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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.29 by root, Wed Oct 22 23:28:11 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
107	requested URL when following redirects).	107	requested URL when following redirects).
108		108
109	If the server sends a header multiple lines, then their contents will be	109	If the server sends a header multiple times, then their contents will be
110	joined together with C<\x00>.	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"} \|\|= $USERAGENT;
265
266	my ($scheme, $authority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
267	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
268		364
269	$scheme = lc $scheme;	365	$uscheme = lc $uscheme;
270		366
271	my $uport = $scheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
272	: $scheme 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		370
275	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
276
277	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/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;
282		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		378	unless exists $hdr{host};
		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%^/?%/%;
287		384
288	# cookie processing	385	# cookie processing
289	if (my $jar = $arg{cookie_jar}) {	386	if (my $jar = $arg{cookie_jar}) {
290	%$jar = () if $jar->{version} < 1;	387	%$jar = () if $jar->{version} != 1;
291		388
292	my @cookie;	389	my @cookie;
293		390
294	while (my ($chost, $v) = each %$jar) {	391	while (my ($chost, $v) = each %$jar) {
		392	if ($chost =~ /^\./) {
295	next unless $chost eq substr $uhost, -length $chost;	393	next unless $chost eq substr $uhost, -length $chost;
296	next unless $chost =~ /^\./;	394	} elsif ($chost =~ /\./) {
		395	next unless $chost eq $uhost;
		396	} else {
		397	next;
		398	}
297		399
298	while (my ($cpath, $v) = each %$v) {	400	while (my ($cpath, $v) = each %$v) {
299	next unless $cpath eq substr $upath, 0, length $cpath;	401	next unless $cpath eq substr $upath, 0, length $cpath;
300		402
301	while (my ($k, $v) = each %$v) {	403	while (my ($k, $v) = each %$v) {
302	next if $scheme ne "https" && exists $v->{secure};	404	next if $uscheme ne "https" && exists $v->{secure};
		405	my $value = $v->{value};
		406	$value =~ s/([\\"])/\\$1/g;
303	push @cookie, "$k=$v->{value}";	407	push @cookie, "$k=\"$value\"";
304	}	408	}
305	}	409	}
306	}	410	}
307		411
308	$hdr{cookie} = join "; ", @cookie	412	$hdr{cookie} = join "; ", @cookie
309	if @cookie;	413	if @cookie;
310	}	414	}
311		415
312	my ($rhost, $rport, $rpath); # request host, port, path	416	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
313		417
314	if ($proxy) {	418	if ($proxy) {
315	($rhost, $rport, $scheme) = @$proxy;	419	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
316	$rpath = $url;	420
		421	$rscheme = "http" unless defined $rscheme;
		422
		423	# don't support https requests over https-proxy transport,
		424	# can't be done with tls as spec'ed, unless you double-encrypt.
		425	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
317	} else {	426	} else {
318	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
319	$hdr{host} = $uhost;
320	}	428	}
321		429
		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
322	$hdr{"content-length"} = length $arg{body};	434	$hdr{"content-length"} = length $arg{body}
		435	if length $arg{body} \|\| $method ne "GET";
323		436
324	my %state = (connect_guard => 1);	437	my %state = (connect_guard => 1);
325		438
326	_get_slot $uhost, sub {	439	_get_slot $uhost, sub {
327	$state{slot_guard} = shift;	440	$state{slot_guard} = shift;
328		441
329	return unless $state{connect_guard};	442	return unless $state{connect_guard};
330		443
331	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
332	$state{fh} = shift	445	$state{fh} = shift
		446	or do {
		447	my $err = "$!";
		448	%state = ();
333	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		450	};
334		451
335	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};
336		455
337	# get handle	456	# get handle
338	$state{handle} = new AnyEvent::Handle	457	$state{handle} = new AnyEvent::Handle
339	fh => $state{fh},	458	fh => $state{fh},
340	($scheme eq "https" ? (tls => "connect") : ());	459	timeout => $timeout,
		460	peername => $rhost,
		461	tls_ctx => $arg{tls_ctx};
341		462
342	# limit the number of persistent connections	463	# limit the number of persistent connections
		464	# keepalive not yet supported
