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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.33 by root, Mon Oct 27 11:09:54 2008 UTC vs.
Revision 1.53 by root, Sat Dec 5 15:37:07 2009 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 ();	48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	49	use AnyEvent::Handle ();
50		50
51	use base Exporter::;	51	use base Exporter::;
52		52
53	our $VERSION = '1.05';	53	our $VERSION = '1.44';
54		54
55	our @EXPORT = qw(http_get http_post http_head http_request);	55	our @EXPORT = qw(http_get http_post http_head http_request);
56		56
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	57	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	58	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	59	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	60	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	61	our $TIMEOUT = 300;
62		62
63	# changing these is evil	63	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	64	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	65	our $MAX_PER_HOST = 4;
66		66
67	our $PROXY;	67	our $PROXY;
68	our $ACTIVE = 0;	68	our $ACTIVE = 0;
69		69
…		…
94	When called in void context, nothing is returned. In other contexts,	94	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	95	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	96	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	97	destroyed before the callbakc is called, the request will be cancelled.
98		98
99	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
100	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
101	response headers as second argument.	101	second argument.
102		102
103	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
105	contain the three parts of the HTTP Status-Line of the same name. The	105	contain the three parts of the HTTP Status-Line of the same name. The
106	pseudo-header C<URL> contains the original URL (which can differ from the	106	pseudo-header C<URL> contains the original URL (which can differ from the
…		…
108		108
109	If the server sends a header multiple times, then their contents will be	109	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.	110	joined together with a comma (C<,>), as per the HTTP spec.
111		111
112	If an internal error occurs, such as not being able to resolve a hostname,	112	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	114	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		115	message.
115		116
116	A typical callback might look like this:	117	A typical callback might look like this:
117		118
118	sub {	119	sub {
119	my ($body, $hdr) = @_;	120	my ($body, $hdr) = @_;
…		…
137		138
138	=item headers => hashref	139	=item headers => hashref
139		140
140	The request headers to use. Currently, C<http_request> may provide its	141	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	142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	143	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		144	suppressed by using C<undef> for these headers in which case they won't be
		145	sent at all).
143		146
144	=item timeout => $seconds	147	=item timeout => $seconds
145		148
146	The time-out to use for various stages - each connect attempt will reset	149	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	150	the timeout, as will read or write activity, i.e. this is not an overall
		151	timeout.
		152
		153	Default timeout is 5 minutes.
148		154
149	=item proxy => [$host, $port[, $scheme]] or undef	155	=item proxy => [$host, $port[, $scheme]] or undef
150		156
151	Use the given http proxy for all requests. If not specified, then the	157	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	158	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		159
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	160	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	161	HTTPS.
156		162
157	=item body => $string	163	=item body => $string
158		164
159	The request body, usually empty. Will be-sent as-is (future versions of	165	The request body, usually empty. Will be-sent as-is (future versions of
…		…
165	based on the original netscape specification.	171	based on the original netscape specification.
166		172
167	The C<$hash_ref> must be an (initially empty) hash reference which will	173	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	174	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	175	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	176	recommended, as expiry times are currently being ignored.
171		177
172	Note that this cookie implementation is not of very high quality, nor	178	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	179	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	180	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	181	cookie-using sites working. Cookies are a privacy disaster, do not use
176	them unless required to.	182	them unless required to.
		183
		184	=item tls_ctx => $scheme \| $tls_ctx
		185
		186	Specifies the AnyEvent::TLS context to be used for https connections. This
		187	parameter follows the same rules as the C<tls_ctx> parameter to
		188	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		189	C<high> can be specified, which give you a predefined low-security (no
		190	verification, highest compatibility) and high-security (CA and common-name
		191	verification) TLS context.
		192
		193	The default for this option is C<low>, which could be interpreted as "give
		194	me the page, no matter what".
