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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.40 by root, Sun Jul 5 01:45:01 2009 UTC vs.
Revision 1.55 by root, Wed Jun 16 19:17:30 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 4.452 ();	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 = '1.12';	53	our $VERSION = '1.45';
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 $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$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" (uppercase to avoid clashing with possible
		105	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	106	three parts of the HTTP Status-Line of the same name.
		107
106	pseudo-header C<URL> contains the original URL (which can differ from the	108	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	109	the requested URL when following redirects - for example, you might get
		110	an error that your URL scheme is not supported even though your URL is a
		111	valid http URL because it redirected to an ftp URL, in which case you can
		112	look at the URL pseudo header).
		113
		114	The pseudo-header C<Redirect> only exists when the request was a result
		115	of an internal redirect. In that case it is an array reference with
		116	the C<($data, $headers)> from the redirect response. Note that this
		117	response could in turn be the result of a redirect itself, and C<<
		118	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		119	response, and so on.
108		120
109	If the server sends a header multiple times, then their contents will be	121	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	122	joined together with a comma (C<,>), as per the HTTP spec.
111		123
112	If an internal error occurs, such as not being able to resolve a hostname,	124	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	125	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	126	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		127	message.
115		128
116	A typical callback might look like this:	129	A typical callback might look like this:
117		130
118	sub {	131	sub {
119	my ($body, $hdr) = @_;	132	my ($body, $hdr) = @_;
…		…
137		150
138	=item headers => hashref	151	=item headers => hashref
139		152
140	The request headers to use. Currently, C<http_request> may provide its	153	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	154	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	155	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		156	suppressed by using C<undef> for these headers in which case they won't be
		157	sent at all).
143		158
144	=item timeout => $seconds	159	=item timeout => $seconds
145		160
146	The time-out to use for various stages - each connect attempt will reset	161	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	162	the timeout, as will read or write activity, i.e. this is not an overall
		163	timeout.
		164
		165	Default timeout is 5 minutes.
148		166
149	=item proxy => [$host, $port[, $scheme]] or undef	167	=item proxy => [$host, $port[, $scheme]] or undef
150		168
151	Use the given http proxy for all requests. If not specified, then the	169	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	170	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		171
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	172	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	173	HTTPS.
156		174
157	=item body => $string	175	=item body => $string
158		176
159	The request body, usually empty. Will be-sent as-is (future versions of	177	The request body, usually empty. Will be-sent as-is (future versions of
…		…
184	verification, highest compatibility) and high-security (CA and common-name	202	verification, highest compatibility) and high-security (CA and common-name
185	verification) TLS context.	203	verification) TLS context.
186		204
187	The default for this option is C<low>, which could be interpreted as "give	205	The default for this option is C<low>, which could be interpreted as "give
188	me the page, no matter what".	206	me the page, no matter what".
		207
		208	=item on_prepare => $callback->($fh)
		209
		210	In rare cases you need to "tune" the socket before it is used to
		211	connect (for exmaple, to bind it on a given IP address). This parameter
		212	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		213	and behaves exactly the same way (e.g. it has to provide a
		214	timeout). See the description for the C<$prepare_cb> argument of
		215	C<AnyEvent::Socket::tcp_connect> for details.
		216
		217	=item on_header => $callback->($headers)
		218
		219	When specified, this callback will be called with the header hash as soon
		220	as headers have been successfully received from the remote server (not on
		221	locally-generated errors).
		222
		223	It has to return either true (in which case AnyEvent::HTTP will continue),
		224	or false, in which case AnyEvent::HTTP will cancel the download (and call
		225	the finish callback with an error code of C<598>).
		226
		227	This callback is useful, among other things, to quickly reject unwanted
		228	content, which, if it is supposed to be rare, can be faster than first
		229	doing a C<HEAD> request.
		230
		231	Example: cancel the request unless the content-type is "text/html".
		232
		233	on_header => sub {
		234	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		235	},
		236
		237	=item on_body => $callback->($partial_body, $headers)
		238
		239	When specified, all body data will be passed to this callback instead of
		240	to the completion callback. The completion callback will get the empty
		241	string instead of the body data.
