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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.35 by root, Thu Oct 30 03:47:01 2008 UTC vs.
Revision 1.54 by root, Wed Jun 16 18:09:52 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 ();	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 = '1.1';	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
242	our $qr_nl = qr<\015?\012>;	331	our $qr_nl = qr{\015?\012};
243	our $qr_nlnl = qr<\015?\012\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" };
244		336
245	sub http_request($$@) {	337	sub http_request($$@) {
246	my $cb = pop;	338	my $cb = pop;
247	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
248		340
249	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";
250		345
251	$method = uc $method;	346	$method = uc $method;
252		347
253	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
254	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
…		…
256	}	351	}
257	}	352	}
258		353
259	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
260		355
261	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
262	if $recurse < 0;	357	if $recurse < 0;
263		358
264	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
265	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
266		361
267	$hdr{"user-agent"} \|\|= $USERAGENT;
268
269	my ($uscheme, $uauthority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
270	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
271		364
272	$uscheme = lc $uscheme;	365	$uscheme = lc $uscheme;
273		366
274	my $uport = $uscheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
275	: $uscheme eq "https" ? 443	368	: $uscheme eq "https" ? 443
276	: 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 });
277
278	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
279		370
280	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
281	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
282		373
283	my $uhost = $1;	374	my $uhost = $1;
284	$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};
285		379
286	$uhost =~ s/^\[(.*)\]$/$1/;	380	$uhost =~ s/^\[(.*)\]$/$1/;
287	$upath .= "?$query" if length $query;	381	$upath .= "?$query" if length $query;
288		382
289	$upath =~ s%^/?%/%;	383	$upath =~ s%^/?%/%;
…		…
320	}	414	}
321		415
322	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	416	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
323		417
324	if ($proxy) {	418	if ($proxy) {
325	($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);	419	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		420
		421	$rscheme = "http" unless defined $rscheme;
326		422
327	# don't support https requests over https-proxy transport,	423	# don't support https requests over https-proxy transport,
328	# can't be done with tls as spec'ed.	424	# can't be done with tls as spec'ed, unless you double-encrypt.
329	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	425	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
330	} else {	426	} else {
331	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
332	}	428	}
333		429
334	$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
335	$hdr{"content-length"} = length $arg{body};	434	$hdr{"content-length"} = length $arg{body}
		435	if length $arg{body} \|\| $method ne "GET";
336		436
337	my %state = (connect_guard => 1);	437	my %state = (connect_guard => 1);
338		438
339	_get_slot $uhost, sub {	439	_get_slot $uhost, sub {
340	$state{slot_guard} = shift;	440	$state{slot_guard} = shift;
341		441
342	return unless $state{connect_guard};	442	return unless $state{connect_guard};
343		443
344	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
345	$state{fh} = shift	445	$state{fh} = shift
		446	or do {
		447	my $err = "$!";
		448	%state = ();
346	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		450	};
		451
347	pop; # free memory, save a tree	452	pop; # free memory, save a tree
348		453
349	return unless delete $state{connect_guard};	454	return unless delete $state{connect_guard};
350		455
351	# get handle	456	# get handle
352	$state{handle} = new AnyEvent::Handle	457	$state{handle} = new AnyEvent::Handle
353	fh => $state{fh},	458	fh => $state{fh},
354	timeout => $timeout;	459	timeout => $timeout,
		460	peername => $rhost,
		461	tls_ctx => $arg{tls_ctx};
355		462
356	# limit the number of persistent connections	463	# limit the number of persistent connections
357	# keepalive not yet supported	464	# keepalive not yet supported
358	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