		195
		196	=item on_prepare => $callback->($fh)
		197
		198	In rare cases you need to "tune" the socket before it is used to
		199	connect (for exmaple, to bind it on a given IP address). This parameter
		200	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		201	and behaves exactly the same way (e.g. it has to provide a
		202	timeout). See the description for the C<$prepare_cb> argument of
		203	C<AnyEvent::Socket::tcp_connect> for details.
		204
		205	=item on_header => $callback->($headers)
		206
		207	When specified, this callback will be called with the header hash as soon
		208	as headers have been successfully received from the remote server (not on
		209	locally-generated errors).
		210
		211	It has to return either true (in which case AnyEvent::HTTP will continue),
		212	or false, in which case AnyEvent::HTTP will cancel the download (and call
		213	the finish callback with an error code of C<598>).
		214
		215	This callback is useful, among other things, to quickly reject unwanted
		216	content, which, if it is supposed to be rare, can be faster than first
		217	doing a C<HEAD> request.
		218
		219	Example: cancel the request unless the content-type is "text/html".
		220
		221	on_header => sub {
		222	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		223	},
		224
		225	=item on_body => $callback->($partial_body, $headers)
		226
		227	When specified, all body data will be passed to this callback instead of
		228	to the completion callback. The completion callback will get the empty
		229	string instead of the body data.
		230
		231	It has to return either true (in which case AnyEvent::HTTP will continue),
		232	or false, in which case AnyEvent::HTTP will cancel the download (and call
		233	the completion callback with an error code of C<598>).
		234
		235	This callback is useful when the data is too large to be held in memory
		236	(so the callback writes it to a file) or when only some information should
		237	be extracted, or when the body should be processed incrementally.
		238
		239	It is usually preferred over doing your own body handling via
		240	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		241	only used to create a connection, C<want_body_handle> is the better
		242	alternative, as it allows you to install your own event handler, reducing
		243	resource usage.
		244
		245	=item want_body_handle => $enable
		246
		247	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		248	changes considerably: after parsing the headers, and instead of
		249	downloading the body (if any), the completion callback will be
		250	called. Instead of the C<$body> argument containing the body data, the
		251	callback will receive the L<AnyEvent::Handle> object associated with the
		252	connection. In error cases, C<undef> will be passed. When there is no body
		253	(e.g. status C<304>), the empty string will be passed.
		254
		255	The handle object might or might not be in TLS mode, might be connected to
		256	a proxy, be a persistent connection etc., and configured in unspecified
		257	ways. The user is responsible for this handle (it will not be used by this
		258	module anymore).
		259
		260	This is useful with some push-type services, where, after the initial
		261	headers, an interactive protocol is used (typical example would be the
		262	push-style twitter API which starts a JSON/XML stream).
		263
		264	If you think you need this, first have a look at C<on_body>, to see if
		265	that doesn't solve your problem in a better way.
177		266
178	=back	267	=back
179		268
180	Example: make a simple HTTP GET request for http://www.nethype.de/	269	Example: make a simple HTTP GET request for http://www.nethype.de/
181		270
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		327
239	_slot_schedule $_[0];	328	_slot_schedule $_[0];
240	}	329	}
241		330
		331	our $qr_nl = qr{\015?\012};
		332	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		333
		334	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		335	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		336
242	sub http_request($$@) {	337	sub http_request($$@) {
243	my $cb = pop;	338	my $cb = pop;
244	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
245		340
246	my %hdr;	341	my %hdr;
		342
		343	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		344	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
247		345
248	$method = uc $method;	346	$method = uc $method;
249		347
250	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
251	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
…		…
253	}	351	}
254	}	352	}
255		353
256	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
257		355
258	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
259	if $recurse < 0;	357	if $recurse < 0;
260		358
261	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
262	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
263		361
264	$hdr{"user-agent"} \|\|= $USERAGENT;
265
266	my ($uscheme, $uauthority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
267	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
268		364
269	$uscheme = lc $uscheme;	365	$uscheme = lc $uscheme;
270		366
271	my $uport = $uscheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
272	: $uscheme eq "https" ? 443	368	: $uscheme eq "https" ? 443
273	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	369	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });
274
275	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
276		370
277	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
278	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
279		373
280	my $uhost = $1;	374	my $uhost = $1;
281	$uport = $2 if defined $2;	375	$uport = $2 if defined $2;
		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		378	unless exists $hdr{host};
282		379
283	$uhost =~ s/^\[(.*)\]$/$1/;	380	$uhost =~ s/^\[(.*)\]$/$1/;
284	$upath .= "?$query" if length $query;	381	$upath .= "?$query" if length $query;
285		382
286	$upath =~ s%^/?%/%;	383	$upath =~ s%^/?%/%;
…		…
317	}	414	}
318		415
319	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	416	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
320		417
321	if ($proxy) {	418	if ($proxy) {
322	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	419	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		420
		421	$rscheme = "http" unless defined $rscheme;
323		422
324	# don't support https requests over https-proxy transport,	423	# don't support https requests over https-proxy transport,
325	# can't be done with tls as spec'ed.	424	# can't be done with tls as spec'ed, unless you double-encrypt.