		242
		243	It has to return either true (in which case AnyEvent::HTTP will continue),
		244	or false, in which case AnyEvent::HTTP will cancel the download (and call
		245	the completion callback with an error code of C<598>).
		246
		247	This callback is useful when the data is too large to be held in memory
		248	(so the callback writes it to a file) or when only some information should
		249	be extracted, or when the body should be processed incrementally.
		250
		251	It is usually preferred over doing your own body handling via
		252	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		253	only used to create a connection, C<want_body_handle> is the better
		254	alternative, as it allows you to install your own event handler, reducing
		255	resource usage.
		256
		257	=item want_body_handle => $enable
		258
		259	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		260	changes considerably: after parsing the headers, and instead of
		261	downloading the body (if any), the completion callback will be
		262	called. Instead of the C<$body> argument containing the body data, the
		263	callback will receive the L<AnyEvent::Handle> object associated with the
		264	connection. In error cases, C<undef> will be passed. When there is no body
		265	(e.g. status C<304>), the empty string will be passed.
		266
		267	The handle object might or might not be in TLS mode, might be connected to
		268	a proxy, be a persistent connection etc., and configured in unspecified
		269	ways. The user is responsible for this handle (it will not be used by this
		270	module anymore).
		271
		272	This is useful with some push-type services, where, after the initial
		273	headers, an interactive protocol is used (typical example would be the
		274	push-style twitter API which starts a JSON/XML stream).
		275
		276	If you think you need this, first have a look at C<on_body>, to see if
		277	that doesn't solve your problem in a better way.
189		278
190	=back	279	=back
191		280
192	Example: make a simple HTTP GET request for http://www.nethype.de/	281	Example: make a simple HTTP GET request for http://www.nethype.de/
193		282
…		…
249	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
250		339
251	_slot_schedule $_[0];	340	_slot_schedule $_[0];
252	}	341	}
253		342
254	our $qr_nl = qr<\015?\012>;	343	our $qr_nl = qr{\015?\012};
255	our $qr_nlnl = qr<\015?\012\015?\012>;	344	our $qr_nlnl = qr{(?<![^\012])\015?\012};
256		345
257	our $TLS_CTX_LOW = { cache => 1, dh => undef, sslv2 => 1 };	346	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
258	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_cn => "https", dh => "skip4096" };	347	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
259		348
260	sub http_request($$@) {	349	sub http_request($$@) {
261	my $cb = pop;	350	my $cb = pop;
262	my ($method, $url, %arg) = @_;	351	my ($method, $url, %arg) = @_;
263		352
…		…
272	while (my ($k, $v) = each %$hdr) {	361	while (my ($k, $v) = each %$hdr) {
273	$hdr{lc $k} = $v;	362	$hdr{lc $k} = $v;
274	}	363	}
275	}	364	}
276		365
		366	# pseudo headers for all subsequent responses
		367	my @pseudo = (URL => $url);
		368	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		369
277	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	370	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
278		371
279	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	372	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
280	if $recurse < 0;	373	if $recurse < 0;
281		374
282	my $proxy = $arg{proxy} \|\| $PROXY;	375	my $proxy = $arg{proxy} \|\| $PROXY;
283	my $timeout = $arg{timeout} \|\| $TIMEOUT;	376	my $timeout = $arg{timeout} \|\| $TIMEOUT;
284		377
285	$hdr{"user-agent"} \|\|= $USERAGENT;
286
287	my ($uscheme, $uauthority, $upath, $query, $fragment) =	378	my ($uscheme, $uauthority, $upath, $query, $fragment) =
288	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	379	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
289		380
290	$uscheme = lc $uscheme;	381	$uscheme = lc $uscheme;
291		382
292	my $uport = $uscheme eq "http" ? 80	383	my $uport = $uscheme eq "http" ? 80
293	: $uscheme eq "https" ? 443	384	: $uscheme eq "https" ? 443
294	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported (not '$uscheme')", URL => $url });	385	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
295
296	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
297		386
298	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	387	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
299	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	388	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
300		389
301	my $uhost = $1;	390	my $uhost = $1;
302	$uport = $2 if defined $2;	391	$uport = $2 if defined $2;
		392
		393	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		394	unless exists $hdr{host};
303		395
304	$uhost =~ s/^\[(.*)\]$/$1/;	396	$uhost =~ s/^\[(.*)\]$/$1/;
305	$upath .= "?$query" if length $query;	397	$upath .= "?$query" if length $query;
306		398
307	$upath =~ s%^/?%/%;	399	$upath =~ s%^/?%/%;
…		…
340	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	432	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
341		433
342	if ($proxy) {	434	if ($proxy) {
343	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	435	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
344		436
		437	$rscheme = "http" unless defined $rscheme;
		438
345	# don't support https requests over https-proxy transport,	439	# don't support https requests over https-proxy transport,
346	# can't be done with tls as spec'ed, unless you double-encrypt.	440	# can't be done with tls as spec'ed, unless you double-encrypt.