343	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
344	++$KA_COUNT{$_[1]};	466	++$KA_COUNT{$_[1]};
345	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	467	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		468	--$KA_COUNT{$_[1]}
		469	};
346	$hdr{connection} = "keep-alive";	470	$hdr{connection} = "keep-alive";
347	delete $hdr{connection}; # keep-alive not yet supported
348	} else {	471	} else {
349	delete $hdr{connection};	472	delete $hdr{connection};
350	}	473	}
351		474
352	# (re-)configure handle	475	# (re-)configure handle
353	$state{handle}->timeout ($timeout);
354	$state{handle}->on_error (sub {	476	$state{handle}->on_error (sub {
355	my $errno = "$!";
356	%state = ();	477	%state = ();
357	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });	478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
358	});	479	});
359	$state{handle}->on_eof (sub {	480	$state{handle}->on_eof (sub {
360	%state = ();	481	%state = ();
361	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });	482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
362	});	483	});
363		484
		485	$state{handle}->starttls ("connect") if $rscheme eq "https";
		486
		487	# handle actual, non-tunneled, request
		488	my $handle_actual_request = sub {
		489	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		490
364	# send request	491	# send request
365	$state{handle}->push_write (	492	$state{handle}->push_write (
366	"$method $rpath HTTP/1.0\015\012"	493	"$method $rpath HTTP/1.0\015\012"
367	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
368	. "\015\012"	495	. "\015\012"
369	. (delete $arg{body})	496	. (delete $arg{body})
370	);
371
372	%hdr = (); # reduce memory usage, save a kitten
373
374	# status line
375	$state{handle}->push_read (line => qr/\015?\012/, sub {
376	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
377	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
378
379	my %hdr = ( # response headers
380	HTTPVersion => "\x00$1",
381	Status => "\x00$2",
382	Reason => "\x00$3",
383	URL => "\x00$url"
384	);	497	);
385		498
		499	%hdr = (); # reduce memory usage, save a kitten
		500
		501	# status line
		502	$state{handle}->push_read (line => $qr_nl, sub {
		503	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		504	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
		505
		506	my %hdr = ( # response headers
		507	HTTPVersion => ",$1",
		508	Status => ",$2",
		509	Reason => ",$3",
		510	URL => ",$url"
		511	);
		512
386	# headers, could be optimized a bit	513	# headers, could be optimized a bit
387	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	514	$state{handle}->unshift_read (line => $qr_nlnl, sub {
388	for ("$_[1]\012") {	515	for ("$_[1]") {
389	# we support spaces in field names, as lotus domino	516	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
390	# creates them.	517
		518	# things seen, not parsed:
		519	# p3pP="NON CUR OTPi OUR NOR UNI"
		520
391	$hdr{lc $1} .= "\x00$2"	521	$hdr{lc $1} .= ",$2"
392	while /\G	522	while /\G
393	([^:\000-\037]+):	523	([^:\000-\037]*):
394	[\011\040]*	524	[\011\040]*
395	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	525	((?: [^\012]+ \| \012[\011\040] )*)
396	\015?\012	526	\012
397	/gxc;	527	/gxc;
398		528
399	/\G$/	529	/\G$/
400	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 }));
401	}
402
403	substr $_, 0, 1, ""
404	for values %hdr;
405
406	my $finish = sub {
407	%state = ();
408
409	# set-cookie processing
410	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
411	for (split /\x00/, $hdr{"set-cookie"}) {
412	my ($cookie, @arg) = split /;\s*/;
413	my ($name, $value) = split /=/, $cookie, 2;
414	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
415
416	my $cdom = (delete $kv{domain}) \|\| $uhost;
417	my $cpath = (delete $kv{path}) \|\| "/";
418
419	$cdom =~ s/^\.?/./; # make sure it starts with a "."
420
421	next if $cdom =~ /\.$/;
422
423	# this is not rfc-like and not netscape-like. go figure.
424	my $ndots = $cdom =~ y/.//;
425	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
426
427	# store it
428	$arg{cookie_jar}{version} = 1;
429	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
430	}
431	}	531	}
432		532
		533	substr $_, 0, 1, ""
		534	for values %hdr;
		535
		536	# redirect handling
433	# microsoft and other shitheads don't give a shit for following standards,	537	# microsoft and other shitheads don't give a shit for following standards,
434	# try to support some common forms of broken Location headers.	538	# try to support some common forms of broken Location headers.