326	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	425	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
327	} else {	426	} else {
328	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
329	}	428	}
330		429
331	$hdr{host} = $uhost;	430	# leave out fragment and query string, just a heuristic
		431	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		432	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		433
332	$hdr{"content-length"} = length $arg{body};	434	$hdr{"content-length"} = length $arg{body}
		435	if length $arg{body} \|\| $method ne "GET";
333		436
334	my %state = (connect_guard => 1);	437	my %state = (connect_guard => 1);
335		438
336	_get_slot $uhost, sub {	439	_get_slot $uhost, sub {
337	$state{slot_guard} = shift;	440	$state{slot_guard} = shift;
338		441
339	return unless $state{connect_guard};	442	return unless $state{connect_guard};
340		443
341	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
342	$state{fh} = shift	445	$state{fh} = shift
		446	or do {
		447	my $err = "$!";
		448	%state = ();
343	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		450	};
344		451
345	delete $state{connect_guard}; # reduce memory usage, save a tree	452	pop; # free memory, save a tree
		453
		454	return unless delete $state{connect_guard};
346		455
347	# get handle	456	# get handle
348	$state{handle} = new AnyEvent::Handle	457	$state{handle} = new AnyEvent::Handle
349	fh => $state{fh};	458	fh => $state{fh},
		459	timeout => $timeout,
		460	peername => $rhost,
		461	tls_ctx => $arg{tls_ctx};
350		462
351	# limit the number of persistent connections	463	# limit the number of persistent connections
		464	# keepalive not yet supported
352	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
353	++$KA_COUNT{$_[1]};	466	++$KA_COUNT{$_[1]};
354	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	467	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		468	--$KA_COUNT{$_[1]}
		469	};
355	$hdr{connection} = "keep-alive";	470	$hdr{connection} = "keep-alive";
356	delete $hdr{connection}; # keep-alive not yet supported
357	} else {	471	} else {
358	delete $hdr{connection};	472	delete $hdr{connection};
359	}	473	}
360		474
361	# (re-)configure handle	475	# (re-)configure handle
362	$state{handle}->timeout ($timeout);
363	$state{handle}->on_error (sub {	476	$state{handle}->on_error (sub {
364	my $errno = "$!";
365	%state = ();	477	%state = ();
366	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });	478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
367	});	479	});
368	$state{handle}->on_eof (sub {	480	$state{handle}->on_eof (sub {
369	%state = ();	481	%state = ();
370	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });	482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
371	});	483	});
372		484
373	$state{handle}->starttls ("connect") if $rscheme eq "https";	485	$state{handle}->starttls ("connect") if $rscheme eq "https";
374		486
375	# handle actual, non-tunneled, request	487	# handle actual, non-tunneled, request
376	my $handle_actual_request = sub {	488	my $handle_actual_request = sub {
377	$state{handle}->starttls ("connect") if $uscheme eq "https";	489	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
378		490
379	# send request	491	# send request
380	$state{handle}->push_write (	492	$state{handle}->push_write (
381	"$method $rpath HTTP/1.0\015\012"	493	"$method $rpath HTTP/1.0\015\012"
382	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