359	++$KA_COUNT{$_[1]};	466	++$KA_COUNT{$_[1]};
…		…
365	delete $hdr{connection};	472	delete $hdr{connection};
366	}	473	}
367		474
368	# (re-)configure handle	475	# (re-)configure handle
369	$state{handle}->on_error (sub {	476	$state{handle}->on_error (sub {
370	my $errno = "$!";
371	%state = ();	477	%state = ();
372	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });	478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
373	});	479	});
374	$state{handle}->on_eof (sub {	480	$state{handle}->on_eof (sub {
375	%state = ();	481	%state = ();
376	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });	482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
377	});	483	});
378		484
379	$state{handle}->starttls ("connect") if $rscheme eq "https";	485	$state{handle}->starttls ("connect") if $rscheme eq "https";
380		486
381	# handle actual, non-tunneled, request	487	# handle actual, non-tunneled, request
…		…
383	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	489	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384		490
385	# send request	491	# send request
386	$state{handle}->push_write (	492	$state{handle}->push_write (
387	"$method $rpath HTTP/1.0\015\012"	493	"$method $rpath HTTP/1.0\015\012"
388	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
389	. "\015\012"	495	. "\015\012"
390	. (delete $arg{body})	496	. (delete $arg{body})
391	);	497	);
392		498
		499	# return if error occured during push_write()
		500	return unless %state;
		501
393	%hdr = (); # reduce memory usage, save a kitten	502	%hdr = (); # reduce memory usage, save a kitten
394		503
395	# status line	504	# status line
396	$state{handle}->push_read (line => $qr_nl, sub {	505	$state{handle}->push_read (line => $qr_nl, sub {
397	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	506	$_[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 }));	507	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
399		508
400	my %hdr = ( # response headers	509	my %hdr = ( # response headers
401	HTTPVersion => ",$1",	510	HTTPVersion => ",$1",
402	Status => ",$2",	511	Status => ",$2",
403	Reason => ",$3",	512	Reason => ",$3",
404	URL => ",$url"	513	URL => ",$url"
405	);	514	);
406		515
407	# headers, could be optimized a bit	516	# headers, could be optimized a bit
408	$state{handle}->unshift_read (line => $qr_nlnl, sub {	517	$state{handle}->unshift_read (line => $qr_nlnl, sub {
409	for ("$_[1]\012") {	518	for ("$_[1]") {
410	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	519	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411		520
412	# we support spaces in field names, as lotus domino	521	# things seen, not parsed:
413	# creates them (actually spaces around seperators	522	# p3pP="NON CUR OTPi OUR NOR UNI"
414	# are strictly allowed in http, they are a security issue).	523
415	$hdr{lc $1} .= ",$2"	524	$hdr{lc $1} .= ",$2"
416	while /\G	525	while /\G
417	([^:\000-\037]+):	526	([^:\000-\037]*):
418	[\011\040]*	527	[\011\040]*
419	((?: [^\012]+ \| \012[\011\040] )*)	528	((?: [^\012]+ \| \012[\011\040] )*)
420	\012	529	\012
421	/gxc;	530	/gxc;
422		531
423	/\G$/	532	/\G$/
424	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	533	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
425	}	534	}
426		535
427	substr $_, 0, 1, ""	536	substr $_, 0, 1, ""
428	for values %hdr;	537	for values %hdr;
429		538
		539	# redirect handling
		540	# microsoft and other shitheads don't give a shit for following standards,
		541	# try to support some common forms of broken Location headers.
		542	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		543	$hdr{location} =~ s/^\.\/+//;
		544
		545	my $url = "$rscheme://$uhost:$uport";
		546
		547	unless ($hdr{location} =~ s/^\///) {
		548	$url .= $upath;
		549	$url =~ s/\/[^\/]*$//;
		550	}
		551
		552	$hdr{location} = "$url/$hdr{location}";
		553	}
		554
		555	my $redirect;
		556
		557	if ($recurse) {
		558	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
		559	# apparently, mozilla et al. just change POST to GET here
		560	# more research is needed before we do the same
		561	$redirect = 1;
		562	} elsif ($hdr{Status} == 303) {
		563	# even http/1.1 is unclear on how to mutate the method
		564	$method = "GET" unless $method eq "HEAD";
		565	$redirect = 1;
		566	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		567	$redirect = 1;
		568	}
		569	}
		570
430	my $finish = sub {	571	my $finish = sub {
431	$state{handle}->destroy;	572	$state{handle}->destroy if $state{handle};
432	%state = ();	573	%state = ();
433		574
434	# set-cookie processing	575	# set-cookie processing