435	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	539	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
436	$_[1]{location} =~ s/^\.\/+//;	540	$hdr{location} =~ s/^\.\/+//;
437		541
438	my $url = "$scheme://$uhost:$uport";	542	my $url = "$rscheme://$uhost:$uport";
439		543
440	unless ($_[1]{location} =~ s/^\///) {	544	unless ($hdr{location} =~ s/^\///) {
441	$url .= $upath;	545	$url .= $upath;
442	$url =~ s/\/[^\/]*$//;	546	$url =~ s/\/[^\/]*$//;
443	}	547	}
444		548
445	$_[1]{location} = "$url/$_[1]{location}";	549	$hdr{location} = "$url/$hdr{location}";
446	}	550	}
447		551
		552	my $redirect;
		553
		554	if ($recurse) {
448	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {	555	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
449	# apparently, mozilla et al. just change POST to GET here	556	# apparently, mozilla et al. just change POST to GET here
450	# more research is needed before we do the same	557	# more research is needed before we do the same
451	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	558	$redirect = 1;
452	} elsif ($_[1]{Status} == 303 && $recurse) {	559	} elsif ($hdr{Status} == 303) {
453	# even http/1.1 is unlear on how to mutate the method	560	# even http/1.1 is unclear on how to mutate the method
454	$method = "GET" unless $method eq "HEAD";	561	$method = "GET" unless $method eq "HEAD";
		562	$redirect = 1;
		563	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		564	$redirect = 1;
		565	}
		566	}
		567
		568	my $finish = sub {
		569	$state{handle}->destroy if $state{handle};
		570	%state = ();
		571
		572	# set-cookie processing
		573	if ($arg{cookie_jar}) {
		574	for ($_[1]{"set-cookie"}) {
		575	# parse NAME=VALUE
		576	my @kv;
		577
		578	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		579	my $name = $1;
		580	my $value = $3;
		581
		582	unless ($value) {
		583	$value = $2;
		584	$value =~ s/\\(.)/$1/gs;
		585	}
		586
		587	push @kv, $name => $value;
		588
		589	last unless /\G\s*;/gc;
		590	}
		591
		592	last unless @kv;
		593
		594	my $name = shift @kv;
		595	my %kv = (value => shift @kv, @kv);
		596
		597	my $cdom;
		598	my $cpath = (delete $kv{path}) \|\| "/";
		599
		600	if (exists $kv{domain}) {
		601	$cdom = delete $kv{domain};
		602
		603	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		604
		605	next if $cdom =~ /\.$/;
		606
		607	# this is not rfc-like and not netscape-like. go figure.
		608	my $ndots = $cdom =~ y/.//;
		609	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		610	} else {
		611	$cdom = $uhost;
		612	}
		613
		614	# store it
		615	$arg{cookie_jar}{version} = 1;
		616	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		617
		618	redo if /\G\s*,/gc;
		619	}
		620	}
		621
		622	if ($redirect && exists $hdr{location}) {
		623	# we ignore any errors, as it is very common to receive
		624	# Content-Length != 0 but no actual body
		625	# we also access %hdr, as $_[1] might be an erro
455	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	626	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
456	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {	627	} else {
457	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	628	$cb->($_[0], $_[1]);
		629	}
		630	};
		631
		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
		642	$finish->("", \%hdr);
458	} else {	643	} else {
459	$cb->($_[0], $_[1]);	644	# body handling, four different code paths
		645	# for want_body_handle, on_body (2x), normal (2x)
		646	# we might read too much here, but it does not matter yet (no pers. connections)
		647	if (!$redirect && $arg{want_body_handle}) {
		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);
		666	});
		667	} else {
		668	$_[0]->on_eof (sub {
		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	});
		675	}
		676	} else {
		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	});
		691	$_[0]->on_read (sub { });
		692	}
		693	}
460	}	694	}
461	};	695	});
		696	});
		697	};
462		698
463	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	699	# now handle proxy-CONNECT method
464	$finish->(undef, \%hdr);	700	if ($proxy && $uscheme eq "https") {
		701	# oh dear, we have to wrap it into a connect request
		702
		703	# maybe re-use $uauthority with patched port?