347	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	441	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
348	} else {	442	} else {
349	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	443	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
350	}	444	}
351		445
352	$hdr{host} = $uhost;	446	# leave out fragment and query string, just a heuristic
		447	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		448	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		449
353	$hdr{"content-length"} = length $arg{body};	450	$hdr{"content-length"} = length $arg{body}
		451	if length $arg{body} \|\| $method ne "GET";
354		452
355	my %state = (connect_guard => 1);	453	my %state = (connect_guard => 1);
356		454
357	_get_slot $uhost, sub {	455	_get_slot $uhost, sub {
358	$state{slot_guard} = shift;	456	$state{slot_guard} = shift;
359		457
360	return unless $state{connect_guard};	458	return unless $state{connect_guard};
361		459
362	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	460	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
363	$state{fh} = shift	461	$state{fh} = shift
		462	or do {
		463	my $err = "$!";
		464	%state = ();
364	or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url }));	465	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		466	};
		467
365	pop; # free memory, save a tree	468	pop; # free memory, save a tree
366		469
367	return unless delete $state{connect_guard};	470	return unless delete $state{connect_guard};
368		471
369	# get handle	472	# get handle
…		…
386	}	489	}
387		490
388	# (re-)configure handle	491	# (re-)configure handle
389	$state{handle}->on_error (sub {	492	$state{handle}->on_error (sub {
390	%state = ();	493	%state = ();
391	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });	494	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
392	});	495	});
393	$state{handle}->on_eof (sub {	496	$state{handle}->on_eof (sub {
394	%state = ();	497	%state = ();
395	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });	498	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
396	});	499	});
397		500
398	$state{handle}->starttls ("connect") if $rscheme eq "https";	501	$state{handle}->starttls ("connect") if $rscheme eq "https";
399		502
400	# handle actual, non-tunneled, request	503	# handle actual, non-tunneled, request
…		…
402	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	505	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
403		506
404	# send request	507	# send request
405	$state{handle}->push_write (	508	$state{handle}->push_write (
406	"$method $rpath HTTP/1.0\015\012"	509	"$method $rpath HTTP/1.0\015\012"
407	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	510	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
408	. "\015\012"	511	. "\015\012"
409	. (delete $arg{body})	512	. (delete $arg{body})
410	);	513	);
411		514
		515	# return if error occured during push_write()
		516	return unless %state;
		517
412	%hdr = (); # reduce memory usage, save a kitten	518	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
413		519
414	# status line	520	# status line
415	$state{handle}->push_read (line => $qr_nl, sub {	521	$state{handle}->push_read (line => $qr_nl, sub {
416	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	522	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
417	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));	523	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", @pseudo }));
418		524
419	my %hdr = ( # response headers	525	push @pseudo,
420	HTTPVersion => ",$1",	526	HTTPVersion => $1,
421	Status => ",$2",	527	Status => $2,
422	Reason => ",$3",	528	Reason => $3,
423	URL => ",$url"
424	);	529	;
425		530
426	# headers, could be optimized a bit	531	# headers, could be optimized a bit
427	$state{handle}->unshift_read (line => $qr_nlnl, sub {	532	$state{handle}->unshift_read (line => $qr_nlnl, sub {
428	for ("$_[1]\012") {	533	for ("$_[1]") {
429	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	534	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
430		535
431	# things seen, not parsed:	536	# things seen, not parsed:
432	# p3pP="NON CUR OTPi OUR NOR UNI"	537	# p3pP="NON CUR OTPi OUR NOR UNI"
433		538
434	$hdr{lc $1} .= ",$2"	539	$hdr{lc $1} .= ",$2"
435	while /\G	540	while /\G
436	([^:\000-\037]+):	541	([^:\000-\037]*):
437	[\011\040]*	542	[\011\040]*
438	((?: [^\012]+ \| \012[\011\040] )*)	543	((?: [^\012]+ \| \012[\011\040] )*)
439	\012	544	\012
440	/gxc;	545	/gxc;
441		546
442	/\G$/	547	/\G$/
443	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));	548	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
444	}	549	}
445		550
		551	# remove the "," prefix we added to all headers above
446	substr $_, 0, 1, ""	552	substr $_, 0, 1, ""
447	for values %hdr;	553	for values %hdr;
448		554
		555	# patch in all pseudo headers
		556	%hdr = (%hdr, @pseudo);
		557
		558	# redirect handling
		559	# microsoft and other shitheads don't give a shit for following standards,
		560	# try to support some common forms of broken Location headers.
		561	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		562	$hdr{location} =~ s/^\.\/+//;
		563
		564	my $url = "$rscheme://$uhost:$uport";
		565
		566	unless ($hdr{location} =~ s/^\///) {
		567	$url .= $upath;
		568	$url =~ s/\/[^\/]*$//;
		569	}
		570
		571	$hdr{location} = "$url/$hdr{location}";
		572	}
		573
		574	my $redirect;
		575
		576	if ($recurse) {
		577	my $status = $hdr{Status};
		578
		579	if (($status == 301 \|\| $status == 302) && $method ne "POST") {
		580	# apparently, mozilla et al. just change POST to GET here
		581	# more research is needed before we do the same
		582	$redirect = 1;
		583	} elsif ($status == 303) {
		584	# even http/1.1 is unclear on how to mutate the method
		585	$method = "GET" unless $method eq "HEAD";
		586	$redirect = 1;
		587	} elsif ($status == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		588	$redirect = 1;
		589	}
		590	}
		591
449	my $finish = sub {	592	my $finish = sub {
450	$state{handle}->destroy;	593	$state{handle}->destroy if $state{handle};
451	%state = ();	594	%state = ();
452		595
453	# set-cookie processing	596	# set-cookie processing
454	if ($arg{cookie_jar}) {	597	if ($arg{cookie_jar}) {
455	for ($hdr{"set-cookie"}) {	598	for ($_[1]{"set-cookie"}) {
456	# parse NAME=VALUE	599	# parse NAME=VALUE
457	my @kv;	600	my @kv;
458		601
459	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {	602	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
460	my $name = $1;	603	my $name = $1;
…		…
498		641
499	redo if /\G\s*,/gc;	642	redo if /\G\s*,/gc;
500	}	643	}
501	}	644	}
502		645
503	# microsoft and other shitheads don't give a shit for following standards,	646	if ($redirect && exists $hdr{location}) {
504	# try to support some common forms of broken Location headers.	647	# we ignore any errors, as it is very common to receive
505	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	648	# Content-Length != 0 but no actual body
506	$_[1]{location} =~ s/^\.\/+//;	649	# we also access %hdr, as $_[1] might be an erro
507		650	http_request (
508	my $url = "$rscheme://$uhost:$uport";	651	$method => $hdr{location},
509
510	unless ($_[1]{location} =~ s/^\///) {
511	$url .= $upath;
512	$url =~ s/\/[^\/]*$//;
513	}	652	%arg,
514		653	recurse => $recurse - 1,
515	$_[1]{location} = "$url/$_[1]{location}";	654	Redirect => \@_,
516	}	655	$cb);
517
518	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
519	# apparently, mozilla et al. just change POST to GET here
520	# more research is needed before we do the same
521	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
522	} elsif ($_[1]{Status} == 303 && $recurse) {
523	# even http/1.1 is unclear on how to mutate the method
524	$method = "GET" unless $method eq "HEAD";
525	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
526	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
527	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
528	} else {	656	} else {
529	$cb->($_[0], $_[1]);	657	$cb->($_[0], $_[1]);
530	}	658	}
531	};	659	};
532		660
533	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	661	my $len = $hdr{"content-length"};
		662
