642		982
643	1	983	1
644		984

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.31 by root, Fri Oct 24 01:25:54 2008 UTC vs. Revision 1.65 by root, Fri Dec 31 03:47:32 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.31 by root, Fri Oct 24 01:25:54 2008 UTC vs.
Revision 1.65 by root, Fri Dec 31 03:47:32 2010 UTC