		704	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		705	$state{handle}->push_read (line => $qr_nlnl, sub {
		706	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		707	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
		708
		709	if ($2 == 200) {
		710	$rpath = $upath;
		711	&$handle_actual_request;
465	} else {	712	} else {
466	if (exists $hdr{"content-length"}) {	713	%state = ();
467	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	714	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
468	# could cache persistent connection now
469	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
470	# but we don't, due to misdesigns, this is annoyingly complex
471	};
472
473	$finish->($_[1], \%hdr);
474	});
475	} else {
476	# too bad, need to read until we get an error or EOF,
477	# no way to detect winged data.
478	$_[0]->on_error (sub {
479	$finish->($_[0]{rbuf}, \%hdr);
480	});
481	$_[0]->on_eof (undef);
482	$_[0]->on_read (sub { });
483	}
484	}	715	}
485	});	716	});
		717	} else {
		718	&$handle_actual_request;
486	});	719	}
487	}, sub {	720
488	$timeout	721	}, $arg{on_prepare} \|\| sub { $timeout };
489	};
490	};	722	};
491		723
492	defined wantarray && AnyEvent::Util::guard { %state = () }	724	defined wantarray && AnyEvent::Util::guard { %state = () }
493	}	725	}
494		726
…		…
515	=over 4	747	=over 4
516		748
517	=item AnyEvent::HTTP::set_proxy "proxy-url"	749	=item AnyEvent::HTTP::set_proxy "proxy-url"
518		750
519	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
520	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>.
521		756
522	=item $AnyEvent::HTTP::MAX_RECURSE	757	=item $AnyEvent::HTTP::MAX_RECURSE
523		758
524	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>).
525		760
526	=item $AnyEvent::HTTP::USERAGENT	761	=item $AnyEvent::HTTP::USERAGENT
527		762
528	The default value for the C<User-Agent> header (the default is	763	The default value for the C<User-Agent> header (the default is
529	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	764	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
530		765
531	=item $AnyEvent::HTTP::MAX_PERSISTENT	766	=item $AnyEvent::HTTP::MAX_PER_HOST
532		767
533	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.
534		771
535	Not implemented currently.	772	The default value for this is C<4>, and it is highly advisable to not
536		773	increase it.
537	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
538
539	The maximum time to cache a persistent connection, in seconds (default: 2).
540
541	Not implemented currently.
542		774
543	=item $AnyEvent::HTTP::ACTIVE	775	=item $AnyEvent::HTTP::ACTIVE
544		776
545	The number of active connections. This is not the number of currently	777	The number of active connections. This is not the number of currently
546	running requests, but the number of currently open and non-idle TCP	778	running requests, but the number of currently open and non-idle TCP
…		…
549	=back	781	=back
550		782
551	=cut	783	=cut
552		784
553	sub set_proxy($) {	785	sub set_proxy($) {
		786	if (length $_[0]) {
554	$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	}
555	}	793	}
556		794
557	# initialise proxy from environment	795	# initialise proxy from environment
		796	eval {
558	set_proxy $ENV{http_proxy};	797	set_proxy $ENV{http_proxy};
		798	};
559		799
560	=head1 SEE ALSO	800	=head1 SEE ALSO
561		801
562	L<AnyEvent>.	802	L<AnyEvent>.
563		803
564	=head1 AUTHOR	804	=head1 AUTHOR
565		805
566	Marc Lehmann <schmorp@schmorp.de>	806	Marc Lehmann <schmorp@schmorp.de>
567	http://home.schmorp.de/	807	http://home.schmorp.de/
568		808
		809	With many thanks to Дмитрий Шалашов, who provided countless
		810	testcases and bugreports.
		811
569	=cut	812	=cut
570		813
571	1	814	1
572		815

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.29 by root, Wed Oct 22 23:28:11 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 1.29 by root, Wed Oct 22 23:28:11 2008 UTC vs.
Revision 1.53 by root, Sat Dec 5 15:37:07 2009 UTC