		663	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		664	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		665	} elsif (
		666	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		667	or $method eq "HEAD"
		668	or (defined $len && !$len)
		669	) {
		670	# no body
534	$finish->(undef, \%hdr);	671	$finish->("", \%hdr);
535	} else {	672	} else {
536	if (exists $hdr{"content-length"}) {	673	# body handling, four different code paths
537	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	674	# for want_body_handle, on_body (2x), normal (2x)
538	# could cache persistent connection now	675	# we might read too much here, but it does not matter yet (no pers. connections)
539	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	676	if (!$redirect && $arg{want_body_handle}) {
540	# but we don't, due to misdesigns, this is annoyingly complex	677	$_[0]->on_eof (undef);
		678	$_[0]->on_error (undef);
		679	$_[0]->on_read (undef);
		680
		681	$finish->(delete $state{handle}, \%hdr);
		682
		683	} elsif ($arg{on_body}) {
		684	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		685	if ($len) {
		686	$_[0]->on_eof (undef);
		687	$_[0]->on_read (sub {
		688	$len -= length $_[0]{rbuf};
		689
		690	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		691	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		692
		693	$len > 0
		694	or $finish->("", \%hdr);
541	};	695	});
542		696	} else {
		697	$_[0]->on_eof (sub {
543	$finish->($_[1], \%hdr);	698	$finish->("", \%hdr);
		699	});
		700	$_[0]->on_read (sub {
		701	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		702	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		703	});
544	});	704	}
545	} else {	705	} else {
546	# too bad, need to read until we get an error or EOF,
547	# no way to detect winged data.
548	$_[0]->on_error (sub {
549	# delete ought to be more efficient, as we would have to make
550	# a copy otherwise as $_[0] gets destroyed.
551	$finish->(delete $_[0]{rbuf}, \%hdr);
552	});
553	$_[0]->on_eof (undef);	706	$_[0]->on_eof (undef);
		707
		708	if ($len) {
		709	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		710	$_[0]->on_read (sub {
		711	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		712	if $len <= length $_[0]{rbuf};
		713	});
		714	} else {
		715	$_[0]->on_error (sub {
		716	$! == Errno::EPIPE \|\| !$!
		717	? $finish->(delete $_[0]{rbuf}, \%hdr)
		718	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		719	});
554	$_[0]->on_read (sub { });	720	$_[0]->on_read (sub { });
		721	}
555	}	722	}
556	}	723	}
557	});	724	});
558	});	725	});
559	};	726	};
…		…
564		731
565	# maybe re-use $uauthority with patched port?	732	# maybe re-use $uauthority with patched port?
566	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	733	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
567	$state{handle}->push_read (line => $qr_nlnl, sub {	734	$state{handle}->push_read (line => $qr_nlnl, sub {
568	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	735	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
569	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));	736	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
570		737
571	if ($2 == 200) {	738	if ($2 == 200) {
572	$rpath = $upath;	739	$rpath = $upath;
573	&$handle_actual_request;	740	&$handle_actual_request;
574	} else {	741	} else {
575	%state = ();	742	%state = ();
576	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	743	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
577	}	744	}
578	});	745	});
579	} else {	746	} else {
580	&$handle_actual_request;	747	&$handle_actual_request;
581	}	748	}
582		749
583	}, sub {	750	}, $arg{on_prepare} \|\| sub { $timeout };
584	$timeout
585	};
586	};	751	};
587		752
588	defined wantarray && AnyEvent::Util::guard { %state = () }	753	defined wantarray && AnyEvent::Util::guard { %state = () }
589	}	754	}
590		755
…		…
604	&http_request	769	&http_request
605	}	770	}
606		771
607	=back	772	=back
608		773
		774	=head2 DNS CACHING
		775
		776	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		777	the actual connection, which in turn uses AnyEvent::DNS to resolve