383	. "\015\012"	495	. "\015\012"
384	. (delete $arg{body})	496	. (delete $arg{body})
385	);	497	);
386		498
387	%hdr = (); # reduce memory usage, save a kitten	499	%hdr = (); # reduce memory usage, save a kitten
388		500
389	# status line	501	# status line
390	$state{handle}->push_read (line => qr/\015?\012/, sub {	502	$state{handle}->push_read (line => $qr_nl, sub {
391	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	503	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
392	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));	504	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
393		505
394	my %hdr = ( # response headers	506	my %hdr = ( # response headers
395	HTTPVersion => ",$1",	507	HTTPVersion => ",$1",
396	Status => ",$2",	508	Status => ",$2",
397	Reason => ",$3",	509	Reason => ",$3",
398	URL => ",$url"	510	URL => ",$url"
399	);	511	);
400		512
401	# headers, could be optimized a bit	513	# headers, could be optimized a bit
402	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	514	$state{handle}->unshift_read (line => $qr_nlnl, sub {
403	for ("$_[1]\012") {	515	for ("$_[1]") {
404	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	516	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
405		517
406	# we support spaces in field names, as lotus domino	518	# things seen, not parsed:
407	# creates them (actually spaces around seperators	519	# p3pP="NON CUR OTPi OUR NOR UNI"
408	# are strictly allowed in http, they are a security issue).	520
409	$hdr{lc $1} .= ",$2"	521	$hdr{lc $1} .= ",$2"
410	while /\G	522	while /\G
411	([^:\000-\037]+):	523	([^:\000-\037]*):
412	[\011\040]*	524	[\011\040]*
413	((?: [^\012]+ \| \012[\011\040] )*)	525	((?: [^\012]+ \| \012[\011\040] )*)
414	\012	526	\012
415	/gxc;	527	/gxc;
416		528
417	/\G$/	529	/\G$/
418	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	530	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
419	}	531	}
420		532
421	substr $_, 0, 1, ""	533	substr $_, 0, 1, ""
422	for values %hdr;	534	for values %hdr;
423		535
		536	# redirect handling
		537	# microsoft and other shitheads don't give a shit for following standards,
		538	# try to support some common forms of broken Location headers.
		539	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		540	$hdr{location} =~ s/^\.\/+//;
		541
		542	my $url = "$rscheme://$uhost:$uport";
		543
		544	unless ($hdr{location} =~ s/^\///) {
		545	$url .= $upath;
		546	$url =~ s/\/[^\/]*$//;
		547	}
		548
		549	$hdr{location} = "$url/$hdr{location}";
		550	}
		551
		552	my $redirect;
		553
		554	if ($recurse) {
		555	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
		556	# apparently, mozilla et al. just change POST to GET here
		557	# more research is needed before we do the same
		558	$redirect = 1;
		559	} elsif ($hdr{Status} == 303) {
		560	# even http/1.1 is unclear on how to mutate the method
		561	$method = "GET" unless $method eq "HEAD";
		562	$redirect = 1;
		563	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		564	$redirect = 1;
		565	}
		566	}
		567
424	my $finish = sub {	568	my $finish = sub {
425	# TODO: use destroy method, when/if available
426	#$state{handle}->destroy;	569	$state{handle}->destroy if $state{handle};
427	$state{handle}->on_eof (undef);
428	$state{handle}->on_error (undef);
429	%state = ();	570	%state = ();
430		571
431	# set-cookie processing	572	# set-cookie processing