435	if ($arg{cookie_jar}) {	576	if ($arg{cookie_jar}) {
436	for ($hdr{"set-cookie"}) {	577	for ($_[1]{"set-cookie"}) {
437	# parse NAME=VALUE	578	# parse NAME=VALUE
438	my @kv;	579	my @kv;
439		580
440	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	581	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
441	my $name = $1;	582	my $name = $1;
…		…
479		620
480	redo if /\G\s*,/gc;	621	redo if /\G\s*,/gc;
481	}	622	}
482	}	623	}
483		624
484	# microsoft and other shitheads don't give a shit for following standards,	625	if ($redirect && exists $hdr{location}) {
485	# try to support some common forms of broken Location headers.	626	# we ignore any errors, as it is very common to receive
486	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	627	# Content-Length != 0 but no actual body
487	$_[1]{location} =~ s/^\.\/+//;	628	# we also access %hdr, as $_[1] might be an erro
488
489	my $url = "$rscheme://$uhost:$uport";
490
491	unless ($_[1]{location} =~ s/^\///) {
492	$url .= $upath;
493	$url =~ s/\/[^\/]*$//;
494	}
495
496	$_[1]{location} = "$url/$_[1]{location}";
497	}
498
499	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
500	# apparently, mozilla et al. just change POST to GET here
501	# more research is needed before we do the same
502	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
503	} elsif ($_[1]{Status} == 303 && $recurse) {
504	# even http/1.1 is unclear on how to mutate the method
505	$method = "GET" unless $method eq "HEAD";
506	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	629	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
507	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
508	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
509	} else {	630	} else {
510	$cb->($_[0], $_[1]);	631	$cb->($_[0], $_[1]);
511	}	632	}
512	};	633	};
513		634
514	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	635	my $len = $hdr{"content-length"};
		636
		637	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		638	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
		639	} elsif (
		640	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		641	or $method eq "HEAD"
		642	or (defined $len && !$len)
		643	) {
		644	# no body
515	$finish->(undef, \%hdr);	645	$finish->("", \%hdr);
516	} else {	646	} else {
517	if (exists $hdr{"content-length"}) {	647	# body handling, four different code paths
518	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	648	# for want_body_handle, on_body (2x), normal (2x)
519	# could cache persistent connection now	649	# we might read too much here, but it does not matter yet (no pers. connections)
520	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	650	if (!$redirect && $arg{want_body_handle}) {
521	# but we don't, due to misdesigns, this is annoyingly complex	651	$_[0]->on_eof (undef);
		652	$_[0]->on_error (undef);
		653	$_[0]->on_read (undef);
		654
		655	$finish->(delete $state{handle}, \%hdr);
		656
		657	} elsif ($arg{on_body}) {
		658	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		659	if ($len) {
		660	$_[0]->on_eof (undef);
		661	$_[0]->on_read (sub {
		662	$len -= length $_[0]{rbuf};
		663
		664	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		665	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		666
		667	$len > 0
		668	or $finish->("", \%hdr);
522	};	669	});
523		670	} else {
		671	$_[0]->on_eof (sub {
524	$finish->($_[1], \%hdr);	672	$finish->("", \%hdr);
		673	});
		674	$_[0]->on_read (sub {
		675	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		676	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		677	});
525	});	678	}
526	} else {	679	} else {
527	# too bad, need to read until we get an error or EOF,
528	# no way to detect winged data.
529	$_[0]->on_error (sub {
530	$finish->($_[0]{rbuf}, \%hdr);
531	});
532	$_[0]->on_eof (undef);	680	$_[0]->on_eof (undef);
		681
		682	if ($len) {
		683	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		684	$_[0]->on_read (sub {
		685	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		686	if $len <= length $_[0]{rbuf};
		687	});
		688	} else {
		689	$_[0]->on_error (sub {
		690	$! == Errno::EPIPE \|\| !$!
		691	? $finish->(delete $_[0]{rbuf}, \%hdr)
		692	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
		693	});
533	$_[0]->on_read (sub { });	694	$_[0]->on_read (sub { });
		695	}
534	}	696	}
535	}	697	}
536	});	698	});
537	});	699	});
538	};	700	};
…		…
543		705
544	# maybe re-use $uauthority with patched port?	706	# maybe re-use $uauthority with patched port?