		778	hostnames. The latter is a simple stub resolver and does no caching
		779	on its own. If you want DNS caching, you currently have to provide
		780	your own default resolver (by storing a suitable resolver object in
		781	C<$AnyEvent::DNS::RESOLVER>).
		782
609	=head2 GLOBAL FUNCTIONS AND VARIABLES	783	=head2 GLOBAL FUNCTIONS AND VARIABLES
610		784
611	=over 4	785	=over 4
612		786
613	=item AnyEvent::HTTP::set_proxy "proxy-url"	787	=item AnyEvent::HTTP::set_proxy "proxy-url"
614		788
615	Sets the default proxy server to use. The proxy-url must begin with a	789	Sets the default proxy server to use. The proxy-url must begin with a
616	string of the form C<http://host:port> (optionally C<https:...>).	790	string of the form C<http://host:port> (optionally C<https:...>), croaks
		791	otherwise.
		792
		793	To clear an already-set proxy, use C<undef>.
617		794
618	=item $AnyEvent::HTTP::MAX_RECURSE	795	=item $AnyEvent::HTTP::MAX_RECURSE
619		796
620	The default value for the C<recurse> request parameter (default: C<10>).	797	The default value for the C<recurse> request parameter (default: C<10>).
621		798
622	=item $AnyEvent::HTTP::USERAGENT	799	=item $AnyEvent::HTTP::USERAGENT
623		800
624	The default value for the C<User-Agent> header (the default is	801	The default value for the C<User-Agent> header (the default is
625	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	802	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
626		803
627	=item $AnyEvent::HTTP::MAX_PERSISTENT	804	=item $AnyEvent::HTTP::MAX_PER_HOST
628		805
629	The maximum number of persistent connections to keep open (default: 8).	806	The maximum number of concurrent connections to the same host (identified
		807	by the hostname). If the limit is exceeded, then the additional requests
		808	are queued until previous connections are closed.
630		809
631	Not implemented currently.	810	The default value for this is C<4>, and it is highly advisable to not
632		811	increase it.
633	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
634
635	The maximum time to cache a persistent connection, in seconds (default: 2).
636
637	Not implemented currently.
638		812
639	=item $AnyEvent::HTTP::ACTIVE	813	=item $AnyEvent::HTTP::ACTIVE
640		814
641	The number of active connections. This is not the number of currently	815	The number of active connections. This is not the number of currently
642	running requests, but the number of currently open and non-idle TCP	816	running requests, but the number of currently open and non-idle TCP
…		…
645	=back	819	=back
646		820
647	=cut	821	=cut
648		822
649	sub set_proxy($) {	823	sub set_proxy($) {
		824	if (length $_[0]) {
650	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	825	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		826	or Carp::croak "$_[0]: invalid proxy URL";
		827	$PROXY = [$2, $3 \|\| 3128, $1]
		828	} else {
		829	undef $PROXY;
		830	}
651	}	831	}
652		832
653	# initialise proxy from environment	833	# initialise proxy from environment
		834	eval {
654	set_proxy $ENV{http_proxy};	835	set_proxy $ENV{http_proxy};
		836	};
655		837
656	=head1 SEE ALSO	838	=head1 SEE ALSO
657		839
658	L<AnyEvent>.	840	L<AnyEvent>.
659		841

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.40 by root, Sun Jul 5 01:45:01 2009 UTC vs. Revision 1.55 by root, Wed Jun 16 19:17:30 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.40 by root, Sun Jul 5 01:45:01 2009 UTC vs.
Revision 1.55 by root, Wed Jun 16 19:17:30 2010 UTC