432	if ($arg{cookie_jar}) {	573	if ($arg{cookie_jar}) {
433	for ($hdr{"set-cookie"}) {	574	for ($_[1]{"set-cookie"}) {
434	# parse NAME=VALUE	575	# parse NAME=VALUE
435	my @kv;	576	my @kv;
436		577
437	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	578	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
438	my $name = $1;	579	my $name = $1;
…		…
476		617
477	redo if /\G\s*,/gc;	618	redo if /\G\s*,/gc;
478	}	619	}
479	}	620	}
480		621
481	# microsoft and other shitheads don't give a shit for following standards,	622	if ($redirect && exists $hdr{location}) {
482	# try to support some common forms of broken Location headers.	623	# we ignore any errors, as it is very common to receive
483	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	624	# Content-Length != 0 but no actual body
484	$_[1]{location} =~ s/^\.\/+//;	625	# we also access %hdr, as $_[1] might be an erro
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, $cb);	626	http_request ($method => $hdr{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 {	627	} else {
507	$cb->($_[0], $_[1]);	628	$cb->($_[0], $_[1]);
508	}	629	}
509	};	630	};
510		631
511	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	632	my $len = $hdr{"content-length"};
		633
		634	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		635	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
		636	} elsif (
		637	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		638	or $method eq "HEAD"
		639	or (defined $len && !$len)
		640	) {
		641	# no body
512	$finish->(undef, \%hdr);	642	$finish->("", \%hdr);
513	} else {	643	} else {
514	if (exists $hdr{"content-length"}) {	644	# body handling, four different code paths
515	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	645	# for want_body_handle, on_body (2x), normal (2x)
516	# could cache persistent connection now	646	# we might read too much here, but it does not matter yet (no pers. connections)
517	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	647	if (!$redirect && $arg{want_body_handle}) {
518	# but we don't, due to misdesigns, this is annoyingly complex	648	$_[0]->on_eof (undef);
		649	$_[0]->on_error (undef);
		650	$_[0]->on_read (undef);
		651
		652	$finish->(delete $state{handle}, \%hdr);
		653
		654	} elsif ($arg{on_body}) {
		655	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		656	if ($len) {
		657	$_[0]->on_eof (undef);
		658	$_[0]->on_read (sub {
		659	$len -= length $_[0]{rbuf};
		660
		661	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		662	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		663
		664	$len > 0
		665	or $finish->("", \%hdr);
519	};	666	});
520		667	} else {
		668	$_[0]->on_eof (sub {
521	$finish->($_[1], \%hdr);	669	$finish->("", \%hdr);
		670	});
		671	$_[0]->on_read (sub {
		672	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		673	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		674	});
522	});	675	}
523	} else {	676	} else {
524	# too bad, need to read until we get an error or EOF,
525	# no way to detect winged data.
526	$_[0]->on_error (sub {
527	$finish->($_[0]{rbuf}, \%hdr);
528	});
529	$_[0]->on_eof (undef);	677	$_[0]->on_eof (undef);
		678
		679	if ($len) {
		680	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		681	$_[0]->on_read (sub {
		682	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		683	if $len <= length $_[0]{rbuf};
		684	});
		685	} else {
		686	$_[0]->on_error (sub {
		687	$! == Errno::EPIPE \|\| !$!