545	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	707	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
546	$state{handle}->push_read (line => $qr_nlnl, sub {	708	$state{handle}->push_read (line => $qr_nlnl, sub {
547	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	709	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
548	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));	710	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
549		711
550	if ($2 == 200) {	712	if ($2 == 200) {
551	$rpath = $upath;	713	$rpath = $upath;
552	&$handle_actual_request;	714	&$handle_actual_request;
553	} else {	715	} else {
…		…
557	});	719	});
558	} else {	720	} else {
559	&$handle_actual_request;	721	&$handle_actual_request;
560	}	722	}
561		723
562	}, sub {	724	}, $arg{on_prepare} \|\| sub { $timeout };
563	$timeout
564	};
565	};	725	};
566		726
567	defined wantarray && AnyEvent::Util::guard { %state = () }	727	defined wantarray && AnyEvent::Util::guard { %state = () }
568	}	728	}
569		729
…		…
590	=over 4	750	=over 4
591		751
592	=item AnyEvent::HTTP::set_proxy "proxy-url"	752	=item AnyEvent::HTTP::set_proxy "proxy-url"
593		753
594	Sets the default proxy server to use. The proxy-url must begin with a	754	Sets the default proxy server to use. The proxy-url must begin with a
595	string of the form C<http://host:port> (optionally C<https:...>).	755	string of the form C<http://host:port> (optionally C<https:...>), croaks
		756	otherwise.
		757
		758	To clear an already-set proxy, use C<undef>.
596		759
597	=item $AnyEvent::HTTP::MAX_RECURSE	760	=item $AnyEvent::HTTP::MAX_RECURSE
598		761
599	The default value for the C<recurse> request parameter (default: C<10>).	762	The default value for the C<recurse> request parameter (default: C<10>).
600		763
601	=item $AnyEvent::HTTP::USERAGENT	764	=item $AnyEvent::HTTP::USERAGENT
602		765
603	The default value for the C<User-Agent> header (the default is	766	The default value for the C<User-Agent> header (the default is
604	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	767	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
605		768
606	=item $AnyEvent::HTTP::MAX_PERSISTENT	769	=item $AnyEvent::HTTP::MAX_PER_HOST
607		770
608	The maximum number of persistent connections to keep open (default: 8).	771	The maximum number of concurrent connections to the same host (identified
		772	by the hostname). If the limit is exceeded, then the additional requests
		773	are queued until previous connections are closed.
609		774
610	Not implemented currently.	775	The default value for this is C<4>, and it is highly advisable to not
611		776	increase it.
612	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
613
614	The maximum time to cache a persistent connection, in seconds (default: 2).
615
616	Not implemented currently.
617		777
618	=item $AnyEvent::HTTP::ACTIVE	778	=item $AnyEvent::HTTP::ACTIVE
619		779
620	The number of active connections. This is not the number of currently	780	The number of active connections. This is not the number of currently
621	running requests, but the number of currently open and non-idle TCP	781	running requests, but the number of currently open and non-idle TCP
…		…
624	=back	784	=back
625		785
626	=cut	786	=cut
627		787
628	sub set_proxy($) {	788	sub set_proxy($) {
		789	if (length $_[0]) {
629	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	790	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		791	or Carp::croak "$_[0]: invalid proxy URL";
		792	$PROXY = [$2, $3 \|\| 3128, $1]
		793	} else {
		794	undef $PROXY;
		795	}
630	}	796	}
631		797
632	# initialise proxy from environment	798	# initialise proxy from environment
		799	eval {
633	set_proxy $ENV{http_proxy};	800	set_proxy $ENV{http_proxy};
		801	};
634		802
635	=head1 SEE ALSO	803	=head1 SEE ALSO
636		804
637	L<AnyEvent>.	805	L<AnyEvent>.
638		806
639	=head1 AUTHOR	807	=head1 AUTHOR
640		808
641	Marc Lehmann <schmorp@schmorp.de>	809	Marc Lehmann <schmorp@schmorp.de>
642	http://home.schmorp.de/	810	http://home.schmorp.de/
643		811
		812	With many thanks to Дмитрий Шалашов, who provided countless
		813	testcases and bugreports.
		814
644	=cut	815	=cut
645		816
646	1	817	1
647		818

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.35 by root, Thu Oct 30 03:47:01 2008 UTC vs. Revision 1.54 by root, Wed Jun 16 18:09:52 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.35 by root, Thu Oct 30 03:47:01 2008 UTC vs.
Revision 1.54 by root, Wed Jun 16 18:09:52 2010 UTC