		688	? $finish->(delete $_[0]{rbuf}, \%hdr)
		689	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
		690	});
530	$_[0]->on_read (sub { });	691	$_[0]->on_read (sub { });
		692	}
531	}	693	}
532	}	694	}
533	});	695	});
534	});	696	});
535	};	697	};
…		…
538	if ($proxy && $uscheme eq "https") {	700	if ($proxy && $uscheme eq "https") {
539	# oh dear, we have to wrap it into a connect request	701	# oh dear, we have to wrap it into a connect request
540		702
541	# maybe re-use $uauthority with patched port?	703	# 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");	704	$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 {	705	$state{handle}->push_read (line => $qr_nlnl, sub {
544	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	706	$_[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 }));	707	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
546		708
547	if ($2 == 200) {	709	if ($2 == 200) {
548	$rpath = $upath;	710	$rpath = $upath;
549	&$handle_actual_request;	711	&$handle_actual_request;
550	} else {	712	} else {
…		…
554	});	716	});
555	} else {	717	} else {
556	&$handle_actual_request;	718	&$handle_actual_request;
557	}	719	}
558		720
559	}, sub {	721	}, $arg{on_prepare} \|\| sub { $timeout };
560	$timeout
561	};
562	};	722	};
563		723
564	defined wantarray && AnyEvent::Util::guard { %state = () }	724	defined wantarray && AnyEvent::Util::guard { %state = () }
565	}	725	}
566		726
…		…
587	=over 4	747	=over 4
588		748
589	=item AnyEvent::HTTP::set_proxy "proxy-url"	749	=item AnyEvent::HTTP::set_proxy "proxy-url"
590		750
591	Sets the default proxy server to use. The proxy-url must begin with a	751	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:...>).	752	string of the form C<http://host:port> (optionally C<https:...>), croaks
		753	otherwise.
		754
		755	To clear an already-set proxy, use C<undef>.
593		756
594	=item $AnyEvent::HTTP::MAX_RECURSE	757	=item $AnyEvent::HTTP::MAX_RECURSE
595		758
596	The default value for the C<recurse> request parameter (default: C<10>).	759	The default value for the C<recurse> request parameter (default: C<10>).
597		760
598	=item $AnyEvent::HTTP::USERAGENT	761	=item $AnyEvent::HTTP::USERAGENT
599		762
600	The default value for the C<User-Agent> header (the default is	763	The default value for the C<User-Agent> header (the default is
601	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	764	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
602		765
603	=item $AnyEvent::HTTP::MAX_PERSISTENT	766	=item $AnyEvent::HTTP::MAX_PER_HOST
604		767
605	The maximum number of persistent connections to keep open (default: 8).	768	The maximum number of concurrent connections to the same host (identified
		769	by the hostname). If the limit is exceeded, then the additional requests
		770	are queued until previous connections are closed.
606		771
607	Not implemented currently.	772	The default value for this is C<4>, and it is highly advisable to not
608		773	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		774
615	=item $AnyEvent::HTTP::ACTIVE	775	=item $AnyEvent::HTTP::ACTIVE
616		776
617	The number of active connections. This is not the number of currently	777	The number of active connections. This is not the number of currently
618	running requests, but the number of currently open and non-idle TCP	778	running requests, but the number of currently open and non-idle TCP
…		…
621	=back	781	=back
622		782
623	=cut	783	=cut
624		784
625	sub set_proxy($) {	785	sub set_proxy($) {
		786	if (length $_[0]) {
626	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	787	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		788	or Carp::croak "$_[0]: invalid proxy URL";
		789	$PROXY = [$2, $3 \|\| 3128, $1]
		790	} else {
		791	undef $PROXY;
		792	}
627	}	793	}
628		794
629	# initialise proxy from environment	795	# initialise proxy from environment
		796	eval {
630	set_proxy $ENV{http_proxy};	797	set_proxy $ENV{http_proxy};
		798	};
631		799
632	=head1 SEE ALSO	800	=head1 SEE ALSO
633		801
634	L<AnyEvent>.	802	L<AnyEvent>.
635		803
636	=head1 AUTHOR	804	=head1 AUTHOR
637		805
638	Marc Lehmann <schmorp@schmorp.de>	806	Marc Lehmann <schmorp@schmorp.de>
639	http://home.schmorp.de/	807	http://home.schmorp.de/
640		808
		809	With many thanks to Дмитрий Шалашов, who provided countless
		810	testcases and bugreports.
		811
641	=cut	812	=cut
642		813
643	1	814	1
644		815

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.33 by root, Mon Oct 27 11:09:54 2008 UTC vs. Revision 1.53 by root, Sat Dec 5 15:37:07 2009 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.33 by root, Mon Oct 27 11:09:54 2008 UTC vs.
Revision 1.53 by root, Sat Dec 5 15:37:07 2009 UTC